Merge branch 'devicetree/merge' of git://git.secretlab.ca/git/linux-2.6
* 'devicetree/merge' of git://git.secretlab.ca/git/linux-2.6:
dt: add empty of_machine_is_compatible
ahci: add DT binding for Calxeda AHCI controller
dt/platform: minor cleanup
dt: add empty of_alias_get_id() for non-dt builds
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index fe23269..66bd97a 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -50,6 +50,13 @@
implementation may choose to ignore flags that affect the location of
the returned memory, like GFP_DMA).
+void *
+dma_zalloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag)
+
+Wraps dma_alloc_coherent() and also zeroes the returned memory if the
+allocation attempt succeeded.
+
void
dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
dma_addr_t dma_handle)
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 06eb6d9..cc0ebc5 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -418,7 +418,6 @@
# The following additional stats are dependent on CONFIG_DEBUG_VM.
-inactive_ratio - VM internal parameter. (see mm/page_alloc.c)
recent_rotated_anon - VM internal parameter. (see mm/vmscan.c)
recent_rotated_file - VM internal parameter. (see mm/vmscan.c)
recent_scanned_anon - VM internal parameter. (see mm/vmscan.c)
diff --git a/Documentation/device-mapper/dm-log.txt b/Documentation/device-mapper/dm-log.txt
index 994dd75..c155ac5 100644
--- a/Documentation/device-mapper/dm-log.txt
+++ b/Documentation/device-mapper/dm-log.txt
@@ -48,7 +48,7 @@
communication.
There are currently two userspace log implementations that leverage this
-framework - "clustered_disk" and "clustered_core". These implementations
+framework - "clustered-disk" and "clustered-core". These implementations
provide a cluster-coherent log for shared-storage. Device-mapper mirroring
can be used in a shared-storage environment when the cluster log implementations
are employed.
diff --git a/Documentation/device-mapper/persistent-data.txt b/Documentation/device-mapper/persistent-data.txt
new file mode 100644
index 0000000..0e5df9b
--- /dev/null
+++ b/Documentation/device-mapper/persistent-data.txt
@@ -0,0 +1,84 @@
+Introduction
+============
+
+The more-sophisticated device-mapper targets require complex metadata
+that is managed in kernel. In late 2010 we were seeing that various
+different targets were rolling their own data strutures, for example:
+
+- Mikulas Patocka's multisnap implementation
+- Heinz Mauelshagen's thin provisioning target
+- Another btree-based caching target posted to dm-devel
+- Another multi-snapshot target based on a design of Daniel Phillips
+
+Maintaining these data structures takes a lot of work, so if possible
+we'd like to reduce the number.
+
+The persistent-data library is an attempt to provide a re-usable
+framework for people who want to store metadata in device-mapper
+targets. It's currently used by the thin-provisioning target and an
+upcoming hierarchical storage target.
+
+Overview
+========
+
+The main documentation is in the header files which can all be found
+under drivers/md/persistent-data.
+
+The block manager
+-----------------
+
+dm-block-manager.[hc]
+
+This provides access to the data on disk in fixed sized-blocks. There
+is a read/write locking interface to prevent concurrent accesses, and
+keep data that is being used in the cache.
+
+Clients of persistent-data are unlikely to use this directly.
+
+The transaction manager
+-----------------------
+
+dm-transaction-manager.[hc]
+
+This restricts access to blocks and enforces copy-on-write semantics.
+The only way you can get hold of a writable block through the
+transaction manager is by shadowing an existing block (ie. doing
+copy-on-write) or allocating a fresh one. Shadowing is elided within
+the same transaction so performance is reasonable. The commit method
+ensures that all data is flushed before it writes the superblock.
+On power failure your metadata will be as it was when last committed.
+
+The Space Maps
+--------------
+
+dm-space-map.h
+dm-space-map-metadata.[hc]
+dm-space-map-disk.[hc]
+
+On-disk data structures that keep track of reference counts of blocks.
+Also acts as the allocator of new blocks. Currently two
+implementations: a simpler one for managing blocks on a different
+device (eg. thinly-provisioned data blocks); and one for managing
+the metadata space. The latter is complicated by the need to store
+its own data within the space it's managing.
+
+The data structures
+-------------------
+
+dm-btree.[hc]
+dm-btree-remove.c
+dm-btree-spine.c
+dm-btree-internal.h
+
+Currently there is only one data structure, a hierarchical btree.
+There are plans to add more. For example, something with an
+array-like interface would see a lot of use.
+
+The btree is 'hierarchical' in that you can define it to be composed
+of nested btrees, and take multiple keys. For example, the
+thin-provisioning target uses a btree with two levels of nesting.
+The first maps a device id to a mapping tree, and that in turn maps a
+virtual block to a physical block.
+
+Values stored in the btrees can have arbitrary size. Keys are always
+64bits, although nesting allows you to use multiple keys.
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
new file mode 100644
index 0000000..801d9d1
--- /dev/null
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -0,0 +1,285 @@
+Introduction
+============
+
+This document descibes a collection of device-mapper targets that
+between them implement thin-provisioning and snapshots.
+
+The main highlight of this implementation, compared to the previous
+implementation of snapshots, is that it allows many virtual devices to
+be stored on the same data volume. This simplifies administration and
+allows the sharing of data between volumes, thus reducing disk usage.
+
+Another significant feature is support for an arbitrary depth of
+recursive snapshots (snapshots of snapshots of snapshots ...). The
+previous implementation of snapshots did this by chaining together
+lookup tables, and so performance was O(depth). This new
+implementation uses a single data structure to avoid this degradation
+with depth. Fragmentation may still be an issue, however, in some
+scenarios.
+
+Metadata is stored on a separate device from data, giving the
+administrator some freedom, for example to:
+
+- Improve metadata resilience by storing metadata on a mirrored volume
+ but data on a non-mirrored one.
+
+- Improve performance by storing the metadata on SSD.
+
+Status
+======
+
+These targets are very much still in the EXPERIMENTAL state. Please
+do not yet rely on them in production. But do experiment and offer us
+feedback. Different use cases will have different performance
+characteristics, for example due to fragmentation of the data volume.
+
+If you find this software is not performing as expected please mail
+dm-devel@redhat.com with details and we'll try our best to improve
+things for you.
+
+Userspace tools for checking and repairing the metadata are under
+development.
+
+Cookbook
+========
+
+This section describes some quick recipes for using thin provisioning.
+They use the dmsetup program to control the device-mapper driver
+directly. End users will be advised to use a higher-level volume
+manager such as LVM2 once support has been added.
+
+Pool device
+-----------
+
+The pool device ties together the metadata volume and the data volume.
+It maps I/O linearly to the data volume and updates the metadata via
+two mechanisms:
+
+- Function calls from the thin targets
+
+- Device-mapper 'messages' from userspace which control the creation of new
+ virtual devices amongst other things.
+
+Setting up a fresh pool device
+------------------------------
+
+Setting up a pool device requires a valid metadata device, and a
+data device. If you do not have an existing metadata device you can
+make one by zeroing the first 4k to indicate empty metadata.
+
+ dd if=/dev/zero of=$metadata_dev bs=4096 count=1
+
+The amount of metadata you need will vary according to how many blocks
+are shared between thin devices (i.e. through snapshots). If you have
+less sharing than average you'll need a larger-than-average metadata device.
+
+As a guide, we suggest you calculate the number of bytes to use in the
+metadata device as 48 * $data_dev_size / $data_block_size but round it up
+to 2MB if the answer is smaller. The largest size supported is 16GB.
+
+If you're creating large numbers of snapshots which are recording large
+amounts of change, you may need find you need to increase this.
+
+Reloading a pool table
+----------------------
+
+You may reload a pool's table, indeed this is how the pool is resized
+if it runs out of space. (N.B. While specifying a different metadata
+device when reloading is not forbidden at the moment, things will go
+wrong if it does not route I/O to exactly the same on-disk location as
+previously.)
+
+Using an existing pool device
+-----------------------------
+
+ dmsetup create pool \
+ --table "0 20971520 thin-pool $metadata_dev $data_dev \
+ $data_block_size $low_water_mark"
+
+$data_block_size gives the smallest unit of disk space that can be
+allocated at a time expressed in units of 512-byte sectors. People
+primarily interested in thin provisioning may want to use a value such
+as 1024 (512KB). People doing lots of snapshotting may want a smaller value
+such as 128 (64KB). If you are not zeroing newly-allocated data,
+a larger $data_block_size in the region of 256000 (128MB) is suggested.
+$data_block_size must be the same for the lifetime of the
+metadata device.
+
+$low_water_mark is expressed in blocks of size $data_block_size. If
+free space on the data device drops below this level then a dm event
+will be triggered which a userspace daemon should catch allowing it to
+extend the pool device. Only one such event will be sent.
+Resuming a device with a new table itself triggers an event so the
+userspace daemon can use this to detect a situation where a new table
+already exceeds the threshold.
+
+Thin provisioning
+-----------------
+
+i) Creating a new thinly-provisioned volume.
+
+ To create a new thinly- provisioned volume you must send a message to an
+ active pool device, /dev/mapper/pool in this example.
+
+ dmsetup message /dev/mapper/pool 0 "create_thin 0"
+
+ Here '0' is an identifier for the volume, a 24-bit number. It's up
+ to the caller to allocate and manage these identifiers. If the
+ identifier is already in use, the message will fail with -EEXIST.
+
+ii) Using a thinly-provisioned volume.
+
+ Thinly-provisioned volumes are activated using the 'thin' target:
+
+ dmsetup create thin --table "0 2097152 thin /dev/mapper/pool 0"
+
+ The last parameter is the identifier for the thinp device.
+
+Internal snapshots
+------------------
+
+i) Creating an internal snapshot.
+
+ Snapshots are created with another message to the pool.
+
+ N.B. If the origin device that you wish to snapshot is active, you
+ must suspend it before creating the snapshot to avoid corruption.
+ This is NOT enforced at the moment, so please be careful!
+
+ dmsetup suspend /dev/mapper/thin
+ dmsetup message /dev/mapper/pool 0 "create_snap 1 0"
+ dmsetup resume /dev/mapper/thin
+
+ Here '1' is the identifier for the volume, a 24-bit number. '0' is the
+ identifier for the origin device.
+
+ii) Using an internal snapshot.
+
+ Once created, the user doesn't have to worry about any connection
+ between the origin and the snapshot. Indeed the snapshot is no
+ different from any other thinly-provisioned device and can be
+ snapshotted itself via the same method. It's perfectly legal to
+ have only one of them active, and there's no ordering requirement on
+ activating or removing them both. (This differs from conventional
+ device-mapper snapshots.)
+
+ Activate it exactly the same way as any other thinly-provisioned volume:
+
+ dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 1"
+
+Deactivation
+------------
+
+All devices using a pool must be deactivated before the pool itself
+can be.
+
+ dmsetup remove thin
+ dmsetup remove snap
+ dmsetup remove pool
+
+Reference
+=========
+
+'thin-pool' target
+------------------
+
+i) Constructor
+
+ thin-pool <metadata dev> <data dev> <data block size (sectors)> \
+ <low water mark (blocks)> [<number of feature args> [<arg>]*]
+
+ Optional feature arguments:
+ - 'skip_block_zeroing': skips the zeroing of newly-provisioned blocks.
+
+ Data block size must be between 64KB (128 sectors) and 1GB
+ (2097152 sectors) inclusive.
+
+
+ii) Status
+
+ <transaction id> <used metadata blocks>/<total metadata blocks>
+ <used data blocks>/<total data blocks> <held metadata root>
+
+
+ transaction id:
+ A 64-bit number used by userspace to help synchronise with metadata
+ from volume managers.
+
+ used data blocks / total data blocks
+ If the number of free blocks drops below the pool's low water mark a
+ dm event will be sent to userspace. This event is edge-triggered and
+ it will occur only once after each resume so volume manager writers
+ should register for the event and then check the target's status.
+
+ held metadata root:
+ The location, in sectors, of the metadata root that has been
+ 'held' for userspace read access. '-' indicates there is no
+ held root. This feature is not yet implemented so '-' is
+ always returned.
+
+iii) Messages
+
+ create_thin <dev id>
+
+ Create a new thinly-provisioned device.
+ <dev id> is an arbitrary unique 24-bit identifier chosen by
+ the caller.
+
+ create_snap <dev id> <origin id>
+
+ Create a new snapshot of another thinly-provisioned device.
+ <dev id> is an arbitrary unique 24-bit identifier chosen by
+ the caller.
+ <origin id> is the identifier of the thinly-provisioned device
+ of which the new device will be a snapshot.
+
+ delete <dev id>
+
+ Deletes a thin device. Irreversible.
+
+ trim <dev id> <new size in sectors>
+
+ Delete mappings from the end of a thin device. Irreversible.
+ You might want to use this if you're reducing the size of
+ your thinly-provisioned device. In many cases, due to the
+ sharing of blocks between devices, it is not possible to
+ determine in advance how much space 'trim' will release. (In
+ future a userspace tool might be able to perform this
+ calculation.)
+
+ set_transaction_id <current id> <new id>
+
+ Userland volume managers, such as LVM, need a way to
+ synchronise their external metadata with the internal metadata of the
+ pool target. The thin-pool target offers to store an
+ arbitrary 64-bit transaction id and return it on the target's
+ status line. To avoid races you must provide what you think
+ the current transaction id is when you change it with this
+ compare-and-swap message.
+
+'thin' target
+-------------
+
+i) Constructor
+
+ thin <pool dev> <dev id>
+
+ pool dev:
+ the thin-pool device, e.g. /dev/mapper/my_pool or 253:0
+
+ dev id:
+ the internal device identifier of the device to be
+ activated.
+
+The pool doesn't store any size against the thin devices. If you
+load a thin target that is smaller than you've been using previously,
+then you'll have no access to blocks mapped beyond the end. If you
+load a target that is bigger than before, then extra blocks will be
+provisioned as and when needed.
+
+If you wish to reduce the size of your thin device and potentially
+regain some space then send the 'trim' message to the pool.
+
+ii) Status
+
+ <nr mapped sectors> <highest mapped sector>
diff --git a/Documentation/devicetree/bindings/virtio/mmio.txt b/Documentation/devicetree/bindings/virtio/mmio.txt
new file mode 100644
index 0000000..5069c1b
--- /dev/null
+++ b/Documentation/devicetree/bindings/virtio/mmio.txt
@@ -0,0 +1,17 @@
+* virtio memory mapped device
+
+See http://ozlabs.org/~rusty/virtio-spec/ for more details.
+
+Required properties:
+
+- compatible: "virtio,mmio" compatibility string
+- reg: control registers base address and size including configuration space
+- interrupts: interrupt generated by the device
+
+Example:
+
+ virtio_block@3000 {
+ compatible = "virtio,mmio";
+ reg = <0x3000 0x100>;
+ interrupts = <41>;
+ }
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 7c799fc..3d84912 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -133,41 +133,6 @@
---------------------------
-What: sys_sysctl
-When: September 2010
-Option: CONFIG_SYSCTL_SYSCALL
-Why: The same information is available in a more convenient from
- /proc/sys, and none of the sysctl variables appear to be
- important performance wise.
-
- Binary sysctls are a long standing source of subtle kernel
- bugs and security issues.
-
- When I looked several months ago all I could find after
- searching several distributions were 5 user space programs and
- glibc (which falls back to /proc/sys) using this syscall.
-
- The man page for sysctl(2) documents it as unusable for user
- space programs.
-
- sysctl(2) is not generally ABI compatible to a 32bit user
- space application on a 64bit and a 32bit kernel.
-
- For the last several months the policy has been no new binary
- sysctls and no one has put forward an argument to use them.
-
- Binary sysctls issues seem to keep happening appearing so
- properly deprecating them (with a warning to user space) and a
- 2 year grace warning period will mean eventually we can kill
- them and end the pain.
-
- In the mean time individual binary sysctls can be dealt with
- in a piecewise fashion.
-
-Who: Eric Biederman <ebiederm@xmission.com>
-
----------------------------
-
What: /proc/<pid>/oom_adj
When: August 2012
Why: /proc/<pid>/oom_adj allows userspace to influence the oom killer's
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 6533807..d819ba1 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -29,6 +29,7 @@
d_compare: yes no no maybe
d_delete: no yes no no
d_release: no no yes no
+d_prune: no yes no no
d_iput: no no yes no
d_dname: no no no no
d_automount: no no yes no
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 22f3a0e..b100adc 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -73,14 +73,6 @@
also be used to enable or disable barriers, for
consistency with other ext3 mount options.
-orlov (*) This enables the new Orlov block allocator. It is
- enabled by default.
-
-oldalloc This disables the Orlov block allocator and enables
- the old block allocator. Orlov should have better
- performance - we'd like to get some feedback if it's
- the contrary for you.
-
user_xattr Enables Extended User Attributes. Additionally, you
need to have extended attribute support enabled in the
kernel configuration (CONFIG_EXT3_FS_XATTR). See the
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 232a575..4917cf2 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -160,7 +160,9 @@
lead to any number of problems.
data=journal All data are committed into the journal prior to being
- written into the main file system.
+ written into the main file system. Enabling
+ this mode will disable delayed allocation and
+ O_DIRECT support.
data=ordered (*) All data are forced directly out to the main file
system prior to its metadata being committed to the
@@ -201,30 +203,19 @@
table readahead algorithm will pre-read into
the buffer cache. The default value is 32 blocks.
-orlov (*) This enables the new Orlov block allocator. It is
- enabled by default.
-
-oldalloc This disables the Orlov block allocator and enables
- the old block allocator. Orlov should have better
- performance - we'd like to get some feedback if it's
- the contrary for you.
-
-user_xattr Enables Extended User Attributes. Additionally, you
- need to have extended attribute support enabled in the
- kernel configuration (CONFIG_EXT4_FS_XATTR). See the
- attr(5) manual page and http://acl.bestbits.at/ to
- learn more about extended attributes.
-
-nouser_xattr Disables Extended User Attributes.
-
-acl Enables POSIX Access Control Lists support.
- Additionally, you need to have ACL support enabled in
- the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL).
- See the acl(5) manual page and http://acl.bestbits.at/
- for more information.
+nouser_xattr Disables Extended User Attributes. If you have extended
+ attribute support enabled in the kernel configuration
+ (CONFIG_EXT4_FS_XATTR), extended attribute support
+ is enabled by default on mount. See the attr(5) manual
+ page and http://acl.bestbits.at/ for more information
+ about extended attributes.
noacl This option disables POSIX Access Control List
- support.
+ support. If ACL support is enabled in the kernel
+ configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is
+ enabled by default on mount. See the acl(5) manual
+ page and http://acl.bestbits.at/ for more information
+ about acl.
bsddf (*) Make 'df' act like BSD.
minixdf Make 'df' act like Minix.
@@ -419,8 +410,8 @@
In the event of a crash, the journal can be replayed, bringing both data and
metadata into a consistent state. This mode is the slowest except when data
needs to be read from and written to disk at the same time where it
-outperforms all others modes. Currently ext4 does not have delayed
-allocation support if this data journalling mode is selected.
+outperforms all others modes. Enabling this mode will disable delayed
+allocation and O_DIRECT support.
/proc entries
=============
diff --git a/Documentation/hwspinlock.txt b/Documentation/hwspinlock.txt
index 7dcd1a4..a903ee5 100644
--- a/Documentation/hwspinlock.txt
+++ b/Documentation/hwspinlock.txt
@@ -39,23 +39,20 @@
in case an unused hwspinlock isn't available. Users of this
API will usually want to communicate the lock's id to the remote core
before it can be used to achieve synchronization.
- Can be called from an atomic context (this function will not sleep) but
- not from within interrupt context.
+ Should be called from a process context (might sleep).
struct hwspinlock *hwspin_lock_request_specific(unsigned int id);
- assign a specific hwspinlock id and return its address, or NULL
if that hwspinlock is already in use. Usually board code will
be calling this function in order to reserve specific hwspinlock
ids for predefined purposes.
- Can be called from an atomic context (this function will not sleep) but
- not from within interrupt context.
+ Should be called from a process context (might sleep).
int hwspin_lock_free(struct hwspinlock *hwlock);
- free a previously-assigned hwspinlock; returns 0 on success, or an
appropriate error code on failure (e.g. -EINVAL if the hwspinlock
is already free).
- Can be called from an atomic context (this function will not sleep) but
- not from within interrupt context.
+ Should be called from a process context (might sleep).
int hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int timeout);
- lock a previously-assigned hwspinlock with a timeout limit (specified in
@@ -230,45 +227,62 @@
4. API for implementors
- int hwspin_lock_register(struct hwspinlock *hwlock);
+ int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev,
+ const struct hwspinlock_ops *ops, int base_id, int num_locks);
- to be called from the underlying platform-specific implementation, in
- order to register a new hwspinlock instance. Can be called from an atomic
- context (this function will not sleep) but not from within interrupt
- context. Returns 0 on success, or appropriate error code on failure.
+ order to register a new hwspinlock device (which is usually a bank of
+ numerous locks). Should be called from a process context (this function
+ might sleep).
+ Returns 0 on success, or appropriate error code on failure.
- struct hwspinlock *hwspin_lock_unregister(unsigned int id);
+ int hwspin_lock_unregister(struct hwspinlock_device *bank);
- to be called from the underlying vendor-specific implementation, in order
- to unregister an existing (and unused) hwspinlock instance.
- Can be called from an atomic context (will not sleep) but not from
- within interrupt context.
+ to unregister an hwspinlock device (which is usually a bank of numerous
+ locks).
+ Should be called from a process context (this function might sleep).
Returns the address of hwspinlock on success, or NULL on error (e.g.
if the hwspinlock is sill in use).
-5. struct hwspinlock
+5. Important structs
-This struct represents an hwspinlock instance. It is registered by the
-underlying hwspinlock implementation using the hwspin_lock_register() API.
+struct hwspinlock_device is a device which usually contains a bank
+of hardware locks. It is registered by the underlying hwspinlock
+implementation using the hwspin_lock_register() API.
/**
- * struct hwspinlock - vendor-specific hwspinlock implementation
- *
- * @dev: underlying device, will be used with runtime PM api
- * @ops: vendor-specific hwspinlock handlers
- * @id: a global, unique, system-wide, index of the lock.
- * @lock: initialized and used by hwspinlock core
- * @owner: underlying implementation module, used to maintain module ref count
+ * struct hwspinlock_device - a device which usually spans numerous hwspinlocks
+ * @dev: underlying device, will be used to invoke runtime PM api
+ * @ops: platform-specific hwspinlock handlers
+ * @base_id: id index of the first lock in this device
+ * @num_locks: number of locks in this device
+ * @lock: dynamically allocated array of 'struct hwspinlock'
*/
-struct hwspinlock {
+struct hwspinlock_device {
struct device *dev;
const struct hwspinlock_ops *ops;
- int id;
- spinlock_t lock;
- struct module *owner;
+ int base_id;
+ int num_locks;
+ struct hwspinlock lock[0];
};
-The underlying implementation is responsible to assign the dev, ops, id and
-owner members. The lock member, OTOH, is initialized and used by the hwspinlock
-core.
+struct hwspinlock_device contains an array of hwspinlock structs, each
+of which represents a single hardware lock:
+
+/**
+ * struct hwspinlock - this struct represents a single hwspinlock instance
+ * @bank: the hwspinlock_device structure which owns this lock
+ * @lock: initialized and used by hwspinlock core
+ * @priv: private data, owned by the underlying platform-specific hwspinlock drv
+ */
+struct hwspinlock {
+ struct hwspinlock_device *bank;
+ spinlock_t lock;
+ void *priv;
+};
+
+When registering a bank of locks, the hwspinlock driver only needs to
+set the priv members of the locks. The rest of the members are set and
+initialized by the hwspinlock core itself.
6. Implementation callbacks
diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt
index 4ccdbca..f2a2488 100644
--- a/Documentation/networking/ipvs-sysctl.txt
+++ b/Documentation/networking/ipvs-sysctl.txt
@@ -15,6 +15,23 @@
enabled and the variable is automatically set to 2, otherwise
the strategy is disabled and the variable is set to 1.
+conntrack - BOOLEAN
+ 0 - disabled (default)
+ not 0 - enabled
+
+ If set, maintain connection tracking entries for
+ connections handled by IPVS.
+
+ This should be enabled if connections handled by IPVS are to be
+ also handled by stateful firewall rules. That is, iptables rules
+ that make use of connection tracking. It is a performance
+ optimisation to disable this setting otherwise.
+
+ Connections handled by the IPVS FTP application module
+ will have connection tracking entries regardless of this setting.
+
+ Only available when IPVS is compiled with CONFIG_IP_VS_NFCT enabled.
+
cache_bypass - BOOLEAN
0 - disabled (default)
not 0 - enabled
@@ -39,7 +56,7 @@
11 - IPVS packet handling (ip_vs_in/ip_vs_out)
12 or more - packet traversal
- Only available when IPVS is compiled with the CONFIG_IPVS_DEBUG
+ Only available when IPVS is compiled with CONFIG_IP_VS_DEBUG enabled.
Higher debugging levels include the messages for lower debugging
levels, so setting debug level 2, includes level 0, 1 and 2
@@ -123,13 +140,11 @@
secure_tcp - INTEGER
0 - disabled (default)
- The secure_tcp defense is to use a more complicated state
- transition table and some possible short timeouts of each
- state. In the VS/NAT, it delays the entering the ESTABLISHED
- until the real server starts to send data and ACK packet
- (after 3-way handshake).
+ The secure_tcp defense is to use a more complicated TCP state
+ transition table. For VS/NAT, it also delays entering the
+ TCP ESTABLISHED state until the three way handshake is completed.
- The value definition is the same as that of drop_entry or
+ The value definition is the same as that of drop_entry and
drop_packet.
sync_threshold - INTEGER
@@ -141,3 +156,36 @@
synchronized, every time the number of its incoming packets
modulus 50 equals the threshold. The range of the threshold is
from 0 to 49.
+
+snat_reroute - BOOLEAN
+ 0 - disabled
+ not 0 - enabled (default)
+
+ If enabled, recalculate the route of SNATed packets from
+ realservers so that they are routed as if they originate from the
+ director. Otherwise they are routed as if they are forwarded by the
+ director.
+
+ If policy routing is in effect then it is possible that the route
+ of a packet originating from a director is routed differently to a
+ packet being forwarded by the director.
+
+ If policy routing is not in effect then the recalculated route will
+ always be the same as the original route so it is an optimisation
+ to disable snat_reroute and avoid the recalculation.
+
+sync_version - INTEGER
+ default 1
+
+ The version of the synchronisation protocol used when sending
+ synchronisation messages.
+
+ 0 selects the original synchronisation protocol (version 0). This
+ should be used when sending synchronisation messages to a legacy
+ system that only understands the original synchronisation protocol.
+
+ 1 selects the current synchronisation protocol (version 1). This
+ should be used where possible.
+
+ Kernels with this sync_version entry are able to receive messages
+ of both version 1 and version 2 of the synchronisation protocol.
diff --git a/Documentation/rapidio/rapidio.txt b/Documentation/rapidio/rapidio.txt
index be70ee1..c75694b 100644
--- a/Documentation/rapidio/rapidio.txt
+++ b/Documentation/rapidio/rapidio.txt
@@ -144,7 +144,7 @@
After the host has completed enumeration of the entire network it releases
devices by clearing device ID locks (calls rio_clear_locks()). For each endpoint
-in the system, it sets the Master Enable bit in the Port General Control CSR
+in the system, it sets the Discovered bit in the Port General Control CSR
to indicate that enumeration is completed and agents are allowed to execute
passive discovery of the network.
diff --git a/Documentation/rapidio/tsi721.txt b/Documentation/rapidio/tsi721.txt
new file mode 100644
index 0000000..335f3c6
--- /dev/null
+++ b/Documentation/rapidio/tsi721.txt
@@ -0,0 +1,49 @@
+RapidIO subsystem mport driver for IDT Tsi721 PCI Express-to-SRIO bridge.
+=========================================================================
+
+I. Overview
+
+This driver implements all currently defined RapidIO mport callback functions.
+It supports maintenance read and write operations, inbound and outbound RapidIO
+doorbells, inbound maintenance port-writes and RapidIO messaging.
+
+To generate SRIO maintenance transactions this driver uses one of Tsi721 DMA
+channels. This mechanism provides access to larger range of hop counts and
+destination IDs without need for changes in outbound window translation.
+
+RapidIO messaging support uses dedicated messaging channels for each mailbox.
+For inbound messages this driver uses destination ID matching to forward messages
+into the corresponding message queue. Messaging callbacks are implemented to be
+fully compatible with RIONET driver (Ethernet over RapidIO messaging services).
+
+II. Known problems
+
+ None.
+
+III. To do
+
+ Add DMA data transfers (non-messaging).
+ Add inbound region (SRIO-to-PCIe) mapping.
+
+IV. Version History
+
+ 1.0.0 - Initial driver release.
+
+V. License
+-----------------------------------------------
+
+ Copyright(c) 2011 Integrated Device Technology, Inc. All rights reserved.
+
+ This program is free software; you can redistribute it and/or modify it
+ under the terms of the GNU General Public License as published by the Free
+ Software Foundation; either version 2 of the License, or (at your option)
+ any later version.
+
+ This program is distributed in the hope that it will be useful, but WITHOUT
+ ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ more details.
+
+ You should have received a copy of the GNU General Public License along with
+ this program; if not, write to the Free Software Foundation, Inc.,
+ 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
diff --git a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
index 5d0fc8b..77dfecf 100644
--- a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
+++ b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
@@ -134,13 +134,13 @@
______________________________________________________________________
- 11.. IInnttrroodduuccttiioonn
+ 1. Introduction
Welcome to User Mode Linux. It's going to be fun.
- 11..11.. HHooww iiss UUsseerr MMooddee LLiinnuuxx DDiiffffeerreenntt??
+ 1.1. How is User Mode Linux Different?
Normally, the Linux Kernel talks straight to your hardware (video
card, keyboard, hard drives, etc), and any programs which run ask the
@@ -181,7 +181,7 @@
- 11..22.. WWhhyy WWoouulldd II WWaanntt UUsseerr MMooddee LLiinnuuxx??
+ 1.2. Why Would I Want User Mode Linux?
1. If User Mode Linux crashes, your host kernel is still fine.
@@ -206,12 +206,12 @@
- 22.. CCoommppiilliinngg tthhee kkeerrnneell aanndd mmoodduulleess
+ 2. Compiling the kernel and modules
- 22..11.. CCoommppiilliinngg tthhee kkeerrnneell
+ 2.1. Compiling the kernel
Compiling the user mode kernel is just like compiling any other
@@ -322,7 +322,7 @@
bug fixes and enhancements that have gone into subsequent releases.
- 22..22.. CCoommppiilliinngg aanndd iinnssttaalllliinngg kkeerrnneell mmoodduulleess
+ 2.2. Compiling and installing kernel modules
UML modules are built in the same way as the native kernel (with the
exception of the 'ARCH=um' that you always need for UML):
@@ -386,19 +386,19 @@
- 22..33.. CCoommppiilliinngg aanndd iinnssttaalllliinngg uummll__uuttiilliittiieess
+ 2.3. Compiling and installing uml_utilities
Many features of the UML kernel require a user-space helper program,
so a uml_utilities package is distributed separately from the kernel
patch which provides these helpers. Included within this is:
- +o port-helper - Used by consoles which connect to xterms or ports
+ o port-helper - Used by consoles which connect to xterms or ports
- +o tunctl - Configuration tool to create and delete tap devices
+ o tunctl - Configuration tool to create and delete tap devices
- +o uml_net - Setuid binary for automatic tap device configuration
+ o uml_net - Setuid binary for automatic tap device configuration
- +o uml_switch - User-space virtual switch required for daemon
+ o uml_switch - User-space virtual switch required for daemon
transport
The uml_utilities tree is compiled with:
@@ -423,11 +423,11 @@
- 33.. RRuunnnniinngg UUMMLL aanndd llooggggiinngg iinn
+ 3. Running UML and logging in
- 33..11.. RRuunnnniinngg UUMMLL
+ 3.1. Running UML
It runs on 2.2.15 or later, and all 2.4 kernels.
@@ -454,7 +454,7 @@
- 33..22.. LLooggggiinngg iinn
+ 3.2. Logging in
@@ -468,7 +468,7 @@
There are a couple of other ways to log in:
- +o On a virtual console
+ o On a virtual console
@@ -480,7 +480,7 @@
- +o Over the serial line
+ o Over the serial line
In the boot output, find a line that looks like:
@@ -503,7 +503,7 @@
- +o Over the net
+ o Over the net
If the network is running, then you can telnet to the virtual
@@ -514,13 +514,13 @@
down and the process will exit.
- 33..33.. EExxaammpplleess
+ 3.3. Examples
Here are some examples of UML in action:
- +o A login session <http://user-mode-linux.sourceforge.net/login.html>
+ o A login session <http://user-mode-linux.sourceforge.net/login.html>
- +o A virtual network <http://user-mode-linux.sourceforge.net/net.html>
+ o A virtual network <http://user-mode-linux.sourceforge.net/net.html>
@@ -528,12 +528,12 @@
- 44.. UUMMLL oonn 22GG//22GG hhoossttss
+ 4. UML on 2G/2G hosts
- 44..11.. IInnttrroodduuccttiioonn
+ 4.1. Introduction
Most Linux machines are configured so that the kernel occupies the
@@ -546,7 +546,7 @@
- 44..22.. TThhee pprroobblleemm
+ 4.2. The problem
The prebuilt UML binaries on this site will not run on 2G/2G hosts
@@ -558,7 +558,7 @@
- 44..33.. TThhee ssoolluuttiioonn
+ 4.3. The solution
The fix for this is to rebuild UML from source after enabling
@@ -576,7 +576,7 @@
- 55.. SSeettttiinngg uupp sseerriiaall lliinneess aanndd ccoonnssoolleess
+ 5. Setting up serial lines and consoles
It is possible to attach UML serial lines and consoles to many types
@@ -586,12 +586,12 @@
You can attach them to host ptys, ttys, file descriptors, and ports.
This allows you to do things like
- +o have a UML console appear on an unused host console,
+ o have a UML console appear on an unused host console,
- +o hook two virtual machines together by having one attach to a pty
+ o hook two virtual machines together by having one attach to a pty
and having the other attach to the corresponding tty
- +o make a virtual machine accessible from the net by attaching a
+ o make a virtual machine accessible from the net by attaching a
console to a port on the host.
@@ -599,7 +599,7 @@
- 55..11.. SSppeecciiffyyiinngg tthhee ddeevviiccee
+ 5.1. Specifying the device
Devices are specified with "con" or "ssl" (console or serial line,
respectively), optionally with a device number if you are talking
@@ -626,13 +626,13 @@
- 55..22.. SSppeecciiffyyiinngg tthhee cchhaannnneell
+ 5.2. Specifying the channel
There are a number of different types of channels to attach a UML
device to, each with a different way of specifying exactly what to
attach to.
- +o pseudo-terminals - device=pty pts terminals - device=pts
+ o pseudo-terminals - device=pty pts terminals - device=pts
This will cause UML to allocate a free host pseudo-terminal for the
@@ -640,20 +640,20 @@
log. You access it by attaching a terminal program to the
corresponding tty:
- +o screen /dev/pts/n
+ o screen /dev/pts/n
- +o screen /dev/ttyxx
+ o screen /dev/ttyxx
- +o minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
+ o minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
devices
- +o kermit - start it up, 'open' the device, then 'connect'
+ o kermit - start it up, 'open' the device, then 'connect'
- +o terminals - device=tty:tty device file
+ o terminals - device=tty:tty device file
This will make UML attach the device to the specified tty (i.e
@@ -672,7 +672,7 @@
- +o xterms - device=xterm
+ o xterms - device=xterm
UML will run an xterm and the device will be attached to it.
@@ -681,7 +681,7 @@
- +o Port - device=port:port number
+ o Port - device=port:port number
This will attach the UML devices to the specified host port.
@@ -725,7 +725,7 @@
- +o already-existing file descriptors - device=file descriptor
+ o already-existing file descriptors - device=file descriptor
If you set up a file descriptor on the UML command line, you can
@@ -743,7 +743,7 @@
- +o Nothing - device=null
+ o Nothing - device=null
This allows the device to be opened, in contrast to 'none', but
@@ -754,7 +754,7 @@
- +o None - device=none
+ o None - device=none
This causes the device to disappear.
@@ -770,7 +770,7 @@
- will cause serial line 3 to accept input on the host's /dev/tty3 and
+ will cause serial line 3 to accept input on the host's /dev/tty2 and
display output on an xterm. That's a silly example - the most common
use of this syntax is to reattach the main console to stdin and stdout
as shown above.
@@ -785,7 +785,7 @@
- 55..33.. EExxaammpplleess
+ 5.3. Examples
There are a number of interesting things you can do with this
capability.
@@ -838,7 +838,7 @@
prompt of the other virtual machine.
- 66.. SSeettttiinngg uupp tthhee nneettwwoorrkk
+ 6. Setting up the network
@@ -858,19 +858,19 @@
There are currently five transport types available for a UML virtual
machine to exchange packets with other hosts:
- +o ethertap
+ o ethertap
- +o TUN/TAP
+ o TUN/TAP
- +o Multicast
+ o Multicast
- +o a switch daemon
+ o a switch daemon
- +o slip
+ o slip
- +o slirp
+ o slirp
- +o pcap
+ o pcap
The TUN/TAP, ethertap, slip, and slirp transports allow a UML
instance to exchange packets with the host. They may be directed
@@ -893,28 +893,28 @@
With so many host transports, which one should you use? Here's when
you should use each one:
- +o ethertap - if you want access to the host networking and it is
+ o ethertap - if you want access to the host networking and it is
running 2.2
- +o TUN/TAP - if you want access to the host networking and it is
+ o TUN/TAP - if you want access to the host networking and it is
running 2.4. Also, the TUN/TAP transport is able to use a
preconfigured device, allowing it to avoid using the setuid uml_net
helper, which is a security advantage.
- +o Multicast - if you want a purely virtual network and you don't want
+ o Multicast - if you want a purely virtual network and you don't want
to set up anything but the UML
- +o a switch daemon - if you want a purely virtual network and you
+ o a switch daemon - if you want a purely virtual network and you
don't mind running the daemon in order to get somewhat better
performance
- +o slip - there is no particular reason to run the slip backend unless
+ o slip - there is no particular reason to run the slip backend unless
ethertap and TUN/TAP are just not available for some reason
- +o slirp - if you don't have root access on the host to setup
+ o slirp - if you don't have root access on the host to setup
networking, or if you don't want to allocate an IP to your UML
- +o pcap - not much use for actual network connectivity, but great for
+ o pcap - not much use for actual network connectivity, but great for
monitoring traffic on the host
Ethertap is available on 2.4 and works fine. TUN/TAP is preferred
@@ -926,7 +926,7 @@
exploit the helper's root privileges.
- 66..11.. GGeenneerraall sseettuupp
+ 6.1. General setup
First, you must have the virtual network enabled in your UML. If are
running a prebuilt kernel from this site, everything is already
@@ -995,7 +995,7 @@
- 66..22.. UUsseerrssppaaccee ddaaeemmoonnss
+ 6.2. Userspace daemons
You will likely need the setuid helper, or the switch daemon, or both.
They are both installed with the RPM and deb, so if you've installed
@@ -1011,7 +1011,7 @@
- 66..33.. SSppeecciiffyyiinngg eetthheerrnneett aaddddrreesssseess
+ 6.3. Specifying ethernet addresses
Below, you will see that the TUN/TAP, ethertap, and daemon interfaces
allow you to specify hardware addresses for the virtual ethernet
@@ -1023,11 +1023,11 @@
sufficient to guarantee a unique hardware address for the device. A
couple of exceptions are:
- +o Another set of virtual ethernet devices are on the same network and
+ o Another set of virtual ethernet devices are on the same network and
they are assigned hardware addresses using a different scheme which
may conflict with the UML IP address-based scheme
- +o You aren't going to use the device for IP networking, so you don't
+ o You aren't going to use the device for IP networking, so you don't
assign the device an IP address
If you let the driver provide the hardware address, you should make
@@ -1049,7 +1049,7 @@
- 66..44.. UUMMLL iinntteerrffaaccee sseettuupp
+ 6.4. UML interface setup
Once the network devices have been described on the command line, you
should boot UML and log in.
@@ -1131,7 +1131,7 @@
- 66..55.. MMuullttiiccaasstt
+ 6.5. Multicast
The simplest way to set up a virtual network between multiple UMLs is
to use the mcast transport. This was written by Harald Welte and is
@@ -1194,7 +1194,7 @@
- 66..66.. TTUUNN//TTAAPP wwiitthh tthhee uummll__nneett hheellppeerr
+ 6.6. TUN/TAP with the uml_net helper
TUN/TAP is the preferred mechanism on 2.4 to exchange packets with the
host. The TUN/TAP backend has been in UML since 2.4.9-3um.
@@ -1247,10 +1247,10 @@
There are a couple potential problems with running the TUN/TAP
transport on a 2.4 host kernel
- +o TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host
+ o TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host
kernel or use the ethertap transport.
- +o With an upgraded kernel, TUN/TAP may fail with
+ o With an upgraded kernel, TUN/TAP may fail with
File descriptor in bad state
@@ -1269,7 +1269,7 @@
- 66..77.. TTUUNN//TTAAPP wwiitthh aa pprreeccoonnffiigguurreedd ttaapp ddeevviiccee
+ 6.7. TUN/TAP with a preconfigured tap device
If you prefer not to have UML use uml_net (which is somewhat
insecure), with UML 2.4.17-11, you can set up a TUN/TAP device
@@ -1277,7 +1277,7 @@
there is no need for root assistance. Setting up the device is done
as follows:
- +o Create the device with tunctl (available from the UML utilities
+ o Create the device with tunctl (available from the UML utilities
tarball)
@@ -1291,7 +1291,7 @@
where uid is the user id or username that UML will be run as. This
will tell you what device was created.
- +o Configure the device IP (change IP addresses and device name to
+ o Configure the device IP (change IP addresses and device name to
suit)
@@ -1303,7 +1303,7 @@
- +o Set up routing and arping if desired - this is my recipe, there are
+ o Set up routing and arping if desired - this is my recipe, there are
other ways of doing the same thing
@@ -1338,7 +1338,7 @@
utility which reads the information from a config file and sets up
devices at boot time.
- +o Rather than using up two IPs and ARPing for one of them, you can
+ o Rather than using up two IPs and ARPing for one of them, you can
also provide direct access to your LAN by the UML by using a
bridge.
@@ -1417,7 +1417,7 @@
Note that 'br0' should be setup using ifconfig with the existing IP
address of eth0, as eth0 no longer has its own IP.
- +o
+ o
Also, the /dev/net/tun device must be writable by the user running
@@ -1438,11 +1438,11 @@
devices and chgrp /dev/net/tun to that group with mode 664 or 660.
- +o Once the device is set up, run UML with 'eth0=tuntap,device name'
+ o Once the device is set up, run UML with 'eth0=tuntap,device name'
(i.e. 'eth0=tuntap,tap0') on the command line (or do it with the
mconsole config command).
- +o Bring the eth device up in UML and you're in business.
+ o Bring the eth device up in UML and you're in business.
If you don't want that tap device any more, you can make it non-
persistent with
@@ -1465,7 +1465,7 @@
- 66..88.. EEtthheerrttaapp
+ 6.8. Ethertap
Ethertap is the general mechanism on 2.2 for userspace processes to
exchange packets with the kernel.
@@ -1561,9 +1561,9 @@
- 66..99.. TThhee sswwiittcchh ddaaeemmoonn
+ 6.9. The switch daemon
- NNoottee: This is the daemon formerly known as uml_router, but which was
+ Note: This is the daemon formerly known as uml_router, but which was
renamed so the network weenies of the world would stop growling at me.
@@ -1649,7 +1649,7 @@
- 66..1100.. SSlliipp
+ 6.10. Slip
Slip is another, less general, mechanism for a process to communicate
with the host networking. In contrast to the ethertap interface,
@@ -1681,7 +1681,7 @@
- 66..1111.. SSlliirrpp
+ 6.11. Slirp
slirp uses an external program, usually /usr/bin/slirp, to provide IP
only networking connectivity through the host. This is similar to IP
@@ -1737,7 +1737,7 @@
- 66..1122.. ppccaapp
+ 6.12. pcap
The pcap transport is attached to a UML ethernet device on the command
line or with uml_mconsole with the following syntax:
@@ -1777,7 +1777,7 @@
- 66..1133.. SSeettttiinngg uupp tthhee hhoosstt yyoouurrsseellff
+ 6.13. Setting up the host yourself
If you don't specify an address for the host side of the ethertap or
slip device, UML won't do any setup on the host. So this is what is
@@ -1785,7 +1785,7 @@
192.168.0.251 and a UML-side IP of 192.168.0.250 - adjust to suit your
own network):
- +o The device needs to be configured with its IP address. Tap devices
+ o The device needs to be configured with its IP address. Tap devices
are also configured with an mtu of 1484. Slip devices are
configured with a point-to-point address pointing at the UML ip
address.
@@ -1805,7 +1805,7 @@
- +o If a tap device is being set up, a route is set to the UML IP.
+ o If a tap device is being set up, a route is set to the UML IP.
UML# route add -host 192.168.0.250 gw 192.168.0.251
@@ -1814,7 +1814,7 @@
- +o To allow other hosts on your network to see the virtual machine,
+ o To allow other hosts on your network to see the virtual machine,
proxy arp is set up for it.
@@ -1824,7 +1824,7 @@
- +o Finally, the host is set up to route packets.
+ o Finally, the host is set up to route packets.
host# echo 1 > /proc/sys/net/ipv4/ip_forward
@@ -1838,12 +1838,12 @@
- 77.. SShhaarriinngg FFiilleessyysstteemmss bbeettwweeeenn VViirrttuuaall MMaacchhiinneess
+ 7. Sharing Filesystems between Virtual Machines
- 77..11.. AA wwaarrnniinngg
+ 7.1. A warning
Don't attempt to share filesystems simply by booting two UMLs from the
same file. That's the same thing as booting two physical machines
@@ -1851,7 +1851,7 @@
- 77..22.. UUssiinngg llaayyeerreedd bblloocckk ddeevviicceess
+ 7.2. Using layered block devices
The way to share a filesystem between two virtual machines is to use
the copy-on-write (COW) layering capability of the ubd block driver.
@@ -1896,7 +1896,7 @@
- 77..33.. NNoottee!!
+ 7.3. Note!
When checking the size of the COW file in order to see the gobs of
space that you're saving, make sure you use 'ls -ls' to see the actual
@@ -1926,7 +1926,7 @@
- 77..44.. AAnnootthheerr wwaarrnniinngg
+ 7.4. Another warning
Once a filesystem is being used as a readonly backing file for a COW
file, do not boot directly from it or modify it in any way. Doing so
@@ -1952,7 +1952,7 @@
- 77..55.. uummll__mmoooo :: MMeerrggiinngg aa CCOOWW ffiillee wwiitthh iittss bbaacckkiinngg ffiillee
+ 7.5. uml_moo : Merging a COW file with its backing file
Depending on how you use UML and COW devices, it may be advisable to
merge the changes in the COW file into the backing file every once in
@@ -2001,7 +2001,7 @@
- 88.. CCrreeaattiinngg ffiilleessyysstteemmss
+ 8. Creating filesystems
You may want to create and mount new UML filesystems, either because
@@ -2015,7 +2015,7 @@
should be easy to translate to the filesystem of your choice.
- 88..11.. CCrreeaattee tthhee ffiilleessyysstteemm ffiillee
+ 8.1. Create the filesystem file
dd is your friend. All you need to do is tell dd to create an empty
file of the appropriate size. I usually make it sparse to save time
@@ -2032,7 +2032,7 @@
- 88..22.. AAssssiiggnn tthhee ffiillee ttoo aa UUMMLL ddeevviiccee
+ 8.2. Assign the file to a UML device
Add an argument like the following to the UML command line:
@@ -2045,7 +2045,7 @@
- 88..33.. CCrreeaattiinngg aanndd mmoouunnttiinngg tthhee ffiilleessyysstteemm
+ 8.3. Creating and mounting the filesystem
Make sure that the filesystem is available, either by being built into
the kernel, or available as a module, then boot up UML and log in. If
@@ -2096,7 +2096,7 @@
- 99.. HHoosstt ffiillee aacccceessss
+ 9. Host file access
If you want to access files on the host machine from inside UML, you
@@ -2112,7 +2112,7 @@
files contained in it just as you would on the host.
- 99..11.. UUssiinngg hhoossttffss
+ 9.1. Using hostfs
To begin with, make sure that hostfs is available inside the virtual
machine with
@@ -2151,7 +2151,7 @@
- 99..22.. hhoossttffss aass tthhee rroooott ffiilleessyysstteemm
+ 9.2. hostfs as the root filesystem
It's possible to boot from a directory hierarchy on the host using
hostfs rather than using the standard filesystem in a file.
@@ -2194,20 +2194,20 @@
UML should then boot as it does normally.
- 99..33.. BBuuiillddiinngg hhoossttffss
+ 9.3. Building hostfs
If you need to build hostfs because it's not in your kernel, you have
two choices:
- +o Compiling hostfs into the kernel:
+ o Compiling hostfs into the kernel:
Reconfigure the kernel and set the 'Host filesystem' option under
- +o Compiling hostfs as a module:
+ o Compiling hostfs as a module:
Reconfigure the kernel and set the 'Host filesystem' option under
@@ -2228,7 +2228,7 @@
- 1100.. TThhee MMaannaaggeemmeenntt CCoonnssoollee
+ 10. The Management Console
@@ -2240,15 +2240,15 @@
There are a number of things you can do with the mconsole interface:
- +o get the kernel version
+ o get the kernel version
- +o add and remove devices
+ o add and remove devices
- +o halt or reboot the machine
+ o halt or reboot the machine
- +o Send SysRq commands
+ o Send SysRq commands
- +o Pause and resume the UML
+ o Pause and resume the UML
You need the mconsole client (uml_mconsole) which is present in CVS
@@ -2300,28 +2300,28 @@
You'll get a prompt, at which you can run one of these commands:
- +o version
+ o version
- +o halt
+ o halt
- +o reboot
+ o reboot
- +o config
+ o config
- +o remove
+ o remove
- +o sysrq
+ o sysrq
- +o help
+ o help
- +o cad
+ o cad
- +o stop
+ o stop
- +o go
+ o go
- 1100..11.. vveerrssiioonn
+ 10.1. version
This takes no arguments. It prints the UML version.
@@ -2342,7 +2342,7 @@
- 1100..22.. hhaalltt aanndd rreebboooott
+ 10.2. halt and reboot
These take no arguments. They shut the machine down immediately, with
no syncing of disks and no clean shutdown of userspace. So, they are
@@ -2357,7 +2357,7 @@
- 1100..33.. ccoonnffiigg
+ 10.3. config
"config" adds a new device to the virtual machine. Currently the ubd
and network drivers support this. It takes one argument, which is the
@@ -2378,7 +2378,7 @@
- 1100..44.. rreemmoovvee
+ 10.4. remove
"remove" deletes a device from the system. Its argument is just the
name of the device to be removed. The device must be idle in whatever
@@ -2397,7 +2397,7 @@
- 1100..55.. ssyyssrrqq
+ 10.5. sysrq
This takes one argument, which is a single letter. It calls the
generic kernel's SysRq driver, which does whatever is called for by
@@ -2407,14 +2407,14 @@
- 1100..66.. hheellpp
+ 10.6. help
"help" returns a string listing the valid commands and what each one
does.
- 1100..77.. ccaadd
+ 10.7. cad
This invokes the Ctl-Alt-Del action on init. What exactly this ends
up doing is up to /etc/inittab. Normally, it reboots the machine.
@@ -2432,7 +2432,7 @@
- 1100..88.. ssttoopp
+ 10.8. stop
This puts the UML in a loop reading mconsole requests until a 'go'
mconsole command is received. This is very useful for making backups
@@ -2448,7 +2448,7 @@
- 1100..99.. ggoo
+ 10.9. go
This resumes a UML after being paused by a 'stop' command. Note that
when the UML has resumed, TCP connections may have timed out and if
@@ -2462,10 +2462,10 @@
- 1111.. KKeerrnneell ddeebbuuggggiinngg
+ 11. Kernel debugging
- NNoottee:: The interface that makes debugging, as described here, possible
+ Note: The interface that makes debugging, as described here, possible
is present in 2.4.0-test6 kernels and later.
@@ -2485,7 +2485,7 @@
- 1111..11.. SSttaarrttiinngg tthhee kkeerrnneell uunnddeerr ggddbb
+ 11.1. Starting the kernel under gdb
You can have the kernel running under the control of gdb from the
beginning by putting 'debug' on the command line. You will get an
@@ -2498,7 +2498,7 @@
There is a transcript of a debugging session here <debug-
session.html> , with breakpoints being set in the scheduler and in an
interrupt handler.
- 1111..22.. EExxaammiinniinngg sslleeeeppiinngg pprroocceesssseess
+ 11.2. Examining sleeping processes
Not every bug is evident in the currently running process. Sometimes,
processes hang in the kernel when they shouldn't because they've
@@ -2516,7 +2516,7 @@
Now what you do is this:
- +o detach from the current thread
+ o detach from the current thread
(UML gdb) det
@@ -2525,7 +2525,7 @@
- +o attach to the thread you are interested in
+ o attach to the thread you are interested in
(UML gdb) att <host pid>
@@ -2534,7 +2534,7 @@
- +o look at its stack and anything else of interest
+ o look at its stack and anything else of interest
(UML gdb) bt
@@ -2545,7 +2545,7 @@
Note that you can't do anything at this point that requires that a
process execute, e.g. calling a function
- +o when you're done looking at that process, reattach to the current
+ o when you're done looking at that process, reattach to the current
thread and continue it
@@ -2569,12 +2569,12 @@
- 1111..33.. RRuunnnniinngg dddddd oonn UUMMLL
+ 11.3. Running ddd on UML
ddd works on UML, but requires a special kludge. The process goes
like this:
- +o Start ddd
+ o Start ddd
host% ddd linux
@@ -2583,14 +2583,14 @@
- +o With ps, get the pid of the gdb that ddd started. You can ask the
+ o With ps, get the pid of the gdb that ddd started. You can ask the
gdb to tell you, but for some reason that confuses things and
causes a hang.
- +o run UML with 'debug=parent gdb-pid=<pid>' added to the command line
+ o run UML with 'debug=parent gdb-pid=<pid>' added to the command line
- it will just sit there after you hit return
- +o type 'att 1' to the ddd gdb and you will see something like
+ o type 'att 1' to the ddd gdb and you will see something like
0xa013dc51 in __kill ()
@@ -2602,12 +2602,12 @@
- +o At this point, type 'c', UML will boot up, and you can use ddd just
+ o At this point, type 'c', UML will boot up, and you can use ddd just
as you do on any other process.
- 1111..44.. DDeebbuuggggiinngg mmoodduulleess
+ 11.4. Debugging modules
gdb has support for debugging code which is dynamically loaded into
the process. This support is what is needed to debug kernel modules
@@ -2823,7 +2823,7 @@
- 1111..55.. AAttttaacchhiinngg ggddbb ttoo tthhee kkeerrnneell
+ 11.5. Attaching gdb to the kernel
If you don't have the kernel running under gdb, you can attach gdb to
it later by sending the tracing thread a SIGUSR1. The first line of
@@ -2857,7 +2857,7 @@
- 1111..66.. UUssiinngg aalltteerrnnaattee ddeebbuuggggeerrss
+ 11.6. Using alternate debuggers
UML has support for attaching to an already running debugger rather
than starting gdb itself. This is present in CVS as of 17 Apr 2001.
@@ -2886,7 +2886,7 @@
An example of an alternate debugger is strace. You can strace the
actual kernel as follows:
- +o Run the following in a shell
+ o Run the following in a shell
host%
@@ -2894,10 +2894,10 @@
- +o Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
+ o Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
by the previous command
- +o Hit return in the shell, and UML will start running, and strace
+ o Hit return in the shell, and UML will start running, and strace
output will start accumulating in the output file.
Note that this is different from running
@@ -2917,9 +2917,9 @@
- 1122.. KKeerrnneell ddeebbuuggggiinngg eexxaammpplleess
+ 12. Kernel debugging examples
- 1122..11.. TThhee ccaassee ooff tthhee hhuunngg ffsscckk
+ 12.1. The case of the hung fsck
When booting up the kernel, fsck failed, and dropped me into a shell
to fix things up. I ran fsck -y, which hung:
@@ -3154,9 +3154,9 @@
The interesting things here are :
- +o There are two segfaults on this stack (frames 9 and 14)
+ o There are two segfaults on this stack (frames 9 and 14)
- +o The first faulting address (frame 11) is 0x50000800
+ o The first faulting address (frame 11) is 0x50000800
(gdb) p (void *)1342179328
$16 = (void *) 0x50000800
@@ -3399,7 +3399,7 @@
on will be somewhat clearer.
- 1122..22.. EEppiissooddee 22:: TThhee ccaassee ooff tthhee hhuunngg ffsscckk
+ 12.2. Episode 2: The case of the hung fsck
After setting a trap in the SEGV handler for accesses to the signal
thread's stack, I reran the kernel.
@@ -3788,12 +3788,12 @@
- 1133.. WWhhaatt ttoo ddoo wwhheenn UUMMLL ddooeessnn''tt wwoorrkk
+ 13. What to do when UML doesn't work
- 1133..11.. SSttrraannggee ccoommppiillaattiioonn eerrrroorrss wwhheenn yyoouu bbuuiilldd ffrroomm ssoouurrccee
+ 13.1. Strange compilation errors when you build from source
As of test11, it is necessary to have "ARCH=um" in the environment or
on the make command line for all steps in building UML, including
@@ -3824,8 +3824,8 @@
- 1133..33.. AA vvaarriieettyy ooff ppaanniiccss aanndd hhaannggss wwiitthh //ttmmpp oonn aa rreeiisseerrffss ffiilleessyyss--
- tteemm
+ 13.3. A variety of panics and hangs with /tmp on a reiserfs filesys-
+ tem
I saw this on reiserfs 3.5.21 and it seems to be fixed in 3.5.27.
Panics preceded by
@@ -3842,8 +3842,8 @@
- 1133..44.. TThhee ccoommppiillee ffaaiillss wwiitthh eerrrroorrss aabboouutt ccoonnfflliiccttiinngg ttyyppeess ffoorr
- ''ooppeenn'',, ''dduupp'',, aanndd ''wwaaiittppiidd''
+ 13.4. The compile fails with errors about conflicting types for
+ 'open', 'dup', and 'waitpid'
This happens when you build in /usr/src/linux. The UML build makes
the include/asm link point to include/asm-um. /usr/include/asm points
@@ -3854,14 +3854,14 @@
- 1133..55.. UUMMLL ddooeessnn''tt wwoorrkk wwhheenn //ttmmpp iiss aann NNFFSS ffiilleessyysstteemm
+ 13.5. UML doesn't work when /tmp is an NFS filesystem
This seems to be a similar situation with the ReiserFS problem above.
Some versions of NFS seems not to handle mmap correctly, which UML
depends on. The workaround is have /tmp be a non-NFS directory.
- 1133..66.. UUMMLL hhaannggss oonn bboooott wwhheenn ccoommppiilleedd wwiitthh ggpprrooff ssuuppppoorrtt
+ 13.6. UML hangs on boot when compiled with gprof support
If you build UML with gprof support and, early in the boot, it does
this
@@ -3878,7 +3878,7 @@
- 1133..77.. ssyyssllooggdd ddiieess wwiitthh aa SSIIGGTTEERRMM oonn ssttaarrttuupp
+ 13.7. syslogd dies with a SIGTERM on startup
The exact boot error depends on the distribution that you're booting,
but Debian produces this:
@@ -3897,17 +3897,17 @@
- 1133..88.. TTUUNN//TTAAPP nneettwwoorrkkiinngg ddooeessnn''tt wwoorrkk oonn aa 22..44 hhoosstt
+ 13.8. TUN/TAP networking doesn't work on a 2.4 host
There are a couple of problems which were
<http://www.geocrawler.com/lists/3/SourceForge/597/0/> name="pointed
out"> by Tim Robinson <timro at trkr dot net>
- +o It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
+ o It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
The fix is to upgrade to something more recent and then read the
next item.
- +o If you see
+ o If you see
File descriptor in bad state
@@ -3921,8 +3921,8 @@
- 1133..99.. YYoouu ccaann nneettwwoorrkk ttoo tthhee hhoosstt bbuutt nnoott ttoo ootthheerr mmaacchhiinneess oonn tthhee
- nneett
+ 13.9. You can network to the host but not to other machines on the
+ net
If you can connect to the host, and the host can connect to UML, but
you cannot connect to any other machines, then you may need to enable
@@ -3972,7 +3972,7 @@
- 1133..1100.. II hhaavvee nnoo rroooott aanndd II wwaanntt ttoo ssccrreeaamm
+ 13.10. I have no root and I want to scream
Thanks to Birgit Wahlich for telling me about this strange one. It
turns out that there's a limit of six environment variables on the
@@ -3987,7 +3987,7 @@
- 1133..1111.. UUMMLL bbuuiilldd ccoonnfflliicctt bbeettwweeeenn ppttrraaccee..hh aanndd uuccoonntteexxtt..hh
+ 13.11. UML build conflict between ptrace.h and ucontext.h
On some older systems, /usr/include/asm/ptrace.h and
/usr/include/sys/ucontext.h define the same names. So, when they're
@@ -4007,7 +4007,7 @@
- 1133..1122.. TThhee UUMMLL BBooggooMMiippss iiss eexxaaccttllyy hhaallff tthhee hhoosstt''ss BBooggooMMiippss
+ 13.12. The UML BogoMips is exactly half the host's BogoMips
On i386 kernels, there are two ways of running the loop that is used
to calculate the BogoMips rating, using the TSC if it's there or using
@@ -4019,7 +4019,7 @@
- 1133..1133.. WWhheenn yyoouu rruunn UUMMLL,, iitt iimmmmeeddiiaatteellyy sseeggffaauullttss
+ 13.13. When you run UML, it immediately segfaults
If the host is configured with the 2G/2G address space split, that's
why. See ``UML on 2G/2G hosts'' for the details on getting UML to
@@ -4027,7 +4027,7 @@
- 1133..1144.. xxtteerrmmss aappppeeaarr,, tthheenn iimmmmeeddiiaatteellyy ddiissaappppeeaarr
+ 13.14. xterms appear, then immediately disappear
If you're running an up to date kernel with an old release of
uml_utilities, the port-helper program will not work properly, so
@@ -4039,7 +4039,7 @@
- 1133..1155.. AAnnyy ootthheerr ppaanniicc,, hhaanngg,, oorr ssttrraannggee bbeehhaavviioorr
+ 13.15. Any other panic, hang, or strange behavior
If you're seeing truly strange behavior, such as hangs or panics that
happen in random places, or you try running the debugger to see what's
@@ -4059,7 +4059,7 @@
If you want to be super-helpful, read ``Diagnosing Problems'' and
follow the instructions contained therein.
- 1144.. DDiiaaggnnoossiinngg PPrroobblleemmss
+ 14. Diagnosing Problems
If you get UML to crash, hang, or otherwise misbehave, you should
@@ -4078,7 +4078,7 @@
``Kernel debugging'' UML first.
- 1144..11.. CCaassee 11 :: NNoorrmmaall kkeerrnneell ppaanniiccss
+ 14.1. Case 1 : Normal kernel panics
The most common case is for a normal thread to panic. To debug this,
you will need to run it under the debugger (add 'debug' to the command
@@ -4128,7 +4128,7 @@
to get that information from the faulting ip.
- 1144..22.. CCaassee 22 :: TTrraacciinngg tthhrreeaadd ppaanniiccss
+ 14.2. Case 2 : Tracing thread panics
The less common and more painful case is when the tracing thread
panics. In this case, the kernel debugger will be useless because it
@@ -4161,7 +4161,7 @@
backtrace in and wait for our crack debugging team to fix the problem.
- 1144..33.. CCaassee 33 :: TTrraacciinngg tthhrreeaadd ppaanniiccss ccaauusseedd bbyy ootthheerr tthhrreeaaddss
+ 14.3. Case 3 : Tracing thread panics caused by other threads
However, there are cases where the misbehavior of another thread
caused the problem. The most common panic of this type is:
@@ -4227,7 +4227,7 @@
- 1144..44.. CCaassee 44 :: HHaannggss
+ 14.4. Case 4 : Hangs
Hangs seem to be fairly rare, but they sometimes happen. When a hang
happens, we need a backtrace from the offending process. Run the
@@ -4257,7 +4257,7 @@
- 1155.. TThhaannkkss
+ 15. Thanks
A number of people have helped this project in various ways, and this
@@ -4274,20 +4274,20 @@
bookkeeping lapses and I forget about contributions.
- 1155..11.. CCooddee aanndd DDooccuummeennttaattiioonn
+ 15.1. Code and Documentation
Rusty Russell <rusty at linuxcare.com.au> -
- +o wrote the HOWTO <http://user-mode-
+ o wrote the HOWTO <http://user-mode-
linux.sourceforge.net/UserModeLinux-HOWTO.html>
- +o prodded me into making this project official and putting it on
+ o prodded me into making this project official and putting it on
SourceForge
- +o came up with the way cool UML logo <http://user-mode-
+ o came up with the way cool UML logo <http://user-mode-
linux.sourceforge.net/uml-small.png>
- +o redid the config process
+ o redid the config process
Peter Moulder <reiter at netspace.net.au> - Fixed my config and build
@@ -4296,18 +4296,18 @@
Bill Stearns <wstearns at pobox.com> -
- +o HOWTO updates
+ o HOWTO updates
- +o lots of bug reports
+ o lots of bug reports
- +o lots of testing
+ o lots of testing
- +o dedicated a box (uml.ists.dartmouth.edu) to support UML development
+ o dedicated a box (uml.ists.dartmouth.edu) to support UML development
- +o wrote the mkrootfs script, which allows bootable filesystems of
+ o wrote the mkrootfs script, which allows bootable filesystems of
RPM-based distributions to be cranked out
- +o cranked out a large number of filesystems with said script
+ o cranked out a large number of filesystems with said script
Jim Leu <jleu at mindspring.com> - Wrote the virtual ethernet driver
@@ -4375,176 +4375,176 @@
David Coulson <http://davidcoulson.net> -
- +o Set up the usermodelinux.org <http://usermodelinux.org> site,
+ o Set up the usermodelinux.org <http://usermodelinux.org> site,
which is a great way of keeping the UML user community on top of
UML goings-on.
- +o Site documentation and updates
+ o Site documentation and updates
- +o Nifty little UML management daemon UMLd
+ o Nifty little UML management daemon UMLd
<http://uml.openconsultancy.com/umld/>
- +o Lots of testing and bug reports
+ o Lots of testing and bug reports
- 1155..22.. FFlluusshhiinngg oouutt bbuuggss
+ 15.2. Flushing out bugs
- +o Yuri Pudgorodsky
+ o Yuri Pudgorodsky
- +o Gerald Britton
+ o Gerald Britton
- +o Ian Wehrman
+ o Ian Wehrman
- +o Gord Lamb
+ o Gord Lamb
- +o Eugene Koontz
+ o Eugene Koontz
- +o John H. Hartman
+ o John H. Hartman
- +o Anders Karlsson
+ o Anders Karlsson
- +o Daniel Phillips
+ o Daniel Phillips
- +o John Fremlin
+ o John Fremlin
- +o Rainer Burgstaller
+ o Rainer Burgstaller
- +o James Stevenson
+ o James Stevenson
- +o Matt Clay
+ o Matt Clay
- +o Cliff Jefferies
+ o Cliff Jefferies
- +o Geoff Hoff
+ o Geoff Hoff
- +o Lennert Buytenhek
+ o Lennert Buytenhek
- +o Al Viro
+ o Al Viro
- +o Frank Klingenhoefer
+ o Frank Klingenhoefer
- +o Livio Baldini Soares
+ o Livio Baldini Soares
- +o Jon Burgess
+ o Jon Burgess
- +o Petru Paler
+ o Petru Paler
- +o Paul
+ o Paul
- +o Chris Reahard
+ o Chris Reahard
- +o Sverker Nilsson
+ o Sverker Nilsson
- +o Gong Su
+ o Gong Su
- +o johan verrept
+ o johan verrept
- +o Bjorn Eriksson
+ o Bjorn Eriksson
- +o Lorenzo Allegrucci
+ o Lorenzo Allegrucci
- +o Muli Ben-Yehuda
+ o Muli Ben-Yehuda
- +o David Mansfield
+ o David Mansfield
- +o Howard Goff
+ o Howard Goff
- +o Mike Anderson
+ o Mike Anderson
- +o John Byrne
+ o John Byrne
- +o Sapan J. Batia
+ o Sapan J. Batia
- +o Iris Huang
+ o Iris Huang
- +o Jan Hudec
+ o Jan Hudec
- +o Voluspa
+ o Voluspa
- 1155..33.. BBuugglleettss aanndd cclleeaann--uuppss
+ 15.3. Buglets and clean-ups
- +o Dave Zarzycki
+ o Dave Zarzycki
- +o Adam Lazur
+ o Adam Lazur
- +o Boria Feigin
+ o Boria Feigin
- +o Brian J. Murrell
+ o Brian J. Murrell
- +o JS
+ o JS
- +o Roman Zippel
+ o Roman Zippel
- +o Wil Cooley
+ o Wil Cooley
- +o Ayelet Shemesh
+ o Ayelet Shemesh
- +o Will Dyson
+ o Will Dyson
- +o Sverker Nilsson
+ o Sverker Nilsson
- +o dvorak
+ o dvorak
- +o v.naga srinivas
+ o v.naga srinivas
- +o Shlomi Fish
+ o Shlomi Fish
- +o Roger Binns
+ o Roger Binns
- +o johan verrept
+ o johan verrept
- +o MrChuoi
+ o MrChuoi
- +o Peter Cleve
+ o Peter Cleve
- +o Vincent Guffens
+ o Vincent Guffens
- +o Nathan Scott
+ o Nathan Scott
- +o Patrick Caulfield
+ o Patrick Caulfield
- +o jbearce
+ o jbearce
- +o Catalin Marinas
+ o Catalin Marinas
- +o Shane Spencer
+ o Shane Spencer
- +o Zou Min
+ o Zou Min
- +o Ryan Boder
+ o Ryan Boder
- +o Lorenzo Colitti
+ o Lorenzo Colitti
- +o Gwendal Grignou
+ o Gwendal Grignou
- +o Andre' Breiler
+ o Andre' Breiler
- +o Tsutomu Yasuda
+ o Tsutomu Yasuda
- 1155..44.. CCaassee SSttuuddiieess
+ 15.4. Case Studies
- +o Jon Wright
+ o Jon Wright
- +o William McEwan
+ o William McEwan
- +o Michael Richardson
+ o Michael Richardson
- 1155..55.. OOtthheerr ccoonnttrriibbuuttiioonnss
+ 15.5. Other contributions
Bill Carr <Bill.Carr at compaq.com> made the Red Hat mkrootfs script
diff --git a/MAINTAINERS b/MAINTAINERS
index c406f9b..a6afe34 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1716,6 +1716,7 @@
F: include/linux/can/core.h
F: include/linux/can/bcm.h
F: include/linux/can/raw.h
+F: include/linux/can/gw.h
CAN NETWORK DRIVERS
M: Wolfgang Grandegger <wg@grandegger.com>
@@ -2467,8 +2468,6 @@
W: bluesmoke.sourceforge.net
S: Maintained
F: drivers/edac/i7core_edac.c
-F: drivers/edac/edac_mce.c
-F: include/linux/edac_mce.h
EDAC-I82975X
M: Ranganathan Desikan <ravi@jetztechnologies.com>
@@ -2492,6 +2491,13 @@
S: Maintained
F: drivers/edac/r82600_edac.c
+EDAC-SBRIDGE
+M: Mauro Carvalho Chehab <mchehab@redhat.com>
+L: linux-edac@vger.kernel.org
+W: bluesmoke.sourceforge.net
+S: Maintained
+F: drivers/edac/sb_edac.c
+
EDIROL UA-101/UA-1000 DRIVER
M: Clemens Ladisch <clemens@ladisch.de>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
@@ -3013,6 +3019,13 @@
F: drivers/char/hw_random/
F: include/linux/hw_random.h
+HARDWARE SPINLOCK CORE
+M: Ohad Ben-Cohen <ohad@wizery.com>
+S: Maintained
+F: Documentation/hwspinlock.txt
+F: drivers/hwspinlock/hwspinlock_*
+F: include/linux/hwspinlock.h
+
HARMONY SOUND DRIVER
M: Kyle McMartin <kyle@mcmartin.ca>
L: linux-parisc@vger.kernel.org
@@ -3205,8 +3218,7 @@
M: Tony Luck <tony.luck@intel.com>
M: Fenghua Yu <fenghua.yu@intel.com>
L: linux-ia64@vger.kernel.org
-W: http://www.ia64-linux.org/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux.git
S: Maintained
F: arch/ia64/
@@ -4465,11 +4477,9 @@
F: drivers/net/ethernet/neterion/
NETFILTER/IPTABLES/IPCHAINS
-P: Rusty Russell
-P: Marc Boucher
-P: James Morris
P: Harald Welte
P: Jozsef Kadlecsik
+M: Pablo Neira Ayuso <pablo@netfilter.org>
M: Patrick McHardy <kaber@trash.net>
L: netfilter-devel@vger.kernel.org
L: netfilter@vger.kernel.org
@@ -4710,6 +4720,13 @@
F: drivers/video/omap2/
F: Documentation/arm/OMAP/DSS
+OMAP HARDWARE SPINLOCK SUPPORT
+M: Ohad Ben-Cohen <ohad@wizery.com>
+L: linux-omap@vger.kernel.org
+S: Maintained
+F: drivers/hwspinlock/omap_hwspinlock.c
+F: arch/arm/mach-omap2/hwspinlock.c
+
OMAP MMC SUPPORT
M: Jarkko Lavinen <jarkko.lavinen@nokia.com>
L: linux-omap@vger.kernel.org
@@ -6683,7 +6700,6 @@
UDF FILESYSTEM
M: Jan Kara <jack@suse.cz>
-W: http://linux-udf.sourceforge.net
S: Maintained
F: Documentation/filesystems/udf.txt
F: fs/udf/
diff --git a/arch/arm/mach-imx/mach-mx27_3ds.c b/arch/arm/mach-imx/mach-mx27_3ds.c
index cfa8417..ba232d7 100644
--- a/arch/arm/mach-imx/mach-mx27_3ds.c
+++ b/arch/arm/mach-imx/mach-mx27_3ds.c
@@ -293,8 +293,7 @@
.num_regulators = ARRAY_SIZE(mx27_3ds_regulators),
},
- .flags = MC13783_USE_REGULATOR | MC13783_USE_TOUCHSCREEN |
- MC13783_USE_RTC,
+ .flags = MC13XXX_USE_TOUCHSCREEN | MC13XXX_USE_RTC,
};
/* SPI */
diff --git a/arch/arm/mach-imx/mach-mx31_3ds.c b/arch/arm/mach-imx/mach-mx31_3ds.c
index 60f1fda..b8c54b8 100644
--- a/arch/arm/mach-imx/mach-mx31_3ds.c
+++ b/arch/arm/mach-imx/mach-mx31_3ds.c
@@ -492,7 +492,7 @@
.regulators = mx31_3ds_regulators,
.num_regulators = ARRAY_SIZE(mx31_3ds_regulators),
},
- .flags = MC13783_USE_REGULATOR | MC13783_USE_TOUCHSCREEN,
+ .flags = MC13XXX_USE_TOUCHSCREEN,
};
/* SPI */
diff --git a/arch/arm/mach-imx/mach-mx31lite.c b/arch/arm/mach-imx/mach-mx31lite.c
index c97c26d..05f1c71 100644
--- a/arch/arm/mach-imx/mach-mx31lite.c
+++ b/arch/arm/mach-imx/mach-mx31lite.c
@@ -112,8 +112,7 @@
};
static struct mc13xxx_platform_data mc13783_pdata __initdata = {
- .flags = MC13XXX_USE_RTC |
- MC13XXX_USE_REGULATOR,
+ .flags = MC13XXX_USE_RTC,
};
static struct spi_board_info mc13783_spi_dev __initdata = {
diff --git a/arch/arm/mach-imx/mach-mx31moboard.c b/arch/arm/mach-imx/mach-mx31moboard.c
index fff7791..07034f4 100644
--- a/arch/arm/mach-imx/mach-mx31moboard.c
+++ b/arch/arm/mach-imx/mach-mx31moboard.c
@@ -31,6 +31,7 @@
#include <linux/clk.h>
#include <linux/io.h>
#include <linux/err.h>
+#include <linux/input.h>
#include <linux/usb/otg.h>
#include <linux/usb/ulpi.h>
@@ -225,7 +226,7 @@
},
};
-static struct mc13783_led_platform_data moboard_led[] = {
+static struct mc13xxx_led_platform_data moboard_led[] = {
{
.id = MC13783_LED_R1,
.name = "coreboard-led-4:red",
@@ -258,7 +259,7 @@
},
};
-static struct mc13783_leds_platform_data moboard_leds = {
+static struct mc13xxx_leds_platform_data moboard_leds = {
.num_leds = ARRAY_SIZE(moboard_led),
.led = moboard_led,
.flags = MC13783_LED_SLEWLIMTC,
@@ -267,14 +268,20 @@
.tc2_period = MC13783_LED_PERIOD_10MS,
};
+static struct mc13xxx_buttons_platform_data moboard_buttons = {
+ .b1on_flags = MC13783_BUTTON_DBNC_750MS | MC13783_BUTTON_ENABLE |
+ MC13783_BUTTON_POL_INVERT,
+ .b1on_key = KEY_POWER,
+};
+
static struct mc13xxx_platform_data moboard_pmic = {
.regulators = {
.regulators = moboard_regulators,
.num_regulators = ARRAY_SIZE(moboard_regulators),
},
.leds = &moboard_leds,
- .flags = MC13XXX_USE_REGULATOR | MC13XXX_USE_RTC |
- MC13XXX_USE_ADC | MC13XXX_USE_LED,
+ .buttons = &moboard_buttons,
+ .flags = MC13XXX_USE_RTC | MC13XXX_USE_ADC,
};
static struct spi_board_info moboard_spi_board_info[] __initdata = {
diff --git a/arch/arm/mach-imx/mach-pcm038.c b/arch/arm/mach-imx/mach-pcm038.c
index 100bc73..a17e9c7 100644
--- a/arch/arm/mach-imx/mach-pcm038.c
+++ b/arch/arm/mach-imx/mach-pcm038.c
@@ -268,8 +268,7 @@
.regulators = pcm038_regulators,
.num_regulators = ARRAY_SIZE(pcm038_regulators),
},
- .flags = MC13783_USE_ADC | MC13783_USE_REGULATOR |
- MC13783_USE_TOUCHSCREEN,
+ .flags = MC13XXX_USE_ADC | MC13XXX_USE_TOUCHSCREEN,
};
static struct spi_board_info pcm038_spi_board_info[] __initdata = {
diff --git a/arch/arm/mach-mx5/mx51_efika.c b/arch/arm/mach-mx5/mx51_efika.c
index b004e17..ec6ca91 100644
--- a/arch/arm/mach-mx5/mx51_efika.c
+++ b/arch/arm/mach-mx5/mx51_efika.c
@@ -565,7 +565,7 @@
};
static struct mc13xxx_platform_data mx51_efika_mc13892_data = {
- .flags = MC13XXX_USE_RTC | MC13XXX_USE_REGULATOR,
+ .flags = MC13XXX_USE_RTC,
.regulators = {
.num_regulators = ARRAY_SIZE(mx51_efika_regulators),
.regulators = mx51_efika_regulators,
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 497e9dc..5034147 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -14,7 +14,6 @@
select SERIAL_OMAP_CONSOLE
select I2C
select I2C_OMAP
- select MFD_SUPPORT
select MENELAUS if ARCH_OMAP2
select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4
select TWL4030_POWER if ARCH_OMAP3 || ARCH_OMAP4
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index 70261bc..4a71cb7 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -378,7 +378,8 @@
static int __init omap3_beagle_i2c_init(void)
{
omap3_pmic_get_config(&beagle_twldata,
- TWL_COMMON_PDATA_USB | TWL_COMMON_PDATA_AUDIO,
+ TWL_COMMON_PDATA_USB | TWL_COMMON_PDATA_MADC |
+ TWL_COMMON_PDATA_AUDIO,
TWL_COMMON_REGULATOR_VDAC | TWL_COMMON_REGULATOR_VPLL2);
beagle_twldata.vpll2->constraints.name = "VDVI";
@@ -444,9 +445,15 @@
},
};
+static struct platform_device madc_hwmon = {
+ .name = "twl4030_madc_hwmon",
+ .id = -1,
+};
+
static struct platform_device *omap3_beagle_devices[] __initdata = {
&leds_gpio,
&keys_gpio,
+ &madc_hwmon,
};
static const struct usbhs_omap_board_data usbhs_bdata __initconst = {
diff --git a/arch/arm/mach-omap2/hwspinlock.c b/arch/arm/mach-omap2/hwspinlock.c
index 36e2109..454dfce 100644
--- a/arch/arm/mach-omap2/hwspinlock.c
+++ b/arch/arm/mach-omap2/hwspinlock.c
@@ -19,10 +19,15 @@
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/err.h>
+#include <linux/hwspinlock.h>
#include <plat/omap_hwmod.h>
#include <plat/omap_device.h>
+static struct hwspinlock_pdata omap_hwspinlock_pdata __initdata = {
+ .base_id = 0,
+};
+
int __init hwspinlocks_init(void)
{
int retval = 0;
@@ -40,7 +45,9 @@
if (oh == NULL)
return -EINVAL;
- pdev = omap_device_build(dev_name, 0, oh, NULL, 0, NULL, 0, false);
+ pdev = omap_device_build(dev_name, 0, oh, &omap_hwspinlock_pdata,
+ sizeof(struct hwspinlock_pdata),
+ NULL, 0, false);
if (IS_ERR(pdev)) {
pr_err("Can't build omap_device for %s:%s\n", dev_name,
oh_name);
diff --git a/arch/arm/mach-u300/i2c.c b/arch/arm/mach-u300/i2c.c
index f0394ba..5140dee 100644
--- a/arch/arm/mach-u300/i2c.c
+++ b/arch/arm/mach-u300/i2c.c
@@ -256,57 +256,8 @@
};
#endif
-#ifdef CONFIG_AB3550_CORE
-static struct abx500_init_settings ab3550_init_settings[] = {
- {
- .bank = 0,
- .reg = AB3550_IMR1,
- .setting = 0xff
- },
- {
- .bank = 0,
- .reg = AB3550_IMR2,
- .setting = 0xff
- },
- {
- .bank = 0,
- .reg = AB3550_IMR3,
- .setting = 0xff
- },
- {
- .bank = 0,
- .reg = AB3550_IMR4,
- .setting = 0xff
- },
- {
- .bank = 0,
- .reg = AB3550_IMR5,
- /* The two most significant bits are not used */
- .setting = 0x3f
- },
-};
-
-static struct ab3550_platform_data ab3550_plf_data = {
- .irq = {
- .base = IRQ_AB3550_BASE,
- .count = (IRQ_AB3550_END - IRQ_AB3550_BASE + 1),
- },
- .dev_data = {
- },
- .init_settings = ab3550_init_settings,
- .init_settings_sz = ARRAY_SIZE(ab3550_init_settings),
-};
-#endif
-
static struct i2c_board_info __initdata bus0_i2c_board_info[] = {
-#if defined(CONFIG_AB3550_CORE)
- {
- .type = "ab3550",
- .addr = 0x4A,
- .irq = IRQ_U300_IRQ0_EXT,
- .platform_data = &ab3550_plf_data,
- },
-#elif defined(CONFIG_AB3100_CORE)
+#ifdef CONFIG_AB3100_CORE
{
.type = "ab3100",
.addr = 0x48,
diff --git a/arch/arm/mach-u300/include/mach/irqs.h b/arch/arm/mach-u300/include/mach/irqs.h
index d270fea..db3fbfa 100644
--- a/arch/arm/mach-u300/include/mach/irqs.h
+++ b/arch/arm/mach-u300/include/mach/irqs.h
@@ -117,14 +117,6 @@
#define IRQ_U300_GPIO_END (U300_VIC_IRQS_END)
#endif
-/* Optional AB3550 mixsig chip */
-#ifdef CONFIG_AB3550_CORE
-#define IRQ_AB3550_BASE (IRQ_U300_GPIO_END)
-#define IRQ_AB3550_END (IRQ_AB3550_BASE + 38)
-#else
-#define IRQ_AB3550_END (IRQ_U300_GPIO_END)
-#endif
-
-#define NR_IRQS (IRQ_AB3550_END)
+#define NR_IRQS (IRQ_U300_GPIO_END)
#endif
diff --git a/arch/arm/mach-ux500/board-u5500.c b/arch/arm/mach-ux500/board-u5500.c
index e014aa7..82025ba 100644
--- a/arch/arm/mach-ux500/board-u5500.c
+++ b/arch/arm/mach-ux500/board-u5500.c
@@ -10,6 +10,7 @@
#include <linux/amba/bus.h>
#include <linux/irq.h>
#include <linux/i2c.h>
+#include <linux/mfd/ab5500/ab5500.h>
#include <asm/mach/arch.h>
#include <asm/mach-types.h>
@@ -87,7 +88,6 @@
.brt_val = 0x7F, /* Max brightness */
};
-
static struct i2c_board_info __initdata u5500_i2c2_devices[] = {
{
/* Backlight */
@@ -101,6 +101,30 @@
db5500_add_i2c2(&u5500_i2c2_data);
i2c_register_board_info(2, ARRAY_AND_SIZE(u5500_i2c2_devices));
}
+
+static struct ab5500_platform_data ab5500_plf_data = {
+ .irq = {
+ .base = 0,
+ .count = 0,
+ },
+ .init_settings = NULL,
+ .init_settings_sz = 0,
+ .pm_power_off = false,
+};
+
+static struct platform_device ab5500_device = {
+ .name = "ab5500-core",
+ .id = 0,
+ .dev = {
+ .platform_data = &ab5500_plf_data,
+ },
+ .num_resources = 0,
+};
+
+static struct platform_device *u5500_platform_devices[] __initdata = {
+ &ab5500_device,
+};
+
static void __init u5500_uart_init(void)
{
db5500_add_uart0(NULL);
@@ -115,6 +139,9 @@
u5500_i2c_init();
u5500_sdi_init();
u5500_uart_init();
+
+ platform_add_devices(u5500_platform_devices,
+ ARRAY_SIZE(u5500_platform_devices));
}
MACHINE_START(U5500, "ST-Ericsson U5500 Platform")
diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c
index 1405d0e..f418574 100644
--- a/arch/arm/mach-ux500/cpu.c
+++ b/arch/arm/mach-ux500/cpu.c
@@ -47,6 +47,6 @@
if (cpu_is_u5500())
db5500_prcmu_early_init();
if (cpu_is_u8500())
- prcmu_early_init();
+ db8500_prcmu_early_init();
clk_init();
}
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 3ff7785..27489b6 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -92,7 +92,7 @@
def_bool y
config GENERIC_GPIO
- def_bool y
+ bool
config DMI
bool
diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index 43ab1cd..954d81e 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -87,6 +87,7 @@
CONFIG_NET_TULIP=y
CONFIG_TULIP=m
CONFIG_NET_PCI=y
+CONFIG_NET_VENDOR_INTEL=y
CONFIG_E100=m
CONFIG_E1000=y
CONFIG_IGB=y
diff --git a/arch/ia64/configs/gensparse_defconfig b/arch/ia64/configs/gensparse_defconfig
index b11fa88..91c41ec 100644
--- a/arch/ia64/configs/gensparse_defconfig
+++ b/arch/ia64/configs/gensparse_defconfig
@@ -75,6 +75,7 @@
CONFIG_NET_TULIP=y
CONFIG_TULIP=m
CONFIG_NET_PCI=y
+CONFIG_NET_VENDOR_INTEL=y
CONFIG_E100=m
CONFIG_E1000=y
CONFIG_TIGON3=y
diff --git a/arch/ia64/configs/tiger_defconfig b/arch/ia64/configs/tiger_defconfig
index 137a453..a5a9e02 100644
--- a/arch/ia64/configs/tiger_defconfig
+++ b/arch/ia64/configs/tiger_defconfig
@@ -77,6 +77,7 @@
CONFIG_NET_TULIP=y
CONFIG_TULIP=m
CONFIG_NET_PCI=y
+CONFIG_NET_VENDOR_INTEL=y
CONFIG_E100=m
CONFIG_E1000=y
CONFIG_TIGON3=y
diff --git a/arch/ia64/configs/xen_domu_defconfig b/arch/ia64/configs/xen_domu_defconfig
index 2bf76e4..37b9b42 100644
--- a/arch/ia64/configs/xen_domu_defconfig
+++ b/arch/ia64/configs/xen_domu_defconfig
@@ -80,6 +80,7 @@
CONFIG_NET_TULIP=y
CONFIG_TULIP=m
CONFIG_NET_PCI=y
+CONFIG_NET_VENDOR_INTEL=y
CONFIG_E100=m
CONFIG_E1000=y
CONFIG_TIGON3=y
diff --git a/arch/ia64/configs/zx1_defconfig b/arch/ia64/configs/zx1_defconfig
index 1d42827..fc7aba0 100644
--- a/arch/ia64/configs/zx1_defconfig
+++ b/arch/ia64/configs/zx1_defconfig
@@ -57,6 +57,7 @@
CONFIG_TULIP_NAPI=y
CONFIG_TULIP_NAPI_HW_MITIGATION=y
CONFIG_NET_PCI=y
+CONFIG_NET_VENDOR_INTEL=y
CONFIG_E100=y
CONFIG_E1000=y
CONFIG_TIGON3=y
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index 30862c0..2de41d4 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -615,11 +615,15 @@
}
}
- if (cpu == SN_HWPERF_ARG_ANY_CPU || cpu == get_cpu()) {
- /* don't care, or already on correct cpu */
+ if (cpu == SN_HWPERF_ARG_ANY_CPU) {
+ /* don't care which cpu */
sn_hwperf_call_sal(op_info);
- }
- else {
+ } else if (cpu == get_cpu()) {
+ /* already on correct cpu */
+ sn_hwperf_call_sal(op_info);
+ put_cpu();
+ } else {
+ put_cpu();
if (use_ipi) {
/* use an interprocessor interrupt to call SAL */
smp_call_function_single(cpu, sn_hwperf_call_sal,
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 4cbc6d8..62b9677 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -47,6 +47,8 @@
select GENERIC_GPIO
select ARCH_WANT_OPTIONAL_GPIOLIB
select SYS_SUPPORTS_ZBOOT
+ select USB_ARCH_HAS_OHCI
+ select USB_ARCH_HAS_EHCI
config AR7
bool "Texas Instruments AR7"
@@ -206,6 +208,7 @@
select SYS_HAS_EARLY_PRINTK
select HAVE_PWM
select HAVE_CLK
+ select GENERIC_IRQ_CHIP
config LANTIQ
bool "Lantiq based platforms"
@@ -2092,7 +2095,7 @@
config HW_PERF_EVENTS
bool "Enable hardware performance counter support for perf events"
- depends on PERF_EVENTS && !MIPS_MT_SMTC && OPROFILE=n && CPU_MIPS32
+ depends on PERF_EVENTS && !MIPS_MT_SMTC && OPROFILE=n && (CPU_MIPS32 || CPU_MIPS64 || CPU_R10000 || CPU_SB1 || CPU_CAVIUM_OCTEON)
default y
help
Enable hardware performance counter support for perf events. If
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 53e3514..9b4cb00 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -226,7 +226,7 @@
ifdef CONFIG_MIPS
CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -xc /dev/null | \
egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \
- sed -e 's/^\#define /-D/' -e "s/ /='/" -e "s/$$/'/")
+ sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/")
ifdef CONFIG_64BIT
CHECKFLAGS += -m64
endif
@@ -295,7 +295,9 @@
install:
$(Q)install -D -m 755 vmlinux $(INSTALL_PATH)/vmlinux-$(KERNELRELEASE)
+ifdef CONFIG_SYS_SUPPORTS_ZBOOT
$(Q)install -D -m 755 vmlinuz $(INSTALL_PATH)/vmlinuz-$(KERNELRELEASE)
+endif
$(Q)install -D -m 644 .config $(INSTALL_PATH)/config-$(KERNELRELEASE)
$(Q)install -D -m 644 System.map $(INSTALL_PATH)/System.map-$(KERNELRELEASE)
diff --git a/arch/mips/alchemy/Kconfig b/arch/mips/alchemy/Kconfig
index 2ccfd4a..2a68be6 100644
--- a/arch/mips/alchemy/Kconfig
+++ b/arch/mips/alchemy/Kconfig
@@ -18,20 +18,20 @@
bool "4G Systems MTX-1 board"
select DMA_NONCOHERENT
select HW_HAS_PCI
- select SOC_AU1500
+ select ALCHEMY_GPIOINT_AU1000
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_HAS_EARLY_PRINTK
config MIPS_BOSPORUS
bool "Alchemy Bosporus board"
- select SOC_AU1500
+ select ALCHEMY_GPIOINT_AU1000
select DMA_NONCOHERENT
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_HAS_EARLY_PRINTK
config MIPS_DB1000
bool "Alchemy DB1000 board"
- select SOC_AU1000
+ select ALCHEMY_GPIOINT_AU1000
select DMA_NONCOHERENT
select HW_HAS_PCI
select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -39,14 +39,14 @@
config MIPS_DB1100
bool "Alchemy DB1100 board"
- select SOC_AU1100
+ select ALCHEMY_GPIOINT_AU1000
select DMA_NONCOHERENT
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_HAS_EARLY_PRINTK
config MIPS_DB1200
bool "Alchemy DB1200 board"
- select SOC_AU1200
+ select ALCHEMY_GPIOINT_AU1000
select DMA_COHERENT
select MIPS_DISABLE_OBSOLETE_IDE
select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -54,7 +54,7 @@
config MIPS_DB1500
bool "Alchemy DB1500 board"
- select SOC_AU1500
+ select ALCHEMY_GPIOINT_AU1000
select DMA_NONCOHERENT
select HW_HAS_PCI
select MIPS_DISABLE_OBSOLETE_IDE
@@ -64,7 +64,7 @@
config MIPS_DB1550
bool "Alchemy DB1550 board"
- select SOC_AU1550
+ select ALCHEMY_GPIOINT_AU1000
select HW_HAS_PCI
select DMA_NONCOHERENT
select MIPS_DISABLE_OBSOLETE_IDE
@@ -74,13 +74,13 @@
config MIPS_MIRAGE
bool "Alchemy Mirage board"
select DMA_NONCOHERENT
- select SOC_AU1500
+ select ALCHEMY_GPIOINT_AU1000
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_HAS_EARLY_PRINTK
config MIPS_PB1000
bool "Alchemy PB1000 board"
- select SOC_AU1000
+ select ALCHEMY_GPIOINT_AU1000
select DMA_NONCOHERENT
select HW_HAS_PCI
select SWAP_IO_SPACE
@@ -89,7 +89,7 @@
config MIPS_PB1100
bool "Alchemy PB1100 board"
- select SOC_AU1100
+ select ALCHEMY_GPIOINT_AU1000
select DMA_NONCOHERENT
select HW_HAS_PCI
select SWAP_IO_SPACE
@@ -98,7 +98,7 @@
config MIPS_PB1200
bool "Alchemy PB1200 board"
- select SOC_AU1200
+ select ALCHEMY_GPIOINT_AU1000
select DMA_NONCOHERENT
select MIPS_DISABLE_OBSOLETE_IDE
select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -106,7 +106,7 @@
config MIPS_PB1500
bool "Alchemy PB1500 board"
- select SOC_AU1500
+ select ALCHEMY_GPIOINT_AU1000
select DMA_NONCOHERENT
select HW_HAS_PCI
select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -114,7 +114,7 @@
config MIPS_PB1550
bool "Alchemy PB1550 board"
- select SOC_AU1550
+ select ALCHEMY_GPIOINT_AU1000
select DMA_NONCOHERENT
select HW_HAS_PCI
select MIPS_DISABLE_OBSOLETE_IDE
@@ -124,13 +124,13 @@
config MIPS_XXS1500
bool "MyCable XXS1500 board"
select DMA_NONCOHERENT
- select SOC_AU1500
+ select ALCHEMY_GPIOINT_AU1000
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_HAS_EARLY_PRINTK
config MIPS_GPR
bool "Trapeze ITS GPR board"
- select SOC_AU1550
+ select ALCHEMY_GPIOINT_AU1000
select HW_HAS_PCI
select DMA_NONCOHERENT
select MIPS_DISABLE_OBSOLETE_IDE
@@ -138,23 +138,3 @@
select SYS_HAS_EARLY_PRINTK
endchoice
-
-config SOC_AU1000
- bool
- select ALCHEMY_GPIOINT_AU1000
-
-config SOC_AU1100
- bool
- select ALCHEMY_GPIOINT_AU1000
-
-config SOC_AU1500
- bool
- select ALCHEMY_GPIOINT_AU1000
-
-config SOC_AU1550
- bool
- select ALCHEMY_GPIOINT_AU1000
-
-config SOC_AU1200
- bool
- select ALCHEMY_GPIOINT_AU1000
diff --git a/arch/mips/alchemy/common/Makefile b/arch/mips/alchemy/common/Makefile
index 27811fe..811ece7 100644
--- a/arch/mips/alchemy/common/Makefile
+++ b/arch/mips/alchemy/common/Makefile
@@ -12,9 +12,5 @@
# optional gpiolib support
ifeq ($(CONFIG_ALCHEMY_GPIO_INDIRECT),)
- ifeq ($(CONFIG_GPIOLIB),y)
- obj-$(CONFIG_ALCHEMY_GPIOINT_AU1000) += gpiolib-au1000.o
- endif
+ obj-$(CONFIG_GPIOLIB) += gpiolib.o
endif
-
-obj-$(CONFIG_PCI) += pci.o
diff --git a/arch/mips/alchemy/common/dbdma.c b/arch/mips/alchemy/common/dbdma.c
index 3a5abb5..0e63ee4 100644
--- a/arch/mips/alchemy/common/dbdma.c
+++ b/arch/mips/alchemy/common/dbdma.c
@@ -40,8 +40,6 @@
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1xxx_dbdma.h>
-#if defined(CONFIG_SOC_AU1550) || defined(CONFIG_SOC_AU1200)
-
/*
* The Descriptor Based DMA supports up to 16 channels.
*
@@ -62,120 +60,96 @@
(dbdma_global_t *)KSEG1ADDR(AU1550_DBDMA_CONF_PHYS_ADDR);
static int dbdma_initialized;
-static dbdev_tab_t dbdev_tab[] = {
-#ifdef CONFIG_SOC_AU1550
+static dbdev_tab_t *dbdev_tab;
+
+static dbdev_tab_t au1550_dbdev_tab[] __initdata = {
/* UARTS */
- { DSCR_CMD0_UART0_TX, DEV_FLAGS_OUT, 0, 8, 0x11100004, 0, 0 },
- { DSCR_CMD0_UART0_RX, DEV_FLAGS_IN, 0, 8, 0x11100000, 0, 0 },
- { DSCR_CMD0_UART3_TX, DEV_FLAGS_OUT, 0, 8, 0x11400004, 0, 0 },
- { DSCR_CMD0_UART3_RX, DEV_FLAGS_IN, 0, 8, 0x11400000, 0, 0 },
+ { AU1550_DSCR_CMD0_UART0_TX, DEV_FLAGS_OUT, 0, 8, 0x11100004, 0, 0 },
+ { AU1550_DSCR_CMD0_UART0_RX, DEV_FLAGS_IN, 0, 8, 0x11100000, 0, 0 },
+ { AU1550_DSCR_CMD0_UART3_TX, DEV_FLAGS_OUT, 0, 8, 0x11400004, 0, 0 },
+ { AU1550_DSCR_CMD0_UART3_RX, DEV_FLAGS_IN, 0, 8, 0x11400000, 0, 0 },
/* EXT DMA */
- { DSCR_CMD0_DMA_REQ0, 0, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_DMA_REQ1, 0, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_DMA_REQ2, 0, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_DMA_REQ3, 0, 0, 0, 0x00000000, 0, 0 },
+ { AU1550_DSCR_CMD0_DMA_REQ0, 0, 0, 0, 0x00000000, 0, 0 },
+ { AU1550_DSCR_CMD0_DMA_REQ1, 0, 0, 0, 0x00000000, 0, 0 },
+ { AU1550_DSCR_CMD0_DMA_REQ2, 0, 0, 0, 0x00000000, 0, 0 },
+ { AU1550_DSCR_CMD0_DMA_REQ3, 0, 0, 0, 0x00000000, 0, 0 },
/* USB DEV */
- { DSCR_CMD0_USBDEV_RX0, DEV_FLAGS_IN, 4, 8, 0x10200000, 0, 0 },
- { DSCR_CMD0_USBDEV_TX0, DEV_FLAGS_OUT, 4, 8, 0x10200004, 0, 0 },
- { DSCR_CMD0_USBDEV_TX1, DEV_FLAGS_OUT, 4, 8, 0x10200008, 0, 0 },
- { DSCR_CMD0_USBDEV_TX2, DEV_FLAGS_OUT, 4, 8, 0x1020000c, 0, 0 },
- { DSCR_CMD0_USBDEV_RX3, DEV_FLAGS_IN, 4, 8, 0x10200010, 0, 0 },
- { DSCR_CMD0_USBDEV_RX4, DEV_FLAGS_IN, 4, 8, 0x10200014, 0, 0 },
+ { AU1550_DSCR_CMD0_USBDEV_RX0, DEV_FLAGS_IN, 4, 8, 0x10200000, 0, 0 },
+ { AU1550_DSCR_CMD0_USBDEV_TX0, DEV_FLAGS_OUT, 4, 8, 0x10200004, 0, 0 },
+ { AU1550_DSCR_CMD0_USBDEV_TX1, DEV_FLAGS_OUT, 4, 8, 0x10200008, 0, 0 },
+ { AU1550_DSCR_CMD0_USBDEV_TX2, DEV_FLAGS_OUT, 4, 8, 0x1020000c, 0, 0 },
+ { AU1550_DSCR_CMD0_USBDEV_RX3, DEV_FLAGS_IN, 4, 8, 0x10200010, 0, 0 },
+ { AU1550_DSCR_CMD0_USBDEV_RX4, DEV_FLAGS_IN, 4, 8, 0x10200014, 0, 0 },
- /* PSC 0 */
- { DSCR_CMD0_PSC0_TX, DEV_FLAGS_OUT, 0, 0, 0x11a0001c, 0, 0 },
- { DSCR_CMD0_PSC0_RX, DEV_FLAGS_IN, 0, 0, 0x11a0001c, 0, 0 },
+ /* PSCs */
+ { AU1550_DSCR_CMD0_PSC0_TX, DEV_FLAGS_OUT, 0, 0, 0x11a0001c, 0, 0 },
+ { AU1550_DSCR_CMD0_PSC0_RX, DEV_FLAGS_IN, 0, 0, 0x11a0001c, 0, 0 },
+ { AU1550_DSCR_CMD0_PSC1_TX, DEV_FLAGS_OUT, 0, 0, 0x11b0001c, 0, 0 },
+ { AU1550_DSCR_CMD0_PSC1_RX, DEV_FLAGS_IN, 0, 0, 0x11b0001c, 0, 0 },
+ { AU1550_DSCR_CMD0_PSC2_TX, DEV_FLAGS_OUT, 0, 0, 0x10a0001c, 0, 0 },
+ { AU1550_DSCR_CMD0_PSC2_RX, DEV_FLAGS_IN, 0, 0, 0x10a0001c, 0, 0 },
+ { AU1550_DSCR_CMD0_PSC3_TX, DEV_FLAGS_OUT, 0, 0, 0x10b0001c, 0, 0 },
+ { AU1550_DSCR_CMD0_PSC3_RX, DEV_FLAGS_IN, 0, 0, 0x10b0001c, 0, 0 },
- /* PSC 1 */
- { DSCR_CMD0_PSC1_TX, DEV_FLAGS_OUT, 0, 0, 0x11b0001c, 0, 0 },
- { DSCR_CMD0_PSC1_RX, DEV_FLAGS_IN, 0, 0, 0x11b0001c, 0, 0 },
-
- /* PSC 2 */
- { DSCR_CMD0_PSC2_TX, DEV_FLAGS_OUT, 0, 0, 0x10a0001c, 0, 0 },
- { DSCR_CMD0_PSC2_RX, DEV_FLAGS_IN, 0, 0, 0x10a0001c, 0, 0 },
-
- /* PSC 3 */
- { DSCR_CMD0_PSC3_TX, DEV_FLAGS_OUT, 0, 0, 0x10b0001c, 0, 0 },
- { DSCR_CMD0_PSC3_RX, DEV_FLAGS_IN, 0, 0, 0x10b0001c, 0, 0 },
-
- { DSCR_CMD0_PCI_WRITE, 0, 0, 0, 0x00000000, 0, 0 }, /* PCI */
- { DSCR_CMD0_NAND_FLASH, 0, 0, 0, 0x00000000, 0, 0 }, /* NAND */
+ { AU1550_DSCR_CMD0_PCI_WRITE, 0, 0, 0, 0x00000000, 0, 0 }, /* PCI */
+ { AU1550_DSCR_CMD0_NAND_FLASH, 0, 0, 0, 0x00000000, 0, 0 }, /* NAND */
/* MAC 0 */
- { DSCR_CMD0_MAC0_RX, DEV_FLAGS_IN, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_MAC0_TX, DEV_FLAGS_OUT, 0, 0, 0x00000000, 0, 0 },
+ { AU1550_DSCR_CMD0_MAC0_RX, DEV_FLAGS_IN, 0, 0, 0x00000000, 0, 0 },
+ { AU1550_DSCR_CMD0_MAC0_TX, DEV_FLAGS_OUT, 0, 0, 0x00000000, 0, 0 },
/* MAC 1 */
- { DSCR_CMD0_MAC1_RX, DEV_FLAGS_IN, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_MAC1_TX, DEV_FLAGS_OUT, 0, 0, 0x00000000, 0, 0 },
-
-#endif /* CONFIG_SOC_AU1550 */
-
-#ifdef CONFIG_SOC_AU1200
- { DSCR_CMD0_UART0_TX, DEV_FLAGS_OUT, 0, 8, 0x11100004, 0, 0 },
- { DSCR_CMD0_UART0_RX, DEV_FLAGS_IN, 0, 8, 0x11100000, 0, 0 },
- { DSCR_CMD0_UART1_TX, DEV_FLAGS_OUT, 0, 8, 0x11200004, 0, 0 },
- { DSCR_CMD0_UART1_RX, DEV_FLAGS_IN, 0, 8, 0x11200000, 0, 0 },
-
- { DSCR_CMD0_DMA_REQ0, 0, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_DMA_REQ1, 0, 0, 0, 0x00000000, 0, 0 },
-
- { DSCR_CMD0_MAE_BE, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_MAE_FE, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_MAE_BOTH, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_LCD, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
-
- { DSCR_CMD0_SDMS_TX0, DEV_FLAGS_OUT, 4, 8, 0x10600000, 0, 0 },
- { DSCR_CMD0_SDMS_RX0, DEV_FLAGS_IN, 4, 8, 0x10600004, 0, 0 },
- { DSCR_CMD0_SDMS_TX1, DEV_FLAGS_OUT, 4, 8, 0x10680000, 0, 0 },
- { DSCR_CMD0_SDMS_RX1, DEV_FLAGS_IN, 4, 8, 0x10680004, 0, 0 },
-
- { DSCR_CMD0_AES_RX, DEV_FLAGS_IN , 4, 32, 0x10300008, 0, 0 },
- { DSCR_CMD0_AES_TX, DEV_FLAGS_OUT, 4, 32, 0x10300004, 0, 0 },
-
- { DSCR_CMD0_PSC0_TX, DEV_FLAGS_OUT, 0, 16, 0x11a0001c, 0, 0 },
- { DSCR_CMD0_PSC0_RX, DEV_FLAGS_IN, 0, 16, 0x11a0001c, 0, 0 },
- { DSCR_CMD0_PSC0_SYNC, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
-
- { DSCR_CMD0_PSC1_TX, DEV_FLAGS_OUT, 0, 16, 0x11b0001c, 0, 0 },
- { DSCR_CMD0_PSC1_RX, DEV_FLAGS_IN, 0, 16, 0x11b0001c, 0, 0 },
- { DSCR_CMD0_PSC1_SYNC, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
-
- { DSCR_CMD0_CIM_RXA, DEV_FLAGS_IN, 0, 32, 0x14004020, 0, 0 },
- { DSCR_CMD0_CIM_RXB, DEV_FLAGS_IN, 0, 32, 0x14004040, 0, 0 },
- { DSCR_CMD0_CIM_RXC, DEV_FLAGS_IN, 0, 32, 0x14004060, 0, 0 },
- { DSCR_CMD0_CIM_SYNC, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
-
- { DSCR_CMD0_NAND_FLASH, DEV_FLAGS_IN, 0, 0, 0x00000000, 0, 0 },
-
-#endif /* CONFIG_SOC_AU1200 */
+ { AU1550_DSCR_CMD0_MAC1_RX, DEV_FLAGS_IN, 0, 0, 0x00000000, 0, 0 },
+ { AU1550_DSCR_CMD0_MAC1_TX, DEV_FLAGS_OUT, 0, 0, 0x00000000, 0, 0 },
{ DSCR_CMD0_THROTTLE, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
- { DSCR_CMD0_ALWAYS, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
-
- /* Provide 16 user definable device types */
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
- { ~0, 0, 0, 0, 0, 0, 0 },
+ { DSCR_CMD0_ALWAYS, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
};
-#define DBDEV_TAB_SIZE ARRAY_SIZE(dbdev_tab)
+static dbdev_tab_t au1200_dbdev_tab[] __initdata = {
+ { AU1200_DSCR_CMD0_UART0_TX, DEV_FLAGS_OUT, 0, 8, 0x11100004, 0, 0 },
+ { AU1200_DSCR_CMD0_UART0_RX, DEV_FLAGS_IN, 0, 8, 0x11100000, 0, 0 },
+ { AU1200_DSCR_CMD0_UART1_TX, DEV_FLAGS_OUT, 0, 8, 0x11200004, 0, 0 },
+ { AU1200_DSCR_CMD0_UART1_RX, DEV_FLAGS_IN, 0, 8, 0x11200000, 0, 0 },
+ { AU1200_DSCR_CMD0_DMA_REQ0, 0, 0, 0, 0x00000000, 0, 0 },
+ { AU1200_DSCR_CMD0_DMA_REQ1, 0, 0, 0, 0x00000000, 0, 0 },
+
+ { AU1200_DSCR_CMD0_MAE_BE, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
+ { AU1200_DSCR_CMD0_MAE_FE, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
+ { AU1200_DSCR_CMD0_MAE_BOTH, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
+ { AU1200_DSCR_CMD0_LCD, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
+
+ { AU1200_DSCR_CMD0_SDMS_TX0, DEV_FLAGS_OUT, 4, 8, 0x10600000, 0, 0 },
+ { AU1200_DSCR_CMD0_SDMS_RX0, DEV_FLAGS_IN, 4, 8, 0x10600004, 0, 0 },
+ { AU1200_DSCR_CMD0_SDMS_TX1, DEV_FLAGS_OUT, 4, 8, 0x10680000, 0, 0 },
+ { AU1200_DSCR_CMD0_SDMS_RX1, DEV_FLAGS_IN, 4, 8, 0x10680004, 0, 0 },
+
+ { AU1200_DSCR_CMD0_AES_RX, DEV_FLAGS_IN , 4, 32, 0x10300008, 0, 0 },
+ { AU1200_DSCR_CMD0_AES_TX, DEV_FLAGS_OUT, 4, 32, 0x10300004, 0, 0 },
+
+ { AU1200_DSCR_CMD0_PSC0_TX, DEV_FLAGS_OUT, 0, 16, 0x11a0001c, 0, 0 },
+ { AU1200_DSCR_CMD0_PSC0_RX, DEV_FLAGS_IN, 0, 16, 0x11a0001c, 0, 0 },
+ { AU1200_DSCR_CMD0_PSC0_SYNC, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
+ { AU1200_DSCR_CMD0_PSC1_TX, DEV_FLAGS_OUT, 0, 16, 0x11b0001c, 0, 0 },
+ { AU1200_DSCR_CMD0_PSC1_RX, DEV_FLAGS_IN, 0, 16, 0x11b0001c, 0, 0 },
+ { AU1200_DSCR_CMD0_PSC1_SYNC, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
+
+ { AU1200_DSCR_CMD0_CIM_RXA, DEV_FLAGS_IN, 0, 32, 0x14004020, 0, 0 },
+ { AU1200_DSCR_CMD0_CIM_RXB, DEV_FLAGS_IN, 0, 32, 0x14004040, 0, 0 },
+ { AU1200_DSCR_CMD0_CIM_RXC, DEV_FLAGS_IN, 0, 32, 0x14004060, 0, 0 },
+ { AU1200_DSCR_CMD0_CIM_SYNC, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
+
+ { AU1200_DSCR_CMD0_NAND_FLASH, DEV_FLAGS_IN, 0, 0, 0x00000000, 0, 0 },
+
+ { DSCR_CMD0_THROTTLE, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
+ { DSCR_CMD0_ALWAYS, DEV_FLAGS_ANYUSE, 0, 0, 0x00000000, 0, 0 },
+};
+
+/* 32 predefined plus 32 custom */
+#define DBDEV_TAB_SIZE 64
static chan_tab_t *chan_tab_ptr[NUM_DBDMA_CHANS];
@@ -1028,38 +1002,43 @@
.resume = alchemy_dbdma_resume,
};
-static int __init au1xxx_dbdma_init(void)
+static int __init dbdma_setup(unsigned int irq, dbdev_tab_t *idtable)
{
- int irq_nr, ret;
+ int ret;
+
+ dbdev_tab = kzalloc(sizeof(dbdev_tab_t) * DBDEV_TAB_SIZE, GFP_KERNEL);
+ if (!dbdev_tab)
+ return -ENOMEM;
+
+ memcpy(dbdev_tab, idtable, 32 * sizeof(dbdev_tab_t));
+ for (ret = 32; ret < DBDEV_TAB_SIZE; ret++)
+ dbdev_tab[ret].dev_id = ~0;
dbdma_gptr->ddma_config = 0;
dbdma_gptr->ddma_throttle = 0;
dbdma_gptr->ddma_inten = 0xffff;
au_sync();
- switch (alchemy_get_cputype()) {
- case ALCHEMY_CPU_AU1550:
- irq_nr = AU1550_DDMA_INT;
- break;
- case ALCHEMY_CPU_AU1200:
- irq_nr = AU1200_DDMA_INT;
- break;
- default:
- return -ENODEV;
- }
-
- ret = request_irq(irq_nr, dbdma_interrupt, IRQF_DISABLED,
- "Au1xxx dbdma", (void *)dbdma_gptr);
+ ret = request_irq(irq, dbdma_interrupt, IRQF_DISABLED, "dbdma",
+ (void *)dbdma_gptr);
if (ret)
printk(KERN_ERR "Cannot grab DBDMA interrupt!\n");
else {
dbdma_initialized = 1;
- printk(KERN_INFO "Alchemy DBDMA initialized\n");
register_syscore_ops(&alchemy_dbdma_syscore_ops);
}
return ret;
}
-subsys_initcall(au1xxx_dbdma_init);
-#endif /* defined(CONFIG_SOC_AU1550) || defined(CONFIG_SOC_AU1200) */
+static int __init alchemy_dbdma_init(void)
+{
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1550:
+ return dbdma_setup(AU1550_DDMA_INT, au1550_dbdev_tab);
+ case ALCHEMY_CPU_AU1200:
+ return dbdma_setup(AU1200_DDMA_INT, au1200_dbdev_tab);
+ }
+ return 0;
+}
+subsys_initcall(alchemy_dbdma_init);
diff --git a/arch/mips/alchemy/common/dma.c b/arch/mips/alchemy/common/dma.c
index 347980e..9b624e2 100644
--- a/arch/mips/alchemy/common/dma.c
+++ b/arch/mips/alchemy/common/dma.c
@@ -40,8 +40,6 @@
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1000_dma.h>
-#if defined(CONFIG_SOC_AU1000) || defined(CONFIG_SOC_AU1500) || \
- defined(CONFIG_SOC_AU1100)
/*
* A note on resource allocation:
*
@@ -88,12 +86,12 @@
{ AU1000_AC97_PHYS_ADDR + 0x08, DMA_DW16 | DMA_DR }, /* AC97 RX c */
{ AU1000_UART3_PHYS_ADDR + 0x04, DMA_DW8 | DMA_NC }, /* UART3_TX */
{ AU1000_UART3_PHYS_ADDR + 0x00, DMA_DW8 | DMA_NC | DMA_DR }, /* UART3_RX */
- { AU1000_USBD_PHYS_ADDR + 0x00, DMA_DW8 | DMA_NC | DMA_DR }, /* EP0RD */
- { AU1000_USBD_PHYS_ADDR + 0x04, DMA_DW8 | DMA_NC }, /* EP0WR */
- { AU1000_USBD_PHYS_ADDR + 0x08, DMA_DW8 | DMA_NC }, /* EP2WR */
- { AU1000_USBD_PHYS_ADDR + 0x0c, DMA_DW8 | DMA_NC }, /* EP3WR */
- { AU1000_USBD_PHYS_ADDR + 0x10, DMA_DW8 | DMA_NC | DMA_DR }, /* EP4RD */
- { AU1000_USBD_PHYS_ADDR + 0x14, DMA_DW8 | DMA_NC | DMA_DR }, /* EP5RD */
+ { AU1000_USB_UDC_PHYS_ADDR + 0x00, DMA_DW8 | DMA_NC | DMA_DR }, /* EP0RD */
+ { AU1000_USB_UDC_PHYS_ADDR + 0x04, DMA_DW8 | DMA_NC }, /* EP0WR */
+ { AU1000_USB_UDC_PHYS_ADDR + 0x08, DMA_DW8 | DMA_NC }, /* EP2WR */
+ { AU1000_USB_UDC_PHYS_ADDR + 0x0c, DMA_DW8 | DMA_NC }, /* EP3WR */
+ { AU1000_USB_UDC_PHYS_ADDR + 0x10, DMA_DW8 | DMA_NC | DMA_DR }, /* EP4RD */
+ { AU1000_USB_UDC_PHYS_ADDR + 0x14, DMA_DW8 | DMA_NC | DMA_DR }, /* EP5RD */
/* on Au1500, these 2 are DMA_REQ2/3 (GPIO208/209) instead! */
{ AU1000_I2S_PHYS_ADDR + 0x00, DMA_DW32 | DMA_NC}, /* I2S TX */
{ AU1000_I2S_PHYS_ADDR + 0x00, DMA_DW32 | DMA_NC | DMA_DR}, /* I2S RX */
@@ -170,13 +168,13 @@
const struct dma_dev *dev;
int i, ret;
-#if defined(CONFIG_SOC_AU1100)
- if (dev_id < 0 || dev_id >= (DMA_NUM_DEV + DMA_NUM_DEV_BANK2))
- return -EINVAL;
-#else
- if (dev_id < 0 || dev_id >= DMA_NUM_DEV)
- return -EINVAL;
-#endif
+ if (alchemy_get_cputype() == ALCHEMY_CPU_AU1100) {
+ if (dev_id < 0 || dev_id >= (DMA_NUM_DEV + DMA_NUM_DEV_BANK2))
+ return -EINVAL;
+ } else {
+ if (dev_id < 0 || dev_id >= DMA_NUM_DEV)
+ return -EINVAL;
+ }
for (i = 0; i < NUM_AU1000_DMA_CHANNELS; i++)
if (au1000_dma_table[i].dev_id < 0)
@@ -239,30 +237,28 @@
static int __init au1000_dma_init(void)
{
- int base, i;
+ int base, i;
- switch (alchemy_get_cputype()) {
- case ALCHEMY_CPU_AU1000:
- base = AU1000_DMA_INT_BASE;
- break;
- case ALCHEMY_CPU_AU1500:
- base = AU1500_DMA_INT_BASE;
- break;
- case ALCHEMY_CPU_AU1100:
- base = AU1100_DMA_INT_BASE;
- break;
- default:
- goto out;
- }
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1000:
+ base = AU1000_DMA_INT_BASE;
+ break;
+ case ALCHEMY_CPU_AU1500:
+ base = AU1500_DMA_INT_BASE;
+ break;
+ case ALCHEMY_CPU_AU1100:
+ base = AU1100_DMA_INT_BASE;
+ break;
+ default:
+ goto out;
+ }
- for (i = 0; i < NUM_AU1000_DMA_CHANNELS; i++)
- au1000_dma_table[i].irq = base + i;
+ for (i = 0; i < NUM_AU1000_DMA_CHANNELS; i++)
+ au1000_dma_table[i].irq = base + i;
- printk(KERN_INFO "Alchemy DMA initialized\n");
+ printk(KERN_INFO "Alchemy DMA initialized\n");
out:
- return 0;
+ return 0;
}
arch_initcall(au1000_dma_init);
-
-#endif /* AU1000 AU1500 AU1100 */
diff --git a/arch/mips/alchemy/common/gpiolib-au1000.c b/arch/mips/alchemy/common/gpiolib.c
similarity index 83%
rename from arch/mips/alchemy/common/gpiolib-au1000.c
rename to arch/mips/alchemy/common/gpiolib.c
index c8e1a94..91fb4d9 100644
--- a/arch/mips/alchemy/common/gpiolib-au1000.c
+++ b/arch/mips/alchemy/common/gpiolib.c
@@ -1,6 +1,6 @@
/*
* Copyright (C) 2007-2009, OpenWrt.org, Florian Fainelli <florian@openwrt.org>
- * GPIOLIB support for Au1000, Au1500, Au1100, Au1550 and Au12x0.
+ * GPIOLIB support for Alchemy chips.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
@@ -23,18 +23,18 @@
* 675 Mass Ave, Cambridge, MA 02139, USA.
*
* Notes :
- * au1000 SoC have only one GPIO block : GPIO1
- * Au1100, Au15x0, Au12x0 have a second one : GPIO2
+ * This file must ONLY be built when CONFIG_GPIOLIB=y and
+ * CONFIG_ALCHEMY_GPIO_INDIRECT=n, otherwise compilation will fail!
+ * au1000 SoC have only one GPIO block : GPIO1
+ * Au1100, Au15x0, Au12x0 have a second one : GPIO2
*/
+#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
-#include <linux/platform_device.h>
#include <linux/gpio.h>
-
-#include <asm/mach-au1x00/au1000.h>
-#include <asm/mach-au1x00/gpio.h>
+#include <asm/mach-au1x00/gpio-au1000.h>
static int gpio2_get(struct gpio_chip *chip, unsigned offset)
{
@@ -115,12 +115,19 @@
},
};
-static int __init alchemy_gpiolib_init(void)
+static int __init alchemy_gpiochip_init(void)
{
- gpiochip_add(&alchemy_gpio_chip[0]);
- if (alchemy_get_cputype() != ALCHEMY_CPU_AU1000)
- gpiochip_add(&alchemy_gpio_chip[1]);
+ int ret = 0;
- return 0;
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1000:
+ ret = gpiochip_add(&alchemy_gpio_chip[0]);
+ break;
+ case ALCHEMY_CPU_AU1500...ALCHEMY_CPU_AU1200:
+ ret = gpiochip_add(&alchemy_gpio_chip[0]);
+ ret |= gpiochip_add(&alchemy_gpio_chip[1]);
+ break;
+ }
+ return ret;
}
-arch_initcall(alchemy_gpiolib_init);
+arch_initcall(alchemy_gpiochip_init);
diff --git a/arch/mips/alchemy/common/pci.c b/arch/mips/alchemy/common/pci.c
deleted file mode 100644
index 7866cf5..0000000
--- a/arch/mips/alchemy/common/pci.c
+++ /dev/null
@@ -1,104 +0,0 @@
-/*
- * BRIEF MODULE DESCRIPTION
- * Alchemy/AMD Au1x00 PCI support.
- *
- * Copyright 2001-2003, 2007-2008 MontaVista Software Inc.
- * Author: MontaVista Software, Inc. <source@mvista.com>
- *
- * Copyright (C) 2004 by Ralf Baechle (ralf@linux-mips.org)
- *
- * Support for all devices (greater than 16) added by David Gathright.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
- * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
- * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
- * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
- * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
- * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/pci.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-
-#include <asm/mach-au1x00/au1000.h>
-
-/* TBD */
-static struct resource pci_io_resource = {
- .start = PCI_IO_START,
- .end = PCI_IO_END,
- .name = "PCI IO space",
- .flags = IORESOURCE_IO
-};
-
-static struct resource pci_mem_resource = {
- .start = PCI_MEM_START,
- .end = PCI_MEM_END,
- .name = "PCI memory space",
- .flags = IORESOURCE_MEM
-};
-
-extern struct pci_ops au1x_pci_ops;
-
-static struct pci_controller au1x_controller = {
- .pci_ops = &au1x_pci_ops,
- .io_resource = &pci_io_resource,
- .mem_resource = &pci_mem_resource,
-};
-
-#if defined(CONFIG_SOC_AU1500) || defined(CONFIG_SOC_AU1550)
-static unsigned long virt_io_addr;
-#endif
-
-static int __init au1x_pci_setup(void)
-{
- extern void au1x_pci_cfg_init(void);
-
-#if defined(CONFIG_SOC_AU1500) || defined(CONFIG_SOC_AU1550)
- virt_io_addr = (unsigned long)ioremap(Au1500_PCI_IO_START,
- Au1500_PCI_IO_END - Au1500_PCI_IO_START + 1);
-
- if (!virt_io_addr) {
- printk(KERN_ERR "Unable to ioremap pci space\n");
- return 1;
- }
- au1x_controller.io_map_base = virt_io_addr;
-
-#ifdef CONFIG_DMA_NONCOHERENT
- {
- /*
- * Set the NC bit in controller for Au1500 pre-AC silicon
- */
- u32 prid = read_c0_prid();
-
- if ((prid & 0xFF000000) == 0x01000000 && prid < 0x01030202) {
- au_writel((1 << 16) | au_readl(Au1500_PCI_CFG),
- Au1500_PCI_CFG);
- printk(KERN_INFO "Non-coherent PCI accesses enabled\n");
- }
- }
-#endif
-
- set_io_port_base(virt_io_addr);
-#endif
-
- au1x_pci_cfg_init();
-
- register_pci_controller(&au1x_controller);
- return 0;
-}
-
-arch_initcall(au1x_pci_setup);
diff --git a/arch/mips/alchemy/common/platform.c b/arch/mips/alchemy/common/platform.c
index f72c48d..c8e5d72 100644
--- a/arch/mips/alchemy/common/platform.c
+++ b/arch/mips/alchemy/common/platform.c
@@ -18,7 +18,7 @@
#include <linux/serial_8250.h>
#include <linux/slab.h>
-#include <asm/mach-au1x00/au1xxx.h>
+#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1xxx_dbdma.h>
#include <asm/mach-au1x00/au1100_mmc.h>
#include <asm/mach-au1x00/au1xxx_eth.h>
@@ -111,270 +111,87 @@
printk(KERN_INFO "Alchemy: failed to register UARTs\n");
}
-/* OHCI (USB full speed host controller) */
-static struct resource au1xxx_usb_ohci_resources[] = {
- [0] = {
- .start = USB_OHCI_BASE,
- .end = USB_OHCI_BASE + USB_OHCI_LEN - 1,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = FOR_PLATFORM_C_USB_HOST_INT,
- .end = FOR_PLATFORM_C_USB_HOST_INT,
- .flags = IORESOURCE_IRQ,
- },
+
+/* The dmamask must be set for OHCI/EHCI to work */
+static u64 alchemy_ohci_dmamask = DMA_BIT_MASK(32);
+static u64 __maybe_unused alchemy_ehci_dmamask = DMA_BIT_MASK(32);
+
+static unsigned long alchemy_ohci_data[][2] __initdata = {
+ [ALCHEMY_CPU_AU1000] = { AU1000_USB_OHCI_PHYS_ADDR, AU1000_USB_HOST_INT },
+ [ALCHEMY_CPU_AU1500] = { AU1000_USB_OHCI_PHYS_ADDR, AU1500_USB_HOST_INT },
+ [ALCHEMY_CPU_AU1100] = { AU1000_USB_OHCI_PHYS_ADDR, AU1100_USB_HOST_INT },
+ [ALCHEMY_CPU_AU1550] = { AU1550_USB_OHCI_PHYS_ADDR, AU1550_USB_HOST_INT },
+ [ALCHEMY_CPU_AU1200] = { AU1200_USB_OHCI_PHYS_ADDR, AU1200_USB_INT },
};
-/* The dmamask must be set for OHCI to work */
-static u64 ohci_dmamask = DMA_BIT_MASK(32);
-
-static struct platform_device au1xxx_usb_ohci_device = {
- .name = "au1xxx-ohci",
- .id = 0,
- .dev = {
- .dma_mask = &ohci_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(32),
- },
- .num_resources = ARRAY_SIZE(au1xxx_usb_ohci_resources),
- .resource = au1xxx_usb_ohci_resources,
+static unsigned long alchemy_ehci_data[][2] __initdata = {
+ [ALCHEMY_CPU_AU1200] = { AU1200_USB_EHCI_PHYS_ADDR, AU1200_USB_INT },
};
-/*** AU1100 LCD controller ***/
-
-#ifdef CONFIG_FB_AU1100
-static struct resource au1100_lcd_resources[] = {
- [0] = {
- .start = LCD_PHYS_ADDR,
- .end = LCD_PHYS_ADDR + 0x800 - 1,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = AU1100_LCD_INT,
- .end = AU1100_LCD_INT,
- .flags = IORESOURCE_IRQ,
+static int __init _new_usbres(struct resource **r, struct platform_device **d)
+{
+ *r = kzalloc(sizeof(struct resource) * 2, GFP_KERNEL);
+ if (!*r)
+ return -ENOMEM;
+ *d = kzalloc(sizeof(struct platform_device), GFP_KERNEL);
+ if (!*d) {
+ kfree(*r);
+ return -ENOMEM;
}
-};
-static u64 au1100_lcd_dmamask = DMA_BIT_MASK(32);
+ (*d)->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+ (*d)->num_resources = 2;
+ (*d)->resource = *r;
-static struct platform_device au1100_lcd_device = {
- .name = "au1100-lcd",
- .id = 0,
- .dev = {
- .dma_mask = &au1100_lcd_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(32),
- },
- .num_resources = ARRAY_SIZE(au1100_lcd_resources),
- .resource = au1100_lcd_resources,
-};
-#endif
+ return 0;
+}
-#ifdef CONFIG_SOC_AU1200
-/* EHCI (USB high speed host controller) */
-static struct resource au1xxx_usb_ehci_resources[] = {
- [0] = {
- .start = USB_EHCI_BASE,
- .end = USB_EHCI_BASE + USB_EHCI_LEN - 1,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = AU1200_USB_INT,
- .end = AU1200_USB_INT,
- .flags = IORESOURCE_IRQ,
- },
-};
+static void __init alchemy_setup_usb(int ctype)
+{
+ struct resource *res;
+ struct platform_device *pdev;
-static u64 ehci_dmamask = DMA_BIT_MASK(32);
+ /* setup OHCI0. Every variant has one */
+ if (_new_usbres(&res, &pdev))
+ return;
-static struct platform_device au1xxx_usb_ehci_device = {
- .name = "au1xxx-ehci",
- .id = 0,
- .dev = {
- .dma_mask = &ehci_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(32),
- },
- .num_resources = ARRAY_SIZE(au1xxx_usb_ehci_resources),
- .resource = au1xxx_usb_ehci_resources,
-};
+ res[0].start = alchemy_ohci_data[ctype][0];
+ res[0].end = res[0].start + 0x100 - 1;
+ res[0].flags = IORESOURCE_MEM;
+ res[1].start = alchemy_ohci_data[ctype][1];
+ res[1].end = res[1].start;
+ res[1].flags = IORESOURCE_IRQ;
+ pdev->name = "au1xxx-ohci";
+ pdev->id = 0;
+ pdev->dev.dma_mask = &alchemy_ohci_dmamask;
-/* Au1200 UDC (USB gadget controller) */
-static struct resource au1xxx_usb_gdt_resources[] = {
- [0] = {
- .start = USB_UDC_BASE,
- .end = USB_UDC_BASE + USB_UDC_LEN - 1,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = AU1200_USB_INT,
- .end = AU1200_USB_INT,
- .flags = IORESOURCE_IRQ,
- },
-};
+ if (platform_device_register(pdev))
+ printk(KERN_INFO "Alchemy USB: cannot add OHCI0\n");
-static u64 udc_dmamask = DMA_BIT_MASK(32);
-static struct platform_device au1xxx_usb_gdt_device = {
- .name = "au1xxx-udc",
- .id = 0,
- .dev = {
- .dma_mask = &udc_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(32),
- },
- .num_resources = ARRAY_SIZE(au1xxx_usb_gdt_resources),
- .resource = au1xxx_usb_gdt_resources,
-};
+ /* setup EHCI0: Au1200 */
+ if (ctype == ALCHEMY_CPU_AU1200) {
+ if (_new_usbres(&res, &pdev))
+ return;
-/* Au1200 UOC (USB OTG controller) */
-static struct resource au1xxx_usb_otg_resources[] = {
- [0] = {
- .start = USB_UOC_BASE,
- .end = USB_UOC_BASE + USB_UOC_LEN - 1,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = AU1200_USB_INT,
- .end = AU1200_USB_INT,
- .flags = IORESOURCE_IRQ,
- },
-};
+ res[0].start = alchemy_ehci_data[ctype][0];
+ res[0].end = res[0].start + 0x100 - 1;
+ res[0].flags = IORESOURCE_MEM;
+ res[1].start = alchemy_ehci_data[ctype][1];
+ res[1].end = res[1].start;
+ res[1].flags = IORESOURCE_IRQ;
+ pdev->name = "au1xxx-ehci";
+ pdev->id = 0;
+ pdev->dev.dma_mask = &alchemy_ehci_dmamask;
-static u64 uoc_dmamask = DMA_BIT_MASK(32);
-
-static struct platform_device au1xxx_usb_otg_device = {
- .name = "au1xxx-uoc",
- .id = 0,
- .dev = {
- .dma_mask = &uoc_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(32),
- },
- .num_resources = ARRAY_SIZE(au1xxx_usb_otg_resources),
- .resource = au1xxx_usb_otg_resources,
-};
-
-static struct resource au1200_lcd_resources[] = {
- [0] = {
- .start = LCD_PHYS_ADDR,
- .end = LCD_PHYS_ADDR + 0x800 - 1,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = AU1200_LCD_INT,
- .end = AU1200_LCD_INT,
- .flags = IORESOURCE_IRQ,
+ if (platform_device_register(pdev))
+ printk(KERN_INFO "Alchemy USB: cannot add EHCI0\n");
}
-};
-
-static u64 au1200_lcd_dmamask = DMA_BIT_MASK(32);
-
-static struct platform_device au1200_lcd_device = {
- .name = "au1200-lcd",
- .id = 0,
- .dev = {
- .dma_mask = &au1200_lcd_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(32),
- },
- .num_resources = ARRAY_SIZE(au1200_lcd_resources),
- .resource = au1200_lcd_resources,
-};
-
-static u64 au1xxx_mmc_dmamask = DMA_BIT_MASK(32);
-
-extern struct au1xmmc_platform_data au1xmmc_platdata[2];
-
-static struct resource au1200_mmc0_resources[] = {
- [0] = {
- .start = AU1100_SD0_PHYS_ADDR,
- .end = AU1100_SD0_PHYS_ADDR + 0xfff,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = AU1200_SD_INT,
- .end = AU1200_SD_INT,
- .flags = IORESOURCE_IRQ,
- },
- [2] = {
- .start = DSCR_CMD0_SDMS_TX0,
- .end = DSCR_CMD0_SDMS_TX0,
- .flags = IORESOURCE_DMA,
- },
- [3] = {
- .start = DSCR_CMD0_SDMS_RX0,
- .end = DSCR_CMD0_SDMS_RX0,
- .flags = IORESOURCE_DMA,
- }
-};
-
-static struct platform_device au1200_mmc0_device = {
- .name = "au1xxx-mmc",
- .id = 0,
- .dev = {
- .dma_mask = &au1xxx_mmc_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(32),
- .platform_data = &au1xmmc_platdata[0],
- },
- .num_resources = ARRAY_SIZE(au1200_mmc0_resources),
- .resource = au1200_mmc0_resources,
-};
-
-#ifndef CONFIG_MIPS_DB1200
-static struct resource au1200_mmc1_resources[] = {
- [0] = {
- .start = AU1100_SD1_PHYS_ADDR,
- .end = AU1100_SD1_PHYS_ADDR + 0xfff,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = AU1200_SD_INT,
- .end = AU1200_SD_INT,
- .flags = IORESOURCE_IRQ,
- },
- [2] = {
- .start = DSCR_CMD0_SDMS_TX1,
- .end = DSCR_CMD0_SDMS_TX1,
- .flags = IORESOURCE_DMA,
- },
- [3] = {
- .start = DSCR_CMD0_SDMS_RX1,
- .end = DSCR_CMD0_SDMS_RX1,
- .flags = IORESOURCE_DMA,
- }
-};
-
-static struct platform_device au1200_mmc1_device = {
- .name = "au1xxx-mmc",
- .id = 1,
- .dev = {
- .dma_mask = &au1xxx_mmc_dmamask,
- .coherent_dma_mask = DMA_BIT_MASK(32),
- .platform_data = &au1xmmc_platdata[1],
- },
- .num_resources = ARRAY_SIZE(au1200_mmc1_resources),
- .resource = au1200_mmc1_resources,
-};
-#endif /* #ifndef CONFIG_MIPS_DB1200 */
-#endif /* #ifdef CONFIG_SOC_AU1200 */
-
-/* All Alchemy demoboards with I2C have this #define in their headers */
-#ifdef SMBUS_PSC_BASE
-static struct resource pbdb_smbus_resources[] = {
- {
- .start = CPHYSADDR(SMBUS_PSC_BASE),
- .end = CPHYSADDR(SMBUS_PSC_BASE + 0xfffff),
- .flags = IORESOURCE_MEM,
- },
-};
-
-static struct platform_device pbdb_smbus_device = {
- .name = "au1xpsc_smbus",
- .id = 0, /* bus number */
- .num_resources = ARRAY_SIZE(pbdb_smbus_resources),
- .resource = pbdb_smbus_resources,
-};
-#endif
+}
/* Macro to help defining the Ethernet MAC resources */
-#define MAC_RES_COUNT 3 /* MAC regs base, MAC enable reg, MAC INT */
-#define MAC_RES(_base, _enable, _irq) \
+#define MAC_RES_COUNT 4 /* MAC regs, MAC en, MAC INT, MACDMA regs */
+#define MAC_RES(_base, _enable, _irq, _macdma) \
{ \
.start = _base, \
.end = _base + 0xffff, \
@@ -389,28 +206,37 @@
.start = _irq, \
.end = _irq, \
.flags = IORESOURCE_IRQ \
+ }, \
+ { \
+ .start = _macdma, \
+ .end = _macdma + 0x1ff, \
+ .flags = IORESOURCE_MEM, \
}
static struct resource au1xxx_eth0_resources[][MAC_RES_COUNT] __initdata = {
[ALCHEMY_CPU_AU1000] = {
MAC_RES(AU1000_MAC0_PHYS_ADDR,
AU1000_MACEN_PHYS_ADDR,
- AU1000_MAC0_DMA_INT)
+ AU1000_MAC0_DMA_INT,
+ AU1000_MACDMA0_PHYS_ADDR)
},
[ALCHEMY_CPU_AU1500] = {
MAC_RES(AU1500_MAC0_PHYS_ADDR,
AU1500_MACEN_PHYS_ADDR,
- AU1500_MAC0_DMA_INT)
+ AU1500_MAC0_DMA_INT,
+ AU1000_MACDMA0_PHYS_ADDR)
},
[ALCHEMY_CPU_AU1100] = {
MAC_RES(AU1000_MAC0_PHYS_ADDR,
AU1000_MACEN_PHYS_ADDR,
- AU1100_MAC0_DMA_INT)
+ AU1100_MAC0_DMA_INT,
+ AU1000_MACDMA0_PHYS_ADDR)
},
[ALCHEMY_CPU_AU1550] = {
MAC_RES(AU1000_MAC0_PHYS_ADDR,
AU1000_MACEN_PHYS_ADDR,
- AU1550_MAC0_DMA_INT)
+ AU1550_MAC0_DMA_INT,
+ AU1000_MACDMA0_PHYS_ADDR)
},
};
@@ -429,17 +255,20 @@
[ALCHEMY_CPU_AU1000] = {
MAC_RES(AU1000_MAC1_PHYS_ADDR,
AU1000_MACEN_PHYS_ADDR + 4,
- AU1000_MAC1_DMA_INT)
+ AU1000_MAC1_DMA_INT,
+ AU1000_MACDMA1_PHYS_ADDR)
},
[ALCHEMY_CPU_AU1500] = {
MAC_RES(AU1500_MAC1_PHYS_ADDR,
AU1500_MACEN_PHYS_ADDR + 4,
- AU1500_MAC1_DMA_INT)
+ AU1500_MAC1_DMA_INT,
+ AU1000_MACDMA1_PHYS_ADDR)
},
[ALCHEMY_CPU_AU1550] = {
MAC_RES(AU1000_MAC1_PHYS_ADDR,
AU1000_MACEN_PHYS_ADDR + 4,
- AU1550_MAC1_DMA_INT)
+ AU1550_MAC1_DMA_INT,
+ AU1000_MACDMA1_PHYS_ADDR)
},
};
@@ -521,36 +350,15 @@
}
}
-static struct platform_device *au1xxx_platform_devices[] __initdata = {
- &au1xxx_usb_ohci_device,
-#ifdef CONFIG_FB_AU1100
- &au1100_lcd_device,
-#endif
-#ifdef CONFIG_SOC_AU1200
- &au1xxx_usb_ehci_device,
- &au1xxx_usb_gdt_device,
- &au1xxx_usb_otg_device,
- &au1200_lcd_device,
- &au1200_mmc0_device,
-#ifndef CONFIG_MIPS_DB1200
- &au1200_mmc1_device,
-#endif
-#endif
-#ifdef SMBUS_PSC_BASE
- &pbdb_smbus_device,
-#endif
-};
-
static int __init au1xxx_platform_init(void)
{
- int err, ctype = alchemy_get_cputype();
+ int ctype = alchemy_get_cputype();
alchemy_setup_uarts(ctype);
alchemy_setup_macs(ctype);
+ alchemy_setup_usb(ctype);
- err = platform_add_devices(au1xxx_platform_devices,
- ARRAY_SIZE(au1xxx_platform_devices));
- return err;
+ return 0;
}
arch_initcall(au1xxx_platform_init);
diff --git a/arch/mips/alchemy/common/power.c b/arch/mips/alchemy/common/power.c
index b86324a..bdd6651 100644
--- a/arch/mips/alchemy/common/power.c
+++ b/arch/mips/alchemy/common/power.c
@@ -37,8 +37,6 @@
#include <asm/uaccess.h>
#include <asm/mach-au1x00/au1000.h>
-#ifdef CONFIG_PM
-
/*
* We need to save/restore a bunch of core registers that are
* either volatile or reset to some state across a processor sleep.
@@ -49,7 +47,6 @@
* We only have to save/restore registers that aren't otherwise
* done as part of a driver pm_* function.
*/
-static unsigned int sleep_usb[2];
static unsigned int sleep_sys_clocks[5];
static unsigned int sleep_sys_pinfunc;
static unsigned int sleep_static_memctlr[4][3];
@@ -57,31 +54,6 @@
static void save_core_regs(void)
{
-#ifndef CONFIG_SOC_AU1200
- /* Shutdown USB host/device. */
- sleep_usb[0] = au_readl(USB_HOST_CONFIG);
-
- /* There appears to be some undocumented reset register.... */
- au_writel(0, 0xb0100004);
- au_sync();
- au_writel(0, USB_HOST_CONFIG);
- au_sync();
-
- sleep_usb[1] = au_readl(USBD_ENABLE);
- au_writel(0, USBD_ENABLE);
- au_sync();
-
-#else /* AU1200 */
-
- /* enable access to OTG mmio so we can save OTG CAP/MUX.
- * FIXME: write an OTG driver and move this stuff there!
- */
- au_writel(au_readl(USB_MSR_BASE + 4) | (1 << 6), USB_MSR_BASE + 4);
- au_sync();
- sleep_usb[0] = au_readl(0xb4020020); /* OTG_CAP */
- sleep_usb[1] = au_readl(0xb4020024); /* OTG_MUX */
-#endif
-
/* Clocks and PLLs. */
sleep_sys_clocks[0] = au_readl(SYS_FREQCTRL0);
sleep_sys_clocks[1] = au_readl(SYS_FREQCTRL1);
@@ -125,22 +97,6 @@
au_writel(sleep_sys_pinfunc, SYS_PINFUNC);
au_sync();
-#ifndef CONFIG_SOC_AU1200
- au_writel(sleep_usb[0], USB_HOST_CONFIG);
- au_writel(sleep_usb[1], USBD_ENABLE);
- au_sync();
-#else
- /* enable access to OTG memory */
- au_writel(au_readl(USB_MSR_BASE + 4) | (1 << 6), USB_MSR_BASE + 4);
- au_sync();
-
- /* restore OTG caps and port mux. */
- au_writel(sleep_usb[0], 0xb4020020 + 0); /* OTG_CAP */
- au_sync();
- au_writel(sleep_usb[1], 0xb4020020 + 4); /* OTG_MUX */
- au_sync();
-#endif
-
/* Restore the static memory controller configuration. */
au_writel(sleep_static_memctlr[0][0], MEM_STCFG0);
au_writel(sleep_static_memctlr[0][1], MEM_STTIME0);
@@ -174,5 +130,3 @@
restore_core_regs();
}
-
-#endif /* CONFIG_PM */
diff --git a/arch/mips/alchemy/common/setup.c b/arch/mips/alchemy/common/setup.c
index 1b887c8..37ffd99 100644
--- a/arch/mips/alchemy/common/setup.c
+++ b/arch/mips/alchemy/common/setup.c
@@ -73,8 +73,8 @@
/* This routine should be valid for all Au1x based boards */
phys_t __fixup_bigphys_addr(phys_t phys_addr, phys_t size)
{
- u32 start = (u32)Au1500_PCI_MEM_START;
- u32 end = (u32)Au1500_PCI_MEM_END;
+ unsigned long start = ALCHEMY_PCI_MEMWIN_START;
+ unsigned long end = ALCHEMY_PCI_MEMWIN_END;
/* Don't fixup 36-bit addresses */
if ((phys_addr >> 32) != 0)
@@ -82,7 +82,7 @@
/* Check for PCI memory window */
if (phys_addr >= start && (phys_addr + size - 1) <= end)
- return (phys_t)((phys_addr - start) + Au1500_PCI_MEM_START);
+ return (phys_t)(AU1500_PCI_MEM_PHYS_ADDR + phys_addr);
/* default nop */
return phys_addr;
diff --git a/arch/mips/alchemy/devboards/db1200/platform.c b/arch/mips/alchemy/devboards/db1200/platform.c
index dda090b..c61867c 100644
--- a/arch/mips/alchemy/devboards/db1200/platform.c
+++ b/arch/mips/alchemy/devboards/db1200/platform.c
@@ -213,7 +213,12 @@
.start = DB1200_IDE_INT,
.end = DB1200_IDE_INT,
.flags = IORESOURCE_IRQ,
- }
+ },
+ [2] = {
+ .start = AU1200_DSCR_CMD0_DMA_REQ1,
+ .end = AU1200_DSCR_CMD0_DMA_REQ1,
+ .flags = IORESOURCE_DMA,
+ },
};
static u64 ide_dmamask = DMA_BIT_MASK(32);
@@ -328,23 +333,85 @@
.brightness_set = db1200_mmcled_set,
};
-/* needed by arch/mips/alchemy/common/platform.c */
-struct au1xmmc_platform_data au1xmmc_platdata[] = {
+static struct au1xmmc_platform_data db1200mmc_platdata = {
+ .cd_setup = db1200_mmc_cd_setup,
+ .set_power = db1200_mmc_set_power,
+ .card_inserted = db1200_mmc_card_inserted,
+ .card_readonly = db1200_mmc_card_readonly,
+ .led = &db1200_mmc_led,
+};
+
+static struct resource au1200_mmc0_resources[] = {
[0] = {
- .cd_setup = db1200_mmc_cd_setup,
- .set_power = db1200_mmc_set_power,
- .card_inserted = db1200_mmc_card_inserted,
- .card_readonly = db1200_mmc_card_readonly,
- .led = &db1200_mmc_led,
+ .start = AU1100_SD0_PHYS_ADDR,
+ .end = AU1100_SD0_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
},
+ [1] = {
+ .start = AU1200_SD_INT,
+ .end = AU1200_SD_INT,
+ .flags = IORESOURCE_IRQ,
+ },
+ [2] = {
+ .start = AU1200_DSCR_CMD0_SDMS_TX0,
+ .end = AU1200_DSCR_CMD0_SDMS_TX0,
+ .flags = IORESOURCE_DMA,
+ },
+ [3] = {
+ .start = AU1200_DSCR_CMD0_SDMS_RX0,
+ .end = AU1200_DSCR_CMD0_SDMS_RX0,
+ .flags = IORESOURCE_DMA,
+ }
+};
+
+static u64 au1xxx_mmc_dmamask = DMA_BIT_MASK(32);
+
+static struct platform_device db1200_mmc0_dev = {
+ .name = "au1xxx-mmc",
+ .id = 0,
+ .dev = {
+ .dma_mask = &au1xxx_mmc_dmamask,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
+ .platform_data = &db1200mmc_platdata,
+ },
+ .num_resources = ARRAY_SIZE(au1200_mmc0_resources),
+ .resource = au1200_mmc0_resources,
+};
+
+/**********************************************************************/
+
+static struct resource au1200_lcd_res[] = {
+ [0] = {
+ .start = AU1200_LCD_PHYS_ADDR,
+ .end = AU1200_LCD_PHYS_ADDR + 0x800 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = AU1200_LCD_INT,
+ .end = AU1200_LCD_INT,
+ .flags = IORESOURCE_IRQ,
+ }
+};
+
+static u64 au1200_lcd_dmamask = DMA_BIT_MASK(32);
+
+static struct platform_device au1200_lcd_dev = {
+ .name = "au1200-lcd",
+ .id = 0,
+ .dev = {
+ .dma_mask = &au1200_lcd_dmamask,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
+ },
+ .num_resources = ARRAY_SIZE(au1200_lcd_res),
+ .resource = au1200_lcd_res,
};
/**********************************************************************/
static struct resource au1200_psc0_res[] = {
[0] = {
- .start = PSC0_PHYS_ADDR,
- .end = PSC0_PHYS_ADDR + 0x000fffff,
+ .start = AU1550_PSC0_PHYS_ADDR,
+ .end = AU1550_PSC0_PHYS_ADDR + 0xfff,
.flags = IORESOURCE_MEM,
},
[1] = {
@@ -353,13 +420,13 @@
.flags = IORESOURCE_IRQ,
},
[2] = {
- .start = DSCR_CMD0_PSC0_TX,
- .end = DSCR_CMD0_PSC0_TX,
+ .start = AU1200_DSCR_CMD0_PSC0_TX,
+ .end = AU1200_DSCR_CMD0_PSC0_TX,
.flags = IORESOURCE_DMA,
},
[3] = {
- .start = DSCR_CMD0_PSC0_RX,
- .end = DSCR_CMD0_PSC0_RX,
+ .start = AU1200_DSCR_CMD0_PSC0_RX,
+ .end = AU1200_DSCR_CMD0_PSC0_RX,
.flags = IORESOURCE_DMA,
},
};
@@ -401,8 +468,8 @@
static struct resource au1200_psc1_res[] = {
[0] = {
- .start = PSC1_PHYS_ADDR,
- .end = PSC1_PHYS_ADDR + 0x000fffff,
+ .start = AU1550_PSC1_PHYS_ADDR,
+ .end = AU1550_PSC1_PHYS_ADDR + 0xfff,
.flags = IORESOURCE_MEM,
},
[1] = {
@@ -411,13 +478,13 @@
.flags = IORESOURCE_IRQ,
},
[2] = {
- .start = DSCR_CMD0_PSC1_TX,
- .end = DSCR_CMD0_PSC1_TX,
+ .start = AU1200_DSCR_CMD0_PSC1_TX,
+ .end = AU1200_DSCR_CMD0_PSC1_TX,
.flags = IORESOURCE_DMA,
},
[3] = {
- .start = DSCR_CMD0_PSC1_RX,
- .end = DSCR_CMD0_PSC1_RX,
+ .start = AU1200_DSCR_CMD0_PSC1_RX,
+ .end = AU1200_DSCR_CMD0_PSC1_RX,
.flags = IORESOURCE_DMA,
},
};
@@ -449,6 +516,8 @@
static struct platform_device *db1200_devs[] __initdata = {
NULL, /* PSC0, selected by S6.8 */
&db1200_ide_dev,
+ &db1200_mmc0_dev,
+ &au1200_lcd_dev,
&db1200_eth_dev,
&db1200_rtc_dev,
&db1200_nand_dev,
@@ -526,32 +595,28 @@
/* Audio PSC clock is supplied externally. (FIXME: platdata!!) */
__raw_writel(PSC_SEL_CLK_SERCLK,
- (void __iomem *)KSEG1ADDR(PSC1_PHYS_ADDR) + PSC_SEL_OFFSET);
+ (void __iomem *)KSEG1ADDR(AU1550_PSC1_PHYS_ADDR) + PSC_SEL_OFFSET);
wmb();
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR,
- PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_MEM_PHYS_ADDR,
- PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_IO_PHYS_ADDR,
- PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
- DB1200_PC0_INT,
- DB1200_PC0_INSERT_INT,
- /*DB1200_PC0_STSCHG_INT*/0,
- DB1200_PC0_EJECT_INT,
- 0);
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
+ DB1200_PC0_INT, DB1200_PC0_INSERT_INT,
+ /*DB1200_PC0_STSCHG_INT*/0, DB1200_PC0_EJECT_INT, 0);
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR + 0x004000000,
- PCMCIA_ATTR_PHYS_ADDR + 0x004400000 - 1,
- PCMCIA_MEM_PHYS_ADDR + 0x004000000,
- PCMCIA_MEM_PHYS_ADDR + 0x004400000 - 1,
- PCMCIA_IO_PHYS_ADDR + 0x004000000,
- PCMCIA_IO_PHYS_ADDR + 0x004010000 - 1,
- DB1200_PC1_INT,
- DB1200_PC1_INSERT_INT,
- /*DB1200_PC1_STSCHG_INT*/0,
- DB1200_PC1_EJECT_INT,
- 1);
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x004000000,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x004400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x004000000,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x004400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x004000000,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x004010000 - 1,
+ DB1200_PC1_INT, DB1200_PC1_INSERT_INT,
+ /*DB1200_PC1_STSCHG_INT*/0, DB1200_PC1_EJECT_INT, 1);
swapped = bcsr_read(BCSR_STATUS) & BCSR_STATUS_DB1200_SWAPBOOT;
db1x_register_norflash(64 << 20, 2, swapped);
diff --git a/arch/mips/alchemy/devboards/db1x00/board_setup.c b/arch/mips/alchemy/devboards/db1x00/board_setup.c
index 5c956fe..7cd36e6 100644
--- a/arch/mips/alchemy/devboards/db1x00/board_setup.c
+++ b/arch/mips/alchemy/devboards/db1x00/board_setup.c
@@ -40,24 +40,6 @@
#include <prom.h>
-#ifdef CONFIG_MIPS_DB1500
-char irq_tab_alchemy[][5] __initdata = {
- [12] = { -1, AU1500_PCI_INTA, 0xff, 0xff, 0xff }, /* IDSEL 12 - HPT371 */
- [13] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTB, AU1500_PCI_INTC, AU1500_PCI_INTD }, /* IDSEL 13 - PCI slot */
-};
-
-#endif
-
-
-#ifdef CONFIG_MIPS_DB1550
-char irq_tab_alchemy[][5] __initdata = {
- [11] = { -1, AU1550_PCI_INTC, 0xff, 0xff, 0xff }, /* IDSEL 11 - on-board HPT371 */
- [12] = { -1, AU1550_PCI_INTB, AU1550_PCI_INTC, AU1550_PCI_INTD, AU1550_PCI_INTA }, /* IDSEL 12 - PCI slot 2 (left) */
- [13] = { -1, AU1550_PCI_INTA, AU1550_PCI_INTB, AU1550_PCI_INTC, AU1550_PCI_INTD }, /* IDSEL 13 - PCI slot 1 (right) */
-};
-#endif
-
-
#ifdef CONFIG_MIPS_BOSPORUS
char irq_tab_alchemy[][5] __initdata = {
[11] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTB, 0xff, 0xff }, /* IDSEL 11 - miniPCI */
@@ -91,12 +73,6 @@
#ifdef CONFIG_MIPS_MIRAGE
-char irq_tab_alchemy[][5] __initdata = {
- [11] = { -1, AU1500_PCI_INTD, 0xff, 0xff, 0xff }, /* IDSEL 11 - SMI VGX */
- [12] = { -1, 0xff, 0xff, AU1500_PCI_INTC, 0xff }, /* IDSEL 12 - PNX1300 */
- [13] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTB, 0xff, 0xff }, /* IDSEL 13 - miniPCI */
-};
-
static void mirage_power_off(void)
{
alchemy_gpio_direction_output(210, 1);
@@ -158,9 +134,7 @@
/* initialize board register space */
bcsr_init(bcsr1, bcsr2);
- /* Not valid for Au1550 */
-#if defined(CONFIG_IRDA) && \
- (defined(CONFIG_SOC_AU1000) || defined(CONFIG_SOC_AU1100))
+#if defined(CONFIG_IRDA) && defined(CONFIG_AU1000_FIR)
{
u32 pin_func;
diff --git a/arch/mips/alchemy/devboards/db1x00/platform.c b/arch/mips/alchemy/devboards/db1x00/platform.c
index 7057d28..9e6b3d4 100644
--- a/arch/mips/alchemy/devboards/db1x00/platform.c
+++ b/arch/mips/alchemy/devboards/db1x00/platform.c
@@ -20,14 +20,16 @@
#include <linux/init.h>
#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
#include <linux/platform_device.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1000_dma.h>
-#include <asm/mach-au1x00/au1xxx.h>
#include <asm/mach-db1x00/bcsr.h>
#include "../platform.h"
+struct pci_dev;
+
/* DB1xxx PCMCIA interrupt sources:
* CD0/1 GPIO0/3
* STSCHG0/1 GPIO1/4
@@ -88,6 +90,155 @@
#endif
#endif
+#ifdef CONFIG_PCI
+#ifdef CONFIG_MIPS_DB1500
+static int db1xxx_map_pci_irq(const struct pci_dev *d, u8 slot, u8 pin)
+{
+ if ((slot < 12) || (slot > 13) || pin == 0)
+ return -1;
+ if (slot == 12)
+ return (pin == 1) ? AU1500_PCI_INTA : 0xff;
+ if (slot == 13) {
+ switch (pin) {
+ case 1: return AU1500_PCI_INTA;
+ case 2: return AU1500_PCI_INTB;
+ case 3: return AU1500_PCI_INTC;
+ case 4: return AU1500_PCI_INTD;
+ }
+ }
+ return -1;
+}
+#endif
+
+#ifdef CONFIG_MIPS_DB1550
+static int db1xxx_map_pci_irq(const struct pci_dev *d, u8 slot, u8 pin)
+{
+ if ((slot < 11) || (slot > 13) || pin == 0)
+ return -1;
+ if (slot == 11)
+ return (pin == 1) ? AU1550_PCI_INTC : 0xff;
+ if (slot == 12) {
+ switch (pin) {
+ case 1: return AU1550_PCI_INTB;
+ case 2: return AU1550_PCI_INTC;
+ case 3: return AU1550_PCI_INTD;
+ case 4: return AU1550_PCI_INTA;
+ }
+ }
+ if (slot == 13) {
+ switch (pin) {
+ case 1: return AU1550_PCI_INTA;
+ case 2: return AU1550_PCI_INTB;
+ case 3: return AU1550_PCI_INTC;
+ case 4: return AU1550_PCI_INTD;
+ }
+ }
+ return -1;
+}
+#endif
+
+#ifdef CONFIG_MIPS_BOSPORUS
+static int db1xxx_map_pci_irq(const struct pci_dev *d, u8 slot, u8 pin)
+{
+ if ((slot < 11) || (slot > 13) || pin == 0)
+ return -1;
+ if (slot == 12)
+ return (pin == 1) ? AU1500_PCI_INTA : 0xff;
+ if (slot == 11) {
+ switch (pin) {
+ case 1: return AU1500_PCI_INTA;
+ case 2: return AU1500_PCI_INTB;
+ default: return 0xff;
+ }
+ }
+ if (slot == 13) {
+ switch (pin) {
+ case 1: return AU1500_PCI_INTA;
+ case 2: return AU1500_PCI_INTB;
+ case 3: return AU1500_PCI_INTC;
+ case 4: return AU1500_PCI_INTD;
+ }
+ }
+ return -1;
+}
+#endif
+
+#ifdef CONFIG_MIPS_MIRAGE
+static int db1xxx_map_pci_irq(const struct pci_dev *d, u8 slot, u8 pin)
+{
+ if ((slot < 11) || (slot > 13) || pin == 0)
+ return -1;
+ if (slot == 11)
+ return (pin == 1) ? AU1500_PCI_INTD : 0xff;
+ if (slot == 12)
+ return (pin == 3) ? AU1500_PCI_INTC : 0xff;
+ if (slot == 13) {
+ switch (pin) {
+ case 1: return AU1500_PCI_INTA;
+ case 2: return AU1500_PCI_INTB;
+ default: return 0xff;
+ }
+ }
+ return -1;
+}
+#endif
+
+static struct resource alchemy_pci_host_res[] = {
+ [0] = {
+ .start = AU1500_PCI_PHYS_ADDR,
+ .end = AU1500_PCI_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct alchemy_pci_platdata db1xxx_pci_pd = {
+ .board_map_irq = db1xxx_map_pci_irq,
+};
+
+static struct platform_device db1xxx_pci_host_dev = {
+ .dev.platform_data = &db1xxx_pci_pd,
+ .name = "alchemy-pci",
+ .id = 0,
+ .num_resources = ARRAY_SIZE(alchemy_pci_host_res),
+ .resource = alchemy_pci_host_res,
+};
+
+static int __init db15x0_pci_init(void)
+{
+ return platform_device_register(&db1xxx_pci_host_dev);
+}
+/* must be arch_initcall; MIPS PCI scans busses in a subsys_initcall */
+arch_initcall(db15x0_pci_init);
+#endif
+
+#ifdef CONFIG_MIPS_DB1100
+static struct resource au1100_lcd_resources[] = {
+ [0] = {
+ .start = AU1100_LCD_PHYS_ADDR,
+ .end = AU1100_LCD_PHYS_ADDR + 0x800 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = AU1100_LCD_INT,
+ .end = AU1100_LCD_INT,
+ .flags = IORESOURCE_IRQ,
+ }
+};
+
+static u64 au1100_lcd_dmamask = DMA_BIT_MASK(32);
+
+static struct platform_device au1100_lcd_device = {
+ .name = "au1100-lcd",
+ .id = 0,
+ .dev = {
+ .dma_mask = &au1100_lcd_dmamask,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
+ },
+ .num_resources = ARRAY_SIZE(au1100_lcd_resources),
+ .resource = au1100_lcd_resources,
+};
+#endif
+
static struct resource alchemy_ac97c_res[] = {
[0] = {
.start = AU1000_AC97_PHYS_ADDR,
@@ -130,29 +281,28 @@
static int __init db1xxx_dev_init(void)
{
#ifdef DB1XXX_HAS_PCMCIA
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR,
- PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_MEM_PHYS_ADDR,
- PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_IO_PHYS_ADDR,
- PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
- DB1XXX_PCMCIA_CARD0,
- DB1XXX_PCMCIA_CD0,
- /*DB1XXX_PCMCIA_STSCHG0*/0,
- 0,
- 0);
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
+ DB1XXX_PCMCIA_CARD0, DB1XXX_PCMCIA_CD0,
+ /*DB1XXX_PCMCIA_STSCHG0*/0, 0, 0);
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR + 0x004000000,
- PCMCIA_ATTR_PHYS_ADDR + 0x004400000 - 1,
- PCMCIA_MEM_PHYS_ADDR + 0x004000000,
- PCMCIA_MEM_PHYS_ADDR + 0x004400000 - 1,
- PCMCIA_IO_PHYS_ADDR + 0x004000000,
- PCMCIA_IO_PHYS_ADDR + 0x004010000 - 1,
- DB1XXX_PCMCIA_CARD1,
- DB1XXX_PCMCIA_CD1,
- /*DB1XXX_PCMCIA_STSCHG1*/0,
- 0,
- 1);
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x004000000,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x004400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x004000000,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x004400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x004000000,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x004010000 - 1,
+ DB1XXX_PCMCIA_CARD1, DB1XXX_PCMCIA_CD1,
+ /*DB1XXX_PCMCIA_STSCHG1*/0, 0, 1);
+#endif
+#ifdef CONFIG_MIPS_DB1100
+ platform_device_register(&au1100_lcd_device);
#endif
db1x_register_norflash(BOARD_FLASH_SIZE, BOARD_FLASH_WIDTH, F_SWAPPED);
diff --git a/arch/mips/alchemy/devboards/pb1100/platform.c b/arch/mips/alchemy/devboards/pb1100/platform.c
index 2c8dc29..9c57c01 100644
--- a/arch/mips/alchemy/devboards/pb1100/platform.c
+++ b/arch/mips/alchemy/devboards/pb1100/platform.c
@@ -19,31 +19,58 @@
*/
#include <linux/init.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-db1x00/bcsr.h>
#include "../platform.h"
+static struct resource au1100_lcd_resources[] = {
+ [0] = {
+ .start = AU1100_LCD_PHYS_ADDR,
+ .end = AU1100_LCD_PHYS_ADDR + 0x800 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = AU1100_LCD_INT,
+ .end = AU1100_LCD_INT,
+ .flags = IORESOURCE_IRQ,
+ }
+};
+
+static u64 au1100_lcd_dmamask = DMA_BIT_MASK(32);
+
+static struct platform_device au1100_lcd_device = {
+ .name = "au1100-lcd",
+ .id = 0,
+ .dev = {
+ .dma_mask = &au1100_lcd_dmamask,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
+ },
+ .num_resources = ARRAY_SIZE(au1100_lcd_resources),
+ .resource = au1100_lcd_resources,
+};
+
static int __init pb1100_dev_init(void)
{
int swapped;
/* PCMCIA. single socket, identical to Pb1500 */
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR,
- PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_MEM_PHYS_ADDR,
- PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_IO_PHYS_ADDR,
- PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
- AU1100_GPIO11_INT, /* card */
- AU1100_GPIO9_INT, /* insert */
- /*AU1100_GPIO10_INT*/0, /* stschg */
- 0, /* eject */
- 0); /* id */
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
+ AU1100_GPIO11_INT, AU1100_GPIO9_INT, /* card / insert */
+ /*AU1100_GPIO10_INT*/0, 0, 0); /* stschg / eject / id */
swapped = bcsr_read(BCSR_STATUS) & BCSR_STATUS_DB1000_SWAPBOOT;
db1x_register_norflash(64 * 1024 * 1024, 4, swapped);
+ platform_device_register(&au1100_lcd_device);
return 0;
}
diff --git a/arch/mips/alchemy/devboards/pb1200/platform.c b/arch/mips/alchemy/devboards/pb1200/platform.c
index 3ef2dce..54f7f7b 100644
--- a/arch/mips/alchemy/devboards/pb1200/platform.c
+++ b/arch/mips/alchemy/devboards/pb1200/platform.c
@@ -24,9 +24,11 @@
#include <linux/platform_device.h>
#include <linux/smc91x.h>
-#include <asm/mach-au1x00/au1xxx.h>
+#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1100_mmc.h>
+#include <asm/mach-au1x00/au1xxx_dbdma.h>
#include <asm/mach-db1x00/bcsr.h>
+#include <asm/mach-pb1x00/pb1200.h>
#include "../platform.h"
@@ -88,7 +90,7 @@
return (bcsr_read(BCSR_SIGSTAT) & BCSR_INT_SD1INSERT) ? 1 : 0;
}
-const struct au1xmmc_platform_data au1xmmc_platdata[2] = {
+static struct au1xmmc_platform_data pb1200mmc_platdata[2] = {
[0] = {
.set_power = pb1200mmc0_set_power,
.card_inserted = pb1200mmc0_card_inserted,
@@ -105,6 +107,79 @@
},
};
+static u64 au1xxx_mmc_dmamask = DMA_BIT_MASK(32);
+
+static struct resource au1200_mmc0_res[] = {
+ [0] = {
+ .start = AU1100_SD0_PHYS_ADDR,
+ .end = AU1100_SD0_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = AU1200_SD_INT,
+ .end = AU1200_SD_INT,
+ .flags = IORESOURCE_IRQ,
+ },
+ [2] = {
+ .start = AU1200_DSCR_CMD0_SDMS_TX0,
+ .end = AU1200_DSCR_CMD0_SDMS_TX0,
+ .flags = IORESOURCE_DMA,
+ },
+ [3] = {
+ .start = AU1200_DSCR_CMD0_SDMS_RX0,
+ .end = AU1200_DSCR_CMD0_SDMS_RX0,
+ .flags = IORESOURCE_DMA,
+ }
+};
+
+static struct platform_device pb1200_mmc0_dev = {
+ .name = "au1xxx-mmc",
+ .id = 0,
+ .dev = {
+ .dma_mask = &au1xxx_mmc_dmamask,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
+ .platform_data = &pb1200mmc_platdata[0],
+ },
+ .num_resources = ARRAY_SIZE(au1200_mmc0_res),
+ .resource = au1200_mmc0_res,
+};
+
+static struct resource au1200_mmc1_res[] = {
+ [0] = {
+ .start = AU1100_SD1_PHYS_ADDR,
+ .end = AU1100_SD1_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = AU1200_SD_INT,
+ .end = AU1200_SD_INT,
+ .flags = IORESOURCE_IRQ,
+ },
+ [2] = {
+ .start = AU1200_DSCR_CMD0_SDMS_TX1,
+ .end = AU1200_DSCR_CMD0_SDMS_TX1,
+ .flags = IORESOURCE_DMA,
+ },
+ [3] = {
+ .start = AU1200_DSCR_CMD0_SDMS_RX1,
+ .end = AU1200_DSCR_CMD0_SDMS_RX1,
+ .flags = IORESOURCE_DMA,
+ }
+};
+
+static struct platform_device pb1200_mmc1_dev = {
+ .name = "au1xxx-mmc",
+ .id = 1,
+ .dev = {
+ .dma_mask = &au1xxx_mmc_dmamask,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
+ .platform_data = &pb1200mmc_platdata[1],
+ },
+ .num_resources = ARRAY_SIZE(au1200_mmc1_res),
+ .resource = au1200_mmc1_res,
+};
+
+
static struct resource ide_resources[] = {
[0] = {
.start = IDE_PHYS_ADDR,
@@ -115,7 +190,12 @@
.start = IDE_INT,
.end = IDE_INT,
.flags = IORESOURCE_IRQ
- }
+ },
+ [2] = {
+ .start = AU1200_DSCR_CMD0_DMA_REQ1,
+ .end = AU1200_DSCR_CMD0_DMA_REQ1,
+ .flags = IORESOURCE_DMA,
+ },
};
static u64 ide_dmamask = DMA_BIT_MASK(32);
@@ -161,38 +241,94 @@
.resource = smc91c111_resources
};
+static struct resource au1200_psc0_res[] = {
+ [0] = {
+ .start = AU1550_PSC0_PHYS_ADDR,
+ .end = AU1550_PSC0_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = AU1200_PSC0_INT,
+ .end = AU1200_PSC0_INT,
+ .flags = IORESOURCE_IRQ,
+ },
+ [2] = {
+ .start = AU1200_DSCR_CMD0_PSC0_TX,
+ .end = AU1200_DSCR_CMD0_PSC0_TX,
+ .flags = IORESOURCE_DMA,
+ },
+ [3] = {
+ .start = AU1200_DSCR_CMD0_PSC0_RX,
+ .end = AU1200_DSCR_CMD0_PSC0_RX,
+ .flags = IORESOURCE_DMA,
+ },
+};
+
+static struct platform_device pb1200_i2c_dev = {
+ .name = "au1xpsc_smbus",
+ .id = 0, /* bus number */
+ .num_resources = ARRAY_SIZE(au1200_psc0_res),
+ .resource = au1200_psc0_res,
+};
+
+static struct resource au1200_lcd_res[] = {
+ [0] = {
+ .start = AU1200_LCD_PHYS_ADDR,
+ .end = AU1200_LCD_PHYS_ADDR + 0x800 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = AU1200_LCD_INT,
+ .end = AU1200_LCD_INT,
+ .flags = IORESOURCE_IRQ,
+ }
+};
+
+static u64 au1200_lcd_dmamask = DMA_BIT_MASK(32);
+
+static struct platform_device au1200_lcd_dev = {
+ .name = "au1200-lcd",
+ .id = 0,
+ .dev = {
+ .dma_mask = &au1200_lcd_dmamask,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
+ },
+ .num_resources = ARRAY_SIZE(au1200_lcd_res),
+ .resource = au1200_lcd_res,
+};
+
static struct platform_device *board_platform_devices[] __initdata = {
&ide_device,
- &smc91c111_device
+ &smc91c111_device,
+ &pb1200_i2c_dev,
+ &pb1200_mmc0_dev,
+ &pb1200_mmc1_dev,
+ &au1200_lcd_dev,
};
static int __init board_register_devices(void)
{
int swapped;
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR,
- PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_MEM_PHYS_ADDR,
- PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_IO_PHYS_ADDR,
- PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
- PB1200_PC0_INT,
- PB1200_PC0_INSERT_INT,
- /*PB1200_PC0_STSCHG_INT*/0,
- PB1200_PC0_EJECT_INT,
- 0);
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
+ PB1200_PC0_INT, PB1200_PC0_INSERT_INT,
+ /*PB1200_PC0_STSCHG_INT*/0, PB1200_PC0_EJECT_INT, 0);
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR + 0x008000000,
- PCMCIA_ATTR_PHYS_ADDR + 0x008400000 - 1,
- PCMCIA_MEM_PHYS_ADDR + 0x008000000,
- PCMCIA_MEM_PHYS_ADDR + 0x008400000 - 1,
- PCMCIA_IO_PHYS_ADDR + 0x008000000,
- PCMCIA_IO_PHYS_ADDR + 0x008010000 - 1,
- PB1200_PC1_INT,
- PB1200_PC1_INSERT_INT,
- /*PB1200_PC1_STSCHG_INT*/0,
- PB1200_PC1_EJECT_INT,
- 1);
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x008000000,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x008400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x008000000,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x008400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x008000000,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x008010000 - 1,
+ PB1200_PC1_INT, PB1200_PC1_INSERT_INT,
+ /*PB1200_PC1_STSCHG_INT*/0, PB1200_PC1_EJECT_INT, 1);
swapped = bcsr_read(BCSR_STATUS) & BCSR_STATUS_DB1200_SWAPBOOT;
db1x_register_norflash(128 * 1024 * 1024, 2, swapped);
diff --git a/arch/mips/alchemy/devboards/pb1500/board_setup.c b/arch/mips/alchemy/devboards/pb1500/board_setup.c
index 3b4fa32..37c1883 100644
--- a/arch/mips/alchemy/devboards/pb1500/board_setup.c
+++ b/arch/mips/alchemy/devboards/pb1500/board_setup.c
@@ -33,13 +33,6 @@
#include <prom.h>
-
-char irq_tab_alchemy[][5] __initdata = {
- [12] = { -1, AU1500_PCI_INTA, 0xff, 0xff, 0xff }, /* IDSEL 12 - HPT370 */
- [13] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTB, AU1500_PCI_INTC, AU1500_PCI_INTD }, /* IDSEL 13 - PCI slot */
-};
-
-
const char *get_system_type(void)
{
return "Alchemy Pb1500";
@@ -101,20 +94,18 @@
#endif /* defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) */
#ifdef CONFIG_PCI
- /* Setup PCI bus controller */
- au_writel(0, Au1500_PCI_CMEM);
- au_writel(0x00003fff, Au1500_CFG_BASE);
-#if defined(__MIPSEB__)
- au_writel(0xf | (2 << 6) | (1 << 4), Au1500_PCI_CFG);
-#else
- au_writel(0xf, Au1500_PCI_CFG);
-#endif
- au_writel(0xf0000000, Au1500_PCI_MWMASK_DEV);
- au_writel(0, Au1500_PCI_MWBASE_REV_CCL);
- au_writel(0x02a00356, Au1500_PCI_STATCMD);
- au_writel(0x00003c04, Au1500_PCI_HDRTYPE);
- au_writel(0x00000008, Au1500_PCI_MBAR);
- au_sync();
+ {
+ void __iomem *base =
+ (void __iomem *)KSEG1ADDR(AU1500_PCI_PHYS_ADDR);
+ /* Setup PCI bus controller */
+ __raw_writel(0x00003fff, base + PCI_REG_CMEM);
+ __raw_writel(0xf0000000, base + PCI_REG_MWMASK_DEV);
+ __raw_writel(0, base + PCI_REG_MWBASE_REV_CCL);
+ __raw_writel(0x02a00356, base + PCI_REG_STATCMD);
+ __raw_writel(0x00003c04, base + PCI_REG_PARAM);
+ __raw_writel(0x00000008, base + PCI_REG_MBAR);
+ wmb();
+ }
#endif
/* Enable sys bus clock divider when IDLE state or no bus activity. */
diff --git a/arch/mips/alchemy/devboards/pb1500/platform.c b/arch/mips/alchemy/devboards/pb1500/platform.c
index d443bc7..1e52a01 100644
--- a/arch/mips/alchemy/devboards/pb1500/platform.c
+++ b/arch/mips/alchemy/devboards/pb1500/platform.c
@@ -18,32 +18,77 @@
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
+#include <linux/dma-mapping.h>
#include <linux/init.h>
+#include <linux/platform_device.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-db1x00/bcsr.h>
#include "../platform.h"
+static int pb1500_map_pci_irq(const struct pci_dev *d, u8 slot, u8 pin)
+{
+ if ((slot < 12) || (slot > 13) || pin == 0)
+ return -1;
+ if (slot == 12)
+ return (pin == 1) ? AU1500_PCI_INTA : 0xff;
+ if (slot == 13) {
+ switch (pin) {
+ case 1: return AU1500_PCI_INTA;
+ case 2: return AU1500_PCI_INTB;
+ case 3: return AU1500_PCI_INTC;
+ case 4: return AU1500_PCI_INTD;
+ }
+ }
+ return -1;
+}
+
+static struct resource alchemy_pci_host_res[] = {
+ [0] = {
+ .start = AU1500_PCI_PHYS_ADDR,
+ .end = AU1500_PCI_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct alchemy_pci_platdata pb1500_pci_pd = {
+ .board_map_irq = pb1500_map_pci_irq,
+ .pci_cfg_set = PCI_CONFIG_AEN | PCI_CONFIG_R2H | PCI_CONFIG_R1H |
+ PCI_CONFIG_CH |
+#if defined(__MIPSEB__)
+ PCI_CONFIG_SIC_HWA_DAT | PCI_CONFIG_SM,
+#else
+ 0,
+#endif
+};
+
+static struct platform_device pb1500_pci_host = {
+ .dev.platform_data = &pb1500_pci_pd,
+ .name = "alchemy-pci",
+ .id = 0,
+ .num_resources = ARRAY_SIZE(alchemy_pci_host_res),
+ .resource = alchemy_pci_host_res,
+};
+
static int __init pb1500_dev_init(void)
{
int swapped;
- /* PCMCIA. single socket, identical to Pb1500 */
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR,
- PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_MEM_PHYS_ADDR,
- PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_IO_PHYS_ADDR,
- PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
- AU1500_GPIO11_INT, /* card */
- AU1500_GPIO9_INT, /* insert */
- /*AU1500_GPIO10_INT*/0, /* stschg */
- 0, /* eject */
- 0); /* id */
+ /* PCMCIA. single socket, identical to Pb1100 */
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
+ AU1500_GPIO11_INT, AU1500_GPIO9_INT, /* card / insert */
+ /*AU1500_GPIO10_INT*/0, 0, 0); /* stschg / eject / id */
swapped = bcsr_read(BCSR_STATUS) & BCSR_STATUS_DB1000_SWAPBOOT;
db1x_register_norflash(64 * 1024 * 1024, 4, swapped);
+ platform_device_register(&pb1500_pci_host);
return 0;
}
-device_initcall(pb1500_dev_init);
+arch_initcall(pb1500_dev_init);
diff --git a/arch/mips/alchemy/devboards/pb1550/board_setup.c b/arch/mips/alchemy/devboards/pb1550/board_setup.c
index b790213..0f62d1e 100644
--- a/arch/mips/alchemy/devboards/pb1550/board_setup.c
+++ b/arch/mips/alchemy/devboards/pb1550/board_setup.c
@@ -37,12 +37,6 @@
#include <prom.h>
-
-char irq_tab_alchemy[][5] __initdata = {
- [12] = { -1, AU1550_PCI_INTB, AU1550_PCI_INTC, AU1550_PCI_INTD, AU1550_PCI_INTA }, /* IDSEL 12 - PCI slot 2 (left) */
- [13] = { -1, AU1550_PCI_INTA, AU1550_PCI_INTB, AU1550_PCI_INTC, AU1550_PCI_INTD }, /* IDSEL 13 - PCI slot 1 (right) */
-};
-
const char *get_system_type(void)
{
return "Alchemy Pb1550";
diff --git a/arch/mips/alchemy/devboards/pb1550/platform.c b/arch/mips/alchemy/devboards/pb1550/platform.c
index d7150d0..a4604b8 100644
--- a/arch/mips/alchemy/devboards/pb1550/platform.c
+++ b/arch/mips/alchemy/devboards/pb1550/platform.c
@@ -18,14 +18,89 @@
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
+#include <linux/dma-mapping.h>
#include <linux/init.h>
-
+#include <linux/platform_device.h>
#include <asm/mach-au1x00/au1000.h>
+#include <asm/mach-au1x00/au1xxx_dbdma.h>
#include <asm/mach-pb1x00/pb1550.h>
#include <asm/mach-db1x00/bcsr.h>
#include "../platform.h"
+static int pb1550_map_pci_irq(const struct pci_dev *d, u8 slot, u8 pin)
+{
+ if ((slot < 12) || (slot > 13) || pin == 0)
+ return -1;
+ if (slot == 12) {
+ switch (pin) {
+ case 1: return AU1500_PCI_INTB;
+ case 2: return AU1500_PCI_INTC;
+ case 3: return AU1500_PCI_INTD;
+ case 4: return AU1500_PCI_INTA;
+ }
+ }
+ if (slot == 13) {
+ switch (pin) {
+ case 1: return AU1500_PCI_INTA;
+ case 2: return AU1500_PCI_INTB;
+ case 3: return AU1500_PCI_INTC;
+ case 4: return AU1500_PCI_INTD;
+ }
+ }
+ return -1;
+}
+
+static struct resource alchemy_pci_host_res[] = {
+ [0] = {
+ .start = AU1500_PCI_PHYS_ADDR,
+ .end = AU1500_PCI_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct alchemy_pci_platdata pb1550_pci_pd = {
+ .board_map_irq = pb1550_map_pci_irq,
+};
+
+static struct platform_device pb1550_pci_host = {
+ .dev.platform_data = &pb1550_pci_pd,
+ .name = "alchemy-pci",
+ .id = 0,
+ .num_resources = ARRAY_SIZE(alchemy_pci_host_res),
+ .resource = alchemy_pci_host_res,
+};
+
+static struct resource au1550_psc2_res[] = {
+ [0] = {
+ .start = AU1550_PSC2_PHYS_ADDR,
+ .end = AU1550_PSC2_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = AU1550_PSC2_INT,
+ .end = AU1550_PSC2_INT,
+ .flags = IORESOURCE_IRQ,
+ },
+ [2] = {
+ .start = AU1550_DSCR_CMD0_PSC2_TX,
+ .end = AU1550_DSCR_CMD0_PSC2_TX,
+ .flags = IORESOURCE_DMA,
+ },
+ [3] = {
+ .start = AU1550_DSCR_CMD0_PSC2_RX,
+ .end = AU1550_DSCR_CMD0_PSC2_RX,
+ .flags = IORESOURCE_DMA,
+ },
+};
+
+static struct platform_device pb1550_i2c_dev = {
+ .name = "au1xpsc_smbus",
+ .id = 0, /* bus number */
+ .num_resources = ARRAY_SIZE(au1550_psc2_res),
+ .resource = au1550_psc2_res,
+};
+
static int __init pb1550_dev_init(void)
{
int swapped;
@@ -37,33 +112,29 @@
* drivers are used to shared irqs and b) statuschange isn't really use-
* ful anyway.
*/
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR,
- PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_MEM_PHYS_ADDR,
- PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
- PCMCIA_IO_PHYS_ADDR,
- PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
- AU1550_GPIO201_205_INT,
- AU1550_GPIO0_INT,
- 0,
- 0,
- 0);
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1,
+ AU1550_GPIO201_205_INT, AU1550_GPIO0_INT, 0, 0, 0);
- db1x_register_pcmcia_socket(PCMCIA_ATTR_PHYS_ADDR + 0x008000000,
- PCMCIA_ATTR_PHYS_ADDR + 0x008400000 - 1,
- PCMCIA_MEM_PHYS_ADDR + 0x008000000,
- PCMCIA_MEM_PHYS_ADDR + 0x008400000 - 1,
- PCMCIA_IO_PHYS_ADDR + 0x008000000,
- PCMCIA_IO_PHYS_ADDR + 0x008010000 - 1,
- AU1550_GPIO201_205_INT,
- AU1550_GPIO1_INT,
- 0,
- 0,
- 1);
+ db1x_register_pcmcia_socket(
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x008000000,
+ AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x008400000 - 1,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x008000000,
+ AU1000_PCMCIA_MEM_PHYS_ADDR + 0x008400000 - 1,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x008000000,
+ AU1000_PCMCIA_IO_PHYS_ADDR + 0x008010000 - 1,
+ AU1550_GPIO201_205_INT, AU1550_GPIO1_INT, 0, 0, 1);
swapped = bcsr_read(BCSR_STATUS) & BCSR_STATUS_PB1550_SWAPBOOT;
db1x_register_norflash(128 * 1024 * 1024, 4, swapped);
+ platform_device_register(&pb1550_pci_host);
+ platform_device_register(&pb1550_i2c_dev);
return 0;
}
-device_initcall(pb1550_dev_init);
+arch_initcall(pb1550_dev_init);
diff --git a/arch/mips/alchemy/gpr/board_setup.c b/arch/mips/alchemy/gpr/board_setup.c
index 5f8f069..dea45c7 100644
--- a/arch/mips/alchemy/gpr/board_setup.c
+++ b/arch/mips/alchemy/gpr/board_setup.c
@@ -36,10 +36,6 @@
#include <prom.h>
-char irq_tab_alchemy[][5] __initdata = {
- [0] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTB, 0xff, 0xff },
-};
-
static void gpr_reset(char *c)
{
/* switch System-LED to orange (red# and green# on) */
@@ -76,12 +72,4 @@
/* Take away Reset of UMTS-card */
alchemy_gpio_direction_output(215, 1);
-
-#ifdef CONFIG_PCI
-#if defined(__MIPSEB__)
- au_writel(0xf | (2 << 6) | (1 << 4), Au1500_PCI_CFG);
-#else
- au_writel(0xf, Au1500_PCI_CFG);
-#endif
-#endif
}
diff --git a/arch/mips/alchemy/gpr/platform.c b/arch/mips/alchemy/gpr/platform.c
index 14b4662..982ce85 100644
--- a/arch/mips/alchemy/gpr/platform.c
+++ b/arch/mips/alchemy/gpr/platform.c
@@ -167,6 +167,45 @@
}
};
+
+
+static struct resource alchemy_pci_host_res[] = {
+ [0] = {
+ .start = AU1500_PCI_PHYS_ADDR,
+ .end = AU1500_PCI_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static int gpr_map_pci_irq(const struct pci_dev *d, u8 slot, u8 pin)
+{
+ if ((slot == 0) && (pin == 1))
+ return AU1550_PCI_INTA;
+ else if ((slot == 0) && (pin == 2))
+ return AU1550_PCI_INTB;
+
+ return -1;
+}
+
+static struct alchemy_pci_platdata gpr_pci_pd = {
+ .board_map_irq = gpr_map_pci_irq,
+ .pci_cfg_set = PCI_CONFIG_AEN | PCI_CONFIG_R2H | PCI_CONFIG_R1H |
+ PCI_CONFIG_CH |
+#if defined(__MIPSEB__)
+ PCI_CONFIG_SIC_HWA_DAT | PCI_CONFIG_SM,
+#else
+ 0,
+#endif
+};
+
+static struct platform_device gpr_pci_host_dev = {
+ .dev.platform_data = &gpr_pci_pd,
+ .name = "alchemy-pci",
+ .id = 0,
+ .num_resources = ARRAY_SIZE(alchemy_pci_host_res),
+ .resource = alchemy_pci_host_res,
+};
+
static struct platform_device *gpr_devices[] __initdata = {
&gpr_wdt_device,
&gpr_mtd_device,
@@ -174,6 +213,14 @@
&gpr_led_devices,
};
+static int __init gpr_pci_init(void)
+{
+ return platform_device_register(&gpr_pci_host_dev);
+}
+/* must be arch_initcall; MIPS PCI scans busses in a subsys_initcall */
+arch_initcall(gpr_pci_init);
+
+
static int __init gpr_dev_init(void)
{
i2c_register_board_info(0, gpr_i2c_info, ARRAY_SIZE(gpr_i2c_info));
diff --git a/arch/mips/alchemy/mtx-1/board_setup.c b/arch/mips/alchemy/mtx-1/board_setup.c
index 3ae984c..851a5ab 100644
--- a/arch/mips/alchemy/mtx-1/board_setup.c
+++ b/arch/mips/alchemy/mtx-1/board_setup.c
@@ -38,20 +38,6 @@
#include <prom.h>
-char irq_tab_alchemy[][5] __initdata = {
- [0] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTA, 0xff, 0xff }, /* IDSEL 00 - AdapterA-Slot0 (top) */
- [1] = { -1, AU1500_PCI_INTB, AU1500_PCI_INTA, 0xff, 0xff }, /* IDSEL 01 - AdapterA-Slot1 (bottom) */
- [2] = { -1, AU1500_PCI_INTC, AU1500_PCI_INTD, 0xff, 0xff }, /* IDSEL 02 - AdapterB-Slot0 (top) */
- [3] = { -1, AU1500_PCI_INTD, AU1500_PCI_INTC, 0xff, 0xff }, /* IDSEL 03 - AdapterB-Slot1 (bottom) */
- [4] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTB, 0xff, 0xff }, /* IDSEL 04 - AdapterC-Slot0 (top) */
- [5] = { -1, AU1500_PCI_INTB, AU1500_PCI_INTA, 0xff, 0xff }, /* IDSEL 05 - AdapterC-Slot1 (bottom) */
- [6] = { -1, AU1500_PCI_INTC, AU1500_PCI_INTD, 0xff, 0xff }, /* IDSEL 06 - AdapterD-Slot0 (top) */
- [7] = { -1, AU1500_PCI_INTD, AU1500_PCI_INTC, 0xff, 0xff }, /* IDSEL 07 - AdapterD-Slot1 (bottom) */
-};
-
-extern int (*board_pci_idsel)(unsigned int devsel, int assert);
-int mtx1_pci_idsel(unsigned int devsel, int assert);
-
static void mtx1_reset(char *c)
{
/* Jump to the reset vector */
@@ -74,15 +60,6 @@
alchemy_gpio_direction_output(204, 0);
#endif /* defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) */
-#ifdef CONFIG_PCI
-#if defined(__MIPSEB__)
- au_writel(0xf | (2 << 6) | (1 << 4), Au1500_PCI_CFG);
-#else
- au_writel(0xf, Au1500_PCI_CFG);
-#endif
- board_pci_idsel = mtx1_pci_idsel;
-#endif
-
/* Initialize sys_pinfunc */
au_writel(SYS_PF_NI2, SYS_PINFUNC);
@@ -104,23 +81,6 @@
printk(KERN_INFO "4G Systems MTX-1 Board\n");
}
-int
-mtx1_pci_idsel(unsigned int devsel, int assert)
-{
- /* This function is only necessary to support a proprietary Cardbus
- * adapter on the mtx-1 "singleboard" variant. It triggers a custom
- * logic chip connected to EXT_IO3 (GPIO1) to suppress IDSEL signals.
- */
- if (assert && devsel != 0)
- /* Suppress signal to Cardbus */
- alchemy_gpio_set_value(1, 0); /* set EXT_IO3 OFF */
- else
- alchemy_gpio_set_value(1, 1); /* set EXT_IO3 ON */
-
- udelay(1);
- return 1;
-}
-
static int __init mtx1_init_irq(void)
{
irq_set_irq_type(AU1500_GPIO204_INT, IRQF_TRIGGER_HIGH);
diff --git a/arch/mips/alchemy/mtx-1/platform.c b/arch/mips/alchemy/mtx-1/platform.c
index 55628e3..cc47b68 100644
--- a/arch/mips/alchemy/mtx-1/platform.c
+++ b/arch/mips/alchemy/mtx-1/platform.c
@@ -135,7 +135,69 @@
.resource = &mtx1_mtd_resource,
};
+static struct resource alchemy_pci_host_res[] = {
+ [0] = {
+ .start = AU1500_PCI_PHYS_ADDR,
+ .end = AU1500_PCI_PHYS_ADDR + 0xfff,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static int mtx1_pci_idsel(unsigned int devsel, int assert)
+{
+ /* This function is only necessary to support a proprietary Cardbus
+ * adapter on the mtx-1 "singleboard" variant. It triggers a custom
+ * logic chip connected to EXT_IO3 (GPIO1) to suppress IDSEL signals.
+ */
+ if (assert && devsel != 0)
+ /* Suppress signal to Cardbus */
+ alchemy_gpio_set_value(1, 0); /* set EXT_IO3 OFF */
+ else
+ alchemy_gpio_set_value(1, 1); /* set EXT_IO3 ON */
+
+ udelay(1);
+ return 1;
+}
+
+static const char mtx1_irqtab[][5] = {
+ [0] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTA, 0xff, 0xff }, /* IDSEL 00 - AdapterA-Slot0 (top) */
+ [1] = { -1, AU1500_PCI_INTB, AU1500_PCI_INTA, 0xff, 0xff }, /* IDSEL 01 - AdapterA-Slot1 (bottom) */
+ [2] = { -1, AU1500_PCI_INTC, AU1500_PCI_INTD, 0xff, 0xff }, /* IDSEL 02 - AdapterB-Slot0 (top) */
+ [3] = { -1, AU1500_PCI_INTD, AU1500_PCI_INTC, 0xff, 0xff }, /* IDSEL 03 - AdapterB-Slot1 (bottom) */
+ [4] = { -1, AU1500_PCI_INTA, AU1500_PCI_INTB, 0xff, 0xff }, /* IDSEL 04 - AdapterC-Slot0 (top) */
+ [5] = { -1, AU1500_PCI_INTB, AU1500_PCI_INTA, 0xff, 0xff }, /* IDSEL 05 - AdapterC-Slot1 (bottom) */
+ [6] = { -1, AU1500_PCI_INTC, AU1500_PCI_INTD, 0xff, 0xff }, /* IDSEL 06 - AdapterD-Slot0 (top) */
+ [7] = { -1, AU1500_PCI_INTD, AU1500_PCI_INTC, 0xff, 0xff }, /* IDSEL 07 - AdapterD-Slot1 (bottom) */
+};
+
+static int mtx1_map_pci_irq(const struct pci_dev *d, u8 slot, u8 pin)
+{
+ return mtx1_irqtab[slot][pin];
+}
+
+static struct alchemy_pci_platdata mtx1_pci_pd = {
+ .board_map_irq = mtx1_map_pci_irq,
+ .board_pci_idsel = mtx1_pci_idsel,
+ .pci_cfg_set = PCI_CONFIG_AEN | PCI_CONFIG_R2H | PCI_CONFIG_R1H |
+ PCI_CONFIG_CH |
+#if defined(__MIPSEB__)
+ PCI_CONFIG_SIC_HWA_DAT | PCI_CONFIG_SM,
+#else
+ 0,
+#endif
+};
+
+static struct platform_device mtx1_pci_host = {
+ .dev.platform_data = &mtx1_pci_pd,
+ .name = "alchemy-pci",
+ .id = 0,
+ .num_resources = ARRAY_SIZE(alchemy_pci_host_res),
+ .resource = alchemy_pci_host_res,
+};
+
+
static struct __initdata platform_device * mtx1_devs[] = {
+ &mtx1_pci_host,
&mtx1_gpio_leds,
&mtx1_wdt,
&mtx1_button,
diff --git a/arch/mips/alchemy/xxs1500/board_setup.c b/arch/mips/alchemy/xxs1500/board_setup.c
index 81e57fa..3fa83f7 100644
--- a/arch/mips/alchemy/xxs1500/board_setup.c
+++ b/arch/mips/alchemy/xxs1500/board_setup.c
@@ -70,14 +70,6 @@
/* Enable DTR (MCR bit 0) = USB power up */
__raw_writel(1, (void __iomem *)KSEG1ADDR(AU1000_UART3_PHYS_ADDR + 0x18));
wmb();
-
-#ifdef CONFIG_PCI
-#if defined(__MIPSEB__)
- au_writel(0xf | (2 << 6) | (1 << 4), Au1500_PCI_CFG);
-#else
- au_writel(0xf, Au1500_PCI_CFG);
-#endif
-#endif
}
static int __init xxs1500_init_irq(void)
diff --git a/arch/mips/alchemy/xxs1500/platform.c b/arch/mips/alchemy/xxs1500/platform.c
index e87c45c..06a3a45 100644
--- a/arch/mips/alchemy/xxs1500/platform.c
+++ b/arch/mips/alchemy/xxs1500/platform.c
@@ -27,20 +27,20 @@
{
.name = "pcmcia-io",
.flags = IORESOURCE_MEM,
- .start = PCMCIA_IO_PHYS_ADDR,
- .end = PCMCIA_IO_PHYS_ADDR + 0x000400000 - 1,
+ .start = AU1000_PCMCIA_IO_PHYS_ADDR,
+ .end = AU1000_PCMCIA_IO_PHYS_ADDR + 0x000400000 - 1,
},
{
.name = "pcmcia-attr",
.flags = IORESOURCE_MEM,
- .start = PCMCIA_ATTR_PHYS_ADDR,
- .end = PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
+ .start = AU1000_PCMCIA_ATTR_PHYS_ADDR,
+ .end = AU1000_PCMCIA_ATTR_PHYS_ADDR + 0x000400000 - 1,
},
{
.name = "pcmcia-mem",
.flags = IORESOURCE_MEM,
- .start = PCMCIA_MEM_PHYS_ADDR,
- .end = PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
+ .start = AU1000_PCMCIA_MEM_PHYS_ADDR,
+ .end = AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1,
},
};
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index 40bb9fd..69468de 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -114,4 +114,28 @@
extern void *kmap_coherent(struct page *page, unsigned long addr);
extern void kunmap_coherent(void);
+#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+static inline void flush_kernel_dcache_page(struct page *page)
+{
+ BUG_ON(cpu_has_dc_aliases && PageHighMem(page));
+}
+
+/*
+ * For now flush_kernel_vmap_range and invalidate_kernel_vmap_range both do a
+ * cache writeback and invalidate operation.
+ */
+extern void (*__flush_kernel_vmap_range)(unsigned long vaddr, int size);
+
+static inline void flush_kernel_vmap_range(void *vaddr, int size)
+{
+ if (cpu_has_dc_aliases)
+ __flush_kernel_vmap_range((unsigned long) vaddr, size);
+}
+
+static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
+{
+ if (cpu_has_dc_aliases)
+ __flush_kernel_vmap_range((unsigned long) vaddr, size);
+}
+
#endif /* _ASM_CACHEFLUSH_H */
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 5f95a4b..2f7f418 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -135,6 +135,9 @@
#define PRID_IMP_CAVIUM_CN50XX 0x0600
#define PRID_IMP_CAVIUM_CN52XX 0x0700
#define PRID_IMP_CAVIUM_CN63XX 0x9000
+#define PRID_IMP_CAVIUM_CN68XX 0x9100
+#define PRID_IMP_CAVIUM_CN66XX 0x9200
+#define PRID_IMP_CAVIUM_CN61XX 0x9300
/*
* These are the PRID's for when 23:16 == PRID_COMP_INGENIC
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index b04e4de..a58f229 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -329,14 +329,10 @@
"dsrl32 %L0, %L0, 0" "\n\t" \
"dsll32 %M0, %M0, 0" "\n\t" \
"or %L0, %L0, %M0" "\n\t" \
- ".set push" "\n\t" \
- ".set noreorder" "\n\t" \
- ".set nomacro" "\n\t" \
"sd %L0, %2" "\n\t" \
- ".set pop" "\n\t" \
".set mips0" "\n" \
: "=r" (__tmp) \
- : "0" (__val), "R" (*__mem)); \
+ : "0" (__val), "m" (*__mem)); \
if (irq) \
local_irq_restore(__flags); \
} else \
@@ -359,16 +355,12 @@
local_irq_save(__flags); \
__asm__ __volatile__( \
".set mips3" "\t\t# __readq" "\n\t" \
- ".set push" "\n\t" \
- ".set noreorder" "\n\t" \
- ".set nomacro" "\n\t" \
"ld %L0, %1" "\n\t" \
- ".set pop" "\n\t" \
"dsra32 %M0, %L0, 0" "\n\t" \
"sll %L0, %L0, 0" "\n\t" \
".set mips0" "\n" \
: "=r" (__val) \
- : "R" (*__mem)); \
+ : "m" (*__mem)); \
if (irq) \
local_irq_restore(__flags); \
} else { \
diff --git a/arch/mips/include/asm/mach-au1x00/au1000.h b/arch/mips/include/asm/mach-au1x00/au1000.h
index f260ebe..de24ec57 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000.h
@@ -245,6 +245,23 @@
void alchemy_sleep_au1550(void);
void au_sleep(void);
+/* USB: drivers/usb/host/alchemy-common.c */
+enum alchemy_usb_block {
+ ALCHEMY_USB_OHCI0,
+ ALCHEMY_USB_UDC0,
+ ALCHEMY_USB_EHCI0,
+ ALCHEMY_USB_OTG0,
+};
+int alchemy_usb_control(int block, int enable);
+
+/* PCI controller platform data */
+struct alchemy_pci_platdata {
+ int (*board_map_irq)(const struct pci_dev *d, u8 slot, u8 pin);
+ int (*board_pci_idsel)(unsigned int devsel, int assert);
+ /* bits to set/clear in PCI_CONFIG register */
+ unsigned long pci_cfg_set;
+ unsigned long pci_cfg_clr;
+};
/* SOC Interrupt numbers */
@@ -575,38 +592,95 @@
#endif /* !defined (_LANGUAGE_ASSEMBLY) */
/*
- * SDRAM register offsets
+ * Physical base addresses for integrated peripherals
+ * 0..au1000 1..au1500 2..au1100 3..au1550 4..au1200
*/
-#if defined(CONFIG_SOC_AU1000) || defined(CONFIG_SOC_AU1500) || \
- defined(CONFIG_SOC_AU1100)
-#define MEM_SDMODE0 0x0000
-#define MEM_SDMODE1 0x0004
-#define MEM_SDMODE2 0x0008
-#define MEM_SDADDR0 0x000C
-#define MEM_SDADDR1 0x0010
-#define MEM_SDADDR2 0x0014
-#define MEM_SDREFCFG 0x0018
-#define MEM_SDPRECMD 0x001C
-#define MEM_SDAUTOREF 0x0020
-#define MEM_SDWRMD0 0x0024
-#define MEM_SDWRMD1 0x0028
-#define MEM_SDWRMD2 0x002C
-#define MEM_SDSLEEP 0x0030
-#define MEM_SDSMCKE 0x0034
-/*
- * MEM_SDMODE register content definitions
- */
+#define AU1000_AC97_PHYS_ADDR 0x10000000 /* 012 */
+#define AU1000_USB_OHCI_PHYS_ADDR 0x10100000 /* 012 */
+#define AU1000_USB_UDC_PHYS_ADDR 0x10200000 /* 0123 */
+#define AU1000_IRDA_PHYS_ADDR 0x10300000 /* 02 */
+#define AU1200_AES_PHYS_ADDR 0x10300000 /* 4 */
+#define AU1000_IC0_PHYS_ADDR 0x10400000 /* 01234 */
+#define AU1000_MAC0_PHYS_ADDR 0x10500000 /* 023 */
+#define AU1000_MAC1_PHYS_ADDR 0x10510000 /* 023 */
+#define AU1000_MACEN_PHYS_ADDR 0x10520000 /* 023 */
+#define AU1100_SD0_PHYS_ADDR 0x10600000 /* 24 */
+#define AU1100_SD1_PHYS_ADDR 0x10680000 /* 24 */
+#define AU1550_PSC2_PHYS_ADDR 0x10A00000 /* 3 */
+#define AU1550_PSC3_PHYS_ADDR 0x10B00000 /* 3 */
+#define AU1000_I2S_PHYS_ADDR 0x11000000 /* 02 */
+#define AU1500_MAC0_PHYS_ADDR 0x11500000 /* 1 */
+#define AU1500_MAC1_PHYS_ADDR 0x11510000 /* 1 */
+#define AU1500_MACEN_PHYS_ADDR 0x11520000 /* 1 */
+#define AU1000_UART0_PHYS_ADDR 0x11100000 /* 01234 */
+#define AU1200_SWCNT_PHYS_ADDR 0x1110010C /* 4 */
+#define AU1000_UART1_PHYS_ADDR 0x11200000 /* 0234 */
+#define AU1000_UART2_PHYS_ADDR 0x11300000 /* 0 */
+#define AU1000_UART3_PHYS_ADDR 0x11400000 /* 0123 */
+#define AU1000_SSI0_PHYS_ADDR 0x11600000 /* 02 */
+#define AU1000_SSI1_PHYS_ADDR 0x11680000 /* 02 */
+#define AU1500_GPIO2_PHYS_ADDR 0x11700000 /* 1234 */
+#define AU1000_IC1_PHYS_ADDR 0x11800000 /* 01234 */
+#define AU1000_SYS_PHYS_ADDR 0x11900000 /* 01234 */
+#define AU1550_PSC0_PHYS_ADDR 0x11A00000 /* 34 */
+#define AU1550_PSC1_PHYS_ADDR 0x11B00000 /* 34 */
+#define AU1000_MEM_PHYS_ADDR 0x14000000 /* 01234 */
+#define AU1000_STATIC_MEM_PHYS_ADDR 0x14001000 /* 01234 */
+#define AU1000_DMA_PHYS_ADDR 0x14002000 /* 012 */
+#define AU1550_DBDMA_PHYS_ADDR 0x14002000 /* 34 */
+#define AU1550_DBDMA_CONF_PHYS_ADDR 0x14003000 /* 34 */
+#define AU1000_MACDMA0_PHYS_ADDR 0x14004000 /* 0123 */
+#define AU1000_MACDMA1_PHYS_ADDR 0x14004200 /* 0123 */
+#define AU1200_CIM_PHYS_ADDR 0x14004000 /* 4 */
+#define AU1500_PCI_PHYS_ADDR 0x14005000 /* 13 */
+#define AU1550_PE_PHYS_ADDR 0x14008000 /* 3 */
+#define AU1200_MAEBE_PHYS_ADDR 0x14010000 /* 4 */
+#define AU1200_MAEFE_PHYS_ADDR 0x14012000 /* 4 */
+#define AU1550_USB_OHCI_PHYS_ADDR 0x14020000 /* 3 */
+#define AU1200_USB_CTL_PHYS_ADDR 0x14020000 /* 4 */
+#define AU1200_USB_OTG_PHYS_ADDR 0x14020020 /* 4 */
+#define AU1200_USB_OHCI_PHYS_ADDR 0x14020100 /* 4 */
+#define AU1200_USB_EHCI_PHYS_ADDR 0x14020200 /* 4 */
+#define AU1200_USB_UDC_PHYS_ADDR 0x14022000 /* 4 */
+#define AU1100_LCD_PHYS_ADDR 0x15000000 /* 2 */
+#define AU1200_LCD_PHYS_ADDR 0x15000000 /* 4 */
+#define AU1500_PCI_MEM_PHYS_ADDR 0x400000000ULL /* 13 */
+#define AU1500_PCI_IO_PHYS_ADDR 0x500000000ULL /* 13 */
+#define AU1500_PCI_CONFIG0_PHYS_ADDR 0x600000000ULL /* 13 */
+#define AU1500_PCI_CONFIG1_PHYS_ADDR 0x680000000ULL /* 13 */
+#define AU1000_PCMCIA_IO_PHYS_ADDR 0xF00000000ULL /* 01234 */
+#define AU1000_PCMCIA_ATTR_PHYS_ADDR 0xF40000000ULL /* 01234 */
+#define AU1000_PCMCIA_MEM_PHYS_ADDR 0xF80000000ULL /* 01234 */
+
+
+/* Au1000 SDRAM memory controller register offsets */
+#define AU1000_MEM_SDMODE0 0x0000
+#define AU1000_MEM_SDMODE1 0x0004
+#define AU1000_MEM_SDMODE2 0x0008
+#define AU1000_MEM_SDADDR0 0x000C
+#define AU1000_MEM_SDADDR1 0x0010
+#define AU1000_MEM_SDADDR2 0x0014
+#define AU1000_MEM_SDREFCFG 0x0018
+#define AU1000_MEM_SDPRECMD 0x001C
+#define AU1000_MEM_SDAUTOREF 0x0020
+#define AU1000_MEM_SDWRMD0 0x0024
+#define AU1000_MEM_SDWRMD1 0x0028
+#define AU1000_MEM_SDWRMD2 0x002C
+#define AU1000_MEM_SDSLEEP 0x0030
+#define AU1000_MEM_SDSMCKE 0x0034
+
+/* MEM_SDMODE register content definitions */
#define MEM_SDMODE_F (1 << 22)
#define MEM_SDMODE_SR (1 << 21)
#define MEM_SDMODE_BS (1 << 20)
#define MEM_SDMODE_RS (3 << 18)
#define MEM_SDMODE_CS (7 << 15)
-#define MEM_SDMODE_TRAS (15 << 11)
-#define MEM_SDMODE_TMRD (3 << 9)
+#define MEM_SDMODE_TRAS (15 << 11)
+#define MEM_SDMODE_TMRD (3 << 9)
#define MEM_SDMODE_TWR (3 << 7)
#define MEM_SDMODE_TRP (3 << 5)
-#define MEM_SDMODE_TRCD (3 << 3)
+#define MEM_SDMODE_TRCD (3 << 3)
#define MEM_SDMODE_TCL (7 << 0)
#define MEM_SDMODE_BS_2Bank (0 << 20)
@@ -628,173 +702,43 @@
#define MEM_SDMODE_TRCD_N(N) ((N) << 3)
#define MEM_SDMODE_TCL_N(N) ((N) << 0)
-/*
- * MEM_SDADDR register contents definitions
- */
+/* MEM_SDADDR register contents definitions */
#define MEM_SDADDR_E (1 << 20)
-#define MEM_SDADDR_CSBA (0x03FF << 10)
+#define MEM_SDADDR_CSBA (0x03FF << 10)
#define MEM_SDADDR_CSMASK (0x03FF << 0)
#define MEM_SDADDR_CSBA_N(N) ((N) & (0x03FF << 22) >> 12)
#define MEM_SDADDR_CSMASK_N(N) ((N)&(0x03FF << 22) >> 22)
-/*
- * MEM_SDREFCFG register content definitions
- */
+/* MEM_SDREFCFG register content definitions */
#define MEM_SDREFCFG_TRC (15 << 28)
#define MEM_SDREFCFG_TRPM (3 << 26)
#define MEM_SDREFCFG_E (1 << 25)
-#define MEM_SDREFCFG_RE (0x1ffffff << 0)
+#define MEM_SDREFCFG_RE (0x1ffffff << 0)
#define MEM_SDREFCFG_TRC_N(N) ((N) << MEM_SDREFCFG_TRC)
#define MEM_SDREFCFG_TRPM_N(N) ((N) << MEM_SDREFCFG_TRPM)
#define MEM_SDREFCFG_REF_N(N) (N)
-#endif
-/***********************************************************************/
-
-/*
- * Au1550 SDRAM Register Offsets
- */
-
-/***********************************************************************/
-
-#if defined(CONFIG_SOC_AU1550) || defined(CONFIG_SOC_AU1200)
-#define MEM_SDMODE0 0x0800
-#define MEM_SDMODE1 0x0808
-#define MEM_SDMODE2 0x0810
-#define MEM_SDADDR0 0x0820
-#define MEM_SDADDR1 0x0828
-#define MEM_SDADDR2 0x0830
-#define MEM_SDCONFIGA 0x0840
-#define MEM_SDCONFIGB 0x0848
-#define MEM_SDSTAT 0x0850
-#define MEM_SDERRADDR 0x0858
-#define MEM_SDSTRIDE0 0x0860
-#define MEM_SDSTRIDE1 0x0868
-#define MEM_SDSTRIDE2 0x0870
-#define MEM_SDWRMD0 0x0880
-#define MEM_SDWRMD1 0x0888
-#define MEM_SDWRMD2 0x0890
-#define MEM_SDPRECMD 0x08C0
-#define MEM_SDAUTOREF 0x08C8
-#define MEM_SDSREF 0x08D0
-#define MEM_SDSLEEP MEM_SDSREF
-
-#endif
-
-/*
- * Physical base addresses for integrated peripherals
- * 0..au1000 1..au1500 2..au1100 3..au1550 4..au1200
- */
-
-#define AU1000_AC97_PHYS_ADDR 0x10000000 /* 012 */
-#define AU1000_USBD_PHYS_ADDR 0x10200000 /* 0123 */
-#define AU1000_IC0_PHYS_ADDR 0x10400000 /* 01234 */
-#define AU1000_MAC0_PHYS_ADDR 0x10500000 /* 023 */
-#define AU1000_MAC1_PHYS_ADDR 0x10510000 /* 023 */
-#define AU1000_MACEN_PHYS_ADDR 0x10520000 /* 023 */
-#define AU1100_SD0_PHYS_ADDR 0x10600000 /* 24 */
-#define AU1100_SD1_PHYS_ADDR 0x10680000 /* 24 */
-#define AU1000_I2S_PHYS_ADDR 0x11000000 /* 02 */
-#define AU1500_MAC0_PHYS_ADDR 0x11500000 /* 1 */
-#define AU1500_MAC1_PHYS_ADDR 0x11510000 /* 1 */
-#define AU1500_MACEN_PHYS_ADDR 0x11520000 /* 1 */
-#define AU1000_UART0_PHYS_ADDR 0x11100000 /* 01234 */
-#define AU1000_UART1_PHYS_ADDR 0x11200000 /* 0234 */
-#define AU1000_UART2_PHYS_ADDR 0x11300000 /* 0 */
-#define AU1000_UART3_PHYS_ADDR 0x11400000 /* 0123 */
-#define AU1500_GPIO2_PHYS_ADDR 0x11700000 /* 1234 */
-#define AU1000_IC1_PHYS_ADDR 0x11800000 /* 01234 */
-#define AU1000_SYS_PHYS_ADDR 0x11900000 /* 01234 */
-#define AU1000_DMA_PHYS_ADDR 0x14002000 /* 012 */
-#define AU1550_DBDMA_PHYS_ADDR 0x14002000 /* 34 */
-#define AU1550_DBDMA_CONF_PHYS_ADDR 0x14003000 /* 34 */
-#define AU1000_MACDMA0_PHYS_ADDR 0x14004000 /* 0123 */
-#define AU1000_MACDMA1_PHYS_ADDR 0x14004200 /* 0123 */
-
-
-#ifdef CONFIG_SOC_AU1000
-#define MEM_PHYS_ADDR 0x14000000
-#define STATIC_MEM_PHYS_ADDR 0x14001000
-#define USBH_PHYS_ADDR 0x10100000
-#define IRDA_PHYS_ADDR 0x10300000
-#define SSI0_PHYS_ADDR 0x11600000
-#define SSI1_PHYS_ADDR 0x11680000
-#define PCMCIA_IO_PHYS_ADDR 0xF00000000ULL
-#define PCMCIA_ATTR_PHYS_ADDR 0xF40000000ULL
-#define PCMCIA_MEM_PHYS_ADDR 0xF80000000ULL
-#endif
-
-/********************************************************************/
-
-#ifdef CONFIG_SOC_AU1500
-#define MEM_PHYS_ADDR 0x14000000
-#define STATIC_MEM_PHYS_ADDR 0x14001000
-#define USBH_PHYS_ADDR 0x10100000
-#define PCI_PHYS_ADDR 0x14005000
-#define PCI_MEM_PHYS_ADDR 0x400000000ULL
-#define PCI_IO_PHYS_ADDR 0x500000000ULL
-#define PCI_CONFIG0_PHYS_ADDR 0x600000000ULL
-#define PCI_CONFIG1_PHYS_ADDR 0x680000000ULL
-#define PCMCIA_IO_PHYS_ADDR 0xF00000000ULL
-#define PCMCIA_ATTR_PHYS_ADDR 0xF40000000ULL
-#define PCMCIA_MEM_PHYS_ADDR 0xF80000000ULL
-#endif
-
-/********************************************************************/
-
-#ifdef CONFIG_SOC_AU1100
-#define MEM_PHYS_ADDR 0x14000000
-#define STATIC_MEM_PHYS_ADDR 0x14001000
-#define USBH_PHYS_ADDR 0x10100000
-#define IRDA_PHYS_ADDR 0x10300000
-#define SSI0_PHYS_ADDR 0x11600000
-#define SSI1_PHYS_ADDR 0x11680000
-#define LCD_PHYS_ADDR 0x15000000
-#define PCMCIA_IO_PHYS_ADDR 0xF00000000ULL
-#define PCMCIA_ATTR_PHYS_ADDR 0xF40000000ULL
-#define PCMCIA_MEM_PHYS_ADDR 0xF80000000ULL
-#endif
-
-/***********************************************************************/
-
-#ifdef CONFIG_SOC_AU1550
-#define MEM_PHYS_ADDR 0x14000000
-#define STATIC_MEM_PHYS_ADDR 0x14001000
-#define USBH_PHYS_ADDR 0x14020000
-#define PCI_PHYS_ADDR 0x14005000
-#define PE_PHYS_ADDR 0x14008000
-#define PSC0_PHYS_ADDR 0x11A00000
-#define PSC1_PHYS_ADDR 0x11B00000
-#define PSC2_PHYS_ADDR 0x10A00000
-#define PSC3_PHYS_ADDR 0x10B00000
-#define PCI_MEM_PHYS_ADDR 0x400000000ULL
-#define PCI_IO_PHYS_ADDR 0x500000000ULL
-#define PCI_CONFIG0_PHYS_ADDR 0x600000000ULL
-#define PCI_CONFIG1_PHYS_ADDR 0x680000000ULL
-#define PCMCIA_IO_PHYS_ADDR 0xF00000000ULL
-#define PCMCIA_ATTR_PHYS_ADDR 0xF40000000ULL
-#define PCMCIA_MEM_PHYS_ADDR 0xF80000000ULL
-#endif
-
-/***********************************************************************/
-
-#ifdef CONFIG_SOC_AU1200
-#define MEM_PHYS_ADDR 0x14000000
-#define STATIC_MEM_PHYS_ADDR 0x14001000
-#define AES_PHYS_ADDR 0x10300000
-#define CIM_PHYS_ADDR 0x14004000
-#define USBM_PHYS_ADDR 0x14020000
-#define USBH_PHYS_ADDR 0x14020100
-#define PSC0_PHYS_ADDR 0x11A00000
-#define PSC1_PHYS_ADDR 0x11B00000
-#define LCD_PHYS_ADDR 0x15000000
-#define SWCNT_PHYS_ADDR 0x1110010C
-#define MAEFE_PHYS_ADDR 0x14012000
-#define MAEBE_PHYS_ADDR 0x14010000
-#define PCMCIA_IO_PHYS_ADDR 0xF00000000ULL
-#define PCMCIA_ATTR_PHYS_ADDR 0xF40000000ULL
-#define PCMCIA_MEM_PHYS_ADDR 0xF80000000ULL
-#endif
+/* Au1550 SDRAM Register Offsets */
+#define AU1550_MEM_SDMODE0 0x0800
+#define AU1550_MEM_SDMODE1 0x0808
+#define AU1550_MEM_SDMODE2 0x0810
+#define AU1550_MEM_SDADDR0 0x0820
+#define AU1550_MEM_SDADDR1 0x0828
+#define AU1550_MEM_SDADDR2 0x0830
+#define AU1550_MEM_SDCONFIGA 0x0840
+#define AU1550_MEM_SDCONFIGB 0x0848
+#define AU1550_MEM_SDSTAT 0x0850
+#define AU1550_MEM_SDERRADDR 0x0858
+#define AU1550_MEM_SDSTRIDE0 0x0860
+#define AU1550_MEM_SDSTRIDE1 0x0868
+#define AU1550_MEM_SDSTRIDE2 0x0870
+#define AU1550_MEM_SDWRMD0 0x0880
+#define AU1550_MEM_SDWRMD1 0x0888
+#define AU1550_MEM_SDWRMD2 0x0890
+#define AU1550_MEM_SDPRECMD 0x08C0
+#define AU1550_MEM_SDAUTOREF 0x08C8
+#define AU1550_MEM_SDSREF 0x08D0
+#define AU1550_MEM_SDSLEEP MEM_SDSREF
/* Static Bus Controller */
#define MEM_STCFG0 0xB4001000
@@ -813,81 +757,14 @@
#define MEM_STTIME3 0xB4001034
#define MEM_STADDR3 0xB4001038
-#if defined(CONFIG_SOC_AU1550) || defined(CONFIG_SOC_AU1200)
#define MEM_STNDCTL 0xB4001100
#define MEM_STSTAT 0xB4001104
#define MEM_STNAND_CMD 0x0
#define MEM_STNAND_ADDR 0x4
#define MEM_STNAND_DATA 0x20
-#endif
-
-
-/* Au1000 */
-#ifdef CONFIG_SOC_AU1000
-
-#define USB_OHCI_BASE 0x10100000 /* phys addr for ioremap */
-#define USB_HOST_CONFIG 0xB017FFFC
-#define FOR_PLATFORM_C_USB_HOST_INT AU1000_USB_HOST_INT
-#endif /* CONFIG_SOC_AU1000 */
-
-/* Au1500 */
-#ifdef CONFIG_SOC_AU1500
-
-#define USB_OHCI_BASE 0x10100000 /* phys addr for ioremap */
-#define USB_HOST_CONFIG 0xB017fffc
-#define FOR_PLATFORM_C_USB_HOST_INT AU1500_USB_HOST_INT
-#endif /* CONFIG_SOC_AU1500 */
-
-/* Au1100 */
-#ifdef CONFIG_SOC_AU1100
-
-#define USB_OHCI_BASE 0x10100000 /* phys addr for ioremap */
-#define USB_HOST_CONFIG 0xB017FFFC
-#define FOR_PLATFORM_C_USB_HOST_INT AU1100_USB_HOST_INT
-#endif /* CONFIG_SOC_AU1100 */
-
-#ifdef CONFIG_SOC_AU1550
-
-#define USB_OHCI_BASE 0x14020000 /* phys addr for ioremap */
-#define USB_OHCI_LEN 0x00060000
-#define USB_HOST_CONFIG 0xB4027ffc
-#define FOR_PLATFORM_C_USB_HOST_INT AU1550_USB_HOST_INT
-#endif /* CONFIG_SOC_AU1550 */
-
-
-#ifdef CONFIG_SOC_AU1200
-
-#define USB_UOC_BASE 0x14020020
-#define USB_UOC_LEN 0x20
-#define USB_OHCI_BASE 0x14020100
-#define USB_OHCI_LEN 0x100
-#define USB_EHCI_BASE 0x14020200
-#define USB_EHCI_LEN 0x100
-#define USB_UDC_BASE 0x14022000
-#define USB_UDC_LEN 0x2000
-#define USB_MSR_BASE 0xB4020000
-#define USB_MSR_MCFG 4
-#define USBMSRMCFG_OMEMEN 0
-#define USBMSRMCFG_OBMEN 1
-#define USBMSRMCFG_EMEMEN 2
-#define USBMSRMCFG_EBMEN 3
-#define USBMSRMCFG_DMEMEN 4
-#define USBMSRMCFG_DBMEN 5
-#define USBMSRMCFG_GMEMEN 6
-#define USBMSRMCFG_OHCCLKEN 16
-#define USBMSRMCFG_EHCCLKEN 17
-#define USBMSRMCFG_UDCCLKEN 18
-#define USBMSRMCFG_PHYPLLEN 19
-#define USBMSRMCFG_RDCOMB 30
-#define USBMSRMCFG_PFEN 31
-
-#define FOR_PLATFORM_C_USB_HOST_INT AU1200_USB_INT
-
-#endif /* CONFIG_SOC_AU1200 */
-
/* Programmable Counters 0 and 1 */
#define SYS_BASE 0xB1900000
#define SYS_COUNTER_CNTRL (SYS_BASE + 0x14)
@@ -958,56 +835,6 @@
# define I2S_CONTROL_D (1 << 1)
# define I2S_CONTROL_CE (1 << 0)
-/* USB Host Controller */
-#ifndef USB_OHCI_LEN
-#define USB_OHCI_LEN 0x00100000
-#endif
-
-#ifndef CONFIG_SOC_AU1200
-
-/* USB Device Controller */
-#define USBD_EP0RD 0xB0200000
-#define USBD_EP0WR 0xB0200004
-#define USBD_EP2WR 0xB0200008
-#define USBD_EP3WR 0xB020000C
-#define USBD_EP4RD 0xB0200010
-#define USBD_EP5RD 0xB0200014
-#define USBD_INTEN 0xB0200018
-#define USBD_INTSTAT 0xB020001C
-# define USBDEV_INT_SOF (1 << 12)
-# define USBDEV_INT_HF_BIT 6
-# define USBDEV_INT_HF_MASK (0x3f << USBDEV_INT_HF_BIT)
-# define USBDEV_INT_CMPLT_BIT 0
-# define USBDEV_INT_CMPLT_MASK (0x3f << USBDEV_INT_CMPLT_BIT)
-#define USBD_CONFIG 0xB0200020
-#define USBD_EP0CS 0xB0200024
-#define USBD_EP2CS 0xB0200028
-#define USBD_EP3CS 0xB020002C
-#define USBD_EP4CS 0xB0200030
-#define USBD_EP5CS 0xB0200034
-# define USBDEV_CS_SU (1 << 14)
-# define USBDEV_CS_NAK (1 << 13)
-# define USBDEV_CS_ACK (1 << 12)
-# define USBDEV_CS_BUSY (1 << 11)
-# define USBDEV_CS_TSIZE_BIT 1
-# define USBDEV_CS_TSIZE_MASK (0x3ff << USBDEV_CS_TSIZE_BIT)
-# define USBDEV_CS_STALL (1 << 0)
-#define USBD_EP0RDSTAT 0xB0200040
-#define USBD_EP0WRSTAT 0xB0200044
-#define USBD_EP2WRSTAT 0xB0200048
-#define USBD_EP3WRSTAT 0xB020004C
-#define USBD_EP4RDSTAT 0xB0200050
-#define USBD_EP5RDSTAT 0xB0200054
-# define USBDEV_FSTAT_FLUSH (1 << 6)
-# define USBDEV_FSTAT_UF (1 << 5)
-# define USBDEV_FSTAT_OF (1 << 4)
-# define USBDEV_FSTAT_FCNT_BIT 0
-# define USBDEV_FSTAT_FCNT_MASK (0x0f << USBDEV_FSTAT_FCNT_BIT)
-#define USBD_ENABLE 0xB0200058
-# define USBDEV_ENABLE (1 << 1)
-# define USBDEV_CE (1 << 0)
-
-#endif /* !CONFIG_SOC_AU1200 */
/* Ethernet Controllers */
@@ -1322,7 +1149,6 @@
# define SYS_PF_MUST_BE_SET ((1 << 5) | (1 << 2))
/* Au1200 only */
-#ifdef CONFIG_SOC_AU1200
#define SYS_PINFUNC_DMA (1 << 31)
#define SYS_PINFUNC_S0A (1 << 30)
#define SYS_PINFUNC_S1A (1 << 29)
@@ -1350,7 +1176,6 @@
#define SYS_PINFUNC_P0B (1 << 4)
#define SYS_PINFUNC_U0T (1 << 3)
#define SYS_PINFUNC_S1B (1 << 2)
-#endif
/* Power Management */
#define SYS_SCRATCH0 0xB1900018
@@ -1406,12 +1231,12 @@
# define SYS_CS_MI2_MASK (0x7 << SYS_CS_MI2_BIT)
# define SYS_CS_DI2 (1 << 16)
# define SYS_CS_CI2 (1 << 15)
-#ifdef CONFIG_SOC_AU1100
+
# define SYS_CS_ML_BIT 7
# define SYS_CS_ML_MASK (0x7 << SYS_CS_ML_BIT)
# define SYS_CS_DL (1 << 6)
# define SYS_CS_CL (1 << 5)
-#else
+
# define SYS_CS_MUH_BIT 12
# define SYS_CS_MUH_MASK (0x7 << SYS_CS_MUH_BIT)
# define SYS_CS_DUH (1 << 11)
@@ -1420,7 +1245,7 @@
# define SYS_CS_MUD_MASK (0x7 << SYS_CS_MUD_BIT)
# define SYS_CS_DUD (1 << 6)
# define SYS_CS_CUD (1 << 5)
-#endif
+
# define SYS_CS_MIR_BIT 2
# define SYS_CS_MIR_MASK (0x7 << SYS_CS_MIR_BIT)
# define SYS_CS_DIR (1 << 1)
@@ -1467,58 +1292,30 @@
# define AC97C_RS (1 << 1)
# define AC97C_CE (1 << 0)
-#if defined(CONFIG_SOC_AU1500) || defined(CONFIG_SOC_AU1550)
-/* Au1500 PCI Controller */
-#define Au1500_CFG_BASE 0xB4005000 /* virtual, KSEG1 addr */
-#define Au1500_PCI_CMEM (Au1500_CFG_BASE + 0)
-#define Au1500_PCI_CFG (Au1500_CFG_BASE + 4)
-# define PCI_ERROR ((1 << 22) | (1 << 23) | (1 << 24) | \
- (1 << 25) | (1 << 26) | (1 << 27))
-#define Au1500_PCI_B2BMASK_CCH (Au1500_CFG_BASE + 8)
-#define Au1500_PCI_B2B0_VID (Au1500_CFG_BASE + 0xC)
-#define Au1500_PCI_B2B1_ID (Au1500_CFG_BASE + 0x10)
-#define Au1500_PCI_MWMASK_DEV (Au1500_CFG_BASE + 0x14)
-#define Au1500_PCI_MWBASE_REV_CCL (Au1500_CFG_BASE + 0x18)
-#define Au1500_PCI_ERR_ADDR (Au1500_CFG_BASE + 0x1C)
-#define Au1500_PCI_SPEC_INTACK (Au1500_CFG_BASE + 0x20)
-#define Au1500_PCI_ID (Au1500_CFG_BASE + 0x100)
-#define Au1500_PCI_STATCMD (Au1500_CFG_BASE + 0x104)
-#define Au1500_PCI_CLASSREV (Au1500_CFG_BASE + 0x108)
-#define Au1500_PCI_HDRTYPE (Au1500_CFG_BASE + 0x10C)
-#define Au1500_PCI_MBAR (Au1500_CFG_BASE + 0x110)
-#define Au1500_PCI_HDR 0xB4005100 /* virtual, KSEG1 addr */
-
-/*
- * All of our structures, like PCI resource, have 32-bit members.
- * Drivers are expected to do an ioremap on the PCI MEM resource, but it's
- * hard to store 0x4 0000 0000 in a 32-bit type. We require a small patch
- * to __ioremap to check for addresses between (u32)Au1500_PCI_MEM_START and
- * (u32)Au1500_PCI_MEM_END and change those to the full 36-bit PCI MEM
- * addresses. For PCI I/O, it's simpler because we get to do the ioremap
- * ourselves and then adjust the device's resources.
+/* The PCI chip selects are outside the 32bit space, and since we can't
+ * just program the 36bit addresses into BARs, we have to take a chunk
+ * out of the 32bit space and reserve it for PCI. When these addresses
+ * are ioremap()ed, they'll be fixed up to the real 36bit address before
+ * being passed to the real ioremap function.
*/
-#define Au1500_EXT_CFG 0x600000000ULL
-#define Au1500_EXT_CFG_TYPE1 0x680000000ULL
-#define Au1500_PCI_IO_START 0x500000000ULL
-#define Au1500_PCI_IO_END 0x5000FFFFFULL
-#define Au1500_PCI_MEM_START 0x440000000ULL
-#define Au1500_PCI_MEM_END 0x44FFFFFFFULL
+#define ALCHEMY_PCI_MEMWIN_START (AU1500_PCI_MEM_PHYS_ADDR >> 4)
+#define ALCHEMY_PCI_MEMWIN_END (ALCHEMY_PCI_MEMWIN_START + 0x0FFFFFFF)
-#define PCI_IO_START 0x00001000
-#define PCI_IO_END 0x000FFFFF
-#define PCI_MEM_START 0x40000000
-#define PCI_MEM_END 0x4FFFFFFF
+/* for PCI IO it's simpler because we get to do the ioremap ourselves and then
+ * adjust the device's resources.
+ */
+#define ALCHEMY_PCI_IOWIN_START 0x00001000
+#define ALCHEMY_PCI_IOWIN_END 0x0000FFFF
-#define PCI_FIRST_DEVFN (0 << 3)
-#define PCI_LAST_DEVFN (19 << 3)
+#ifdef CONFIG_PCI
#define IOPORT_RESOURCE_START 0x00001000 /* skip legacy probing */
#define IOPORT_RESOURCE_END 0xffffffff
#define IOMEM_RESOURCE_START 0x10000000
#define IOMEM_RESOURCE_END 0xfffffffffULL
-#else /* Au1000 and Au1100 and Au1200 */
+#else
/* Don't allow any legacy ports probing */
#define IOPORT_RESOURCE_START 0x10000000
@@ -1526,13 +1323,77 @@
#define IOMEM_RESOURCE_START 0x10000000
#define IOMEM_RESOURCE_END 0xfffffffffULL
-#define PCI_IO_START 0
-#define PCI_IO_END 0
-#define PCI_MEM_START 0
-#define PCI_MEM_END 0
-#define PCI_FIRST_DEVFN 0
-#define PCI_LAST_DEVFN 0
-
#endif
+/* PCI controller block register offsets */
+#define PCI_REG_CMEM 0x0000
+#define PCI_REG_CONFIG 0x0004
+#define PCI_REG_B2BMASK_CCH 0x0008
+#define PCI_REG_B2BBASE0_VID 0x000C
+#define PCI_REG_B2BBASE1_SID 0x0010
+#define PCI_REG_MWMASK_DEV 0x0014
+#define PCI_REG_MWBASE_REV_CCL 0x0018
+#define PCI_REG_ERR_ADDR 0x001C
+#define PCI_REG_SPEC_INTACK 0x0020
+#define PCI_REG_ID 0x0100
+#define PCI_REG_STATCMD 0x0104
+#define PCI_REG_CLASSREV 0x0108
+#define PCI_REG_PARAM 0x010C
+#define PCI_REG_MBAR 0x0110
+#define PCI_REG_TIMEOUT 0x0140
+
+/* PCI controller block register bits */
+#define PCI_CMEM_E (1 << 28) /* enable cacheable memory */
+#define PCI_CMEM_CMBASE(x) (((x) & 0x3fff) << 14)
+#define PCI_CMEM_CMMASK(x) ((x) & 0x3fff)
+#define PCI_CONFIG_ERD (1 << 27) /* pci error during R/W */
+#define PCI_CONFIG_ET (1 << 26) /* error in target mode */
+#define PCI_CONFIG_EF (1 << 25) /* fatal error */
+#define PCI_CONFIG_EP (1 << 24) /* parity error */
+#define PCI_CONFIG_EM (1 << 23) /* multiple errors */
+#define PCI_CONFIG_BM (1 << 22) /* bad master error */
+#define PCI_CONFIG_PD (1 << 20) /* PCI Disable */
+#define PCI_CONFIG_BME (1 << 19) /* Byte Mask Enable for reads */
+#define PCI_CONFIG_NC (1 << 16) /* mark mem access non-coherent */
+#define PCI_CONFIG_IA (1 << 15) /* INTA# enabled (target mode) */
+#define PCI_CONFIG_IP (1 << 13) /* int on PCI_PERR# */
+#define PCI_CONFIG_IS (1 << 12) /* int on PCI_SERR# */
+#define PCI_CONFIG_IMM (1 << 11) /* int on master abort */
+#define PCI_CONFIG_ITM (1 << 10) /* int on target abort (as master) */
+#define PCI_CONFIG_ITT (1 << 9) /* int on target abort (as target) */
+#define PCI_CONFIG_IPB (1 << 8) /* int on PERR# in bus master acc */
+#define PCI_CONFIG_SIC_NO (0 << 6) /* no byte mask changes */
+#define PCI_CONFIG_SIC_BA_ADR (1 << 6) /* on byte/hw acc, invert adr bits */
+#define PCI_CONFIG_SIC_HWA_DAT (2 << 6) /* on halfword acc, swap data */
+#define PCI_CONFIG_SIC_ALL (3 << 6) /* swap data bytes on all accesses */
+#define PCI_CONFIG_ST (1 << 5) /* swap data by target transactions */
+#define PCI_CONFIG_SM (1 << 4) /* swap data from PCI ctl */
+#define PCI_CONFIG_AEN (1 << 3) /* enable internal arbiter */
+#define PCI_CONFIG_R2H (1 << 2) /* REQ2# to hi-prio arbiter */
+#define PCI_CONFIG_R1H (1 << 1) /* REQ1# to hi-prio arbiter */
+#define PCI_CONFIG_CH (1 << 0) /* PCI ctl to hi-prio arbiter */
+#define PCI_B2BMASK_B2BMASK(x) (((x) & 0xffff) << 16)
+#define PCI_B2BMASK_CCH(x) ((x) & 0xffff) /* 16 upper bits of class code */
+#define PCI_B2BBASE0_VID_B0(x) (((x) & 0xffff) << 16)
+#define PCI_B2BBASE0_VID_SV(x) ((x) & 0xffff)
+#define PCI_B2BBASE1_SID_B1(x) (((x) & 0xffff) << 16)
+#define PCI_B2BBASE1_SID_SI(x) ((x) & 0xffff)
+#define PCI_MWMASKDEV_MWMASK(x) (((x) & 0xffff) << 16)
+#define PCI_MWMASKDEV_DEVID(x) ((x) & 0xffff)
+#define PCI_MWBASEREVCCL_BASE(x) (((x) & 0xffff) << 16)
+#define PCI_MWBASEREVCCL_REV(x) (((x) & 0xff) << 8)
+#define PCI_MWBASEREVCCL_CCL(x) ((x) & 0xff)
+#define PCI_ID_DID(x) (((x) & 0xffff) << 16)
+#define PCI_ID_VID(x) ((x) & 0xffff)
+#define PCI_STATCMD_STATUS(x) (((x) & 0xffff) << 16)
+#define PCI_STATCMD_CMD(x) ((x) & 0xffff)
+#define PCI_CLASSREV_CLASS(x) (((x) & 0x00ffffff) << 8)
+#define PCI_CLASSREV_REV(x) ((x) & 0xff)
+#define PCI_PARAM_BIST(x) (((x) & 0xff) << 24)
+#define PCI_PARAM_HT(x) (((x) & 0xff) << 16)
+#define PCI_PARAM_LT(x) (((x) & 0xff) << 8)
+#define PCI_PARAM_CLS(x) ((x) & 0xff)
+#define PCI_TIMEOUT_RETRIES(x) (((x) & 0xff) << 8) /* max retries */
+#define PCI_TIMEOUT_TO(x) ((x) & 0xff) /* target ready timeout */
+
#endif
diff --git a/arch/mips/include/asm/mach-au1x00/au1xxx.h b/arch/mips/include/asm/mach-au1x00/au1xxx.h
deleted file mode 100644
index 1b36550..0000000
--- a/arch/mips/include/asm/mach-au1x00/au1xxx.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
- * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
- * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
- * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
- * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
- * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#ifndef _AU1XXX_H_
-#define _AU1XXX_H_
-
-#include <asm/mach-au1x00/au1000.h>
-
-#if defined(CONFIG_MIPS_DB1000) || defined(CONFIG_MIPS_DB1100) || \
- defined(CONFIG_MIPS_DB1500) || defined(CONFIG_MIPS_DB1550)
-#include <asm/mach-db1x00/db1x00.h>
-
-#elif defined(CONFIG_MIPS_PB1550)
-#include <asm/mach-pb1x00/pb1550.h>
-
-#elif defined(CONFIG_MIPS_PB1200)
-#include <asm/mach-pb1x00/pb1200.h>
-
-#elif defined(CONFIG_MIPS_DB1200)
-#include <asm/mach-db1x00/db1200.h>
-
-#endif
-
-#endif /* _AU1XXX_H_ */
diff --git a/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h b/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h
index 2fdacfe..323ce2d 100644
--- a/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h
+++ b/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h
@@ -126,66 +126,62 @@
#define SW_STATUS_INUSE (1 << 0)
/* Command 0 device IDs. */
-#ifdef CONFIG_SOC_AU1550
-#define DSCR_CMD0_UART0_TX 0
-#define DSCR_CMD0_UART0_RX 1
-#define DSCR_CMD0_UART3_TX 2
-#define DSCR_CMD0_UART3_RX 3
-#define DSCR_CMD0_DMA_REQ0 4
-#define DSCR_CMD0_DMA_REQ1 5
-#define DSCR_CMD0_DMA_REQ2 6
-#define DSCR_CMD0_DMA_REQ3 7
-#define DSCR_CMD0_USBDEV_RX0 8
-#define DSCR_CMD0_USBDEV_TX0 9
-#define DSCR_CMD0_USBDEV_TX1 10
-#define DSCR_CMD0_USBDEV_TX2 11
-#define DSCR_CMD0_USBDEV_RX3 12
-#define DSCR_CMD0_USBDEV_RX4 13
-#define DSCR_CMD0_PSC0_TX 14
-#define DSCR_CMD0_PSC0_RX 15
-#define DSCR_CMD0_PSC1_TX 16
-#define DSCR_CMD0_PSC1_RX 17
-#define DSCR_CMD0_PSC2_TX 18
-#define DSCR_CMD0_PSC2_RX 19
-#define DSCR_CMD0_PSC3_TX 20
-#define DSCR_CMD0_PSC3_RX 21
-#define DSCR_CMD0_PCI_WRITE 22
-#define DSCR_CMD0_NAND_FLASH 23
-#define DSCR_CMD0_MAC0_RX 24
-#define DSCR_CMD0_MAC0_TX 25
-#define DSCR_CMD0_MAC1_RX 26
-#define DSCR_CMD0_MAC1_TX 27
-#endif /* CONFIG_SOC_AU1550 */
+#define AU1550_DSCR_CMD0_UART0_TX 0
+#define AU1550_DSCR_CMD0_UART0_RX 1
+#define AU1550_DSCR_CMD0_UART3_TX 2
+#define AU1550_DSCR_CMD0_UART3_RX 3
+#define AU1550_DSCR_CMD0_DMA_REQ0 4
+#define AU1550_DSCR_CMD0_DMA_REQ1 5
+#define AU1550_DSCR_CMD0_DMA_REQ2 6
+#define AU1550_DSCR_CMD0_DMA_REQ3 7
+#define AU1550_DSCR_CMD0_USBDEV_RX0 8
+#define AU1550_DSCR_CMD0_USBDEV_TX0 9
+#define AU1550_DSCR_CMD0_USBDEV_TX1 10
+#define AU1550_DSCR_CMD0_USBDEV_TX2 11
+#define AU1550_DSCR_CMD0_USBDEV_RX3 12
+#define AU1550_DSCR_CMD0_USBDEV_RX4 13
+#define AU1550_DSCR_CMD0_PSC0_TX 14
+#define AU1550_DSCR_CMD0_PSC0_RX 15
+#define AU1550_DSCR_CMD0_PSC1_TX 16
+#define AU1550_DSCR_CMD0_PSC1_RX 17
+#define AU1550_DSCR_CMD0_PSC2_TX 18
+#define AU1550_DSCR_CMD0_PSC2_RX 19
+#define AU1550_DSCR_CMD0_PSC3_TX 20
+#define AU1550_DSCR_CMD0_PSC3_RX 21
+#define AU1550_DSCR_CMD0_PCI_WRITE 22
+#define AU1550_DSCR_CMD0_NAND_FLASH 23
+#define AU1550_DSCR_CMD0_MAC0_RX 24
+#define AU1550_DSCR_CMD0_MAC0_TX 25
+#define AU1550_DSCR_CMD0_MAC1_RX 26
+#define AU1550_DSCR_CMD0_MAC1_TX 27
-#ifdef CONFIG_SOC_AU1200
-#define DSCR_CMD0_UART0_TX 0
-#define DSCR_CMD0_UART0_RX 1
-#define DSCR_CMD0_UART1_TX 2
-#define DSCR_CMD0_UART1_RX 3
-#define DSCR_CMD0_DMA_REQ0 4
-#define DSCR_CMD0_DMA_REQ1 5
-#define DSCR_CMD0_MAE_BE 6
-#define DSCR_CMD0_MAE_FE 7
-#define DSCR_CMD0_SDMS_TX0 8
-#define DSCR_CMD0_SDMS_RX0 9
-#define DSCR_CMD0_SDMS_TX1 10
-#define DSCR_CMD0_SDMS_RX1 11
-#define DSCR_CMD0_AES_TX 13
-#define DSCR_CMD0_AES_RX 12
-#define DSCR_CMD0_PSC0_TX 14
-#define DSCR_CMD0_PSC0_RX 15
-#define DSCR_CMD0_PSC1_TX 16
-#define DSCR_CMD0_PSC1_RX 17
-#define DSCR_CMD0_CIM_RXA 18
-#define DSCR_CMD0_CIM_RXB 19
-#define DSCR_CMD0_CIM_RXC 20
-#define DSCR_CMD0_MAE_BOTH 21
-#define DSCR_CMD0_LCD 22
-#define DSCR_CMD0_NAND_FLASH 23
-#define DSCR_CMD0_PSC0_SYNC 24
-#define DSCR_CMD0_PSC1_SYNC 25
-#define DSCR_CMD0_CIM_SYNC 26
-#endif /* CONFIG_SOC_AU1200 */
+#define AU1200_DSCR_CMD0_UART0_TX 0
+#define AU1200_DSCR_CMD0_UART0_RX 1
+#define AU1200_DSCR_CMD0_UART1_TX 2
+#define AU1200_DSCR_CMD0_UART1_RX 3
+#define AU1200_DSCR_CMD0_DMA_REQ0 4
+#define AU1200_DSCR_CMD0_DMA_REQ1 5
+#define AU1200_DSCR_CMD0_MAE_BE 6
+#define AU1200_DSCR_CMD0_MAE_FE 7
+#define AU1200_DSCR_CMD0_SDMS_TX0 8
+#define AU1200_DSCR_CMD0_SDMS_RX0 9
+#define AU1200_DSCR_CMD0_SDMS_TX1 10
+#define AU1200_DSCR_CMD0_SDMS_RX1 11
+#define AU1200_DSCR_CMD0_AES_TX 13
+#define AU1200_DSCR_CMD0_AES_RX 12
+#define AU1200_DSCR_CMD0_PSC0_TX 14
+#define AU1200_DSCR_CMD0_PSC0_RX 15
+#define AU1200_DSCR_CMD0_PSC1_TX 16
+#define AU1200_DSCR_CMD0_PSC1_RX 17
+#define AU1200_DSCR_CMD0_CIM_RXA 18
+#define AU1200_DSCR_CMD0_CIM_RXB 19
+#define AU1200_DSCR_CMD0_CIM_RXC 20
+#define AU1200_DSCR_CMD0_MAE_BOTH 21
+#define AU1200_DSCR_CMD0_LCD 22
+#define AU1200_DSCR_CMD0_NAND_FLASH 23
+#define AU1200_DSCR_CMD0_PSC0_SYNC 24
+#define AU1200_DSCR_CMD0_PSC1_SYNC 25
+#define AU1200_DSCR_CMD0_CIM_SYNC 26
#define DSCR_CMD0_THROTTLE 30
#define DSCR_CMD0_ALWAYS 31
diff --git a/arch/mips/include/asm/mach-au1x00/au1xxx_ide.h b/arch/mips/include/asm/mach-au1x00/au1xxx_ide.h
index 5656c72..e306384 100644
--- a/arch/mips/include/asm/mach-au1x00/au1xxx_ide.h
+++ b/arch/mips/include/asm/mach-au1x00/au1xxx_ide.h
@@ -58,6 +58,7 @@
#endif
int irq;
u32 regbase;
+ int ddma_id;
} _auide_hwif;
/******************************************************************************/
diff --git a/arch/mips/include/asm/mach-au1x00/au1xxx_psc.h b/arch/mips/include/asm/mach-au1x00/au1xxx_psc.h
index 5a5cb73..4e3f3bc 100644
--- a/arch/mips/include/asm/mach-au1x00/au1xxx_psc.h
+++ b/arch/mips/include/asm/mach-au1x00/au1xxx_psc.h
@@ -33,19 +33,6 @@
#ifndef _AU1000_PSC_H_
#define _AU1000_PSC_H_
-/* The PSC base addresses. */
-#ifdef CONFIG_SOC_AU1550
-#define PSC0_BASE_ADDR 0xb1a00000
-#define PSC1_BASE_ADDR 0xb1b00000
-#define PSC2_BASE_ADDR 0xb0a00000
-#define PSC3_BASE_ADDR 0xb0b00000
-#endif
-
-#ifdef CONFIG_SOC_AU1200
-#define PSC0_BASE_ADDR 0xb1a00000
-#define PSC1_BASE_ADDR 0xb1b00000
-#endif
-
/*
* The PSC select and control registers are common to all protocols.
*/
@@ -80,19 +67,6 @@
#define PSC_AC97GPO_OFFSET 0x00000028
#define PSC_AC97GPI_OFFSET 0x0000002c
-#define AC97_PSC_SEL (AC97_PSC_BASE + PSC_SEL_OFFSET)
-#define AC97_PSC_CTRL (AC97_PSC_BASE + PSC_CTRL_OFFSET)
-#define PSC_AC97CFG (AC97_PSC_BASE + PSC_AC97CFG_OFFSET)
-#define PSC_AC97MSK (AC97_PSC_BASE + PSC_AC97MSK_OFFSET)
-#define PSC_AC97PCR (AC97_PSC_BASE + PSC_AC97PCR_OFFSET)
-#define PSC_AC97STAT (AC97_PSC_BASE + PSC_AC97STAT_OFFSET)
-#define PSC_AC97EVNT (AC97_PSC_BASE + PSC_AC97EVNT_OFFSET)
-#define PSC_AC97TXRX (AC97_PSC_BASE + PSC_AC97TXRX_OFFSET)
-#define PSC_AC97CDC (AC97_PSC_BASE + PSC_AC97CDC_OFFSET)
-#define PSC_AC97RST (AC97_PSC_BASE + PSC_AC97RST_OFFSET)
-#define PSC_AC97GPO (AC97_PSC_BASE + PSC_AC97GPO_OFFSET)
-#define PSC_AC97GPI (AC97_PSC_BASE + PSC_AC97GPI_OFFSET)
-
/* AC97 Config Register. */
#define PSC_AC97CFG_RT_MASK (3 << 30)
#define PSC_AC97CFG_RT_FIFO1 (0 << 30)
diff --git a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
index 1f41a52..73853b5 100644
--- a/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/gpio-au1000.h
@@ -347,17 +347,6 @@
/**********************************************************************/
-/* On Au1000, Au1500 and Au1100 GPIOs won't work as inputs before
- * SYS_PININPUTEN is written to at least once. On Au1550/Au1200 this
- * register enables use of GPIOs as wake source.
- */
-static inline void alchemy_gpio1_input_enable(void)
-{
- void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_SYS_PHYS_ADDR);
- __raw_writel(0, base + SYS_PININPUTEN); /* the write op is key */
- wmb();
-}
-
/* GPIO2 shared interrupts and control */
static inline void __alchemy_gpio2_mod_int(int gpio2, int en)
@@ -561,6 +550,7 @@
#ifndef CONFIG_GPIOLIB
+#ifdef CONFIG_ALCHEMY_GPIOINT_AU1000
#ifndef CONFIG_ALCHEMY_GPIO_INDIRECT /* case (4) */
@@ -665,24 +655,7 @@
#endif /* !CONFIG_ALCHEMY_GPIO_INDIRECT */
-
-#else /* CONFIG GPIOLIB */
-
-
- /* using gpiolib to provide up to 2 gpio_chips for on-chip gpios */
-#ifndef CONFIG_ALCHEMY_GPIO_INDIRECT /* case (2) */
-
-/* get everything through gpiolib */
-#define gpio_to_irq __gpio_to_irq
-#define gpio_get_value __gpio_get_value
-#define gpio_set_value __gpio_set_value
-#define gpio_cansleep __gpio_cansleep
-#define irq_to_gpio alchemy_irq_to_gpio
-
-#include <asm-generic/gpio.h>
-
-#endif /* !CONFIG_ALCHEMY_GPIO_INDIRECT */
-
+#endif /* CONFIG_ALCHEMY_GPIOINT_AU1000 */
#endif /* !CONFIG_GPIOLIB */
diff --git a/arch/mips/include/asm/mach-au1x00/gpio.h b/arch/mips/include/asm/mach-au1x00/gpio.h
index c3f60cd..fcdc8c4 100644
--- a/arch/mips/include/asm/mach-au1x00/gpio.h
+++ b/arch/mips/include/asm/mach-au1x00/gpio.h
@@ -1,10 +1,83 @@
+/*
+ * Alchemy GPIO support.
+ *
+ * With CONFIG_GPIOLIB=y different types of on-chip GPIO can be supported within
+ * the same kernel image.
+ * With CONFIG_GPIOLIB=n, your board must select ALCHEMY_GPIOINT_AU1XXX for the
+ * appropriate CPU type (AU1000 currently).
+ */
+
#ifndef _ALCHEMY_GPIO_H_
#define _ALCHEMY_GPIO_H_
-#if defined(CONFIG_ALCHEMY_GPIOINT_AU1000)
-
+#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/gpio-au1000.h>
-#endif
+/* On Au1000, Au1500 and Au1100 GPIOs won't work as inputs before
+ * SYS_PININPUTEN is written to at least once. On Au1550/Au1200/Au1300 this
+ * register enables use of GPIOs as wake source.
+ */
+static inline void alchemy_gpio1_input_enable(void)
+{
+ void __iomem *base = (void __iomem *)KSEG1ADDR(AU1000_SYS_PHYS_ADDR);
+ __raw_writel(0, base + 0x110); /* the write op is key */
+ wmb();
+}
+
+
+/* Linux gpio framework integration.
+*
+* 4 use cases of Alchemy GPIOS:
+*(1) GPIOLIB=y, ALCHEMY_GPIO_INDIRECT=y:
+* Board must register gpiochips.
+*(2) GPIOLIB=y, ALCHEMY_GPIO_INDIRECT=n:
+* A gpiochip for the 75 GPIOs is registered.
+*
+*(3) GPIOLIB=n, ALCHEMY_GPIO_INDIRECT=y:
+* the boards' gpio.h must provide the linux gpio wrapper functions,
+*
+*(4) GPIOLIB=n, ALCHEMY_GPIO_INDIRECT=n:
+* inlinable gpio functions are provided which enable access to the
+* Au1300 gpios only by using the numbers straight out of the data-
+* sheets.
+
+* Cases 1 and 3 are intended for boards which want to provide their own
+* GPIO namespace and -operations (i.e. for example you have 8 GPIOs
+* which are in part provided by spare Au1300 GPIO pins and in part by
+* an external FPGA but you still want them to be accssible in linux
+* as gpio0-7. The board can of course use the alchemy_gpioX_* functions
+* as required).
+*/
+
+#ifdef CONFIG_GPIOLIB
+
+/* wraps the cpu-dependent irq_to_gpio functions */
+/* FIXME: gpiolib needs an irq_to_gpio hook */
+static inline int __au_irq_to_gpio(unsigned int irq)
+{
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1000...ALCHEMY_CPU_AU1200:
+ return alchemy_irq_to_gpio(irq);
+ }
+ return -EINVAL;
+}
+
+
+/* using gpiolib to provide up to 2 gpio_chips for on-chip gpios */
+#ifndef CONFIG_ALCHEMY_GPIO_INDIRECT /* case (2) */
+
+/* get everything through gpiolib */
+#define gpio_to_irq __gpio_to_irq
+#define gpio_get_value __gpio_get_value
+#define gpio_set_value __gpio_set_value
+#define gpio_cansleep __gpio_cansleep
+#define irq_to_gpio __au_irq_to_gpio
+
+#include <asm-generic/gpio.h>
+
+#endif /* !CONFIG_ALCHEMY_GPIO_INDIRECT */
+
+
+#endif /* CONFIG_GPIOLIB */
#endif /* _ALCHEMY_GPIO_H_ */
diff --git a/arch/mips/include/asm/mach-db1x00/db1200.h b/arch/mips/include/asm/mach-db1x00/db1200.h
index 3404248..7a39657 100644
--- a/arch/mips/include/asm/mach-db1x00/db1200.h
+++ b/arch/mips/include/asm/mach-db1x00/db1200.h
@@ -46,8 +46,6 @@
#define IDE_PHYS_ADDR 0x18800000
#define IDE_REG_SHIFT 5
-#define IDE_DDMA_REQ DSCR_CMD0_DMA_REQ1
-#define IDE_RQSIZE 128
#define DB1200_IDE_PHYS_ADDR IDE_PHYS_ADDR
#define DB1200_IDE_PHYS_LEN (16 << IDE_REG_SHIFT)
diff --git a/arch/mips/include/asm/mach-db1x00/db1x00.h b/arch/mips/include/asm/mach-db1x00/db1x00.h
index a919dac..a5affb0 100644
--- a/arch/mips/include/asm/mach-db1x00/db1x00.h
+++ b/arch/mips/include/asm/mach-db1x00/db1x00.h
@@ -31,15 +31,15 @@
#ifdef CONFIG_MIPS_DB1550
-#define DBDMA_AC97_TX_CHAN DSCR_CMD0_PSC1_TX
-#define DBDMA_AC97_RX_CHAN DSCR_CMD0_PSC1_RX
-#define DBDMA_I2S_TX_CHAN DSCR_CMD0_PSC3_TX
-#define DBDMA_I2S_RX_CHAN DSCR_CMD0_PSC3_RX
+#define DBDMA_AC97_TX_CHAN AU1550_DSCR_CMD0_PSC1_TX
+#define DBDMA_AC97_RX_CHAN AU1550_DSCR_CMD0_PSC1_RX
+#define DBDMA_I2S_TX_CHAN AU1550_DSCR_CMD0_PSC3_TX
+#define DBDMA_I2S_RX_CHAN AU1550_DSCR_CMD0_PSC3_RX
-#define SPI_PSC_BASE PSC0_BASE_ADDR
-#define AC97_PSC_BASE PSC1_BASE_ADDR
-#define SMBUS_PSC_BASE PSC2_BASE_ADDR
-#define I2S_PSC_BASE PSC3_BASE_ADDR
+#define SPI_PSC_BASE AU1550_PSC0_PHYS_ADDR
+#define AC97_PSC_BASE AU1550_PSC1_PHYS_ADDR
+#define SMBUS_PSC_BASE AU1550_PSC2_PHYS_ADDR
+#define I2S_PSC_BASE AU1550_PSC3_PHYS_ADDR
#define NAND_PHYS_ADDR 0x20000000
diff --git a/arch/mips/include/asm/mach-pb1x00/pb1200.h b/arch/mips/include/asm/mach-pb1x00/pb1200.h
index fce4332..374416a 100644
--- a/arch/mips/include/asm/mach-pb1x00/pb1200.h
+++ b/arch/mips/include/asm/mach-pb1x00/pb1200.h
@@ -28,23 +28,23 @@
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1xxx_psc.h>
-#define DBDMA_AC97_TX_CHAN DSCR_CMD0_PSC1_TX
-#define DBDMA_AC97_RX_CHAN DSCR_CMD0_PSC1_RX
-#define DBDMA_I2S_TX_CHAN DSCR_CMD0_PSC1_TX
-#define DBDMA_I2S_RX_CHAN DSCR_CMD0_PSC1_RX
+#define DBDMA_AC97_TX_CHAN AU1200_DSCR_CMD0_PSC1_TX
+#define DBDMA_AC97_RX_CHAN AU1200_DSCR_CMD0_PSC1_RX
+#define DBDMA_I2S_TX_CHAN AU1200_DSCR_CMD0_PSC1_TX
+#define DBDMA_I2S_RX_CHAN AU1200_DSCR_CMD0_PSC1_RX
/*
* SPI and SMB are muxed on the Pb1200 board.
* Refer to board documentation.
*/
-#define SPI_PSC_BASE PSC0_BASE_ADDR
-#define SMBUS_PSC_BASE PSC0_BASE_ADDR
+#define SPI_PSC_BASE AU1550_PSC0_PHYS_ADDR
+#define SMBUS_PSC_BASE AU1550_PSC0_PHYS_ADDR
/*
* AC97 and I2S are muxed on the Pb1200 board.
* Refer to board documentation.
*/
-#define AC97_PSC_BASE PSC1_BASE_ADDR
-#define I2S_PSC_BASE PSC1_BASE_ADDR
+#define AC97_PSC_BASE AU1550_PSC1_PHYS_ADDR
+#define I2S_PSC_BASE AU1550_PSC1_PHYS_ADDR
#define BCSR_SYSTEM_VDDI 0x001F
@@ -76,8 +76,6 @@
#define IDE_REG_SHIFT 5
#define IDE_PHYS_LEN (16 << IDE_REG_SHIFT)
#define IDE_INT PB1200_IDE_INT
-#define IDE_DDMA_REQ DSCR_CMD0_DMA_REQ1
-#define IDE_RQSIZE 128
#define NAND_PHYS_ADDR 0x1C000000
diff --git a/arch/mips/include/asm/mach-pb1x00/pb1550.h b/arch/mips/include/asm/mach-pb1x00/pb1550.h
index f835c88..443b88a 100644
--- a/arch/mips/include/asm/mach-pb1x00/pb1550.h
+++ b/arch/mips/include/asm/mach-pb1x00/pb1550.h
@@ -30,15 +30,15 @@
#include <linux/types.h>
#include <asm/mach-au1x00/au1xxx_psc.h>
-#define DBDMA_AC97_TX_CHAN DSCR_CMD0_PSC1_TX
-#define DBDMA_AC97_RX_CHAN DSCR_CMD0_PSC1_RX
-#define DBDMA_I2S_TX_CHAN DSCR_CMD0_PSC3_TX
-#define DBDMA_I2S_RX_CHAN DSCR_CMD0_PSC3_RX
+#define DBDMA_AC97_TX_CHAN AU1550_DSCR_CMD0_PSC1_TX
+#define DBDMA_AC97_RX_CHAN AU1550_DSCR_CMD0_PSC1_RX
+#define DBDMA_I2S_TX_CHAN AU1550_DSCR_CMD0_PSC3_TX
+#define DBDMA_I2S_RX_CHAN AU1550_DSCR_CMD0_PSC3_RX
-#define SPI_PSC_BASE PSC0_BASE_ADDR
-#define AC97_PSC_BASE PSC1_BASE_ADDR
-#define SMBUS_PSC_BASE PSC2_BASE_ADDR
-#define I2S_PSC_BASE PSC3_BASE_ADDR
+#define SPI_PSC_BASE AU1550_PSC0_PHYS_ADDR
+#define AC97_PSC_BASE AU1550_PSC1_PHYS_ADDR
+#define SMBUS_PSC_BASE AU1550_PSC2_PHYS_ADDR
+#define I2S_PSC_BASE AU1550_PSC3_PHYS_ADDR
/*
* Timing values as described in databook, * ns value stripped of
diff --git a/arch/mips/include/asm/mipsprom.h b/arch/mips/include/asm/mipsprom.h
index 146d41b..e93943f 100644
--- a/arch/mips/include/asm/mipsprom.h
+++ b/arch/mips/include/asm/mipsprom.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_MIPS_PROM_H
-#define __ASM_MIPS_PROM_H
+#ifndef __ASM_MIPSPROM_H
+#define __ASM_MIPSPROM_H
#define PROM_RESET 0
#define PROM_EXEC 1
@@ -73,4 +73,4 @@
extern char *prom_getenv(char *);
-#endif /* __ASM_MIPS_PROM_H */
+#endif /* __ASM_MIPSPROM_H */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 6a6f8a8..2ea7b81 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1006,18 +1006,26 @@
#define write_c0_perfctrl0(val) __write_32bit_c0_register($25, 0, val)
#define read_c0_perfcntr0() __read_32bit_c0_register($25, 1)
#define write_c0_perfcntr0(val) __write_32bit_c0_register($25, 1, val)
+#define read_c0_perfcntr0_64() __read_64bit_c0_register($25, 1)
+#define write_c0_perfcntr0_64(val) __write_64bit_c0_register($25, 1, val)
#define read_c0_perfctrl1() __read_32bit_c0_register($25, 2)
#define write_c0_perfctrl1(val) __write_32bit_c0_register($25, 2, val)
#define read_c0_perfcntr1() __read_32bit_c0_register($25, 3)
#define write_c0_perfcntr1(val) __write_32bit_c0_register($25, 3, val)
+#define read_c0_perfcntr1_64() __read_64bit_c0_register($25, 3)
+#define write_c0_perfcntr1_64(val) __write_64bit_c0_register($25, 3, val)
#define read_c0_perfctrl2() __read_32bit_c0_register($25, 4)
#define write_c0_perfctrl2(val) __write_32bit_c0_register($25, 4, val)
#define read_c0_perfcntr2() __read_32bit_c0_register($25, 5)
#define write_c0_perfcntr2(val) __write_32bit_c0_register($25, 5, val)
+#define read_c0_perfcntr2_64() __read_64bit_c0_register($25, 5)
+#define write_c0_perfcntr2_64(val) __write_64bit_c0_register($25, 5, val)
#define read_c0_perfctrl3() __read_32bit_c0_register($25, 6)
#define write_c0_perfctrl3(val) __write_32bit_c0_register($25, 6, val)
#define read_c0_perfcntr3() __read_32bit_c0_register($25, 7)
#define write_c0_perfcntr3(val) __write_32bit_c0_register($25, 7, val)
+#define read_c0_perfcntr3_64() __read_64bit_c0_register($25, 7)
+#define write_c0_perfcntr3_64(val) __write_64bit_c0_register($25, 7, val)
/* RM9000 PerfCount performance counter register */
#define read_c0_perfcount() __read_64bit_c0_register($25, 0)
diff --git a/arch/mips/include/asm/prom.h b/arch/mips/include/asm/prom.h
index 857d9b7..7a6e82e 100644
--- a/arch/mips/include/asm/prom.h
+++ b/arch/mips/include/asm/prom.h
@@ -8,8 +8,8 @@
* published by the Free Software Foundation.
*
*/
-#ifndef __ASM_MIPS_PROM_H
-#define __ASM_MIPS_PROM_H
+#ifndef __ASM_PROM_H
+#define __ASM_PROM_H
#ifdef CONFIG_OF
#include <asm/bootinfo.h>
@@ -25,4 +25,4 @@
static inline void device_tree_init(void) { }
#endif /* CONFIG_OF */
-#endif /* _ASM_MIPS_PROM_H */
+#endif /* __ASM_PROM_H */
diff --git a/arch/mips/include/asm/regdef.h b/arch/mips/include/asm/regdef.h
index 7c8ecb6..785a518 100644
--- a/arch/mips/include/asm/regdef.h
+++ b/arch/mips/include/asm/regdef.h
@@ -6,6 +6,8 @@
* Copyright (C) 1985 MIPS Computer Systems, Inc.
* Copyright (C) 1994, 95, 99, 2003 by Ralf Baechle
* Copyright (C) 1990 - 1992, 1999 Silicon Graphics, Inc.
+ * Copyright (C) 2011 Wind River Systems,
+ * written by Ralf Baechle <ralf@linux-mips.org>
*/
#ifndef _ASM_REGDEF_H
#define _ASM_REGDEF_H
@@ -30,9 +32,13 @@
#define t2 $10
#define t3 $11
#define t4 $12
+#define ta0 $12
#define t5 $13
+#define ta1 $13
#define t6 $14
+#define ta2 $14
#define t7 $15
+#define ta3 $15
#define s0 $16 /* callee saved */
#define s1 $17
#define s2 $18
diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c
index 4397972..e1ddb95 100644
--- a/arch/mips/jz4740/gpio.c
+++ b/arch/mips/jz4740/gpio.c
@@ -17,8 +17,6 @@
#include <linux/module.h>
#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/syscore_ops.h>
#include <linux/io.h>
#include <linux/gpio.h>
#include <linux/delay.h>
@@ -30,6 +28,8 @@
#include <asm/mach-jz4740/base.h>
+#include "irq.h"
+
#define JZ4740_GPIO_BASE_A (32*0)
#define JZ4740_GPIO_BASE_B (32*1)
#define JZ4740_GPIO_BASE_C (32*2)
@@ -77,14 +77,10 @@
struct jz_gpio_chip {
unsigned int irq;
unsigned int irq_base;
- uint32_t wakeup;
- uint32_t suspend_mask;
uint32_t edge_trigger_both;
void __iomem *base;
- spinlock_t lock;
-
struct gpio_chip gpio_chip;
};
@@ -102,7 +98,8 @@
static inline struct jz_gpio_chip *irq_to_jz_gpio_chip(struct irq_data *data)
{
- return irq_data_get_irq_chip_data(data);
+ struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
+ return gc->private;
}
static inline void jz_gpio_write_bit(unsigned int gpio, unsigned int reg)
@@ -304,21 +301,15 @@
{
uint32_t flag;
unsigned int gpio_irq;
- unsigned int gpio_bank;
struct jz_gpio_chip *chip = irq_desc_get_handler_data(desc);
- gpio_bank = JZ4740_IRQ_GPIO0 - irq;
-
flag = readl(chip->base + JZ_REG_GPIO_FLAG);
-
if (!flag)
return;
- gpio_irq = __fls(flag);
+ gpio_irq = chip->irq_base + __fls(flag);
- jz_gpio_check_trigger_both(chip, irq);
-
- gpio_irq += (gpio_bank << 5) + JZ4740_IRQ_GPIO(0);
+ jz_gpio_check_trigger_both(chip, gpio_irq);
generic_handle_irq(gpio_irq);
};
@@ -329,18 +320,12 @@
writel(IRQ_TO_BIT(data->irq), chip->base + reg);
}
-static void jz_gpio_irq_mask(struct irq_data *data)
-{
- jz_gpio_set_irq_bit(data, JZ_REG_GPIO_MASK_SET);
-};
-
static void jz_gpio_irq_unmask(struct irq_data *data)
{
struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data);
jz_gpio_check_trigger_both(chip, data->irq);
-
- jz_gpio_set_irq_bit(data, JZ_REG_GPIO_MASK_CLEAR);
+ irq_gc_unmask_enable_reg(data);
};
/* TODO: Check if function is gpio */
@@ -353,18 +338,13 @@
static void jz_gpio_irq_shutdown(struct irq_data *data)
{
- jz_gpio_irq_mask(data);
+ irq_gc_mask_disable_reg(data);
/* Set direction to input */
jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_CLEAR);
jz_gpio_set_irq_bit(data, JZ_REG_GPIO_SELECT_CLEAR);
}
-static void jz_gpio_irq_ack(struct irq_data *data)
-{
- jz_gpio_set_irq_bit(data, JZ_REG_GPIO_FLAG_CLEAR);
-};
-
static int jz_gpio_irq_set_type(struct irq_data *data, unsigned int flow_type)
{
struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data);
@@ -408,35 +388,13 @@
static int jz_gpio_irq_set_wake(struct irq_data *data, unsigned int on)
{
struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data);
- spin_lock(&chip->lock);
- if (on)
- chip->wakeup |= IRQ_TO_BIT(data->irq);
- else
- chip->wakeup &= ~IRQ_TO_BIT(data->irq);
- spin_unlock(&chip->lock);
+ irq_gc_set_wake(data, on);
irq_set_irq_wake(chip->irq, on);
+
return 0;
}
-static struct irq_chip jz_gpio_irq_chip = {
- .name = "GPIO",
- .irq_mask = jz_gpio_irq_mask,
- .irq_unmask = jz_gpio_irq_unmask,
- .irq_ack = jz_gpio_irq_ack,
- .irq_startup = jz_gpio_irq_startup,
- .irq_shutdown = jz_gpio_irq_shutdown,
- .irq_set_type = jz_gpio_irq_set_type,
- .irq_set_wake = jz_gpio_irq_set_wake,
- .flags = IRQCHIP_SET_TYPE_MASKED,
-};
-
-/*
- * This lock class tells lockdep that GPIO irqs are in a different
- * category than their parents, so it won't report false recursion.
- */
-static struct lock_class_key gpio_lock_class;
-
#define JZ4740_GPIO_CHIP(_bank) { \
.irq_base = JZ4740_IRQ_GPIO_BASE_ ## _bank, \
.gpio_chip = { \
@@ -458,64 +416,44 @@
JZ4740_GPIO_CHIP(D),
};
-static void jz4740_gpio_suspend_chip(struct jz_gpio_chip *chip)
-{
- chip->suspend_mask = readl(chip->base + JZ_REG_GPIO_MASK);
- writel(~(chip->wakeup), chip->base + JZ_REG_GPIO_MASK_SET);
- writel(chip->wakeup, chip->base + JZ_REG_GPIO_MASK_CLEAR);
-}
-
-static int jz4740_gpio_suspend(void)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(jz4740_gpio_chips); i++)
- jz4740_gpio_suspend_chip(&jz4740_gpio_chips[i]);
-
- return 0;
-}
-
-static void jz4740_gpio_resume_chip(struct jz_gpio_chip *chip)
-{
- uint32_t mask = chip->suspend_mask;
-
- writel(~mask, chip->base + JZ_REG_GPIO_MASK_CLEAR);
- writel(mask, chip->base + JZ_REG_GPIO_MASK_SET);
-}
-
-static void jz4740_gpio_resume(void)
-{
- int i;
-
- for (i = ARRAY_SIZE(jz4740_gpio_chips) - 1; i >= 0 ; i--)
- jz4740_gpio_resume_chip(&jz4740_gpio_chips[i]);
-}
-
-static struct syscore_ops jz4740_gpio_syscore_ops = {
- .suspend = jz4740_gpio_suspend,
- .resume = jz4740_gpio_resume,
-};
-
static void jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id)
{
- int irq;
-
- spin_lock_init(&chip->lock);
+ struct irq_chip_generic *gc;
+ struct irq_chip_type *ct;
chip->base = ioremap(JZ4740_GPIO_BASE_ADDR + (id * 0x100), 0x100);
- gpiochip_add(&chip->gpio_chip);
-
chip->irq = JZ4740_IRQ_INTC_GPIO(id);
irq_set_handler_data(chip->irq, chip);
irq_set_chained_handler(chip->irq, jz_gpio_irq_demux_handler);
- for (irq = chip->irq_base; irq < chip->irq_base + chip->gpio_chip.ngpio; ++irq) {
- irq_set_lockdep_class(irq, &gpio_lock_class);
- irq_set_chip_data(irq, chip);
- irq_set_chip_and_handler(irq, &jz_gpio_irq_chip,
- handle_level_irq);
- }
+ gc = irq_alloc_generic_chip(chip->gpio_chip.label, 1, chip->irq_base,
+ chip->base, handle_level_irq);
+
+ gc->wake_enabled = IRQ_MSK(chip->gpio_chip.ngpio);
+ gc->private = chip;
+
+ ct = gc->chip_types;
+ ct->regs.enable = JZ_REG_GPIO_MASK_CLEAR;
+ ct->regs.disable = JZ_REG_GPIO_MASK_SET;
+ ct->regs.ack = JZ_REG_GPIO_FLAG_CLEAR;
+
+ ct->chip.name = "GPIO";
+ ct->chip.irq_mask = irq_gc_mask_disable_reg;
+ ct->chip.irq_unmask = jz_gpio_irq_unmask;
+ ct->chip.irq_ack = irq_gc_ack_set_bit;
+ ct->chip.irq_suspend = jz4740_irq_suspend;
+ ct->chip.irq_resume = jz4740_irq_resume;
+ ct->chip.irq_startup = jz_gpio_irq_startup;
+ ct->chip.irq_shutdown = jz_gpio_irq_shutdown;
+ ct->chip.irq_set_type = jz_gpio_irq_set_type;
+ ct->chip.irq_set_wake = jz_gpio_irq_set_wake;
+ ct->chip.flags = IRQCHIP_SET_TYPE_MASKED;
+
+ irq_setup_generic_chip(gc, IRQ_MSK(chip->gpio_chip.ngpio),
+ IRQ_GC_INIT_NESTED_LOCK, 0, IRQ_NOPROBE | IRQ_LEVEL);
+
+ gpiochip_add(&chip->gpio_chip);
}
static int __init jz4740_gpio_init(void)
@@ -525,8 +463,6 @@
for (i = 0; i < ARRAY_SIZE(jz4740_gpio_chips); ++i)
jz4740_gpio_chip_init(&jz4740_gpio_chips[i], i);
- register_syscore_ops(&jz4740_gpio_syscore_ops);
-
printk(KERN_INFO "JZ4740 GPIO initialized\n");
return 0;
diff --git a/arch/mips/jz4740/irq.c b/arch/mips/jz4740/irq.c
index d82c0c4..fc57ded 100644
--- a/arch/mips/jz4740/irq.c
+++ b/arch/mips/jz4740/irq.c
@@ -32,8 +32,6 @@
#include <asm/mach-jz4740/base.h>
static void __iomem *jz_intc_base;
-static uint32_t jz_intc_wakeup;
-static uint32_t jz_intc_saved;
#define JZ_REG_INTC_STATUS 0x00
#define JZ_REG_INTC_MASK 0x04
@@ -41,41 +39,6 @@
#define JZ_REG_INTC_CLEAR_MASK 0x0c
#define JZ_REG_INTC_PENDING 0x10
-#define IRQ_BIT(x) BIT((x) - JZ4740_IRQ_BASE)
-
-static inline unsigned long intc_irq_bit(struct irq_data *data)
-{
- return (unsigned long)irq_data_get_irq_chip_data(data);
-}
-
-static void intc_irq_unmask(struct irq_data *data)
-{
- writel(intc_irq_bit(data), jz_intc_base + JZ_REG_INTC_CLEAR_MASK);
-}
-
-static void intc_irq_mask(struct irq_data *data)
-{
- writel(intc_irq_bit(data), jz_intc_base + JZ_REG_INTC_SET_MASK);
-}
-
-static int intc_irq_set_wake(struct irq_data *data, unsigned int on)
-{
- if (on)
- jz_intc_wakeup |= intc_irq_bit(data);
- else
- jz_intc_wakeup &= ~intc_irq_bit(data);
-
- return 0;
-}
-
-static struct irq_chip intc_irq_type = {
- .name = "INTC",
- .irq_mask = intc_irq_mask,
- .irq_mask_ack = intc_irq_mask,
- .irq_unmask = intc_irq_unmask,
- .irq_set_wake = intc_irq_set_wake,
-};
-
static irqreturn_t jz4740_cascade(int irq, void *data)
{
uint32_t irq_reg;
@@ -88,6 +51,26 @@
return IRQ_HANDLED;
}
+static void jz4740_irq_set_mask(struct irq_chip_generic *gc, uint32_t mask)
+{
+ struct irq_chip_regs *regs = &gc->chip_types->regs;
+
+ writel(mask, gc->reg_base + regs->enable);
+ writel(~mask, gc->reg_base + regs->disable);
+}
+
+void jz4740_irq_suspend(struct irq_data *data)
+{
+ struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
+ jz4740_irq_set_mask(gc, gc->wake_active);
+}
+
+void jz4740_irq_resume(struct irq_data *data)
+{
+ struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
+ jz4740_irq_set_mask(gc, gc->mask_cache);
+}
+
static struct irqaction jz4740_cascade_action = {
.handler = jz4740_cascade,
.name = "JZ4740 cascade interrupt",
@@ -95,7 +78,9 @@
void __init arch_init_irq(void)
{
- int i;
+ struct irq_chip_generic *gc;
+ struct irq_chip_type *ct;
+
mips_cpu_irq_init();
jz_intc_base = ioremap(JZ4740_INTC_BASE_ADDR, 0x14);
@@ -103,10 +88,22 @@
/* Mask all irqs */
writel(0xffffffff, jz_intc_base + JZ_REG_INTC_SET_MASK);
- for (i = JZ4740_IRQ_BASE; i < JZ4740_IRQ_BASE + 32; i++) {
- irq_set_chip_data(i, (void *)IRQ_BIT(i));
- irq_set_chip_and_handler(i, &intc_irq_type, handle_level_irq);
- }
+ gc = irq_alloc_generic_chip("INTC", 1, JZ4740_IRQ_BASE, jz_intc_base,
+ handle_level_irq);
+
+ gc->wake_enabled = IRQ_MSK(32);
+
+ ct = gc->chip_types;
+ ct->regs.enable = JZ_REG_INTC_CLEAR_MASK;
+ ct->regs.disable = JZ_REG_INTC_SET_MASK;
+ ct->chip.irq_unmask = irq_gc_unmask_enable_reg;
+ ct->chip.irq_mask = irq_gc_mask_disable_reg;
+ ct->chip.irq_mask_ack = irq_gc_mask_disable_reg;
+ ct->chip.irq_set_wake = irq_gc_set_wake;
+ ct->chip.irq_suspend = jz4740_irq_suspend;
+ ct->chip.irq_resume = jz4740_irq_resume;
+
+ irq_setup_generic_chip(gc, IRQ_MSK(32), 0, 0, IRQ_NOPROBE | IRQ_LEVEL);
setup_irq(2, &jz4740_cascade_action);
}
@@ -122,19 +119,6 @@
spurious_interrupt();
}
-void jz4740_intc_suspend(void)
-{
- jz_intc_saved = readl(jz_intc_base + JZ_REG_INTC_MASK);
- writel(~jz_intc_wakeup, jz_intc_base + JZ_REG_INTC_SET_MASK);
- writel(jz_intc_wakeup, jz_intc_base + JZ_REG_INTC_CLEAR_MASK);
-}
-
-void jz4740_intc_resume(void)
-{
- writel(~jz_intc_saved, jz_intc_base + JZ_REG_INTC_CLEAR_MASK);
- writel(jz_intc_saved, jz_intc_base + JZ_REG_INTC_SET_MASK);
-}
-
#ifdef CONFIG_DEBUG_FS
static inline void intc_seq_reg(struct seq_file *s, const char *name,
diff --git a/arch/mips/jz4740/irq.h b/arch/mips/jz4740/irq.h
index 56b5ead..f75e39d 100644
--- a/arch/mips/jz4740/irq.h
+++ b/arch/mips/jz4740/irq.h
@@ -15,7 +15,9 @@
#ifndef __MIPS_JZ4740_IRQ_H__
#define __MIPS_JZ4740_IRQ_H__
-extern void jz4740_intc_suspend(void);
-extern void jz4740_intc_resume(void);
+#include <linux/irq.h>
+
+extern void jz4740_irq_suspend(struct irq_data *data);
+extern void jz4740_irq_resume(struct irq_data *data);
#endif
diff --git a/arch/mips/jz4740/pm.c b/arch/mips/jz4740/pm.c
index 902d5b5..6744fa7 100644
--- a/arch/mips/jz4740/pm.c
+++ b/arch/mips/jz4740/pm.c
@@ -21,11 +21,9 @@
#include <asm/mach-jz4740/clock.h>
#include "clock.h"
-#include "irq.h"
static int jz4740_pm_enter(suspend_state_t state)
{
- jz4740_intc_suspend();
jz4740_clock_suspend();
jz4740_clock_set_wait_mode(JZ4740_WAIT_MODE_SLEEP);
@@ -37,7 +35,6 @@
jz4740_clock_set_wait_mode(JZ4740_WAIT_MODE_IDLE);
jz4740_clock_resume();
- jz4740_intc_resume();
return 0;
}
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 83bba33..1a96618 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -11,6 +11,8 @@
ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_ftrace.o = -pg
CFLAGS_REMOVE_early_printk.o = -pg
+CFLAGS_REMOVE_perf_event.o = -pg
+CFLAGS_REMOVE_perf_event_mipsxx.o = -pg
endif
obj-$(CONFIG_CEVT_BCM1480) += cevt-bcm1480.o
@@ -106,7 +108,8 @@
obj-$(CONFIG_MIPS_CPUFREQ) += cpufreq/
-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_HW_PERF_EVENTS) += perf_event_mipsxx.o
obj-$(CONFIG_JUMP_LABEL) += jump_label.o
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index ebc0cd2..aa327a7 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -978,7 +978,10 @@
platform:
set_elf_platform(cpu, "octeon");
break;
+ case PRID_IMP_CAVIUM_CN61XX:
case PRID_IMP_CAVIUM_CN63XX:
+ case PRID_IMP_CAVIUM_CN66XX:
+ case PRID_IMP_CAVIUM_CN68XX:
c->cputype = CPU_CAVIUM_OCTEON2;
__cpu_name[cpu] = "Cavium Octeon II";
set_elf_platform(cpu, "octeon2");
diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c
index 0aee944..c1cf9c6 100644
--- a/arch/mips/kernel/perf_event.c
+++ b/arch/mips/kernel/perf_event.c
@@ -14,533 +14,16 @@
* published by the Free Software Foundation.
*/
-#include <linux/cpumask.h>
-#include <linux/interrupt.h>
-#include <linux/smp.h>
-#include <linux/kernel.h>
#include <linux/perf_event.h>
-#include <linux/uaccess.h>
-#include <asm/irq.h>
-#include <asm/irq_regs.h>
#include <asm/stacktrace.h>
-#include <asm/time.h> /* For perf_irq */
-
-/* These are for 32bit counters. For 64bit ones, define them accordingly. */
-#define MAX_PERIOD ((1ULL << 32) - 1)
-#define VALID_COUNT 0x7fffffff
-#define TOTAL_BITS 32
-#define HIGHEST_BIT 31
-
-#define MIPS_MAX_HWEVENTS 4
-
-struct cpu_hw_events {
- /* Array of events on this cpu. */
- struct perf_event *events[MIPS_MAX_HWEVENTS];
-
- /*
- * Set the bit (indexed by the counter number) when the counter
- * is used for an event.
- */
- unsigned long used_mask[BITS_TO_LONGS(MIPS_MAX_HWEVENTS)];
-
- /*
- * The borrowed MSB for the performance counter. A MIPS performance
- * counter uses its bit 31 (for 32bit counters) or bit 63 (for 64bit
- * counters) as a factor of determining whether a counter overflow
- * should be signaled. So here we use a separate MSB for each
- * counter to make things easy.
- */
- unsigned long msbs[BITS_TO_LONGS(MIPS_MAX_HWEVENTS)];
-
- /*
- * Software copy of the control register for each performance counter.
- * MIPS CPUs vary in performance counters. They use this differently,
- * and even may not use it.
- */
- unsigned int saved_ctrl[MIPS_MAX_HWEVENTS];
-};
-DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
- .saved_ctrl = {0},
-};
-
-/* The description of MIPS performance events. */
-struct mips_perf_event {
- unsigned int event_id;
- /*
- * MIPS performance counters are indexed starting from 0.
- * CNTR_EVEN indicates the indexes of the counters to be used are
- * even numbers.
- */
- unsigned int cntr_mask;
- #define CNTR_EVEN 0x55555555
- #define CNTR_ODD 0xaaaaaaaa
-#ifdef CONFIG_MIPS_MT_SMP
- enum {
- T = 0,
- V = 1,
- P = 2,
- } range;
-#else
- #define T
- #define V
- #define P
-#endif
-};
-
-static struct mips_perf_event raw_event;
-static DEFINE_MUTEX(raw_event_mutex);
-
-#define UNSUPPORTED_PERF_EVENT_ID 0xffffffff
-#define C(x) PERF_COUNT_HW_CACHE_##x
-
-struct mips_pmu {
- const char *name;
- int irq;
- irqreturn_t (*handle_irq)(int irq, void *dev);
- int (*handle_shared_irq)(void);
- void (*start)(void);
- void (*stop)(void);
- int (*alloc_counter)(struct cpu_hw_events *cpuc,
- struct hw_perf_event *hwc);
- u64 (*read_counter)(unsigned int idx);
- void (*write_counter)(unsigned int idx, u64 val);
- void (*enable_event)(struct hw_perf_event *evt, int idx);
- void (*disable_event)(int idx);
- const struct mips_perf_event *(*map_raw_event)(u64 config);
- const struct mips_perf_event (*general_event_map)[PERF_COUNT_HW_MAX];
- const struct mips_perf_event (*cache_event_map)
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX];
- unsigned int num_counters;
-};
-
-static const struct mips_pmu *mipspmu;
-
-static int
-mipspmu_event_set_period(struct perf_event *event,
- struct hw_perf_event *hwc,
- int idx)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- s64 left = local64_read(&hwc->period_left);
- s64 period = hwc->sample_period;
- int ret = 0;
- u64 uleft;
- unsigned long flags;
-
- if (unlikely(left <= -period)) {
- left = period;
- local64_set(&hwc->period_left, left);
- hwc->last_period = period;
- ret = 1;
- }
-
- if (unlikely(left <= 0)) {
- left += period;
- local64_set(&hwc->period_left, left);
- hwc->last_period = period;
- ret = 1;
- }
-
- if (left > (s64)MAX_PERIOD)
- left = MAX_PERIOD;
-
- local64_set(&hwc->prev_count, (u64)-left);
-
- local_irq_save(flags);
- uleft = (u64)(-left) & MAX_PERIOD;
- uleft > VALID_COUNT ?
- set_bit(idx, cpuc->msbs) : clear_bit(idx, cpuc->msbs);
- mipspmu->write_counter(idx, (u64)(-left) & VALID_COUNT);
- local_irq_restore(flags);
-
- perf_event_update_userpage(event);
-
- return ret;
-}
-
-static void mipspmu_event_update(struct perf_event *event,
- struct hw_perf_event *hwc,
- int idx)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- unsigned long flags;
- int shift = 64 - TOTAL_BITS;
- s64 prev_raw_count, new_raw_count;
- u64 delta;
-
-again:
- prev_raw_count = local64_read(&hwc->prev_count);
- local_irq_save(flags);
- /* Make the counter value be a "real" one. */
- new_raw_count = mipspmu->read_counter(idx);
- if (new_raw_count & (test_bit(idx, cpuc->msbs) << HIGHEST_BIT)) {
- new_raw_count &= VALID_COUNT;
- clear_bit(idx, cpuc->msbs);
- } else
- new_raw_count |= (test_bit(idx, cpuc->msbs) << HIGHEST_BIT);
- local_irq_restore(flags);
-
- if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
- new_raw_count) != prev_raw_count)
- goto again;
-
- delta = (new_raw_count << shift) - (prev_raw_count << shift);
- delta >>= shift;
-
- local64_add(delta, &event->count);
- local64_sub(delta, &hwc->period_left);
-}
-
-static void mipspmu_start(struct perf_event *event, int flags)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- if (!mipspmu)
- return;
-
- if (flags & PERF_EF_RELOAD)
- WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
-
- hwc->state = 0;
-
- /* Set the period for the event. */
- mipspmu_event_set_period(event, hwc, hwc->idx);
-
- /* Enable the event. */
- mipspmu->enable_event(hwc, hwc->idx);
-}
-
-static void mipspmu_stop(struct perf_event *event, int flags)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- if (!mipspmu)
- return;
-
- if (!(hwc->state & PERF_HES_STOPPED)) {
- /* We are working on a local event. */
- mipspmu->disable_event(hwc->idx);
- barrier();
- mipspmu_event_update(event, hwc, hwc->idx);
- hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
- }
-}
-
-static int mipspmu_add(struct perf_event *event, int flags)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct hw_perf_event *hwc = &event->hw;
- int idx;
- int err = 0;
-
- perf_pmu_disable(event->pmu);
-
- /* To look for a free counter for this event. */
- idx = mipspmu->alloc_counter(cpuc, hwc);
- if (idx < 0) {
- err = idx;
- goto out;
- }
-
- /*
- * If there is an event in the counter we are going to use then
- * make sure it is disabled.
- */
- event->hw.idx = idx;
- mipspmu->disable_event(idx);
- cpuc->events[idx] = event;
-
- hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
- if (flags & PERF_EF_START)
- mipspmu_start(event, PERF_EF_RELOAD);
-
- /* Propagate our changes to the userspace mapping. */
- perf_event_update_userpage(event);
-
-out:
- perf_pmu_enable(event->pmu);
- return err;
-}
-
-static void mipspmu_del(struct perf_event *event, int flags)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct hw_perf_event *hwc = &event->hw;
- int idx = hwc->idx;
-
- WARN_ON(idx < 0 || idx >= mipspmu->num_counters);
-
- mipspmu_stop(event, PERF_EF_UPDATE);
- cpuc->events[idx] = NULL;
- clear_bit(idx, cpuc->used_mask);
-
- perf_event_update_userpage(event);
-}
-
-static void mipspmu_read(struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- /* Don't read disabled counters! */
- if (hwc->idx < 0)
- return;
-
- mipspmu_event_update(event, hwc, hwc->idx);
-}
-
-static void mipspmu_enable(struct pmu *pmu)
-{
- if (mipspmu)
- mipspmu->start();
-}
-
-static void mipspmu_disable(struct pmu *pmu)
-{
- if (mipspmu)
- mipspmu->stop();
-}
-
-static atomic_t active_events = ATOMIC_INIT(0);
-static DEFINE_MUTEX(pmu_reserve_mutex);
-static int (*save_perf_irq)(void);
-
-static int mipspmu_get_irq(void)
-{
- int err;
-
- if (mipspmu->irq >= 0) {
- /* Request my own irq handler. */
- err = request_irq(mipspmu->irq, mipspmu->handle_irq,
- IRQF_DISABLED | IRQF_NOBALANCING,
- "mips_perf_pmu", NULL);
- if (err) {
- pr_warning("Unable to request IRQ%d for MIPS "
- "performance counters!\n", mipspmu->irq);
- }
- } else if (cp0_perfcount_irq < 0) {
- /*
- * We are sharing the irq number with the timer interrupt.
- */
- save_perf_irq = perf_irq;
- perf_irq = mipspmu->handle_shared_irq;
- err = 0;
- } else {
- pr_warning("The platform hasn't properly defined its "
- "interrupt controller.\n");
- err = -ENOENT;
- }
-
- return err;
-}
-
-static void mipspmu_free_irq(void)
-{
- if (mipspmu->irq >= 0)
- free_irq(mipspmu->irq, NULL);
- else if (cp0_perfcount_irq < 0)
- perf_irq = save_perf_irq;
-}
-
-/*
- * mipsxx/rm9000/loongson2 have different performance counters, they have
- * specific low-level init routines.
- */
-static void reset_counters(void *arg);
-static int __hw_perf_event_init(struct perf_event *event);
-
-static void hw_perf_event_destroy(struct perf_event *event)
-{
- if (atomic_dec_and_mutex_lock(&active_events,
- &pmu_reserve_mutex)) {
- /*
- * We must not call the destroy function with interrupts
- * disabled.
- */
- on_each_cpu(reset_counters,
- (void *)(long)mipspmu->num_counters, 1);
- mipspmu_free_irq();
- mutex_unlock(&pmu_reserve_mutex);
- }
-}
-
-static int mipspmu_event_init(struct perf_event *event)
-{
- int err = 0;
-
- switch (event->attr.type) {
- case PERF_TYPE_RAW:
- case PERF_TYPE_HARDWARE:
- case PERF_TYPE_HW_CACHE:
- break;
-
- default:
- return -ENOENT;
- }
-
- if (!mipspmu || event->cpu >= nr_cpumask_bits ||
- (event->cpu >= 0 && !cpu_online(event->cpu)))
- return -ENODEV;
-
- if (!atomic_inc_not_zero(&active_events)) {
- if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
- atomic_dec(&active_events);
- return -ENOSPC;
- }
-
- mutex_lock(&pmu_reserve_mutex);
- if (atomic_read(&active_events) == 0)
- err = mipspmu_get_irq();
-
- if (!err)
- atomic_inc(&active_events);
- mutex_unlock(&pmu_reserve_mutex);
- }
-
- if (err)
- return err;
-
- err = __hw_perf_event_init(event);
- if (err)
- hw_perf_event_destroy(event);
-
- return err;
-}
-
-static struct pmu pmu = {
- .pmu_enable = mipspmu_enable,
- .pmu_disable = mipspmu_disable,
- .event_init = mipspmu_event_init,
- .add = mipspmu_add,
- .del = mipspmu_del,
- .start = mipspmu_start,
- .stop = mipspmu_stop,
- .read = mipspmu_read,
-};
-
-static inline unsigned int
-mipspmu_perf_event_encode(const struct mips_perf_event *pev)
-{
-/*
- * Top 8 bits for range, next 16 bits for cntr_mask, lowest 8 bits for
- * event_id.
- */
-#ifdef CONFIG_MIPS_MT_SMP
- return ((unsigned int)pev->range << 24) |
- (pev->cntr_mask & 0xffff00) |
- (pev->event_id & 0xff);
-#else
- return (pev->cntr_mask & 0xffff00) |
- (pev->event_id & 0xff);
-#endif
-}
-
-static const struct mips_perf_event *
-mipspmu_map_general_event(int idx)
-{
- const struct mips_perf_event *pev;
-
- pev = ((*mipspmu->general_event_map)[idx].event_id ==
- UNSUPPORTED_PERF_EVENT_ID ? ERR_PTR(-EOPNOTSUPP) :
- &(*mipspmu->general_event_map)[idx]);
-
- return pev;
-}
-
-static const struct mips_perf_event *
-mipspmu_map_cache_event(u64 config)
-{
- unsigned int cache_type, cache_op, cache_result;
- const struct mips_perf_event *pev;
-
- cache_type = (config >> 0) & 0xff;
- if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
- return ERR_PTR(-EINVAL);
-
- cache_op = (config >> 8) & 0xff;
- if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
- return ERR_PTR(-EINVAL);
-
- cache_result = (config >> 16) & 0xff;
- if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
- return ERR_PTR(-EINVAL);
-
- pev = &((*mipspmu->cache_event_map)
- [cache_type]
- [cache_op]
- [cache_result]);
-
- if (pev->event_id == UNSUPPORTED_PERF_EVENT_ID)
- return ERR_PTR(-EOPNOTSUPP);
-
- return pev;
-
-}
-
-static int validate_event(struct cpu_hw_events *cpuc,
- struct perf_event *event)
-{
- struct hw_perf_event fake_hwc = event->hw;
-
- /* Allow mixed event group. So return 1 to pass validation. */
- if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
- return 1;
-
- return mipspmu->alloc_counter(cpuc, &fake_hwc) >= 0;
-}
-
-static int validate_group(struct perf_event *event)
-{
- struct perf_event *sibling, *leader = event->group_leader;
- struct cpu_hw_events fake_cpuc;
-
- memset(&fake_cpuc, 0, sizeof(fake_cpuc));
-
- if (!validate_event(&fake_cpuc, leader))
- return -ENOSPC;
-
- list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
- if (!validate_event(&fake_cpuc, sibling))
- return -ENOSPC;
- }
-
- if (!validate_event(&fake_cpuc, event))
- return -ENOSPC;
-
- return 0;
-}
-
-/* This is needed by specific irq handlers in perf_event_*.c */
-static void
-handle_associated_event(struct cpu_hw_events *cpuc,
- int idx, struct perf_sample_data *data, struct pt_regs *regs)
-{
- struct perf_event *event = cpuc->events[idx];
- struct hw_perf_event *hwc = &event->hw;
-
- mipspmu_event_update(event, hwc, idx);
- data->period = event->hw.last_period;
- if (!mipspmu_event_set_period(event, hwc, idx))
- return;
-
- if (perf_event_overflow(event, data, regs))
- mipspmu->disable_event(idx);
-}
-
-#include "perf_event_mipsxx.c"
/* Callchain handling code. */
/*
* Leave userspace callchain empty for now. When we find a way to trace
- * the user stack callchains, we add here.
+ * the user stack callchains, we will add it here.
*/
-void perf_callchain_user(struct perf_callchain_entry *entry,
- struct pt_regs *regs)
-{
-}
static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
unsigned long reg29)
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index e5ad09a..4f2971b 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -1,13 +1,112 @@
-#if defined(CONFIG_CPU_MIPS32) || defined(CONFIG_CPU_MIPS64) || \
- defined(CONFIG_CPU_R10000) || defined(CONFIG_CPU_SB1)
+/*
+ * Linux performance counter support for MIPS.
+ *
+ * Copyright (C) 2010 MIPS Technologies, Inc.
+ * Copyright (C) 2011 Cavium Networks, Inc.
+ * Author: Deng-Cheng Zhu
+ *
+ * This code is based on the implementation for ARM, which is in turn
+ * based on the sparc64 perf event code and the x86 code. Performance
+ * counter access is based on the MIPS Oprofile code. And the callchain
+ * support references the code of MIPS stacktrace.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/cpumask.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+
+#include <asm/irq.h>
+#include <asm/irq_regs.h>
+#include <asm/stacktrace.h>
+#include <asm/time.h> /* For perf_irq */
+
+#define MIPS_MAX_HWEVENTS 4
+
+struct cpu_hw_events {
+ /* Array of events on this cpu. */
+ struct perf_event *events[MIPS_MAX_HWEVENTS];
+
+ /*
+ * Set the bit (indexed by the counter number) when the counter
+ * is used for an event.
+ */
+ unsigned long used_mask[BITS_TO_LONGS(MIPS_MAX_HWEVENTS)];
+
+ /*
+ * Software copy of the control register for each performance counter.
+ * MIPS CPUs vary in performance counters. They use this differently,
+ * and even may not use it.
+ */
+ unsigned int saved_ctrl[MIPS_MAX_HWEVENTS];
+};
+DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
+ .saved_ctrl = {0},
+};
+
+/* The description of MIPS performance events. */
+struct mips_perf_event {
+ unsigned int event_id;
+ /*
+ * MIPS performance counters are indexed starting from 0.
+ * CNTR_EVEN indicates the indexes of the counters to be used are
+ * even numbers.
+ */
+ unsigned int cntr_mask;
+ #define CNTR_EVEN 0x55555555
+ #define CNTR_ODD 0xaaaaaaaa
+ #define CNTR_ALL 0xffffffff
+#ifdef CONFIG_MIPS_MT_SMP
+ enum {
+ T = 0,
+ V = 1,
+ P = 2,
+ } range;
+#else
+ #define T
+ #define V
+ #define P
+#endif
+};
+
+static struct mips_perf_event raw_event;
+static DEFINE_MUTEX(raw_event_mutex);
+
+#define UNSUPPORTED_PERF_EVENT_ID 0xffffffff
+#define C(x) PERF_COUNT_HW_CACHE_##x
+
+struct mips_pmu {
+ u64 max_period;
+ u64 valid_count;
+ u64 overflow;
+ const char *name;
+ int irq;
+ u64 (*read_counter)(unsigned int idx);
+ void (*write_counter)(unsigned int idx, u64 val);
+ const struct mips_perf_event *(*map_raw_event)(u64 config);
+ const struct mips_perf_event (*general_event_map)[PERF_COUNT_HW_MAX];
+ const struct mips_perf_event (*cache_event_map)
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX];
+ unsigned int num_counters;
+};
+
+static struct mips_pmu mipspmu;
#define M_CONFIG1_PC (1 << 4)
-#define M_PERFCTL_EXL (1UL << 0)
-#define M_PERFCTL_KERNEL (1UL << 1)
-#define M_PERFCTL_SUPERVISOR (1UL << 2)
-#define M_PERFCTL_USER (1UL << 3)
-#define M_PERFCTL_INTERRUPT_ENABLE (1UL << 4)
+#define M_PERFCTL_EXL (1 << 0)
+#define M_PERFCTL_KERNEL (1 << 1)
+#define M_PERFCTL_SUPERVISOR (1 << 2)
+#define M_PERFCTL_USER (1 << 3)
+#define M_PERFCTL_INTERRUPT_ENABLE (1 << 4)
#define M_PERFCTL_EVENT(event) (((event) & 0x3ff) << 5)
#define M_PERFCTL_VPEID(vpe) ((vpe) << 16)
#define M_PERFCTL_MT_EN(filter) ((filter) << 20)
@@ -15,8 +114,8 @@
#define M_TC_EN_VPE M_PERFCTL_MT_EN(1)
#define M_TC_EN_TC M_PERFCTL_MT_EN(2)
#define M_PERFCTL_TCID(tcid) ((tcid) << 22)
-#define M_PERFCTL_WIDE (1UL << 30)
-#define M_PERFCTL_MORE (1UL << 31)
+#define M_PERFCTL_WIDE (1 << 30)
+#define M_PERFCTL_MORE (1 << 31)
#define M_PERFCTL_COUNT_EVENT_WHENEVER (M_PERFCTL_EXL | \
M_PERFCTL_KERNEL | \
@@ -31,11 +130,12 @@
#endif
#define M_PERFCTL_EVENT_MASK 0xfe0
-#define M_COUNTER_OVERFLOW (1UL << 31)
#ifdef CONFIG_MIPS_MT_SMP
static int cpu_has_mipsmt_pertccounters;
+static DEFINE_RWLOCK(pmuint_rwlock);
+
/*
* FIXME: For VSMP, vpe_id() is redefined for Perf-events, because
* cpu_data[cpuid].vpe_id reports 0 for _both_ CPUs.
@@ -49,79 +149,621 @@
#endif
/* Copied from op_model_mipsxx.c */
-static inline unsigned int vpe_shift(void)
+static unsigned int vpe_shift(void)
{
if (num_possible_cpus() > 1)
return 1;
return 0;
}
-#else /* !CONFIG_MIPS_MT_SMP */
-#define vpe_id() 0
-static inline unsigned int vpe_shift(void)
-{
- return 0;
-}
-#endif /* CONFIG_MIPS_MT_SMP */
-
-static inline unsigned int
-counters_total_to_per_cpu(unsigned int counters)
+static unsigned int counters_total_to_per_cpu(unsigned int counters)
{
return counters >> vpe_shift();
}
-static inline unsigned int
-counters_per_cpu_to_total(unsigned int counters)
+static unsigned int counters_per_cpu_to_total(unsigned int counters)
{
return counters << vpe_shift();
}
-#define __define_perf_accessors(r, n, np) \
- \
-static inline unsigned int r_c0_ ## r ## n(void) \
-{ \
- unsigned int cpu = vpe_id(); \
- \
- switch (cpu) { \
- case 0: \
- return read_c0_ ## r ## n(); \
- case 1: \
- return read_c0_ ## r ## np(); \
- default: \
- BUG(); \
- } \
- return 0; \
-} \
- \
-static inline void w_c0_ ## r ## n(unsigned int value) \
-{ \
- unsigned int cpu = vpe_id(); \
- \
- switch (cpu) { \
- case 0: \
- write_c0_ ## r ## n(value); \
- return; \
- case 1: \
- write_c0_ ## r ## np(value); \
- return; \
- default: \
- BUG(); \
- } \
- return; \
-} \
+#else /* !CONFIG_MIPS_MT_SMP */
+#define vpe_id() 0
-__define_perf_accessors(perfcntr, 0, 2)
-__define_perf_accessors(perfcntr, 1, 3)
-__define_perf_accessors(perfcntr, 2, 0)
-__define_perf_accessors(perfcntr, 3, 1)
+#endif /* CONFIG_MIPS_MT_SMP */
-__define_perf_accessors(perfctrl, 0, 2)
-__define_perf_accessors(perfctrl, 1, 3)
-__define_perf_accessors(perfctrl, 2, 0)
-__define_perf_accessors(perfctrl, 3, 1)
+static void resume_local_counters(void);
+static void pause_local_counters(void);
+static irqreturn_t mipsxx_pmu_handle_irq(int, void *);
+static int mipsxx_pmu_handle_shared_irq(void);
-static inline int __n_counters(void)
+static unsigned int mipsxx_pmu_swizzle_perf_idx(unsigned int idx)
+{
+ if (vpe_id() == 1)
+ idx = (idx + 2) & 3;
+ return idx;
+}
+
+static u64 mipsxx_pmu_read_counter(unsigned int idx)
+{
+ idx = mipsxx_pmu_swizzle_perf_idx(idx);
+
+ switch (idx) {
+ case 0:
+ /*
+ * The counters are unsigned, we must cast to truncate
+ * off the high bits.
+ */
+ return (u32)read_c0_perfcntr0();
+ case 1:
+ return (u32)read_c0_perfcntr1();
+ case 2:
+ return (u32)read_c0_perfcntr2();
+ case 3:
+ return (u32)read_c0_perfcntr3();
+ default:
+ WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+ return 0;
+ }
+}
+
+static u64 mipsxx_pmu_read_counter_64(unsigned int idx)
+{
+ idx = mipsxx_pmu_swizzle_perf_idx(idx);
+
+ switch (idx) {
+ case 0:
+ return read_c0_perfcntr0_64();
+ case 1:
+ return read_c0_perfcntr1_64();
+ case 2:
+ return read_c0_perfcntr2_64();
+ case 3:
+ return read_c0_perfcntr3_64();
+ default:
+ WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+ return 0;
+ }
+}
+
+static void mipsxx_pmu_write_counter(unsigned int idx, u64 val)
+{
+ idx = mipsxx_pmu_swizzle_perf_idx(idx);
+
+ switch (idx) {
+ case 0:
+ write_c0_perfcntr0(val);
+ return;
+ case 1:
+ write_c0_perfcntr1(val);
+ return;
+ case 2:
+ write_c0_perfcntr2(val);
+ return;
+ case 3:
+ write_c0_perfcntr3(val);
+ return;
+ }
+}
+
+static void mipsxx_pmu_write_counter_64(unsigned int idx, u64 val)
+{
+ idx = mipsxx_pmu_swizzle_perf_idx(idx);
+
+ switch (idx) {
+ case 0:
+ write_c0_perfcntr0_64(val);
+ return;
+ case 1:
+ write_c0_perfcntr1_64(val);
+ return;
+ case 2:
+ write_c0_perfcntr2_64(val);
+ return;
+ case 3:
+ write_c0_perfcntr3_64(val);
+ return;
+ }
+}
+
+static unsigned int mipsxx_pmu_read_control(unsigned int idx)
+{
+ idx = mipsxx_pmu_swizzle_perf_idx(idx);
+
+ switch (idx) {
+ case 0:
+ return read_c0_perfctrl0();
+ case 1:
+ return read_c0_perfctrl1();
+ case 2:
+ return read_c0_perfctrl2();
+ case 3:
+ return read_c0_perfctrl3();
+ default:
+ WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+ return 0;
+ }
+}
+
+static void mipsxx_pmu_write_control(unsigned int idx, unsigned int val)
+{
+ idx = mipsxx_pmu_swizzle_perf_idx(idx);
+
+ switch (idx) {
+ case 0:
+ write_c0_perfctrl0(val);
+ return;
+ case 1:
+ write_c0_perfctrl1(val);
+ return;
+ case 2:
+ write_c0_perfctrl2(val);
+ return;
+ case 3:
+ write_c0_perfctrl3(val);
+ return;
+ }
+}
+
+static int mipsxx_pmu_alloc_counter(struct cpu_hw_events *cpuc,
+ struct hw_perf_event *hwc)
+{
+ int i;
+
+ /*
+ * We only need to care the counter mask. The range has been
+ * checked definitely.
+ */
+ unsigned long cntr_mask = (hwc->event_base >> 8) & 0xffff;
+
+ for (i = mipspmu.num_counters - 1; i >= 0; i--) {
+ /*
+ * Note that some MIPS perf events can be counted by both
+ * even and odd counters, wheresas many other are only by
+ * even _or_ odd counters. This introduces an issue that
+ * when the former kind of event takes the counter the
+ * latter kind of event wants to use, then the "counter
+ * allocation" for the latter event will fail. In fact if
+ * they can be dynamically swapped, they both feel happy.
+ * But here we leave this issue alone for now.
+ */
+ if (test_bit(i, &cntr_mask) &&
+ !test_and_set_bit(i, cpuc->used_mask))
+ return i;
+ }
+
+ return -EAGAIN;
+}
+
+static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+ WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
+
+ cpuc->saved_ctrl[idx] = M_PERFCTL_EVENT(evt->event_base & 0xff) |
+ (evt->config_base & M_PERFCTL_CONFIG_MASK) |
+ /* Make sure interrupt enabled. */
+ M_PERFCTL_INTERRUPT_ENABLE;
+ /*
+ * We do not actually let the counter run. Leave it until start().
+ */
+}
+
+static void mipsxx_pmu_disable_event(int idx)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ unsigned long flags;
+
+ WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
+
+ local_irq_save(flags);
+ cpuc->saved_ctrl[idx] = mipsxx_pmu_read_control(idx) &
+ ~M_PERFCTL_COUNT_EVENT_WHENEVER;
+ mipsxx_pmu_write_control(idx, cpuc->saved_ctrl[idx]);
+ local_irq_restore(flags);
+}
+
+static int mipspmu_event_set_period(struct perf_event *event,
+ struct hw_perf_event *hwc,
+ int idx)
+{
+ u64 left = local64_read(&hwc->period_left);
+ u64 period = hwc->sample_period;
+ int ret = 0;
+
+ if (unlikely((left + period) & (1ULL << 63))) {
+ /* left underflowed by more than period. */
+ left = period;
+ local64_set(&hwc->period_left, left);
+ hwc->last_period = period;
+ ret = 1;
+ } else if (unlikely((left + period) <= period)) {
+ /* left underflowed by less than period. */
+ left += period;
+ local64_set(&hwc->period_left, left);
+ hwc->last_period = period;
+ ret = 1;
+ }
+
+ if (left > mipspmu.max_period) {
+ left = mipspmu.max_period;
+ local64_set(&hwc->period_left, left);
+ }
+
+ local64_set(&hwc->prev_count, mipspmu.overflow - left);
+
+ mipspmu.write_counter(idx, mipspmu.overflow - left);
+
+ perf_event_update_userpage(event);
+
+ return ret;
+}
+
+static void mipspmu_event_update(struct perf_event *event,
+ struct hw_perf_event *hwc,
+ int idx)
+{
+ u64 prev_raw_count, new_raw_count;
+ u64 delta;
+
+again:
+ prev_raw_count = local64_read(&hwc->prev_count);
+ new_raw_count = mipspmu.read_counter(idx);
+
+ if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+ new_raw_count) != prev_raw_count)
+ goto again;
+
+ delta = new_raw_count - prev_raw_count;
+
+ local64_add(delta, &event->count);
+ local64_sub(delta, &hwc->period_left);
+}
+
+static void mipspmu_start(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (flags & PERF_EF_RELOAD)
+ WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+ hwc->state = 0;
+
+ /* Set the period for the event. */
+ mipspmu_event_set_period(event, hwc, hwc->idx);
+
+ /* Enable the event. */
+ mipsxx_pmu_enable_event(hwc, hwc->idx);
+}
+
+static void mipspmu_stop(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!(hwc->state & PERF_HES_STOPPED)) {
+ /* We are working on a local event. */
+ mipsxx_pmu_disable_event(hwc->idx);
+ barrier();
+ mipspmu_event_update(event, hwc, hwc->idx);
+ hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+ }
+}
+
+static int mipspmu_add(struct perf_event *event, int flags)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx;
+ int err = 0;
+
+ perf_pmu_disable(event->pmu);
+
+ /* To look for a free counter for this event. */
+ idx = mipsxx_pmu_alloc_counter(cpuc, hwc);
+ if (idx < 0) {
+ err = idx;
+ goto out;
+ }
+
+ /*
+ * If there is an event in the counter we are going to use then
+ * make sure it is disabled.
+ */
+ event->hw.idx = idx;
+ mipsxx_pmu_disable_event(idx);
+ cpuc->events[idx] = event;
+
+ hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+ if (flags & PERF_EF_START)
+ mipspmu_start(event, PERF_EF_RELOAD);
+
+ /* Propagate our changes to the userspace mapping. */
+ perf_event_update_userpage(event);
+
+out:
+ perf_pmu_enable(event->pmu);
+ return err;
+}
+
+static void mipspmu_del(struct perf_event *event, int flags)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+
+ WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
+
+ mipspmu_stop(event, PERF_EF_UPDATE);
+ cpuc->events[idx] = NULL;
+ clear_bit(idx, cpuc->used_mask);
+
+ perf_event_update_userpage(event);
+}
+
+static void mipspmu_read(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ /* Don't read disabled counters! */
+ if (hwc->idx < 0)
+ return;
+
+ mipspmu_event_update(event, hwc, hwc->idx);
+}
+
+static void mipspmu_enable(struct pmu *pmu)
+{
+#ifdef CONFIG_MIPS_MT_SMP
+ write_unlock(&pmuint_rwlock);
+#endif
+ resume_local_counters();
+}
+
+/*
+ * MIPS performance counters can be per-TC. The control registers can
+ * not be directly accessed accross CPUs. Hence if we want to do global
+ * control, we need cross CPU calls. on_each_cpu() can help us, but we
+ * can not make sure this function is called with interrupts enabled. So
+ * here we pause local counters and then grab a rwlock and leave the
+ * counters on other CPUs alone. If any counter interrupt raises while
+ * we own the write lock, simply pause local counters on that CPU and
+ * spin in the handler. Also we know we won't be switched to another
+ * CPU after pausing local counters and before grabbing the lock.
+ */
+static void mipspmu_disable(struct pmu *pmu)
+{
+ pause_local_counters();
+#ifdef CONFIG_MIPS_MT_SMP
+ write_lock(&pmuint_rwlock);
+#endif
+}
+
+static atomic_t active_events = ATOMIC_INIT(0);
+static DEFINE_MUTEX(pmu_reserve_mutex);
+static int (*save_perf_irq)(void);
+
+static int mipspmu_get_irq(void)
+{
+ int err;
+
+ if (mipspmu.irq >= 0) {
+ /* Request my own irq handler. */
+ err = request_irq(mipspmu.irq, mipsxx_pmu_handle_irq,
+ IRQF_PERCPU | IRQF_NOBALANCING,
+ "mips_perf_pmu", NULL);
+ if (err) {
+ pr_warning("Unable to request IRQ%d for MIPS "
+ "performance counters!\n", mipspmu.irq);
+ }
+ } else if (cp0_perfcount_irq < 0) {
+ /*
+ * We are sharing the irq number with the timer interrupt.
+ */
+ save_perf_irq = perf_irq;
+ perf_irq = mipsxx_pmu_handle_shared_irq;
+ err = 0;
+ } else {
+ pr_warning("The platform hasn't properly defined its "
+ "interrupt controller.\n");
+ err = -ENOENT;
+ }
+
+ return err;
+}
+
+static void mipspmu_free_irq(void)
+{
+ if (mipspmu.irq >= 0)
+ free_irq(mipspmu.irq, NULL);
+ else if (cp0_perfcount_irq < 0)
+ perf_irq = save_perf_irq;
+}
+
+/*
+ * mipsxx/rm9000/loongson2 have different performance counters, they have
+ * specific low-level init routines.
+ */
+static void reset_counters(void *arg);
+static int __hw_perf_event_init(struct perf_event *event);
+
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+ if (atomic_dec_and_mutex_lock(&active_events,
+ &pmu_reserve_mutex)) {
+ /*
+ * We must not call the destroy function with interrupts
+ * disabled.
+ */
+ on_each_cpu(reset_counters,
+ (void *)(long)mipspmu.num_counters, 1);
+ mipspmu_free_irq();
+ mutex_unlock(&pmu_reserve_mutex);
+ }
+}
+
+static int mipspmu_event_init(struct perf_event *event)
+{
+ int err = 0;
+
+ switch (event->attr.type) {
+ case PERF_TYPE_RAW:
+ case PERF_TYPE_HARDWARE:
+ case PERF_TYPE_HW_CACHE:
+ break;
+
+ default:
+ return -ENOENT;
+ }
+
+ if (event->cpu >= nr_cpumask_bits ||
+ (event->cpu >= 0 && !cpu_online(event->cpu)))
+ return -ENODEV;
+
+ if (!atomic_inc_not_zero(&active_events)) {
+ if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
+ atomic_dec(&active_events);
+ return -ENOSPC;
+ }
+
+ mutex_lock(&pmu_reserve_mutex);
+ if (atomic_read(&active_events) == 0)
+ err = mipspmu_get_irq();
+
+ if (!err)
+ atomic_inc(&active_events);
+ mutex_unlock(&pmu_reserve_mutex);
+ }
+
+ if (err)
+ return err;
+
+ err = __hw_perf_event_init(event);
+ if (err)
+ hw_perf_event_destroy(event);
+
+ return err;
+}
+
+static struct pmu pmu = {
+ .pmu_enable = mipspmu_enable,
+ .pmu_disable = mipspmu_disable,
+ .event_init = mipspmu_event_init,
+ .add = mipspmu_add,
+ .del = mipspmu_del,
+ .start = mipspmu_start,
+ .stop = mipspmu_stop,
+ .read = mipspmu_read,
+};
+
+static unsigned int mipspmu_perf_event_encode(const struct mips_perf_event *pev)
+{
+/*
+ * Top 8 bits for range, next 16 bits for cntr_mask, lowest 8 bits for
+ * event_id.
+ */
+#ifdef CONFIG_MIPS_MT_SMP
+ return ((unsigned int)pev->range << 24) |
+ (pev->cntr_mask & 0xffff00) |
+ (pev->event_id & 0xff);
+#else
+ return (pev->cntr_mask & 0xffff00) |
+ (pev->event_id & 0xff);
+#endif
+}
+
+static const struct mips_perf_event *mipspmu_map_general_event(int idx)
+{
+ const struct mips_perf_event *pev;
+
+ pev = ((*mipspmu.general_event_map)[idx].event_id ==
+ UNSUPPORTED_PERF_EVENT_ID ? ERR_PTR(-EOPNOTSUPP) :
+ &(*mipspmu.general_event_map)[idx]);
+
+ return pev;
+}
+
+static const struct mips_perf_event *mipspmu_map_cache_event(u64 config)
+{
+ unsigned int cache_type, cache_op, cache_result;
+ const struct mips_perf_event *pev;
+
+ cache_type = (config >> 0) & 0xff;
+ if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
+ return ERR_PTR(-EINVAL);
+
+ cache_op = (config >> 8) & 0xff;
+ if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
+ return ERR_PTR(-EINVAL);
+
+ cache_result = (config >> 16) & 0xff;
+ if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+ return ERR_PTR(-EINVAL);
+
+ pev = &((*mipspmu.cache_event_map)
+ [cache_type]
+ [cache_op]
+ [cache_result]);
+
+ if (pev->event_id == UNSUPPORTED_PERF_EVENT_ID)
+ return ERR_PTR(-EOPNOTSUPP);
+
+ return pev;
+
+}
+
+static int validate_event(struct cpu_hw_events *cpuc,
+ struct perf_event *event)
+{
+ struct hw_perf_event fake_hwc = event->hw;
+
+ /* Allow mixed event group. So return 1 to pass validation. */
+ if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
+ return 1;
+
+ return mipsxx_pmu_alloc_counter(cpuc, &fake_hwc) >= 0;
+}
+
+static int validate_group(struct perf_event *event)
+{
+ struct perf_event *sibling, *leader = event->group_leader;
+ struct cpu_hw_events fake_cpuc;
+
+ memset(&fake_cpuc, 0, sizeof(fake_cpuc));
+
+ if (!validate_event(&fake_cpuc, leader))
+ return -ENOSPC;
+
+ list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
+ if (!validate_event(&fake_cpuc, sibling))
+ return -ENOSPC;
+ }
+
+ if (!validate_event(&fake_cpuc, event))
+ return -ENOSPC;
+
+ return 0;
+}
+
+/* This is needed by specific irq handlers in perf_event_*.c */
+static void handle_associated_event(struct cpu_hw_events *cpuc,
+ int idx, struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ struct perf_event *event = cpuc->events[idx];
+ struct hw_perf_event *hwc = &event->hw;
+
+ mipspmu_event_update(event, hwc, idx);
+ data->period = event->hw.last_period;
+ if (!mipspmu_event_set_period(event, hwc, idx))
+ return;
+
+ if (perf_event_overflow(event, data, regs))
+ mipsxx_pmu_disable_event(idx);
+}
+
+
+static int __n_counters(void)
{
if (!(read_c0_config1() & M_CONFIG1_PC))
return 0;
@@ -135,7 +777,7 @@
return 4;
}
-static inline int n_counters(void)
+static int n_counters(void)
{
int counters;
@@ -161,98 +803,20 @@
int counters = (int)(long)arg;
switch (counters) {
case 4:
- w_c0_perfctrl3(0);
- w_c0_perfcntr3(0);
+ mipsxx_pmu_write_control(3, 0);
+ mipspmu.write_counter(3, 0);
case 3:
- w_c0_perfctrl2(0);
- w_c0_perfcntr2(0);
+ mipsxx_pmu_write_control(2, 0);
+ mipspmu.write_counter(2, 0);
case 2:
- w_c0_perfctrl1(0);
- w_c0_perfcntr1(0);
+ mipsxx_pmu_write_control(1, 0);
+ mipspmu.write_counter(1, 0);
case 1:
- w_c0_perfctrl0(0);
- w_c0_perfcntr0(0);
+ mipsxx_pmu_write_control(0, 0);
+ mipspmu.write_counter(0, 0);
}
}
-static inline u64
-mipsxx_pmu_read_counter(unsigned int idx)
-{
- switch (idx) {
- case 0:
- return r_c0_perfcntr0();
- case 1:
- return r_c0_perfcntr1();
- case 2:
- return r_c0_perfcntr2();
- case 3:
- return r_c0_perfcntr3();
- default:
- WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
- return 0;
- }
-}
-
-static inline void
-mipsxx_pmu_write_counter(unsigned int idx, u64 val)
-{
- switch (idx) {
- case 0:
- w_c0_perfcntr0(val);
- return;
- case 1:
- w_c0_perfcntr1(val);
- return;
- case 2:
- w_c0_perfcntr2(val);
- return;
- case 3:
- w_c0_perfcntr3(val);
- return;
- }
-}
-
-static inline unsigned int
-mipsxx_pmu_read_control(unsigned int idx)
-{
- switch (idx) {
- case 0:
- return r_c0_perfctrl0();
- case 1:
- return r_c0_perfctrl1();
- case 2:
- return r_c0_perfctrl2();
- case 3:
- return r_c0_perfctrl3();
- default:
- WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
- return 0;
- }
-}
-
-static inline void
-mipsxx_pmu_write_control(unsigned int idx, unsigned int val)
-{
- switch (idx) {
- case 0:
- w_c0_perfctrl0(val);
- return;
- case 1:
- w_c0_perfctrl1(val);
- return;
- case 2:
- w_c0_perfctrl2(val);
- return;
- case 3:
- w_c0_perfctrl3(val);
- return;
- }
-}
-
-#ifdef CONFIG_MIPS_MT_SMP
-static DEFINE_RWLOCK(pmuint_rwlock);
-#endif
-
/* 24K/34K/1004K cores can share the same event map. */
static const struct mips_perf_event mipsxxcore_event_map
[PERF_COUNT_HW_MAX] = {
@@ -277,6 +841,16 @@
[PERF_COUNT_HW_BUS_CYCLES] = { UNSUPPORTED_PERF_EVENT_ID },
};
+static const struct mips_perf_event octeon_event_map[PERF_COUNT_HW_MAX] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = { 0x01, CNTR_ALL },
+ [PERF_COUNT_HW_INSTRUCTIONS] = { 0x03, CNTR_ALL },
+ [PERF_COUNT_HW_CACHE_REFERENCES] = { 0x2b, CNTR_ALL },
+ [PERF_COUNT_HW_CACHE_MISSES] = { 0x2e, CNTR_ALL },
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { 0x08, CNTR_ALL },
+ [PERF_COUNT_HW_BRANCH_MISSES] = { 0x09, CNTR_ALL },
+ [PERF_COUNT_HW_BUS_CYCLES] = { 0x25, CNTR_ALL },
+};
+
/* 24K/34K/1004K cores can share the same cache event map. */
static const struct mips_perf_event mipsxxcore_cache_map
[PERF_COUNT_HW_CACHE_MAX]
@@ -510,10 +1084,105 @@
},
};
+
+static const struct mips_perf_event octeon_cache_map
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { 0x2b, CNTR_ALL },
+ [C(RESULT_MISS)] = { 0x2e, CNTR_ALL },
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = { 0x30, CNTR_ALL },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+},
+[C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { 0x18, CNTR_ALL },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = { 0x19, CNTR_ALL },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+},
+[C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+},
+[C(DTLB)] = {
+ /*
+ * Only general DTLB misses are counted use the same event for
+ * read and write.
+ */
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { 0x35, CNTR_ALL },
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { 0x35, CNTR_ALL },
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+},
+[C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { 0x37, CNTR_ALL },
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+},
+[C(BPU)] = {
+ /* Using the same code for *HW_BRANCH* */
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+},
+};
+
#ifdef CONFIG_MIPS_MT_SMP
-static void
-check_and_calc_range(struct perf_event *event,
- const struct mips_perf_event *pev)
+static void check_and_calc_range(struct perf_event *event,
+ const struct mips_perf_event *pev)
{
struct hw_perf_event *hwc = &event->hw;
@@ -536,9 +1205,8 @@
hwc->config_base |= M_TC_EN_ALL;
}
#else
-static void
-check_and_calc_range(struct perf_event *event,
- const struct mips_perf_event *pev)
+static void check_and_calc_range(struct perf_event *event,
+ const struct mips_perf_event *pev)
{
}
#endif
@@ -560,7 +1228,7 @@
} else if (PERF_TYPE_RAW == event->attr.type) {
/* We are working on the global raw event. */
mutex_lock(&raw_event_mutex);
- pev = mipspmu->map_raw_event(event->attr.config);
+ pev = mipspmu.map_raw_event(event->attr.config);
} else {
/* The event type is not (yet) supported. */
return -EOPNOTSUPP;
@@ -605,7 +1273,7 @@
hwc->config = 0;
if (!hwc->sample_period) {
- hwc->sample_period = MAX_PERIOD;
+ hwc->sample_period = mipspmu.max_period;
hwc->last_period = hwc->sample_period;
local64_set(&hwc->period_left, hwc->sample_period);
}
@@ -618,70 +1286,47 @@
}
event->destroy = hw_perf_event_destroy;
-
return err;
}
static void pause_local_counters(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- int counters = mipspmu->num_counters;
+ int ctr = mipspmu.num_counters;
unsigned long flags;
local_irq_save(flags);
- switch (counters) {
- case 4:
- cpuc->saved_ctrl[3] = r_c0_perfctrl3();
- w_c0_perfctrl3(cpuc->saved_ctrl[3] &
- ~M_PERFCTL_COUNT_EVENT_WHENEVER);
- case 3:
- cpuc->saved_ctrl[2] = r_c0_perfctrl2();
- w_c0_perfctrl2(cpuc->saved_ctrl[2] &
- ~M_PERFCTL_COUNT_EVENT_WHENEVER);
- case 2:
- cpuc->saved_ctrl[1] = r_c0_perfctrl1();
- w_c0_perfctrl1(cpuc->saved_ctrl[1] &
- ~M_PERFCTL_COUNT_EVENT_WHENEVER);
- case 1:
- cpuc->saved_ctrl[0] = r_c0_perfctrl0();
- w_c0_perfctrl0(cpuc->saved_ctrl[0] &
- ~M_PERFCTL_COUNT_EVENT_WHENEVER);
- }
+ do {
+ ctr--;
+ cpuc->saved_ctrl[ctr] = mipsxx_pmu_read_control(ctr);
+ mipsxx_pmu_write_control(ctr, cpuc->saved_ctrl[ctr] &
+ ~M_PERFCTL_COUNT_EVENT_WHENEVER);
+ } while (ctr > 0);
local_irq_restore(flags);
}
static void resume_local_counters(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- int counters = mipspmu->num_counters;
- unsigned long flags;
+ int ctr = mipspmu.num_counters;
- local_irq_save(flags);
- switch (counters) {
- case 4:
- w_c0_perfctrl3(cpuc->saved_ctrl[3]);
- case 3:
- w_c0_perfctrl2(cpuc->saved_ctrl[2]);
- case 2:
- w_c0_perfctrl1(cpuc->saved_ctrl[1]);
- case 1:
- w_c0_perfctrl0(cpuc->saved_ctrl[0]);
- }
- local_irq_restore(flags);
+ do {
+ ctr--;
+ mipsxx_pmu_write_control(ctr, cpuc->saved_ctrl[ctr]);
+ } while (ctr > 0);
}
static int mipsxx_pmu_handle_shared_irq(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct perf_sample_data data;
- unsigned int counters = mipspmu->num_counters;
- unsigned int counter;
+ unsigned int counters = mipspmu.num_counters;
+ u64 counter;
int handled = IRQ_NONE;
struct pt_regs *regs;
if (cpu_has_mips_r2 && !(read_c0_cause() & (1 << 26)))
return handled;
-
/*
* First we pause the local counters, so that when we are locked
* here, the counters are all paused. When it gets locked due to
@@ -702,13 +1347,9 @@
#define HANDLE_COUNTER(n) \
case n + 1: \
if (test_bit(n, cpuc->used_mask)) { \
- counter = r_c0_perfcntr ## n(); \
- if (counter & M_COUNTER_OVERFLOW) { \
- w_c0_perfcntr ## n(counter & \
- VALID_COUNT); \
- if (test_and_change_bit(n, cpuc->msbs)) \
- handle_associated_event(cpuc, \
- n, &data, regs); \
+ counter = mipspmu.read_counter(n); \
+ if (counter & mipspmu.overflow) { \
+ handle_associated_event(cpuc, n, &data, regs); \
handled = IRQ_HANDLED; \
} \
}
@@ -733,104 +1374,11 @@
return handled;
}
-static irqreturn_t
-mipsxx_pmu_handle_irq(int irq, void *dev)
+static irqreturn_t mipsxx_pmu_handle_irq(int irq, void *dev)
{
return mipsxx_pmu_handle_shared_irq();
}
-static void mipsxx_pmu_start(void)
-{
-#ifdef CONFIG_MIPS_MT_SMP
- write_unlock(&pmuint_rwlock);
-#endif
- resume_local_counters();
-}
-
-/*
- * MIPS performance counters can be per-TC. The control registers can
- * not be directly accessed across CPUs. Hence if we want to do global
- * control, we need cross CPU calls. on_each_cpu() can help us, but we
- * can not make sure this function is called with interrupts enabled. So
- * here we pause local counters and then grab a rwlock and leave the
- * counters on other CPUs alone. If any counter interrupt raises while
- * we own the write lock, simply pause local counters on that CPU and
- * spin in the handler. Also we know we won't be switched to another
- * CPU after pausing local counters and before grabbing the lock.
- */
-static void mipsxx_pmu_stop(void)
-{
- pause_local_counters();
-#ifdef CONFIG_MIPS_MT_SMP
- write_lock(&pmuint_rwlock);
-#endif
-}
-
-static int
-mipsxx_pmu_alloc_counter(struct cpu_hw_events *cpuc,
- struct hw_perf_event *hwc)
-{
- int i;
-
- /*
- * We only need to care the counter mask. The range has been
- * checked definitely.
- */
- unsigned long cntr_mask = (hwc->event_base >> 8) & 0xffff;
-
- for (i = mipspmu->num_counters - 1; i >= 0; i--) {
- /*
- * Note that some MIPS perf events can be counted by both
- * even and odd counters, wheresas many other are only by
- * even _or_ odd counters. This introduces an issue that
- * when the former kind of event takes the counter the
- * latter kind of event wants to use, then the "counter
- * allocation" for the latter event will fail. In fact if
- * they can be dynamically swapped, they both feel happy.
- * But here we leave this issue alone for now.
- */
- if (test_bit(i, &cntr_mask) &&
- !test_and_set_bit(i, cpuc->used_mask))
- return i;
- }
-
- return -EAGAIN;
-}
-
-static void
-mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- unsigned long flags;
-
- WARN_ON(idx < 0 || idx >= mipspmu->num_counters);
-
- local_irq_save(flags);
- cpuc->saved_ctrl[idx] = M_PERFCTL_EVENT(evt->event_base & 0xff) |
- (evt->config_base & M_PERFCTL_CONFIG_MASK) |
- /* Make sure interrupt enabled. */
- M_PERFCTL_INTERRUPT_ENABLE;
- /*
- * We do not actually let the counter run. Leave it until start().
- */
- local_irq_restore(flags);
-}
-
-static void
-mipsxx_pmu_disable_event(int idx)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- unsigned long flags;
-
- WARN_ON(idx < 0 || idx >= mipspmu->num_counters);
-
- local_irq_save(flags);
- cpuc->saved_ctrl[idx] = mipsxx_pmu_read_control(idx) &
- ~M_PERFCTL_COUNT_EVENT_WHENEVER;
- mipsxx_pmu_write_control(idx, cpuc->saved_ctrl[idx]);
- local_irq_restore(flags);
-}
-
/* 24K */
#define IS_UNSUPPORTED_24K_EVENT(r, b) \
((b) == 12 || (r) == 151 || (r) == 152 || (b) == 26 || \
@@ -892,8 +1440,7 @@
* then 128 needs to be added to 15 as the input for the event config,
* i.e., 143 (0x8F) to be used.
*/
-static const struct mips_perf_event *
-mipsxx_pmu_map_raw_event(u64 config)
+static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config)
{
unsigned int raw_id = config & 0xff;
unsigned int base_id = raw_id & 0x7f;
@@ -970,40 +1517,44 @@
return &raw_event;
}
-static struct mips_pmu mipsxxcore_pmu = {
- .handle_irq = mipsxx_pmu_handle_irq,
- .handle_shared_irq = mipsxx_pmu_handle_shared_irq,
- .start = mipsxx_pmu_start,
- .stop = mipsxx_pmu_stop,
- .alloc_counter = mipsxx_pmu_alloc_counter,
- .read_counter = mipsxx_pmu_read_counter,
- .write_counter = mipsxx_pmu_write_counter,
- .enable_event = mipsxx_pmu_enable_event,
- .disable_event = mipsxx_pmu_disable_event,
- .map_raw_event = mipsxx_pmu_map_raw_event,
- .general_event_map = &mipsxxcore_event_map,
- .cache_event_map = &mipsxxcore_cache_map,
-};
+static const struct mips_perf_event *octeon_pmu_map_raw_event(u64 config)
+{
+ unsigned int raw_id = config & 0xff;
+ unsigned int base_id = raw_id & 0x7f;
-static struct mips_pmu mipsxx74Kcore_pmu = {
- .handle_irq = mipsxx_pmu_handle_irq,
- .handle_shared_irq = mipsxx_pmu_handle_shared_irq,
- .start = mipsxx_pmu_start,
- .stop = mipsxx_pmu_stop,
- .alloc_counter = mipsxx_pmu_alloc_counter,
- .read_counter = mipsxx_pmu_read_counter,
- .write_counter = mipsxx_pmu_write_counter,
- .enable_event = mipsxx_pmu_enable_event,
- .disable_event = mipsxx_pmu_disable_event,
- .map_raw_event = mipsxx_pmu_map_raw_event,
- .general_event_map = &mipsxx74Kcore_event_map,
- .cache_event_map = &mipsxx74Kcore_cache_map,
-};
+
+ raw_event.cntr_mask = CNTR_ALL;
+ raw_event.event_id = base_id;
+
+ if (current_cpu_type() == CPU_CAVIUM_OCTEON2) {
+ if (base_id > 0x42)
+ return ERR_PTR(-EOPNOTSUPP);
+ } else {
+ if (base_id > 0x3a)
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+
+ switch (base_id) {
+ case 0x00:
+ case 0x0f:
+ case 0x1e:
+ case 0x1f:
+ case 0x2f:
+ case 0x34:
+ case 0x3b ... 0x3f:
+ return ERR_PTR(-EOPNOTSUPP);
+ default:
+ break;
+ }
+
+ return &raw_event;
+}
static int __init
init_hw_perf_events(void)
{
int counters, irq;
+ int counter_bits;
pr_info("Performance counters: ");
@@ -1035,32 +1586,36 @@
}
#endif
- on_each_cpu(reset_counters, (void *)(long)counters, 1);
+ mipspmu.map_raw_event = mipsxx_pmu_map_raw_event;
switch (current_cpu_type()) {
case CPU_24K:
- mipsxxcore_pmu.name = "mips/24K";
- mipsxxcore_pmu.num_counters = counters;
- mipsxxcore_pmu.irq = irq;
- mipspmu = &mipsxxcore_pmu;
+ mipspmu.name = "mips/24K";
+ mipspmu.general_event_map = &mipsxxcore_event_map;
+ mipspmu.cache_event_map = &mipsxxcore_cache_map;
break;
case CPU_34K:
- mipsxxcore_pmu.name = "mips/34K";
- mipsxxcore_pmu.num_counters = counters;
- mipsxxcore_pmu.irq = irq;
- mipspmu = &mipsxxcore_pmu;
+ mipspmu.name = "mips/34K";
+ mipspmu.general_event_map = &mipsxxcore_event_map;
+ mipspmu.cache_event_map = &mipsxxcore_cache_map;
break;
case CPU_74K:
- mipsxx74Kcore_pmu.name = "mips/74K";
- mipsxx74Kcore_pmu.num_counters = counters;
- mipsxx74Kcore_pmu.irq = irq;
- mipspmu = &mipsxx74Kcore_pmu;
+ mipspmu.name = "mips/74K";
+ mipspmu.general_event_map = &mipsxx74Kcore_event_map;
+ mipspmu.cache_event_map = &mipsxx74Kcore_cache_map;
break;
case CPU_1004K:
- mipsxxcore_pmu.name = "mips/1004K";
- mipsxxcore_pmu.num_counters = counters;
- mipsxxcore_pmu.irq = irq;
- mipspmu = &mipsxxcore_pmu;
+ mipspmu.name = "mips/1004K";
+ mipspmu.general_event_map = &mipsxxcore_event_map;
+ mipspmu.cache_event_map = &mipsxxcore_cache_map;
+ break;
+ case CPU_CAVIUM_OCTEON:
+ case CPU_CAVIUM_OCTEON_PLUS:
+ case CPU_CAVIUM_OCTEON2:
+ mipspmu.name = "octeon";
+ mipspmu.general_event_map = &octeon_event_map;
+ mipspmu.cache_event_map = &octeon_cache_map;
+ mipspmu.map_raw_event = octeon_pmu_map_raw_event;
break;
default:
pr_cont("Either hardware does not support performance "
@@ -1068,15 +1623,33 @@
return -ENODEV;
}
- if (mipspmu)
- pr_cont("%s PMU enabled, %d counters available to each "
- "CPU, irq %d%s\n", mipspmu->name, counters, irq,
- irq < 0 ? " (share with timer interrupt)" : "");
+ mipspmu.num_counters = counters;
+ mipspmu.irq = irq;
+
+ if (read_c0_perfctrl0() & M_PERFCTL_WIDE) {
+ mipspmu.max_period = (1ULL << 63) - 1;
+ mipspmu.valid_count = (1ULL << 63) - 1;
+ mipspmu.overflow = 1ULL << 63;
+ mipspmu.read_counter = mipsxx_pmu_read_counter_64;
+ mipspmu.write_counter = mipsxx_pmu_write_counter_64;
+ counter_bits = 64;
+ } else {
+ mipspmu.max_period = (1ULL << 31) - 1;
+ mipspmu.valid_count = (1ULL << 31) - 1;
+ mipspmu.overflow = 1ULL << 31;
+ mipspmu.read_counter = mipsxx_pmu_read_counter;
+ mipspmu.write_counter = mipsxx_pmu_write_counter;
+ counter_bits = 32;
+ }
+
+ on_each_cpu(reset_counters, (void *)(long)counters, 1);
+
+ pr_cont("%s PMU enabled, %d %d-bit counters available to each "
+ "CPU, irq %d%s\n", mipspmu.name, counters, counter_bits, irq,
+ irq < 0 ? " (share with timer interrupt)" : "");
perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
return 0;
}
early_initcall(init_hw_perf_events);
-
-#endif /* defined(CONFIG_CPU_MIPS32)... */
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 865bc7a..4792065 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -496,7 +496,7 @@
sys sys_lookup_dcookie 4
sys sys_epoll_create 1
sys sys_epoll_ctl 4
- sys sys_epoll_wait 3 /* 4250 */
+ sys sys_epoll_wait 4 /* 4250 */
sys sys_remap_file_pages 5
sys sys_set_tid_address 1
sys sys_restart_syscall 0
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index 16c4d25..daa81f7 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -169,6 +169,10 @@
octeon_flush_icache_all_cores(vma);
}
+static void octeon_flush_kernel_vmap_range(unsigned long vaddr, int size)
+{
+ BUG();
+}
/**
* Probe Octeon's caches
@@ -273,6 +277,8 @@
flush_icache_range = octeon_flush_icache_range;
local_flush_icache_range = local_octeon_flush_icache_range;
+ __flush_kernel_vmap_range = octeon_flush_kernel_vmap_range;
+
build_clear_page();
build_copy_page();
}
diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c
index e6b0efd..0765583 100644
--- a/arch/mips/mm/c-r3k.c
+++ b/arch/mips/mm/c-r3k.c
@@ -299,6 +299,11 @@
write_c0_status(flags);
}
+static void r3k_flush_kernel_vmap_range(unsigned long vaddr, int size)
+{
+ BUG();
+}
+
static void r3k_dma_cache_wback_inv(unsigned long start, unsigned long size)
{
/* Catch bad driver code */
@@ -323,6 +328,8 @@
flush_icache_range = r3k_flush_icache_range;
local_flush_icache_range = r3k_flush_icache_range;
+ __flush_kernel_vmap_range = r3k_flush_kernel_vmap_range;
+
flush_cache_sigtramp = r3k_flush_cache_sigtramp;
local_flush_data_cache_page = local_r3k_flush_data_cache_page;
flush_data_cache_page = r3k_flush_data_cache_page;
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index b9aabb9..a79fe9a 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -722,6 +722,39 @@
r4k_blast_icache();
}
+struct flush_kernel_vmap_range_args {
+ unsigned long vaddr;
+ int size;
+};
+
+static inline void local_r4k_flush_kernel_vmap_range(void *args)
+{
+ struct flush_kernel_vmap_range_args *vmra = args;
+ unsigned long vaddr = vmra->vaddr;
+ int size = vmra->size;
+
+ /*
+ * Aliases only affect the primary caches so don't bother with
+ * S-caches or T-caches.
+ */
+ if (cpu_has_safe_index_cacheops && size >= dcache_size)
+ r4k_blast_dcache();
+ else {
+ R4600_HIT_CACHEOP_WAR_IMPL;
+ blast_dcache_range(vaddr, vaddr + size);
+ }
+}
+
+static void r4k_flush_kernel_vmap_range(unsigned long vaddr, int size)
+{
+ struct flush_kernel_vmap_range_args args;
+
+ args.vaddr = (unsigned long) vaddr;
+ args.size = size;
+
+ r4k_on_each_cpu(local_r4k_flush_kernel_vmap_range, &args);
+}
+
static inline void rm7k_erratum31(void)
{
const unsigned long ic_lsize = 32;
@@ -1403,6 +1436,8 @@
flush_cache_page = r4k_flush_cache_page;
flush_cache_range = r4k_flush_cache_range;
+ __flush_kernel_vmap_range = r4k_flush_kernel_vmap_range;
+
flush_cache_sigtramp = r4k_flush_cache_sigtramp;
flush_icache_all = r4k_flush_icache_all;
local_flush_data_cache_page = local_r4k_flush_data_cache_page;
diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c
index d352fad..a43c197c 100644
--- a/arch/mips/mm/c-tx39.c
+++ b/arch/mips/mm/c-tx39.c
@@ -253,6 +253,11 @@
}
}
+static void tx39_flush_kernel_vmap_range(unsigned long vaddr, int size)
+{
+ BUG();
+}
+
static void tx39_dma_cache_wback_inv(unsigned long addr, unsigned long size)
{
unsigned long end;
@@ -394,6 +399,8 @@
flush_icache_range = tx39_flush_icache_range;
local_flush_icache_range = tx39_flush_icache_range;
+ __flush_kernel_vmap_range = tx39_flush_kernel_vmap_range;
+
flush_cache_sigtramp = tx39_flush_cache_sigtramp;
local_flush_data_cache_page = local_tx39_flush_data_cache_page;
flush_data_cache_page = tx39_flush_data_cache_page;
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 12af739..829320c 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -35,6 +35,11 @@
void (*__flush_cache_vmap)(void);
void (*__flush_cache_vunmap)(void);
+void (*__flush_kernel_vmap_range)(unsigned long vaddr, int size);
+void (*__invalidate_kernel_vmap_range)(unsigned long vaddr, int size);
+
+EXPORT_SYMBOL_GPL(__flush_kernel_vmap_range);
+
/* MIPS specific cache operations */
void (*flush_cache_sigtramp)(unsigned long addr);
void (*local_flush_data_cache_page)(void * addr);
diff --git a/arch/mips/mm/tlb-r3k.c b/arch/mips/mm/tlb-r3k.c
index 40424af..87bb85d 100644
--- a/arch/mips/mm/tlb-r3k.c
+++ b/arch/mips/mm/tlb-r3k.c
@@ -223,8 +223,8 @@
local_irq_restore(flags);
}
-void __init add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
- unsigned long entryhi, unsigned long pagemask)
+void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
+ unsigned long entryhi, unsigned long pagemask)
{
unsigned long flags;
unsigned long old_ctx;
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index ba40325..0d394e0 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -337,8 +337,8 @@
EXIT_CRITICAL(flags);
}
-void __init add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
- unsigned long entryhi, unsigned long pagemask)
+void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
+ unsigned long entryhi, unsigned long pagemask)
{
unsigned long flags;
unsigned long wired;
diff --git a/arch/mips/netlogic/Platform b/arch/mips/netlogic/Platform
index f87c164..b648b48 100644
--- a/arch/mips/netlogic/Platform
+++ b/arch/mips/netlogic/Platform
@@ -5,6 +5,11 @@
cflags-$(CONFIG_NLM_COMMON) += -I$(srctree)/arch/mips/include/asm/netlogic
#
+# use mips64 if xlr is not available
+#
+cflags-$(CONFIG_NLM_XLR) += $(call cc-option,-march=xlr,-march=mips64)
+
+#
# NETLOGIC XLR/XLS SoC, Simulator and boards
#
core-$(CONFIG_NLM_XLR) += arch/mips/netlogic/xlr/
diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c
index 4828025..cee25dd 100644
--- a/arch/mips/netlogic/xlr/setup.c
+++ b/arch/mips/netlogic/xlr/setup.c
@@ -53,7 +53,7 @@
unsigned long nlm_common_ebase = 0x0;
struct psb_info nlm_prom_info;
-static void nlm_early_serial_setup(void)
+static void __init nlm_early_serial_setup(void)
{
struct uart_port s;
nlm_reg_t *uart_base;
@@ -101,7 +101,7 @@
/* Nothing yet */
}
-static void build_arcs_cmdline(int *argv)
+static void __init build_arcs_cmdline(int *argv)
{
int i, remain, len;
char *arg;
diff --git a/arch/mips/netlogic/xlr/smp.c b/arch/mips/netlogic/xlr/smp.c
index d842bce..080284d 100644
--- a/arch/mips/netlogic/xlr/smp.c
+++ b/arch/mips/netlogic/xlr/smp.c
@@ -158,6 +158,10 @@
num_cpus = 1;
for (i = 0; i < NR_CPUS; i++) {
+ /*
+ * BSP is not set in nlm_cpu_ready array, it is only for
+ * ASPs (goto see smpboot.S)
+ */
if (nlm_cpu_ready[i]) {
cpu_set(i, phys_cpu_present_map);
__cpu_number_map[i] = num_cpus;
@@ -191,7 +195,7 @@
unsigned long secondary_entry_point;
-int nlm_wakeup_secondary_cpus(u32 wakeup_mask)
+int __cpuinit nlm_wakeup_secondary_cpus(u32 wakeup_mask)
{
unsigned int tid, pid, ipi, i, boot_cpu;
void *reset_vec;
diff --git a/arch/mips/netlogic/xlr/smpboot.S b/arch/mips/netlogic/xlr/smpboot.S
index b8e0744..8cb7889 100644
--- a/arch/mips/netlogic/xlr/smpboot.S
+++ b/arch/mips/netlogic/xlr/smpboot.S
@@ -32,17 +32,19 @@
* IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
+#include <linux/init.h>
+
#include <asm/asm.h>
#include <asm/asm-offsets.h>
#include <asm/regdef.h>
#include <asm/mipsregs.h>
-
-/* Don't jump to linux function from Bootloader stack. Change it
- * here. Kernel might allocate bootloader memory before all the CPUs are
- * brought up (eg: Inode cache region) and we better don't overwrite this
- * memory
+/*
+ * Early code for secondary CPUs. This will get them out of the bootloader
+ * code and into linux. Needed because the bootloader area will be taken
+ * and initialized by linux.
*/
+ __CPUINIT
NESTED(prom_pre_boot_secondary_cpus, 16, sp)
.set mips64
mfc0 t0, $15, 1 # read ebase
@@ -73,7 +75,11 @@
jr t0
nop
END(prom_pre_boot_secondary_cpus)
+ __FINIT
+/*
+ * NMI code, used for CPU wakeup, copied to reset entry
+ */
NESTED(nlm_boot_smp_nmi, 0, sp)
.set push
.set noat
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index 4df8799..bb82cbd 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -18,14 +18,13 @@
obj-$(CONFIG_BCM47XX) += pci-bcm47xx.o
obj-$(CONFIG_BCM63XX) += pci-bcm63xx.o fixup-bcm63xx.o \
ops-bcm63xx.o
+obj-$(CONFIG_MIPS_ALCHEMY) += pci-alchemy.o
#
# These are still pretty much in the old state, watch, go blind.
#
obj-$(CONFIG_LASAT) += pci-lasat.o
obj-$(CONFIG_MIPS_COBALT) += fixup-cobalt.o
-obj-$(CONFIG_SOC_AU1500) += fixup-au1000.o ops-au1000.o
-obj-$(CONFIG_SOC_AU1550) += fixup-au1000.o ops-au1000.o
obj-$(CONFIG_SOC_PNX8550) += fixup-pnx8550.o ops-pnx8550.o
obj-$(CONFIG_LEMOTE_FULOONG2E) += fixup-fuloong2e.o ops-loongson2.o
obj-$(CONFIG_LEMOTE_MACH2F) += fixup-lemote2f.o ops-loongson2.o
diff --git a/arch/mips/pci/fixup-au1000.c b/arch/mips/pci/fixup-au1000.c
deleted file mode 100644
index e2ddfc4..0000000
--- a/arch/mips/pci/fixup-au1000.c
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * BRIEF MODULE DESCRIPTION
- * Board specific PCI fixups.
- *
- * Copyright 2001-2003, 2008 MontaVista Software Inc.
- * Author: MontaVista Software, Inc. <source@mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
- * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
- * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
- * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
- * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
- * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/pci.h>
-#include <linux/init.h>
-
-extern char irq_tab_alchemy[][5];
-
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
-{
- return irq_tab_alchemy[slot][pin];
-}
-
-/* Do platform specific device initialization at pci_enable_device() time */
-int pcibios_plat_dev_init(struct pci_dev *dev)
-{
- return 0;
-}
diff --git a/arch/mips/pci/ops-au1000.c b/arch/mips/pci/ops-au1000.c
deleted file mode 100644
index 9a57c5a..0000000
--- a/arch/mips/pci/ops-au1000.c
+++ /dev/null
@@ -1,308 +0,0 @@
-/*
- * BRIEF MODULE DESCRIPTION
- * Alchemy/AMD Au1xx0 PCI support.
- *
- * Copyright 2001-2003, 2007-2008 MontaVista Software Inc.
- * Author: MontaVista Software, Inc. <source@mvista.com>
- *
- * Support for all devices (greater than 16) added by David Gathright.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
- * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
- * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
- * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
- * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
- * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/types.h>
-#include <linux/pci.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/vmalloc.h>
-
-#include <asm/mach-au1x00/au1000.h>
-
-#undef DEBUG
-#ifdef DEBUG
-#define DBG(x...) printk(KERN_DEBUG x)
-#else
-#define DBG(x...)
-#endif
-
-#define PCI_ACCESS_READ 0
-#define PCI_ACCESS_WRITE 1
-
-int (*board_pci_idsel)(unsigned int devsel, int assert);
-
-void mod_wired_entry(int entry, unsigned long entrylo0,
- unsigned long entrylo1, unsigned long entryhi,
- unsigned long pagemask)
-{
- unsigned long old_pagemask;
- unsigned long old_ctx;
-
- /* Save old context and create impossible VPN2 value */
- old_ctx = read_c0_entryhi() & 0xff;
- old_pagemask = read_c0_pagemask();
- write_c0_index(entry);
- write_c0_pagemask(pagemask);
- write_c0_entryhi(entryhi);
- write_c0_entrylo0(entrylo0);
- write_c0_entrylo1(entrylo1);
- tlb_write_indexed();
- write_c0_entryhi(old_ctx);
- write_c0_pagemask(old_pagemask);
-}
-
-static struct vm_struct *pci_cfg_vm;
-static int pci_cfg_wired_entry;
-static unsigned long last_entryLo0, last_entryLo1;
-
-/*
- * We can't ioremap the entire pci config space because it's too large.
- * Nor can we call ioremap dynamically because some device drivers use
- * the PCI config routines from within interrupt handlers and that
- * becomes a problem in get_vm_area(). We use one wired TLB to handle
- * all config accesses for all busses.
- */
-void __init au1x_pci_cfg_init(void)
-{
- /* Reserve a wired entry for PCI config accesses */
- pci_cfg_vm = get_vm_area(0x2000, VM_IOREMAP);
- if (!pci_cfg_vm)
- panic(KERN_ERR "PCI unable to get vm area\n");
- pci_cfg_wired_entry = read_c0_wired();
- add_wired_entry(0, 0, (unsigned long)pci_cfg_vm->addr, PM_4K);
- last_entryLo0 = last_entryLo1 = 0xffffffff;
-}
-
-static int config_access(unsigned char access_type, struct pci_bus *bus,
- unsigned int dev_fn, unsigned char where, u32 *data)
-{
-#if defined(CONFIG_SOC_AU1500) || defined(CONFIG_SOC_AU1550)
- unsigned int device = PCI_SLOT(dev_fn);
- unsigned int function = PCI_FUNC(dev_fn);
- unsigned long offset, status;
- unsigned long cfg_base;
- unsigned long flags;
- int error = PCIBIOS_SUCCESSFUL;
- unsigned long entryLo0, entryLo1;
-
- if (device > 19) {
- *data = 0xffffffff;
- return -1;
- }
-
- local_irq_save(flags);
- au_writel(((0x2000 << 16) | (au_readl(Au1500_PCI_STATCMD) & 0xffff)),
- Au1500_PCI_STATCMD);
- au_sync_udelay(1);
-
- /*
- * Allow board vendors to implement their own off-chip IDSEL.
- * If it doesn't succeed, may as well bail out at this point.
- */
- if (board_pci_idsel && board_pci_idsel(device, 1) == 0) {
- *data = 0xffffffff;
- local_irq_restore(flags);
- return -1;
- }
-
- /* Setup the config window */
- if (bus->number == 0)
- cfg_base = (1 << device) << 11;
- else
- cfg_base = 0x80000000 | (bus->number << 16) | (device << 11);
-
- /* Setup the lower bits of the 36-bit address */
- offset = (function << 8) | (where & ~0x3);
- /* Pick up any address that falls below the page mask */
- offset |= cfg_base & ~PAGE_MASK;
-
- /* Page boundary */
- cfg_base = cfg_base & PAGE_MASK;
-
- /*
- * To improve performance, if the current device is the same as
- * the last device accessed, we don't touch the TLB.
- */
- entryLo0 = (6 << 26) | (cfg_base >> 6) | (2 << 3) | 7;
- entryLo1 = (6 << 26) | (cfg_base >> 6) | (0x1000 >> 6) | (2 << 3) | 7;
- if ((entryLo0 != last_entryLo0) || (entryLo1 != last_entryLo1)) {
- mod_wired_entry(pci_cfg_wired_entry, entryLo0, entryLo1,
- (unsigned long)pci_cfg_vm->addr, PM_4K);
- last_entryLo0 = entryLo0;
- last_entryLo1 = entryLo1;
- }
-
- if (access_type == PCI_ACCESS_WRITE)
- au_writel(*data, (int)(pci_cfg_vm->addr + offset));
- else
- *data = au_readl((int)(pci_cfg_vm->addr + offset));
-
- au_sync_udelay(2);
-
- DBG("cfg_access %d bus->number %u dev %u at %x *data %x conf %lx\n",
- access_type, bus->number, device, where, *data, offset);
-
- /* Check master abort */
- status = au_readl(Au1500_PCI_STATCMD);
-
- if (status & (1 << 29)) {
- *data = 0xffffffff;
- error = -1;
- DBG("Au1x Master Abort\n");
- } else if ((status >> 28) & 0xf) {
- DBG("PCI ERR detected: device %u, status %lx\n",
- device, (status >> 28) & 0xf);
-
- /* Clear errors */
- au_writel(status & 0xf000ffff, Au1500_PCI_STATCMD);
-
- *data = 0xffffffff;
- error = -1;
- }
-
- /* Take away the IDSEL. */
- if (board_pci_idsel)
- (void)board_pci_idsel(device, 0);
-
- local_irq_restore(flags);
- return error;
-#endif
-}
-
-static int read_config_byte(struct pci_bus *bus, unsigned int devfn,
- int where, u8 *val)
-{
- u32 data;
- int ret;
-
- ret = config_access(PCI_ACCESS_READ, bus, devfn, where, &data);
- if (where & 1)
- data >>= 8;
- if (where & 2)
- data >>= 16;
- *val = data & 0xff;
- return ret;
-}
-
-static int read_config_word(struct pci_bus *bus, unsigned int devfn,
- int where, u16 *val)
-{
- u32 data;
- int ret;
-
- ret = config_access(PCI_ACCESS_READ, bus, devfn, where, &data);
- if (where & 2)
- data >>= 16;
- *val = data & 0xffff;
- return ret;
-}
-
-static int read_config_dword(struct pci_bus *bus, unsigned int devfn,
- int where, u32 *val)
-{
- int ret;
-
- ret = config_access(PCI_ACCESS_READ, bus, devfn, where, val);
- return ret;
-}
-
-static int write_config_byte(struct pci_bus *bus, unsigned int devfn,
- int where, u8 val)
-{
- u32 data = 0;
-
- if (config_access(PCI_ACCESS_READ, bus, devfn, where, &data))
- return -1;
-
- data = (data & ~(0xff << ((where & 3) << 3))) |
- (val << ((where & 3) << 3));
-
- if (config_access(PCI_ACCESS_WRITE, bus, devfn, where, &data))
- return -1;
-
- return PCIBIOS_SUCCESSFUL;
-}
-
-static int write_config_word(struct pci_bus *bus, unsigned int devfn,
- int where, u16 val)
-{
- u32 data = 0;
-
- if (config_access(PCI_ACCESS_READ, bus, devfn, where, &data))
- return -1;
-
- data = (data & ~(0xffff << ((where & 3) << 3))) |
- (val << ((where & 3) << 3));
-
- if (config_access(PCI_ACCESS_WRITE, bus, devfn, where, &data))
- return -1;
-
- return PCIBIOS_SUCCESSFUL;
-}
-
-static int write_config_dword(struct pci_bus *bus, unsigned int devfn,
- int where, u32 val)
-{
- if (config_access(PCI_ACCESS_WRITE, bus, devfn, where, &val))
- return -1;
-
- return PCIBIOS_SUCCESSFUL;
-}
-
-static int config_read(struct pci_bus *bus, unsigned int devfn,
- int where, int size, u32 *val)
-{
- switch (size) {
- case 1: {
- u8 _val;
- int rc = read_config_byte(bus, devfn, where, &_val);
-
- *val = _val;
- return rc;
- }
- case 2: {
- u16 _val;
- int rc = read_config_word(bus, devfn, where, &_val);
-
- *val = _val;
- return rc;
- }
- default:
- return read_config_dword(bus, devfn, where, val);
- }
-}
-
-static int config_write(struct pci_bus *bus, unsigned int devfn,
- int where, int size, u32 val)
-{
- switch (size) {
- case 1:
- return write_config_byte(bus, devfn, where, (u8) val);
- case 2:
- return write_config_word(bus, devfn, where, (u16) val);
- default:
- return write_config_dword(bus, devfn, where, val);
- }
-}
-
-struct pci_ops au1x_pci_ops = {
- config_read,
- config_write
-};
diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c
new file mode 100644
index 0000000..4ee5710
--- /dev/null
+++ b/arch/mips/pci/pci-alchemy.c
@@ -0,0 +1,516 @@
+/*
+ * Alchemy PCI host mode support.
+ *
+ * Copyright 2001-2003, 2007-2008 MontaVista Software Inc.
+ * Author: MontaVista Software, Inc. <source@mvista.com>
+ *
+ * Support for all devices (greater than 16) added by David Gathright.
+ */
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/vmalloc.h>
+
+#include <asm/mach-au1x00/au1000.h>
+
+#ifdef CONFIG_DEBUG_PCI
+#define DBG(x...) printk(KERN_DEBUG x)
+#else
+#define DBG(x...) do {} while (0)
+#endif
+
+#define PCI_ACCESS_READ 0
+#define PCI_ACCESS_WRITE 1
+
+struct alchemy_pci_context {
+ struct pci_controller alchemy_pci_ctrl; /* leave as first member! */
+ void __iomem *regs; /* ctrl base */
+ /* tools for wired entry for config space access */
+ unsigned long last_elo0;
+ unsigned long last_elo1;
+ int wired_entry;
+ struct vm_struct *pci_cfg_vm;
+
+ unsigned long pm[12];
+
+ int (*board_map_irq)(const struct pci_dev *d, u8 slot, u8 pin);
+ int (*board_pci_idsel)(unsigned int devsel, int assert);
+};
+
+/* IO/MEM resources for PCI. Keep the memres in sync with __fixup_bigphys_addr
+ * in arch/mips/alchemy/common/setup.c
+ */
+static struct resource alchemy_pci_def_memres = {
+ .start = ALCHEMY_PCI_MEMWIN_START,
+ .end = ALCHEMY_PCI_MEMWIN_END,
+ .name = "PCI memory space",
+ .flags = IORESOURCE_MEM
+};
+
+static struct resource alchemy_pci_def_iores = {
+ .start = ALCHEMY_PCI_IOWIN_START,
+ .end = ALCHEMY_PCI_IOWIN_END,
+ .name = "PCI IO space",
+ .flags = IORESOURCE_IO
+};
+
+static void mod_wired_entry(int entry, unsigned long entrylo0,
+ unsigned long entrylo1, unsigned long entryhi,
+ unsigned long pagemask)
+{
+ unsigned long old_pagemask;
+ unsigned long old_ctx;
+
+ /* Save old context and create impossible VPN2 value */
+ old_ctx = read_c0_entryhi() & 0xff;
+ old_pagemask = read_c0_pagemask();
+ write_c0_index(entry);
+ write_c0_pagemask(pagemask);
+ write_c0_entryhi(entryhi);
+ write_c0_entrylo0(entrylo0);
+ write_c0_entrylo1(entrylo1);
+ tlb_write_indexed();
+ write_c0_entryhi(old_ctx);
+ write_c0_pagemask(old_pagemask);
+}
+
+static void alchemy_pci_wired_entry(struct alchemy_pci_context *ctx)
+{
+ ctx->wired_entry = read_c0_wired();
+ add_wired_entry(0, 0, (unsigned long)ctx->pci_cfg_vm->addr, PM_4K);
+ ctx->last_elo0 = ctx->last_elo1 = ~0;
+}
+
+static int config_access(unsigned char access_type, struct pci_bus *bus,
+ unsigned int dev_fn, unsigned char where, u32 *data)
+{
+ struct alchemy_pci_context *ctx = bus->sysdata;
+ unsigned int device = PCI_SLOT(dev_fn);
+ unsigned int function = PCI_FUNC(dev_fn);
+ unsigned long offset, status, cfg_base, flags, entryLo0, entryLo1, r;
+ int error = PCIBIOS_SUCCESSFUL;
+
+ if (device > 19) {
+ *data = 0xffffffff;
+ return -1;
+ }
+
+ /* YAMON on all db1xxx boards wipes the TLB and writes zero to C0_wired
+ * on resume, clearing our wired entry. Unfortunately the ->resume()
+ * callback is called way way way too late (and ->suspend() too early)
+ * to have them destroy and recreate it. Instead just test if c0_wired
+ * is now lower than the index we retrieved before suspending and then
+ * recreate the entry if necessary. Of course this is totally bonkers
+ * and breaks as soon as someone else adds another wired entry somewhere
+ * else. Anyone have any ideas how to handle this better?
+ */
+ if (unlikely(read_c0_wired() < ctx->wired_entry))
+ alchemy_pci_wired_entry(ctx);
+
+ local_irq_save(flags);
+ r = __raw_readl(ctx->regs + PCI_REG_STATCMD) & 0x0000ffff;
+ r |= PCI_STATCMD_STATUS(0x2000);
+ __raw_writel(r, ctx->regs + PCI_REG_STATCMD);
+ wmb();
+
+ /* Allow board vendors to implement their own off-chip IDSEL.
+ * If it doesn't succeed, may as well bail out at this point.
+ */
+ if (ctx->board_pci_idsel(device, 1) == 0) {
+ *data = 0xffffffff;
+ local_irq_restore(flags);
+ return -1;
+ }
+
+ /* Setup the config window */
+ if (bus->number == 0)
+ cfg_base = (1 << device) << 11;
+ else
+ cfg_base = 0x80000000 | (bus->number << 16) | (device << 11);
+
+ /* Setup the lower bits of the 36-bit address */
+ offset = (function << 8) | (where & ~0x3);
+ /* Pick up any address that falls below the page mask */
+ offset |= cfg_base & ~PAGE_MASK;
+
+ /* Page boundary */
+ cfg_base = cfg_base & PAGE_MASK;
+
+ /* To improve performance, if the current device is the same as
+ * the last device accessed, we don't touch the TLB.
+ */
+ entryLo0 = (6 << 26) | (cfg_base >> 6) | (2 << 3) | 7;
+ entryLo1 = (6 << 26) | (cfg_base >> 6) | (0x1000 >> 6) | (2 << 3) | 7;
+ if ((entryLo0 != ctx->last_elo0) || (entryLo1 != ctx->last_elo1)) {
+ mod_wired_entry(ctx->wired_entry, entryLo0, entryLo1,
+ (unsigned long)ctx->pci_cfg_vm->addr, PM_4K);
+ ctx->last_elo0 = entryLo0;
+ ctx->last_elo1 = entryLo1;
+ }
+
+ if (access_type == PCI_ACCESS_WRITE)
+ __raw_writel(*data, ctx->pci_cfg_vm->addr + offset);
+ else
+ *data = __raw_readl(ctx->pci_cfg_vm->addr + offset);
+ wmb();
+
+ DBG("alchemy-pci: cfg access %d bus %u dev %u at %x dat %x conf %lx\n",
+ access_type, bus->number, device, where, *data, offset);
+
+ /* check for errors, master abort */
+ status = __raw_readl(ctx->regs + PCI_REG_STATCMD);
+ if (status & (1 << 29)) {
+ *data = 0xffffffff;
+ error = -1;
+ DBG("alchemy-pci: master abort on cfg access %d bus %d dev %d",
+ access_type, bus->number, device);
+ } else if ((status >> 28) & 0xf) {
+ DBG("alchemy-pci: PCI ERR detected: dev %d, status %lx\n",
+ device, (status >> 28) & 0xf);
+
+ /* clear errors */
+ __raw_writel(status & 0xf000ffff, ctx->regs + PCI_REG_STATCMD);
+
+ *data = 0xffffffff;
+ error = -1;
+ }
+
+ /* Take away the IDSEL. */
+ (void)ctx->board_pci_idsel(device, 0);
+
+ local_irq_restore(flags);
+ return error;
+}
+
+static int read_config_byte(struct pci_bus *bus, unsigned int devfn,
+ int where, u8 *val)
+{
+ u32 data;
+ int ret = config_access(PCI_ACCESS_READ, bus, devfn, where, &data);
+
+ if (where & 1)
+ data >>= 8;
+ if (where & 2)
+ data >>= 16;
+ *val = data & 0xff;
+ return ret;
+}
+
+static int read_config_word(struct pci_bus *bus, unsigned int devfn,
+ int where, u16 *val)
+{
+ u32 data;
+ int ret = config_access(PCI_ACCESS_READ, bus, devfn, where, &data);
+
+ if (where & 2)
+ data >>= 16;
+ *val = data & 0xffff;
+ return ret;
+}
+
+static int read_config_dword(struct pci_bus *bus, unsigned int devfn,
+ int where, u32 *val)
+{
+ return config_access(PCI_ACCESS_READ, bus, devfn, where, val);
+}
+
+static int write_config_byte(struct pci_bus *bus, unsigned int devfn,
+ int where, u8 val)
+{
+ u32 data = 0;
+
+ if (config_access(PCI_ACCESS_READ, bus, devfn, where, &data))
+ return -1;
+
+ data = (data & ~(0xff << ((where & 3) << 3))) |
+ (val << ((where & 3) << 3));
+
+ if (config_access(PCI_ACCESS_WRITE, bus, devfn, where, &data))
+ return -1;
+
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static int write_config_word(struct pci_bus *bus, unsigned int devfn,
+ int where, u16 val)
+{
+ u32 data = 0;
+
+ if (config_access(PCI_ACCESS_READ, bus, devfn, where, &data))
+ return -1;
+
+ data = (data & ~(0xffff << ((where & 3) << 3))) |
+ (val << ((where & 3) << 3));
+
+ if (config_access(PCI_ACCESS_WRITE, bus, devfn, where, &data))
+ return -1;
+
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static int write_config_dword(struct pci_bus *bus, unsigned int devfn,
+ int where, u32 val)
+{
+ return config_access(PCI_ACCESS_WRITE, bus, devfn, where, &val);
+}
+
+static int alchemy_pci_read(struct pci_bus *bus, unsigned int devfn,
+ int where, int size, u32 *val)
+{
+ switch (size) {
+ case 1: {
+ u8 _val;
+ int rc = read_config_byte(bus, devfn, where, &_val);
+
+ *val = _val;
+ return rc;
+ }
+ case 2: {
+ u16 _val;
+ int rc = read_config_word(bus, devfn, where, &_val);
+
+ *val = _val;
+ return rc;
+ }
+ default:
+ return read_config_dword(bus, devfn, where, val);
+ }
+}
+
+static int alchemy_pci_write(struct pci_bus *bus, unsigned int devfn,
+ int where, int size, u32 val)
+{
+ switch (size) {
+ case 1:
+ return write_config_byte(bus, devfn, where, (u8) val);
+ case 2:
+ return write_config_word(bus, devfn, where, (u16) val);
+ default:
+ return write_config_dword(bus, devfn, where, val);
+ }
+}
+
+static struct pci_ops alchemy_pci_ops = {
+ .read = alchemy_pci_read,
+ .write = alchemy_pci_write,
+};
+
+static int alchemy_pci_def_idsel(unsigned int devsel, int assert)
+{
+ return 1; /* success */
+}
+
+static int __devinit alchemy_pci_probe(struct platform_device *pdev)
+{
+ struct alchemy_pci_platdata *pd = pdev->dev.platform_data;
+ struct alchemy_pci_context *ctx;
+ void __iomem *virt_io;
+ unsigned long val;
+ struct resource *r;
+ int ret;
+
+ /* need at least PCI IRQ mapping table */
+ if (!pd) {
+ dev_err(&pdev->dev, "need platform data for PCI setup\n");
+ ret = -ENODEV;
+ goto out;
+ }
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx) {
+ dev_err(&pdev->dev, "no memory for pcictl context\n");
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!r) {
+ dev_err(&pdev->dev, "no pcictl ctrl regs resource\n");
+ ret = -ENODEV;
+ goto out1;
+ }
+
+ if (!request_mem_region(r->start, resource_size(r), pdev->name)) {
+ dev_err(&pdev->dev, "cannot claim pci regs\n");
+ ret = -ENODEV;
+ goto out1;
+ }
+
+ ctx->regs = ioremap_nocache(r->start, resource_size(r));
+ if (!ctx->regs) {
+ dev_err(&pdev->dev, "cannot map pci regs\n");
+ ret = -ENODEV;
+ goto out2;
+ }
+
+ /* map parts of the PCI IO area */
+ /* REVISIT: if this changes with a newer variant (doubt it) make this
+ * a platform resource.
+ */
+ virt_io = ioremap(AU1500_PCI_IO_PHYS_ADDR, 0x00100000);
+ if (!virt_io) {
+ dev_err(&pdev->dev, "cannot remap pci io space\n");
+ ret = -ENODEV;
+ goto out3;
+ }
+ ctx->alchemy_pci_ctrl.io_map_base = (unsigned long)virt_io;
+
+#ifdef CONFIG_DMA_NONCOHERENT
+ /* Au1500 revisions older than AD have borked coherent PCI */
+ if ((alchemy_get_cputype() == ALCHEMY_CPU_AU1500) &&
+ (read_c0_prid() < 0x01030202)) {
+ val = __raw_readl(ctx->regs + PCI_REG_CONFIG);
+ val |= PCI_CONFIG_NC;
+ __raw_writel(val, ctx->regs + PCI_REG_CONFIG);
+ wmb();
+ dev_info(&pdev->dev, "non-coherent PCI on Au1500 AA/AB/AC\n");
+ }
+#endif
+
+ if (pd->board_map_irq)
+ ctx->board_map_irq = pd->board_map_irq;
+
+ if (pd->board_pci_idsel)
+ ctx->board_pci_idsel = pd->board_pci_idsel;
+ else
+ ctx->board_pci_idsel = alchemy_pci_def_idsel;
+
+ /* fill in relevant pci_controller members */
+ ctx->alchemy_pci_ctrl.pci_ops = &alchemy_pci_ops;
+ ctx->alchemy_pci_ctrl.mem_resource = &alchemy_pci_def_memres;
+ ctx->alchemy_pci_ctrl.io_resource = &alchemy_pci_def_iores;
+
+ /* we can't ioremap the entire pci config space because it's too large,
+ * nor can we dynamically ioremap it because some drivers use the
+ * PCI config routines from within atomic contex and that becomes a
+ * problem in get_vm_area(). Instead we use one wired TLB entry to
+ * handle all config accesses for all busses.
+ */
+ ctx->pci_cfg_vm = get_vm_area(0x2000, VM_IOREMAP);
+ if (!ctx->pci_cfg_vm) {
+ dev_err(&pdev->dev, "unable to get vm area\n");
+ ret = -ENOMEM;
+ goto out4;
+ }
+ ctx->wired_entry = 8192; /* impossibly high value */
+
+ set_io_port_base((unsigned long)ctx->alchemy_pci_ctrl.io_map_base);
+
+ /* board may want to modify bits in the config register, do it now */
+ val = __raw_readl(ctx->regs + PCI_REG_CONFIG);
+ val &= ~pd->pci_cfg_clr;
+ val |= pd->pci_cfg_set;
+ val &= ~PCI_CONFIG_PD; /* clear disable bit */
+ __raw_writel(val, ctx->regs + PCI_REG_CONFIG);
+ wmb();
+
+ platform_set_drvdata(pdev, ctx);
+ register_pci_controller(&ctx->alchemy_pci_ctrl);
+
+ return 0;
+
+out4:
+ iounmap(virt_io);
+out3:
+ iounmap(ctx->regs);
+out2:
+ release_mem_region(r->start, resource_size(r));
+out1:
+ kfree(ctx);
+out:
+ return ret;
+}
+
+
+#ifdef CONFIG_PM
+/* save PCI controller register contents. */
+static int alchemy_pci_suspend(struct device *dev)
+{
+ struct alchemy_pci_context *ctx = dev_get_drvdata(dev);
+
+ ctx->pm[0] = __raw_readl(ctx->regs + PCI_REG_CMEM);
+ ctx->pm[1] = __raw_readl(ctx->regs + PCI_REG_CONFIG) & 0x0009ffff;
+ ctx->pm[2] = __raw_readl(ctx->regs + PCI_REG_B2BMASK_CCH);
+ ctx->pm[3] = __raw_readl(ctx->regs + PCI_REG_B2BBASE0_VID);
+ ctx->pm[4] = __raw_readl(ctx->regs + PCI_REG_B2BBASE1_SID);
+ ctx->pm[5] = __raw_readl(ctx->regs + PCI_REG_MWMASK_DEV);
+ ctx->pm[6] = __raw_readl(ctx->regs + PCI_REG_MWBASE_REV_CCL);
+ ctx->pm[7] = __raw_readl(ctx->regs + PCI_REG_ID);
+ ctx->pm[8] = __raw_readl(ctx->regs + PCI_REG_CLASSREV);
+ ctx->pm[9] = __raw_readl(ctx->regs + PCI_REG_PARAM);
+ ctx->pm[10] = __raw_readl(ctx->regs + PCI_REG_MBAR);
+ ctx->pm[11] = __raw_readl(ctx->regs + PCI_REG_TIMEOUT);
+
+ return 0;
+}
+
+static int alchemy_pci_resume(struct device *dev)
+{
+ struct alchemy_pci_context *ctx = dev_get_drvdata(dev);
+
+ __raw_writel(ctx->pm[0], ctx->regs + PCI_REG_CMEM);
+ __raw_writel(ctx->pm[2], ctx->regs + PCI_REG_B2BMASK_CCH);
+ __raw_writel(ctx->pm[3], ctx->regs + PCI_REG_B2BBASE0_VID);
+ __raw_writel(ctx->pm[4], ctx->regs + PCI_REG_B2BBASE1_SID);
+ __raw_writel(ctx->pm[5], ctx->regs + PCI_REG_MWMASK_DEV);
+ __raw_writel(ctx->pm[6], ctx->regs + PCI_REG_MWBASE_REV_CCL);
+ __raw_writel(ctx->pm[7], ctx->regs + PCI_REG_ID);
+ __raw_writel(ctx->pm[8], ctx->regs + PCI_REG_CLASSREV);
+ __raw_writel(ctx->pm[9], ctx->regs + PCI_REG_PARAM);
+ __raw_writel(ctx->pm[10], ctx->regs + PCI_REG_MBAR);
+ __raw_writel(ctx->pm[11], ctx->regs + PCI_REG_TIMEOUT);
+ wmb();
+ __raw_writel(ctx->pm[1], ctx->regs + PCI_REG_CONFIG);
+ wmb();
+
+ return 0;
+}
+
+static const struct dev_pm_ops alchemy_pci_pmops = {
+ .suspend = alchemy_pci_suspend,
+ .resume = alchemy_pci_resume,
+};
+
+#define ALCHEMY_PCICTL_PM (&alchemy_pci_pmops)
+
+#else
+#define ALCHEMY_PCICTL_PM NULL
+#endif
+
+static struct platform_driver alchemy_pcictl_driver = {
+ .probe = alchemy_pci_probe,
+ .driver = {
+ .name = "alchemy-pci",
+ .owner = THIS_MODULE,
+ .pm = ALCHEMY_PCICTL_PM,
+ },
+};
+
+static int __init alchemy_pci_init(void)
+{
+ /* Au1500/Au1550 have PCI */
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1500:
+ case ALCHEMY_CPU_AU1550:
+ return platform_driver_register(&alchemy_pcictl_driver);
+ }
+ return 0;
+}
+arch_initcall(alchemy_pci_init);
+
+
+int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+ struct alchemy_pci_context *ctx = dev->sysdata;
+ if (ctx && ctx->board_map_irq)
+ return ctx->board_map_irq(dev, slot, pin);
+ return -1;
+}
+
+int pcibios_plat_dev_init(struct pci_dev *dev)
+{
+ return 0;
+}
diff --git a/arch/mips/pmc-sierra/msp71xx/msp_setup.c b/arch/mips/pmc-sierra/msp71xx/msp_setup.c
index 0abfbe0..655308a 100644
--- a/arch/mips/pmc-sierra/msp71xx/msp_setup.c
+++ b/arch/mips/pmc-sierra/msp71xx/msp_setup.c
@@ -14,6 +14,7 @@
#include <asm/cacheflush.h>
#include <asm/r4kcache.h>
#include <asm/reboot.h>
+#include <asm/smp-ops.h>
#include <asm/time.h>
#include <msp_prom.h>
diff --git a/arch/mips/pmc-sierra/yosemite/py-console.c b/arch/mips/pmc-sierra/yosemite/py-console.c
index 434d7b1..b7f1d9c 100644
--- a/arch/mips/pmc-sierra/yosemite/py-console.c
+++ b/arch/mips/pmc-sierra/yosemite/py-console.c
@@ -65,15 +65,11 @@
__asm__ __volatile__ (
" .set mips3 \n"
- " .set push \n"
- " .set noreorder \n"
- " .set nomacro \n"
" ld %0, %1 \n"
- " .set pop \n"
" lbu %0, (%0) \n"
" .set mips0 \n"
: "=r" (res)
- : "R" (vaddr));
+ : "m" (vaddr));
write_c0_status(sr);
ssnop_4();
@@ -93,15 +89,11 @@
__asm__ __volatile__ (
" .set mips3 \n"
- " .set push \n"
- " .set noreorder \n"
- " .set nomacro \n"
" ld %0, %1 \n"
- " .set pop \n"
" sb %2, (%0) \n"
" .set mips0 \n"
: "=&r" (tmp)
- : "R" (vaddr), "r" (c));
+ : "m" (vaddr), "r" (c));
write_c0_status(sr);
ssnop_4();
diff --git a/arch/mips/pnx8550/common/prom.c b/arch/mips/pnx8550/common/prom.c
index 32f7009..49639e8 100644
--- a/arch/mips/pnx8550/common/prom.c
+++ b/arch/mips/pnx8550/common/prom.c
@@ -30,7 +30,7 @@
}t_env_var;
-char * prom_getcmdline(void)
+char * __init prom_getcmdline(void)
{
return &(arcs_cmdline[0]);
}
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index b18b04e..f90dce3 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -337,12 +337,12 @@
.irq_unmask = enable_bridge_irq,
};
-void __devinit register_bridge_irq(unsigned int irq)
+void register_bridge_irq(unsigned int irq)
{
irq_set_chip_and_handler(irq, &bridge_irq_type, handle_level_irq);
}
-int __devinit request_bridge_irq(struct bridge_controller *bc)
+int request_bridge_irq(struct bridge_controller *bc)
{
int irq = allocate_irqno();
int swlevel, cpu;
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index fec1320..d7efdbf 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -16,16 +16,6 @@
#ifdef __HAVE_ARCH_PTE_SPECIAL
-static inline void get_huge_page_tail(struct page *page)
-{
- /*
- * __split_huge_page_refcount() cannot run
- * from under us.
- */
- VM_BUG_ON(atomic_read(&page->_count) < 0);
- atomic_inc(&page->_count);
-}
-
/*
* The performance critical leaf functions are made noinline otherwise gcc
* inlines everything into a single function which results in too much
@@ -57,8 +47,6 @@
put_page(page);
return 0;
}
- if (PageTail(page))
- get_huge_page_tail(page);
pages[*nr] = page;
(*nr)++;
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0b9a5c1..da5eb38 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -390,7 +390,7 @@
{
unsigned long mask;
unsigned long pte_end;
- struct page *head, *page;
+ struct page *head, *page, *tail;
pte_t pte;
int refs;
@@ -413,6 +413,7 @@
head = pte_page(pte);
page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+ tail = page;
do {
VM_BUG_ON(compound_head(page) != head);
pages[*nr] = page;
@@ -428,10 +429,20 @@
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
/* Could be optimized better */
- while (*nr) {
- put_page(page);
- (*nr)--;
- }
+ *nr -= refs;
+ while (refs--)
+ put_page(head);
+ return 0;
+ }
+
+ /*
+ * Any tail page need their mapcount reference taken before we
+ * return.
+ */
+ while (refs--) {
+ if (PageTail(tail))
+ get_huge_page_tail(tail);
+ tail++;
}
return 1;
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index c65f75a..22ffccd 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -1608,6 +1608,7 @@
return 0;
err:
iounmap(priv->regs_win);
+ release_resource(&port->iores);
err_res:
kfree(priv);
err_priv:
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 6fe874f..481f4f7 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -108,9 +108,7 @@
ret->i_gid = hypfs_info->gid;
ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME;
if (mode & S_IFDIR)
- ret->i_nlink = 2;
- else
- ret->i_nlink = 1;
+ set_nlink(ret, 2);
}
return ret;
}
@@ -361,7 +359,7 @@
} else if (mode & S_IFDIR) {
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
- parent->d_inode->i_nlink++;
+ inc_nlink(parent->d_inode);
} else
BUG();
inode->i_private = data;
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 45b405c..65cb06e 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -52,7 +52,7 @@
unsigned long end, int write, struct page **pages, int *nr)
{
unsigned long mask, result;
- struct page *head, *page;
+ struct page *head, *page, *tail;
int refs;
result = write ? 0 : _SEGMENT_ENTRY_RO;
@@ -64,6 +64,7 @@
refs = 0;
head = pmd_page(pmd);
page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+ tail = page;
do {
VM_BUG_ON(compound_head(page) != head);
pages[*nr] = page;
@@ -81,6 +82,17 @@
*nr -= refs;
while (refs--)
put_page(head);
+ return 0;
+ }
+
+ /*
+ * Any tail page need their mapcount reference taken before we
+ * return.
+ */
+ while (refs--) {
+ if (PageTail(tail))
+ get_huge_page_tail(tail);
+ tail++;
}
return 1;
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index ff9177c..5629e20 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -101,10 +101,6 @@
def_bool y
depends on SMP && PREEMPT
-config SYS_SUPPORTS_PM
- bool
- depends on !SMP
-
config ARCH_SUSPEND_POSSIBLE
def_bool n
@@ -649,7 +645,7 @@
a specially reserved region and then later executed after
a crash by kdump/kexec. The crash dump kernel must be compiled
to a memory address not used by the main kernel using
- MEMORY_START.
+ PHYSICAL_START.
For more details see Documentation/kdump/kdump.txt
@@ -660,6 +656,17 @@
Jump between original kernel and kexeced kernel and invoke
code via KEXEC
+config PHYSICAL_START
+ hex "Physical address where the kernel is loaded" if (EXPERT || CRASH_DUMP)
+ default MEMORY_START
+ ---help---
+ This gives the physical address where the kernel is loaded
+ and is ordinarily the same as MEMORY_START.
+
+ Different values are primarily used in the case of kexec on panic
+ where the fail safe kernel needs to run at a different address
+ than the panic-ed kernel.
+
config SECCOMP
bool "Enable seccomp to safely compute untrusted bytecode"
depends on PROC_FS
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index 99385d0..3fc0f41 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -80,6 +80,7 @@
defaultimage-$(CONFIG_SH_URQUELL) := uImage
defaultimage-$(CONFIG_SH_MIGOR) := uImage
defaultimage-$(CONFIG_SH_AP325RXA) := uImage
+defaultimage-$(CONFIG_SH_SH7757LCR) := uImage
defaultimage-$(CONFIG_SH_7724_SOLUTION_ENGINE) := uImage
defaultimage-$(CONFIG_SH_7206_SOLUTION_ENGINE) := vmlinux
defaultimage-$(CONFIG_SH_7619_SOLUTION_ENGINE) := vmlinux
diff --git a/arch/sh/boards/board-espt.c b/arch/sh/boards/board-espt.c
index 9da92ac..b3ae9d3 100644
--- a/arch/sh/boards/board-espt.c
+++ b/arch/sh/boards/board-espt.c
@@ -13,9 +13,9 @@
#include <linux/interrupt.h>
#include <linux/mtd/physmap.h>
#include <linux/io.h>
+#include <linux/sh_eth.h>
#include <asm/machvec.h>
#include <asm/sizes.h>
-#include <asm/sh_eth.h>
/* NOR Flash */
static struct mtd_partition espt_nor_flash_partitions[] = {
diff --git a/arch/sh/boards/board-secureedge5410.c b/arch/sh/boards/board-secureedge5410.c
index f968f17..03820c3 100644
--- a/arch/sh/boards/board-secureedge5410.c
+++ b/arch/sh/boards/board-secureedge5410.c
@@ -41,8 +41,7 @@
printk("SnapGear: EraseConfig init\n");
/* Setup "EraseConfig" switch on external IRQ 0 */
- if (request_irq(irq, eraseconfig_interrupt, IRQF_DISABLED,
- "Erase Config", NULL))
+ if (request_irq(irq, eraseconfig_interrupt, 0, "Erase Config", NULL))
printk("SnapGear: failed to register IRQ%d for Reset witch\n",
irq);
else
diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c
index fa2a208..ec8c84c 100644
--- a/arch/sh/boards/board-sh7757lcr.c
+++ b/arch/sh/boards/board-sh7757lcr.c
@@ -18,8 +18,8 @@
#include <linux/mmc/host.h>
#include <linux/mmc/sh_mmcif.h>
#include <linux/mmc/sh_mobile_sdhi.h>
+#include <linux/sh_eth.h>
#include <cpu/sh7757.h>
-#include <asm/sh_eth.h>
#include <asm/heartbeat.h>
static struct resource heartbeat_resource = {
diff --git a/arch/sh/boards/mach-cayman/irq.c b/arch/sh/boards/mach-cayman/irq.c
index 311bceb..724e8b7 100644
--- a/arch/sh/boards/mach-cayman/irq.c
+++ b/arch/sh/boards/mach-cayman/irq.c
@@ -46,13 +46,11 @@
static struct irqaction cayman_action_smsc = {
.name = "Cayman SMSC Mux",
.handler = cayman_interrupt_smsc,
- .flags = IRQF_DISABLED,
};
static struct irqaction cayman_action_pci2 = {
.name = "Cayman PCI2 Mux",
.handler = cayman_interrupt_pci2,
- .flags = IRQF_DISABLED,
};
static void enable_cayman_irq(struct irq_data *data)
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index b24d69d..92ddce4 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -28,13 +28,13 @@
#include <linux/spi/mmc_spi.h>
#include <linux/input.h>
#include <linux/input/sh_keysc.h>
+#include <linux/sh_eth.h>
#include <video/sh_mobile_lcdc.h>
#include <sound/sh_fsi.h>
#include <media/sh_mobile_ceu.h>
#include <media/tw9910.h>
#include <media/mt9t112.h>
#include <asm/heartbeat.h>
-#include <asm/sh_eth.h>
#include <asm/clock.h>
#include <asm/suspend.h>
#include <cpu/sh7724.h>
@@ -248,6 +248,10 @@
.driver_param = {
.buswait_bwait = 4,
.detection_delay = 5,
+ .d0_tx_id = SHDMA_SLAVE_USB1D0_TX,
+ .d0_rx_id = SHDMA_SLAVE_USB1D0_RX,
+ .d1_tx_id = SHDMA_SLAVE_USB1D1_TX,
+ .d1_rx_id = SHDMA_SLAVE_USB1D1_RX,
},
};
diff --git a/arch/sh/boards/mach-hp6xx/hp6xx_apm.c b/arch/sh/boards/mach-hp6xx/hp6xx_apm.c
index b49535c..865d8d6 100644
--- a/arch/sh/boards/mach-hp6xx/hp6xx_apm.c
+++ b/arch/sh/boards/mach-hp6xx/hp6xx_apm.c
@@ -86,7 +86,7 @@
int ret;
ret = request_irq(HP680_BTN_IRQ, hp6x0_apm_interrupt,
- IRQF_DISABLED, MODNAME, NULL);
+ 0, MODNAME, NULL);
if (unlikely(ret < 0)) {
printk(KERN_ERR MODNAME ": IRQ %d request failed\n",
HP680_BTN_IRQ);
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index d007567..b747c0a 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -23,12 +23,12 @@
#include <linux/input.h>
#include <linux/input/sh_keysc.h>
#include <linux/usb/r8a66597.h>
+#include <linux/sh_eth.h>
#include <video/sh_mobile_lcdc.h>
#include <media/sh_mobile_ceu.h>
#include <sound/sh_fsi.h>
#include <asm/io.h>
#include <asm/heartbeat.h>
-#include <asm/sh_eth.h>
#include <asm/clock.h>
#include <asm/suspend.h>
#include <cpu/sh7724.h>
diff --git a/arch/sh/boards/mach-sh7763rdp/setup.c b/arch/sh/boards/mach-sh7763rdp/setup.c
index f3d828f..dd036f1 100644
--- a/arch/sh/boards/mach-sh7763rdp/setup.c
+++ b/arch/sh/boards/mach-sh7763rdp/setup.c
@@ -17,8 +17,8 @@
#include <linux/mtd/physmap.h>
#include <linux/fb.h>
#include <linux/io.h>
+#include <linux/sh_eth.h>
#include <mach/sh7763rdp.h>
-#include <asm/sh_eth.h>
#include <asm/sh7760fb.h>
/* NOR Flash */
diff --git a/arch/sh/boot/Makefile b/arch/sh/boot/Makefile
index ba515d8..e4ea31a 100644
--- a/arch/sh/boot/Makefile
+++ b/arch/sh/boot/Makefile
@@ -19,6 +19,7 @@
CONFIG_BOOT_LINK_OFFSET ?= 0x00800000
CONFIG_ZERO_PAGE_OFFSET ?= 0x00001000
CONFIG_ENTRY_OFFSET ?= 0x00001000
+CONFIG_PHYSICAL_START ?= $(CONFIG_MEMORY_START)
suffix-y := bin
suffix-$(CONFIG_KERNEL_GZIP) := gz
@@ -48,7 +49,7 @@
$(Q)$(MAKE) $(build)=$(obj)/romimage $@
KERNEL_MEMORY := $(shell /bin/bash -c 'printf "0x%08x" \
- $$[$(CONFIG_MEMORY_START) & 0x1fffffff]')
+ $$[$(CONFIG_PHYSICAL_START) & 0x1fffffff]')
KERNEL_LOAD := $(shell /bin/bash -c 'printf "0x%08x" \
$$[$(CONFIG_PAGE_OFFSET) + \
@@ -114,4 +115,5 @@
@echo ' Image $@ is ready'
export CONFIG_PAGE_OFFSET CONFIG_MEMORY_START CONFIG_BOOT_LINK_OFFSET \
- CONFIG_ZERO_PAGE_OFFSET CONFIG_ENTRY_OFFSET KERNEL_MEMORY suffix-y
+ CONFIG_PHYSICAL_START CONFIG_ZERO_PAGE_OFFSET CONFIG_ENTRY_OFFSET \
+ KERNEL_MEMORY suffix-y
diff --git a/arch/sh/drivers/dma/dma-g2.c b/arch/sh/drivers/dma/dma-g2.c
index af7bb58..be9ca7c 100644
--- a/arch/sh/drivers/dma/dma-g2.c
+++ b/arch/sh/drivers/dma/dma-g2.c
@@ -170,7 +170,7 @@
{
int ret;
- ret = request_irq(HW_EVENT_G2_DMA, g2_dma_interrupt, IRQF_DISABLED,
+ ret = request_irq(HW_EVENT_G2_DMA, g2_dma_interrupt, 0,
"g2 DMA handler", &g2_dma_info);
if (unlikely(ret))
return -EINVAL;
diff --git a/arch/sh/drivers/dma/dma-pvr2.c b/arch/sh/drivers/dma/dma-pvr2.c
index 3cee58e..706a343 100644
--- a/arch/sh/drivers/dma/dma-pvr2.c
+++ b/arch/sh/drivers/dma/dma-pvr2.c
@@ -70,7 +70,6 @@
static struct irqaction pvr2_dma_irq = {
.name = "pvr2 DMA handler",
.handler = pvr2_dma_interrupt,
- .flags = IRQF_DISABLED,
};
static struct dma_ops pvr2_dma_ops = {
diff --git a/arch/sh/drivers/dma/dma-sh.c b/arch/sh/drivers/dma/dma-sh.c
index 8272087..a60da6d 100644
--- a/arch/sh/drivers/dma/dma-sh.c
+++ b/arch/sh/drivers/dma/dma-sh.c
@@ -95,7 +95,7 @@
#if defined(CONFIG_SH_DMA_IRQ_MULTI)
IRQF_SHARED,
#else
- IRQF_DISABLED,
+ 0,
#endif
chan->dev_id, chan);
}
@@ -305,7 +305,7 @@
#if defined(CONFIG_SH_DMA_IRQ_MULTI)
IRQF_SHARED,
#else
- IRQF_DISABLED,
+ 0,
#endif
dmae_name[n], (void *)dmae_name[n]);
if (unlikely(i < 0)) {
diff --git a/arch/sh/drivers/dma/dmabrg.c b/arch/sh/drivers/dma/dmabrg.c
index 6ab9c4a..3d66a32 100644
--- a/arch/sh/drivers/dma/dmabrg.c
+++ b/arch/sh/drivers/dma/dmabrg.c
@@ -174,17 +174,17 @@
or = __raw_readl(DMAOR);
__raw_writel(or | DMAOR_BRG | DMAOR_DMEN, DMAOR);
- ret = request_irq(DMABRGI0, dmabrg_irq, IRQF_DISABLED,
+ ret = request_irq(DMABRGI0, dmabrg_irq, 0,
"DMABRG USB address error", NULL);
if (ret)
goto out0;
- ret = request_irq(DMABRGI1, dmabrg_irq, IRQF_DISABLED,
+ ret = request_irq(DMABRGI1, dmabrg_irq, 0,
"DMABRG Transfer End", NULL);
if (ret)
goto out1;
- ret = request_irq(DMABRGI2, dmabrg_irq, IRQF_DISABLED,
+ ret = request_irq(DMABRGI2, dmabrg_irq, 0,
"DMABRG Transfer Half", NULL);
if (ret == 0)
return ret;
diff --git a/arch/sh/drivers/pci/pci-sh5.c b/arch/sh/drivers/pci/pci-sh5.c
index 0bf296c..16c1e72 100644
--- a/arch/sh/drivers/pci/pci-sh5.c
+++ b/arch/sh/drivers/pci/pci-sh5.c
@@ -107,13 +107,13 @@
u32 uval;
if (request_irq(IRQ_ERR, pcish5_err_irq,
- IRQF_DISABLED, "PCI Error",NULL) < 0) {
+ 0, "PCI Error",NULL) < 0) {
printk(KERN_ERR "PCISH5: Cannot hook PCI_PERR interrupt\n");
return -EINVAL;
}
if (request_irq(IRQ_SERR, pcish5_serr_irq,
- IRQF_DISABLED, "PCI SERR interrupt", NULL) < 0) {
+ 0, "PCI SERR interrupt", NULL) < 0) {
printk(KERN_ERR "PCISH5: Cannot hook PCI_SERR interrupt\n");
return -EINVAL;
}
diff --git a/arch/sh/drivers/pci/pci-sh7780.c b/arch/sh/drivers/pci/pci-sh7780.c
index edb7cca..fa7b978 100644
--- a/arch/sh/drivers/pci/pci-sh7780.c
+++ b/arch/sh/drivers/pci/pci-sh7780.c
@@ -172,7 +172,7 @@
PCI_STATUS_SIG_TARGET_ABORT | \
PCI_STATUS_PARITY, hose->reg_base + PCI_STATUS);
- ret = request_irq(hose->serr_irq, sh7780_pci_serr_irq, IRQF_DISABLED,
+ ret = request_irq(hose->serr_irq, sh7780_pci_serr_irq, 0,
"PCI SERR interrupt", hose);
if (unlikely(ret)) {
printk(KERN_ERR "PCI: Failed hooking SERR IRQ\n");
diff --git a/arch/sh/drivers/push-switch.c b/arch/sh/drivers/push-switch.c
index afc2455..637b79b 100644
--- a/arch/sh/drivers/push-switch.c
+++ b/arch/sh/drivers/push-switch.c
@@ -63,7 +63,7 @@
BUG_ON(!psw_info);
ret = request_irq(irq, psw_info->irq_handler,
- IRQF_DISABLED | psw_info->irq_flags,
+ psw_info->irq_flags,
psw_info->name ? psw_info->name : DRV_NAME, pdev);
if (unlikely(ret < 0))
goto err;
diff --git a/arch/sh/include/asm/page.h b/arch/sh/include/asm/page.h
index 822d608..0dca9a5 100644
--- a/arch/sh/include/asm/page.h
+++ b/arch/sh/include/asm/page.h
@@ -113,6 +113,16 @@
#define __MEMORY_SIZE CONFIG_MEMORY_SIZE
/*
+ * PHYSICAL_OFFSET is the offset in physical memory where the base
+ * of the kernel is loaded.
+ */
+#ifdef CONFIG_PHYSICAL_START
+#define PHYSICAL_OFFSET (CONFIG_PHYSICAL_START - __MEMORY_START)
+#else
+#define PHYSICAL_OFFSET 0
+#endif
+
+/*
* PAGE_OFFSET is the virtual address of the start of kernel address
* space.
*/
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
index 3b097b0..19222da 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
@@ -113,7 +113,14 @@
/* MSTP32 clocks */
CLKDEV_CON_ID("sdhi0", &mstp_clks[MSTP004]),
- CLKDEV_CON_ID("riic", &mstp_clks[MSTP000]),
+ CLKDEV_CON_ID("riic0", &mstp_clks[MSTP000]),
+ CLKDEV_CON_ID("riic1", &mstp_clks[MSTP000]),
+ CLKDEV_CON_ID("riic2", &mstp_clks[MSTP000]),
+ CLKDEV_CON_ID("riic3", &mstp_clks[MSTP000]),
+ CLKDEV_CON_ID("riic4", &mstp_clks[MSTP000]),
+ CLKDEV_CON_ID("riic5", &mstp_clks[MSTP000]),
+ CLKDEV_CON_ID("riic6", &mstp_clks[MSTP000]),
+ CLKDEV_CON_ID("riic7", &mstp_clks[MSTP000]),
CLKDEV_ICK_ID("tmu_fck", "sh_tmu.0", &mstp_clks[MSTP113]),
CLKDEV_ICK_ID("tmu_fck", "sh_tmu.1", &mstp_clks[MSTP114]),
@@ -121,6 +128,7 @@
CLKDEV_ICK_ID("sci_fck", "sh-sci.1", &mstp_clks[MSTP111]),
CLKDEV_ICK_ID("sci_fck", "sh-sci.0", &mstp_clks[MSTP110]),
+ CLKDEV_CON_ID("usb_fck", &mstp_clks[MSTP103]),
CLKDEV_CON_ID("usb0", &mstp_clks[MSTP102]),
CLKDEV_CON_ID("mmc0", &mstp_clks[MSTP220]),
};
diff --git a/arch/sh/kernel/cpu/sh4a/smp-shx3.c b/arch/sh/kernel/cpu/sh4a/smp-shx3.c
index de865ca..03f2b55 100644
--- a/arch/sh/kernel/cpu/sh4a/smp-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/smp-shx3.c
@@ -79,7 +79,7 @@
for (i = 0; i < SMP_MSG_NR; i++)
request_irq(104 + i, ipi_interrupt_handler,
- IRQF_DISABLED | IRQF_PERCPU, "IPI", (void *)(long)i);
+ IRQF_PERCPU, "IPI", (void *)(long)i);
for (i = 0; i < max_cpus; i++)
set_cpu_present(i, true);
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 58bff45..1a0e946 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -211,13 +211,16 @@
}
/*
- * We don't know which RAM region contains kernel data,
- * so we try it repeatedly and let the resource manager
- * test it.
+ * We don't know which RAM region contains kernel data or
+ * the reserved crashkernel region, so try it repeatedly
+ * and let the resource manager test it.
*/
request_resource(res, &code_resource);
request_resource(res, &data_resource);
request_resource(res, &bss_resource);
+#ifdef CONFIG_KEXEC
+ request_resource(res, &crashk_res);
+#endif
/*
* Also make sure that there is a PMB mapping that covers this
diff --git a/arch/sh/kernel/topology.c b/arch/sh/kernel/topology.c
index 38e8628..ecc2d3d 100644
--- a/arch/sh/kernel/topology.c
+++ b/arch/sh/kernel/topology.c
@@ -11,6 +11,7 @@
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/percpu.h>
+#include <linux/topology.h>
#include <linux/node.h>
#include <linux/nodemask.h>
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index 731c10c..c98905f 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -23,7 +23,7 @@
ENTRY(_start)
SECTIONS
{
- . = PAGE_OFFSET + MEMORY_OFFSET + CONFIG_ZERO_PAGE_OFFSET;
+ . = PAGE_OFFSET + MEMORY_OFFSET + PHYSICAL_OFFSET + CONFIG_ZERO_PAGE_OFFSET;
_text = .; /* Text and read-only data */
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 58a93fb3..c9dbace 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -287,6 +287,8 @@
static void __init early_reserve_mem(void)
{
unsigned long start_pfn;
+ u32 zero_base = (u32)__MEMORY_START + (u32)PHYSICAL_OFFSET;
+ u32 start = zero_base + (u32)CONFIG_ZERO_PAGE_OFFSET;
/*
* Partially used pages are not usable - thus
@@ -300,15 +302,13 @@
* this catches the (definitely buggy) case of us accidentally
* initializing the bootmem allocator with an invalid RAM area.
*/
- memblock_reserve(__MEMORY_START + CONFIG_ZERO_PAGE_OFFSET,
- (PFN_PHYS(start_pfn) + PAGE_SIZE - 1) -
- (__MEMORY_START + CONFIG_ZERO_PAGE_OFFSET));
+ memblock_reserve(start, (PFN_PHYS(start_pfn) + PAGE_SIZE - 1) - start);
/*
* Reserve physical pages below CONFIG_ZERO_PAGE_OFFSET.
*/
if (CONFIG_ZERO_PAGE_OFFSET != 0)
- memblock_reserve(__MEMORY_START, CONFIG_ZERO_PAGE_OFFSET);
+ memblock_reserve(zero_base, CONFIG_ZERO_PAGE_OFFSET);
/*
* Handle additional early reservations
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index a986b5d..42c55df 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -56,6 +56,8 @@
put_page(head);
return 0;
}
+ if (head != page)
+ get_huge_page_tail(page);
pages[*nr] = page;
(*nr)++;
diff --git a/arch/um/Kconfig.char b/arch/um/Kconfig.char
index 70dabd1..b9d7c42 100644
--- a/arch/um/Kconfig.char
+++ b/arch/um/Kconfig.char
@@ -1,5 +1,4 @@
-
-menu "Character Devices"
+menu "UML Character Devices"
config STDERR_CONSOLE
bool "stderr console"
@@ -105,92 +104,6 @@
this if you expect the UML that you build to be run in environments
which don't have a set of /dev/pty* devices.
-config UNIX98_PTYS
- bool "Unix98 PTY support"
- help
- A pseudo terminal (PTY) is a software device consisting of two
- halves: a master and a slave. The slave device behaves identical to
- a physical terminal; the master device is used by a process to
- read data from and write data to the slave, thereby emulating a
- terminal. Typical programs for the master side are telnet servers
- and xterms.
-
- Linux has traditionally used the BSD-like names /dev/ptyxx for
- masters and /dev/ttyxx for slaves of pseudo terminals. This scheme
- has a number of problems. The GNU C library glibc 2.1 and later,
- however, supports the Unix98 naming standard: in order to acquire a
- pseudo terminal, a process opens /dev/ptmx; the number of the pseudo
- terminal is then made available to the process and the pseudo
- terminal slave can be accessed as /dev/pts/<number>. What was
- traditionally /dev/ttyp2 will then be /dev/pts/2, for example.
-
- All modern Linux systems use the Unix98 ptys. Say Y unless
- you're on an embedded system and want to conserve memory.
-
-config LEGACY_PTYS
- bool "Legacy (BSD) PTY support"
- default y
- help
- A pseudo terminal (PTY) is a software device consisting of two
- halves: a master and a slave. The slave device behaves identical to
- a physical terminal; the master device is used by a process to
- read data from and write data to the slave, thereby emulating a
- terminal. Typical programs for the master side are telnet servers
- and xterms.
-
- Linux has traditionally used the BSD-like names /dev/ptyxx
- for masters and /dev/ttyxx for slaves of pseudo
- terminals. This scheme has a number of problems, including
- security. This option enables these legacy devices; on most
- systems, it is safe to say N.
-
-config RAW_DRIVER
- tristate "RAW driver (/dev/raw/rawN)"
- depends on BLOCK
- help
- The raw driver permits block devices to be bound to /dev/raw/rawN.
- Once bound, I/O against /dev/raw/rawN uses efficient zero-copy I/O.
- See the raw(8) manpage for more details.
-
- Applications should preferably open the device (eg /dev/hda1)
- with the O_DIRECT flag.
-
-config MAX_RAW_DEVS
- int "Maximum number of RAW devices to support (1-8192)"
- depends on RAW_DRIVER
- default "256"
- help
- The maximum number of RAW devices that are supported.
- Default is 256. Increase this number in case you need lots of
- raw devices.
-
-config LEGACY_PTY_COUNT
- int "Maximum number of legacy PTY in use"
- depends on LEGACY_PTYS
- default "256"
- help
- The maximum number of legacy PTYs that can be used at any one time.
- The default is 256, and should be more than enough. Embedded
- systems may want to reduce this to save memory.
-
- When not in use, each legacy PTY occupies 12 bytes on 32-bit
- architectures and 24 bytes on 64-bit architectures.
-
-config WATCHDOG
- bool "Watchdog Timer Support"
-
-config WATCHDOG_NOWAYOUT
- bool "Disable watchdog shutdown on close"
- depends on WATCHDOG
-
-config SOFT_WATCHDOG
- tristate "Software Watchdog"
- depends on WATCHDOG
-
-config UML_WATCHDOG
- tristate "UML watchdog"
- depends on WATCHDOG
-
config UML_SOUND
tristate "Sound support"
help
@@ -211,29 +124,4 @@
tristate
default UML_SOUND
-#It is selected elsewhere, so kconfig would warn without this.
-config HW_RANDOM
- tristate
- default n
-
-config UML_RANDOM
- tristate "Hardware random number generator"
- help
- This option enables UML's "hardware" random number generator. It
- attaches itself to the host's /dev/random, supplying as much entropy
- as the host has, rather than the small amount the UML gets from its
- own drivers. It registers itself as a standard hardware random number
- generator, major 10, minor 183, and the canonical device name is
- /dev/hwrng.
- The way to make use of this is to install the rng-tools package
- (check your distro, or download from
- http://sourceforge.net/projects/gkernel/). rngd periodically reads
- /dev/hwrng and injects the entropy into /dev/random.
-
-config MMAPPER
- tristate "iomem emulation driver"
- help
- This driver allows a host file to be used as emulated IO memory inside
- UML.
-
endmenu
diff --git a/arch/um/Kconfig.rest b/arch/um/Kconfig.rest
index 0ccad0f..567eb5f 100644
--- a/arch/um/Kconfig.rest
+++ b/arch/um/Kconfig.rest
@@ -2,20 +2,14 @@
source "kernel/Kconfig.freezer"
-source "drivers/block/Kconfig"
-
source "arch/um/Kconfig.char"
-source "drivers/base/Kconfig"
+source "drivers/Kconfig"
source "net/Kconfig"
source "arch/um/Kconfig.net"
-source "drivers/net/Kconfig"
-
-source "drivers/connector/Kconfig"
-
source "fs/Kconfig"
source "security/Kconfig"
@@ -24,19 +18,4 @@
source "lib/Kconfig"
-source "drivers/scsi/Kconfig"
-
-source "drivers/md/Kconfig"
-
-if BROKEN
- source "drivers/mtd/Kconfig"
-endif
-
-source "drivers/leds/Kconfig"
-
-#This is just to shut up some Kconfig warnings, so no prompt.
-config INPUT
- tristate
- default n
-
source "arch/um/Kconfig.debug"
diff --git a/arch/um/Kconfig.um b/arch/um/Kconfig.um
index b5e675e..70fd690 100644
--- a/arch/um/Kconfig.um
+++ b/arch/um/Kconfig.um
@@ -148,5 +148,11 @@
be 1 << order pages. The default is OK unless you're running Valgrind
on UML, in which case, set this to 3.
+config MMAPPER
+ tristate "iomem emulation driver"
+ help
+ This driver allows a host file to be used as emulated IO memory inside
+ UML.
+
config NO_DMA
def_bool y
diff --git a/arch/um/Makefile b/arch/um/Makefile
index c0f712c..7730af6 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -20,15 +20,27 @@
MODE_INCLUDE += -I$(srctree)/$(ARCH_DIR)/include/shared/skas
+HEADER_ARCH := $(SUBARCH)
+
+# Additional ARCH settings for x86
+ifeq ($(SUBARCH),i386)
+ HEADER_ARCH := x86
+endif
+ifeq ($(SUBARCH),x86_64)
+ HEADER_ARCH := x86
+endif
+
+HOST_DIR := arch/$(HEADER_ARCH)
+
include $(srctree)/$(ARCH_DIR)/Makefile-skas
+include $(srctree)/$(HOST_DIR)/Makefile.um
+
+core-y += $(HOST_DIR)/um/
SHARED_HEADERS := $(ARCH_DIR)/include/shared
ARCH_INCLUDE := -I$(srctree)/$(SHARED_HEADERS)
-ARCH_INCLUDE += -I$(srctree)/$(ARCH_DIR)/sys-$(SUBARCH)/shared
-ifneq ($(KBUILD_SRC),)
-ARCH_INCLUDE += -I$(SHARED_HEADERS)
-endif
-KBUILD_CPPFLAGS += -I$(srctree)/$(ARCH_DIR)/sys-$(SUBARCH)
+ARCH_INCLUDE += -I$(srctree)/$(HOST_DIR)/um/shared
+KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/um
# -Dvmap=kernel_vmap prevents anything from referencing the libpcap.o symbol so
# named - it's a common symbol in libpcap, so we get a binary which crashes.
@@ -47,14 +59,12 @@
USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -D__KERNEL__,,\
$(patsubst -I%,,$(KBUILD_CFLAGS)))) $(ARCH_INCLUDE) $(MODE_INCLUDE) \
- $(filter -I%,$(CFLAGS)) -D_FILE_OFFSET_BITS=64
-
-include $(srctree)/$(ARCH_DIR)/Makefile-$(SUBARCH)
+ $(filter -I%,$(CFLAGS)) -D_FILE_OFFSET_BITS=64 -idirafter include
#This will adjust *FLAGS accordingly to the platform.
include $(srctree)/$(ARCH_DIR)/Makefile-os-$(OS)
-KBUILD_CPPFLAGS += -I$(srctree)/arch/$(HEADER_ARCH)/include
+KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/include
# -Derrno=kernel_errno - This turns all kernel references to errno into
# kernel_errno to separate them from the libc errno. This allows -fno-common
@@ -84,10 +94,9 @@
echo ' find in the kernel root.'
endef
-KBUILD_KCONFIG := arch/um/Kconfig.$(HEADER_ARCH)
+KBUILD_KCONFIG := $(HOST_DIR)/um/Kconfig
-archprepare: $(SHARED_HEADERS)/user_constants.h
-archprepare: $(SHARED_HEADERS)/kern_constants.h
+archprepare: include/generated/user_constants.h
LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib
@@ -118,9 +127,7 @@
# When cleaning we don't include .config, so we don't include
# TT or skas makefiles and don't clean skas_ptregs.h.
-CLEAN_FILES += linux x.i gmon.out \
- $(SHARED_HEADERS)/user_constants.h \
- $(SHARED_HEADERS)/kern_constants.h
+CLEAN_FILES += linux x.i gmon.out
archclean:
@find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \
@@ -128,8 +135,8 @@
# Generated files
-$(ARCH_DIR)/sys-$(SUBARCH)/user-offsets.s: FORCE
- $(Q)$(MAKE) $(build)=$(ARCH_DIR)/sys-$(SUBARCH) $@
+$(HOST_DIR)/um/user-offsets.s: FORCE
+ $(Q)$(MAKE) $(build)=$(HOST_DIR)/um $@
define filechk_gen-asm-offsets
(set -e; \
@@ -144,11 +151,7 @@
echo ""; )
endef
-$(SHARED_HEADERS)/user_constants.h: $(ARCH_DIR)/sys-$(SUBARCH)/user-offsets.s
+include/generated/user_constants.h: $(HOST_DIR)/um/user-offsets.s
$(call filechk,gen-asm-offsets)
-$(SHARED_HEADERS)/kern_constants.h:
- $(Q)mkdir -p $(dir $@)
- $(Q)echo '#include "../../../../include/generated/asm-offsets.h"' >$@
-
-export SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS HEADER_ARCH DEV_NULL_PATH
+export SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS DEV_NULL_PATH
diff --git a/arch/um/Makefile-x86_64 b/arch/um/Makefile-x86_64
deleted file mode 100644
index a9cd7e7..0000000
--- a/arch/um/Makefile-x86_64
+++ /dev/null
@@ -1,26 +0,0 @@
-# Copyright 2003 - 2004 Pathscale, Inc
-# Released under the GPL
-
-core-y += arch/um/sys-x86_64/ arch/x86/crypto/
-START := 0x60000000
-
-_extra_flags_ = -fno-builtin -m64
-
-KBUILD_CFLAGS += $(_extra_flags_)
-
-CHECKFLAGS += -m64 -D__x86_64__
-KBUILD_AFLAGS += -m64
-LDFLAGS += -m elf_x86_64
-KBUILD_CPPFLAGS += -m64
-
-ELF_ARCH := i386:x86-64
-ELF_FORMAT := elf64-x86-64
-HEADER_ARCH := x86
-
-# Not on all 64-bit distros /lib is a symlink to /lib64. PLD is an example.
-
-LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib64
-LINK-y += -m64
-
-# Do unit-at-a-time unconditionally on x86_64, following the host
-KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
diff --git a/arch/um/include/shared/chan_kern.h b/arch/um/drivers/chan.h
similarity index 94%
rename from arch/um/include/shared/chan_kern.h
rename to arch/um/drivers/chan.h
index 1e65145..8df0fd9 100644
--- a/arch/um/include/shared/chan_kern.h
+++ b/arch/um/drivers/chan.h
@@ -6,9 +6,9 @@
#ifndef __CHAN_KERN_H__
#define __CHAN_KERN_H__
-#include "linux/tty.h"
-#include "linux/list.h"
-#include "linux/console.h"
+#include <linux/tty.h>
+#include <linux/list.h>
+#include <linux/console.h>
#include "chan_user.h"
#include "line.h"
diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c
index d4191fe..420e2c8 100644
--- a/arch/um/drivers/chan_kern.c
+++ b/arch/um/drivers/chan_kern.c
@@ -6,7 +6,7 @@
#include <linux/slab.h>
#include <linux/tty.h>
#include <linux/tty_flip.h>
-#include "chan_kern.h"
+#include "chan.h"
#include "os.h"
#ifdef CONFIG_NOCONFIG_CHAN
@@ -358,11 +358,11 @@
return 0;
}
-static void free_one_chan(struct chan *chan, int delay_free_irq)
+static void free_one_chan(struct chan *chan)
{
list_del(&chan->list);
- close_one_chan(chan, delay_free_irq);
+ close_one_chan(chan, 0);
if (chan->ops->free != NULL)
(*chan->ops->free)(chan->data);
@@ -372,14 +372,14 @@
kfree(chan);
}
-static void free_chan(struct list_head *chans, int delay_free_irq)
+static void free_chan(struct list_head *chans)
{
struct list_head *ele, *next;
struct chan *chan;
list_for_each_safe(ele, next, chans) {
chan = list_entry(ele, struct chan, list);
- free_one_chan(chan, delay_free_irq);
+ free_one_chan(chan);
}
}
@@ -547,7 +547,7 @@
char *in, *out;
if (!list_empty(chans)) {
- free_chan(chans, 0);
+ free_chan(chans);
INIT_LIST_HEAD(chans);
}
diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c
index cfeb3f4..f180813 100644
--- a/arch/um/drivers/chan_user.c
+++ b/arch/um/drivers/chan_user.c
@@ -11,10 +11,8 @@
#include <termios.h>
#include <sys/ioctl.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
void generic_close(int fd, void *unused)
{
@@ -283,7 +281,12 @@
return;
pid = tcgetpgrp(fd);
- if (!is_skas_winch(pid, fd, tty) && (pid == -1)) {
+ if (is_skas_winch(pid, fd, tty)) {
+ register_winch_irq(-1, fd, -1, tty, 0);
+ return;
+ }
+
+ if (pid == -1) {
thread = winch_tramp(fd, tty, &thread_fd, &stack);
if (thread < 0)
return;
diff --git a/arch/um/include/shared/chan_user.h b/arch/um/drivers/chan_user.h
similarity index 100%
rename from arch/um/include/shared/chan_user.h
rename to arch/um/drivers/chan_user.h
diff --git a/arch/um/drivers/cow_sys.h b/arch/um/drivers/cow_sys.h
index f5701fd..7f2ed0b 100644
--- a/arch/um/drivers/cow_sys.h
+++ b/arch/um/drivers/cow_sys.h
@@ -3,7 +3,6 @@
#include "kern_util.h"
#include "os.h"
-#include "user.h"
#include "um_malloc.h"
static inline void *cow_malloc(int size)
diff --git a/arch/um/drivers/daemon_user.c b/arch/um/drivers/daemon_user.c
index f8e85e0..a4fd7bc 100644
--- a/arch/um/drivers/daemon_user.c
+++ b/arch/um/drivers/daemon_user.c
@@ -17,7 +17,6 @@
#include "net_user.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
enum request_type { REQ_NEW_CONTROL };
diff --git a/arch/um/drivers/fd.c b/arch/um/drivers/fd.c
index f5a981a..5b81d25 100644
--- a/arch/um/drivers/fd.c
+++ b/arch/um/drivers/fd.c
@@ -9,10 +9,8 @@
#include <errno.h>
#include <termios.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
struct fd_chan {
int fd;
diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c
index 84dce3f..0345d62 100644
--- a/arch/um/drivers/harddog_user.c
+++ b/arch/um/drivers/harddog_user.c
@@ -7,7 +7,6 @@
#include <unistd.h>
#include <errno.h>
#include "os.h"
-#include "user.h"
struct dog_data {
int stdin;
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index 364c8a1..c1cf220 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -7,7 +7,7 @@
#include "linux/kd.h"
#include "linux/sched.h"
#include "linux/slab.h"
-#include "chan_kern.h"
+#include "chan.h"
#include "irq_kern.h"
#include "irq_user.h"
#include "kern_util.h"
diff --git a/arch/um/include/shared/line.h b/arch/um/drivers/line.h
similarity index 100%
rename from arch/um/include/shared/line.h
rename to arch/um/drivers/line.h
diff --git a/arch/um/include/shared/mconsole.h b/arch/um/drivers/mconsole.h
similarity index 100%
rename from arch/um/include/shared/mconsole.h
rename to arch/um/drivers/mconsole.h
diff --git a/arch/um/include/shared/mconsole_kern.h b/arch/um/drivers/mconsole_kern.h
similarity index 100%
rename from arch/um/include/shared/mconsole_kern.h
rename to arch/um/drivers/mconsole_kern.h
diff --git a/arch/um/drivers/mconsole_user.c b/arch/um/drivers/mconsole_user.c
index f8cf4c8..9920982 100644
--- a/arch/um/drivers/mconsole_user.c
+++ b/arch/um/drivers/mconsole_user.c
@@ -10,9 +10,7 @@
#include <sys/socket.h>
#include <sys/uio.h>
#include <sys/un.h>
-#include "kern_constants.h"
#include "mconsole.h"
-#include "user.h"
static struct mconsole_command commands[] = {
/*
diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c
index 5201188..05090c3 100644
--- a/arch/um/drivers/net_user.c
+++ b/arch/um/drivers/net_user.c
@@ -12,10 +12,8 @@
#include <sys/socket.h>
#include <sys/wait.h>
#include "net_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
int tap_open_common(void *dev, char *gate_addr)
{
diff --git a/arch/um/drivers/pcap_user.c b/arch/um/drivers/pcap_user.c
index 5f90358..702a75b 100644
--- a/arch/um/drivers/pcap_user.c
+++ b/arch/um/drivers/pcap_user.c
@@ -9,9 +9,7 @@
#include <asm/types.h>
#include "net_user.h"
#include "pcap_user.h"
-#include "kern_constants.h"
#include "um_malloc.h"
-#include "user.h"
#define PCAP_FD(p) (*(int *)(p))
diff --git a/arch/um/drivers/port_user.c b/arch/um/drivers/port_user.c
index b49bf56..7b010b7 100644
--- a/arch/um/drivers/port_user.c
+++ b/arch/um/drivers/port_user.c
@@ -10,11 +10,9 @@
#include <unistd.h>
#include <netinet/in.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "port.h"
#include "um_malloc.h"
-#include "user.h"
struct port_chan {
int raw;
diff --git a/arch/um/drivers/pty.c b/arch/um/drivers/pty.c
index 1113911..cff2b75 100644
--- a/arch/um/drivers/pty.c
+++ b/arch/um/drivers/pty.c
@@ -12,10 +12,8 @@
#include <termios.h>
#include <sys/stat.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
struct pty_chan {
void (*announce)(char *dev_name, int dev);
diff --git a/arch/um/drivers/slip_user.c b/arch/um/drivers/slip_user.c
index cbacfc4..932b4d6 100644
--- a/arch/um/drivers/slip_user.c
+++ b/arch/um/drivers/slip_user.c
@@ -11,12 +11,10 @@
#include <string.h>
#include <sys/termios.h>
#include <sys/wait.h>
-#include "kern_constants.h"
#include "net_user.h"
#include "os.h"
#include "slip.h"
#include "um_malloc.h"
-#include "user.h"
static int slip_user_init(void *data, void *dev)
{
diff --git a/arch/um/drivers/slirp_user.c b/arch/um/drivers/slirp_user.c
index a0ada8f..db4adb6 100644
--- a/arch/um/drivers/slirp_user.c
+++ b/arch/um/drivers/slirp_user.c
@@ -7,11 +7,9 @@
#include <errno.h>
#include <string.h>
#include <sys/wait.h>
-#include "kern_constants.h"
#include "net_user.h"
#include "os.h"
#include "slirp.h"
-#include "user.h"
static int slirp_user_init(void *data, void *dev)
{
diff --git a/arch/um/drivers/ssl.c b/arch/um/drivers/ssl.c
index f1786e6..9d8c20a 100644
--- a/arch/um/drivers/ssl.c
+++ b/arch/um/drivers/ssl.c
@@ -12,10 +12,8 @@
#include "linux/console.h"
#include "asm/termbits.h"
#include "asm/irq.h"
-#include "line.h"
#include "ssl.h"
-#include "chan_kern.h"
-#include "kern.h"
+#include "chan.h"
#include "init.h"
#include "irq_user.h"
#include "mconsole_kern.h"
diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c
index 49266f6..088776f 100644
--- a/arch/um/drivers/stdio_console.c
+++ b/arch/um/drivers/stdio_console.c
@@ -20,8 +20,7 @@
#include "asm/current.h"
#include "asm/irq.h"
#include "stdio_console.h"
-#include "line.h"
-#include "chan_kern.h"
+#include "chan.h"
#include "irq_user.h"
#include "mconsole_kern.h"
#include "init.h"
diff --git a/arch/um/drivers/tty.c b/arch/um/drivers/tty.c
index 495858a..a97391f 100644
--- a/arch/um/drivers/tty.c
+++ b/arch/um/drivers/tty.c
@@ -7,10 +7,8 @@
#include <fcntl.h>
#include <termios.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
struct tty_chan {
char *dev;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 620f5b7..944453a 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -46,7 +46,6 @@
#include "asm/tlbflush.h"
#include "mem_user.h"
#include "kern_util.h"
-#include "kern.h"
#include "mconsole_kern.h"
#include "init.h"
#include "irq_user.h"
@@ -54,7 +53,6 @@
#include "ubd_user.h"
#include "os.h"
#include "mem.h"
-#include "mem_kern.h"
#include "cow.h"
enum ubd_req { UBD_READ, UBD_WRITE };
@@ -513,8 +511,37 @@
static inline int ubd_file_size(struct ubd *ubd_dev, __u64 *size_out)
{
char *file;
+ int fd;
+ int err;
- file = ubd_dev->cow.file ? ubd_dev->cow.file : ubd_dev->file;
+ __u32 version;
+ __u32 align;
+ char *backing_file;
+ time_t mtime;
+ unsigned long long size;
+ int sector_size;
+ int bitmap_offset;
+
+ if (ubd_dev->file && ubd_dev->cow.file) {
+ file = ubd_dev->cow.file;
+
+ goto out;
+ }
+
+ fd = os_open_file(ubd_dev->file, global_openflags, 0);
+ if (fd < 0)
+ return fd;
+
+ err = read_cow_header(file_reader, &fd, &version, &backing_file, \
+ &mtime, &size, §or_size, &align, &bitmap_offset);
+ os_close_file(fd);
+
+ if(err == -EINVAL)
+ file = ubd_dev->file;
+ else
+ file = backing_file;
+
+out:
return os_file_size(file, size_out);
}
diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c
index b591bb9..007b94d 100644
--- a/arch/um/drivers/ubd_user.c
+++ b/arch/um/drivers/ubd_user.c
@@ -16,7 +16,6 @@
#include <sys/mman.h>
#include <sys/param.h>
#include "asm/types.h"
-#include "user.h"
#include "ubd_user.h"
#include "os.h"
#include "cow.h"
diff --git a/arch/um/include/shared/ubd_user.h b/arch/um/drivers/ubd_user.h
similarity index 100%
rename from arch/um/include/shared/ubd_user.h
rename to arch/um/drivers/ubd_user.h
diff --git a/arch/um/drivers/umcast_user.c b/arch/um/drivers/umcast_user.c
index 59c56fd..010fa2d 100644
--- a/arch/um/drivers/umcast_user.c
+++ b/arch/um/drivers/umcast_user.c
@@ -15,11 +15,9 @@
#include <unistd.h>
#include <errno.h>
#include <netinet/in.h>
-#include "kern_constants.h"
#include "umcast.h"
#include "net_user.h"
#include "um_malloc.h"
-#include "user.h"
static struct sockaddr_in *new_addr(char *addr, unsigned short port)
{
diff --git a/arch/um/drivers/vde_user.c b/arch/um/drivers/vde_user.c
index c5c4325..b8c2867 100644
--- a/arch/um/drivers/vde_user.c
+++ b/arch/um/drivers/vde_user.c
@@ -6,10 +6,8 @@
#include <stddef.h>
#include <errno.h>
#include <libvdeplug.h>
-#include "kern_constants.h"
#include "net_user.h"
#include "um_malloc.h"
-#include "user.h"
#include "vde.h"
static int vde_user_init(void *data, void *dev)
diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c
index 2e1de57..969110e 100644
--- a/arch/um/drivers/xterm.c
+++ b/arch/um/drivers/xterm.c
@@ -11,10 +11,8 @@
#include <string.h>
#include <termios.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
#include "xterm.h"
struct xterm_chan {
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
new file mode 100644
index 0000000..451f451
--- /dev/null
+++ b/arch/um/include/asm/Kbuild
@@ -0,0 +1,3 @@
+generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
+generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
+generic-y += ftrace.h
diff --git a/arch/um/include/asm/bug.h b/arch/um/include/asm/bug.h
deleted file mode 100644
index 9e33b86..0000000
--- a/arch/um/include/asm/bug.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_BUG_H
-#define __UM_BUG_H
-
-#include <asm-generic/bug.h>
-
-#endif
diff --git a/arch/um/include/asm/checksum.h b/arch/um/include/asm/checksum.h
deleted file mode 100644
index 5b50136..0000000
--- a/arch/um/include/asm/checksum.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_CHECKSUM_H
-#define __UM_CHECKSUM_H
-
-#include "sysdep/checksum.h"
-
-#endif
diff --git a/arch/um/include/asm/cputime.h b/arch/um/include/asm/cputime.h
deleted file mode 100644
index c84acba..0000000
--- a/arch/um/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_CPUTIME_H
-#define __UM_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __UM_CPUTIME_H */
diff --git a/arch/um/include/asm/device.h b/arch/um/include/asm/device.h
deleted file mode 100644
index d8f9872..0000000
--- a/arch/um/include/asm/device.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-#include <asm-generic/device.h>
-
diff --git a/arch/um/include/asm/emergency-restart.h b/arch/um/include/asm/emergency-restart.h
deleted file mode 100644
index 108d8c4..0000000
--- a/arch/um/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/um/include/asm/ftrace.h b/arch/um/include/asm/ftrace.h
deleted file mode 100644
index 40a8c17..0000000
--- a/arch/um/include/asm/ftrace.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/um/include/asm/futex.h b/arch/um/include/asm/futex.h
deleted file mode 100644
index 6a332a9..0000000
--- a/arch/um/include/asm/futex.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_FUTEX_H
-#define _ASM_FUTEX_H
-
-#include <asm-generic/futex.h>
-
-#endif
diff --git a/arch/um/include/asm/hardirq.h b/arch/um/include/asm/hardirq.h
deleted file mode 100644
index fb3c05a..0000000
--- a/arch/um/include/asm/hardirq.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/hardirq.h>
diff --git a/arch/um/include/asm/hw_irq.h b/arch/um/include/asm/hw_irq.h
deleted file mode 100644
index 1cf84cf..0000000
--- a/arch/um/include/asm/hw_irq.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ASM_UM_HW_IRQ_H
-#define _ASM_UM_HW_IRQ_H
-
-#include "asm/irq.h"
-#include "asm/archparam.h"
-
-#endif
diff --git a/arch/um/include/asm/irq_regs.h b/arch/um/include/asm/irq_regs.h
deleted file mode 100644
index 3dd9c0b..0000000
--- a/arch/um/include/asm/irq_regs.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/um/include/asm/irqflags.h b/arch/um/include/asm/irqflags.h
index 659b9ab..c780d8a 100644
--- a/arch/um/include/asm/irqflags.h
+++ b/arch/um/include/asm/irqflags.h
@@ -1,6 +1,42 @@
#ifndef __UM_IRQFLAGS_H
#define __UM_IRQFLAGS_H
-/* Empty for now */
+extern int get_signals(void);
+extern int set_signals(int enable);
+extern void block_signals(void);
+extern void unblock_signals(void);
+
+static inline unsigned long arch_local_save_flags(void)
+{
+ return get_signals();
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+ set_signals(flags);
+}
+
+static inline void arch_local_irq_enable(void)
+{
+ unblock_signals();
+}
+
+static inline void arch_local_irq_disable(void)
+{
+ block_signals();
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+ unsigned long flags;
+ flags = arch_local_save_flags();
+ arch_local_irq_disable();
+ return flags;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+ return arch_local_save_flags() == 0;
+}
#endif
diff --git a/arch/um/include/asm/kdebug.h b/arch/um/include/asm/kdebug.h
deleted file mode 100644
index 6ece1b0..0000000
--- a/arch/um/include/asm/kdebug.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/kdebug.h>
diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h
index cf259de..30509b9 100644
--- a/arch/um/include/asm/mmu.h
+++ b/arch/um/include/asm/mmu.h
@@ -1,12 +1,24 @@
/*
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*/
-#ifndef __MMU_H
-#define __MMU_H
+#ifndef __ARCH_UM_MMU_H
+#define __ARCH_UM_MMU_H
-#include "um_mmu.h"
+#include "mm_id.h"
+#include <asm/mm_context.h>
+
+typedef struct mm_context {
+ struct mm_id id;
+ struct uml_arch_mm_context arch;
+ struct page **stub_pages;
+} mm_context_t;
+
+extern void __switch_mm(struct mm_id * mm_idp);
+
+/* Avoid tangled inclusion with asm/ldt.h */
+extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm);
+extern void free_ldt(struct mm_context *mm);
#endif
-
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index 34d8130..591b3d8 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -6,15 +6,12 @@
#ifndef __UM_MMU_CONTEXT_H
#define __UM_MMU_CONTEXT_H
-#include "linux/sched.h"
-#include "um_mmu.h"
+#include <linux/sched.h>
+#include <asm/mmu.h>
extern void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm);
extern void arch_exit_mmap(struct mm_struct *mm);
-#define get_mmu_context(task) do ; while(0)
-#define activate_context(tsk) do ; while(0)
-
#define deactivate_mm(tsk,mm) do { } while (0)
extern void force_flush_all(void);
diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h
index 4cc9b6c..7cfc3ce 100644
--- a/arch/um/include/asm/page.h
+++ b/arch/um/include/asm/page.h
@@ -19,7 +19,7 @@
struct page;
#include <linux/types.h>
-#include <sysdep/vm-flags.h>
+#include <asm/vm-flags.h>
/*
* These are used to make use of C type-checking..
diff --git a/arch/um/include/asm/page_offset.h b/arch/um/include/asm/page_offset.h
deleted file mode 100644
index 1c168df..0000000
--- a/arch/um/include/asm/page_offset.h
+++ /dev/null
@@ -1 +0,0 @@
-#define PAGE_OFFSET_RAW (uml_physmem)
diff --git a/arch/um/include/asm/pda.h b/arch/um/include/asm/pda.h
deleted file mode 100644
index ddcd774..0000000
--- a/arch/um/include/asm/pda.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_PDA_X86_64_H
-#define __UM_PDA_X86_64_H
-
-/* XXX */
-struct foo {
- unsigned int __softirq_pending;
- unsigned int __nmi_count;
-};
-
-extern struct foo me;
-
-#define read_pda(me) (&me)
-
-#endif
-
diff --git a/arch/um/include/asm/percpu.h b/arch/um/include/asm/percpu.h
deleted file mode 100644
index efe7508..0000000
--- a/arch/um/include/asm/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_PERCPU_H
-#define __UM_PERCPU_H
-
-#include <asm-generic/percpu.h>
-
-#endif /* __UM_PERCPU_H */
diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h
index 1a7d275..f605d3c 100644
--- a/arch/um/include/asm/ptrace-generic.h
+++ b/arch/um/include/asm/ptrace-generic.h
@@ -23,17 +23,10 @@
#define PT_REGS_IP(r) UPT_IP(&(r)->regs)
#define PT_REGS_SP(r) UPT_SP(&(r)->regs)
-#define PT_REG(r, reg) UPT_REG(&(r)->regs, reg)
-#define PT_REGS_SET(r, reg, val) UPT_SET(&(r)->regs, reg, val)
-
-#define PT_REGS_SET_SYSCALL_RETURN(r, res) \
- UPT_SET_SYSCALL_RETURN(&(r)->regs, res)
#define PT_REGS_RESTART_SYSCALL(r) UPT_RESTART_SYSCALL(&(r)->regs)
#define PT_REGS_SYSCALL_NR(r) UPT_SYSCALL_NR(&(r)->regs)
-#define PT_REGS_SC(r) UPT_SC(&(r)->regs)
-
#define instruction_pointer(regs) PT_REGS_IP(regs)
struct task_struct;
diff --git a/arch/um/include/asm/sections.h b/arch/um/include/asm/sections.h
deleted file mode 100644
index 6b0231e..0000000
--- a/arch/um/include/asm/sections.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _UM_SECTIONS_H
-#define _UM_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/arch/um/include/asm/system.h b/arch/um/include/asm/system.h
deleted file mode 100644
index 68a90ec..0000000
--- a/arch/um/include/asm/system.h
+++ /dev/null
@@ -1,47 +0,0 @@
-#ifndef __UM_SYSTEM_GENERIC_H
-#define __UM_SYSTEM_GENERIC_H
-
-#include "sysdep/system.h"
-
-extern int get_signals(void);
-extern int set_signals(int enable);
-extern void block_signals(void);
-extern void unblock_signals(void);
-
-static inline unsigned long arch_local_save_flags(void)
-{
- return get_signals();
-}
-
-static inline void arch_local_irq_restore(unsigned long flags)
-{
- set_signals(flags);
-}
-
-static inline void arch_local_irq_enable(void)
-{
- unblock_signals();
-}
-
-static inline void arch_local_irq_disable(void)
-{
- block_signals();
-}
-
-static inline unsigned long arch_local_irq_save(void)
-{
- unsigned long flags;
- flags = arch_local_save_flags();
- arch_local_irq_disable();
- return flags;
-}
-
-static inline bool arch_irqs_disabled(void)
-{
- return arch_local_save_flags() == 0;
-}
-
-extern void *_switch_to(void *prev, void *next, void *last);
-#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
-
-#endif
diff --git a/arch/um/include/asm/topology.h b/arch/um/include/asm/topology.h
deleted file mode 100644
index 0905e4f..0000000
--- a/arch/um/include/asm/topology.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_UM_TOPOLOGY_H
-#define _ASM_UM_TOPOLOGY_H
-
-#include <asm-generic/topology.h>
-
-#endif
diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h
index b9a895d..3f22fbf 100644
--- a/arch/um/include/asm/uaccess.h
+++ b/arch/um/include/asm/uaccess.h
@@ -6,15 +6,15 @@
#ifndef __UM_UACCESS_H
#define __UM_UACCESS_H
-#include <asm/errno.h>
-#include <asm/processor.h>
-
/* thread_info has a mm_segment_t in it, so put the definition up here */
typedef struct {
unsigned long seg;
} mm_segment_t;
-#include "linux/thread_info.h"
+#include <linux/thread_info.h>
+#include <linux/errno.h>
+#include <asm/processor.h>
+#include <asm/elf.h>
#define VERIFY_READ 0
#define VERIFY_WRITE 1
@@ -38,7 +38,86 @@
#define segment_eq(a, b) ((a).seg == (b).seg)
-#include "um_uaccess.h"
+#define __under_task_size(addr, size) \
+ (((unsigned long) (addr) < TASK_SIZE) && \
+ (((unsigned long) (addr) + (size)) < TASK_SIZE))
+
+#define __access_ok_vsyscall(type, addr, size) \
+ ((type == VERIFY_READ) && \
+ ((unsigned long) (addr) >= FIXADDR_USER_START) && \
+ ((unsigned long) (addr) + (size) <= FIXADDR_USER_END) && \
+ ((unsigned long) (addr) + (size) >= (unsigned long)(addr)))
+
+#define __addr_range_nowrap(addr, size) \
+ ((unsigned long) (addr) <= ((unsigned long) (addr) + (size)))
+
+#define access_ok(type, addr, size) \
+ (__addr_range_nowrap(addr, size) && \
+ (__under_task_size(addr, size) || \
+ __access_ok_vsyscall(type, addr, size) || \
+ segment_eq(get_fs(), KERNEL_DS)))
+
+extern int copy_from_user(void *to, const void __user *from, int n);
+extern int copy_to_user(void __user *to, const void *from, int n);
+
+/*
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst: Destination address, in kernel space. This buffer must be at
+ * least @count bytes long.
+ * @src: Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+
+extern int strncpy_from_user(char *dst, const char __user *src, int count);
+
+/*
+ * __clear_user: - Zero a block of memory in user space, with less checking.
+ * @to: Destination address, in user space.
+ * @n: Number of bytes to zero.
+ *
+ * Zero a block of memory in user space. Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+extern int __clear_user(void __user *mem, int len);
+
+/*
+ * clear_user: - Zero a block of memory in user space.
+ * @to: Destination address, in user space.
+ * @n: Number of bytes to zero.
+ *
+ * Zero a block of memory in user space.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+extern int clear_user(void __user *mem, int len);
+
+/*
+ * strlen_user: - Get the size of a string in user space.
+ * @str: The string to measure.
+ * @n: The maximum valid length
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * On exception, returns 0.
+ * If the string is too long, returns a value greater than @n.
+ */
+extern int strnlen_user(const void __user *str, int len);
#define __copy_from_user(to, from, n) copy_from_user(to, from, n)
diff --git a/arch/um/include/asm/xor.h b/arch/um/include/asm/xor.h
deleted file mode 100644
index a19db3e..0000000
--- a/arch/um/include/asm/xor.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_XOR_H
-#define __UM_XOR_H
-
-#include "asm-generic/xor.h"
-
-#endif
diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h
index a92b678..896e166 100644
--- a/arch/um/include/shared/as-layout.h
+++ b/arch/um/include/shared/as-layout.h
@@ -6,7 +6,7 @@
#ifndef __START_H__
#define __START_H__
-#include "kern_constants.h"
+#include <generated/asm-offsets.h>
/*
* Stolen from linux/const.h, which can't be directly included since
diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h
index 72009c7..d7fe563 100644
--- a/arch/um/include/shared/common-offsets.h
+++ b/arch/um/include/shared/common-offsets.h
@@ -2,7 +2,6 @@
DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE);
-OFFSET(HOST_TASK_REGS, task_struct, thread.regs);
OFFSET(HOST_TASK_PID, task_struct, pid);
DEFINE(UM_KERN_PAGE_SIZE, PAGE_SIZE);
diff --git a/arch/um/include/shared/initrd.h b/arch/um/include/shared/initrd.h
deleted file mode 100644
index 22673bc..0000000
--- a/arch/um/include/shared/initrd.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * Copyright (C) 2000 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __INITRD_USER_H__
-#define __INITRD_USER_H__
-
-extern int load_initrd(char *filename, void *buf, int size);
-
-#endif
-
diff --git a/arch/um/include/shared/kern.h b/arch/um/include/shared/kern.h
index 4ce3fc6..6cd0124 100644
--- a/arch/um/include/shared/kern.h
+++ b/arch/um/include/shared/kern.h
@@ -13,28 +13,10 @@
* includes.
*/
-extern int errno;
-
-extern int clone(int (*proc)(void *), void *sp, int flags, void *data);
-extern int sleep(int);
extern int printf(const char *fmt, ...);
-extern char *strerror(int errnum);
-extern char *ptsname(int __fd);
-extern int munmap(void *, int);
extern void *sbrk(int increment);
-extern void *malloc(int size);
-extern void perror(char *err);
-extern int kill(int pid, int sig);
-extern int getuid(void);
-extern int getgid(void);
extern int pause(void);
-extern int write(int, const void *, int);
extern void exit(int);
-extern int close(int);
-extern int read(unsigned int, char *, int);
-extern int pipe(int *);
-extern int sched_yield(void);
-extern int ptrace(int op, int pid, long addr, long data);
#endif
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index 3c34122..0f14838 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -21,7 +21,6 @@
extern void free_stack(unsigned long stack, int order);
extern int do_signal(void);
-extern void copy_sc(struct uml_pt_regs *regs, void *from);
extern void interrupt_end(void);
extern void relay_signal(int sig, struct uml_pt_regs *regs);
diff --git a/arch/um/include/shared/ldt.h b/arch/um/include/shared/ldt.h
deleted file mode 100644
index a7f999a..0000000
--- a/arch/um/include/shared/ldt.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright (C) 2004 Fujitsu Siemens Computers GmbH
- * Licensed under the GPL
- *
- * Author: Bodo Stroesser <bstroesser@fujitsu-siemens.com>
- */
-
-#ifndef __ASM_LDT_H
-#define __ASM_LDT_H
-
-#include <linux/mutex.h>
-#include <sysdep/host_ldt.h>
-
-extern void ldt_host_info(void);
-
-#define LDT_PAGES_MAX \
- ((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE)
-#define LDT_ENTRIES_PER_PAGE \
- (PAGE_SIZE/LDT_ENTRY_SIZE)
-#define LDT_DIRECT_ENTRIES \
- ((LDT_PAGES_MAX*sizeof(void *))/LDT_ENTRY_SIZE)
-
-struct ldt_entry {
- __u32 a;
- __u32 b;
-};
-
-typedef struct uml_ldt {
- int entry_count;
- struct mutex lock;
- union {
- struct ldt_entry * pages[LDT_PAGES_MAX];
- struct ldt_entry entries[LDT_DIRECT_ENTRIES];
- } u;
-} uml_ldt_t;
-
-#endif
diff --git a/arch/um/include/shared/mem_kern.h b/arch/um/include/shared/mem_kern.h
deleted file mode 100644
index 69be0fd..0000000
--- a/arch/um/include/shared/mem_kern.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (C) 2003 Jeff Dike (jdike@addtoit.com)
- * Licensed under the GPL
- */
-
-#ifndef __MEM_KERN_H__
-#define __MEM_KERN_H__
-
-#include "linux/list.h"
-#include "linux/types.h"
-
-struct remapper {
- struct list_head list;
- int (*proc)(int, unsigned long, int, __u64);
-};
-
-extern void register_remapper(struct remapper *info);
-
-#endif
-
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 83c7c2e..89b686c1 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -10,7 +10,6 @@
#include "irq_user.h"
#include "longjmp.h"
#include "mm_id.h"
-#include "sysdep/tls.h"
#define CATCH_EINTR(expr) while ((errno = 0, ((expr) < 0)) && (errno == EINTR))
@@ -203,12 +202,6 @@
extern int can_drop_memory(void);
extern void os_flush_stdout(void);
-/* uaccess.c */
-extern unsigned long __do_user_copy(void *to, const void *from, int n,
- void **fault_addr, jmp_buf **fault_catcher,
- void (*op)(void *to, const void *from,
- int n), int *faulted_out);
-
/* execvp.c */
extern int execvp_noalloc(char *buf, const char *file, char *const argv[]);
/* helper.c */
@@ -218,10 +211,6 @@
extern int helper_wait(int pid);
-/* tls.c */
-extern int os_set_thread_area(user_desc_t *info, int pid);
-extern int os_get_thread_area(user_desc_t *info, int pid);
-
/* umid.c */
extern int umid_file_name(char *name, char *buf, int len);
extern int set_umid(char *name);
@@ -231,7 +220,7 @@
extern void timer_init(void);
extern void set_sigstack(void *sig_stack, int size);
extern void remove_sigstack(void);
-extern void set_handler(int sig, void (*handler)(int), int flags, ...);
+extern void set_handler(int sig);
extern int change_sig(int signal, int on);
extern void block_signals(void);
extern void unblock_signals(void);
diff --git a/arch/um/include/shared/process.h b/arch/um/include/shared/process.h
deleted file mode 100644
index bb873a5..0000000
--- a/arch/um/include/shared/process.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Copyright (C) 2000 - 2008 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __PROCESS_H__
-#define __PROCESS_H__
-
-#include <signal.h>
-
-/* Copied from linux/compiler-gcc.h since we can't include it directly */
-#define barrier() __asm__ __volatile__("": : :"memory")
-
-extern void sig_handler(int sig, struct sigcontext *sc);
-extern void alarm_handler(int sig, struct sigcontext *sc);
-
-#endif
diff --git a/arch/um/include/shared/ptrace_user.h b/arch/um/include/shared/ptrace_user.h
index 7fd8539..56b2f28 100644
--- a/arch/um/include/shared/ptrace_user.h
+++ b/arch/um/include/shared/ptrace_user.h
@@ -6,7 +6,8 @@
#ifndef __PTRACE_USER_H__
#define __PTRACE_USER_H__
-#include "sysdep/ptrace_user.h"
+#include <sys/ptrace.h>
+#include <sysdep/ptrace_user.h>
extern int ptrace_getregs(long pid, unsigned long *regs_out);
extern int ptrace_setregs(long pid, unsigned long *regs_in);
diff --git a/arch/um/include/shared/skas_ptregs.h b/arch/um/include/shared/skas_ptregs.h
deleted file mode 100644
index 73db19e..0000000
--- a/arch/um/include/shared/skas_ptregs.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __SKAS_PT_REGS_
-#define __SKAS_PT_REGS_
-
-#include <user_constants.h>
-
-#endif
diff --git a/arch/um/include/shared/syscall.h b/arch/um/include/shared/syscall.h
deleted file mode 100644
index dda1df9..0000000
--- a/arch/um/include/shared/syscall.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __SYSCALL_USER_H
-#define __SYSCALL_USER_H
-
-extern int record_syscall_start(int syscall);
-extern void record_syscall_end(int index, long result);
-
-#endif
diff --git a/arch/um/include/shared/task.h b/arch/um/include/shared/task.h
deleted file mode 100644
index 3fe726b..0000000
--- a/arch/um/include/shared/task.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __TASK_H
-#define __TASK_H
-
-#include <kern_constants.h>
-
-#define TASK_REGS(task) ((struct uml_pt_regs *) &(((char *) (task))[HOST_TASK_REGS]))
-#define TASK_PID(task) *((int *) &(((char *) (task))[HOST_TASK_PID]))
-
-#endif
diff --git a/arch/um/include/shared/tlb.h b/arch/um/include/shared/tlb.h
deleted file mode 100644
index ecd2265..0000000
--- a/arch/um/include/shared/tlb.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __TLB_H__
-#define __TLB_H__
-
-#include "um_mmu.h"
-
-extern void force_flush_all(void);
-extern int flush_tlb_kernel_range_common(unsigned long start,
- unsigned long end);
-
-#endif
diff --git a/arch/um/include/shared/um_malloc.h b/arch/um/include/shared/um_malloc.h
index c554d70..6395fef 100644
--- a/arch/um/include/shared/um_malloc.h
+++ b/arch/um/include/shared/um_malloc.h
@@ -6,7 +6,7 @@
#ifndef __UM_MALLOC_H__
#define __UM_MALLOC_H__
-#include "kern_constants.h"
+#include <generated/asm-offsets.h>
extern void *uml_kmalloc(int size, int flags);
extern void kfree(const void *ptr);
diff --git a/arch/um/include/shared/um_mmu.h b/arch/um/include/shared/um_mmu.h
deleted file mode 100644
index b1a7e47..0000000
--- a/arch/um/include/shared/um_mmu.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __ARCH_UM_MMU_H
-#define __ARCH_UM_MMU_H
-
-#include "mm_id.h"
-#include "ldt.h"
-
-typedef struct mm_context {
- struct mm_id id;
- struct uml_ldt ldt;
- struct page **stub_pages;
-} mm_context_t;
-
-extern void __switch_mm(struct mm_id * mm_idp);
-
-/* Avoid tangled inclusion with asm/ldt.h */
-extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm);
-extern void free_ldt(struct mm_context *mm);
-
-#endif
diff --git a/arch/um/include/shared/um_uaccess.h b/arch/um/include/shared/um_uaccess.h
deleted file mode 100644
index 45c0499..0000000
--- a/arch/um/include/shared/um_uaccess.h
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __ARCH_UM_UACCESS_H
-#define __ARCH_UM_UACCESS_H
-
-#include <asm/elf.h>
-#include <asm/fixmap.h>
-#include "sysdep/archsetjmp.h"
-
-#define __under_task_size(addr, size) \
- (((unsigned long) (addr) < TASK_SIZE) && \
- (((unsigned long) (addr) + (size)) < TASK_SIZE))
-
-#define __access_ok_vsyscall(type, addr, size) \
- ((type == VERIFY_READ) && \
- ((unsigned long) (addr) >= FIXADDR_USER_START) && \
- ((unsigned long) (addr) + (size) <= FIXADDR_USER_END) && \
- ((unsigned long) (addr) + (size) >= (unsigned long)(addr)))
-
-#define __addr_range_nowrap(addr, size) \
- ((unsigned long) (addr) <= ((unsigned long) (addr) + (size)))
-
-#define access_ok(type, addr, size) \
- (__addr_range_nowrap(addr, size) && \
- (__under_task_size(addr, size) || \
- __access_ok_vsyscall(type, addr, size) || \
- segment_eq(get_fs(), KERNEL_DS)))
-
-extern int copy_from_user(void *to, const void __user *from, int n);
-extern int copy_to_user(void __user *to, const void *from, int n);
-
-extern int __do_copy_to_user(void *to, const void *from, int n,
- void **fault_addr, jmp_buf **fault_catcher);
-
-/*
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst: Destination address, in kernel space. This buffer must be at
- * least @count bytes long.
- * @src: Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-
-extern int strncpy_from_user(char *dst, const char __user *src, int count);
-
-/*
- * __clear_user: - Zero a block of memory in user space, with less checking.
- * @to: Destination address, in user space.
- * @n: Number of bytes to zero.
- *
- * Zero a block of memory in user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be cleared.
- * On success, this will be zero.
- */
-extern int __clear_user(void __user *mem, int len);
-
-/*
- * clear_user: - Zero a block of memory in user space.
- * @to: Destination address, in user space.
- * @n: Number of bytes to zero.
- *
- * Zero a block of memory in user space.
- *
- * Returns number of bytes that could not be cleared.
- * On success, this will be zero.
- */
-extern int clear_user(void __user *mem, int len);
-
-/*
- * strlen_user: - Get the size of a string in user space.
- * @str: The string to measure.
- * @n: The maximum valid length
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- * If the string is too long, returns a value greater than @n.
- */
-extern int strnlen_user(const void __user *str, int len);
-
-#endif
diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h
index 293f7c7..4fa82c0 100644
--- a/arch/um/include/shared/user.h
+++ b/arch/um/include/shared/user.h
@@ -6,7 +6,7 @@
#ifndef __USER_H__
#define __USER_H__
-#include "kern_constants.h"
+#include <generated/asm-offsets.h>
/*
* The usual definition - copied here because the kernel provides its own,
@@ -36,10 +36,11 @@
}
#endif
-extern void schedule(void);
extern int in_aton(char *str);
-extern int open_gdb_chan(void);
extern size_t strlcpy(char *, const char *, size_t);
extern size_t strlcat(char *, const char *, size_t);
+/* Copied from linux/compiler-gcc.h since we can't include it directly */
+#define barrier() __asm__ __volatile__("": : :"memory")
+
#endif
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index c4491c1..bc49474 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -11,7 +11,7 @@
obj-y = config.o exec.o exitcode.o init_task.o irq.o ksyms.o mem.o \
physmem.o process.o ptrace.o reboot.o sigio.o \
- signal.o smp.o syscall.o sysrq.o time.o tlb.o trap.o uaccess.o \
+ signal.o smp.o syscall.o sysrq.o time.o tlb.o trap.o \
um_arch.o umid.o skas/
obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 939a4a6..6cade93 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -3,14 +3,15 @@
* Licensed under the GPL
*/
-#include "linux/stddef.h"
-#include "linux/fs.h"
-#include "linux/ptrace.h"
-#include "linux/sched.h"
-#include "linux/slab.h"
-#include "asm/current.h"
-#include "asm/processor.h"
-#include "asm/uaccess.h"
+#include <linux/stddef.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <asm/current.h>
+#include <asm/processor.h>
+#include <asm/uaccess.h>
#include "as-layout.h"
#include "mem_user.h"
#include "skas.h"
@@ -41,6 +42,7 @@
PT_REGS_IP(regs) = eip;
PT_REGS_SP(regs) = esp;
}
+EXPORT_SYMBOL(start_thread);
static long execve1(const char *file,
const char __user *const __user *argv,
diff --git a/arch/um/kernel/gmon_syms.c b/arch/um/kernel/gmon_syms.c
index 72eccd2..e9bcf247 100644
--- a/arch/um/kernel/gmon_syms.c
+++ b/arch/um/kernel/gmon_syms.c
@@ -7,18 +7,3 @@
extern void __bb_init_func(void *) __attribute__((weak));
EXPORT_SYMBOL(__bb_init_func);
-
-/*
- * This is defined (and referred to in profiling stub code) only by some GCC
- * versions in libgcov.
- *
- * Since SuSE backported the fix, we cannot handle it depending on GCC version.
- * So, unconditionally export it. But also give it a weak declaration, which
- * will be overridden by any other one.
- */
-
-extern void __gcov_init(void *) __attribute__((weak));
-EXPORT_SYMBOL(__gcov_init);
-
-extern void __gcov_merge_add(void *) __attribute__((weak));
-EXPORT_SYMBOL(__gcov_merge_add);
diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c
index d386c75..10cc18f 100644
--- a/arch/um/kernel/initrd.c
+++ b/arch/um/kernel/initrd.c
@@ -7,12 +7,12 @@
#include "linux/bootmem.h"
#include "linux/initrd.h"
#include "asm/types.h"
-#include "initrd.h"
#include "init.h"
#include "os.h"
/* Changed by uml_initrd_setup, which is a setup */
static char *initrd __initdata = NULL;
+static int load_initrd(char *filename, void *buf, int size);
static int __init read_initrd(void)
{
@@ -62,7 +62,7 @@
" name of the file containing the image.\n\n"
);
-int load_initrd(char *filename, void *buf, int size)
+static int load_initrd(char *filename, void *buf, int size)
{
int fd, n;
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 9e485c7..71b8c94 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -258,6 +258,7 @@
ignore_sigio_fd(fd);
}
+EXPORT_SYMBOL(deactivate_fd);
/*
* Called just before shutdown in order to provide a clean exec
diff --git a/arch/um/kernel/ksyms.c b/arch/um/kernel/ksyms.c
index 0ae0dfc..e17bea0 100644
--- a/arch/um/kernel/ksyms.c
+++ b/arch/um/kernel/ksyms.c
@@ -3,33 +3,11 @@
* Licensed under the GPL
*/
-#include "linux/module.h"
-#include "linux/syscalls.h"
-#include "asm/tlbflush.h"
-#include "asm/uaccess.h"
-#include "as-layout.h"
-#include "kern_util.h"
-#include "mem_user.h"
+#include <linux/module.h>
#include "os.h"
-EXPORT_SYMBOL(uml_physmem);
EXPORT_SYMBOL(set_signals);
EXPORT_SYMBOL(get_signals);
-EXPORT_SYMBOL(kernel_thread);
-EXPORT_SYMBOL(sys_waitpid);
-EXPORT_SYMBOL(flush_tlb_range);
-
-EXPORT_SYMBOL(high_physmem);
-EXPORT_SYMBOL(empty_zero_page);
-EXPORT_SYMBOL(handle_page_fault);
-EXPORT_SYMBOL(find_iomem);
-
-EXPORT_SYMBOL(strnlen_user);
-EXPORT_SYMBOL(strncpy_from_user);
-EXPORT_SYMBOL(copy_to_user);
-EXPORT_SYMBOL(copy_from_user);
-EXPORT_SYMBOL(clear_user);
-EXPORT_SYMBOL(uml_strdup);
EXPORT_SYMBOL(os_stat_fd);
EXPORT_SYMBOL(os_stat_file);
@@ -57,24 +35,10 @@
EXPORT_SYMBOL(os_accept_connection);
EXPORT_SYMBOL(os_rcv_fd);
EXPORT_SYMBOL(run_helper);
-EXPORT_SYMBOL(start_thread);
EXPORT_SYMBOL(os_major);
EXPORT_SYMBOL(os_minor);
EXPORT_SYMBOL(os_makedev);
EXPORT_SYMBOL(add_sigio_fd);
EXPORT_SYMBOL(ignore_sigio_fd);
-EXPORT_SYMBOL(deactivate_fd);
EXPORT_SYMBOL(sigio_broken);
-
-#ifdef CONFIG_SMP
-
-/* required for SMP */
-
-extern void __write_lock_failed(rwlock_t *rw);
-EXPORT_SYMBOL(__write_lock_failed);
-
-extern void __read_lock_failed(rwlock_t *rw);
-EXPORT_SYMBOL(__read_lock_failed);
-
-#endif
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 8137ccc..ebb86b2 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -4,6 +4,7 @@
*/
#include <linux/stddef.h>
+#include <linux/module.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/mm.h>
@@ -20,6 +21,7 @@
/* allocated in paging_init, zeroed in mem_init, and unchanged thereafter */
unsigned long *empty_zero_page = NULL;
+EXPORT_SYMBOL(empty_zero_page);
/* allocated in paging_init and unchanged thereafter */
static unsigned long *empty_bad_page = NULL;
diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c
index a1a9090..f116db1 100644
--- a/arch/um/kernel/physmem.c
+++ b/arch/um/kernel/physmem.c
@@ -3,20 +3,22 @@
* Licensed under the GPL
*/
-#include "linux/bootmem.h"
-#include "linux/mm.h"
-#include "linux/pfn.h"
-#include "asm/page.h"
-#include "as-layout.h"
-#include "init.h"
-#include "kern.h"
-#include "mem_user.h"
-#include "os.h"
+#include <linux/module.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/pfn.h>
+#include <asm/page.h>
+#include <as-layout.h>
+#include <init.h>
+#include <kern.h>
+#include <mem_user.h>
+#include <os.h>
static int physmem_fd = -1;
/* Changed during early boot */
unsigned long high_physmem;
+EXPORT_SYMBOL(high_physmem);
extern unsigned long long physmem_size;
@@ -184,6 +186,7 @@
return 0;
}
+EXPORT_SYMBOL(find_iomem);
static int setup_iomem(void)
{
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 21c1ae7..c533835 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -20,12 +20,12 @@
#include <linux/threads.h>
#include <asm/current.h>
#include <asm/pgtable.h>
+#include <asm/mmu_context.h>
#include <asm/uaccess.h>
#include "as-layout.h"
#include "kern_util.h"
#include "os.h"
#include "skas.h"
-#include "tlb.h"
/*
* This is a per-cpu array. A processor only modifies its entry and it only
@@ -78,6 +78,7 @@
¤t->thread.regs, 0, NULL, NULL);
return pid;
}
+EXPORT_SYMBOL(kernel_thread);
static inline void set_current(struct task_struct *task)
{
@@ -286,6 +287,7 @@
{
return kstrdup(string, GFP_KERNEL);
}
+EXPORT_SYMBOL(uml_strdup);
int copy_to_user_proc(void __user *to, void *from, int size)
{
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index b5c094c..e8b889d 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -11,7 +11,6 @@
#include <asm/unistd.h>
#include "frame_kern.h"
#include "kern_util.h"
-#include <sysdep/sigcontext.h>
EXPORT_SYMBOL(block_signals);
EXPORT_SYMBOL(unblock_signals);
diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c
index 2c8583c..e1fd066 100644
--- a/arch/um/kernel/skas/clone.c
+++ b/arch/um/kernel/skas/clone.c
@@ -8,7 +8,6 @@
#include <asm/unistd.h>
#include <sys/time.h>
#include "as-layout.h"
-#include "kern_constants.h"
#include "ptrace_user.h"
#include "stub-data.h"
#include "sysdep/stub.h"
diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c
index 6966342..9fefd92 100644
--- a/arch/um/kernel/skas/uaccess.c
+++ b/arch/um/kernel/skas/uaccess.c
@@ -6,6 +6,7 @@
#include <linux/err.h>
#include <linux/highmem.h>
#include <linux/mm.h>
+#include <linux/module.h>
#include <linux/sched.h>
#include <asm/current.h>
#include <asm/page.h>
@@ -149,6 +150,7 @@
buffer_op((unsigned long) from, n, 0, copy_chunk_from_user, &to):
n;
}
+EXPORT_SYMBOL(copy_from_user);
static int copy_chunk_to_user(unsigned long to, int len, void *arg)
{
@@ -170,6 +172,7 @@
buffer_op((unsigned long) to, n, 1, copy_chunk_to_user, &from) :
n;
}
+EXPORT_SYMBOL(copy_to_user);
static int strncpy_chunk_from_user(unsigned long from, int len, void *arg)
{
@@ -204,6 +207,7 @@
return -EFAULT;
return strnlen(dst, count);
}
+EXPORT_SYMBOL(strncpy_from_user);
static int clear_chunk(unsigned long addr, int len, void *unused)
{
@@ -226,6 +230,7 @@
return access_ok(VERIFY_WRITE, mem, len) ?
buffer_op((unsigned long) mem, len, 1, clear_chunk, NULL) : len;
}
+EXPORT_SYMBOL(clear_user);
static int strnlen_chunk(unsigned long str, int len, void *arg)
{
@@ -251,3 +256,4 @@
return count + 1;
return -EFAULT;
}
+EXPORT_SYMBOL(strnlen_user);
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index d175d05..7f3d4d8 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -4,6 +4,7 @@
*/
#include <linux/mm.h>
+#include <linux/module.h>
#include <linux/sched.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
@@ -11,7 +12,6 @@
#include "mem_user.h"
#include "os.h"
#include "skas.h"
-#include "tlb.h"
struct host_vm_change {
struct host_vm_op {
@@ -287,7 +287,7 @@
}
}
-int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
+static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
{
struct mm_struct *mm;
pgd_t *pgd;
@@ -499,6 +499,7 @@
flush_tlb_kernel_range_common(start, end);
else fix_range(vma->vm_mm, start, end, 0);
}
+EXPORT_SYMBOL(flush_tlb_range);
void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end)
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 8c7b882..dafc947 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -6,6 +6,7 @@
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/hardirq.h>
+#include <linux/module.h>
#include <asm/current.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
@@ -14,7 +15,6 @@
#include "kern_util.h"
#include "os.h"
#include "skas.h"
-#include "sysdep/sigcontext.h"
/*
* Note this is constrained to return 0, -EFAULT, -EACCESS, -ENOMEM by
@@ -112,6 +112,7 @@
pagefault_out_of_memory();
return 0;
}
+EXPORT_SYMBOL(handle_page_fault);
static void show_segv_info(struct uml_pt_regs *regs)
{
diff --git a/arch/um/kernel/uaccess.c b/arch/um/kernel/uaccess.c
deleted file mode 100644
index dd33f04..0000000
--- a/arch/um/kernel/uaccess.c
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * Copyright (C) 2001 Chris Emerson (cemerson@chiark.greenend.org.uk)
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-/*
- * These are here rather than tt/uaccess.c because skas mode needs them in
- * order to do SIGBUS recovery when a tmpfs mount runs out of room.
- */
-
-#include <linux/string.h>
-#include "os.h"
-
-static void __do_copy(void *to, const void *from, int n)
-{
- memcpy(to, from, n);
-}
-
-
-int __do_copy_to_user(void *to, const void *from, int n,
- void **fault_addr, jmp_buf **fault_catcher)
-{
- unsigned long fault;
- int faulted;
-
- fault = __do_user_copy(to, from, n, fault_addr, fault_catcher,
- __do_copy, &faulted);
- if (!faulted)
- return 0;
- else
- return n - (fault - (unsigned long) to);
-}
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 8d84250..ba00eae 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -102,6 +102,8 @@
/* Set in linux_main */
unsigned long uml_physmem;
+EXPORT_SYMBOL(uml_physmem);
+
unsigned long uml_reserved; /* Also modified in mem_init */
unsigned long start_vm;
unsigned long end_vm;
diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile
index b33f4df..dd76410 100644
--- a/arch/um/os-Linux/Makefile
+++ b/arch/um/os-Linux/Makefile
@@ -4,14 +4,14 @@
#
obj-y = aio.o execvp.o file.o helper.o irq.o main.o mem.o process.o \
- registers.o sigio.o signal.o start_up.o time.o tty.o uaccess.o \
- umid.o tls.o user_syms.o util.o drivers/ sys-$(SUBARCH)/ skas/
+ registers.o sigio.o signal.o start_up.o time.o tty.o \
+ umid.o user_syms.o util.o drivers/ skas/
obj-$(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) += elf_aux.o
USER_OBJS := $(user-objs-y) aio.o elf_aux.o execvp.o file.o helper.o irq.o \
main.o mem.o process.o registers.o sigio.o signal.o start_up.o time.o \
- tty.o tls.o uaccess.o umid.o util.o
+ tty.o umid.o util.o
CFLAGS_user_syms.o += -DSUBARCH_$(SUBARCH)
diff --git a/arch/um/os-Linux/aio.c b/arch/um/os-Linux/aio.c
index 57e3d46..c5d039e 100644
--- a/arch/um/os-Linux/aio.c
+++ b/arch/um/os-Linux/aio.c
@@ -11,10 +11,8 @@
#include <asm/unistd.h>
#include "aio.h"
#include "init.h"
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
-#include "user.h"
struct aio_thread_req {
enum aio_type type;
diff --git a/arch/um/os-Linux/drivers/ethertap_user.c b/arch/um/os-Linux/drivers/ethertap_user.c
index cc72cb2..db3d648 100644
--- a/arch/um/os-Linux/drivers/ethertap_user.c
+++ b/arch/um/os-Linux/drivers/ethertap_user.c
@@ -13,11 +13,9 @@
#include <sys/socket.h>
#include <sys/wait.h>
#include "etap.h"
-#include "kern_constants.h"
#include "os.h"
#include "net_user.h"
#include "um_malloc.h"
-#include "user.h"
#define MAX_PACKET ETH_MAX_PACKET
diff --git a/arch/um/os-Linux/drivers/tuntap_user.c b/arch/um/os-Linux/drivers/tuntap_user.c
index 2448be0..a2aacff 100644
--- a/arch/um/os-Linux/drivers/tuntap_user.c
+++ b/arch/um/os-Linux/drivers/tuntap_user.c
@@ -13,11 +13,9 @@
#include <sys/socket.h>
#include <sys/wait.h>
#include <sys/uio.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
#include "tuntap.h"
-#include "user.h"
static int tuntap_user_init(void *data, void *dev)
{
diff --git a/arch/um/os-Linux/elf_aux.c b/arch/um/os-Linux/elf_aux.c
index 9533237..d895271 100644
--- a/arch/um/os-Linux/elf_aux.c
+++ b/arch/um/os-Linux/elf_aux.c
@@ -12,7 +12,6 @@
#include "init.h"
#include "elf_user.h"
#include "mem_user.h"
-#include <kern_constants.h>
typedef Elf32_auxv_t elf_auxv_t;
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index 140e587..b049a63 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -13,9 +13,7 @@
#include <sys/socket.h>
#include <sys/stat.h>
#include <sys/un.h>
-#include "kern_constants.h"
#include "os.h"
-#include "user.h"
static void copy_stat(struct uml_stat *dst, const struct stat64 *src)
{
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index feff22d..cf26c4a 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -10,11 +10,9 @@
#include <linux/limits.h>
#include <sys/socket.h>
#include <sys/wait.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
struct helper_data {
void (*pre_exec)(void*);
diff --git a/arch/um/os-Linux/internal.h b/arch/um/os-Linux/internal.h
new file mode 100644
index 0000000..2c3c3ec
--- /dev/null
+++ b/arch/um/os-Linux/internal.h
@@ -0,0 +1 @@
+void alarm_handler(int, mcontext_t *);
diff --git a/arch/um/os-Linux/irq.c b/arch/um/os-Linux/irq.c
index 0348b97..9a49908 100644
--- a/arch/um/os-Linux/irq.c
+++ b/arch/um/os-Linux/irq.c
@@ -9,11 +9,8 @@
#include <signal.h>
#include <string.h>
#include "irq_user.h"
-#include "kern_constants.h"
#include "os.h"
-#include "process.h"
#include "um_malloc.h"
-#include "user.h"
/*
* Locked by irq_lock in arch/um/kernel/irq.c. Changed by os_create_pollfd
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index 8471b81..7a86dd5 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -12,7 +12,6 @@
#include <sys/resource.h>
#include "as-layout.h"
#include "init.h"
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
#include "um_malloc.h"
diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c
index 62878cf..8e421e1 100644
--- a/arch/um/os-Linux/mem.c
+++ b/arch/um/os-Linux/mem.c
@@ -14,9 +14,7 @@
#include <sys/mman.h>
#include <sys/param.h>
#include "init.h"
-#include "kern_constants.h"
#include "os.h"
-#include "user.h"
/* Modified by which_tmpdir, which is called during early boot */
static char *default_tmpdir = "/tmp";
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index 0c45dc8..307f173 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -13,12 +13,9 @@
#include <sys/wait.h>
#include <asm/unistd.h>
#include "init.h"
-#include "kern_constants.h"
#include "longjmp.h"
#include "os.h"
-#include "process.h"
#include "skas_ptrace.h"
-#include "user.h"
#define ARBITRARY_ADDR -1
#define FAILURE_PID -1
@@ -237,21 +234,13 @@
void init_new_thread_signals(void)
{
- set_handler(SIGSEGV, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
- set_handler(SIGTRAP, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
- set_handler(SIGFPE, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
- set_handler(SIGILL, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
- set_handler(SIGBUS, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
+ set_handler(SIGSEGV);
+ set_handler(SIGTRAP);
+ set_handler(SIGFPE);
+ set_handler(SIGILL);
+ set_handler(SIGBUS);
signal(SIGHUP, SIG_IGN);
-
- set_handler(SIGIO, (__sighandler_t) sig_handler,
- SA_ONSTACK | SA_RESTART, SIGUSR1, SIGIO, SIGWINCH, SIGALRM,
- SIGVTALRM, -1);
+ set_handler(SIGIO);
signal(SIGWINCH, SIG_IGN);
signal(SIGTERM, SIG_DFL);
}
diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c
index 63d299d..3c16121 100644
--- a/arch/um/os-Linux/sigio.c
+++ b/arch/um/os-Linux/sigio.c
@@ -11,14 +11,11 @@
#include <sched.h>
#include <signal.h>
#include <string.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "init.h"
#include "os.h"
-#include "process.h"
#include "sigio.h"
#include "um_malloc.h"
-#include "user.h"
/*
* Protected by sigio_lock(), also used by sigio_cleanup, which is an
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 6ae1807..2d22f1f 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -12,13 +12,7 @@
#include "as-layout.h"
#include "kern_util.h"
#include "os.h"
-#include "process.h"
-#include "sysdep/barrier.h"
-#include "sysdep/sigcontext.h"
-#include "user.h"
-
-/* Copied from linux/compiler-gcc.h since we can't include it directly */
-#define barrier() __asm__ __volatile__("": : :"memory")
+#include "sysdep/mcontext.h"
void (*sig_info[NSIG])(int, struct uml_pt_regs *) = {
[SIGTRAP] = relay_signal,
@@ -30,7 +24,7 @@
[SIGIO] = sigio_handler,
[SIGVTALRM] = timer_handler };
-static void sig_handler_common(int sig, struct sigcontext *sc)
+static void sig_handler_common(int sig, mcontext_t *mc)
{
struct uml_pt_regs r;
int save_errno = errno;
@@ -38,8 +32,8 @@
r.is_user = 0;
if (sig == SIGSEGV) {
/* For segfaults, we want the data from the sigcontext. */
- copy_sc(&r, sc);
- GET_FAULTINFO_FROM_SC(r.faultinfo, sc);
+ get_regs_from_mc(&r, mc);
+ GET_FAULTINFO_FROM_MC(r.faultinfo, mc);
}
/* enable signals if sig isn't IRQ signal */
@@ -66,7 +60,7 @@
static int signals_enabled;
static unsigned int signals_pending;
-void sig_handler(int sig, struct sigcontext *sc)
+void sig_handler(int sig, mcontext_t *mc)
{
int enabled;
@@ -78,23 +72,23 @@
block_signals();
- sig_handler_common(sig, sc);
+ sig_handler_common(sig, mc);
set_signals(enabled);
}
-static void real_alarm_handler(struct sigcontext *sc)
+static void real_alarm_handler(mcontext_t *mc)
{
struct uml_pt_regs regs;
- if (sc != NULL)
- copy_sc(®s, sc);
+ if (mc != NULL)
+ get_regs_from_mc(®s, mc);
regs.is_user = 0;
unblock_signals();
timer_handler(SIGVTALRM, ®s);
}
-void alarm_handler(int sig, struct sigcontext *sc)
+void alarm_handler(int sig, mcontext_t *mc)
{
int enabled;
@@ -106,14 +100,13 @@
block_signals();
- real_alarm_handler(sc);
+ real_alarm_handler(mc);
set_signals(enabled);
}
void timer_init(void)
{
- set_handler(SIGVTALRM, (__sighandler_t) alarm_handler,
- SA_ONSTACK | SA_RESTART, SIGUSR1, SIGIO, SIGWINCH, -1);
+ set_handler(SIGVTALRM);
}
void set_sigstack(void *sig_stack, int size)
@@ -126,10 +119,23 @@
panic("enabling signal stack failed, errno = %d\n", errno);
}
-static void (*handlers[_NSIG])(int sig, struct sigcontext *sc);
+static void (*handlers[_NSIG])(int sig, mcontext_t *mc) = {
+ [SIGSEGV] = sig_handler,
+ [SIGBUS] = sig_handler,
+ [SIGILL] = sig_handler,
+ [SIGFPE] = sig_handler,
+ [SIGTRAP] = sig_handler,
-void handle_signal(int sig, struct sigcontext *sc)
+ [SIGIO] = sig_handler,
+ [SIGWINCH] = sig_handler,
+ [SIGVTALRM] = alarm_handler
+};
+
+
+static void hard_handler(int sig, siginfo_t *info, void *p)
{
+ struct ucontext *uc = p;
+ mcontext_t *mc = &uc->uc_mcontext;
unsigned long pending = 1UL << sig;
do {
@@ -155,7 +161,7 @@
while ((sig = ffs(pending)) != 0){
sig--;
pending &= ~(1 << sig);
- (*handlers[sig])(sig, sc);
+ (*handlers[sig])(sig, mc);
}
/*
@@ -169,28 +175,26 @@
} while (pending);
}
-extern void hard_handler(int sig);
-
-void set_handler(int sig, void (*handler)(int), int flags, ...)
+void set_handler(int sig)
{
struct sigaction action;
- va_list ap;
+ int flags = SA_SIGINFO | SA_ONSTACK;
sigset_t sig_mask;
- int mask;
- handlers[sig] = (void (*)(int, struct sigcontext *)) handler;
- action.sa_handler = hard_handler;
+ action.sa_sigaction = hard_handler;
+ /* block irq ones */
sigemptyset(&action.sa_mask);
-
- va_start(ap, flags);
- while ((mask = va_arg(ap, int)) != -1)
- sigaddset(&action.sa_mask, mask);
- va_end(ap);
+ sigaddset(&action.sa_mask, SIGVTALRM);
+ sigaddset(&action.sa_mask, SIGIO);
+ sigaddset(&action.sa_mask, SIGWINCH);
if (sig == SIGSEGV)
flags |= SA_NODEFER;
+ if (sigismember(&action.sa_mask, sig))
+ flags |= SA_RESTART; /* if it's an irq signal */
+
action.sa_flags = flags;
action.sa_restorer = NULL;
if (sigaction(sig, &action, NULL) < 0)
diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c
index e771398..c0afff7 100644
--- a/arch/um/os-Linux/skas/mem.c
+++ b/arch/um/os-Linux/skas/mem.c
@@ -9,7 +9,6 @@
#include <string.h>
#include <sys/mman.h>
#include "init.h"
-#include "kern_constants.h"
#include "as-layout.h"
#include "mm_id.h"
#include "os.h"
@@ -17,7 +16,6 @@
#include "ptrace_user.h"
#include "registers.h"
#include "skas.h"
-#include "user.h"
#include "sysdep/ptrace.h"
#include "sysdep/stub.h"
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index dee0e8c..cd65727 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -9,31 +9,23 @@
#include <errno.h>
#include <string.h>
#include <sys/mman.h>
-#include <sys/ptrace.h>
#include <sys/wait.h>
#include <asm/unistd.h>
#include "as-layout.h"
-#include "chan_user.h"
-#include "kern_constants.h"
+#include "init.h"
#include "kern_util.h"
#include "mem.h"
#include "os.h"
-#include "process.h"
#include "proc_mm.h"
#include "ptrace_user.h"
#include "registers.h"
#include "skas.h"
#include "skas_ptrace.h"
-#include "user.h"
#include "sysdep/stub.h"
int is_skas_winch(int pid, int fd, void *data)
{
- if (pid != getpgrp())
- return 0;
-
- register_winch_irq(-1, fd, -1, data, 0);
- return 1;
+ return pid == getpgrp();
}
static int ptrace_dump_regs(int pid)
@@ -169,7 +161,7 @@
if (!local_using_sysemu)
{
- err = ptrace(PTRACE_POKEUSR, pid, PT_SYSCALL_NR_OFFSET,
+ err = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET,
__NR_getpid);
if (err < 0) {
printk(UM_KERN_ERR "handle_trap - nullifying syscall "
@@ -257,8 +249,8 @@
set_sigstack((void *) STUB_DATA, UM_KERN_PAGE_SIZE);
sigemptyset(&sa.sa_mask);
- sa.sa_flags = SA_ONSTACK | SA_NODEFER;
- sa.sa_handler = (void *) v;
+ sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
+ sa.sa_sigaction = (void *) v;
sa.sa_restorer = NULL;
if (sigaction(SIGSEGV, &sa, NULL) < 0) {
printk(UM_KERN_ERR "userspace_tramp - setting SIGSEGV "
@@ -661,8 +653,7 @@
{
int n;
- set_handler(SIGWINCH, (__sighandler_t) sig_handler,
- SA_ONSTACK | SA_RESTART, SIGUSR1, SIGIO, SIGVTALRM, -1);
+ set_handler(SIGWINCH);
/*
* Can't use UML_SETJMP or UML_LONGJMP here because they save
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index 02ee9ad..425162e 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -13,12 +13,10 @@
#include <signal.h>
#include <string.h>
#include <sys/mman.h>
-#include <sys/ptrace.h>
#include <sys/stat.h>
#include <sys/wait.h>
#include <asm/unistd.h>
#include "init.h"
-#include "kern_constants.h"
#include "os.h"
#include "mem_user.h"
#include "ptrace_user.h"
@@ -225,7 +223,7 @@
goto fail;
}
- n = ptrace(PTRACE_POKEUSR, pid, PT_SYSCALL_RET_OFFSET, os_getpid());
+ n = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_RET_OFFSET, os_getpid());
if (n < 0) {
non_fatal("check_sysemu : failed to modify system call "
"return");
@@ -261,7 +259,7 @@
"doesn't singlestep");
goto fail;
}
- n = ptrace(PTRACE_POKEUSR, pid, PT_SYSCALL_RET_OFFSET,
+ n = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_RET_OFFSET,
os_getpid());
if (n < 0)
fatal_perror("check_sysemu : failed to modify "
@@ -317,10 +315,10 @@
fatal("check_ptrace : expected (SIGTRAP|0x80), "
"got status = %d", status);
- syscall = ptrace(PTRACE_PEEKUSR, pid, PT_SYSCALL_NR_OFFSET,
+ syscall = ptrace(PTRACE_PEEKUSER, pid, PT_SYSCALL_NR_OFFSET,
0);
if (syscall == __NR_getpid) {
- n = ptrace(PTRACE_POKEUSR, pid, PT_SYSCALL_NR_OFFSET,
+ n = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET,
__NR_getppid);
if (n < 0)
fatal_perror("check_ptrace : failed to modify "
diff --git a/arch/um/os-Linux/sys-i386/signal.c b/arch/um/os-Linux/sys-i386/signal.c
deleted file mode 100644
index f311609..0000000
--- a/arch/um/os-Linux/sys-i386/signal.c
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- * Copyright (C) 2006 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <signal.h>
-
-extern void handle_signal(int sig, struct sigcontext *sc);
-
-void hard_handler(int sig)
-{
- handle_signal(sig, (struct sigcontext *) (&sig + 1));
-}
diff --git a/arch/um/os-Linux/sys-i386/tls.c b/arch/um/os-Linux/sys-i386/tls.c
deleted file mode 100644
index 32ed41e..0000000
--- a/arch/um/os-Linux/sys-i386/tls.c
+++ /dev/null
@@ -1,36 +0,0 @@
-#include <errno.h>
-#include <linux/unistd.h>
-
-#include <sys/syscall.h>
-#include <unistd.h>
-
-#include "sysdep/tls.h"
-#include "user.h"
-
-/* Checks whether host supports TLS, and sets *tls_min according to the value
- * valid on the host.
- * i386 host have it == 6; x86_64 host have it == 12, for i386 emulation. */
-void check_host_supports_tls(int *supports_tls, int *tls_min) {
- /* Values for x86 and x86_64.*/
- int val[] = {GDT_ENTRY_TLS_MIN_I386, GDT_ENTRY_TLS_MIN_X86_64};
- int i;
-
- for (i = 0; i < ARRAY_SIZE(val); i++) {
- user_desc_t info;
- info.entry_number = val[i];
-
- if (syscall(__NR_get_thread_area, &info) == 0) {
- *tls_min = val[i];
- *supports_tls = 1;
- return;
- } else {
- if (errno == EINVAL)
- continue;
- else if (errno == ENOSYS)
- *supports_tls = 0;
- return;
- }
- }
-
- *supports_tls = 0;
-}
diff --git a/arch/um/os-Linux/sys-x86_64/Makefile b/arch/um/os-Linux/sys-x86_64/Makefile
deleted file mode 100644
index a44a47f..0000000
--- a/arch/um/os-Linux/sys-x86_64/Makefile
+++ /dev/null
@@ -1,10 +0,0 @@
-#
-# Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
-# Licensed under the GPL
-#
-
-obj-y = registers.o prctl.o signal.o task_size.o
-
-USER_OBJS := $(obj-y)
-
-include arch/um/scripts/Makefile.rules
diff --git a/arch/um/os-Linux/sys-x86_64/registers.c b/arch/um/os-Linux/sys-x86_64/registers.c
deleted file mode 100644
index 594d97a..0000000
--- a/arch/um/os-Linux/sys-x86_64/registers.c
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright (C) 2006 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <errno.h>
-#include <sys/ptrace.h>
-#define __FRAME_OFFSETS
-#include <asm/ptrace.h>
-#include "kern_constants.h"
-#include "longjmp.h"
-#include "user.h"
-
-int save_fp_registers(int pid, unsigned long *fp_regs)
-{
- if (ptrace(PTRACE_GETFPREGS, pid, 0, fp_regs) < 0)
- return -errno;
- return 0;
-}
-
-int restore_fp_registers(int pid, unsigned long *fp_regs)
-{
- if (ptrace(PTRACE_SETFPREGS, pid, 0, fp_regs) < 0)
- return -errno;
- return 0;
-}
-
-unsigned long get_thread_reg(int reg, jmp_buf *buf)
-{
- switch (reg) {
- case RIP:
- return buf[0]->__rip;
- case RSP:
- return buf[0]->__rsp;
- case RBP:
- return buf[0]->__rbp;
- default:
- printk(UM_KERN_ERR "get_thread_regs - unknown register %d\n",
- reg);
- return 0;
- }
-}
-
-int get_fp_registers(int pid, unsigned long *regs)
-{
- return save_fp_registers(pid, regs);
-}
-
-int put_fp_registers(int pid, unsigned long *regs)
-{
- return restore_fp_registers(pid, regs);
-}
diff --git a/arch/um/os-Linux/sys-x86_64/signal.c b/arch/um/os-Linux/sys-x86_64/signal.c
deleted file mode 100644
index 82a3888..0000000
--- a/arch/um/os-Linux/sys-x86_64/signal.c
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * Copyright (C) 2006 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <signal.h>
-
-extern void handle_signal(int sig, struct sigcontext *sc);
-
-void hard_handler(int sig)
-{
- struct ucontext *uc;
- asm("movq %%rdx, %0" : "=r" (uc));
-
- handle_signal(sig, (struct sigcontext *) &uc->uc_mcontext);
-}
diff --git a/arch/um/os-Linux/sys-x86_64/task_size.c b/arch/um/os-Linux/sys-x86_64/task_size.c
deleted file mode 100644
index 26a0dd1..0000000
--- a/arch/um/os-Linux/sys-x86_64/task_size.c
+++ /dev/null
@@ -1,5 +0,0 @@
-unsigned long os_get_top_address(unsigned long shift)
-{
- /* The old value of CONFIG_TOP_ADDR */
- return 0x7fc0000000;
-}
diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c
index 6e3359d..910499d 100644
--- a/arch/um/os-Linux/time.c
+++ b/arch/um/os-Linux/time.c
@@ -8,11 +8,9 @@
#include <signal.h>
#include <time.h>
#include <sys/time.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
-#include "process.h"
-#include "user.h"
+#include "internal.h"
int set_interval(void)
{
diff --git a/arch/um/os-Linux/tls.c b/arch/um/os-Linux/tls.c
deleted file mode 100644
index 7327780..0000000
--- a/arch/um/os-Linux/tls.c
+++ /dev/null
@@ -1,35 +0,0 @@
-#include <errno.h>
-#include <sys/ptrace.h>
-#include "sysdep/tls.h"
-
-/* TLS support - we basically rely on the host's one.*/
-
-#ifndef PTRACE_GET_THREAD_AREA
-#define PTRACE_GET_THREAD_AREA 25
-#endif
-
-#ifndef PTRACE_SET_THREAD_AREA
-#define PTRACE_SET_THREAD_AREA 26
-#endif
-
-int os_set_thread_area(user_desc_t *info, int pid)
-{
- int ret;
-
- ret = ptrace(PTRACE_SET_THREAD_AREA, pid, info->entry_number,
- (unsigned long) info);
- if (ret < 0)
- ret = -errno;
- return ret;
-}
-
-int os_get_thread_area(user_desc_t *info, int pid)
-{
- int ret;
-
- ret = ptrace(PTRACE_GET_THREAD_AREA, pid, info->entry_number,
- (unsigned long) info);
- if (ret < 0)
- ret = -errno;
- return ret;
-}
diff --git a/arch/um/os-Linux/tty.c b/arch/um/os-Linux/tty.c
index b09ff66..dd12b99 100644
--- a/arch/um/os-Linux/tty.c
+++ b/arch/um/os-Linux/tty.c
@@ -7,10 +7,8 @@
#include <unistd.h>
#include <errno.h>
#include <fcntl.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
-#include "user.h"
struct grantpt_info {
int fd;
diff --git a/arch/um/os-Linux/uaccess.c b/arch/um/os-Linux/uaccess.c
deleted file mode 100644
index 087ed74..0000000
--- a/arch/um/os-Linux/uaccess.c
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * Copyright (C) 2001 Chris Emerson (cemerson@chiark.greenend.org.uk)
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <stddef.h>
-#include "longjmp.h"
-
-unsigned long __do_user_copy(void *to, const void *from, int n,
- void **fault_addr, jmp_buf **fault_catcher,
- void (*op)(void *to, const void *from,
- int n), int *faulted_out)
-{
- unsigned long *faddrp = (unsigned long *) fault_addr, ret;
-
- jmp_buf jbuf;
- *fault_catcher = &jbuf;
- if (UML_SETJMP(&jbuf) == 0) {
- (*op)(to, from, n);
- ret = 0;
- *faulted_out = 0;
- }
- else {
- ret = *faddrp;
- *faulted_out = 1;
- }
- *fault_addr = NULL;
- *fault_catcher = NULL;
- return ret;
-}
-
diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c
index a27defb..4832eb5 100644
--- a/arch/um/os-Linux/umid.c
+++ b/arch/um/os-Linux/umid.c
@@ -13,9 +13,7 @@
#include <unistd.h>
#include <sys/stat.h>
#include "init.h"
-#include "kern_constants.h"
#include "os.h"
-#include "user.h"
#define UML_DIR "~/.uml/"
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index 5803b18..9e3b43b 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -13,9 +13,7 @@
#include <wait.h>
#include <sys/mman.h>
#include <sys/utsname.h>
-#include "kern_constants.h"
#include "os.h"
-#include "user.h"
void stack_protections(unsigned long address)
{
diff --git a/arch/um/scripts/Makefile.rules b/arch/um/scripts/Makefile.rules
index 61107b6..2eb2843 100644
--- a/arch/um/scripts/Makefile.rules
+++ b/arch/um/scripts/Makefile.rules
@@ -8,7 +8,7 @@
USER_OBJS := $(foreach file,$(USER_OBJS),$(obj)/$(file))
$(USER_OBJS:.o=.%): \
- c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) $(CFLAGS_$(basetarget).o)
+ c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) -include user.h $(CFLAGS_$(basetarget).o)
$(USER_OBJS) : CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ \
-Dunix -D__unix__ -D__$(SUBARCH)__ $(CF)
@@ -25,8 +25,3 @@
define unprofile
$(patsubst -pg,,$(patsubst -fprofile-arcs -ftest-coverage,,$(1)))
endef
-
-ifdef subarch-obj-y
-obj-y += subarch.o
-subarch-y = $(addprefix ../../$(HEADER_ARCH)/,$(subarch-obj-y))
-endif
diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile
deleted file mode 100644
index 3923cfb..0000000
--- a/arch/um/sys-i386/Makefile
+++ /dev/null
@@ -1,24 +0,0 @@
-#
-# Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
-#
-
-obj-y = bug.o bugs.o checksum.o delay.o fault.o ksyms.o ldt.o ptrace.o \
- ptrace_user.o setjmp.o signal.o stub.o stub_segv.o syscalls.o sysrq.o \
- sys_call_table.o tls.o atomic64_cx8_32.o mem.o
-
-obj-$(CONFIG_BINFMT_ELF) += elfcore.o
-
-subarch-obj-y = lib/string_32.o
-subarch-obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += lib/rwsem.o
-subarch-obj-$(CONFIG_HIGHMEM) += mm/highmem_32.o
-subarch-obj-$(CONFIG_MODULES) += kernel/module.o
-
-USER_OBJS := bugs.o ptrace_user.o fault.o
-
-USER_OBJS += user-offsets.s
-extra-y += user-offsets.s
-
-UNPROFILE_OBJS := stub_segv.o
-CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING)
-
-include arch/um/scripts/Makefile.rules
diff --git a/arch/um/sys-i386/asm/elf.h b/arch/um/sys-i386/asm/elf.h
deleted file mode 100644
index 4230555..0000000
--- a/arch/um/sys-i386/asm/elf.h
+++ /dev/null
@@ -1,125 +0,0 @@
-/*
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-#ifndef __UM_ELF_I386_H
-#define __UM_ELF_I386_H
-
-#include <asm/user.h>
-#include "skas.h"
-
-#define R_386_NONE 0
-#define R_386_32 1
-#define R_386_PC32 2
-#define R_386_GOT32 3
-#define R_386_PLT32 4
-#define R_386_COPY 5
-#define R_386_GLOB_DAT 6
-#define R_386_JMP_SLOT 7
-#define R_386_RELATIVE 8
-#define R_386_GOTOFF 9
-#define R_386_GOTPC 10
-#define R_386_NUM 11
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_i387_struct elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) \
- (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
-
-#define ELF_CLASS ELFCLASS32
-#define ELF_DATA ELFDATA2LSB
-#define ELF_ARCH EM_386
-
-#define ELF_PLAT_INIT(regs, load_addr) do { \
- PT_REGS_EBX(regs) = 0; \
- PT_REGS_ECX(regs) = 0; \
- PT_REGS_EDX(regs) = 0; \
- PT_REGS_ESI(regs) = 0; \
- PT_REGS_EDI(regs) = 0; \
- PT_REGS_EBP(regs) = 0; \
- PT_REGS_EAX(regs) = 0; \
-} while (0)
-
-#define ELF_EXEC_PAGESIZE 4096
-
-#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
-
-/* Shamelessly stolen from include/asm-i386/elf.h */
-
-#define ELF_CORE_COPY_REGS(pr_reg, regs) do { \
- pr_reg[0] = PT_REGS_EBX(regs); \
- pr_reg[1] = PT_REGS_ECX(regs); \
- pr_reg[2] = PT_REGS_EDX(regs); \
- pr_reg[3] = PT_REGS_ESI(regs); \
- pr_reg[4] = PT_REGS_EDI(regs); \
- pr_reg[5] = PT_REGS_EBP(regs); \
- pr_reg[6] = PT_REGS_EAX(regs); \
- pr_reg[7] = PT_REGS_DS(regs); \
- pr_reg[8] = PT_REGS_ES(regs); \
- /* fake once used fs and gs selectors? */ \
- pr_reg[9] = PT_REGS_DS(regs); \
- pr_reg[10] = PT_REGS_DS(regs); \
- pr_reg[11] = PT_REGS_SYSCALL_NR(regs); \
- pr_reg[12] = PT_REGS_IP(regs); \
- pr_reg[13] = PT_REGS_CS(regs); \
- pr_reg[14] = PT_REGS_EFLAGS(regs); \
- pr_reg[15] = PT_REGS_SP(regs); \
- pr_reg[16] = PT_REGS_SS(regs); \
-} while (0);
-
-#define task_pt_regs(t) (&(t)->thread.regs)
-
-struct task_struct;
-
-extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
-
-#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
-
-extern long elf_aux_hwcap;
-#define ELF_HWCAP (elf_aux_hwcap)
-
-extern char * elf_aux_platform;
-#define ELF_PLATFORM (elf_aux_platform)
-
-#define SET_PERSONALITY(ex) do { } while (0)
-
-extern unsigned long vsyscall_ehdr;
-extern unsigned long vsyscall_end;
-extern unsigned long __kernel_vsyscall;
-
-#define VSYSCALL_BASE vsyscall_ehdr
-#define VSYSCALL_END vsyscall_end
-
-/*
- * This is the range that is readable by user mode, and things
- * acting like user mode such as get_user_pages.
- */
-#define FIXADDR_USER_START VSYSCALL_BASE
-#define FIXADDR_USER_END VSYSCALL_END
-
-#define __HAVE_ARCH_GATE_AREA 1
-
-/*
- * Architecture-neutral AT_ values in 0-17, leave some room
- * for more of them, start the x86-specific ones at 32.
- */
-#define AT_SYSINFO 32
-#define AT_SYSINFO_EHDR 33
-
-#define ARCH_DLINFO \
-do { \
- if ( vsyscall_ehdr ) { \
- NEW_AUX_ENT(AT_SYSINFO, __kernel_vsyscall); \
- NEW_AUX_ENT(AT_SYSINFO_EHDR, vsyscall_ehdr); \
- } \
-} while (0)
-
-#endif
diff --git a/arch/um/sys-i386/asm/module.h b/arch/um/sys-i386/asm/module.h
deleted file mode 100644
index 5ead4a0..0000000
--- a/arch/um/sys-i386/asm/module.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __UM_MODULE_I386_H
-#define __UM_MODULE_I386_H
-
-/* UML is simple */
-struct mod_arch_specific
-{
-};
-
-#define Elf_Shdr Elf32_Shdr
-#define Elf_Sym Elf32_Sym
-#define Elf_Ehdr Elf32_Ehdr
-
-#endif
diff --git a/arch/um/sys-i386/atomic64_cx8_32.S b/arch/um/sys-i386/atomic64_cx8_32.S
deleted file mode 100644
index 1e901d3..0000000
--- a/arch/um/sys-i386/atomic64_cx8_32.S
+++ /dev/null
@@ -1,225 +0,0 @@
-/*
- * atomic64_t for 586+
- *
- * Copied from arch/x86/lib/atomic64_cx8_32.S
- *
- * Copyright © 2010 Luca Barbieri
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- */
-
-#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
-
-.macro SAVE reg
- pushl_cfi %\reg
- CFI_REL_OFFSET \reg, 0
-.endm
-
-.macro RESTORE reg
- popl_cfi %\reg
- CFI_RESTORE \reg
-.endm
-
-.macro read64 reg
- movl %ebx, %eax
- movl %ecx, %edx
-/* we need LOCK_PREFIX since otherwise cmpxchg8b always does the write */
- LOCK_PREFIX
- cmpxchg8b (\reg)
-.endm
-
-ENTRY(atomic64_read_cx8)
- CFI_STARTPROC
-
- read64 %ecx
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_read_cx8)
-
-ENTRY(atomic64_set_cx8)
- CFI_STARTPROC
-
-1:
-/* we don't need LOCK_PREFIX since aligned 64-bit writes
- * are atomic on 586 and newer */
- cmpxchg8b (%esi)
- jne 1b
-
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_set_cx8)
-
-ENTRY(atomic64_xchg_cx8)
- CFI_STARTPROC
-
- movl %ebx, %eax
- movl %ecx, %edx
-1:
- LOCK_PREFIX
- cmpxchg8b (%esi)
- jne 1b
-
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_xchg_cx8)
-
-.macro addsub_return func ins insc
-ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- SAVE ebp
- SAVE ebx
- SAVE esi
- SAVE edi
-
- movl %eax, %esi
- movl %edx, %edi
- movl %ecx, %ebp
-
- read64 %ebp
-1:
- movl %eax, %ebx
- movl %edx, %ecx
- \ins\()l %esi, %ebx
- \insc\()l %edi, %ecx
- LOCK_PREFIX
- cmpxchg8b (%ebp)
- jne 1b
-
-10:
- movl %ebx, %eax
- movl %ecx, %edx
- RESTORE edi
- RESTORE esi
- RESTORE ebx
- RESTORE ebp
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_\func\()_return_cx8)
-.endm
-
-addsub_return add add adc
-addsub_return sub sub sbb
-
-.macro incdec_return func ins insc
-ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- SAVE ebx
-
- read64 %esi
-1:
- movl %eax, %ebx
- movl %edx, %ecx
- \ins\()l $1, %ebx
- \insc\()l $0, %ecx
- LOCK_PREFIX
- cmpxchg8b (%esi)
- jne 1b
-
-10:
- movl %ebx, %eax
- movl %ecx, %edx
- RESTORE ebx
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_\func\()_return_cx8)
-.endm
-
-incdec_return inc add adc
-incdec_return dec sub sbb
-
-ENTRY(atomic64_dec_if_positive_cx8)
- CFI_STARTPROC
- SAVE ebx
-
- read64 %esi
-1:
- movl %eax, %ebx
- movl %edx, %ecx
- subl $1, %ebx
- sbb $0, %ecx
- js 2f
- LOCK_PREFIX
- cmpxchg8b (%esi)
- jne 1b
-
-2:
- movl %ebx, %eax
- movl %ecx, %edx
- RESTORE ebx
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_dec_if_positive_cx8)
-
-ENTRY(atomic64_add_unless_cx8)
- CFI_STARTPROC
- SAVE ebp
- SAVE ebx
-/* these just push these two parameters on the stack */
- SAVE edi
- SAVE esi
-
- movl %ecx, %ebp
- movl %eax, %esi
- movl %edx, %edi
-
- read64 %ebp
-1:
- cmpl %eax, 0(%esp)
- je 4f
-2:
- movl %eax, %ebx
- movl %edx, %ecx
- addl %esi, %ebx
- adcl %edi, %ecx
- LOCK_PREFIX
- cmpxchg8b (%ebp)
- jne 1b
-
- movl $1, %eax
-3:
- addl $8, %esp
- CFI_ADJUST_CFA_OFFSET -8
- RESTORE ebx
- RESTORE ebp
- ret
-4:
- cmpl %edx, 4(%esp)
- jne 2b
- xorl %eax, %eax
- jmp 3b
- CFI_ENDPROC
-ENDPROC(atomic64_add_unless_cx8)
-
-ENTRY(atomic64_inc_not_zero_cx8)
- CFI_STARTPROC
- SAVE ebx
-
- read64 %esi
-1:
- testl %eax, %eax
- je 4f
-2:
- movl %eax, %ebx
- movl %edx, %ecx
- addl $1, %ebx
- adcl $0, %ecx
- LOCK_PREFIX
- cmpxchg8b (%esi)
- jne 1b
-
- movl $1, %eax
-3:
- RESTORE ebx
- ret
-4:
- testl %edx, %edx
- jne 2b
- jmp 3b
- CFI_ENDPROC
-ENDPROC(atomic64_inc_not_zero_cx8)
diff --git a/arch/um/sys-i386/bug.c b/arch/um/sys-i386/bug.c
deleted file mode 100644
index 8d4f273..0000000
--- a/arch/um/sys-i386/bug.c
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright (C) 2006 Jeff Dike (jdike@addtoit.com)
- * Licensed under the GPL V2
- */
-
-#include <linux/uaccess.h>
-#include <asm/errno.h>
-
-/* Mostly copied from i386/x86_86 - eliminated the eip < PAGE_OFFSET because
- * that's not relevant in skas mode.
- */
-
-int is_valid_bugaddr(unsigned long eip)
-{
- unsigned short ud2;
-
- if (probe_kernel_address((unsigned short __user *)eip, ud2))
- return 0;
-
- return ud2 == 0x0b0f;
-}
diff --git a/arch/um/sys-i386/ksyms.c b/arch/um/sys-i386/ksyms.c
deleted file mode 100644
index bfbefd3..0000000
--- a/arch/um/sys-i386/ksyms.c
+++ /dev/null
@@ -1,5 +0,0 @@
-#include "linux/module.h"
-#include "asm/checksum.h"
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_partial);
diff --git a/arch/um/sys-i386/shared/sysdep/barrier.h b/arch/um/sys-i386/shared/sysdep/barrier.h
deleted file mode 100644
index b58d52c..0000000
--- a/arch/um/sys-i386/shared/sysdep/barrier.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __SYSDEP_I386_BARRIER_H
-#define __SYSDEP_I386_BARRIER_H
-
-/* Copied from include/asm-i386 for use by userspace. i386 has the option
- * of using mfence, but I'm just using this, which works everywhere, for now.
- */
-#define mb() asm volatile("lock; addl $0,0(%esp)")
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/host_ldt.h b/arch/um/sys-i386/shared/sysdep/host_ldt.h
deleted file mode 100644
index 0953cc4..0000000
--- a/arch/um/sys-i386/shared/sysdep/host_ldt.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef __ASM_HOST_LDT_I386_H
-#define __ASM_HOST_LDT_I386_H
-
-#include <asm/ldt.h>
-
-/*
- * macros stolen from include/asm-i386/desc.h
- */
-#define LDT_entry_a(info) \
- ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
-
-#define LDT_entry_b(info) \
- (((info)->base_addr & 0xff000000) | \
- (((info)->base_addr & 0x00ff0000) >> 16) | \
- ((info)->limit & 0xf0000) | \
- (((info)->read_exec_only ^ 1) << 9) | \
- ((info)->contents << 10) | \
- (((info)->seg_not_present ^ 1) << 15) | \
- ((info)->seg_32bit << 22) | \
- ((info)->limit_in_pages << 23) | \
- ((info)->useable << 20) | \
- 0x7000)
-
-#define LDT_empty(info) (\
- (info)->base_addr == 0 && \
- (info)->limit == 0 && \
- (info)->contents == 0 && \
- (info)->read_exec_only == 1 && \
- (info)->seg_32bit == 0 && \
- (info)->limit_in_pages == 0 && \
- (info)->seg_not_present == 1 && \
- (info)->useable == 0 )
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/ptrace.h b/arch/um/sys-i386/shared/sysdep/ptrace.h
deleted file mode 100644
index c398a50..0000000
--- a/arch/um/sys-i386/shared/sysdep/ptrace.h
+++ /dev/null
@@ -1,171 +0,0 @@
-/*
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_I386_PTRACE_H
-#define __SYSDEP_I386_PTRACE_H
-
-#include "user_constants.h"
-#include "sysdep/faultinfo.h"
-
-#define MAX_REG_NR (UM_FRAME_SIZE / sizeof(unsigned long))
-#define MAX_REG_OFFSET (UM_FRAME_SIZE)
-
-static inline void update_debugregs(int seq) {}
-
-/* syscall emulation path in ptrace */
-
-#ifndef PTRACE_SYSEMU
-#define PTRACE_SYSEMU 31
-#endif
-
-void set_using_sysemu(int value);
-int get_using_sysemu(void);
-extern int sysemu_supported;
-
-#include "skas_ptregs.h"
-
-#define REGS_IP(r) ((r)[HOST_IP])
-#define REGS_SP(r) ((r)[HOST_SP])
-#define REGS_EFLAGS(r) ((r)[HOST_EFLAGS])
-#define REGS_EAX(r) ((r)[HOST_EAX])
-#define REGS_EBX(r) ((r)[HOST_EBX])
-#define REGS_ECX(r) ((r)[HOST_ECX])
-#define REGS_EDX(r) ((r)[HOST_EDX])
-#define REGS_ESI(r) ((r)[HOST_ESI])
-#define REGS_EDI(r) ((r)[HOST_EDI])
-#define REGS_EBP(r) ((r)[HOST_EBP])
-#define REGS_CS(r) ((r)[HOST_CS])
-#define REGS_SS(r) ((r)[HOST_SS])
-#define REGS_DS(r) ((r)[HOST_DS])
-#define REGS_ES(r) ((r)[HOST_ES])
-#define REGS_FS(r) ((r)[HOST_FS])
-#define REGS_GS(r) ((r)[HOST_GS])
-
-#define REGS_SET_SYSCALL_RETURN(r, res) REGS_EAX(r) = (res)
-
-#define REGS_RESTART_SYSCALL(r) IP_RESTART_SYSCALL(REGS_IP(r))
-
-#ifndef PTRACE_SYSEMU_SINGLESTEP
-#define PTRACE_SYSEMU_SINGLESTEP 32
-#endif
-
-struct uml_pt_regs {
- unsigned long gp[MAX_REG_NR];
- unsigned long fp[HOST_FPX_SIZE];
- struct faultinfo faultinfo;
- long syscall;
- int is_user;
-};
-
-#define EMPTY_UML_PT_REGS { }
-
-#define UPT_IP(r) REGS_IP((r)->gp)
-#define UPT_SP(r) REGS_SP((r)->gp)
-#define UPT_EFLAGS(r) REGS_EFLAGS((r)->gp)
-#define UPT_EAX(r) REGS_EAX((r)->gp)
-#define UPT_EBX(r) REGS_EBX((r)->gp)
-#define UPT_ECX(r) REGS_ECX((r)->gp)
-#define UPT_EDX(r) REGS_EDX((r)->gp)
-#define UPT_ESI(r) REGS_ESI((r)->gp)
-#define UPT_EDI(r) REGS_EDI((r)->gp)
-#define UPT_EBP(r) REGS_EBP((r)->gp)
-#define UPT_ORIG_EAX(r) ((r)->syscall)
-#define UPT_CS(r) REGS_CS((r)->gp)
-#define UPT_SS(r) REGS_SS((r)->gp)
-#define UPT_DS(r) REGS_DS((r)->gp)
-#define UPT_ES(r) REGS_ES((r)->gp)
-#define UPT_FS(r) REGS_FS((r)->gp)
-#define UPT_GS(r) REGS_GS((r)->gp)
-
-#define UPT_SYSCALL_ARG1(r) UPT_EBX(r)
-#define UPT_SYSCALL_ARG2(r) UPT_ECX(r)
-#define UPT_SYSCALL_ARG3(r) UPT_EDX(r)
-#define UPT_SYSCALL_ARG4(r) UPT_ESI(r)
-#define UPT_SYSCALL_ARG5(r) UPT_EDI(r)
-#define UPT_SYSCALL_ARG6(r) UPT_EBP(r)
-
-extern int user_context(unsigned long sp);
-
-#define UPT_IS_USER(r) ((r)->is_user)
-
-struct syscall_args {
- unsigned long args[6];
-};
-
-#define SYSCALL_ARGS(r) ((struct syscall_args) \
- { .args = { UPT_SYSCALL_ARG1(r), \
- UPT_SYSCALL_ARG2(r), \
- UPT_SYSCALL_ARG3(r), \
- UPT_SYSCALL_ARG4(r), \
- UPT_SYSCALL_ARG5(r), \
- UPT_SYSCALL_ARG6(r) } } )
-
-#define UPT_REG(regs, reg) \
- ({ unsigned long val; \
- switch(reg){ \
- case EIP: val = UPT_IP(regs); break; \
- case UESP: val = UPT_SP(regs); break; \
- case EAX: val = UPT_EAX(regs); break; \
- case EBX: val = UPT_EBX(regs); break; \
- case ECX: val = UPT_ECX(regs); break; \
- case EDX: val = UPT_EDX(regs); break; \
- case ESI: val = UPT_ESI(regs); break; \
- case EDI: val = UPT_EDI(regs); break; \
- case EBP: val = UPT_EBP(regs); break; \
- case ORIG_EAX: val = UPT_ORIG_EAX(regs); break; \
- case CS: val = UPT_CS(regs); break; \
- case SS: val = UPT_SS(regs); break; \
- case DS: val = UPT_DS(regs); break; \
- case ES: val = UPT_ES(regs); break; \
- case FS: val = UPT_FS(regs); break; \
- case GS: val = UPT_GS(regs); break; \
- case EFL: val = UPT_EFLAGS(regs); break; \
- default : \
- panic("Bad register in UPT_REG : %d\n", reg); \
- val = -1; \
- } \
- val; \
- })
-
-#define UPT_SET(regs, reg, val) \
- do { \
- switch(reg){ \
- case EIP: UPT_IP(regs) = val; break; \
- case UESP: UPT_SP(regs) = val; break; \
- case EAX: UPT_EAX(regs) = val; break; \
- case EBX: UPT_EBX(regs) = val; break; \
- case ECX: UPT_ECX(regs) = val; break; \
- case EDX: UPT_EDX(regs) = val; break; \
- case ESI: UPT_ESI(regs) = val; break; \
- case EDI: UPT_EDI(regs) = val; break; \
- case EBP: UPT_EBP(regs) = val; break; \
- case ORIG_EAX: UPT_ORIG_EAX(regs) = val; break; \
- case CS: UPT_CS(regs) = val; break; \
- case SS: UPT_SS(regs) = val; break; \
- case DS: UPT_DS(regs) = val; break; \
- case ES: UPT_ES(regs) = val; break; \
- case FS: UPT_FS(regs) = val; break; \
- case GS: UPT_GS(regs) = val; break; \
- case EFL: UPT_EFLAGS(regs) = val; break; \
- default : \
- panic("Bad register in UPT_SET : %d\n", reg); \
- break; \
- } \
- } while (0)
-
-#define UPT_SET_SYSCALL_RETURN(r, res) \
- REGS_SET_SYSCALL_RETURN((r)->regs, (res))
-
-#define UPT_RESTART_SYSCALL(r) REGS_RESTART_SYSCALL((r)->gp)
-
-#define UPT_ORIG_SYSCALL(r) UPT_EAX(r)
-#define UPT_SYSCALL_NR(r) UPT_ORIG_EAX(r)
-#define UPT_SYSCALL_RET(r) UPT_EAX(r)
-
-#define UPT_FAULTINFO(r) (&(r)->faultinfo)
-
-extern void arch_init_registers(int pid);
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/ptrace_user.h b/arch/um/sys-i386/shared/sysdep/ptrace_user.h
deleted file mode 100644
index ef56247..0000000
--- a/arch/um/sys-i386/shared/sysdep/ptrace_user.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_I386_PTRACE_USER_H__
-#define __SYSDEP_I386_PTRACE_USER_H__
-
-#include <sys/ptrace.h>
-#include <linux/ptrace.h>
-#include <asm/ptrace.h>
-#include "user_constants.h"
-
-#define PT_OFFSET(r) ((r) * sizeof(long))
-
-#define PT_SYSCALL_NR(regs) ((regs)[ORIG_EAX])
-#define PT_SYSCALL_NR_OFFSET PT_OFFSET(ORIG_EAX)
-
-#define PT_SYSCALL_ARG1_OFFSET PT_OFFSET(EBX)
-#define PT_SYSCALL_ARG2_OFFSET PT_OFFSET(ECX)
-#define PT_SYSCALL_ARG3_OFFSET PT_OFFSET(EDX)
-#define PT_SYSCALL_ARG4_OFFSET PT_OFFSET(ESI)
-#define PT_SYSCALL_ARG5_OFFSET PT_OFFSET(EDI)
-#define PT_SYSCALL_ARG6_OFFSET PT_OFFSET(EBP)
-
-#define PT_SYSCALL_RET_OFFSET PT_OFFSET(EAX)
-
-#define REGS_SYSCALL_NR EAX /* This is used before a system call */
-#define REGS_SYSCALL_ARG1 EBX
-#define REGS_SYSCALL_ARG2 ECX
-#define REGS_SYSCALL_ARG3 EDX
-#define REGS_SYSCALL_ARG4 ESI
-#define REGS_SYSCALL_ARG5 EDI
-#define REGS_SYSCALL_ARG6 EBP
-
-#define REGS_IP_INDEX EIP
-#define REGS_SP_INDEX UESP
-
-#define PT_IP_OFFSET PT_OFFSET(EIP)
-#define PT_IP(regs) ((regs)[EIP])
-#define PT_SP_OFFSET PT_OFFSET(UESP)
-#define PT_SP(regs) ((regs)[UESP])
-
-#define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE)
-
-#ifndef FRAME_SIZE
-#define FRAME_SIZE (17)
-#endif
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/sc.h b/arch/um/sys-i386/shared/sysdep/sc.h
deleted file mode 100644
index c57d178..0000000
--- a/arch/um/sys-i386/shared/sysdep/sc.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef __SYSDEP_I386_SC_H
-#define __SYSDEP_I386_SC_H
-
-#include <user_constants.h>
-
-#define SC_OFFSET(sc, field) \
- *((unsigned long *) &(((char *) (sc))[HOST_##field]))
-#define SC_FP_OFFSET(sc, field) \
- *((unsigned long *) &(((char *) (SC_FPSTATE(sc)))[HOST_##field]))
-#define SC_FP_OFFSET_PTR(sc, field, type) \
- ((type *) &(((char *) (SC_FPSTATE(sc)))[HOST_##field]))
-
-#define SC_IP(sc) SC_OFFSET(sc, SC_IP)
-#define SC_SP(sc) SC_OFFSET(sc, SC_SP)
-#define SC_FS(sc) SC_OFFSET(sc, SC_FS)
-#define SC_GS(sc) SC_OFFSET(sc, SC_GS)
-#define SC_DS(sc) SC_OFFSET(sc, SC_DS)
-#define SC_ES(sc) SC_OFFSET(sc, SC_ES)
-#define SC_SS(sc) SC_OFFSET(sc, SC_SS)
-#define SC_CS(sc) SC_OFFSET(sc, SC_CS)
-#define SC_EFLAGS(sc) SC_OFFSET(sc, SC_EFLAGS)
-#define SC_EAX(sc) SC_OFFSET(sc, SC_EAX)
-#define SC_EBX(sc) SC_OFFSET(sc, SC_EBX)
-#define SC_ECX(sc) SC_OFFSET(sc, SC_ECX)
-#define SC_EDX(sc) SC_OFFSET(sc, SC_EDX)
-#define SC_EDI(sc) SC_OFFSET(sc, SC_EDI)
-#define SC_ESI(sc) SC_OFFSET(sc, SC_ESI)
-#define SC_EBP(sc) SC_OFFSET(sc, SC_EBP)
-#define SC_TRAPNO(sc) SC_OFFSET(sc, SC_TRAPNO)
-#define SC_ERR(sc) SC_OFFSET(sc, SC_ERR)
-#define SC_CR2(sc) SC_OFFSET(sc, SC_CR2)
-#define SC_FPSTATE(sc) SC_OFFSET(sc, SC_FPSTATE)
-#define SC_SIGMASK(sc) SC_OFFSET(sc, SC_SIGMASK)
-#define SC_FP_CW(sc) SC_FP_OFFSET(sc, SC_FP_CW)
-#define SC_FP_SW(sc) SC_FP_OFFSET(sc, SC_FP_SW)
-#define SC_FP_TAG(sc) SC_FP_OFFSET(sc, SC_FP_TAG)
-#define SC_FP_IPOFF(sc) SC_FP_OFFSET(sc, SC_FP_IPOFF)
-#define SC_FP_CSSEL(sc) SC_FP_OFFSET(sc, SC_FP_CSSEL)
-#define SC_FP_DATAOFF(sc) SC_FP_OFFSET(sc, SC_FP_DATAOFF)
-#define SC_FP_DATASEL(sc) SC_FP_OFFSET(sc, SC_FP_DATASEL)
-#define SC_FP_ST(sc) SC_FP_OFFSET_PTR(sc, SC_FP_ST, struct _fpstate)
-#define SC_FXSR_ENV(sc) SC_FP_OFFSET_PTR(sc, SC_FXSR_ENV, void)
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/sigcontext.h b/arch/um/sys-i386/shared/sysdep/sigcontext.h
deleted file mode 100644
index f583c87..0000000
--- a/arch/um/sys-i386/shared/sysdep/sigcontext.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __SYS_SIGCONTEXT_I386_H
-#define __SYS_SIGCONTEXT_I386_H
-
-#include "sysdep/sc.h"
-
-#define IP_RESTART_SYSCALL(ip) ((ip) -= 2)
-
-#define GET_FAULTINFO_FROM_SC(fi, sc) \
- { \
- (fi).cr2 = SC_CR2(sc); \
- (fi).error_code = SC_ERR(sc); \
- (fi).trap_no = SC_TRAPNO(sc); \
- }
-
-/* This is Page Fault */
-#define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14)
-
-/* SKAS3 has no trap_no on i386, but get_skas_faultinfo() sets it to 0. */
-#define SEGV_MAYBE_FIXABLE(fi) ((fi)->trap_no == 0 && ptrace_faultinfo)
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/vm-flags.h b/arch/um/sys-i386/shared/sysdep/vm-flags.h
deleted file mode 100644
index e0d24c5..0000000
--- a/arch/um/sys-i386/shared/sysdep/vm-flags.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * Copyright (C) 2004 Jeff Dike (jdike@addtoit.com)
- * Licensed under the GPL
- */
-
-#ifndef __VM_FLAGS_I386_H
-#define __VM_FLAGS_I386_H
-
-#define VM_DATA_DEFAULT_FLAGS \
- (VM_READ | VM_WRITE | \
- ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
- VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-#endif
diff --git a/arch/um/sys-i386/stub_segv.c b/arch/um/sys-i386/stub_segv.c
deleted file mode 100644
index 28ccf73..0000000
--- a/arch/um/sys-i386/stub_segv.c
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Copyright (C) 2004 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include "sysdep/stub.h"
-#include "sysdep/sigcontext.h"
-
-void __attribute__ ((__section__ (".__syscall_stub")))
-stub_segv_handler(int sig)
-{
- struct sigcontext *sc = (struct sigcontext *) (&sig + 1);
-
- GET_FAULTINFO_FROM_SC(*((struct faultinfo *) STUB_DATA), sc);
-
- trap_myself();
-}
diff --git a/arch/um/sys-i386/user-offsets.c b/arch/um/sys-i386/user-offsets.c
deleted file mode 100644
index 5f883bf..0000000
--- a/arch/um/sys-i386/user-offsets.c
+++ /dev/null
@@ -1,53 +0,0 @@
-#include <stdio.h>
-#include <stddef.h>
-#include <signal.h>
-#include <sys/poll.h>
-#include <sys/user.h>
-#include <sys/mman.h>
-#include <asm/ptrace.h>
-
-#define DEFINE(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define DEFINE_LONGS(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long)))
-
-#define OFFSET(sym, str, mem) \
- DEFINE(sym, offsetof(struct str, mem));
-
-void foo(void)
-{
- OFFSET(HOST_SC_TRAPNO, sigcontext, trapno);
- OFFSET(HOST_SC_ERR, sigcontext, err);
- OFFSET(HOST_SC_CR2, sigcontext, cr2);
-
- DEFINE_LONGS(HOST_FP_SIZE, sizeof(struct user_fpregs_struct));
- DEFINE_LONGS(HOST_FPX_SIZE, sizeof(struct user_fpxregs_struct));
-
- DEFINE(HOST_IP, EIP);
- DEFINE(HOST_SP, UESP);
- DEFINE(HOST_EFLAGS, EFL);
- DEFINE(HOST_EAX, EAX);
- DEFINE(HOST_EBX, EBX);
- DEFINE(HOST_ECX, ECX);
- DEFINE(HOST_EDX, EDX);
- DEFINE(HOST_ESI, ESI);
- DEFINE(HOST_EDI, EDI);
- DEFINE(HOST_EBP, EBP);
- DEFINE(HOST_CS, CS);
- DEFINE(HOST_SS, SS);
- DEFINE(HOST_DS, DS);
- DEFINE(HOST_FS, FS);
- DEFINE(HOST_ES, ES);
- DEFINE(HOST_GS, GS);
- DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct));
-
- /* XXX Duplicated between i386 and x86_64 */
- DEFINE(UM_POLLIN, POLLIN);
- DEFINE(UM_POLLPRI, POLLPRI);
- DEFINE(UM_POLLOUT, POLLOUT);
-
- DEFINE(UM_PROT_READ, PROT_READ);
- DEFINE(UM_PROT_WRITE, PROT_WRITE);
- DEFINE(UM_PROT_EXEC, PROT_EXEC);
-}
diff --git a/arch/um/sys-x86_64/Makefile b/arch/um/sys-x86_64/Makefile
deleted file mode 100644
index bd4d1d3..0000000
--- a/arch/um/sys-x86_64/Makefile
+++ /dev/null
@@ -1,27 +0,0 @@
-#
-# Copyright 2003 PathScale, Inc.
-#
-# Licensed under the GPL
-#
-
-obj-y = bug.o bugs.o delay.o fault.o ldt.o ptrace.o ptrace_user.o mem.o \
- setjmp.o signal.o stub.o stub_segv.o syscalls.o syscall_table.o \
- sysrq.o ksyms.o tls.o
-
-obj-y += vdso/
-
-subarch-obj-y = lib/csum-partial_64.o lib/memcpy_64.o lib/thunk_64.o \
- lib/rwsem.o
-subarch-obj-$(CONFIG_MODULES) += kernel/module.o
-
-ldt-y = ../sys-i386/ldt.o
-
-USER_OBJS := ptrace_user.o
-
-USER_OBJS += user-offsets.s
-extra-y += user-offsets.s
-
-UNPROFILE_OBJS := stub_segv.o
-CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING)
-
-include arch/um/scripts/Makefile.rules
diff --git a/arch/um/sys-x86_64/asm/archparam.h b/arch/um/sys-x86_64/asm/archparam.h
deleted file mode 100644
index 6c08366..0000000
--- a/arch/um/sys-x86_64/asm/archparam.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_ARCHPARAM_X86_64_H
-#define __UM_ARCHPARAM_X86_64_H
-
-
-/* No user-accessible fixmap addresses, i.e. vsyscall */
-#define FIXADDR_USER_START 0
-#define FIXADDR_USER_END 0
-
-#endif
-
diff --git a/arch/um/sys-x86_64/asm/elf.h b/arch/um/sys-x86_64/asm/elf.h
deleted file mode 100644
index 11a2bfb..0000000
--- a/arch/um/sys-x86_64/asm/elf.h
+++ /dev/null
@@ -1,132 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- *
- * Licensed under the GPL
- */
-#ifndef __UM_ELF_X86_64_H
-#define __UM_ELF_X86_64_H
-
-#include <asm/user.h>
-#include "skas.h"
-
-/* x86-64 relocation types, taken from asm-x86_64/elf.h */
-#define R_X86_64_NONE 0 /* No reloc */
-#define R_X86_64_64 1 /* Direct 64 bit */
-#define R_X86_64_PC32 2 /* PC relative 32 bit signed */
-#define R_X86_64_GOT32 3 /* 32 bit GOT entry */
-#define R_X86_64_PLT32 4 /* 32 bit PLT address */
-#define R_X86_64_COPY 5 /* Copy symbol at runtime */
-#define R_X86_64_GLOB_DAT 6 /* Create GOT entry */
-#define R_X86_64_JUMP_SLOT 7 /* Create PLT entry */
-#define R_X86_64_RELATIVE 8 /* Adjust by program base */
-#define R_X86_64_GOTPCREL 9 /* 32 bit signed pc relative
- offset to GOT */
-#define R_X86_64_32 10 /* Direct 32 bit zero extended */
-#define R_X86_64_32S 11 /* Direct 32 bit sign extended */
-#define R_X86_64_16 12 /* Direct 16 bit zero extended */
-#define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */
-#define R_X86_64_8 14 /* Direct 8 bit sign extended */
-#define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */
-
-#define R_X86_64_NUM 16
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_i387_struct elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) \
- ((x)->e_machine == EM_X86_64)
-
-#define ELF_CLASS ELFCLASS64
-#define ELF_DATA ELFDATA2LSB
-#define ELF_ARCH EM_X86_64
-
-#define ELF_PLAT_INIT(regs, load_addr) do { \
- PT_REGS_RBX(regs) = 0; \
- PT_REGS_RCX(regs) = 0; \
- PT_REGS_RDX(regs) = 0; \
- PT_REGS_RSI(regs) = 0; \
- PT_REGS_RDI(regs) = 0; \
- PT_REGS_RBP(regs) = 0; \
- PT_REGS_RAX(regs) = 0; \
- PT_REGS_R8(regs) = 0; \
- PT_REGS_R9(regs) = 0; \
- PT_REGS_R10(regs) = 0; \
- PT_REGS_R11(regs) = 0; \
- PT_REGS_R12(regs) = 0; \
- PT_REGS_R13(regs) = 0; \
- PT_REGS_R14(regs) = 0; \
- PT_REGS_R15(regs) = 0; \
-} while (0)
-
-#define ELF_CORE_COPY_REGS(pr_reg, _regs) \
- (pr_reg)[0] = (_regs)->regs.gp[0]; \
- (pr_reg)[1] = (_regs)->regs.gp[1]; \
- (pr_reg)[2] = (_regs)->regs.gp[2]; \
- (pr_reg)[3] = (_regs)->regs.gp[3]; \
- (pr_reg)[4] = (_regs)->regs.gp[4]; \
- (pr_reg)[5] = (_regs)->regs.gp[5]; \
- (pr_reg)[6] = (_regs)->regs.gp[6]; \
- (pr_reg)[7] = (_regs)->regs.gp[7]; \
- (pr_reg)[8] = (_regs)->regs.gp[8]; \
- (pr_reg)[9] = (_regs)->regs.gp[9]; \
- (pr_reg)[10] = (_regs)->regs.gp[10]; \
- (pr_reg)[11] = (_regs)->regs.gp[11]; \
- (pr_reg)[12] = (_regs)->regs.gp[12]; \
- (pr_reg)[13] = (_regs)->regs.gp[13]; \
- (pr_reg)[14] = (_regs)->regs.gp[14]; \
- (pr_reg)[15] = (_regs)->regs.gp[15]; \
- (pr_reg)[16] = (_regs)->regs.gp[16]; \
- (pr_reg)[17] = (_regs)->regs.gp[17]; \
- (pr_reg)[18] = (_regs)->regs.gp[18]; \
- (pr_reg)[19] = (_regs)->regs.gp[19]; \
- (pr_reg)[20] = (_regs)->regs.gp[20]; \
- (pr_reg)[21] = current->thread.arch.fs; \
- (pr_reg)[22] = 0; \
- (pr_reg)[23] = 0; \
- (pr_reg)[24] = 0; \
- (pr_reg)[25] = 0; \
- (pr_reg)[26] = 0;
-
-#define task_pt_regs(t) (&(t)->thread.regs)
-
-struct task_struct;
-
-extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
-
-#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
-
-#ifdef TIF_IA32 /* XXX */
-#error XXX, indeed
- clear_thread_flag(TIF_IA32);
-#endif
-
-#define ELF_EXEC_PAGESIZE 4096
-
-#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
-
-extern long elf_aux_hwcap;
-#define ELF_HWCAP (elf_aux_hwcap)
-
-#define ELF_PLATFORM "x86_64"
-
-#define SET_PERSONALITY(ex) do ; while(0)
-
-#define __HAVE_ARCH_GATE_AREA 1
-#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
-struct linux_binprm;
-extern int arch_setup_additional_pages(struct linux_binprm *bprm,
- int uses_interp);
-
-extern unsigned long um_vdso_addr;
-#define AT_SYSINFO_EHDR 33
-#define ARCH_DLINFO NEW_AUX_ENT(AT_SYSINFO_EHDR, um_vdso_addr)
-
-#endif
diff --git a/arch/um/sys-x86_64/asm/module.h b/arch/um/sys-x86_64/asm/module.h
deleted file mode 100644
index 8eb79c2..0000000
--- a/arch/um/sys-x86_64/asm/module.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_MODULE_X86_64_H
-#define __UM_MODULE_X86_64_H
-
-/* UML is simple */
-struct mod_arch_specific
-{
-};
-
-#define Elf_Shdr Elf64_Shdr
-#define Elf_Sym Elf64_Sym
-#define Elf_Ehdr Elf64_Ehdr
-
-#endif
-
diff --git a/arch/um/sys-x86_64/delay.c b/arch/um/sys-x86_64/delay.c
deleted file mode 100644
index f3fe1a6..0000000
--- a/arch/um/sys-x86_64/delay.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * Copyright (C) 2011 Richard Weinberger <richrd@nod.at>
- * Mostly copied from arch/x86/lib/delay.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <asm/param.h>
-
-void __delay(unsigned long loops)
-{
- asm volatile(
- "test %0,%0\n"
- "jz 3f\n"
- "jmp 1f\n"
-
- ".align 16\n"
- "1: jmp 2f\n"
-
- ".align 16\n"
- "2: dec %0\n"
- " jnz 2b\n"
- "3: dec %0\n"
-
- : /* we don't need output */
- : "a" (loops)
- );
-}
-EXPORT_SYMBOL(__delay);
-
-inline void __const_udelay(unsigned long xloops)
-{
- int d0;
-
- xloops *= 4;
- asm("mull %%edx"
- : "=d" (xloops), "=&a" (d0)
- : "1" (xloops), "0"
- (loops_per_jiffy * (HZ/4)));
-
- __delay(++xloops);
-}
-EXPORT_SYMBOL(__const_udelay);
-
-void __udelay(unsigned long usecs)
-{
- __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
-}
-EXPORT_SYMBOL(__udelay);
-
-void __ndelay(unsigned long nsecs)
-{
- __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
-}
-EXPORT_SYMBOL(__ndelay);
diff --git a/arch/um/sys-x86_64/fault.c b/arch/um/sys-x86_64/fault.c
deleted file mode 100644
index ce85117..0000000
--- a/arch/um/sys-x86_64/fault.c
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#include "sysdep/ptrace.h"
-
-/* These two are from asm-um/uaccess.h and linux/module.h, check them. */
-struct exception_table_entry
-{
- unsigned long insn;
- unsigned long fixup;
-};
-
-const struct exception_table_entry *search_exception_tables(unsigned long add);
-
-int arch_fixup(unsigned long address, struct uml_pt_regs *regs)
-{
- const struct exception_table_entry *fixup;
-
- fixup = search_exception_tables(address);
- if (fixup != 0) {
- UPT_IP(regs) = fixup->fixup;
- return 1;
- }
- return 0;
-}
diff --git a/arch/um/sys-x86_64/ptrace_user.c b/arch/um/sys-x86_64/ptrace_user.c
deleted file mode 100644
index c57a496..0000000
--- a/arch/um/sys-x86_64/ptrace_user.c
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#include <errno.h>
-#include "ptrace_user.h"
-
-int ptrace_getregs(long pid, unsigned long *regs_out)
-{
- if (ptrace(PTRACE_GETREGS, pid, 0, regs_out) < 0)
- return -errno;
- return(0);
-}
-
-int ptrace_setregs(long pid, unsigned long *regs_out)
-{
- if (ptrace(PTRACE_SETREGS, pid, 0, regs_out) < 0)
- return -errno;
- return(0);
-}
diff --git a/arch/um/sys-x86_64/shared/sysdep/barrier.h b/arch/um/sys-x86_64/shared/sysdep/barrier.h
deleted file mode 100644
index 7b610be..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/barrier.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __SYSDEP_X86_64_BARRIER_H
-#define __SYSDEP_X86_64_BARRIER_H
-
-/* Copied from include/asm-x86_64 for use by userspace. */
-#define mb() asm volatile("mfence":::"memory")
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/host_ldt.h b/arch/um/sys-x86_64/shared/sysdep/host_ldt.h
deleted file mode 100644
index e8b1be1..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/host_ldt.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#ifndef __ASM_HOST_LDT_X86_64_H
-#define __ASM_HOST_LDT_X86_64_H
-
-#include <asm/ldt.h>
-
-/*
- * macros stolen from include/asm-x86_64/desc.h
- */
-#define LDT_entry_a(info) \
- ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
-
-/* Don't allow setting of the lm bit. It is useless anyways because
- * 64bit system calls require __USER_CS. */
-#define LDT_entry_b(info) \
- (((info)->base_addr & 0xff000000) | \
- (((info)->base_addr & 0x00ff0000) >> 16) | \
- ((info)->limit & 0xf0000) | \
- (((info)->read_exec_only ^ 1) << 9) | \
- ((info)->contents << 10) | \
- (((info)->seg_not_present ^ 1) << 15) | \
- ((info)->seg_32bit << 22) | \
- ((info)->limit_in_pages << 23) | \
- ((info)->useable << 20) | \
- /* ((info)->lm << 21) | */ \
- 0x7000)
-
-#define LDT_empty(info) (\
- (info)->base_addr == 0 && \
- (info)->limit == 0 && \
- (info)->contents == 0 && \
- (info)->read_exec_only == 1 && \
- (info)->seg_32bit == 0 && \
- (info)->limit_in_pages == 0 && \
- (info)->seg_not_present == 1 && \
- (info)->useable == 0 && \
- (info)->lm == 0)
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/kernel-offsets.h b/arch/um/sys-x86_64/shared/sysdep/kernel-offsets.h
deleted file mode 100644
index a307237..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/kernel-offsets.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#include <linux/stddef.h>
-#include <linux/sched.h>
-#include <linux/time.h>
-#include <linux/elf.h>
-#include <linux/crypto.h>
-#include <asm/page.h>
-#include <asm/mman.h>
-
-#define DEFINE(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define DEFINE_STR1(x) #x
-#define DEFINE_STR(sym, val) asm volatile("\n->" #sym " " DEFINE_STR1(val) " " #val: : )
-
-#define BLANK() asm volatile("\n->" : : )
-
-#define OFFSET(sym, str, mem) \
- DEFINE(sym, offsetof(struct str, mem));
-
-void foo(void)
-{
-#include <common-offsets.h>
-}
diff --git a/arch/um/sys-x86_64/shared/sysdep/ptrace.h b/arch/um/sys-x86_64/shared/sysdep/ptrace.h
deleted file mode 100644
index 8ee8f8e..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/ptrace.h
+++ /dev/null
@@ -1,240 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- *
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_X86_64_PTRACE_H
-#define __SYSDEP_X86_64_PTRACE_H
-
-#include "user_constants.h"
-#include "sysdep/faultinfo.h"
-
-#define MAX_REG_OFFSET (UM_FRAME_SIZE)
-#define MAX_REG_NR ((MAX_REG_OFFSET) / sizeof(unsigned long))
-
-#include "skas_ptregs.h"
-
-#define REGS_IP(r) ((r)[HOST_IP])
-#define REGS_SP(r) ((r)[HOST_SP])
-
-#define REGS_RBX(r) ((r)[HOST_RBX])
-#define REGS_RCX(r) ((r)[HOST_RCX])
-#define REGS_RDX(r) ((r)[HOST_RDX])
-#define REGS_RSI(r) ((r)[HOST_RSI])
-#define REGS_RDI(r) ((r)[HOST_RDI])
-#define REGS_RBP(r) ((r)[HOST_RBP])
-#define REGS_RAX(r) ((r)[HOST_RAX])
-#define REGS_R8(r) ((r)[HOST_R8])
-#define REGS_R9(r) ((r)[HOST_R9])
-#define REGS_R10(r) ((r)[HOST_R10])
-#define REGS_R11(r) ((r)[HOST_R11])
-#define REGS_R12(r) ((r)[HOST_R12])
-#define REGS_R13(r) ((r)[HOST_R13])
-#define REGS_R14(r) ((r)[HOST_R14])
-#define REGS_R15(r) ((r)[HOST_R15])
-#define REGS_CS(r) ((r)[HOST_CS])
-#define REGS_EFLAGS(r) ((r)[HOST_EFLAGS])
-#define REGS_SS(r) ((r)[HOST_SS])
-
-#define HOST_FS_BASE 21
-#define HOST_GS_BASE 22
-#define HOST_DS 23
-#define HOST_ES 24
-#define HOST_FS 25
-#define HOST_GS 26
-
-/* Also defined in asm/ptrace-x86_64.h, but not in libc headers. So, these
- * are already defined for kernel code, but not for userspace code.
- */
-#ifndef FS_BASE
-/* These aren't defined in ptrace.h, but exist in struct user_regs_struct,
- * which is what x86_64 ptrace actually uses.
- */
-#define FS_BASE (HOST_FS_BASE * sizeof(long))
-#define GS_BASE (HOST_GS_BASE * sizeof(long))
-#define DS (HOST_DS * sizeof(long))
-#define ES (HOST_ES * sizeof(long))
-#define FS (HOST_FS * sizeof(long))
-#define GS (HOST_GS * sizeof(long))
-#endif
-
-#define REGS_FS_BASE(r) ((r)[HOST_FS_BASE])
-#define REGS_GS_BASE(r) ((r)[HOST_GS_BASE])
-#define REGS_DS(r) ((r)[HOST_DS])
-#define REGS_ES(r) ((r)[HOST_ES])
-#define REGS_FS(r) ((r)[HOST_FS])
-#define REGS_GS(r) ((r)[HOST_GS])
-
-#define REGS_ORIG_RAX(r) ((r)[HOST_ORIG_RAX])
-
-#define REGS_SET_SYSCALL_RETURN(r, res) REGS_RAX(r) = (res)
-
-#define REGS_RESTART_SYSCALL(r) IP_RESTART_SYSCALL(REGS_IP(r))
-
-#define REGS_SEGV_IS_FIXABLE(r) SEGV_IS_FIXABLE((r)->trap_type)
-
-#define REGS_FAULT_ADDR(r) ((r)->fault_addr)
-
-#define REGS_FAULT_WRITE(r) FAULT_WRITE((r)->fault_type)
-
-#define REGS_TRAP(r) ((r)->trap_type)
-
-#define REGS_ERR(r) ((r)->fault_type)
-
-struct uml_pt_regs {
- unsigned long gp[MAX_REG_NR];
- unsigned long fp[HOST_FP_SIZE];
- struct faultinfo faultinfo;
- long syscall;
- int is_user;
-};
-
-#define EMPTY_UML_PT_REGS { }
-
-#define UPT_RBX(r) REGS_RBX((r)->gp)
-#define UPT_RCX(r) REGS_RCX((r)->gp)
-#define UPT_RDX(r) REGS_RDX((r)->gp)
-#define UPT_RSI(r) REGS_RSI((r)->gp)
-#define UPT_RDI(r) REGS_RDI((r)->gp)
-#define UPT_RBP(r) REGS_RBP((r)->gp)
-#define UPT_RAX(r) REGS_RAX((r)->gp)
-#define UPT_R8(r) REGS_R8((r)->gp)
-#define UPT_R9(r) REGS_R9((r)->gp)
-#define UPT_R10(r) REGS_R10((r)->gp)
-#define UPT_R11(r) REGS_R11((r)->gp)
-#define UPT_R12(r) REGS_R12((r)->gp)
-#define UPT_R13(r) REGS_R13((r)->gp)
-#define UPT_R14(r) REGS_R14((r)->gp)
-#define UPT_R15(r) REGS_R15((r)->gp)
-#define UPT_CS(r) REGS_CS((r)->gp)
-#define UPT_FS_BASE(r) REGS_FS_BASE((r)->gp)
-#define UPT_FS(r) REGS_FS((r)->gp)
-#define UPT_GS_BASE(r) REGS_GS_BASE((r)->gp)
-#define UPT_GS(r) REGS_GS((r)->gp)
-#define UPT_DS(r) REGS_DS((r)->gp)
-#define UPT_ES(r) REGS_ES((r)->gp)
-#define UPT_CS(r) REGS_CS((r)->gp)
-#define UPT_SS(r) REGS_SS((r)->gp)
-#define UPT_ORIG_RAX(r) REGS_ORIG_RAX((r)->gp)
-
-#define UPT_IP(r) REGS_IP((r)->gp)
-#define UPT_SP(r) REGS_SP((r)->gp)
-
-#define UPT_EFLAGS(r) REGS_EFLAGS((r)->gp)
-#define UPT_SYSCALL_NR(r) ((r)->syscall)
-#define UPT_SYSCALL_RET(r) UPT_RAX(r)
-
-extern int user_context(unsigned long sp);
-
-#define UPT_IS_USER(r) ((r)->is_user)
-
-#define UPT_SYSCALL_ARG1(r) UPT_RDI(r)
-#define UPT_SYSCALL_ARG2(r) UPT_RSI(r)
-#define UPT_SYSCALL_ARG3(r) UPT_RDX(r)
-#define UPT_SYSCALL_ARG4(r) UPT_R10(r)
-#define UPT_SYSCALL_ARG5(r) UPT_R8(r)
-#define UPT_SYSCALL_ARG6(r) UPT_R9(r)
-
-struct syscall_args {
- unsigned long args[6];
-};
-
-#define SYSCALL_ARGS(r) ((struct syscall_args) \
- { .args = { UPT_SYSCALL_ARG1(r), \
- UPT_SYSCALL_ARG2(r), \
- UPT_SYSCALL_ARG3(r), \
- UPT_SYSCALL_ARG4(r), \
- UPT_SYSCALL_ARG5(r), \
- UPT_SYSCALL_ARG6(r) } } )
-
-#define UPT_REG(regs, reg) \
- ({ unsigned long val; \
- switch(reg){ \
- case R8: val = UPT_R8(regs); break; \
- case R9: val = UPT_R9(regs); break; \
- case R10: val = UPT_R10(regs); break; \
- case R11: val = UPT_R11(regs); break; \
- case R12: val = UPT_R12(regs); break; \
- case R13: val = UPT_R13(regs); break; \
- case R14: val = UPT_R14(regs); break; \
- case R15: val = UPT_R15(regs); break; \
- case RIP: val = UPT_IP(regs); break; \
- case RSP: val = UPT_SP(regs); break; \
- case RAX: val = UPT_RAX(regs); break; \
- case RBX: val = UPT_RBX(regs); break; \
- case RCX: val = UPT_RCX(regs); break; \
- case RDX: val = UPT_RDX(regs); break; \
- case RSI: val = UPT_RSI(regs); break; \
- case RDI: val = UPT_RDI(regs); break; \
- case RBP: val = UPT_RBP(regs); break; \
- case ORIG_RAX: val = UPT_ORIG_RAX(regs); break; \
- case CS: val = UPT_CS(regs); break; \
- case SS: val = UPT_SS(regs); break; \
- case FS_BASE: val = UPT_FS_BASE(regs); break; \
- case GS_BASE: val = UPT_GS_BASE(regs); break; \
- case DS: val = UPT_DS(regs); break; \
- case ES: val = UPT_ES(regs); break; \
- case FS : val = UPT_FS (regs); break; \
- case GS: val = UPT_GS(regs); break; \
- case EFLAGS: val = UPT_EFLAGS(regs); break; \
- default : \
- panic("Bad register in UPT_REG : %d\n", reg); \
- val = -1; \
- } \
- val; \
- })
-
-
-#define UPT_SET(regs, reg, val) \
- ({ unsigned long __upt_val = val; \
- switch(reg){ \
- case R8: UPT_R8(regs) = __upt_val; break; \
- case R9: UPT_R9(regs) = __upt_val; break; \
- case R10: UPT_R10(regs) = __upt_val; break; \
- case R11: UPT_R11(regs) = __upt_val; break; \
- case R12: UPT_R12(regs) = __upt_val; break; \
- case R13: UPT_R13(regs) = __upt_val; break; \
- case R14: UPT_R14(regs) = __upt_val; break; \
- case R15: UPT_R15(regs) = __upt_val; break; \
- case RIP: UPT_IP(regs) = __upt_val; break; \
- case RSP: UPT_SP(regs) = __upt_val; break; \
- case RAX: UPT_RAX(regs) = __upt_val; break; \
- case RBX: UPT_RBX(regs) = __upt_val; break; \
- case RCX: UPT_RCX(regs) = __upt_val; break; \
- case RDX: UPT_RDX(regs) = __upt_val; break; \
- case RSI: UPT_RSI(regs) = __upt_val; break; \
- case RDI: UPT_RDI(regs) = __upt_val; break; \
- case RBP: UPT_RBP(regs) = __upt_val; break; \
- case ORIG_RAX: UPT_ORIG_RAX(regs) = __upt_val; break; \
- case CS: UPT_CS(regs) = __upt_val; break; \
- case SS: UPT_SS(regs) = __upt_val; break; \
- case FS_BASE: UPT_FS_BASE(regs) = __upt_val; break; \
- case GS_BASE: UPT_GS_BASE(regs) = __upt_val; break; \
- case DS: UPT_DS(regs) = __upt_val; break; \
- case ES: UPT_ES(regs) = __upt_val; break; \
- case FS: UPT_FS(regs) = __upt_val; break; \
- case GS: UPT_GS(regs) = __upt_val; break; \
- case EFLAGS: UPT_EFLAGS(regs) = __upt_val; break; \
- default : \
- panic("Bad register in UPT_SET : %d\n", reg); \
- break; \
- } \
- __upt_val; \
- })
-
-#define UPT_SET_SYSCALL_RETURN(r, res) \
- REGS_SET_SYSCALL_RETURN((r)->regs, (res))
-
-#define UPT_RESTART_SYSCALL(r) REGS_RESTART_SYSCALL((r)->gp)
-
-#define UPT_SEGV_IS_FIXABLE(r) REGS_SEGV_IS_FIXABLE(&r->skas)
-
-#define UPT_FAULTINFO(r) (&(r)->faultinfo)
-
-static inline void arch_init_registers(int pid)
-{
-}
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/ptrace_user.h b/arch/um/sys-x86_64/shared/sysdep/ptrace_user.h
deleted file mode 100644
index 4dbccdb..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/ptrace_user.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_X86_64_PTRACE_USER_H__
-#define __SYSDEP_X86_64_PTRACE_USER_H__
-
-#define __FRAME_OFFSETS
-#include <sys/ptrace.h>
-#include <linux/ptrace.h>
-#include <asm/ptrace.h>
-#undef __FRAME_OFFSETS
-#include "user_constants.h"
-
-#define PT_INDEX(off) ((off) / sizeof(unsigned long))
-
-#define PT_SYSCALL_NR(regs) ((regs)[PT_INDEX(ORIG_RAX)])
-#define PT_SYSCALL_NR_OFFSET (ORIG_RAX)
-
-#define PT_SYSCALL_ARG1(regs) (((unsigned long *) (regs))[PT_INDEX(RDI)])
-#define PT_SYSCALL_ARG1_OFFSET (RDI)
-
-#define PT_SYSCALL_ARG2(regs) (((unsigned long *) (regs))[PT_INDEX(RSI)])
-#define PT_SYSCALL_ARG2_OFFSET (RSI)
-
-#define PT_SYSCALL_ARG3(regs) (((unsigned long *) (regs))[PT_INDEX(RDX)])
-#define PT_SYSCALL_ARG3_OFFSET (RDX)
-
-#define PT_SYSCALL_ARG4(regs) (((unsigned long *) (regs))[PT_INDEX(RCX)])
-#define PT_SYSCALL_ARG4_OFFSET (RCX)
-
-#define PT_SYSCALL_ARG5(regs) (((unsigned long *) (regs))[PT_INDEX(R8)])
-#define PT_SYSCALL_ARG5_OFFSET (R8)
-
-#define PT_SYSCALL_ARG6(regs) (((unsigned long *) (regs))[PT_INDEX(R9)])
-#define PT_SYSCALL_ARG6_OFFSET (R9)
-
-#define PT_SYSCALL_RET_OFFSET (RAX)
-
-#define PT_IP_OFFSET (RIP)
-#define PT_IP(regs) ((regs)[PT_INDEX(RIP)])
-
-#define PT_SP_OFFSET (RSP)
-#define PT_SP(regs) ((regs)[PT_INDEX(RSP)])
-
-#define PT_ORIG_RAX_OFFSET (ORIG_RAX)
-#define PT_ORIG_RAX(regs) ((regs)[PT_INDEX(ORIG_RAX)])
-
-/*
- * x86_64 FC3 doesn't define this in /usr/include/linux/ptrace.h even though
- * it's defined in the kernel's include/linux/ptrace.h. Additionally, use the
- * 2.4 name and value for 2.4 host compatibility.
- */
-#ifndef PTRACE_OLDSETOPTIONS
-#define PTRACE_OLDSETOPTIONS 21
-#endif
-
-/*
- * These are before the system call, so the system call number is RAX
- * rather than ORIG_RAX, and arg4 is R10 rather than RCX
- */
-#define REGS_SYSCALL_NR PT_INDEX(RAX)
-#define REGS_SYSCALL_ARG1 PT_INDEX(RDI)
-#define REGS_SYSCALL_ARG2 PT_INDEX(RSI)
-#define REGS_SYSCALL_ARG3 PT_INDEX(RDX)
-#define REGS_SYSCALL_ARG4 PT_INDEX(R10)
-#define REGS_SYSCALL_ARG5 PT_INDEX(R8)
-#define REGS_SYSCALL_ARG6 PT_INDEX(R9)
-
-#define REGS_IP_INDEX PT_INDEX(RIP)
-#define REGS_SP_INDEX PT_INDEX(RSP)
-
-#define FP_SIZE (HOST_FP_SIZE)
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/sc.h b/arch/um/sys-x86_64/shared/sysdep/sc.h
deleted file mode 100644
index 8aee45b..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/sc.h
+++ /dev/null
@@ -1,45 +0,0 @@
-#ifndef __SYSDEP_X86_64_SC_H
-#define __SYSDEP_X86_64_SC_H
-
-/* Copyright (C) 2003 - 2004 PathScale, Inc
- * Released under the GPL
- */
-
-#include <user_constants.h>
-
-#define SC_OFFSET(sc, field) \
- *((unsigned long *) &(((char *) (sc))[HOST_##field]))
-
-#define SC_RBX(sc) SC_OFFSET(sc, SC_RBX)
-#define SC_RCX(sc) SC_OFFSET(sc, SC_RCX)
-#define SC_RDX(sc) SC_OFFSET(sc, SC_RDX)
-#define SC_RSI(sc) SC_OFFSET(sc, SC_RSI)
-#define SC_RDI(sc) SC_OFFSET(sc, SC_RDI)
-#define SC_RBP(sc) SC_OFFSET(sc, SC_RBP)
-#define SC_RAX(sc) SC_OFFSET(sc, SC_RAX)
-#define SC_R8(sc) SC_OFFSET(sc, SC_R8)
-#define SC_R9(sc) SC_OFFSET(sc, SC_R9)
-#define SC_R10(sc) SC_OFFSET(sc, SC_R10)
-#define SC_R11(sc) SC_OFFSET(sc, SC_R11)
-#define SC_R12(sc) SC_OFFSET(sc, SC_R12)
-#define SC_R13(sc) SC_OFFSET(sc, SC_R13)
-#define SC_R14(sc) SC_OFFSET(sc, SC_R14)
-#define SC_R15(sc) SC_OFFSET(sc, SC_R15)
-#define SC_IP(sc) SC_OFFSET(sc, SC_IP)
-#define SC_SP(sc) SC_OFFSET(sc, SC_SP)
-#define SC_CR2(sc) SC_OFFSET(sc, SC_CR2)
-#define SC_ERR(sc) SC_OFFSET(sc, SC_ERR)
-#define SC_TRAPNO(sc) SC_OFFSET(sc, SC_TRAPNO)
-#define SC_CS(sc) SC_OFFSET(sc, SC_CS)
-#define SC_FS(sc) SC_OFFSET(sc, SC_FS)
-#define SC_GS(sc) SC_OFFSET(sc, SC_GS)
-#define SC_EFLAGS(sc) SC_OFFSET(sc, SC_EFLAGS)
-#define SC_SIGMASK(sc) SC_OFFSET(sc, SC_SIGMASK)
-#define SC_SS(sc) SC_OFFSET(sc, SC_SS)
-#if 0
-#define SC_ORIG_RAX(sc) SC_OFFSET(sc, SC_ORIG_RAX)
-#define SC_DS(sc) SC_OFFSET(sc, SC_DS)
-#define SC_ES(sc) SC_OFFSET(sc, SC_ES)
-#endif
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/sigcontext.h b/arch/um/sys-x86_64/shared/sysdep/sigcontext.h
deleted file mode 100644
index 0155133..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/sigcontext.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_X86_64_SIGCONTEXT_H
-#define __SYSDEP_X86_64_SIGCONTEXT_H
-
-#include <sysdep/sc.h>
-
-#define IP_RESTART_SYSCALL(ip) ((ip) -= 2)
-
-#define GET_FAULTINFO_FROM_SC(fi, sc) \
- { \
- (fi).cr2 = SC_CR2(sc); \
- (fi).error_code = SC_ERR(sc); \
- (fi).trap_no = SC_TRAPNO(sc); \
- }
-
-/* This is Page Fault */
-#define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14)
-
-/* No broken SKAS API, which doesn't pass trap_no, here. */
-#define SEGV_MAYBE_FIXABLE(fi) 0
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/skas_ptrace.h b/arch/um/sys-x86_64/shared/sysdep/skas_ptrace.h
deleted file mode 100644
index 95db4be7..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/skas_ptrace.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_X86_64_SKAS_PTRACE_H
-#define __SYSDEP_X86_64_SKAS_PTRACE_H
-
-struct ptrace_faultinfo {
- int is_write;
- unsigned long addr;
-};
-
-struct ptrace_ldt {
- int func;
- void *ptr;
- unsigned long bytecount;
-};
-
-#define PTRACE_LDT 54
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/system.h b/arch/um/sys-x86_64/shared/sysdep/system.h
deleted file mode 100644
index d1b93c4..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/system.h
+++ /dev/null
@@ -1,132 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_H_
-#define _ASM_X86_SYSTEM_H_
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
-# define AT_VECTOR_SIZE_ARCH 2
-#else
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-void default_idle(void);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() asm volatile("mfence":::"memory")
-#define rmb() asm volatile("lfence":::"memory")
-#define wmb() asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier. All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads. This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies. See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- * CPU 0 CPU 1
- *
- * b = 2;
- * memory_barrier();
- * p = &b; q = p;
- * read_barrier_depends();
- * d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends(). However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- * CPU 0 CPU 1
- *
- * a = 2;
- * memory_barrier();
- * b = 3; y = b;
- * read_barrier_depends();
- * x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b". Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends() do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb() mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb() rmb()
-#else
-# define smp_rmb() barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() wmb()
-#else
-# define smp_wmb() barrier()
-#endif
-#define smp_read_barrier_depends() read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb() barrier()
-#define smp_rmb() barrier()
-#define smp_wmb() barrier()
-#define smp_read_barrier_depends() do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static inline void rdtsc_barrier(void)
-{
- alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
- alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/tls.h b/arch/um/sys-x86_64/shared/sysdep/tls.h
deleted file mode 100644
index 18c000d..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/tls.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef _SYSDEP_TLS_H
-#define _SYSDEP_TLS_H
-
-# ifndef __KERNEL__
-
-/* Change name to avoid conflicts with the original one from <asm/ldt.h>, which
- * may be named user_desc (but in 2.4 and in header matching its API was named
- * modify_ldt_ldt_s). */
-
-typedef struct um_dup_user_desc {
- unsigned int entry_number;
- unsigned int base_addr;
- unsigned int limit;
- unsigned int seg_32bit:1;
- unsigned int contents:2;
- unsigned int read_exec_only:1;
- unsigned int limit_in_pages:1;
- unsigned int seg_not_present:1;
- unsigned int useable:1;
- unsigned int lm:1;
-} user_desc_t;
-
-# else /* __KERNEL__ */
-
-# include <ldt.h>
-typedef struct user_desc user_desc_t;
-
-# endif /* __KERNEL__ */
-#endif /* _SYSDEP_TLS_H */
diff --git a/arch/um/sys-x86_64/shared/sysdep/vm-flags.h b/arch/um/sys-x86_64/shared/sysdep/vm-flags.h
deleted file mode 100644
index 3978e55..0000000
--- a/arch/um/sys-x86_64/shared/sysdep/vm-flags.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Copyright (C) 2004 Jeff Dike (jdike@addtoit.com)
- * Copyright 2003 PathScale, Inc.
- * Licensed under the GPL
- */
-
-#ifndef __VM_FLAGS_X86_64_H
-#define __VM_FLAGS_X86_64_H
-
-#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \
- VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-#define VM_STACK_DEFAULT_FLAGS (VM_GROWSDOWN | VM_READ | VM_WRITE | \
- VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-#endif
diff --git a/arch/um/sys-x86_64/signal.c b/arch/um/sys-x86_64/signal.c
deleted file mode 100644
index b6b65c7..0000000
--- a/arch/um/sys-x86_64/signal.c
+++ /dev/null
@@ -1,290 +0,0 @@
-/*
- * Copyright (C) 2003 PathScale, Inc.
- * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <linux/personality.h>
-#include <linux/ptrace.h>
-#include <linux/kernel.h>
-#include <asm/unistd.h>
-#include <asm/uaccess.h>
-#include <asm/ucontext.h>
-#include "frame_kern.h"
-#include "skas.h"
-
-void copy_sc(struct uml_pt_regs *regs, void *from)
-{
- struct sigcontext *sc = from;
-
-#define GETREG(regs, regno, sc, regname) \
- (regs)->gp[(regno) / sizeof(unsigned long)] = (sc)->regname
-
- GETREG(regs, R8, sc, r8);
- GETREG(regs, R9, sc, r9);
- GETREG(regs, R10, sc, r10);
- GETREG(regs, R11, sc, r11);
- GETREG(regs, R12, sc, r12);
- GETREG(regs, R13, sc, r13);
- GETREG(regs, R14, sc, r14);
- GETREG(regs, R15, sc, r15);
- GETREG(regs, RDI, sc, di);
- GETREG(regs, RSI, sc, si);
- GETREG(regs, RBP, sc, bp);
- GETREG(regs, RBX, sc, bx);
- GETREG(regs, RDX, sc, dx);
- GETREG(regs, RAX, sc, ax);
- GETREG(regs, RCX, sc, cx);
- GETREG(regs, RSP, sc, sp);
- GETREG(regs, RIP, sc, ip);
- GETREG(regs, EFLAGS, sc, flags);
- GETREG(regs, CS, sc, cs);
-
-#undef GETREG
-}
-
-static int copy_sc_from_user(struct pt_regs *regs,
- struct sigcontext __user *from,
- struct _fpstate __user *fpp)
-{
- struct user_i387_struct fp;
- int err = 0;
-
-#define GETREG(regs, regno, sc, regname) \
- __get_user((regs)->regs.gp[(regno) / sizeof(unsigned long)], \
- &(sc)->regname)
-
- err |= GETREG(regs, R8, from, r8);
- err |= GETREG(regs, R9, from, r9);
- err |= GETREG(regs, R10, from, r10);
- err |= GETREG(regs, R11, from, r11);
- err |= GETREG(regs, R12, from, r12);
- err |= GETREG(regs, R13, from, r13);
- err |= GETREG(regs, R14, from, r14);
- err |= GETREG(regs, R15, from, r15);
- err |= GETREG(regs, RDI, from, di);
- err |= GETREG(regs, RSI, from, si);
- err |= GETREG(regs, RBP, from, bp);
- err |= GETREG(regs, RBX, from, bx);
- err |= GETREG(regs, RDX, from, dx);
- err |= GETREG(regs, RAX, from, ax);
- err |= GETREG(regs, RCX, from, cx);
- err |= GETREG(regs, RSP, from, sp);
- err |= GETREG(regs, RIP, from, ip);
- err |= GETREG(regs, EFLAGS, from, flags);
- err |= GETREG(regs, CS, from, cs);
- if (err)
- return 1;
-
-#undef GETREG
-
- err = copy_from_user(&fp, fpp, sizeof(struct user_i387_struct));
- if (err)
- return 1;
-
- err = restore_fp_registers(userspace_pid[current_thread_info()->cpu],
- (unsigned long *) &fp);
- if (err < 0) {
- printk(KERN_ERR "copy_sc_from_user - "
- "restore_fp_registers failed, errno = %d\n",
- -err);
- return 1;
- }
-
- return 0;
-}
-
-static int copy_sc_to_user(struct sigcontext __user *to,
- struct _fpstate __user *to_fp, struct pt_regs *regs,
- unsigned long mask, unsigned long sp)
-{
- struct faultinfo * fi = ¤t->thread.arch.faultinfo;
- struct user_i387_struct fp;
- int err = 0;
-
- err |= __put_user(0, &to->gs);
- err |= __put_user(0, &to->fs);
-
-#define PUTREG(regs, regno, sc, regname) \
- __put_user((regs)->regs.gp[(regno) / sizeof(unsigned long)], \
- &(sc)->regname)
-
- err |= PUTREG(regs, RDI, to, di);
- err |= PUTREG(regs, RSI, to, si);
- err |= PUTREG(regs, RBP, to, bp);
- /*
- * Must use original RSP, which is passed in, rather than what's in
- * the pt_regs, because that's already been updated to point at the
- * signal frame.
- */
- err |= __put_user(sp, &to->sp);
- err |= PUTREG(regs, RBX, to, bx);
- err |= PUTREG(regs, RDX, to, dx);
- err |= PUTREG(regs, RCX, to, cx);
- err |= PUTREG(regs, RAX, to, ax);
- err |= PUTREG(regs, R8, to, r8);
- err |= PUTREG(regs, R9, to, r9);
- err |= PUTREG(regs, R10, to, r10);
- err |= PUTREG(regs, R11, to, r11);
- err |= PUTREG(regs, R12, to, r12);
- err |= PUTREG(regs, R13, to, r13);
- err |= PUTREG(regs, R14, to, r14);
- err |= PUTREG(regs, R15, to, r15);
- err |= PUTREG(regs, CS, to, cs); /* XXX x86_64 doesn't do this */
-
- err |= __put_user(fi->cr2, &to->cr2);
- err |= __put_user(fi->error_code, &to->err);
- err |= __put_user(fi->trap_no, &to->trapno);
-
- err |= PUTREG(regs, RIP, to, ip);
- err |= PUTREG(regs, EFLAGS, to, flags);
-#undef PUTREG
-
- err |= __put_user(mask, &to->oldmask);
- if (err)
- return 1;
-
- err = save_fp_registers(userspace_pid[current_thread_info()->cpu],
- (unsigned long *) &fp);
- if (err < 0) {
- printk(KERN_ERR "copy_sc_from_user - restore_fp_registers "
- "failed, errno = %d\n", -err);
- return 1;
- }
-
- if (copy_to_user(to_fp, &fp, sizeof(struct user_i387_struct)))
- return 1;
-
- return err;
-}
-
-struct rt_sigframe
-{
- char __user *pretcode;
- struct ucontext uc;
- struct siginfo info;
- struct _fpstate fpstate;
-};
-
-int setup_signal_stack_si(unsigned long stack_top, int sig,
- struct k_sigaction *ka, struct pt_regs * regs,
- siginfo_t *info, sigset_t *set)
-{
- struct rt_sigframe __user *frame;
- unsigned long save_sp = PT_REGS_RSP(regs);
- int err = 0;
- struct task_struct *me = current;
-
- frame = (struct rt_sigframe __user *)
- round_down(stack_top - sizeof(struct rt_sigframe), 16);
- /* Subtract 128 for a red zone and 8 for proper alignment */
- frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8);
-
- if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
- goto out;
-
- if (ka->sa.sa_flags & SA_SIGINFO) {
- err |= copy_siginfo_to_user(&frame->info, info);
- if (err)
- goto out;
- }
-
- /*
- * Update SP now because the page fault handler refuses to extend
- * the stack if the faulting address is too far below the current
- * SP, which frame now certainly is. If there's an error, the original
- * value is restored on the way out.
- * When writing the sigcontext to the stack, we have to write the
- * original value, so that's passed to copy_sc_to_user, which does
- * the right thing with it.
- */
- PT_REGS_RSP(regs) = (unsigned long) frame;
-
- /* Create the ucontext. */
- err |= __put_user(0, &frame->uc.uc_flags);
- err |= __put_user(0, &frame->uc.uc_link);
- err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- err |= __put_user(sas_ss_flags(save_sp),
- &frame->uc.uc_stack.ss_flags);
- err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs,
- set->sig[0], save_sp);
- err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate);
- if (sizeof(*set) == 16) {
- __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
- __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
- }
- else
- err |= __copy_to_user(&frame->uc.uc_sigmask, set,
- sizeof(*set));
-
- /*
- * Set up to return from userspace. If provided, use a stub
- * already in userspace.
- */
- /* x86-64 should always use SA_RESTORER. */
- if (ka->sa.sa_flags & SA_RESTORER)
- err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
- else
- /* could use a vstub here */
- goto restore_sp;
-
- if (err)
- goto restore_sp;
-
- /* Set up registers for signal handler */
- {
- struct exec_domain *ed = current_thread_info()->exec_domain;
- if (unlikely(ed && ed->signal_invmap && sig < 32))
- sig = ed->signal_invmap[sig];
- }
-
- PT_REGS_RDI(regs) = sig;
- /* In case the signal handler was declared without prototypes */
- PT_REGS_RAX(regs) = 0;
-
- /*
- * This also works for non SA_SIGINFO handlers because they expect the
- * next argument after the signal number on the stack.
- */
- PT_REGS_RSI(regs) = (unsigned long) &frame->info;
- PT_REGS_RDX(regs) = (unsigned long) &frame->uc;
- PT_REGS_RIP(regs) = (unsigned long) ka->sa.sa_handler;
- out:
- return err;
-
-restore_sp:
- PT_REGS_RSP(regs) = save_sp;
- return err;
-}
-
-long sys_rt_sigreturn(struct pt_regs *regs)
-{
- unsigned long sp = PT_REGS_SP(¤t->thread.regs);
- struct rt_sigframe __user *frame =
- (struct rt_sigframe __user *)(sp - 8);
- struct ucontext __user *uc = &frame->uc;
- sigset_t set;
-
- if (copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
- goto segfault;
-
- sigdelsetmask(&set, ~_BLOCKABLE);
-
- spin_lock_irq(¤t->sighand->siglock);
- current->blocked = set;
- recalc_sigpending();
- spin_unlock_irq(¤t->sighand->siglock);
-
- if (copy_sc_from_user(¤t->thread.regs, &uc->uc_mcontext,
- &frame->fpstate))
- goto segfault;
-
- /* Avoid ERESTART handling */
- PT_REGS_SYSCALL_NR(¤t->thread.regs) = -1;
- return PT_REGS_SYSCALL_RET(¤t->thread.regs);
-
- segfault:
- force_sig(SIGSEGV, current);
- return 0;
-}
diff --git a/arch/um/sys-x86_64/stub_segv.c b/arch/um/sys-x86_64/stub_segv.c
deleted file mode 100644
index ced051a..0000000
--- a/arch/um/sys-x86_64/stub_segv.c
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright (C) 2004 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <signal.h>
-#include "as-layout.h"
-#include "sysdep/stub.h"
-#include "sysdep/faultinfo.h"
-#include "sysdep/sigcontext.h"
-
-void __attribute__ ((__section__ (".__syscall_stub")))
-stub_segv_handler(int sig)
-{
- struct ucontext *uc;
-
- __asm__ __volatile__("movq %%rdx, %0" : "=g" (uc) :);
- GET_FAULTINFO_FROM_SC(*((struct faultinfo *) STUB_DATA),
- &uc->uc_mcontext);
- trap_myself();
-}
-
diff --git a/arch/um/sys-x86_64/user-offsets.c b/arch/um/sys-x86_64/user-offsets.c
deleted file mode 100644
index 9735854..0000000
--- a/arch/um/sys-x86_64/user-offsets.c
+++ /dev/null
@@ -1,65 +0,0 @@
-#include <stdio.h>
-#include <stddef.h>
-#include <signal.h>
-#include <sys/poll.h>
-#include <sys/mman.h>
-#include <sys/user.h>
-#define __FRAME_OFFSETS
-#include <asm/ptrace.h>
-#include <asm/types.h>
-
-#define DEFINE(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define DEFINE_LONGS(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long)))
-
-#define OFFSET(sym, str, mem) \
- DEFINE(sym, offsetof(struct str, mem));
-
-void foo(void)
-{
- OFFSET(HOST_SC_CR2, sigcontext, cr2);
- OFFSET(HOST_SC_ERR, sigcontext, err);
- OFFSET(HOST_SC_TRAPNO, sigcontext, trapno);
-
- DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long));
- DEFINE_LONGS(HOST_RBX, RBX);
- DEFINE_LONGS(HOST_RCX, RCX);
- DEFINE_LONGS(HOST_RDI, RDI);
- DEFINE_LONGS(HOST_RSI, RSI);
- DEFINE_LONGS(HOST_RDX, RDX);
- DEFINE_LONGS(HOST_RBP, RBP);
- DEFINE_LONGS(HOST_RAX, RAX);
- DEFINE_LONGS(HOST_R8, R8);
- DEFINE_LONGS(HOST_R9, R9);
- DEFINE_LONGS(HOST_R10, R10);
- DEFINE_LONGS(HOST_R11, R11);
- DEFINE_LONGS(HOST_R12, R12);
- DEFINE_LONGS(HOST_R13, R13);
- DEFINE_LONGS(HOST_R14, R14);
- DEFINE_LONGS(HOST_R15, R15);
- DEFINE_LONGS(HOST_ORIG_RAX, ORIG_RAX);
- DEFINE_LONGS(HOST_CS, CS);
- DEFINE_LONGS(HOST_SS, SS);
- DEFINE_LONGS(HOST_EFLAGS, EFLAGS);
-#if 0
- DEFINE_LONGS(HOST_FS, FS);
- DEFINE_LONGS(HOST_GS, GS);
- DEFINE_LONGS(HOST_DS, DS);
- DEFINE_LONGS(HOST_ES, ES);
-#endif
-
- DEFINE_LONGS(HOST_IP, RIP);
- DEFINE_LONGS(HOST_SP, RSP);
- DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct));
-
- /* XXX Duplicated between i386 and x86_64 */
- DEFINE(UM_POLLIN, POLLIN);
- DEFINE(UM_POLLPRI, POLLPRI);
- DEFINE(UM_POLLOUT, POLLOUT);
-
- DEFINE(UM_PROT_READ, PROT_READ);
- DEFINE(UM_PROT_WRITE, PROT_WRITE);
- DEFINE(UM_PROT_EXEC, PROT_EXEC);
-}
diff --git a/arch/um/Makefile-i386 b/arch/x86/Makefile.um
similarity index 64%
rename from arch/um/Makefile-i386
rename to arch/x86/Makefile.um
index 302cbe5..36ddec6 100644
--- a/arch/um/Makefile-i386
+++ b/arch/x86/Makefile.um
@@ -1,14 +1,11 @@
-core-y += arch/um/sys-i386/ arch/x86/crypto/
+core-y += arch/x86/crypto/
-TOP_ADDR := $(CONFIG_TOP_ADDR)
-
+ifeq ($(CONFIG_X86_32),y)
START := 0x8048000
LDFLAGS += -m elf_i386
-ELF_ARCH := $(SUBARCH)
-ELF_FORMAT := elf32-$(SUBARCH)
-OBJCOPYFLAGS := -O binary -R .note -R .comment -S
-HEADER_ARCH := x86
+ELF_ARCH := i386
+ELF_FORMAT := elf32-i386
CHECKFLAGS += -D__i386__
ifeq ("$(origin SUBARCH)", "command line")
@@ -16,9 +13,8 @@
KBUILD_CFLAGS += $(call cc-option,-m32)
KBUILD_AFLAGS += $(call cc-option,-m32)
LINK-y += $(call cc-option,-m32)
-UML_OBJCOPYFLAGS += -F $(ELF_FORMAT)
-export LDFLAGS HOSTCFLAGS HOSTLDFLAGS UML_OBJCOPYFLAGS
+export LDFLAGS
endif
endif
@@ -40,3 +36,26 @@
else echo $(call cc-option,-funit-at-a-time); fi ;)
KBUILD_CFLAGS += $(cflags-y)
+
+else
+
+START := 0x60000000
+
+KBUILD_CFLAGS += -fno-builtin -m64
+
+CHECKFLAGS += -m64 -D__x86_64__
+KBUILD_AFLAGS += -m64
+LDFLAGS += -m elf_x86_64
+KBUILD_CPPFLAGS += -m64
+
+ELF_ARCH := i386:x86-64
+ELF_FORMAT := elf64-x86-64
+
+# Not on all 64-bit distros /lib is a symlink to /lib64. PLD is an example.
+
+LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib64
+LINK-y += -m64
+
+# Do unit-at-a-time unconditionally on x86_64, following the host
+KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
+endif
diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h
index 29f6679..4420993 100644
--- a/arch/x86/include/asm/intel_scu_ipc.h
+++ b/arch/x86/include/asm/intel_scu_ipc.h
@@ -1,6 +1,8 @@
#ifndef _ASM_X86_INTEL_SCU_IPC_H_
#define _ASM_X86_INTEL_SCU_IPC_H_
+#include <linux/notifier.h>
+
#define IPCMSG_VRTC 0xFA /* Set vRTC device */
/* Command id associated with message IPCMSG_VRTC */
@@ -44,4 +46,24 @@
/* Update FW version */
int intel_scu_ipc_fw_update(u8 *buffer, u32 length);
+extern struct blocking_notifier_head intel_scu_notifier;
+
+static inline void intel_scu_notifier_add(struct notifier_block *nb)
+{
+ blocking_notifier_chain_register(&intel_scu_notifier, nb);
+}
+
+static inline void intel_scu_notifier_remove(struct notifier_block *nb)
+{
+ blocking_notifier_chain_unregister(&intel_scu_notifier, nb);
+}
+
+static inline int intel_scu_notifier_post(unsigned long v, void *p)
+{
+ return blocking_notifier_call_chain(&intel_scu_notifier, v, p);
+}
+
+#define SCU_AVAILABLE 1
+#define SCU_DOWN 2
+
#endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7b5063a..864830e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -36,7 +36,6 @@
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/debugfs.h>
-#include <linux/edac_mce.h>
#include <linux/irq_work.h>
#include <asm/processor.h>
@@ -144,23 +143,20 @@
void mce_log(struct mce *mce)
{
unsigned next, entry;
+ int ret = 0;
/* Emit the trace record: */
trace_mce_record(mce);
+ ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+ if (ret == NOTIFY_STOP)
+ return;
+
mce->finished = 0;
wmb();
for (;;) {
entry = rcu_dereference_check_mce(mcelog.next);
for (;;) {
- /*
- * If edac_mce is enabled, it will check the error type
- * and will process it, if it is a known error.
- * Otherwise, the error will be sent through mcelog
- * interface
- */
- if (edac_mce_parse(mce))
- return;
/*
* When the buffer fills up discard new entries.
@@ -556,10 +552,8 @@
* Don't get the IP here because it's unlikely to
* have anything to do with the actual error location.
*/
- if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
+ if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce)
mce_log(&m);
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
- }
/*
* Clear state for this bank.
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dbe34b9..ea30585 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -108,16 +108,6 @@
SetPageReferenced(page);
}
-static inline void get_huge_page_tail(struct page *page)
-{
- /*
- * __split_huge_page_refcount() cannot run
- * from under us.
- */
- VM_BUG_ON(atomic_read(&page->_count) < 0);
- atomic_inc(&page->_count);
-}
-
static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index e637952..6ed7afd 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -26,6 +26,8 @@
#include <linux/platform_device.h>
#include <linux/irq.h>
#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/mfd/intel_msic.h>
#include <asm/setup.h>
#include <asm/mpspec_def.h>
@@ -483,6 +485,128 @@
return NULL;
}
+static struct resource msic_resources[] = {
+ {
+ .start = INTEL_MSIC_IRQ_PHYS_BASE,
+ .end = INTEL_MSIC_IRQ_PHYS_BASE + 64 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct intel_msic_platform_data msic_pdata;
+
+static struct platform_device msic_device = {
+ .name = "intel_msic",
+ .id = -1,
+ .dev = {
+ .platform_data = &msic_pdata,
+ },
+ .num_resources = ARRAY_SIZE(msic_resources),
+ .resource = msic_resources,
+};
+
+static inline bool mrst_has_msic(void)
+{
+ return mrst_identify_cpu() == MRST_CPU_CHIP_PENWELL;
+}
+
+static int msic_scu_status_change(struct notifier_block *nb,
+ unsigned long code, void *data)
+{
+ if (code == SCU_DOWN) {
+ platform_device_unregister(&msic_device);
+ return 0;
+ }
+
+ return platform_device_register(&msic_device);
+}
+
+static int __init msic_init(void)
+{
+ static struct notifier_block msic_scu_notifier = {
+ .notifier_call = msic_scu_status_change,
+ };
+
+ /*
+ * We need to be sure that the SCU IPC is ready before MSIC device
+ * can be registered.
+ */
+ if (mrst_has_msic())
+ intel_scu_notifier_add(&msic_scu_notifier);
+
+ return 0;
+}
+arch_initcall(msic_init);
+
+/*
+ * msic_generic_platform_data - sets generic platform data for the block
+ * @info: pointer to the SFI device table entry for this block
+ * @block: MSIC block
+ *
+ * Function sets IRQ number from the SFI table entry for given device to
+ * the MSIC platform data.
+ */
+static void *msic_generic_platform_data(void *info, enum intel_msic_block block)
+{
+ struct sfi_device_table_entry *entry = info;
+
+ BUG_ON(block < 0 || block >= INTEL_MSIC_BLOCK_LAST);
+ msic_pdata.irq[block] = entry->irq;
+
+ return no_platform_data(info);
+}
+
+static void *msic_battery_platform_data(void *info)
+{
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_BATTERY);
+}
+
+static void *msic_gpio_platform_data(void *info)
+{
+ static struct intel_msic_gpio_pdata pdata;
+ int gpio = get_gpio_by_name("msic_gpio_base");
+
+ if (gpio < 0)
+ return NULL;
+
+ pdata.gpio_base = gpio;
+ msic_pdata.gpio = &pdata;
+
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_GPIO);
+}
+
+static void *msic_audio_platform_data(void *info)
+{
+ struct platform_device *pdev;
+
+ pdev = platform_device_register_simple("sst-platform", -1, NULL, 0);
+ if (IS_ERR(pdev)) {
+ pr_err("failed to create audio platform device\n");
+ return NULL;
+ }
+
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_AUDIO);
+}
+
+static void *msic_power_btn_platform_data(void *info)
+{
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_POWER_BTN);
+}
+
+static void *msic_ocd_platform_data(void *info)
+{
+ static struct intel_msic_ocd_pdata pdata;
+ int gpio = get_gpio_by_name("ocd_gpio");
+
+ if (gpio < 0)
+ return NULL;
+
+ pdata.gpio = gpio;
+ msic_pdata.ocd = &pdata;
+
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_OCD);
+}
+
static const struct devs_id __initconst device_ids[] = {
{"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data},
{"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data},
@@ -491,7 +615,14 @@
{"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data},
{"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data},
{"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
- {"msic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
+
+ /* MSIC subdevices */
+ {"msic_battery", SFI_DEV_TYPE_IPC, 1, &msic_battery_platform_data},
+ {"msic_gpio", SFI_DEV_TYPE_IPC, 1, &msic_gpio_platform_data},
+ {"msic_audio", SFI_DEV_TYPE_IPC, 1, &msic_audio_platform_data},
+ {"msic_power_btn", SFI_DEV_TYPE_IPC, 1, &msic_power_btn_platform_data},
+ {"msic_ocd", SFI_DEV_TYPE_IPC, 1, &msic_ocd_platform_data},
+
{},
};
@@ -558,6 +689,9 @@
i2c_devs[i2c_next_dev++] = new_dev;
}
+BLOCKING_NOTIFIER_HEAD(intel_scu_notifier);
+EXPORT_SYMBOL_GPL(intel_scu_notifier);
+
/* Called by IPC driver */
void intel_scu_devices_create(void)
{
@@ -582,6 +716,7 @@
} else
i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1);
}
+ intel_scu_notifier_post(SCU_AVAILABLE, 0L);
}
EXPORT_SYMBOL_GPL(intel_scu_devices_create);
@@ -590,6 +725,8 @@
{
int i;
+ intel_scu_notifier_post(SCU_DOWN, 0L);
+
for (i = 0; i < ipc_next_dev; i++)
platform_device_del(ipc_devs[i]);
}
@@ -606,19 +743,37 @@
platform_device_add_resources(pdev, &res, 1);
}
-static void __init sfi_handle_ipc_dev(struct platform_device *pdev)
+static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *entry)
{
const struct devs_id *dev = device_ids;
+ struct platform_device *pdev;
void *pdata = NULL;
while (dev->name[0]) {
if (dev->type == SFI_DEV_TYPE_IPC &&
- !strncmp(dev->name, pdev->name, SFI_NAME_LEN)) {
- pdata = dev->get_platform_data(pdev);
+ !strncmp(dev->name, entry->name, SFI_NAME_LEN)) {
+ pdata = dev->get_platform_data(entry);
break;
}
dev++;
}
+
+ /*
+ * On Medfield the platform device creation is handled by the MSIC
+ * MFD driver so we don't need to do it here.
+ */
+ if (mrst_has_msic())
+ return;
+
+ /* ID as IRQ is a hack that will go away */
+ pdev = platform_device_alloc(entry->name, entry->irq);
+ if (pdev == NULL) {
+ pr_err("out of memory for SFI platform device '%s'.\n",
+ entry->name);
+ return;
+ }
+ install_irq_resource(pdev, entry->irq);
+
pdev->dev.platform_data = pdata;
intel_scu_device_register(pdev);
}
@@ -671,7 +826,6 @@
struct sfi_device_table_entry *pentry;
struct spi_board_info spi_info;
struct i2c_board_info i2c_info;
- struct platform_device *pdev;
int num, i, bus;
int ioapic;
struct io_apic_irq_attr irq_attr;
@@ -699,17 +853,9 @@
switch (pentry->type) {
case SFI_DEV_TYPE_IPC:
- /* ID as IRQ is a hack that will go away */
- pdev = platform_device_alloc(pentry->name, irq);
- if (pdev == NULL) {
- pr_err("out of memory for SFI platform device '%s'.\n",
- pentry->name);
- continue;
- }
- install_irq_resource(pdev, irq);
pr_debug("info[%2d]: IPC bus, name = %16.16s, "
- "irq = 0x%2x\n", i, pentry->name, irq);
- sfi_handle_ipc_dev(pdev);
+ "irq = 0x%2x\n", i, pentry->name, pentry->irq);
+ sfi_handle_ipc_dev(pentry);
break;
case SFI_DEV_TYPE_SPI:
memset(&spi_info, 0, sizeof(spi_info));
diff --git a/arch/um/Kconfig.x86 b/arch/x86/um/Kconfig
similarity index 100%
rename from arch/um/Kconfig.x86
rename to arch/x86/um/Kconfig
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
new file mode 100644
index 0000000..8fb5840
--- /dev/null
+++ b/arch/x86/um/Makefile
@@ -0,0 +1,45 @@
+#
+# Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+#
+
+ifeq ($(CONFIG_X86_32),y)
+ BITS := 32
+else
+ BITS := 64
+endif
+
+obj-y = bug.o bugs_$(BITS).o delay.o fault.o ksyms.o ldt.o \
+ ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \
+ stub_$(BITS).o stub_segv.o syscalls_$(BITS).o \
+ sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \
+ mem_$(BITS).o subarch.o os-$(OS)/
+
+ifeq ($(CONFIG_X86_32),y)
+
+obj-y += checksum_32.o
+obj-$(CONFIG_BINFMT_ELF) += elfcore.o
+
+subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
+subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o
+subarch-$(CONFIG_HIGHMEM) += ../mm/highmem_32.o
+
+else
+
+obj-y += vdso/
+
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../lib/thunk_64.o \
+ ../lib/rwsem.o
+
+endif
+
+subarch-$(CONFIG_MODULES) += ../kernel/module.o
+
+USER_OBJS := bugs_$(BITS).o ptrace_user.o fault.o
+
+extra-y += user-offsets.s
+$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS)
+
+UNPROFILE_OBJS := stub_segv.o
+CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING)
+
+include arch/um/scripts/Makefile.rules
diff --git a/arch/um/include/asm/apic.h b/arch/x86/um/asm/apic.h
similarity index 100%
rename from arch/um/include/asm/apic.h
rename to arch/x86/um/asm/apic.h
diff --git a/arch/um/include/asm/arch_hweight.h b/arch/x86/um/asm/arch_hweight.h
similarity index 100%
rename from arch/um/include/asm/arch_hweight.h
rename to arch/x86/um/asm/arch_hweight.h
diff --git a/arch/um/sys-i386/asm/archparam.h b/arch/x86/um/asm/archparam.h
similarity index 62%
rename from arch/um/sys-i386/asm/archparam.h
rename to arch/x86/um/asm/archparam.h
index 2a18a88..c17cf68 100644
--- a/arch/um/sys-i386/asm/archparam.h
+++ b/arch/x86/um/asm/archparam.h
@@ -1,10 +1,13 @@
/*
* Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com)
+ * Copyright 2003 PathScale, Inc.
* Licensed under the GPL
*/
-#ifndef __UM_ARCHPARAM_I386_H
-#define __UM_ARCHPARAM_I386_H
+#ifndef __UM_ARCHPARAM_H
+#define __UM_ARCHPARAM_H
+
+#ifdef CONFIG_X86_32
#ifdef CONFIG_X86_PAE
#define LAST_PKMAP 512
@@ -14,3 +17,4 @@
#endif
+#endif
diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h
new file mode 100644
index 0000000..b6efe23
--- /dev/null
+++ b/arch/x86/um/asm/checksum.h
@@ -0,0 +1,10 @@
+#ifndef __UM_CHECKSUM_H
+#define __UM_CHECKSUM_H
+
+#ifdef CONFIG_X86_32
+# include "checksum_32.h"
+#else
+# include "checksum_64.h"
+#endif
+
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/checksum.h b/arch/x86/um/asm/checksum_32.h
similarity index 99%
rename from arch/um/sys-i386/shared/sysdep/checksum.h
rename to arch/x86/um/asm/checksum_32.h
index ed47445..caab742 100644
--- a/arch/um/sys-i386/shared/sysdep/checksum.h
+++ b/arch/x86/um/asm/checksum_32.h
@@ -1,4 +1,4 @@
-/*
+/*
* Licensed under the GPL
*/
diff --git a/arch/um/sys-x86_64/shared/sysdep/checksum.h b/arch/x86/um/asm/checksum_64.h
similarity index 100%
rename from arch/um/sys-x86_64/shared/sysdep/checksum.h
rename to arch/x86/um/asm/checksum_64.h
diff --git a/arch/um/include/asm/desc.h b/arch/x86/um/asm/desc.h
similarity index 100%
rename from arch/um/include/asm/desc.h
rename to arch/x86/um/asm/desc.h
diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h
new file mode 100644
index 0000000..f3b0633
--- /dev/null
+++ b/arch/x86/um/asm/elf.h
@@ -0,0 +1,221 @@
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+#ifndef __UM_ELF_X86_H
+#define __UM_ELF_X86_H
+
+#include <asm/user.h>
+#include "skas.h"
+
+#ifdef CONFIG_X86_32
+
+#define R_386_NONE 0
+#define R_386_32 1
+#define R_386_PC32 2
+#define R_386_GOT32 3
+#define R_386_PLT32 4
+#define R_386_COPY 5
+#define R_386_GLOB_DAT 6
+#define R_386_JMP_SLOT 7
+#define R_386_RELATIVE 8
+#define R_386_GOTOFF 9
+#define R_386_GOTPC 10
+#define R_386_NUM 11
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) \
+ (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
+
+#define ELF_CLASS ELFCLASS32
+#define ELF_DATA ELFDATA2LSB
+#define ELF_ARCH EM_386
+
+#define ELF_PLAT_INIT(regs, load_addr) do { \
+ PT_REGS_EBX(regs) = 0; \
+ PT_REGS_ECX(regs) = 0; \
+ PT_REGS_EDX(regs) = 0; \
+ PT_REGS_ESI(regs) = 0; \
+ PT_REGS_EDI(regs) = 0; \
+ PT_REGS_EBP(regs) = 0; \
+ PT_REGS_EAX(regs) = 0; \
+} while (0)
+
+/* Shamelessly stolen from include/asm-i386/elf.h */
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs) do { \
+ pr_reg[0] = PT_REGS_EBX(regs); \
+ pr_reg[1] = PT_REGS_ECX(regs); \
+ pr_reg[2] = PT_REGS_EDX(regs); \
+ pr_reg[3] = PT_REGS_ESI(regs); \
+ pr_reg[4] = PT_REGS_EDI(regs); \
+ pr_reg[5] = PT_REGS_EBP(regs); \
+ pr_reg[6] = PT_REGS_EAX(regs); \
+ pr_reg[7] = PT_REGS_DS(regs); \
+ pr_reg[8] = PT_REGS_ES(regs); \
+ /* fake once used fs and gs selectors? */ \
+ pr_reg[9] = PT_REGS_DS(regs); \
+ pr_reg[10] = PT_REGS_DS(regs); \
+ pr_reg[11] = PT_REGS_SYSCALL_NR(regs); \
+ pr_reg[12] = PT_REGS_IP(regs); \
+ pr_reg[13] = PT_REGS_CS(regs); \
+ pr_reg[14] = PT_REGS_EFLAGS(regs); \
+ pr_reg[15] = PT_REGS_SP(regs); \
+ pr_reg[16] = PT_REGS_SS(regs); \
+} while (0);
+
+extern char * elf_aux_platform;
+#define ELF_PLATFORM (elf_aux_platform)
+
+extern unsigned long vsyscall_ehdr;
+extern unsigned long vsyscall_end;
+extern unsigned long __kernel_vsyscall;
+
+/*
+ * This is the range that is readable by user mode, and things
+ * acting like user mode such as get_user_pages.
+ */
+#define FIXADDR_USER_START vsyscall_ehdr
+#define FIXADDR_USER_END vsyscall_end
+
+
+/*
+ * Architecture-neutral AT_ values in 0-17, leave some room
+ * for more of them, start the x86-specific ones at 32.
+ */
+#define AT_SYSINFO 32
+#define AT_SYSINFO_EHDR 33
+
+#define ARCH_DLINFO \
+do { \
+ if ( vsyscall_ehdr ) { \
+ NEW_AUX_ENT(AT_SYSINFO, __kernel_vsyscall); \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, vsyscall_ehdr); \
+ } \
+} while (0)
+
+#else
+
+/* x86-64 relocation types, taken from asm-x86_64/elf.h */
+#define R_X86_64_NONE 0 /* No reloc */
+#define R_X86_64_64 1 /* Direct 64 bit */
+#define R_X86_64_PC32 2 /* PC relative 32 bit signed */
+#define R_X86_64_GOT32 3 /* 32 bit GOT entry */
+#define R_X86_64_PLT32 4 /* 32 bit PLT address */
+#define R_X86_64_COPY 5 /* Copy symbol at runtime */
+#define R_X86_64_GLOB_DAT 6 /* Create GOT entry */
+#define R_X86_64_JUMP_SLOT 7 /* Create PLT entry */
+#define R_X86_64_RELATIVE 8 /* Adjust by program base */
+#define R_X86_64_GOTPCREL 9 /* 32 bit signed pc relative
+ offset to GOT */
+#define R_X86_64_32 10 /* Direct 32 bit zero extended */
+#define R_X86_64_32S 11 /* Direct 32 bit sign extended */
+#define R_X86_64_16 12 /* Direct 16 bit zero extended */
+#define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */
+#define R_X86_64_8 14 /* Direct 8 bit sign extended */
+#define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */
+
+#define R_X86_64_NUM 16
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) \
+ ((x)->e_machine == EM_X86_64)
+
+#define ELF_CLASS ELFCLASS64
+#define ELF_DATA ELFDATA2LSB
+#define ELF_ARCH EM_X86_64
+
+#define ELF_PLAT_INIT(regs, load_addr) do { \
+ PT_REGS_RBX(regs) = 0; \
+ PT_REGS_RCX(regs) = 0; \
+ PT_REGS_RDX(regs) = 0; \
+ PT_REGS_RSI(regs) = 0; \
+ PT_REGS_RDI(regs) = 0; \
+ PT_REGS_RBP(regs) = 0; \
+ PT_REGS_RAX(regs) = 0; \
+ PT_REGS_R8(regs) = 0; \
+ PT_REGS_R9(regs) = 0; \
+ PT_REGS_R10(regs) = 0; \
+ PT_REGS_R11(regs) = 0; \
+ PT_REGS_R12(regs) = 0; \
+ PT_REGS_R13(regs) = 0; \
+ PT_REGS_R14(regs) = 0; \
+ PT_REGS_R15(regs) = 0; \
+} while (0)
+
+#define ELF_CORE_COPY_REGS(pr_reg, _regs) \
+ (pr_reg)[0] = (_regs)->regs.gp[0]; \
+ (pr_reg)[1] = (_regs)->regs.gp[1]; \
+ (pr_reg)[2] = (_regs)->regs.gp[2]; \
+ (pr_reg)[3] = (_regs)->regs.gp[3]; \
+ (pr_reg)[4] = (_regs)->regs.gp[4]; \
+ (pr_reg)[5] = (_regs)->regs.gp[5]; \
+ (pr_reg)[6] = (_regs)->regs.gp[6]; \
+ (pr_reg)[7] = (_regs)->regs.gp[7]; \
+ (pr_reg)[8] = (_regs)->regs.gp[8]; \
+ (pr_reg)[9] = (_regs)->regs.gp[9]; \
+ (pr_reg)[10] = (_regs)->regs.gp[10]; \
+ (pr_reg)[11] = (_regs)->regs.gp[11]; \
+ (pr_reg)[12] = (_regs)->regs.gp[12]; \
+ (pr_reg)[13] = (_regs)->regs.gp[13]; \
+ (pr_reg)[14] = (_regs)->regs.gp[14]; \
+ (pr_reg)[15] = (_regs)->regs.gp[15]; \
+ (pr_reg)[16] = (_regs)->regs.gp[16]; \
+ (pr_reg)[17] = (_regs)->regs.gp[17]; \
+ (pr_reg)[18] = (_regs)->regs.gp[18]; \
+ (pr_reg)[19] = (_regs)->regs.gp[19]; \
+ (pr_reg)[20] = (_regs)->regs.gp[20]; \
+ (pr_reg)[21] = current->thread.arch.fs; \
+ (pr_reg)[22] = 0; \
+ (pr_reg)[23] = 0; \
+ (pr_reg)[24] = 0; \
+ (pr_reg)[25] = 0; \
+ (pr_reg)[26] = 0;
+
+#define ELF_PLATFORM "x86_64"
+
+/* No user-accessible fixmap addresses, i.e. vsyscall */
+#define FIXADDR_USER_START 0
+#define FIXADDR_USER_END 0
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp);
+
+extern unsigned long um_vdso_addr;
+#define AT_SYSINFO_EHDR 33
+#define ARCH_DLINFO NEW_AUX_ENT(AT_SYSINFO_EHDR, um_vdso_addr)
+
+#endif
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_i387_struct elf_fpregset_t;
+
+#define task_pt_regs(t) (&(t)->thread.regs)
+
+struct task_struct;
+
+extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
+
+#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
+
+#define ELF_EXEC_PAGESIZE 4096
+
+#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
+
+extern long elf_aux_hwcap;
+#define ELF_HWCAP (elf_aux_hwcap)
+
+#define SET_PERSONALITY(ex) do ; while(0)
+#define __HAVE_ARCH_GATE_AREA 1
+
+#endif
diff --git a/arch/um/include/asm/irq_vectors.h b/arch/x86/um/asm/irq_vectors.h
similarity index 100%
rename from arch/um/include/asm/irq_vectors.h
rename to arch/x86/um/asm/irq_vectors.h
diff --git a/arch/x86/um/asm/mm_context.h b/arch/x86/um/asm/mm_context.h
new file mode 100644
index 0000000..4a73d63
--- /dev/null
+++ b/arch/x86/um/asm/mm_context.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2004 Fujitsu Siemens Computers GmbH
+ * Licensed under the GPL
+ *
+ * Author: Bodo Stroesser <bstroesser@fujitsu-siemens.com>
+ */
+
+#ifndef __ASM_LDT_H
+#define __ASM_LDT_H
+
+#include <linux/mutex.h>
+#include <asm/ldt.h>
+
+extern void ldt_host_info(void);
+
+#define LDT_PAGES_MAX \
+ ((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE)
+#define LDT_ENTRIES_PER_PAGE \
+ (PAGE_SIZE/LDT_ENTRY_SIZE)
+#define LDT_DIRECT_ENTRIES \
+ ((LDT_PAGES_MAX*sizeof(void *))/LDT_ENTRY_SIZE)
+
+struct ldt_entry {
+ __u32 a;
+ __u32 b;
+};
+
+typedef struct uml_ldt {
+ int entry_count;
+ struct mutex lock;
+ union {
+ struct ldt_entry * pages[LDT_PAGES_MAX];
+ struct ldt_entry entries[LDT_DIRECT_ENTRIES];
+ } u;
+} uml_ldt_t;
+
+#define LDT_entry_a(info) \
+ ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
+
+#define LDT_entry_b(info) \
+ (((info)->base_addr & 0xff000000) | \
+ (((info)->base_addr & 0x00ff0000) >> 16) | \
+ ((info)->limit & 0xf0000) | \
+ (((info)->read_exec_only ^ 1) << 9) | \
+ ((info)->contents << 10) | \
+ (((info)->seg_not_present ^ 1) << 15) | \
+ ((info)->seg_32bit << 22) | \
+ ((info)->limit_in_pages << 23) | \
+ ((info)->useable << 20) | \
+ 0x7000)
+
+#define _LDT_empty(info) (\
+ (info)->base_addr == 0 && \
+ (info)->limit == 0 && \
+ (info)->contents == 0 && \
+ (info)->read_exec_only == 1 && \
+ (info)->seg_32bit == 0 && \
+ (info)->limit_in_pages == 0 && \
+ (info)->seg_not_present == 1 && \
+ (info)->useable == 0 )
+
+#ifdef CONFIG_X86_64
+#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
+#else
+#define LDT_empty(info) (_LDT_empty(info))
+#endif
+
+struct uml_arch_mm_context {
+ uml_ldt_t ldt;
+};
+
+#endif
diff --git a/arch/x86/um/asm/module.h b/arch/x86/um/asm/module.h
new file mode 100644
index 0000000..61af80e
--- /dev/null
+++ b/arch/x86/um/asm/module.h
@@ -0,0 +1,23 @@
+#ifndef __UM_MODULE_H
+#define __UM_MODULE_H
+
+/* UML is simple */
+struct mod_arch_specific
+{
+};
+
+#ifdef CONFIG_X86_32
+
+#define Elf_Shdr Elf32_Shdr
+#define Elf_Sym Elf32_Sym
+#define Elf_Ehdr Elf32_Ehdr
+
+#else
+
+#define Elf_Shdr Elf64_Shdr
+#define Elf_Sym Elf64_Sym
+#define Elf_Ehdr Elf64_Ehdr
+
+#endif
+
+#endif
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
new file mode 100644
index 0000000..118c143
--- /dev/null
+++ b/arch/x86/um/asm/processor.h
@@ -0,0 +1,22 @@
+#ifndef __UM_PROCESSOR_H
+#define __UM_PROCESSOR_H
+
+/* include faultinfo structure */
+#include <sysdep/faultinfo.h>
+
+#ifdef CONFIG_X86_32
+# include "processor_32.h"
+#else
+# include "processor_64.h"
+#endif
+
+#define KSTK_EIP(tsk) KSTK_REG(tsk, HOST_IP)
+#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_IP)
+#define KSTK_EBP(tsk) KSTK_REG(tsk, HOST_BP)
+
+#define ARCH_IS_STACKGROW(address) \
+ (address + 65536 + 32 * sizeof(unsigned long) >= UPT_SP(¤t->thread.regs.regs))
+
+#include <asm/processor-generic.h>
+
+#endif
diff --git a/arch/um/sys-i386/asm/processor.h b/arch/x86/um/asm/processor_32.h
similarity index 77%
rename from arch/um/sys-i386/asm/processor.h
rename to arch/x86/um/asm/processor_32.h
index 82a9061..018f732 100644
--- a/arch/um/sys-i386/asm/processor.h
+++ b/arch/x86/um/asm/processor_32.h
@@ -6,15 +6,12 @@
#ifndef __UM_PROCESSOR_I386_H
#define __UM_PROCESSOR_I386_H
-#include "linux/string.h"
-#include <sysdep/host_ldt.h>
-#include "asm/segment.h"
+#include <linux/string.h>
+#include <asm/segment.h>
+#include <asm/ldt.h>
extern int host_has_cmov;
-/* include faultinfo structure */
-#include "sysdep/faultinfo.h"
-
struct uml_tls_struct {
struct user_desc tls;
unsigned flushed:1;
@@ -66,13 +63,4 @@
#define current_text_addr() \
({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; })
-#define ARCH_IS_STACKGROW(address) \
- (address + 32 >= UPT_SP(¤t->thread.regs.regs))
-
-#define KSTK_EIP(tsk) KSTK_REG(tsk, EIP)
-#define KSTK_ESP(tsk) KSTK_REG(tsk, UESP)
-#define KSTK_EBP(tsk) KSTK_REG(tsk, EBP)
-
-#include "asm/processor-generic.h"
-
#endif
diff --git a/arch/um/sys-x86_64/asm/processor.h b/arch/x86/um/asm/processor_64.h
similarity index 76%
rename from arch/um/sys-x86_64/asm/processor.h
rename to arch/x86/um/asm/processor_64.h
index 875a26a..61de92d 100644
--- a/arch/um/sys-x86_64/asm/processor.h
+++ b/arch/x86/um/asm/processor_64.h
@@ -7,9 +7,6 @@
#ifndef __UM_PROCESSOR_X86_64_H
#define __UM_PROCESSOR_X86_64_H
-/* include faultinfo structure */
-#include "sysdep/faultinfo.h"
-
struct arch_thread {
unsigned long debugregs[8];
int debugregs_seq;
@@ -45,12 +42,4 @@
#define current_text_addr() \
({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; })
-#define ARCH_IS_STACKGROW(address) \
- (address + 128 >= UPT_SP(¤t->thread.regs.regs))
-
-#define KSTK_EIP(tsk) KSTK_REG(tsk, RIP)
-#define KSTK_ESP(tsk) KSTK_REG(tsk, RSP)
-
-#include "asm/processor-generic.h"
-
#endif
diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h
new file mode 100644
index 0000000..c8aca8c
--- /dev/null
+++ b/arch/x86/um/asm/ptrace.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "ptrace_32.h"
+#else
+# include "ptrace_64.h"
+#endif
diff --git a/arch/um/sys-i386/asm/ptrace.h b/arch/x86/um/asm/ptrace_32.h
similarity index 100%
rename from arch/um/sys-i386/asm/ptrace.h
rename to arch/x86/um/asm/ptrace_32.h
diff --git a/arch/um/sys-x86_64/asm/ptrace.h b/arch/x86/um/asm/ptrace_64.h
similarity index 97%
rename from arch/um/sys-x86_64/asm/ptrace.h
rename to arch/x86/um/asm/ptrace_64.h
index 83d8c47..706a0d8 100644
--- a/arch/um/sys-x86_64/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace_64.h
@@ -40,7 +40,7 @@
#define PT_REGS_ORIG_RAX(r) UPT_ORIG_RAX(&(r)->regs)
#define PT_REGS_RIP(r) UPT_IP(&(r)->regs)
-#define PT_REGS_RSP(r) UPT_SP(&(r)->regs)
+#define PT_REGS_SP(r) UPT_SP(&(r)->regs)
#define PT_REGS_EFLAGS(r) UPT_EFLAGS(&(r)->regs)
diff --git a/arch/um/include/asm/required-features.h b/arch/x86/um/asm/required-features.h
similarity index 100%
rename from arch/um/include/asm/required-features.h
rename to arch/x86/um/asm/required-features.h
diff --git a/arch/um/include/asm/segment.h b/arch/x86/um/asm/segment.h
similarity index 100%
rename from arch/um/include/asm/segment.h
rename to arch/x86/um/asm/segment.h
diff --git a/arch/um/sys-i386/shared/sysdep/system.h b/arch/x86/um/asm/system.h
similarity index 96%
rename from arch/um/sys-i386/shared/sysdep/system.h
rename to arch/x86/um/asm/system.h
index d1b93c4..a459fd9 100644
--- a/arch/um/sys-i386/shared/sysdep/system.h
+++ b/arch/x86/um/asm/system.h
@@ -129,4 +129,7 @@
alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
}
+extern void *_switch_to(void *prev, void *next, void *last);
+#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
+
#endif
diff --git a/arch/x86/um/asm/vm-flags.h b/arch/x86/um/asm/vm-flags.h
new file mode 100644
index 0000000..7c297e9
--- /dev/null
+++ b/arch/x86/um/asm/vm-flags.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2004 Jeff Dike (jdike@addtoit.com)
+ * Copyright 2003 PathScale, Inc.
+ * Licensed under the GPL
+ */
+
+#ifndef __VM_FLAGS_X86_H
+#define __VM_FLAGS_X86_H
+
+#ifdef CONFIG_X86_32
+
+#define VM_DATA_DEFAULT_FLAGS \
+ (VM_READ | VM_WRITE | \
+ ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#else
+
+#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define VM_STACK_DEFAULT_FLAGS (VM_GROWSDOWN | VM_READ | VM_WRITE | \
+ VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#endif
+#endif
diff --git a/arch/um/sys-x86_64/bug.c b/arch/x86/um/bug.c
similarity index 100%
rename from arch/um/sys-x86_64/bug.c
rename to arch/x86/um/bug.c
diff --git a/arch/um/sys-i386/bugs.c b/arch/x86/um/bugs_32.c
similarity index 93%
rename from arch/um/sys-i386/bugs.c
rename to arch/x86/um/bugs_32.c
index 2c6d0d7..a1fba5f 100644
--- a/arch/um/sys-i386/bugs.c
+++ b/arch/x86/um/bugs_32.c
@@ -4,17 +4,17 @@
*/
#include <signal.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "longjmp.h"
-#include "task.h"
-#include "user.h"
#include "sysdep/ptrace.h"
+#include <generated/asm-offsets.h>
/* Set during early boot */
static int host_has_cmov = 1;
static jmp_buf cmov_test_return;
+#define TASK_PID(task) *((int *) &(((char *) (task))[HOST_TASK_PID]))
+
static void cmov_sigill_test_handler(int sig)
{
host_has_cmov = 0;
diff --git a/arch/um/sys-x86_64/bugs.c b/arch/x86/um/bugs_64.c
similarity index 100%
rename from arch/um/sys-x86_64/bugs.c
rename to arch/x86/um/bugs_64.c
diff --git a/arch/um/sys-i386/checksum.S b/arch/x86/um/checksum_32.S
similarity index 100%
rename from arch/um/sys-i386/checksum.S
rename to arch/x86/um/checksum_32.S
diff --git a/arch/um/sys-i386/delay.c b/arch/x86/um/delay.c
similarity index 100%
rename from arch/um/sys-i386/delay.c
rename to arch/x86/um/delay.c
diff --git a/arch/um/sys-i386/elfcore.c b/arch/x86/um/elfcore.c
similarity index 100%
rename from arch/um/sys-i386/elfcore.c
rename to arch/x86/um/elfcore.c
diff --git a/arch/um/sys-i386/fault.c b/arch/x86/um/fault.c
similarity index 100%
rename from arch/um/sys-i386/fault.c
rename to arch/x86/um/fault.c
diff --git a/arch/um/sys-x86_64/ksyms.c b/arch/x86/um/ksyms.c
similarity index 90%
rename from arch/um/sys-x86_64/ksyms.c
rename to arch/x86/um/ksyms.c
index 1db2fce..2e8f43e 100644
--- a/arch/um/sys-x86_64/ksyms.c
+++ b/arch/x86/um/ksyms.c
@@ -2,10 +2,12 @@
#include <asm/string.h>
#include <asm/checksum.h>
+#ifndef CONFIG_X86_32
/*XXX: we need them because they would be exported by x86_64 */
#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
EXPORT_SYMBOL(memcpy);
#else
EXPORT_SYMBOL(__memcpy);
#endif
+#endif
EXPORT_SYMBOL(csum_partial);
diff --git a/arch/um/sys-i386/ldt.c b/arch/x86/um/ldt.c
similarity index 92%
rename from arch/um/sys-i386/ldt.c
rename to arch/x86/um/ldt.c
index 3f2bf20..26b0e39 100644
--- a/arch/um/sys-i386/ldt.c
+++ b/arch/x86/um/ldt.c
@@ -137,7 +137,7 @@
{
int i, err = 0;
unsigned long size;
- uml_ldt_t * ldt = ¤t->mm->context.ldt;
+ uml_ldt_t *ldt = ¤t->mm->context.arch.ldt;
if (!ldt->entry_count)
goto out;
@@ -205,7 +205,7 @@
static int write_ldt(void __user * ptr, unsigned long bytecount, int func)
{
- uml_ldt_t * ldt = ¤t->mm->context.ldt;
+ uml_ldt_t *ldt = ¤t->mm->context.arch.ldt;
struct mm_id * mm_idp = ¤t->mm->context.id;
int i, err;
struct user_desc ldt_info;
@@ -397,7 +397,7 @@
if (!ptrace_ldt)
- mutex_init(&new_mm->ldt.lock);
+ mutex_init(&new_mm->arch.ldt.lock);
if (!from_mm) {
memset(&desc, 0, sizeof(desc));
@@ -429,7 +429,7 @@
break;
}
}
- new_mm->ldt.entry_count = 0;
+ new_mm->arch.ldt.entry_count = 0;
goto out;
}
@@ -457,26 +457,26 @@
* i.e., we have to use the stub for modify_ldt, which
* can't handle the big read buffer of up to 64kB.
*/
- mutex_lock(&from_mm->ldt.lock);
- if (from_mm->ldt.entry_count <= LDT_DIRECT_ENTRIES)
- memcpy(new_mm->ldt.u.entries, from_mm->ldt.u.entries,
- sizeof(new_mm->ldt.u.entries));
+ mutex_lock(&from_mm->arch.ldt.lock);
+ if (from_mm->arch.ldt.entry_count <= LDT_DIRECT_ENTRIES)
+ memcpy(new_mm->arch.ldt.u.entries, from_mm->arch.ldt.u.entries,
+ sizeof(new_mm->arch.ldt.u.entries));
else {
- i = from_mm->ldt.entry_count / LDT_ENTRIES_PER_PAGE;
+ i = from_mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE;
while (i-->0) {
page = __get_free_page(GFP_KERNEL|__GFP_ZERO);
if (!page) {
err = -ENOMEM;
break;
}
- new_mm->ldt.u.pages[i] =
+ new_mm->arch.ldt.u.pages[i] =
(struct ldt_entry *) page;
- memcpy(new_mm->ldt.u.pages[i],
- from_mm->ldt.u.pages[i], PAGE_SIZE);
+ memcpy(new_mm->arch.ldt.u.pages[i],
+ from_mm->arch.ldt.u.pages[i], PAGE_SIZE);
}
}
- new_mm->ldt.entry_count = from_mm->ldt.entry_count;
- mutex_unlock(&from_mm->ldt.lock);
+ new_mm->arch.ldt.entry_count = from_mm->arch.ldt.entry_count;
+ mutex_unlock(&from_mm->arch.ldt.lock);
}
out:
@@ -488,12 +488,12 @@
{
int i;
- if (!ptrace_ldt && mm->ldt.entry_count > LDT_DIRECT_ENTRIES) {
- i = mm->ldt.entry_count / LDT_ENTRIES_PER_PAGE;
+ if (!ptrace_ldt && mm->arch.ldt.entry_count > LDT_DIRECT_ENTRIES) {
+ i = mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE;
while (i-- > 0)
- free_page((long) mm->ldt.u.pages[i]);
+ free_page((long) mm->arch.ldt.u.pages[i]);
}
- mm->ldt.entry_count = 0;
+ mm->arch.ldt.entry_count = 0;
}
int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount)
diff --git a/arch/um/sys-i386/mem.c b/arch/x86/um/mem_32.c
similarity index 100%
rename from arch/um/sys-i386/mem.c
rename to arch/x86/um/mem_32.c
diff --git a/arch/um/sys-x86_64/mem.c b/arch/x86/um/mem_64.c
similarity index 100%
rename from arch/um/sys-x86_64/mem.c
rename to arch/x86/um/mem_64.c
diff --git a/arch/um/os-Linux/sys-i386/Makefile b/arch/x86/um/os-Linux/Makefile
similarity index 61%
rename from arch/um/os-Linux/sys-i386/Makefile
rename to arch/x86/um/os-Linux/Makefile
index b4bc6ac..253bfb8 100644
--- a/arch/um/os-Linux/sys-i386/Makefile
+++ b/arch/x86/um/os-Linux/Makefile
@@ -3,7 +3,10 @@
# Licensed under the GPL
#
-obj-y = registers.o signal.o task_size.o tls.o
+obj-y = registers.o task_size.o mcontext.o
+
+obj-$(CONFIG_X86_32) += tls.o
+obj-$(CONFIG_64BIT) += prctl.o
USER_OBJS := $(obj-y)
diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c
new file mode 100644
index 0000000..1d33d72
--- /dev/null
+++ b/arch/x86/um/os-Linux/mcontext.c
@@ -0,0 +1,31 @@
+#include <sys/ucontext.h>
+#define __FRAME_OFFSETS
+#include <asm/ptrace.h>
+#include <sysdep/ptrace.h>
+
+void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
+{
+#ifdef __i386__
+#define COPY2(X,Y) regs->gp[X] = mc->gregs[REG_##Y]
+#define COPY(X) regs->gp[X] = mc->gregs[REG_##X]
+#define COPY_SEG(X) regs->gp[X] = mc->gregs[REG_##X] & 0xffff;
+#define COPY_SEG_CPL3(X) regs->gp[X] = (mc->gregs[REG_##X] & 0xffff) | 3;
+ COPY_SEG(GS); COPY_SEG(FS); COPY_SEG(ES); COPY_SEG(DS);
+ COPY(EDI); COPY(ESI); COPY(EBP);
+ COPY2(UESP, ESP); /* sic */
+ COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX);
+ COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS);
+#else
+#define COPY2(X,Y) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##Y]
+#define COPY(X) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##X]
+ COPY(R8); COPY(R9); COPY(R10); COPY(R11);
+ COPY(R12); COPY(R13); COPY(R14); COPY(R15);
+ COPY(RDI); COPY(RSI); COPY(RBP); COPY(RBX);
+ COPY(RDX); COPY(RAX); COPY(RCX); COPY(RSP);
+ COPY(RIP);
+ COPY2(EFLAGS, EFL);
+ COPY2(CS, CSGSFS);
+ regs->gp[CS / sizeof(unsigned long)] &= 0xffff;
+ regs->gp[CS / sizeof(unsigned long)] |= 3;
+#endif
+}
diff --git a/arch/um/os-Linux/sys-x86_64/prctl.c b/arch/x86/um/os-Linux/prctl.c
similarity index 100%
rename from arch/um/os-Linux/sys-x86_64/prctl.c
rename to arch/x86/um/os-Linux/prctl.c
diff --git a/arch/um/os-Linux/sys-i386/registers.c b/arch/x86/um/os-Linux/registers.c
similarity index 79%
rename from arch/um/os-Linux/sys-i386/registers.c
rename to arch/x86/um/os-Linux/registers.c
index 229f7a5..0cdbb86 100644
--- a/arch/um/os-Linux/sys-i386/registers.c
+++ b/arch/x86/um/os-Linux/registers.c
@@ -6,10 +6,10 @@
#include <errno.h>
#include <sys/ptrace.h>
+#ifdef __i386__
#include <sys/user.h>
-#include "kern_constants.h"
+#endif
#include "longjmp.h"
-#include "user.h"
#include "sysdep/ptrace_user.h"
int save_fp_registers(int pid, unsigned long *fp_regs)
@@ -26,6 +26,8 @@
return 0;
}
+#ifdef __i386__
+int have_fpx_regs = 1;
int save_fpx_registers(int pid, unsigned long *fp_regs)
{
if (ptrace(PTRACE_GETFPXREGS, pid, 0, fp_regs) < 0)
@@ -40,24 +42,6 @@
return 0;
}
-unsigned long get_thread_reg(int reg, jmp_buf *buf)
-{
- switch (reg) {
- case EIP:
- return buf[0]->__eip;
- case UESP:
- return buf[0]->__esp;
- case EBP:
- return buf[0]->__ebp;
- default:
- printk(UM_KERN_ERR "get_thread_regs - unknown register %d\n",
- reg);
- return 0;
- }
-}
-
-int have_fpx_regs = 1;
-
int get_fp_registers(int pid, unsigned long *regs)
{
if (have_fpx_regs)
@@ -89,3 +73,41 @@
have_fpx_regs = 0;
}
+#else
+
+int get_fp_registers(int pid, unsigned long *regs)
+{
+ return save_fp_registers(pid, regs);
+}
+
+int put_fp_registers(int pid, unsigned long *regs)
+{
+ return restore_fp_registers(pid, regs);
+}
+
+#endif
+
+unsigned long get_thread_reg(int reg, jmp_buf *buf)
+{
+ switch (reg) {
+#ifdef __i386__
+ case HOST_IP:
+ return buf[0]->__eip;
+ case HOST_SP:
+ return buf[0]->__esp;
+ case HOST_BP:
+ return buf[0]->__ebp;
+#else
+ case HOST_IP:
+ return buf[0]->__rip;
+ case HOST_SP:
+ return buf[0]->__rsp;
+ case HOST_BP:
+ return buf[0]->__rbp;
+#endif
+ default:
+ printk(UM_KERN_ERR "get_thread_regs - unknown register %d\n",
+ reg);
+ return 0;
+ }
+}
diff --git a/arch/um/os-Linux/sys-i386/task_size.c b/arch/x86/um/os-Linux/task_size.c
similarity index 95%
rename from arch/um/os-Linux/sys-i386/task_size.c
rename to arch/x86/um/os-Linux/task_size.c
index be04c1e..efb16c5 100644
--- a/arch/um/os-Linux/sys-i386/task_size.c
+++ b/arch/x86/um/os-Linux/task_size.c
@@ -3,7 +3,8 @@
#include <signal.h>
#include <sys/mman.h>
#include "longjmp.h"
-#include "kern_constants.h"
+
+#ifdef __i386__
static jmp_buf buf;
@@ -137,3 +138,13 @@
return top;
}
+
+#else
+
+unsigned long os_get_top_address(void)
+{
+ /* The old value of CONFIG_TOP_ADDR */
+ return 0x7fc0000000;
+}
+
+#endif
diff --git a/arch/x86/um/os-Linux/tls.c b/arch/x86/um/os-Linux/tls.c
new file mode 100644
index 0000000..82276b6
--- /dev/null
+++ b/arch/x86/um/os-Linux/tls.c
@@ -0,0 +1,67 @@
+#include <errno.h>
+#include <linux/unistd.h>
+
+#include <sys/ptrace.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "sysdep/tls.h"
+
+#ifndef PTRACE_GET_THREAD_AREA
+#define PTRACE_GET_THREAD_AREA 25
+#endif
+
+#ifndef PTRACE_SET_THREAD_AREA
+#define PTRACE_SET_THREAD_AREA 26
+#endif
+
+/* Checks whether host supports TLS, and sets *tls_min according to the value
+ * valid on the host.
+ * i386 host have it == 6; x86_64 host have it == 12, for i386 emulation. */
+void check_host_supports_tls(int *supports_tls, int *tls_min)
+{
+ /* Values for x86 and x86_64.*/
+ int val[] = {GDT_ENTRY_TLS_MIN_I386, GDT_ENTRY_TLS_MIN_X86_64};
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(val); i++) {
+ user_desc_t info;
+ info.entry_number = val[i];
+
+ if (syscall(__NR_get_thread_area, &info) == 0) {
+ *tls_min = val[i];
+ *supports_tls = 1;
+ return;
+ } else {
+ if (errno == EINVAL)
+ continue;
+ else if (errno == ENOSYS)
+ *supports_tls = 0;
+ return;
+ }
+ }
+
+ *supports_tls = 0;
+}
+
+int os_set_thread_area(user_desc_t *info, int pid)
+{
+ int ret;
+
+ ret = ptrace(PTRACE_SET_THREAD_AREA, pid, info->entry_number,
+ (unsigned long) info);
+ if (ret < 0)
+ ret = -errno;
+ return ret;
+}
+
+int os_get_thread_area(user_desc_t *info, int pid)
+{
+ int ret;
+
+ ret = ptrace(PTRACE_GET_THREAD_AREA, pid, info->entry_number,
+ (unsigned long) info);
+ if (ret < 0)
+ ret = -errno;
+ return ret;
+}
diff --git a/arch/um/sys-i386/ptrace.c b/arch/x86/um/ptrace_32.c
similarity index 82%
rename from arch/um/sys-i386/ptrace.c
rename to arch/x86/um/ptrace_32.c
index 3375c27..3b949da 100644
--- a/arch/um/sys-i386/ptrace.c
+++ b/arch/x86/um/ptrace_32.c
@@ -50,20 +50,47 @@
/* 1 = access 0 = no access */
#define FLAG_MASK 0x00044dd5
+static const int reg_offsets[] = {
+ [EBX] = HOST_BX,
+ [ECX] = HOST_CX,
+ [EDX] = HOST_DX,
+ [ESI] = HOST_SI,
+ [EDI] = HOST_DI,
+ [EBP] = HOST_BP,
+ [EAX] = HOST_AX,
+ [DS] = HOST_DS,
+ [ES] = HOST_ES,
+ [FS] = HOST_FS,
+ [GS] = HOST_GS,
+ [EIP] = HOST_IP,
+ [CS] = HOST_CS,
+ [EFL] = HOST_EFLAGS,
+ [UESP] = HOST_SP,
+ [SS] = HOST_SS,
+};
+
int putreg(struct task_struct *child, int regno, unsigned long value)
{
regno >>= 2;
switch (regno) {
+ case EBX:
+ case ECX:
+ case EDX:
+ case ESI:
+ case EDI:
+ case EBP:
+ case EAX:
+ case EIP:
+ case UESP:
+ break;
case FS:
if (value && (value & 3) != 3)
return -EIO;
- PT_REGS_FS(&child->thread.regs) = value;
- return 0;
+ break;
case GS:
if (value && (value & 3) != 3)
return -EIO;
- PT_REGS_GS(&child->thread.regs) = value;
- return 0;
+ break;
case DS:
case ES:
if (value && (value & 3) != 3)
@@ -78,10 +105,15 @@
break;
case EFL:
value &= FLAG_MASK;
- value |= PT_REGS_EFLAGS(&child->thread.regs);
- break;
+ child->thread.regs.regs.gp[HOST_EFLAGS] |= value;
+ return 0;
+ case ORIG_EAX:
+ child->thread.regs.regs.syscall = value;
+ return 0;
+ default :
+ panic("Bad register in putreg() : %d\n", regno);
}
- PT_REGS_SET(&child->thread.regs, regno, value);
+ child->thread.regs.regs.gp[reg_offsets[regno]] = value;
return 0;
}
@@ -106,22 +138,35 @@
unsigned long getreg(struct task_struct *child, int regno)
{
- unsigned long retval = ~0UL;
+ unsigned long mask = ~0UL;
regno >>= 2;
switch (regno) {
+ case ORIG_EAX:
+ return child->thread.regs.regs.syscall;
case FS:
case GS:
case DS:
case ES:
case SS:
case CS:
- retval = 0xffff;
- /* fall through */
+ mask = 0xffff;
+ break;
+ case EIP:
+ case UESP:
+ case EAX:
+ case EBX:
+ case ECX:
+ case EDX:
+ case ESI:
+ case EDI:
+ case EBP:
+ case EFL:
+ break;
default:
- retval &= PT_REG(&child->thread.regs, regno);
+ panic("Bad register in getreg() : %d\n", regno);
}
- return retval;
+ return mask & child->thread.regs.regs.gp[reg_offsets[regno]];
}
/* read the word at location addr in the USER area. */
diff --git a/arch/um/sys-x86_64/ptrace.c b/arch/x86/um/ptrace_64.c
similarity index 72%
rename from arch/um/sys-x86_64/ptrace.c
rename to arch/x86/um/ptrace_64.c
index 4005506..3b52bf0 100644
--- a/arch/um/sys-x86_64/ptrace.c
+++ b/arch/x86/um/ptrace_64.c
@@ -18,10 +18,39 @@
*/
#define FLAG_MASK 0x44dd5UL
+static const int reg_offsets[] =
+{
+ [R8 >> 3] = HOST_R8,
+ [R9 >> 3] = HOST_R9,
+ [R10 >> 3] = HOST_R10,
+ [R11 >> 3] = HOST_R11,
+ [R12 >> 3] = HOST_R12,
+ [R13 >> 3] = HOST_R13,
+ [R14 >> 3] = HOST_R14,
+ [R15 >> 3] = HOST_R15,
+ [RIP >> 3] = HOST_IP,
+ [RSP >> 3] = HOST_SP,
+ [RAX >> 3] = HOST_AX,
+ [RBX >> 3] = HOST_BX,
+ [RCX >> 3] = HOST_CX,
+ [RDX >> 3] = HOST_DX,
+ [RSI >> 3] = HOST_SI,
+ [RDI >> 3] = HOST_DI,
+ [RBP >> 3] = HOST_BP,
+ [CS >> 3] = HOST_CS,
+ [SS >> 3] = HOST_SS,
+ [FS_BASE >> 3] = HOST_FS_BASE,
+ [GS_BASE >> 3] = HOST_GS_BASE,
+ [DS >> 3] = HOST_DS,
+ [ES >> 3] = HOST_ES,
+ [FS >> 3] = HOST_FS,
+ [GS >> 3] = HOST_GS,
+ [EFLAGS >> 3] = HOST_EFLAGS,
+ [ORIG_RAX >> 3] = HOST_ORIG_AX,
+};
+
int putreg(struct task_struct *child, int regno, unsigned long value)
{
- unsigned long tmp;
-
#ifdef TIF_IA32
/*
* Some code in the 64bit emulation may not be 64bit clean.
@@ -31,6 +60,26 @@
value &= 0xffffffff;
#endif
switch (regno) {
+ case R8:
+ case R9:
+ case R10:
+ case R11:
+ case R12:
+ case R13:
+ case R14:
+ case R15:
+ case RIP:
+ case RSP:
+ case RAX:
+ case RBX:
+ case RCX:
+ case RDX:
+ case RSI:
+ case RDI:
+ case RBP:
+ case ORIG_RAX:
+ break;
+
case FS:
case GS:
case DS:
@@ -50,12 +99,14 @@
case EFLAGS:
value &= FLAG_MASK;
- tmp = PT_REGS_EFLAGS(&child->thread.regs) & ~FLAG_MASK;
- value |= tmp;
- break;
+ child->thread.regs.regs.gp[HOST_EFLAGS] |= value;
+ return 0;
+
+ default:
+ panic("Bad register in putreg(): %d\n", regno);
}
- PT_REGS_SET(&child->thread.regs, regno, value);
+ child->thread.regs.regs.gp[reg_offsets[regno >> 3]] = value;
return 0;
}
@@ -80,24 +131,46 @@
unsigned long getreg(struct task_struct *child, int regno)
{
- unsigned long retval = ~0UL;
+ unsigned long mask = ~0UL;
+#ifdef TIF_IA32
+ if (test_tsk_thread_flag(child, TIF_IA32))
+ mask = 0xffffffff;
+#endif
switch (regno) {
+ case R8:
+ case R9:
+ case R10:
+ case R11:
+ case R12:
+ case R13:
+ case R14:
+ case R15:
+ case RIP:
+ case RSP:
+ case RAX:
+ case RBX:
+ case RCX:
+ case RDX:
+ case RSI:
+ case RDI:
+ case RBP:
+ case ORIG_RAX:
+ case EFLAGS:
+ case FS_BASE:
+ case GS_BASE:
+ break;
case FS:
case GS:
case DS:
case ES:
case SS:
case CS:
- retval = 0xffff;
- /* fall through */
+ mask = 0xffff;
+ break;
default:
- retval &= PT_REG(&child->thread.regs, regno);
-#ifdef TIF_IA32
- if (test_tsk_thread_flag(child, TIF_IA32))
- retval &= 0xffffffff;
-#endif
+ panic("Bad register in getreg: %d\n", regno);
}
- return retval;
+ return mask & child->thread.regs.regs.gp[reg_offsets[regno >> 3]];
}
int peek_user(struct task_struct *child, long addr, long data)
diff --git a/arch/um/sys-i386/ptrace_user.c b/arch/x86/um/ptrace_user.c
similarity index 93%
rename from arch/um/sys-i386/ptrace_user.c
rename to arch/x86/um/ptrace_user.c
index 0b10c3e..3960ca1 100644
--- a/arch/um/sys-i386/ptrace_user.c
+++ b/arch/x86/um/ptrace_user.c
@@ -4,7 +4,7 @@
*/
#include <errno.h>
-#include <sys/ptrace.h>
+#include "ptrace_user.h"
int ptrace_getregs(long pid, unsigned long *regs_out)
{
diff --git a/arch/um/sys-i386/setjmp.S b/arch/x86/um/setjmp_32.S
similarity index 100%
rename from arch/um/sys-i386/setjmp.S
rename to arch/x86/um/setjmp_32.S
diff --git a/arch/um/sys-x86_64/setjmp.S b/arch/x86/um/setjmp_64.S
similarity index 100%
rename from arch/um/sys-x86_64/setjmp.S
rename to arch/x86/um/setjmp_64.S
diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h
new file mode 100644
index 0000000..ff7766d
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/archsetjmp.h
@@ -0,0 +1,5 @@
+#ifdef __i386__
+#include "archsetjmp_32.h"
+#else
+#include "archsetjmp_64.h"
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp_32.h
similarity index 100%
rename from arch/um/sys-i386/shared/sysdep/archsetjmp.h
rename to arch/x86/um/shared/sysdep/archsetjmp_32.h
diff --git a/arch/um/sys-x86_64/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp_64.h
similarity index 100%
rename from arch/um/sys-x86_64/shared/sysdep/archsetjmp.h
rename to arch/x86/um/shared/sysdep/archsetjmp_64.h
diff --git a/arch/x86/um/shared/sysdep/faultinfo.h b/arch/x86/um/shared/sysdep/faultinfo.h
new file mode 100644
index 0000000..862ecb1
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/faultinfo.h
@@ -0,0 +1,5 @@
+#ifdef __i386__
+#include "faultinfo_32.h"
+#else
+#include "faultinfo_64.h"
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/faultinfo.h b/arch/x86/um/shared/sysdep/faultinfo_32.h
similarity index 79%
rename from arch/um/sys-i386/shared/sysdep/faultinfo.h
rename to arch/x86/um/shared/sysdep/faultinfo_32.h
index db437cc..a26086b 100644
--- a/arch/um/sys-i386/shared/sysdep/faultinfo.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_32.h
@@ -24,6 +24,12 @@
#define FAULT_WRITE(fi) ((fi).error_code & 2)
#define FAULT_ADDRESS(fi) ((fi).cr2)
+/* This is Page Fault */
+#define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14)
+
+/* SKAS3 has no trap_no on i386, but get_skas_faultinfo() sets it to 0. */
+#define SEGV_MAYBE_FIXABLE(fi) ((fi)->trap_no == 0 && ptrace_faultinfo)
+
#define PTRACE_FULL_FAULTINFO 0
#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/faultinfo.h b/arch/x86/um/shared/sysdep/faultinfo_64.h
similarity index 83%
rename from arch/um/sys-x86_64/shared/sysdep/faultinfo.h
rename to arch/x86/um/shared/sysdep/faultinfo_64.h
index cb917b0..f811cbe 100644
--- a/arch/um/sys-x86_64/shared/sysdep/faultinfo.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_64.h
@@ -24,6 +24,12 @@
#define FAULT_WRITE(fi) ((fi).error_code & 2)
#define FAULT_ADDRESS(fi) ((fi).cr2)
+/* This is Page Fault */
+#define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14)
+
+/* No broken SKAS API, which doesn't pass trap_no, here. */
+#define SEGV_MAYBE_FIXABLE(fi) 0
+
#define PTRACE_FULL_FAULTINFO 1
#endif
diff --git a/arch/um/sys-i386/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h
similarity index 100%
rename from arch/um/sys-i386/shared/sysdep/kernel-offsets.h
rename to arch/x86/um/shared/sysdep/kernel-offsets.h
diff --git a/arch/x86/um/shared/sysdep/mcontext.h b/arch/x86/um/shared/sysdep/mcontext.h
new file mode 100644
index 0000000..b724c54
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/mcontext.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __SYS_SIGCONTEXT_X86_H
+#define __SYS_SIGCONTEXT_X86_H
+
+extern void get_regs_from_mc(struct uml_pt_regs *, mcontext_t *);
+
+#ifdef __i386__
+
+#define GET_FAULTINFO_FROM_MC(fi, mc) \
+ { \
+ (fi).cr2 = (mc)->cr2; \
+ (fi).error_code = (mc)->gregs[REG_ERR]; \
+ (fi).trap_no = (mc)->gregs[REG_TRAPNO]; \
+ }
+
+#else
+
+#define GET_FAULTINFO_FROM_MC(fi, mc) \
+ { \
+ (fi).cr2 = (mc)->gregs[REG_CR2]; \
+ (fi).error_code = (mc)->gregs[REG_ERR]; \
+ (fi).trap_no = (mc)->gregs[REG_TRAPNO]; \
+ }
+
+#endif
+
+#endif
diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h
new file mode 100644
index 0000000..711b162
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/ptrace.h
@@ -0,0 +1,5 @@
+#ifdef __i386__
+#include "ptrace_32.h"
+#else
+#include "ptrace_64.h"
+#endif
diff --git a/arch/x86/um/shared/sysdep/ptrace_32.h b/arch/x86/um/shared/sysdep/ptrace_32.h
new file mode 100644
index 0000000..befd1df
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/ptrace_32.h
@@ -0,0 +1,114 @@
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __SYSDEP_I386_PTRACE_H
+#define __SYSDEP_I386_PTRACE_H
+
+#include <generated/user_constants.h>
+#include "sysdep/faultinfo.h"
+
+#define MAX_REG_NR (UM_FRAME_SIZE / sizeof(unsigned long))
+#define MAX_REG_OFFSET (UM_FRAME_SIZE)
+
+static inline void update_debugregs(int seq) {}
+
+/* syscall emulation path in ptrace */
+
+#ifndef PTRACE_SYSEMU
+#define PTRACE_SYSEMU 31
+#endif
+
+void set_using_sysemu(int value);
+int get_using_sysemu(void);
+extern int sysemu_supported;
+
+#define REGS_IP(r) ((r)[HOST_IP])
+#define REGS_SP(r) ((r)[HOST_SP])
+#define REGS_EFLAGS(r) ((r)[HOST_EFLAGS])
+#define REGS_EAX(r) ((r)[HOST_AX])
+#define REGS_EBX(r) ((r)[HOST_BX])
+#define REGS_ECX(r) ((r)[HOST_CX])
+#define REGS_EDX(r) ((r)[HOST_DX])
+#define REGS_ESI(r) ((r)[HOST_SI])
+#define REGS_EDI(r) ((r)[HOST_DI])
+#define REGS_EBP(r) ((r)[HOST_BP])
+#define REGS_CS(r) ((r)[HOST_CS])
+#define REGS_SS(r) ((r)[HOST_SS])
+#define REGS_DS(r) ((r)[HOST_DS])
+#define REGS_ES(r) ((r)[HOST_ES])
+#define REGS_FS(r) ((r)[HOST_FS])
+#define REGS_GS(r) ((r)[HOST_GS])
+
+#define REGS_SET_SYSCALL_RETURN(r, res) REGS_EAX(r) = (res)
+
+#define IP_RESTART_SYSCALL(ip) ((ip) -= 2)
+#define REGS_RESTART_SYSCALL(r) IP_RESTART_SYSCALL(REGS_IP(r))
+
+#ifndef PTRACE_SYSEMU_SINGLESTEP
+#define PTRACE_SYSEMU_SINGLESTEP 32
+#endif
+
+struct uml_pt_regs {
+ unsigned long gp[MAX_REG_NR];
+ unsigned long fp[HOST_FPX_SIZE];
+ struct faultinfo faultinfo;
+ long syscall;
+ int is_user;
+};
+
+#define EMPTY_UML_PT_REGS { }
+
+#define UPT_IP(r) REGS_IP((r)->gp)
+#define UPT_SP(r) REGS_SP((r)->gp)
+#define UPT_EFLAGS(r) REGS_EFLAGS((r)->gp)
+#define UPT_EAX(r) REGS_EAX((r)->gp)
+#define UPT_EBX(r) REGS_EBX((r)->gp)
+#define UPT_ECX(r) REGS_ECX((r)->gp)
+#define UPT_EDX(r) REGS_EDX((r)->gp)
+#define UPT_ESI(r) REGS_ESI((r)->gp)
+#define UPT_EDI(r) REGS_EDI((r)->gp)
+#define UPT_EBP(r) REGS_EBP((r)->gp)
+#define UPT_ORIG_EAX(r) ((r)->syscall)
+#define UPT_CS(r) REGS_CS((r)->gp)
+#define UPT_SS(r) REGS_SS((r)->gp)
+#define UPT_DS(r) REGS_DS((r)->gp)
+#define UPT_ES(r) REGS_ES((r)->gp)
+#define UPT_FS(r) REGS_FS((r)->gp)
+#define UPT_GS(r) REGS_GS((r)->gp)
+
+#define UPT_SYSCALL_ARG1(r) UPT_EBX(r)
+#define UPT_SYSCALL_ARG2(r) UPT_ECX(r)
+#define UPT_SYSCALL_ARG3(r) UPT_EDX(r)
+#define UPT_SYSCALL_ARG4(r) UPT_ESI(r)
+#define UPT_SYSCALL_ARG5(r) UPT_EDI(r)
+#define UPT_SYSCALL_ARG6(r) UPT_EBP(r)
+
+extern int user_context(unsigned long sp);
+
+#define UPT_IS_USER(r) ((r)->is_user)
+
+struct syscall_args {
+ unsigned long args[6];
+};
+
+#define SYSCALL_ARGS(r) ((struct syscall_args) \
+ { .args = { UPT_SYSCALL_ARG1(r), \
+ UPT_SYSCALL_ARG2(r), \
+ UPT_SYSCALL_ARG3(r), \
+ UPT_SYSCALL_ARG4(r), \
+ UPT_SYSCALL_ARG5(r), \
+ UPT_SYSCALL_ARG6(r) } } )
+
+#define UPT_RESTART_SYSCALL(r) REGS_RESTART_SYSCALL((r)->gp)
+
+#define UPT_ORIG_SYSCALL(r) UPT_EAX(r)
+#define UPT_SYSCALL_NR(r) UPT_ORIG_EAX(r)
+#define UPT_SYSCALL_RET(r) UPT_EAX(r)
+
+#define UPT_FAULTINFO(r) (&(r)->faultinfo)
+
+extern void arch_init_registers(int pid);
+
+#endif
diff --git a/arch/x86/um/shared/sysdep/ptrace_64.h b/arch/x86/um/shared/sysdep/ptrace_64.h
new file mode 100644
index 0000000..031edc5
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/ptrace_64.h
@@ -0,0 +1,157 @@
+/*
+ * Copyright 2003 PathScale, Inc.
+ * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ *
+ * Licensed under the GPL
+ */
+
+#ifndef __SYSDEP_X86_64_PTRACE_H
+#define __SYSDEP_X86_64_PTRACE_H
+
+#include <generated/user_constants.h>
+#include "sysdep/faultinfo.h"
+
+#define MAX_REG_OFFSET (UM_FRAME_SIZE)
+#define MAX_REG_NR ((MAX_REG_OFFSET) / sizeof(unsigned long))
+
+#define REGS_IP(r) ((r)[HOST_IP])
+#define REGS_SP(r) ((r)[HOST_SP])
+
+#define REGS_RBX(r) ((r)[HOST_BX])
+#define REGS_RCX(r) ((r)[HOST_CX])
+#define REGS_RDX(r) ((r)[HOST_DX])
+#define REGS_RSI(r) ((r)[HOST_SI])
+#define REGS_RDI(r) ((r)[HOST_DI])
+#define REGS_RBP(r) ((r)[HOST_BP])
+#define REGS_RAX(r) ((r)[HOST_AX])
+#define REGS_R8(r) ((r)[HOST_R8])
+#define REGS_R9(r) ((r)[HOST_R9])
+#define REGS_R10(r) ((r)[HOST_R10])
+#define REGS_R11(r) ((r)[HOST_R11])
+#define REGS_R12(r) ((r)[HOST_R12])
+#define REGS_R13(r) ((r)[HOST_R13])
+#define REGS_R14(r) ((r)[HOST_R14])
+#define REGS_R15(r) ((r)[HOST_R15])
+#define REGS_CS(r) ((r)[HOST_CS])
+#define REGS_EFLAGS(r) ((r)[HOST_EFLAGS])
+#define REGS_SS(r) ((r)[HOST_SS])
+
+#define HOST_FS_BASE 21
+#define HOST_GS_BASE 22
+#define HOST_DS 23
+#define HOST_ES 24
+#define HOST_FS 25
+#define HOST_GS 26
+
+/* Also defined in asm/ptrace-x86_64.h, but not in libc headers. So, these
+ * are already defined for kernel code, but not for userspace code.
+ */
+#ifndef FS_BASE
+/* These aren't defined in ptrace.h, but exist in struct user_regs_struct,
+ * which is what x86_64 ptrace actually uses.
+ */
+#define FS_BASE (HOST_FS_BASE * sizeof(long))
+#define GS_BASE (HOST_GS_BASE * sizeof(long))
+#define DS (HOST_DS * sizeof(long))
+#define ES (HOST_ES * sizeof(long))
+#define FS (HOST_FS * sizeof(long))
+#define GS (HOST_GS * sizeof(long))
+#endif
+
+#define REGS_FS_BASE(r) ((r)[HOST_FS_BASE])
+#define REGS_GS_BASE(r) ((r)[HOST_GS_BASE])
+#define REGS_DS(r) ((r)[HOST_DS])
+#define REGS_ES(r) ((r)[HOST_ES])
+#define REGS_FS(r) ((r)[HOST_FS])
+#define REGS_GS(r) ((r)[HOST_GS])
+
+#define REGS_ORIG_RAX(r) ((r)[HOST_ORIG_AX])
+
+#define REGS_SET_SYSCALL_RETURN(r, res) REGS_RAX(r) = (res)
+
+#define IP_RESTART_SYSCALL(ip) ((ip) -= 2)
+#define REGS_RESTART_SYSCALL(r) IP_RESTART_SYSCALL(REGS_IP(r))
+
+#define REGS_FAULT_ADDR(r) ((r)->fault_addr)
+
+#define REGS_FAULT_WRITE(r) FAULT_WRITE((r)->fault_type)
+
+#define REGS_TRAP(r) ((r)->trap_type)
+
+#define REGS_ERR(r) ((r)->fault_type)
+
+struct uml_pt_regs {
+ unsigned long gp[MAX_REG_NR];
+ unsigned long fp[HOST_FP_SIZE];
+ struct faultinfo faultinfo;
+ long syscall;
+ int is_user;
+};
+
+#define EMPTY_UML_PT_REGS { }
+
+#define UPT_RBX(r) REGS_RBX((r)->gp)
+#define UPT_RCX(r) REGS_RCX((r)->gp)
+#define UPT_RDX(r) REGS_RDX((r)->gp)
+#define UPT_RSI(r) REGS_RSI((r)->gp)
+#define UPT_RDI(r) REGS_RDI((r)->gp)
+#define UPT_RBP(r) REGS_RBP((r)->gp)
+#define UPT_RAX(r) REGS_RAX((r)->gp)
+#define UPT_R8(r) REGS_R8((r)->gp)
+#define UPT_R9(r) REGS_R9((r)->gp)
+#define UPT_R10(r) REGS_R10((r)->gp)
+#define UPT_R11(r) REGS_R11((r)->gp)
+#define UPT_R12(r) REGS_R12((r)->gp)
+#define UPT_R13(r) REGS_R13((r)->gp)
+#define UPT_R14(r) REGS_R14((r)->gp)
+#define UPT_R15(r) REGS_R15((r)->gp)
+#define UPT_CS(r) REGS_CS((r)->gp)
+#define UPT_FS_BASE(r) REGS_FS_BASE((r)->gp)
+#define UPT_FS(r) REGS_FS((r)->gp)
+#define UPT_GS_BASE(r) REGS_GS_BASE((r)->gp)
+#define UPT_GS(r) REGS_GS((r)->gp)
+#define UPT_DS(r) REGS_DS((r)->gp)
+#define UPT_ES(r) REGS_ES((r)->gp)
+#define UPT_CS(r) REGS_CS((r)->gp)
+#define UPT_SS(r) REGS_SS((r)->gp)
+#define UPT_ORIG_RAX(r) REGS_ORIG_RAX((r)->gp)
+
+#define UPT_IP(r) REGS_IP((r)->gp)
+#define UPT_SP(r) REGS_SP((r)->gp)
+
+#define UPT_EFLAGS(r) REGS_EFLAGS((r)->gp)
+#define UPT_SYSCALL_NR(r) ((r)->syscall)
+#define UPT_SYSCALL_RET(r) UPT_RAX(r)
+
+extern int user_context(unsigned long sp);
+
+#define UPT_IS_USER(r) ((r)->is_user)
+
+#define UPT_SYSCALL_ARG1(r) UPT_RDI(r)
+#define UPT_SYSCALL_ARG2(r) UPT_RSI(r)
+#define UPT_SYSCALL_ARG3(r) UPT_RDX(r)
+#define UPT_SYSCALL_ARG4(r) UPT_R10(r)
+#define UPT_SYSCALL_ARG5(r) UPT_R8(r)
+#define UPT_SYSCALL_ARG6(r) UPT_R9(r)
+
+struct syscall_args {
+ unsigned long args[6];
+};
+
+#define SYSCALL_ARGS(r) ((struct syscall_args) \
+ { .args = { UPT_SYSCALL_ARG1(r), \
+ UPT_SYSCALL_ARG2(r), \
+ UPT_SYSCALL_ARG3(r), \
+ UPT_SYSCALL_ARG4(r), \
+ UPT_SYSCALL_ARG5(r), \
+ UPT_SYSCALL_ARG6(r) } } )
+
+#define UPT_RESTART_SYSCALL(r) REGS_RESTART_SYSCALL((r)->gp)
+
+#define UPT_FAULTINFO(r) (&(r)->faultinfo)
+
+static inline void arch_init_registers(int pid)
+{
+}
+
+#endif
diff --git a/arch/x86/um/shared/sysdep/ptrace_user.h b/arch/x86/um/shared/sysdep/ptrace_user.h
new file mode 100644
index 0000000..16cd6b5
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/ptrace_user.h
@@ -0,0 +1,27 @@
+#include <generated/user_constants.h>
+
+#define PT_OFFSET(r) ((r) * sizeof(long))
+
+#define PT_SYSCALL_NR(regs) ((regs)[HOST_ORIG_AX])
+#define PT_SYSCALL_NR_OFFSET PT_OFFSET(HOST_ORIG_AX)
+
+#define PT_SYSCALL_RET_OFFSET PT_OFFSET(HOST_AX)
+
+#define REGS_IP_INDEX HOST_IP
+#define REGS_SP_INDEX HOST_SP
+
+#ifdef __i386__
+#define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE)
+#else
+#define FP_SIZE HOST_FP_SIZE
+
+/*
+ * x86_64 FC3 doesn't define this in /usr/include/linux/ptrace.h even though
+ * it's defined in the kernel's include/linux/ptrace.h. Additionally, use the
+ * 2.4 name and value for 2.4 host compatibility.
+ */
+#ifndef PTRACE_OLDSETOPTIONS
+#define PTRACE_OLDSETOPTIONS 21
+#endif
+
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/skas_ptrace.h b/arch/x86/um/shared/sysdep/skas_ptrace.h
similarity index 80%
rename from arch/um/sys-i386/shared/sysdep/skas_ptrace.h
rename to arch/x86/um/shared/sysdep/skas_ptrace.h
index e27b8a7..453febe 100644
--- a/arch/um/sys-i386/shared/sysdep/skas_ptrace.h
+++ b/arch/x86/um/shared/sysdep/skas_ptrace.h
@@ -3,8 +3,8 @@
* Licensed under the GPL
*/
-#ifndef __SYSDEP_I386_SKAS_PTRACE_H
-#define __SYSDEP_I386_SKAS_PTRACE_H
+#ifndef __SYSDEP_X86_SKAS_PTRACE_H
+#define __SYSDEP_X86_SKAS_PTRACE_H
struct ptrace_faultinfo {
int is_write;
diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h
new file mode 100644
index 0000000..bd161e3
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/stub.h
@@ -0,0 +1,14 @@
+#include <asm/unistd.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include "as-layout.h"
+#include "stub-data.h"
+
+#ifdef __i386__
+#include "stub_32.h"
+#else
+#include "stub_64.h"
+#endif
+
+extern void stub_segv_handler(int, siginfo_t *, void *);
+extern void stub_clone_handler(void);
diff --git a/arch/um/sys-i386/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub_32.h
similarity index 90%
rename from arch/um/sys-i386/shared/sysdep/stub.h
rename to arch/x86/um/shared/sysdep/stub_32.h
index 977dedd..51fd256 100644
--- a/arch/um/sys-i386/shared/sysdep/stub.h
+++ b/arch/x86/um/shared/sysdep/stub_32.h
@@ -6,15 +6,7 @@
#ifndef __SYSDEP_STUB_H
#define __SYSDEP_STUB_H
-#include <sys/mman.h>
#include <asm/ptrace.h>
-#include <asm/unistd.h>
-#include "as-layout.h"
-#include "stub-data.h"
-#include "kern_constants.h"
-
-extern void stub_segv_handler(int sig);
-extern void stub_clone_handler(void);
#define STUB_SYSCALL_RET EAX
#define STUB_MMAP_NR __NR_mmap2
diff --git a/arch/um/sys-x86_64/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub_64.h
similarity index 90%
rename from arch/um/sys-x86_64/shared/sysdep/stub.h
rename to arch/x86/um/shared/sysdep/stub_64.h
index 3432aa2..994df93 100644
--- a/arch/um/sys-x86_64/shared/sysdep/stub.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -6,15 +6,7 @@
#ifndef __SYSDEP_STUB_H
#define __SYSDEP_STUB_H
-#include <sys/mman.h>
-#include <asm/unistd.h>
#include <sysdep/ptrace_user.h>
-#include "as-layout.h"
-#include "stub-data.h"
-#include "kern_constants.h"
-
-extern void stub_segv_handler(int sig);
-extern void stub_clone_handler(void);
#define STUB_SYSCALL_RET PT_INDEX(RAX)
#define STUB_MMAP_NR __NR_mmap
diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h
new file mode 100644
index 0000000..bd9a89b
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/syscalls.h
@@ -0,0 +1,5 @@
+#ifdef __i386__
+#include "syscalls_32.h"
+#else
+#include "syscalls_64.h"
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls_32.h
similarity index 100%
rename from arch/um/sys-i386/shared/sysdep/syscalls.h
rename to arch/x86/um/shared/sysdep/syscalls_32.h
diff --git a/arch/um/sys-x86_64/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls_64.h
similarity index 96%
rename from arch/um/sys-x86_64/shared/sysdep/syscalls.h
rename to arch/x86/um/shared/sysdep/syscalls_64.h
index 7cfb0b08..8a7d5e1 100644
--- a/arch/um/sys-x86_64/shared/sysdep/syscalls.h
+++ b/arch/x86/um/shared/sysdep/syscalls_64.h
@@ -9,7 +9,6 @@
#include <linux/msg.h>
#include <linux/shm.h>
-#include <kern_constants.h>
typedef long syscall_handler_t(void);
diff --git a/arch/um/sys-i386/shared/sysdep/tls.h b/arch/x86/um/shared/sysdep/tls.h
similarity index 79%
rename from arch/um/sys-i386/shared/sysdep/tls.h
rename to arch/x86/um/shared/sysdep/tls.h
index 3455075..27cce00 100644
--- a/arch/um/sys-i386/shared/sysdep/tls.h
+++ b/arch/x86/um/shared/sysdep/tls.h
@@ -17,16 +17,23 @@
unsigned int limit_in_pages:1;
unsigned int seg_not_present:1;
unsigned int useable:1;
+#ifdef __x86_64__
+ unsigned int lm:1;
+#endif
} user_desc_t;
# else /* __KERNEL__ */
-# include <ldt.h>
typedef struct user_desc user_desc_t;
# endif /* __KERNEL__ */
+extern int os_set_thread_area(user_desc_t *info, int pid);
+extern int os_get_thread_area(user_desc_t *info, int pid);
+
+#ifdef __i386__
#define GDT_ENTRY_TLS_MIN_I386 6
#define GDT_ENTRY_TLS_MIN_X86_64 12
+#endif
#endif /* _SYSDEP_TLS_H */
diff --git a/arch/um/sys-i386/signal.c b/arch/x86/um/signal.c
similarity index 69%
rename from arch/um/sys-i386/signal.c
rename to arch/x86/um/signal.c
index 89a4662..4883b95 100644
--- a/arch/um/sys-i386/signal.c
+++ b/arch/x86/um/signal.c
@@ -1,36 +1,20 @@
/*
- * Copyright (C) 2004 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright (C) 2003 PathScale, Inc.
+ * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*/
+
+#include <linux/personality.h>
#include <linux/ptrace.h>
+#include <linux/kernel.h>
#include <asm/unistd.h>
#include <asm/uaccess.h>
#include <asm/ucontext.h>
#include "frame_kern.h"
#include "skas.h"
-void copy_sc(struct uml_pt_regs *regs, void *from)
-{
- struct sigcontext *sc = from;
-
- REGS_GS(regs->gp) = sc->gs;
- REGS_FS(regs->gp) = sc->fs;
- REGS_ES(regs->gp) = sc->es;
- REGS_DS(regs->gp) = sc->ds;
- REGS_EDI(regs->gp) = sc->di;
- REGS_ESI(regs->gp) = sc->si;
- REGS_EBP(regs->gp) = sc->bp;
- REGS_SP(regs->gp) = sc->sp;
- REGS_EBX(regs->gp) = sc->bx;
- REGS_EDX(regs->gp) = sc->dx;
- REGS_ECX(regs->gp) = sc->cx;
- REGS_EAX(regs->gp) = sc->ax;
- REGS_IP(regs->gp) = sc->ip;
- REGS_CS(regs->gp) = sc->cs;
- REGS_EFLAGS(regs->gp) = sc->flags;
- REGS_SS(regs->gp) = sc->ss;
-}
+#ifdef CONFIG_X86_32
/*
* FPU tag word conversions.
@@ -164,6 +148,8 @@
extern int have_fpx_regs;
+#endif
+
static int copy_sc_from_user(struct pt_regs *regs,
struct sigcontext __user *from)
{
@@ -174,8 +160,45 @@
if (err)
return err;
+#define GETREG(regno, regname) regs->regs.gp[HOST_##regno] = sc.regname
+
+#ifdef CONFIG_X86_32
+ GETREG(GS, gs);
+ GETREG(FS, fs);
+ GETREG(ES, es);
+ GETREG(DS, ds);
+#endif
+ GETREG(DI, di);
+ GETREG(SI, si);
+ GETREG(BP, bp);
+ GETREG(SP, sp);
+ GETREG(BX, bx);
+ GETREG(DX, dx);
+ GETREG(CX, cx);
+ GETREG(AX, ax);
+ GETREG(IP, ip);
+
+#ifdef CONFIG_X86_64
+ GETREG(R8, r8);
+ GETREG(R9, r9);
+ GETREG(R10, r10);
+ GETREG(R11, r11);
+ GETREG(R12, r12);
+ GETREG(R13, r13);
+ GETREG(R14, r14);
+ GETREG(R15, r15);
+#endif
+
+ GETREG(CS, cs);
+ GETREG(EFLAGS, flags);
+#ifdef CONFIG_X86_32
+ GETREG(SS, ss);
+#endif
+
+#undef GETREG
+
pid = userspace_pid[current_thread_info()->cpu];
- copy_sc(®s->regs, &sc);
+#ifdef CONFIG_X86_32
if (have_fpx_regs) {
struct user_fxsr_struct fpx;
@@ -196,8 +219,9 @@
-err);
return 1;
}
- }
- else {
+ } else
+#endif
+ {
struct user_i387_struct fp;
err = copy_from_user(&fp, sc.fpstate,
@@ -213,43 +237,66 @@
return 1;
}
}
-
return 0;
}
static int copy_sc_to_user(struct sigcontext __user *to,
struct _fpstate __user *to_fp, struct pt_regs *regs,
- unsigned long sp)
+ unsigned long mask)
{
struct sigcontext sc;
struct faultinfo * fi = ¤t->thread.arch.faultinfo;
int err, pid;
+ memset(&sc, 0, sizeof(struct sigcontext));
- sc.gs = REGS_GS(regs->regs.gp);
- sc.fs = REGS_FS(regs->regs.gp);
- sc.es = REGS_ES(regs->regs.gp);
- sc.ds = REGS_DS(regs->regs.gp);
- sc.di = REGS_EDI(regs->regs.gp);
- sc.si = REGS_ESI(regs->regs.gp);
- sc.bp = REGS_EBP(regs->regs.gp);
- sc.sp = sp;
- sc.bx = REGS_EBX(regs->regs.gp);
- sc.dx = REGS_EDX(regs->regs.gp);
- sc.cx = REGS_ECX(regs->regs.gp);
- sc.ax = REGS_EAX(regs->regs.gp);
- sc.ip = REGS_IP(regs->regs.gp);
- sc.cs = REGS_CS(regs->regs.gp);
- sc.flags = REGS_EFLAGS(regs->regs.gp);
- sc.sp_at_signal = regs->regs.gp[UESP];
- sc.ss = regs->regs.gp[SS];
+#define PUTREG(regno, regname) sc.regname = regs->regs.gp[HOST_##regno]
+
+#ifdef CONFIG_X86_32
+ PUTREG(GS, gs);
+ PUTREG(FS, fs);
+ PUTREG(ES, es);
+ PUTREG(DS, ds);
+#endif
+ PUTREG(DI, di);
+ PUTREG(SI, si);
+ PUTREG(BP, bp);
+ PUTREG(SP, sp);
+ PUTREG(BX, bx);
+ PUTREG(DX, dx);
+ PUTREG(CX, cx);
+ PUTREG(AX, ax);
+#ifdef CONFIG_X86_64
+ PUTREG(R8, r8);
+ PUTREG(R9, r9);
+ PUTREG(R10, r10);
+ PUTREG(R11, r11);
+ PUTREG(R12, r12);
+ PUTREG(R13, r13);
+ PUTREG(R14, r14);
+ PUTREG(R15, r15);
+#endif
+
sc.cr2 = fi->cr2;
sc.err = fi->error_code;
sc.trapno = fi->trap_no;
-
- to_fp = (to_fp ? to_fp : (struct _fpstate __user *) (to + 1));
+ PUTREG(IP, ip);
+ PUTREG(CS, cs);
+ PUTREG(EFLAGS, flags);
+#ifdef CONFIG_X86_32
+ PUTREG(SP, sp_at_signal);
+ PUTREG(SS, ss);
+#endif
+#undef PUTREG
+ sc.oldmask = mask;
sc.fpstate = to_fp;
+ err = copy_to_user(to, &sc, sizeof(struct sigcontext));
+ if (err)
+ return 1;
+
pid = userspace_pid[current_thread_info()->cpu];
+
+#ifdef CONFIG_X86_32
if (have_fpx_regs) {
struct user_fxsr_struct fpx;
@@ -272,8 +319,9 @@
if (copy_to_user(&to_fp->_fxsr_env[0], &fpx,
sizeof(struct user_fxsr_struct)))
return 1;
- }
- else {
+ } else
+#endif
+ {
struct user_i387_struct fp;
err = save_fp_registers(pid, (unsigned long *) &fp);
@@ -281,9 +329,10 @@
return 1;
}
- return copy_to_user(to, &sc, sizeof(sc));
+ return 0;
}
+#ifdef CONFIG_X86_32
static int copy_ucontext_to_user(struct ucontext __user *uc,
struct _fpstate __user *fp, sigset_t *set,
unsigned long sp)
@@ -293,7 +342,7 @@
err |= put_user(current->sas_ss_sp, &uc->uc_stack.ss_sp);
err |= put_user(sas_ss_flags(sp), &uc->uc_stack.ss_flags);
err |= put_user(current->sas_ss_size, &uc->uc_stack.ss_size);
- err |= copy_sc_to_user(&uc->uc_mcontext, fp, ¤t->thread.regs, sp);
+ err |= copy_sc_to_user(&uc->uc_mcontext, fp, ¤t->thread.regs, 0);
err |= copy_to_user(&uc->uc_sigmask, set, sizeof(*set));
return err;
}
@@ -326,7 +375,6 @@
{
struct sigframe __user *frame;
void __user *restorer;
- unsigned long save_sp = PT_REGS_SP(regs);
int err = 0;
/* This is the same calculation as i386 - ((sp + 4) & 15) == 0 */
@@ -339,20 +387,9 @@
if (ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
- /* Update SP now because the page fault handler refuses to extend
- * the stack if the faulting address is too far below the current
- * SP, which frame now certainly is. If there's an error, the original
- * value is restored on the way out.
- * When writing the sigcontext to the stack, we have to write the
- * original value, so that's passed to copy_sc_to_user, which does
- * the right thing with it.
- */
- PT_REGS_SP(regs) = (unsigned long) frame;
-
err |= __put_user(restorer, &frame->pretcode);
err |= __put_user(sig, &frame->sig);
- err |= copy_sc_to_user(&frame->sc, NULL, regs, save_sp);
- err |= __put_user(mask->sig[0], &frame->sc.oldmask);
+ err |= copy_sc_to_user(&frame->sc, &frame->fpstate, regs, mask->sig[0]);
if (_NSIG_WORDS > 1)
err |= __copy_to_user(&frame->extramask, &mask->sig[1],
sizeof(frame->extramask));
@@ -369,7 +406,7 @@
err |= __put_user(0x80cd, (short __user *)(frame->retcode+6));
if (err)
- goto err;
+ return err;
PT_REGS_SP(regs) = (unsigned long) frame;
PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler;
@@ -380,10 +417,6 @@
if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
ptrace_notify(SIGTRAP);
return 0;
-
-err:
- PT_REGS_SP(regs) = save_sp;
- return err;
}
int setup_signal_stack_si(unsigned long stack_top, int sig,
@@ -392,7 +425,6 @@
{
struct rt_sigframe __user *frame;
void __user *restorer;
- unsigned long save_sp = PT_REGS_SP(regs);
int err = 0;
stack_top &= -8UL;
@@ -404,16 +436,13 @@
if (ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
- /* See comment above about why this is here */
- PT_REGS_SP(regs) = (unsigned long) frame;
-
err |= __put_user(restorer, &frame->pretcode);
err |= __put_user(sig, &frame->sig);
err |= __put_user(&frame->info, &frame->pinfo);
err |= __put_user(&frame->uc, &frame->puc);
err |= copy_siginfo_to_user(&frame->info, info);
err |= copy_ucontext_to_user(&frame->uc, &frame->fpstate, mask,
- save_sp);
+ PT_REGS_SP(regs));
/*
* This is movl $,%eax ; int $0x80
@@ -427,8 +456,9 @@
err |= __put_user(0x80cd, (short __user *)(frame->retcode+5));
if (err)
- goto err;
+ return err;
+ PT_REGS_SP(regs) = (unsigned long) frame;
PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler;
PT_REGS_EAX(regs) = (unsigned long) sig;
PT_REGS_EDX(regs) = (unsigned long) &frame->info;
@@ -437,13 +467,9 @@
if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
ptrace_notify(SIGTRAP);
return 0;
-
-err:
- PT_REGS_SP(regs) = save_sp;
- return err;
}
-long sys_sigreturn(struct pt_regs regs)
+long sys_sigreturn(struct pt_regs *regs)
{
unsigned long sp = PT_REGS_SP(¤t->thread.regs);
struct sigframe __user *frame = (struct sigframe __user *)(sp - 8);
@@ -458,11 +484,7 @@
goto segfault;
sigdelsetmask(&set, ~_BLOCKABLE);
-
- spin_lock_irq(¤t->sighand->siglock);
- current->blocked = set;
- recalc_sigpending();
- spin_unlock_irq(¤t->sighand->siglock);
+ set_current_blocked(&set);
if (copy_sc_from_user(¤t->thread.regs, sc))
goto segfault;
@@ -476,24 +498,107 @@
return 0;
}
-long sys_rt_sigreturn(struct pt_regs regs)
+#else
+
+struct rt_sigframe
+{
+ char __user *pretcode;
+ struct ucontext uc;
+ struct siginfo info;
+ struct _fpstate fpstate;
+};
+
+int setup_signal_stack_si(unsigned long stack_top, int sig,
+ struct k_sigaction *ka, struct pt_regs * regs,
+ siginfo_t *info, sigset_t *set)
+{
+ struct rt_sigframe __user *frame;
+ int err = 0;
+ struct task_struct *me = current;
+
+ frame = (struct rt_sigframe __user *)
+ round_down(stack_top - sizeof(struct rt_sigframe), 16);
+ /* Subtract 128 for a red zone and 8 for proper alignment */
+ frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8);
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto out;
+
+ if (ka->sa.sa_flags & SA_SIGINFO) {
+ err |= copy_siginfo_to_user(&frame->info, info);
+ if (err)
+ goto out;
+ }
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(0, &frame->uc.uc_link);
+ err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ err |= __put_user(sas_ss_flags(PT_REGS_SP(regs)),
+ &frame->uc.uc_stack.ss_flags);
+ err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs,
+ set->sig[0]);
+ err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate);
+ if (sizeof(*set) == 16) {
+ __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
+ __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
+ }
+ else
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set,
+ sizeof(*set));
+
+ /*
+ * Set up to return from userspace. If provided, use a stub
+ * already in userspace.
+ */
+ /* x86-64 should always use SA_RESTORER. */
+ if (ka->sa.sa_flags & SA_RESTORER)
+ err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+ else
+ /* could use a vstub here */
+ return err;
+
+ if (err)
+ return err;
+
+ /* Set up registers for signal handler */
+ {
+ struct exec_domain *ed = current_thread_info()->exec_domain;
+ if (unlikely(ed && ed->signal_invmap && sig < 32))
+ sig = ed->signal_invmap[sig];
+ }
+
+ PT_REGS_SP(regs) = (unsigned long) frame;
+ PT_REGS_RDI(regs) = sig;
+ /* In case the signal handler was declared without prototypes */
+ PT_REGS_RAX(regs) = 0;
+
+ /*
+ * This also works for non SA_SIGINFO handlers because they expect the
+ * next argument after the signal number on the stack.
+ */
+ PT_REGS_RSI(regs) = (unsigned long) &frame->info;
+ PT_REGS_RDX(regs) = (unsigned long) &frame->uc;
+ PT_REGS_RIP(regs) = (unsigned long) ka->sa.sa_handler;
+ out:
+ return err;
+}
+#endif
+
+long sys_rt_sigreturn(struct pt_regs *regs)
{
unsigned long sp = PT_REGS_SP(¤t->thread.regs);
struct rt_sigframe __user *frame =
- (struct rt_sigframe __user *) (sp - 4);
- sigset_t set;
+ (struct rt_sigframe __user *)(sp - sizeof(long));
struct ucontext __user *uc = &frame->uc;
- int sig_size = _NSIG_WORDS * sizeof(unsigned long);
+ sigset_t set;
- if (copy_from_user(&set, &uc->uc_sigmask, sig_size))
+ if (copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
goto segfault;
sigdelsetmask(&set, ~_BLOCKABLE);
-
- spin_lock_irq(¤t->sighand->siglock);
- current->blocked = set;
- recalc_sigpending();
- spin_unlock_irq(¤t->sighand->siglock);
+ set_current_blocked(&set);
if (copy_sc_from_user(¤t->thread.regs, &uc->uc_mcontext))
goto segfault;
@@ -506,3 +611,14 @@
force_sig(SIGSEGV, current);
return 0;
}
+
+#ifdef CONFIG_X86_32
+long ptregs_sigreturn(void)
+{
+ return sys_sigreturn(NULL);
+}
+long ptregs_rt_sigreturn(void)
+{
+ return sys_rt_sigreturn(NULL);
+}
+#endif
diff --git a/arch/um/sys-i386/stub.S b/arch/x86/um/stub_32.S
similarity index 100%
rename from arch/um/sys-i386/stub.S
rename to arch/x86/um/stub_32.S
diff --git a/arch/um/sys-x86_64/stub.S b/arch/x86/um/stub_64.S
similarity index 100%
rename from arch/um/sys-x86_64/stub.S
rename to arch/x86/um/stub_64.S
diff --git a/arch/x86/um/stub_segv.c b/arch/x86/um/stub_segv.c
new file mode 100644
index 0000000..b7450bd
--- /dev/null
+++ b/arch/x86/um/stub_segv.c
@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) 2004 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#include "sysdep/stub.h"
+#include "sysdep/faultinfo.h"
+#include "sysdep/mcontext.h"
+
+void __attribute__ ((__section__ (".__syscall_stub")))
+stub_segv_handler(int sig, siginfo_t *info, void *p)
+{
+ struct ucontext *uc = p;
+
+ GET_FAULTINFO_FROM_MC(*((struct faultinfo *) STUB_DATA),
+ &uc->uc_mcontext);
+ trap_myself();
+}
+
diff --git a/arch/um/sys-i386/sys_call_table.S b/arch/x86/um/sys_call_table_32.S
similarity index 81%
rename from arch/um/sys-i386/sys_call_table.S
rename to arch/x86/um/sys_call_table_32.S
index de274071..a7ca80d 100644
--- a/arch/um/sys-i386/sys_call_table.S
+++ b/arch/x86/um/sys_call_table_32.S
@@ -13,16 +13,14 @@
#define ptregs_execve sys_execve
#define ptregs_iopl sys_iopl
#define ptregs_vm86old sys_vm86old
-#define ptregs_sigreturn sys_sigreturn
#define ptregs_clone sys_clone
#define ptregs_vm86 sys_vm86
-#define ptregs_rt_sigreturn sys_rt_sigreturn
#define ptregs_sigaltstack sys_sigaltstack
#define ptregs_vfork sys_vfork
.section .rodata,"a"
-#include "../../x86/kernel/syscall_table_32.S"
+#include "../kernel/syscall_table_32.S"
ENTRY(syscall_table_size)
.long .-sys_call_table
diff --git a/arch/um/sys-x86_64/syscall_table.c b/arch/x86/um/sys_call_table_64.c
similarity index 95%
rename from arch/um/sys-x86_64/syscall_table.c
rename to arch/x86/um/sys_call_table_64.c
index 47d469e..99522f7 100644
--- a/arch/um/sys-x86_64/syscall_table.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -6,7 +6,6 @@
#include <linux/linkage.h>
#include <linux/sys.h>
#include <linux/cache.h>
-#include <kern_constants.h>
#define __NO_STUBS
@@ -59,7 +58,7 @@
*/
sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
-#include "../../x86/include/asm/unistd_64.h"
+#include <asm/unistd_64.h>
};
int syscall_table_size = sizeof(sys_call_table);
diff --git a/arch/um/sys-i386/syscalls.c b/arch/x86/um/syscalls_32.c
similarity index 100%
rename from arch/um/sys-i386/syscalls.c
rename to arch/x86/um/syscalls_32.c
diff --git a/arch/um/sys-x86_64/syscalls.c b/arch/x86/um/syscalls_64.c
similarity index 100%
rename from arch/um/sys-x86_64/syscalls.c
rename to arch/x86/um/syscalls_64.c
diff --git a/arch/um/sys-i386/sysrq.c b/arch/x86/um/sysrq_32.c
similarity index 100%
rename from arch/um/sys-i386/sysrq.c
rename to arch/x86/um/sysrq_32.c
diff --git a/arch/um/sys-x86_64/sysrq.c b/arch/x86/um/sysrq_64.c
similarity index 94%
rename from arch/um/sys-x86_64/sysrq.c
rename to arch/x86/um/sysrq_64.c
index f4f82be..e891343 100644
--- a/arch/um/sys-x86_64/sysrq.c
+++ b/arch/x86/um/sysrq_64.c
@@ -20,7 +20,7 @@
current->comm, print_tainted(), init_utsname()->release);
printk(KERN_INFO "RIP: %04lx:[<%016lx>]\n", PT_REGS_CS(regs) & 0xffff,
PT_REGS_RIP(regs));
- printk(KERN_INFO "RSP: %016lx EFLAGS: %08lx\n", PT_REGS_RSP(regs),
+ printk(KERN_INFO "RSP: %016lx EFLAGS: %08lx\n", PT_REGS_SP(regs),
PT_REGS_EFLAGS(regs));
printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
PT_REGS_RAX(regs), PT_REGS_RBX(regs), PT_REGS_RCX(regs));
diff --git a/arch/um/sys-i386/tls.c b/arch/x86/um/tls_32.c
similarity index 100%
rename from arch/um/sys-i386/tls.c
rename to arch/x86/um/tls_32.c
diff --git a/arch/um/sys-x86_64/tls.c b/arch/x86/um/tls_64.c
similarity index 100%
rename from arch/um/sys-x86_64/tls.c
rename to arch/x86/um/tls_64.c
diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c
new file mode 100644
index 0000000..ca49be8
--- /dev/null
+++ b/arch/x86/um/user-offsets.c
@@ -0,0 +1,80 @@
+#include <stdio.h>
+#include <stddef.h>
+#include <signal.h>
+#include <sys/poll.h>
+#include <sys/mman.h>
+#include <sys/user.h>
+#define __FRAME_OFFSETS
+#include <asm/ptrace.h>
+#include <asm/types.h>
+
+#define DEFINE(sym, val) \
+ asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+
+#define DEFINE_LONGS(sym, val) \
+ asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long)))
+
+void foo(void)
+{
+#ifdef __i386__
+ DEFINE_LONGS(HOST_FP_SIZE, sizeof(struct user_fpregs_struct));
+ DEFINE_LONGS(HOST_FPX_SIZE, sizeof(struct user_fpxregs_struct));
+
+ DEFINE(HOST_IP, EIP);
+ DEFINE(HOST_SP, UESP);
+ DEFINE(HOST_EFLAGS, EFL);
+ DEFINE(HOST_AX, EAX);
+ DEFINE(HOST_BX, EBX);
+ DEFINE(HOST_CX, ECX);
+ DEFINE(HOST_DX, EDX);
+ DEFINE(HOST_SI, ESI);
+ DEFINE(HOST_DI, EDI);
+ DEFINE(HOST_BP, EBP);
+ DEFINE(HOST_CS, CS);
+ DEFINE(HOST_SS, SS);
+ DEFINE(HOST_DS, DS);
+ DEFINE(HOST_FS, FS);
+ DEFINE(HOST_ES, ES);
+ DEFINE(HOST_GS, GS);
+ DEFINE(HOST_ORIG_AX, ORIG_EAX);
+#else
+ DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long));
+ DEFINE_LONGS(HOST_BX, RBX);
+ DEFINE_LONGS(HOST_CX, RCX);
+ DEFINE_LONGS(HOST_DI, RDI);
+ DEFINE_LONGS(HOST_SI, RSI);
+ DEFINE_LONGS(HOST_DX, RDX);
+ DEFINE_LONGS(HOST_BP, RBP);
+ DEFINE_LONGS(HOST_AX, RAX);
+ DEFINE_LONGS(HOST_R8, R8);
+ DEFINE_LONGS(HOST_R9, R9);
+ DEFINE_LONGS(HOST_R10, R10);
+ DEFINE_LONGS(HOST_R11, R11);
+ DEFINE_LONGS(HOST_R12, R12);
+ DEFINE_LONGS(HOST_R13, R13);
+ DEFINE_LONGS(HOST_R14, R14);
+ DEFINE_LONGS(HOST_R15, R15);
+ DEFINE_LONGS(HOST_ORIG_AX, ORIG_RAX);
+ DEFINE_LONGS(HOST_CS, CS);
+ DEFINE_LONGS(HOST_SS, SS);
+ DEFINE_LONGS(HOST_EFLAGS, EFLAGS);
+#if 0
+ DEFINE_LONGS(HOST_FS, FS);
+ DEFINE_LONGS(HOST_GS, GS);
+ DEFINE_LONGS(HOST_DS, DS);
+ DEFINE_LONGS(HOST_ES, ES);
+#endif
+
+ DEFINE_LONGS(HOST_IP, RIP);
+ DEFINE_LONGS(HOST_SP, RSP);
+#endif
+
+ DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct));
+ DEFINE(UM_POLLIN, POLLIN);
+ DEFINE(UM_POLLPRI, POLLPRI);
+ DEFINE(UM_POLLOUT, POLLOUT);
+
+ DEFINE(UM_PROT_READ, PROT_READ);
+ DEFINE(UM_PROT_WRITE, PROT_WRITE);
+ DEFINE(UM_PROT_EXEC, PROT_EXEC);
+}
diff --git a/arch/um/sys-x86_64/vdso/Makefile b/arch/x86/um/vdso/Makefile
similarity index 94%
rename from arch/um/sys-x86_64/vdso/Makefile
rename to arch/x86/um/vdso/Makefile
index 5dffe6d..6c803ca 100644
--- a/arch/um/sys-x86_64/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -46,8 +46,8 @@
#
# vDSO code runs in userspace and -pg doesn't help with profiling anyway.
#
-CFLAGS_REMOVE_vdso-note.o = -pg
-CFLAGS_REMOVE_um_vdso.o = -pg
+CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage
+CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage
targets += vdso-syms.lds
obj-$(VDSO64-y) += vdso-syms.lds
diff --git a/arch/um/sys-x86_64/vdso/checkundef.sh b/arch/x86/um/vdso/checkundef.sh
similarity index 100%
rename from arch/um/sys-x86_64/vdso/checkundef.sh
rename to arch/x86/um/vdso/checkundef.sh
diff --git a/arch/um/sys-x86_64/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c
similarity index 100%
rename from arch/um/sys-x86_64/vdso/um_vdso.c
rename to arch/x86/um/vdso/um_vdso.c
diff --git a/arch/um/sys-x86_64/vdso/vdso-layout.lds.S b/arch/x86/um/vdso/vdso-layout.lds.S
similarity index 100%
rename from arch/um/sys-x86_64/vdso/vdso-layout.lds.S
rename to arch/x86/um/vdso/vdso-layout.lds.S
diff --git a/arch/um/sys-x86_64/vdso/vdso-note.S b/arch/x86/um/vdso/vdso-note.S
similarity index 100%
rename from arch/um/sys-x86_64/vdso/vdso-note.S
rename to arch/x86/um/vdso/vdso-note.S
diff --git a/arch/um/sys-x86_64/vdso/vdso.S b/arch/x86/um/vdso/vdso.S
similarity index 69%
rename from arch/um/sys-x86_64/vdso/vdso.S
rename to arch/x86/um/vdso/vdso.S
index ec82c16..1cb468a 100644
--- a/arch/um/sys-x86_64/vdso/vdso.S
+++ b/arch/x86/um/vdso/vdso.S
@@ -4,7 +4,7 @@
.globl vdso_start, vdso_end
vdso_start:
- .incbin "arch/um/sys-x86_64/vdso/vdso.so"
+ .incbin "arch/x86/um/vdso/vdso.so"
vdso_end:
__FINIT
diff --git a/arch/um/sys-x86_64/vdso/vdso.lds.S b/arch/x86/um/vdso/vdso.lds.S
similarity index 100%
rename from arch/um/sys-x86_64/vdso/vdso.lds.S
rename to arch/x86/um/vdso/vdso.lds.S
diff --git a/arch/um/sys-x86_64/vdso/vma.c b/arch/x86/um/vdso/vma.c
similarity index 95%
rename from arch/um/sys-x86_64/vdso/vma.c
rename to arch/x86/um/vdso/vma.c
index 9495c8d..91f4ec9 100644
--- a/arch/um/sys-x86_64/vdso/vma.c
+++ b/arch/x86/um/vdso/vma.c
@@ -28,7 +28,7 @@
um_vdso_addr = task_size - PAGE_SIZE;
- vdsop = kmalloc(GFP_KERNEL, sizeof(struct page *));
+ vdsop = kmalloc(sizeof(struct page *), GFP_KERNEL);
if (!vdsop)
goto oom;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 079c088..e7a5750 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -8,10 +8,13 @@
#include <linux/scatterlist.h>
#include <linux/string_helpers.h>
#include <scsi/scsi_cmnd.h>
+#include <linux/idr.h>
#define PART_BITS 4
-static int major, index;
+static int major;
+static DEFINE_IDA(vd_index_ida);
+
struct workqueue_struct *virtblk_wq;
struct virtio_blk
@@ -35,6 +38,9 @@
/* What host tells us, plus 2 for header & tailer. */
unsigned int sg_elems;
+ /* Ida index - used to track minor number allocations. */
+ int index;
+
/* Scatterlist: can be too big for stack. */
struct scatterlist sg[/*sg_elems*/];
};
@@ -276,6 +282,11 @@
return index << PART_BITS;
}
+static int minor_to_index(int minor)
+{
+ return minor >> PART_BITS;
+}
+
static ssize_t virtblk_serial_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -341,14 +352,17 @@
{
struct virtio_blk *vblk;
struct request_queue *q;
- int err;
+ int err, index;
u64 cap;
u32 v, blk_size, sg_elems, opt_io_size;
u16 min_io_size;
u8 physical_block_exp, alignment_offset;
- if (index_to_minor(index) >= 1 << MINORBITS)
- return -ENOSPC;
+ err = ida_simple_get(&vd_index_ida, 0, minor_to_index(1 << MINORBITS),
+ GFP_KERNEL);
+ if (err < 0)
+ goto out;
+ index = err;
/* We need to know how many segments before we allocate. */
err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX,
@@ -365,7 +379,7 @@
sizeof(vblk->sg[0]) * sg_elems, GFP_KERNEL);
if (!vblk) {
err = -ENOMEM;
- goto out;
+ goto out_free_index;
}
INIT_LIST_HEAD(&vblk->reqs);
@@ -421,7 +435,7 @@
vblk->disk->private_data = vblk;
vblk->disk->fops = &virtblk_fops;
vblk->disk->driverfs_dev = &vdev->dev;
- index++;
+ vblk->index = index;
/* configure queue flush support */
if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
@@ -516,6 +530,8 @@
vdev->config->del_vqs(vdev);
out_free_vblk:
kfree(vblk);
+out_free_index:
+ ida_simple_remove(&vd_index_ida, index);
out:
return err;
}
@@ -523,6 +539,7 @@
static void __devexit virtblk_remove(struct virtio_device *vdev)
{
struct virtio_blk *vblk = vdev->priv;
+ int index = vblk->index;
flush_work(&vblk->config_work);
@@ -538,6 +555,7 @@
mempool_destroy(vblk->pool);
vdev->config->del_vqs(vdev);
kfree(vblk);
+ ida_simple_remove(&vd_index_ida, index);
}
static const struct virtio_device_id id_table[] = {
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 423fd56..4364303 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -298,7 +298,7 @@
config RTC
tristate "Enhanced Real Time Clock Support (legacy PC RTC driver)"
depends on !PPC && !PARISC && !IA64 && !M68K && !SPARC && !FRV \
- && !ARM && !SUPERH && !S390 && !AVR32 && !BLACKFIN
+ && !ARM && !SUPERH && !S390 && !AVR32 && !BLACKFIN && !UML
---help---
If you say Y here and create a character special file /dev/rtc with
major number 10 and minor number 135 using mknod ("man mknod"), you
@@ -346,7 +346,7 @@
config GEN_RTC
tristate "Generic /dev/rtc emulation"
- depends on RTC!=y && !IA64 && !ARM && !M32R && !MIPS && !SPARC && !FRV && !S390 && !SUPERH && !AVR32 && !BLACKFIN
+ depends on RTC!=y && !IA64 && !ARM && !M32R && !MIPS && !SPARC && !FRV && !S390 && !SUPERH && !AVR32 && !BLACKFIN && !UML
---help---
If you say Y here and create a character special file /dev/rtc with
major number 10 and minor number 135 using mknod ("man mknod"), you
@@ -490,7 +490,7 @@
config PC8736x_GPIO
tristate "NatSemi PC8736x GPIO Support"
- depends on X86_32
+ depends on X86_32 && !UML
default SCx200_GPIO # mostly N
select NSC_GPIO # needed for support routines
help
diff --git a/drivers/char/agp/hp-agp.c b/drivers/char/agp/hp-agp.c
index 056b289..3695773 100644
--- a/drivers/char/agp/hp-agp.c
+++ b/drivers/char/agp/hp-agp.c
@@ -336,7 +336,8 @@
off_t j, io_pg_start;
int io_pg_count;
- if (type != 0 || mem->type != 0) {
+ if (type != mem->type ||
+ agp_bridge->driver->agp_type_to_mask_type(agp_bridge, type)) {
return -EINVAL;
}
@@ -380,7 +381,8 @@
struct _hp_private *hp = &hp_private;
int i, io_pg_start, io_pg_count;
- if (type != 0 || mem->type != 0) {
+ if (type != mem->type ||
+ agp_bridge->driver->agp_type_to_mask_type(agp_bridge, type)) {
return -EINVAL;
}
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index e013587..0689bf6 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -235,3 +235,18 @@
module will be called ppc4xx-rng.
If unsure, say N.
+
+config UML_RANDOM
+ depends on UML
+ tristate "Hardware random number generator"
+ help
+ This option enables UML's "hardware" random number generator. It
+ attaches itself to the host's /dev/random, supplying as much entropy
+ as the host has, rather than the small amount the UML gets from its
+ own drivers. It registers itself as a standard hardware random number
+ generator, major 10, minor 183, and the canonical device name is
+ /dev/hwrng.
+ The way to make use of this is to install the rng-tools package
+ (check your distro, or download from
+ http://sourceforge.net/projects/gkernel/). rngd periodically reads
+ /dev/hwrng and injects the entropy into /dev/random.
diff --git a/drivers/char/ttyprintk.c b/drivers/char/ttyprintk.c
index a1f68af..f228615 100644
--- a/drivers/char/ttyprintk.c
+++ b/drivers/char/ttyprintk.c
@@ -170,7 +170,7 @@
.ioctl = tpk_ioctl,
};
-struct tty_port_operations null_ops = { };
+static struct tty_port_operations null_ops = { };
static struct tty_driver *ttyprintk_driver;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index fb68b12..4ca181f 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -19,8 +19,10 @@
*/
#include <linux/cdev.h>
#include <linux/debugfs.h>
+#include <linux/completion.h>
#include <linux/device.h>
#include <linux/err.h>
+#include <linux/freezer.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/list.h>
@@ -73,6 +75,7 @@
static struct ports_driver_data pdrvdata;
DEFINE_SPINLOCK(pdrvdata_lock);
+DECLARE_COMPLETION(early_console_added);
/* This struct holds information that's relevant only for console ports */
struct console {
@@ -151,6 +154,10 @@
int chr_major;
};
+struct port_stats {
+ unsigned long bytes_sent, bytes_received, bytes_discarded;
+};
+
/* This struct holds the per-port data */
struct port {
/* Next port in the list, head is in the ports_device */
@@ -179,6 +186,13 @@
struct dentry *debugfs_file;
/*
+ * Keep count of the bytes sent, received and discarded for
+ * this port for accounting and debugging purposes. These
+ * counts are not reset across port open / close events.
+ */
+ struct port_stats stats;
+
+ /*
* The entries in this struct will be valid if this port is
* hooked up to an hvc console
*/
@@ -347,17 +361,19 @@
}
/* Callers should take appropriate locks */
-static void *get_inbuf(struct port *port)
+static struct port_buffer *get_inbuf(struct port *port)
{
struct port_buffer *buf;
- struct virtqueue *vq;
unsigned int len;
- vq = port->in_vq;
- buf = virtqueue_get_buf(vq, &len);
+ if (port->inbuf)
+ return port->inbuf;
+
+ buf = virtqueue_get_buf(port->in_vq, &len);
if (buf) {
buf->len = len;
buf->offset = 0;
+ port->stats.bytes_received += len;
}
return buf;
}
@@ -384,32 +400,27 @@
static void discard_port_data(struct port *port)
{
struct port_buffer *buf;
- struct virtqueue *vq;
- unsigned int len;
- int ret;
+ unsigned int err;
if (!port->portdev) {
/* Device has been unplugged. vqs are already gone. */
return;
}
- vq = port->in_vq;
- if (port->inbuf)
- buf = port->inbuf;
- else
- buf = virtqueue_get_buf(vq, &len);
+ buf = get_inbuf(port);
- ret = 0;
+ err = 0;
while (buf) {
- if (add_inbuf(vq, buf) < 0) {
- ret++;
+ port->stats.bytes_discarded += buf->len - buf->offset;
+ if (add_inbuf(port->in_vq, buf) < 0) {
+ err++;
free_buf(buf);
}
- buf = virtqueue_get_buf(vq, &len);
+ port->inbuf = NULL;
+ buf = get_inbuf(port);
}
- port->inbuf = NULL;
- if (ret)
+ if (err)
dev_warn(port->dev, "Errors adding %d buffers back to vq\n",
- ret);
+ err);
}
static bool port_has_data(struct port *port)
@@ -417,18 +428,12 @@
unsigned long flags;
bool ret;
- spin_lock_irqsave(&port->inbuf_lock, flags);
- if (port->inbuf) {
- ret = true;
- goto out;
- }
- port->inbuf = get_inbuf(port);
- if (port->inbuf) {
- ret = true;
- goto out;
- }
ret = false;
-out:
+ spin_lock_irqsave(&port->inbuf_lock, flags);
+ port->inbuf = get_inbuf(port);
+ if (port->inbuf)
+ ret = true;
+
spin_unlock_irqrestore(&port->inbuf_lock, flags);
return ret;
}
@@ -529,6 +534,8 @@
cpu_relax();
done:
spin_unlock_irqrestore(&port->outvq_lock, flags);
+
+ port->stats.bytes_sent += in_count;
/*
* We're expected to return the amount of data we wrote -- all
* of it
@@ -633,8 +640,8 @@
if (filp->f_flags & O_NONBLOCK)
return -EAGAIN;
- ret = wait_event_interruptible(port->waitqueue,
- !will_read_block(port));
+ ret = wait_event_freezable(port->waitqueue,
+ !will_read_block(port));
if (ret < 0)
return ret;
}
@@ -677,8 +684,8 @@
if (nonblock)
return -EAGAIN;
- ret = wait_event_interruptible(port->waitqueue,
- !will_write_block(port));
+ ret = wait_event_freezable(port->waitqueue,
+ !will_write_block(port));
if (ret < 0)
return ret;
}
@@ -1059,6 +1066,14 @@
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"outvq_full: %d\n", port->outvq_full);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "bytes_sent: %lu\n", port->stats.bytes_sent);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "bytes_received: %lu\n",
+ port->stats.bytes_received);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "bytes_discarded: %lu\n",
+ port->stats.bytes_discarded);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
"is_console: %s\n",
is_console_port(port) ? "yes" : "no");
out_offset += snprintf(buf + out_offset, out_count - out_offset,
@@ -1143,6 +1158,7 @@
port->cons.ws.ws_row = port->cons.ws.ws_col = 0;
port->host_connected = port->guest_connected = false;
+ port->stats = (struct port_stats) { 0 };
port->outvq_full = false;
@@ -1352,6 +1368,7 @@
break;
init_port_console(port);
+ complete(&early_console_added);
/*
* Could remove the port here in case init fails - but
* have to notify the host first.
@@ -1394,6 +1411,13 @@
break;
case VIRTIO_CONSOLE_PORT_NAME:
/*
+ * If we woke up after hibernation, we can get this
+ * again. Skip it in that case.
+ */
+ if (port->name)
+ break;
+
+ /*
* Skip the size of the header and the cpkt to get the size
* of the name that was sent
*/
@@ -1481,8 +1505,7 @@
return;
spin_lock_irqsave(&port->inbuf_lock, flags);
- if (!port->inbuf)
- port->inbuf = get_inbuf(port);
+ port->inbuf = get_inbuf(port);
/*
* Don't queue up data when port is closed. This condition
@@ -1563,7 +1586,7 @@
portdev->out_vqs = kmalloc(nr_ports * sizeof(struct virtqueue *),
GFP_KERNEL);
if (!vqs || !io_callbacks || !io_names || !portdev->in_vqs ||
- !portdev->out_vqs) {
+ !portdev->out_vqs) {
err = -ENOMEM;
goto free;
}
@@ -1648,6 +1671,10 @@
struct ports_device *portdev;
int err;
bool multiport;
+ bool early = early_put_chars != NULL;
+
+ /* Ensure to read early_put_chars now */
+ barrier();
portdev = kmalloc(sizeof(*portdev), GFP_KERNEL);
if (!portdev) {
@@ -1675,13 +1702,11 @@
multiport = false;
portdev->config.max_nr_ports = 1;
- if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) {
+ if (virtio_config_val(vdev, VIRTIO_CONSOLE_F_MULTIPORT,
+ offsetof(struct virtio_console_config,
+ max_nr_ports),
+ &portdev->config.max_nr_ports) == 0)
multiport = true;
- vdev->config->get(vdev, offsetof(struct virtio_console_config,
- max_nr_ports),
- &portdev->config.max_nr_ports,
- sizeof(portdev->config.max_nr_ports));
- }
err = init_vqs(portdev);
if (err < 0) {
@@ -1719,6 +1744,19 @@
__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
VIRTIO_CONSOLE_DEVICE_READY, 1);
+
+ /*
+ * If there was an early virtio console, assume that there are no
+ * other consoles. We need to wait until the hvc_alloc matches the
+ * hvc_instantiate, otherwise tty_open will complain, resulting in
+ * a "Warning: unable to open an initial console" boot failure.
+ * Without multiport this is done in add_port above. With multiport
+ * this might take some host<->guest communication - thus we have to
+ * wait.
+ */
+ if (multiport && early)
+ wait_for_completion(&early_console_added);
+
return 0;
free_vqs:
diff --git a/drivers/cpufreq/db8500-cpufreq.c b/drivers/cpufreq/db8500-cpufreq.c
index d90456a..edaa987 100644
--- a/drivers/cpufreq/db8500-cpufreq.c
+++ b/drivers/cpufreq/db8500-cpufreq.c
@@ -12,30 +12,35 @@
#include <linux/cpufreq.h>
#include <linux/delay.h>
#include <linux/slab.h>
-#include <linux/mfd/db8500-prcmu.h>
+#include <linux/mfd/dbx500-prcmu.h>
#include <mach/id.h>
static struct cpufreq_frequency_table freq_table[] = {
[0] = {
.index = 0,
- .frequency = 300000,
+ .frequency = 200000,
},
[1] = {
.index = 1,
- .frequency = 600000,
+ .frequency = 300000,
},
[2] = {
- /* Used for MAX_OPP, if available */
.index = 2,
- .frequency = CPUFREQ_TABLE_END,
+ .frequency = 600000,
},
[3] = {
+ /* Used for MAX_OPP, if available */
.index = 3,
.frequency = CPUFREQ_TABLE_END,
},
+ [4] = {
+ .index = 4,
+ .frequency = CPUFREQ_TABLE_END,
+ },
};
static enum arm_opp idx2opp[] = {
+ ARM_EXTCLK,
ARM_50_OPP,
ARM_100_OPP,
ARM_MAX_OPP
@@ -72,13 +77,13 @@
freqs.old = policy->cur;
freqs.new = freq_table[idx].frequency;
- freqs.cpu = policy->cpu;
if (freqs.old == freqs.new)
return 0;
/* pre-change notification */
- cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+ for_each_cpu(freqs.cpu, policy->cpus)
+ cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
/* request the PRCM unit for opp change */
if (prcmu_set_arm_opp(idx2opp[idx])) {
@@ -87,7 +92,8 @@
}
/* post change notification */
- cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+ for_each_cpu(freqs.cpu, policy->cpus)
+ cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
return 0;
}
@@ -104,16 +110,18 @@
static int __cpuinit db8500_cpufreq_init(struct cpufreq_policy *policy)
{
int res;
- int i;
BUILD_BUG_ON(ARRAY_SIZE(idx2opp) + 1 != ARRAY_SIZE(freq_table));
- if (cpu_is_u8500v2() && !prcmu_is_u8400()) {
- freq_table[0].frequency = 400000;
- freq_table[1].frequency = 800000;
+ if (!prcmu_is_u8400()) {
+ freq_table[1].frequency = 400000;
+ freq_table[2].frequency = 800000;
if (prcmu_has_arm_maxopp())
- freq_table[2].frequency = 1000000;
+ freq_table[3].frequency = 1000000;
}
+ pr_info("db8500-cpufreq : Available frequencies:\n");
+ while (freq_table[i].frequency != CPUFREQ_TABLE_END)
+ pr_info(" %d Mhz\n", freq_table[i++].frequency/1000);
/* get policy fields based on the table */
res = cpufreq_frequency_table_cpuinfo(policy, freq_table);
@@ -127,10 +135,6 @@
policy->min = policy->cpuinfo.min_freq;
policy->max = policy->cpuinfo.max_freq;
policy->cur = db8500_cpufreq_getspeed(policy->cpu);
-
- for (i = 0; freq_table[i].frequency != policy->cur; i++)
- ;
-
policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
/*
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index 35a257d..4bd6815 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -19,6 +19,11 @@
#include <asm/msr.h>
#include <asm/tsc.h>
+#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+#include <linux/acpi.h>
+#include <acpi/processor.h>
+#endif
+
#define EPS_BRAND_C7M 0
#define EPS_BRAND_C7 1
#define EPS_BRAND_EDEN 2
@@ -27,11 +32,59 @@
struct eps_cpu_data {
u32 fsb;
+#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+ u32 bios_limit;
+#endif
struct cpufreq_frequency_table freq_table[];
};
static struct eps_cpu_data *eps_cpu[NR_CPUS];
+/* Module parameters */
+static int freq_failsafe_off;
+static int voltage_failsafe_off;
+static int set_max_voltage;
+
+#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+static int ignore_acpi_limit;
+
+static struct acpi_processor_performance *eps_acpi_cpu_perf;
+
+/* Minimum necessary to get acpi_processor_get_bios_limit() working */
+static int eps_acpi_init(void)
+{
+ eps_acpi_cpu_perf = kzalloc(sizeof(struct acpi_processor_performance),
+ GFP_KERNEL);
+ if (!eps_acpi_cpu_perf)
+ return -ENOMEM;
+
+ if (!zalloc_cpumask_var(&eps_acpi_cpu_perf->shared_cpu_map,
+ GFP_KERNEL)) {
+ kfree(eps_acpi_cpu_perf);
+ eps_acpi_cpu_perf = NULL;
+ return -ENOMEM;
+ }
+
+ if (acpi_processor_register_performance(eps_acpi_cpu_perf, 0)) {
+ free_cpumask_var(eps_acpi_cpu_perf->shared_cpu_map);
+ kfree(eps_acpi_cpu_perf);
+ eps_acpi_cpu_perf = NULL;
+ return -EIO;
+ }
+ return 0;
+}
+
+static int eps_acpi_exit(struct cpufreq_policy *policy)
+{
+ if (eps_acpi_cpu_perf) {
+ acpi_processor_unregister_performance(eps_acpi_cpu_perf, 0);
+ free_cpumask_var(eps_acpi_cpu_perf->shared_cpu_map);
+ kfree(eps_acpi_cpu_perf);
+ eps_acpi_cpu_perf = NULL;
+ }
+ return 0;
+}
+#endif
static unsigned int eps_get(unsigned int cpu)
{
@@ -164,6 +217,9 @@
int k, step, voltage;
int ret;
int states;
+#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+ unsigned int limit;
+#endif
if (policy->cpu != 0)
return -ENODEV;
@@ -244,11 +300,62 @@
return -EINVAL;
if (current_voltage > 0x1f || max_voltage > 0x1f)
return -EINVAL;
- if (max_voltage < min_voltage)
+ if (max_voltage < min_voltage
+ || current_voltage < min_voltage
+ || current_voltage > max_voltage)
return -EINVAL;
+ /* Check for systems using underclocked CPU */
+ if (!freq_failsafe_off && max_multiplier != current_multiplier) {
+ printk(KERN_INFO "eps: Your processor is running at different "
+ "frequency then its maximum. Aborting.\n");
+ printk(KERN_INFO "eps: You can use freq_failsafe_off option "
+ "to disable this check.\n");
+ return -EINVAL;
+ }
+ if (!voltage_failsafe_off && max_voltage != current_voltage) {
+ printk(KERN_INFO "eps: Your processor is running at different "
+ "voltage then its maximum. Aborting.\n");
+ printk(KERN_INFO "eps: You can use voltage_failsafe_off "
+ "option to disable this check.\n");
+ return -EINVAL;
+ }
+
/* Calc FSB speed */
fsb = cpu_khz / current_multiplier;
+
+#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+ /* Check for ACPI processor speed limit */
+ if (!ignore_acpi_limit && !eps_acpi_init()) {
+ if (!acpi_processor_get_bios_limit(policy->cpu, &limit)) {
+ printk(KERN_INFO "eps: ACPI limit %u.%uGHz\n",
+ limit/1000000,
+ (limit%1000000)/10000);
+ eps_acpi_exit(policy);
+ /* Check if max_multiplier is in BIOS limits */
+ if (limit && max_multiplier * fsb > limit) {
+ printk(KERN_INFO "eps: Aborting.\n");
+ return -EINVAL;
+ }
+ }
+ }
+#endif
+
+ /* Allow user to set lower maximum voltage then that reported
+ * by processor */
+ if (brand == EPS_BRAND_C7M && set_max_voltage) {
+ u32 v;
+
+ /* Change mV to something hardware can use */
+ v = (set_max_voltage - 700) / 16;
+ /* Check if voltage is within limits */
+ if (v >= min_voltage && v <= max_voltage) {
+ printk(KERN_INFO "eps: Setting %dmV as maximum.\n",
+ v * 16 + 700);
+ max_voltage = v;
+ }
+ }
+
/* Calc number of p-states supported */
if (brand == EPS_BRAND_C7M)
states = max_multiplier - min_multiplier + 1;
@@ -265,6 +372,9 @@
/* Copy basic values */
centaur->fsb = fsb;
+#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+ centaur->bios_limit = limit;
+#endif
/* Fill frequency and MSR value table */
f_table = ¢aur->freq_table[0];
@@ -303,17 +413,7 @@
static int eps_cpu_exit(struct cpufreq_policy *policy)
{
unsigned int cpu = policy->cpu;
- struct eps_cpu_data *centaur;
- u32 lo, hi;
- if (eps_cpu[cpu] == NULL)
- return -ENODEV;
- centaur = eps_cpu[cpu];
-
- /* Get max frequency */
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- /* Set max frequency */
- eps_set_state(centaur, cpu, hi & 0xffff);
/* Bye */
cpufreq_frequency_table_put_attr(policy->cpu);
kfree(eps_cpu[cpu]);
@@ -359,6 +459,19 @@
cpufreq_unregister_driver(&eps_driver);
}
+/* Allow user to overclock his machine or to change frequency to higher after
+ * unloading module */
+module_param(freq_failsafe_off, int, 0644);
+MODULE_PARM_DESC(freq_failsafe_off, "Disable current vs max frequency check");
+module_param(voltage_failsafe_off, int, 0644);
+MODULE_PARM_DESC(voltage_failsafe_off, "Disable current vs max voltage check");
+#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+module_param(ignore_acpi_limit, int, 0644);
+MODULE_PARM_DESC(ignore_acpi_limit, "Don't check ACPI's processor speed limit");
+#endif
+module_param(set_max_voltage, int, 0644);
+MODULE_PARM_DESC(set_max_voltage, "Set maximum CPU voltage (mV) C7-M only");
+
MODULE_AUTHOR("Rafal Bilski <rafalbilski@interia.pl>");
MODULE_DESCRIPTION("Enhanced PowerSaver driver for VIA C7 CPU's.");
MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/exynos4210-cpufreq.c b/drivers/cpufreq/exynos4210-cpufreq.c
index b7c3a84..ab9741f 100644
--- a/drivers/cpufreq/exynos4210-cpufreq.c
+++ b/drivers/cpufreq/exynos4210-cpufreq.c
@@ -17,6 +17,8 @@
#include <linux/slab.h>
#include <linux/regulator/consumer.h>
#include <linux/cpufreq.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
#include <mach/map.h>
#include <mach/regs-clock.h>
@@ -36,6 +38,10 @@
static struct cpufreq_freqs freqs;
static unsigned int memtype;
+static unsigned int locking_frequency;
+static bool frequency_locked;
+static DEFINE_MUTEX(cpufreq_lock);
+
enum exynos4_memory_type {
DDR2 = 4,
LPDDR2,
@@ -405,22 +411,32 @@
{
unsigned int index, old_index;
unsigned int arm_volt, int_volt;
+ int err = -EINVAL;
freqs.old = exynos4_getspeed(policy->cpu);
+ mutex_lock(&cpufreq_lock);
+
+ if (frequency_locked && target_freq != locking_frequency) {
+ err = -EAGAIN;
+ goto out;
+ }
+
if (cpufreq_frequency_table_target(policy, exynos4_freq_table,
freqs.old, relation, &old_index))
- return -EINVAL;
+ goto out;
if (cpufreq_frequency_table_target(policy, exynos4_freq_table,
target_freq, relation, &index))
- return -EINVAL;
+ goto out;
+
+ err = 0;
freqs.new = exynos4_freq_table[index].frequency;
freqs.cpu = policy->cpu;
if (freqs.new == freqs.old)
- return 0;
+ goto out;
/* get the voltage value */
arm_volt = exynos4_volt_table[index].arm_volt;
@@ -447,10 +463,16 @@
cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
- return 0;
+out:
+ mutex_unlock(&cpufreq_lock);
+ return err;
}
#ifdef CONFIG_PM
+/*
+ * These suspend/resume are used as syscore_ops, it is already too
+ * late to set regulator voltages at this stage.
+ */
static int exynos4_cpufreq_suspend(struct cpufreq_policy *policy)
{
return 0;
@@ -462,8 +484,82 @@
}
#endif
+/**
+ * exynos4_cpufreq_pm_notifier - block CPUFREQ's activities in suspend-resume
+ * context
+ * @notifier
+ * @pm_event
+ * @v
+ *
+ * While frequency_locked == true, target() ignores every frequency but
+ * locking_frequency. The locking_frequency value is the initial frequency,
+ * which is set by the bootloader. In order to eliminate possible
+ * inconsistency in clock values, we save and restore frequencies during
+ * suspend and resume and block CPUFREQ activities. Note that the standard
+ * suspend/resume cannot be used as they are too deep (syscore_ops) for
+ * regulator actions.
+ */
+static int exynos4_cpufreq_pm_notifier(struct notifier_block *notifier,
+ unsigned long pm_event, void *v)
+{
+ struct cpufreq_policy *policy = cpufreq_cpu_get(0); /* boot CPU */
+ static unsigned int saved_frequency;
+ unsigned int temp;
+
+ mutex_lock(&cpufreq_lock);
+ switch (pm_event) {
+ case PM_SUSPEND_PREPARE:
+ if (frequency_locked)
+ goto out;
+ frequency_locked = true;
+
+ if (locking_frequency) {
+ saved_frequency = exynos4_getspeed(0);
+
+ mutex_unlock(&cpufreq_lock);
+ exynos4_target(policy, locking_frequency,
+ CPUFREQ_RELATION_H);
+ mutex_lock(&cpufreq_lock);
+ }
+
+ break;
+ case PM_POST_SUSPEND:
+
+ if (saved_frequency) {
+ /*
+ * While frequency_locked, only locking_frequency
+ * is valid for target(). In order to use
+ * saved_frequency while keeping frequency_locked,
+ * we temporarly overwrite locking_frequency.
+ */
+ temp = locking_frequency;
+ locking_frequency = saved_frequency;
+
+ mutex_unlock(&cpufreq_lock);
+ exynos4_target(policy, locking_frequency,
+ CPUFREQ_RELATION_H);
+ mutex_lock(&cpufreq_lock);
+
+ locking_frequency = temp;
+ }
+
+ frequency_locked = false;
+ break;
+ }
+out:
+ mutex_unlock(&cpufreq_lock);
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block exynos4_cpufreq_nb = {
+ .notifier_call = exynos4_cpufreq_pm_notifier,
+};
+
static int exynos4_cpufreq_cpu_init(struct cpufreq_policy *policy)
{
+ int ret;
+
policy->cur = policy->min = policy->max = exynos4_getspeed(policy->cpu);
cpufreq_frequency_table_get_attr(exynos4_freq_table, policy->cpu);
@@ -479,16 +575,35 @@
*/
cpumask_setall(policy->cpus);
- return cpufreq_frequency_table_cpuinfo(policy, exynos4_freq_table);
+ ret = cpufreq_frequency_table_cpuinfo(policy, exynos4_freq_table);
+ if (ret)
+ return ret;
+
+ cpufreq_frequency_table_get_attr(exynos4_freq_table, policy->cpu);
+
+ return 0;
}
+static int exynos4_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+ cpufreq_frequency_table_put_attr(policy->cpu);
+ return 0;
+}
+
+static struct freq_attr *exynos4_cpufreq_attr[] = {
+ &cpufreq_freq_attr_scaling_available_freqs,
+ NULL,
+};
+
static struct cpufreq_driver exynos4_driver = {
.flags = CPUFREQ_STICKY,
.verify = exynos4_verify_speed,
.target = exynos4_target,
.get = exynos4_getspeed,
.init = exynos4_cpufreq_cpu_init,
+ .exit = exynos4_cpufreq_cpu_exit,
.name = "exynos4_cpufreq",
+ .attr = exynos4_cpufreq_attr,
#ifdef CONFIG_PM
.suspend = exynos4_cpufreq_suspend,
.resume = exynos4_cpufreq_resume,
@@ -501,6 +616,8 @@
if (IS_ERR(cpu_clk))
return PTR_ERR(cpu_clk);
+ locking_frequency = exynos4_getspeed(0);
+
moutcore = clk_get(NULL, "moutcore");
if (IS_ERR(moutcore))
goto out;
@@ -540,6 +657,8 @@
printk(KERN_DEBUG "%s: memtype= 0x%x\n", __func__, memtype);
}
+ register_pm_notifier(&exynos4_cpufreq_nb);
+
return cpufreq_register_driver(&exynos4_driver);
out:
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index af1a17d..5948a21 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -41,7 +41,7 @@
config EDAC_DECODE_MCE
tristate "Decode MCEs in human-readable form (only on AMD for now)"
- depends on CPU_SUP_AMD && X86_MCE
+ depends on CPU_SUP_AMD && X86_MCE_AMD
default y
---help---
Enable this option if you want to decode Machine Check Exceptions
@@ -71,9 +71,6 @@
occurred so that a particular failing memory module can be
replaced. If unsure, select 'Y'.
-config EDAC_MCE
- bool
-
config EDAC_AMD64
tristate "AMD64 (Opteron, Athlon64) K8, F10h"
depends on EDAC_MM_EDAC && AMD_NB && X86_64 && EDAC_DECODE_MCE
@@ -173,8 +170,7 @@
config EDAC_I7CORE
tristate "Intel i7 Core (Nehalem) processors"
- depends on EDAC_MM_EDAC && PCI && X86
- select EDAC_MCE
+ depends on EDAC_MM_EDAC && PCI && X86 && X86_MCE_INTEL
help
Support for error detection and correction the Intel
i7 Core (Nehalem) Integrated Memory Controller that exists on
@@ -216,6 +212,14 @@
Support for error detection and correction the Intel
Clarksboro MCH (Intel 7300 chipset).
+config EDAC_SBRIDGE
+ tristate "Intel Sandy-Bridge Integrated MC"
+ depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL
+ depends on EXPERIMENTAL
+ help
+ Support for error detection and correction the Intel
+ Sandy Bridge Integrated Memory Controller.
+
config EDAC_MPC85XX
tristate "Freescale MPC83xx / MPC85xx"
depends on EDAC_MM_EDAC && FSL_SOC && (PPC_83xx || PPC_85xx)
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 3e23913..196a63d 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -8,7 +8,6 @@
obj-$(CONFIG_EDAC) := edac_stub.o
obj-$(CONFIG_EDAC_MM_EDAC) += edac_core.o
-obj-$(CONFIG_EDAC_MCE) += edac_mce.o
edac_core-y := edac_mc.o edac_device.o edac_mc_sysfs.o edac_pci_sysfs.o
edac_core-y += edac_module.o edac_device_sysfs.o
@@ -29,6 +28,7 @@
obj-$(CONFIG_EDAC_I5400) += i5400_edac.o
obj-$(CONFIG_EDAC_I7300) += i7300_edac.o
obj-$(CONFIG_EDAC_I7CORE) += i7core_edac.o
+obj-$(CONFIG_EDAC_SBRIDGE) += sb_edac.o
obj-$(CONFIG_EDAC_E7XXX) += e7xxx_edac.o
obj-$(CONFIG_EDAC_E752X) += e752x_edac.o
obj-$(CONFIG_EDAC_I82443BXGX) += i82443bxgx_edac.o
diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h
index 55b8278..fe90cd4 100644
--- a/drivers/edac/edac_core.h
+++ b/drivers/edac/edac_core.h
@@ -34,11 +34,10 @@
#include <linux/platform_device.h>
#include <linux/sysdev.h>
#include <linux/workqueue.h>
+#include <linux/edac.h>
-#define EDAC_MC_LABEL_LEN 31
#define EDAC_DEVICE_NAME_LEN 31
#define EDAC_ATTRIB_VALUE_LEN 15
-#define MC_PROC_NAME_MAX_LEN 7
#if PAGE_SHIFT < 20
#define PAGES_TO_MiB(pages) ((pages) >> (20 - PAGE_SHIFT))
@@ -101,353 +100,6 @@
#define edac_dev_name(dev) (dev)->dev_name
-/* memory devices */
-enum dev_type {
- DEV_UNKNOWN = 0,
- DEV_X1,
- DEV_X2,
- DEV_X4,
- DEV_X8,
- DEV_X16,
- DEV_X32, /* Do these parts exist? */
- DEV_X64 /* Do these parts exist? */
-};
-
-#define DEV_FLAG_UNKNOWN BIT(DEV_UNKNOWN)
-#define DEV_FLAG_X1 BIT(DEV_X1)
-#define DEV_FLAG_X2 BIT(DEV_X2)
-#define DEV_FLAG_X4 BIT(DEV_X4)
-#define DEV_FLAG_X8 BIT(DEV_X8)
-#define DEV_FLAG_X16 BIT(DEV_X16)
-#define DEV_FLAG_X32 BIT(DEV_X32)
-#define DEV_FLAG_X64 BIT(DEV_X64)
-
-/* memory types */
-enum mem_type {
- MEM_EMPTY = 0, /* Empty csrow */
- MEM_RESERVED, /* Reserved csrow type */
- MEM_UNKNOWN, /* Unknown csrow type */
- MEM_FPM, /* Fast page mode */
- MEM_EDO, /* Extended data out */
- MEM_BEDO, /* Burst Extended data out */
- MEM_SDR, /* Single data rate SDRAM */
- MEM_RDR, /* Registered single data rate SDRAM */
- MEM_DDR, /* Double data rate SDRAM */
- MEM_RDDR, /* Registered Double data rate SDRAM */
- MEM_RMBS, /* Rambus DRAM */
- MEM_DDR2, /* DDR2 RAM */
- MEM_FB_DDR2, /* fully buffered DDR2 */
- MEM_RDDR2, /* Registered DDR2 RAM */
- MEM_XDR, /* Rambus XDR */
- MEM_DDR3, /* DDR3 RAM */
- MEM_RDDR3, /* Registered DDR3 RAM */
-};
-
-#define MEM_FLAG_EMPTY BIT(MEM_EMPTY)
-#define MEM_FLAG_RESERVED BIT(MEM_RESERVED)
-#define MEM_FLAG_UNKNOWN BIT(MEM_UNKNOWN)
-#define MEM_FLAG_FPM BIT(MEM_FPM)
-#define MEM_FLAG_EDO BIT(MEM_EDO)
-#define MEM_FLAG_BEDO BIT(MEM_BEDO)
-#define MEM_FLAG_SDR BIT(MEM_SDR)
-#define MEM_FLAG_RDR BIT(MEM_RDR)
-#define MEM_FLAG_DDR BIT(MEM_DDR)
-#define MEM_FLAG_RDDR BIT(MEM_RDDR)
-#define MEM_FLAG_RMBS BIT(MEM_RMBS)
-#define MEM_FLAG_DDR2 BIT(MEM_DDR2)
-#define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2)
-#define MEM_FLAG_RDDR2 BIT(MEM_RDDR2)
-#define MEM_FLAG_XDR BIT(MEM_XDR)
-#define MEM_FLAG_DDR3 BIT(MEM_DDR3)
-#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3)
-
-/* chipset Error Detection and Correction capabilities and mode */
-enum edac_type {
- EDAC_UNKNOWN = 0, /* Unknown if ECC is available */
- EDAC_NONE, /* Doesn't support ECC */
- EDAC_RESERVED, /* Reserved ECC type */
- EDAC_PARITY, /* Detects parity errors */
- EDAC_EC, /* Error Checking - no correction */
- EDAC_SECDED, /* Single bit error correction, Double detection */
- EDAC_S2ECD2ED, /* Chipkill x2 devices - do these exist? */
- EDAC_S4ECD4ED, /* Chipkill x4 devices */
- EDAC_S8ECD8ED, /* Chipkill x8 devices */
- EDAC_S16ECD16ED, /* Chipkill x16 devices */
-};
-
-#define EDAC_FLAG_UNKNOWN BIT(EDAC_UNKNOWN)
-#define EDAC_FLAG_NONE BIT(EDAC_NONE)
-#define EDAC_FLAG_PARITY BIT(EDAC_PARITY)
-#define EDAC_FLAG_EC BIT(EDAC_EC)
-#define EDAC_FLAG_SECDED BIT(EDAC_SECDED)
-#define EDAC_FLAG_S2ECD2ED BIT(EDAC_S2ECD2ED)
-#define EDAC_FLAG_S4ECD4ED BIT(EDAC_S4ECD4ED)
-#define EDAC_FLAG_S8ECD8ED BIT(EDAC_S8ECD8ED)
-#define EDAC_FLAG_S16ECD16ED BIT(EDAC_S16ECD16ED)
-
-/* scrubbing capabilities */
-enum scrub_type {
- SCRUB_UNKNOWN = 0, /* Unknown if scrubber is available */
- SCRUB_NONE, /* No scrubber */
- SCRUB_SW_PROG, /* SW progressive (sequential) scrubbing */
- SCRUB_SW_SRC, /* Software scrub only errors */
- SCRUB_SW_PROG_SRC, /* Progressive software scrub from an error */
- SCRUB_SW_TUNABLE, /* Software scrub frequency is tunable */
- SCRUB_HW_PROG, /* HW progressive (sequential) scrubbing */
- SCRUB_HW_SRC, /* Hardware scrub only errors */
- SCRUB_HW_PROG_SRC, /* Progressive hardware scrub from an error */
- SCRUB_HW_TUNABLE /* Hardware scrub frequency is tunable */
-};
-
-#define SCRUB_FLAG_SW_PROG BIT(SCRUB_SW_PROG)
-#define SCRUB_FLAG_SW_SRC BIT(SCRUB_SW_SRC)
-#define SCRUB_FLAG_SW_PROG_SRC BIT(SCRUB_SW_PROG_SRC)
-#define SCRUB_FLAG_SW_TUN BIT(SCRUB_SW_SCRUB_TUNABLE)
-#define SCRUB_FLAG_HW_PROG BIT(SCRUB_HW_PROG)
-#define SCRUB_FLAG_HW_SRC BIT(SCRUB_HW_SRC)
-#define SCRUB_FLAG_HW_PROG_SRC BIT(SCRUB_HW_PROG_SRC)
-#define SCRUB_FLAG_HW_TUN BIT(SCRUB_HW_TUNABLE)
-
-/* FIXME - should have notify capabilities: NMI, LOG, PROC, etc */
-
-/* EDAC internal operation states */
-#define OP_ALLOC 0x100
-#define OP_RUNNING_POLL 0x201
-#define OP_RUNNING_INTERRUPT 0x202
-#define OP_RUNNING_POLL_INTR 0x203
-#define OP_OFFLINE 0x300
-
-/*
- * There are several things to be aware of that aren't at all obvious:
- *
- *
- * SOCKETS, SOCKET SETS, BANKS, ROWS, CHIP-SELECT ROWS, CHANNELS, etc..
- *
- * These are some of the many terms that are thrown about that don't always
- * mean what people think they mean (Inconceivable!). In the interest of
- * creating a common ground for discussion, terms and their definitions
- * will be established.
- *
- * Memory devices: The individual chip on a memory stick. These devices
- * commonly output 4 and 8 bits each. Grouping several
- * of these in parallel provides 64 bits which is common
- * for a memory stick.
- *
- * Memory Stick: A printed circuit board that aggregates multiple
- * memory devices in parallel. This is the atomic
- * memory component that is purchaseable by Joe consumer
- * and loaded into a memory socket.
- *
- * Socket: A physical connector on the motherboard that accepts
- * a single memory stick.
- *
- * Channel: Set of memory devices on a memory stick that must be
- * grouped in parallel with one or more additional
- * channels from other memory sticks. This parallel
- * grouping of the output from multiple channels are
- * necessary for the smallest granularity of memory access.
- * Some memory controllers are capable of single channel -
- * which means that memory sticks can be loaded
- * individually. Other memory controllers are only
- * capable of dual channel - which means that memory
- * sticks must be loaded as pairs (see "socket set").
- *
- * Chip-select row: All of the memory devices that are selected together.
- * for a single, minimum grain of memory access.
- * This selects all of the parallel memory devices across
- * all of the parallel channels. Common chip-select rows
- * for single channel are 64 bits, for dual channel 128
- * bits.
- *
- * Single-Ranked stick: A Single-ranked stick has 1 chip-select row of memory.
- * Motherboards commonly drive two chip-select pins to
- * a memory stick. A single-ranked stick, will occupy
- * only one of those rows. The other will be unused.
- *
- * Double-Ranked stick: A double-ranked stick has two chip-select rows which
- * access different sets of memory devices. The two
- * rows cannot be accessed concurrently.
- *
- * Double-sided stick: DEPRECATED TERM, see Double-Ranked stick.
- * A double-sided stick has two chip-select rows which
- * access different sets of memory devices. The two
- * rows cannot be accessed concurrently. "Double-sided"
- * is irrespective of the memory devices being mounted
- * on both sides of the memory stick.
- *
- * Socket set: All of the memory sticks that are required for
- * a single memory access or all of the memory sticks
- * spanned by a chip-select row. A single socket set
- * has two chip-select rows and if double-sided sticks
- * are used these will occupy those chip-select rows.
- *
- * Bank: This term is avoided because it is unclear when
- * needing to distinguish between chip-select rows and
- * socket sets.
- *
- * Controller pages:
- *
- * Physical pages:
- *
- * Virtual pages:
- *
- *
- * STRUCTURE ORGANIZATION AND CHOICES
- *
- *
- *
- * PS - I enjoyed writing all that about as much as you enjoyed reading it.
- */
-
-struct channel_info {
- int chan_idx; /* channel index */
- u32 ce_count; /* Correctable Errors for this CHANNEL */
- char label[EDAC_MC_LABEL_LEN + 1]; /* DIMM label on motherboard */
- struct csrow_info *csrow; /* the parent */
-};
-
-struct csrow_info {
- unsigned long first_page; /* first page number in dimm */
- unsigned long last_page; /* last page number in dimm */
- unsigned long page_mask; /* used for interleaving -
- * 0UL for non intlv
- */
- u32 nr_pages; /* number of pages in csrow */
- u32 grain; /* granularity of reported error in bytes */
- int csrow_idx; /* the chip-select row */
- enum dev_type dtype; /* memory device type */
- u32 ue_count; /* Uncorrectable Errors for this csrow */
- u32 ce_count; /* Correctable Errors for this csrow */
- enum mem_type mtype; /* memory csrow type */
- enum edac_type edac_mode; /* EDAC mode for this csrow */
- struct mem_ctl_info *mci; /* the parent */
-
- struct kobject kobj; /* sysfs kobject for this csrow */
-
- /* channel information for this csrow */
- u32 nr_channels;
- struct channel_info *channels;
-};
-
-struct mcidev_sysfs_group {
- const char *name; /* group name */
- const struct mcidev_sysfs_attribute *mcidev_attr; /* group attributes */
-};
-
-struct mcidev_sysfs_group_kobj {
- struct list_head list; /* list for all instances within a mc */
-
- struct kobject kobj; /* kobj for the group */
-
- const struct mcidev_sysfs_group *grp; /* group description table */
- struct mem_ctl_info *mci; /* the parent */
-};
-
-/* mcidev_sysfs_attribute structure
- * used for driver sysfs attributes and in mem_ctl_info
- * sysfs top level entries
- */
-struct mcidev_sysfs_attribute {
- /* It should use either attr or grp */
- struct attribute attr;
- const struct mcidev_sysfs_group *grp; /* Points to a group of attributes */
-
- /* Ops for show/store values at the attribute - not used on group */
- ssize_t (*show)(struct mem_ctl_info *,char *);
- ssize_t (*store)(struct mem_ctl_info *, const char *,size_t);
-};
-
-/* MEMORY controller information structure
- */
-struct mem_ctl_info {
- struct list_head link; /* for global list of mem_ctl_info structs */
-
- struct module *owner; /* Module owner of this control struct */
-
- unsigned long mtype_cap; /* memory types supported by mc */
- unsigned long edac_ctl_cap; /* Mem controller EDAC capabilities */
- unsigned long edac_cap; /* configuration capabilities - this is
- * closely related to edac_ctl_cap. The
- * difference is that the controller may be
- * capable of s4ecd4ed which would be listed
- * in edac_ctl_cap, but if channels aren't
- * capable of s4ecd4ed then the edac_cap would
- * not have that capability.
- */
- unsigned long scrub_cap; /* chipset scrub capabilities */
- enum scrub_type scrub_mode; /* current scrub mode */
-
- /* Translates sdram memory scrub rate given in bytes/sec to the
- internal representation and configures whatever else needs
- to be configured.
- */
- int (*set_sdram_scrub_rate) (struct mem_ctl_info * mci, u32 bw);
-
- /* Get the current sdram memory scrub rate from the internal
- representation and converts it to the closest matching
- bandwidth in bytes/sec.
- */
- int (*get_sdram_scrub_rate) (struct mem_ctl_info * mci);
-
-
- /* pointer to edac checking routine */
- void (*edac_check) (struct mem_ctl_info * mci);
-
- /*
- * Remaps memory pages: controller pages to physical pages.
- * For most MC's, this will be NULL.
- */
- /* FIXME - why not send the phys page to begin with? */
- unsigned long (*ctl_page_to_phys) (struct mem_ctl_info * mci,
- unsigned long page);
- int mc_idx;
- int nr_csrows;
- struct csrow_info *csrows;
- /*
- * FIXME - what about controllers on other busses? - IDs must be
- * unique. dev pointer should be sufficiently unique, but
- * BUS:SLOT.FUNC numbers may not be unique.
- */
- struct device *dev;
- const char *mod_name;
- const char *mod_ver;
- const char *ctl_name;
- const char *dev_name;
- char proc_name[MC_PROC_NAME_MAX_LEN + 1];
- void *pvt_info;
- u32 ue_noinfo_count; /* Uncorrectable Errors w/o info */
- u32 ce_noinfo_count; /* Correctable Errors w/o info */
- u32 ue_count; /* Total Uncorrectable Errors for this MC */
- u32 ce_count; /* Total Correctable Errors for this MC */
- unsigned long start_time; /* mci load start time (in jiffies) */
-
- struct completion complete;
-
- /* edac sysfs device control */
- struct kobject edac_mci_kobj;
-
- /* list for all grp instances within a mc */
- struct list_head grp_kobj_list;
-
- /* Additional top controller level attributes, but specified
- * by the low level driver.
- *
- * Set by the low level driver to provide attributes at the
- * controller level, same level as 'ue_count' and 'ce_count' above.
- * An array of structures, NULL terminated
- *
- * If attributes are desired, then set to array of attributes
- * If no attributes are desired, leave NULL
- */
- const struct mcidev_sysfs_attribute *mc_driver_sysfs_attributes;
-
- /* work struct for this MC */
- struct delayed_work work;
-
- /* the internal state of this controller instance */
- int op_state;
-};
-
/*
* The following are the structures to provide for a generic
* or abstract 'edac_device'. This set of structures and the
diff --git a/drivers/edac/edac_mce.c b/drivers/edac/edac_mce.c
deleted file mode 100644
index 9ccdc5b..0000000
--- a/drivers/edac/edac_mce.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/* Provides edac interface to mcelog events
- *
- * This file may be distributed under the terms of the
- * GNU General Public License version 2.
- *
- * Copyright (c) 2009 by:
- * Mauro Carvalho Chehab <mchehab@redhat.com>
- *
- * Red Hat Inc. http://www.redhat.com
- */
-
-#include <linux/module.h>
-#include <linux/edac_mce.h>
-#include <asm/mce.h>
-
-int edac_mce_enabled;
-EXPORT_SYMBOL_GPL(edac_mce_enabled);
-
-
-/*
- * Extension interface
- */
-
-static LIST_HEAD(edac_mce_list);
-static DEFINE_MUTEX(edac_mce_lock);
-
-int edac_mce_register(struct edac_mce *edac_mce)
-{
- mutex_lock(&edac_mce_lock);
- list_add_tail(&edac_mce->list, &edac_mce_list);
- mutex_unlock(&edac_mce_lock);
- return 0;
-}
-EXPORT_SYMBOL(edac_mce_register);
-
-void edac_mce_unregister(struct edac_mce *edac_mce)
-{
- mutex_lock(&edac_mce_lock);
- list_del(&edac_mce->list);
- mutex_unlock(&edac_mce_lock);
-}
-EXPORT_SYMBOL(edac_mce_unregister);
-
-int edac_mce_parse(struct mce *mce)
-{
- struct edac_mce *edac_mce;
-
- list_for_each_entry(edac_mce, &edac_mce_list, list) {
- if (edac_mce->check_error(edac_mce->priv, mce))
- return 1;
- }
-
- /* Nobody queued the error */
- return 0;
-}
-EXPORT_SYMBOL_GPL(edac_mce_parse);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@redhat.com>");
-MODULE_AUTHOR("Red Hat Inc. (http://www.redhat.com)");
-MODULE_DESCRIPTION("EDAC Driver for mcelog captured errors");
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index a76fe83..6104dba 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -372,7 +372,7 @@
static void i7300_process_error_global(struct mem_ctl_info *mci)
{
struct i7300_pvt *pvt;
- u32 errnum, value;
+ u32 errnum, error_reg;
unsigned long errors;
const char *specific;
bool is_fatal;
@@ -381,9 +381,9 @@
/* read in the 1st FATAL error register */
pci_read_config_dword(pvt->pci_dev_16_2_fsb_err_regs,
- FERR_GLOBAL_HI, &value);
- if (unlikely(value)) {
- errors = value;
+ FERR_GLOBAL_HI, &error_reg);
+ if (unlikely(error_reg)) {
+ errors = error_reg;
errnum = find_first_bit(&errors,
ARRAY_SIZE(ferr_global_hi_name));
specific = GET_ERR_FROM_TABLE(ferr_global_hi_name, errnum);
@@ -391,15 +391,15 @@
/* Clear the error bit */
pci_write_config_dword(pvt->pci_dev_16_2_fsb_err_regs,
- FERR_GLOBAL_HI, value);
+ FERR_GLOBAL_HI, error_reg);
goto error_global;
}
pci_read_config_dword(pvt->pci_dev_16_2_fsb_err_regs,
- FERR_GLOBAL_LO, &value);
- if (unlikely(value)) {
- errors = value;
+ FERR_GLOBAL_LO, &error_reg);
+ if (unlikely(error_reg)) {
+ errors = error_reg;
errnum = find_first_bit(&errors,
ARRAY_SIZE(ferr_global_lo_name));
specific = GET_ERR_FROM_TABLE(ferr_global_lo_name, errnum);
@@ -407,7 +407,7 @@
/* Clear the error bit */
pci_write_config_dword(pvt->pci_dev_16_2_fsb_err_regs,
- FERR_GLOBAL_LO, value);
+ FERR_GLOBAL_LO, error_reg);
goto error_global;
}
@@ -427,7 +427,7 @@
static void i7300_process_fbd_error(struct mem_ctl_info *mci)
{
struct i7300_pvt *pvt;
- u32 errnum, value;
+ u32 errnum, value, error_reg;
u16 val16;
unsigned branch, channel, bank, rank, cas, ras;
u32 syndrome;
@@ -440,14 +440,14 @@
/* read in the 1st FATAL error register */
pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
- FERR_FAT_FBD, &value);
- if (unlikely(value & FERR_FAT_FBD_ERR_MASK)) {
- errors = value & FERR_FAT_FBD_ERR_MASK ;
+ FERR_FAT_FBD, &error_reg);
+ if (unlikely(error_reg & FERR_FAT_FBD_ERR_MASK)) {
+ errors = error_reg & FERR_FAT_FBD_ERR_MASK ;
errnum = find_first_bit(&errors,
ARRAY_SIZE(ferr_fat_fbd_name));
specific = GET_ERR_FROM_TABLE(ferr_fat_fbd_name, errnum);
+ branch = (GET_FBD_FAT_IDX(error_reg) == 2) ? 1 : 0;
- branch = (GET_FBD_FAT_IDX(value) == 2) ? 1 : 0;
pci_read_config_word(pvt->pci_dev_16_1_fsb_addr_map,
NRECMEMA, &val16);
bank = NRECMEMA_BANK(val16);
@@ -455,11 +455,14 @@
pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
NRECMEMB, &value);
-
is_wr = NRECMEMB_IS_WR(value);
cas = NRECMEMB_CAS(value);
ras = NRECMEMB_RAS(value);
+ /* Clean the error register */
+ pci_write_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
+ FERR_FAT_FBD, error_reg);
+
snprintf(pvt->tmp_prt_buffer, PAGE_SIZE,
"FATAL (Branch=%d DRAM-Bank=%d %s "
"RAS=%d CAS=%d Err=0x%lx (%s))",
@@ -476,21 +479,17 @@
/* read in the 1st NON-FATAL error register */
pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
- FERR_NF_FBD, &value);
- if (unlikely(value & FERR_NF_FBD_ERR_MASK)) {
- errors = value & FERR_NF_FBD_ERR_MASK;
+ FERR_NF_FBD, &error_reg);
+ if (unlikely(error_reg & FERR_NF_FBD_ERR_MASK)) {
+ errors = error_reg & FERR_NF_FBD_ERR_MASK;
errnum = find_first_bit(&errors,
ARRAY_SIZE(ferr_nf_fbd_name));
specific = GET_ERR_FROM_TABLE(ferr_nf_fbd_name, errnum);
-
- /* Clear the error bit */
- pci_write_config_dword(pvt->pci_dev_16_2_fsb_err_regs,
- FERR_GLOBAL_LO, value);
+ branch = (GET_FBD_FAT_IDX(error_reg) == 2) ? 1 : 0;
pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
REDMEMA, &syndrome);
- branch = (GET_FBD_FAT_IDX(value) == 2) ? 1 : 0;
pci_read_config_word(pvt->pci_dev_16_1_fsb_addr_map,
RECMEMA, &val16);
bank = RECMEMA_BANK(val16);
@@ -498,18 +497,20 @@
pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
RECMEMB, &value);
-
is_wr = RECMEMB_IS_WR(value);
cas = RECMEMB_CAS(value);
ras = RECMEMB_RAS(value);
pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
REDMEMB, &value);
-
channel = (branch << 1);
if (IS_SECOND_CH(value))
channel++;
+ /* Clear the error bit */
+ pci_write_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
+ FERR_NF_FBD, error_reg);
+
/* Form out message */
snprintf(pvt->tmp_prt_buffer, PAGE_SIZE,
"Corrected error (Branch=%d, Channel %d), "
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index f6cf448..70ad892 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -31,11 +31,13 @@
#include <linux/pci_ids.h>
#include <linux/slab.h>
#include <linux/delay.h>
+#include <linux/dmi.h>
#include <linux/edac.h>
#include <linux/mmzone.h>
-#include <linux/edac_mce.h>
#include <linux/smp.h>
+#include <asm/mce.h>
#include <asm/processor.h>
+#include <asm/div64.h>
#include "edac_core.h"
@@ -78,6 +80,8 @@
/* OFFSETS for Device 0 Function 0 */
#define MC_CFG_CONTROL 0x90
+ #define MC_CFG_UNLOCK 0x02
+ #define MC_CFG_LOCK 0x00
/* OFFSETS for Device 3 Function 0 */
@@ -98,6 +102,15 @@
#define DIMM0_COR_ERR(r) ((r) & 0x7fff)
/* OFFSETS for Device 3 Function 2, as inicated on Xeon 5500 datasheet */
+#define MC_SSRCONTROL 0x48
+ #define SSR_MODE_DISABLE 0x00
+ #define SSR_MODE_ENABLE 0x01
+ #define SSR_MODE_MASK 0x03
+
+#define MC_SCRUB_CONTROL 0x4c
+ #define STARTSCRUB (1 << 24)
+ #define SCRUBINTERVAL_MASK 0xffffff
+
#define MC_COR_ECC_CNT_0 0x80
#define MC_COR_ECC_CNT_1 0x84
#define MC_COR_ECC_CNT_2 0x88
@@ -253,10 +266,7 @@
unsigned long rdimm_ce_count[NUM_CHANS][MAX_DIMMS];
int rdimm_last_ce_count[NUM_CHANS][MAX_DIMMS];
- unsigned int is_registered;
-
- /* mcelog glue */
- struct edac_mce edac_mce;
+ bool is_registered, enable_scrub;
/* Fifo double buffers */
struct mce mce_entry[MCE_LOG_LEN];
@@ -268,6 +278,9 @@
/* Count indicator to show errors not got */
unsigned mce_overrun;
+ /* DCLK Frequency used for computing scrub rate */
+ int dclk_freq;
+
/* Struct to control EDAC polling */
struct edac_pci_ctl_info *i7core_pci;
};
@@ -281,8 +294,7 @@
/* Memory controller */
{ PCI_DESCR(3, 0, PCI_DEVICE_ID_INTEL_I7_MCR) },
{ PCI_DESCR(3, 1, PCI_DEVICE_ID_INTEL_I7_MC_TAD) },
-
- /* Exists only for RDIMM */
+ /* Exists only for RDIMM */
{ PCI_DESCR(3, 2, PCI_DEVICE_ID_INTEL_I7_MC_RAS), .optional = 1 },
{ PCI_DESCR(3, 4, PCI_DEVICE_ID_INTEL_I7_MC_TEST) },
@@ -303,6 +315,16 @@
{ PCI_DESCR(6, 1, PCI_DEVICE_ID_INTEL_I7_MC_CH2_ADDR) },
{ PCI_DESCR(6, 2, PCI_DEVICE_ID_INTEL_I7_MC_CH2_RANK) },
{ PCI_DESCR(6, 3, PCI_DEVICE_ID_INTEL_I7_MC_CH2_TC) },
+
+ /* Generic Non-core registers */
+ /*
+ * This is the PCI device on i7core and on Xeon 35xx (8086:2c41)
+ * On Xeon 55xx, however, it has a different id (8086:2c40). So,
+ * the probing code needs to test for the other address in case of
+ * failure of this one
+ */
+ { PCI_DESCR(0, 0, PCI_DEVICE_ID_INTEL_I7_NONCORE) },
+
};
static const struct pci_id_descr pci_dev_descr_lynnfield[] = {
@@ -319,6 +341,12 @@
{ PCI_DESCR( 5, 1, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_ADDR) },
{ PCI_DESCR( 5, 2, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_RANK) },
{ PCI_DESCR( 5, 3, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_TC) },
+
+ /*
+ * This is the PCI device has an alternate address on some
+ * processors like Core i7 860
+ */
+ { PCI_DESCR( 0, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE) },
};
static const struct pci_id_descr pci_dev_descr_i7core_westmere[] = {
@@ -346,6 +374,10 @@
{ PCI_DESCR(6, 1, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH2_ADDR_REV2) },
{ PCI_DESCR(6, 2, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH2_RANK_REV2) },
{ PCI_DESCR(6, 3, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH2_TC_REV2) },
+
+ /* Generic Non-core registers */
+ { PCI_DESCR(0, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_REV2) },
+
};
#define PCI_ID_TABLE_ENTRY(A) { .descr=A, .n_devs = ARRAY_SIZE(A) }
@@ -714,6 +746,10 @@
csr->edac_mode = mode;
csr->mtype = mtype;
+ snprintf(csr->channels[0].label,
+ sizeof(csr->channels[0].label),
+ "CPU#%uChannel#%u_DIMM#%u",
+ pvt->i7core_dev->socket, i, j);
csrow++;
}
@@ -731,7 +767,7 @@
debugf1("\t\t%#x\t%#x\t%#x\n",
(value[j] >> 27) & 0x1,
(value[j] >> 24) & 0x7,
- (value[j] && ((1 << 24) - 1)));
+ (value[j] & ((1 << 24) - 1)));
}
return 0;
@@ -1324,6 +1360,20 @@
pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
dev_descr->dev_id, *prev);
+ /*
+ * On Xeon 55xx, the Intel Quckpath Arch Generic Non-core regs
+ * is at addr 8086:2c40, instead of 8086:2c41. So, we need
+ * to probe for the alternate address in case of failure
+ */
+ if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev)
+ pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_I7_NONCORE_ALT, *prev);
+
+ if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && !pdev)
+ pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_ALT,
+ *prev);
+
if (!pdev) {
if (*prev) {
*prev = pdev;
@@ -1444,8 +1494,10 @@
struct i7core_pvt *pvt = mci->pvt_info;
struct pci_dev *pdev;
int i, func, slot;
+ char *family;
- pvt->is_registered = 0;
+ pvt->is_registered = false;
+ pvt->enable_scrub = false;
for (i = 0; i < i7core_dev->n_devs; i++) {
pdev = i7core_dev->pdev[i];
if (!pdev)
@@ -1461,9 +1513,37 @@
if (unlikely(func > MAX_CHAN_FUNC))
goto error;
pvt->pci_ch[slot - 4][func] = pdev;
- } else if (!slot && !func)
+ } else if (!slot && !func) {
pvt->pci_noncore = pdev;
- else
+
+ /* Detect the processor family */
+ switch (pdev->device) {
+ case PCI_DEVICE_ID_INTEL_I7_NONCORE:
+ family = "Xeon 35xx/ i7core";
+ pvt->enable_scrub = false;
+ break;
+ case PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_ALT:
+ family = "i7-800/i5-700";
+ pvt->enable_scrub = false;
+ break;
+ case PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE:
+ family = "Xeon 34xx";
+ pvt->enable_scrub = false;
+ break;
+ case PCI_DEVICE_ID_INTEL_I7_NONCORE_ALT:
+ family = "Xeon 55xx";
+ pvt->enable_scrub = true;
+ break;
+ case PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_REV2:
+ family = "Xeon 56xx / i7-900";
+ pvt->enable_scrub = true;
+ break;
+ default:
+ family = "unknown";
+ pvt->enable_scrub = false;
+ }
+ debugf0("Detected a processor type %s\n", family);
+ } else
goto error;
debugf0("Associated fn %d.%d, dev = %p, socket %d\n",
@@ -1472,7 +1552,7 @@
if (PCI_SLOT(pdev->devfn) == 3 &&
PCI_FUNC(pdev->devfn) == 2)
- pvt->is_registered = 1;
+ pvt->is_registered = true;
}
return 0;
@@ -1826,33 +1906,43 @@
* WARNING: As this routine should be called at NMI time, extra care should
* be taken to avoid deadlocks, and to be as fast as possible.
*/
-static int i7core_mce_check_error(void *priv, struct mce *mce)
+static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
+ void *data)
{
- struct mem_ctl_info *mci = priv;
- struct i7core_pvt *pvt = mci->pvt_info;
+ struct mce *mce = (struct mce *)data;
+ struct i7core_dev *i7_dev;
+ struct mem_ctl_info *mci;
+ struct i7core_pvt *pvt;
+
+ i7_dev = get_i7core_dev(mce->socketid);
+ if (!i7_dev)
+ return NOTIFY_BAD;
+
+ mci = i7_dev->mci;
+ pvt = mci->pvt_info;
/*
* Just let mcelog handle it if the error is
* outside the memory controller
*/
if (((mce->status & 0xffff) >> 7) != 1)
- return 0;
+ return NOTIFY_DONE;
/* Bank 8 registers are the only ones that we know how to handle */
if (mce->bank != 8)
- return 0;
+ return NOTIFY_DONE;
#ifdef CONFIG_SMP
/* Only handle if it is the right mc controller */
- if (cpu_data(mce->cpu).phys_proc_id != pvt->i7core_dev->socket)
- return 0;
+ if (mce->socketid != pvt->i7core_dev->socket)
+ return NOTIFY_DONE;
#endif
smp_rmb();
if ((pvt->mce_out + 1) % MCE_LOG_LEN == pvt->mce_in) {
smp_wmb();
pvt->mce_overrun++;
- return 0;
+ return NOTIFY_DONE;
}
/* Copy memory error at the ringbuffer */
@@ -1865,7 +1955,240 @@
i7core_check_error(mci);
/* Advise mcelog that the errors were handled */
- return 1;
+ return NOTIFY_STOP;
+}
+
+static struct notifier_block i7_mce_dec = {
+ .notifier_call = i7core_mce_check_error,
+};
+
+struct memdev_dmi_entry {
+ u8 type;
+ u8 length;
+ u16 handle;
+ u16 phys_mem_array_handle;
+ u16 mem_err_info_handle;
+ u16 total_width;
+ u16 data_width;
+ u16 size;
+ u8 form;
+ u8 device_set;
+ u8 device_locator;
+ u8 bank_locator;
+ u8 memory_type;
+ u16 type_detail;
+ u16 speed;
+ u8 manufacturer;
+ u8 serial_number;
+ u8 asset_tag;
+ u8 part_number;
+ u8 attributes;
+ u32 extended_size;
+ u16 conf_mem_clk_speed;
+} __attribute__((__packed__));
+
+
+/*
+ * Decode the DRAM Clock Frequency, be paranoid, make sure that all
+ * memory devices show the same speed, and if they don't then consider
+ * all speeds to be invalid.
+ */
+static void decode_dclk(const struct dmi_header *dh, void *_dclk_freq)
+{
+ int *dclk_freq = _dclk_freq;
+ u16 dmi_mem_clk_speed;
+
+ if (*dclk_freq == -1)
+ return;
+
+ if (dh->type == DMI_ENTRY_MEM_DEVICE) {
+ struct memdev_dmi_entry *memdev_dmi_entry =
+ (struct memdev_dmi_entry *)dh;
+ unsigned long conf_mem_clk_speed_offset =
+ (unsigned long)&memdev_dmi_entry->conf_mem_clk_speed -
+ (unsigned long)&memdev_dmi_entry->type;
+ unsigned long speed_offset =
+ (unsigned long)&memdev_dmi_entry->speed -
+ (unsigned long)&memdev_dmi_entry->type;
+
+ /* Check that a DIMM is present */
+ if (memdev_dmi_entry->size == 0)
+ return;
+
+ /*
+ * Pick the configured speed if it's available, otherwise
+ * pick the DIMM speed, or we don't have a speed.
+ */
+ if (memdev_dmi_entry->length > conf_mem_clk_speed_offset) {
+ dmi_mem_clk_speed =
+ memdev_dmi_entry->conf_mem_clk_speed;
+ } else if (memdev_dmi_entry->length > speed_offset) {
+ dmi_mem_clk_speed = memdev_dmi_entry->speed;
+ } else {
+ *dclk_freq = -1;
+ return;
+ }
+
+ if (*dclk_freq == 0) {
+ /* First pass, speed was 0 */
+ if (dmi_mem_clk_speed > 0) {
+ /* Set speed if a valid speed is read */
+ *dclk_freq = dmi_mem_clk_speed;
+ } else {
+ /* Otherwise we don't have a valid speed */
+ *dclk_freq = -1;
+ }
+ } else if (*dclk_freq > 0 &&
+ *dclk_freq != dmi_mem_clk_speed) {
+ /*
+ * If we have a speed, check that all DIMMS are the same
+ * speed, otherwise set the speed as invalid.
+ */
+ *dclk_freq = -1;
+ }
+ }
+}
+
+/*
+ * The default DCLK frequency is used as a fallback if we
+ * fail to find anything reliable in the DMI. The value
+ * is taken straight from the datasheet.
+ */
+#define DEFAULT_DCLK_FREQ 800
+
+static int get_dclk_freq(void)
+{
+ int dclk_freq = 0;
+
+ dmi_walk(decode_dclk, (void *)&dclk_freq);
+
+ if (dclk_freq < 1)
+ return DEFAULT_DCLK_FREQ;
+
+ return dclk_freq;
+}
+
+/*
+ * set_sdram_scrub_rate This routine sets byte/sec bandwidth scrub rate
+ * to hardware according to SCRUBINTERVAL formula
+ * found in datasheet.
+ */
+static int set_sdram_scrub_rate(struct mem_ctl_info *mci, u32 new_bw)
+{
+ struct i7core_pvt *pvt = mci->pvt_info;
+ struct pci_dev *pdev;
+ u32 dw_scrub;
+ u32 dw_ssr;
+
+ /* Get data from the MC register, function 2 */
+ pdev = pvt->pci_mcr[2];
+ if (!pdev)
+ return -ENODEV;
+
+ pci_read_config_dword(pdev, MC_SCRUB_CONTROL, &dw_scrub);
+
+ if (new_bw == 0) {
+ /* Prepare to disable petrol scrub */
+ dw_scrub &= ~STARTSCRUB;
+ /* Stop the patrol scrub engine */
+ write_and_test(pdev, MC_SCRUB_CONTROL,
+ dw_scrub & ~SCRUBINTERVAL_MASK);
+
+ /* Get current status of scrub rate and set bit to disable */
+ pci_read_config_dword(pdev, MC_SSRCONTROL, &dw_ssr);
+ dw_ssr &= ~SSR_MODE_MASK;
+ dw_ssr |= SSR_MODE_DISABLE;
+ } else {
+ const int cache_line_size = 64;
+ const u32 freq_dclk_mhz = pvt->dclk_freq;
+ unsigned long long scrub_interval;
+ /*
+ * Translate the desired scrub rate to a register value and
+ * program the corresponding register value.
+ */
+ scrub_interval = (unsigned long long)freq_dclk_mhz *
+ cache_line_size * 1000000;
+ do_div(scrub_interval, new_bw);
+
+ if (!scrub_interval || scrub_interval > SCRUBINTERVAL_MASK)
+ return -EINVAL;
+
+ dw_scrub = SCRUBINTERVAL_MASK & scrub_interval;
+
+ /* Start the patrol scrub engine */
+ pci_write_config_dword(pdev, MC_SCRUB_CONTROL,
+ STARTSCRUB | dw_scrub);
+
+ /* Get current status of scrub rate and set bit to enable */
+ pci_read_config_dword(pdev, MC_SSRCONTROL, &dw_ssr);
+ dw_ssr &= ~SSR_MODE_MASK;
+ dw_ssr |= SSR_MODE_ENABLE;
+ }
+ /* Disable or enable scrubbing */
+ pci_write_config_dword(pdev, MC_SSRCONTROL, dw_ssr);
+
+ return new_bw;
+}
+
+/*
+ * get_sdram_scrub_rate This routine convert current scrub rate value
+ * into byte/sec bandwidth accourding to
+ * SCRUBINTERVAL formula found in datasheet.
+ */
+static int get_sdram_scrub_rate(struct mem_ctl_info *mci)
+{
+ struct i7core_pvt *pvt = mci->pvt_info;
+ struct pci_dev *pdev;
+ const u32 cache_line_size = 64;
+ const u32 freq_dclk_mhz = pvt->dclk_freq;
+ unsigned long long scrub_rate;
+ u32 scrubval;
+
+ /* Get data from the MC register, function 2 */
+ pdev = pvt->pci_mcr[2];
+ if (!pdev)
+ return -ENODEV;
+
+ /* Get current scrub control data */
+ pci_read_config_dword(pdev, MC_SCRUB_CONTROL, &scrubval);
+
+ /* Mask highest 8-bits to 0 */
+ scrubval &= SCRUBINTERVAL_MASK;
+ if (!scrubval)
+ return 0;
+
+ /* Calculate scrub rate value into byte/sec bandwidth */
+ scrub_rate = (unsigned long long)freq_dclk_mhz *
+ 1000000 * cache_line_size;
+ do_div(scrub_rate, scrubval);
+ return (int)scrub_rate;
+}
+
+static void enable_sdram_scrub_setting(struct mem_ctl_info *mci)
+{
+ struct i7core_pvt *pvt = mci->pvt_info;
+ u32 pci_lock;
+
+ /* Unlock writes to pci registers */
+ pci_read_config_dword(pvt->pci_noncore, MC_CFG_CONTROL, &pci_lock);
+ pci_lock &= ~0x3;
+ pci_write_config_dword(pvt->pci_noncore, MC_CFG_CONTROL,
+ pci_lock | MC_CFG_UNLOCK);
+
+ mci->set_sdram_scrub_rate = set_sdram_scrub_rate;
+ mci->get_sdram_scrub_rate = get_sdram_scrub_rate;
+}
+
+static void disable_sdram_scrub_setting(struct mem_ctl_info *mci)
+{
+ struct i7core_pvt *pvt = mci->pvt_info;
+ u32 pci_lock;
+
+ /* Lock writes to pci registers */
+ pci_read_config_dword(pvt->pci_noncore, MC_CFG_CONTROL, &pci_lock);
+ pci_lock &= ~0x3;
+ pci_write_config_dword(pvt->pci_noncore, MC_CFG_CONTROL,
+ pci_lock | MC_CFG_LOCK);
}
static void i7core_pci_ctl_create(struct i7core_pvt *pvt)
@@ -1874,7 +2197,8 @@
&pvt->i7core_dev->pdev[0]->dev,
EDAC_MOD_STR);
if (unlikely(!pvt->i7core_pci))
- pr_warn("Unable to setup PCI error report via EDAC\n");
+ i7core_printk(KERN_WARNING,
+ "Unable to setup PCI error report via EDAC\n");
}
static void i7core_pci_ctl_release(struct i7core_pvt *pvt)
@@ -1906,8 +2230,11 @@
debugf0("MC: " __FILE__ ": %s(): mci = %p, dev = %p\n",
__func__, mci, &i7core_dev->pdev[0]->dev);
- /* Disable MCE NMI handler */
- edac_mce_unregister(&pvt->edac_mce);
+ /* Disable scrubrate setting */
+ if (pvt->enable_scrub)
+ disable_sdram_scrub_setting(mci);
+
+ atomic_notifier_chain_unregister(&x86_mce_decoder_chain, &i7_mce_dec);
/* Disable EDAC polling */
i7core_pci_ctl_release(pvt);
@@ -1979,6 +2306,10 @@
/* Set the function pointer to an actual operation function */
mci->edac_check = i7core_check_error;
+ /* Enable scrubrate setting */
+ if (pvt->enable_scrub)
+ enable_sdram_scrub_setting(mci);
+
/* add this new MC control structure to EDAC's list of MCs */
if (unlikely(edac_mc_add_mc(mci))) {
debugf0("MC: " __FILE__
@@ -2002,21 +2333,13 @@
/* allocating generic PCI control info */
i7core_pci_ctl_create(pvt);
- /* Registers on edac_mce in order to receive memory errors */
- pvt->edac_mce.priv = mci;
- pvt->edac_mce.check_error = i7core_mce_check_error;
- rc = edac_mce_register(&pvt->edac_mce);
- if (unlikely(rc < 0)) {
- debugf0("MC: " __FILE__
- ": %s(): failed edac_mce_register()\n", __func__);
- goto fail1;
- }
+ /* DCLK for scrub rate setting */
+ pvt->dclk_freq = get_dclk_freq();
+
+ atomic_notifier_chain_register(&x86_mce_decoder_chain, &i7_mce_dec);
return 0;
-fail1:
- i7core_pci_ctl_release(pvt);
- edac_mc_del_mc(mci->dev);
fail0:
kfree(mci->ctl_name);
edac_mc_free(mci);
@@ -2035,7 +2358,7 @@
static int __devinit i7core_probe(struct pci_dev *pdev,
const struct pci_device_id *id)
{
- int rc;
+ int rc, count = 0;
struct i7core_dev *i7core_dev;
/* get the pci devices we want to reserve for our use */
@@ -2055,12 +2378,28 @@
goto fail0;
list_for_each_entry(i7core_dev, &i7core_edac_list, list) {
+ count++;
rc = i7core_register_mci(i7core_dev);
if (unlikely(rc < 0))
goto fail1;
}
- i7core_printk(KERN_INFO, "Driver loaded.\n");
+ /*
+ * Nehalem-EX uses a different memory controller. However, as the
+ * memory controller is not visible on some Nehalem/Nehalem-EP, we
+ * need to indirectly probe via a X58 PCI device. The same devices
+ * are found on (some) Nehalem-EX. So, on those machines, the
+ * probe routine needs to return -ENODEV, as the actual Memory
+ * Controller registers won't be detected.
+ */
+ if (!count) {
+ rc = -ENODEV;
+ goto fail1;
+ }
+
+ i7core_printk(KERN_INFO,
+ "Driver loaded, %d memory controller(s) found.\n",
+ count);
mutex_unlock(&i7core_edac_lock);
return 0;
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
new file mode 100644
index 0000000..7a402bf
--- /dev/null
+++ b/drivers/edac/sb_edac.c
@@ -0,0 +1,1893 @@
+/* Intel Sandy Bridge -EN/-EP/-EX Memory Controller kernel module
+ *
+ * This driver supports the memory controllers found on the Intel
+ * processor family Sandy Bridge.
+ *
+ * This file may be distributed under the terms of the
+ * GNU General Public License version 2 only.
+ *
+ * Copyright (c) 2011 by:
+ * Mauro Carvalho Chehab <mchehab@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/edac.h>
+#include <linux/mmzone.h>
+#include <linux/smp.h>
+#include <linux/bitmap.h>
+#include <asm/processor.h>
+#include <asm/mce.h>
+
+#include "edac_core.h"
+
+/* Static vars */
+static LIST_HEAD(sbridge_edac_list);
+static DEFINE_MUTEX(sbridge_edac_lock);
+static int probed;
+
+/*
+ * Alter this version for the module when modifications are made
+ */
+#define SBRIDGE_REVISION " Ver: 1.0.0 "
+#define EDAC_MOD_STR "sbridge_edac"
+
+/*
+ * Debug macros
+ */
+#define sbridge_printk(level, fmt, arg...) \
+ edac_printk(level, "sbridge", fmt, ##arg)
+
+#define sbridge_mc_printk(mci, level, fmt, arg...) \
+ edac_mc_chipset_printk(mci, level, "sbridge", fmt, ##arg)
+
+/*
+ * Get a bit field at register value <v>, from bit <lo> to bit <hi>
+ */
+#define GET_BITFIELD(v, lo, hi) \
+ (((v) & ((1ULL << ((hi) - (lo) + 1)) - 1) << (lo)) >> (lo))
+
+/*
+ * sbridge Memory Controller Registers
+ */
+
+/*
+ * FIXME: For now, let's order by device function, as it makes
+ * easier for driver's development proccess. This table should be
+ * moved to pci_id.h when submitted upstream
+ */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0 0x3cf4 /* 12.6 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1 0x3cf6 /* 12.7 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_BR 0x3cf5 /* 13.6 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0 0x3ca0 /* 14.0 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA 0x3ca8 /* 15.0 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS 0x3c71 /* 15.1 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0 0x3caa /* 15.2 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1 0x3cab /* 15.3 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2 0x3cac /* 15.4 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3 0x3cad /* 15.5 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO 0x3cb8 /* 17.0 */
+
+ /*
+ * Currently, unused, but will be needed in the future
+ * implementations, as they hold the error counters
+ */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR0 0x3c72 /* 16.2 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR1 0x3c73 /* 16.3 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR2 0x3c76 /* 16.6 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR3 0x3c77 /* 16.7 */
+
+/* Devices 12 Function 6, Offsets 0x80 to 0xcc */
+static const u32 dram_rule[] = {
+ 0x80, 0x88, 0x90, 0x98, 0xa0,
+ 0xa8, 0xb0, 0xb8, 0xc0, 0xc8,
+};
+#define MAX_SAD ARRAY_SIZE(dram_rule)
+
+#define SAD_LIMIT(reg) ((GET_BITFIELD(reg, 6, 25) << 26) | 0x3ffffff)
+#define DRAM_ATTR(reg) GET_BITFIELD(reg, 2, 3)
+#define INTERLEAVE_MODE(reg) GET_BITFIELD(reg, 1, 1)
+#define DRAM_RULE_ENABLE(reg) GET_BITFIELD(reg, 0, 0)
+
+static char *get_dram_attr(u32 reg)
+{
+ switch(DRAM_ATTR(reg)) {
+ case 0:
+ return "DRAM";
+ case 1:
+ return "MMCFG";
+ case 2:
+ return "NXM";
+ default:
+ return "unknown";
+ }
+}
+
+static const u32 interleave_list[] = {
+ 0x84, 0x8c, 0x94, 0x9c, 0xa4,
+ 0xac, 0xb4, 0xbc, 0xc4, 0xcc,
+};
+#define MAX_INTERLEAVE ARRAY_SIZE(interleave_list)
+
+#define SAD_PKG0(reg) GET_BITFIELD(reg, 0, 2)
+#define SAD_PKG1(reg) GET_BITFIELD(reg, 3, 5)
+#define SAD_PKG2(reg) GET_BITFIELD(reg, 8, 10)
+#define SAD_PKG3(reg) GET_BITFIELD(reg, 11, 13)
+#define SAD_PKG4(reg) GET_BITFIELD(reg, 16, 18)
+#define SAD_PKG5(reg) GET_BITFIELD(reg, 19, 21)
+#define SAD_PKG6(reg) GET_BITFIELD(reg, 24, 26)
+#define SAD_PKG7(reg) GET_BITFIELD(reg, 27, 29)
+
+static inline int sad_pkg(u32 reg, int interleave)
+{
+ switch (interleave) {
+ case 0:
+ return SAD_PKG0(reg);
+ case 1:
+ return SAD_PKG1(reg);
+ case 2:
+ return SAD_PKG2(reg);
+ case 3:
+ return SAD_PKG3(reg);
+ case 4:
+ return SAD_PKG4(reg);
+ case 5:
+ return SAD_PKG5(reg);
+ case 6:
+ return SAD_PKG6(reg);
+ case 7:
+ return SAD_PKG7(reg);
+ default:
+ return -EINVAL;
+ }
+}
+
+/* Devices 12 Function 7 */
+
+#define TOLM 0x80
+#define TOHM 0x84
+
+#define GET_TOLM(reg) ((GET_BITFIELD(reg, 0, 3) << 28) | 0x3ffffff)
+#define GET_TOHM(reg) ((GET_BITFIELD(reg, 0, 20) << 25) | 0x3ffffff)
+
+/* Device 13 Function 6 */
+
+#define SAD_TARGET 0xf0
+
+#define SOURCE_ID(reg) GET_BITFIELD(reg, 9, 11)
+
+#define SAD_CONTROL 0xf4
+
+#define NODE_ID(reg) GET_BITFIELD(reg, 0, 2)
+
+/* Device 14 function 0 */
+
+static const u32 tad_dram_rule[] = {
+ 0x40, 0x44, 0x48, 0x4c,
+ 0x50, 0x54, 0x58, 0x5c,
+ 0x60, 0x64, 0x68, 0x6c,
+};
+#define MAX_TAD ARRAY_SIZE(tad_dram_rule)
+
+#define TAD_LIMIT(reg) ((GET_BITFIELD(reg, 12, 31) << 26) | 0x3ffffff)
+#define TAD_SOCK(reg) GET_BITFIELD(reg, 10, 11)
+#define TAD_CH(reg) GET_BITFIELD(reg, 8, 9)
+#define TAD_TGT3(reg) GET_BITFIELD(reg, 6, 7)
+#define TAD_TGT2(reg) GET_BITFIELD(reg, 4, 5)
+#define TAD_TGT1(reg) GET_BITFIELD(reg, 2, 3)
+#define TAD_TGT0(reg) GET_BITFIELD(reg, 0, 1)
+
+/* Device 15, function 0 */
+
+#define MCMTR 0x7c
+
+#define IS_ECC_ENABLED(mcmtr) GET_BITFIELD(mcmtr, 2, 2)
+#define IS_LOCKSTEP_ENABLED(mcmtr) GET_BITFIELD(mcmtr, 1, 1)
+#define IS_CLOSE_PG(mcmtr) GET_BITFIELD(mcmtr, 0, 0)
+
+/* Device 15, function 1 */
+
+#define RASENABLES 0xac
+#define IS_MIRROR_ENABLED(reg) GET_BITFIELD(reg, 0, 0)
+
+/* Device 15, functions 2-5 */
+
+static const int mtr_regs[] = {
+ 0x80, 0x84, 0x88,
+};
+
+#define RANK_DISABLE(mtr) GET_BITFIELD(mtr, 16, 19)
+#define IS_DIMM_PRESENT(mtr) GET_BITFIELD(mtr, 14, 14)
+#define RANK_CNT_BITS(mtr) GET_BITFIELD(mtr, 12, 13)
+#define RANK_WIDTH_BITS(mtr) GET_BITFIELD(mtr, 2, 4)
+#define COL_WIDTH_BITS(mtr) GET_BITFIELD(mtr, 0, 1)
+
+static const u32 tad_ch_nilv_offset[] = {
+ 0x90, 0x94, 0x98, 0x9c,
+ 0xa0, 0xa4, 0xa8, 0xac,
+ 0xb0, 0xb4, 0xb8, 0xbc,
+};
+#define CHN_IDX_OFFSET(reg) GET_BITFIELD(reg, 28, 29)
+#define TAD_OFFSET(reg) (GET_BITFIELD(reg, 6, 25) << 26)
+
+static const u32 rir_way_limit[] = {
+ 0x108, 0x10c, 0x110, 0x114, 0x118,
+};
+#define MAX_RIR_RANGES ARRAY_SIZE(rir_way_limit)
+
+#define IS_RIR_VALID(reg) GET_BITFIELD(reg, 31, 31)
+#define RIR_WAY(reg) GET_BITFIELD(reg, 28, 29)
+#define RIR_LIMIT(reg) ((GET_BITFIELD(reg, 1, 10) << 29)| 0x1fffffff)
+
+#define MAX_RIR_WAY 8
+
+static const u32 rir_offset[MAX_RIR_RANGES][MAX_RIR_WAY] = {
+ { 0x120, 0x124, 0x128, 0x12c, 0x130, 0x134, 0x138, 0x13c },
+ { 0x140, 0x144, 0x148, 0x14c, 0x150, 0x154, 0x158, 0x15c },
+ { 0x160, 0x164, 0x168, 0x16c, 0x170, 0x174, 0x178, 0x17c },
+ { 0x180, 0x184, 0x188, 0x18c, 0x190, 0x194, 0x198, 0x19c },
+ { 0x1a0, 0x1a4, 0x1a8, 0x1ac, 0x1b0, 0x1b4, 0x1b8, 0x1bc },
+};
+
+#define RIR_RNK_TGT(reg) GET_BITFIELD(reg, 16, 19)
+#define RIR_OFFSET(reg) GET_BITFIELD(reg, 2, 14)
+
+/* Device 16, functions 2-7 */
+
+/*
+ * FIXME: Implement the error count reads directly
+ */
+
+static const u32 correrrcnt[] = {
+ 0x104, 0x108, 0x10c, 0x110,
+};
+
+#define RANK_ODD_OV(reg) GET_BITFIELD(reg, 31, 31)
+#define RANK_ODD_ERR_CNT(reg) GET_BITFIELD(reg, 16, 30)
+#define RANK_EVEN_OV(reg) GET_BITFIELD(reg, 15, 15)
+#define RANK_EVEN_ERR_CNT(reg) GET_BITFIELD(reg, 0, 14)
+
+static const u32 correrrthrsld[] = {
+ 0x11c, 0x120, 0x124, 0x128,
+};
+
+#define RANK_ODD_ERR_THRSLD(reg) GET_BITFIELD(reg, 16, 30)
+#define RANK_EVEN_ERR_THRSLD(reg) GET_BITFIELD(reg, 0, 14)
+
+
+/* Device 17, function 0 */
+
+#define RANK_CFG_A 0x0328
+
+#define IS_RDIMM_ENABLED(reg) GET_BITFIELD(reg, 11, 11)
+
+/*
+ * sbridge structs
+ */
+
+#define NUM_CHANNELS 4
+#define MAX_DIMMS 3 /* Max DIMMS per channel */
+
+struct sbridge_info {
+ u32 mcmtr;
+};
+
+struct sbridge_channel {
+ u32 ranks;
+ u32 dimms;
+};
+
+struct pci_id_descr {
+ int dev;
+ int func;
+ int dev_id;
+ int optional;
+};
+
+struct pci_id_table {
+ const struct pci_id_descr *descr;
+ int n_devs;
+};
+
+struct sbridge_dev {
+ struct list_head list;
+ u8 bus, mc;
+ u8 node_id, source_id;
+ struct pci_dev **pdev;
+ int n_devs;
+ struct mem_ctl_info *mci;
+};
+
+struct sbridge_pvt {
+ struct pci_dev *pci_ta, *pci_ddrio, *pci_ras;
+ struct pci_dev *pci_sad0, *pci_sad1, *pci_ha0;
+ struct pci_dev *pci_br;
+ struct pci_dev *pci_tad[NUM_CHANNELS];
+
+ struct sbridge_dev *sbridge_dev;
+
+ struct sbridge_info info;
+ struct sbridge_channel channel[NUM_CHANNELS];
+
+ int csrow_map[NUM_CHANNELS][MAX_DIMMS];
+
+ /* Memory type detection */
+ bool is_mirrored, is_lockstep, is_close_pg;
+
+ /* Fifo double buffers */
+ struct mce mce_entry[MCE_LOG_LEN];
+ struct mce mce_outentry[MCE_LOG_LEN];
+
+ /* Fifo in/out counters */
+ unsigned mce_in, mce_out;
+
+ /* Count indicator to show errors not got */
+ unsigned mce_overrun;
+
+ /* Memory description */
+ u64 tolm, tohm;
+};
+
+#define PCI_DESCR(device, function, device_id) \
+ .dev = (device), \
+ .func = (function), \
+ .dev_id = (device_id)
+
+static const struct pci_id_descr pci_dev_descr_sbridge[] = {
+ /* Processor Home Agent */
+ { PCI_DESCR(14, 0, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0) },
+
+ /* Memory controller */
+ { PCI_DESCR(15, 0, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA) },
+ { PCI_DESCR(15, 1, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS) },
+ { PCI_DESCR(15, 2, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0) },
+ { PCI_DESCR(15, 3, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1) },
+ { PCI_DESCR(15, 4, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2) },
+ { PCI_DESCR(15, 5, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3) },
+ { PCI_DESCR(17, 0, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO) },
+
+ /* System Address Decoder */
+ { PCI_DESCR(12, 6, PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0) },
+ { PCI_DESCR(12, 7, PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1) },
+
+ /* Broadcast Registers */
+ { PCI_DESCR(13, 6, PCI_DEVICE_ID_INTEL_SBRIDGE_BR) },
+};
+
+#define PCI_ID_TABLE_ENTRY(A) { .descr=A, .n_devs = ARRAY_SIZE(A) }
+static const struct pci_id_table pci_dev_descr_sbridge_table[] = {
+ PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge),
+ {0,} /* 0 terminated list. */
+};
+
+/*
+ * pci_device_id table for which devices we are looking for
+ */
+static const struct pci_device_id sbridge_pci_tbl[] __devinitdata = {
+ {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA)},
+ {0,} /* 0 terminated list. */
+};
+
+
+/****************************************************************************
+ Anciliary status routines
+ ****************************************************************************/
+
+static inline int numrank(u32 mtr)
+{
+ int ranks = (1 << RANK_CNT_BITS(mtr));
+
+ if (ranks > 4) {
+ debugf0("Invalid number of ranks: %d (max = 4) raw value = %x (%04x)",
+ ranks, (unsigned int)RANK_CNT_BITS(mtr), mtr);
+ return -EINVAL;
+ }
+
+ return ranks;
+}
+
+static inline int numrow(u32 mtr)
+{
+ int rows = (RANK_WIDTH_BITS(mtr) + 12);
+
+ if (rows < 13 || rows > 18) {
+ debugf0("Invalid number of rows: %d (should be between 14 and 17) raw value = %x (%04x)",
+ rows, (unsigned int)RANK_WIDTH_BITS(mtr), mtr);
+ return -EINVAL;
+ }
+
+ return 1 << rows;
+}
+
+static inline int numcol(u32 mtr)
+{
+ int cols = (COL_WIDTH_BITS(mtr) + 10);
+
+ if (cols > 12) {
+ debugf0("Invalid number of cols: %d (max = 4) raw value = %x (%04x)",
+ cols, (unsigned int)COL_WIDTH_BITS(mtr), mtr);
+ return -EINVAL;
+ }
+
+ return 1 << cols;
+}
+
+static struct sbridge_dev *get_sbridge_dev(u8 bus)
+{
+ struct sbridge_dev *sbridge_dev;
+
+ list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) {
+ if (sbridge_dev->bus == bus)
+ return sbridge_dev;
+ }
+
+ return NULL;
+}
+
+static struct sbridge_dev *alloc_sbridge_dev(u8 bus,
+ const struct pci_id_table *table)
+{
+ struct sbridge_dev *sbridge_dev;
+
+ sbridge_dev = kzalloc(sizeof(*sbridge_dev), GFP_KERNEL);
+ if (!sbridge_dev)
+ return NULL;
+
+ sbridge_dev->pdev = kzalloc(sizeof(*sbridge_dev->pdev) * table->n_devs,
+ GFP_KERNEL);
+ if (!sbridge_dev->pdev) {
+ kfree(sbridge_dev);
+ return NULL;
+ }
+
+ sbridge_dev->bus = bus;
+ sbridge_dev->n_devs = table->n_devs;
+ list_add_tail(&sbridge_dev->list, &sbridge_edac_list);
+
+ return sbridge_dev;
+}
+
+static void free_sbridge_dev(struct sbridge_dev *sbridge_dev)
+{
+ list_del(&sbridge_dev->list);
+ kfree(sbridge_dev->pdev);
+ kfree(sbridge_dev);
+}
+
+/****************************************************************************
+ Memory check routines
+ ****************************************************************************/
+static struct pci_dev *get_pdev_slot_func(u8 bus, unsigned slot,
+ unsigned func)
+{
+ struct sbridge_dev *sbridge_dev = get_sbridge_dev(bus);
+ int i;
+
+ if (!sbridge_dev)
+ return NULL;
+
+ for (i = 0; i < sbridge_dev->n_devs; i++) {
+ if (!sbridge_dev->pdev[i])
+ continue;
+
+ if (PCI_SLOT(sbridge_dev->pdev[i]->devfn) == slot &&
+ PCI_FUNC(sbridge_dev->pdev[i]->devfn) == func) {
+ debugf1("Associated %02x.%02x.%d with %p\n",
+ bus, slot, func, sbridge_dev->pdev[i]);
+ return sbridge_dev->pdev[i];
+ }
+ }
+
+ return NULL;
+}
+
+/**
+ * sbridge_get_active_channels() - gets the number of channels and csrows
+ * bus: Device bus
+ * @channels: Number of channels that will be returned
+ * @csrows: Number of csrows found
+ *
+ * Since EDAC core needs to know in advance the number of available channels
+ * and csrows, in order to allocate memory for csrows/channels, it is needed
+ * to run two similar steps. At the first step, implemented on this function,
+ * it checks the number of csrows/channels present at one socket, identified
+ * by the associated PCI bus.
+ * this is used in order to properly allocate the size of mci components.
+ * Note: one csrow is one dimm.
+ */
+static int sbridge_get_active_channels(const u8 bus, unsigned *channels,
+ unsigned *csrows)
+{
+ struct pci_dev *pdev = NULL;
+ int i, j;
+ u32 mcmtr;
+
+ *channels = 0;
+ *csrows = 0;
+
+ pdev = get_pdev_slot_func(bus, 15, 0);
+ if (!pdev) {
+ sbridge_printk(KERN_ERR, "Couldn't find PCI device "
+ "%2x.%02d.%d!!!\n",
+ bus, 15, 0);
+ return -ENODEV;
+ }
+
+ pci_read_config_dword(pdev, MCMTR, &mcmtr);
+ if (!IS_ECC_ENABLED(mcmtr)) {
+ sbridge_printk(KERN_ERR, "ECC is disabled. Aborting\n");
+ return -ENODEV;
+ }
+
+ for (i = 0; i < NUM_CHANNELS; i++) {
+ u32 mtr;
+
+ /* Device 15 functions 2 - 5 */
+ pdev = get_pdev_slot_func(bus, 15, 2 + i);
+ if (!pdev) {
+ sbridge_printk(KERN_ERR, "Couldn't find PCI device "
+ "%2x.%02d.%d!!!\n",
+ bus, 15, 2 + i);
+ return -ENODEV;
+ }
+ (*channels)++;
+
+ for (j = 0; j < ARRAY_SIZE(mtr_regs); j++) {
+ pci_read_config_dword(pdev, mtr_regs[j], &mtr);
+ debugf1("Bus#%02x channel #%d MTR%d = %x\n", bus, i, j, mtr);
+ if (IS_DIMM_PRESENT(mtr))
+ (*csrows)++;
+ }
+ }
+
+ debugf0("Number of active channels: %d, number of active dimms: %d\n",
+ *channels, *csrows);
+
+ return 0;
+}
+
+static int get_dimm_config(const struct mem_ctl_info *mci)
+{
+ struct sbridge_pvt *pvt = mci->pvt_info;
+ struct csrow_info *csr;
+ int i, j, banks, ranks, rows, cols, size, npages;
+ int csrow = 0;
+ unsigned long last_page = 0;
+ u32 reg;
+ enum edac_type mode;
+ enum mem_type mtype;
+
+ pci_read_config_dword(pvt->pci_br, SAD_TARGET, ®);
+ pvt->sbridge_dev->source_id = SOURCE_ID(reg);
+
+ pci_read_config_dword(pvt->pci_br, SAD_CONTROL, ®);
+ pvt->sbridge_dev->node_id = NODE_ID(reg);
+ debugf0("mc#%d: Node ID: %d, source ID: %d\n",
+ pvt->sbridge_dev->mc,
+ pvt->sbridge_dev->node_id,
+ pvt->sbridge_dev->source_id);
+
+ pci_read_config_dword(pvt->pci_ras, RASENABLES, ®);
+ if (IS_MIRROR_ENABLED(reg)) {
+ debugf0("Memory mirror is enabled\n");
+ pvt->is_mirrored = true;
+ } else {
+ debugf0("Memory mirror is disabled\n");
+ pvt->is_mirrored = false;
+ }
+
+ pci_read_config_dword(pvt->pci_ta, MCMTR, &pvt->info.mcmtr);
+ if (IS_LOCKSTEP_ENABLED(pvt->info.mcmtr)) {
+ debugf0("Lockstep is enabled\n");
+ mode = EDAC_S8ECD8ED;
+ pvt->is_lockstep = true;
+ } else {
+ debugf0("Lockstep is disabled\n");
+ mode = EDAC_S4ECD4ED;
+ pvt->is_lockstep = false;
+ }
+ if (IS_CLOSE_PG(pvt->info.mcmtr)) {
+ debugf0("address map is on closed page mode\n");
+ pvt->is_close_pg = true;
+ } else {
+ debugf0("address map is on open page mode\n");
+ pvt->is_close_pg = false;
+ }
+
+ pci_read_config_dword(pvt->pci_ta, RANK_CFG_A, ®);
+ if (IS_RDIMM_ENABLED(reg)) {
+ /* FIXME: Can also be LRDIMM */
+ debugf0("Memory is registered\n");
+ mtype = MEM_RDDR3;
+ } else {
+ debugf0("Memory is unregistered\n");
+ mtype = MEM_DDR3;
+ }
+
+ /* On all supported DDR3 DIMM types, there are 8 banks available */
+ banks = 8;
+
+ for (i = 0; i < NUM_CHANNELS; i++) {
+ u32 mtr;
+
+ for (j = 0; j < ARRAY_SIZE(mtr_regs); j++) {
+ pci_read_config_dword(pvt->pci_tad[i],
+ mtr_regs[j], &mtr);
+ debugf4("Channel #%d MTR%d = %x\n", i, j, mtr);
+ if (IS_DIMM_PRESENT(mtr)) {
+ pvt->channel[i].dimms++;
+
+ ranks = numrank(mtr);
+ rows = numrow(mtr);
+ cols = numcol(mtr);
+
+ /* DDR3 has 8 I/O banks */
+ size = (rows * cols * banks * ranks) >> (20 - 3);
+ npages = MiB_TO_PAGES(size);
+
+ debugf0("mc#%d: channel %d, dimm %d, %d Mb (%d pages) bank: %d, rank: %d, row: %#x, col: %#x\n",
+ pvt->sbridge_dev->mc, i, j,
+ size, npages,
+ banks, ranks, rows, cols);
+ csr = &mci->csrows[csrow];
+
+ csr->first_page = last_page;
+ csr->last_page = last_page + npages - 1;
+ csr->page_mask = 0UL; /* Unused */
+ csr->nr_pages = npages;
+ csr->grain = 32;
+ csr->csrow_idx = csrow;
+ csr->dtype = (banks == 8) ? DEV_X8 : DEV_X4;
+ csr->ce_count = 0;
+ csr->ue_count = 0;
+ csr->mtype = mtype;
+ csr->edac_mode = mode;
+ csr->nr_channels = 1;
+ csr->channels[0].chan_idx = i;
+ csr->channels[0].ce_count = 0;
+ pvt->csrow_map[i][j] = csrow;
+ snprintf(csr->channels[0].label,
+ sizeof(csr->channels[0].label),
+ "CPU_SrcID#%u_Channel#%u_DIMM#%u",
+ pvt->sbridge_dev->source_id, i, j);
+ last_page += npages;
+ csrow++;
+ }
+ }
+ }
+
+ return 0;
+}
+
+static void get_memory_layout(const struct mem_ctl_info *mci)
+{
+ struct sbridge_pvt *pvt = mci->pvt_info;
+ int i, j, k, n_sads, n_tads, sad_interl;
+ u32 reg;
+ u64 limit, prv = 0;
+ u64 tmp_mb;
+ u32 rir_way;
+
+ /*
+ * Step 1) Get TOLM/TOHM ranges
+ */
+
+ /* Address range is 32:28 */
+ pci_read_config_dword(pvt->pci_sad1, TOLM,
+ ®);
+ pvt->tolm = GET_TOLM(reg);
+ tmp_mb = (1 + pvt->tolm) >> 20;
+
+ debugf0("TOLM: %Lu.%03Lu GB (0x%016Lx)\n",
+ tmp_mb / 1000, tmp_mb % 1000, (u64)pvt->tolm);
+
+ /* Address range is already 45:25 */
+ pci_read_config_dword(pvt->pci_sad1, TOHM,
+ ®);
+ pvt->tohm = GET_TOHM(reg);
+ tmp_mb = (1 + pvt->tohm) >> 20;
+
+ debugf0("TOHM: %Lu.%03Lu GB (0x%016Lx)",
+ tmp_mb / 1000, tmp_mb % 1000, (u64)pvt->tohm);
+
+ /*
+ * Step 2) Get SAD range and SAD Interleave list
+ * TAD registers contain the interleave wayness. However, it
+ * seems simpler to just discover it indirectly, with the
+ * algorithm bellow.
+ */
+ prv = 0;
+ for (n_sads = 0; n_sads < MAX_SAD; n_sads++) {
+ /* SAD_LIMIT Address range is 45:26 */
+ pci_read_config_dword(pvt->pci_sad0, dram_rule[n_sads],
+ ®);
+ limit = SAD_LIMIT(reg);
+
+ if (!DRAM_RULE_ENABLE(reg))
+ continue;
+
+ if (limit <= prv)
+ break;
+
+ tmp_mb = (limit + 1) >> 20;
+ debugf0("SAD#%d %s up to %Lu.%03Lu GB (0x%016Lx) %s reg=0x%08x\n",
+ n_sads,
+ get_dram_attr(reg),
+ tmp_mb / 1000, tmp_mb % 1000,
+ ((u64)tmp_mb) << 20L,
+ INTERLEAVE_MODE(reg) ? "Interleave: 8:6" : "Interleave: [8:6]XOR[18:16]",
+ reg);
+ prv = limit;
+
+ pci_read_config_dword(pvt->pci_sad0, interleave_list[n_sads],
+ ®);
+ sad_interl = sad_pkg(reg, 0);
+ for (j = 0; j < 8; j++) {
+ if (j > 0 && sad_interl == sad_pkg(reg, j))
+ break;
+
+ debugf0("SAD#%d, interleave #%d: %d\n",
+ n_sads, j, sad_pkg(reg, j));
+ }
+ }
+
+ /*
+ * Step 3) Get TAD range
+ */
+ prv = 0;
+ for (n_tads = 0; n_tads < MAX_TAD; n_tads++) {
+ pci_read_config_dword(pvt->pci_ha0, tad_dram_rule[n_tads],
+ ®);
+ limit = TAD_LIMIT(reg);
+ if (limit <= prv)
+ break;
+ tmp_mb = (limit + 1) >> 20;
+
+ debugf0("TAD#%d: up to %Lu.%03Lu GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n",
+ n_tads, tmp_mb / 1000, tmp_mb % 1000,
+ ((u64)tmp_mb) << 20L,
+ (u32)TAD_SOCK(reg),
+ (u32)TAD_CH(reg),
+ (u32)TAD_TGT0(reg),
+ (u32)TAD_TGT1(reg),
+ (u32)TAD_TGT2(reg),
+ (u32)TAD_TGT3(reg),
+ reg);
+ prv = tmp_mb;
+ }
+
+ /*
+ * Step 4) Get TAD offsets, per each channel
+ */
+ for (i = 0; i < NUM_CHANNELS; i++) {
+ if (!pvt->channel[i].dimms)
+ continue;
+ for (j = 0; j < n_tads; j++) {
+ pci_read_config_dword(pvt->pci_tad[i],
+ tad_ch_nilv_offset[j],
+ ®);
+ tmp_mb = TAD_OFFSET(reg) >> 20;
+ debugf0("TAD CH#%d, offset #%d: %Lu.%03Lu GB (0x%016Lx), reg=0x%08x\n",
+ i, j,
+ tmp_mb / 1000, tmp_mb % 1000,
+ ((u64)tmp_mb) << 20L,
+ reg);
+ }
+ }
+
+ /*
+ * Step 6) Get RIR Wayness/Limit, per each channel
+ */
+ for (i = 0; i < NUM_CHANNELS; i++) {
+ if (!pvt->channel[i].dimms)
+ continue;
+ for (j = 0; j < MAX_RIR_RANGES; j++) {
+ pci_read_config_dword(pvt->pci_tad[i],
+ rir_way_limit[j],
+ ®);
+
+ if (!IS_RIR_VALID(reg))
+ continue;
+
+ tmp_mb = RIR_LIMIT(reg) >> 20;
+ rir_way = 1 << RIR_WAY(reg);
+ debugf0("CH#%d RIR#%d, limit: %Lu.%03Lu GB (0x%016Lx), way: %d, reg=0x%08x\n",
+ i, j,
+ tmp_mb / 1000, tmp_mb % 1000,
+ ((u64)tmp_mb) << 20L,
+ rir_way,
+ reg);
+
+ for (k = 0; k < rir_way; k++) {
+ pci_read_config_dword(pvt->pci_tad[i],
+ rir_offset[j][k],
+ ®);
+ tmp_mb = RIR_OFFSET(reg) << 6;
+
+ debugf0("CH#%d RIR#%d INTL#%d, offset %Lu.%03Lu GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
+ i, j, k,
+ tmp_mb / 1000, tmp_mb % 1000,
+ ((u64)tmp_mb) << 20L,
+ (u32)RIR_RNK_TGT(reg),
+ reg);
+ }
+ }
+ }
+}
+
+struct mem_ctl_info *get_mci_for_node_id(u8 node_id)
+{
+ struct sbridge_dev *sbridge_dev;
+
+ list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) {
+ if (sbridge_dev->node_id == node_id)
+ return sbridge_dev->mci;
+ }
+ return NULL;
+}
+
+static int get_memory_error_data(struct mem_ctl_info *mci,
+ u64 addr,
+ u8 *socket,
+ long *channel_mask,
+ u8 *rank,
+ char *area_type)
+{
+ struct mem_ctl_info *new_mci;
+ struct sbridge_pvt *pvt = mci->pvt_info;
+ char msg[256];
+ int n_rir, n_sads, n_tads, sad_way, sck_xch;
+ int sad_interl, idx, base_ch;
+ int interleave_mode;
+ unsigned sad_interleave[MAX_INTERLEAVE];
+ u32 reg;
+ u8 ch_way,sck_way;
+ u32 tad_offset;
+ u32 rir_way;
+ u64 ch_addr, offset, limit, prv = 0;
+
+
+ /*
+ * Step 0) Check if the address is at special memory ranges
+ * The check bellow is probably enough to fill all cases where
+ * the error is not inside a memory, except for the legacy
+ * range (e. g. VGA addresses). It is unlikely, however, that the
+ * memory controller would generate an error on that range.
+ */
+ if ((addr > (u64) pvt->tolm) && (addr < (1L << 32))) {
+ sprintf(msg, "Error at TOLM area, on addr 0x%08Lx", addr);
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ if (addr >= (u64)pvt->tohm) {
+ sprintf(msg, "Error at MMIOH area, on addr 0x%016Lx", addr);
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+
+ /*
+ * Step 1) Get socket
+ */
+ for (n_sads = 0; n_sads < MAX_SAD; n_sads++) {
+ pci_read_config_dword(pvt->pci_sad0, dram_rule[n_sads],
+ ®);
+
+ if (!DRAM_RULE_ENABLE(reg))
+ continue;
+
+ limit = SAD_LIMIT(reg);
+ if (limit <= prv) {
+ sprintf(msg, "Can't discover the memory socket");
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ if (addr <= limit)
+ break;
+ prv = limit;
+ }
+ if (n_sads == MAX_SAD) {
+ sprintf(msg, "Can't discover the memory socket");
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ area_type = get_dram_attr(reg);
+ interleave_mode = INTERLEAVE_MODE(reg);
+
+ pci_read_config_dword(pvt->pci_sad0, interleave_list[n_sads],
+ ®);
+ sad_interl = sad_pkg(reg, 0);
+ for (sad_way = 0; sad_way < 8; sad_way++) {
+ if (sad_way > 0 && sad_interl == sad_pkg(reg, sad_way))
+ break;
+ sad_interleave[sad_way] = sad_pkg(reg, sad_way);
+ debugf0("SAD interleave #%d: %d\n",
+ sad_way, sad_interleave[sad_way]);
+ }
+ debugf0("mc#%d: Error detected on SAD#%d: address 0x%016Lx < 0x%016Lx, Interleave [%d:6]%s\n",
+ pvt->sbridge_dev->mc,
+ n_sads,
+ addr,
+ limit,
+ sad_way + 7,
+ INTERLEAVE_MODE(reg) ? "" : "XOR[18:16]");
+ if (interleave_mode)
+ idx = ((addr >> 6) ^ (addr >> 16)) & 7;
+ else
+ idx = (addr >> 6) & 7;
+ switch (sad_way) {
+ case 1:
+ idx = 0;
+ break;
+ case 2:
+ idx = idx & 1;
+ break;
+ case 4:
+ idx = idx & 3;
+ break;
+ case 8:
+ break;
+ default:
+ sprintf(msg, "Can't discover socket interleave");
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ *socket = sad_interleave[idx];
+ debugf0("SAD interleave index: %d (wayness %d) = CPU socket %d\n",
+ idx, sad_way, *socket);
+
+ /*
+ * Move to the proper node structure, in order to access the
+ * right PCI registers
+ */
+ new_mci = get_mci_for_node_id(*socket);
+ if (!new_mci) {
+ sprintf(msg, "Struct for socket #%u wasn't initialized",
+ *socket);
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ mci = new_mci;
+ pvt = mci->pvt_info;
+
+ /*
+ * Step 2) Get memory channel
+ */
+ prv = 0;
+ for (n_tads = 0; n_tads < MAX_TAD; n_tads++) {
+ pci_read_config_dword(pvt->pci_ha0, tad_dram_rule[n_tads],
+ ®);
+ limit = TAD_LIMIT(reg);
+ if (limit <= prv) {
+ sprintf(msg, "Can't discover the memory channel");
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ if (addr <= limit)
+ break;
+ prv = limit;
+ }
+ ch_way = TAD_CH(reg) + 1;
+ sck_way = TAD_SOCK(reg) + 1;
+ /*
+ * FIXME: Is it right to always use channel 0 for offsets?
+ */
+ pci_read_config_dword(pvt->pci_tad[0],
+ tad_ch_nilv_offset[n_tads],
+ &tad_offset);
+
+ if (ch_way == 3)
+ idx = addr >> 6;
+ else
+ idx = addr >> (6 + sck_way);
+ idx = idx % ch_way;
+
+ /*
+ * FIXME: Shouldn't we use CHN_IDX_OFFSET() here, when ch_way == 3 ???
+ */
+ switch (idx) {
+ case 0:
+ base_ch = TAD_TGT0(reg);
+ break;
+ case 1:
+ base_ch = TAD_TGT1(reg);
+ break;
+ case 2:
+ base_ch = TAD_TGT2(reg);
+ break;
+ case 3:
+ base_ch = TAD_TGT3(reg);
+ break;
+ default:
+ sprintf(msg, "Can't discover the TAD target");
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ *channel_mask = 1 << base_ch;
+
+ if (pvt->is_mirrored) {
+ *channel_mask |= 1 << ((base_ch + 2) % 4);
+ switch(ch_way) {
+ case 2:
+ case 4:
+ sck_xch = 1 << sck_way * (ch_way >> 1);
+ break;
+ default:
+ sprintf(msg, "Invalid mirror set. Can't decode addr");
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ } else
+ sck_xch = (1 << sck_way) * ch_way;
+
+ if (pvt->is_lockstep)
+ *channel_mask |= 1 << ((base_ch + 1) % 4);
+
+ offset = TAD_OFFSET(tad_offset);
+
+ debugf0("TAD#%d: address 0x%016Lx < 0x%016Lx, socket interleave %d, channel interleave %d (offset 0x%08Lx), index %d, base ch: %d, ch mask: 0x%02lx\n",
+ n_tads,
+ addr,
+ limit,
+ (u32)TAD_SOCK(reg),
+ ch_way,
+ offset,
+ idx,
+ base_ch,
+ *channel_mask);
+
+ /* Calculate channel address */
+ /* Remove the TAD offset */
+
+ if (offset > addr) {
+ sprintf(msg, "Can't calculate ch addr: TAD offset 0x%08Lx is too high for addr 0x%08Lx!",
+ offset, addr);
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ addr -= offset;
+ /* Store the low bits [0:6] of the addr */
+ ch_addr = addr & 0x7f;
+ /* Remove socket wayness and remove 6 bits */
+ addr >>= 6;
+ addr /= sck_xch;
+#if 0
+ /* Divide by channel way */
+ addr = addr / ch_way;
+#endif
+ /* Recover the last 6 bits */
+ ch_addr |= addr << 6;
+
+ /*
+ * Step 3) Decode rank
+ */
+ for (n_rir = 0; n_rir < MAX_RIR_RANGES; n_rir++) {
+ pci_read_config_dword(pvt->pci_tad[base_ch],
+ rir_way_limit[n_rir],
+ ®);
+
+ if (!IS_RIR_VALID(reg))
+ continue;
+
+ limit = RIR_LIMIT(reg);
+
+ debugf0("RIR#%d, limit: %Lu.%03Lu GB (0x%016Lx), way: %d\n",
+ n_rir,
+ (limit >> 20) / 1000, (limit >> 20) % 1000,
+ limit,
+ 1 << RIR_WAY(reg));
+ if (ch_addr <= limit)
+ break;
+ }
+ if (n_rir == MAX_RIR_RANGES) {
+ sprintf(msg, "Can't discover the memory rank for ch addr 0x%08Lx",
+ ch_addr);
+ edac_mc_handle_ce_no_info(mci, msg);
+ return -EINVAL;
+ }
+ rir_way = RIR_WAY(reg);
+ if (pvt->is_close_pg)
+ idx = (ch_addr >> 6);
+ else
+ idx = (ch_addr >> 13); /* FIXME: Datasheet says to shift by 15 */
+ idx %= 1 << rir_way;
+
+ pci_read_config_dword(pvt->pci_tad[base_ch],
+ rir_offset[n_rir][idx],
+ ®);
+ *rank = RIR_RNK_TGT(reg);
+
+ debugf0("RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n",
+ n_rir,
+ ch_addr,
+ limit,
+ rir_way,
+ idx);
+
+ return 0;
+}
+
+/****************************************************************************
+ Device initialization routines: put/get, init/exit
+ ****************************************************************************/
+
+/*
+ * sbridge_put_all_devices 'put' all the devices that we have
+ * reserved via 'get'
+ */
+static void sbridge_put_devices(struct sbridge_dev *sbridge_dev)
+{
+ int i;
+
+ debugf0(__FILE__ ": %s()\n", __func__);
+ for (i = 0; i < sbridge_dev->n_devs; i++) {
+ struct pci_dev *pdev = sbridge_dev->pdev[i];
+ if (!pdev)
+ continue;
+ debugf0("Removing dev %02x:%02x.%d\n",
+ pdev->bus->number,
+ PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));
+ pci_dev_put(pdev);
+ }
+}
+
+static void sbridge_put_all_devices(void)
+{
+ struct sbridge_dev *sbridge_dev, *tmp;
+
+ list_for_each_entry_safe(sbridge_dev, tmp, &sbridge_edac_list, list) {
+ sbridge_put_devices(sbridge_dev);
+ free_sbridge_dev(sbridge_dev);
+ }
+}
+
+/*
+ * sbridge_get_all_devices Find and perform 'get' operation on the MCH's
+ * device/functions we want to reference for this driver
+ *
+ * Need to 'get' device 16 func 1 and func 2
+ */
+static int sbridge_get_onedevice(struct pci_dev **prev,
+ u8 *num_mc,
+ const struct pci_id_table *table,
+ const unsigned devno)
+{
+ struct sbridge_dev *sbridge_dev;
+ const struct pci_id_descr *dev_descr = &table->descr[devno];
+
+ struct pci_dev *pdev = NULL;
+ u8 bus = 0;
+
+ sbridge_printk(KERN_INFO,
+ "Seeking for: dev %02x.%d PCI ID %04x:%04x\n",
+ dev_descr->dev, dev_descr->func,
+ PCI_VENDOR_ID_INTEL, dev_descr->dev_id);
+
+ pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+ dev_descr->dev_id, *prev);
+
+ if (!pdev) {
+ if (*prev) {
+ *prev = pdev;
+ return 0;
+ }
+
+ if (dev_descr->optional)
+ return 0;
+
+ if (devno == 0)
+ return -ENODEV;
+
+ sbridge_printk(KERN_INFO,
+ "Device not found: dev %02x.%d PCI ID %04x:%04x\n",
+ dev_descr->dev, dev_descr->func,
+ PCI_VENDOR_ID_INTEL, dev_descr->dev_id);
+
+ /* End of list, leave */
+ return -ENODEV;
+ }
+ bus = pdev->bus->number;
+
+ sbridge_dev = get_sbridge_dev(bus);
+ if (!sbridge_dev) {
+ sbridge_dev = alloc_sbridge_dev(bus, table);
+ if (!sbridge_dev) {
+ pci_dev_put(pdev);
+ return -ENOMEM;
+ }
+ (*num_mc)++;
+ }
+
+ if (sbridge_dev->pdev[devno]) {
+ sbridge_printk(KERN_ERR,
+ "Duplicated device for "
+ "dev %02x:%d.%d PCI ID %04x:%04x\n",
+ bus, dev_descr->dev, dev_descr->func,
+ PCI_VENDOR_ID_INTEL, dev_descr->dev_id);
+ pci_dev_put(pdev);
+ return -ENODEV;
+ }
+
+ sbridge_dev->pdev[devno] = pdev;
+
+ /* Sanity check */
+ if (unlikely(PCI_SLOT(pdev->devfn) != dev_descr->dev ||
+ PCI_FUNC(pdev->devfn) != dev_descr->func)) {
+ sbridge_printk(KERN_ERR,
+ "Device PCI ID %04x:%04x "
+ "has dev %02x:%d.%d instead of dev %02x:%02x.%d\n",
+ PCI_VENDOR_ID_INTEL, dev_descr->dev_id,
+ bus, PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn),
+ bus, dev_descr->dev, dev_descr->func);
+ return -ENODEV;
+ }
+
+ /* Be sure that the device is enabled */
+ if (unlikely(pci_enable_device(pdev) < 0)) {
+ sbridge_printk(KERN_ERR,
+ "Couldn't enable "
+ "dev %02x:%d.%d PCI ID %04x:%04x\n",
+ bus, dev_descr->dev, dev_descr->func,
+ PCI_VENDOR_ID_INTEL, dev_descr->dev_id);
+ return -ENODEV;
+ }
+
+ debugf0("Detected dev %02x:%d.%d PCI ID %04x:%04x\n",
+ bus, dev_descr->dev,
+ dev_descr->func,
+ PCI_VENDOR_ID_INTEL, dev_descr->dev_id);
+
+ /*
+ * As stated on drivers/pci/search.c, the reference count for
+ * @from is always decremented if it is not %NULL. So, as we need
+ * to get all devices up to null, we need to do a get for the device
+ */
+ pci_dev_get(pdev);
+
+ *prev = pdev;
+
+ return 0;
+}
+
+static int sbridge_get_all_devices(u8 *num_mc)
+{
+ int i, rc;
+ struct pci_dev *pdev = NULL;
+ const struct pci_id_table *table = pci_dev_descr_sbridge_table;
+
+ while (table && table->descr) {
+ for (i = 0; i < table->n_devs; i++) {
+ pdev = NULL;
+ do {
+ rc = sbridge_get_onedevice(&pdev, num_mc,
+ table, i);
+ if (rc < 0) {
+ if (i == 0) {
+ i = table->n_devs;
+ break;
+ }
+ sbridge_put_all_devices();
+ return -ENODEV;
+ }
+ } while (pdev);
+ }
+ table++;
+ }
+
+ return 0;
+}
+
+static int mci_bind_devs(struct mem_ctl_info *mci,
+ struct sbridge_dev *sbridge_dev)
+{
+ struct sbridge_pvt *pvt = mci->pvt_info;
+ struct pci_dev *pdev;
+ int i, func, slot;
+
+ for (i = 0; i < sbridge_dev->n_devs; i++) {
+ pdev = sbridge_dev->pdev[i];
+ if (!pdev)
+ continue;
+ slot = PCI_SLOT(pdev->devfn);
+ func = PCI_FUNC(pdev->devfn);
+ switch (slot) {
+ case 12:
+ switch (func) {
+ case 6:
+ pvt->pci_sad0 = pdev;
+ break;
+ case 7:
+ pvt->pci_sad1 = pdev;
+ break;
+ default:
+ goto error;
+ }
+ break;
+ case 13:
+ switch (func) {
+ case 6:
+ pvt->pci_br = pdev;
+ break;
+ default:
+ goto error;
+ }
+ break;
+ case 14:
+ switch (func) {
+ case 0:
+ pvt->pci_ha0 = pdev;
+ break;
+ default:
+ goto error;
+ }
+ break;
+ case 15:
+ switch (func) {
+ case 0:
+ pvt->pci_ta = pdev;
+ break;
+ case 1:
+ pvt->pci_ras = pdev;
+ break;
+ case 2:
+ case 3:
+ case 4:
+ case 5:
+ pvt->pci_tad[func - 2] = pdev;
+ break;
+ default:
+ goto error;
+ }
+ break;
+ case 17:
+ switch (func) {
+ case 0:
+ pvt->pci_ddrio = pdev;
+ break;
+ default:
+ goto error;
+ }
+ break;
+ default:
+ goto error;
+ }
+
+ debugf0("Associated PCI %02x.%02d.%d with dev = %p\n",
+ sbridge_dev->bus,
+ PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn),
+ pdev);
+ }
+
+ /* Check if everything were registered */
+ if (!pvt->pci_sad0 || !pvt->pci_sad1 || !pvt->pci_ha0 ||
+ !pvt-> pci_tad || !pvt->pci_ras || !pvt->pci_ta ||
+ !pvt->pci_ddrio)
+ goto enodev;
+
+ for (i = 0; i < NUM_CHANNELS; i++) {
+ if (!pvt->pci_tad[i])
+ goto enodev;
+ }
+ return 0;
+
+enodev:
+ sbridge_printk(KERN_ERR, "Some needed devices are missing\n");
+ return -ENODEV;
+
+error:
+ sbridge_printk(KERN_ERR, "Device %d, function %d "
+ "is out of the expected range\n",
+ slot, func);
+ return -EINVAL;
+}
+
+/****************************************************************************
+ Error check routines
+ ****************************************************************************/
+
+/*
+ * While Sandy Bridge has error count registers, SMI BIOS read values from
+ * and resets the counters. So, they are not reliable for the OS to read
+ * from them. So, we have no option but to just trust on whatever MCE is
+ * telling us about the errors.
+ */
+static void sbridge_mce_output_error(struct mem_ctl_info *mci,
+ const struct mce *m)
+{
+ struct mem_ctl_info *new_mci;
+ struct sbridge_pvt *pvt = mci->pvt_info;
+ char *type, *optype, *msg, *recoverable_msg;
+ bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0);
+ bool overflow = GET_BITFIELD(m->status, 62, 62);
+ bool uncorrected_error = GET_BITFIELD(m->status, 61, 61);
+ bool recoverable = GET_BITFIELD(m->status, 56, 56);
+ u32 core_err_cnt = GET_BITFIELD(m->status, 38, 52);
+ u32 mscod = GET_BITFIELD(m->status, 16, 31);
+ u32 errcode = GET_BITFIELD(m->status, 0, 15);
+ u32 channel = GET_BITFIELD(m->status, 0, 3);
+ u32 optypenum = GET_BITFIELD(m->status, 4, 6);
+ long channel_mask, first_channel;
+ u8 rank, socket;
+ int csrow, rc, dimm;
+ char *area_type = "Unknown";
+
+ if (ripv)
+ type = "NON_FATAL";
+ else
+ type = "FATAL";
+
+ /*
+ * According with Table 15-9 of the Intel Archictecture spec vol 3A,
+ * memory errors should fit in this mask:
+ * 000f 0000 1mmm cccc (binary)
+ * where:
+ * f = Correction Report Filtering Bit. If 1, subsequent errors
+ * won't be shown
+ * mmm = error type
+ * cccc = channel
+ * If the mask doesn't match, report an error to the parsing logic
+ */
+ if (! ((errcode & 0xef80) == 0x80)) {
+ optype = "Can't parse: it is not a mem";
+ } else {
+ switch (optypenum) {
+ case 0:
+ optype = "generic undef request";
+ break;
+ case 1:
+ optype = "memory read";
+ break;
+ case 2:
+ optype = "memory write";
+ break;
+ case 3:
+ optype = "addr/cmd";
+ break;
+ case 4:
+ optype = "memory scrubbing";
+ break;
+ default:
+ optype = "reserved";
+ break;
+ }
+ }
+
+ rc = get_memory_error_data(mci, m->addr, &socket,
+ &channel_mask, &rank, area_type);
+ if (rc < 0)
+ return;
+ new_mci = get_mci_for_node_id(socket);
+ if (!new_mci) {
+ edac_mc_handle_ce_no_info(mci, "Error: socket got corrupted!");
+ return;
+ }
+ mci = new_mci;
+ pvt = mci->pvt_info;
+
+ first_channel = find_first_bit(&channel_mask, NUM_CHANNELS);
+
+ if (rank < 4)
+ dimm = 0;
+ else if (rank < 8)
+ dimm = 1;
+ else
+ dimm = 2;
+
+ csrow = pvt->csrow_map[first_channel][dimm];
+
+ if (uncorrected_error && recoverable)
+ recoverable_msg = " recoverable";
+ else
+ recoverable_msg = "";
+
+ /*
+ * FIXME: What should we do with "channel" information on mcelog?
+ * Probably, we can just discard it, as the channel information
+ * comes from the get_memory_error_data() address decoding
+ */
+ msg = kasprintf(GFP_ATOMIC,
+ "%d %s error(s): %s on %s area %s%s: cpu=%d Err=%04x:%04x (ch=%d), "
+ "addr = 0x%08llx => socket=%d, Channel=%ld(mask=%ld), rank=%d\n",
+ core_err_cnt,
+ area_type,
+ optype,
+ type,
+ recoverable_msg,
+ overflow ? "OVERFLOW" : "",
+ m->cpu,
+ mscod, errcode,
+ channel, /* 1111b means not specified */
+ (long long) m->addr,
+ socket,
+ first_channel, /* This is the real channel on SB */
+ channel_mask,
+ rank);
+
+ debugf0("%s", msg);
+
+ /* Call the helper to output message */
+ if (uncorrected_error)
+ edac_mc_handle_fbd_ue(mci, csrow, 0, 0, msg);
+ else
+ edac_mc_handle_fbd_ce(mci, csrow, 0, msg);
+
+ kfree(msg);
+}
+
+/*
+ * sbridge_check_error Retrieve and process errors reported by the
+ * hardware. Called by the Core module.
+ */
+static void sbridge_check_error(struct mem_ctl_info *mci)
+{
+ struct sbridge_pvt *pvt = mci->pvt_info;
+ int i;
+ unsigned count = 0;
+ struct mce *m;
+
+ /*
+ * MCE first step: Copy all mce errors into a temporary buffer
+ * We use a double buffering here, to reduce the risk of
+ * loosing an error.
+ */
+ smp_rmb();
+ count = (pvt->mce_out + MCE_LOG_LEN - pvt->mce_in)
+ % MCE_LOG_LEN;
+ if (!count)
+ return;
+
+ m = pvt->mce_outentry;
+ if (pvt->mce_in + count > MCE_LOG_LEN) {
+ unsigned l = MCE_LOG_LEN - pvt->mce_in;
+
+ memcpy(m, &pvt->mce_entry[pvt->mce_in], sizeof(*m) * l);
+ smp_wmb();
+ pvt->mce_in = 0;
+ count -= l;
+ m += l;
+ }
+ memcpy(m, &pvt->mce_entry[pvt->mce_in], sizeof(*m) * count);
+ smp_wmb();
+ pvt->mce_in += count;
+
+ smp_rmb();
+ if (pvt->mce_overrun) {
+ sbridge_printk(KERN_ERR, "Lost %d memory errors\n",
+ pvt->mce_overrun);
+ smp_wmb();
+ pvt->mce_overrun = 0;
+ }
+
+ /*
+ * MCE second step: parse errors and display
+ */
+ for (i = 0; i < count; i++)
+ sbridge_mce_output_error(mci, &pvt->mce_outentry[i]);
+}
+
+/*
+ * sbridge_mce_check_error Replicates mcelog routine to get errors
+ * This routine simply queues mcelog errors, and
+ * return. The error itself should be handled later
+ * by sbridge_check_error.
+ * WARNING: As this routine should be called at NMI time, extra care should
+ * be taken to avoid deadlocks, and to be as fast as possible.
+ */
+static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct mce *mce = (struct mce *)data;
+ struct mem_ctl_info *mci;
+ struct sbridge_pvt *pvt;
+
+ mci = get_mci_for_node_id(mce->socketid);
+ if (!mci)
+ return NOTIFY_BAD;
+ pvt = mci->pvt_info;
+
+ /*
+ * Just let mcelog handle it if the error is
+ * outside the memory controller. A memory error
+ * is indicated by bit 7 = 1 and bits = 8-11,13-15 = 0.
+ * bit 12 has an special meaning.
+ */
+ if ((mce->status & 0xefff) >> 7 != 1)
+ return NOTIFY_DONE;
+
+ printk("sbridge: HANDLING MCE MEMORY ERROR\n");
+
+ printk("CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
+ mce->extcpu, mce->mcgstatus, mce->bank, mce->status);
+ printk("TSC %llx ", mce->tsc);
+ printk("ADDR %llx ", mce->addr);
+ printk("MISC %llx ", mce->misc);
+
+ printk("PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
+ mce->cpuvendor, mce->cpuid, mce->time,
+ mce->socketid, mce->apicid);
+
+#ifdef CONFIG_SMP
+ /* Only handle if it is the right mc controller */
+ if (cpu_data(mce->cpu).phys_proc_id != pvt->sbridge_dev->mc)
+ return NOTIFY_DONE;
+#endif
+
+ smp_rmb();
+ if ((pvt->mce_out + 1) % MCE_LOG_LEN == pvt->mce_in) {
+ smp_wmb();
+ pvt->mce_overrun++;
+ return NOTIFY_DONE;
+ }
+
+ /* Copy memory error at the ringbuffer */
+ memcpy(&pvt->mce_entry[pvt->mce_out], mce, sizeof(*mce));
+ smp_wmb();
+ pvt->mce_out = (pvt->mce_out + 1) % MCE_LOG_LEN;
+
+ /* Handle fatal errors immediately */
+ if (mce->mcgstatus & 1)
+ sbridge_check_error(mci);
+
+ /* Advice mcelog that the error were handled */
+ return NOTIFY_STOP;
+}
+
+static struct notifier_block sbridge_mce_dec = {
+ .notifier_call = sbridge_mce_check_error,
+};
+
+/****************************************************************************
+ EDAC register/unregister logic
+ ****************************************************************************/
+
+static void sbridge_unregister_mci(struct sbridge_dev *sbridge_dev)
+{
+ struct mem_ctl_info *mci = sbridge_dev->mci;
+ struct sbridge_pvt *pvt;
+
+ if (unlikely(!mci || !mci->pvt_info)) {
+ debugf0("MC: " __FILE__ ": %s(): dev = %p\n",
+ __func__, &sbridge_dev->pdev[0]->dev);
+
+ sbridge_printk(KERN_ERR, "Couldn't find mci handler\n");
+ return;
+ }
+
+ pvt = mci->pvt_info;
+
+ debugf0("MC: " __FILE__ ": %s(): mci = %p, dev = %p\n",
+ __func__, mci, &sbridge_dev->pdev[0]->dev);
+
+ atomic_notifier_chain_unregister(&x86_mce_decoder_chain,
+ &sbridge_mce_dec);
+
+ /* Remove MC sysfs nodes */
+ edac_mc_del_mc(mci->dev);
+
+ debugf1("%s: free mci struct\n", mci->ctl_name);
+ kfree(mci->ctl_name);
+ edac_mc_free(mci);
+ sbridge_dev->mci = NULL;
+}
+
+static int sbridge_register_mci(struct sbridge_dev *sbridge_dev)
+{
+ struct mem_ctl_info *mci;
+ struct sbridge_pvt *pvt;
+ int rc, channels, csrows;
+
+ /* Check the number of active and not disabled channels */
+ rc = sbridge_get_active_channels(sbridge_dev->bus, &channels, &csrows);
+ if (unlikely(rc < 0))
+ return rc;
+
+ /* allocate a new MC control structure */
+ mci = edac_mc_alloc(sizeof(*pvt), csrows, channels, sbridge_dev->mc);
+ if (unlikely(!mci))
+ return -ENOMEM;
+
+ debugf0("MC: " __FILE__ ": %s(): mci = %p, dev = %p\n",
+ __func__, mci, &sbridge_dev->pdev[0]->dev);
+
+ pvt = mci->pvt_info;
+ memset(pvt, 0, sizeof(*pvt));
+
+ /* Associate sbridge_dev and mci for future usage */
+ pvt->sbridge_dev = sbridge_dev;
+ sbridge_dev->mci = mci;
+
+ mci->mtype_cap = MEM_FLAG_DDR3;
+ mci->edac_ctl_cap = EDAC_FLAG_NONE;
+ mci->edac_cap = EDAC_FLAG_NONE;
+ mci->mod_name = "sbridge_edac.c";
+ mci->mod_ver = SBRIDGE_REVISION;
+ mci->ctl_name = kasprintf(GFP_KERNEL, "Sandy Bridge Socket#%d", mci->mc_idx);
+ mci->dev_name = pci_name(sbridge_dev->pdev[0]);
+ mci->ctl_page_to_phys = NULL;
+
+ /* Set the function pointer to an actual operation function */
+ mci->edac_check = sbridge_check_error;
+
+ /* Store pci devices at mci for faster access */
+ rc = mci_bind_devs(mci, sbridge_dev);
+ if (unlikely(rc < 0))
+ goto fail0;
+
+ /* Get dimm basic config and the memory layout */
+ get_dimm_config(mci);
+ get_memory_layout(mci);
+
+ /* record ptr to the generic device */
+ mci->dev = &sbridge_dev->pdev[0]->dev;
+
+ /* add this new MC control structure to EDAC's list of MCs */
+ if (unlikely(edac_mc_add_mc(mci))) {
+ debugf0("MC: " __FILE__
+ ": %s(): failed edac_mc_add_mc()\n", __func__);
+ rc = -EINVAL;
+ goto fail0;
+ }
+
+ atomic_notifier_chain_register(&x86_mce_decoder_chain,
+ &sbridge_mce_dec);
+ return 0;
+
+fail0:
+ kfree(mci->ctl_name);
+ edac_mc_free(mci);
+ sbridge_dev->mci = NULL;
+ return rc;
+}
+
+/*
+ * sbridge_probe Probe for ONE instance of device to see if it is
+ * present.
+ * return:
+ * 0 for FOUND a device
+ * < 0 for error code
+ */
+
+static int __devinit sbridge_probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ int rc;
+ u8 mc, num_mc = 0;
+ struct sbridge_dev *sbridge_dev;
+
+ /* get the pci devices we want to reserve for our use */
+ mutex_lock(&sbridge_edac_lock);
+
+ /*
+ * All memory controllers are allocated at the first pass.
+ */
+ if (unlikely(probed >= 1)) {
+ mutex_unlock(&sbridge_edac_lock);
+ return -ENODEV;
+ }
+ probed++;
+
+ rc = sbridge_get_all_devices(&num_mc);
+ if (unlikely(rc < 0))
+ goto fail0;
+ mc = 0;
+
+ list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) {
+ debugf0("Registering MC#%d (%d of %d)\n", mc, mc + 1, num_mc);
+ sbridge_dev->mc = mc++;
+ rc = sbridge_register_mci(sbridge_dev);
+ if (unlikely(rc < 0))
+ goto fail1;
+ }
+
+ sbridge_printk(KERN_INFO, "Driver loaded.\n");
+
+ mutex_unlock(&sbridge_edac_lock);
+ return 0;
+
+fail1:
+ list_for_each_entry(sbridge_dev, &sbridge_edac_list, list)
+ sbridge_unregister_mci(sbridge_dev);
+
+ sbridge_put_all_devices();
+fail0:
+ mutex_unlock(&sbridge_edac_lock);
+ return rc;
+}
+
+/*
+ * sbridge_remove destructor for one instance of device
+ *
+ */
+static void __devexit sbridge_remove(struct pci_dev *pdev)
+{
+ struct sbridge_dev *sbridge_dev;
+
+ debugf0(__FILE__ ": %s()\n", __func__);
+
+ /*
+ * we have a trouble here: pdev value for removal will be wrong, since
+ * it will point to the X58 register used to detect that the machine
+ * is a Nehalem or upper design. However, due to the way several PCI
+ * devices are grouped together to provide MC functionality, we need
+ * to use a different method for releasing the devices
+ */
+
+ mutex_lock(&sbridge_edac_lock);
+
+ if (unlikely(!probed)) {
+ mutex_unlock(&sbridge_edac_lock);
+ return;
+ }
+
+ list_for_each_entry(sbridge_dev, &sbridge_edac_list, list)
+ sbridge_unregister_mci(sbridge_dev);
+
+ /* Release PCI resources */
+ sbridge_put_all_devices();
+
+ probed--;
+
+ mutex_unlock(&sbridge_edac_lock);
+}
+
+MODULE_DEVICE_TABLE(pci, sbridge_pci_tbl);
+
+/*
+ * sbridge_driver pci_driver structure for this module
+ *
+ */
+static struct pci_driver sbridge_driver = {
+ .name = "sbridge_edac",
+ .probe = sbridge_probe,
+ .remove = __devexit_p(sbridge_remove),
+ .id_table = sbridge_pci_tbl,
+};
+
+/*
+ * sbridge_init Module entry function
+ * Try to initialize this module for its devices
+ */
+static int __init sbridge_init(void)
+{
+ int pci_rc;
+
+ debugf2("MC: " __FILE__ ": %s()\n", __func__);
+
+ /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+ opstate_init();
+
+ pci_rc = pci_register_driver(&sbridge_driver);
+
+ if (pci_rc >= 0)
+ return 0;
+
+ sbridge_printk(KERN_ERR, "Failed to register device with error %d.\n",
+ pci_rc);
+
+ return pci_rc;
+}
+
+/*
+ * sbridge_exit() Module exit function
+ * Unregister the driver
+ */
+static void __exit sbridge_exit(void)
+{
+ debugf2("MC: " __FILE__ ": %s()\n", __func__);
+ pci_unregister_driver(&sbridge_driver);
+}
+
+module_init(sbridge_init);
+module_exit(sbridge_exit);
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@redhat.com>");
+MODULE_AUTHOR("Red Hat Inc. (http://www.redhat.com)");
+MODULE_DESCRIPTION("MC Driver for Intel Sandy Bridge memory controllers - "
+ SBRIDGE_REVISION);
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index cb0bd07..8b3c745 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -189,7 +189,7 @@
config GPIO_VX855
tristate "VIA VX855/VX875 GPIO"
- depends on MFD_SUPPORT && PCI
+ depends on PCI
select MFD_CORE
select MFD_VX855
help
@@ -428,7 +428,6 @@
config GPIO_RDC321X
tristate "RDC R-321x GPIO support"
depends on PCI
- select MFD_SUPPORT
select MFD_CORE
select MFD_RDC321X
help
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 9bc7b03..8cdb4b4 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -458,6 +458,9 @@
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_ISO),
.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN |
APPLE_ISO_KEYBOARD },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO),
+ .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN |
+ APPLE_ISO_KEYBOARD },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_JIS),
.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ANSI),
@@ -508,6 +511,12 @@
.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS),
.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI),
+ .driver_data = APPLE_HAS_FN },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO),
+ .driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS),
+ .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI),
.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO),
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 91adcc5..848a56c 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1362,6 +1362,9 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ANSI) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ISO) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_JIS) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_JIS) },
@@ -1374,6 +1377,7 @@
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ASUS, USB_DEVICE_ID_ASUS_T91MT) },
@@ -1942,6 +1946,9 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ANSI) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_ISO) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5_JIS) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_ANSI) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_ISO) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6_JIS) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 1680e99..06ce996 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -112,6 +112,9 @@
#define USB_DEVICE_ID_APPLE_ALU_REVB_ANSI 0x024f
#define USB_DEVICE_ID_APPLE_ALU_REVB_ISO 0x0250
#define USB_DEVICE_ID_APPLE_ALU_REVB_JIS 0x0251
+#define USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI 0x0252
+#define USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO 0x0253
+#define USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS 0x0254
#define USB_DEVICE_ID_APPLE_WELLSPRING6A_ANSI 0x0249
#define USB_DEVICE_ID_APPLE_WELLSPRING6A_ISO 0x024a
#define USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS 0x024b
@@ -121,6 +124,7 @@
#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI 0x0239
#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO 0x023a
#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS 0x023b
+#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO 0x0256
#define USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY 0x030a
#define USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY 0x030b
#define USB_DEVICE_ID_APPLE_ATV_IRCONTROL 0x8241
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index fa5d7a1..f1c909f 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -291,7 +291,6 @@
td->last_slot_field = usage->hid;
td->last_field_index = field->index;
td->last_mt_collection = usage->collection_index;
- hdev->quirks &= ~HID_QUIRK_MULTITOUCH;
return 1;
case HID_DG_WIDTH:
hid_map_usage(hi, usage, bit, max,
@@ -530,44 +529,12 @@
}
}
-/* a list of devices for which there is a specialized multitouch driver */
-static const struct hid_device_id mt_have_special_driver[] = {
- { HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, 0x0001) },
- { HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, 0x0006) },
- { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA,
- USB_DEVICE_ID_PIXART_IMAGING_INC_OPTICAL_TOUCH_SCREEN) },
- { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA,
- USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH) },
- { }
-};
-
-static bool mt_match_one_id(struct hid_device *hdev,
- const struct hid_device_id *id)
-{
- return id->bus == hdev->bus &&
- (id->vendor == HID_ANY_ID || id->vendor == hdev->vendor) &&
- (id->product == HID_ANY_ID || id->product == hdev->product);
-}
-
-static const struct hid_device_id *mt_match_id(struct hid_device *hdev,
- const struct hid_device_id *id)
-{
- for (; id->bus; id++)
- if (mt_match_one_id(hdev, id))
- return id;
-
- return NULL;
-}
-
static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
{
int ret, i;
struct mt_device *td;
struct mt_class *mtclass = mt_classes; /* MT_CLS_DEFAULT */
- if (mt_match_id(hdev, mt_have_special_driver))
- return -ENODEV;
-
for (i = 0; mt_classes[i].name ; i++) {
if (id->driver_data == mt_classes[i].name) {
mtclass = &(mt_classes[i]);
@@ -575,6 +542,10 @@
}
}
+ /* This allows the driver to correctly support devices
+ * that emit events over several HID messages.
+ */
+ hdev->quirks |= HID_QUIRK_NO_INPUT_SYNC;
td = kzalloc(sizeof(struct mt_device), GFP_KERNEL);
if (!td) {
@@ -590,16 +561,10 @@
if (ret != 0)
goto fail;
- hdev->quirks |= HID_QUIRK_MULTITOUCH;
ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
if (ret)
goto fail;
- /* This allows the driver to correctly support devices
- * that emit events over several HID messages.
- */
- hdev->quirks |= HID_QUIRK_NO_INPUT_SYNC;
-
td->slots = kzalloc(td->maxcontacts * sizeof(struct mt_slot),
GFP_KERNEL);
if (!td->slots) {
@@ -793,10 +758,6 @@
HID_USB_DEVICE(USB_VENDOR_ID_XAT,
USB_DEVICE_ID_XAT_CSR) },
- /* Rest of the world */
- { .driver_data = MT_CLS_DEFAULT,
- HID_USB_DEVICE(HID_ANY_ID, HID_ANY_ID) },
-
{ }
};
MODULE_DEVICE_TABLE(hid, mt_devices);
diff --git a/drivers/hid/hid-roccat.c b/drivers/hid/hid-roccat.c
index 5666e75..56ce12c 100644
--- a/drivers/hid/hid-roccat.c
+++ b/drivers/hid/hid-roccat.c
@@ -162,27 +162,27 @@
device = devices[minor];
- mutex_lock(&device->readers_lock);
-
if (!device) {
pr_emerg("roccat device with minor %d doesn't exist\n", minor);
error = -ENODEV;
- goto exit_err;
+ goto exit_err_devices;
}
+ mutex_lock(&device->readers_lock);
+
if (!device->open++) {
/* power on device on adding first reader */
error = hid_hw_power(device->hid, PM_HINT_FULLON);
if (error < 0) {
--device->open;
- goto exit_err;
+ goto exit_err_readers;
}
error = hid_hw_open(device->hid);
if (error < 0) {
hid_hw_power(device->hid, PM_HINT_NORMAL);
--device->open;
- goto exit_err;
+ goto exit_err_readers;
}
}
@@ -193,13 +193,13 @@
list_add_tail(&reader->node, &device->readers);
file->private_data = reader;
-exit_unlock:
+exit_err_readers:
mutex_unlock(&device->readers_lock);
+exit_err_devices:
mutex_unlock(&devices_lock);
+ if (error)
+ kfree(reader);
return error;
-exit_err:
- kfree(reader);
- goto exit_unlock;
}
static int roccat_release(struct inode *inode, struct file *file)
diff --git a/drivers/hwmon/mc13783-adc.c b/drivers/hwmon/mc13783-adc.c
index d5226c9..ef65ab5 100644
--- a/drivers/hwmon/mc13783-adc.c
+++ b/drivers/hwmon/mc13783-adc.c
@@ -31,7 +31,7 @@
#define MC13783_ADC_NAME "mc13783-adc"
struct mc13783_adc_priv {
- struct mc13783 *mc13783;
+ struct mc13xxx *mc13xxx;
struct device *hwmon_dev;
};
@@ -51,8 +51,8 @@
unsigned int sample[4];
int ret;
- ret = mc13783_adc_do_conversion(priv->mc13783,
- MC13783_ADC_MODE_MULT_CHAN,
+ ret = mc13xxx_adc_do_conversion(priv->mc13xxx,
+ MC13XXX_ADC_MODE_MULT_CHAN,
channel, sample);
if (ret)
return ret;
@@ -147,9 +147,9 @@
static int mc13783_adc_use_touchscreen(struct platform_device *pdev)
{
struct mc13783_adc_priv *priv = platform_get_drvdata(pdev);
- unsigned flags = mc13783_get_flags(priv->mc13783);
+ unsigned flags = mc13xxx_get_flags(priv->mc13xxx);
- return flags & MC13783_USE_TOUCHSCREEN;
+ return flags & MC13XXX_USE_TOUCHSCREEN;
}
static int __init mc13783_adc_probe(struct platform_device *pdev)
@@ -161,7 +161,7 @@
if (!priv)
return -ENOMEM;
- priv->mc13783 = dev_get_drvdata(pdev->dev.parent);
+ priv->mc13xxx = dev_get_drvdata(pdev->dev.parent);
platform_set_drvdata(pdev, priv);
diff --git a/drivers/hwspinlock/Kconfig b/drivers/hwspinlock/Kconfig
index 1f29bab..c7c3128 100644
--- a/drivers/hwspinlock/Kconfig
+++ b/drivers/hwspinlock/Kconfig
@@ -2,22 +2,31 @@
# Generic HWSPINLOCK framework
#
+# HWSPINLOCK always gets selected by whoever wants it.
config HWSPINLOCK
- tristate "Generic Hardware Spinlock framework"
- depends on ARCH_OMAP4
- help
- Say y here to support the generic hardware spinlock framework.
- You only need to enable this if you have hardware spinlock module
- on your system (usually only relevant if your system has remote slave
- coprocessors).
+ tristate
- If unsure, say N.
+menu "Hardware Spinlock drivers"
config HWSPINLOCK_OMAP
tristate "OMAP Hardware Spinlock device"
- depends on HWSPINLOCK && ARCH_OMAP4
+ depends on ARCH_OMAP4
+ select HWSPINLOCK
help
Say y here to support the OMAP Hardware Spinlock device (firstly
introduced in OMAP4).
If unsure, say N.
+
+config HSEM_U8500
+ tristate "STE Hardware Semaphore functionality"
+ depends on ARCH_U8500
+ select HWSPINLOCK
+ help
+ Say y here to support the STE Hardware Semaphore functionality, which
+ provides a synchronisation mechanism for the various processor on the
+ SoC.
+
+ If unsure, say N.
+
+endmenu
diff --git a/drivers/hwspinlock/Makefile b/drivers/hwspinlock/Makefile
index 5729a3f..93eb64b 100644
--- a/drivers/hwspinlock/Makefile
+++ b/drivers/hwspinlock/Makefile
@@ -4,3 +4,4 @@
obj-$(CONFIG_HWSPINLOCK) += hwspinlock_core.o
obj-$(CONFIG_HWSPINLOCK_OMAP) += omap_hwspinlock.o
+obj-$(CONFIG_HSEM_U8500) += u8500_hsem.o
diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c
index 43a6271..61c9cf1 100644
--- a/drivers/hwspinlock/hwspinlock_core.c
+++ b/drivers/hwspinlock/hwspinlock_core.c
@@ -26,6 +26,7 @@
#include <linux/radix-tree.h>
#include <linux/hwspinlock.h>
#include <linux/pm_runtime.h>
+#include <linux/mutex.h>
#include "hwspinlock_internal.h"
@@ -52,10 +53,12 @@
static RADIX_TREE(hwspinlock_tree, GFP_KERNEL);
/*
- * Synchronization of access to the tree is achieved using this spinlock,
+ * Synchronization of access to the tree is achieved using this mutex,
* as the radix-tree API requires that users provide all synchronisation.
+ * A mutex is needed because we're using non-atomic radix tree allocations.
*/
-static DEFINE_SPINLOCK(hwspinlock_tree_lock);
+static DEFINE_MUTEX(hwspinlock_tree_lock);
+
/**
* __hwspin_trylock() - attempt to lock a specific hwspinlock
@@ -114,7 +117,7 @@
return -EBUSY;
/* try to take the hwspinlock device */
- ret = hwlock->ops->trylock(hwlock);
+ ret = hwlock->bank->ops->trylock(hwlock);
/* if hwlock is already taken, undo spin_trylock_* and exit */
if (!ret) {
@@ -196,8 +199,8 @@
* Allow platform-specific relax handlers to prevent
* hogging the interconnect (no sleeping, though)
*/
- if (hwlock->ops->relax)
- hwlock->ops->relax(hwlock);
+ if (hwlock->bank->ops->relax)
+ hwlock->bank->ops->relax(hwlock);
}
return ret;
@@ -242,7 +245,7 @@
*/
mb();
- hwlock->ops->unlock(hwlock);
+ hwlock->bank->ops->unlock(hwlock);
/* Undo the spin_trylock{_irq, _irqsave} called while locking */
if (mode == HWLOCK_IRQSTATE)
@@ -254,68 +257,37 @@
}
EXPORT_SYMBOL_GPL(__hwspin_unlock);
-/**
- * hwspin_lock_register() - register a new hw spinlock
- * @hwlock: hwspinlock to register.
- *
- * This function should be called from the underlying platform-specific
- * implementation, to register a new hwspinlock instance.
- *
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context.
- *
- * Returns 0 on success, or an appropriate error code on failure
- */
-int hwspin_lock_register(struct hwspinlock *hwlock)
+static int hwspin_lock_register_single(struct hwspinlock *hwlock, int id)
{
struct hwspinlock *tmp;
int ret;
- if (!hwlock || !hwlock->ops ||
- !hwlock->ops->trylock || !hwlock->ops->unlock) {
- pr_err("invalid parameters\n");
- return -EINVAL;
+ mutex_lock(&hwspinlock_tree_lock);
+
+ ret = radix_tree_insert(&hwspinlock_tree, id, hwlock);
+ if (ret) {
+ if (ret == -EEXIST)
+ pr_err("hwspinlock id %d already exists!\n", id);
+ goto out;
}
- spin_lock_init(&hwlock->lock);
-
- spin_lock(&hwspinlock_tree_lock);
-
- ret = radix_tree_insert(&hwspinlock_tree, hwlock->id, hwlock);
- if (ret)
- goto out;
-
/* mark this hwspinlock as available */
- tmp = radix_tree_tag_set(&hwspinlock_tree, hwlock->id,
- HWSPINLOCK_UNUSED);
+ tmp = radix_tree_tag_set(&hwspinlock_tree, id, HWSPINLOCK_UNUSED);
/* self-sanity check which should never fail */
WARN_ON(tmp != hwlock);
out:
- spin_unlock(&hwspinlock_tree_lock);
- return ret;
+ mutex_unlock(&hwspinlock_tree_lock);
+ return 0;
}
-EXPORT_SYMBOL_GPL(hwspin_lock_register);
-/**
- * hwspin_lock_unregister() - unregister an hw spinlock
- * @id: index of the specific hwspinlock to unregister
- *
- * This function should be called from the underlying platform-specific
- * implementation, to unregister an existing (and unused) hwspinlock.
- *
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context.
- *
- * Returns the address of hwspinlock @id on success, or NULL on failure
- */
-struct hwspinlock *hwspin_lock_unregister(unsigned int id)
+static struct hwspinlock *hwspin_lock_unregister_single(unsigned int id)
{
struct hwspinlock *hwlock = NULL;
int ret;
- spin_lock(&hwspinlock_tree_lock);
+ mutex_lock(&hwspinlock_tree_lock);
/* make sure the hwspinlock is not in use (tag is set) */
ret = radix_tree_tag_get(&hwspinlock_tree, id, HWSPINLOCK_UNUSED);
@@ -331,9 +303,91 @@
}
out:
- spin_unlock(&hwspinlock_tree_lock);
+ mutex_unlock(&hwspinlock_tree_lock);
return hwlock;
}
+
+/**
+ * hwspin_lock_register() - register a new hw spinlock device
+ * @bank: the hwspinlock device, which usually provides numerous hw locks
+ * @dev: the backing device
+ * @ops: hwspinlock handlers for this device
+ * @base_id: id of the first hardware spinlock in this bank
+ * @num_locks: number of hwspinlocks provided by this device
+ *
+ * This function should be called from the underlying platform-specific
+ * implementation, to register a new hwspinlock device instance.
+ *
+ * Should be called from a process context (might sleep)
+ *
+ * Returns 0 on success, or an appropriate error code on failure
+ */
+int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev,
+ const struct hwspinlock_ops *ops, int base_id, int num_locks)
+{
+ struct hwspinlock *hwlock;
+ int ret = 0, i;
+
+ if (!bank || !ops || !dev || !num_locks || !ops->trylock ||
+ !ops->unlock) {
+ pr_err("invalid parameters\n");
+ return -EINVAL;
+ }
+
+ bank->dev = dev;
+ bank->ops = ops;
+ bank->base_id = base_id;
+ bank->num_locks = num_locks;
+
+ for (i = 0; i < num_locks; i++) {
+ hwlock = &bank->lock[i];
+
+ spin_lock_init(&hwlock->lock);
+ hwlock->bank = bank;
+
+ ret = hwspin_lock_register_single(hwlock, i);
+ if (ret)
+ goto reg_failed;
+ }
+
+ return 0;
+
+reg_failed:
+ while (--i >= 0)
+ hwspin_lock_unregister_single(i);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(hwspin_lock_register);
+
+/**
+ * hwspin_lock_unregister() - unregister an hw spinlock device
+ * @bank: the hwspinlock device, which usually provides numerous hw locks
+ *
+ * This function should be called from the underlying platform-specific
+ * implementation, to unregister an existing (and unused) hwspinlock.
+ *
+ * Should be called from a process context (might sleep)
+ *
+ * Returns 0 on success, or an appropriate error code on failure
+ */
+int hwspin_lock_unregister(struct hwspinlock_device *bank)
+{
+ struct hwspinlock *hwlock, *tmp;
+ int i;
+
+ for (i = 0; i < bank->num_locks; i++) {
+ hwlock = &bank->lock[i];
+
+ tmp = hwspin_lock_unregister_single(bank->base_id + i);
+ if (!tmp)
+ return -EBUSY;
+
+ /* self-sanity check that should never fail */
+ WARN_ON(tmp != hwlock);
+ }
+
+ return 0;
+}
EXPORT_SYMBOL_GPL(hwspin_lock_unregister);
/**
@@ -348,24 +402,25 @@
*/
static int __hwspin_lock_request(struct hwspinlock *hwlock)
{
+ struct device *dev = hwlock->bank->dev;
struct hwspinlock *tmp;
int ret;
/* prevent underlying implementation from being removed */
- if (!try_module_get(hwlock->owner)) {
- dev_err(hwlock->dev, "%s: can't get owner\n", __func__);
+ if (!try_module_get(dev->driver->owner)) {
+ dev_err(dev, "%s: can't get owner\n", __func__);
return -EINVAL;
}
/* notify PM core that power is now needed */
- ret = pm_runtime_get_sync(hwlock->dev);
+ ret = pm_runtime_get_sync(dev);
if (ret < 0) {
- dev_err(hwlock->dev, "%s: can't power on device\n", __func__);
+ dev_err(dev, "%s: can't power on device\n", __func__);
return ret;
}
/* mark hwspinlock as used, should not fail */
- tmp = radix_tree_tag_clear(&hwspinlock_tree, hwlock->id,
+ tmp = radix_tree_tag_clear(&hwspinlock_tree, hwlock_to_id(hwlock),
HWSPINLOCK_UNUSED);
/* self-sanity check that should never fail */
@@ -387,7 +442,7 @@
return -EINVAL;
}
- return hwlock->id;
+ return hwlock_to_id(hwlock);
}
EXPORT_SYMBOL_GPL(hwspin_lock_get_id);
@@ -400,9 +455,7 @@
* to the remote core before it can be used for synchronization (to get the
* id of a given hwlock, use hwspin_lock_get_id()).
*
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context (simply because there is no use case for
- * that yet).
+ * Should be called from a process context (might sleep)
*
* Returns the address of the assigned hwspinlock, or NULL on error
*/
@@ -411,7 +464,7 @@
struct hwspinlock *hwlock;
int ret;
- spin_lock(&hwspinlock_tree_lock);
+ mutex_lock(&hwspinlock_tree_lock);
/* look for an unused lock */
ret = radix_tree_gang_lookup_tag(&hwspinlock_tree, (void **)&hwlock,
@@ -431,7 +484,7 @@
hwlock = NULL;
out:
- spin_unlock(&hwspinlock_tree_lock);
+ mutex_unlock(&hwspinlock_tree_lock);
return hwlock;
}
EXPORT_SYMBOL_GPL(hwspin_lock_request);
@@ -445,9 +498,7 @@
* Usually early board code will be calling this function in order to
* reserve specific hwspinlock ids for predefined purposes.
*
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context (simply because there is no use case for
- * that yet).
+ * Should be called from a process context (might sleep)
*
* Returns the address of the assigned hwspinlock, or NULL on error
*/
@@ -456,7 +507,7 @@
struct hwspinlock *hwlock;
int ret;
- spin_lock(&hwspinlock_tree_lock);
+ mutex_lock(&hwspinlock_tree_lock);
/* make sure this hwspinlock exists */
hwlock = radix_tree_lookup(&hwspinlock_tree, id);
@@ -466,7 +517,7 @@
}
/* sanity check (this shouldn't happen) */
- WARN_ON(hwlock->id != id);
+ WARN_ON(hwlock_to_id(hwlock) != id);
/* make sure this hwspinlock is unused */
ret = radix_tree_tag_get(&hwspinlock_tree, id, HWSPINLOCK_UNUSED);
@@ -482,7 +533,7 @@
hwlock = NULL;
out:
- spin_unlock(&hwspinlock_tree_lock);
+ mutex_unlock(&hwspinlock_tree_lock);
return hwlock;
}
EXPORT_SYMBOL_GPL(hwspin_lock_request_specific);
@@ -495,14 +546,13 @@
* Should only be called with an @hwlock that was retrieved from
* an earlier call to omap_hwspin_lock_request{_specific}.
*
- * Can be called from an atomic context (will not sleep) but not from
- * within interrupt context (simply because there is no use case for
- * that yet).
+ * Should be called from a process context (might sleep)
*
* Returns 0 on success, or an appropriate error code on failure
*/
int hwspin_lock_free(struct hwspinlock *hwlock)
{
+ struct device *dev = hwlock->bank->dev;
struct hwspinlock *tmp;
int ret;
@@ -511,34 +561,34 @@
return -EINVAL;
}
- spin_lock(&hwspinlock_tree_lock);
+ mutex_lock(&hwspinlock_tree_lock);
/* make sure the hwspinlock is used */
- ret = radix_tree_tag_get(&hwspinlock_tree, hwlock->id,
+ ret = radix_tree_tag_get(&hwspinlock_tree, hwlock_to_id(hwlock),
HWSPINLOCK_UNUSED);
if (ret == 1) {
- dev_err(hwlock->dev, "%s: hwlock is already free\n", __func__);
+ dev_err(dev, "%s: hwlock is already free\n", __func__);
dump_stack();
ret = -EINVAL;
goto out;
}
/* notify the underlying device that power is not needed */
- ret = pm_runtime_put(hwlock->dev);
+ ret = pm_runtime_put(dev);
if (ret < 0)
goto out;
/* mark this hwspinlock as available */
- tmp = radix_tree_tag_set(&hwspinlock_tree, hwlock->id,
+ tmp = radix_tree_tag_set(&hwspinlock_tree, hwlock_to_id(hwlock),
HWSPINLOCK_UNUSED);
/* sanity check (this shouldn't happen) */
WARN_ON(tmp != hwlock);
- module_put(hwlock->owner);
+ module_put(dev->driver->owner);
out:
- spin_unlock(&hwspinlock_tree_lock);
+ mutex_unlock(&hwspinlock_tree_lock);
return ret;
}
EXPORT_SYMBOL_GPL(hwspin_lock_free);
diff --git a/drivers/hwspinlock/hwspinlock_internal.h b/drivers/hwspinlock/hwspinlock_internal.h
index 69935e6..d26f78b 100644
--- a/drivers/hwspinlock/hwspinlock_internal.h
+++ b/drivers/hwspinlock/hwspinlock_internal.h
@@ -21,6 +21,8 @@
#include <linux/spinlock.h>
#include <linux/device.h>
+struct hwspinlock_device;
+
/**
* struct hwspinlock_ops - platform-specific hwspinlock handlers
*
@@ -39,23 +41,37 @@
/**
* struct hwspinlock - this struct represents a single hwspinlock instance
- *
- * @dev: underlying device, will be used to invoke runtime PM api
- * @ops: platform-specific hwspinlock handlers
- * @id: a global, unique, system-wide, index of the lock.
+ * @bank: the hwspinlock_device structure which owns this lock
* @lock: initialized and used by hwspinlock core
- * @owner: underlying implementation module, used to maintain module ref count
- *
- * Note: currently simplicity was opted for, but later we can squeeze some
- * memory bytes by grouping the dev, ops and owner members in a single
- * per-platform struct, and have all hwspinlocks point at it.
+ * @priv: private data, owned by the underlying platform-specific hwspinlock drv
*/
struct hwspinlock {
+ struct hwspinlock_device *bank;
+ spinlock_t lock;
+ void *priv;
+};
+
+/**
+ * struct hwspinlock_device - a device which usually spans numerous hwspinlocks
+ * @dev: underlying device, will be used to invoke runtime PM api
+ * @ops: platform-specific hwspinlock handlers
+ * @base_id: id index of the first lock in this device
+ * @num_locks: number of locks in this device
+ * @lock: dynamically allocated array of 'struct hwspinlock'
+ */
+struct hwspinlock_device {
struct device *dev;
const struct hwspinlock_ops *ops;
- int id;
- spinlock_t lock;
- struct module *owner;
+ int base_id;
+ int num_locks;
+ struct hwspinlock lock[0];
};
+static inline int hwlock_to_id(struct hwspinlock *hwlock)
+{
+ int local_id = hwlock - &hwlock->bank->lock[0];
+
+ return hwlock->bank->base_id + local_id;
+}
+
#endif /* __HWSPINLOCK_HWSPINLOCK_H */
diff --git a/drivers/hwspinlock/omap_hwspinlock.c b/drivers/hwspinlock/omap_hwspinlock.c
index a8f0273..887d34e 100644
--- a/drivers/hwspinlock/omap_hwspinlock.c
+++ b/drivers/hwspinlock/omap_hwspinlock.c
@@ -41,33 +41,20 @@
#define SPINLOCK_NOTTAKEN (0) /* free */
#define SPINLOCK_TAKEN (1) /* locked */
-#define to_omap_hwspinlock(lock) \
- container_of(lock, struct omap_hwspinlock, lock)
-
-struct omap_hwspinlock {
- struct hwspinlock lock;
- void __iomem *addr;
-};
-
-struct omap_hwspinlock_state {
- int num_locks; /* Total number of locks in system */
- void __iomem *io_base; /* Mapped base address */
-};
-
static int omap_hwspinlock_trylock(struct hwspinlock *lock)
{
- struct omap_hwspinlock *omap_lock = to_omap_hwspinlock(lock);
+ void __iomem *lock_addr = lock->priv;
/* attempt to acquire the lock by reading its value */
- return (SPINLOCK_NOTTAKEN == readl(omap_lock->addr));
+ return (SPINLOCK_NOTTAKEN == readl(lock_addr));
}
static void omap_hwspinlock_unlock(struct hwspinlock *lock)
{
- struct omap_hwspinlock *omap_lock = to_omap_hwspinlock(lock);
+ void __iomem *lock_addr = lock->priv;
/* release the lock by writing 0 to it */
- writel(SPINLOCK_NOTTAKEN, omap_lock->addr);
+ writel(SPINLOCK_NOTTAKEN, lock_addr);
}
/*
@@ -93,26 +80,23 @@
static int __devinit omap_hwspinlock_probe(struct platform_device *pdev)
{
- struct omap_hwspinlock *omap_lock;
- struct omap_hwspinlock_state *state;
- struct hwspinlock *lock;
+ struct hwspinlock_pdata *pdata = pdev->dev.platform_data;
+ struct hwspinlock_device *bank;
+ struct hwspinlock *hwlock;
struct resource *res;
void __iomem *io_base;
- int i, ret;
+ int num_locks, i, ret;
+
+ if (!pdata)
+ return -ENODEV;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!res)
return -ENODEV;
- state = kzalloc(sizeof(*state), GFP_KERNEL);
- if (!state)
- return -ENOMEM;
-
io_base = ioremap(res->start, resource_size(res));
- if (!io_base) {
- ret = -ENOMEM;
- goto free_state;
- }
+ if (!io_base)
+ return -ENOMEM;
/* Determine number of locks */
i = readl(io_base + SYSSTATUS_OFFSET);
@@ -124,10 +108,18 @@
goto iounmap_base;
}
- state->num_locks = i * 32;
- state->io_base = io_base;
+ num_locks = i * 32; /* actual number of locks in this device */
- platform_set_drvdata(pdev, state);
+ bank = kzalloc(sizeof(*bank) + num_locks * sizeof(*hwlock), GFP_KERNEL);
+ if (!bank) {
+ ret = -ENOMEM;
+ goto iounmap_base;
+ }
+
+ platform_set_drvdata(pdev, bank);
+
+ for (i = 0, hwlock = &bank->lock[0]; i < num_locks; i++, hwlock++)
+ hwlock->priv = io_base + LOCK_BASE_OFFSET + sizeof(u32) * i;
/*
* runtime PM will make sure the clock of this module is
@@ -135,79 +127,46 @@
*/
pm_runtime_enable(&pdev->dev);
- for (i = 0; i < state->num_locks; i++) {
- omap_lock = kzalloc(sizeof(*omap_lock), GFP_KERNEL);
- if (!omap_lock) {
- ret = -ENOMEM;
- goto free_locks;
- }
-
- omap_lock->lock.dev = &pdev->dev;
- omap_lock->lock.owner = THIS_MODULE;
- omap_lock->lock.id = i;
- omap_lock->lock.ops = &omap_hwspinlock_ops;
- omap_lock->addr = io_base + LOCK_BASE_OFFSET + sizeof(u32) * i;
-
- ret = hwspin_lock_register(&omap_lock->lock);
- if (ret) {
- kfree(omap_lock);
- goto free_locks;
- }
- }
+ ret = hwspin_lock_register(bank, &pdev->dev, &omap_hwspinlock_ops,
+ pdata->base_id, num_locks);
+ if (ret)
+ goto reg_fail;
return 0;
-free_locks:
- while (--i >= 0) {
- lock = hwspin_lock_unregister(i);
- /* this should't happen, but let's give our best effort */
- if (!lock) {
- dev_err(&pdev->dev, "%s: cleanups failed\n", __func__);
- continue;
- }
- omap_lock = to_omap_hwspinlock(lock);
- kfree(omap_lock);
- }
+reg_fail:
pm_runtime_disable(&pdev->dev);
+ kfree(bank);
iounmap_base:
iounmap(io_base);
-free_state:
- kfree(state);
return ret;
}
-static int omap_hwspinlock_remove(struct platform_device *pdev)
+static int __devexit omap_hwspinlock_remove(struct platform_device *pdev)
{
- struct omap_hwspinlock_state *state = platform_get_drvdata(pdev);
- struct hwspinlock *lock;
- struct omap_hwspinlock *omap_lock;
- int i;
+ struct hwspinlock_device *bank = platform_get_drvdata(pdev);
+ void __iomem *io_base = bank->lock[0].priv - LOCK_BASE_OFFSET;
+ int ret;
- for (i = 0; i < state->num_locks; i++) {
- lock = hwspin_lock_unregister(i);
- /* this shouldn't happen at this point. if it does, at least
- * don't continue with the remove */
- if (!lock) {
- dev_err(&pdev->dev, "%s: failed on %d\n", __func__, i);
- return -EBUSY;
- }
-
- omap_lock = to_omap_hwspinlock(lock);
- kfree(omap_lock);
+ ret = hwspin_lock_unregister(bank);
+ if (ret) {
+ dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret);
+ return ret;
}
pm_runtime_disable(&pdev->dev);
- iounmap(state->io_base);
- kfree(state);
+ iounmap(io_base);
+ kfree(bank);
return 0;
}
static struct platform_driver omap_hwspinlock_driver = {
.probe = omap_hwspinlock_probe,
- .remove = omap_hwspinlock_remove,
+ .remove = __devexit_p(omap_hwspinlock_remove),
.driver = {
.name = "omap_hwspinlock",
+ .owner = THIS_MODULE,
},
};
diff --git a/drivers/hwspinlock/u8500_hsem.c b/drivers/hwspinlock/u8500_hsem.c
new file mode 100644
index 0000000..143461a
--- /dev/null
+++ b/drivers/hwspinlock/u8500_hsem.c
@@ -0,0 +1,198 @@
+/*
+ * u8500 HWSEM driver
+ *
+ * Copyright (C) 2010-2011 ST-Ericsson
+ *
+ * Implements u8500 semaphore handling for protocol 1, no interrupts.
+ *
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ * Heavily borrowed from the work of :
+ * Simon Que <sque@ti.com>
+ * Hari Kanigeri <h-kanigeri2@ti.com>
+ * Ohad Ben-Cohen <ohad@wizery.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/hwspinlock.h>
+#include <linux/platform_device.h>
+
+#include "hwspinlock_internal.h"
+
+/*
+ * Implementation of STE's HSem protocol 1 without interrutps.
+ * The only masterID we allow is '0x01' to force people to use
+ * HSems for synchronisation between processors rather than processes
+ * on the ARM core.
+ */
+
+#define U8500_MAX_SEMAPHORE 32 /* a total of 32 semaphore */
+#define RESET_SEMAPHORE (0) /* free */
+
+/*
+ * CPU ID for master running u8500 kernel.
+ * Hswpinlocks should only be used to synchonise operations
+ * between the Cortex A9 core and the other CPUs. Hence
+ * forcing the masterID to a preset value.
+ */
+#define HSEM_MASTER_ID 0x01
+
+#define HSEM_REGISTER_OFFSET 0x08
+
+#define HSEM_CTRL_REG 0x00
+#define HSEM_ICRALL 0x90
+#define HSEM_PROTOCOL_1 0x01
+
+static int u8500_hsem_trylock(struct hwspinlock *lock)
+{
+ void __iomem *lock_addr = lock->priv;
+
+ writel(HSEM_MASTER_ID, lock_addr);
+
+ /* get only first 4 bit and compare to masterID.
+ * if equal, we have the semaphore, otherwise
+ * someone else has it.
+ */
+ return (HSEM_MASTER_ID == (0x0F & readl(lock_addr)));
+}
+
+static void u8500_hsem_unlock(struct hwspinlock *lock)
+{
+ void __iomem *lock_addr = lock->priv;
+
+ /* release the lock by writing 0 to it */
+ writel(RESET_SEMAPHORE, lock_addr);
+}
+
+/*
+ * u8500: what value is recommended here ?
+ */
+static void u8500_hsem_relax(struct hwspinlock *lock)
+{
+ ndelay(50);
+}
+
+static const struct hwspinlock_ops u8500_hwspinlock_ops = {
+ .trylock = u8500_hsem_trylock,
+ .unlock = u8500_hsem_unlock,
+ .relax = u8500_hsem_relax,
+};
+
+static int __devinit u8500_hsem_probe(struct platform_device *pdev)
+{
+ struct hwspinlock_pdata *pdata = pdev->dev.platform_data;
+ struct hwspinlock_device *bank;
+ struct hwspinlock *hwlock;
+ struct resource *res;
+ void __iomem *io_base;
+ int i, ret, num_locks = U8500_MAX_SEMAPHORE;
+ ulong val;
+
+ if (!pdata)
+ return -ENODEV;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENODEV;
+
+ io_base = ioremap(res->start, resource_size(res));
+ if (!io_base) {
+ ret = -ENOMEM;
+ goto free_state;
+ }
+
+ /* make sure protocol 1 is selected */
+ val = readl(io_base + HSEM_CTRL_REG);
+ writel((val & ~HSEM_PROTOCOL_1), io_base + HSEM_CTRL_REG);
+
+ /* clear all interrupts */
+ writel(0xFFFF, io_base + HSEM_ICRALL);
+
+ bank = kzalloc(sizeof(*bank) + num_locks * sizeof(*hwlock), GFP_KERNEL);
+ if (!bank) {
+ ret = -ENOMEM;
+ goto iounmap_base;
+ }
+
+ platform_set_drvdata(pdev, bank);
+
+ for (i = 0, hwlock = &bank->lock[0]; i < num_locks; i++, hwlock++)
+ hwlock->priv = io_base + HSEM_REGISTER_OFFSET + sizeof(u32) * i;
+
+ /* no pm needed for HSem but required to comply with hwspilock core */
+ pm_runtime_enable(&pdev->dev);
+
+ ret = hwspin_lock_register(bank, &pdev->dev, &u8500_hwspinlock_ops,
+ pdata->base_id, num_locks);
+ if (ret)
+ goto reg_fail;
+
+ return 0;
+
+reg_fail:
+ pm_runtime_disable(&pdev->dev);
+ kfree(bank);
+iounmap_base:
+ iounmap(io_base);
+ return ret;
+}
+
+static int __devexit u8500_hsem_remove(struct platform_device *pdev)
+{
+ struct hwspinlock_device *bank = platform_get_drvdata(pdev);
+ void __iomem *io_base = bank->lock[0].priv - HSEM_REGISTER_OFFSET;
+ int ret;
+
+ /* clear all interrupts */
+ writel(0xFFFF, io_base + HSEM_ICRALL);
+
+ ret = hwspin_lock_unregister(bank);
+ if (ret) {
+ dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret);
+ return ret;
+ }
+
+ pm_runtime_disable(&pdev->dev);
+ iounmap(io_base);
+ kfree(bank);
+
+ return 0;
+}
+
+static struct platform_driver u8500_hsem_driver = {
+ .probe = u8500_hsem_probe,
+ .remove = __devexit_p(u8500_hsem_remove),
+ .driver = {
+ .name = "u8500_hsem",
+ .owner = THIS_MODULE,
+ },
+};
+
+static int __init u8500_hsem_init(void)
+{
+ return platform_driver_register(&u8500_hsem_driver);
+}
+/* board init code might need to reserve hwspinlocks for predefined purposes */
+postcore_initcall(u8500_hsem_init);
+
+static void __exit u8500_hsem_exit(void)
+{
+ platform_driver_unregister(&u8500_hsem_driver);
+}
+module_exit(u8500_hsem_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Hardware Spinlock driver for u8500");
+MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>");
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index b2b8562..a3afac4 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -110,7 +110,6 @@
config I2C_ISCH
tristate "Intel SCH SMBus 1.0"
depends on PCI
- select MFD_CORE
select LPC_SCH
help
Say Y here if you want to use SMBus controller on the Intel SCH
@@ -301,7 +300,7 @@
config I2C_AU1550
tristate "Au1550/Au1200 SMBus interface"
- depends on SOC_AU1550 || SOC_AU1200
+ depends on MIPS_ALCHEMY
help
If you say yes to this option, support will be included for the
Au1550 and Au1200 SMBus interface.
diff --git a/drivers/i2c/busses/i2c-au1550.c b/drivers/i2c/busses/i2c-au1550.c
index 4f757a2..f314d7f 100644
--- a/drivers/i2c/busses/i2c-au1550.c
+++ b/drivers/i2c/busses/i2c-au1550.c
@@ -36,7 +36,7 @@
#include <linux/i2c.h>
#include <linux/slab.h>
-#include <asm/mach-au1x00/au1xxx.h>
+#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1xxx_psc.h>
#define PSC_SEL 0x00
diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig
index 76b6d98..5a26584 100644
--- a/drivers/ide/Kconfig
+++ b/drivers/ide/Kconfig
@@ -677,19 +677,19 @@
config BLK_DEV_IDE_AU1XXX
bool "IDE for AMD Alchemy Au1200"
- depends on SOC_AU1200
+ depends on MIPS_ALCHEMY
select IDE_XFER_MODE
choice
prompt "IDE Mode for AMD Alchemy Au1200"
default BLK_DEV_IDE_AU1XXX_PIO_DBDMA
- depends on SOC_AU1200 && BLK_DEV_IDE_AU1XXX
+ depends on BLK_DEV_IDE_AU1XXX
config BLK_DEV_IDE_AU1XXX_PIO_DBDMA
bool "PIO+DbDMA IDE for AMD Alchemy Au1200"
config BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA
bool "MDMA2+DbDMA IDE for AMD Alchemy Au1200"
- depends on SOC_AU1200 && BLK_DEV_IDE_AU1XXX
+ depends on BLK_DEV_IDE_AU1XXX
endchoice
config BLK_DEV_IDE_TX4938
diff --git a/drivers/ide/au1xxx-ide.c b/drivers/ide/au1xxx-ide.c
index b26c234..259786c 100644
--- a/drivers/ide/au1xxx-ide.c
+++ b/drivers/ide/au1xxx-ide.c
@@ -36,13 +36,17 @@
#include <linux/ide.h>
#include <linux/scatterlist.h>
-#include <asm/mach-au1x00/au1xxx.h>
+#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1xxx_dbdma.h>
#include <asm/mach-au1x00/au1xxx_ide.h>
#define DRV_NAME "au1200-ide"
#define DRV_AUTHOR "Enrico Walther <enrico.walther@amd.com> / Pete Popov <ppopov@embeddedalley.com>"
+#ifndef IDE_REG_SHIFT
+#define IDE_REG_SHIFT 5
+#endif
+
/* enable the burstmode in the dbdma */
#define IDE_AU1XXX_BURSTMODE 1
@@ -317,10 +321,11 @@
}
#endif /* end CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA */
-static void auide_init_dbdma_dev(dbdev_tab_t *dev, u32 dev_id, u32 tsize, u32 devwidth, u32 flags)
+static void auide_init_dbdma_dev(dbdev_tab_t *dev, u32 dev_id, u32 tsize,
+ u32 devwidth, u32 flags, u32 regbase)
{
dev->dev_id = dev_id;
- dev->dev_physaddr = (u32)IDE_PHYS_ADDR;
+ dev->dev_physaddr = CPHYSADDR(regbase);
dev->dev_intlevel = 0;
dev->dev_intpolarity = 0;
dev->dev_tsize = tsize;
@@ -344,7 +349,7 @@
dbdev_tab_t source_dev_tab, target_dev_tab;
u32 dev_id, tsize, devwidth, flags;
- dev_id = IDE_DDMA_REQ;
+ dev_id = hwif->ddma_id;
tsize = 8; /* 1 */
devwidth = 32; /* 16 */
@@ -356,20 +361,17 @@
#endif
/* setup dev_tab for tx channel */
- auide_init_dbdma_dev( &source_dev_tab,
- dev_id,
- tsize, devwidth, DEV_FLAGS_OUT | flags);
+ auide_init_dbdma_dev(&source_dev_tab, dev_id, tsize, devwidth,
+ DEV_FLAGS_OUT | flags, auide->regbase);
auide->tx_dev_id = au1xxx_ddma_add_device( &source_dev_tab );
- auide_init_dbdma_dev( &source_dev_tab,
- dev_id,
- tsize, devwidth, DEV_FLAGS_IN | flags);
+ auide_init_dbdma_dev(&source_dev_tab, dev_id, tsize, devwidth,
+ DEV_FLAGS_IN | flags, auide->regbase);
auide->rx_dev_id = au1xxx_ddma_add_device( &source_dev_tab );
/* We also need to add a target device for the DMA */
- auide_init_dbdma_dev( &target_dev_tab,
- (u32)DSCR_CMD0_ALWAYS,
- tsize, devwidth, DEV_FLAGS_ANYUSE);
+ auide_init_dbdma_dev(&target_dev_tab, (u32)DSCR_CMD0_ALWAYS, tsize,
+ devwidth, DEV_FLAGS_ANYUSE, auide->regbase);
auide->target_dev_id = au1xxx_ddma_add_device(&target_dev_tab);
/* Get a channel for TX */
@@ -411,14 +413,12 @@
#endif
/* setup dev_tab for tx channel */
- auide_init_dbdma_dev( &source_dev_tab,
- (u32)DSCR_CMD0_ALWAYS,
- 8, 32, DEV_FLAGS_OUT | flags);
+ auide_init_dbdma_dev(&source_dev_tab, (u32)DSCR_CMD0_ALWAYS, 8, 32,
+ DEV_FLAGS_OUT | flags, auide->regbase);
auide->tx_dev_id = au1xxx_ddma_add_device( &source_dev_tab );
- auide_init_dbdma_dev( &source_dev_tab,
- (u32)DSCR_CMD0_ALWAYS,
- 8, 32, DEV_FLAGS_IN | flags);
+ auide_init_dbdma_dev(&source_dev_tab, (u32)DSCR_CMD0_ALWAYS, 8, 32,
+ DEV_FLAGS_IN | flags, auide->regbase);
auide->rx_dev_id = au1xxx_ddma_add_device( &source_dev_tab );
/* Get a channel for TX */
@@ -540,6 +540,14 @@
goto out;
}
+ res = platform_get_resource(dev, IORESOURCE_DMA, 0);
+ if (!res) {
+ pr_debug("%s: no DDMA ID resource\n", DRV_NAME);
+ ret = -ENODEV;
+ goto out;
+ }
+ ahwif->ddma_id = res->start;
+
memset(&hw, 0, sizeof(hw));
auide_setup_ports(&hw, ahwif);
hw.irq = ahwif->irq;
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index 23e82e4..001b147 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -3,7 +3,7 @@
#
menu "Input device support"
- depends on !S390
+ depends on !S390 && !UML
config INPUT
tristate "Generic input layer (needed for keyboard, mouse, ...)" if EXPERT
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 56aa465..22d875f 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -134,6 +134,16 @@
To compile this driver as a module, choose M here: the module
will be called max8925_onkey.
+config INPUT_MC13783_PWRBUTTON
+ tristate "MC13783 ON buttons"
+ depends on MFD_MC13783
+ help
+ Support the ON buttons of MC13783 PMIC as an input device
+ reporting power button status.
+
+ To compile this driver as a module, choose M here: the module
+ will be called mc13783-pwrbutton.
+
config INPUT_MMA8450
tristate "MMA8450 - Freescale's 3-Axis, 8/12-bit Digital Accelerometer"
depends on I2C
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index 62dcd79..a244fc6 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -28,6 +28,7 @@
obj-$(CONFIG_INPUT_KXTJ9) += kxtj9.o
obj-$(CONFIG_INPUT_M68K_BEEP) += m68kspkr.o
obj-$(CONFIG_INPUT_MAX8925_ONKEY) += max8925_onkey.o
+obj-$(CONFIG_INPUT_MC13783_PWRBUTTON) += mc13783-pwrbutton.o
obj-$(CONFIG_INPUT_MMA8450) += mma8450.o
obj-$(CONFIG_INPUT_MPU3050) += mpu3050.o
obj-$(CONFIG_INPUT_PCAP) += pcap_keys.o
diff --git a/drivers/input/misc/mc13783-pwrbutton.c b/drivers/input/misc/mc13783-pwrbutton.c
new file mode 100644
index 0000000..09b0522
--- /dev/null
+++ b/drivers/input/misc/mc13783-pwrbutton.c
@@ -0,0 +1,282 @@
+/**
+ * Copyright (C) 2011 Philippe Rétornaz
+ *
+ * Based on twl4030-pwrbutton driver by:
+ * Peter De Schrijver <peter.de-schrijver@nokia.com>
+ * Felipe Balbi <felipe.balbi@nokia.com>
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file "COPYING" in the main directory of this
+ * archive for more details.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Suite 500, Boston, MA 02110-1335 USA
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/mc13783.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+struct mc13783_pwrb {
+ struct input_dev *pwr;
+ struct mc13xxx *mc13783;
+#define MC13783_PWRB_B1_POL_INVERT (1 << 0)
+#define MC13783_PWRB_B2_POL_INVERT (1 << 1)
+#define MC13783_PWRB_B3_POL_INVERT (1 << 2)
+ int flags;
+ unsigned short keymap[3];
+};
+
+#define MC13783_REG_INTERRUPT_SENSE_1 5
+#define MC13783_IRQSENSE1_ONOFD1S (1 << 3)
+#define MC13783_IRQSENSE1_ONOFD2S (1 << 4)
+#define MC13783_IRQSENSE1_ONOFD3S (1 << 5)
+
+#define MC13783_REG_POWER_CONTROL_2 15
+#define MC13783_POWER_CONTROL_2_ON1BDBNC 4
+#define MC13783_POWER_CONTROL_2_ON2BDBNC 6
+#define MC13783_POWER_CONTROL_2_ON3BDBNC 8
+#define MC13783_POWER_CONTROL_2_ON1BRSTEN (1 << 1)
+#define MC13783_POWER_CONTROL_2_ON2BRSTEN (1 << 2)
+#define MC13783_POWER_CONTROL_2_ON3BRSTEN (1 << 3)
+
+static irqreturn_t button_irq(int irq, void *_priv)
+{
+ struct mc13783_pwrb *priv = _priv;
+ int val;
+
+ mc13xxx_irq_ack(priv->mc13783, irq);
+ mc13xxx_reg_read(priv->mc13783, MC13783_REG_INTERRUPT_SENSE_1, &val);
+
+ switch (irq) {
+ case MC13783_IRQ_ONOFD1:
+ val = val & MC13783_IRQSENSE1_ONOFD1S ? 1 : 0;
+ if (priv->flags & MC13783_PWRB_B1_POL_INVERT)
+ val ^= 1;
+ input_report_key(priv->pwr, priv->keymap[0], val);
+ break;
+
+ case MC13783_IRQ_ONOFD2:
+ val = val & MC13783_IRQSENSE1_ONOFD2S ? 1 : 0;
+ if (priv->flags & MC13783_PWRB_B2_POL_INVERT)
+ val ^= 1;
+ input_report_key(priv->pwr, priv->keymap[1], val);
+ break;
+
+ case MC13783_IRQ_ONOFD3:
+ val = val & MC13783_IRQSENSE1_ONOFD3S ? 1 : 0;
+ if (priv->flags & MC13783_PWRB_B3_POL_INVERT)
+ val ^= 1;
+ input_report_key(priv->pwr, priv->keymap[2], val);
+ break;
+ }
+
+ input_sync(priv->pwr);
+
+ return IRQ_HANDLED;
+}
+
+static int __devinit mc13783_pwrbutton_probe(struct platform_device *pdev)
+{
+ const struct mc13xxx_buttons_platform_data *pdata;
+ struct mc13xxx *mc13783 = dev_get_drvdata(pdev->dev.parent);
+ struct input_dev *pwr;
+ struct mc13783_pwrb *priv;
+ int err = 0;
+ int reg = 0;
+
+ pdata = dev_get_platdata(&pdev->dev);
+ if (!pdata) {
+ dev_err(&pdev->dev, "missing platform data\n");
+ return -ENODEV;
+ }
+
+ pwr = input_allocate_device();
+ if (!pwr) {
+ dev_dbg(&pdev->dev, "Can't allocate power button\n");
+ return -ENOMEM;
+ }
+
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (!priv) {
+ err = -ENOMEM;
+ dev_dbg(&pdev->dev, "Can't allocate power button\n");
+ goto free_input_dev;
+ }
+
+ reg |= (pdata->b1on_flags & 0x3) << MC13783_POWER_CONTROL_2_ON1BDBNC;
+ reg |= (pdata->b2on_flags & 0x3) << MC13783_POWER_CONTROL_2_ON2BDBNC;
+ reg |= (pdata->b3on_flags & 0x3) << MC13783_POWER_CONTROL_2_ON3BDBNC;
+
+ priv->pwr = pwr;
+ priv->mc13783 = mc13783;
+
+ mc13xxx_lock(mc13783);
+
+ if (pdata->b1on_flags & MC13783_BUTTON_ENABLE) {
+ priv->keymap[0] = pdata->b1on_key;
+ if (pdata->b1on_key != KEY_RESERVED)
+ __set_bit(pdata->b1on_key, pwr->keybit);
+
+ if (pdata->b1on_flags & MC13783_BUTTON_POL_INVERT)
+ priv->flags |= MC13783_PWRB_B1_POL_INVERT;
+
+ if (pdata->b1on_flags & MC13783_BUTTON_RESET_EN)
+ reg |= MC13783_POWER_CONTROL_2_ON1BRSTEN;
+
+ err = mc13xxx_irq_request(mc13783, MC13783_IRQ_ONOFD1,
+ button_irq, "b1on", priv);
+ if (err) {
+ dev_dbg(&pdev->dev, "Can't request irq\n");
+ goto free_priv;
+ }
+ }
+
+ if (pdata->b2on_flags & MC13783_BUTTON_ENABLE) {
+ priv->keymap[1] = pdata->b2on_key;
+ if (pdata->b2on_key != KEY_RESERVED)
+ __set_bit(pdata->b2on_key, pwr->keybit);
+
+ if (pdata->b2on_flags & MC13783_BUTTON_POL_INVERT)
+ priv->flags |= MC13783_PWRB_B2_POL_INVERT;
+
+ if (pdata->b2on_flags & MC13783_BUTTON_RESET_EN)
+ reg |= MC13783_POWER_CONTROL_2_ON2BRSTEN;
+
+ err = mc13xxx_irq_request(mc13783, MC13783_IRQ_ONOFD2,
+ button_irq, "b2on", priv);
+ if (err) {
+ dev_dbg(&pdev->dev, "Can't request irq\n");
+ goto free_irq_b1;
+ }
+ }
+
+ if (pdata->b3on_flags & MC13783_BUTTON_ENABLE) {
+ priv->keymap[2] = pdata->b3on_key;
+ if (pdata->b3on_key != KEY_RESERVED)
+ __set_bit(pdata->b3on_key, pwr->keybit);
+
+ if (pdata->b3on_flags & MC13783_BUTTON_POL_INVERT)
+ priv->flags |= MC13783_PWRB_B3_POL_INVERT;
+
+ if (pdata->b3on_flags & MC13783_BUTTON_RESET_EN)
+ reg |= MC13783_POWER_CONTROL_2_ON3BRSTEN;
+
+ err = mc13xxx_irq_request(mc13783, MC13783_IRQ_ONOFD3,
+ button_irq, "b3on", priv);
+ if (err) {
+ dev_dbg(&pdev->dev, "Can't request irq: %d\n", err);
+ goto free_irq_b2;
+ }
+ }
+
+ mc13xxx_reg_rmw(mc13783, MC13783_REG_POWER_CONTROL_2, 0x3FE, reg);
+
+ mc13xxx_unlock(mc13783);
+
+ pwr->name = "mc13783_pwrbutton";
+ pwr->phys = "mc13783_pwrbutton/input0";
+ pwr->dev.parent = &pdev->dev;
+
+ pwr->keycode = priv->keymap;
+ pwr->keycodemax = ARRAY_SIZE(priv->keymap);
+ pwr->keycodesize = sizeof(priv->keymap[0]);
+ __set_bit(EV_KEY, pwr->evbit);
+
+ err = input_register_device(pwr);
+ if (err) {
+ dev_dbg(&pdev->dev, "Can't register power button: %d\n", err);
+ goto free_irq;
+ }
+
+ platform_set_drvdata(pdev, priv);
+
+ return 0;
+
+free_irq:
+ mc13xxx_lock(mc13783);
+
+ if (pdata->b3on_flags & MC13783_BUTTON_ENABLE)
+ mc13xxx_irq_free(mc13783, MC13783_IRQ_ONOFD3, priv);
+
+free_irq_b2:
+ if (pdata->b2on_flags & MC13783_BUTTON_ENABLE)
+ mc13xxx_irq_free(mc13783, MC13783_IRQ_ONOFD2, priv);
+
+free_irq_b1:
+ if (pdata->b1on_flags & MC13783_BUTTON_ENABLE)
+ mc13xxx_irq_free(mc13783, MC13783_IRQ_ONOFD1, priv);
+
+free_priv:
+ mc13xxx_unlock(mc13783);
+ kfree(priv);
+
+free_input_dev:
+ input_free_device(pwr);
+
+ return err;
+}
+
+static int __devexit mc13783_pwrbutton_remove(struct platform_device *pdev)
+{
+ struct mc13783_pwrb *priv = platform_get_drvdata(pdev);
+ const struct mc13xxx_buttons_platform_data *pdata;
+
+ pdata = dev_get_platdata(&pdev->dev);
+
+ mc13xxx_lock(priv->mc13783);
+
+ if (pdata->b3on_flags & MC13783_BUTTON_ENABLE)
+ mc13xxx_irq_free(priv->mc13783, MC13783_IRQ_ONOFD3, priv);
+ if (pdata->b2on_flags & MC13783_BUTTON_ENABLE)
+ mc13xxx_irq_free(priv->mc13783, MC13783_IRQ_ONOFD2, priv);
+ if (pdata->b1on_flags & MC13783_BUTTON_ENABLE)
+ mc13xxx_irq_free(priv->mc13783, MC13783_IRQ_ONOFD1, priv);
+
+ mc13xxx_unlock(priv->mc13783);
+
+ input_unregister_device(priv->pwr);
+ kfree(priv);
+ platform_set_drvdata(pdev, NULL);
+
+ return 0;
+}
+
+struct platform_driver mc13783_pwrbutton_driver = {
+ .probe = mc13783_pwrbutton_probe,
+ .remove = __devexit_p(mc13783_pwrbutton_remove),
+ .driver = {
+ .name = "mc13783-pwrbutton",
+ .owner = THIS_MODULE,
+ },
+};
+
+static int __init mc13783_pwrbutton_init(void)
+{
+ return platform_driver_register(&mc13783_pwrbutton_driver);
+}
+module_init(mc13783_pwrbutton_init);
+
+static void __exit mc13783_pwrbutton_exit(void)
+{
+ platform_driver_unregister(&mc13783_pwrbutton_driver);
+}
+module_exit(mc13783_pwrbutton_exit);
+
+MODULE_ALIAS("platform:mc13783-pwrbutton");
+MODULE_DESCRIPTION("MC13783 Power Button");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Philippe Retornaz");
diff --git a/drivers/input/touchscreen/mc13783_ts.c b/drivers/input/touchscreen/mc13783_ts.c
index c5bc62d..ede0274 100644
--- a/drivers/input/touchscreen/mc13783_ts.c
+++ b/drivers/input/touchscreen/mc13783_ts.c
@@ -35,7 +35,7 @@
struct mc13783_ts_priv {
struct input_dev *idev;
- struct mc13783 *mc13783;
+ struct mc13xxx *mc13xxx;
struct delayed_work work;
struct workqueue_struct *workq;
unsigned int sample[4];
@@ -45,7 +45,7 @@
{
struct mc13783_ts_priv *priv = data;
- mc13783_irq_ack(priv->mc13783, irq);
+ mc13xxx_irq_ack(priv->mc13xxx, irq);
/*
* Kick off reading coordinates. Note that if work happens already
@@ -121,10 +121,10 @@
{
struct mc13783_ts_priv *priv =
container_of(work, struct mc13783_ts_priv, work.work);
- unsigned int mode = MC13783_ADC_MODE_TS;
+ unsigned int mode = MC13XXX_ADC_MODE_TS;
unsigned int channel = 12;
- if (mc13783_adc_do_conversion(priv->mc13783,
+ if (mc13xxx_adc_do_conversion(priv->mc13xxx,
mode, channel, priv->sample) == 0)
mc13783_ts_report_sample(priv);
}
@@ -134,21 +134,21 @@
struct mc13783_ts_priv *priv = input_get_drvdata(dev);
int ret;
- mc13783_lock(priv->mc13783);
+ mc13xxx_lock(priv->mc13xxx);
- mc13783_irq_ack(priv->mc13783, MC13783_IRQ_TS);
+ mc13xxx_irq_ack(priv->mc13xxx, MC13XXX_IRQ_TS);
- ret = mc13783_irq_request(priv->mc13783, MC13783_IRQ_TS,
+ ret = mc13xxx_irq_request(priv->mc13xxx, MC13XXX_IRQ_TS,
mc13783_ts_handler, MC13783_TS_NAME, priv);
if (ret)
goto out;
- ret = mc13783_reg_rmw(priv->mc13783, MC13783_ADC0,
- MC13783_ADC0_TSMOD_MASK, MC13783_ADC0_TSMOD0);
+ ret = mc13xxx_reg_rmw(priv->mc13xxx, MC13XXX_ADC0,
+ MC13XXX_ADC0_TSMOD_MASK, MC13XXX_ADC0_TSMOD0);
if (ret)
- mc13783_irq_free(priv->mc13783, MC13783_IRQ_TS, priv);
+ mc13xxx_irq_free(priv->mc13xxx, MC13XXX_IRQ_TS, priv);
out:
- mc13783_unlock(priv->mc13783);
+ mc13xxx_unlock(priv->mc13xxx);
return ret;
}
@@ -156,11 +156,11 @@
{
struct mc13783_ts_priv *priv = input_get_drvdata(dev);
- mc13783_lock(priv->mc13783);
- mc13783_reg_rmw(priv->mc13783, MC13783_ADC0,
- MC13783_ADC0_TSMOD_MASK, 0);
- mc13783_irq_free(priv->mc13783, MC13783_IRQ_TS, priv);
- mc13783_unlock(priv->mc13783);
+ mc13xxx_lock(priv->mc13xxx);
+ mc13xxx_reg_rmw(priv->mc13xxx, MC13XXX_ADC0,
+ MC13XXX_ADC0_TSMOD_MASK, 0);
+ mc13xxx_irq_free(priv->mc13xxx, MC13XXX_IRQ_TS, priv);
+ mc13xxx_unlock(priv->mc13xxx);
cancel_delayed_work_sync(&priv->work);
}
@@ -177,7 +177,7 @@
goto err_free_mem;
INIT_DELAYED_WORK(&priv->work, mc13783_ts_work);
- priv->mc13783 = dev_get_drvdata(pdev->dev.parent);
+ priv->mc13xxx = dev_get_drvdata(pdev->dev.parent);
priv->idev = idev;
/*
diff --git a/drivers/isdn/Kconfig b/drivers/isdn/Kconfig
index 4fb6016..a233ed5 100644
--- a/drivers/isdn/Kconfig
+++ b/drivers/isdn/Kconfig
@@ -5,7 +5,7 @@
menuconfig ISDN
bool "ISDN support"
depends on NET
- depends on !S390
+ depends on !S390 && !UML
---help---
ISDN ("Integrated Services Digital Network", called RNIS in France)
is a fully digital telephone service that can be used for voice and
diff --git a/drivers/isdn/hisax/l3dss1.c b/drivers/isdn/hisax/l3dss1.c
index b0d9ab1..6a8acf6 100644
--- a/drivers/isdn/hisax/l3dss1.c
+++ b/drivers/isdn/hisax/l3dss1.c
@@ -353,7 +353,7 @@
{ l3dss1_dummy_invoke(st, cr, id, ident, p, nlen);
return;
}
-#ifdef HISAX_DE_AOC
+#ifdef CONFIG_DE_AOC
{
#define FOO1(s,a,b) \
@@ -422,9 +422,9 @@
#undef FOO1
}
-#else /* not HISAX_DE_AOC */
+#else /* not CONFIG_DE_AOC */
l3_debug(st, "invoke break");
-#endif /* not HISAX_DE_AOC */
+#endif /* not CONFIG_DE_AOC */
break;
case 2: /* return result */
/* if no process available handle separately */
diff --git a/drivers/leds/leds-asic3.c b/drivers/leds/leds-asic3.c
index 22f847c..fbd5d88 100644
--- a/drivers/leds/leds-asic3.c
+++ b/drivers/leds/leds-asic3.c
@@ -107,9 +107,10 @@
}
led->cdev->name = led->name;
- led->cdev->default_trigger = led->default_trigger;
+ led->cdev->flags = LED_CORE_SUSPENDRESUME;
led->cdev->brightness_set = brightness_set;
led->cdev->blink_set = blink_set;
+ led->cdev->default_trigger = led->default_trigger;
ret = led_classdev_register(&pdev->dev, led->cdev);
if (ret < 0)
@@ -136,12 +137,44 @@
return mfd_cell_disable(pdev);
}
+static int asic3_led_suspend(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ const struct mfd_cell *cell = mfd_get_cell(pdev);
+ int ret;
+
+ ret = 0;
+ if (cell->suspend)
+ ret = (*cell->suspend)(pdev);
+
+ return ret;
+}
+
+static int asic3_led_resume(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ const struct mfd_cell *cell = mfd_get_cell(pdev);
+ int ret;
+
+ ret = 0;
+ if (cell->resume)
+ ret = (*cell->resume)(pdev);
+
+ return ret;
+}
+
+static const struct dev_pm_ops asic3_led_pm_ops = {
+ .suspend = asic3_led_suspend,
+ .resume = asic3_led_resume,
+};
+
static struct platform_driver asic3_led_driver = {
.probe = asic3_led_probe,
.remove = __devexit_p(asic3_led_remove),
.driver = {
.name = "leds-asic3",
.owner = THIS_MODULE,
+ .pm = &asic3_led_pm_ops,
},
};
diff --git a/drivers/leds/leds-mc13783.c b/drivers/leds/leds-mc13783.c
index f369e56..b3393a9 100644
--- a/drivers/leds/leds-mc13783.c
+++ b/drivers/leds/leds-mc13783.c
@@ -21,13 +21,13 @@
#include <linux/platform_device.h>
#include <linux/leds.h>
#include <linux/workqueue.h>
-#include <linux/mfd/mc13783.h>
+#include <linux/mfd/mc13xxx.h>
#include <linux/slab.h>
struct mc13783_led {
struct led_classdev cdev;
struct work_struct work;
- struct mc13783 *master;
+ struct mc13xxx *master;
enum led_brightness new_brightness;
int id;
};
@@ -111,11 +111,11 @@
break;
}
- mc13783_lock(led->master);
+ mc13xxx_lock(led->master);
- mc13783_reg_rmw(led->master, reg, mask, value);
+ mc13xxx_reg_rmw(led->master, reg, mask, value);
- mc13783_unlock(led->master);
+ mc13xxx_unlock(led->master);
}
static void mc13783_led_set(struct led_classdev *led_cdev,
@@ -172,23 +172,23 @@
break;
}
- mc13783_lock(led->master);
+ mc13xxx_lock(led->master);
- ret = mc13783_reg_rmw(led->master, reg, mask << shift,
+ ret = mc13xxx_reg_rmw(led->master, reg, mask << shift,
value << shift);
- mc13783_unlock(led->master);
+ mc13xxx_unlock(led->master);
return ret;
}
static int __devinit mc13783_leds_prepare(struct platform_device *pdev)
{
- struct mc13783_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
- struct mc13783 *dev = dev_get_drvdata(pdev->dev.parent);
+ struct mc13xxx_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
+ struct mc13xxx *dev = dev_get_drvdata(pdev->dev.parent);
int ret = 0;
int reg = 0;
- mc13783_lock(dev);
+ mc13xxx_lock(dev);
if (pdata->flags & MC13783_LED_TC1HALF)
reg |= MC13783_LED_C1_TC1HALF_BIT;
@@ -196,7 +196,7 @@
if (pdata->flags & MC13783_LED_SLEWLIMTC)
reg |= MC13783_LED_Cx_SLEWLIM_BIT;
- ret = mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_1, reg);
+ ret = mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_1, reg);
if (ret)
goto out;
@@ -206,7 +206,7 @@
if (pdata->flags & MC13783_LED_SLEWLIMBL)
reg |= MC13783_LED_Cx_SLEWLIM_BIT;
- ret = mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_2, reg);
+ ret = mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_2, reg);
if (ret)
goto out;
@@ -216,7 +216,7 @@
if (pdata->flags & MC13783_LED_TRIODE_TC1)
reg |= MC13783_LED_Cx_TRIODE_TC_BIT;
- ret = mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_3, reg);
+ ret = mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_3, reg);
if (ret)
goto out;
@@ -226,7 +226,7 @@
if (pdata->flags & MC13783_LED_TRIODE_TC2)
reg |= MC13783_LED_Cx_TRIODE_TC_BIT;
- ret = mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_4, reg);
+ ret = mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_4, reg);
if (ret)
goto out;
@@ -236,7 +236,7 @@
if (pdata->flags & MC13783_LED_TRIODE_TC3)
reg |= MC13783_LED_Cx_TRIODE_TC_BIT;
- ret = mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_5, reg);
+ ret = mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_5, reg);
if (ret)
goto out;
@@ -255,17 +255,17 @@
reg |= (pdata->abref & MC13783_LED_C0_ABREF_MASK) <<
MC13783_LED_C0_ABREF;
- ret = mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_0, reg);
+ ret = mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_0, reg);
out:
- mc13783_unlock(dev);
+ mc13xxx_unlock(dev);
return ret;
}
static int __devinit mc13783_led_probe(struct platform_device *pdev)
{
- struct mc13783_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
- struct mc13783_led_platform_data *led_cur;
+ struct mc13xxx_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
+ struct mc13xxx_led_platform_data *led_cur;
struct mc13783_led *led, *led_dat;
int ret, i;
int init_led = 0;
@@ -351,9 +351,9 @@
static int __devexit mc13783_led_remove(struct platform_device *pdev)
{
- struct mc13783_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
+ struct mc13xxx_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct mc13783_led *led = platform_get_drvdata(pdev);
- struct mc13783 *dev = dev_get_drvdata(pdev->dev.parent);
+ struct mc13xxx *dev = dev_get_drvdata(pdev->dev.parent);
int i;
for (i = 0; i < pdata->num_leds; i++) {
@@ -361,16 +361,16 @@
cancel_work_sync(&led[i].work);
}
- mc13783_lock(dev);
+ mc13xxx_lock(dev);
- mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_0, 0);
- mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_1, 0);
- mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_2, 0);
- mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_3, 0);
- mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_4, 0);
- mc13783_reg_write(dev, MC13783_REG_LED_CONTROL_5, 0);
+ mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_0, 0);
+ mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_1, 0);
+ mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_2, 0);
+ mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_3, 0);
+ mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_4, 0);
+ mc13xxx_reg_write(dev, MC13783_REG_LED_CONTROL_5, 0);
- mc13783_unlock(dev);
+ mc13xxx_unlock(dev);
kfree(led);
return 0;
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index f75a66e..faa4741 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -208,6 +208,16 @@
If unsure, say N.
+config DM_BUFIO
+ tristate
+ depends on BLK_DEV_DM && EXPERIMENTAL
+ ---help---
+ This interface allows you to do buffered I/O on a device and acts
+ as a cache, holding recently-read blocks in memory and performing
+ delayed writes.
+
+source "drivers/md/persistent-data/Kconfig"
+
config DM_CRYPT
tristate "Crypt target support"
depends on BLK_DEV_DM
@@ -233,6 +243,32 @@
---help---
Allow volume managers to take writable snapshots of a device.
+config DM_THIN_PROVISIONING
+ tristate "Thin provisioning target (EXPERIMENTAL)"
+ depends on BLK_DEV_DM && EXPERIMENTAL
+ select DM_PERSISTENT_DATA
+ ---help---
+ Provides thin provisioning and snapshots that share a data store.
+
+config DM_DEBUG_BLOCK_STACK_TRACING
+ boolean "Keep stack trace of thin provisioning block lock holders"
+ depends on STACKTRACE_SUPPORT && DM_THIN_PROVISIONING
+ select STACKTRACE
+ ---help---
+ Enable this for messages that may help debug problems with the
+ block manager locking used by thin provisioning.
+
+ If unsure, say N.
+
+config DM_DEBUG_SPACE_MAPS
+ boolean "Extra validation for thin provisioning space maps"
+ depends on DM_THIN_PROVISIONING
+ ---help---
+ Enable this for messages that may help debug problems with the
+ space maps used by thin provisioning.
+
+ If unsure, say N.
+
config DM_MIRROR
tristate "Mirror target"
depends on BLK_DEV_DM
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 448838b..046860c 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -10,6 +10,7 @@
dm-mirror-y += dm-raid1.o
dm-log-userspace-y \
+= dm-log-userspace-base.o dm-log-userspace-transfer.o
+dm-thin-pool-y += dm-thin.o dm-thin-metadata.o
md-mod-y += md.o bitmap.o
raid456-y += raid5.o
@@ -27,6 +28,7 @@
obj-$(CONFIG_MD_FAULTY) += faulty.o
obj-$(CONFIG_BLK_DEV_MD) += md-mod.o
obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o
+obj-$(CONFIG_DM_BUFIO) += dm-bufio.o
obj-$(CONFIG_DM_CRYPT) += dm-crypt.o
obj-$(CONFIG_DM_DELAY) += dm-delay.o
obj-$(CONFIG_DM_FLAKEY) += dm-flakey.o
@@ -34,10 +36,12 @@
obj-$(CONFIG_DM_MULTIPATH_QL) += dm-queue-length.o
obj-$(CONFIG_DM_MULTIPATH_ST) += dm-service-time.o
obj-$(CONFIG_DM_SNAPSHOT) += dm-snapshot.o
+obj-$(CONFIG_DM_PERSISTENT_DATA) += persistent-data/
obj-$(CONFIG_DM_MIRROR) += dm-mirror.o dm-log.o dm-region-hash.o
obj-$(CONFIG_DM_LOG_USERSPACE) += dm-log-userspace.o
obj-$(CONFIG_DM_ZERO) += dm-zero.o
obj-$(CONFIG_DM_RAID) += dm-raid.o
+obj-$(CONFIG_DM_THIN_PROVISIONING) += dm-thin-pool.o
ifeq ($(CONFIG_DM_UEVENT),y)
dm-mod-objs += dm-uevent.o
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
new file mode 100644
index 0000000..cb24666
--- /dev/null
+++ b/drivers/md/dm-bufio.c
@@ -0,0 +1,1699 @@
+/*
+ * Copyright (C) 2009-2011 Red Hat, Inc.
+ *
+ * Author: Mikulas Patocka <mpatocka@redhat.com>
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-bufio.h"
+
+#include <linux/device-mapper.h>
+#include <linux/dm-io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/version.h>
+#include <linux/shrinker.h>
+
+#define DM_MSG_PREFIX "bufio"
+
+/*
+ * Memory management policy:
+ * Limit the number of buffers to DM_BUFIO_MEMORY_PERCENT of main memory
+ * or DM_BUFIO_VMALLOC_PERCENT of vmalloc memory (whichever is lower).
+ * Always allocate at least DM_BUFIO_MIN_BUFFERS buffers.
+ * Start background writeback when there are DM_BUFIO_WRITEBACK_PERCENT
+ * dirty buffers.
+ */
+#define DM_BUFIO_MIN_BUFFERS 8
+
+#define DM_BUFIO_MEMORY_PERCENT 2
+#define DM_BUFIO_VMALLOC_PERCENT 25
+#define DM_BUFIO_WRITEBACK_PERCENT 75
+
+/*
+ * Check buffer ages in this interval (seconds)
+ */
+#define DM_BUFIO_WORK_TIMER_SECS 10
+
+/*
+ * Free buffers when they are older than this (seconds)
+ */
+#define DM_BUFIO_DEFAULT_AGE_SECS 60
+
+/*
+ * The number of bvec entries that are embedded directly in the buffer.
+ * If the chunk size is larger, dm-io is used to do the io.
+ */
+#define DM_BUFIO_INLINE_VECS 16
+
+/*
+ * Buffer hash
+ */
+#define DM_BUFIO_HASH_BITS 20
+#define DM_BUFIO_HASH(block) \
+ ((((block) >> DM_BUFIO_HASH_BITS) ^ (block)) & \
+ ((1 << DM_BUFIO_HASH_BITS) - 1))
+
+/*
+ * Don't try to use kmem_cache_alloc for blocks larger than this.
+ * For explanation, see alloc_buffer_data below.
+ */
+#define DM_BUFIO_BLOCK_SIZE_SLAB_LIMIT (PAGE_SIZE >> 1)
+#define DM_BUFIO_BLOCK_SIZE_GFP_LIMIT (PAGE_SIZE << (MAX_ORDER - 1))
+
+/*
+ * dm_buffer->list_mode
+ */
+#define LIST_CLEAN 0
+#define LIST_DIRTY 1
+#define LIST_SIZE 2
+
+/*
+ * Linking of buffers:
+ * All buffers are linked to cache_hash with their hash_list field.
+ *
+ * Clean buffers that are not being written (B_WRITING not set)
+ * are linked to lru[LIST_CLEAN] with their lru_list field.
+ *
+ * Dirty and clean buffers that are being written are linked to
+ * lru[LIST_DIRTY] with their lru_list field. When the write
+ * finishes, the buffer cannot be relinked immediately (because we
+ * are in an interrupt context and relinking requires process
+ * context), so some clean-not-writing buffers can be held on
+ * dirty_lru too. They are later added to lru in the process
+ * context.
+ */
+struct dm_bufio_client {
+ struct mutex lock;
+
+ struct list_head lru[LIST_SIZE];
+ unsigned long n_buffers[LIST_SIZE];
+
+ struct block_device *bdev;
+ unsigned block_size;
+ unsigned char sectors_per_block_bits;
+ unsigned char pages_per_block_bits;
+ unsigned char blocks_per_page_bits;
+ unsigned aux_size;
+ void (*alloc_callback)(struct dm_buffer *);
+ void (*write_callback)(struct dm_buffer *);
+
+ struct dm_io_client *dm_io;
+
+ struct list_head reserved_buffers;
+ unsigned need_reserved_buffers;
+
+ struct hlist_head *cache_hash;
+ wait_queue_head_t free_buffer_wait;
+
+ int async_write_error;
+
+ struct list_head client_list;
+ struct shrinker shrinker;
+};
+
+/*
+ * Buffer state bits.
+ */
+#define B_READING 0
+#define B_WRITING 1
+#define B_DIRTY 2
+
+/*
+ * Describes how the block was allocated:
+ * kmem_cache_alloc(), __get_free_pages() or vmalloc().
+ * See the comment at alloc_buffer_data.
+ */
+enum data_mode {
+ DATA_MODE_SLAB = 0,
+ DATA_MODE_GET_FREE_PAGES = 1,
+ DATA_MODE_VMALLOC = 2,
+ DATA_MODE_LIMIT = 3
+};
+
+struct dm_buffer {
+ struct hlist_node hash_list;
+ struct list_head lru_list;
+ sector_t block;
+ void *data;
+ enum data_mode data_mode;
+ unsigned char list_mode; /* LIST_* */
+ unsigned hold_count;
+ int read_error;
+ int write_error;
+ unsigned long state;
+ unsigned long last_accessed;
+ struct dm_bufio_client *c;
+ struct bio bio;
+ struct bio_vec bio_vec[DM_BUFIO_INLINE_VECS];
+};
+
+/*----------------------------------------------------------------*/
+
+static struct kmem_cache *dm_bufio_caches[PAGE_SHIFT - SECTOR_SHIFT];
+static char *dm_bufio_cache_names[PAGE_SHIFT - SECTOR_SHIFT];
+
+static inline int dm_bufio_cache_index(struct dm_bufio_client *c)
+{
+ unsigned ret = c->blocks_per_page_bits - 1;
+
+ BUG_ON(ret >= ARRAY_SIZE(dm_bufio_caches));
+
+ return ret;
+}
+
+#define DM_BUFIO_CACHE(c) (dm_bufio_caches[dm_bufio_cache_index(c)])
+#define DM_BUFIO_CACHE_NAME(c) (dm_bufio_cache_names[dm_bufio_cache_index(c)])
+
+#define dm_bufio_in_request() (!!current->bio_list)
+
+static void dm_bufio_lock(struct dm_bufio_client *c)
+{
+ mutex_lock_nested(&c->lock, dm_bufio_in_request());
+}
+
+static int dm_bufio_trylock(struct dm_bufio_client *c)
+{
+ return mutex_trylock(&c->lock);
+}
+
+static void dm_bufio_unlock(struct dm_bufio_client *c)
+{
+ mutex_unlock(&c->lock);
+}
+
+/*
+ * FIXME Move to sched.h?
+ */
+#ifdef CONFIG_PREEMPT_VOLUNTARY
+# define dm_bufio_cond_resched() \
+do { \
+ if (unlikely(need_resched())) \
+ _cond_resched(); \
+} while (0)
+#else
+# define dm_bufio_cond_resched() do { } while (0)
+#endif
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Default cache size: available memory divided by the ratio.
+ */
+static unsigned long dm_bufio_default_cache_size;
+
+/*
+ * Total cache size set by the user.
+ */
+static unsigned long dm_bufio_cache_size;
+
+/*
+ * A copy of dm_bufio_cache_size because dm_bufio_cache_size can change
+ * at any time. If it disagrees, the user has changed cache size.
+ */
+static unsigned long dm_bufio_cache_size_latch;
+
+static DEFINE_SPINLOCK(param_spinlock);
+
+/*
+ * Buffers are freed after this timeout
+ */
+static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS;
+
+static unsigned long dm_bufio_peak_allocated;
+static unsigned long dm_bufio_allocated_kmem_cache;
+static unsigned long dm_bufio_allocated_get_free_pages;
+static unsigned long dm_bufio_allocated_vmalloc;
+static unsigned long dm_bufio_current_allocated;
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Per-client cache: dm_bufio_cache_size / dm_bufio_client_count
+ */
+static unsigned long dm_bufio_cache_size_per_client;
+
+/*
+ * The current number of clients.
+ */
+static int dm_bufio_client_count;
+
+/*
+ * The list of all clients.
+ */
+static LIST_HEAD(dm_bufio_all_clients);
+
+/*
+ * This mutex protects dm_bufio_cache_size_latch,
+ * dm_bufio_cache_size_per_client and dm_bufio_client_count
+ */
+static DEFINE_MUTEX(dm_bufio_clients_lock);
+
+/*----------------------------------------------------------------*/
+
+static void adjust_total_allocated(enum data_mode data_mode, long diff)
+{
+ static unsigned long * const class_ptr[DATA_MODE_LIMIT] = {
+ &dm_bufio_allocated_kmem_cache,
+ &dm_bufio_allocated_get_free_pages,
+ &dm_bufio_allocated_vmalloc,
+ };
+
+ spin_lock(¶m_spinlock);
+
+ *class_ptr[data_mode] += diff;
+
+ dm_bufio_current_allocated += diff;
+
+ if (dm_bufio_current_allocated > dm_bufio_peak_allocated)
+ dm_bufio_peak_allocated = dm_bufio_current_allocated;
+
+ spin_unlock(¶m_spinlock);
+}
+
+/*
+ * Change the number of clients and recalculate per-client limit.
+ */
+static void __cache_size_refresh(void)
+{
+ BUG_ON(!mutex_is_locked(&dm_bufio_clients_lock));
+ BUG_ON(dm_bufio_client_count < 0);
+
+ dm_bufio_cache_size_latch = dm_bufio_cache_size;
+
+ barrier();
+
+ /*
+ * Use default if set to 0 and report the actual cache size used.
+ */
+ if (!dm_bufio_cache_size_latch) {
+ (void)cmpxchg(&dm_bufio_cache_size, 0,
+ dm_bufio_default_cache_size);
+ dm_bufio_cache_size_latch = dm_bufio_default_cache_size;
+ }
+
+ dm_bufio_cache_size_per_client = dm_bufio_cache_size_latch /
+ (dm_bufio_client_count ? : 1);
+}
+
+/*
+ * Allocating buffer data.
+ *
+ * Small buffers are allocated with kmem_cache, to use space optimally.
+ *
+ * For large buffers, we choose between get_free_pages and vmalloc.
+ * Each has advantages and disadvantages.
+ *
+ * __get_free_pages can randomly fail if the memory is fragmented.
+ * __vmalloc won't randomly fail, but vmalloc space is limited (it may be
+ * as low as 128M) so using it for caching is not appropriate.
+ *
+ * If the allocation may fail we use __get_free_pages. Memory fragmentation
+ * won't have a fatal effect here, but it just causes flushes of some other
+ * buffers and more I/O will be performed. Don't use __get_free_pages if it
+ * always fails (i.e. order >= MAX_ORDER).
+ *
+ * If the allocation shouldn't fail we use __vmalloc. This is only for the
+ * initial reserve allocation, so there's no risk of wasting all vmalloc
+ * space.
+ */
+static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask,
+ enum data_mode *data_mode)
+{
+ if (c->block_size <= DM_BUFIO_BLOCK_SIZE_SLAB_LIMIT) {
+ *data_mode = DATA_MODE_SLAB;
+ return kmem_cache_alloc(DM_BUFIO_CACHE(c), gfp_mask);
+ }
+
+ if (c->block_size <= DM_BUFIO_BLOCK_SIZE_GFP_LIMIT &&
+ gfp_mask & __GFP_NORETRY) {
+ *data_mode = DATA_MODE_GET_FREE_PAGES;
+ return (void *)__get_free_pages(gfp_mask,
+ c->pages_per_block_bits);
+ }
+
+ *data_mode = DATA_MODE_VMALLOC;
+ return __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL);
+}
+
+/*
+ * Free buffer's data.
+ */
+static void free_buffer_data(struct dm_bufio_client *c,
+ void *data, enum data_mode data_mode)
+{
+ switch (data_mode) {
+ case DATA_MODE_SLAB:
+ kmem_cache_free(DM_BUFIO_CACHE(c), data);
+ break;
+
+ case DATA_MODE_GET_FREE_PAGES:
+ free_pages((unsigned long)data, c->pages_per_block_bits);
+ break;
+
+ case DATA_MODE_VMALLOC:
+ vfree(data);
+ break;
+
+ default:
+ DMCRIT("dm_bufio_free_buffer_data: bad data mode: %d",
+ data_mode);
+ BUG();
+ }
+}
+
+/*
+ * Allocate buffer and its data.
+ */
+static struct dm_buffer *alloc_buffer(struct dm_bufio_client *c, gfp_t gfp_mask)
+{
+ struct dm_buffer *b = kmalloc(sizeof(struct dm_buffer) + c->aux_size,
+ gfp_mask);
+
+ if (!b)
+ return NULL;
+
+ b->c = c;
+
+ b->data = alloc_buffer_data(c, gfp_mask, &b->data_mode);
+ if (!b->data) {
+ kfree(b);
+ return NULL;
+ }
+
+ adjust_total_allocated(b->data_mode, (long)c->block_size);
+
+ return b;
+}
+
+/*
+ * Free buffer and its data.
+ */
+static void free_buffer(struct dm_buffer *b)
+{
+ struct dm_bufio_client *c = b->c;
+
+ adjust_total_allocated(b->data_mode, -(long)c->block_size);
+
+ free_buffer_data(c, b->data, b->data_mode);
+ kfree(b);
+}
+
+/*
+ * Link buffer to the hash list and clean or dirty queue.
+ */
+static void __link_buffer(struct dm_buffer *b, sector_t block, int dirty)
+{
+ struct dm_bufio_client *c = b->c;
+
+ c->n_buffers[dirty]++;
+ b->block = block;
+ b->list_mode = dirty;
+ list_add(&b->lru_list, &c->lru[dirty]);
+ hlist_add_head(&b->hash_list, &c->cache_hash[DM_BUFIO_HASH(block)]);
+ b->last_accessed = jiffies;
+}
+
+/*
+ * Unlink buffer from the hash list and dirty or clean queue.
+ */
+static void __unlink_buffer(struct dm_buffer *b)
+{
+ struct dm_bufio_client *c = b->c;
+
+ BUG_ON(!c->n_buffers[b->list_mode]);
+
+ c->n_buffers[b->list_mode]--;
+ hlist_del(&b->hash_list);
+ list_del(&b->lru_list);
+}
+
+/*
+ * Place the buffer to the head of dirty or clean LRU queue.
+ */
+static void __relink_lru(struct dm_buffer *b, int dirty)
+{
+ struct dm_bufio_client *c = b->c;
+
+ BUG_ON(!c->n_buffers[b->list_mode]);
+
+ c->n_buffers[b->list_mode]--;
+ c->n_buffers[dirty]++;
+ b->list_mode = dirty;
+ list_del(&b->lru_list);
+ list_add(&b->lru_list, &c->lru[dirty]);
+}
+
+/*----------------------------------------------------------------
+ * Submit I/O on the buffer.
+ *
+ * Bio interface is faster but it has some problems:
+ * the vector list is limited (increasing this limit increases
+ * memory-consumption per buffer, so it is not viable);
+ *
+ * the memory must be direct-mapped, not vmalloced;
+ *
+ * the I/O driver can reject requests spuriously if it thinks that
+ * the requests are too big for the device or if they cross a
+ * controller-defined memory boundary.
+ *
+ * If the buffer is small enough (up to DM_BUFIO_INLINE_VECS pages) and
+ * it is not vmalloced, try using the bio interface.
+ *
+ * If the buffer is big, if it is vmalloced or if the underlying device
+ * rejects the bio because it is too large, use dm-io layer to do the I/O.
+ * The dm-io layer splits the I/O into multiple requests, avoiding the above
+ * shortcomings.
+ *--------------------------------------------------------------*/
+
+/*
+ * dm-io completion routine. It just calls b->bio.bi_end_io, pretending
+ * that the request was handled directly with bio interface.
+ */
+static void dmio_complete(unsigned long error, void *context)
+{
+ struct dm_buffer *b = context;
+
+ b->bio.bi_end_io(&b->bio, error ? -EIO : 0);
+}
+
+static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
+ bio_end_io_t *end_io)
+{
+ int r;
+ struct dm_io_request io_req = {
+ .bi_rw = rw,
+ .notify.fn = dmio_complete,
+ .notify.context = b,
+ .client = b->c->dm_io,
+ };
+ struct dm_io_region region = {
+ .bdev = b->c->bdev,
+ .sector = block << b->c->sectors_per_block_bits,
+ .count = b->c->block_size >> SECTOR_SHIFT,
+ };
+
+ if (b->data_mode != DATA_MODE_VMALLOC) {
+ io_req.mem.type = DM_IO_KMEM;
+ io_req.mem.ptr.addr = b->data;
+ } else {
+ io_req.mem.type = DM_IO_VMA;
+ io_req.mem.ptr.vma = b->data;
+ }
+
+ b->bio.bi_end_io = end_io;
+
+ r = dm_io(&io_req, 1, ®ion, NULL);
+ if (r)
+ end_io(&b->bio, r);
+}
+
+static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
+ bio_end_io_t *end_io)
+{
+ char *ptr;
+ int len;
+
+ bio_init(&b->bio);
+ b->bio.bi_io_vec = b->bio_vec;
+ b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS;
+ b->bio.bi_sector = block << b->c->sectors_per_block_bits;
+ b->bio.bi_bdev = b->c->bdev;
+ b->bio.bi_end_io = end_io;
+
+ /*
+ * We assume that if len >= PAGE_SIZE ptr is page-aligned.
+ * If len < PAGE_SIZE the buffer doesn't cross page boundary.
+ */
+ ptr = b->data;
+ len = b->c->block_size;
+
+ if (len >= PAGE_SIZE)
+ BUG_ON((unsigned long)ptr & (PAGE_SIZE - 1));
+ else
+ BUG_ON((unsigned long)ptr & (len - 1));
+
+ do {
+ if (!bio_add_page(&b->bio, virt_to_page(ptr),
+ len < PAGE_SIZE ? len : PAGE_SIZE,
+ virt_to_phys(ptr) & (PAGE_SIZE - 1))) {
+ BUG_ON(b->c->block_size <= PAGE_SIZE);
+ use_dmio(b, rw, block, end_io);
+ return;
+ }
+
+ len -= PAGE_SIZE;
+ ptr += PAGE_SIZE;
+ } while (len > 0);
+
+ submit_bio(rw, &b->bio);
+}
+
+static void submit_io(struct dm_buffer *b, int rw, sector_t block,
+ bio_end_io_t *end_io)
+{
+ if (rw == WRITE && b->c->write_callback)
+ b->c->write_callback(b);
+
+ if (b->c->block_size <= DM_BUFIO_INLINE_VECS * PAGE_SIZE &&
+ b->data_mode != DATA_MODE_VMALLOC)
+ use_inline_bio(b, rw, block, end_io);
+ else
+ use_dmio(b, rw, block, end_io);
+}
+
+/*----------------------------------------------------------------
+ * Writing dirty buffers
+ *--------------------------------------------------------------*/
+
+/*
+ * The endio routine for write.
+ *
+ * Set the error, clear B_WRITING bit and wake anyone who was waiting on
+ * it.
+ */
+static void write_endio(struct bio *bio, int error)
+{
+ struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
+
+ b->write_error = error;
+ if (error) {
+ struct dm_bufio_client *c = b->c;
+ (void)cmpxchg(&c->async_write_error, 0, error);
+ }
+
+ BUG_ON(!test_bit(B_WRITING, &b->state));
+
+ smp_mb__before_clear_bit();
+ clear_bit(B_WRITING, &b->state);
+ smp_mb__after_clear_bit();
+
+ wake_up_bit(&b->state, B_WRITING);
+}
+
+/*
+ * This function is called when wait_on_bit is actually waiting.
+ */
+static int do_io_schedule(void *word)
+{
+ io_schedule();
+
+ return 0;
+}
+
+/*
+ * Initiate a write on a dirty buffer, but don't wait for it.
+ *
+ * - If the buffer is not dirty, exit.
+ * - If there some previous write going on, wait for it to finish (we can't
+ * have two writes on the same buffer simultaneously).
+ * - Submit our write and don't wait on it. We set B_WRITING indicating
+ * that there is a write in progress.
+ */
+static void __write_dirty_buffer(struct dm_buffer *b)
+{
+ if (!test_bit(B_DIRTY, &b->state))
+ return;
+
+ clear_bit(B_DIRTY, &b->state);
+ wait_on_bit_lock(&b->state, B_WRITING,
+ do_io_schedule, TASK_UNINTERRUPTIBLE);
+
+ submit_io(b, WRITE, b->block, write_endio);
+}
+
+/*
+ * Wait until any activity on the buffer finishes. Possibly write the
+ * buffer if it is dirty. When this function finishes, there is no I/O
+ * running on the buffer and the buffer is not dirty.
+ */
+static void __make_buffer_clean(struct dm_buffer *b)
+{
+ BUG_ON(b->hold_count);
+
+ if (!b->state) /* fast case */
+ return;
+
+ wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE);
+ __write_dirty_buffer(b);
+ wait_on_bit(&b->state, B_WRITING, do_io_schedule, TASK_UNINTERRUPTIBLE);
+}
+
+/*
+ * Find some buffer that is not held by anybody, clean it, unlink it and
+ * return it.
+ */
+static struct dm_buffer *__get_unclaimed_buffer(struct dm_bufio_client *c)
+{
+ struct dm_buffer *b;
+
+ list_for_each_entry_reverse(b, &c->lru[LIST_CLEAN], lru_list) {
+ BUG_ON(test_bit(B_WRITING, &b->state));
+ BUG_ON(test_bit(B_DIRTY, &b->state));
+
+ if (!b->hold_count) {
+ __make_buffer_clean(b);
+ __unlink_buffer(b);
+ return b;
+ }
+ dm_bufio_cond_resched();
+ }
+
+ list_for_each_entry_reverse(b, &c->lru[LIST_DIRTY], lru_list) {
+ BUG_ON(test_bit(B_READING, &b->state));
+
+ if (!b->hold_count) {
+ __make_buffer_clean(b);
+ __unlink_buffer(b);
+ return b;
+ }
+ dm_bufio_cond_resched();
+ }
+
+ return NULL;
+}
+
+/*
+ * Wait until some other threads free some buffer or release hold count on
+ * some buffer.
+ *
+ * This function is entered with c->lock held, drops it and regains it
+ * before exiting.
+ */
+static void __wait_for_free_buffer(struct dm_bufio_client *c)
+{
+ DECLARE_WAITQUEUE(wait, current);
+
+ add_wait_queue(&c->free_buffer_wait, &wait);
+ set_task_state(current, TASK_UNINTERRUPTIBLE);
+ dm_bufio_unlock(c);
+
+ io_schedule();
+
+ set_task_state(current, TASK_RUNNING);
+ remove_wait_queue(&c->free_buffer_wait, &wait);
+
+ dm_bufio_lock(c);
+}
+
+/*
+ * Allocate a new buffer. If the allocation is not possible, wait until
+ * some other thread frees a buffer.
+ *
+ * May drop the lock and regain it.
+ */
+static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client *c)
+{
+ struct dm_buffer *b;
+
+ /*
+ * dm-bufio is resistant to allocation failures (it just keeps
+ * one buffer reserved in cases all the allocations fail).
+ * So set flags to not try too hard:
+ * GFP_NOIO: don't recurse into the I/O layer
+ * __GFP_NORETRY: don't retry and rather return failure
+ * __GFP_NOMEMALLOC: don't use emergency reserves
+ * __GFP_NOWARN: don't print a warning in case of failure
+ *
+ * For debugging, if we set the cache size to 1, no new buffers will
+ * be allocated.
+ */
+ while (1) {
+ if (dm_bufio_cache_size_latch != 1) {
+ b = alloc_buffer(c, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+ if (b)
+ return b;
+ }
+
+ if (!list_empty(&c->reserved_buffers)) {
+ b = list_entry(c->reserved_buffers.next,
+ struct dm_buffer, lru_list);
+ list_del(&b->lru_list);
+ c->need_reserved_buffers++;
+
+ return b;
+ }
+
+ b = __get_unclaimed_buffer(c);
+ if (b)
+ return b;
+
+ __wait_for_free_buffer(c);
+ }
+}
+
+static struct dm_buffer *__alloc_buffer_wait(struct dm_bufio_client *c)
+{
+ struct dm_buffer *b = __alloc_buffer_wait_no_callback(c);
+
+ if (c->alloc_callback)
+ c->alloc_callback(b);
+
+ return b;
+}
+
+/*
+ * Free a buffer and wake other threads waiting for free buffers.
+ */
+static void __free_buffer_wake(struct dm_buffer *b)
+{
+ struct dm_bufio_client *c = b->c;
+
+ if (!c->need_reserved_buffers)
+ free_buffer(b);
+ else {
+ list_add(&b->lru_list, &c->reserved_buffers);
+ c->need_reserved_buffers--;
+ }
+
+ wake_up(&c->free_buffer_wait);
+}
+
+static void __write_dirty_buffers_async(struct dm_bufio_client *c, int no_wait)
+{
+ struct dm_buffer *b, *tmp;
+
+ list_for_each_entry_safe_reverse(b, tmp, &c->lru[LIST_DIRTY], lru_list) {
+ BUG_ON(test_bit(B_READING, &b->state));
+
+ if (!test_bit(B_DIRTY, &b->state) &&
+ !test_bit(B_WRITING, &b->state)) {
+ __relink_lru(b, LIST_CLEAN);
+ continue;
+ }
+
+ if (no_wait && test_bit(B_WRITING, &b->state))
+ return;
+
+ __write_dirty_buffer(b);
+ dm_bufio_cond_resched();
+ }
+}
+
+/*
+ * Get writeback threshold and buffer limit for a given client.
+ */
+static void __get_memory_limit(struct dm_bufio_client *c,
+ unsigned long *threshold_buffers,
+ unsigned long *limit_buffers)
+{
+ unsigned long buffers;
+
+ if (dm_bufio_cache_size != dm_bufio_cache_size_latch) {
+ mutex_lock(&dm_bufio_clients_lock);
+ __cache_size_refresh();
+ mutex_unlock(&dm_bufio_clients_lock);
+ }
+
+ buffers = dm_bufio_cache_size_per_client >>
+ (c->sectors_per_block_bits + SECTOR_SHIFT);
+
+ if (buffers < DM_BUFIO_MIN_BUFFERS)
+ buffers = DM_BUFIO_MIN_BUFFERS;
+
+ *limit_buffers = buffers;
+ *threshold_buffers = buffers * DM_BUFIO_WRITEBACK_PERCENT / 100;
+}
+
+/*
+ * Check if we're over watermark.
+ * If we are over threshold_buffers, start freeing buffers.
+ * If we're over "limit_buffers", block until we get under the limit.
+ */
+static void __check_watermark(struct dm_bufio_client *c)
+{
+ unsigned long threshold_buffers, limit_buffers;
+
+ __get_memory_limit(c, &threshold_buffers, &limit_buffers);
+
+ while (c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY] >
+ limit_buffers) {
+
+ struct dm_buffer *b = __get_unclaimed_buffer(c);
+
+ if (!b)
+ return;
+
+ __free_buffer_wake(b);
+ dm_bufio_cond_resched();
+ }
+
+ if (c->n_buffers[LIST_DIRTY] > threshold_buffers)
+ __write_dirty_buffers_async(c, 1);
+}
+
+/*
+ * Find a buffer in the hash.
+ */
+static struct dm_buffer *__find(struct dm_bufio_client *c, sector_t block)
+{
+ struct dm_buffer *b;
+ struct hlist_node *hn;
+
+ hlist_for_each_entry(b, hn, &c->cache_hash[DM_BUFIO_HASH(block)],
+ hash_list) {
+ dm_bufio_cond_resched();
+ if (b->block == block)
+ return b;
+ }
+
+ return NULL;
+}
+
+/*----------------------------------------------------------------
+ * Getting a buffer
+ *--------------------------------------------------------------*/
+
+enum new_flag {
+ NF_FRESH = 0,
+ NF_READ = 1,
+ NF_GET = 2
+};
+
+static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block,
+ enum new_flag nf, struct dm_buffer **bp,
+ int *need_submit)
+{
+ struct dm_buffer *b, *new_b = NULL;
+
+ *need_submit = 0;
+
+ b = __find(c, block);
+ if (b) {
+ b->hold_count++;
+ __relink_lru(b, test_bit(B_DIRTY, &b->state) ||
+ test_bit(B_WRITING, &b->state));
+ return b;
+ }
+
+ if (nf == NF_GET)
+ return NULL;
+
+ new_b = __alloc_buffer_wait(c);
+
+ /*
+ * We've had a period where the mutex was unlocked, so need to
+ * recheck the hash table.
+ */
+ b = __find(c, block);
+ if (b) {
+ __free_buffer_wake(new_b);
+ b->hold_count++;
+ __relink_lru(b, test_bit(B_DIRTY, &b->state) ||
+ test_bit(B_WRITING, &b->state));
+ return b;
+ }
+
+ __check_watermark(c);
+
+ b = new_b;
+ b->hold_count = 1;
+ b->read_error = 0;
+ b->write_error = 0;
+ __link_buffer(b, block, LIST_CLEAN);
+
+ if (nf == NF_FRESH) {
+ b->state = 0;
+ return b;
+ }
+
+ b->state = 1 << B_READING;
+ *need_submit = 1;
+
+ return b;
+}
+
+/*
+ * The endio routine for reading: set the error, clear the bit and wake up
+ * anyone waiting on the buffer.
+ */
+static void read_endio(struct bio *bio, int error)
+{
+ struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
+
+ b->read_error = error;
+
+ BUG_ON(!test_bit(B_READING, &b->state));
+
+ smp_mb__before_clear_bit();
+ clear_bit(B_READING, &b->state);
+ smp_mb__after_clear_bit();
+
+ wake_up_bit(&b->state, B_READING);
+}
+
+/*
+ * A common routine for dm_bufio_new and dm_bufio_read. Operation of these
+ * functions is similar except that dm_bufio_new doesn't read the
+ * buffer from the disk (assuming that the caller overwrites all the data
+ * and uses dm_bufio_mark_buffer_dirty to write new data back).
+ */
+static void *new_read(struct dm_bufio_client *c, sector_t block,
+ enum new_flag nf, struct dm_buffer **bp)
+{
+ int need_submit;
+ struct dm_buffer *b;
+
+ dm_bufio_lock(c);
+ b = __bufio_new(c, block, nf, bp, &need_submit);
+ dm_bufio_unlock(c);
+
+ if (!b || IS_ERR(b))
+ return b;
+
+ if (need_submit)
+ submit_io(b, READ, b->block, read_endio);
+
+ wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE);
+
+ if (b->read_error) {
+ int error = b->read_error;
+
+ dm_bufio_release(b);
+
+ return ERR_PTR(error);
+ }
+
+ *bp = b;
+
+ return b->data;
+}
+
+void *dm_bufio_get(struct dm_bufio_client *c, sector_t block,
+ struct dm_buffer **bp)
+{
+ return new_read(c, block, NF_GET, bp);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get);
+
+void *dm_bufio_read(struct dm_bufio_client *c, sector_t block,
+ struct dm_buffer **bp)
+{
+ BUG_ON(dm_bufio_in_request());
+
+ return new_read(c, block, NF_READ, bp);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_read);
+
+void *dm_bufio_new(struct dm_bufio_client *c, sector_t block,
+ struct dm_buffer **bp)
+{
+ BUG_ON(dm_bufio_in_request());
+
+ return new_read(c, block, NF_FRESH, bp);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_new);
+
+void dm_bufio_release(struct dm_buffer *b)
+{
+ struct dm_bufio_client *c = b->c;
+
+ dm_bufio_lock(c);
+
+ BUG_ON(test_bit(B_READING, &b->state));
+ BUG_ON(!b->hold_count);
+
+ b->hold_count--;
+ if (!b->hold_count) {
+ wake_up(&c->free_buffer_wait);
+
+ /*
+ * If there were errors on the buffer, and the buffer is not
+ * to be written, free the buffer. There is no point in caching
+ * invalid buffer.
+ */
+ if ((b->read_error || b->write_error) &&
+ !test_bit(B_WRITING, &b->state) &&
+ !test_bit(B_DIRTY, &b->state)) {
+ __unlink_buffer(b);
+ __free_buffer_wake(b);
+ }
+ }
+
+ dm_bufio_unlock(c);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_release);
+
+void dm_bufio_mark_buffer_dirty(struct dm_buffer *b)
+{
+ struct dm_bufio_client *c = b->c;
+
+ dm_bufio_lock(c);
+
+ if (!test_and_set_bit(B_DIRTY, &b->state))
+ __relink_lru(b, LIST_DIRTY);
+
+ dm_bufio_unlock(c);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_mark_buffer_dirty);
+
+void dm_bufio_write_dirty_buffers_async(struct dm_bufio_client *c)
+{
+ BUG_ON(dm_bufio_in_request());
+
+ dm_bufio_lock(c);
+ __write_dirty_buffers_async(c, 0);
+ dm_bufio_unlock(c);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers_async);
+
+/*
+ * For performance, it is essential that the buffers are written asynchronously
+ * and simultaneously (so that the block layer can merge the writes) and then
+ * waited upon.
+ *
+ * Finally, we flush hardware disk cache.
+ */
+int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c)
+{
+ int a, f;
+ unsigned long buffers_processed = 0;
+ struct dm_buffer *b, *tmp;
+
+ dm_bufio_lock(c);
+ __write_dirty_buffers_async(c, 0);
+
+again:
+ list_for_each_entry_safe_reverse(b, tmp, &c->lru[LIST_DIRTY], lru_list) {
+ int dropped_lock = 0;
+
+ if (buffers_processed < c->n_buffers[LIST_DIRTY])
+ buffers_processed++;
+
+ BUG_ON(test_bit(B_READING, &b->state));
+
+ if (test_bit(B_WRITING, &b->state)) {
+ if (buffers_processed < c->n_buffers[LIST_DIRTY]) {
+ dropped_lock = 1;
+ b->hold_count++;
+ dm_bufio_unlock(c);
+ wait_on_bit(&b->state, B_WRITING,
+ do_io_schedule,
+ TASK_UNINTERRUPTIBLE);
+ dm_bufio_lock(c);
+ b->hold_count--;
+ } else
+ wait_on_bit(&b->state, B_WRITING,
+ do_io_schedule,
+ TASK_UNINTERRUPTIBLE);
+ }
+
+ if (!test_bit(B_DIRTY, &b->state) &&
+ !test_bit(B_WRITING, &b->state))
+ __relink_lru(b, LIST_CLEAN);
+
+ dm_bufio_cond_resched();
+
+ /*
+ * If we dropped the lock, the list is no longer consistent,
+ * so we must restart the search.
+ *
+ * In the most common case, the buffer just processed is
+ * relinked to the clean list, so we won't loop scanning the
+ * same buffer again and again.
+ *
+ * This may livelock if there is another thread simultaneously
+ * dirtying buffers, so we count the number of buffers walked
+ * and if it exceeds the total number of buffers, it means that
+ * someone is doing some writes simultaneously with us. In
+ * this case, stop, dropping the lock.
+ */
+ if (dropped_lock)
+ goto again;
+ }
+ wake_up(&c->free_buffer_wait);
+ dm_bufio_unlock(c);
+
+ a = xchg(&c->async_write_error, 0);
+ f = dm_bufio_issue_flush(c);
+ if (a)
+ return a;
+
+ return f;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers);
+
+/*
+ * Use dm-io to send and empty barrier flush the device.
+ */
+int dm_bufio_issue_flush(struct dm_bufio_client *c)
+{
+ struct dm_io_request io_req = {
+ .bi_rw = REQ_FLUSH,
+ .mem.type = DM_IO_KMEM,
+ .mem.ptr.addr = NULL,
+ .client = c->dm_io,
+ };
+ struct dm_io_region io_reg = {
+ .bdev = c->bdev,
+ .sector = 0,
+ .count = 0,
+ };
+
+ BUG_ON(dm_bufio_in_request());
+
+ return dm_io(&io_req, 1, &io_reg, NULL);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_issue_flush);
+
+/*
+ * We first delete any other buffer that may be at that new location.
+ *
+ * Then, we write the buffer to the original location if it was dirty.
+ *
+ * Then, if we are the only one who is holding the buffer, relink the buffer
+ * in the hash queue for the new location.
+ *
+ * If there was someone else holding the buffer, we write it to the new
+ * location but not relink it, because that other user needs to have the buffer
+ * at the same place.
+ */
+void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block)
+{
+ struct dm_bufio_client *c = b->c;
+ struct dm_buffer *new;
+
+ BUG_ON(dm_bufio_in_request());
+
+ dm_bufio_lock(c);
+
+retry:
+ new = __find(c, new_block);
+ if (new) {
+ if (new->hold_count) {
+ __wait_for_free_buffer(c);
+ goto retry;
+ }
+
+ /*
+ * FIXME: Is there any point waiting for a write that's going
+ * to be overwritten in a bit?
+ */
+ __make_buffer_clean(new);
+ __unlink_buffer(new);
+ __free_buffer_wake(new);
+ }
+
+ BUG_ON(!b->hold_count);
+ BUG_ON(test_bit(B_READING, &b->state));
+
+ __write_dirty_buffer(b);
+ if (b->hold_count == 1) {
+ wait_on_bit(&b->state, B_WRITING,
+ do_io_schedule, TASK_UNINTERRUPTIBLE);
+ set_bit(B_DIRTY, &b->state);
+ __unlink_buffer(b);
+ __link_buffer(b, new_block, LIST_DIRTY);
+ } else {
+ sector_t old_block;
+ wait_on_bit_lock(&b->state, B_WRITING,
+ do_io_schedule, TASK_UNINTERRUPTIBLE);
+ /*
+ * Relink buffer to "new_block" so that write_callback
+ * sees "new_block" as a block number.
+ * After the write, link the buffer back to old_block.
+ * All this must be done in bufio lock, so that block number
+ * change isn't visible to other threads.
+ */
+ old_block = b->block;
+ __unlink_buffer(b);
+ __link_buffer(b, new_block, b->list_mode);
+ submit_io(b, WRITE, new_block, write_endio);
+ wait_on_bit(&b->state, B_WRITING,
+ do_io_schedule, TASK_UNINTERRUPTIBLE);
+ __unlink_buffer(b);
+ __link_buffer(b, old_block, b->list_mode);
+ }
+
+ dm_bufio_unlock(c);
+ dm_bufio_release(b);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_release_move);
+
+unsigned dm_bufio_get_block_size(struct dm_bufio_client *c)
+{
+ return c->block_size;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_block_size);
+
+sector_t dm_bufio_get_device_size(struct dm_bufio_client *c)
+{
+ return i_size_read(c->bdev->bd_inode) >>
+ (SECTOR_SHIFT + c->sectors_per_block_bits);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_device_size);
+
+sector_t dm_bufio_get_block_number(struct dm_buffer *b)
+{
+ return b->block;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_block_number);
+
+void *dm_bufio_get_block_data(struct dm_buffer *b)
+{
+ return b->data;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_block_data);
+
+void *dm_bufio_get_aux_data(struct dm_buffer *b)
+{
+ return b + 1;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_aux_data);
+
+struct dm_bufio_client *dm_bufio_get_client(struct dm_buffer *b)
+{
+ return b->c;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_client);
+
+static void drop_buffers(struct dm_bufio_client *c)
+{
+ struct dm_buffer *b;
+ int i;
+
+ BUG_ON(dm_bufio_in_request());
+
+ /*
+ * An optimization so that the buffers are not written one-by-one.
+ */
+ dm_bufio_write_dirty_buffers_async(c);
+
+ dm_bufio_lock(c);
+
+ while ((b = __get_unclaimed_buffer(c)))
+ __free_buffer_wake(b);
+
+ for (i = 0; i < LIST_SIZE; i++)
+ list_for_each_entry(b, &c->lru[i], lru_list)
+ DMERR("leaked buffer %llx, hold count %u, list %d",
+ (unsigned long long)b->block, b->hold_count, i);
+
+ for (i = 0; i < LIST_SIZE; i++)
+ BUG_ON(!list_empty(&c->lru[i]));
+
+ dm_bufio_unlock(c);
+}
+
+/*
+ * Test if the buffer is unused and too old, and commit it.
+ * At if noio is set, we must not do any I/O because we hold
+ * dm_bufio_clients_lock and we would risk deadlock if the I/O gets rerouted to
+ * different bufio client.
+ */
+static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp,
+ unsigned long max_jiffies)
+{
+ if (jiffies - b->last_accessed < max_jiffies)
+ return 1;
+
+ if (!(gfp & __GFP_IO)) {
+ if (test_bit(B_READING, &b->state) ||
+ test_bit(B_WRITING, &b->state) ||
+ test_bit(B_DIRTY, &b->state))
+ return 1;
+ }
+
+ if (b->hold_count)
+ return 1;
+
+ __make_buffer_clean(b);
+ __unlink_buffer(b);
+ __free_buffer_wake(b);
+
+ return 0;
+}
+
+static void __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
+ struct shrink_control *sc)
+{
+ int l;
+ struct dm_buffer *b, *tmp;
+
+ for (l = 0; l < LIST_SIZE; l++) {
+ list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list)
+ if (!__cleanup_old_buffer(b, sc->gfp_mask, 0) &&
+ !--nr_to_scan)
+ return;
+ dm_bufio_cond_resched();
+ }
+}
+
+static int shrink(struct shrinker *shrinker, struct shrink_control *sc)
+{
+ struct dm_bufio_client *c =
+ container_of(shrinker, struct dm_bufio_client, shrinker);
+ unsigned long r;
+ unsigned long nr_to_scan = sc->nr_to_scan;
+
+ if (sc->gfp_mask & __GFP_IO)
+ dm_bufio_lock(c);
+ else if (!dm_bufio_trylock(c))
+ return !nr_to_scan ? 0 : -1;
+
+ if (nr_to_scan)
+ __scan(c, nr_to_scan, sc);
+
+ r = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
+ if (r > INT_MAX)
+ r = INT_MAX;
+
+ dm_bufio_unlock(c);
+
+ return r;
+}
+
+/*
+ * Create the buffering interface
+ */
+struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsigned block_size,
+ unsigned reserved_buffers, unsigned aux_size,
+ void (*alloc_callback)(struct dm_buffer *),
+ void (*write_callback)(struct dm_buffer *))
+{
+ int r;
+ struct dm_bufio_client *c;
+ unsigned i;
+
+ BUG_ON(block_size < 1 << SECTOR_SHIFT ||
+ (block_size & (block_size - 1)));
+
+ c = kmalloc(sizeof(*c), GFP_KERNEL);
+ if (!c) {
+ r = -ENOMEM;
+ goto bad_client;
+ }
+ c->cache_hash = vmalloc(sizeof(struct hlist_head) << DM_BUFIO_HASH_BITS);
+ if (!c->cache_hash) {
+ r = -ENOMEM;
+ goto bad_hash;
+ }
+
+ c->bdev = bdev;
+ c->block_size = block_size;
+ c->sectors_per_block_bits = ffs(block_size) - 1 - SECTOR_SHIFT;
+ c->pages_per_block_bits = (ffs(block_size) - 1 >= PAGE_SHIFT) ?
+ ffs(block_size) - 1 - PAGE_SHIFT : 0;
+ c->blocks_per_page_bits = (ffs(block_size) - 1 < PAGE_SHIFT ?
+ PAGE_SHIFT - (ffs(block_size) - 1) : 0);
+
+ c->aux_size = aux_size;
+ c->alloc_callback = alloc_callback;
+ c->write_callback = write_callback;
+
+ for (i = 0; i < LIST_SIZE; i++) {
+ INIT_LIST_HEAD(&c->lru[i]);
+ c->n_buffers[i] = 0;
+ }
+
+ for (i = 0; i < 1 << DM_BUFIO_HASH_BITS; i++)
+ INIT_HLIST_HEAD(&c->cache_hash[i]);
+
+ mutex_init(&c->lock);
+ INIT_LIST_HEAD(&c->reserved_buffers);
+ c->need_reserved_buffers = reserved_buffers;
+
+ init_waitqueue_head(&c->free_buffer_wait);
+ c->async_write_error = 0;
+
+ c->dm_io = dm_io_client_create();
+ if (IS_ERR(c->dm_io)) {
+ r = PTR_ERR(c->dm_io);
+ goto bad_dm_io;
+ }
+
+ mutex_lock(&dm_bufio_clients_lock);
+ if (c->blocks_per_page_bits) {
+ if (!DM_BUFIO_CACHE_NAME(c)) {
+ DM_BUFIO_CACHE_NAME(c) = kasprintf(GFP_KERNEL, "dm_bufio_cache-%u", c->block_size);
+ if (!DM_BUFIO_CACHE_NAME(c)) {
+ r = -ENOMEM;
+ mutex_unlock(&dm_bufio_clients_lock);
+ goto bad_cache;
+ }
+ }
+
+ if (!DM_BUFIO_CACHE(c)) {
+ DM_BUFIO_CACHE(c) = kmem_cache_create(DM_BUFIO_CACHE_NAME(c),
+ c->block_size,
+ c->block_size, 0, NULL);
+ if (!DM_BUFIO_CACHE(c)) {
+ r = -ENOMEM;
+ mutex_unlock(&dm_bufio_clients_lock);
+ goto bad_cache;
+ }
+ }
+ }
+ mutex_unlock(&dm_bufio_clients_lock);
+
+ while (c->need_reserved_buffers) {
+ struct dm_buffer *b = alloc_buffer(c, GFP_KERNEL);
+
+ if (!b) {
+ r = -ENOMEM;
+ goto bad_buffer;
+ }
+ __free_buffer_wake(b);
+ }
+
+ mutex_lock(&dm_bufio_clients_lock);
+ dm_bufio_client_count++;
+ list_add(&c->client_list, &dm_bufio_all_clients);
+ __cache_size_refresh();
+ mutex_unlock(&dm_bufio_clients_lock);
+
+ c->shrinker.shrink = shrink;
+ c->shrinker.seeks = 1;
+ c->shrinker.batch = 0;
+ register_shrinker(&c->shrinker);
+
+ return c;
+
+bad_buffer:
+bad_cache:
+ while (!list_empty(&c->reserved_buffers)) {
+ struct dm_buffer *b = list_entry(c->reserved_buffers.next,
+ struct dm_buffer, lru_list);
+ list_del(&b->lru_list);
+ free_buffer(b);
+ }
+ dm_io_client_destroy(c->dm_io);
+bad_dm_io:
+ vfree(c->cache_hash);
+bad_hash:
+ kfree(c);
+bad_client:
+ return ERR_PTR(r);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_client_create);
+
+/*
+ * Free the buffering interface.
+ * It is required that there are no references on any buffers.
+ */
+void dm_bufio_client_destroy(struct dm_bufio_client *c)
+{
+ unsigned i;
+
+ drop_buffers(c);
+
+ unregister_shrinker(&c->shrinker);
+
+ mutex_lock(&dm_bufio_clients_lock);
+
+ list_del(&c->client_list);
+ dm_bufio_client_count--;
+ __cache_size_refresh();
+
+ mutex_unlock(&dm_bufio_clients_lock);
+
+ for (i = 0; i < 1 << DM_BUFIO_HASH_BITS; i++)
+ BUG_ON(!hlist_empty(&c->cache_hash[i]));
+
+ BUG_ON(c->need_reserved_buffers);
+
+ while (!list_empty(&c->reserved_buffers)) {
+ struct dm_buffer *b = list_entry(c->reserved_buffers.next,
+ struct dm_buffer, lru_list);
+ list_del(&b->lru_list);
+ free_buffer(b);
+ }
+
+ for (i = 0; i < LIST_SIZE; i++)
+ if (c->n_buffers[i])
+ DMERR("leaked buffer count %d: %ld", i, c->n_buffers[i]);
+
+ for (i = 0; i < LIST_SIZE; i++)
+ BUG_ON(c->n_buffers[i]);
+
+ dm_io_client_destroy(c->dm_io);
+ vfree(c->cache_hash);
+ kfree(c);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_client_destroy);
+
+static void cleanup_old_buffers(void)
+{
+ unsigned long max_age = dm_bufio_max_age;
+ struct dm_bufio_client *c;
+
+ barrier();
+
+ if (max_age > ULONG_MAX / HZ)
+ max_age = ULONG_MAX / HZ;
+
+ mutex_lock(&dm_bufio_clients_lock);
+ list_for_each_entry(c, &dm_bufio_all_clients, client_list) {
+ if (!dm_bufio_trylock(c))
+ continue;
+
+ while (!list_empty(&c->lru[LIST_CLEAN])) {
+ struct dm_buffer *b;
+ b = list_entry(c->lru[LIST_CLEAN].prev,
+ struct dm_buffer, lru_list);
+ if (__cleanup_old_buffer(b, 0, max_age * HZ))
+ break;
+ dm_bufio_cond_resched();
+ }
+
+ dm_bufio_unlock(c);
+ dm_bufio_cond_resched();
+ }
+ mutex_unlock(&dm_bufio_clients_lock);
+}
+
+static struct workqueue_struct *dm_bufio_wq;
+static struct delayed_work dm_bufio_work;
+
+static void work_fn(struct work_struct *w)
+{
+ cleanup_old_buffers();
+
+ queue_delayed_work(dm_bufio_wq, &dm_bufio_work,
+ DM_BUFIO_WORK_TIMER_SECS * HZ);
+}
+
+/*----------------------------------------------------------------
+ * Module setup
+ *--------------------------------------------------------------*/
+
+/*
+ * This is called only once for the whole dm_bufio module.
+ * It initializes memory limit.
+ */
+static int __init dm_bufio_init(void)
+{
+ __u64 mem;
+
+ memset(&dm_bufio_caches, 0, sizeof dm_bufio_caches);
+ memset(&dm_bufio_cache_names, 0, sizeof dm_bufio_cache_names);
+
+ mem = (__u64)((totalram_pages - totalhigh_pages) *
+ DM_BUFIO_MEMORY_PERCENT / 100) << PAGE_SHIFT;
+
+ if (mem > ULONG_MAX)
+ mem = ULONG_MAX;
+
+#ifdef CONFIG_MMU
+ /*
+ * Get the size of vmalloc space the same way as VMALLOC_TOTAL
+ * in fs/proc/internal.h
+ */
+ if (mem > (VMALLOC_END - VMALLOC_START) * DM_BUFIO_VMALLOC_PERCENT / 100)
+ mem = (VMALLOC_END - VMALLOC_START) * DM_BUFIO_VMALLOC_PERCENT / 100;
+#endif
+
+ dm_bufio_default_cache_size = mem;
+
+ mutex_lock(&dm_bufio_clients_lock);
+ __cache_size_refresh();
+ mutex_unlock(&dm_bufio_clients_lock);
+
+ dm_bufio_wq = create_singlethread_workqueue("dm_bufio_cache");
+ if (!dm_bufio_wq)
+ return -ENOMEM;
+
+ INIT_DELAYED_WORK(&dm_bufio_work, work_fn);
+ queue_delayed_work(dm_bufio_wq, &dm_bufio_work,
+ DM_BUFIO_WORK_TIMER_SECS * HZ);
+
+ return 0;
+}
+
+/*
+ * This is called once when unloading the dm_bufio module.
+ */
+static void __exit dm_bufio_exit(void)
+{
+ int bug = 0;
+ int i;
+
+ cancel_delayed_work_sync(&dm_bufio_work);
+ destroy_workqueue(dm_bufio_wq);
+
+ for (i = 0; i < ARRAY_SIZE(dm_bufio_caches); i++) {
+ struct kmem_cache *kc = dm_bufio_caches[i];
+
+ if (kc)
+ kmem_cache_destroy(kc);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(dm_bufio_cache_names); i++)
+ kfree(dm_bufio_cache_names[i]);
+
+ if (dm_bufio_client_count) {
+ DMCRIT("%s: dm_bufio_client_count leaked: %d",
+ __func__, dm_bufio_client_count);
+ bug = 1;
+ }
+
+ if (dm_bufio_current_allocated) {
+ DMCRIT("%s: dm_bufio_current_allocated leaked: %lu",
+ __func__, dm_bufio_current_allocated);
+ bug = 1;
+ }
+
+ if (dm_bufio_allocated_get_free_pages) {
+ DMCRIT("%s: dm_bufio_allocated_get_free_pages leaked: %lu",
+ __func__, dm_bufio_allocated_get_free_pages);
+ bug = 1;
+ }
+
+ if (dm_bufio_allocated_vmalloc) {
+ DMCRIT("%s: dm_bufio_vmalloc leaked: %lu",
+ __func__, dm_bufio_allocated_vmalloc);
+ bug = 1;
+ }
+
+ if (bug)
+ BUG();
+}
+
+module_init(dm_bufio_init)
+module_exit(dm_bufio_exit)
+
+module_param_named(max_cache_size_bytes, dm_bufio_cache_size, ulong, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache");
+
+module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds");
+
+module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(peak_allocated_bytes, "Tracks the maximum allocated memory");
+
+module_param_named(allocated_kmem_cache_bytes, dm_bufio_allocated_kmem_cache, ulong, S_IRUGO);
+MODULE_PARM_DESC(allocated_kmem_cache_bytes, "Memory allocated with kmem_cache_alloc");
+
+module_param_named(allocated_get_free_pages_bytes, dm_bufio_allocated_get_free_pages, ulong, S_IRUGO);
+MODULE_PARM_DESC(allocated_get_free_pages_bytes, "Memory allocated with get_free_pages");
+
+module_param_named(allocated_vmalloc_bytes, dm_bufio_allocated_vmalloc, ulong, S_IRUGO);
+MODULE_PARM_DESC(allocated_vmalloc_bytes, "Memory allocated with vmalloc");
+
+module_param_named(current_allocated_bytes, dm_bufio_current_allocated, ulong, S_IRUGO);
+MODULE_PARM_DESC(current_allocated_bytes, "Memory currently used by the cache");
+
+MODULE_AUTHOR("Mikulas Patocka <dm-devel@redhat.com>");
+MODULE_DESCRIPTION(DM_NAME " buffered I/O library");
+MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm-bufio.h b/drivers/md/dm-bufio.h
new file mode 100644
index 0000000..5c4c3a0
--- /dev/null
+++ b/drivers/md/dm-bufio.h
@@ -0,0 +1,112 @@
+/*
+ * Copyright (C) 2009-2011 Red Hat, Inc.
+ *
+ * Author: Mikulas Patocka <mpatocka@redhat.com>
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_BUFIO_H
+#define DM_BUFIO_H
+
+#include <linux/blkdev.h>
+#include <linux/types.h>
+
+/*----------------------------------------------------------------*/
+
+struct dm_bufio_client;
+struct dm_buffer;
+
+/*
+ * Create a buffered IO cache on a given device
+ */
+struct dm_bufio_client *
+dm_bufio_client_create(struct block_device *bdev, unsigned block_size,
+ unsigned reserved_buffers, unsigned aux_size,
+ void (*alloc_callback)(struct dm_buffer *),
+ void (*write_callback)(struct dm_buffer *));
+
+/*
+ * Release a buffered IO cache.
+ */
+void dm_bufio_client_destroy(struct dm_bufio_client *c);
+
+/*
+ * WARNING: to avoid deadlocks, these conditions are observed:
+ *
+ * - At most one thread can hold at most "reserved_buffers" simultaneously.
+ * - Each other threads can hold at most one buffer.
+ * - Threads which call only dm_bufio_get can hold unlimited number of
+ * buffers.
+ */
+
+/*
+ * Read a given block from disk. Returns pointer to data. Returns a
+ * pointer to dm_buffer that can be used to release the buffer or to make
+ * it dirty.
+ */
+void *dm_bufio_read(struct dm_bufio_client *c, sector_t block,
+ struct dm_buffer **bp);
+
+/*
+ * Like dm_bufio_read, but return buffer from cache, don't read
+ * it. If the buffer is not in the cache, return NULL.
+ */
+void *dm_bufio_get(struct dm_bufio_client *c, sector_t block,
+ struct dm_buffer **bp);
+
+/*
+ * Like dm_bufio_read, but don't read anything from the disk. It is
+ * expected that the caller initializes the buffer and marks it dirty.
+ */
+void *dm_bufio_new(struct dm_bufio_client *c, sector_t block,
+ struct dm_buffer **bp);
+
+/*
+ * Release a reference obtained with dm_bufio_{read,get,new}. The data
+ * pointer and dm_buffer pointer is no longer valid after this call.
+ */
+void dm_bufio_release(struct dm_buffer *b);
+
+/*
+ * Mark a buffer dirty. It should be called after the buffer is modified.
+ *
+ * In case of memory pressure, the buffer may be written after
+ * dm_bufio_mark_buffer_dirty, but before dm_bufio_write_dirty_buffers. So
+ * dm_bufio_write_dirty_buffers guarantees that the buffer is on-disk but
+ * the actual writing may occur earlier.
+ */
+void dm_bufio_mark_buffer_dirty(struct dm_buffer *b);
+
+/*
+ * Initiate writing of dirty buffers, without waiting for completion.
+ */
+void dm_bufio_write_dirty_buffers_async(struct dm_bufio_client *c);
+
+/*
+ * Write all dirty buffers. Guarantees that all dirty buffers created prior
+ * to this call are on disk when this call exits.
+ */
+int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c);
+
+/*
+ * Send an empty write barrier to the device to flush hardware disk cache.
+ */
+int dm_bufio_issue_flush(struct dm_bufio_client *c);
+
+/*
+ * Like dm_bufio_release but also move the buffer to the new
+ * block. dm_bufio_write_dirty_buffers is needed to commit the new block.
+ */
+void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block);
+
+unsigned dm_bufio_get_block_size(struct dm_bufio_client *c);
+sector_t dm_bufio_get_device_size(struct dm_bufio_client *c);
+sector_t dm_bufio_get_block_number(struct dm_buffer *b);
+void *dm_bufio_get_block_data(struct dm_buffer *b);
+void *dm_bufio_get_aux_data(struct dm_buffer *b);
+struct dm_bufio_client *dm_bufio_get_client(struct dm_buffer *b);
+
+/*----------------------------------------------------------------*/
+
+#endif
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 2e9a3ca..31c2dc2 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1215,6 +1215,7 @@
struct hash_cell *hc;
struct dm_table *t;
struct mapped_device *md;
+ struct target_type *immutable_target_type;
md = find_device(param);
if (!md)
@@ -1230,6 +1231,16 @@
goto out;
}
+ immutable_target_type = dm_get_immutable_target_type(md);
+ if (immutable_target_type &&
+ (immutable_target_type != dm_table_get_immutable_target_type(t))) {
+ DMWARN("can't replace immutable target type %s",
+ immutable_target_type->name);
+ dm_table_destroy(t);
+ r = -EINVAL;
+ goto out;
+ }
+
/* Protect md->type and md->queue against concurrent table loads. */
dm_lock_md_type(md);
if (dm_get_md_type(md) == DM_TYPE_NONE)
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 32ac708..bed444c 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -66,6 +66,8 @@
struct list_head pages_jobs;
};
+static struct page_list zero_page_list;
+
static void wake(struct dm_kcopyd_client *kc)
{
queue_work(kc->kcopyd_wq, &kc->kcopyd_work);
@@ -254,6 +256,9 @@
if (!_job_cache)
return -ENOMEM;
+ zero_page_list.next = &zero_page_list;
+ zero_page_list.page = ZERO_PAGE(0);
+
return 0;
}
@@ -322,7 +327,7 @@
dm_kcopyd_notify_fn fn = job->fn;
struct dm_kcopyd_client *kc = job->kc;
- if (job->pages)
+ if (job->pages && job->pages != &zero_page_list)
kcopyd_put_pages(kc, job->pages);
/*
* If this is the master job, the sub jobs have already
@@ -484,6 +489,8 @@
atomic_inc(&kc->nr_jobs);
if (unlikely(!job->source.count))
push(&kc->complete_jobs, job);
+ else if (job->pages == &zero_page_list)
+ push(&kc->io_jobs, job);
else
push(&kc->pages_jobs, job);
wake(kc);
@@ -592,14 +599,20 @@
job->flags = flags;
job->read_err = 0;
job->write_err = 0;
- job->rw = READ;
-
- job->source = *from;
job->num_dests = num_dests;
memcpy(&job->dests, dests, sizeof(*dests) * num_dests);
- job->pages = NULL;
+ if (from) {
+ job->source = *from;
+ job->pages = NULL;
+ job->rw = READ;
+ } else {
+ memset(&job->source, 0, sizeof job->source);
+ job->source.count = job->dests[0].count;
+ job->pages = &zero_page_list;
+ job->rw = WRITE;
+ }
job->fn = fn;
job->context = context;
@@ -617,6 +630,14 @@
}
EXPORT_SYMBOL(dm_kcopyd_copy);
+int dm_kcopyd_zero(struct dm_kcopyd_client *kc,
+ unsigned num_dests, struct dm_io_region *dests,
+ unsigned flags, dm_kcopyd_notify_fn fn, void *context)
+{
+ return dm_kcopyd_copy(kc, NULL, num_dests, dests, flags, fn, context);
+}
+EXPORT_SYMBOL(dm_kcopyd_zero);
+
void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc,
dm_kcopyd_notify_fn fn, void *context)
{
diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c
index 1021c89..8db3862 100644
--- a/drivers/md/dm-log-userspace-base.c
+++ b/drivers/md/dm-log-userspace-base.c
@@ -30,6 +30,7 @@
struct log_c {
struct dm_target *ti;
+ struct dm_dev *log_dev;
uint32_t region_size;
region_t region_count;
uint64_t luid;
@@ -146,7 +147,7 @@
* <UUID> <other args>
* Where 'other args' is the userspace implementation specific log
* arguments. An example might be:
- * <UUID> clustered_disk <arg count> <log dev> <region_size> [[no]sync]
+ * <UUID> clustered-disk <arg count> <log dev> <region_size> [[no]sync]
*
* So, this module will strip off the <UUID> for identification purposes
* when communicating with userspace about a log; but will pass on everything
@@ -161,13 +162,15 @@
struct log_c *lc = NULL;
uint64_t rdata;
size_t rdata_size = sizeof(rdata);
+ char *devices_rdata = NULL;
+ size_t devices_rdata_size = DM_NAME_LEN;
if (argc < 3) {
DMWARN("Too few arguments to userspace dirty log");
return -EINVAL;
}
- lc = kmalloc(sizeof(*lc), GFP_KERNEL);
+ lc = kzalloc(sizeof(*lc), GFP_KERNEL);
if (!lc) {
DMWARN("Unable to allocate userspace log context.");
return -ENOMEM;
@@ -195,9 +198,19 @@
return str_size;
}
- /* Send table string */
+ devices_rdata = kzalloc(devices_rdata_size, GFP_KERNEL);
+ if (!devices_rdata) {
+ DMERR("Failed to allocate memory for device information");
+ r = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * Send table string and get back any opened device.
+ */
r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR,
- ctr_str, str_size, NULL, NULL);
+ ctr_str, str_size,
+ devices_rdata, &devices_rdata_size);
if (r < 0) {
if (r == -ESRCH)
@@ -220,7 +233,20 @@
lc->region_size = (uint32_t)rdata;
lc->region_count = dm_sector_div_up(ti->len, lc->region_size);
+ if (devices_rdata_size) {
+ if (devices_rdata[devices_rdata_size - 1] != '\0') {
+ DMERR("DM_ULOG_CTR device return string not properly terminated");
+ r = -EINVAL;
+ goto out;
+ }
+ r = dm_get_device(ti, devices_rdata,
+ dm_table_get_mode(ti->table), &lc->log_dev);
+ if (r)
+ DMERR("Failed to register %s with device-mapper",
+ devices_rdata);
+ }
out:
+ kfree(devices_rdata);
if (r) {
kfree(lc);
kfree(ctr_str);
@@ -241,6 +267,9 @@
NULL, 0,
NULL, NULL);
+ if (lc->log_dev)
+ dm_put_device(lc->ti, lc->log_dev);
+
kfree(lc->usr_argv_str);
kfree(lc);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 37a3726..11fa96d 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1017,30 +1017,56 @@
struct raid_set *rs = ti->private;
unsigned raid_param_cnt = 1; /* at least 1 for chunksize */
unsigned sz = 0;
- int i;
+ int i, array_in_sync = 0;
sector_t sync;
switch (type) {
case STATUSTYPE_INFO:
DMEMIT("%s %d ", rs->raid_type->name, rs->md.raid_disks);
- for (i = 0; i < rs->md.raid_disks; i++) {
- if (test_bit(Faulty, &rs->dev[i].rdev.flags))
- DMEMIT("D");
- else if (test_bit(In_sync, &rs->dev[i].rdev.flags))
- DMEMIT("A");
- else
- DMEMIT("a");
- }
-
if (test_bit(MD_RECOVERY_RUNNING, &rs->md.recovery))
sync = rs->md.curr_resync_completed;
else
sync = rs->md.recovery_cp;
- if (sync > rs->md.resync_max_sectors)
+ if (sync >= rs->md.resync_max_sectors) {
+ array_in_sync = 1;
sync = rs->md.resync_max_sectors;
+ } else {
+ /*
+ * The array may be doing an initial sync, or it may
+ * be rebuilding individual components. If all the
+ * devices are In_sync, then it is the array that is
+ * being initialized.
+ */
+ for (i = 0; i < rs->md.raid_disks; i++)
+ if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
+ array_in_sync = 1;
+ }
+ /*
+ * Status characters:
+ * 'D' = Dead/Failed device
+ * 'a' = Alive but not in-sync
+ * 'A' = Alive and in-sync
+ */
+ for (i = 0; i < rs->md.raid_disks; i++) {
+ if (test_bit(Faulty, &rs->dev[i].rdev.flags))
+ DMEMIT("D");
+ else if (!array_in_sync ||
+ !test_bit(In_sync, &rs->dev[i].rdev.flags))
+ DMEMIT("a");
+ else
+ DMEMIT("A");
+ }
+ /*
+ * In-sync ratio:
+ * The in-sync ratio shows the progress of:
+ * - Initializing the array
+ * - Rebuilding a subset of devices of the array
+ * The user can distinguish between the two by referring
+ * to the status characters.
+ */
DMEMIT(" %llu/%llu",
(unsigned long long) sync,
(unsigned long long) rs->md.resync_max_sectors);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index bc04518..8e91321 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -54,7 +54,9 @@
sector_t *highs;
struct dm_target *targets;
+ struct target_type *immutable_target_type;
unsigned integrity_supported:1;
+ unsigned singleton:1;
/*
* Indicates the rw permissions for the new logical
@@ -740,6 +742,12 @@
char **argv;
struct dm_target *tgt;
+ if (t->singleton) {
+ DMERR("%s: target type %s must appear alone in table",
+ dm_device_name(t->md), t->targets->type->name);
+ return -EINVAL;
+ }
+
if ((r = check_space(t)))
return r;
@@ -758,6 +766,36 @@
return -EINVAL;
}
+ if (dm_target_needs_singleton(tgt->type)) {
+ if (t->num_targets) {
+ DMERR("%s: target type %s must appear alone in table",
+ dm_device_name(t->md), type);
+ return -EINVAL;
+ }
+ t->singleton = 1;
+ }
+
+ if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) {
+ DMERR("%s: target type %s may not be included in read-only tables",
+ dm_device_name(t->md), type);
+ return -EINVAL;
+ }
+
+ if (t->immutable_target_type) {
+ if (t->immutable_target_type != tgt->type) {
+ DMERR("%s: immutable target type %s cannot be mixed with other target types",
+ dm_device_name(t->md), t->immutable_target_type->name);
+ return -EINVAL;
+ }
+ } else if (dm_target_is_immutable(tgt->type)) {
+ if (t->num_targets) {
+ DMERR("%s: immutable target type %s cannot be mixed with other target types",
+ dm_device_name(t->md), tgt->type->name);
+ return -EINVAL;
+ }
+ t->immutable_target_type = tgt->type;
+ }
+
tgt->table = t;
tgt->begin = start;
tgt->len = len;
@@ -915,6 +953,11 @@
return t->type;
}
+struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
+{
+ return t->immutable_target_type;
+}
+
bool dm_table_request_based(struct dm_table *t)
{
return dm_table_get_type(t) == DM_TYPE_REQUEST_BASED;
@@ -1299,6 +1342,31 @@
return 1;
}
+static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+
+ return q && blk_queue_nonrot(q);
+}
+
+static bool dm_table_is_nonrot(struct dm_table *t)
+{
+ struct dm_target *ti;
+ unsigned i = 0;
+
+ /* Ensure that all underlying device are non-rotational. */
+ while (i < dm_table_get_num_targets(t)) {
+ ti = dm_table_get_target(t, i++);
+
+ if (!ti->type->iterate_devices ||
+ !ti->type->iterate_devices(ti, device_is_nonrot, NULL))
+ return 0;
+ }
+
+ return 1;
+}
+
void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
struct queue_limits *limits)
{
@@ -1324,6 +1392,11 @@
if (!dm_table_discard_zeroes_data(t))
q->limits.discard_zeroes_data = 0;
+ if (dm_table_is_nonrot(t))
+ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+ else
+ queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, q);
+
dm_table_set_integrity(t);
/*
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
new file mode 100644
index 0000000..59c4f04
--- /dev/null
+++ b/drivers/md/dm-thin-metadata.c
@@ -0,0 +1,1391 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-thin-metadata.h"
+#include "persistent-data/dm-btree.h"
+#include "persistent-data/dm-space-map.h"
+#include "persistent-data/dm-space-map-disk.h"
+#include "persistent-data/dm-transaction-manager.h"
+
+#include <linux/list.h>
+#include <linux/device-mapper.h>
+#include <linux/workqueue.h>
+
+/*--------------------------------------------------------------------------
+ * As far as the metadata goes, there is:
+ *
+ * - A superblock in block zero, taking up fewer than 512 bytes for
+ * atomic writes.
+ *
+ * - A space map managing the metadata blocks.
+ *
+ * - A space map managing the data blocks.
+ *
+ * - A btree mapping our internal thin dev ids onto struct disk_device_details.
+ *
+ * - A hierarchical btree, with 2 levels which effectively maps (thin
+ * dev id, virtual block) -> block_time. Block time is a 64-bit
+ * field holding the time in the low 24 bits, and block in the top 48
+ * bits.
+ *
+ * BTrees consist solely of btree_nodes, that fill a block. Some are
+ * internal nodes, as such their values are a __le64 pointing to other
+ * nodes. Leaf nodes can store data of any reasonable size (ie. much
+ * smaller than the block size). The nodes consist of the header,
+ * followed by an array of keys, followed by an array of values. We have
+ * to binary search on the keys so they're all held together to help the
+ * cpu cache.
+ *
+ * Space maps have 2 btrees:
+ *
+ * - One maps a uint64_t onto a struct index_entry. Which points to a
+ * bitmap block, and has some details about how many free entries there
+ * are etc.
+ *
+ * - The bitmap blocks have a header (for the checksum). Then the rest
+ * of the block is pairs of bits. With the meaning being:
+ *
+ * 0 - ref count is 0
+ * 1 - ref count is 1
+ * 2 - ref count is 2
+ * 3 - ref count is higher than 2
+ *
+ * - If the count is higher than 2 then the ref count is entered in a
+ * second btree that directly maps the block_address to a uint32_t ref
+ * count.
+ *
+ * The space map metadata variant doesn't have a bitmaps btree. Instead
+ * it has one single blocks worth of index_entries. This avoids
+ * recursive issues with the bitmap btree needing to allocate space in
+ * order to insert. With a small data block size such as 64k the
+ * metadata support data devices that are hundreds of terrabytes.
+ *
+ * The space maps allocate space linearly from front to back. Space that
+ * is freed in a transaction is never recycled within that transaction.
+ * To try and avoid fragmenting _free_ space the allocator always goes
+ * back and fills in gaps.
+ *
+ * All metadata io is in THIN_METADATA_BLOCK_SIZE sized/aligned chunks
+ * from the block manager.
+ *--------------------------------------------------------------------------*/
+
+#define DM_MSG_PREFIX "thin metadata"
+
+#define THIN_SUPERBLOCK_MAGIC 27022010
+#define THIN_SUPERBLOCK_LOCATION 0
+#define THIN_VERSION 1
+#define THIN_METADATA_CACHE_SIZE 64
+#define SECTOR_TO_BLOCK_SHIFT 3
+
+/* This should be plenty */
+#define SPACE_MAP_ROOT_SIZE 128
+
+/*
+ * Little endian on-disk superblock and device details.
+ */
+struct thin_disk_superblock {
+ __le32 csum; /* Checksum of superblock except for this field. */
+ __le32 flags;
+ __le64 blocknr; /* This block number, dm_block_t. */
+
+ __u8 uuid[16];
+ __le64 magic;
+ __le32 version;
+ __le32 time;
+
+ __le64 trans_id;
+
+ /*
+ * Root held by userspace transactions.
+ */
+ __le64 held_root;
+
+ __u8 data_space_map_root[SPACE_MAP_ROOT_SIZE];
+ __u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
+
+ /*
+ * 2-level btree mapping (dev_id, (dev block, time)) -> data block
+ */
+ __le64 data_mapping_root;
+
+ /*
+ * Device detail root mapping dev_id -> device_details
+ */
+ __le64 device_details_root;
+
+ __le32 data_block_size; /* In 512-byte sectors. */
+
+ __le32 metadata_block_size; /* In 512-byte sectors. */
+ __le64 metadata_nr_blocks;
+
+ __le32 compat_flags;
+ __le32 compat_ro_flags;
+ __le32 incompat_flags;
+} __packed;
+
+struct disk_device_details {
+ __le64 mapped_blocks;
+ __le64 transaction_id; /* When created. */
+ __le32 creation_time;
+ __le32 snapshotted_time;
+} __packed;
+
+struct dm_pool_metadata {
+ struct hlist_node hash;
+
+ struct block_device *bdev;
+ struct dm_block_manager *bm;
+ struct dm_space_map *metadata_sm;
+ struct dm_space_map *data_sm;
+ struct dm_transaction_manager *tm;
+ struct dm_transaction_manager *nb_tm;
+
+ /*
+ * Two-level btree.
+ * First level holds thin_dev_t.
+ * Second level holds mappings.
+ */
+ struct dm_btree_info info;
+
+ /*
+ * Non-blocking version of the above.
+ */
+ struct dm_btree_info nb_info;
+
+ /*
+ * Just the top level for deleting whole devices.
+ */
+ struct dm_btree_info tl_info;
+
+ /*
+ * Just the bottom level for creating new devices.
+ */
+ struct dm_btree_info bl_info;
+
+ /*
+ * Describes the device details btree.
+ */
+ struct dm_btree_info details_info;
+
+ struct rw_semaphore root_lock;
+ uint32_t time;
+ int need_commit;
+ dm_block_t root;
+ dm_block_t details_root;
+ struct list_head thin_devices;
+ uint64_t trans_id;
+ unsigned long flags;
+ sector_t data_block_size;
+};
+
+struct dm_thin_device {
+ struct list_head list;
+ struct dm_pool_metadata *pmd;
+ dm_thin_id id;
+
+ int open_count;
+ int changed;
+ uint64_t mapped_blocks;
+ uint64_t transaction_id;
+ uint32_t creation_time;
+ uint32_t snapshotted_time;
+};
+
+/*----------------------------------------------------------------
+ * superblock validator
+ *--------------------------------------------------------------*/
+
+#define SUPERBLOCK_CSUM_XOR 160774
+
+static void sb_prepare_for_write(struct dm_block_validator *v,
+ struct dm_block *b,
+ size_t block_size)
+{
+ struct thin_disk_superblock *disk_super = dm_block_data(b);
+
+ disk_super->blocknr = cpu_to_le64(dm_block_location(b));
+ disk_super->csum = cpu_to_le32(dm_bm_checksum(&disk_super->flags,
+ block_size - sizeof(__le32),
+ SUPERBLOCK_CSUM_XOR));
+}
+
+static int sb_check(struct dm_block_validator *v,
+ struct dm_block *b,
+ size_t block_size)
+{
+ struct thin_disk_superblock *disk_super = dm_block_data(b);
+ __le32 csum_le;
+
+ if (dm_block_location(b) != le64_to_cpu(disk_super->blocknr)) {
+ DMERR("sb_check failed: blocknr %llu: "
+ "wanted %llu", le64_to_cpu(disk_super->blocknr),
+ (unsigned long long)dm_block_location(b));
+ return -ENOTBLK;
+ }
+
+ if (le64_to_cpu(disk_super->magic) != THIN_SUPERBLOCK_MAGIC) {
+ DMERR("sb_check failed: magic %llu: "
+ "wanted %llu", le64_to_cpu(disk_super->magic),
+ (unsigned long long)THIN_SUPERBLOCK_MAGIC);
+ return -EILSEQ;
+ }
+
+ csum_le = cpu_to_le32(dm_bm_checksum(&disk_super->flags,
+ block_size - sizeof(__le32),
+ SUPERBLOCK_CSUM_XOR));
+ if (csum_le != disk_super->csum) {
+ DMERR("sb_check failed: csum %u: wanted %u",
+ le32_to_cpu(csum_le), le32_to_cpu(disk_super->csum));
+ return -EILSEQ;
+ }
+
+ return 0;
+}
+
+static struct dm_block_validator sb_validator = {
+ .name = "superblock",
+ .prepare_for_write = sb_prepare_for_write,
+ .check = sb_check
+};
+
+/*----------------------------------------------------------------
+ * Methods for the btree value types
+ *--------------------------------------------------------------*/
+
+static uint64_t pack_block_time(dm_block_t b, uint32_t t)
+{
+ return (b << 24) | t;
+}
+
+static void unpack_block_time(uint64_t v, dm_block_t *b, uint32_t *t)
+{
+ *b = v >> 24;
+ *t = v & ((1 << 24) - 1);
+}
+
+static void data_block_inc(void *context, void *value_le)
+{
+ struct dm_space_map *sm = context;
+ __le64 v_le;
+ uint64_t b;
+ uint32_t t;
+
+ memcpy(&v_le, value_le, sizeof(v_le));
+ unpack_block_time(le64_to_cpu(v_le), &b, &t);
+ dm_sm_inc_block(sm, b);
+}
+
+static void data_block_dec(void *context, void *value_le)
+{
+ struct dm_space_map *sm = context;
+ __le64 v_le;
+ uint64_t b;
+ uint32_t t;
+
+ memcpy(&v_le, value_le, sizeof(v_le));
+ unpack_block_time(le64_to_cpu(v_le), &b, &t);
+ dm_sm_dec_block(sm, b);
+}
+
+static int data_block_equal(void *context, void *value1_le, void *value2_le)
+{
+ __le64 v1_le, v2_le;
+ uint64_t b1, b2;
+ uint32_t t;
+
+ memcpy(&v1_le, value1_le, sizeof(v1_le));
+ memcpy(&v2_le, value2_le, sizeof(v2_le));
+ unpack_block_time(le64_to_cpu(v1_le), &b1, &t);
+ unpack_block_time(le64_to_cpu(v2_le), &b2, &t);
+
+ return b1 == b2;
+}
+
+static void subtree_inc(void *context, void *value)
+{
+ struct dm_btree_info *info = context;
+ __le64 root_le;
+ uint64_t root;
+
+ memcpy(&root_le, value, sizeof(root_le));
+ root = le64_to_cpu(root_le);
+ dm_tm_inc(info->tm, root);
+}
+
+static void subtree_dec(void *context, void *value)
+{
+ struct dm_btree_info *info = context;
+ __le64 root_le;
+ uint64_t root;
+
+ memcpy(&root_le, value, sizeof(root_le));
+ root = le64_to_cpu(root_le);
+ if (dm_btree_del(info, root))
+ DMERR("btree delete failed\n");
+}
+
+static int subtree_equal(void *context, void *value1_le, void *value2_le)
+{
+ __le64 v1_le, v2_le;
+ memcpy(&v1_le, value1_le, sizeof(v1_le));
+ memcpy(&v2_le, value2_le, sizeof(v2_le));
+
+ return v1_le == v2_le;
+}
+
+/*----------------------------------------------------------------*/
+
+static int superblock_all_zeroes(struct dm_block_manager *bm, int *result)
+{
+ int r;
+ unsigned i;
+ struct dm_block *b;
+ __le64 *data_le, zero = cpu_to_le64(0);
+ unsigned block_size = dm_bm_block_size(bm) / sizeof(__le64);
+
+ /*
+ * We can't use a validator here - it may be all zeroes.
+ */
+ r = dm_bm_read_lock(bm, THIN_SUPERBLOCK_LOCATION, NULL, &b);
+ if (r)
+ return r;
+
+ data_le = dm_block_data(b);
+ *result = 1;
+ for (i = 0; i < block_size; i++) {
+ if (data_le[i] != zero) {
+ *result = 0;
+ break;
+ }
+ }
+
+ return dm_bm_unlock(b);
+}
+
+static int init_pmd(struct dm_pool_metadata *pmd,
+ struct dm_block_manager *bm,
+ dm_block_t nr_blocks, int create)
+{
+ int r;
+ struct dm_space_map *sm, *data_sm;
+ struct dm_transaction_manager *tm;
+ struct dm_block *sblock;
+
+ if (create) {
+ r = dm_tm_create_with_sm(bm, THIN_SUPERBLOCK_LOCATION,
+ &sb_validator, &tm, &sm, &sblock);
+ if (r < 0) {
+ DMERR("tm_create_with_sm failed");
+ return r;
+ }
+
+ data_sm = dm_sm_disk_create(tm, nr_blocks);
+ if (IS_ERR(data_sm)) {
+ DMERR("sm_disk_create failed");
+ r = PTR_ERR(data_sm);
+ goto bad;
+ }
+ } else {
+ struct thin_disk_superblock *disk_super = NULL;
+ size_t space_map_root_offset =
+ offsetof(struct thin_disk_superblock, metadata_space_map_root);
+
+ r = dm_tm_open_with_sm(bm, THIN_SUPERBLOCK_LOCATION,
+ &sb_validator, space_map_root_offset,
+ SPACE_MAP_ROOT_SIZE, &tm, &sm, &sblock);
+ if (r < 0) {
+ DMERR("tm_open_with_sm failed");
+ return r;
+ }
+
+ disk_super = dm_block_data(sblock);
+ data_sm = dm_sm_disk_open(tm, disk_super->data_space_map_root,
+ sizeof(disk_super->data_space_map_root));
+ if (IS_ERR(data_sm)) {
+ DMERR("sm_disk_open failed");
+ r = PTR_ERR(data_sm);
+ goto bad;
+ }
+ }
+
+
+ r = dm_tm_unlock(tm, sblock);
+ if (r < 0) {
+ DMERR("couldn't unlock superblock");
+ goto bad_data_sm;
+ }
+
+ pmd->bm = bm;
+ pmd->metadata_sm = sm;
+ pmd->data_sm = data_sm;
+ pmd->tm = tm;
+ pmd->nb_tm = dm_tm_create_non_blocking_clone(tm);
+ if (!pmd->nb_tm) {
+ DMERR("could not create clone tm");
+ r = -ENOMEM;
+ goto bad_data_sm;
+ }
+
+ pmd->info.tm = tm;
+ pmd->info.levels = 2;
+ pmd->info.value_type.context = pmd->data_sm;
+ pmd->info.value_type.size = sizeof(__le64);
+ pmd->info.value_type.inc = data_block_inc;
+ pmd->info.value_type.dec = data_block_dec;
+ pmd->info.value_type.equal = data_block_equal;
+
+ memcpy(&pmd->nb_info, &pmd->info, sizeof(pmd->nb_info));
+ pmd->nb_info.tm = pmd->nb_tm;
+
+ pmd->tl_info.tm = tm;
+ pmd->tl_info.levels = 1;
+ pmd->tl_info.value_type.context = &pmd->info;
+ pmd->tl_info.value_type.size = sizeof(__le64);
+ pmd->tl_info.value_type.inc = subtree_inc;
+ pmd->tl_info.value_type.dec = subtree_dec;
+ pmd->tl_info.value_type.equal = subtree_equal;
+
+ pmd->bl_info.tm = tm;
+ pmd->bl_info.levels = 1;
+ pmd->bl_info.value_type.context = pmd->data_sm;
+ pmd->bl_info.value_type.size = sizeof(__le64);
+ pmd->bl_info.value_type.inc = data_block_inc;
+ pmd->bl_info.value_type.dec = data_block_dec;
+ pmd->bl_info.value_type.equal = data_block_equal;
+
+ pmd->details_info.tm = tm;
+ pmd->details_info.levels = 1;
+ pmd->details_info.value_type.context = NULL;
+ pmd->details_info.value_type.size = sizeof(struct disk_device_details);
+ pmd->details_info.value_type.inc = NULL;
+ pmd->details_info.value_type.dec = NULL;
+ pmd->details_info.value_type.equal = NULL;
+
+ pmd->root = 0;
+
+ init_rwsem(&pmd->root_lock);
+ pmd->time = 0;
+ pmd->need_commit = 0;
+ pmd->details_root = 0;
+ pmd->trans_id = 0;
+ pmd->flags = 0;
+ INIT_LIST_HEAD(&pmd->thin_devices);
+
+ return 0;
+
+bad_data_sm:
+ dm_sm_destroy(data_sm);
+bad:
+ dm_tm_destroy(tm);
+ dm_sm_destroy(sm);
+
+ return r;
+}
+
+static int __begin_transaction(struct dm_pool_metadata *pmd)
+{
+ int r;
+ u32 features;
+ struct thin_disk_superblock *disk_super;
+ struct dm_block *sblock;
+
+ /*
+ * __maybe_commit_transaction() resets these
+ */
+ WARN_ON(pmd->need_commit);
+
+ /*
+ * We re-read the superblock every time. Shouldn't need to do this
+ * really.
+ */
+ r = dm_bm_read_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION,
+ &sb_validator, &sblock);
+ if (r)
+ return r;
+
+ disk_super = dm_block_data(sblock);
+ pmd->time = le32_to_cpu(disk_super->time);
+ pmd->root = le64_to_cpu(disk_super->data_mapping_root);
+ pmd->details_root = le64_to_cpu(disk_super->device_details_root);
+ pmd->trans_id = le64_to_cpu(disk_super->trans_id);
+ pmd->flags = le32_to_cpu(disk_super->flags);
+ pmd->data_block_size = le32_to_cpu(disk_super->data_block_size);
+
+ features = le32_to_cpu(disk_super->incompat_flags) & ~THIN_FEATURE_INCOMPAT_SUPP;
+ if (features) {
+ DMERR("could not access metadata due to "
+ "unsupported optional features (%lx).",
+ (unsigned long)features);
+ r = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Check for read-only metadata to skip the following RDWR checks.
+ */
+ if (get_disk_ro(pmd->bdev->bd_disk))
+ goto out;
+
+ features = le32_to_cpu(disk_super->compat_ro_flags) & ~THIN_FEATURE_COMPAT_RO_SUPP;
+ if (features) {
+ DMERR("could not access metadata RDWR due to "
+ "unsupported optional features (%lx).",
+ (unsigned long)features);
+ r = -EINVAL;
+ }
+
+out:
+ dm_bm_unlock(sblock);
+ return r;
+}
+
+static int __write_changed_details(struct dm_pool_metadata *pmd)
+{
+ int r;
+ struct dm_thin_device *td, *tmp;
+ struct disk_device_details details;
+ uint64_t key;
+
+ list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
+ if (!td->changed)
+ continue;
+
+ key = td->id;
+
+ details.mapped_blocks = cpu_to_le64(td->mapped_blocks);
+ details.transaction_id = cpu_to_le64(td->transaction_id);
+ details.creation_time = cpu_to_le32(td->creation_time);
+ details.snapshotted_time = cpu_to_le32(td->snapshotted_time);
+ __dm_bless_for_disk(&details);
+
+ r = dm_btree_insert(&pmd->details_info, pmd->details_root,
+ &key, &details, &pmd->details_root);
+ if (r)
+ return r;
+
+ if (td->open_count)
+ td->changed = 0;
+ else {
+ list_del(&td->list);
+ kfree(td);
+ }
+
+ pmd->need_commit = 1;
+ }
+
+ return 0;
+}
+
+static int __commit_transaction(struct dm_pool_metadata *pmd)
+{
+ /*
+ * FIXME: Associated pool should be made read-only on failure.
+ */
+ int r;
+ size_t metadata_len, data_len;
+ struct thin_disk_superblock *disk_super;
+ struct dm_block *sblock;
+
+ /*
+ * We need to know if the thin_disk_superblock exceeds a 512-byte sector.
+ */
+ BUILD_BUG_ON(sizeof(struct thin_disk_superblock) > 512);
+
+ r = __write_changed_details(pmd);
+ if (r < 0)
+ goto out;
+
+ if (!pmd->need_commit)
+ goto out;
+
+ r = dm_sm_commit(pmd->data_sm);
+ if (r < 0)
+ goto out;
+
+ r = dm_tm_pre_commit(pmd->tm);
+ if (r < 0)
+ goto out;
+
+ r = dm_sm_root_size(pmd->metadata_sm, &metadata_len);
+ if (r < 0)
+ goto out;
+
+ r = dm_sm_root_size(pmd->metadata_sm, &data_len);
+ if (r < 0)
+ goto out;
+
+ r = dm_bm_write_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION,
+ &sb_validator, &sblock);
+ if (r)
+ goto out;
+
+ disk_super = dm_block_data(sblock);
+ disk_super->time = cpu_to_le32(pmd->time);
+ disk_super->data_mapping_root = cpu_to_le64(pmd->root);
+ disk_super->device_details_root = cpu_to_le64(pmd->details_root);
+ disk_super->trans_id = cpu_to_le64(pmd->trans_id);
+ disk_super->flags = cpu_to_le32(pmd->flags);
+
+ r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root,
+ metadata_len);
+ if (r < 0)
+ goto out_locked;
+
+ r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root,
+ data_len);
+ if (r < 0)
+ goto out_locked;
+
+ r = dm_tm_commit(pmd->tm, sblock);
+ if (!r)
+ pmd->need_commit = 0;
+
+out:
+ return r;
+
+out_locked:
+ dm_bm_unlock(sblock);
+ return r;
+}
+
+struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
+ sector_t data_block_size)
+{
+ int r;
+ struct thin_disk_superblock *disk_super;
+ struct dm_pool_metadata *pmd;
+ sector_t bdev_size = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+ struct dm_block_manager *bm;
+ int create;
+ struct dm_block *sblock;
+
+ pmd = kmalloc(sizeof(*pmd), GFP_KERNEL);
+ if (!pmd) {
+ DMERR("could not allocate metadata struct");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ /*
+ * Max hex locks:
+ * 3 for btree insert +
+ * 2 for btree lookup used within space map
+ */
+ bm = dm_block_manager_create(bdev, THIN_METADATA_BLOCK_SIZE,
+ THIN_METADATA_CACHE_SIZE, 5);
+ if (!bm) {
+ DMERR("could not create block manager");
+ kfree(pmd);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ r = superblock_all_zeroes(bm, &create);
+ if (r) {
+ dm_block_manager_destroy(bm);
+ kfree(pmd);
+ return ERR_PTR(r);
+ }
+
+
+ r = init_pmd(pmd, bm, 0, create);
+ if (r) {
+ dm_block_manager_destroy(bm);
+ kfree(pmd);
+ return ERR_PTR(r);
+ }
+ pmd->bdev = bdev;
+
+ if (!create) {
+ r = __begin_transaction(pmd);
+ if (r < 0)
+ goto bad;
+ return pmd;
+ }
+
+ /*
+ * Create.
+ */
+ r = dm_bm_write_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION,
+ &sb_validator, &sblock);
+ if (r)
+ goto bad;
+
+ disk_super = dm_block_data(sblock);
+ disk_super->magic = cpu_to_le64(THIN_SUPERBLOCK_MAGIC);
+ disk_super->version = cpu_to_le32(THIN_VERSION);
+ disk_super->time = 0;
+ disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+ disk_super->metadata_nr_blocks = cpu_to_le64(bdev_size >> SECTOR_TO_BLOCK_SHIFT);
+ disk_super->data_block_size = cpu_to_le32(data_block_size);
+
+ r = dm_bm_unlock(sblock);
+ if (r < 0)
+ goto bad;
+
+ r = dm_btree_empty(&pmd->info, &pmd->root);
+ if (r < 0)
+ goto bad;
+
+ r = dm_btree_empty(&pmd->details_info, &pmd->details_root);
+ if (r < 0) {
+ DMERR("couldn't create devices root");
+ goto bad;
+ }
+
+ pmd->flags = 0;
+ pmd->need_commit = 1;
+ r = dm_pool_commit_metadata(pmd);
+ if (r < 0) {
+ DMERR("%s: dm_pool_commit_metadata() failed, error = %d",
+ __func__, r);
+ goto bad;
+ }
+
+ return pmd;
+
+bad:
+ if (dm_pool_metadata_close(pmd) < 0)
+ DMWARN("%s: dm_pool_metadata_close() failed.", __func__);
+ return ERR_PTR(r);
+}
+
+int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
+{
+ int r;
+ unsigned open_devices = 0;
+ struct dm_thin_device *td, *tmp;
+
+ down_read(&pmd->root_lock);
+ list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
+ if (td->open_count)
+ open_devices++;
+ else {
+ list_del(&td->list);
+ kfree(td);
+ }
+ }
+ up_read(&pmd->root_lock);
+
+ if (open_devices) {
+ DMERR("attempt to close pmd when %u device(s) are still open",
+ open_devices);
+ return -EBUSY;
+ }
+
+ r = __commit_transaction(pmd);
+ if (r < 0)
+ DMWARN("%s: __commit_transaction() failed, error = %d",
+ __func__, r);
+
+ dm_tm_destroy(pmd->tm);
+ dm_tm_destroy(pmd->nb_tm);
+ dm_block_manager_destroy(pmd->bm);
+ dm_sm_destroy(pmd->metadata_sm);
+ dm_sm_destroy(pmd->data_sm);
+ kfree(pmd);
+
+ return 0;
+}
+
+static int __open_device(struct dm_pool_metadata *pmd,
+ dm_thin_id dev, int create,
+ struct dm_thin_device **td)
+{
+ int r, changed = 0;
+ struct dm_thin_device *td2;
+ uint64_t key = dev;
+ struct disk_device_details details_le;
+
+ /*
+ * Check the device isn't already open.
+ */
+ list_for_each_entry(td2, &pmd->thin_devices, list)
+ if (td2->id == dev) {
+ td2->open_count++;
+ *td = td2;
+ return 0;
+ }
+
+ /*
+ * Check the device exists.
+ */
+ r = dm_btree_lookup(&pmd->details_info, pmd->details_root,
+ &key, &details_le);
+ if (r) {
+ if (r != -ENODATA || !create)
+ return r;
+
+ changed = 1;
+ details_le.mapped_blocks = 0;
+ details_le.transaction_id = cpu_to_le64(pmd->trans_id);
+ details_le.creation_time = cpu_to_le32(pmd->time);
+ details_le.snapshotted_time = cpu_to_le32(pmd->time);
+ }
+
+ *td = kmalloc(sizeof(**td), GFP_NOIO);
+ if (!*td)
+ return -ENOMEM;
+
+ (*td)->pmd = pmd;
+ (*td)->id = dev;
+ (*td)->open_count = 1;
+ (*td)->changed = changed;
+ (*td)->mapped_blocks = le64_to_cpu(details_le.mapped_blocks);
+ (*td)->transaction_id = le64_to_cpu(details_le.transaction_id);
+ (*td)->creation_time = le32_to_cpu(details_le.creation_time);
+ (*td)->snapshotted_time = le32_to_cpu(details_le.snapshotted_time);
+
+ list_add(&(*td)->list, &pmd->thin_devices);
+
+ return 0;
+}
+
+static void __close_device(struct dm_thin_device *td)
+{
+ --td->open_count;
+}
+
+static int __create_thin(struct dm_pool_metadata *pmd,
+ dm_thin_id dev)
+{
+ int r;
+ dm_block_t dev_root;
+ uint64_t key = dev;
+ struct disk_device_details details_le;
+ struct dm_thin_device *td;
+ __le64 value;
+
+ r = dm_btree_lookup(&pmd->details_info, pmd->details_root,
+ &key, &details_le);
+ if (!r)
+ return -EEXIST;
+
+ /*
+ * Create an empty btree for the mappings.
+ */
+ r = dm_btree_empty(&pmd->bl_info, &dev_root);
+ if (r)
+ return r;
+
+ /*
+ * Insert it into the main mapping tree.
+ */
+ value = cpu_to_le64(dev_root);
+ __dm_bless_for_disk(&value);
+ r = dm_btree_insert(&pmd->tl_info, pmd->root, &key, &value, &pmd->root);
+ if (r) {
+ dm_btree_del(&pmd->bl_info, dev_root);
+ return r;
+ }
+
+ r = __open_device(pmd, dev, 1, &td);
+ if (r) {
+ __close_device(td);
+ dm_btree_remove(&pmd->tl_info, pmd->root, &key, &pmd->root);
+ dm_btree_del(&pmd->bl_info, dev_root);
+ return r;
+ }
+ td->changed = 1;
+ __close_device(td);
+
+ return r;
+}
+
+int dm_pool_create_thin(struct dm_pool_metadata *pmd, dm_thin_id dev)
+{
+ int r;
+
+ down_write(&pmd->root_lock);
+ r = __create_thin(pmd, dev);
+ up_write(&pmd->root_lock);
+
+ return r;
+}
+
+static int __set_snapshot_details(struct dm_pool_metadata *pmd,
+ struct dm_thin_device *snap,
+ dm_thin_id origin, uint32_t time)
+{
+ int r;
+ struct dm_thin_device *td;
+
+ r = __open_device(pmd, origin, 0, &td);
+ if (r)
+ return r;
+
+ td->changed = 1;
+ td->snapshotted_time = time;
+
+ snap->mapped_blocks = td->mapped_blocks;
+ snap->snapshotted_time = time;
+ __close_device(td);
+
+ return 0;
+}
+
+static int __create_snap(struct dm_pool_metadata *pmd,
+ dm_thin_id dev, dm_thin_id origin)
+{
+ int r;
+ dm_block_t origin_root;
+ uint64_t key = origin, dev_key = dev;
+ struct dm_thin_device *td;
+ struct disk_device_details details_le;
+ __le64 value;
+
+ /* check this device is unused */
+ r = dm_btree_lookup(&pmd->details_info, pmd->details_root,
+ &dev_key, &details_le);
+ if (!r)
+ return -EEXIST;
+
+ /* find the mapping tree for the origin */
+ r = dm_btree_lookup(&pmd->tl_info, pmd->root, &key, &value);
+ if (r)
+ return r;
+ origin_root = le64_to_cpu(value);
+
+ /* clone the origin, an inc will do */
+ dm_tm_inc(pmd->tm, origin_root);
+
+ /* insert into the main mapping tree */
+ value = cpu_to_le64(origin_root);
+ __dm_bless_for_disk(&value);
+ key = dev;
+ r = dm_btree_insert(&pmd->tl_info, pmd->root, &key, &value, &pmd->root);
+ if (r) {
+ dm_tm_dec(pmd->tm, origin_root);
+ return r;
+ }
+
+ pmd->time++;
+
+ r = __open_device(pmd, dev, 1, &td);
+ if (r)
+ goto bad;
+
+ r = __set_snapshot_details(pmd, td, origin, pmd->time);
+ if (r)
+ goto bad;
+
+ __close_device(td);
+ return 0;
+
+bad:
+ __close_device(td);
+ dm_btree_remove(&pmd->tl_info, pmd->root, &key, &pmd->root);
+ dm_btree_remove(&pmd->details_info, pmd->details_root,
+ &key, &pmd->details_root);
+ return r;
+}
+
+int dm_pool_create_snap(struct dm_pool_metadata *pmd,
+ dm_thin_id dev,
+ dm_thin_id origin)
+{
+ int r;
+
+ down_write(&pmd->root_lock);
+ r = __create_snap(pmd, dev, origin);
+ up_write(&pmd->root_lock);
+
+ return r;
+}
+
+static int __delete_device(struct dm_pool_metadata *pmd, dm_thin_id dev)
+{
+ int r;
+ uint64_t key = dev;
+ struct dm_thin_device *td;
+
+ /* TODO: failure should mark the transaction invalid */
+ r = __open_device(pmd, dev, 0, &td);
+ if (r)
+ return r;
+
+ if (td->open_count > 1) {
+ __close_device(td);
+ return -EBUSY;
+ }
+
+ list_del(&td->list);
+ kfree(td);
+ r = dm_btree_remove(&pmd->details_info, pmd->details_root,
+ &key, &pmd->details_root);
+ if (r)
+ return r;
+
+ r = dm_btree_remove(&pmd->tl_info, pmd->root, &key, &pmd->root);
+ if (r)
+ return r;
+
+ pmd->need_commit = 1;
+
+ return 0;
+}
+
+int dm_pool_delete_thin_device(struct dm_pool_metadata *pmd,
+ dm_thin_id dev)
+{
+ int r;
+
+ down_write(&pmd->root_lock);
+ r = __delete_device(pmd, dev);
+ up_write(&pmd->root_lock);
+
+ return r;
+}
+
+int dm_pool_set_metadata_transaction_id(struct dm_pool_metadata *pmd,
+ uint64_t current_id,
+ uint64_t new_id)
+{
+ down_write(&pmd->root_lock);
+ if (pmd->trans_id != current_id) {
+ up_write(&pmd->root_lock);
+ DMERR("mismatched transaction id");
+ return -EINVAL;
+ }
+
+ pmd->trans_id = new_id;
+ pmd->need_commit = 1;
+ up_write(&pmd->root_lock);
+
+ return 0;
+}
+
+int dm_pool_get_metadata_transaction_id(struct dm_pool_metadata *pmd,
+ uint64_t *result)
+{
+ down_read(&pmd->root_lock);
+ *result = pmd->trans_id;
+ up_read(&pmd->root_lock);
+
+ return 0;
+}
+
+static int __get_held_metadata_root(struct dm_pool_metadata *pmd,
+ dm_block_t *result)
+{
+ int r;
+ struct thin_disk_superblock *disk_super;
+ struct dm_block *sblock;
+
+ r = dm_bm_write_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION,
+ &sb_validator, &sblock);
+ if (r)
+ return r;
+
+ disk_super = dm_block_data(sblock);
+ *result = le64_to_cpu(disk_super->held_root);
+
+ return dm_bm_unlock(sblock);
+}
+
+int dm_pool_get_held_metadata_root(struct dm_pool_metadata *pmd,
+ dm_block_t *result)
+{
+ int r;
+
+ down_read(&pmd->root_lock);
+ r = __get_held_metadata_root(pmd, result);
+ up_read(&pmd->root_lock);
+
+ return r;
+}
+
+int dm_pool_open_thin_device(struct dm_pool_metadata *pmd, dm_thin_id dev,
+ struct dm_thin_device **td)
+{
+ int r;
+
+ down_write(&pmd->root_lock);
+ r = __open_device(pmd, dev, 0, td);
+ up_write(&pmd->root_lock);
+
+ return r;
+}
+
+int dm_pool_close_thin_device(struct dm_thin_device *td)
+{
+ down_write(&td->pmd->root_lock);
+ __close_device(td);
+ up_write(&td->pmd->root_lock);
+
+ return 0;
+}
+
+dm_thin_id dm_thin_dev_id(struct dm_thin_device *td)
+{
+ return td->id;
+}
+
+static int __snapshotted_since(struct dm_thin_device *td, uint32_t time)
+{
+ return td->snapshotted_time > time;
+}
+
+int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block,
+ int can_block, struct dm_thin_lookup_result *result)
+{
+ int r;
+ uint64_t block_time = 0;
+ __le64 value;
+ struct dm_pool_metadata *pmd = td->pmd;
+ dm_block_t keys[2] = { td->id, block };
+
+ if (can_block) {
+ down_read(&pmd->root_lock);
+ r = dm_btree_lookup(&pmd->info, pmd->root, keys, &value);
+ if (!r)
+ block_time = le64_to_cpu(value);
+ up_read(&pmd->root_lock);
+
+ } else if (down_read_trylock(&pmd->root_lock)) {
+ r = dm_btree_lookup(&pmd->nb_info, pmd->root, keys, &value);
+ if (!r)
+ block_time = le64_to_cpu(value);
+ up_read(&pmd->root_lock);
+
+ } else
+ return -EWOULDBLOCK;
+
+ if (!r) {
+ dm_block_t exception_block;
+ uint32_t exception_time;
+ unpack_block_time(block_time, &exception_block,
+ &exception_time);
+ result->block = exception_block;
+ result->shared = __snapshotted_since(td, exception_time);
+ }
+
+ return r;
+}
+
+static int __insert(struct dm_thin_device *td, dm_block_t block,
+ dm_block_t data_block)
+{
+ int r, inserted;
+ __le64 value;
+ struct dm_pool_metadata *pmd = td->pmd;
+ dm_block_t keys[2] = { td->id, block };
+
+ pmd->need_commit = 1;
+ value = cpu_to_le64(pack_block_time(data_block, pmd->time));
+ __dm_bless_for_disk(&value);
+
+ r = dm_btree_insert_notify(&pmd->info, pmd->root, keys, &value,
+ &pmd->root, &inserted);
+ if (r)
+ return r;
+
+ if (inserted) {
+ td->mapped_blocks++;
+ td->changed = 1;
+ }
+
+ return 0;
+}
+
+int dm_thin_insert_block(struct dm_thin_device *td, dm_block_t block,
+ dm_block_t data_block)
+{
+ int r;
+
+ down_write(&td->pmd->root_lock);
+ r = __insert(td, block, data_block);
+ up_write(&td->pmd->root_lock);
+
+ return r;
+}
+
+static int __remove(struct dm_thin_device *td, dm_block_t block)
+{
+ int r;
+ struct dm_pool_metadata *pmd = td->pmd;
+ dm_block_t keys[2] = { td->id, block };
+
+ r = dm_btree_remove(&pmd->info, pmd->root, keys, &pmd->root);
+ if (r)
+ return r;
+
+ pmd->need_commit = 1;
+
+ return 0;
+}
+
+int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block)
+{
+ int r;
+
+ down_write(&td->pmd->root_lock);
+ r = __remove(td, block);
+ up_write(&td->pmd->root_lock);
+
+ return r;
+}
+
+int dm_pool_alloc_data_block(struct dm_pool_metadata *pmd, dm_block_t *result)
+{
+ int r;
+
+ down_write(&pmd->root_lock);
+
+ r = dm_sm_new_block(pmd->data_sm, result);
+ pmd->need_commit = 1;
+
+ up_write(&pmd->root_lock);
+
+ return r;
+}
+
+int dm_pool_commit_metadata(struct dm_pool_metadata *pmd)
+{
+ int r;
+
+ down_write(&pmd->root_lock);
+
+ r = __commit_transaction(pmd);
+ if (r <= 0)
+ goto out;
+
+ /*
+ * Open the next transaction.
+ */
+ r = __begin_transaction(pmd);
+out:
+ up_write(&pmd->root_lock);
+ return r;
+}
+
+int dm_pool_get_free_block_count(struct dm_pool_metadata *pmd, dm_block_t *result)
+{
+ int r;
+
+ down_read(&pmd->root_lock);
+ r = dm_sm_get_nr_free(pmd->data_sm, result);
+ up_read(&pmd->root_lock);
+
+ return r;
+}
+
+int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd,
+ dm_block_t *result)
+{
+ int r;
+
+ down_read(&pmd->root_lock);
+ r = dm_sm_get_nr_free(pmd->metadata_sm, result);
+ up_read(&pmd->root_lock);
+
+ return r;
+}
+
+int dm_pool_get_metadata_dev_size(struct dm_pool_metadata *pmd,
+ dm_block_t *result)
+{
+ int r;
+
+ down_read(&pmd->root_lock);
+ r = dm_sm_get_nr_blocks(pmd->metadata_sm, result);
+ up_read(&pmd->root_lock);
+
+ return r;
+}
+
+int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result)
+{
+ down_read(&pmd->root_lock);
+ *result = pmd->data_block_size;
+ up_read(&pmd->root_lock);
+
+ return 0;
+}
+
+int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result)
+{
+ int r;
+
+ down_read(&pmd->root_lock);
+ r = dm_sm_get_nr_blocks(pmd->data_sm, result);
+ up_read(&pmd->root_lock);
+
+ return r;
+}
+
+int dm_thin_get_mapped_count(struct dm_thin_device *td, dm_block_t *result)
+{
+ struct dm_pool_metadata *pmd = td->pmd;
+
+ down_read(&pmd->root_lock);
+ *result = td->mapped_blocks;
+ up_read(&pmd->root_lock);
+
+ return 0;
+}
+
+static int __highest_block(struct dm_thin_device *td, dm_block_t *result)
+{
+ int r;
+ __le64 value_le;
+ dm_block_t thin_root;
+ struct dm_pool_metadata *pmd = td->pmd;
+
+ r = dm_btree_lookup(&pmd->tl_info, pmd->root, &td->id, &value_le);
+ if (r)
+ return r;
+
+ thin_root = le64_to_cpu(value_le);
+
+ return dm_btree_find_highest_key(&pmd->bl_info, thin_root, result);
+}
+
+int dm_thin_get_highest_mapped_block(struct dm_thin_device *td,
+ dm_block_t *result)
+{
+ int r;
+ struct dm_pool_metadata *pmd = td->pmd;
+
+ down_read(&pmd->root_lock);
+ r = __highest_block(td, result);
+ up_read(&pmd->root_lock);
+
+ return r;
+}
+
+static int __resize_data_dev(struct dm_pool_metadata *pmd, dm_block_t new_count)
+{
+ int r;
+ dm_block_t old_count;
+
+ r = dm_sm_get_nr_blocks(pmd->data_sm, &old_count);
+ if (r)
+ return r;
+
+ if (new_count == old_count)
+ return 0;
+
+ if (new_count < old_count) {
+ DMERR("cannot reduce size of data device");
+ return -EINVAL;
+ }
+
+ r = dm_sm_extend(pmd->data_sm, new_count - old_count);
+ if (!r)
+ pmd->need_commit = 1;
+
+ return r;
+}
+
+int dm_pool_resize_data_dev(struct dm_pool_metadata *pmd, dm_block_t new_count)
+{
+ int r;
+
+ down_write(&pmd->root_lock);
+ r = __resize_data_dev(pmd, new_count);
+ up_write(&pmd->root_lock);
+
+ return r;
+}
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
new file mode 100644
index 0000000..859c168
--- /dev/null
+++ b/drivers/md/dm-thin-metadata.h
@@ -0,0 +1,156 @@
+/*
+ * Copyright (C) 2010-2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_THIN_METADATA_H
+#define DM_THIN_METADATA_H
+
+#include "persistent-data/dm-block-manager.h"
+
+#define THIN_METADATA_BLOCK_SIZE 4096
+
+/*----------------------------------------------------------------*/
+
+struct dm_pool_metadata;
+struct dm_thin_device;
+
+/*
+ * Device identifier
+ */
+typedef uint64_t dm_thin_id;
+
+/*
+ * Reopens or creates a new, empty metadata volume.
+ */
+struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
+ sector_t data_block_size);
+
+int dm_pool_metadata_close(struct dm_pool_metadata *pmd);
+
+/*
+ * Compat feature flags. Any incompat flags beyond the ones
+ * specified below will prevent use of the thin metadata.
+ */
+#define THIN_FEATURE_COMPAT_SUPP 0UL
+#define THIN_FEATURE_COMPAT_RO_SUPP 0UL
+#define THIN_FEATURE_INCOMPAT_SUPP 0UL
+
+/*
+ * Device creation/deletion.
+ */
+int dm_pool_create_thin(struct dm_pool_metadata *pmd, dm_thin_id dev);
+
+/*
+ * An internal snapshot.
+ *
+ * You can only snapshot a quiesced origin i.e. one that is either
+ * suspended or not instanced at all.
+ */
+int dm_pool_create_snap(struct dm_pool_metadata *pmd, dm_thin_id dev,
+ dm_thin_id origin);
+
+/*
+ * Deletes a virtual device from the metadata. It _is_ safe to call this
+ * when that device is open. Operations on that device will just start
+ * failing. You still need to call close() on the device.
+ */
+int dm_pool_delete_thin_device(struct dm_pool_metadata *pmd,
+ dm_thin_id dev);
+
+/*
+ * Commits _all_ metadata changes: device creation, deletion, mapping
+ * updates.
+ */
+int dm_pool_commit_metadata(struct dm_pool_metadata *pmd);
+
+/*
+ * Set/get userspace transaction id.
+ */
+int dm_pool_set_metadata_transaction_id(struct dm_pool_metadata *pmd,
+ uint64_t current_id,
+ uint64_t new_id);
+
+int dm_pool_get_metadata_transaction_id(struct dm_pool_metadata *pmd,
+ uint64_t *result);
+
+/*
+ * Hold/get root for userspace transaction.
+ */
+int dm_pool_hold_metadata_root(struct dm_pool_metadata *pmd);
+
+int dm_pool_get_held_metadata_root(struct dm_pool_metadata *pmd,
+ dm_block_t *result);
+
+/*
+ * Actions on a single virtual device.
+ */
+
+/*
+ * Opening the same device more than once will fail with -EBUSY.
+ */
+int dm_pool_open_thin_device(struct dm_pool_metadata *pmd, dm_thin_id dev,
+ struct dm_thin_device **td);
+
+int dm_pool_close_thin_device(struct dm_thin_device *td);
+
+dm_thin_id dm_thin_dev_id(struct dm_thin_device *td);
+
+struct dm_thin_lookup_result {
+ dm_block_t block;
+ int shared;
+};
+
+/*
+ * Returns:
+ * -EWOULDBLOCK iff @can_block is set and would block.
+ * -ENODATA iff that mapping is not present.
+ * 0 success
+ */
+int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block,
+ int can_block, struct dm_thin_lookup_result *result);
+
+/*
+ * Obtain an unused block.
+ */
+int dm_pool_alloc_data_block(struct dm_pool_metadata *pmd, dm_block_t *result);
+
+/*
+ * Insert or remove block.
+ */
+int dm_thin_insert_block(struct dm_thin_device *td, dm_block_t block,
+ dm_block_t data_block);
+
+int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block);
+
+/*
+ * Queries.
+ */
+int dm_thin_get_highest_mapped_block(struct dm_thin_device *td,
+ dm_block_t *highest_mapped);
+
+int dm_thin_get_mapped_count(struct dm_thin_device *td, dm_block_t *result);
+
+int dm_pool_get_free_block_count(struct dm_pool_metadata *pmd,
+ dm_block_t *result);
+
+int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd,
+ dm_block_t *result);
+
+int dm_pool_get_metadata_dev_size(struct dm_pool_metadata *pmd,
+ dm_block_t *result);
+
+int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result);
+
+int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result);
+
+/*
+ * Returns -ENOSPC if the new size is too small and already allocated
+ * blocks would be lost.
+ */
+int dm_pool_resize_data_dev(struct dm_pool_metadata *pmd, dm_block_t new_size);
+
+/*----------------------------------------------------------------*/
+
+#endif
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
new file mode 100644
index 0000000..c308757
--- /dev/null
+++ b/drivers/md/dm-thin.c
@@ -0,0 +1,2428 @@
+/*
+ * Copyright (C) 2011 Red Hat UK.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-thin-metadata.h"
+
+#include <linux/device-mapper.h>
+#include <linux/dm-io.h>
+#include <linux/dm-kcopyd.h>
+#include <linux/list.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#define DM_MSG_PREFIX "thin"
+
+/*
+ * Tunable constants
+ */
+#define ENDIO_HOOK_POOL_SIZE 10240
+#define DEFERRED_SET_SIZE 64
+#define MAPPING_POOL_SIZE 1024
+#define PRISON_CELLS 1024
+
+/*
+ * The block size of the device holding pool data must be
+ * between 64KB and 1GB.
+ */
+#define DATA_DEV_BLOCK_SIZE_MIN_SECTORS (64 * 1024 >> SECTOR_SHIFT)
+#define DATA_DEV_BLOCK_SIZE_MAX_SECTORS (1024 * 1024 * 1024 >> SECTOR_SHIFT)
+
+/*
+ * The metadata device is currently limited in size. The limitation is
+ * checked lower down in dm-space-map-metadata, but we also check it here
+ * so we can fail early.
+ *
+ * We have one block of index, which can hold 255 index entries. Each
+ * index entry contains allocation info about 16k metadata blocks.
+ */
+#define METADATA_DEV_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
+
+/*
+ * Device id is restricted to 24 bits.
+ */
+#define MAX_DEV_ID ((1 << 24) - 1)
+
+/*
+ * How do we handle breaking sharing of data blocks?
+ * =================================================
+ *
+ * We use a standard copy-on-write btree to store the mappings for the
+ * devices (note I'm talking about copy-on-write of the metadata here, not
+ * the data). When you take an internal snapshot you clone the root node
+ * of the origin btree. After this there is no concept of an origin or a
+ * snapshot. They are just two device trees that happen to point to the
+ * same data blocks.
+ *
+ * When we get a write in we decide if it's to a shared data block using
+ * some timestamp magic. If it is, we have to break sharing.
+ *
+ * Let's say we write to a shared block in what was the origin. The
+ * steps are:
+ *
+ * i) plug io further to this physical block. (see bio_prison code).
+ *
+ * ii) quiesce any read io to that shared data block. Obviously
+ * including all devices that share this block. (see deferred_set code)
+ *
+ * iii) copy the data block to a newly allocate block. This step can be
+ * missed out if the io covers the block. (schedule_copy).
+ *
+ * iv) insert the new mapping into the origin's btree
+ * (process_prepared_mappings). This act of inserting breaks some
+ * sharing of btree nodes between the two devices. Breaking sharing only
+ * effects the btree of that specific device. Btrees for the other
+ * devices that share the block never change. The btree for the origin
+ * device as it was after the last commit is untouched, ie. we're using
+ * persistent data structures in the functional programming sense.
+ *
+ * v) unplug io to this physical block, including the io that triggered
+ * the breaking of sharing.
+ *
+ * Steps (ii) and (iii) occur in parallel.
+ *
+ * The metadata _doesn't_ need to be committed before the io continues. We
+ * get away with this because the io is always written to a _new_ block.
+ * If there's a crash, then:
+ *
+ * - The origin mapping will point to the old origin block (the shared
+ * one). This will contain the data as it was before the io that triggered
+ * the breaking of sharing came in.
+ *
+ * - The snap mapping still points to the old block. As it would after
+ * the commit.
+ *
+ * The downside of this scheme is the timestamp magic isn't perfect, and
+ * will continue to think that data block in the snapshot device is shared
+ * even after the write to the origin has broken sharing. I suspect data
+ * blocks will typically be shared by many different devices, so we're
+ * breaking sharing n + 1 times, rather than n, where n is the number of
+ * devices that reference this data block. At the moment I think the
+ * benefits far, far outweigh the disadvantages.
+ */
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Sometimes we can't deal with a bio straight away. We put them in prison
+ * where they can't cause any mischief. Bios are put in a cell identified
+ * by a key, multiple bios can be in the same cell. When the cell is
+ * subsequently unlocked the bios become available.
+ */
+struct bio_prison;
+
+struct cell_key {
+ int virtual;
+ dm_thin_id dev;
+ dm_block_t block;
+};
+
+struct cell {
+ struct hlist_node list;
+ struct bio_prison *prison;
+ struct cell_key key;
+ unsigned count;
+ struct bio_list bios;
+};
+
+struct bio_prison {
+ spinlock_t lock;
+ mempool_t *cell_pool;
+
+ unsigned nr_buckets;
+ unsigned hash_mask;
+ struct hlist_head *cells;
+};
+
+static uint32_t calc_nr_buckets(unsigned nr_cells)
+{
+ uint32_t n = 128;
+
+ nr_cells /= 4;
+ nr_cells = min(nr_cells, 8192u);
+
+ while (n < nr_cells)
+ n <<= 1;
+
+ return n;
+}
+
+/*
+ * @nr_cells should be the number of cells you want in use _concurrently_.
+ * Don't confuse it with the number of distinct keys.
+ */
+static struct bio_prison *prison_create(unsigned nr_cells)
+{
+ unsigned i;
+ uint32_t nr_buckets = calc_nr_buckets(nr_cells);
+ size_t len = sizeof(struct bio_prison) +
+ (sizeof(struct hlist_head) * nr_buckets);
+ struct bio_prison *prison = kmalloc(len, GFP_KERNEL);
+
+ if (!prison)
+ return NULL;
+
+ spin_lock_init(&prison->lock);
+ prison->cell_pool = mempool_create_kmalloc_pool(nr_cells,
+ sizeof(struct cell));
+ if (!prison->cell_pool) {
+ kfree(prison);
+ return NULL;
+ }
+
+ prison->nr_buckets = nr_buckets;
+ prison->hash_mask = nr_buckets - 1;
+ prison->cells = (struct hlist_head *) (prison + 1);
+ for (i = 0; i < nr_buckets; i++)
+ INIT_HLIST_HEAD(prison->cells + i);
+
+ return prison;
+}
+
+static void prison_destroy(struct bio_prison *prison)
+{
+ mempool_destroy(prison->cell_pool);
+ kfree(prison);
+}
+
+static uint32_t hash_key(struct bio_prison *prison, struct cell_key *key)
+{
+ const unsigned long BIG_PRIME = 4294967291UL;
+ uint64_t hash = key->block * BIG_PRIME;
+
+ return (uint32_t) (hash & prison->hash_mask);
+}
+
+static int keys_equal(struct cell_key *lhs, struct cell_key *rhs)
+{
+ return (lhs->virtual == rhs->virtual) &&
+ (lhs->dev == rhs->dev) &&
+ (lhs->block == rhs->block);
+}
+
+static struct cell *__search_bucket(struct hlist_head *bucket,
+ struct cell_key *key)
+{
+ struct cell *cell;
+ struct hlist_node *tmp;
+
+ hlist_for_each_entry(cell, tmp, bucket, list)
+ if (keys_equal(&cell->key, key))
+ return cell;
+
+ return NULL;
+}
+
+/*
+ * This may block if a new cell needs allocating. You must ensure that
+ * cells will be unlocked even if the calling thread is blocked.
+ *
+ * Returns the number of entries in the cell prior to the new addition
+ * or < 0 on failure.
+ */
+static int bio_detain(struct bio_prison *prison, struct cell_key *key,
+ struct bio *inmate, struct cell **ref)
+{
+ int r;
+ unsigned long flags;
+ uint32_t hash = hash_key(prison, key);
+ struct cell *uninitialized_var(cell), *cell2 = NULL;
+
+ BUG_ON(hash > prison->nr_buckets);
+
+ spin_lock_irqsave(&prison->lock, flags);
+ cell = __search_bucket(prison->cells + hash, key);
+
+ if (!cell) {
+ /*
+ * Allocate a new cell
+ */
+ spin_unlock_irqrestore(&prison->lock, flags);
+ cell2 = mempool_alloc(prison->cell_pool, GFP_NOIO);
+ spin_lock_irqsave(&prison->lock, flags);
+
+ /*
+ * We've been unlocked, so we have to double check that
+ * nobody else has inserted this cell in the meantime.
+ */
+ cell = __search_bucket(prison->cells + hash, key);
+
+ if (!cell) {
+ cell = cell2;
+ cell2 = NULL;
+
+ cell->prison = prison;
+ memcpy(&cell->key, key, sizeof(cell->key));
+ cell->count = 0;
+ bio_list_init(&cell->bios);
+ hlist_add_head(&cell->list, prison->cells + hash);
+ }
+ }
+
+ r = cell->count++;
+ bio_list_add(&cell->bios, inmate);
+ spin_unlock_irqrestore(&prison->lock, flags);
+
+ if (cell2)
+ mempool_free(cell2, prison->cell_pool);
+
+ *ref = cell;
+
+ return r;
+}
+
+/*
+ * @inmates must have been initialised prior to this call
+ */
+static void __cell_release(struct cell *cell, struct bio_list *inmates)
+{
+ struct bio_prison *prison = cell->prison;
+
+ hlist_del(&cell->list);
+
+ if (inmates)
+ bio_list_merge(inmates, &cell->bios);
+
+ mempool_free(cell, prison->cell_pool);
+}
+
+static void cell_release(struct cell *cell, struct bio_list *bios)
+{
+ unsigned long flags;
+ struct bio_prison *prison = cell->prison;
+
+ spin_lock_irqsave(&prison->lock, flags);
+ __cell_release(cell, bios);
+ spin_unlock_irqrestore(&prison->lock, flags);
+}
+
+/*
+ * There are a couple of places where we put a bio into a cell briefly
+ * before taking it out again. In these situations we know that no other
+ * bio may be in the cell. This function releases the cell, and also does
+ * a sanity check.
+ */
+static void cell_release_singleton(struct cell *cell, struct bio *bio)
+{
+ struct bio_prison *prison = cell->prison;
+ struct bio_list bios;
+ struct bio *b;
+ unsigned long flags;
+
+ bio_list_init(&bios);
+
+ spin_lock_irqsave(&prison->lock, flags);
+ __cell_release(cell, &bios);
+ spin_unlock_irqrestore(&prison->lock, flags);
+
+ b = bio_list_pop(&bios);
+ BUG_ON(b != bio);
+ BUG_ON(!bio_list_empty(&bios));
+}
+
+static void cell_error(struct cell *cell)
+{
+ struct bio_prison *prison = cell->prison;
+ struct bio_list bios;
+ struct bio *bio;
+ unsigned long flags;
+
+ bio_list_init(&bios);
+
+ spin_lock_irqsave(&prison->lock, flags);
+ __cell_release(cell, &bios);
+ spin_unlock_irqrestore(&prison->lock, flags);
+
+ while ((bio = bio_list_pop(&bios)))
+ bio_io_error(bio);
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * We use the deferred set to keep track of pending reads to shared blocks.
+ * We do this to ensure the new mapping caused by a write isn't performed
+ * until these prior reads have completed. Otherwise the insertion of the
+ * new mapping could free the old block that the read bios are mapped to.
+ */
+
+struct deferred_set;
+struct deferred_entry {
+ struct deferred_set *ds;
+ unsigned count;
+ struct list_head work_items;
+};
+
+struct deferred_set {
+ spinlock_t lock;
+ unsigned current_entry;
+ unsigned sweeper;
+ struct deferred_entry entries[DEFERRED_SET_SIZE];
+};
+
+static void ds_init(struct deferred_set *ds)
+{
+ int i;
+
+ spin_lock_init(&ds->lock);
+ ds->current_entry = 0;
+ ds->sweeper = 0;
+ for (i = 0; i < DEFERRED_SET_SIZE; i++) {
+ ds->entries[i].ds = ds;
+ ds->entries[i].count = 0;
+ INIT_LIST_HEAD(&ds->entries[i].work_items);
+ }
+}
+
+static struct deferred_entry *ds_inc(struct deferred_set *ds)
+{
+ unsigned long flags;
+ struct deferred_entry *entry;
+
+ spin_lock_irqsave(&ds->lock, flags);
+ entry = ds->entries + ds->current_entry;
+ entry->count++;
+ spin_unlock_irqrestore(&ds->lock, flags);
+
+ return entry;
+}
+
+static unsigned ds_next(unsigned index)
+{
+ return (index + 1) % DEFERRED_SET_SIZE;
+}
+
+static void __sweep(struct deferred_set *ds, struct list_head *head)
+{
+ while ((ds->sweeper != ds->current_entry) &&
+ !ds->entries[ds->sweeper].count) {
+ list_splice_init(&ds->entries[ds->sweeper].work_items, head);
+ ds->sweeper = ds_next(ds->sweeper);
+ }
+
+ if ((ds->sweeper == ds->current_entry) && !ds->entries[ds->sweeper].count)
+ list_splice_init(&ds->entries[ds->sweeper].work_items, head);
+}
+
+static void ds_dec(struct deferred_entry *entry, struct list_head *head)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&entry->ds->lock, flags);
+ BUG_ON(!entry->count);
+ --entry->count;
+ __sweep(entry->ds, head);
+ spin_unlock_irqrestore(&entry->ds->lock, flags);
+}
+
+/*
+ * Returns 1 if deferred or 0 if no pending items to delay job.
+ */
+static int ds_add_work(struct deferred_set *ds, struct list_head *work)
+{
+ int r = 1;
+ unsigned long flags;
+ unsigned next_entry;
+
+ spin_lock_irqsave(&ds->lock, flags);
+ if ((ds->sweeper == ds->current_entry) &&
+ !ds->entries[ds->current_entry].count)
+ r = 0;
+ else {
+ list_add(work, &ds->entries[ds->current_entry].work_items);
+ next_entry = ds_next(ds->current_entry);
+ if (!ds->entries[next_entry].count)
+ ds->current_entry = next_entry;
+ }
+ spin_unlock_irqrestore(&ds->lock, flags);
+
+ return r;
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Key building.
+ */
+static void build_data_key(struct dm_thin_device *td,
+ dm_block_t b, struct cell_key *key)
+{
+ key->virtual = 0;
+ key->dev = dm_thin_dev_id(td);
+ key->block = b;
+}
+
+static void build_virtual_key(struct dm_thin_device *td, dm_block_t b,
+ struct cell_key *key)
+{
+ key->virtual = 1;
+ key->dev = dm_thin_dev_id(td);
+ key->block = b;
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * A pool device ties together a metadata device and a data device. It
+ * also provides the interface for creating and destroying internal
+ * devices.
+ */
+struct new_mapping;
+struct pool {
+ struct list_head list;
+ struct dm_target *ti; /* Only set if a pool target is bound */
+
+ struct mapped_device *pool_md;
+ struct block_device *md_dev;
+ struct dm_pool_metadata *pmd;
+
+ uint32_t sectors_per_block;
+ unsigned block_shift;
+ dm_block_t offset_mask;
+ dm_block_t low_water_blocks;
+
+ unsigned zero_new_blocks:1;
+ unsigned low_water_triggered:1; /* A dm event has been sent */
+ unsigned no_free_space:1; /* A -ENOSPC warning has been issued */
+
+ struct bio_prison *prison;
+ struct dm_kcopyd_client *copier;
+
+ struct workqueue_struct *wq;
+ struct work_struct worker;
+
+ unsigned ref_count;
+
+ spinlock_t lock;
+ struct bio_list deferred_bios;
+ struct bio_list deferred_flush_bios;
+ struct list_head prepared_mappings;
+
+ struct bio_list retry_on_resume_list;
+
+ struct deferred_set ds; /* FIXME: move to thin_c */
+
+ struct new_mapping *next_mapping;
+ mempool_t *mapping_pool;
+ mempool_t *endio_hook_pool;
+};
+
+/*
+ * Target context for a pool.
+ */
+struct pool_c {
+ struct dm_target *ti;
+ struct pool *pool;
+ struct dm_dev *data_dev;
+ struct dm_dev *metadata_dev;
+ struct dm_target_callbacks callbacks;
+
+ dm_block_t low_water_blocks;
+ unsigned zero_new_blocks:1;
+};
+
+/*
+ * Target context for a thin.
+ */
+struct thin_c {
+ struct dm_dev *pool_dev;
+ dm_thin_id dev_id;
+
+ struct pool *pool;
+ struct dm_thin_device *td;
+};
+
+/*----------------------------------------------------------------*/
+
+/*
+ * A global list of pools that uses a struct mapped_device as a key.
+ */
+static struct dm_thin_pool_table {
+ struct mutex mutex;
+ struct list_head pools;
+} dm_thin_pool_table;
+
+static void pool_table_init(void)
+{
+ mutex_init(&dm_thin_pool_table.mutex);
+ INIT_LIST_HEAD(&dm_thin_pool_table.pools);
+}
+
+static void __pool_table_insert(struct pool *pool)
+{
+ BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex));
+ list_add(&pool->list, &dm_thin_pool_table.pools);
+}
+
+static void __pool_table_remove(struct pool *pool)
+{
+ BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex));
+ list_del(&pool->list);
+}
+
+static struct pool *__pool_table_lookup(struct mapped_device *md)
+{
+ struct pool *pool = NULL, *tmp;
+
+ BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex));
+
+ list_for_each_entry(tmp, &dm_thin_pool_table.pools, list) {
+ if (tmp->pool_md == md) {
+ pool = tmp;
+ break;
+ }
+ }
+
+ return pool;
+}
+
+static struct pool *__pool_table_lookup_metadata_dev(struct block_device *md_dev)
+{
+ struct pool *pool = NULL, *tmp;
+
+ BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex));
+
+ list_for_each_entry(tmp, &dm_thin_pool_table.pools, list) {
+ if (tmp->md_dev == md_dev) {
+ pool = tmp;
+ break;
+ }
+ }
+
+ return pool;
+}
+
+/*----------------------------------------------------------------*/
+
+static void __requeue_bio_list(struct thin_c *tc, struct bio_list *master)
+{
+ struct bio *bio;
+ struct bio_list bios;
+
+ bio_list_init(&bios);
+ bio_list_merge(&bios, master);
+ bio_list_init(master);
+
+ while ((bio = bio_list_pop(&bios))) {
+ if (dm_get_mapinfo(bio)->ptr == tc)
+ bio_endio(bio, DM_ENDIO_REQUEUE);
+ else
+ bio_list_add(master, bio);
+ }
+}
+
+static void requeue_io(struct thin_c *tc)
+{
+ struct pool *pool = tc->pool;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ __requeue_bio_list(tc, &pool->deferred_bios);
+ __requeue_bio_list(tc, &pool->retry_on_resume_list);
+ spin_unlock_irqrestore(&pool->lock, flags);
+}
+
+/*
+ * This section of code contains the logic for processing a thin device's IO.
+ * Much of the code depends on pool object resources (lists, workqueues, etc)
+ * but most is exclusively called from the thin target rather than the thin-pool
+ * target.
+ */
+
+static dm_block_t get_bio_block(struct thin_c *tc, struct bio *bio)
+{
+ return bio->bi_sector >> tc->pool->block_shift;
+}
+
+static void remap(struct thin_c *tc, struct bio *bio, dm_block_t block)
+{
+ struct pool *pool = tc->pool;
+
+ bio->bi_bdev = tc->pool_dev->bdev;
+ bio->bi_sector = (block << pool->block_shift) +
+ (bio->bi_sector & pool->offset_mask);
+}
+
+static void remap_and_issue(struct thin_c *tc, struct bio *bio,
+ dm_block_t block)
+{
+ struct pool *pool = tc->pool;
+ unsigned long flags;
+
+ remap(tc, bio, block);
+
+ /*
+ * Batch together any FUA/FLUSH bios we find and then issue
+ * a single commit for them in process_deferred_bios().
+ */
+ if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+ spin_lock_irqsave(&pool->lock, flags);
+ bio_list_add(&pool->deferred_flush_bios, bio);
+ spin_unlock_irqrestore(&pool->lock, flags);
+ } else
+ generic_make_request(bio);
+}
+
+/*
+ * wake_worker() is used when new work is queued and when pool_resume is
+ * ready to continue deferred IO processing.
+ */
+static void wake_worker(struct pool *pool)
+{
+ queue_work(pool->wq, &pool->worker);
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Bio endio functions.
+ */
+struct endio_hook {
+ struct thin_c *tc;
+ bio_end_io_t *saved_bi_end_io;
+ struct deferred_entry *entry;
+};
+
+struct new_mapping {
+ struct list_head list;
+
+ int prepared;
+
+ struct thin_c *tc;
+ dm_block_t virt_block;
+ dm_block_t data_block;
+ struct cell *cell;
+ int err;
+
+ /*
+ * If the bio covers the whole area of a block then we can avoid
+ * zeroing or copying. Instead this bio is hooked. The bio will
+ * still be in the cell, so care has to be taken to avoid issuing
+ * the bio twice.
+ */
+ struct bio *bio;
+ bio_end_io_t *saved_bi_end_io;
+};
+
+static void __maybe_add_mapping(struct new_mapping *m)
+{
+ struct pool *pool = m->tc->pool;
+
+ if (list_empty(&m->list) && m->prepared) {
+ list_add(&m->list, &pool->prepared_mappings);
+ wake_worker(pool);
+ }
+}
+
+static void copy_complete(int read_err, unsigned long write_err, void *context)
+{
+ unsigned long flags;
+ struct new_mapping *m = context;
+ struct pool *pool = m->tc->pool;
+
+ m->err = read_err || write_err ? -EIO : 0;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ m->prepared = 1;
+ __maybe_add_mapping(m);
+ spin_unlock_irqrestore(&pool->lock, flags);
+}
+
+static void overwrite_endio(struct bio *bio, int err)
+{
+ unsigned long flags;
+ struct new_mapping *m = dm_get_mapinfo(bio)->ptr;
+ struct pool *pool = m->tc->pool;
+
+ m->err = err;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ m->prepared = 1;
+ __maybe_add_mapping(m);
+ spin_unlock_irqrestore(&pool->lock, flags);
+}
+
+static void shared_read_endio(struct bio *bio, int err)
+{
+ struct list_head mappings;
+ struct new_mapping *m, *tmp;
+ struct endio_hook *h = dm_get_mapinfo(bio)->ptr;
+ unsigned long flags;
+ struct pool *pool = h->tc->pool;
+
+ bio->bi_end_io = h->saved_bi_end_io;
+ bio_endio(bio, err);
+
+ INIT_LIST_HEAD(&mappings);
+ ds_dec(h->entry, &mappings);
+
+ spin_lock_irqsave(&pool->lock, flags);
+ list_for_each_entry_safe(m, tmp, &mappings, list) {
+ list_del(&m->list);
+ INIT_LIST_HEAD(&m->list);
+ __maybe_add_mapping(m);
+ }
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ mempool_free(h, pool->endio_hook_pool);
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Workqueue.
+ */
+
+/*
+ * Prepared mapping jobs.
+ */
+
+/*
+ * This sends the bios in the cell back to the deferred_bios list.
+ */
+static void cell_defer(struct thin_c *tc, struct cell *cell,
+ dm_block_t data_block)
+{
+ struct pool *pool = tc->pool;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ cell_release(cell, &pool->deferred_bios);
+ spin_unlock_irqrestore(&tc->pool->lock, flags);
+
+ wake_worker(pool);
+}
+
+/*
+ * Same as cell_defer above, except it omits one particular detainee,
+ * a write bio that covers the block and has already been processed.
+ */
+static void cell_defer_except(struct thin_c *tc, struct cell *cell,
+ struct bio *exception)
+{
+ struct bio_list bios;
+ struct bio *bio;
+ struct pool *pool = tc->pool;
+ unsigned long flags;
+
+ bio_list_init(&bios);
+ cell_release(cell, &bios);
+
+ spin_lock_irqsave(&pool->lock, flags);
+ while ((bio = bio_list_pop(&bios)))
+ if (bio != exception)
+ bio_list_add(&pool->deferred_bios, bio);
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ wake_worker(pool);
+}
+
+static void process_prepared_mapping(struct new_mapping *m)
+{
+ struct thin_c *tc = m->tc;
+ struct bio *bio;
+ int r;
+
+ bio = m->bio;
+ if (bio)
+ bio->bi_end_io = m->saved_bi_end_io;
+
+ if (m->err) {
+ cell_error(m->cell);
+ return;
+ }
+
+ /*
+ * Commit the prepared block into the mapping btree.
+ * Any I/O for this block arriving after this point will get
+ * remapped to it directly.
+ */
+ r = dm_thin_insert_block(tc->td, m->virt_block, m->data_block);
+ if (r) {
+ DMERR("dm_thin_insert_block() failed");
+ cell_error(m->cell);
+ return;
+ }
+
+ /*
+ * Release any bios held while the block was being provisioned.
+ * If we are processing a write bio that completely covers the block,
+ * we already processed it so can ignore it now when processing
+ * the bios in the cell.
+ */
+ if (bio) {
+ cell_defer_except(tc, m->cell, bio);
+ bio_endio(bio, 0);
+ } else
+ cell_defer(tc, m->cell, m->data_block);
+
+ list_del(&m->list);
+ mempool_free(m, tc->pool->mapping_pool);
+}
+
+static void process_prepared_mappings(struct pool *pool)
+{
+ unsigned long flags;
+ struct list_head maps;
+ struct new_mapping *m, *tmp;
+
+ INIT_LIST_HEAD(&maps);
+ spin_lock_irqsave(&pool->lock, flags);
+ list_splice_init(&pool->prepared_mappings, &maps);
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ list_for_each_entry_safe(m, tmp, &maps, list)
+ process_prepared_mapping(m);
+}
+
+/*
+ * Deferred bio jobs.
+ */
+static int io_overwrites_block(struct pool *pool, struct bio *bio)
+{
+ return ((bio_data_dir(bio) == WRITE) &&
+ !(bio->bi_sector & pool->offset_mask)) &&
+ (bio->bi_size == (pool->sectors_per_block << SECTOR_SHIFT));
+}
+
+static void save_and_set_endio(struct bio *bio, bio_end_io_t **save,
+ bio_end_io_t *fn)
+{
+ *save = bio->bi_end_io;
+ bio->bi_end_io = fn;
+}
+
+static int ensure_next_mapping(struct pool *pool)
+{
+ if (pool->next_mapping)
+ return 0;
+
+ pool->next_mapping = mempool_alloc(pool->mapping_pool, GFP_ATOMIC);
+
+ return pool->next_mapping ? 0 : -ENOMEM;
+}
+
+static struct new_mapping *get_next_mapping(struct pool *pool)
+{
+ struct new_mapping *r = pool->next_mapping;
+
+ BUG_ON(!pool->next_mapping);
+
+ pool->next_mapping = NULL;
+
+ return r;
+}
+
+static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
+ dm_block_t data_origin, dm_block_t data_dest,
+ struct cell *cell, struct bio *bio)
+{
+ int r;
+ struct pool *pool = tc->pool;
+ struct new_mapping *m = get_next_mapping(pool);
+
+ INIT_LIST_HEAD(&m->list);
+ m->prepared = 0;
+ m->tc = tc;
+ m->virt_block = virt_block;
+ m->data_block = data_dest;
+ m->cell = cell;
+ m->err = 0;
+ m->bio = NULL;
+
+ ds_add_work(&pool->ds, &m->list);
+
+ /*
+ * IO to pool_dev remaps to the pool target's data_dev.
+ *
+ * If the whole block of data is being overwritten, we can issue the
+ * bio immediately. Otherwise we use kcopyd to clone the data first.
+ */
+ if (io_overwrites_block(pool, bio)) {
+ m->bio = bio;
+ save_and_set_endio(bio, &m->saved_bi_end_io, overwrite_endio);
+ dm_get_mapinfo(bio)->ptr = m;
+ remap_and_issue(tc, bio, data_dest);
+ } else {
+ struct dm_io_region from, to;
+
+ from.bdev = tc->pool_dev->bdev;
+ from.sector = data_origin * pool->sectors_per_block;
+ from.count = pool->sectors_per_block;
+
+ to.bdev = tc->pool_dev->bdev;
+ to.sector = data_dest * pool->sectors_per_block;
+ to.count = pool->sectors_per_block;
+
+ r = dm_kcopyd_copy(pool->copier, &from, 1, &to,
+ 0, copy_complete, m);
+ if (r < 0) {
+ mempool_free(m, pool->mapping_pool);
+ DMERR("dm_kcopyd_copy() failed");
+ cell_error(cell);
+ }
+ }
+}
+
+static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
+ dm_block_t data_block, struct cell *cell,
+ struct bio *bio)
+{
+ struct pool *pool = tc->pool;
+ struct new_mapping *m = get_next_mapping(pool);
+
+ INIT_LIST_HEAD(&m->list);
+ m->prepared = 0;
+ m->tc = tc;
+ m->virt_block = virt_block;
+ m->data_block = data_block;
+ m->cell = cell;
+ m->err = 0;
+ m->bio = NULL;
+
+ /*
+ * If the whole block of data is being overwritten or we are not
+ * zeroing pre-existing data, we can issue the bio immediately.
+ * Otherwise we use kcopyd to zero the data first.
+ */
+ if (!pool->zero_new_blocks)
+ process_prepared_mapping(m);
+
+ else if (io_overwrites_block(pool, bio)) {
+ m->bio = bio;
+ save_and_set_endio(bio, &m->saved_bi_end_io, overwrite_endio);
+ dm_get_mapinfo(bio)->ptr = m;
+ remap_and_issue(tc, bio, data_block);
+
+ } else {
+ int r;
+ struct dm_io_region to;
+
+ to.bdev = tc->pool_dev->bdev;
+ to.sector = data_block * pool->sectors_per_block;
+ to.count = pool->sectors_per_block;
+
+ r = dm_kcopyd_zero(pool->copier, 1, &to, 0, copy_complete, m);
+ if (r < 0) {
+ mempool_free(m, pool->mapping_pool);
+ DMERR("dm_kcopyd_zero() failed");
+ cell_error(cell);
+ }
+ }
+}
+
+static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
+{
+ int r;
+ dm_block_t free_blocks;
+ unsigned long flags;
+ struct pool *pool = tc->pool;
+
+ r = dm_pool_get_free_block_count(pool->pmd, &free_blocks);
+ if (r)
+ return r;
+
+ if (free_blocks <= pool->low_water_blocks && !pool->low_water_triggered) {
+ DMWARN("%s: reached low water mark, sending event.",
+ dm_device_name(pool->pool_md));
+ spin_lock_irqsave(&pool->lock, flags);
+ pool->low_water_triggered = 1;
+ spin_unlock_irqrestore(&pool->lock, flags);
+ dm_table_event(pool->ti->table);
+ }
+
+ if (!free_blocks) {
+ if (pool->no_free_space)
+ return -ENOSPC;
+ else {
+ /*
+ * Try to commit to see if that will free up some
+ * more space.
+ */
+ r = dm_pool_commit_metadata(pool->pmd);
+ if (r) {
+ DMERR("%s: dm_pool_commit_metadata() failed, error = %d",
+ __func__, r);
+ return r;
+ }
+
+ r = dm_pool_get_free_block_count(pool->pmd, &free_blocks);
+ if (r)
+ return r;
+
+ /*
+ * If we still have no space we set a flag to avoid
+ * doing all this checking and return -ENOSPC.
+ */
+ if (!free_blocks) {
+ DMWARN("%s: no free space available.",
+ dm_device_name(pool->pool_md));
+ spin_lock_irqsave(&pool->lock, flags);
+ pool->no_free_space = 1;
+ spin_unlock_irqrestore(&pool->lock, flags);
+ return -ENOSPC;
+ }
+ }
+ }
+
+ r = dm_pool_alloc_data_block(pool->pmd, result);
+ if (r)
+ return r;
+
+ return 0;
+}
+
+/*
+ * If we have run out of space, queue bios until the device is
+ * resumed, presumably after having been reloaded with more space.
+ */
+static void retry_on_resume(struct bio *bio)
+{
+ struct thin_c *tc = dm_get_mapinfo(bio)->ptr;
+ struct pool *pool = tc->pool;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ bio_list_add(&pool->retry_on_resume_list, bio);
+ spin_unlock_irqrestore(&pool->lock, flags);
+}
+
+static void no_space(struct cell *cell)
+{
+ struct bio *bio;
+ struct bio_list bios;
+
+ bio_list_init(&bios);
+ cell_release(cell, &bios);
+
+ while ((bio = bio_list_pop(&bios)))
+ retry_on_resume(bio);
+}
+
+static void break_sharing(struct thin_c *tc, struct bio *bio, dm_block_t block,
+ struct cell_key *key,
+ struct dm_thin_lookup_result *lookup_result,
+ struct cell *cell)
+{
+ int r;
+ dm_block_t data_block;
+
+ r = alloc_data_block(tc, &data_block);
+ switch (r) {
+ case 0:
+ schedule_copy(tc, block, lookup_result->block,
+ data_block, cell, bio);
+ break;
+
+ case -ENOSPC:
+ no_space(cell);
+ break;
+
+ default:
+ DMERR("%s: alloc_data_block() failed, error = %d", __func__, r);
+ cell_error(cell);
+ break;
+ }
+}
+
+static void process_shared_bio(struct thin_c *tc, struct bio *bio,
+ dm_block_t block,
+ struct dm_thin_lookup_result *lookup_result)
+{
+ struct cell *cell;
+ struct pool *pool = tc->pool;
+ struct cell_key key;
+
+ /*
+ * If cell is already occupied, then sharing is already in the process
+ * of being broken so we have nothing further to do here.
+ */
+ build_data_key(tc->td, lookup_result->block, &key);
+ if (bio_detain(pool->prison, &key, bio, &cell))
+ return;
+
+ if (bio_data_dir(bio) == WRITE)
+ break_sharing(tc, bio, block, &key, lookup_result, cell);
+ else {
+ struct endio_hook *h;
+ h = mempool_alloc(pool->endio_hook_pool, GFP_NOIO);
+
+ h->tc = tc;
+ h->entry = ds_inc(&pool->ds);
+ save_and_set_endio(bio, &h->saved_bi_end_io, shared_read_endio);
+ dm_get_mapinfo(bio)->ptr = h;
+
+ cell_release_singleton(cell, bio);
+ remap_and_issue(tc, bio, lookup_result->block);
+ }
+}
+
+static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block,
+ struct cell *cell)
+{
+ int r;
+ dm_block_t data_block;
+
+ /*
+ * Remap empty bios (flushes) immediately, without provisioning.
+ */
+ if (!bio->bi_size) {
+ cell_release_singleton(cell, bio);
+ remap_and_issue(tc, bio, 0);
+ return;
+ }
+
+ /*
+ * Fill read bios with zeroes and complete them immediately.
+ */
+ if (bio_data_dir(bio) == READ) {
+ zero_fill_bio(bio);
+ cell_release_singleton(cell, bio);
+ bio_endio(bio, 0);
+ return;
+ }
+
+ r = alloc_data_block(tc, &data_block);
+ switch (r) {
+ case 0:
+ schedule_zero(tc, block, data_block, cell, bio);
+ break;
+
+ case -ENOSPC:
+ no_space(cell);
+ break;
+
+ default:
+ DMERR("%s: alloc_data_block() failed, error = %d", __func__, r);
+ cell_error(cell);
+ break;
+ }
+}
+
+static void process_bio(struct thin_c *tc, struct bio *bio)
+{
+ int r;
+ dm_block_t block = get_bio_block(tc, bio);
+ struct cell *cell;
+ struct cell_key key;
+ struct dm_thin_lookup_result lookup_result;
+
+ /*
+ * If cell is already occupied, then the block is already
+ * being provisioned so we have nothing further to do here.
+ */
+ build_virtual_key(tc->td, block, &key);
+ if (bio_detain(tc->pool->prison, &key, bio, &cell))
+ return;
+
+ r = dm_thin_find_block(tc->td, block, 1, &lookup_result);
+ switch (r) {
+ case 0:
+ /*
+ * We can release this cell now. This thread is the only
+ * one that puts bios into a cell, and we know there were
+ * no preceding bios.
+ */
+ /*
+ * TODO: this will probably have to change when discard goes
+ * back in.
+ */
+ cell_release_singleton(cell, bio);
+
+ if (lookup_result.shared)
+ process_shared_bio(tc, bio, block, &lookup_result);
+ else
+ remap_and_issue(tc, bio, lookup_result.block);
+ break;
+
+ case -ENODATA:
+ provision_block(tc, bio, block, cell);
+ break;
+
+ default:
+ DMERR("dm_thin_find_block() failed, error = %d", r);
+ bio_io_error(bio);
+ break;
+ }
+}
+
+static void process_deferred_bios(struct pool *pool)
+{
+ unsigned long flags;
+ struct bio *bio;
+ struct bio_list bios;
+ int r;
+
+ bio_list_init(&bios);
+
+ spin_lock_irqsave(&pool->lock, flags);
+ bio_list_merge(&bios, &pool->deferred_bios);
+ bio_list_init(&pool->deferred_bios);
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ while ((bio = bio_list_pop(&bios))) {
+ struct thin_c *tc = dm_get_mapinfo(bio)->ptr;
+ /*
+ * If we've got no free new_mapping structs, and processing
+ * this bio might require one, we pause until there are some
+ * prepared mappings to process.
+ */
+ if (ensure_next_mapping(pool)) {
+ spin_lock_irqsave(&pool->lock, flags);
+ bio_list_merge(&pool->deferred_bios, &bios);
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ break;
+ }
+ process_bio(tc, bio);
+ }
+
+ /*
+ * If there are any deferred flush bios, we must commit
+ * the metadata before issuing them.
+ */
+ bio_list_init(&bios);
+ spin_lock_irqsave(&pool->lock, flags);
+ bio_list_merge(&bios, &pool->deferred_flush_bios);
+ bio_list_init(&pool->deferred_flush_bios);
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ if (bio_list_empty(&bios))
+ return;
+
+ r = dm_pool_commit_metadata(pool->pmd);
+ if (r) {
+ DMERR("%s: dm_pool_commit_metadata() failed, error = %d",
+ __func__, r);
+ while ((bio = bio_list_pop(&bios)))
+ bio_io_error(bio);
+ return;
+ }
+
+ while ((bio = bio_list_pop(&bios)))
+ generic_make_request(bio);
+}
+
+static void do_worker(struct work_struct *ws)
+{
+ struct pool *pool = container_of(ws, struct pool, worker);
+
+ process_prepared_mappings(pool);
+ process_deferred_bios(pool);
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Mapping functions.
+ */
+
+/*
+ * Called only while mapping a thin bio to hand it over to the workqueue.
+ */
+static void thin_defer_bio(struct thin_c *tc, struct bio *bio)
+{
+ unsigned long flags;
+ struct pool *pool = tc->pool;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ bio_list_add(&pool->deferred_bios, bio);
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ wake_worker(pool);
+}
+
+/*
+ * Non-blocking function called from the thin target's map function.
+ */
+static int thin_bio_map(struct dm_target *ti, struct bio *bio,
+ union map_info *map_context)
+{
+ int r;
+ struct thin_c *tc = ti->private;
+ dm_block_t block = get_bio_block(tc, bio);
+ struct dm_thin_device *td = tc->td;
+ struct dm_thin_lookup_result result;
+
+ /*
+ * Save the thin context for easy access from the deferred bio later.
+ */
+ map_context->ptr = tc;
+
+ if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+ thin_defer_bio(tc, bio);
+ return DM_MAPIO_SUBMITTED;
+ }
+
+ r = dm_thin_find_block(td, block, 0, &result);
+
+ /*
+ * Note that we defer readahead too.
+ */
+ switch (r) {
+ case 0:
+ if (unlikely(result.shared)) {
+ /*
+ * We have a race condition here between the
+ * result.shared value returned by the lookup and
+ * snapshot creation, which may cause new
+ * sharing.
+ *
+ * To avoid this always quiesce the origin before
+ * taking the snap. You want to do this anyway to
+ * ensure a consistent application view
+ * (i.e. lockfs).
+ *
+ * More distant ancestors are irrelevant. The
+ * shared flag will be set in their case.
+ */
+ thin_defer_bio(tc, bio);
+ r = DM_MAPIO_SUBMITTED;
+ } else {
+ remap(tc, bio, result.block);
+ r = DM_MAPIO_REMAPPED;
+ }
+ break;
+
+ case -ENODATA:
+ /*
+ * In future, the failed dm_thin_find_block above could
+ * provide the hint to load the metadata into cache.
+ */
+ case -EWOULDBLOCK:
+ thin_defer_bio(tc, bio);
+ r = DM_MAPIO_SUBMITTED;
+ break;
+ }
+
+ return r;
+}
+
+static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
+{
+ int r;
+ unsigned long flags;
+ struct pool_c *pt = container_of(cb, struct pool_c, callbacks);
+
+ spin_lock_irqsave(&pt->pool->lock, flags);
+ r = !bio_list_empty(&pt->pool->retry_on_resume_list);
+ spin_unlock_irqrestore(&pt->pool->lock, flags);
+
+ if (!r) {
+ struct request_queue *q = bdev_get_queue(pt->data_dev->bdev);
+ r = bdi_congested(&q->backing_dev_info, bdi_bits);
+ }
+
+ return r;
+}
+
+static void __requeue_bios(struct pool *pool)
+{
+ bio_list_merge(&pool->deferred_bios, &pool->retry_on_resume_list);
+ bio_list_init(&pool->retry_on_resume_list);
+}
+
+/*----------------------------------------------------------------
+ * Binding of control targets to a pool object
+ *--------------------------------------------------------------*/
+static int bind_control_target(struct pool *pool, struct dm_target *ti)
+{
+ struct pool_c *pt = ti->private;
+
+ pool->ti = ti;
+ pool->low_water_blocks = pt->low_water_blocks;
+ pool->zero_new_blocks = pt->zero_new_blocks;
+
+ return 0;
+}
+
+static void unbind_control_target(struct pool *pool, struct dm_target *ti)
+{
+ if (pool->ti == ti)
+ pool->ti = NULL;
+}
+
+/*----------------------------------------------------------------
+ * Pool creation
+ *--------------------------------------------------------------*/
+static void __pool_destroy(struct pool *pool)
+{
+ __pool_table_remove(pool);
+
+ if (dm_pool_metadata_close(pool->pmd) < 0)
+ DMWARN("%s: dm_pool_metadata_close() failed.", __func__);
+
+ prison_destroy(pool->prison);
+ dm_kcopyd_client_destroy(pool->copier);
+
+ if (pool->wq)
+ destroy_workqueue(pool->wq);
+
+ if (pool->next_mapping)
+ mempool_free(pool->next_mapping, pool->mapping_pool);
+ mempool_destroy(pool->mapping_pool);
+ mempool_destroy(pool->endio_hook_pool);
+ kfree(pool);
+}
+
+static struct pool *pool_create(struct mapped_device *pool_md,
+ struct block_device *metadata_dev,
+ unsigned long block_size, char **error)
+{
+ int r;
+ void *err_p;
+ struct pool *pool;
+ struct dm_pool_metadata *pmd;
+
+ pmd = dm_pool_metadata_open(metadata_dev, block_size);
+ if (IS_ERR(pmd)) {
+ *error = "Error creating metadata object";
+ return (struct pool *)pmd;
+ }
+
+ pool = kmalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool) {
+ *error = "Error allocating memory for pool";
+ err_p = ERR_PTR(-ENOMEM);
+ goto bad_pool;
+ }
+
+ pool->pmd = pmd;
+ pool->sectors_per_block = block_size;
+ pool->block_shift = ffs(block_size) - 1;
+ pool->offset_mask = block_size - 1;
+ pool->low_water_blocks = 0;
+ pool->zero_new_blocks = 1;
+ pool->prison = prison_create(PRISON_CELLS);
+ if (!pool->prison) {
+ *error = "Error creating pool's bio prison";
+ err_p = ERR_PTR(-ENOMEM);
+ goto bad_prison;
+ }
+
+ pool->copier = dm_kcopyd_client_create();
+ if (IS_ERR(pool->copier)) {
+ r = PTR_ERR(pool->copier);
+ *error = "Error creating pool's kcopyd client";
+ err_p = ERR_PTR(r);
+ goto bad_kcopyd_client;
+ }
+
+ /*
+ * Create singlethreaded workqueue that will service all devices
+ * that use this metadata.
+ */
+ pool->wq = alloc_ordered_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM);
+ if (!pool->wq) {
+ *error = "Error creating pool's workqueue";
+ err_p = ERR_PTR(-ENOMEM);
+ goto bad_wq;
+ }
+
+ INIT_WORK(&pool->worker, do_worker);
+ spin_lock_init(&pool->lock);
+ bio_list_init(&pool->deferred_bios);
+ bio_list_init(&pool->deferred_flush_bios);
+ INIT_LIST_HEAD(&pool->prepared_mappings);
+ pool->low_water_triggered = 0;
+ pool->no_free_space = 0;
+ bio_list_init(&pool->retry_on_resume_list);
+ ds_init(&pool->ds);
+
+ pool->next_mapping = NULL;
+ pool->mapping_pool =
+ mempool_create_kmalloc_pool(MAPPING_POOL_SIZE, sizeof(struct new_mapping));
+ if (!pool->mapping_pool) {
+ *error = "Error creating pool's mapping mempool";
+ err_p = ERR_PTR(-ENOMEM);
+ goto bad_mapping_pool;
+ }
+
+ pool->endio_hook_pool =
+ mempool_create_kmalloc_pool(ENDIO_HOOK_POOL_SIZE, sizeof(struct endio_hook));
+ if (!pool->endio_hook_pool) {
+ *error = "Error creating pool's endio_hook mempool";
+ err_p = ERR_PTR(-ENOMEM);
+ goto bad_endio_hook_pool;
+ }
+ pool->ref_count = 1;
+ pool->pool_md = pool_md;
+ pool->md_dev = metadata_dev;
+ __pool_table_insert(pool);
+
+ return pool;
+
+bad_endio_hook_pool:
+ mempool_destroy(pool->mapping_pool);
+bad_mapping_pool:
+ destroy_workqueue(pool->wq);
+bad_wq:
+ dm_kcopyd_client_destroy(pool->copier);
+bad_kcopyd_client:
+ prison_destroy(pool->prison);
+bad_prison:
+ kfree(pool);
+bad_pool:
+ if (dm_pool_metadata_close(pmd))
+ DMWARN("%s: dm_pool_metadata_close() failed.", __func__);
+
+ return err_p;
+}
+
+static void __pool_inc(struct pool *pool)
+{
+ BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex));
+ pool->ref_count++;
+}
+
+static void __pool_dec(struct pool *pool)
+{
+ BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex));
+ BUG_ON(!pool->ref_count);
+ if (!--pool->ref_count)
+ __pool_destroy(pool);
+}
+
+static struct pool *__pool_find(struct mapped_device *pool_md,
+ struct block_device *metadata_dev,
+ unsigned long block_size, char **error)
+{
+ struct pool *pool = __pool_table_lookup_metadata_dev(metadata_dev);
+
+ if (pool) {
+ if (pool->pool_md != pool_md)
+ return ERR_PTR(-EBUSY);
+ __pool_inc(pool);
+
+ } else {
+ pool = __pool_table_lookup(pool_md);
+ if (pool) {
+ if (pool->md_dev != metadata_dev)
+ return ERR_PTR(-EINVAL);
+ __pool_inc(pool);
+
+ } else
+ pool = pool_create(pool_md, metadata_dev, block_size, error);
+ }
+
+ return pool;
+}
+
+/*----------------------------------------------------------------
+ * Pool target methods
+ *--------------------------------------------------------------*/
+static void pool_dtr(struct dm_target *ti)
+{
+ struct pool_c *pt = ti->private;
+
+ mutex_lock(&dm_thin_pool_table.mutex);
+
+ unbind_control_target(pt->pool, ti);
+ __pool_dec(pt->pool);
+ dm_put_device(ti, pt->metadata_dev);
+ dm_put_device(ti, pt->data_dev);
+ kfree(pt);
+
+ mutex_unlock(&dm_thin_pool_table.mutex);
+}
+
+struct pool_features {
+ unsigned zero_new_blocks:1;
+};
+
+static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf,
+ struct dm_target *ti)
+{
+ int r;
+ unsigned argc;
+ const char *arg_name;
+
+ static struct dm_arg _args[] = {
+ {0, 1, "Invalid number of pool feature arguments"},
+ };
+
+ /*
+ * No feature arguments supplied.
+ */
+ if (!as->argc)
+ return 0;
+
+ r = dm_read_arg_group(_args, as, &argc, &ti->error);
+ if (r)
+ return -EINVAL;
+
+ while (argc && !r) {
+ arg_name = dm_shift_arg(as);
+ argc--;
+
+ if (!strcasecmp(arg_name, "skip_block_zeroing")) {
+ pf->zero_new_blocks = 0;
+ continue;
+ }
+
+ ti->error = "Unrecognised pool feature requested";
+ r = -EINVAL;
+ }
+
+ return r;
+}
+
+/*
+ * thin-pool <metadata dev> <data dev>
+ * <data block size (sectors)>
+ * <low water mark (blocks)>
+ * [<#feature args> [<arg>]*]
+ *
+ * Optional feature arguments are:
+ * skip_block_zeroing: skips the zeroing of newly-provisioned blocks.
+ */
+static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
+{
+ int r;
+ struct pool_c *pt;
+ struct pool *pool;
+ struct pool_features pf;
+ struct dm_arg_set as;
+ struct dm_dev *data_dev;
+ unsigned long block_size;
+ dm_block_t low_water_blocks;
+ struct dm_dev *metadata_dev;
+ sector_t metadata_dev_size;
+
+ /*
+ * FIXME Remove validation from scope of lock.
+ */
+ mutex_lock(&dm_thin_pool_table.mutex);
+
+ if (argc < 4) {
+ ti->error = "Invalid argument count";
+ r = -EINVAL;
+ goto out_unlock;
+ }
+ as.argc = argc;
+ as.argv = argv;
+
+ r = dm_get_device(ti, argv[0], FMODE_READ | FMODE_WRITE, &metadata_dev);
+ if (r) {
+ ti->error = "Error opening metadata block device";
+ goto out_unlock;
+ }
+
+ metadata_dev_size = i_size_read(metadata_dev->bdev->bd_inode) >> SECTOR_SHIFT;
+ if (metadata_dev_size > METADATA_DEV_MAX_SECTORS) {
+ ti->error = "Metadata device is too large";
+ r = -EINVAL;
+ goto out_metadata;
+ }
+
+ r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev);
+ if (r) {
+ ti->error = "Error getting data device";
+ goto out_metadata;
+ }
+
+ if (kstrtoul(argv[2], 10, &block_size) || !block_size ||
+ block_size < DATA_DEV_BLOCK_SIZE_MIN_SECTORS ||
+ block_size > DATA_DEV_BLOCK_SIZE_MAX_SECTORS ||
+ !is_power_of_2(block_size)) {
+ ti->error = "Invalid block size";
+ r = -EINVAL;
+ goto out;
+ }
+
+ if (kstrtoull(argv[3], 10, (unsigned long long *)&low_water_blocks)) {
+ ti->error = "Invalid low water mark";
+ r = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Set default pool features.
+ */
+ memset(&pf, 0, sizeof(pf));
+ pf.zero_new_blocks = 1;
+
+ dm_consume_args(&as, 4);
+ r = parse_pool_features(&as, &pf, ti);
+ if (r)
+ goto out;
+
+ pt = kzalloc(sizeof(*pt), GFP_KERNEL);
+ if (!pt) {
+ r = -ENOMEM;
+ goto out;
+ }
+
+ pool = __pool_find(dm_table_get_md(ti->table), metadata_dev->bdev,
+ block_size, &ti->error);
+ if (IS_ERR(pool)) {
+ r = PTR_ERR(pool);
+ goto out_free_pt;
+ }
+
+ pt->pool = pool;
+ pt->ti = ti;
+ pt->metadata_dev = metadata_dev;
+ pt->data_dev = data_dev;
+ pt->low_water_blocks = low_water_blocks;
+ pt->zero_new_blocks = pf.zero_new_blocks;
+ ti->num_flush_requests = 1;
+ ti->num_discard_requests = 0;
+ ti->private = pt;
+
+ pt->callbacks.congested_fn = pool_is_congested;
+ dm_table_add_target_callbacks(ti->table, &pt->callbacks);
+
+ mutex_unlock(&dm_thin_pool_table.mutex);
+
+ return 0;
+
+out_free_pt:
+ kfree(pt);
+out:
+ dm_put_device(ti, data_dev);
+out_metadata:
+ dm_put_device(ti, metadata_dev);
+out_unlock:
+ mutex_unlock(&dm_thin_pool_table.mutex);
+
+ return r;
+}
+
+static int pool_map(struct dm_target *ti, struct bio *bio,
+ union map_info *map_context)
+{
+ int r;
+ struct pool_c *pt = ti->private;
+ struct pool *pool = pt->pool;
+ unsigned long flags;
+
+ /*
+ * As this is a singleton target, ti->begin is always zero.
+ */
+ spin_lock_irqsave(&pool->lock, flags);
+ bio->bi_bdev = pt->data_dev->bdev;
+ r = DM_MAPIO_REMAPPED;
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ return r;
+}
+
+/*
+ * Retrieves the number of blocks of the data device from
+ * the superblock and compares it to the actual device size,
+ * thus resizing the data device in case it has grown.
+ *
+ * This both copes with opening preallocated data devices in the ctr
+ * being followed by a resume
+ * -and-
+ * calling the resume method individually after userspace has
+ * grown the data device in reaction to a table event.
+ */
+static int pool_preresume(struct dm_target *ti)
+{
+ int r;
+ struct pool_c *pt = ti->private;
+ struct pool *pool = pt->pool;
+ dm_block_t data_size, sb_data_size;
+
+ /*
+ * Take control of the pool object.
+ */
+ r = bind_control_target(pool, ti);
+ if (r)
+ return r;
+
+ data_size = ti->len >> pool->block_shift;
+ r = dm_pool_get_data_dev_size(pool->pmd, &sb_data_size);
+ if (r) {
+ DMERR("failed to retrieve data device size");
+ return r;
+ }
+
+ if (data_size < sb_data_size) {
+ DMERR("pool target too small, is %llu blocks (expected %llu)",
+ data_size, sb_data_size);
+ return -EINVAL;
+
+ } else if (data_size > sb_data_size) {
+ r = dm_pool_resize_data_dev(pool->pmd, data_size);
+ if (r) {
+ DMERR("failed to resize data device");
+ return r;
+ }
+
+ r = dm_pool_commit_metadata(pool->pmd);
+ if (r) {
+ DMERR("%s: dm_pool_commit_metadata() failed, error = %d",
+ __func__, r);
+ return r;
+ }
+ }
+
+ return 0;
+}
+
+static void pool_resume(struct dm_target *ti)
+{
+ struct pool_c *pt = ti->private;
+ struct pool *pool = pt->pool;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ pool->low_water_triggered = 0;
+ pool->no_free_space = 0;
+ __requeue_bios(pool);
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ wake_worker(pool);
+}
+
+static void pool_postsuspend(struct dm_target *ti)
+{
+ int r;
+ struct pool_c *pt = ti->private;
+ struct pool *pool = pt->pool;
+
+ flush_workqueue(pool->wq);
+
+ r = dm_pool_commit_metadata(pool->pmd);
+ if (r < 0) {
+ DMERR("%s: dm_pool_commit_metadata() failed, error = %d",
+ __func__, r);
+ /* FIXME: invalidate device? error the next FUA or FLUSH bio ?*/
+ }
+}
+
+static int check_arg_count(unsigned argc, unsigned args_required)
+{
+ if (argc != args_required) {
+ DMWARN("Message received with %u arguments instead of %u.",
+ argc, args_required);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int read_dev_id(char *arg, dm_thin_id *dev_id, int warning)
+{
+ if (!kstrtoull(arg, 10, (unsigned long long *)dev_id) &&
+ *dev_id <= MAX_DEV_ID)
+ return 0;
+
+ if (warning)
+ DMWARN("Message received with invalid device id: %s", arg);
+
+ return -EINVAL;
+}
+
+static int process_create_thin_mesg(unsigned argc, char **argv, struct pool *pool)
+{
+ dm_thin_id dev_id;
+ int r;
+
+ r = check_arg_count(argc, 2);
+ if (r)
+ return r;
+
+ r = read_dev_id(argv[1], &dev_id, 1);
+ if (r)
+ return r;
+
+ r = dm_pool_create_thin(pool->pmd, dev_id);
+ if (r) {
+ DMWARN("Creation of new thinly-provisioned device with id %s failed.",
+ argv[1]);
+ return r;
+ }
+
+ return 0;
+}
+
+static int process_create_snap_mesg(unsigned argc, char **argv, struct pool *pool)
+{
+ dm_thin_id dev_id;
+ dm_thin_id origin_dev_id;
+ int r;
+
+ r = check_arg_count(argc, 3);
+ if (r)
+ return r;
+
+ r = read_dev_id(argv[1], &dev_id, 1);
+ if (r)
+ return r;
+
+ r = read_dev_id(argv[2], &origin_dev_id, 1);
+ if (r)
+ return r;
+
+ r = dm_pool_create_snap(pool->pmd, dev_id, origin_dev_id);
+ if (r) {
+ DMWARN("Creation of new snapshot %s of device %s failed.",
+ argv[1], argv[2]);
+ return r;
+ }
+
+ return 0;
+}
+
+static int process_delete_mesg(unsigned argc, char **argv, struct pool *pool)
+{
+ dm_thin_id dev_id;
+ int r;
+
+ r = check_arg_count(argc, 2);
+ if (r)
+ return r;
+
+ r = read_dev_id(argv[1], &dev_id, 1);
+ if (r)
+ return r;
+
+ r = dm_pool_delete_thin_device(pool->pmd, dev_id);
+ if (r)
+ DMWARN("Deletion of thin device %s failed.", argv[1]);
+
+ return r;
+}
+
+static int process_set_transaction_id_mesg(unsigned argc, char **argv, struct pool *pool)
+{
+ dm_thin_id old_id, new_id;
+ int r;
+
+ r = check_arg_count(argc, 3);
+ if (r)
+ return r;
+
+ if (kstrtoull(argv[1], 10, (unsigned long long *)&old_id)) {
+ DMWARN("set_transaction_id message: Unrecognised id %s.", argv[1]);
+ return -EINVAL;
+ }
+
+ if (kstrtoull(argv[2], 10, (unsigned long long *)&new_id)) {
+ DMWARN("set_transaction_id message: Unrecognised new id %s.", argv[2]);
+ return -EINVAL;
+ }
+
+ r = dm_pool_set_metadata_transaction_id(pool->pmd, old_id, new_id);
+ if (r) {
+ DMWARN("Failed to change transaction id from %s to %s.",
+ argv[1], argv[2]);
+ return r;
+ }
+
+ return 0;
+}
+
+/*
+ * Messages supported:
+ * create_thin <dev_id>
+ * create_snap <dev_id> <origin_id>
+ * delete <dev_id>
+ * trim <dev_id> <new_size_in_sectors>
+ * set_transaction_id <current_trans_id> <new_trans_id>
+ */
+static int pool_message(struct dm_target *ti, unsigned argc, char **argv)
+{
+ int r = -EINVAL;
+ struct pool_c *pt = ti->private;
+ struct pool *pool = pt->pool;
+
+ if (!strcasecmp(argv[0], "create_thin"))
+ r = process_create_thin_mesg(argc, argv, pool);
+
+ else if (!strcasecmp(argv[0], "create_snap"))
+ r = process_create_snap_mesg(argc, argv, pool);
+
+ else if (!strcasecmp(argv[0], "delete"))
+ r = process_delete_mesg(argc, argv, pool);
+
+ else if (!strcasecmp(argv[0], "set_transaction_id"))
+ r = process_set_transaction_id_mesg(argc, argv, pool);
+
+ else
+ DMWARN("Unrecognised thin pool target message received: %s", argv[0]);
+
+ if (!r) {
+ r = dm_pool_commit_metadata(pool->pmd);
+ if (r)
+ DMERR("%s message: dm_pool_commit_metadata() failed, error = %d",
+ argv[0], r);
+ }
+
+ return r;
+}
+
+/*
+ * Status line is:
+ * <transaction id> <used metadata sectors>/<total metadata sectors>
+ * <used data sectors>/<total data sectors> <held metadata root>
+ */
+static int pool_status(struct dm_target *ti, status_type_t type,
+ char *result, unsigned maxlen)
+{
+ int r;
+ unsigned sz = 0;
+ uint64_t transaction_id;
+ dm_block_t nr_free_blocks_data;
+ dm_block_t nr_free_blocks_metadata;
+ dm_block_t nr_blocks_data;
+ dm_block_t nr_blocks_metadata;
+ dm_block_t held_root;
+ char buf[BDEVNAME_SIZE];
+ char buf2[BDEVNAME_SIZE];
+ struct pool_c *pt = ti->private;
+ struct pool *pool = pt->pool;
+
+ switch (type) {
+ case STATUSTYPE_INFO:
+ r = dm_pool_get_metadata_transaction_id(pool->pmd,
+ &transaction_id);
+ if (r)
+ return r;
+
+ r = dm_pool_get_free_metadata_block_count(pool->pmd,
+ &nr_free_blocks_metadata);
+ if (r)
+ return r;
+
+ r = dm_pool_get_metadata_dev_size(pool->pmd, &nr_blocks_metadata);
+ if (r)
+ return r;
+
+ r = dm_pool_get_free_block_count(pool->pmd,
+ &nr_free_blocks_data);
+ if (r)
+ return r;
+
+ r = dm_pool_get_data_dev_size(pool->pmd, &nr_blocks_data);
+ if (r)
+ return r;
+
+ r = dm_pool_get_held_metadata_root(pool->pmd, &held_root);
+ if (r)
+ return r;
+
+ DMEMIT("%llu %llu/%llu %llu/%llu ",
+ (unsigned long long)transaction_id,
+ (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
+ (unsigned long long)nr_blocks_metadata,
+ (unsigned long long)(nr_blocks_data - nr_free_blocks_data),
+ (unsigned long long)nr_blocks_data);
+
+ if (held_root)
+ DMEMIT("%llu", held_root);
+ else
+ DMEMIT("-");
+
+ break;
+
+ case STATUSTYPE_TABLE:
+ DMEMIT("%s %s %lu %llu ",
+ format_dev_t(buf, pt->metadata_dev->bdev->bd_dev),
+ format_dev_t(buf2, pt->data_dev->bdev->bd_dev),
+ (unsigned long)pool->sectors_per_block,
+ (unsigned long long)pt->low_water_blocks);
+
+ DMEMIT("%u ", !pool->zero_new_blocks);
+
+ if (!pool->zero_new_blocks)
+ DMEMIT("skip_block_zeroing ");
+ break;
+ }
+
+ return 0;
+}
+
+static int pool_iterate_devices(struct dm_target *ti,
+ iterate_devices_callout_fn fn, void *data)
+{
+ struct pool_c *pt = ti->private;
+
+ return fn(ti, pt->data_dev, 0, ti->len, data);
+}
+
+static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
+ struct bio_vec *biovec, int max_size)
+{
+ struct pool_c *pt = ti->private;
+ struct request_queue *q = bdev_get_queue(pt->data_dev->bdev);
+
+ if (!q->merge_bvec_fn)
+ return max_size;
+
+ bvm->bi_bdev = pt->data_dev->bdev;
+
+ return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
+}
+
+static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+ struct pool_c *pt = ti->private;
+ struct pool *pool = pt->pool;
+
+ blk_limits_io_min(limits, 0);
+ blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT);
+}
+
+static struct target_type pool_target = {
+ .name = "thin-pool",
+ .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
+ DM_TARGET_IMMUTABLE,
+ .version = {1, 0, 0},
+ .module = THIS_MODULE,
+ .ctr = pool_ctr,
+ .dtr = pool_dtr,
+ .map = pool_map,
+ .postsuspend = pool_postsuspend,
+ .preresume = pool_preresume,
+ .resume = pool_resume,
+ .message = pool_message,
+ .status = pool_status,
+ .merge = pool_merge,
+ .iterate_devices = pool_iterate_devices,
+ .io_hints = pool_io_hints,
+};
+
+/*----------------------------------------------------------------
+ * Thin target methods
+ *--------------------------------------------------------------*/
+static void thin_dtr(struct dm_target *ti)
+{
+ struct thin_c *tc = ti->private;
+
+ mutex_lock(&dm_thin_pool_table.mutex);
+
+ __pool_dec(tc->pool);
+ dm_pool_close_thin_device(tc->td);
+ dm_put_device(ti, tc->pool_dev);
+ kfree(tc);
+
+ mutex_unlock(&dm_thin_pool_table.mutex);
+}
+
+/*
+ * Thin target parameters:
+ *
+ * <pool_dev> <dev_id>
+ *
+ * pool_dev: the path to the pool (eg, /dev/mapper/my_pool)
+ * dev_id: the internal device identifier
+ */
+static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
+{
+ int r;
+ struct thin_c *tc;
+ struct dm_dev *pool_dev;
+ struct mapped_device *pool_md;
+
+ mutex_lock(&dm_thin_pool_table.mutex);
+
+ if (argc != 2) {
+ ti->error = "Invalid argument count";
+ r = -EINVAL;
+ goto out_unlock;
+ }
+
+ tc = ti->private = kzalloc(sizeof(*tc), GFP_KERNEL);
+ if (!tc) {
+ ti->error = "Out of memory";
+ r = -ENOMEM;
+ goto out_unlock;
+ }
+
+ r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &pool_dev);
+ if (r) {
+ ti->error = "Error opening pool device";
+ goto bad_pool_dev;
+ }
+ tc->pool_dev = pool_dev;
+
+ if (read_dev_id(argv[1], (unsigned long long *)&tc->dev_id, 0)) {
+ ti->error = "Invalid device id";
+ r = -EINVAL;
+ goto bad_common;
+ }
+
+ pool_md = dm_get_md(tc->pool_dev->bdev->bd_dev);
+ if (!pool_md) {
+ ti->error = "Couldn't get pool mapped device";
+ r = -EINVAL;
+ goto bad_common;
+ }
+
+ tc->pool = __pool_table_lookup(pool_md);
+ if (!tc->pool) {
+ ti->error = "Couldn't find pool object";
+ r = -EINVAL;
+ goto bad_pool_lookup;
+ }
+ __pool_inc(tc->pool);
+
+ r = dm_pool_open_thin_device(tc->pool->pmd, tc->dev_id, &tc->td);
+ if (r) {
+ ti->error = "Couldn't open thin internal device";
+ goto bad_thin_open;
+ }
+
+ ti->split_io = tc->pool->sectors_per_block;
+ ti->num_flush_requests = 1;
+ ti->num_discard_requests = 0;
+ ti->discards_supported = 0;
+
+ dm_put(pool_md);
+
+ mutex_unlock(&dm_thin_pool_table.mutex);
+
+ return 0;
+
+bad_thin_open:
+ __pool_dec(tc->pool);
+bad_pool_lookup:
+ dm_put(pool_md);
+bad_common:
+ dm_put_device(ti, tc->pool_dev);
+bad_pool_dev:
+ kfree(tc);
+out_unlock:
+ mutex_unlock(&dm_thin_pool_table.mutex);
+
+ return r;
+}
+
+static int thin_map(struct dm_target *ti, struct bio *bio,
+ union map_info *map_context)
+{
+ bio->bi_sector -= ti->begin;
+
+ return thin_bio_map(ti, bio, map_context);
+}
+
+static void thin_postsuspend(struct dm_target *ti)
+{
+ if (dm_noflush_suspending(ti))
+ requeue_io((struct thin_c *)ti->private);
+}
+
+/*
+ * <nr mapped sectors> <highest mapped sector>
+ */
+static int thin_status(struct dm_target *ti, status_type_t type,
+ char *result, unsigned maxlen)
+{
+ int r;
+ ssize_t sz = 0;
+ dm_block_t mapped, highest;
+ char buf[BDEVNAME_SIZE];
+ struct thin_c *tc = ti->private;
+
+ if (!tc->td)
+ DMEMIT("-");
+ else {
+ switch (type) {
+ case STATUSTYPE_INFO:
+ r = dm_thin_get_mapped_count(tc->td, &mapped);
+ if (r)
+ return r;
+
+ r = dm_thin_get_highest_mapped_block(tc->td, &highest);
+ if (r < 0)
+ return r;
+
+ DMEMIT("%llu ", mapped * tc->pool->sectors_per_block);
+ if (r)
+ DMEMIT("%llu", ((highest + 1) *
+ tc->pool->sectors_per_block) - 1);
+ else
+ DMEMIT("-");
+ break;
+
+ case STATUSTYPE_TABLE:
+ DMEMIT("%s %lu",
+ format_dev_t(buf, tc->pool_dev->bdev->bd_dev),
+ (unsigned long) tc->dev_id);
+ break;
+ }
+ }
+
+ return 0;
+}
+
+static int thin_iterate_devices(struct dm_target *ti,
+ iterate_devices_callout_fn fn, void *data)
+{
+ dm_block_t blocks;
+ struct thin_c *tc = ti->private;
+
+ /*
+ * We can't call dm_pool_get_data_dev_size() since that blocks. So
+ * we follow a more convoluted path through to the pool's target.
+ */
+ if (!tc->pool->ti)
+ return 0; /* nothing is bound */
+
+ blocks = tc->pool->ti->len >> tc->pool->block_shift;
+ if (blocks)
+ return fn(ti, tc->pool_dev, 0, tc->pool->sectors_per_block * blocks, data);
+
+ return 0;
+}
+
+static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+ struct thin_c *tc = ti->private;
+
+ blk_limits_io_min(limits, 0);
+ blk_limits_io_opt(limits, tc->pool->sectors_per_block << SECTOR_SHIFT);
+}
+
+static struct target_type thin_target = {
+ .name = "thin",
+ .version = {1, 0, 0},
+ .module = THIS_MODULE,
+ .ctr = thin_ctr,
+ .dtr = thin_dtr,
+ .map = thin_map,
+ .postsuspend = thin_postsuspend,
+ .status = thin_status,
+ .iterate_devices = thin_iterate_devices,
+ .io_hints = thin_io_hints,
+};
+
+/*----------------------------------------------------------------*/
+
+static int __init dm_thin_init(void)
+{
+ int r;
+
+ pool_table_init();
+
+ r = dm_register_target(&thin_target);
+ if (r)
+ return r;
+
+ r = dm_register_target(&pool_target);
+ if (r)
+ dm_unregister_target(&thin_target);
+
+ return r;
+}
+
+static void dm_thin_exit(void)
+{
+ dm_unregister_target(&thin_target);
+ dm_unregister_target(&pool_target);
+}
+
+module_init(dm_thin_init);
+module_exit(dm_thin_exit);
+
+MODULE_DESCRIPTION(DM_NAME "device-mapper thin provisioning target");
+MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 52b39f3..6b6616a 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -25,6 +25,16 @@
#define DM_MSG_PREFIX "core"
+#ifdef CONFIG_PRINTK
+/*
+ * ratelimit state to be used in DMXXX_LIMIT().
+ */
+DEFINE_RATELIMIT_STATE(dm_ratelimit_state,
+ DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+EXPORT_SYMBOL(dm_ratelimit_state);
+#endif
+
/*
* Cookies are numeric values sent with CHANGE and REMOVE
* uevents while resuming, removing or renaming the device.
@@ -130,6 +140,8 @@
/* Protect queue and type against concurrent access. */
struct mutex type_lock;
+ struct target_type *immutable_target_type;
+
struct gendisk *disk;
char name[16];
@@ -2086,6 +2098,8 @@
write_lock_irqsave(&md->map_lock, flags);
old_map = md->map;
md->map = t;
+ md->immutable_target_type = dm_table_get_immutable_target_type(t);
+
dm_table_set_restrictions(t, q, limits);
if (merge_is_optional)
set_bit(DMF_MERGE_IS_OPTIONAL, &md->flags);
@@ -2156,6 +2170,11 @@
return md->type;
}
+struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
+{
+ return md->immutable_target_type;
+}
+
/*
* Fully initialize a request-based queue (->elevator, ->request_fn, etc).
*/
@@ -2231,6 +2250,7 @@
return md;
}
+EXPORT_SYMBOL_GPL(dm_get_md);
void *dm_get_mdptr(struct mapped_device *md)
{
@@ -2316,7 +2336,6 @@
while (1) {
set_current_state(interruptible);
- smp_mb();
if (!md_in_flight(md))
break;
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 6745dbd..b7dacd5 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -60,6 +60,7 @@
int dm_table_any_congested(struct dm_table *t, int bdi_bits);
int dm_table_any_busy_target(struct dm_table *t);
unsigned dm_table_get_type(struct dm_table *t);
+struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
bool dm_table_request_based(struct dm_table *t);
bool dm_table_supports_discards(struct dm_table *t);
int dm_table_alloc_md_mempools(struct dm_table *t);
@@ -72,6 +73,7 @@
void dm_unlock_md_type(struct mapped_device *md);
void dm_set_md_type(struct mapped_device *md, unsigned type);
unsigned dm_get_md_type(struct mapped_device *md);
+struct target_type *dm_get_immutable_target_type(struct mapped_device *md);
int dm_setup_md_queue(struct mapped_device *md);
diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig
new file mode 100644
index 0000000..ceb3590
--- /dev/null
+++ b/drivers/md/persistent-data/Kconfig
@@ -0,0 +1,8 @@
+config DM_PERSISTENT_DATA
+ tristate
+ depends on BLK_DEV_DM && EXPERIMENTAL
+ select LIBCRC32C
+ select DM_BUFIO
+ ---help---
+ Library providing immutable on-disk data structure support for
+ device-mapper targets such as the thin provisioning target.
diff --git a/drivers/md/persistent-data/Makefile b/drivers/md/persistent-data/Makefile
new file mode 100644
index 0000000..cfa95f6
--- /dev/null
+++ b/drivers/md/persistent-data/Makefile
@@ -0,0 +1,11 @@
+obj-$(CONFIG_DM_PERSISTENT_DATA) += dm-persistent-data.o
+dm-persistent-data-objs := \
+ dm-block-manager.o \
+ dm-space-map-checker.o \
+ dm-space-map-common.o \
+ dm-space-map-disk.o \
+ dm-space-map-metadata.o \
+ dm-transaction-manager.o \
+ dm-btree.o \
+ dm-btree-remove.o \
+ dm-btree-spine.o
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
new file mode 100644
index 0000000..0317ecd
--- /dev/null
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -0,0 +1,620 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+#include "dm-block-manager.h"
+#include "dm-persistent-data-internal.h"
+#include "../dm-bufio.h"
+
+#include <linux/crc32c.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/rwsem.h>
+#include <linux/device-mapper.h>
+#include <linux/stacktrace.h>
+
+#define DM_MSG_PREFIX "block manager"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * This is a read/write semaphore with a couple of differences.
+ *
+ * i) There is a restriction on the number of concurrent read locks that
+ * may be held at once. This is just an implementation detail.
+ *
+ * ii) Recursive locking attempts are detected and return EINVAL. A stack
+ * trace is also emitted for the previous lock aquisition.
+ *
+ * iii) Priority is given to write locks.
+ */
+#define MAX_HOLDERS 4
+#define MAX_STACK 10
+
+typedef unsigned long stack_entries[MAX_STACK];
+
+struct block_lock {
+ spinlock_t lock;
+ __s32 count;
+ struct list_head waiters;
+ struct task_struct *holders[MAX_HOLDERS];
+
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+ struct stack_trace traces[MAX_HOLDERS];
+ stack_entries entries[MAX_HOLDERS];
+#endif
+};
+
+struct waiter {
+ struct list_head list;
+ struct task_struct *task;
+ int wants_write;
+};
+
+static unsigned __find_holder(struct block_lock *lock,
+ struct task_struct *task)
+{
+ unsigned i;
+
+ for (i = 0; i < MAX_HOLDERS; i++)
+ if (lock->holders[i] == task)
+ break;
+
+ BUG_ON(i == MAX_HOLDERS);
+ return i;
+}
+
+/* call this *after* you increment lock->count */
+static void __add_holder(struct block_lock *lock, struct task_struct *task)
+{
+ unsigned h = __find_holder(lock, NULL);
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+ struct stack_trace *t;
+#endif
+
+ get_task_struct(task);
+ lock->holders[h] = task;
+
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+ t = lock->traces + h;
+ t->nr_entries = 0;
+ t->max_entries = MAX_STACK;
+ t->entries = lock->entries[h];
+ t->skip = 2;
+ save_stack_trace(t);
+#endif
+}
+
+/* call this *before* you decrement lock->count */
+static void __del_holder(struct block_lock *lock, struct task_struct *task)
+{
+ unsigned h = __find_holder(lock, task);
+ lock->holders[h] = NULL;
+ put_task_struct(task);
+}
+
+static int __check_holder(struct block_lock *lock)
+{
+ unsigned i;
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+ static struct stack_trace t;
+ static stack_entries entries;
+#endif
+
+ for (i = 0; i < MAX_HOLDERS; i++) {
+ if (lock->holders[i] == current) {
+ DMERR("recursive lock detected in pool metadata");
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+ DMERR("previously held here:");
+ print_stack_trace(lock->traces + i, 4);
+
+ DMERR("subsequent aquisition attempted here:");
+ t.nr_entries = 0;
+ t.max_entries = MAX_STACK;
+ t.entries = entries;
+ t.skip = 3;
+ save_stack_trace(&t);
+ print_stack_trace(&t, 4);
+#endif
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static void __wait(struct waiter *w)
+{
+ for (;;) {
+ set_task_state(current, TASK_UNINTERRUPTIBLE);
+
+ if (!w->task)
+ break;
+
+ schedule();
+ }
+
+ set_task_state(current, TASK_RUNNING);
+}
+
+static void __wake_waiter(struct waiter *w)
+{
+ struct task_struct *task;
+
+ list_del(&w->list);
+ task = w->task;
+ smp_mb();
+ w->task = NULL;
+ wake_up_process(task);
+}
+
+/*
+ * We either wake a few readers or a single writer.
+ */
+static void __wake_many(struct block_lock *lock)
+{
+ struct waiter *w, *tmp;
+
+ BUG_ON(lock->count < 0);
+ list_for_each_entry_safe(w, tmp, &lock->waiters, list) {
+ if (lock->count >= MAX_HOLDERS)
+ return;
+
+ if (w->wants_write) {
+ if (lock->count > 0)
+ return; /* still read locked */
+
+ lock->count = -1;
+ __add_holder(lock, w->task);
+ __wake_waiter(w);
+ return;
+ }
+
+ lock->count++;
+ __add_holder(lock, w->task);
+ __wake_waiter(w);
+ }
+}
+
+static void bl_init(struct block_lock *lock)
+{
+ int i;
+
+ spin_lock_init(&lock->lock);
+ lock->count = 0;
+ INIT_LIST_HEAD(&lock->waiters);
+ for (i = 0; i < MAX_HOLDERS; i++)
+ lock->holders[i] = NULL;
+}
+
+static int __available_for_read(struct block_lock *lock)
+{
+ return lock->count >= 0 &&
+ lock->count < MAX_HOLDERS &&
+ list_empty(&lock->waiters);
+}
+
+static int bl_down_read(struct block_lock *lock)
+{
+ int r;
+ struct waiter w;
+
+ spin_lock(&lock->lock);
+ r = __check_holder(lock);
+ if (r) {
+ spin_unlock(&lock->lock);
+ return r;
+ }
+
+ if (__available_for_read(lock)) {
+ lock->count++;
+ __add_holder(lock, current);
+ spin_unlock(&lock->lock);
+ return 0;
+ }
+
+ get_task_struct(current);
+
+ w.task = current;
+ w.wants_write = 0;
+ list_add_tail(&w.list, &lock->waiters);
+ spin_unlock(&lock->lock);
+
+ __wait(&w);
+ put_task_struct(current);
+ return 0;
+}
+
+static int bl_down_read_nonblock(struct block_lock *lock)
+{
+ int r;
+
+ spin_lock(&lock->lock);
+ r = __check_holder(lock);
+ if (r)
+ goto out;
+
+ if (__available_for_read(lock)) {
+ lock->count++;
+ __add_holder(lock, current);
+ r = 0;
+ } else
+ r = -EWOULDBLOCK;
+
+out:
+ spin_unlock(&lock->lock);
+ return r;
+}
+
+static void bl_up_read(struct block_lock *lock)
+{
+ spin_lock(&lock->lock);
+ BUG_ON(lock->count <= 0);
+ __del_holder(lock, current);
+ --lock->count;
+ if (!list_empty(&lock->waiters))
+ __wake_many(lock);
+ spin_unlock(&lock->lock);
+}
+
+static int bl_down_write(struct block_lock *lock)
+{
+ int r;
+ struct waiter w;
+
+ spin_lock(&lock->lock);
+ r = __check_holder(lock);
+ if (r) {
+ spin_unlock(&lock->lock);
+ return r;
+ }
+
+ if (lock->count == 0 && list_empty(&lock->waiters)) {
+ lock->count = -1;
+ __add_holder(lock, current);
+ spin_unlock(&lock->lock);
+ return 0;
+ }
+
+ get_task_struct(current);
+ w.task = current;
+ w.wants_write = 1;
+
+ /*
+ * Writers given priority. We know there's only one mutator in the
+ * system, so ignoring the ordering reversal.
+ */
+ list_add(&w.list, &lock->waiters);
+ spin_unlock(&lock->lock);
+
+ __wait(&w);
+ put_task_struct(current);
+
+ return 0;
+}
+
+static void bl_up_write(struct block_lock *lock)
+{
+ spin_lock(&lock->lock);
+ __del_holder(lock, current);
+ lock->count = 0;
+ if (!list_empty(&lock->waiters))
+ __wake_many(lock);
+ spin_unlock(&lock->lock);
+}
+
+static void report_recursive_bug(dm_block_t b, int r)
+{
+ if (r == -EINVAL)
+ DMERR("recursive acquisition of block %llu requested.",
+ (unsigned long long) b);
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Block manager is currently implemented using dm-bufio. struct
+ * dm_block_manager and struct dm_block map directly onto a couple of
+ * structs in the bufio interface. I want to retain the freedom to move
+ * away from bufio in the future. So these structs are just cast within
+ * this .c file, rather than making it through to the public interface.
+ */
+static struct dm_buffer *to_buffer(struct dm_block *b)
+{
+ return (struct dm_buffer *) b;
+}
+
+static struct dm_bufio_client *to_bufio(struct dm_block_manager *bm)
+{
+ return (struct dm_bufio_client *) bm;
+}
+
+dm_block_t dm_block_location(struct dm_block *b)
+{
+ return dm_bufio_get_block_number(to_buffer(b));
+}
+EXPORT_SYMBOL_GPL(dm_block_location);
+
+void *dm_block_data(struct dm_block *b)
+{
+ return dm_bufio_get_block_data(to_buffer(b));
+}
+EXPORT_SYMBOL_GPL(dm_block_data);
+
+struct buffer_aux {
+ struct dm_block_validator *validator;
+ struct block_lock lock;
+ int write_locked;
+};
+
+static void dm_block_manager_alloc_callback(struct dm_buffer *buf)
+{
+ struct buffer_aux *aux = dm_bufio_get_aux_data(buf);
+ aux->validator = NULL;
+ bl_init(&aux->lock);
+}
+
+static void dm_block_manager_write_callback(struct dm_buffer *buf)
+{
+ struct buffer_aux *aux = dm_bufio_get_aux_data(buf);
+ if (aux->validator) {
+ aux->validator->prepare_for_write(aux->validator, (struct dm_block *) buf,
+ dm_bufio_get_block_size(dm_bufio_get_client(buf)));
+ }
+}
+
+/*----------------------------------------------------------------
+ * Public interface
+ *--------------------------------------------------------------*/
+struct dm_block_manager *dm_block_manager_create(struct block_device *bdev,
+ unsigned block_size,
+ unsigned cache_size,
+ unsigned max_held_per_thread)
+{
+ return (struct dm_block_manager *)
+ dm_bufio_client_create(bdev, block_size, max_held_per_thread,
+ sizeof(struct buffer_aux),
+ dm_block_manager_alloc_callback,
+ dm_block_manager_write_callback);
+}
+EXPORT_SYMBOL_GPL(dm_block_manager_create);
+
+void dm_block_manager_destroy(struct dm_block_manager *bm)
+{
+ return dm_bufio_client_destroy(to_bufio(bm));
+}
+EXPORT_SYMBOL_GPL(dm_block_manager_destroy);
+
+unsigned dm_bm_block_size(struct dm_block_manager *bm)
+{
+ return dm_bufio_get_block_size(to_bufio(bm));
+}
+EXPORT_SYMBOL_GPL(dm_bm_block_size);
+
+dm_block_t dm_bm_nr_blocks(struct dm_block_manager *bm)
+{
+ return dm_bufio_get_device_size(to_bufio(bm));
+}
+
+static int dm_bm_validate_buffer(struct dm_block_manager *bm,
+ struct dm_buffer *buf,
+ struct buffer_aux *aux,
+ struct dm_block_validator *v)
+{
+ if (unlikely(!aux->validator)) {
+ int r;
+ if (!v)
+ return 0;
+ r = v->check(v, (struct dm_block *) buf, dm_bufio_get_block_size(to_bufio(bm)));
+ if (unlikely(r))
+ return r;
+ aux->validator = v;
+ } else {
+ if (unlikely(aux->validator != v)) {
+ DMERR("validator mismatch (old=%s vs new=%s) for block %llu",
+ aux->validator->name, v ? v->name : "NULL",
+ (unsigned long long)
+ dm_bufio_get_block_number(buf));
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+int dm_bm_read_lock(struct dm_block_manager *bm, dm_block_t b,
+ struct dm_block_validator *v,
+ struct dm_block **result)
+{
+ struct buffer_aux *aux;
+ void *p;
+ int r;
+
+ p = dm_bufio_read(to_bufio(bm), b, (struct dm_buffer **) result);
+ if (unlikely(IS_ERR(p)))
+ return PTR_ERR(p);
+
+ aux = dm_bufio_get_aux_data(to_buffer(*result));
+ r = bl_down_read(&aux->lock);
+ if (unlikely(r)) {
+ dm_bufio_release(to_buffer(*result));
+ report_recursive_bug(b, r);
+ return r;
+ }
+
+ aux->write_locked = 0;
+
+ r = dm_bm_validate_buffer(bm, to_buffer(*result), aux, v);
+ if (unlikely(r)) {
+ bl_up_read(&aux->lock);
+ dm_bufio_release(to_buffer(*result));
+ return r;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(dm_bm_read_lock);
+
+int dm_bm_write_lock(struct dm_block_manager *bm,
+ dm_block_t b, struct dm_block_validator *v,
+ struct dm_block **result)
+{
+ struct buffer_aux *aux;
+ void *p;
+ int r;
+
+ p = dm_bufio_read(to_bufio(bm), b, (struct dm_buffer **) result);
+ if (unlikely(IS_ERR(p)))
+ return PTR_ERR(p);
+
+ aux = dm_bufio_get_aux_data(to_buffer(*result));
+ r = bl_down_write(&aux->lock);
+ if (r) {
+ dm_bufio_release(to_buffer(*result));
+ report_recursive_bug(b, r);
+ return r;
+ }
+
+ aux->write_locked = 1;
+
+ r = dm_bm_validate_buffer(bm, to_buffer(*result), aux, v);
+ if (unlikely(r)) {
+ bl_up_write(&aux->lock);
+ dm_bufio_release(to_buffer(*result));
+ return r;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(dm_bm_write_lock);
+
+int dm_bm_read_try_lock(struct dm_block_manager *bm,
+ dm_block_t b, struct dm_block_validator *v,
+ struct dm_block **result)
+{
+ struct buffer_aux *aux;
+ void *p;
+ int r;
+
+ p = dm_bufio_get(to_bufio(bm), b, (struct dm_buffer **) result);
+ if (unlikely(IS_ERR(p)))
+ return PTR_ERR(p);
+ if (unlikely(!p))
+ return -EWOULDBLOCK;
+
+ aux = dm_bufio_get_aux_data(to_buffer(*result));
+ r = bl_down_read_nonblock(&aux->lock);
+ if (r < 0) {
+ dm_bufio_release(to_buffer(*result));
+ report_recursive_bug(b, r);
+ return r;
+ }
+ aux->write_locked = 0;
+
+ r = dm_bm_validate_buffer(bm, to_buffer(*result), aux, v);
+ if (unlikely(r)) {
+ bl_up_read(&aux->lock);
+ dm_bufio_release(to_buffer(*result));
+ return r;
+ }
+
+ return 0;
+}
+
+int dm_bm_write_lock_zero(struct dm_block_manager *bm,
+ dm_block_t b, struct dm_block_validator *v,
+ struct dm_block **result)
+{
+ int r;
+ struct buffer_aux *aux;
+ void *p;
+
+ p = dm_bufio_new(to_bufio(bm), b, (struct dm_buffer **) result);
+ if (unlikely(IS_ERR(p)))
+ return PTR_ERR(p);
+
+ memset(p, 0, dm_bm_block_size(bm));
+
+ aux = dm_bufio_get_aux_data(to_buffer(*result));
+ r = bl_down_write(&aux->lock);
+ if (r) {
+ dm_bufio_release(to_buffer(*result));
+ return r;
+ }
+
+ aux->write_locked = 1;
+ aux->validator = v;
+
+ return 0;
+}
+
+int dm_bm_unlock(struct dm_block *b)
+{
+ struct buffer_aux *aux;
+ aux = dm_bufio_get_aux_data(to_buffer(b));
+
+ if (aux->write_locked) {
+ dm_bufio_mark_buffer_dirty(to_buffer(b));
+ bl_up_write(&aux->lock);
+ } else
+ bl_up_read(&aux->lock);
+
+ dm_bufio_release(to_buffer(b));
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(dm_bm_unlock);
+
+int dm_bm_unlock_move(struct dm_block *b, dm_block_t n)
+{
+ struct buffer_aux *aux;
+
+ aux = dm_bufio_get_aux_data(to_buffer(b));
+
+ if (aux->write_locked) {
+ dm_bufio_mark_buffer_dirty(to_buffer(b));
+ bl_up_write(&aux->lock);
+ } else
+ bl_up_read(&aux->lock);
+
+ dm_bufio_release_move(to_buffer(b), n);
+ return 0;
+}
+
+int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
+ struct dm_block *superblock)
+{
+ int r;
+
+ r = dm_bufio_write_dirty_buffers(to_bufio(bm));
+ if (unlikely(r))
+ return r;
+ r = dm_bufio_issue_flush(to_bufio(bm));
+ if (unlikely(r))
+ return r;
+
+ dm_bm_unlock(superblock);
+
+ r = dm_bufio_write_dirty_buffers(to_bufio(bm));
+ if (unlikely(r))
+ return r;
+ r = dm_bufio_issue_flush(to_bufio(bm));
+ if (unlikely(r))
+ return r;
+
+ return 0;
+}
+
+u32 dm_bm_checksum(const void *data, size_t len, u32 init_xor)
+{
+ return crc32c(~(u32) 0, data, len) ^ init_xor;
+}
+EXPORT_SYMBOL_GPL(dm_bm_checksum);
+
+/*----------------------------------------------------------------*/
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
+MODULE_DESCRIPTION("Immutable metadata library for dm");
+
+/*----------------------------------------------------------------*/
diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h
new file mode 100644
index 0000000..924833d
--- /dev/null
+++ b/drivers/md/persistent-data/dm-block-manager.h
@@ -0,0 +1,123 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef _LINUX_DM_BLOCK_MANAGER_H
+#define _LINUX_DM_BLOCK_MANAGER_H
+
+#include <linux/types.h>
+#include <linux/blkdev.h>
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Block number.
+ */
+typedef uint64_t dm_block_t;
+struct dm_block;
+
+dm_block_t dm_block_location(struct dm_block *b);
+void *dm_block_data(struct dm_block *b);
+
+/*----------------------------------------------------------------*/
+
+/*
+ * @name should be a unique identifier for the block manager, no longer
+ * than 32 chars.
+ *
+ * @max_held_per_thread should be the maximum number of locks, read or
+ * write, that an individual thread holds at any one time.
+ */
+struct dm_block_manager;
+struct dm_block_manager *dm_block_manager_create(
+ struct block_device *bdev, unsigned block_size,
+ unsigned cache_size, unsigned max_held_per_thread);
+void dm_block_manager_destroy(struct dm_block_manager *bm);
+
+unsigned dm_bm_block_size(struct dm_block_manager *bm);
+dm_block_t dm_bm_nr_blocks(struct dm_block_manager *bm);
+
+/*----------------------------------------------------------------*/
+
+/*
+ * The validator allows the caller to verify newly-read data and modify
+ * the data just before writing, e.g. to calculate checksums. It's
+ * important to be consistent with your use of validators. The only time
+ * you can change validators is if you call dm_bm_write_lock_zero.
+ */
+struct dm_block_validator {
+ const char *name;
+ void (*prepare_for_write)(struct dm_block_validator *v, struct dm_block *b, size_t block_size);
+
+ /*
+ * Return 0 if the checksum is valid or < 0 on error.
+ */
+ int (*check)(struct dm_block_validator *v, struct dm_block *b, size_t block_size);
+};
+
+/*----------------------------------------------------------------*/
+
+/*
+ * You can have multiple concurrent readers or a single writer holding a
+ * block lock.
+ */
+
+/*
+ * dm_bm_lock() locks a block and returns through @result a pointer to
+ * memory that holds a copy of that block. If you have write-locked the
+ * block then any changes you make to memory pointed to by @result will be
+ * written back to the disk sometime after dm_bm_unlock is called.
+ */
+int dm_bm_read_lock(struct dm_block_manager *bm, dm_block_t b,
+ struct dm_block_validator *v,
+ struct dm_block **result);
+
+int dm_bm_write_lock(struct dm_block_manager *bm, dm_block_t b,
+ struct dm_block_validator *v,
+ struct dm_block **result);
+
+/*
+ * The *_try_lock variants return -EWOULDBLOCK if the block isn't
+ * available immediately.
+ */
+int dm_bm_read_try_lock(struct dm_block_manager *bm, dm_block_t b,
+ struct dm_block_validator *v,
+ struct dm_block **result);
+
+/*
+ * Use dm_bm_write_lock_zero() when you know you're going to
+ * overwrite the block completely. It saves a disk read.
+ */
+int dm_bm_write_lock_zero(struct dm_block_manager *bm, dm_block_t b,
+ struct dm_block_validator *v,
+ struct dm_block **result);
+
+int dm_bm_unlock(struct dm_block *b);
+
+/*
+ * An optimisation; we often want to copy a block's contents to a new
+ * block. eg, as part of the shadowing operation. It's far better for
+ * bufio to do this move behind the scenes than hold 2 locks and memcpy the
+ * data.
+ */
+int dm_bm_unlock_move(struct dm_block *b, dm_block_t n);
+
+/*
+ * It's a common idiom to have a superblock that should be committed last.
+ *
+ * @superblock should be write-locked on entry. It will be unlocked during
+ * this function. All dirty blocks are guaranteed to be written and flushed
+ * before the superblock.
+ *
+ * This method always blocks.
+ */
+int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
+ struct dm_block *superblock);
+
+u32 dm_bm_checksum(const void *data, size_t len, u32 init_xor);
+
+/*----------------------------------------------------------------*/
+
+#endif /* _LINUX_DM_BLOCK_MANAGER_H */
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
new file mode 100644
index 0000000..d279c76
--- /dev/null
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -0,0 +1,137 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_BTREE_INTERNAL_H
+#define DM_BTREE_INTERNAL_H
+
+#include "dm-btree.h"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * We'll need 2 accessor functions for n->csum and n->blocknr
+ * to support dm-btree-spine.c in that case.
+ */
+
+enum node_flags {
+ INTERNAL_NODE = 1,
+ LEAF_NODE = 1 << 1
+};
+
+/*
+ * Every btree node begins with this structure. Make sure it's a multiple
+ * of 8-bytes in size, otherwise the 64bit keys will be mis-aligned.
+ */
+struct node_header {
+ __le32 csum;
+ __le32 flags;
+ __le64 blocknr; /* Block this node is supposed to live in. */
+
+ __le32 nr_entries;
+ __le32 max_entries;
+ __le32 value_size;
+ __le32 padding;
+} __packed;
+
+struct node {
+ struct node_header header;
+ __le64 keys[0];
+} __packed;
+
+
+void inc_children(struct dm_transaction_manager *tm, struct node *n,
+ struct dm_btree_value_type *vt);
+
+int new_block(struct dm_btree_info *info, struct dm_block **result);
+int unlock_block(struct dm_btree_info *info, struct dm_block *b);
+
+/*
+ * Spines keep track of the rolling locks. There are 2 variants, read-only
+ * and one that uses shadowing. These are separate structs to allow the
+ * type checker to spot misuse, for example accidentally calling read_lock
+ * on a shadow spine.
+ */
+struct ro_spine {
+ struct dm_btree_info *info;
+
+ int count;
+ struct dm_block *nodes[2];
+};
+
+void init_ro_spine(struct ro_spine *s, struct dm_btree_info *info);
+int exit_ro_spine(struct ro_spine *s);
+int ro_step(struct ro_spine *s, dm_block_t new_child);
+struct node *ro_node(struct ro_spine *s);
+
+struct shadow_spine {
+ struct dm_btree_info *info;
+
+ int count;
+ struct dm_block *nodes[2];
+
+ dm_block_t root;
+};
+
+void init_shadow_spine(struct shadow_spine *s, struct dm_btree_info *info);
+int exit_shadow_spine(struct shadow_spine *s);
+
+int shadow_step(struct shadow_spine *s, dm_block_t b,
+ struct dm_btree_value_type *vt);
+
+/*
+ * The spine must have at least one entry before calling this.
+ */
+struct dm_block *shadow_current(struct shadow_spine *s);
+
+/*
+ * The spine must have at least two entries before calling this.
+ */
+struct dm_block *shadow_parent(struct shadow_spine *s);
+
+int shadow_has_parent(struct shadow_spine *s);
+
+int shadow_root(struct shadow_spine *s);
+
+/*
+ * Some inlines.
+ */
+static inline __le64 *key_ptr(struct node *n, uint32_t index)
+{
+ return n->keys + index;
+}
+
+static inline void *value_base(struct node *n)
+{
+ return &n->keys[le32_to_cpu(n->header.max_entries)];
+}
+
+/*
+ * FIXME: Now that value size is stored in node we don't need the third parm.
+ */
+static inline void *value_ptr(struct node *n, uint32_t index, size_t value_size)
+{
+ BUG_ON(value_size != le32_to_cpu(n->header.value_size));
+ return value_base(n) + (value_size * index);
+}
+
+/*
+ * Assumes the values are suitably-aligned and converts to core format.
+ */
+static inline uint64_t value64(struct node *n, uint32_t index)
+{
+ __le64 *values_le = value_base(n);
+
+ return le64_to_cpu(values_le[index]);
+}
+
+/*
+ * Searching for a key within a single node.
+ */
+int lower_bound(struct node *n, uint64_t key);
+
+extern struct dm_block_validator btree_node_validator;
+
+#endif /* DM_BTREE_INTERNAL_H */
diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c
new file mode 100644
index 0000000..65fd85e
--- /dev/null
+++ b/drivers/md/persistent-data/dm-btree-remove.c
@@ -0,0 +1,566 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-btree.h"
+#include "dm-btree-internal.h"
+#include "dm-transaction-manager.h"
+
+#include <linux/module.h>
+
+/*
+ * Removing an entry from a btree
+ * ==============================
+ *
+ * A very important constraint for our btree is that no node, except the
+ * root, may have fewer than a certain number of entries.
+ * (MIN_ENTRIES <= nr_entries <= MAX_ENTRIES).
+ *
+ * Ensuring this is complicated by the way we want to only ever hold the
+ * locks on 2 nodes concurrently, and only change nodes in a top to bottom
+ * fashion.
+ *
+ * Each node may have a left or right sibling. When decending the spine,
+ * if a node contains only MIN_ENTRIES then we try and increase this to at
+ * least MIN_ENTRIES + 1. We do this in the following ways:
+ *
+ * [A] No siblings => this can only happen if the node is the root, in which
+ * case we copy the childs contents over the root.
+ *
+ * [B] No left sibling
+ * ==> rebalance(node, right sibling)
+ *
+ * [C] No right sibling
+ * ==> rebalance(left sibling, node)
+ *
+ * [D] Both siblings, total_entries(left, node, right) <= DEL_THRESHOLD
+ * ==> delete node adding it's contents to left and right
+ *
+ * [E] Both siblings, total_entries(left, node, right) > DEL_THRESHOLD
+ * ==> rebalance(left, node, right)
+ *
+ * After these operations it's possible that the our original node no
+ * longer contains the desired sub tree. For this reason this rebalancing
+ * is performed on the children of the current node. This also avoids
+ * having a special case for the root.
+ *
+ * Once this rebalancing has occurred we can then step into the child node
+ * for internal nodes. Or delete the entry for leaf nodes.
+ */
+
+/*
+ * Some little utilities for moving node data around.
+ */
+static void node_shift(struct node *n, int shift)
+{
+ uint32_t nr_entries = le32_to_cpu(n->header.nr_entries);
+ uint32_t value_size = le32_to_cpu(n->header.value_size);
+
+ if (shift < 0) {
+ shift = -shift;
+ BUG_ON(shift > nr_entries);
+ BUG_ON((void *) key_ptr(n, shift) >= value_ptr(n, shift, value_size));
+ memmove(key_ptr(n, 0),
+ key_ptr(n, shift),
+ (nr_entries - shift) * sizeof(__le64));
+ memmove(value_ptr(n, 0, value_size),
+ value_ptr(n, shift, value_size),
+ (nr_entries - shift) * value_size);
+ } else {
+ BUG_ON(nr_entries + shift > le32_to_cpu(n->header.max_entries));
+ memmove(key_ptr(n, shift),
+ key_ptr(n, 0),
+ nr_entries * sizeof(__le64));
+ memmove(value_ptr(n, shift, value_size),
+ value_ptr(n, 0, value_size),
+ nr_entries * value_size);
+ }
+}
+
+static void node_copy(struct node *left, struct node *right, int shift)
+{
+ uint32_t nr_left = le32_to_cpu(left->header.nr_entries);
+ uint32_t value_size = le32_to_cpu(left->header.value_size);
+ BUG_ON(value_size != le32_to_cpu(right->header.value_size));
+
+ if (shift < 0) {
+ shift = -shift;
+ BUG_ON(nr_left + shift > le32_to_cpu(left->header.max_entries));
+ memcpy(key_ptr(left, nr_left),
+ key_ptr(right, 0),
+ shift * sizeof(__le64));
+ memcpy(value_ptr(left, nr_left, value_size),
+ value_ptr(right, 0, value_size),
+ shift * value_size);
+ } else {
+ BUG_ON(shift > le32_to_cpu(right->header.max_entries));
+ memcpy(key_ptr(right, 0),
+ key_ptr(left, nr_left - shift),
+ shift * sizeof(__le64));
+ memcpy(value_ptr(right, 0, value_size),
+ value_ptr(left, nr_left - shift, value_size),
+ shift * value_size);
+ }
+}
+
+/*
+ * Delete a specific entry from a leaf node.
+ */
+static void delete_at(struct node *n, unsigned index)
+{
+ unsigned nr_entries = le32_to_cpu(n->header.nr_entries);
+ unsigned nr_to_copy = nr_entries - (index + 1);
+ uint32_t value_size = le32_to_cpu(n->header.value_size);
+ BUG_ON(index >= nr_entries);
+
+ if (nr_to_copy) {
+ memmove(key_ptr(n, index),
+ key_ptr(n, index + 1),
+ nr_to_copy * sizeof(__le64));
+
+ memmove(value_ptr(n, index, value_size),
+ value_ptr(n, index + 1, value_size),
+ nr_to_copy * value_size);
+ }
+
+ n->header.nr_entries = cpu_to_le32(nr_entries - 1);
+}
+
+static unsigned del_threshold(struct node *n)
+{
+ return le32_to_cpu(n->header.max_entries) / 3;
+}
+
+static unsigned merge_threshold(struct node *n)
+{
+ /*
+ * The extra one is because we know we're potentially going to
+ * delete an entry.
+ */
+ return 2 * (le32_to_cpu(n->header.max_entries) / 3) + 1;
+}
+
+struct child {
+ unsigned index;
+ struct dm_block *block;
+ struct node *n;
+};
+
+static struct dm_btree_value_type le64_type = {
+ .context = NULL,
+ .size = sizeof(__le64),
+ .inc = NULL,
+ .dec = NULL,
+ .equal = NULL
+};
+
+static int init_child(struct dm_btree_info *info, struct node *parent,
+ unsigned index, struct child *result)
+{
+ int r, inc;
+ dm_block_t root;
+
+ result->index = index;
+ root = value64(parent, index);
+
+ r = dm_tm_shadow_block(info->tm, root, &btree_node_validator,
+ &result->block, &inc);
+ if (r)
+ return r;
+
+ result->n = dm_block_data(result->block);
+
+ if (inc)
+ inc_children(info->tm, result->n, &le64_type);
+
+ *((__le64 *) value_ptr(parent, index, sizeof(__le64))) =
+ cpu_to_le64(dm_block_location(result->block));
+
+ return 0;
+}
+
+static int exit_child(struct dm_btree_info *info, struct child *c)
+{
+ return dm_tm_unlock(info->tm, c->block);
+}
+
+static void shift(struct node *left, struct node *right, int count)
+{
+ if (!count)
+ return;
+
+ if (count > 0) {
+ node_shift(right, count);
+ node_copy(left, right, count);
+ } else {
+ node_copy(left, right, count);
+ node_shift(right, count);
+ }
+
+ left->header.nr_entries =
+ cpu_to_le32(le32_to_cpu(left->header.nr_entries) - count);
+ BUG_ON(le32_to_cpu(left->header.nr_entries) > le32_to_cpu(left->header.max_entries));
+
+ right->header.nr_entries =
+ cpu_to_le32(le32_to_cpu(right->header.nr_entries) + count);
+ BUG_ON(le32_to_cpu(right->header.nr_entries) > le32_to_cpu(right->header.max_entries));
+}
+
+static void __rebalance2(struct dm_btree_info *info, struct node *parent,
+ struct child *l, struct child *r)
+{
+ struct node *left = l->n;
+ struct node *right = r->n;
+ uint32_t nr_left = le32_to_cpu(left->header.nr_entries);
+ uint32_t nr_right = le32_to_cpu(right->header.nr_entries);
+
+ if (nr_left + nr_right <= merge_threshold(left)) {
+ /*
+ * Merge
+ */
+ node_copy(left, right, -nr_right);
+ left->header.nr_entries = cpu_to_le32(nr_left + nr_right);
+ delete_at(parent, r->index);
+
+ /*
+ * We need to decrement the right block, but not it's
+ * children, since they're still referenced by left.
+ */
+ dm_tm_dec(info->tm, dm_block_location(r->block));
+ } else {
+ /*
+ * Rebalance.
+ */
+ unsigned target_left = (nr_left + nr_right) / 2;
+ unsigned shift_ = nr_left - target_left;
+ BUG_ON(le32_to_cpu(left->header.max_entries) <= nr_left - shift_);
+ BUG_ON(le32_to_cpu(right->header.max_entries) <= nr_right + shift_);
+ shift(left, right, nr_left - target_left);
+ *key_ptr(parent, r->index) = right->keys[0];
+ }
+}
+
+static int rebalance2(struct shadow_spine *s, struct dm_btree_info *info,
+ unsigned left_index)
+{
+ int r;
+ struct node *parent;
+ struct child left, right;
+
+ parent = dm_block_data(shadow_current(s));
+
+ r = init_child(info, parent, left_index, &left);
+ if (r)
+ return r;
+
+ r = init_child(info, parent, left_index + 1, &right);
+ if (r) {
+ exit_child(info, &left);
+ return r;
+ }
+
+ __rebalance2(info, parent, &left, &right);
+
+ r = exit_child(info, &left);
+ if (r) {
+ exit_child(info, &right);
+ return r;
+ }
+
+ return exit_child(info, &right);
+}
+
+static void __rebalance3(struct dm_btree_info *info, struct node *parent,
+ struct child *l, struct child *c, struct child *r)
+{
+ struct node *left = l->n;
+ struct node *center = c->n;
+ struct node *right = r->n;
+
+ uint32_t nr_left = le32_to_cpu(left->header.nr_entries);
+ uint32_t nr_center = le32_to_cpu(center->header.nr_entries);
+ uint32_t nr_right = le32_to_cpu(right->header.nr_entries);
+ uint32_t max_entries = le32_to_cpu(left->header.max_entries);
+
+ unsigned target;
+
+ BUG_ON(left->header.max_entries != center->header.max_entries);
+ BUG_ON(center->header.max_entries != right->header.max_entries);
+
+ if (((nr_left + nr_center + nr_right) / 2) < merge_threshold(center)) {
+ /*
+ * Delete center node:
+ *
+ * We dump as many entries from center as possible into
+ * left, then the rest in right, then rebalance2. This
+ * wastes some cpu, but I want something simple atm.
+ */
+ unsigned shift = min(max_entries - nr_left, nr_center);
+
+ BUG_ON(nr_left + shift > max_entries);
+ node_copy(left, center, -shift);
+ left->header.nr_entries = cpu_to_le32(nr_left + shift);
+
+ if (shift != nr_center) {
+ shift = nr_center - shift;
+ BUG_ON((nr_right + shift) >= max_entries);
+ node_shift(right, shift);
+ node_copy(center, right, shift);
+ right->header.nr_entries = cpu_to_le32(nr_right + shift);
+ }
+ *key_ptr(parent, r->index) = right->keys[0];
+
+ delete_at(parent, c->index);
+ r->index--;
+
+ dm_tm_dec(info->tm, dm_block_location(c->block));
+ __rebalance2(info, parent, l, r);
+
+ return;
+ }
+
+ /*
+ * Rebalance
+ */
+ target = (nr_left + nr_center + nr_right) / 3;
+ BUG_ON(target > max_entries);
+
+ /*
+ * Adjust the left node
+ */
+ shift(left, center, nr_left - target);
+
+ /*
+ * Adjust the right node
+ */
+ shift(center, right, target - nr_right);
+ *key_ptr(parent, c->index) = center->keys[0];
+ *key_ptr(parent, r->index) = right->keys[0];
+}
+
+static int rebalance3(struct shadow_spine *s, struct dm_btree_info *info,
+ unsigned left_index)
+{
+ int r;
+ struct node *parent = dm_block_data(shadow_current(s));
+ struct child left, center, right;
+
+ /*
+ * FIXME: fill out an array?
+ */
+ r = init_child(info, parent, left_index, &left);
+ if (r)
+ return r;
+
+ r = init_child(info, parent, left_index + 1, ¢er);
+ if (r) {
+ exit_child(info, &left);
+ return r;
+ }
+
+ r = init_child(info, parent, left_index + 2, &right);
+ if (r) {
+ exit_child(info, &left);
+ exit_child(info, ¢er);
+ return r;
+ }
+
+ __rebalance3(info, parent, &left, ¢er, &right);
+
+ r = exit_child(info, &left);
+ if (r) {
+ exit_child(info, ¢er);
+ exit_child(info, &right);
+ return r;
+ }
+
+ r = exit_child(info, ¢er);
+ if (r) {
+ exit_child(info, &right);
+ return r;
+ }
+
+ r = exit_child(info, &right);
+ if (r)
+ return r;
+
+ return 0;
+}
+
+static int get_nr_entries(struct dm_transaction_manager *tm,
+ dm_block_t b, uint32_t *result)
+{
+ int r;
+ struct dm_block *block;
+ struct node *n;
+
+ r = dm_tm_read_lock(tm, b, &btree_node_validator, &block);
+ if (r)
+ return r;
+
+ n = dm_block_data(block);
+ *result = le32_to_cpu(n->header.nr_entries);
+
+ return dm_tm_unlock(tm, block);
+}
+
+static int rebalance_children(struct shadow_spine *s,
+ struct dm_btree_info *info, uint64_t key)
+{
+ int i, r, has_left_sibling, has_right_sibling;
+ uint32_t child_entries;
+ struct node *n;
+
+ n = dm_block_data(shadow_current(s));
+
+ if (le32_to_cpu(n->header.nr_entries) == 1) {
+ struct dm_block *child;
+ dm_block_t b = value64(n, 0);
+
+ r = dm_tm_read_lock(info->tm, b, &btree_node_validator, &child);
+ if (r)
+ return r;
+
+ memcpy(n, dm_block_data(child),
+ dm_bm_block_size(dm_tm_get_bm(info->tm)));
+ r = dm_tm_unlock(info->tm, child);
+ if (r)
+ return r;
+
+ dm_tm_dec(info->tm, dm_block_location(child));
+ return 0;
+ }
+
+ i = lower_bound(n, key);
+ if (i < 0)
+ return -ENODATA;
+
+ r = get_nr_entries(info->tm, value64(n, i), &child_entries);
+ if (r)
+ return r;
+
+ if (child_entries > del_threshold(n))
+ return 0;
+
+ has_left_sibling = i > 0;
+ has_right_sibling = i < (le32_to_cpu(n->header.nr_entries) - 1);
+
+ if (!has_left_sibling)
+ r = rebalance2(s, info, i);
+
+ else if (!has_right_sibling)
+ r = rebalance2(s, info, i - 1);
+
+ else
+ r = rebalance3(s, info, i - 1);
+
+ return r;
+}
+
+static int do_leaf(struct node *n, uint64_t key, unsigned *index)
+{
+ int i = lower_bound(n, key);
+
+ if ((i < 0) ||
+ (i >= le32_to_cpu(n->header.nr_entries)) ||
+ (le64_to_cpu(n->keys[i]) != key))
+ return -ENODATA;
+
+ *index = i;
+
+ return 0;
+}
+
+/*
+ * Prepares for removal from one level of the hierarchy. The caller must
+ * call delete_at() to remove the entry at index.
+ */
+static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info,
+ struct dm_btree_value_type *vt, dm_block_t root,
+ uint64_t key, unsigned *index)
+{
+ int i = *index, r;
+ struct node *n;
+
+ for (;;) {
+ r = shadow_step(s, root, vt);
+ if (r < 0)
+ break;
+
+ /*
+ * We have to patch up the parent node, ugly, but I don't
+ * see a way to do this automatically as part of the spine
+ * op.
+ */
+ if (shadow_has_parent(s)) {
+ __le64 location = cpu_to_le64(dm_block_location(shadow_current(s)));
+ memcpy(value_ptr(dm_block_data(shadow_parent(s)), i, sizeof(__le64)),
+ &location, sizeof(__le64));
+ }
+
+ n = dm_block_data(shadow_current(s));
+
+ if (le32_to_cpu(n->header.flags) & LEAF_NODE)
+ return do_leaf(n, key, index);
+
+ r = rebalance_children(s, info, key);
+ if (r)
+ break;
+
+ n = dm_block_data(shadow_current(s));
+ if (le32_to_cpu(n->header.flags) & LEAF_NODE)
+ return do_leaf(n, key, index);
+
+ i = lower_bound(n, key);
+
+ /*
+ * We know the key is present, or else
+ * rebalance_children would have returned
+ * -ENODATA
+ */
+ root = value64(n, i);
+ }
+
+ return r;
+}
+
+int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *keys, dm_block_t *new_root)
+{
+ unsigned level, last_level = info->levels - 1;
+ int index = 0, r = 0;
+ struct shadow_spine spine;
+ struct node *n;
+
+ init_shadow_spine(&spine, info);
+ for (level = 0; level < info->levels; level++) {
+ r = remove_raw(&spine, info,
+ (level == last_level ?
+ &info->value_type : &le64_type),
+ root, keys[level], (unsigned *)&index);
+ if (r < 0)
+ break;
+
+ n = dm_block_data(shadow_current(&spine));
+ if (level != last_level) {
+ root = value64(n, index);
+ continue;
+ }
+
+ BUG_ON(index < 0 || index >= le32_to_cpu(n->header.nr_entries));
+
+ if (info->value_type.dec)
+ info->value_type.dec(info->value_type.context,
+ value_ptr(n, index, info->value_type.size));
+
+ delete_at(n, index);
+ }
+
+ *new_root = shadow_root(&spine);
+ exit_shadow_spine(&spine);
+
+ return r;
+}
+EXPORT_SYMBOL_GPL(dm_btree_remove);
diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
new file mode 100644
index 0000000..d9a7912
--- /dev/null
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -0,0 +1,244 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-btree-internal.h"
+#include "dm-transaction-manager.h"
+
+#include <linux/device-mapper.h>
+
+#define DM_MSG_PREFIX "btree spine"
+
+/*----------------------------------------------------------------*/
+
+#define BTREE_CSUM_XOR 121107
+
+static int node_check(struct dm_block_validator *v,
+ struct dm_block *b,
+ size_t block_size);
+
+static void node_prepare_for_write(struct dm_block_validator *v,
+ struct dm_block *b,
+ size_t block_size)
+{
+ struct node *n = dm_block_data(b);
+ struct node_header *h = &n->header;
+
+ h->blocknr = cpu_to_le64(dm_block_location(b));
+ h->csum = cpu_to_le32(dm_bm_checksum(&h->flags,
+ block_size - sizeof(__le32),
+ BTREE_CSUM_XOR));
+
+ BUG_ON(node_check(v, b, 4096));
+}
+
+static int node_check(struct dm_block_validator *v,
+ struct dm_block *b,
+ size_t block_size)
+{
+ struct node *n = dm_block_data(b);
+ struct node_header *h = &n->header;
+ size_t value_size;
+ __le32 csum_disk;
+ uint32_t flags;
+
+ if (dm_block_location(b) != le64_to_cpu(h->blocknr)) {
+ DMERR("node_check failed blocknr %llu wanted %llu",
+ le64_to_cpu(h->blocknr), dm_block_location(b));
+ return -ENOTBLK;
+ }
+
+ csum_disk = cpu_to_le32(dm_bm_checksum(&h->flags,
+ block_size - sizeof(__le32),
+ BTREE_CSUM_XOR));
+ if (csum_disk != h->csum) {
+ DMERR("node_check failed csum %u wanted %u",
+ le32_to_cpu(csum_disk), le32_to_cpu(h->csum));
+ return -EILSEQ;
+ }
+
+ value_size = le32_to_cpu(h->value_size);
+
+ if (sizeof(struct node_header) +
+ (sizeof(__le64) + value_size) * le32_to_cpu(h->max_entries) > block_size) {
+ DMERR("node_check failed: max_entries too large");
+ return -EILSEQ;
+ }
+
+ if (le32_to_cpu(h->nr_entries) > le32_to_cpu(h->max_entries)) {
+ DMERR("node_check failed, too many entries");
+ return -EILSEQ;
+ }
+
+ /*
+ * The node must be either INTERNAL or LEAF.
+ */
+ flags = le32_to_cpu(h->flags);
+ if (!(flags & INTERNAL_NODE) && !(flags & LEAF_NODE)) {
+ DMERR("node_check failed, node is neither INTERNAL or LEAF");
+ return -EILSEQ;
+ }
+
+ return 0;
+}
+
+struct dm_block_validator btree_node_validator = {
+ .name = "btree_node",
+ .prepare_for_write = node_prepare_for_write,
+ .check = node_check
+};
+
+/*----------------------------------------------------------------*/
+
+static int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+ struct dm_block **result)
+{
+ return dm_tm_read_lock(info->tm, b, &btree_node_validator, result);
+}
+
+static int bn_shadow(struct dm_btree_info *info, dm_block_t orig,
+ struct dm_btree_value_type *vt,
+ struct dm_block **result)
+{
+ int r, inc;
+
+ r = dm_tm_shadow_block(info->tm, orig, &btree_node_validator,
+ result, &inc);
+ if (!r && inc)
+ inc_children(info->tm, dm_block_data(*result), vt);
+
+ return r;
+}
+
+int new_block(struct dm_btree_info *info, struct dm_block **result)
+{
+ return dm_tm_new_block(info->tm, &btree_node_validator, result);
+}
+
+int unlock_block(struct dm_btree_info *info, struct dm_block *b)
+{
+ return dm_tm_unlock(info->tm, b);
+}
+
+/*----------------------------------------------------------------*/
+
+void init_ro_spine(struct ro_spine *s, struct dm_btree_info *info)
+{
+ s->info = info;
+ s->count = 0;
+ s->nodes[0] = NULL;
+ s->nodes[1] = NULL;
+}
+
+int exit_ro_spine(struct ro_spine *s)
+{
+ int r = 0, i;
+
+ for (i = 0; i < s->count; i++) {
+ int r2 = unlock_block(s->info, s->nodes[i]);
+ if (r2 < 0)
+ r = r2;
+ }
+
+ return r;
+}
+
+int ro_step(struct ro_spine *s, dm_block_t new_child)
+{
+ int r;
+
+ if (s->count == 2) {
+ r = unlock_block(s->info, s->nodes[0]);
+ if (r < 0)
+ return r;
+ s->nodes[0] = s->nodes[1];
+ s->count--;
+ }
+
+ r = bn_read_lock(s->info, new_child, s->nodes + s->count);
+ if (!r)
+ s->count++;
+
+ return r;
+}
+
+struct node *ro_node(struct ro_spine *s)
+{
+ struct dm_block *block;
+
+ BUG_ON(!s->count);
+ block = s->nodes[s->count - 1];
+
+ return dm_block_data(block);
+}
+
+/*----------------------------------------------------------------*/
+
+void init_shadow_spine(struct shadow_spine *s, struct dm_btree_info *info)
+{
+ s->info = info;
+ s->count = 0;
+}
+
+int exit_shadow_spine(struct shadow_spine *s)
+{
+ int r = 0, i;
+
+ for (i = 0; i < s->count; i++) {
+ int r2 = unlock_block(s->info, s->nodes[i]);
+ if (r2 < 0)
+ r = r2;
+ }
+
+ return r;
+}
+
+int shadow_step(struct shadow_spine *s, dm_block_t b,
+ struct dm_btree_value_type *vt)
+{
+ int r;
+
+ if (s->count == 2) {
+ r = unlock_block(s->info, s->nodes[0]);
+ if (r < 0)
+ return r;
+ s->nodes[0] = s->nodes[1];
+ s->count--;
+ }
+
+ r = bn_shadow(s->info, b, vt, s->nodes + s->count);
+ if (!r) {
+ if (!s->count)
+ s->root = dm_block_location(s->nodes[0]);
+
+ s->count++;
+ }
+
+ return r;
+}
+
+struct dm_block *shadow_current(struct shadow_spine *s)
+{
+ BUG_ON(!s->count);
+
+ return s->nodes[s->count - 1];
+}
+
+struct dm_block *shadow_parent(struct shadow_spine *s)
+{
+ BUG_ON(s->count != 2);
+
+ return s->count == 2 ? s->nodes[0] : NULL;
+}
+
+int shadow_has_parent(struct shadow_spine *s)
+{
+ return s->count >= 2;
+}
+
+int shadow_root(struct shadow_spine *s)
+{
+ return s->root;
+}
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
new file mode 100644
index 0000000..e0638be
--- /dev/null
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -0,0 +1,805 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-btree-internal.h"
+#include "dm-space-map.h"
+#include "dm-transaction-manager.h"
+
+#include <linux/module.h>
+#include <linux/device-mapper.h>
+
+#define DM_MSG_PREFIX "btree"
+
+/*----------------------------------------------------------------
+ * Array manipulation
+ *--------------------------------------------------------------*/
+static void memcpy_disk(void *dest, const void *src, size_t len)
+ __dm_written_to_disk(src)
+{
+ memcpy(dest, src, len);
+ __dm_unbless_for_disk(src);
+}
+
+static void array_insert(void *base, size_t elt_size, unsigned nr_elts,
+ unsigned index, void *elt)
+ __dm_written_to_disk(elt)
+{
+ if (index < nr_elts)
+ memmove(base + (elt_size * (index + 1)),
+ base + (elt_size * index),
+ (nr_elts - index) * elt_size);
+
+ memcpy_disk(base + (elt_size * index), elt, elt_size);
+}
+
+/*----------------------------------------------------------------*/
+
+/* makes the assumption that no two keys are the same. */
+static int bsearch(struct node *n, uint64_t key, int want_hi)
+{
+ int lo = -1, hi = le32_to_cpu(n->header.nr_entries);
+
+ while (hi - lo > 1) {
+ int mid = lo + ((hi - lo) / 2);
+ uint64_t mid_key = le64_to_cpu(n->keys[mid]);
+
+ if (mid_key == key)
+ return mid;
+
+ if (mid_key < key)
+ lo = mid;
+ else
+ hi = mid;
+ }
+
+ return want_hi ? hi : lo;
+}
+
+int lower_bound(struct node *n, uint64_t key)
+{
+ return bsearch(n, key, 0);
+}
+
+void inc_children(struct dm_transaction_manager *tm, struct node *n,
+ struct dm_btree_value_type *vt)
+{
+ unsigned i;
+ uint32_t nr_entries = le32_to_cpu(n->header.nr_entries);
+
+ if (le32_to_cpu(n->header.flags) & INTERNAL_NODE)
+ for (i = 0; i < nr_entries; i++)
+ dm_tm_inc(tm, value64(n, i));
+ else if (vt->inc)
+ for (i = 0; i < nr_entries; i++)
+ vt->inc(vt->context,
+ value_ptr(n, i, vt->size));
+}
+
+static int insert_at(size_t value_size, struct node *node, unsigned index,
+ uint64_t key, void *value)
+ __dm_written_to_disk(value)
+{
+ uint32_t nr_entries = le32_to_cpu(node->header.nr_entries);
+ __le64 key_le = cpu_to_le64(key);
+
+ if (index > nr_entries ||
+ index >= le32_to_cpu(node->header.max_entries)) {
+ DMERR("too many entries in btree node for insert");
+ __dm_unbless_for_disk(value);
+ return -ENOMEM;
+ }
+
+ __dm_bless_for_disk(&key_le);
+
+ array_insert(node->keys, sizeof(*node->keys), nr_entries, index, &key_le);
+ array_insert(value_base(node), value_size, nr_entries, index, value);
+ node->header.nr_entries = cpu_to_le32(nr_entries + 1);
+
+ return 0;
+}
+
+/*----------------------------------------------------------------*/
+
+/*
+ * We want 3n entries (for some n). This works more nicely for repeated
+ * insert remove loops than (2n + 1).
+ */
+static uint32_t calc_max_entries(size_t value_size, size_t block_size)
+{
+ uint32_t total, n;
+ size_t elt_size = sizeof(uint64_t) + value_size; /* key + value */
+
+ block_size -= sizeof(struct node_header);
+ total = block_size / elt_size;
+ n = total / 3; /* rounds down */
+
+ return 3 * n;
+}
+
+int dm_btree_empty(struct dm_btree_info *info, dm_block_t *root)
+{
+ int r;
+ struct dm_block *b;
+ struct node *n;
+ size_t block_size;
+ uint32_t max_entries;
+
+ r = new_block(info, &b);
+ if (r < 0)
+ return r;
+
+ block_size = dm_bm_block_size(dm_tm_get_bm(info->tm));
+ max_entries = calc_max_entries(info->value_type.size, block_size);
+
+ n = dm_block_data(b);
+ memset(n, 0, block_size);
+ n->header.flags = cpu_to_le32(LEAF_NODE);
+ n->header.nr_entries = cpu_to_le32(0);
+ n->header.max_entries = cpu_to_le32(max_entries);
+ n->header.value_size = cpu_to_le32(info->value_type.size);
+
+ *root = dm_block_location(b);
+ return unlock_block(info, b);
+}
+EXPORT_SYMBOL_GPL(dm_btree_empty);
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Deletion uses a recursive algorithm, since we have limited stack space
+ * we explicitly manage our own stack on the heap.
+ */
+#define MAX_SPINE_DEPTH 64
+struct frame {
+ struct dm_block *b;
+ struct node *n;
+ unsigned level;
+ unsigned nr_children;
+ unsigned current_child;
+};
+
+struct del_stack {
+ struct dm_transaction_manager *tm;
+ int top;
+ struct frame spine[MAX_SPINE_DEPTH];
+};
+
+static int top_frame(struct del_stack *s, struct frame **f)
+{
+ if (s->top < 0) {
+ DMERR("btree deletion stack empty");
+ return -EINVAL;
+ }
+
+ *f = s->spine + s->top;
+
+ return 0;
+}
+
+static int unprocessed_frames(struct del_stack *s)
+{
+ return s->top >= 0;
+}
+
+static int push_frame(struct del_stack *s, dm_block_t b, unsigned level)
+{
+ int r;
+ uint32_t ref_count;
+
+ if (s->top >= MAX_SPINE_DEPTH - 1) {
+ DMERR("btree deletion stack out of memory");
+ return -ENOMEM;
+ }
+
+ r = dm_tm_ref(s->tm, b, &ref_count);
+ if (r)
+ return r;
+
+ if (ref_count > 1)
+ /*
+ * This is a shared node, so we can just decrement it's
+ * reference counter and leave the children.
+ */
+ dm_tm_dec(s->tm, b);
+
+ else {
+ struct frame *f = s->spine + ++s->top;
+
+ r = dm_tm_read_lock(s->tm, b, &btree_node_validator, &f->b);
+ if (r) {
+ s->top--;
+ return r;
+ }
+
+ f->n = dm_block_data(f->b);
+ f->level = level;
+ f->nr_children = le32_to_cpu(f->n->header.nr_entries);
+ f->current_child = 0;
+ }
+
+ return 0;
+}
+
+static void pop_frame(struct del_stack *s)
+{
+ struct frame *f = s->spine + s->top--;
+
+ dm_tm_dec(s->tm, dm_block_location(f->b));
+ dm_tm_unlock(s->tm, f->b);
+}
+
+int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
+{
+ int r;
+ struct del_stack *s;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+ s->tm = info->tm;
+ s->top = -1;
+
+ r = push_frame(s, root, 1);
+ if (r)
+ goto out;
+
+ while (unprocessed_frames(s)) {
+ uint32_t flags;
+ struct frame *f;
+ dm_block_t b;
+
+ r = top_frame(s, &f);
+ if (r)
+ goto out;
+
+ if (f->current_child >= f->nr_children) {
+ pop_frame(s);
+ continue;
+ }
+
+ flags = le32_to_cpu(f->n->header.flags);
+ if (flags & INTERNAL_NODE) {
+ b = value64(f->n, f->current_child);
+ f->current_child++;
+ r = push_frame(s, b, f->level);
+ if (r)
+ goto out;
+
+ } else if (f->level != (info->levels - 1)) {
+ b = value64(f->n, f->current_child);
+ f->current_child++;
+ r = push_frame(s, b, f->level + 1);
+ if (r)
+ goto out;
+
+ } else {
+ if (info->value_type.dec) {
+ unsigned i;
+
+ for (i = 0; i < f->nr_children; i++)
+ info->value_type.dec(info->value_type.context,
+ value_ptr(f->n, i, info->value_type.size));
+ }
+ f->current_child = f->nr_children;
+ }
+ }
+
+out:
+ kfree(s);
+ return r;
+}
+EXPORT_SYMBOL_GPL(dm_btree_del);
+
+/*----------------------------------------------------------------*/
+
+static int btree_lookup_raw(struct ro_spine *s, dm_block_t block, uint64_t key,
+ int (*search_fn)(struct node *, uint64_t),
+ uint64_t *result_key, void *v, size_t value_size)
+{
+ int i, r;
+ uint32_t flags, nr_entries;
+
+ do {
+ r = ro_step(s, block);
+ if (r < 0)
+ return r;
+
+ i = search_fn(ro_node(s), key);
+
+ flags = le32_to_cpu(ro_node(s)->header.flags);
+ nr_entries = le32_to_cpu(ro_node(s)->header.nr_entries);
+ if (i < 0 || i >= nr_entries)
+ return -ENODATA;
+
+ if (flags & INTERNAL_NODE)
+ block = value64(ro_node(s), i);
+
+ } while (!(flags & LEAF_NODE));
+
+ *result_key = le64_to_cpu(ro_node(s)->keys[i]);
+ memcpy(v, value_ptr(ro_node(s), i, value_size), value_size);
+
+ return 0;
+}
+
+int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *keys, void *value_le)
+{
+ unsigned level, last_level = info->levels - 1;
+ int r = -ENODATA;
+ uint64_t rkey;
+ __le64 internal_value_le;
+ struct ro_spine spine;
+
+ init_ro_spine(&spine, info);
+ for (level = 0; level < info->levels; level++) {
+ size_t size;
+ void *value_p;
+
+ if (level == last_level) {
+ value_p = value_le;
+ size = info->value_type.size;
+
+ } else {
+ value_p = &internal_value_le;
+ size = sizeof(uint64_t);
+ }
+
+ r = btree_lookup_raw(&spine, root, keys[level],
+ lower_bound, &rkey,
+ value_p, size);
+
+ if (!r) {
+ if (rkey != keys[level]) {
+ exit_ro_spine(&spine);
+ return -ENODATA;
+ }
+ } else {
+ exit_ro_spine(&spine);
+ return r;
+ }
+
+ root = le64_to_cpu(internal_value_le);
+ }
+ exit_ro_spine(&spine);
+
+ return r;
+}
+EXPORT_SYMBOL_GPL(dm_btree_lookup);
+
+/*
+ * Splits a node by creating a sibling node and shifting half the nodes
+ * contents across. Assumes there is a parent node, and it has room for
+ * another child.
+ *
+ * Before:
+ * +--------+
+ * | Parent |
+ * +--------+
+ * |
+ * v
+ * +----------+
+ * | A ++++++ |
+ * +----------+
+ *
+ *
+ * After:
+ * +--------+
+ * | Parent |
+ * +--------+
+ * | |
+ * v +------+
+ * +---------+ |
+ * | A* +++ | v
+ * +---------+ +-------+
+ * | B +++ |
+ * +-------+
+ *
+ * Where A* is a shadow of A.
+ */
+static int btree_split_sibling(struct shadow_spine *s, dm_block_t root,
+ unsigned parent_index, uint64_t key)
+{
+ int r;
+ size_t size;
+ unsigned nr_left, nr_right;
+ struct dm_block *left, *right, *parent;
+ struct node *ln, *rn, *pn;
+ __le64 location;
+
+ left = shadow_current(s);
+
+ r = new_block(s->info, &right);
+ if (r < 0)
+ return r;
+
+ ln = dm_block_data(left);
+ rn = dm_block_data(right);
+
+ nr_left = le32_to_cpu(ln->header.nr_entries) / 2;
+ nr_right = le32_to_cpu(ln->header.nr_entries) - nr_left;
+
+ ln->header.nr_entries = cpu_to_le32(nr_left);
+
+ rn->header.flags = ln->header.flags;
+ rn->header.nr_entries = cpu_to_le32(nr_right);
+ rn->header.max_entries = ln->header.max_entries;
+ rn->header.value_size = ln->header.value_size;
+ memcpy(rn->keys, ln->keys + nr_left, nr_right * sizeof(rn->keys[0]));
+
+ size = le32_to_cpu(ln->header.flags) & INTERNAL_NODE ?
+ sizeof(uint64_t) : s->info->value_type.size;
+ memcpy(value_ptr(rn, 0, size), value_ptr(ln, nr_left, size),
+ size * nr_right);
+
+ /*
+ * Patch up the parent
+ */
+ parent = shadow_parent(s);
+
+ pn = dm_block_data(parent);
+ location = cpu_to_le64(dm_block_location(left));
+ __dm_bless_for_disk(&location);
+ memcpy_disk(value_ptr(pn, parent_index, sizeof(__le64)),
+ &location, sizeof(__le64));
+
+ location = cpu_to_le64(dm_block_location(right));
+ __dm_bless_for_disk(&location);
+
+ r = insert_at(sizeof(__le64), pn, parent_index + 1,
+ le64_to_cpu(rn->keys[0]), &location);
+ if (r)
+ return r;
+
+ if (key < le64_to_cpu(rn->keys[0])) {
+ unlock_block(s->info, right);
+ s->nodes[1] = left;
+ } else {
+ unlock_block(s->info, left);
+ s->nodes[1] = right;
+ }
+
+ return 0;
+}
+
+/*
+ * Splits a node by creating two new children beneath the given node.
+ *
+ * Before:
+ * +----------+
+ * | A ++++++ |
+ * +----------+
+ *
+ *
+ * After:
+ * +------------+
+ * | A (shadow) |
+ * +------------+
+ * | |
+ * +------+ +----+
+ * | |
+ * v v
+ * +-------+ +-------+
+ * | B +++ | | C +++ |
+ * +-------+ +-------+
+ */
+static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
+{
+ int r;
+ size_t size;
+ unsigned nr_left, nr_right;
+ struct dm_block *left, *right, *new_parent;
+ struct node *pn, *ln, *rn;
+ __le64 val;
+
+ new_parent = shadow_current(s);
+
+ r = new_block(s->info, &left);
+ if (r < 0)
+ return r;
+
+ r = new_block(s->info, &right);
+ if (r < 0) {
+ /* FIXME: put left */
+ return r;
+ }
+
+ pn = dm_block_data(new_parent);
+ ln = dm_block_data(left);
+ rn = dm_block_data(right);
+
+ nr_left = le32_to_cpu(pn->header.nr_entries) / 2;
+ nr_right = le32_to_cpu(pn->header.nr_entries) - nr_left;
+
+ ln->header.flags = pn->header.flags;
+ ln->header.nr_entries = cpu_to_le32(nr_left);
+ ln->header.max_entries = pn->header.max_entries;
+ ln->header.value_size = pn->header.value_size;
+
+ rn->header.flags = pn->header.flags;
+ rn->header.nr_entries = cpu_to_le32(nr_right);
+ rn->header.max_entries = pn->header.max_entries;
+ rn->header.value_size = pn->header.value_size;
+
+ memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0]));
+ memcpy(rn->keys, pn->keys + nr_left, nr_right * sizeof(pn->keys[0]));
+
+ size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ?
+ sizeof(__le64) : s->info->value_type.size;
+ memcpy(value_ptr(ln, 0, size), value_ptr(pn, 0, size), nr_left * size);
+ memcpy(value_ptr(rn, 0, size), value_ptr(pn, nr_left, size),
+ nr_right * size);
+
+ /* new_parent should just point to l and r now */
+ pn->header.flags = cpu_to_le32(INTERNAL_NODE);
+ pn->header.nr_entries = cpu_to_le32(2);
+ pn->header.max_entries = cpu_to_le32(
+ calc_max_entries(sizeof(__le64),
+ dm_bm_block_size(
+ dm_tm_get_bm(s->info->tm))));
+ pn->header.value_size = cpu_to_le32(sizeof(__le64));
+
+ val = cpu_to_le64(dm_block_location(left));
+ __dm_bless_for_disk(&val);
+ pn->keys[0] = ln->keys[0];
+ memcpy_disk(value_ptr(pn, 0, sizeof(__le64)), &val, sizeof(__le64));
+
+ val = cpu_to_le64(dm_block_location(right));
+ __dm_bless_for_disk(&val);
+ pn->keys[1] = rn->keys[0];
+ memcpy_disk(value_ptr(pn, 1, sizeof(__le64)), &val, sizeof(__le64));
+
+ /*
+ * rejig the spine. This is ugly, since it knows too
+ * much about the spine
+ */
+ if (s->nodes[0] != new_parent) {
+ unlock_block(s->info, s->nodes[0]);
+ s->nodes[0] = new_parent;
+ }
+ if (key < le64_to_cpu(rn->keys[0])) {
+ unlock_block(s->info, right);
+ s->nodes[1] = left;
+ } else {
+ unlock_block(s->info, left);
+ s->nodes[1] = right;
+ }
+ s->count = 2;
+
+ return 0;
+}
+
+static int btree_insert_raw(struct shadow_spine *s, dm_block_t root,
+ struct dm_btree_value_type *vt,
+ uint64_t key, unsigned *index)
+{
+ int r, i = *index, top = 1;
+ struct node *node;
+
+ for (;;) {
+ r = shadow_step(s, root, vt);
+ if (r < 0)
+ return r;
+
+ node = dm_block_data(shadow_current(s));
+
+ /*
+ * We have to patch up the parent node, ugly, but I don't
+ * see a way to do this automatically as part of the spine
+ * op.
+ */
+ if (shadow_has_parent(s) && i >= 0) { /* FIXME: second clause unness. */
+ __le64 location = cpu_to_le64(dm_block_location(shadow_current(s)));
+
+ __dm_bless_for_disk(&location);
+ memcpy_disk(value_ptr(dm_block_data(shadow_parent(s)), i, sizeof(uint64_t)),
+ &location, sizeof(__le64));
+ }
+
+ node = dm_block_data(shadow_current(s));
+
+ if (node->header.nr_entries == node->header.max_entries) {
+ if (top)
+ r = btree_split_beneath(s, key);
+ else
+ r = btree_split_sibling(s, root, i, key);
+
+ if (r < 0)
+ return r;
+ }
+
+ node = dm_block_data(shadow_current(s));
+
+ i = lower_bound(node, key);
+
+ if (le32_to_cpu(node->header.flags) & LEAF_NODE)
+ break;
+
+ if (i < 0) {
+ /* change the bounds on the lowest key */
+ node->keys[0] = cpu_to_le64(key);
+ i = 0;
+ }
+
+ root = value64(node, i);
+ top = 0;
+ }
+
+ if (i < 0 || le64_to_cpu(node->keys[i]) != key)
+ i++;
+
+ *index = i;
+ return 0;
+}
+
+static int insert(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *keys, void *value, dm_block_t *new_root,
+ int *inserted)
+ __dm_written_to_disk(value)
+{
+ int r, need_insert;
+ unsigned level, index = -1, last_level = info->levels - 1;
+ dm_block_t block = root;
+ struct shadow_spine spine;
+ struct node *n;
+ struct dm_btree_value_type le64_type;
+
+ le64_type.context = NULL;
+ le64_type.size = sizeof(__le64);
+ le64_type.inc = NULL;
+ le64_type.dec = NULL;
+ le64_type.equal = NULL;
+
+ init_shadow_spine(&spine, info);
+
+ for (level = 0; level < (info->levels - 1); level++) {
+ r = btree_insert_raw(&spine, block, &le64_type, keys[level], &index);
+ if (r < 0)
+ goto bad;
+
+ n = dm_block_data(shadow_current(&spine));
+ need_insert = ((index >= le32_to_cpu(n->header.nr_entries)) ||
+ (le64_to_cpu(n->keys[index]) != keys[level]));
+
+ if (need_insert) {
+ dm_block_t new_tree;
+ __le64 new_le;
+
+ r = dm_btree_empty(info, &new_tree);
+ if (r < 0)
+ goto bad;
+
+ new_le = cpu_to_le64(new_tree);
+ __dm_bless_for_disk(&new_le);
+
+ r = insert_at(sizeof(uint64_t), n, index,
+ keys[level], &new_le);
+ if (r)
+ goto bad;
+ }
+
+ if (level < last_level)
+ block = value64(n, index);
+ }
+
+ r = btree_insert_raw(&spine, block, &info->value_type,
+ keys[level], &index);
+ if (r < 0)
+ goto bad;
+
+ n = dm_block_data(shadow_current(&spine));
+ need_insert = ((index >= le32_to_cpu(n->header.nr_entries)) ||
+ (le64_to_cpu(n->keys[index]) != keys[level]));
+
+ if (need_insert) {
+ if (inserted)
+ *inserted = 1;
+
+ r = insert_at(info->value_type.size, n, index,
+ keys[level], value);
+ if (r)
+ goto bad_unblessed;
+ } else {
+ if (inserted)
+ *inserted = 0;
+
+ if (info->value_type.dec &&
+ (!info->value_type.equal ||
+ !info->value_type.equal(
+ info->value_type.context,
+ value_ptr(n, index, info->value_type.size),
+ value))) {
+ info->value_type.dec(info->value_type.context,
+ value_ptr(n, index, info->value_type.size));
+ }
+ memcpy_disk(value_ptr(n, index, info->value_type.size),
+ value, info->value_type.size);
+ }
+
+ *new_root = shadow_root(&spine);
+ exit_shadow_spine(&spine);
+
+ return 0;
+
+bad:
+ __dm_unbless_for_disk(value);
+bad_unblessed:
+ exit_shadow_spine(&spine);
+ return r;
+}
+
+int dm_btree_insert(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *keys, void *value, dm_block_t *new_root)
+ __dm_written_to_disk(value)
+{
+ return insert(info, root, keys, value, new_root, NULL);
+}
+EXPORT_SYMBOL_GPL(dm_btree_insert);
+
+int dm_btree_insert_notify(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *keys, void *value, dm_block_t *new_root,
+ int *inserted)
+ __dm_written_to_disk(value)
+{
+ return insert(info, root, keys, value, new_root, inserted);
+}
+EXPORT_SYMBOL_GPL(dm_btree_insert_notify);
+
+/*----------------------------------------------------------------*/
+
+static int find_highest_key(struct ro_spine *s, dm_block_t block,
+ uint64_t *result_key, dm_block_t *next_block)
+{
+ int i, r;
+ uint32_t flags;
+
+ do {
+ r = ro_step(s, block);
+ if (r < 0)
+ return r;
+
+ flags = le32_to_cpu(ro_node(s)->header.flags);
+ i = le32_to_cpu(ro_node(s)->header.nr_entries);
+ if (!i)
+ return -ENODATA;
+ else
+ i--;
+
+ *result_key = le64_to_cpu(ro_node(s)->keys[i]);
+ if (next_block || flags & INTERNAL_NODE)
+ block = value64(ro_node(s), i);
+
+ } while (flags & INTERNAL_NODE);
+
+ if (next_block)
+ *next_block = block;
+ return 0;
+}
+
+int dm_btree_find_highest_key(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *result_keys)
+{
+ int r = 0, count = 0, level;
+ struct ro_spine spine;
+
+ init_ro_spine(&spine, info);
+ for (level = 0; level < info->levels; level++) {
+ r = find_highest_key(&spine, root, result_keys + level,
+ level == info->levels - 1 ? NULL : &root);
+ if (r == -ENODATA) {
+ r = 0;
+ break;
+
+ } else if (r)
+ break;
+
+ count++;
+ }
+ exit_ro_spine(&spine);
+
+ return r ? r : count;
+}
+EXPORT_SYMBOL_GPL(dm_btree_find_highest_key);
diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h
new file mode 100644
index 0000000..ae02c84
--- /dev/null
+++ b/drivers/md/persistent-data/dm-btree.h
@@ -0,0 +1,145 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+#ifndef _LINUX_DM_BTREE_H
+#define _LINUX_DM_BTREE_H
+
+#include "dm-block-manager.h"
+
+struct dm_transaction_manager;
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Annotations used to check on-disk metadata is handled as little-endian.
+ */
+#ifdef __CHECKER__
+# define __dm_written_to_disk(x) __releases(x)
+# define __dm_reads_from_disk(x) __acquires(x)
+# define __dm_bless_for_disk(x) __acquire(x)
+# define __dm_unbless_for_disk(x) __release(x)
+#else
+# define __dm_written_to_disk(x)
+# define __dm_reads_from_disk(x)
+# define __dm_bless_for_disk(x)
+# define __dm_unbless_for_disk(x)
+#endif
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Manipulates hierarchical B+ trees with 64-bit keys and arbitrary-sized
+ * values.
+ */
+
+/*
+ * Infomation about the values stored within the btree.
+ */
+struct dm_btree_value_type {
+ void *context;
+
+ /*
+ * The size in bytes of each value.
+ */
+ uint32_t size;
+
+ /*
+ * Any of these methods can be safely set to NULL if you do not
+ * need the corresponding feature.
+ */
+
+ /*
+ * The btree is making a duplicate of the value, for instance
+ * because previously-shared btree nodes have now diverged.
+ * @value argument is the new copy that the copy function may modify.
+ * (Probably it just wants to increment a reference count
+ * somewhere.) This method is _not_ called for insertion of a new
+ * value: It is assumed the ref count is already 1.
+ */
+ void (*inc)(void *context, void *value);
+
+ /*
+ * This value is being deleted. The btree takes care of freeing
+ * the memory pointed to by @value. Often the del function just
+ * needs to decrement a reference count somewhere.
+ */
+ void (*dec)(void *context, void *value);
+
+ /*
+ * A test for equality between two values. When a value is
+ * overwritten with a new one, the old one has the dec method
+ * called _unless_ the new and old value are deemed equal.
+ */
+ int (*equal)(void *context, void *value1, void *value2);
+};
+
+/*
+ * The shape and contents of a btree.
+ */
+struct dm_btree_info {
+ struct dm_transaction_manager *tm;
+
+ /*
+ * Number of nested btrees. (Not the depth of a single tree.)
+ */
+ unsigned levels;
+ struct dm_btree_value_type value_type;
+};
+
+/*
+ * Set up an empty tree. O(1).
+ */
+int dm_btree_empty(struct dm_btree_info *info, dm_block_t *root);
+
+/*
+ * Delete a tree. O(n) - this is the slow one! It can also block, so
+ * please don't call it on an IO path.
+ */
+int dm_btree_del(struct dm_btree_info *info, dm_block_t root);
+
+/*
+ * All the lookup functions return -ENODATA if the key cannot be found.
+ */
+
+/*
+ * Tries to find a key that matches exactly. O(ln(n))
+ */
+int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *keys, void *value_le);
+
+/*
+ * Insertion (or overwrite an existing value). O(ln(n))
+ */
+int dm_btree_insert(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *keys, void *value, dm_block_t *new_root)
+ __dm_written_to_disk(value);
+
+/*
+ * A variant of insert that indicates whether it actually inserted or just
+ * overwrote. Useful if you're keeping track of the number of entries in a
+ * tree.
+ */
+int dm_btree_insert_notify(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *keys, void *value, dm_block_t *new_root,
+ int *inserted)
+ __dm_written_to_disk(value);
+
+/*
+ * Remove a key if present. This doesn't remove empty sub trees. Normally
+ * subtrees represent a separate entity, like a snapshot map, so this is
+ * correct behaviour. O(ln(n)).
+ */
+int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *keys, dm_block_t *new_root);
+
+/*
+ * Returns < 0 on failure. Otherwise the number of key entries that have
+ * been filled out. Remember trees can have zero entries, and as such have
+ * no highest key.
+ */
+int dm_btree_find_highest_key(struct dm_btree_info *info, dm_block_t root,
+ uint64_t *result_keys);
+
+#endif /* _LINUX_DM_BTREE_H */
diff --git a/drivers/md/persistent-data/dm-persistent-data-internal.h b/drivers/md/persistent-data/dm-persistent-data-internal.h
new file mode 100644
index 0000000..c49e26f
--- /dev/null
+++ b/drivers/md/persistent-data/dm-persistent-data-internal.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef _DM_PERSISTENT_DATA_INTERNAL_H
+#define _DM_PERSISTENT_DATA_INTERNAL_H
+
+#include "dm-block-manager.h"
+
+static inline unsigned dm_hash_block(dm_block_t b, unsigned hash_mask)
+{
+ const unsigned BIG_PRIME = 4294967291UL;
+
+ return (((unsigned) b) * BIG_PRIME) & hash_mask;
+}
+
+#endif /* _PERSISTENT_DATA_INTERNAL_H */
diff --git a/drivers/md/persistent-data/dm-space-map-checker.c b/drivers/md/persistent-data/dm-space-map-checker.c
new file mode 100644
index 0000000..bb44a93
--- /dev/null
+++ b/drivers/md/persistent-data/dm-space-map-checker.c
@@ -0,0 +1,437 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-space-map-checker.h"
+
+#include <linux/device-mapper.h>
+
+#ifdef CONFIG_DM_DEBUG_SPACE_MAPS
+
+#define DM_MSG_PREFIX "space map checker"
+
+/*----------------------------------------------------------------*/
+
+struct count_array {
+ dm_block_t nr;
+ dm_block_t nr_free;
+
+ uint32_t *counts;
+};
+
+static int ca_get_count(struct count_array *ca, dm_block_t b, uint32_t *count)
+{
+ if (b >= ca->nr)
+ return -EINVAL;
+
+ *count = ca->counts[b];
+ return 0;
+}
+
+static int ca_count_more_than_one(struct count_array *ca, dm_block_t b, int *r)
+{
+ if (b >= ca->nr)
+ return -EINVAL;
+
+ *r = ca->counts[b] > 1;
+ return 0;
+}
+
+static int ca_set_count(struct count_array *ca, dm_block_t b, uint32_t count)
+{
+ uint32_t old_count;
+
+ if (b >= ca->nr)
+ return -EINVAL;
+
+ old_count = ca->counts[b];
+
+ if (!count && old_count)
+ ca->nr_free++;
+
+ else if (count && !old_count)
+ ca->nr_free--;
+
+ ca->counts[b] = count;
+ return 0;
+}
+
+static int ca_inc_block(struct count_array *ca, dm_block_t b)
+{
+ if (b >= ca->nr)
+ return -EINVAL;
+
+ ca_set_count(ca, b, ca->counts[b] + 1);
+ return 0;
+}
+
+static int ca_dec_block(struct count_array *ca, dm_block_t b)
+{
+ if (b >= ca->nr)
+ return -EINVAL;
+
+ BUG_ON(ca->counts[b] == 0);
+ ca_set_count(ca, b, ca->counts[b] - 1);
+ return 0;
+}
+
+static int ca_create(struct count_array *ca, struct dm_space_map *sm)
+{
+ int r;
+ dm_block_t nr_blocks;
+
+ r = dm_sm_get_nr_blocks(sm, &nr_blocks);
+ if (r)
+ return r;
+
+ ca->nr = nr_blocks;
+ ca->nr_free = nr_blocks;
+ ca->counts = kzalloc(sizeof(*ca->counts) * nr_blocks, GFP_KERNEL);
+ if (!ca->counts)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int ca_load(struct count_array *ca, struct dm_space_map *sm)
+{
+ int r;
+ uint32_t count;
+ dm_block_t nr_blocks, i;
+
+ r = dm_sm_get_nr_blocks(sm, &nr_blocks);
+ if (r)
+ return r;
+
+ BUG_ON(ca->nr != nr_blocks);
+
+ DMWARN("Loading debug space map from disk. This may take some time");
+ for (i = 0; i < nr_blocks; i++) {
+ r = dm_sm_get_count(sm, i, &count);
+ if (r) {
+ DMERR("load failed");
+ return r;
+ }
+
+ ca_set_count(ca, i, count);
+ }
+ DMWARN("Load complete");
+
+ return 0;
+}
+
+static int ca_extend(struct count_array *ca, dm_block_t extra_blocks)
+{
+ dm_block_t nr_blocks = ca->nr + extra_blocks;
+ uint32_t *counts = kzalloc(sizeof(*counts) * nr_blocks, GFP_KERNEL);
+ if (!counts)
+ return -ENOMEM;
+
+ memcpy(counts, ca->counts, sizeof(*counts) * ca->nr);
+ kfree(ca->counts);
+ ca->nr = nr_blocks;
+ ca->nr_free += extra_blocks;
+ ca->counts = counts;
+ return 0;
+}
+
+static int ca_commit(struct count_array *old, struct count_array *new)
+{
+ if (old->nr != new->nr) {
+ BUG_ON(old->nr > new->nr);
+ ca_extend(old, new->nr - old->nr);
+ }
+
+ BUG_ON(old->nr != new->nr);
+ old->nr_free = new->nr_free;
+ memcpy(old->counts, new->counts, sizeof(*old->counts) * old->nr);
+ return 0;
+}
+
+static void ca_destroy(struct count_array *ca)
+{
+ kfree(ca->counts);
+}
+
+/*----------------------------------------------------------------*/
+
+struct sm_checker {
+ struct dm_space_map sm;
+
+ struct count_array old_counts;
+ struct count_array counts;
+
+ struct dm_space_map *real_sm;
+};
+
+static void sm_checker_destroy(struct dm_space_map *sm)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+
+ dm_sm_destroy(smc->real_sm);
+ ca_destroy(&smc->old_counts);
+ ca_destroy(&smc->counts);
+ kfree(smc);
+}
+
+static int sm_checker_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ int r = dm_sm_get_nr_blocks(smc->real_sm, count);
+ if (!r)
+ BUG_ON(smc->old_counts.nr != *count);
+ return r;
+}
+
+static int sm_checker_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ int r = dm_sm_get_nr_free(smc->real_sm, count);
+ if (!r) {
+ /*
+ * Slow, but we know it's correct.
+ */
+ dm_block_t b, n = 0;
+ for (b = 0; b < smc->old_counts.nr; b++)
+ if (smc->old_counts.counts[b] == 0 &&
+ smc->counts.counts[b] == 0)
+ n++;
+
+ if (n != *count)
+ DMERR("free block counts differ, checker %u, sm-disk:%u",
+ (unsigned) n, (unsigned) *count);
+ }
+ return r;
+}
+
+static int sm_checker_new_block(struct dm_space_map *sm, dm_block_t *b)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ int r = dm_sm_new_block(smc->real_sm, b);
+
+ if (!r) {
+ BUG_ON(*b >= smc->old_counts.nr);
+ BUG_ON(smc->old_counts.counts[*b] != 0);
+ BUG_ON(*b >= smc->counts.nr);
+ BUG_ON(smc->counts.counts[*b] != 0);
+ ca_set_count(&smc->counts, *b, 1);
+ }
+
+ return r;
+}
+
+static int sm_checker_inc_block(struct dm_space_map *sm, dm_block_t b)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ int r = dm_sm_inc_block(smc->real_sm, b);
+ int r2 = ca_inc_block(&smc->counts, b);
+ BUG_ON(r != r2);
+ return r;
+}
+
+static int sm_checker_dec_block(struct dm_space_map *sm, dm_block_t b)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ int r = dm_sm_dec_block(smc->real_sm, b);
+ int r2 = ca_dec_block(&smc->counts, b);
+ BUG_ON(r != r2);
+ return r;
+}
+
+static int sm_checker_get_count(struct dm_space_map *sm, dm_block_t b, uint32_t *result)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ uint32_t result2 = 0;
+ int r = dm_sm_get_count(smc->real_sm, b, result);
+ int r2 = ca_get_count(&smc->counts, b, &result2);
+
+ BUG_ON(r != r2);
+ if (!r)
+ BUG_ON(*result != result2);
+ return r;
+}
+
+static int sm_checker_count_more_than_one(struct dm_space_map *sm, dm_block_t b, int *result)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ int result2 = 0;
+ int r = dm_sm_count_is_more_than_one(smc->real_sm, b, result);
+ int r2 = ca_count_more_than_one(&smc->counts, b, &result2);
+
+ BUG_ON(r != r2);
+ if (!r)
+ BUG_ON(!(*result) && result2);
+ return r;
+}
+
+static int sm_checker_set_count(struct dm_space_map *sm, dm_block_t b, uint32_t count)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ uint32_t old_rc;
+ int r = dm_sm_set_count(smc->real_sm, b, count);
+ int r2;
+
+ BUG_ON(b >= smc->counts.nr);
+ old_rc = smc->counts.counts[b];
+ r2 = ca_set_count(&smc->counts, b, count);
+ BUG_ON(r != r2);
+
+ return r;
+}
+
+static int sm_checker_commit(struct dm_space_map *sm)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ int r;
+
+ r = dm_sm_commit(smc->real_sm);
+ if (r)
+ return r;
+
+ r = ca_commit(&smc->old_counts, &smc->counts);
+ if (r)
+ return r;
+
+ return 0;
+}
+
+static int sm_checker_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ int r = dm_sm_extend(smc->real_sm, extra_blocks);
+ if (r)
+ return r;
+
+ return ca_extend(&smc->counts, extra_blocks);
+}
+
+static int sm_checker_root_size(struct dm_space_map *sm, size_t *result)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ return dm_sm_root_size(smc->real_sm, result);
+}
+
+static int sm_checker_copy_root(struct dm_space_map *sm, void *copy_to_here_le, size_t len)
+{
+ struct sm_checker *smc = container_of(sm, struct sm_checker, sm);
+ return dm_sm_copy_root(smc->real_sm, copy_to_here_le, len);
+}
+
+/*----------------------------------------------------------------*/
+
+static struct dm_space_map ops_ = {
+ .destroy = sm_checker_destroy,
+ .get_nr_blocks = sm_checker_get_nr_blocks,
+ .get_nr_free = sm_checker_get_nr_free,
+ .inc_block = sm_checker_inc_block,
+ .dec_block = sm_checker_dec_block,
+ .new_block = sm_checker_new_block,
+ .get_count = sm_checker_get_count,
+ .count_is_more_than_one = sm_checker_count_more_than_one,
+ .set_count = sm_checker_set_count,
+ .commit = sm_checker_commit,
+ .extend = sm_checker_extend,
+ .root_size = sm_checker_root_size,
+ .copy_root = sm_checker_copy_root
+};
+
+struct dm_space_map *dm_sm_checker_create(struct dm_space_map *sm)
+{
+ int r;
+ struct sm_checker *smc;
+
+ if (!sm)
+ return NULL;
+
+ smc = kmalloc(sizeof(*smc), GFP_KERNEL);
+ if (!smc)
+ return NULL;
+
+ memcpy(&smc->sm, &ops_, sizeof(smc->sm));
+ r = ca_create(&smc->old_counts, sm);
+ if (r) {
+ kfree(smc);
+ return NULL;
+ }
+
+ r = ca_create(&smc->counts, sm);
+ if (r) {
+ ca_destroy(&smc->old_counts);
+ kfree(smc);
+ return NULL;
+ }
+
+ smc->real_sm = sm;
+
+ r = ca_load(&smc->counts, sm);
+ if (r) {
+ ca_destroy(&smc->counts);
+ ca_destroy(&smc->old_counts);
+ kfree(smc);
+ return NULL;
+ }
+
+ r = ca_commit(&smc->old_counts, &smc->counts);
+ if (r) {
+ ca_destroy(&smc->counts);
+ ca_destroy(&smc->old_counts);
+ kfree(smc);
+ return NULL;
+ }
+
+ return &smc->sm;
+}
+EXPORT_SYMBOL_GPL(dm_sm_checker_create);
+
+struct dm_space_map *dm_sm_checker_create_fresh(struct dm_space_map *sm)
+{
+ int r;
+ struct sm_checker *smc;
+
+ if (!sm)
+ return NULL;
+
+ smc = kmalloc(sizeof(*smc), GFP_KERNEL);
+ if (!smc)
+ return NULL;
+
+ memcpy(&smc->sm, &ops_, sizeof(smc->sm));
+ r = ca_create(&smc->old_counts, sm);
+ if (r) {
+ kfree(smc);
+ return NULL;
+ }
+
+ r = ca_create(&smc->counts, sm);
+ if (r) {
+ ca_destroy(&smc->old_counts);
+ kfree(smc);
+ return NULL;
+ }
+
+ smc->real_sm = sm;
+ return &smc->sm;
+}
+EXPORT_SYMBOL_GPL(dm_sm_checker_create_fresh);
+
+/*----------------------------------------------------------------*/
+
+#else
+
+struct dm_space_map *dm_sm_checker_create(struct dm_space_map *sm)
+{
+ return sm;
+}
+EXPORT_SYMBOL_GPL(dm_sm_checker_create);
+
+struct dm_space_map *dm_sm_checker_create_fresh(struct dm_space_map *sm)
+{
+ return sm;
+}
+EXPORT_SYMBOL_GPL(dm_sm_checker_create_fresh);
+
+/*----------------------------------------------------------------*/
+
+#endif
diff --git a/drivers/md/persistent-data/dm-space-map-checker.h b/drivers/md/persistent-data/dm-space-map-checker.h
new file mode 100644
index 0000000..444dccf
--- /dev/null
+++ b/drivers/md/persistent-data/dm-space-map-checker.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef SNAPSHOTS_SPACE_MAP_CHECKER_H
+#define SNAPSHOTS_SPACE_MAP_CHECKER_H
+
+#include "dm-space-map.h"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * This space map wraps a real on-disk space map, and verifies all of its
+ * operations. It uses a lot of memory, so only use if you have a specific
+ * problem that you're debugging.
+ *
+ * Ownership of @sm passes.
+ */
+struct dm_space_map *dm_sm_checker_create(struct dm_space_map *sm);
+struct dm_space_map *dm_sm_checker_create_fresh(struct dm_space_map *sm);
+
+/*----------------------------------------------------------------*/
+
+#endif
diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
new file mode 100644
index 0000000..df2494c
--- /dev/null
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -0,0 +1,705 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-space-map-common.h"
+#include "dm-transaction-manager.h"
+
+#include <linux/bitops.h>
+#include <linux/device-mapper.h>
+
+#define DM_MSG_PREFIX "space map common"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Index validator.
+ */
+#define INDEX_CSUM_XOR 160478
+
+static void index_prepare_for_write(struct dm_block_validator *v,
+ struct dm_block *b,
+ size_t block_size)
+{
+ struct disk_metadata_index *mi_le = dm_block_data(b);
+
+ mi_le->blocknr = cpu_to_le64(dm_block_location(b));
+ mi_le->csum = cpu_to_le32(dm_bm_checksum(&mi_le->padding,
+ block_size - sizeof(__le32),
+ INDEX_CSUM_XOR));
+}
+
+static int index_check(struct dm_block_validator *v,
+ struct dm_block *b,
+ size_t block_size)
+{
+ struct disk_metadata_index *mi_le = dm_block_data(b);
+ __le32 csum_disk;
+
+ if (dm_block_location(b) != le64_to_cpu(mi_le->blocknr)) {
+ DMERR("index_check failed blocknr %llu wanted %llu",
+ le64_to_cpu(mi_le->blocknr), dm_block_location(b));
+ return -ENOTBLK;
+ }
+
+ csum_disk = cpu_to_le32(dm_bm_checksum(&mi_le->padding,
+ block_size - sizeof(__le32),
+ INDEX_CSUM_XOR));
+ if (csum_disk != mi_le->csum) {
+ DMERR("index_check failed csum %u wanted %u",
+ le32_to_cpu(csum_disk), le32_to_cpu(mi_le->csum));
+ return -EILSEQ;
+ }
+
+ return 0;
+}
+
+static struct dm_block_validator index_validator = {
+ .name = "index",
+ .prepare_for_write = index_prepare_for_write,
+ .check = index_check
+};
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Bitmap validator
+ */
+#define BITMAP_CSUM_XOR 240779
+
+static void bitmap_prepare_for_write(struct dm_block_validator *v,
+ struct dm_block *b,
+ size_t block_size)
+{
+ struct disk_bitmap_header *disk_header = dm_block_data(b);
+
+ disk_header->blocknr = cpu_to_le64(dm_block_location(b));
+ disk_header->csum = cpu_to_le32(dm_bm_checksum(&disk_header->not_used,
+ block_size - sizeof(__le32),
+ BITMAP_CSUM_XOR));
+}
+
+static int bitmap_check(struct dm_block_validator *v,
+ struct dm_block *b,
+ size_t block_size)
+{
+ struct disk_bitmap_header *disk_header = dm_block_data(b);
+ __le32 csum_disk;
+
+ if (dm_block_location(b) != le64_to_cpu(disk_header->blocknr)) {
+ DMERR("bitmap check failed blocknr %llu wanted %llu",
+ le64_to_cpu(disk_header->blocknr), dm_block_location(b));
+ return -ENOTBLK;
+ }
+
+ csum_disk = cpu_to_le32(dm_bm_checksum(&disk_header->not_used,
+ block_size - sizeof(__le32),
+ BITMAP_CSUM_XOR));
+ if (csum_disk != disk_header->csum) {
+ DMERR("bitmap check failed csum %u wanted %u",
+ le32_to_cpu(csum_disk), le32_to_cpu(disk_header->csum));
+ return -EILSEQ;
+ }
+
+ return 0;
+}
+
+static struct dm_block_validator dm_sm_bitmap_validator = {
+ .name = "sm_bitmap",
+ .prepare_for_write = bitmap_prepare_for_write,
+ .check = bitmap_check
+};
+
+/*----------------------------------------------------------------*/
+
+#define ENTRIES_PER_WORD 32
+#define ENTRIES_SHIFT 5
+
+static void *dm_bitmap_data(struct dm_block *b)
+{
+ return dm_block_data(b) + sizeof(struct disk_bitmap_header);
+}
+
+#define WORD_MASK_HIGH 0xAAAAAAAAAAAAAAAAULL
+
+static unsigned bitmap_word_used(void *addr, unsigned b)
+{
+ __le64 *words_le = addr;
+ __le64 *w_le = words_le + (b >> ENTRIES_SHIFT);
+
+ uint64_t bits = le64_to_cpu(*w_le);
+ uint64_t mask = (bits + WORD_MASK_HIGH + 1) & WORD_MASK_HIGH;
+
+ return !(~bits & mask);
+}
+
+static unsigned sm_lookup_bitmap(void *addr, unsigned b)
+{
+ __le64 *words_le = addr;
+ __le64 *w_le = words_le + (b >> ENTRIES_SHIFT);
+ unsigned hi, lo;
+
+ b = (b & (ENTRIES_PER_WORD - 1)) << 1;
+ hi = !!test_bit_le(b, (void *) w_le);
+ lo = !!test_bit_le(b + 1, (void *) w_le);
+ return (hi << 1) | lo;
+}
+
+static void sm_set_bitmap(void *addr, unsigned b, unsigned val)
+{
+ __le64 *words_le = addr;
+ __le64 *w_le = words_le + (b >> ENTRIES_SHIFT);
+
+ b = (b & (ENTRIES_PER_WORD - 1)) << 1;
+
+ if (val & 2)
+ __set_bit_le(b, (void *) w_le);
+ else
+ __clear_bit_le(b, (void *) w_le);
+
+ if (val & 1)
+ __set_bit_le(b + 1, (void *) w_le);
+ else
+ __clear_bit_le(b + 1, (void *) w_le);
+}
+
+static int sm_find_free(void *addr, unsigned begin, unsigned end,
+ unsigned *result)
+{
+ while (begin < end) {
+ if (!(begin & (ENTRIES_PER_WORD - 1)) &&
+ bitmap_word_used(addr, begin)) {
+ begin += ENTRIES_PER_WORD;
+ continue;
+ }
+
+ if (!sm_lookup_bitmap(addr, begin)) {
+ *result = begin;
+ return 0;
+ }
+
+ begin++;
+ }
+
+ return -ENOSPC;
+}
+
+/*----------------------------------------------------------------*/
+
+static int sm_ll_init(struct ll_disk *ll, struct dm_transaction_manager *tm)
+{
+ ll->tm = tm;
+
+ ll->bitmap_info.tm = tm;
+ ll->bitmap_info.levels = 1;
+
+ /*
+ * Because the new bitmap blocks are created via a shadow
+ * operation, the old entry has already had its reference count
+ * decremented and we don't need the btree to do any bookkeeping.
+ */
+ ll->bitmap_info.value_type.size = sizeof(struct disk_index_entry);
+ ll->bitmap_info.value_type.inc = NULL;
+ ll->bitmap_info.value_type.dec = NULL;
+ ll->bitmap_info.value_type.equal = NULL;
+
+ ll->ref_count_info.tm = tm;
+ ll->ref_count_info.levels = 1;
+ ll->ref_count_info.value_type.size = sizeof(uint32_t);
+ ll->ref_count_info.value_type.inc = NULL;
+ ll->ref_count_info.value_type.dec = NULL;
+ ll->ref_count_info.value_type.equal = NULL;
+
+ ll->block_size = dm_bm_block_size(dm_tm_get_bm(tm));
+
+ if (ll->block_size > (1 << 30)) {
+ DMERR("block size too big to hold bitmaps");
+ return -EINVAL;
+ }
+
+ ll->entries_per_block = (ll->block_size - sizeof(struct disk_bitmap_header)) *
+ ENTRIES_PER_BYTE;
+ ll->nr_blocks = 0;
+ ll->bitmap_root = 0;
+ ll->ref_count_root = 0;
+
+ return 0;
+}
+
+int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
+{
+ int r;
+ dm_block_t i, nr_blocks, nr_indexes;
+ unsigned old_blocks, blocks;
+
+ nr_blocks = ll->nr_blocks + extra_blocks;
+ old_blocks = dm_sector_div_up(ll->nr_blocks, ll->entries_per_block);
+ blocks = dm_sector_div_up(nr_blocks, ll->entries_per_block);
+
+ nr_indexes = dm_sector_div_up(nr_blocks, ll->entries_per_block);
+ if (nr_indexes > ll->max_entries(ll)) {
+ DMERR("space map too large");
+ return -EINVAL;
+ }
+
+ for (i = old_blocks; i < blocks; i++) {
+ struct dm_block *b;
+ struct disk_index_entry idx;
+
+ r = dm_tm_new_block(ll->tm, &dm_sm_bitmap_validator, &b);
+ if (r < 0)
+ return r;
+ idx.blocknr = cpu_to_le64(dm_block_location(b));
+
+ r = dm_tm_unlock(ll->tm, b);
+ if (r < 0)
+ return r;
+
+ idx.nr_free = cpu_to_le32(ll->entries_per_block);
+ idx.none_free_before = 0;
+
+ r = ll->save_ie(ll, i, &idx);
+ if (r < 0)
+ return r;
+ }
+
+ ll->nr_blocks = nr_blocks;
+ return 0;
+}
+
+int sm_ll_lookup_bitmap(struct ll_disk *ll, dm_block_t b, uint32_t *result)
+{
+ int r;
+ dm_block_t index = b;
+ struct disk_index_entry ie_disk;
+ struct dm_block *blk;
+
+ b = do_div(index, ll->entries_per_block);
+ r = ll->load_ie(ll, index, &ie_disk);
+ if (r < 0)
+ return r;
+
+ r = dm_tm_read_lock(ll->tm, le64_to_cpu(ie_disk.blocknr),
+ &dm_sm_bitmap_validator, &blk);
+ if (r < 0)
+ return r;
+
+ *result = sm_lookup_bitmap(dm_bitmap_data(blk), b);
+
+ return dm_tm_unlock(ll->tm, blk);
+}
+
+int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result)
+{
+ __le32 le_rc;
+ int r = sm_ll_lookup_bitmap(ll, b, result);
+
+ if (r)
+ return r;
+
+ if (*result != 3)
+ return r;
+
+ r = dm_btree_lookup(&ll->ref_count_info, ll->ref_count_root, &b, &le_rc);
+ if (r < 0)
+ return r;
+
+ *result = le32_to_cpu(le_rc);
+
+ return r;
+}
+
+int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
+ dm_block_t end, dm_block_t *result)
+{
+ int r;
+ struct disk_index_entry ie_disk;
+ dm_block_t i, index_begin = begin;
+ dm_block_t index_end = dm_sector_div_up(end, ll->entries_per_block);
+
+ /*
+ * FIXME: Use shifts
+ */
+ begin = do_div(index_begin, ll->entries_per_block);
+ end = do_div(end, ll->entries_per_block);
+
+ for (i = index_begin; i < index_end; i++, begin = 0) {
+ struct dm_block *blk;
+ unsigned position;
+ uint32_t bit_end;
+
+ r = ll->load_ie(ll, i, &ie_disk);
+ if (r < 0)
+ return r;
+
+ if (le32_to_cpu(ie_disk.nr_free) == 0)
+ continue;
+
+ r = dm_tm_read_lock(ll->tm, le64_to_cpu(ie_disk.blocknr),
+ &dm_sm_bitmap_validator, &blk);
+ if (r < 0)
+ return r;
+
+ bit_end = (i == index_end - 1) ? end : ll->entries_per_block;
+
+ r = sm_find_free(dm_bitmap_data(blk),
+ max_t(unsigned, begin, le32_to_cpu(ie_disk.none_free_before)),
+ bit_end, &position);
+ if (r == -ENOSPC) {
+ /*
+ * This might happen because we started searching
+ * part way through the bitmap.
+ */
+ dm_tm_unlock(ll->tm, blk);
+ continue;
+
+ } else if (r < 0) {
+ dm_tm_unlock(ll->tm, blk);
+ return r;
+ }
+
+ r = dm_tm_unlock(ll->tm, blk);
+ if (r < 0)
+ return r;
+
+ *result = i * ll->entries_per_block + (dm_block_t) position;
+ return 0;
+ }
+
+ return -ENOSPC;
+}
+
+int sm_ll_insert(struct ll_disk *ll, dm_block_t b,
+ uint32_t ref_count, enum allocation_event *ev)
+{
+ int r;
+ uint32_t bit, old;
+ struct dm_block *nb;
+ dm_block_t index = b;
+ struct disk_index_entry ie_disk;
+ void *bm_le;
+ int inc;
+
+ bit = do_div(index, ll->entries_per_block);
+ r = ll->load_ie(ll, index, &ie_disk);
+ if (r < 0)
+ return r;
+
+ r = dm_tm_shadow_block(ll->tm, le64_to_cpu(ie_disk.blocknr),
+ &dm_sm_bitmap_validator, &nb, &inc);
+ if (r < 0) {
+ DMERR("dm_tm_shadow_block() failed");
+ return r;
+ }
+ ie_disk.blocknr = cpu_to_le64(dm_block_location(nb));
+
+ bm_le = dm_bitmap_data(nb);
+ old = sm_lookup_bitmap(bm_le, bit);
+
+ if (ref_count <= 2) {
+ sm_set_bitmap(bm_le, bit, ref_count);
+
+ r = dm_tm_unlock(ll->tm, nb);
+ if (r < 0)
+ return r;
+
+#if 0
+ /* FIXME: dm_btree_remove doesn't handle this yet */
+ if (old > 2) {
+ r = dm_btree_remove(&ll->ref_count_info,
+ ll->ref_count_root,
+ &b, &ll->ref_count_root);
+ if (r)
+ return r;
+ }
+#endif
+
+ } else {
+ __le32 le_rc = cpu_to_le32(ref_count);
+
+ sm_set_bitmap(bm_le, bit, 3);
+ r = dm_tm_unlock(ll->tm, nb);
+ if (r < 0)
+ return r;
+
+ __dm_bless_for_disk(&le_rc);
+ r = dm_btree_insert(&ll->ref_count_info, ll->ref_count_root,
+ &b, &le_rc, &ll->ref_count_root);
+ if (r < 0) {
+ DMERR("ref count insert failed");
+ return r;
+ }
+ }
+
+ if (ref_count && !old) {
+ *ev = SM_ALLOC;
+ ll->nr_allocated++;
+ ie_disk.nr_free = cpu_to_le32(le32_to_cpu(ie_disk.nr_free) - 1);
+ if (le32_to_cpu(ie_disk.none_free_before) == bit)
+ ie_disk.none_free_before = cpu_to_le32(bit + 1);
+
+ } else if (old && !ref_count) {
+ *ev = SM_FREE;
+ ll->nr_allocated--;
+ ie_disk.nr_free = cpu_to_le32(le32_to_cpu(ie_disk.nr_free) + 1);
+ ie_disk.none_free_before = cpu_to_le32(min(le32_to_cpu(ie_disk.none_free_before), bit));
+ }
+
+ return ll->save_ie(ll, index, &ie_disk);
+}
+
+int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev)
+{
+ int r;
+ uint32_t rc;
+
+ r = sm_ll_lookup(ll, b, &rc);
+ if (r)
+ return r;
+
+ return sm_ll_insert(ll, b, rc + 1, ev);
+}
+
+int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev)
+{
+ int r;
+ uint32_t rc;
+
+ r = sm_ll_lookup(ll, b, &rc);
+ if (r)
+ return r;
+
+ if (!rc)
+ return -EINVAL;
+
+ return sm_ll_insert(ll, b, rc - 1, ev);
+}
+
+int sm_ll_commit(struct ll_disk *ll)
+{
+ return ll->commit(ll);
+}
+
+/*----------------------------------------------------------------*/
+
+static int metadata_ll_load_ie(struct ll_disk *ll, dm_block_t index,
+ struct disk_index_entry *ie)
+{
+ memcpy(ie, ll->mi_le.index + index, sizeof(*ie));
+ return 0;
+}
+
+static int metadata_ll_save_ie(struct ll_disk *ll, dm_block_t index,
+ struct disk_index_entry *ie)
+{
+ memcpy(ll->mi_le.index + index, ie, sizeof(*ie));
+ return 0;
+}
+
+static int metadata_ll_init_index(struct ll_disk *ll)
+{
+ int r;
+ struct dm_block *b;
+
+ r = dm_tm_new_block(ll->tm, &index_validator, &b);
+ if (r < 0)
+ return r;
+
+ memcpy(dm_block_data(b), &ll->mi_le, sizeof(ll->mi_le));
+ ll->bitmap_root = dm_block_location(b);
+
+ return dm_tm_unlock(ll->tm, b);
+}
+
+static int metadata_ll_open(struct ll_disk *ll)
+{
+ int r;
+ struct dm_block *block;
+
+ r = dm_tm_read_lock(ll->tm, ll->bitmap_root,
+ &index_validator, &block);
+ if (r)
+ return r;
+
+ memcpy(&ll->mi_le, dm_block_data(block), sizeof(ll->mi_le));
+ return dm_tm_unlock(ll->tm, block);
+}
+
+static dm_block_t metadata_ll_max_entries(struct ll_disk *ll)
+{
+ return MAX_METADATA_BITMAPS;
+}
+
+static int metadata_ll_commit(struct ll_disk *ll)
+{
+ int r, inc;
+ struct dm_block *b;
+
+ r = dm_tm_shadow_block(ll->tm, ll->bitmap_root, &index_validator, &b, &inc);
+ if (r)
+ return r;
+
+ memcpy(dm_block_data(b), &ll->mi_le, sizeof(ll->mi_le));
+ ll->bitmap_root = dm_block_location(b);
+
+ return dm_tm_unlock(ll->tm, b);
+}
+
+int sm_ll_new_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm)
+{
+ int r;
+
+ r = sm_ll_init(ll, tm);
+ if (r < 0)
+ return r;
+
+ ll->load_ie = metadata_ll_load_ie;
+ ll->save_ie = metadata_ll_save_ie;
+ ll->init_index = metadata_ll_init_index;
+ ll->open_index = metadata_ll_open;
+ ll->max_entries = metadata_ll_max_entries;
+ ll->commit = metadata_ll_commit;
+
+ ll->nr_blocks = 0;
+ ll->nr_allocated = 0;
+
+ r = ll->init_index(ll);
+ if (r < 0)
+ return r;
+
+ r = dm_btree_empty(&ll->ref_count_info, &ll->ref_count_root);
+ if (r < 0)
+ return r;
+
+ return 0;
+}
+
+int sm_ll_open_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm,
+ void *root_le, size_t len)
+{
+ int r;
+ struct disk_sm_root *smr = root_le;
+
+ if (len < sizeof(struct disk_sm_root)) {
+ DMERR("sm_metadata root too small");
+ return -ENOMEM;
+ }
+
+ r = sm_ll_init(ll, tm);
+ if (r < 0)
+ return r;
+
+ ll->load_ie = metadata_ll_load_ie;
+ ll->save_ie = metadata_ll_save_ie;
+ ll->init_index = metadata_ll_init_index;
+ ll->open_index = metadata_ll_open;
+ ll->max_entries = metadata_ll_max_entries;
+ ll->commit = metadata_ll_commit;
+
+ ll->nr_blocks = le64_to_cpu(smr->nr_blocks);
+ ll->nr_allocated = le64_to_cpu(smr->nr_allocated);
+ ll->bitmap_root = le64_to_cpu(smr->bitmap_root);
+ ll->ref_count_root = le64_to_cpu(smr->ref_count_root);
+
+ return ll->open_index(ll);
+}
+
+/*----------------------------------------------------------------*/
+
+static int disk_ll_load_ie(struct ll_disk *ll, dm_block_t index,
+ struct disk_index_entry *ie)
+{
+ return dm_btree_lookup(&ll->bitmap_info, ll->bitmap_root, &index, ie);
+}
+
+static int disk_ll_save_ie(struct ll_disk *ll, dm_block_t index,
+ struct disk_index_entry *ie)
+{
+ __dm_bless_for_disk(ie);
+ return dm_btree_insert(&ll->bitmap_info, ll->bitmap_root,
+ &index, ie, &ll->bitmap_root);
+}
+
+static int disk_ll_init_index(struct ll_disk *ll)
+{
+ return dm_btree_empty(&ll->bitmap_info, &ll->bitmap_root);
+}
+
+static int disk_ll_open(struct ll_disk *ll)
+{
+ /* nothing to do */
+ return 0;
+}
+
+static dm_block_t disk_ll_max_entries(struct ll_disk *ll)
+{
+ return -1ULL;
+}
+
+static int disk_ll_commit(struct ll_disk *ll)
+{
+ return 0;
+}
+
+int sm_ll_new_disk(struct ll_disk *ll, struct dm_transaction_manager *tm)
+{
+ int r;
+
+ r = sm_ll_init(ll, tm);
+ if (r < 0)
+ return r;
+
+ ll->load_ie = disk_ll_load_ie;
+ ll->save_ie = disk_ll_save_ie;
+ ll->init_index = disk_ll_init_index;
+ ll->open_index = disk_ll_open;
+ ll->max_entries = disk_ll_max_entries;
+ ll->commit = disk_ll_commit;
+
+ ll->nr_blocks = 0;
+ ll->nr_allocated = 0;
+
+ r = ll->init_index(ll);
+ if (r < 0)
+ return r;
+
+ r = dm_btree_empty(&ll->ref_count_info, &ll->ref_count_root);
+ if (r < 0)
+ return r;
+
+ return 0;
+}
+
+int sm_ll_open_disk(struct ll_disk *ll, struct dm_transaction_manager *tm,
+ void *root_le, size_t len)
+{
+ int r;
+ struct disk_sm_root *smr = root_le;
+
+ if (len < sizeof(struct disk_sm_root)) {
+ DMERR("sm_metadata root too small");
+ return -ENOMEM;
+ }
+
+ r = sm_ll_init(ll, tm);
+ if (r < 0)
+ return r;
+
+ ll->load_ie = disk_ll_load_ie;
+ ll->save_ie = disk_ll_save_ie;
+ ll->init_index = disk_ll_init_index;
+ ll->open_index = disk_ll_open;
+ ll->max_entries = disk_ll_max_entries;
+ ll->commit = disk_ll_commit;
+
+ ll->nr_blocks = le64_to_cpu(smr->nr_blocks);
+ ll->nr_allocated = le64_to_cpu(smr->nr_allocated);
+ ll->bitmap_root = le64_to_cpu(smr->bitmap_root);
+ ll->ref_count_root = le64_to_cpu(smr->ref_count_root);
+
+ return ll->open_index(ll);
+}
+
+/*----------------------------------------------------------------*/
diff --git a/drivers/md/persistent-data/dm-space-map-common.h b/drivers/md/persistent-data/dm-space-map-common.h
new file mode 100644
index 0000000..8f22082
--- /dev/null
+++ b/drivers/md/persistent-data/dm-space-map-common.h
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_SPACE_MAP_COMMON_H
+#define DM_SPACE_MAP_COMMON_H
+
+#include "dm-btree.h"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Low level disk format
+ *
+ * Bitmap btree
+ * ------------
+ *
+ * Each value stored in the btree is an index_entry. This points to a
+ * block that is used as a bitmap. Within the bitmap hold 2 bits per
+ * entry, which represent UNUSED = 0, REF_COUNT = 1, REF_COUNT = 2 and
+ * REF_COUNT = many.
+ *
+ * Refcount btree
+ * --------------
+ *
+ * Any entry that has a ref count higher than 2 gets entered in the ref
+ * count tree. The leaf values for this tree is the 32-bit ref count.
+ */
+
+struct disk_index_entry {
+ __le64 blocknr;
+ __le32 nr_free;
+ __le32 none_free_before;
+} __packed;
+
+
+#define MAX_METADATA_BITMAPS 255
+struct disk_metadata_index {
+ __le32 csum;
+ __le32 padding;
+ __le64 blocknr;
+
+ struct disk_index_entry index[MAX_METADATA_BITMAPS];
+} __packed;
+
+struct ll_disk;
+
+typedef int (*load_ie_fn)(struct ll_disk *ll, dm_block_t index, struct disk_index_entry *result);
+typedef int (*save_ie_fn)(struct ll_disk *ll, dm_block_t index, struct disk_index_entry *ie);
+typedef int (*init_index_fn)(struct ll_disk *ll);
+typedef int (*open_index_fn)(struct ll_disk *ll);
+typedef dm_block_t (*max_index_entries_fn)(struct ll_disk *ll);
+typedef int (*commit_fn)(struct ll_disk *ll);
+
+struct ll_disk {
+ struct dm_transaction_manager *tm;
+ struct dm_btree_info bitmap_info;
+ struct dm_btree_info ref_count_info;
+
+ uint32_t block_size;
+ uint32_t entries_per_block;
+ dm_block_t nr_blocks;
+ dm_block_t nr_allocated;
+
+ /*
+ * bitmap_root may be a btree root or a simple index.
+ */
+ dm_block_t bitmap_root;
+
+ dm_block_t ref_count_root;
+
+ struct disk_metadata_index mi_le;
+ load_ie_fn load_ie;
+ save_ie_fn save_ie;
+ init_index_fn init_index;
+ open_index_fn open_index;
+ max_index_entries_fn max_entries;
+ commit_fn commit;
+};
+
+struct disk_sm_root {
+ __le64 nr_blocks;
+ __le64 nr_allocated;
+ __le64 bitmap_root;
+ __le64 ref_count_root;
+} __packed;
+
+#define ENTRIES_PER_BYTE 4
+
+struct disk_bitmap_header {
+ __le32 csum;
+ __le32 not_used;
+ __le64 blocknr;
+} __packed;
+
+enum allocation_event {
+ SM_NONE,
+ SM_ALLOC,
+ SM_FREE,
+};
+
+/*----------------------------------------------------------------*/
+
+int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks);
+int sm_ll_lookup_bitmap(struct ll_disk *ll, dm_block_t b, uint32_t *result);
+int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result);
+int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
+ dm_block_t end, dm_block_t *result);
+int sm_ll_insert(struct ll_disk *ll, dm_block_t b, uint32_t ref_count, enum allocation_event *ev);
+int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev);
+int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev);
+int sm_ll_commit(struct ll_disk *ll);
+
+int sm_ll_new_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm);
+int sm_ll_open_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm,
+ void *root_le, size_t len);
+
+int sm_ll_new_disk(struct ll_disk *ll, struct dm_transaction_manager *tm);
+int sm_ll_open_disk(struct ll_disk *ll, struct dm_transaction_manager *tm,
+ void *root_le, size_t len);
+
+/*----------------------------------------------------------------*/
+
+#endif /* DM_SPACE_MAP_COMMON_H */
diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c
new file mode 100644
index 0000000..aeff785
--- /dev/null
+++ b/drivers/md/persistent-data/dm-space-map-disk.c
@@ -0,0 +1,335 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-space-map-checker.h"
+#include "dm-space-map-common.h"
+#include "dm-space-map-disk.h"
+#include "dm-space-map.h"
+#include "dm-transaction-manager.h"
+
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/device-mapper.h>
+
+#define DM_MSG_PREFIX "space map disk"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Space map interface.
+ */
+struct sm_disk {
+ struct dm_space_map sm;
+
+ struct ll_disk ll;
+ struct ll_disk old_ll;
+
+ dm_block_t begin;
+ dm_block_t nr_allocated_this_transaction;
+};
+
+static void sm_disk_destroy(struct dm_space_map *sm)
+{
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+
+ kfree(smd);
+}
+
+static int sm_disk_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
+{
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+
+ return sm_ll_extend(&smd->ll, extra_blocks);
+}
+
+static int sm_disk_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count)
+{
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+ *count = smd->old_ll.nr_blocks;
+
+ return 0;
+}
+
+static int sm_disk_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
+{
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+ *count = (smd->old_ll.nr_blocks - smd->old_ll.nr_allocated) - smd->nr_allocated_this_transaction;
+
+ return 0;
+}
+
+static int sm_disk_get_count(struct dm_space_map *sm, dm_block_t b,
+ uint32_t *result)
+{
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+ return sm_ll_lookup(&smd->ll, b, result);
+}
+
+static int sm_disk_count_is_more_than_one(struct dm_space_map *sm, dm_block_t b,
+ int *result)
+{
+ int r;
+ uint32_t count;
+
+ r = sm_disk_get_count(sm, b, &count);
+ if (r)
+ return r;
+
+ return count > 1;
+}
+
+static int sm_disk_set_count(struct dm_space_map *sm, dm_block_t b,
+ uint32_t count)
+{
+ int r;
+ uint32_t old_count;
+ enum allocation_event ev;
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+
+ r = sm_ll_insert(&smd->ll, b, count, &ev);
+ if (!r) {
+ switch (ev) {
+ case SM_NONE:
+ break;
+
+ case SM_ALLOC:
+ /*
+ * This _must_ be free in the prior transaction
+ * otherwise we've lost atomicity.
+ */
+ smd->nr_allocated_this_transaction++;
+ break;
+
+ case SM_FREE:
+ /*
+ * It's only free if it's also free in the last
+ * transaction.
+ */
+ r = sm_ll_lookup(&smd->old_ll, b, &old_count);
+ if (r)
+ return r;
+
+ if (!old_count)
+ smd->nr_allocated_this_transaction--;
+ break;
+ }
+ }
+
+ return r;
+}
+
+static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b)
+{
+ int r;
+ enum allocation_event ev;
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+
+ r = sm_ll_inc(&smd->ll, b, &ev);
+ if (!r && (ev == SM_ALLOC))
+ /*
+ * This _must_ be free in the prior transaction
+ * otherwise we've lost atomicity.
+ */
+ smd->nr_allocated_this_transaction++;
+
+ return r;
+}
+
+static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b)
+{
+ int r;
+ uint32_t old_count;
+ enum allocation_event ev;
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+
+ r = sm_ll_dec(&smd->ll, b, &ev);
+ if (!r && (ev == SM_FREE)) {
+ /*
+ * It's only free if it's also free in the last
+ * transaction.
+ */
+ r = sm_ll_lookup(&smd->old_ll, b, &old_count);
+ if (r)
+ return r;
+
+ if (!old_count)
+ smd->nr_allocated_this_transaction--;
+ }
+
+ return r;
+}
+
+static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b)
+{
+ int r;
+ enum allocation_event ev;
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+
+ /* FIXME: we should loop round a couple of times */
+ r = sm_ll_find_free_block(&smd->old_ll, smd->begin, smd->old_ll.nr_blocks, b);
+ if (r)
+ return r;
+
+ smd->begin = *b + 1;
+ r = sm_ll_inc(&smd->ll, *b, &ev);
+ if (!r) {
+ BUG_ON(ev != SM_ALLOC);
+ smd->nr_allocated_this_transaction++;
+ }
+
+ return r;
+}
+
+static int sm_disk_commit(struct dm_space_map *sm)
+{
+ int r;
+ dm_block_t nr_free;
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+
+ r = sm_disk_get_nr_free(sm, &nr_free);
+ if (r)
+ return r;
+
+ r = sm_ll_commit(&smd->ll);
+ if (r)
+ return r;
+
+ memcpy(&smd->old_ll, &smd->ll, sizeof(smd->old_ll));
+ smd->begin = 0;
+ smd->nr_allocated_this_transaction = 0;
+
+ r = sm_disk_get_nr_free(sm, &nr_free);
+ if (r)
+ return r;
+
+ return 0;
+}
+
+static int sm_disk_root_size(struct dm_space_map *sm, size_t *result)
+{
+ *result = sizeof(struct disk_sm_root);
+
+ return 0;
+}
+
+static int sm_disk_copy_root(struct dm_space_map *sm, void *where_le, size_t max)
+{
+ struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
+ struct disk_sm_root root_le;
+
+ root_le.nr_blocks = cpu_to_le64(smd->ll.nr_blocks);
+ root_le.nr_allocated = cpu_to_le64(smd->ll.nr_allocated);
+ root_le.bitmap_root = cpu_to_le64(smd->ll.bitmap_root);
+ root_le.ref_count_root = cpu_to_le64(smd->ll.ref_count_root);
+
+ if (max < sizeof(root_le))
+ return -ENOSPC;
+
+ memcpy(where_le, &root_le, sizeof(root_le));
+
+ return 0;
+}
+
+/*----------------------------------------------------------------*/
+
+static struct dm_space_map ops = {
+ .destroy = sm_disk_destroy,
+ .extend = sm_disk_extend,
+ .get_nr_blocks = sm_disk_get_nr_blocks,
+ .get_nr_free = sm_disk_get_nr_free,
+ .get_count = sm_disk_get_count,
+ .count_is_more_than_one = sm_disk_count_is_more_than_one,
+ .set_count = sm_disk_set_count,
+ .inc_block = sm_disk_inc_block,
+ .dec_block = sm_disk_dec_block,
+ .new_block = sm_disk_new_block,
+ .commit = sm_disk_commit,
+ .root_size = sm_disk_root_size,
+ .copy_root = sm_disk_copy_root
+};
+
+static struct dm_space_map *dm_sm_disk_create_real(
+ struct dm_transaction_manager *tm,
+ dm_block_t nr_blocks)
+{
+ int r;
+ struct sm_disk *smd;
+
+ smd = kmalloc(sizeof(*smd), GFP_KERNEL);
+ if (!smd)
+ return ERR_PTR(-ENOMEM);
+
+ smd->begin = 0;
+ smd->nr_allocated_this_transaction = 0;
+ memcpy(&smd->sm, &ops, sizeof(smd->sm));
+
+ r = sm_ll_new_disk(&smd->ll, tm);
+ if (r)
+ goto bad;
+
+ r = sm_ll_extend(&smd->ll, nr_blocks);
+ if (r)
+ goto bad;
+
+ r = sm_disk_commit(&smd->sm);
+ if (r)
+ goto bad;
+
+ return &smd->sm;
+
+bad:
+ kfree(smd);
+ return ERR_PTR(r);
+}
+
+struct dm_space_map *dm_sm_disk_create(struct dm_transaction_manager *tm,
+ dm_block_t nr_blocks)
+{
+ struct dm_space_map *sm = dm_sm_disk_create_real(tm, nr_blocks);
+ return dm_sm_checker_create_fresh(sm);
+}
+EXPORT_SYMBOL_GPL(dm_sm_disk_create);
+
+static struct dm_space_map *dm_sm_disk_open_real(
+ struct dm_transaction_manager *tm,
+ void *root_le, size_t len)
+{
+ int r;
+ struct sm_disk *smd;
+
+ smd = kmalloc(sizeof(*smd), GFP_KERNEL);
+ if (!smd)
+ return ERR_PTR(-ENOMEM);
+
+ smd->begin = 0;
+ smd->nr_allocated_this_transaction = 0;
+ memcpy(&smd->sm, &ops, sizeof(smd->sm));
+
+ r = sm_ll_open_disk(&smd->ll, tm, root_le, len);
+ if (r)
+ goto bad;
+
+ r = sm_disk_commit(&smd->sm);
+ if (r)
+ goto bad;
+
+ return &smd->sm;
+
+bad:
+ kfree(smd);
+ return ERR_PTR(r);
+}
+
+struct dm_space_map *dm_sm_disk_open(struct dm_transaction_manager *tm,
+ void *root_le, size_t len)
+{
+ return dm_sm_checker_create(
+ dm_sm_disk_open_real(tm, root_le, len));
+}
+EXPORT_SYMBOL_GPL(dm_sm_disk_open);
+
+/*----------------------------------------------------------------*/
diff --git a/drivers/md/persistent-data/dm-space-map-disk.h b/drivers/md/persistent-data/dm-space-map-disk.h
new file mode 100644
index 0000000..447a0a9
--- /dev/null
+++ b/drivers/md/persistent-data/dm-space-map-disk.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef _LINUX_DM_SPACE_MAP_DISK_H
+#define _LINUX_DM_SPACE_MAP_DISK_H
+
+#include "dm-block-manager.h"
+
+struct dm_space_map;
+struct dm_transaction_manager;
+
+/*
+ * Unfortunately we have to use two-phase construction due to the cycle
+ * between the tm and sm.
+ */
+struct dm_space_map *dm_sm_disk_create(struct dm_transaction_manager *tm,
+ dm_block_t nr_blocks);
+
+struct dm_space_map *dm_sm_disk_open(struct dm_transaction_manager *tm,
+ void *root, size_t len);
+
+#endif /* _LINUX_DM_SPACE_MAP_DISK_H */
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
new file mode 100644
index 0000000..e89ae5e
--- /dev/null
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -0,0 +1,596 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-space-map.h"
+#include "dm-space-map-common.h"
+#include "dm-space-map-metadata.h"
+
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/device-mapper.h>
+
+#define DM_MSG_PREFIX "space map metadata"
+
+/*----------------------------------------------------------------*/
+
+/*
+ * Space map interface.
+ *
+ * The low level disk format is written using the standard btree and
+ * transaction manager. This means that performing disk operations may
+ * cause us to recurse into the space map in order to allocate new blocks.
+ * For this reason we have a pool of pre-allocated blocks large enough to
+ * service any metadata_ll_disk operation.
+ */
+
+/*
+ * FIXME: we should calculate this based on the size of the device.
+ * Only the metadata space map needs this functionality.
+ */
+#define MAX_RECURSIVE_ALLOCATIONS 1024
+
+enum block_op_type {
+ BOP_INC,
+ BOP_DEC
+};
+
+struct block_op {
+ enum block_op_type type;
+ dm_block_t block;
+};
+
+struct sm_metadata {
+ struct dm_space_map sm;
+
+ struct ll_disk ll;
+ struct ll_disk old_ll;
+
+ dm_block_t begin;
+
+ unsigned recursion_count;
+ unsigned allocated_this_transaction;
+ unsigned nr_uncommitted;
+ struct block_op uncommitted[MAX_RECURSIVE_ALLOCATIONS];
+};
+
+static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t b)
+{
+ struct block_op *op;
+
+ if (smm->nr_uncommitted == MAX_RECURSIVE_ALLOCATIONS) {
+ DMERR("too many recursive allocations");
+ return -ENOMEM;
+ }
+
+ op = smm->uncommitted + smm->nr_uncommitted++;
+ op->type = type;
+ op->block = b;
+
+ return 0;
+}
+
+static int commit_bop(struct sm_metadata *smm, struct block_op *op)
+{
+ int r = 0;
+ enum allocation_event ev;
+
+ switch (op->type) {
+ case BOP_INC:
+ r = sm_ll_inc(&smm->ll, op->block, &ev);
+ break;
+
+ case BOP_DEC:
+ r = sm_ll_dec(&smm->ll, op->block, &ev);
+ break;
+ }
+
+ return r;
+}
+
+static void in(struct sm_metadata *smm)
+{
+ smm->recursion_count++;
+}
+
+static int out(struct sm_metadata *smm)
+{
+ int r = 0;
+
+ /*
+ * If we're not recursing then very bad things are happening.
+ */
+ if (!smm->recursion_count) {
+ DMERR("lost track of recursion depth");
+ return -ENOMEM;
+ }
+
+ if (smm->recursion_count == 1 && smm->nr_uncommitted) {
+ while (smm->nr_uncommitted && !r) {
+ smm->nr_uncommitted--;
+ r = commit_bop(smm, smm->uncommitted +
+ smm->nr_uncommitted);
+ if (r)
+ break;
+ }
+ }
+
+ smm->recursion_count--;
+
+ return r;
+}
+
+/*
+ * When using the out() function above, we often want to combine an error
+ * code for the operation run in the recursive context with that from
+ * out().
+ */
+static int combine_errors(int r1, int r2)
+{
+ return r1 ? r1 : r2;
+}
+
+static int recursing(struct sm_metadata *smm)
+{
+ return smm->recursion_count;
+}
+
+static void sm_metadata_destroy(struct dm_space_map *sm)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ kfree(smm);
+}
+
+static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
+{
+ DMERR("doesn't support extend");
+ return -EINVAL;
+}
+
+static int sm_metadata_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ *count = smm->ll.nr_blocks;
+
+ return 0;
+}
+
+static int sm_metadata_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ *count = smm->old_ll.nr_blocks - smm->old_ll.nr_allocated -
+ smm->allocated_this_transaction;
+
+ return 0;
+}
+
+static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b,
+ uint32_t *result)
+{
+ int r, i;
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+ unsigned adjustment = 0;
+
+ /*
+ * We may have some uncommitted adjustments to add. This list
+ * should always be really short.
+ */
+ for (i = 0; i < smm->nr_uncommitted; i++) {
+ struct block_op *op = smm->uncommitted + i;
+
+ if (op->block != b)
+ continue;
+
+ switch (op->type) {
+ case BOP_INC:
+ adjustment++;
+ break;
+
+ case BOP_DEC:
+ adjustment--;
+ break;
+ }
+ }
+
+ r = sm_ll_lookup(&smm->ll, b, result);
+ if (r)
+ return r;
+
+ *result += adjustment;
+
+ return 0;
+}
+
+static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm,
+ dm_block_t b, int *result)
+{
+ int r, i, adjustment = 0;
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+ uint32_t rc;
+
+ /*
+ * We may have some uncommitted adjustments to add. This list
+ * should always be really short.
+ */
+ for (i = 0; i < smm->nr_uncommitted; i++) {
+ struct block_op *op = smm->uncommitted + i;
+
+ if (op->block != b)
+ continue;
+
+ switch (op->type) {
+ case BOP_INC:
+ adjustment++;
+ break;
+
+ case BOP_DEC:
+ adjustment--;
+ break;
+ }
+ }
+
+ if (adjustment > 1) {
+ *result = 1;
+ return 0;
+ }
+
+ r = sm_ll_lookup_bitmap(&smm->ll, b, &rc);
+ if (r)
+ return r;
+
+ if (rc == 3)
+ /*
+ * We err on the side of caution, and always return true.
+ */
+ *result = 1;
+ else
+ *result = rc + adjustment > 1;
+
+ return 0;
+}
+
+static int sm_metadata_set_count(struct dm_space_map *sm, dm_block_t b,
+ uint32_t count)
+{
+ int r, r2;
+ enum allocation_event ev;
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ if (smm->recursion_count) {
+ DMERR("cannot recurse set_count()");
+ return -EINVAL;
+ }
+
+ in(smm);
+ r = sm_ll_insert(&smm->ll, b, count, &ev);
+ r2 = out(smm);
+
+ return combine_errors(r, r2);
+}
+
+static int sm_metadata_inc_block(struct dm_space_map *sm, dm_block_t b)
+{
+ int r, r2 = 0;
+ enum allocation_event ev;
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ if (recursing(smm))
+ r = add_bop(smm, BOP_INC, b);
+ else {
+ in(smm);
+ r = sm_ll_inc(&smm->ll, b, &ev);
+ r2 = out(smm);
+ }
+
+ return combine_errors(r, r2);
+}
+
+static int sm_metadata_dec_block(struct dm_space_map *sm, dm_block_t b)
+{
+ int r, r2 = 0;
+ enum allocation_event ev;
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ if (recursing(smm))
+ r = add_bop(smm, BOP_DEC, b);
+ else {
+ in(smm);
+ r = sm_ll_dec(&smm->ll, b, &ev);
+ r2 = out(smm);
+ }
+
+ return combine_errors(r, r2);
+}
+
+static int sm_metadata_new_block_(struct dm_space_map *sm, dm_block_t *b)
+{
+ int r, r2 = 0;
+ enum allocation_event ev;
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ r = sm_ll_find_free_block(&smm->old_ll, smm->begin, smm->old_ll.nr_blocks, b);
+ if (r)
+ return r;
+
+ smm->begin = *b + 1;
+
+ if (recursing(smm))
+ r = add_bop(smm, BOP_INC, *b);
+ else {
+ in(smm);
+ r = sm_ll_inc(&smm->ll, *b, &ev);
+ r2 = out(smm);
+ }
+
+ if (!r)
+ smm->allocated_this_transaction++;
+
+ return combine_errors(r, r2);
+}
+
+static int sm_metadata_new_block(struct dm_space_map *sm, dm_block_t *b)
+{
+ int r = sm_metadata_new_block_(sm, b);
+ if (r)
+ DMERR("out of metadata space");
+ return r;
+}
+
+static int sm_metadata_commit(struct dm_space_map *sm)
+{
+ int r;
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ r = sm_ll_commit(&smm->ll);
+ if (r)
+ return r;
+
+ memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll));
+ smm->begin = 0;
+ smm->allocated_this_transaction = 0;
+
+ return 0;
+}
+
+static int sm_metadata_root_size(struct dm_space_map *sm, size_t *result)
+{
+ *result = sizeof(struct disk_sm_root);
+
+ return 0;
+}
+
+static int sm_metadata_copy_root(struct dm_space_map *sm, void *where_le, size_t max)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+ struct disk_sm_root root_le;
+
+ root_le.nr_blocks = cpu_to_le64(smm->ll.nr_blocks);
+ root_le.nr_allocated = cpu_to_le64(smm->ll.nr_allocated);
+ root_le.bitmap_root = cpu_to_le64(smm->ll.bitmap_root);
+ root_le.ref_count_root = cpu_to_le64(smm->ll.ref_count_root);
+
+ if (max < sizeof(root_le))
+ return -ENOSPC;
+
+ memcpy(where_le, &root_le, sizeof(root_le));
+
+ return 0;
+}
+
+static struct dm_space_map ops = {
+ .destroy = sm_metadata_destroy,
+ .extend = sm_metadata_extend,
+ .get_nr_blocks = sm_metadata_get_nr_blocks,
+ .get_nr_free = sm_metadata_get_nr_free,
+ .get_count = sm_metadata_get_count,
+ .count_is_more_than_one = sm_metadata_count_is_more_than_one,
+ .set_count = sm_metadata_set_count,
+ .inc_block = sm_metadata_inc_block,
+ .dec_block = sm_metadata_dec_block,
+ .new_block = sm_metadata_new_block,
+ .commit = sm_metadata_commit,
+ .root_size = sm_metadata_root_size,
+ .copy_root = sm_metadata_copy_root
+};
+
+/*----------------------------------------------------------------*/
+
+/*
+ * When a new space map is created that manages its own space. We use
+ * this tiny bootstrap allocator.
+ */
+static void sm_bootstrap_destroy(struct dm_space_map *sm)
+{
+}
+
+static int sm_bootstrap_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
+{
+ DMERR("boostrap doesn't support extend");
+
+ return -EINVAL;
+}
+
+static int sm_bootstrap_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ return smm->ll.nr_blocks;
+}
+
+static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ *count = smm->ll.nr_blocks - smm->begin;
+
+ return 0;
+}
+
+static int sm_bootstrap_get_count(struct dm_space_map *sm, dm_block_t b,
+ uint32_t *result)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ return b < smm->begin ? 1 : 0;
+}
+
+static int sm_bootstrap_count_is_more_than_one(struct dm_space_map *sm,
+ dm_block_t b, int *result)
+{
+ *result = 0;
+
+ return 0;
+}
+
+static int sm_bootstrap_set_count(struct dm_space_map *sm, dm_block_t b,
+ uint32_t count)
+{
+ DMERR("boostrap doesn't support set_count");
+
+ return -EINVAL;
+}
+
+static int sm_bootstrap_new_block(struct dm_space_map *sm, dm_block_t *b)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ /*
+ * We know the entire device is unused.
+ */
+ if (smm->begin == smm->ll.nr_blocks)
+ return -ENOSPC;
+
+ *b = smm->begin++;
+
+ return 0;
+}
+
+static int sm_bootstrap_inc_block(struct dm_space_map *sm, dm_block_t b)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ return add_bop(smm, BOP_INC, b);
+}
+
+static int sm_bootstrap_dec_block(struct dm_space_map *sm, dm_block_t b)
+{
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ return add_bop(smm, BOP_DEC, b);
+}
+
+static int sm_bootstrap_commit(struct dm_space_map *sm)
+{
+ return 0;
+}
+
+static int sm_bootstrap_root_size(struct dm_space_map *sm, size_t *result)
+{
+ DMERR("boostrap doesn't support root_size");
+
+ return -EINVAL;
+}
+
+static int sm_bootstrap_copy_root(struct dm_space_map *sm, void *where,
+ size_t max)
+{
+ DMERR("boostrap doesn't support copy_root");
+
+ return -EINVAL;
+}
+
+static struct dm_space_map bootstrap_ops = {
+ .destroy = sm_bootstrap_destroy,
+ .extend = sm_bootstrap_extend,
+ .get_nr_blocks = sm_bootstrap_get_nr_blocks,
+ .get_nr_free = sm_bootstrap_get_nr_free,
+ .get_count = sm_bootstrap_get_count,
+ .count_is_more_than_one = sm_bootstrap_count_is_more_than_one,
+ .set_count = sm_bootstrap_set_count,
+ .inc_block = sm_bootstrap_inc_block,
+ .dec_block = sm_bootstrap_dec_block,
+ .new_block = sm_bootstrap_new_block,
+ .commit = sm_bootstrap_commit,
+ .root_size = sm_bootstrap_root_size,
+ .copy_root = sm_bootstrap_copy_root
+};
+
+/*----------------------------------------------------------------*/
+
+struct dm_space_map *dm_sm_metadata_init(void)
+{
+ struct sm_metadata *smm;
+
+ smm = kmalloc(sizeof(*smm), GFP_KERNEL);
+ if (!smm)
+ return ERR_PTR(-ENOMEM);
+
+ memcpy(&smm->sm, &ops, sizeof(smm->sm));
+
+ return &smm->sm;
+}
+
+int dm_sm_metadata_create(struct dm_space_map *sm,
+ struct dm_transaction_manager *tm,
+ dm_block_t nr_blocks,
+ dm_block_t superblock)
+{
+ int r;
+ dm_block_t i;
+ enum allocation_event ev;
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ smm->begin = superblock + 1;
+ smm->recursion_count = 0;
+ smm->allocated_this_transaction = 0;
+ smm->nr_uncommitted = 0;
+
+ memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
+
+ r = sm_ll_new_metadata(&smm->ll, tm);
+ if (r)
+ return r;
+
+ r = sm_ll_extend(&smm->ll, nr_blocks);
+ if (r)
+ return r;
+
+ memcpy(&smm->sm, &ops, sizeof(smm->sm));
+
+ /*
+ * Now we need to update the newly created data structures with the
+ * allocated blocks that they were built from.
+ */
+ for (i = superblock; !r && i < smm->begin; i++)
+ r = sm_ll_inc(&smm->ll, i, &ev);
+
+ if (r)
+ return r;
+
+ return sm_metadata_commit(sm);
+}
+
+int dm_sm_metadata_open(struct dm_space_map *sm,
+ struct dm_transaction_manager *tm,
+ void *root_le, size_t len)
+{
+ int r;
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+ r = sm_ll_open_metadata(&smm->ll, tm, root_le, len);
+ if (r)
+ return r;
+
+ smm->begin = 0;
+ smm->recursion_count = 0;
+ smm->allocated_this_transaction = 0;
+ smm->nr_uncommitted = 0;
+
+ memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll));
+ return 0;
+}
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.h b/drivers/md/persistent-data/dm-space-map-metadata.h
new file mode 100644
index 0000000..39bba08
--- /dev/null
+++ b/drivers/md/persistent-data/dm-space-map-metadata.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_SPACE_MAP_METADATA_H
+#define DM_SPACE_MAP_METADATA_H
+
+#include "dm-transaction-manager.h"
+
+/*
+ * Unfortunately we have to use two-phase construction due to the cycle
+ * between the tm and sm.
+ */
+struct dm_space_map *dm_sm_metadata_init(void);
+
+/*
+ * Create a fresh space map.
+ */
+int dm_sm_metadata_create(struct dm_space_map *sm,
+ struct dm_transaction_manager *tm,
+ dm_block_t nr_blocks,
+ dm_block_t superblock);
+
+/*
+ * Open from a previously-recorded root.
+ */
+int dm_sm_metadata_open(struct dm_space_map *sm,
+ struct dm_transaction_manager *tm,
+ void *root_le, size_t len);
+
+#endif /* DM_SPACE_MAP_METADATA_H */
diff --git a/drivers/md/persistent-data/dm-space-map.h b/drivers/md/persistent-data/dm-space-map.h
new file mode 100644
index 0000000..1cbfc6b
--- /dev/null
+++ b/drivers/md/persistent-data/dm-space-map.h
@@ -0,0 +1,134 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef _LINUX_DM_SPACE_MAP_H
+#define _LINUX_DM_SPACE_MAP_H
+
+#include "dm-block-manager.h"
+
+/*
+ * struct dm_space_map keeps a record of how many times each block in a device
+ * is referenced. It needs to be fixed on disk as part of the transaction.
+ */
+struct dm_space_map {
+ void (*destroy)(struct dm_space_map *sm);
+
+ /*
+ * You must commit before allocating the newly added space.
+ */
+ int (*extend)(struct dm_space_map *sm, dm_block_t extra_blocks);
+
+ /*
+ * Extensions do not appear in this count until after commit has
+ * been called.
+ */
+ int (*get_nr_blocks)(struct dm_space_map *sm, dm_block_t *count);
+
+ /*
+ * Space maps must never allocate a block from the previous
+ * transaction, in case we need to rollback. This complicates the
+ * semantics of get_nr_free(), it should return the number of blocks
+ * that are available for allocation _now_. For instance you may
+ * have blocks with a zero reference count that will not be
+ * available for allocation until after the next commit.
+ */
+ int (*get_nr_free)(struct dm_space_map *sm, dm_block_t *count);
+
+ int (*get_count)(struct dm_space_map *sm, dm_block_t b, uint32_t *result);
+ int (*count_is_more_than_one)(struct dm_space_map *sm, dm_block_t b,
+ int *result);
+ int (*set_count)(struct dm_space_map *sm, dm_block_t b, uint32_t count);
+
+ int (*commit)(struct dm_space_map *sm);
+
+ int (*inc_block)(struct dm_space_map *sm, dm_block_t b);
+ int (*dec_block)(struct dm_space_map *sm, dm_block_t b);
+
+ /*
+ * new_block will increment the returned block.
+ */
+ int (*new_block)(struct dm_space_map *sm, dm_block_t *b);
+
+ /*
+ * The root contains all the information needed to fix the space map.
+ * Generally this info is small, so squirrel it away in a disk block
+ * along with other info.
+ */
+ int (*root_size)(struct dm_space_map *sm, size_t *result);
+ int (*copy_root)(struct dm_space_map *sm, void *copy_to_here_le, size_t len);
+};
+
+/*----------------------------------------------------------------*/
+
+static inline void dm_sm_destroy(struct dm_space_map *sm)
+{
+ sm->destroy(sm);
+}
+
+static inline int dm_sm_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
+{
+ return sm->extend(sm, extra_blocks);
+}
+
+static inline int dm_sm_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count)
+{
+ return sm->get_nr_blocks(sm, count);
+}
+
+static inline int dm_sm_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
+{
+ return sm->get_nr_free(sm, count);
+}
+
+static inline int dm_sm_get_count(struct dm_space_map *sm, dm_block_t b,
+ uint32_t *result)
+{
+ return sm->get_count(sm, b, result);
+}
+
+static inline int dm_sm_count_is_more_than_one(struct dm_space_map *sm,
+ dm_block_t b, int *result)
+{
+ return sm->count_is_more_than_one(sm, b, result);
+}
+
+static inline int dm_sm_set_count(struct dm_space_map *sm, dm_block_t b,
+ uint32_t count)
+{
+ return sm->set_count(sm, b, count);
+}
+
+static inline int dm_sm_commit(struct dm_space_map *sm)
+{
+ return sm->commit(sm);
+}
+
+static inline int dm_sm_inc_block(struct dm_space_map *sm, dm_block_t b)
+{
+ return sm->inc_block(sm, b);
+}
+
+static inline int dm_sm_dec_block(struct dm_space_map *sm, dm_block_t b)
+{
+ return sm->dec_block(sm, b);
+}
+
+static inline int dm_sm_new_block(struct dm_space_map *sm, dm_block_t *b)
+{
+ return sm->new_block(sm, b);
+}
+
+static inline int dm_sm_root_size(struct dm_space_map *sm, size_t *result)
+{
+ return sm->root_size(sm, result);
+}
+
+static inline int dm_sm_copy_root(struct dm_space_map *sm, void *copy_to_here_le, size_t len)
+{
+ return sm->copy_root(sm, copy_to_here_le, len);
+}
+
+#endif /* _LINUX_DM_SPACE_MAP_H */
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
new file mode 100644
index 0000000..728e89a
--- /dev/null
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -0,0 +1,400 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+#include "dm-transaction-manager.h"
+#include "dm-space-map.h"
+#include "dm-space-map-checker.h"
+#include "dm-space-map-disk.h"
+#include "dm-space-map-metadata.h"
+#include "dm-persistent-data-internal.h"
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/device-mapper.h>
+
+#define DM_MSG_PREFIX "transaction manager"
+
+/*----------------------------------------------------------------*/
+
+struct shadow_info {
+ struct hlist_node hlist;
+ dm_block_t where;
+};
+
+/*
+ * It would be nice if we scaled with the size of transaction.
+ */
+#define HASH_SIZE 256
+#define HASH_MASK (HASH_SIZE - 1)
+
+struct dm_transaction_manager {
+ int is_clone;
+ struct dm_transaction_manager *real;
+
+ struct dm_block_manager *bm;
+ struct dm_space_map *sm;
+
+ spinlock_t lock;
+ struct hlist_head buckets[HASH_SIZE];
+};
+
+/*----------------------------------------------------------------*/
+
+static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b)
+{
+ int r = 0;
+ unsigned bucket = dm_hash_block(b, HASH_MASK);
+ struct shadow_info *si;
+ struct hlist_node *n;
+
+ spin_lock(&tm->lock);
+ hlist_for_each_entry(si, n, tm->buckets + bucket, hlist)
+ if (si->where == b) {
+ r = 1;
+ break;
+ }
+ spin_unlock(&tm->lock);
+
+ return r;
+}
+
+/*
+ * This can silently fail if there's no memory. We're ok with this since
+ * creating redundant shadows causes no harm.
+ */
+static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b)
+{
+ unsigned bucket;
+ struct shadow_info *si;
+
+ si = kmalloc(sizeof(*si), GFP_NOIO);
+ if (si) {
+ si->where = b;
+ bucket = dm_hash_block(b, HASH_MASK);
+ spin_lock(&tm->lock);
+ hlist_add_head(&si->hlist, tm->buckets + bucket);
+ spin_unlock(&tm->lock);
+ }
+}
+
+static void wipe_shadow_table(struct dm_transaction_manager *tm)
+{
+ struct shadow_info *si;
+ struct hlist_node *n, *tmp;
+ struct hlist_head *bucket;
+ int i;
+
+ spin_lock(&tm->lock);
+ for (i = 0; i < HASH_SIZE; i++) {
+ bucket = tm->buckets + i;
+ hlist_for_each_entry_safe(si, n, tmp, bucket, hlist)
+ kfree(si);
+
+ INIT_HLIST_HEAD(bucket);
+ }
+
+ spin_unlock(&tm->lock);
+}
+
+/*----------------------------------------------------------------*/
+
+static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm,
+ struct dm_space_map *sm)
+{
+ int i;
+ struct dm_transaction_manager *tm;
+
+ tm = kmalloc(sizeof(*tm), GFP_KERNEL);
+ if (!tm)
+ return ERR_PTR(-ENOMEM);
+
+ tm->is_clone = 0;
+ tm->real = NULL;
+ tm->bm = bm;
+ tm->sm = sm;
+
+ spin_lock_init(&tm->lock);
+ for (i = 0; i < HASH_SIZE; i++)
+ INIT_HLIST_HEAD(tm->buckets + i);
+
+ return tm;
+}
+
+struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transaction_manager *real)
+{
+ struct dm_transaction_manager *tm;
+
+ tm = kmalloc(sizeof(*tm), GFP_KERNEL);
+ if (tm) {
+ tm->is_clone = 1;
+ tm->real = real;
+ }
+
+ return tm;
+}
+EXPORT_SYMBOL_GPL(dm_tm_create_non_blocking_clone);
+
+void dm_tm_destroy(struct dm_transaction_manager *tm)
+{
+ kfree(tm);
+}
+EXPORT_SYMBOL_GPL(dm_tm_destroy);
+
+int dm_tm_pre_commit(struct dm_transaction_manager *tm)
+{
+ int r;
+
+ if (tm->is_clone)
+ return -EWOULDBLOCK;
+
+ r = dm_sm_commit(tm->sm);
+ if (r < 0)
+ return r;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(dm_tm_pre_commit);
+
+int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root)
+{
+ if (tm->is_clone)
+ return -EWOULDBLOCK;
+
+ wipe_shadow_table(tm);
+
+ return dm_bm_flush_and_unlock(tm->bm, root);
+}
+EXPORT_SYMBOL_GPL(dm_tm_commit);
+
+int dm_tm_new_block(struct dm_transaction_manager *tm,
+ struct dm_block_validator *v,
+ struct dm_block **result)
+{
+ int r;
+ dm_block_t new_block;
+
+ if (tm->is_clone)
+ return -EWOULDBLOCK;
+
+ r = dm_sm_new_block(tm->sm, &new_block);
+ if (r < 0)
+ return r;
+
+ r = dm_bm_write_lock_zero(tm->bm, new_block, v, result);
+ if (r < 0) {
+ dm_sm_dec_block(tm->sm, new_block);
+ return r;
+ }
+
+ /*
+ * New blocks count as shadows in that they don't need to be
+ * shadowed again.
+ */
+ insert_shadow(tm, new_block);
+
+ return 0;
+}
+
+static int __shadow_block(struct dm_transaction_manager *tm, dm_block_t orig,
+ struct dm_block_validator *v,
+ struct dm_block **result)
+{
+ int r;
+ dm_block_t new;
+ struct dm_block *orig_block;
+
+ r = dm_sm_new_block(tm->sm, &new);
+ if (r < 0)
+ return r;
+
+ r = dm_sm_dec_block(tm->sm, orig);
+ if (r < 0)
+ return r;
+
+ r = dm_bm_read_lock(tm->bm, orig, v, &orig_block);
+ if (r < 0)
+ return r;
+
+ r = dm_bm_unlock_move(orig_block, new);
+ if (r < 0) {
+ dm_bm_unlock(orig_block);
+ return r;
+ }
+
+ return dm_bm_write_lock(tm->bm, new, v, result);
+}
+
+int dm_tm_shadow_block(struct dm_transaction_manager *tm, dm_block_t orig,
+ struct dm_block_validator *v, struct dm_block **result,
+ int *inc_children)
+{
+ int r;
+
+ if (tm->is_clone)
+ return -EWOULDBLOCK;
+
+ r = dm_sm_count_is_more_than_one(tm->sm, orig, inc_children);
+ if (r < 0)
+ return r;
+
+ if (is_shadow(tm, orig) && !*inc_children)
+ return dm_bm_write_lock(tm->bm, orig, v, result);
+
+ r = __shadow_block(tm, orig, v, result);
+ if (r < 0)
+ return r;
+ insert_shadow(tm, dm_block_location(*result));
+
+ return r;
+}
+
+int dm_tm_read_lock(struct dm_transaction_manager *tm, dm_block_t b,
+ struct dm_block_validator *v,
+ struct dm_block **blk)
+{
+ if (tm->is_clone)
+ return dm_bm_read_try_lock(tm->real->bm, b, v, blk);
+
+ return dm_bm_read_lock(tm->bm, b, v, blk);
+}
+
+int dm_tm_unlock(struct dm_transaction_manager *tm, struct dm_block *b)
+{
+ return dm_bm_unlock(b);
+}
+EXPORT_SYMBOL_GPL(dm_tm_unlock);
+
+void dm_tm_inc(struct dm_transaction_manager *tm, dm_block_t b)
+{
+ /*
+ * The non-blocking clone doesn't support this.
+ */
+ BUG_ON(tm->is_clone);
+
+ dm_sm_inc_block(tm->sm, b);
+}
+EXPORT_SYMBOL_GPL(dm_tm_inc);
+
+void dm_tm_dec(struct dm_transaction_manager *tm, dm_block_t b)
+{
+ /*
+ * The non-blocking clone doesn't support this.
+ */
+ BUG_ON(tm->is_clone);
+
+ dm_sm_dec_block(tm->sm, b);
+}
+EXPORT_SYMBOL_GPL(dm_tm_dec);
+
+int dm_tm_ref(struct dm_transaction_manager *tm, dm_block_t b,
+ uint32_t *result)
+{
+ if (tm->is_clone)
+ return -EWOULDBLOCK;
+
+ return dm_sm_get_count(tm->sm, b, result);
+}
+
+struct dm_block_manager *dm_tm_get_bm(struct dm_transaction_manager *tm)
+{
+ return tm->bm;
+}
+
+/*----------------------------------------------------------------*/
+
+static int dm_tm_create_internal(struct dm_block_manager *bm,
+ dm_block_t sb_location,
+ struct dm_block_validator *sb_validator,
+ size_t root_offset, size_t root_max_len,
+ struct dm_transaction_manager **tm,
+ struct dm_space_map **sm,
+ struct dm_block **sblock,
+ int create)
+{
+ int r;
+ struct dm_space_map *inner;
+
+ inner = dm_sm_metadata_init();
+ if (IS_ERR(inner))
+ return PTR_ERR(inner);
+
+ *tm = dm_tm_create(bm, inner);
+ if (IS_ERR(*tm)) {
+ dm_sm_destroy(inner);
+ return PTR_ERR(*tm);
+ }
+
+ if (create) {
+ r = dm_bm_write_lock_zero(dm_tm_get_bm(*tm), sb_location,
+ sb_validator, sblock);
+ if (r < 0) {
+ DMERR("couldn't lock superblock");
+ goto bad1;
+ }
+
+ r = dm_sm_metadata_create(inner, *tm, dm_bm_nr_blocks(bm),
+ sb_location);
+ if (r) {
+ DMERR("couldn't create metadata space map");
+ goto bad2;
+ }
+
+ *sm = dm_sm_checker_create(inner);
+ if (!*sm)
+ goto bad2;
+
+ } else {
+ r = dm_bm_write_lock(dm_tm_get_bm(*tm), sb_location,
+ sb_validator, sblock);
+ if (r < 0) {
+ DMERR("couldn't lock superblock");
+ goto bad1;
+ }
+
+ r = dm_sm_metadata_open(inner, *tm,
+ dm_block_data(*sblock) + root_offset,
+ root_max_len);
+ if (r) {
+ DMERR("couldn't open metadata space map");
+ goto bad2;
+ }
+
+ *sm = dm_sm_checker_create(inner);
+ if (!*sm)
+ goto bad2;
+ }
+
+ return 0;
+
+bad2:
+ dm_tm_unlock(*tm, *sblock);
+bad1:
+ dm_tm_destroy(*tm);
+ dm_sm_destroy(inner);
+ return r;
+}
+
+int dm_tm_create_with_sm(struct dm_block_manager *bm, dm_block_t sb_location,
+ struct dm_block_validator *sb_validator,
+ struct dm_transaction_manager **tm,
+ struct dm_space_map **sm, struct dm_block **sblock)
+{
+ return dm_tm_create_internal(bm, sb_location, sb_validator,
+ 0, 0, tm, sm, sblock, 1);
+}
+EXPORT_SYMBOL_GPL(dm_tm_create_with_sm);
+
+int dm_tm_open_with_sm(struct dm_block_manager *bm, dm_block_t sb_location,
+ struct dm_block_validator *sb_validator,
+ size_t root_offset, size_t root_max_len,
+ struct dm_transaction_manager **tm,
+ struct dm_space_map **sm, struct dm_block **sblock)
+{
+ return dm_tm_create_internal(bm, sb_location, sb_validator, root_offset,
+ root_max_len, tm, sm, sblock, 0);
+}
+EXPORT_SYMBOL_GPL(dm_tm_open_with_sm);
+
+/*----------------------------------------------------------------*/
diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h
new file mode 100644
index 0000000..6da7848
--- /dev/null
+++ b/drivers/md/persistent-data/dm-transaction-manager.h
@@ -0,0 +1,130 @@
+/*
+ * Copyright (C) 2011 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef _LINUX_DM_TRANSACTION_MANAGER_H
+#define _LINUX_DM_TRANSACTION_MANAGER_H
+
+#include "dm-block-manager.h"
+
+struct dm_transaction_manager;
+struct dm_space_map;
+
+/*----------------------------------------------------------------*/
+
+/*
+ * This manages the scope of a transaction. It also enforces immutability
+ * of the on-disk data structures by limiting access to writeable blocks.
+ *
+ * Clients should not fiddle with the block manager directly.
+ */
+
+void dm_tm_destroy(struct dm_transaction_manager *tm);
+
+/*
+ * The non-blocking version of a transaction manager is intended for use in
+ * fast path code that needs to do lookups e.g. a dm mapping function.
+ * You create the non-blocking variant from a normal tm. The interface is
+ * the same, except that most functions will just return -EWOULDBLOCK.
+ * Methods that return void yet may block should not be called on a clone
+ * viz. dm_tm_inc, dm_tm_dec. Call dm_tm_destroy() as you would with a normal
+ * tm when you've finished with it. You may not destroy the original prior
+ * to clones.
+ */
+struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transaction_manager *real);
+
+/*
+ * We use a 2-phase commit here.
+ *
+ * i) In the first phase the block manager is told to start flushing, and
+ * the changes to the space map are written to disk. You should interrogate
+ * your particular space map to get detail of its root node etc. to be
+ * included in your superblock.
+ *
+ * ii) @root will be committed last. You shouldn't use more than the
+ * first 512 bytes of @root if you wish the transaction to survive a power
+ * failure. You *must* have a write lock held on @root for both stage (i)
+ * and (ii). The commit will drop the write lock.
+ */
+int dm_tm_pre_commit(struct dm_transaction_manager *tm);
+int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root);
+
+/*
+ * These methods are the only way to get hold of a writeable block.
+ */
+
+/*
+ * dm_tm_new_block() is pretty self-explanatory. Make sure you do actually
+ * write to the whole of @data before you unlock, otherwise you could get
+ * a data leak. (The other option is for tm_new_block() to zero new blocks
+ * before handing them out, which will be redundant in most, if not all,
+ * cases).
+ * Zeroes the new block and returns with write lock held.
+ */
+int dm_tm_new_block(struct dm_transaction_manager *tm,
+ struct dm_block_validator *v,
+ struct dm_block **result);
+
+/*
+ * dm_tm_shadow_block() allocates a new block and copies the data from @orig
+ * to it. It then decrements the reference count on original block. Use
+ * this to update the contents of a block in a data structure, don't
+ * confuse this with a clone - you shouldn't access the orig block after
+ * this operation. Because the tm knows the scope of the transaction it
+ * can optimise requests for a shadow of a shadow to a no-op. Don't forget
+ * to unlock when you've finished with the shadow.
+ *
+ * The @inc_children flag is used to tell the caller whether it needs to
+ * adjust reference counts for children. (Data in the block may refer to
+ * other blocks.)
+ *
+ * Shadowing implicitly drops a reference on @orig so you must not have
+ * it locked when you call this.
+ */
+int dm_tm_shadow_block(struct dm_transaction_manager *tm, dm_block_t orig,
+ struct dm_block_validator *v,
+ struct dm_block **result, int *inc_children);
+
+/*
+ * Read access. You can lock any block you want. If there's a write lock
+ * on it outstanding then it'll block.
+ */
+int dm_tm_read_lock(struct dm_transaction_manager *tm, dm_block_t b,
+ struct dm_block_validator *v,
+ struct dm_block **result);
+
+int dm_tm_unlock(struct dm_transaction_manager *tm, struct dm_block *b);
+
+/*
+ * Functions for altering the reference count of a block directly.
+ */
+void dm_tm_inc(struct dm_transaction_manager *tm, dm_block_t b);
+
+void dm_tm_dec(struct dm_transaction_manager *tm, dm_block_t b);
+
+int dm_tm_ref(struct dm_transaction_manager *tm, dm_block_t b,
+ uint32_t *result);
+
+struct dm_block_manager *dm_tm_get_bm(struct dm_transaction_manager *tm);
+
+/*
+ * A little utility that ties the knot by producing a transaction manager
+ * that has a space map managed by the transaction manager...
+ *
+ * Returns a tm that has an open transaction to write the new disk sm.
+ * Caller should store the new sm root and commit.
+ */
+int dm_tm_create_with_sm(struct dm_block_manager *bm, dm_block_t sb_location,
+ struct dm_block_validator *sb_validator,
+ struct dm_transaction_manager **tm,
+ struct dm_space_map **sm, struct dm_block **sblock);
+
+int dm_tm_open_with_sm(struct dm_block_manager *bm, dm_block_t sb_location,
+ struct dm_block_validator *sb_validator,
+ size_t root_offset, size_t root_max_len,
+ struct dm_transaction_manager **tm,
+ struct dm_space_map **sm, struct dm_block **sblock);
+
+#endif /* _LINUX_DM_TRANSACTION_MANAGER_H */
diff --git a/drivers/media/radio/Kconfig b/drivers/media/radio/Kconfig
index 52798a1..ccd5f0d 100644
--- a/drivers/media/radio/Kconfig
+++ b/drivers/media/radio/Kconfig
@@ -426,7 +426,6 @@
config RADIO_WL1273
tristate "Texas Instruments WL1273 I2C FM Radio"
depends on I2C && VIDEO_V4L2
- select MFD_CORE
select MFD_WL1273_CORE
select FW_LOADER
---help---
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index a67adcb..f1391c2 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -2,23 +2,8 @@
# Multifunction miscellaneous devices
#
-menuconfig MFD_SUPPORT
- bool "Multifunction device drivers"
- depends on HAS_IOMEM
- default y
- help
- Multifunction devices embed several functions (e.g. GPIOs,
- touchscreens, keyboards, current regulators, power management chips,
- etc...) in one single integrated circuit. They usually talk to the
- main CPU through one or more IRQ lines and low speed data busses (SPI,
- I2C, etc..). They appear as one single device to the main system
- through the data bus and the MFD framework allows for sub devices
- (a.k.a. functions) to appear as discrete platform devices.
- MFDs are typically found on embedded platforms.
-
- This option alone does not add any kernel code.
-
-if MFD_SUPPORT
+if HAS_IOMEM
+menu "Multifunction device drivers"
config MFD_CORE
tristate
@@ -390,6 +375,7 @@
tristate "Support Wolfson Microelectronics WM8400"
select MFD_CORE
depends on I2C
+ select REGMAP_I2C
help
Support for the Wolfson Microelecronics WM8400 PMIC and audio
CODEC. This driver provides common support for accessing
@@ -503,6 +489,7 @@
config MFD_PCF50633
tristate "Support for NXP PCF50633"
depends on I2C
+ select REGMAP_I2C
help
Say yes here if you have NXP PCF50633 chip on your board.
This core driver provides register access and IRQ handling
@@ -579,6 +566,23 @@
This enables the PCAP ASIC present on EZX Phones. This is
needed for MMC, TouchScreen, Sound, USB, etc..
+config AB5500_CORE
+ bool "ST-Ericsson AB5500 Mixed Signal Power Management chip"
+ depends on ABX500_CORE && MFD_DB5500_PRCMU
+ select MFD_CORE
+ help
+ Select this option to enable access to AB5500 power management
+ chip. This connects to the db5500 chip via the I2C bus via PRCMU.
+ This chip embeds various other multimedia funtionalities as well.
+
+config AB5500_DEBUG
+ bool "Enable debug info via debugfs"
+ depends on AB5500_CORE && DEBUG_FS
+ default y if DEBUG_FS
+ help
+ Select this option if you want debug information from the AB5500
+ using the debug filesystem, debugfs.
+
config AB8500_CORE
bool "ST-Ericsson AB8500 Mixed Signal Power Management chip"
depends on GENERIC_HARDIRQS && ABX500_CORE
@@ -615,20 +619,6 @@
help
AB8500 GPADC driver used to convert Acc and battery/ac/usb voltage
-config AB3550_CORE
- bool "ST-Ericsson AB3550 Mixed Signal Circuit core functions"
- select MFD_CORE
- depends on I2C=y && GENERIC_HARDIRQS && ABX500_CORE
- help
- Select this to enable the AB3550 Mixed Signal IC core
- functionality. This connects to a AB3550 on the I2C bus
- and expose a number of symbols needed for dependent devices
- to read and write registers and subscribe to events from
- this multi-functional IC. This is needed to use other features
- of the AB3550 such as battery-backed RTC, charging control,
- LEDs, vibrator, system power and temperature, power management
- and ALSA sound.
-
config MFD_DB8500_PRCMU
bool "ST-Ericsson DB8500 Power Reset Control Management Unit"
depends on UX500_SOC_DB8500
@@ -773,7 +763,17 @@
additional drivers must be enabled in order to use the
functionality of the device.
-endif # MFD_SUPPORT
+config MFD_INTEL_MSIC
+ bool "Support for Intel MSIC"
+ depends on INTEL_SCU_IPC
+ select MFD_CORE
+ help
+ Select this option to enable access to Intel MSIC (Avatele
+ Passage) chip. This chip embeds audio, battery, GPIO, etc.
+ devices used in Intel Medfield platforms.
+
+endmenu
+endif
menu "Multimedia Capabilities Port drivers"
depends on ARCH_SA1100
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index c580203..b2292eb 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -79,7 +79,8 @@
obj-$(CONFIG_ABX500_CORE) += abx500-core.o
obj-$(CONFIG_AB3100_CORE) += ab3100-core.o
obj-$(CONFIG_AB3100_OTP) += ab3100-otp.o
-obj-$(CONFIG_AB3550_CORE) += ab3550-core.o
+obj-$(CONFIG_AB5500_CORE) += ab5500-core.o
+obj-$(CONFIG_AB5500_DEBUG) += ab5500-debugfs.o
obj-$(CONFIG_AB8500_CORE) += ab8500-core.o ab8500-sysctrl.o
obj-$(CONFIG_AB8500_DEBUG) += ab8500-debugfs.o
obj-$(CONFIG_AB8500_GPADC) += ab8500-gpadc.o
@@ -102,3 +103,4 @@
obj-$(CONFIG_MFD_PM8XXX_IRQ) += pm8xxx-irq.o
obj-$(CONFIG_TPS65911_COMPARATOR) += tps65911-comparator.o
obj-$(CONFIG_MFD_AAT2870_CORE) += aat2870-core.o
+obj-$(CONFIG_MFD_INTEL_MSIC) += intel_msic.o
diff --git a/drivers/mfd/aat2870-core.c b/drivers/mfd/aat2870-core.c
index 345dc65..02c4201 100644
--- a/drivers/mfd/aat2870-core.c
+++ b/drivers/mfd/aat2870-core.c
@@ -295,7 +295,7 @@
{
struct aat2870_data *aat2870 = file->private_data;
char buf[32];
- int buf_size;
+ ssize_t buf_size;
char *start = buf;
unsigned long addr, val;
int ret;
diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c
index a20e1c4..4f57255 100644
--- a/drivers/mfd/ab3100-core.c
+++ b/drivers/mfd/ab3100-core.c
@@ -809,7 +809,7 @@
char *name;
};
-static const struct ab_family_id ids[] __devinitdata = {
+static const struct ab_family_id ids[] __devinitconst = {
/* AB3100 */
{
.id = 0xc0,
diff --git a/drivers/mfd/ab3550-core.c b/drivers/mfd/ab3550-core.c
deleted file mode 100644
index 56ba194..0000000
--- a/drivers/mfd/ab3550-core.c
+++ /dev/null
@@ -1,1380 +0,0 @@
-/*
- * Copyright (C) 2007-2010 ST-Ericsson
- * License terms: GNU General Public License (GPL) version 2
- * Low-level core for exclusive access to the AB3550 IC on the I2C bus
- * and some basic chip-configuration.
- * Author: Bengt Jonsson <bengt.g.jonsson@stericsson.com>
- * Author: Mattias Nilsson <mattias.i.nilsson@stericsson.com>
- * Author: Mattias Wallin <mattias.wallin@stericsson.com>
- * Author: Rickard Andersson <rickard.andersson@stericsson.com>
- */
-
-#include <linux/i2c.h>
-#include <linux/mutex.h>
-#include <linux/err.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/device.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
-#include <linux/random.h>
-#include <linux/workqueue.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-#include <linux/uaccess.h>
-#include <linux/mfd/abx500.h>
-#include <linux/list.h>
-#include <linux/bitops.h>
-#include <linux/spinlock.h>
-#include <linux/mfd/core.h>
-
-#define AB3550_NAME_STRING "ab3550"
-#define AB3550_ID_FORMAT_STRING "AB3550 %s"
-#define AB3550_NUM_BANKS 2
-#define AB3550_NUM_EVENT_REG 5
-
-/* These are the only registers inside AB3550 used in this main file */
-
-/* Chip ID register */
-#define AB3550_CID_REG 0x20
-
-/* Interrupt event registers */
-#define AB3550_EVENT_BANK 0
-#define AB3550_EVENT_REG 0x22
-
-/* Read/write operation values. */
-#define AB3550_PERM_RD (0x01)
-#define AB3550_PERM_WR (0x02)
-
-/* Read/write permissions. */
-#define AB3550_PERM_RO (AB3550_PERM_RD)
-#define AB3550_PERM_RW (AB3550_PERM_RD | AB3550_PERM_WR)
-
-/**
- * struct ab3550
- * @access_mutex: lock out concurrent accesses to the AB registers
- * @i2c_client: I2C client for this chip
- * @chip_name: name of this chip variant
- * @chip_id: 8 bit chip ID for this chip variant
- * @mask_work: a worker for writing to mask registers
- * @event_lock: a lock to protect the event_mask
- * @event_mask: a local copy of the mask event registers
- * @startup_events: a copy of the first reading of the event registers
- * @startup_events_read: whether the first events have been read
- */
-struct ab3550 {
- struct mutex access_mutex;
- struct i2c_client *i2c_client[AB3550_NUM_BANKS];
- char chip_name[32];
- u8 chip_id;
- struct work_struct mask_work;
- spinlock_t event_lock;
- u8 event_mask[AB3550_NUM_EVENT_REG];
- u8 startup_events[AB3550_NUM_EVENT_REG];
- bool startup_events_read;
-#ifdef CONFIG_DEBUG_FS
- unsigned int debug_bank;
- unsigned int debug_address;
-#endif
-};
-
-/**
- * struct ab3550_reg_range
- * @first: the first address of the range
- * @last: the last address of the range
- * @perm: access permissions for the range
- */
-struct ab3550_reg_range {
- u8 first;
- u8 last;
- u8 perm;
-};
-
-/**
- * struct ab3550_reg_ranges
- * @count: the number of ranges in the list
- * @range: the list of register ranges
- */
-struct ab3550_reg_ranges {
- u8 count;
- const struct ab3550_reg_range *range;
-};
-
-/*
- * Permissible register ranges for reading and writing per device and bank.
- *
- * The ranges must be listed in increasing address order, and no overlaps are
- * allowed. It is assumed that write permission implies read permission
- * (i.e. only RO and RW permissions should be used). Ranges with write
- * permission must not be split up.
- */
-
-#define NO_RANGE {.count = 0, .range = NULL,}
-
-static struct
-ab3550_reg_ranges ab3550_reg_ranges[AB3550_NUM_DEVICES][AB3550_NUM_BANKS] = {
- [AB3550_DEVID_DAC] = {
- NO_RANGE,
- {
- .count = 2,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0xb0,
- .last = 0xba,
- .perm = AB3550_PERM_RW,
- },
- {
- .first = 0xbc,
- .last = 0xc3,
- .perm = AB3550_PERM_RW,
- },
- },
- },
- },
- [AB3550_DEVID_LEDS] = {
- NO_RANGE,
- {
- .count = 2,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x5a,
- .last = 0x88,
- .perm = AB3550_PERM_RW,
- },
- {
- .first = 0x8a,
- .last = 0xad,
- .perm = AB3550_PERM_RW,
- },
- }
- },
- },
- [AB3550_DEVID_POWER] = {
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x21,
- .last = 0x21,
- .perm = AB3550_PERM_RO,
- },
- }
- },
- NO_RANGE,
- },
- [AB3550_DEVID_REGULATORS] = {
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x69,
- .last = 0xa3,
- .perm = AB3550_PERM_RW,
- },
- }
- },
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x14,
- .last = 0x16,
- .perm = AB3550_PERM_RW,
- },
- }
- },
- },
- [AB3550_DEVID_SIM] = {
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x21,
- .last = 0x21,
- .perm = AB3550_PERM_RO,
- },
- }
- },
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x14,
- .last = 0x17,
- .perm = AB3550_PERM_RW,
- },
- }
-
- },
- },
- [AB3550_DEVID_UART] = {
- NO_RANGE,
- NO_RANGE,
- },
- [AB3550_DEVID_RTC] = {
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x00,
- .last = 0x0c,
- .perm = AB3550_PERM_RW,
- },
- }
- },
- NO_RANGE,
- },
- [AB3550_DEVID_CHARGER] = {
- {
- .count = 2,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x10,
- .last = 0x1a,
- .perm = AB3550_PERM_RW,
- },
- {
- .first = 0x21,
- .last = 0x21,
- .perm = AB3550_PERM_RO,
- },
- }
- },
- NO_RANGE,
- },
- [AB3550_DEVID_ADC] = {
- NO_RANGE,
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x20,
- .last = 0x56,
- .perm = AB3550_PERM_RW,
- },
-
- }
- },
- },
- [AB3550_DEVID_FUELGAUGE] = {
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x21,
- .last = 0x21,
- .perm = AB3550_PERM_RO,
- },
- }
- },
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x00,
- .last = 0x0e,
- .perm = AB3550_PERM_RW,
- },
- }
- },
- },
- [AB3550_DEVID_VIBRATOR] = {
- NO_RANGE,
- {
- .count = 1,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x10,
- .last = 0x13,
- .perm = AB3550_PERM_RW,
- },
-
- }
- },
- },
- [AB3550_DEVID_CODEC] = {
- {
- .count = 2,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x31,
- .last = 0x63,
- .perm = AB3550_PERM_RW,
- },
- {
- .first = 0x65,
- .last = 0x68,
- .perm = AB3550_PERM_RW,
- },
- }
- },
- NO_RANGE,
- },
-};
-
-static struct mfd_cell ab3550_devs[AB3550_NUM_DEVICES] = {
- [AB3550_DEVID_DAC] = {
- .name = "ab3550-dac",
- .id = AB3550_DEVID_DAC,
- .num_resources = 0,
- },
- [AB3550_DEVID_LEDS] = {
- .name = "ab3550-leds",
- .id = AB3550_DEVID_LEDS,
- },
- [AB3550_DEVID_POWER] = {
- .name = "ab3550-power",
- .id = AB3550_DEVID_POWER,
- },
- [AB3550_DEVID_REGULATORS] = {
- .name = "ab3550-regulators",
- .id = AB3550_DEVID_REGULATORS,
- },
- [AB3550_DEVID_SIM] = {
- .name = "ab3550-sim",
- .id = AB3550_DEVID_SIM,
- },
- [AB3550_DEVID_UART] = {
- .name = "ab3550-uart",
- .id = AB3550_DEVID_UART,
- },
- [AB3550_DEVID_RTC] = {
- .name = "ab3550-rtc",
- .id = AB3550_DEVID_RTC,
- },
- [AB3550_DEVID_CHARGER] = {
- .name = "ab3550-charger",
- .id = AB3550_DEVID_CHARGER,
- },
- [AB3550_DEVID_ADC] = {
- .name = "ab3550-adc",
- .id = AB3550_DEVID_ADC,
- .num_resources = 10,
- .resources = (struct resource[]) {
- {
- .name = "TRIGGER-0",
- .flags = IORESOURCE_IRQ,
- .start = 16,
- .end = 16,
- },
- {
- .name = "TRIGGER-1",
- .flags = IORESOURCE_IRQ,
- .start = 17,
- .end = 17,
- },
- {
- .name = "TRIGGER-2",
- .flags = IORESOURCE_IRQ,
- .start = 18,
- .end = 18,
- },
- {
- .name = "TRIGGER-3",
- .flags = IORESOURCE_IRQ,
- .start = 19,
- .end = 19,
- },
- {
- .name = "TRIGGER-4",
- .flags = IORESOURCE_IRQ,
- .start = 20,
- .end = 20,
- },
- {
- .name = "TRIGGER-5",
- .flags = IORESOURCE_IRQ,
- .start = 21,
- .end = 21,
- },
- {
- .name = "TRIGGER-6",
- .flags = IORESOURCE_IRQ,
- .start = 22,
- .end = 22,
- },
- {
- .name = "TRIGGER-7",
- .flags = IORESOURCE_IRQ,
- .start = 23,
- .end = 23,
- },
- {
- .name = "TRIGGER-VBAT-TXON",
- .flags = IORESOURCE_IRQ,
- .start = 13,
- .end = 13,
- },
- {
- .name = "TRIGGER-VBAT",
- .flags = IORESOURCE_IRQ,
- .start = 12,
- .end = 12,
- },
- },
- },
- [AB3550_DEVID_FUELGAUGE] = {
- .name = "ab3550-fuelgauge",
- .id = AB3550_DEVID_FUELGAUGE,
- },
- [AB3550_DEVID_VIBRATOR] = {
- .name = "ab3550-vibrator",
- .id = AB3550_DEVID_VIBRATOR,
- },
- [AB3550_DEVID_CODEC] = {
- .name = "ab3550-codec",
- .id = AB3550_DEVID_CODEC,
- },
-};
-
-/*
- * I2C transactions with error messages.
- */
-static int ab3550_i2c_master_send(struct ab3550 *ab, u8 bank, u8 *data,
- u8 count)
-{
- int err;
-
- err = i2c_master_send(ab->i2c_client[bank], data, count);
- if (err < 0) {
- dev_err(&ab->i2c_client[0]->dev, "send error: %d\n", err);
- return err;
- }
- return 0;
-}
-
-static int ab3550_i2c_master_recv(struct ab3550 *ab, u8 bank, u8 *data,
- u8 count)
-{
- int err;
-
- err = i2c_master_recv(ab->i2c_client[bank], data, count);
- if (err < 0) {
- dev_err(&ab->i2c_client[0]->dev, "receive error: %d\n", err);
- return err;
- }
- return 0;
-}
-
-/*
- * Functionality for getting/setting register values.
- */
-static int get_register_interruptible(struct ab3550 *ab, u8 bank, u8 reg,
- u8 *value)
-{
- int err;
-
- err = mutex_lock_interruptible(&ab->access_mutex);
- if (err)
- return err;
-
- err = ab3550_i2c_master_send(ab, bank, ®, 1);
- if (!err)
- err = ab3550_i2c_master_recv(ab, bank, value, 1);
-
- mutex_unlock(&ab->access_mutex);
- return err;
-}
-
-static int get_register_page_interruptible(struct ab3550 *ab, u8 bank,
- u8 first_reg, u8 *regvals, u8 numregs)
-{
- int err;
-
- err = mutex_lock_interruptible(&ab->access_mutex);
- if (err)
- return err;
-
- err = ab3550_i2c_master_send(ab, bank, &first_reg, 1);
- if (!err)
- err = ab3550_i2c_master_recv(ab, bank, regvals, numregs);
-
- mutex_unlock(&ab->access_mutex);
- return err;
-}
-
-static int mask_and_set_register_interruptible(struct ab3550 *ab, u8 bank,
- u8 reg, u8 bitmask, u8 bitvalues)
-{
- int err = 0;
-
- if (likely(bitmask)) {
- u8 reg_bits[2] = {reg, 0};
-
- err = mutex_lock_interruptible(&ab->access_mutex);
- if (err)
- return err;
-
- if (bitmask == 0xFF) /* No need to read in this case. */
- reg_bits[1] = bitvalues;
- else { /* Read and modify the register value. */
- u8 bits;
-
- err = ab3550_i2c_master_send(ab, bank, ®, 1);
- if (err)
- goto unlock_and_return;
- err = ab3550_i2c_master_recv(ab, bank, &bits, 1);
- if (err)
- goto unlock_and_return;
- reg_bits[1] = ((~bitmask & bits) |
- (bitmask & bitvalues));
- }
- /* Write the new value. */
- err = ab3550_i2c_master_send(ab, bank, reg_bits, 2);
-unlock_and_return:
- mutex_unlock(&ab->access_mutex);
- }
- return err;
-}
-
-/*
- * Read/write permission checking functions.
- */
-static bool page_write_allowed(const struct ab3550_reg_ranges *ranges,
- u8 first_reg, u8 last_reg)
-{
- u8 i;
-
- if (last_reg < first_reg)
- return false;
-
- for (i = 0; i < ranges->count; i++) {
- if (first_reg < ranges->range[i].first)
- break;
- if ((last_reg <= ranges->range[i].last) &&
- (ranges->range[i].perm & AB3550_PERM_WR))
- return true;
- }
- return false;
-}
-
-static bool reg_write_allowed(const struct ab3550_reg_ranges *ranges, u8 reg)
-{
- return page_write_allowed(ranges, reg, reg);
-}
-
-static bool page_read_allowed(const struct ab3550_reg_ranges *ranges,
- u8 first_reg, u8 last_reg)
-{
- u8 i;
-
- if (last_reg < first_reg)
- return false;
- /* Find the range (if it exists in the list) that includes first_reg. */
- for (i = 0; i < ranges->count; i++) {
- if (first_reg < ranges->range[i].first)
- return false;
- if (first_reg <= ranges->range[i].last)
- break;
- }
- /* Make sure that the entire range up to and including last_reg is
- * readable. This may span several of the ranges in the list.
- */
- while ((i < ranges->count) &&
- (ranges->range[i].perm & AB3550_PERM_RD)) {
- if (last_reg <= ranges->range[i].last)
- return true;
- if ((++i >= ranges->count) ||
- (ranges->range[i].first !=
- (ranges->range[i - 1].last + 1))) {
- break;
- }
- }
- return false;
-}
-
-static bool reg_read_allowed(const struct ab3550_reg_ranges *ranges, u8 reg)
-{
- return page_read_allowed(ranges, reg, reg);
-}
-
-/*
- * The register access functionality.
- */
-static int ab3550_get_chip_id(struct device *dev)
-{
- struct ab3550 *ab = dev_get_drvdata(dev->parent);
- return (int)ab->chip_id;
-}
-
-static int ab3550_mask_and_set_register_interruptible(struct device *dev,
- u8 bank, u8 reg, u8 bitmask, u8 bitvalues)
-{
- struct ab3550 *ab;
- struct platform_device *pdev = to_platform_device(dev);
-
- if ((AB3550_NUM_BANKS <= bank) ||
- !reg_write_allowed(&ab3550_reg_ranges[pdev->id][bank], reg))
- return -EINVAL;
-
- ab = dev_get_drvdata(dev->parent);
- return mask_and_set_register_interruptible(ab, bank, reg,
- bitmask, bitvalues);
-}
-
-static int ab3550_set_register_interruptible(struct device *dev, u8 bank,
- u8 reg, u8 value)
-{
- return ab3550_mask_and_set_register_interruptible(dev, bank, reg, 0xFF,
- value);
-}
-
-static int ab3550_get_register_interruptible(struct device *dev, u8 bank,
- u8 reg, u8 *value)
-{
- struct ab3550 *ab;
- struct platform_device *pdev = to_platform_device(dev);
-
- if ((AB3550_NUM_BANKS <= bank) ||
- !reg_read_allowed(&ab3550_reg_ranges[pdev->id][bank], reg))
- return -EINVAL;
-
- ab = dev_get_drvdata(dev->parent);
- return get_register_interruptible(ab, bank, reg, value);
-}
-
-static int ab3550_get_register_page_interruptible(struct device *dev, u8 bank,
- u8 first_reg, u8 *regvals, u8 numregs)
-{
- struct ab3550 *ab;
- struct platform_device *pdev = to_platform_device(dev);
-
- if ((AB3550_NUM_BANKS <= bank) ||
- !page_read_allowed(&ab3550_reg_ranges[pdev->id][bank],
- first_reg, (first_reg + numregs - 1)))
- return -EINVAL;
-
- ab = dev_get_drvdata(dev->parent);
- return get_register_page_interruptible(ab, bank, first_reg, regvals,
- numregs);
-}
-
-static int ab3550_event_registers_startup_state_get(struct device *dev,
- u8 *event)
-{
- struct ab3550 *ab;
-
- ab = dev_get_drvdata(dev->parent);
- if (!ab->startup_events_read)
- return -EAGAIN; /* Try again later */
-
- memcpy(event, ab->startup_events, AB3550_NUM_EVENT_REG);
- return 0;
-}
-
-static int ab3550_startup_irq_enabled(struct device *dev, unsigned int irq)
-{
- struct ab3550 *ab;
- struct ab3550_platform_data *plf_data;
- bool val;
-
- ab = irq_get_chip_data(irq);
- plf_data = ab->i2c_client[0]->dev.platform_data;
- irq -= plf_data->irq.base;
- val = ((ab->startup_events[irq / 8] & BIT(irq % 8)) != 0);
-
- return val;
-}
-
-static struct abx500_ops ab3550_ops = {
- .get_chip_id = ab3550_get_chip_id,
- .get_register = ab3550_get_register_interruptible,
- .set_register = ab3550_set_register_interruptible,
- .get_register_page = ab3550_get_register_page_interruptible,
- .set_register_page = NULL,
- .mask_and_set_register = ab3550_mask_and_set_register_interruptible,
- .event_registers_startup_state_get =
- ab3550_event_registers_startup_state_get,
- .startup_irq_enabled = ab3550_startup_irq_enabled,
-};
-
-static irqreturn_t ab3550_irq_handler(int irq, void *data)
-{
- struct ab3550 *ab = data;
- int err;
- unsigned int i;
- u8 e[AB3550_NUM_EVENT_REG];
- u8 *events;
- unsigned long flags;
-
- events = (ab->startup_events_read ? e : ab->startup_events);
-
- err = get_register_page_interruptible(ab, AB3550_EVENT_BANK,
- AB3550_EVENT_REG, events, AB3550_NUM_EVENT_REG);
- if (err)
- goto err_event_rd;
-
- if (!ab->startup_events_read) {
- dev_info(&ab->i2c_client[0]->dev,
- "startup events 0x%x,0x%x,0x%x,0x%x,0x%x\n",
- ab->startup_events[0], ab->startup_events[1],
- ab->startup_events[2], ab->startup_events[3],
- ab->startup_events[4]);
- ab->startup_events_read = true;
- goto out;
- }
-
- /* The two highest bits in event[4] are not used. */
- events[4] &= 0x3f;
-
- spin_lock_irqsave(&ab->event_lock, flags);
- for (i = 0; i < AB3550_NUM_EVENT_REG; i++)
- events[i] &= ~ab->event_mask[i];
- spin_unlock_irqrestore(&ab->event_lock, flags);
-
- for (i = 0; i < AB3550_NUM_EVENT_REG; i++) {
- u8 bit;
- u8 event_reg;
-
- dev_dbg(&ab->i2c_client[0]->dev, "IRQ Event[%d]: 0x%2x\n",
- i, events[i]);
-
- event_reg = events[i];
- for (bit = 0; event_reg; bit++, event_reg /= 2) {
- if (event_reg % 2) {
- unsigned int irq;
- struct ab3550_platform_data *plf_data;
-
- plf_data = ab->i2c_client[0]->dev.platform_data;
- irq = plf_data->irq.base + (i * 8) + bit;
- handle_nested_irq(irq);
- }
- }
- }
-out:
- return IRQ_HANDLED;
-
-err_event_rd:
- dev_dbg(&ab->i2c_client[0]->dev, "error reading event registers\n");
- return IRQ_HANDLED;
-}
-
-#ifdef CONFIG_DEBUG_FS
-static struct ab3550_reg_ranges debug_ranges[AB3550_NUM_BANKS] = {
- {
- .count = 6,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x00,
- .last = 0x0e,
- },
- {
- .first = 0x10,
- .last = 0x1a,
- },
- {
- .first = 0x1e,
- .last = 0x4f,
- },
- {
- .first = 0x51,
- .last = 0x63,
- },
- {
- .first = 0x65,
- .last = 0xa3,
- },
- {
- .first = 0xa5,
- .last = 0xa8,
- },
- }
- },
- {
- .count = 8,
- .range = (struct ab3550_reg_range[]) {
- {
- .first = 0x00,
- .last = 0x0e,
- },
- {
- .first = 0x10,
- .last = 0x17,
- },
- {
- .first = 0x1a,
- .last = 0x1c,
- },
- {
- .first = 0x20,
- .last = 0x56,
- },
- {
- .first = 0x5a,
- .last = 0x88,
- },
- {
- .first = 0x8a,
- .last = 0xad,
- },
- {
- .first = 0xb0,
- .last = 0xba,
- },
- {
- .first = 0xbc,
- .last = 0xc3,
- },
- }
- },
-};
-
-static int ab3550_registers_print(struct seq_file *s, void *p)
-{
- struct ab3550 *ab = s->private;
- int bank;
-
- seq_printf(s, AB3550_NAME_STRING " register values:\n");
-
- for (bank = 0; bank < AB3550_NUM_BANKS; bank++) {
- unsigned int i;
-
- seq_printf(s, " bank %d:\n", bank);
- for (i = 0; i < debug_ranges[bank].count; i++) {
- u8 reg;
-
- for (reg = debug_ranges[bank].range[i].first;
- reg <= debug_ranges[bank].range[i].last;
- reg++) {
- u8 value;
-
- get_register_interruptible(ab, bank, reg,
- &value);
- seq_printf(s, " [%d/0x%02X]: 0x%02X\n", bank,
- reg, value);
- }
- }
- }
- return 0;
-}
-
-static int ab3550_registers_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ab3550_registers_print, inode->i_private);
-}
-
-static const struct file_operations ab3550_registers_fops = {
- .open = ab3550_registers_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
- .owner = THIS_MODULE,
-};
-
-static int ab3550_bank_print(struct seq_file *s, void *p)
-{
- struct ab3550 *ab = s->private;
-
- seq_printf(s, "%d\n", ab->debug_bank);
- return 0;
-}
-
-static int ab3550_bank_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ab3550_bank_print, inode->i_private);
-}
-
-static ssize_t ab3550_bank_write(struct file *file,
- const char __user *user_buf,
- size_t count, loff_t *ppos)
-{
- struct ab3550 *ab = ((struct seq_file *)(file->private_data))->private;
- unsigned long user_bank;
- int err;
-
- /* Get userspace string and assure termination */
- err = kstrtoul_from_user(user_buf, count, 0, &user_bank);
- if (err)
- return err;
-
- if (user_bank >= AB3550_NUM_BANKS) {
- dev_err(&ab->i2c_client[0]->dev,
- "debugfs error input > number of banks\n");
- return -EINVAL;
- }
-
- ab->debug_bank = user_bank;
-
- return count;
-}
-
-static int ab3550_address_print(struct seq_file *s, void *p)
-{
- struct ab3550 *ab = s->private;
-
- seq_printf(s, "0x%02X\n", ab->debug_address);
- return 0;
-}
-
-static int ab3550_address_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ab3550_address_print, inode->i_private);
-}
-
-static ssize_t ab3550_address_write(struct file *file,
- const char __user *user_buf,
- size_t count, loff_t *ppos)
-{
- struct ab3550 *ab = ((struct seq_file *)(file->private_data))->private;
- unsigned long user_address;
- int err;
-
- /* Get userspace string and assure termination */
- err = kstrtoul_from_user(user_buf, count, 0, &user_address);
- if (err)
- return err;
-
- if (user_address > 0xff) {
- dev_err(&ab->i2c_client[0]->dev,
- "debugfs error input > 0xff\n");
- return -EINVAL;
- }
- ab->debug_address = user_address;
- return count;
-}
-
-static int ab3550_val_print(struct seq_file *s, void *p)
-{
- struct ab3550 *ab = s->private;
- int err;
- u8 regvalue;
-
- err = get_register_interruptible(ab, (u8)ab->debug_bank,
- (u8)ab->debug_address, ®value);
- if (err)
- return -EINVAL;
- seq_printf(s, "0x%02X\n", regvalue);
-
- return 0;
-}
-
-static int ab3550_val_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ab3550_val_print, inode->i_private);
-}
-
-static ssize_t ab3550_val_write(struct file *file,
- const char __user *user_buf,
- size_t count, loff_t *ppos)
-{
- struct ab3550 *ab = ((struct seq_file *)(file->private_data))->private;
- unsigned long user_val;
- int err;
- u8 regvalue;
-
- /* Get userspace string and assure termination */
- err = kstrtoul_from_user(user_buf, count, 0, &user_val);
- if (err)
- return err;
-
- if (user_val > 0xff) {
- dev_err(&ab->i2c_client[0]->dev,
- "debugfs error input > 0xff\n");
- return -EINVAL;
- }
- err = mask_and_set_register_interruptible(
- ab, (u8)ab->debug_bank,
- (u8)ab->debug_address, 0xFF, (u8)user_val);
- if (err)
- return -EINVAL;
-
- get_register_interruptible(ab, (u8)ab->debug_bank,
- (u8)ab->debug_address, ®value);
- if (err)
- return -EINVAL;
-
- return count;
-}
-
-static const struct file_operations ab3550_bank_fops = {
- .open = ab3550_bank_open,
- .write = ab3550_bank_write,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
- .owner = THIS_MODULE,
-};
-
-static const struct file_operations ab3550_address_fops = {
- .open = ab3550_address_open,
- .write = ab3550_address_write,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
- .owner = THIS_MODULE,
-};
-
-static const struct file_operations ab3550_val_fops = {
- .open = ab3550_val_open,
- .write = ab3550_val_write,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
- .owner = THIS_MODULE,
-};
-
-static struct dentry *ab3550_dir;
-static struct dentry *ab3550_reg_file;
-static struct dentry *ab3550_bank_file;
-static struct dentry *ab3550_address_file;
-static struct dentry *ab3550_val_file;
-
-static inline void ab3550_setup_debugfs(struct ab3550 *ab)
-{
- ab->debug_bank = 0;
- ab->debug_address = 0x00;
-
- ab3550_dir = debugfs_create_dir(AB3550_NAME_STRING, NULL);
- if (!ab3550_dir)
- goto exit_no_debugfs;
-
- ab3550_reg_file = debugfs_create_file("all-registers",
- S_IRUGO, ab3550_dir, ab, &ab3550_registers_fops);
- if (!ab3550_reg_file)
- goto exit_destroy_dir;
-
- ab3550_bank_file = debugfs_create_file("register-bank",
- (S_IRUGO | S_IWUSR), ab3550_dir, ab, &ab3550_bank_fops);
- if (!ab3550_bank_file)
- goto exit_destroy_reg;
-
- ab3550_address_file = debugfs_create_file("register-address",
- (S_IRUGO | S_IWUSR), ab3550_dir, ab, &ab3550_address_fops);
- if (!ab3550_address_file)
- goto exit_destroy_bank;
-
- ab3550_val_file = debugfs_create_file("register-value",
- (S_IRUGO | S_IWUSR), ab3550_dir, ab, &ab3550_val_fops);
- if (!ab3550_val_file)
- goto exit_destroy_address;
-
- return;
-
-exit_destroy_address:
- debugfs_remove(ab3550_address_file);
-exit_destroy_bank:
- debugfs_remove(ab3550_bank_file);
-exit_destroy_reg:
- debugfs_remove(ab3550_reg_file);
-exit_destroy_dir:
- debugfs_remove(ab3550_dir);
-exit_no_debugfs:
- dev_err(&ab->i2c_client[0]->dev, "failed to create debugfs entries.\n");
- return;
-}
-
-static inline void ab3550_remove_debugfs(void)
-{
- debugfs_remove(ab3550_val_file);
- debugfs_remove(ab3550_address_file);
- debugfs_remove(ab3550_bank_file);
- debugfs_remove(ab3550_reg_file);
- debugfs_remove(ab3550_dir);
-}
-
-#else /* !CONFIG_DEBUG_FS */
-static inline void ab3550_setup_debugfs(struct ab3550 *ab)
-{
-}
-static inline void ab3550_remove_debugfs(void)
-{
-}
-#endif
-
-/*
- * Basic set-up, datastructure creation/destruction and I2C interface.
- * This sets up a default config in the AB3550 chip so that it
- * will work as expected.
- */
-static int __init ab3550_setup(struct ab3550 *ab)
-{
- int err = 0;
- int i;
- struct ab3550_platform_data *plf_data;
- struct abx500_init_settings *settings;
-
- plf_data = ab->i2c_client[0]->dev.platform_data;
- settings = plf_data->init_settings;
-
- for (i = 0; i < plf_data->init_settings_sz; i++) {
- err = mask_and_set_register_interruptible(ab,
- settings[i].bank,
- settings[i].reg,
- 0xFF, settings[i].setting);
- if (err)
- goto exit_no_setup;
-
- /* If event mask register update the event mask in ab3550 */
- if ((settings[i].bank == 0) &&
- (AB3550_IMR1 <= settings[i].reg) &&
- (settings[i].reg <= AB3550_IMR5)) {
- ab->event_mask[settings[i].reg - AB3550_IMR1] =
- settings[i].setting;
- }
- }
-exit_no_setup:
- return err;
-}
-
-static void ab3550_mask_work(struct work_struct *work)
-{
- struct ab3550 *ab = container_of(work, struct ab3550, mask_work);
- int i;
- unsigned long flags;
- u8 mask[AB3550_NUM_EVENT_REG];
-
- spin_lock_irqsave(&ab->event_lock, flags);
- for (i = 0; i < AB3550_NUM_EVENT_REG; i++)
- mask[i] = ab->event_mask[i];
- spin_unlock_irqrestore(&ab->event_lock, flags);
-
- for (i = 0; i < AB3550_NUM_EVENT_REG; i++) {
- int err;
-
- err = mask_and_set_register_interruptible(ab, 0,
- (AB3550_IMR1 + i), ~0, mask[i]);
- if (err)
- dev_err(&ab->i2c_client[0]->dev,
- "ab3550_mask_work failed 0x%x,0x%x\n",
- (AB3550_IMR1 + i), mask[i]);
- }
-}
-
-static void ab3550_mask(struct irq_data *data)
-{
- unsigned long flags;
- struct ab3550 *ab;
- struct ab3550_platform_data *plf_data;
- int irq;
-
- ab = irq_data_get_irq_chip_data(data);
- plf_data = ab->i2c_client[0]->dev.platform_data;
- irq = data->irq - plf_data->irq.base;
-
- spin_lock_irqsave(&ab->event_lock, flags);
- ab->event_mask[irq / 8] |= BIT(irq % 8);
- spin_unlock_irqrestore(&ab->event_lock, flags);
-
- schedule_work(&ab->mask_work);
-}
-
-static void ab3550_unmask(struct irq_data *data)
-{
- unsigned long flags;
- struct ab3550 *ab;
- struct ab3550_platform_data *plf_data;
- int irq;
-
- ab = irq_data_get_irq_chip_data(data);
- plf_data = ab->i2c_client[0]->dev.platform_data;
- irq = data->irq - plf_data->irq.base;
-
- spin_lock_irqsave(&ab->event_lock, flags);
- ab->event_mask[irq / 8] &= ~BIT(irq % 8);
- spin_unlock_irqrestore(&ab->event_lock, flags);
-
- schedule_work(&ab->mask_work);
-}
-
-static void noop(struct irq_data *data)
-{
-}
-
-static struct irq_chip ab3550_irq_chip = {
- .name = "ab3550-core", /* Keep the same name as the request */
- .irq_disable = ab3550_mask, /* No default to mask in chip.c */
- .irq_ack = noop,
- .irq_mask = ab3550_mask,
- .irq_unmask = ab3550_unmask,
-};
-
-struct ab_family_id {
- u8 id;
- char *name;
-};
-
-static const struct ab_family_id ids[] __initdata = {
- /* AB3550 */
- {
- .id = AB3550_P1A,
- .name = "P1A"
- },
- /* Terminator */
- {
- .id = 0x00,
- }
-};
-
-static int __init ab3550_probe(struct i2c_client *client,
- const struct i2c_device_id *id)
-{
- struct ab3550 *ab;
- struct ab3550_platform_data *ab3550_plf_data =
- client->dev.platform_data;
- int err;
- int i;
- int num_i2c_clients = 0;
-
- ab = kzalloc(sizeof(struct ab3550), GFP_KERNEL);
- if (!ab) {
- dev_err(&client->dev,
- "could not allocate " AB3550_NAME_STRING " device\n");
- return -ENOMEM;
- }
-
- /* Initialize data structure */
- mutex_init(&ab->access_mutex);
- spin_lock_init(&ab->event_lock);
- ab->i2c_client[0] = client;
-
- i2c_set_clientdata(client, ab);
-
- /* Read chip ID register */
- err = get_register_interruptible(ab, 0, AB3550_CID_REG, &ab->chip_id);
- if (err) {
- dev_err(&client->dev, "could not communicate with the analog "
- "baseband chip\n");
- goto exit_no_detect;
- }
-
- for (i = 0; ids[i].id != 0x0; i++) {
- if (ids[i].id == ab->chip_id) {
- snprintf(&ab->chip_name[0], sizeof(ab->chip_name) - 1,
- AB3550_ID_FORMAT_STRING, ids[i].name);
- break;
- }
- }
-
- if (ids[i].id == 0x0) {
- dev_err(&client->dev, "unknown analog baseband chip id: 0x%x\n",
- ab->chip_id);
- dev_err(&client->dev, "driver not started!\n");
- goto exit_no_detect;
- }
-
- dev_info(&client->dev, "detected AB chip: %s\n", &ab->chip_name[0]);
-
- /* Attach other dummy I2C clients. */
- while (++num_i2c_clients < AB3550_NUM_BANKS) {
- ab->i2c_client[num_i2c_clients] =
- i2c_new_dummy(client->adapter,
- (client->addr + num_i2c_clients));
- if (!ab->i2c_client[num_i2c_clients]) {
- err = -ENOMEM;
- goto exit_no_dummy_client;
- }
- strlcpy(ab->i2c_client[num_i2c_clients]->name, id->name,
- sizeof(ab->i2c_client[num_i2c_clients]->name));
- }
-
- err = ab3550_setup(ab);
- if (err)
- goto exit_no_setup;
-
- INIT_WORK(&ab->mask_work, ab3550_mask_work);
-
- for (i = 0; i < ab3550_plf_data->irq.count; i++) {
- unsigned int irq;
-
- irq = ab3550_plf_data->irq.base + i;
- irq_set_chip_data(irq, ab);
- irq_set_chip_and_handler(irq, &ab3550_irq_chip,
- handle_simple_irq);
- irq_set_nested_thread(irq, 1);
-#ifdef CONFIG_ARM
- set_irq_flags(irq, IRQF_VALID);
-#else
- irq_set_noprobe(irq);
-#endif
- }
-
- err = request_threaded_irq(client->irq, NULL, ab3550_irq_handler,
- IRQF_ONESHOT, "ab3550-core", ab);
- /* This real unpredictable IRQ is of course sampled for entropy */
- rand_initialize_irq(client->irq);
-
- if (err)
- goto exit_no_irq;
-
- err = abx500_register_ops(&client->dev, &ab3550_ops);
- if (err)
- goto exit_no_ops;
-
- /* Set up and register the platform devices. */
- for (i = 0; i < AB3550_NUM_DEVICES; i++) {
- ab3550_devs[i].platform_data = ab3550_plf_data->dev_data[i];
- ab3550_devs[i].pdata_size = ab3550_plf_data->dev_data_sz[i];
- }
-
- err = mfd_add_devices(&client->dev, 0, ab3550_devs,
- ARRAY_SIZE(ab3550_devs), NULL,
- ab3550_plf_data->irq.base);
-
- ab3550_setup_debugfs(ab);
-
- return 0;
-
-exit_no_ops:
-exit_no_irq:
-exit_no_setup:
-exit_no_dummy_client:
- /* Unregister the dummy i2c clients. */
- while (--num_i2c_clients)
- i2c_unregister_device(ab->i2c_client[num_i2c_clients]);
-exit_no_detect:
- kfree(ab);
- return err;
-}
-
-static int __exit ab3550_remove(struct i2c_client *client)
-{
- struct ab3550 *ab = i2c_get_clientdata(client);
- int num_i2c_clients = AB3550_NUM_BANKS;
-
- mfd_remove_devices(&client->dev);
- ab3550_remove_debugfs();
-
- while (--num_i2c_clients)
- i2c_unregister_device(ab->i2c_client[num_i2c_clients]);
-
- /*
- * At this point, all subscribers should have unregistered
- * their notifiers so deactivate IRQ
- */
- free_irq(client->irq, ab);
- kfree(ab);
- return 0;
-}
-
-static const struct i2c_device_id ab3550_id[] = {
- {AB3550_NAME_STRING, 0},
- {}
-};
-MODULE_DEVICE_TABLE(i2c, ab3550_id);
-
-static struct i2c_driver ab3550_driver = {
- .driver = {
- .name = AB3550_NAME_STRING,
- .owner = THIS_MODULE,
- },
- .id_table = ab3550_id,
- .probe = ab3550_probe,
- .remove = __exit_p(ab3550_remove),
-};
-
-static int __init ab3550_i2c_init(void)
-{
- return i2c_add_driver(&ab3550_driver);
-}
-
-static void __exit ab3550_i2c_exit(void)
-{
- i2c_del_driver(&ab3550_driver);
-}
-
-subsys_initcall(ab3550_i2c_init);
-module_exit(ab3550_i2c_exit);
-
-MODULE_AUTHOR("Mattias Wallin <mattias.wallin@stericsson.com>");
-MODULE_DESCRIPTION("AB3550 core driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/ab5500-core.c b/drivers/mfd/ab5500-core.c
new file mode 100644
index 0000000..4175544
--- /dev/null
+++ b/drivers/mfd/ab5500-core.c
@@ -0,0 +1,1439 @@
+/*
+ * Copyright (C) 2007-2011 ST-Ericsson
+ * License terms: GNU General Public License (GPL) version 2
+ * Low-level core for exclusive access to the AB5500 IC on the I2C bus
+ * and some basic chip-configuration.
+ * Author: Bengt Jonsson <bengt.g.jonsson@stericsson.com>
+ * Author: Mattias Nilsson <mattias.i.nilsson@stericsson.com>
+ * Author: Mattias Wallin <mattias.wallin@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ * Author: Karl Komierowski <karl.komierowski@stericsson.com>
+ * Author: Bibek Basu <bibek.basu@stericsson.com>
+ *
+ * TODO: Event handling with irq_chip. Waiting for PRCMU fw support.
+ */
+
+#include <linux/mutex.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/random.h>
+#include <linux/mfd/ab5500/ab5500.h>
+#include <linux/mfd/abx500.h>
+#include <linux/list.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/mfd/core.h>
+#include <linux/version.h>
+#include <linux/mfd/db5500-prcmu.h>
+
+#include "ab5500-core.h"
+#include "ab5500-debugfs.h"
+
+#define AB5500_NUM_EVENT_REG 23
+#define AB5500_IT_LATCH0_REG 0x40
+#define AB5500_IT_MASK0_REG 0x60
+
+/*
+ * Permissible register ranges for reading and writing per device and bank.
+ *
+ * The ranges must be listed in increasing address order, and no overlaps are
+ * allowed. It is assumed that write permission implies read permission
+ * (i.e. only RO and RW permissions should be used). Ranges with write
+ * permission must not be split up.
+ */
+
+#define NO_RANGE {.count = 0, .range = NULL,}
+static struct ab5500_i2c_banks ab5500_bank_ranges[AB5500_NUM_DEVICES] = {
+ [AB5500_DEVID_USB] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_USB,
+ .nranges = 12,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x01,
+ .last = 0x01,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x80,
+ .last = 0x83,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x87,
+ .last = 0x8A,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x8B,
+ .last = 0x8B,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x91,
+ .last = 0x92,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x93,
+ .last = 0x93,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x94,
+ .last = 0x94,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xA8,
+ .last = 0xB0,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xB2,
+ .last = 0xB2,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xB4,
+ .last = 0xBC,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xBF,
+ .last = 0xBF,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xC1,
+ .last = 0xC5,
+ .perm = AB5500_PERM_RO,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_ADC] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_ADC,
+ .nranges = 6,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x1F,
+ .last = 0x22,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x23,
+ .last = 0x24,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x26,
+ .last = 0x2D,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x2F,
+ .last = 0x34,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x37,
+ .last = 0x57,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x58,
+ .last = 0x58,
+ .perm = AB5500_PERM_RO,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_LEDS] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_LED,
+ .nranges = 1,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x0C,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_VIDEO] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_VDENC,
+ .nranges = 12,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x08,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x09,
+ .last = 0x09,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x0A,
+ .last = 0x12,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x15,
+ .last = 0x19,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x1B,
+ .last = 0x21,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x27,
+ .last = 0x2C,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x41,
+ .last = 0x41,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x45,
+ .last = 0x5B,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x5D,
+ .last = 0x5D,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x69,
+ .last = 0x69,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x6C,
+ .last = 0x6D,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x80,
+ .last = 0x81,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_REGULATORS] = {
+ .nbanks = 2,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_STARTUP,
+ .nranges = 12,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x01,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x1F,
+ .last = 0x1F,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x2E,
+ .last = 0x2E,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x2F,
+ .last = 0x30,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x50,
+ .last = 0x51,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x60,
+ .last = 0x61,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x66,
+ .last = 0x8A,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x8C,
+ .last = 0x96,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xAA,
+ .last = 0xB4,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xB7,
+ .last = 0xBF,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xC1,
+ .last = 0xCA,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xD3,
+ .last = 0xE0,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ {
+ .bankid = AB5500_BANK_SIM_USBSIM,
+ .nranges = 1,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x13,
+ .last = 0x19,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_SIM] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_SIM_USBSIM,
+ .nranges = 1,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x13,
+ .last = 0x19,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_RTC] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_RTC,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x04,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x06,
+ .last = 0x0C,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_CHARGER] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_CHG,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x11,
+ .last = 0x11,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x12,
+ .last = 0x1B,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_FUELGAUGE] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_FG_BATTCOM_ACC,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x0B,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x0C,
+ .last = 0x10,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_VIBRATOR] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_VIBRA,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x10,
+ .last = 0x13,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xFE,
+ .last = 0xFE,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_CODEC] = {
+ .nbanks = 1,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_AUDIO_HEADSETUSB,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x48,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xEB,
+ .last = 0xFB,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+ [AB5500_DEVID_POWER] = {
+ .nbanks = 2,
+ .bank = (struct ab5500_i2c_ranges []) {
+ {
+ .bankid = AB5500_BANK_STARTUP,
+ .nranges = 1,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x30,
+ .last = 0x30,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ {
+ .bankid = AB5500_BANK_VIT_IO_I2C_CLK_TST_OTP,
+ .nranges = 1,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x01,
+ .last = 0x01,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ },
+ },
+};
+
+#define AB5500_IRQ(bank, bit) ((bank) * 8 + (bit))
+
+/* I appologize for the resource names beeing a mix of upper case
+ * and lower case but I want them to be exact as the documentation */
+static struct mfd_cell ab5500_devs[AB5500_NUM_DEVICES] = {
+ [AB5500_DEVID_LEDS] = {
+ .name = "ab5500-leds",
+ .id = AB5500_DEVID_LEDS,
+ },
+ [AB5500_DEVID_POWER] = {
+ .name = "ab5500-power",
+ .id = AB5500_DEVID_POWER,
+ },
+ [AB5500_DEVID_REGULATORS] = {
+ .name = "ab5500-regulator",
+ .id = AB5500_DEVID_REGULATORS,
+ },
+ [AB5500_DEVID_SIM] = {
+ .name = "ab5500-sim",
+ .id = AB5500_DEVID_SIM,
+ .num_resources = 1,
+ .resources = (struct resource[]) {
+ {
+ .name = "SIMOFF",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(2, 0), /*rising*/
+ .end = AB5500_IRQ(2, 1), /*falling*/
+ },
+ },
+ },
+ [AB5500_DEVID_RTC] = {
+ .name = "ab5500-rtc",
+ .id = AB5500_DEVID_RTC,
+ .num_resources = 1,
+ .resources = (struct resource[]) {
+ {
+ .name = "RTC_Alarm",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(1, 7),
+ .end = AB5500_IRQ(1, 7),
+ }
+ },
+ },
+ [AB5500_DEVID_CHARGER] = {
+ .name = "ab5500-charger",
+ .id = AB5500_DEVID_CHARGER,
+ },
+ [AB5500_DEVID_ADC] = {
+ .name = "ab5500-adc",
+ .id = AB5500_DEVID_ADC,
+ .num_resources = 10,
+ .resources = (struct resource[]) {
+ {
+ .name = "TRIGGER-0",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 0),
+ .end = AB5500_IRQ(0, 0),
+ },
+ {
+ .name = "TRIGGER-1",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 1),
+ .end = AB5500_IRQ(0, 1),
+ },
+ {
+ .name = "TRIGGER-2",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 2),
+ .end = AB5500_IRQ(0, 2),
+ },
+ {
+ .name = "TRIGGER-3",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 3),
+ .end = AB5500_IRQ(0, 3),
+ },
+ {
+ .name = "TRIGGER-4",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 4),
+ .end = AB5500_IRQ(0, 4),
+ },
+ {
+ .name = "TRIGGER-5",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 5),
+ .end = AB5500_IRQ(0, 5),
+ },
+ {
+ .name = "TRIGGER-6",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 6),
+ .end = AB5500_IRQ(0, 6),
+ },
+ {
+ .name = "TRIGGER-7",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 7),
+ .end = AB5500_IRQ(0, 7),
+ },
+ {
+ .name = "TRIGGER-VBAT",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 8),
+ .end = AB5500_IRQ(0, 8),
+ },
+ {
+ .name = "TRIGGER-VBAT-TXON",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(0, 9),
+ .end = AB5500_IRQ(0, 9),
+ },
+ },
+ },
+ [AB5500_DEVID_FUELGAUGE] = {
+ .name = "ab5500-fuelgauge",
+ .id = AB5500_DEVID_FUELGAUGE,
+ .num_resources = 6,
+ .resources = (struct resource[]) {
+ {
+ .name = "Batt_attach",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(7, 5),
+ .end = AB5500_IRQ(7, 5),
+ },
+ {
+ .name = "Batt_removal",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(7, 6),
+ .end = AB5500_IRQ(7, 6),
+ },
+ {
+ .name = "UART_framing",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(7, 7),
+ .end = AB5500_IRQ(7, 7),
+ },
+ {
+ .name = "UART_overrun",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(8, 0),
+ .end = AB5500_IRQ(8, 0),
+ },
+ {
+ .name = "UART_Rdy_RX",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(8, 1),
+ .end = AB5500_IRQ(8, 1),
+ },
+ {
+ .name = "UART_Rdy_TX",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(8, 2),
+ .end = AB5500_IRQ(8, 2),
+ },
+ },
+ },
+ [AB5500_DEVID_VIBRATOR] = {
+ .name = "ab5500-vibrator",
+ .id = AB5500_DEVID_VIBRATOR,
+ },
+ [AB5500_DEVID_CODEC] = {
+ .name = "ab5500-codec",
+ .id = AB5500_DEVID_CODEC,
+ .num_resources = 3,
+ .resources = (struct resource[]) {
+ {
+ .name = "audio_spkr1_ovc",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(9, 5),
+ .end = AB5500_IRQ(9, 5),
+ },
+ {
+ .name = "audio_plllocked",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(9, 6),
+ .end = AB5500_IRQ(9, 6),
+ },
+ {
+ .name = "audio_spkr2_ovc",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(17, 4),
+ .end = AB5500_IRQ(17, 4),
+ },
+ },
+ },
+ [AB5500_DEVID_USB] = {
+ .name = "ab5500-usb",
+ .id = AB5500_DEVID_USB,
+ .num_resources = 36,
+ .resources = (struct resource[]) {
+ {
+ .name = "Link_Update",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(22, 1),
+ .end = AB5500_IRQ(22, 1),
+ },
+ {
+ .name = "DCIO",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(8, 3),
+ .end = AB5500_IRQ(8, 4),
+ },
+ {
+ .name = "VBUS_R",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(8, 5),
+ .end = AB5500_IRQ(8, 5),
+ },
+ {
+ .name = "VBUS_F",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(8, 6),
+ .end = AB5500_IRQ(8, 6),
+ },
+ {
+ .name = "CHGstate_10_PCVBUSchg",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(8, 7),
+ .end = AB5500_IRQ(8, 7),
+ },
+ {
+ .name = "DCIOreverse_ovc",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(9, 0),
+ .end = AB5500_IRQ(9, 0),
+ },
+ {
+ .name = "USBCharDetDone",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(9, 1),
+ .end = AB5500_IRQ(9, 1),
+ },
+ {
+ .name = "DCIO_no_limit",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(9, 2),
+ .end = AB5500_IRQ(9, 2),
+ },
+ {
+ .name = "USB_suspend",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(9, 3),
+ .end = AB5500_IRQ(9, 3),
+ },
+ {
+ .name = "DCIOreverse_fwdcurrent",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(9, 4),
+ .end = AB5500_IRQ(9, 4),
+ },
+ {
+ .name = "Vbus_Imeasmax_change",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(9, 5),
+ .end = AB5500_IRQ(9, 6),
+ },
+ {
+ .name = "OVV",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(14, 5),
+ .end = AB5500_IRQ(14, 5),
+ },
+ {
+ .name = "USBcharging_NOTok",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(15, 3),
+ .end = AB5500_IRQ(15, 3),
+ },
+ {
+ .name = "usb_adp_sensoroff",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(15, 6),
+ .end = AB5500_IRQ(15, 6),
+ },
+ {
+ .name = "usb_adp_probeplug",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(15, 7),
+ .end = AB5500_IRQ(15, 7),
+ },
+ {
+ .name = "usb_adp_sinkerror",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(16, 0),
+ .end = AB5500_IRQ(16, 6),
+ },
+ {
+ .name = "usb_adp_sourceerror",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(16, 1),
+ .end = AB5500_IRQ(16, 1),
+ },
+ {
+ .name = "usb_idgnd_r",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(16, 2),
+ .end = AB5500_IRQ(16, 2),
+ },
+ {
+ .name = "usb_idgnd_f",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(16, 3),
+ .end = AB5500_IRQ(16, 3),
+ },
+ {
+ .name = "usb_iddetR1",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(16, 4),
+ .end = AB5500_IRQ(16, 5),
+ },
+ {
+ .name = "usb_iddetR2",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(16, 6),
+ .end = AB5500_IRQ(16, 7),
+ },
+ {
+ .name = "usb_iddetR3",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(17, 0),
+ .end = AB5500_IRQ(17, 1),
+ },
+ {
+ .name = "usb_iddetR4",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(17, 2),
+ .end = AB5500_IRQ(17, 3),
+ },
+ {
+ .name = "CharTempWindowOk",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(17, 7),
+ .end = AB5500_IRQ(18, 0),
+ },
+ {
+ .name = "USB_SprDetect",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(18, 1),
+ .end = AB5500_IRQ(18, 1),
+ },
+ {
+ .name = "usb_adp_probe_unplug",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(18, 2),
+ .end = AB5500_IRQ(18, 2),
+ },
+ {
+ .name = "VBUSChDrop",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(18, 3),
+ .end = AB5500_IRQ(18, 4),
+ },
+ {
+ .name = "dcio_char_rec_done",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(18, 5),
+ .end = AB5500_IRQ(18, 5),
+ },
+ {
+ .name = "Charging_stopped_by_temp",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(18, 6),
+ .end = AB5500_IRQ(18, 6),
+ },
+ {
+ .name = "CHGstate_11_SafeModeVBUS",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(21, 1),
+ .end = AB5500_IRQ(21, 2),
+ },
+ {
+ .name = "CHGstate_12_comletedVBUS",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(21, 2),
+ .end = AB5500_IRQ(21, 2),
+ },
+ {
+ .name = "CHGstate_13_completedVBUS",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(21, 3),
+ .end = AB5500_IRQ(21, 3),
+ },
+ {
+ .name = "CHGstate_14_FullChgDCIO",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(21, 4),
+ .end = AB5500_IRQ(21, 4),
+ },
+ {
+ .name = "CHGstate_15_SafeModeDCIO",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(21, 5),
+ .end = AB5500_IRQ(21, 5),
+ },
+ {
+ .name = "CHGstate_16_OFFsuspendDCIO",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(21, 6),
+ .end = AB5500_IRQ(21, 6),
+ },
+ {
+ .name = "CHGstate_17_completedDCIO",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(21, 7),
+ .end = AB5500_IRQ(21, 7),
+ },
+ },
+ },
+ [AB5500_DEVID_OTP] = {
+ .name = "ab5500-otp",
+ .id = AB5500_DEVID_OTP,
+ },
+ [AB5500_DEVID_VIDEO] = {
+ .name = "ab5500-video",
+ .id = AB5500_DEVID_VIDEO,
+ .num_resources = 1,
+ .resources = (struct resource[]) {
+ {
+ .name = "plugTVdet",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(22, 2),
+ .end = AB5500_IRQ(22, 2),
+ },
+ },
+ },
+ [AB5500_DEVID_DBIECI] = {
+ .name = "ab5500-dbieci",
+ .id = AB5500_DEVID_DBIECI,
+ .num_resources = 10,
+ .resources = (struct resource[]) {
+ {
+ .name = "COLL",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(14, 0),
+ .end = AB5500_IRQ(14, 0),
+ },
+ {
+ .name = "RESERR",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(14, 1),
+ .end = AB5500_IRQ(14, 1),
+ },
+ {
+ .name = "FRAERR",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(14, 2),
+ .end = AB5500_IRQ(14, 2),
+ },
+ {
+ .name = "COMERR",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(14, 3),
+ .end = AB5500_IRQ(14, 3),
+ },
+ {
+ .name = "BSI_indicator",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(14, 4),
+ .end = AB5500_IRQ(14, 4),
+ },
+ {
+ .name = "SPDSET",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(14, 6),
+ .end = AB5500_IRQ(14, 6),
+ },
+ {
+ .name = "DSENT",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(14, 7),
+ .end = AB5500_IRQ(14, 7),
+ },
+ {
+ .name = "DREC",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(15, 0),
+ .end = AB5500_IRQ(15, 0),
+ },
+ {
+ .name = "ACCINT",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(15, 1),
+ .end = AB5500_IRQ(15, 1),
+ },
+ {
+ .name = "NOPINT",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(15, 2),
+ .end = AB5500_IRQ(15, 2),
+ },
+ },
+ },
+ [AB5500_DEVID_ONSWA] = {
+ .name = "ab5500-onswa",
+ .id = AB5500_DEVID_ONSWA,
+ .num_resources = 2,
+ .resources = (struct resource[]) {
+ {
+ .name = "ONSWAn_rising",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(1, 3),
+ .end = AB5500_IRQ(1, 3),
+ },
+ {
+ .name = "ONSWAn_falling",
+ .flags = IORESOURCE_IRQ,
+ .start = AB5500_IRQ(1, 4),
+ .end = AB5500_IRQ(1, 4),
+ },
+ },
+ },
+};
+
+/*
+ * Functionality for getting/setting register values.
+ */
+int ab5500_get_register_interruptible_raw(struct ab5500 *ab,
+ u8 bank, u8 reg,
+ u8 *value)
+{
+ int err;
+
+ if (bank >= AB5500_NUM_BANKS)
+ return -EINVAL;
+
+ err = mutex_lock_interruptible(&ab->access_mutex);
+ if (err)
+ return err;
+ err = db5500_prcmu_abb_read(bankinfo[bank].slave_addr, reg, value, 1);
+
+ mutex_unlock(&ab->access_mutex);
+ return err;
+}
+
+static int get_register_page_interruptible(struct ab5500 *ab, u8 bank,
+ u8 first_reg, u8 *regvals, u8 numregs)
+{
+ int err;
+
+ if (bank >= AB5500_NUM_BANKS)
+ return -EINVAL;
+
+ err = mutex_lock_interruptible(&ab->access_mutex);
+ if (err)
+ return err;
+
+ while (numregs) {
+ /* The hardware limit for get page is 4 */
+ u8 curnum = min_t(u8, numregs, 4u);
+
+ err = db5500_prcmu_abb_read(bankinfo[bank].slave_addr,
+ first_reg, regvals, curnum);
+ if (err)
+ goto out;
+
+ numregs -= curnum;
+ first_reg += curnum;
+ regvals += curnum;
+ }
+
+out:
+ mutex_unlock(&ab->access_mutex);
+ return err;
+}
+
+int ab5500_mask_and_set_register_interruptible_raw(struct ab5500 *ab, u8 bank,
+ u8 reg, u8 bitmask, u8 bitvalues)
+{
+ int err = 0;
+
+ if (bank >= AB5500_NUM_BANKS)
+ return -EINVAL;
+
+ if (bitmask) {
+ u8 buf;
+
+ err = mutex_lock_interruptible(&ab->access_mutex);
+ if (err)
+ return err;
+
+ if (bitmask == 0xFF) /* No need to read in this case. */
+ buf = bitvalues;
+ else { /* Read and modify the register value. */
+ err = db5500_prcmu_abb_read(bankinfo[bank].slave_addr,
+ reg, &buf, 1);
+ if (err)
+ return err;
+
+ buf = ((~bitmask & buf) | (bitmask & bitvalues));
+ }
+ /* Write the new value. */
+ err = db5500_prcmu_abb_write(bankinfo[bank].slave_addr, reg,
+ &buf, 1);
+
+ mutex_unlock(&ab->access_mutex);
+ }
+ return err;
+}
+
+static int
+set_register_interruptible(struct ab5500 *ab, u8 bank, u8 reg, u8 value)
+{
+ return ab5500_mask_and_set_register_interruptible_raw(ab, bank, reg,
+ 0xff, value);
+}
+
+/*
+ * Read/write permission checking functions.
+ */
+static const struct ab5500_i2c_ranges *get_bankref(u8 devid, u8 bank)
+{
+ u8 i;
+
+ if (devid < AB5500_NUM_DEVICES) {
+ for (i = 0; i < ab5500_bank_ranges[devid].nbanks; i++) {
+ if (ab5500_bank_ranges[devid].bank[i].bankid == bank)
+ return &ab5500_bank_ranges[devid].bank[i];
+ }
+ }
+ return NULL;
+}
+
+static bool page_write_allowed(u8 devid, u8 bank, u8 first_reg, u8 last_reg)
+{
+ u8 i; /* range loop index */
+ const struct ab5500_i2c_ranges *bankref;
+
+ bankref = get_bankref(devid, bank);
+ if (bankref == NULL || last_reg < first_reg)
+ return false;
+
+ for (i = 0; i < bankref->nranges; i++) {
+ if (first_reg < bankref->range[i].first)
+ break;
+ if ((last_reg <= bankref->range[i].last) &&
+ (bankref->range[i].perm & AB5500_PERM_WR))
+ return true;
+ }
+ return false;
+}
+
+static bool reg_write_allowed(u8 devid, u8 bank, u8 reg)
+{
+ return page_write_allowed(devid, bank, reg, reg);
+}
+
+static bool page_read_allowed(u8 devid, u8 bank, u8 first_reg, u8 last_reg)
+{
+ u8 i;
+ const struct ab5500_i2c_ranges *bankref;
+
+ bankref = get_bankref(devid, bank);
+ if (bankref == NULL || last_reg < first_reg)
+ return false;
+
+
+ /* Find the range (if it exists in the list) that includes first_reg. */
+ for (i = 0; i < bankref->nranges; i++) {
+ if (first_reg < bankref->range[i].first)
+ return false;
+ if (first_reg <= bankref->range[i].last)
+ break;
+ }
+ /* Make sure that the entire range up to and including last_reg is
+ * readable. This may span several of the ranges in the list.
+ */
+ while ((i < bankref->nranges) &&
+ (bankref->range[i].perm & AB5500_PERM_RD)) {
+ if (last_reg <= bankref->range[i].last)
+ return true;
+ if ((++i >= bankref->nranges) ||
+ (bankref->range[i].first !=
+ (bankref->range[i - 1].last + 1))) {
+ break;
+ }
+ }
+ return false;
+}
+
+static bool reg_read_allowed(u8 devid, u8 bank, u8 reg)
+{
+ return page_read_allowed(devid, bank, reg, reg);
+}
+
+
+/*
+ * The exported register access functionality.
+ */
+static int ab5500_get_chip_id(struct device *dev)
+{
+ struct ab5500 *ab = dev_get_drvdata(dev->parent);
+
+ return (int)ab->chip_id;
+}
+
+static int ab5500_mask_and_set_register_interruptible(struct device *dev,
+ u8 bank, u8 reg, u8 bitmask, u8 bitvalues)
+{
+ struct ab5500 *ab;
+ struct platform_device *pdev = to_platform_device(dev);
+
+ if ((AB5500_NUM_BANKS <= bank) ||
+ !reg_write_allowed(pdev->id, bank, reg))
+ return -EINVAL;
+
+ ab = dev_get_drvdata(dev->parent);
+ return ab5500_mask_and_set_register_interruptible_raw(ab, bank, reg,
+ bitmask, bitvalues);
+}
+
+static int ab5500_set_register_interruptible(struct device *dev, u8 bank,
+ u8 reg, u8 value)
+{
+ return ab5500_mask_and_set_register_interruptible(dev, bank, reg, 0xFF,
+ value);
+}
+
+static int ab5500_get_register_interruptible(struct device *dev, u8 bank,
+ u8 reg, u8 *value)
+{
+ struct ab5500 *ab;
+ struct platform_device *pdev = to_platform_device(dev);
+
+ if ((AB5500_NUM_BANKS <= bank) ||
+ !reg_read_allowed(pdev->id, bank, reg))
+ return -EINVAL;
+
+ ab = dev_get_drvdata(dev->parent);
+ return ab5500_get_register_interruptible_raw(ab, bank, reg, value);
+}
+
+static int ab5500_get_register_page_interruptible(struct device *dev, u8 bank,
+ u8 first_reg, u8 *regvals, u8 numregs)
+{
+ struct ab5500 *ab;
+ struct platform_device *pdev = to_platform_device(dev);
+
+ if ((AB5500_NUM_BANKS <= bank) ||
+ !page_read_allowed(pdev->id, bank,
+ first_reg, (first_reg + numregs - 1)))
+ return -EINVAL;
+
+ ab = dev_get_drvdata(dev->parent);
+ return get_register_page_interruptible(ab, bank, first_reg, regvals,
+ numregs);
+}
+
+static int
+ab5500_event_registers_startup_state_get(struct device *dev, u8 *event)
+{
+ struct ab5500 *ab;
+
+ ab = dev_get_drvdata(dev->parent);
+ if (!ab->startup_events_read)
+ return -EAGAIN; /* Try again later */
+
+ memcpy(event, ab->startup_events, AB5500_NUM_EVENT_REG);
+ return 0;
+}
+
+static struct abx500_ops ab5500_ops = {
+ .get_chip_id = ab5500_get_chip_id,
+ .get_register = ab5500_get_register_interruptible,
+ .set_register = ab5500_set_register_interruptible,
+ .get_register_page = ab5500_get_register_page_interruptible,
+ .set_register_page = NULL,
+ .mask_and_set_register = ab5500_mask_and_set_register_interruptible,
+ .event_registers_startup_state_get =
+ ab5500_event_registers_startup_state_get,
+ .startup_irq_enabled = NULL,
+};
+
+/*
+ * ab5500_setup : Basic set-up, datastructure creation/destruction
+ * and I2C interface.This sets up a default config
+ * in the AB5500 chip so that it will work as expected.
+ * @ab : Pointer to ab5500 structure
+ * @settings : Pointer to struct abx500_init_settings
+ * @size : Size of init data
+ */
+static int __init ab5500_setup(struct ab5500 *ab,
+ struct abx500_init_settings *settings, unsigned int size)
+{
+ int err = 0;
+ int i;
+
+ for (i = 0; i < size; i++) {
+ err = ab5500_mask_and_set_register_interruptible_raw(ab,
+ settings[i].bank,
+ settings[i].reg,
+ 0xFF, settings[i].setting);
+ if (err)
+ goto exit_no_setup;
+
+ /* If event mask register update the event mask in ab5500 */
+ if ((settings[i].bank == AB5500_BANK_IT) &&
+ (AB5500_MASK_BASE <= settings[i].reg) &&
+ (settings[i].reg <= AB5500_MASK_END)) {
+ ab->mask[settings[i].reg - AB5500_MASK_BASE] =
+ settings[i].setting;
+ }
+ }
+exit_no_setup:
+ return err;
+}
+
+struct ab_family_id {
+ u8 id;
+ char *name;
+};
+
+static const struct ab_family_id ids[] __initdata = {
+ /* AB5500 */
+ {
+ .id = AB5500_1_0,
+ .name = "1.0"
+ },
+ {
+ .id = AB5500_1_1,
+ .name = "1.1"
+ },
+ /* Terminator */
+ {
+ .id = 0x00,
+ }
+};
+
+static int __init ab5500_probe(struct platform_device *pdev)
+{
+ struct ab5500 *ab;
+ struct ab5500_platform_data *ab5500_plf_data =
+ pdev->dev.platform_data;
+ int err;
+ int i;
+
+ ab = kzalloc(sizeof(struct ab5500), GFP_KERNEL);
+ if (!ab) {
+ dev_err(&pdev->dev,
+ "could not allocate ab5500 device\n");
+ return -ENOMEM;
+ }
+
+ /* Initialize data structure */
+ mutex_init(&ab->access_mutex);
+ mutex_init(&ab->irq_lock);
+ ab->dev = &pdev->dev;
+
+ platform_set_drvdata(pdev, ab);
+
+ /* Read chip ID register */
+ err = ab5500_get_register_interruptible_raw(ab,
+ AB5500_BANK_VIT_IO_I2C_CLK_TST_OTP,
+ AB5500_CHIP_ID, &ab->chip_id);
+ if (err) {
+ dev_err(&pdev->dev, "could not communicate with the analog "
+ "baseband chip\n");
+ goto exit_no_detect;
+ }
+
+ for (i = 0; ids[i].id != 0x0; i++) {
+ if (ids[i].id == ab->chip_id) {
+ snprintf(&ab->chip_name[0], sizeof(ab->chip_name) - 1,
+ "AB5500 %s", ids[i].name);
+ break;
+ }
+ }
+ if (ids[i].id == 0x0) {
+ dev_err(&pdev->dev, "unknown analog baseband chip id: 0x%x\n",
+ ab->chip_id);
+ dev_err(&pdev->dev, "driver not started!\n");
+ goto exit_no_detect;
+ }
+
+ /* Clear and mask all interrupts */
+ for (i = 0; i < AB5500_NUM_IRQ_REGS; i++) {
+ u8 latchreg = AB5500_IT_LATCH0_REG + i;
+ u8 maskreg = AB5500_IT_MASK0_REG + i;
+ u8 val;
+
+ ab5500_get_register_interruptible_raw(ab, AB5500_BANK_IT,
+ latchreg, &val);
+ set_register_interruptible(ab, AB5500_BANK_IT, maskreg, 0xff);
+ ab->mask[i] = ab->oldmask[i] = 0xff;
+ }
+
+ err = abx500_register_ops(&pdev->dev, &ab5500_ops);
+ if (err) {
+ dev_err(&pdev->dev, "ab5500_register ops error\n");
+ goto exit_no_detect;
+ }
+
+ /* Set up and register the platform devices. */
+ for (i = 0; i < AB5500_NUM_DEVICES; i++) {
+ ab5500_devs[i].platform_data = ab5500_plf_data->dev_data[i];
+ ab5500_devs[i].pdata_size =
+ sizeof(ab5500_plf_data->dev_data[i]);
+ }
+
+ err = mfd_add_devices(&pdev->dev, 0, ab5500_devs,
+ ARRAY_SIZE(ab5500_devs), NULL,
+ ab5500_plf_data->irq.base);
+ if (err) {
+ dev_err(&pdev->dev, "ab5500_mfd_add_device error\n");
+ goto exit_no_detect;
+ }
+
+ err = ab5500_setup(ab, ab5500_plf_data->init_settings,
+ ab5500_plf_data->init_settings_sz);
+ if (err) {
+ dev_err(&pdev->dev, "ab5500_setup error\n");
+ goto exit_no_detect;
+ }
+
+ ab5500_setup_debugfs(ab);
+
+ dev_info(&pdev->dev, "detected AB chip: %s\n", &ab->chip_name[0]);
+ return 0;
+
+exit_no_detect:
+ kfree(ab);
+ return err;
+}
+
+static int __exit ab5500_remove(struct platform_device *pdev)
+{
+ struct ab5500 *ab = platform_get_drvdata(pdev);
+
+ ab5500_remove_debugfs();
+ mfd_remove_devices(&pdev->dev);
+ kfree(ab);
+ return 0;
+}
+
+static struct platform_driver ab5500_driver = {
+ .driver = {
+ .name = "ab5500-core",
+ .owner = THIS_MODULE,
+ },
+ .remove = __exit_p(ab5500_remove),
+};
+
+static int __init ab5500_core_init(void)
+{
+ return platform_driver_probe(&ab5500_driver, ab5500_probe);
+}
+
+static void __exit ab5500_core_exit(void)
+{
+ platform_driver_unregister(&ab5500_driver);
+}
+
+subsys_initcall(ab5500_core_init);
+module_exit(ab5500_core_exit);
+
+MODULE_AUTHOR("Mattias Wallin <mattias.wallin@stericsson.com>");
+MODULE_DESCRIPTION("AB5500 core driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/ab5500-core.h b/drivers/mfd/ab5500-core.h
new file mode 100644
index 0000000..63b30b1
--- /dev/null
+++ b/drivers/mfd/ab5500-core.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (C) 2011 ST-Ericsson
+ * License terms: GNU General Public License (GPL) version 2
+ * Shared definitions and data structures for the AB5500 MFD driver
+ */
+
+/* Read/write operation values. */
+#define AB5500_PERM_RD (0x01)
+#define AB5500_PERM_WR (0x02)
+
+/* Read/write permissions. */
+#define AB5500_PERM_RO (AB5500_PERM_RD)
+#define AB5500_PERM_RW (AB5500_PERM_RD | AB5500_PERM_WR)
+
+#define AB5500_MASK_BASE (0x60)
+#define AB5500_MASK_END (0x79)
+#define AB5500_CHIP_ID (0x20)
+
+/**
+ * struct ab5500_reg_range
+ * @first: the first address of the range
+ * @last: the last address of the range
+ * @perm: access permissions for the range
+ */
+struct ab5500_reg_range {
+ u8 first;
+ u8 last;
+ u8 perm;
+};
+
+/**
+ * struct ab5500_i2c_ranges
+ * @count: the number of ranges in the list
+ * @range: the list of register ranges
+ */
+struct ab5500_i2c_ranges {
+ u8 nranges;
+ u8 bankid;
+ const struct ab5500_reg_range *range;
+};
+
+/**
+ * struct ab5500_i2c_banks
+ * @count: the number of ranges in the list
+ * @range: the list of register ranges
+ */
+struct ab5500_i2c_banks {
+ u8 nbanks;
+ const struct ab5500_i2c_ranges *bank;
+};
+
+/**
+ * struct ab5500_bank
+ * @slave_addr: I2C slave_addr found in AB5500 specification
+ * @name: Documentation name of the bank. For reference
+ */
+struct ab5500_bank {
+ u8 slave_addr;
+ const char *name;
+};
+
+static const struct ab5500_bank bankinfo[AB5500_NUM_BANKS] = {
+ [AB5500_BANK_VIT_IO_I2C_CLK_TST_OTP] = {
+ AB5500_ADDR_VIT_IO_I2C_CLK_TST_OTP, "VIT_IO_I2C_CLK_TST_OTP"},
+ [AB5500_BANK_VDDDIG_IO_I2C_CLK_TST] = {
+ AB5500_ADDR_VDDDIG_IO_I2C_CLK_TST, "VDDDIG_IO_I2C_CLK_TST"},
+ [AB5500_BANK_VDENC] = {AB5500_ADDR_VDENC, "VDENC"},
+ [AB5500_BANK_SIM_USBSIM] = {AB5500_ADDR_SIM_USBSIM, "SIM_USBSIM"},
+ [AB5500_BANK_LED] = {AB5500_ADDR_LED, "LED"},
+ [AB5500_BANK_ADC] = {AB5500_ADDR_ADC, "ADC"},
+ [AB5500_BANK_RTC] = {AB5500_ADDR_RTC, "RTC"},
+ [AB5500_BANK_STARTUP] = {AB5500_ADDR_STARTUP, "STARTUP"},
+ [AB5500_BANK_DBI_ECI] = {AB5500_ADDR_DBI_ECI, "DBI-ECI"},
+ [AB5500_BANK_CHG] = {AB5500_ADDR_CHG, "CHG"},
+ [AB5500_BANK_FG_BATTCOM_ACC] = {
+ AB5500_ADDR_FG_BATTCOM_ACC, "FG_BATCOM_ACC"},
+ [AB5500_BANK_USB] = {AB5500_ADDR_USB, "USB"},
+ [AB5500_BANK_IT] = {AB5500_ADDR_IT, "IT"},
+ [AB5500_BANK_VIBRA] = {AB5500_ADDR_VIBRA, "VIBRA"},
+ [AB5500_BANK_AUDIO_HEADSETUSB] = {
+ AB5500_ADDR_AUDIO_HEADSETUSB, "AUDIO_HEADSETUSB"},
+};
+
+int ab5500_get_register_interruptible_raw(struct ab5500 *ab, u8 bank, u8 reg,
+ u8 *value);
+int ab5500_mask_and_set_register_interruptible_raw(struct ab5500 *ab, u8 bank,
+ u8 reg, u8 bitmask, u8 bitvalues);
diff --git a/drivers/mfd/ab5500-debugfs.c b/drivers/mfd/ab5500-debugfs.c
new file mode 100644
index 0000000..6be1fe6
--- /dev/null
+++ b/drivers/mfd/ab5500-debugfs.c
@@ -0,0 +1,806 @@
+/*
+ * Copyright (C) 2011 ST-Ericsson
+ * License terms: GNU General Public License (GPL) version 2
+ * Debugfs support for the AB5500 MFD driver
+ */
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/mfd/ab5500/ab5500.h>
+#include <linux/mfd/abx500.h>
+#include <linux/uaccess.h>
+
+#include "ab5500-core.h"
+#include "ab5500-debugfs.h"
+
+static struct ab5500_i2c_ranges ab5500_reg_ranges[AB5500_NUM_BANKS] = {
+ [AB5500_BANK_LED] = {
+ .bankid = AB5500_BANK_LED,
+ .nranges = 1,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x0C,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_ADC] = {
+ .bankid = AB5500_BANK_ADC,
+ .nranges = 6,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x1F,
+ .last = 0x22,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x23,
+ .last = 0x24,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x26,
+ .last = 0x2D,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x2F,
+ .last = 0x34,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x37,
+ .last = 0x57,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x58,
+ .last = 0x58,
+ .perm = AB5500_PERM_RO,
+ },
+ },
+ },
+ [AB5500_BANK_RTC] = {
+ .bankid = AB5500_BANK_RTC,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x04,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x06,
+ .last = 0x0C,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_STARTUP] = {
+ .bankid = AB5500_BANK_STARTUP,
+ .nranges = 12,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x01,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x1F,
+ .last = 0x1F,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x2E,
+ .last = 0x2E,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x2F,
+ .last = 0x30,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x50,
+ .last = 0x51,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x60,
+ .last = 0x61,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x66,
+ .last = 0x8A,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x8C,
+ .last = 0x96,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xAA,
+ .last = 0xB4,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xB7,
+ .last = 0xBF,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xC1,
+ .last = 0xCA,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xD3,
+ .last = 0xE0,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_DBI_ECI] = {
+ .bankid = AB5500_BANK_DBI_ECI,
+ .nranges = 3,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x07,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x10,
+ .last = 0x10,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x13,
+ .last = 0x13,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_CHG] = {
+ .bankid = AB5500_BANK_CHG,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x11,
+ .last = 0x11,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x12,
+ .last = 0x1B,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_FG_BATTCOM_ACC] = {
+ .bankid = AB5500_BANK_FG_BATTCOM_ACC,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x0B,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x0C,
+ .last = 0x10,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_USB] = {
+ .bankid = AB5500_BANK_USB,
+ .nranges = 12,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x01,
+ .last = 0x01,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x80,
+ .last = 0x83,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x87,
+ .last = 0x8A,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x8B,
+ .last = 0x8B,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x91,
+ .last = 0x92,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x93,
+ .last = 0x93,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x94,
+ .last = 0x94,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xA8,
+ .last = 0xB0,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xB2,
+ .last = 0xB2,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xB4,
+ .last = 0xBC,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xBF,
+ .last = 0xBF,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0xC1,
+ .last = 0xC5,
+ .perm = AB5500_PERM_RO,
+ },
+ },
+ },
+ [AB5500_BANK_IT] = {
+ .bankid = AB5500_BANK_IT,
+ .nranges = 4,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x02,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x20,
+ .last = 0x36,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x40,
+ .last = 0x56,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x60,
+ .last = 0x76,
+ .perm = AB5500_PERM_RO,
+ },
+ },
+ },
+ [AB5500_BANK_VDDDIG_IO_I2C_CLK_TST] = {
+ .bankid = AB5500_BANK_VDDDIG_IO_I2C_CLK_TST,
+ .nranges = 7,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x02,
+ .last = 0x02,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x12,
+ .last = 0x12,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x30,
+ .last = 0x34,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x40,
+ .last = 0x44,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x50,
+ .last = 0x54,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x60,
+ .last = 0x64,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x70,
+ .last = 0x74,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_VIT_IO_I2C_CLK_TST_OTP] = {
+ .bankid = AB5500_BANK_VIT_IO_I2C_CLK_TST_OTP,
+ .nranges = 13,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x01,
+ .last = 0x01,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x02,
+ .last = 0x02,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x0D,
+ .last = 0x0F,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x1C,
+ .last = 0x1C,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x1E,
+ .last = 0x1E,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x20,
+ .last = 0x21,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x25,
+ .last = 0x25,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x28,
+ .last = 0x2A,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x30,
+ .last = 0x33,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x40,
+ .last = 0x43,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x50,
+ .last = 0x53,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x60,
+ .last = 0x63,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x70,
+ .last = 0x73,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_VIBRA] = {
+ .bankid = AB5500_BANK_VIBRA,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x10,
+ .last = 0x13,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xFE,
+ .last = 0xFE,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_AUDIO_HEADSETUSB] = {
+ .bankid = AB5500_BANK_AUDIO_HEADSETUSB,
+ .nranges = 2,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x48,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0xEB,
+ .last = 0xFB,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_SIM_USBSIM] = {
+ .bankid = AB5500_BANK_SIM_USBSIM,
+ .nranges = 1,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x13,
+ .last = 0x19,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+ [AB5500_BANK_VDENC] = {
+ .bankid = AB5500_BANK_VDENC,
+ .nranges = 12,
+ .range = (struct ab5500_reg_range[]) {
+ {
+ .first = 0x00,
+ .last = 0x08,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x09,
+ .last = 0x09,
+ .perm = AB5500_PERM_RO,
+ },
+ {
+ .first = 0x0A,
+ .last = 0x12,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x15,
+ .last = 0x19,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x1B,
+ .last = 0x21,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x27,
+ .last = 0x2C,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x41,
+ .last = 0x41,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x45,
+ .last = 0x5B,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x5D,
+ .last = 0x5D,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x69,
+ .last = 0x69,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x6C,
+ .last = 0x6D,
+ .perm = AB5500_PERM_RW,
+ },
+ {
+ .first = 0x80,
+ .last = 0x81,
+ .perm = AB5500_PERM_RW,
+ },
+ },
+ },
+};
+
+static int ab5500_registers_print(struct seq_file *s, void *p)
+{
+ struct ab5500 *ab = s->private;
+ unsigned int i;
+ u8 bank = (u8)ab->debug_bank;
+
+ seq_printf(s, "ab5500 register values:\n");
+ for (bank = 0; bank < AB5500_NUM_BANKS; bank++) {
+ seq_printf(s, " bank %u, %s (0x%x):\n", bank,
+ bankinfo[bank].name,
+ bankinfo[bank].slave_addr);
+ for (i = 0; i < ab5500_reg_ranges[bank].nranges; i++) {
+ u8 reg;
+ int err;
+
+ for (reg = ab5500_reg_ranges[bank].range[i].first;
+ reg <= ab5500_reg_ranges[bank].range[i].last;
+ reg++) {
+ u8 value;
+
+ err = ab5500_get_register_interruptible_raw(ab,
+ bank, reg,
+ &value);
+ if (err < 0) {
+ dev_err(ab->dev, "get_reg failed %d"
+ "bank 0x%x reg 0x%x\n",
+ err, bank, reg);
+ return err;
+ }
+
+ err = seq_printf(s, "[%d/0x%02X]: 0x%02X\n",
+ bank, reg, value);
+ if (err < 0) {
+ dev_err(ab->dev,
+ "seq_printf overflow\n");
+ /*
+ * Error is not returned here since
+ * the output is wanted in any case
+ */
+ return 0;
+ }
+ }
+ }
+ }
+ return 0;
+}
+
+static int ab5500_registers_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ab5500_registers_print, inode->i_private);
+}
+
+static const struct file_operations ab5500_registers_fops = {
+ .open = ab5500_registers_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .owner = THIS_MODULE,
+};
+
+static int ab5500_bank_print(struct seq_file *s, void *p)
+{
+ struct ab5500 *ab = s->private;
+
+ seq_printf(s, "%d\n", ab->debug_bank);
+ return 0;
+}
+
+static int ab5500_bank_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ab5500_bank_print, inode->i_private);
+}
+
+static ssize_t ab5500_bank_write(struct file *file,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct ab5500 *ab = ((struct seq_file *)(file->private_data))->private;
+ char buf[32];
+ int buf_size;
+ unsigned long user_bank;
+ int err;
+
+ /* Get userspace string and assure termination */
+ buf_size = min(count, (sizeof(buf) - 1));
+ if (copy_from_user(buf, user_buf, buf_size))
+ return -EFAULT;
+ buf[buf_size] = 0;
+
+ err = strict_strtoul(buf, 0, &user_bank);
+ if (err)
+ return -EINVAL;
+
+ if (user_bank >= AB5500_NUM_BANKS) {
+ dev_err(ab->dev,
+ "debugfs error input > number of banks\n");
+ return -EINVAL;
+ }
+
+ ab->debug_bank = user_bank;
+
+ return buf_size;
+}
+
+static int ab5500_address_print(struct seq_file *s, void *p)
+{
+ struct ab5500 *ab = s->private;
+
+ seq_printf(s, "0x%02X\n", ab->debug_address);
+ return 0;
+}
+
+static int ab5500_address_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ab5500_address_print, inode->i_private);
+}
+
+static ssize_t ab5500_address_write(struct file *file,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct ab5500 *ab = ((struct seq_file *)(file->private_data))->private;
+ char buf[32];
+ int buf_size;
+ unsigned long user_address;
+ int err;
+
+ /* Get userspace string and assure termination */
+ buf_size = min(count, (sizeof(buf) - 1));
+ if (copy_from_user(buf, user_buf, buf_size))
+ return -EFAULT;
+ buf[buf_size] = 0;
+
+ err = strict_strtoul(buf, 0, &user_address);
+ if (err)
+ return -EINVAL;
+ if (user_address > 0xff) {
+ dev_err(ab->dev,
+ "debugfs error input > 0xff\n");
+ return -EINVAL;
+ }
+ ab->debug_address = user_address;
+ return buf_size;
+}
+
+static int ab5500_val_print(struct seq_file *s, void *p)
+{
+ struct ab5500 *ab = s->private;
+ int err;
+ u8 regvalue;
+
+ err = ab5500_get_register_interruptible_raw(ab, (u8)ab->debug_bank,
+ (u8)ab->debug_address, ®value);
+ if (err) {
+ dev_err(ab->dev, "get_reg failed %d, bank 0x%x"
+ ", reg 0x%x\n", err, ab->debug_bank,
+ ab->debug_address);
+ return -EINVAL;
+ }
+ seq_printf(s, "0x%02X\n", regvalue);
+
+ return 0;
+}
+
+static int ab5500_val_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ab5500_val_print, inode->i_private);
+}
+
+static ssize_t ab5500_val_write(struct file *file,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct ab5500 *ab = ((struct seq_file *)(file->private_data))->private;
+ char buf[32];
+ int buf_size;
+ unsigned long user_val;
+ int err;
+ u8 regvalue;
+
+ /* Get userspace string and assure termination */
+ buf_size = min(count, (sizeof(buf)-1));
+ if (copy_from_user(buf, user_buf, buf_size))
+ return -EFAULT;
+ buf[buf_size] = 0;
+
+ err = strict_strtoul(buf, 0, &user_val);
+ if (err)
+ return -EINVAL;
+ if (user_val > 0xff) {
+ dev_err(ab->dev,
+ "debugfs error input > 0xff\n");
+ return -EINVAL;
+ }
+ err = ab5500_mask_and_set_register_interruptible_raw(
+ ab, (u8)ab->debug_bank,
+ (u8)ab->debug_address, 0xFF, (u8)user_val);
+ if (err)
+ return -EINVAL;
+
+ ab5500_get_register_interruptible_raw(ab, (u8)ab->debug_bank,
+ (u8)ab->debug_address, ®value);
+ if (err)
+ return -EINVAL;
+
+ return buf_size;
+}
+
+static const struct file_operations ab5500_bank_fops = {
+ .open = ab5500_bank_open,
+ .write = ab5500_bank_write,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .owner = THIS_MODULE,
+};
+
+static const struct file_operations ab5500_address_fops = {
+ .open = ab5500_address_open,
+ .write = ab5500_address_write,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .owner = THIS_MODULE,
+};
+
+static const struct file_operations ab5500_val_fops = {
+ .open = ab5500_val_open,
+ .write = ab5500_val_write,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .owner = THIS_MODULE,
+};
+
+static struct dentry *ab5500_dir;
+static struct dentry *ab5500_reg_file;
+static struct dentry *ab5500_bank_file;
+static struct dentry *ab5500_address_file;
+static struct dentry *ab5500_val_file;
+
+void __init ab5500_setup_debugfs(struct ab5500 *ab)
+{
+ ab->debug_bank = AB5500_BANK_VIT_IO_I2C_CLK_TST_OTP;
+ ab->debug_address = AB5500_CHIP_ID;
+
+ ab5500_dir = debugfs_create_dir("ab5500", NULL);
+ if (!ab5500_dir)
+ goto exit_no_debugfs;
+
+ ab5500_reg_file = debugfs_create_file("all-bank-registers",
+ S_IRUGO, ab5500_dir, ab, &ab5500_registers_fops);
+ if (!ab5500_reg_file)
+ goto exit_destroy_dir;
+
+ ab5500_bank_file = debugfs_create_file("register-bank",
+ (S_IRUGO | S_IWUGO), ab5500_dir, ab, &ab5500_bank_fops);
+ if (!ab5500_bank_file)
+ goto exit_destroy_reg;
+
+ ab5500_address_file = debugfs_create_file("register-address",
+ (S_IRUGO | S_IWUGO), ab5500_dir, ab, &ab5500_address_fops);
+ if (!ab5500_address_file)
+ goto exit_destroy_bank;
+
+ ab5500_val_file = debugfs_create_file("register-value",
+ (S_IRUGO | S_IWUGO), ab5500_dir, ab, &ab5500_val_fops);
+ if (!ab5500_val_file)
+ goto exit_destroy_address;
+
+ return;
+
+exit_destroy_address:
+ debugfs_remove(ab5500_address_file);
+exit_destroy_bank:
+ debugfs_remove(ab5500_bank_file);
+exit_destroy_reg:
+ debugfs_remove(ab5500_reg_file);
+exit_destroy_dir:
+ debugfs_remove(ab5500_dir);
+exit_no_debugfs:
+ dev_err(ab->dev, "failed to create debugfs entries.\n");
+ return;
+}
+
+void __exit ab5500_remove_debugfs(void)
+{
+ debugfs_remove(ab5500_val_file);
+ debugfs_remove(ab5500_address_file);
+ debugfs_remove(ab5500_bank_file);
+ debugfs_remove(ab5500_reg_file);
+ debugfs_remove(ab5500_dir);
+}
diff --git a/drivers/mfd/ab5500-debugfs.h b/drivers/mfd/ab5500-debugfs.h
new file mode 100644
index 0000000..7330a9b
--- /dev/null
+++ b/drivers/mfd/ab5500-debugfs.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2011 ST-Ericsson
+ * License terms: GNU General Public License (GPL) version 2
+ * Debugfs interface to the AB5500 core driver
+ */
+
+#ifdef CONFIG_DEBUG_FS
+
+void ab5500_setup_debugfs(struct ab5500 *ab);
+void ab5500_remove_debugfs(void);
+
+#else /* !CONFIG_DEBUG_FS */
+
+static inline void ab5500_setup_debugfs(struct ab5500 *ab)
+{
+}
+
+static inline void ab5500_remove_debugfs(void)
+{
+}
+
+#endif
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index 387705e..1e91738 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -92,6 +92,8 @@
#define AB8500_REV_REG 0x80
#define AB8500_SWITCH_OFF_STATUS 0x00
+#define AB8500_TURN_ON_STATUS 0x00
+
/*
* Map interrupt numbers to the LATCH and MASK register offsets, Interrupt
* numbers are indexed into this array with (num / 8).
@@ -293,6 +295,7 @@
.irq_bus_lock = ab8500_irq_lock,
.irq_bus_sync_unlock = ab8500_irq_sync_unlock,
.irq_mask = ab8500_irq_mask,
+ .irq_disable = ab8500_irq_mask,
.irq_unmask = ab8500_irq_unmask,
};
@@ -811,12 +814,40 @@
return sprintf(buf, "%#x\n", value);
}
+/*
+ * ab8500 has turned on due to (TURN_ON_STATUS):
+ * 0x01 PORnVbat
+ * 0x02 PonKey1dbF
+ * 0x04 PonKey2dbF
+ * 0x08 RTCAlarm
+ * 0x10 MainChDet
+ * 0x20 VbusDet
+ * 0x40 UsbIDDetect
+ * 0x80 Reserved
+ */
+static ssize_t show_turn_on_status(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int ret;
+ u8 value;
+ struct ab8500 *ab8500;
+
+ ab8500 = dev_get_drvdata(dev);
+ ret = get_register_interruptible(ab8500, AB8500_SYS_CTRL1_BLOCK,
+ AB8500_TURN_ON_STATUS, &value);
+ if (ret < 0)
+ return ret;
+ return sprintf(buf, "%#x\n", value);
+}
+
static DEVICE_ATTR(chip_id, S_IRUGO, show_chip_id, NULL);
static DEVICE_ATTR(switch_off_status, S_IRUGO, show_switch_off_status, NULL);
+static DEVICE_ATTR(turn_on_status, S_IRUGO, show_turn_on_status, NULL);
static struct attribute *ab8500_sysfs_entries[] = {
&dev_attr_chip_id.attr,
&dev_attr_switch_off_status.attr,
+ &dev_attr_turn_on_status.attr,
NULL,
};
@@ -843,11 +874,11 @@
return ret;
switch (value) {
- case AB8500_CUTEARLY:
case AB8500_CUT1P0:
case AB8500_CUT1P1:
case AB8500_CUT2P0:
case AB8500_CUT3P0:
+ case AB8500_CUT3P3:
dev_info(ab8500->dev, "detected chip, revision: %#x\n", value);
break;
default:
diff --git a/drivers/mfd/ab8500-gpadc.c b/drivers/mfd/ab8500-gpadc.c
index f16afb2..e985d17 100644
--- a/drivers/mfd/ab8500-gpadc.c
+++ b/drivers/mfd/ab8500-gpadc.c
@@ -143,12 +143,15 @@
}
EXPORT_SYMBOL(ab8500_gpadc_get);
-static int ab8500_gpadc_ad_to_voltage(struct ab8500_gpadc *gpadc, u8 input,
+/**
+ * ab8500_gpadc_ad_to_voltage() - Convert a raw ADC value to a voltage
+ */
+int ab8500_gpadc_ad_to_voltage(struct ab8500_gpadc *gpadc, u8 channel,
int ad_value)
{
int res;
- switch (input) {
+ switch (channel) {
case MAIN_CHARGER_V:
/* For some reason we don't have calibrated data */
if (!gpadc->cal_data[ADC_INPUT_VMAIN].gain) {
@@ -232,18 +235,46 @@
}
return res;
}
+EXPORT_SYMBOL(ab8500_gpadc_ad_to_voltage);
/**
* ab8500_gpadc_convert() - gpadc conversion
- * @input: analog input to be converted to digital data
+ * @channel: analog channel to be converted to digital data
*
* This function converts the selected analog i/p to digital
* data.
*/
-int ab8500_gpadc_convert(struct ab8500_gpadc *gpadc, u8 input)
+int ab8500_gpadc_convert(struct ab8500_gpadc *gpadc, u8 channel)
+{
+ int ad_value;
+ int voltage;
+
+ ad_value = ab8500_gpadc_read_raw(gpadc, channel);
+ if (ad_value < 0) {
+ dev_err(gpadc->dev, "GPADC raw value failed ch: %d\n", channel);
+ return ad_value;
+ }
+
+ voltage = ab8500_gpadc_ad_to_voltage(gpadc, channel, ad_value);
+
+ if (voltage < 0)
+ dev_err(gpadc->dev, "GPADC to voltage conversion failed ch:"
+ " %d AD: 0x%x\n", channel, ad_value);
+
+ return voltage;
+}
+EXPORT_SYMBOL(ab8500_gpadc_convert);
+
+/**
+ * ab8500_gpadc_read_raw() - gpadc read
+ * @channel: analog channel to be read
+ *
+ * This function obtains the raw ADC value, this then needs
+ * to be converted by calling ab8500_gpadc_ad_to_voltage()
+ */
+int ab8500_gpadc_read_raw(struct ab8500_gpadc *gpadc, u8 channel)
{
int ret;
- u16 data = 0;
int looplimit = 0;
u8 val, low_data, high_data;
@@ -278,9 +309,9 @@
goto out;
}
- /* Select the input source and set average samples to 16 */
+ /* Select the channel source and set average samples to 16 */
ret = abx500_set_register_interruptible(gpadc->dev, AB8500_GPADC,
- AB8500_GPADC_CTRL2_REG, (input | SW_AVG_16));
+ AB8500_GPADC_CTRL2_REG, (channel | SW_AVG_16));
if (ret < 0) {
dev_err(gpadc->dev,
"gpadc_conversion: set avg samples failed\n");
@@ -292,7 +323,7 @@
* charging current sense if it needed, ABB 3.0 needs some special
* treatment too.
*/
- switch (input) {
+ switch (channel) {
case MAIN_CHARGER_C:
case USB_CHARGER_C:
ret = abx500_mask_and_set_register_interruptible(gpadc->dev,
@@ -359,7 +390,6 @@
goto out;
}
- data = (high_data << 8) | low_data;
/* Disable GPADC */
ret = abx500_set_register_interruptible(gpadc->dev, AB8500_GPADC,
AB8500_GPADC_CTRL1_REG, DIS_GPADC);
@@ -370,8 +400,8 @@
/* Disable VTVout LDO this is required for GPADC */
regulator_disable(gpadc->regu);
mutex_unlock(&gpadc->ab8500_gpadc_lock);
- ret = ab8500_gpadc_ad_to_voltage(gpadc, input, data);
- return ret;
+
+ return (high_data << 8) | low_data;
out:
/*
@@ -385,10 +415,10 @@
regulator_disable(gpadc->regu);
mutex_unlock(&gpadc->ab8500_gpadc_lock);
dev_err(gpadc->dev,
- "gpadc_conversion: Failed to AD convert channel %d\n", input);
+ "gpadc_conversion: Failed to AD convert channel %d\n", channel);
return ret;
}
-EXPORT_SYMBOL(ab8500_gpadc_convert);
+EXPORT_SYMBOL(ab8500_gpadc_read_raw);
/**
* ab8500_bm_gpswadcconvend_handler() - isr for s/w gpadc conversion completion
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index c71ae09..3bd85bd 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -584,7 +584,7 @@
return gpiochip_remove(&asic->gpio);
}
-static int asic3_clk_enable(struct asic3 *asic, struct asic3_clk *clk)
+static void asic3_clk_enable(struct asic3 *asic, struct asic3_clk *clk)
{
unsigned long flags;
u32 cdex;
@@ -596,8 +596,6 @@
asic3_write_register(asic, ASIC3_OFFSET(CLOCK, CDEX), cdex);
}
spin_unlock_irqrestore(&asic->lock, flags);
-
- return 0;
}
static void asic3_clk_disable(struct asic3 *asic, struct asic3_clk *clk)
@@ -779,6 +777,8 @@
.name = "tmio-mmc",
.enable = asic3_mmc_enable,
.disable = asic3_mmc_disable,
+ .suspend = asic3_mmc_disable,
+ .resume = asic3_mmc_enable,
.platform_data = &asic3_mmc_data,
.pdata_size = sizeof(asic3_mmc_data),
.num_resources = ARRAY_SIZE(asic3_mmc_resources),
@@ -811,24 +811,43 @@
return 0;
}
+static int asic3_leds_suspend(struct platform_device *pdev)
+{
+ const struct mfd_cell *cell = mfd_get_cell(pdev);
+ struct asic3 *asic = dev_get_drvdata(pdev->dev.parent);
+
+ while (asic3_gpio_get(&asic->gpio, ASIC3_GPIO(C, cell->id)) != 0)
+ msleep(1);
+
+ asic3_clk_disable(asic, &asic->clocks[clock_ledn[cell->id]]);
+
+ return 0;
+}
+
static struct mfd_cell asic3_cell_leds[ASIC3_NUM_LEDS] = {
[0] = {
.name = "leds-asic3",
.id = 0,
.enable = asic3_leds_enable,
.disable = asic3_leds_disable,
+ .suspend = asic3_leds_suspend,
+ .resume = asic3_leds_enable,
},
[1] = {
.name = "leds-asic3",
.id = 1,
.enable = asic3_leds_enable,
.disable = asic3_leds_disable,
+ .suspend = asic3_leds_suspend,
+ .resume = asic3_leds_enable,
},
[2] = {
.name = "leds-asic3",
.id = 2,
.enable = asic3_leds_enable,
.disable = asic3_leds_disable,
+ .suspend = asic3_leds_suspend,
+ .resume = asic3_leds_enable,
},
};
@@ -949,6 +968,7 @@
goto out_unmap;
}
+ asic->gpio.label = "asic3";
asic->gpio.base = pdata->gpio_base;
asic->gpio.ngpio = ASIC3_NUM_GPIOS;
asic->gpio.get = asic3_gpio_get;
diff --git a/drivers/mfd/da903x.c b/drivers/mfd/da903x.c
index 2fadbae..1b79c37 100644
--- a/drivers/mfd/da903x.c
+++ b/drivers/mfd/da903x.c
@@ -523,7 +523,7 @@
chip->ops->read_events(chip, &tmp);
ret = request_irq(client->irq, da903x_irq_handler,
- IRQF_DISABLED | IRQF_TRIGGER_FALLING,
+ IRQF_TRIGGER_FALLING,
"da903x", chip);
if (ret) {
dev_err(&client->dev, "failed to request irq %d\n",
diff --git a/drivers/mfd/db5500-prcmu-regs.h b/drivers/mfd/db5500-prcmu-regs.h
deleted file mode 100644
index 9a8e9e4..0000000
--- a/drivers/mfd/db5500-prcmu-regs.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/*
- * Copyright (C) STMicroelectronics 2009
- * Copyright (C) ST-Ericsson SA 2010
- *
- * Author: Kumar Sanghvi <kumar.sanghvi@stericsson.com>
- * Author: Sundar Iyer <sundar.iyer@stericsson.com>
- *
- * License Terms: GNU General Public License v2
- *
- * PRCM Unit registers
- */
-
-#ifndef __MACH_PRCMU_REGS_H
-#define __MACH_PRCMU_REGS_H
-
-#include <mach/hardware.h>
-
-#define PRCM_ARM_PLLDIVPS (_PRCMU_BASE + 0x118)
-#define PRCM_ARM_PLLDIVPS_ARM_BRM_RATE 0x3f
-#define PRCM_ARM_PLLDIVPS_MAX_MASK 0xf
-
-#define PRCM_PLLARM_LOCKP (_PRCMU_BASE + 0x0a8)
-#define PRCM_PLLARM_LOCKP_PRCM_PLLARM_LOCKP3 0x2
-
-#define PRCM_ARM_CHGCLKREQ (_PRCMU_BASE + 0x114)
-#define PRCM_ARM_CHGCLKREQ_PRCM_ARM_CHGCLKREQ 0x1
-
-#define PRCM_PLLARM_ENABLE (_PRCMU_BASE + 0x98)
-#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_ENABLE 0x1
-#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_COUNTON 0x100
-
-#define PRCM_ARMCLKFIX_MGT (_PRCMU_BASE + 0x0)
-#define PRCM_A9_RESETN_CLR (_PRCMU_BASE + 0x1f4)
-#define PRCM_A9_RESETN_SET (_PRCMU_BASE + 0x1f0)
-#define PRCM_ARM_LS_CLAMP (_PRCMU_BASE + 0x30c)
-#define PRCM_SRAM_A9 (_PRCMU_BASE + 0x308)
-
-/* ARM WFI Standby signal register */
-#define PRCM_ARM_WFI_STANDBY (_PRCMU_BASE + 0x130)
-#define PRCM_IOCR (_PRCMU_BASE + 0x310)
-#define PRCM_IOCR_IOFORCE 0x1
-
-/* CPU mailbox registers */
-#define PRCM_MBOX_CPU_VAL (_PRCMU_BASE + 0x0fc)
-#define PRCM_MBOX_CPU_SET (_PRCMU_BASE + 0x100)
-#define PRCM_MBOX_CPU_CLR (_PRCMU_BASE + 0x104)
-
-/* Dual A9 core interrupt management unit registers */
-#define PRCM_A9_MASK_REQ (_PRCMU_BASE + 0x328)
-#define PRCM_A9_MASK_REQ_PRCM_A9_MASK_REQ 0x1
-
-#define PRCM_A9_MASK_ACK (_PRCMU_BASE + 0x32c)
-#define PRCM_ARMITMSK31TO0 (_PRCMU_BASE + 0x11c)
-#define PRCM_ARMITMSK63TO32 (_PRCMU_BASE + 0x120)
-#define PRCM_ARMITMSK95TO64 (_PRCMU_BASE + 0x124)
-#define PRCM_ARMITMSK127TO96 (_PRCMU_BASE + 0x128)
-#define PRCM_POWER_STATE_VAL (_PRCMU_BASE + 0x25C)
-#define PRCM_ARMITVAL31TO0 (_PRCMU_BASE + 0x260)
-#define PRCM_ARMITVAL63TO32 (_PRCMU_BASE + 0x264)
-#define PRCM_ARMITVAL95TO64 (_PRCMU_BASE + 0x268)
-#define PRCM_ARMITVAL127TO96 (_PRCMU_BASE + 0x26C)
-
-#define PRCM_HOSTACCESS_REQ (_PRCMU_BASE + 0x334)
-#define ARM_WAKEUP_MODEM 0x1
-
-#define PRCM_ARM_IT1_CLEAR (_PRCMU_BASE + 0x48C)
-#define PRCM_ARM_IT1_VAL (_PRCMU_BASE + 0x494)
-#define PRCM_HOLD_EVT (_PRCMU_BASE + 0x174)
-
-#define PRCM_ITSTATUS0 (_PRCMU_BASE + 0x148)
-#define PRCM_ITSTATUS1 (_PRCMU_BASE + 0x150)
-#define PRCM_ITSTATUS2 (_PRCMU_BASE + 0x158)
-#define PRCM_ITSTATUS3 (_PRCMU_BASE + 0x160)
-#define PRCM_ITSTATUS4 (_PRCMU_BASE + 0x168)
-#define PRCM_ITSTATUS5 (_PRCMU_BASE + 0x484)
-#define PRCM_ITCLEAR5 (_PRCMU_BASE + 0x488)
-#define PRCM_ARMIT_MASKXP70_IT (_PRCMU_BASE + 0x1018)
-
-/* System reset register */
-#define PRCM_APE_SOFTRST (_PRCMU_BASE + 0x228)
-
-/* Level shifter and clamp control registers */
-#define PRCM_MMIP_LS_CLAMP_SET (_PRCMU_BASE + 0x420)
-#define PRCM_MMIP_LS_CLAMP_CLR (_PRCMU_BASE + 0x424)
-
-/* PRCMU clock/PLL/reset registers */
-#define PRCM_PLLDSI_FREQ (_PRCMU_BASE + 0x500)
-#define PRCM_PLLDSI_ENABLE (_PRCMU_BASE + 0x504)
-#define PRCM_PLLDSI_LOCKP (_PRCMU_BASE + 0x508)
-#define PRCM_LCDCLK_MGT (_PRCMU_BASE + 0x044)
-#define PRCM_MCDECLK_MGT (_PRCMU_BASE + 0x064)
-#define PRCM_HDMICLK_MGT (_PRCMU_BASE + 0x058)
-#define PRCM_TVCLK_MGT (_PRCMU_BASE + 0x07c)
-#define PRCM_DSI_PLLOUT_SEL (_PRCMU_BASE + 0x530)
-#define PRCM_DSITVCLK_DIV (_PRCMU_BASE + 0x52C)
-#define PRCM_PLLDSI_LOCKP (_PRCMU_BASE + 0x508)
-#define PRCM_APE_RESETN_SET (_PRCMU_BASE + 0x1E4)
-#define PRCM_APE_RESETN_CLR (_PRCMU_BASE + 0x1E8)
-#define PRCM_CLKOCR (_PRCMU_BASE + 0x1CC)
-
-/* ePOD and memory power signal control registers */
-#define PRCM_EPOD_C_SET (_PRCMU_BASE + 0x410)
-#define PRCM_SRAM_LS_SLEEP (_PRCMU_BASE + 0x304)
-
-/* Debug power control unit registers */
-#define PRCM_POWER_STATE_SET (_PRCMU_BASE + 0x254)
-
-/* Miscellaneous unit registers */
-#define PRCM_DSI_SW_RESET (_PRCMU_BASE + 0x324)
-#define PRCM_GPIOCR (_PRCMU_BASE + 0x138)
-#define PRCM_GPIOCR_DBG_STM_MOD_CMD1 0x800
-#define PRCM_GPIOCR_DBG_UARTMOD_CMD0 0x1
-
-
-#endif /* __MACH_PRCMU__REGS_H */
diff --git a/drivers/mfd/db5500-prcmu.c b/drivers/mfd/db5500-prcmu.c
index 9dbb3ca..bb115b2 100644
--- a/drivers/mfd/db5500-prcmu.c
+++ b/drivers/mfd/db5500-prcmu.c
@@ -20,11 +20,11 @@
#include <linux/jiffies.h>
#include <linux/bitops.h>
#include <linux/interrupt.h>
-#include <linux/mfd/db5500-prcmu.h>
+#include <linux/mfd/dbx500-prcmu.h>
#include <mach/hardware.h>
#include <mach/irqs.h>
#include <mach/db5500-regs.h>
-#include "db5500-prcmu-regs.h"
+#include "dbx500-prcmu-regs.h"
#define _PRCM_MB_HEADER (tcdm_base + 0xFE8)
#define PRCM_REQ_MB0_HEADER (_PRCM_MB_HEADER + 0x0)
@@ -109,15 +109,18 @@
#define PRCMU_DSI_CLOCK_SETTING 0x00000128
/* TVCLK_MGT PLLSW=001 (PLLSOC0) PLLDIV=0x13, = 19.05 MHZ */
#define PRCMU_DSI_LP_CLOCK_SETTING 0x00000135
-#define PRCMU_PLLDSI_FREQ_SETTING 0x0004013C
+#define PRCMU_PLLDSI_FREQ_SETTING 0x00020121
#define PRCMU_DSI_PLLOUT_SEL_SETTING 0x00000002
-#define PRCMU_ENABLE_ESCAPE_CLOCK_DIV 0x03000101
+#define PRCMU_ENABLE_ESCAPE_CLOCK_DIV 0x03000201
#define PRCMU_DISABLE_ESCAPE_CLOCK_DIV 0x00000101
#define PRCMU_ENABLE_PLLDSI 0x00000001
#define PRCMU_DISABLE_PLLDSI 0x00000000
#define PRCMU_DSI_RESET_SW 0x00000003
+#define PRCMU_RESOUTN0_PIN 0x00000001
+#define PRCMU_RESOUTN1_PIN 0x00000002
+#define PRCMU_RESOUTN2_PIN 0x00000004
#define PRCMU_PLLDSI_LOCKP_LOCKED 0x3
@@ -315,31 +318,31 @@
r = false;
break;
}
- writel(MBOX_BIT(0), PRCM_ARM_IT1_CLEAR);
+ writel(MBOX_BIT(0), PRCM_ARM_IT1_CLR);
return r;
}
static bool read_mailbox_1(void)
{
- writel(MBOX_BIT(1), PRCM_ARM_IT1_CLEAR);
+ writel(MBOX_BIT(1), PRCM_ARM_IT1_CLR);
return false;
}
static bool read_mailbox_2(void)
{
- writel(MBOX_BIT(2), PRCM_ARM_IT1_CLEAR);
+ writel(MBOX_BIT(2), PRCM_ARM_IT1_CLR);
return false;
}
static bool read_mailbox_3(void)
{
- writel(MBOX_BIT(3), PRCM_ARM_IT1_CLEAR);
+ writel(MBOX_BIT(3), PRCM_ARM_IT1_CLR);
return false;
}
static bool read_mailbox_4(void)
{
- writel(MBOX_BIT(4), PRCM_ARM_IT1_CLEAR);
+ writel(MBOX_BIT(4), PRCM_ARM_IT1_CLR);
return false;
}
@@ -360,19 +363,19 @@
print_unknown_header_warning(5, header);
break;
}
- writel(MBOX_BIT(5), PRCM_ARM_IT1_CLEAR);
+ writel(MBOX_BIT(5), PRCM_ARM_IT1_CLR);
return false;
}
static bool read_mailbox_6(void)
{
- writel(MBOX_BIT(6), PRCM_ARM_IT1_CLEAR);
+ writel(MBOX_BIT(6), PRCM_ARM_IT1_CLR);
return false;
}
static bool read_mailbox_7(void)
{
- writel(MBOX_BIT(7), PRCM_ARM_IT1_CLEAR);
+ writel(MBOX_BIT(7), PRCM_ARM_IT1_CLR);
return false;
}
@@ -434,7 +437,7 @@
return -ENODEV;
/* Clean up the mailbox interrupts after pre-kernel code. */
- writel(ALL_MBOX_BITS, PRCM_ARM_IT1_CLEAR);
+ writel(ALL_MBOX_BITS, PRCM_ARM_IT1_CLR);
r = request_threaded_irq(IRQ_DB5500_PRCMU1, prcmu_irq_handler,
prcmu_irq_thread_fn, 0, "prcmu", NULL);
diff --git a/drivers/mfd/db8500-prcmu-regs.h b/drivers/mfd/db8500-prcmu-regs.h
deleted file mode 100644
index 3bbf04d..0000000
--- a/drivers/mfd/db8500-prcmu-regs.h
+++ /dev/null
@@ -1,166 +0,0 @@
-/*
- * Copyright (C) STMicroelectronics 2009
- * Copyright (C) ST-Ericsson SA 2010
- *
- * Author: Kumar Sanghvi <kumar.sanghvi@stericsson.com>
- * Author: Sundar Iyer <sundar.iyer@stericsson.com>
- *
- * License Terms: GNU General Public License v2
- *
- * PRCM Unit registers
- */
-#ifndef __DB8500_PRCMU_REGS_H
-#define __DB8500_PRCMU_REGS_H
-
-#include <linux/bitops.h>
-#include <mach/hardware.h>
-
-#define BITS(_start, _end) ((BIT(_end) - BIT(_start)) + BIT(_end))
-
-#define PRCM_ARM_PLLDIVPS 0x118
-#define PRCM_ARM_PLLDIVPS_ARM_BRM_RATE BITS(0, 5)
-#define PRCM_ARM_PLLDIVPS_MAX_MASK 0xF
-
-#define PRCM_PLLARM_LOCKP 0x0A8
-#define PRCM_PLLARM_LOCKP_PRCM_PLLARM_LOCKP3 BIT(1)
-
-#define PRCM_ARM_CHGCLKREQ 0x114
-#define PRCM_ARM_CHGCLKREQ_PRCM_ARM_CHGCLKREQ BIT(0)
-
-#define PRCM_PLLARM_ENABLE 0x98
-#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_ENABLE BIT(0)
-#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_COUNTON BIT(8)
-
-#define PRCM_ARMCLKFIX_MGT 0x0
-#define PRCM_A9_RESETN_CLR 0x1f4
-#define PRCM_A9_RESETN_SET 0x1f0
-#define PRCM_ARM_LS_CLAMP 0x30C
-#define PRCM_SRAM_A9 0x308
-
-/* ARM WFI Standby signal register */
-#define PRCM_ARM_WFI_STANDBY 0x130
-#define PRCM_IOCR 0x310
-#define PRCM_IOCR_IOFORCE BIT(0)
-
-/* CPU mailbox registers */
-#define PRCM_MBOX_CPU_VAL 0x0FC
-#define PRCM_MBOX_CPU_SET 0x100
-
-/* Dual A9 core interrupt management unit registers */
-#define PRCM_A9_MASK_REQ 0x328
-#define PRCM_A9_MASK_REQ_PRCM_A9_MASK_REQ BIT(0)
-
-#define PRCM_A9_MASK_ACK 0x32C
-#define PRCM_ARMITMSK31TO0 0x11C
-#define PRCM_ARMITMSK63TO32 0x120
-#define PRCM_ARMITMSK95TO64 0x124
-#define PRCM_ARMITMSK127TO96 0x128
-#define PRCM_POWER_STATE_VAL 0x25C
-#define PRCM_ARMITVAL31TO0 0x260
-#define PRCM_ARMITVAL63TO32 0x264
-#define PRCM_ARMITVAL95TO64 0x268
-#define PRCM_ARMITVAL127TO96 0x26C
-
-#define PRCM_HOSTACCESS_REQ 0x334
-#define PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ BIT(0)
-
-#define PRCM_ARM_IT1_CLR 0x48C
-#define PRCM_ARM_IT1_VAL 0x494
-
-#define PRCM_ITSTATUS0 0x148
-#define PRCM_ITSTATUS1 0x150
-#define PRCM_ITSTATUS2 0x158
-#define PRCM_ITSTATUS3 0x160
-#define PRCM_ITSTATUS4 0x168
-#define PRCM_ITSTATUS5 0x484
-#define PRCM_ITCLEAR5 0x488
-#define PRCM_ARMIT_MASKXP70_IT 0x1018
-
-/* System reset register */
-#define PRCM_APE_SOFTRST 0x228
-
-/* Level shifter and clamp control registers */
-#define PRCM_MMIP_LS_CLAMP_SET 0x420
-#define PRCM_MMIP_LS_CLAMP_CLR 0x424
-
-/* PRCMU HW semaphore */
-#define PRCM_SEM 0x400
-#define PRCM_SEM_PRCM_SEM BIT(0)
-
-/* PRCMU clock/PLL/reset registers */
-#define PRCM_PLLDSI_FREQ 0x500
-#define PRCM_PLLDSI_ENABLE 0x504
-#define PRCM_PLLDSI_LOCKP 0x508
-#define PRCM_DSI_PLLOUT_SEL 0x530
-#define PRCM_DSITVCLK_DIV 0x52C
-#define PRCM_APE_RESETN_SET 0x1E4
-#define PRCM_APE_RESETN_CLR 0x1E8
-
-#define PRCM_TCR 0x1C8
-#define PRCM_TCR_TENSEL_MASK BITS(0, 7)
-#define PRCM_TCR_STOP_TIMERS BIT(16)
-#define PRCM_TCR_DOZE_MODE BIT(17)
-
-#define PRCM_CLKOCR 0x1CC
-#define PRCM_CLKOCR_CLKODIV0_SHIFT 0
-#define PRCM_CLKOCR_CLKODIV0_MASK BITS(0, 5)
-#define PRCM_CLKOCR_CLKOSEL0_SHIFT 6
-#define PRCM_CLKOCR_CLKOSEL0_MASK BITS(6, 8)
-#define PRCM_CLKOCR_CLKODIV1_SHIFT 16
-#define PRCM_CLKOCR_CLKODIV1_MASK BITS(16, 21)
-#define PRCM_CLKOCR_CLKOSEL1_SHIFT 22
-#define PRCM_CLKOCR_CLKOSEL1_MASK BITS(22, 24)
-#define PRCM_CLKOCR_CLK1TYPE BIT(28)
-
-#define PRCM_SGACLK_MGT 0x014
-#define PRCM_UARTCLK_MGT 0x018
-#define PRCM_MSP02CLK_MGT 0x01C
-#define PRCM_MSP1CLK_MGT 0x288
-#define PRCM_I2CCLK_MGT 0x020
-#define PRCM_SDMMCCLK_MGT 0x024
-#define PRCM_SLIMCLK_MGT 0x028
-#define PRCM_PER1CLK_MGT 0x02C
-#define PRCM_PER2CLK_MGT 0x030
-#define PRCM_PER3CLK_MGT 0x034
-#define PRCM_PER5CLK_MGT 0x038
-#define PRCM_PER6CLK_MGT 0x03C
-#define PRCM_PER7CLK_MGT 0x040
-#define PRCM_LCDCLK_MGT 0x044
-#define PRCM_BMLCLK_MGT 0x04C
-#define PRCM_HSITXCLK_MGT 0x050
-#define PRCM_HSIRXCLK_MGT 0x054
-#define PRCM_HDMICLK_MGT 0x058
-#define PRCM_APEATCLK_MGT 0x05C
-#define PRCM_APETRACECLK_MGT 0x060
-#define PRCM_MCDECLK_MGT 0x064
-#define PRCM_IPI2CCLK_MGT 0x068
-#define PRCM_DSIALTCLK_MGT 0x06C
-#define PRCM_DMACLK_MGT 0x074
-#define PRCM_B2R2CLK_MGT 0x078
-#define PRCM_TVCLK_MGT 0x07C
-#define PRCM_UNIPROCLK_MGT 0x278
-#define PRCM_SSPCLK_MGT 0x280
-#define PRCM_RNGCLK_MGT 0x284
-#define PRCM_UICCCLK_MGT 0x27C
-
-#define PRCM_CLK_MGT_CLKPLLDIV_MASK BITS(0, 4)
-#define PRCM_CLK_MGT_CLKPLLSW_MASK BITS(5, 7)
-#define PRCM_CLK_MGT_CLKEN BIT(8)
-
-/* ePOD and memory power signal control registers */
-#define PRCM_EPOD_C_SET 0x410
-#define PRCM_SRAM_LS_SLEEP 0x304
-
-/* Debug power control unit registers */
-#define PRCM_POWER_STATE_SET 0x254
-
-/* Miscellaneous unit registers */
-#define PRCM_DSI_SW_RESET 0x324
-#define PRCM_GPIOCR 0x138
-
-/* GPIOCR register */
-#define PRCM_GPIOCR_SPI2_SELECT BIT(23)
-
-#define PRCM_DDR_SUBSYS_APE_MINBW 0x438
-
-#endif /* __DB8500_PRCMU_REGS_H */
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index 02a15d7..a25ab9c 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -27,14 +27,14 @@
#include <linux/platform_device.h>
#include <linux/uaccess.h>
#include <linux/mfd/core.h>
-#include <linux/mfd/db8500-prcmu.h>
+#include <linux/mfd/dbx500-prcmu.h>
#include <linux/regulator/db8500-prcmu.h>
#include <linux/regulator/machine.h>
#include <mach/hardware.h>
#include <mach/irqs.h>
#include <mach/db8500-regs.h>
#include <mach/id.h>
-#include "db8500-prcmu-regs.h"
+#include "dbx500-prcmu-regs.h"
/* Offset for the firmware version within the TCPM */
#define PRCMU_FW_VERSION_OFFSET 0xA4
@@ -131,12 +131,14 @@
#define MB1H_REQUEST_APE_OPP_100_VOLT 0x3
#define MB1H_RELEASE_APE_OPP_100_VOLT 0x4
#define MB1H_RELEASE_USB_WAKEUP 0x5
+#define MB1H_PLL_ON_OFF 0x6
/* Mailbox 1 Requests */
#define PRCM_REQ_MB1_ARM_OPP (PRCM_REQ_MB1 + 0x0)
#define PRCM_REQ_MB1_APE_OPP (PRCM_REQ_MB1 + 0x1)
-#define PRCM_REQ_MB1_APE_OPP_100_RESTORE (PRCM_REQ_MB1 + 0x4)
-#define PRCM_REQ_MB1_ARM_OPP_100_RESTORE (PRCM_REQ_MB1 + 0x8)
+#define PRCM_REQ_MB1_PLL_ON_OFF (PRCM_REQ_MB1 + 0x4)
+#define PLL_SOC1_OFF 0x4
+#define PLL_SOC1_ON 0x8
/* Mailbox 1 ACKs */
#define PRCM_ACK_MB1_CURRENT_ARM_OPP (PRCM_ACK_MB1 + 0x0)
@@ -184,6 +186,11 @@
#define MB4H_HOTDOG 0x12
#define MB4H_HOTMON 0x13
#define MB4H_HOT_PERIOD 0x14
+#define MB4H_A9WDOG_CONF 0x16
+#define MB4H_A9WDOG_EN 0x17
+#define MB4H_A9WDOG_DIS 0x18
+#define MB4H_A9WDOG_LOAD 0x19
+#define MB4H_A9WDOG_KICK 0x20
/* Mailbox 4 Requests */
#define PRCM_REQ_MB4_DDR_ST_AP_SLEEP_IDLE (PRCM_REQ_MB4 + 0x0)
@@ -196,6 +203,13 @@
#define PRCM_REQ_MB4_HOT_PERIOD (PRCM_REQ_MB4 + 0x0)
#define HOTMON_CONFIG_LOW BIT(0)
#define HOTMON_CONFIG_HIGH BIT(1)
+#define PRCM_REQ_MB4_A9WDOG_0 (PRCM_REQ_MB4 + 0x0)
+#define PRCM_REQ_MB4_A9WDOG_1 (PRCM_REQ_MB4 + 0x1)
+#define PRCM_REQ_MB4_A9WDOG_2 (PRCM_REQ_MB4 + 0x2)
+#define PRCM_REQ_MB4_A9WDOG_3 (PRCM_REQ_MB4 + 0x3)
+#define A9WDOG_AUTO_OFF_EN BIT(7)
+#define A9WDOG_AUTO_OFF_DIS 0
+#define A9WDOG_ID_MASK 0xf
/* Mailbox 5 Requests */
#define PRCM_REQ_MB5_I2C_SLAVE_OP (PRCM_REQ_MB5 + 0x0)
@@ -412,7 +426,7 @@
static DEFINE_SPINLOCK(clk_mgt_lock);
-#define CLK_MGT_ENTRY(_name)[PRCMU_##_name] = { (PRCM_##_name##_MGT), 0 }
+#define CLK_MGT_ENTRY(_name)[PRCMU_##_name] = { (PRCM_##_name##_MGT_OFF), 0 }
struct clk_mgt clk_mgt[PRCMU_NUM_REG_CLOCKS] = {
CLK_MGT_ENTRY(SGACLK),
CLK_MGT_ENTRY(UARTCLK),
@@ -445,6 +459,35 @@
CLK_MGT_ENTRY(UICCCLK),
};
+static struct regulator *hwacc_regulator[NUM_HW_ACC];
+static struct regulator *hwacc_ret_regulator[NUM_HW_ACC];
+
+static bool hwacc_enabled[NUM_HW_ACC];
+static bool hwacc_ret_enabled[NUM_HW_ACC];
+
+static const char *hwacc_regulator_name[NUM_HW_ACC] = {
+ [HW_ACC_SVAMMDSP] = "hwacc-sva-mmdsp",
+ [HW_ACC_SVAPIPE] = "hwacc-sva-pipe",
+ [HW_ACC_SIAMMDSP] = "hwacc-sia-mmdsp",
+ [HW_ACC_SIAPIPE] = "hwacc-sia-pipe",
+ [HW_ACC_SGA] = "hwacc-sga",
+ [HW_ACC_B2R2] = "hwacc-b2r2",
+ [HW_ACC_MCDE] = "hwacc-mcde",
+ [HW_ACC_ESRAM1] = "hwacc-esram1",
+ [HW_ACC_ESRAM2] = "hwacc-esram2",
+ [HW_ACC_ESRAM3] = "hwacc-esram3",
+ [HW_ACC_ESRAM4] = "hwacc-esram4",
+};
+
+static const char *hwacc_ret_regulator_name[NUM_HW_ACC] = {
+ [HW_ACC_SVAMMDSP] = "hwacc-sva-mmdsp-ret",
+ [HW_ACC_SIAMMDSP] = "hwacc-sia-mmdsp-ret",
+ [HW_ACC_ESRAM1] = "hwacc-esram1-ret",
+ [HW_ACC_ESRAM2] = "hwacc-esram2-ret",
+ [HW_ACC_ESRAM3] = "hwacc-esram3-ret",
+ [HW_ACC_ESRAM4] = "hwacc-esram4-ret",
+};
+
/*
* Used by MCDE to setup all necessary PRCMU registers
*/
@@ -493,55 +536,51 @@
} prcmu_version;
-int prcmu_enable_dsipll(void)
+int db8500_prcmu_enable_dsipll(void)
{
int i;
unsigned int plldsifreq;
/* Clear DSIPLL_RESETN */
- writel(PRCMU_RESET_DSIPLL, (_PRCMU_BASE + PRCM_APE_RESETN_CLR));
+ writel(PRCMU_RESET_DSIPLL, PRCM_APE_RESETN_CLR);
/* Unclamp DSIPLL in/out */
- writel(PRCMU_UNCLAMP_DSIPLL, (_PRCMU_BASE + PRCM_MMIP_LS_CLAMP_CLR));
+ writel(PRCMU_UNCLAMP_DSIPLL, PRCM_MMIP_LS_CLAMP_CLR);
if (prcmu_is_u8400())
plldsifreq = PRCMU_PLLDSI_FREQ_SETTING_U8400;
else
plldsifreq = PRCMU_PLLDSI_FREQ_SETTING;
/* Set DSI PLL FREQ */
- writel(plldsifreq, (_PRCMU_BASE + PRCM_PLLDSI_FREQ));
- writel(PRCMU_DSI_PLLOUT_SEL_SETTING,
- (_PRCMU_BASE + PRCM_DSI_PLLOUT_SEL));
+ writel(plldsifreq, PRCM_PLLDSI_FREQ);
+ writel(PRCMU_DSI_PLLOUT_SEL_SETTING, PRCM_DSI_PLLOUT_SEL);
/* Enable Escape clocks */
- writel(PRCMU_ENABLE_ESCAPE_CLOCK_DIV,
- (_PRCMU_BASE + PRCM_DSITVCLK_DIV));
+ writel(PRCMU_ENABLE_ESCAPE_CLOCK_DIV, PRCM_DSITVCLK_DIV);
/* Start DSI PLL */
- writel(PRCMU_ENABLE_PLLDSI, (_PRCMU_BASE + PRCM_PLLDSI_ENABLE));
+ writel(PRCMU_ENABLE_PLLDSI, PRCM_PLLDSI_ENABLE);
/* Reset DSI PLL */
- writel(PRCMU_DSI_RESET_SW, (_PRCMU_BASE + PRCM_DSI_SW_RESET));
+ writel(PRCMU_DSI_RESET_SW, PRCM_DSI_SW_RESET);
for (i = 0; i < 10; i++) {
- if ((readl(_PRCMU_BASE + PRCM_PLLDSI_LOCKP) &
- PRCMU_PLLDSI_LOCKP_LOCKED)
+ if ((readl(PRCM_PLLDSI_LOCKP) & PRCMU_PLLDSI_LOCKP_LOCKED)
== PRCMU_PLLDSI_LOCKP_LOCKED)
break;
udelay(100);
}
/* Set DSIPLL_RESETN */
- writel(PRCMU_RESET_DSIPLL, (_PRCMU_BASE + PRCM_APE_RESETN_SET));
+ writel(PRCMU_RESET_DSIPLL, PRCM_APE_RESETN_SET);
return 0;
}
-int prcmu_disable_dsipll(void)
+int db8500_prcmu_disable_dsipll(void)
{
/* Disable dsi pll */
- writel(PRCMU_DISABLE_PLLDSI, (_PRCMU_BASE + PRCM_PLLDSI_ENABLE));
+ writel(PRCMU_DISABLE_PLLDSI, PRCM_PLLDSI_ENABLE);
/* Disable escapeclock */
- writel(PRCMU_DISABLE_ESCAPE_CLOCK_DIV,
- (_PRCMU_BASE + PRCM_DSITVCLK_DIV));
+ writel(PRCMU_DISABLE_ESCAPE_CLOCK_DIV, PRCM_DSITVCLK_DIV);
return 0;
}
-int prcmu_set_display_clocks(void)
+int db8500_prcmu_set_display_clocks(void)
{
unsigned long flags;
unsigned int dsiclk;
@@ -554,15 +593,15 @@
spin_lock_irqsave(&clk_mgt_lock, flags);
/* Grab the HW semaphore. */
- while ((readl(_PRCMU_BASE + PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
+ while ((readl(PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
cpu_relax();
- writel(dsiclk, (_PRCMU_BASE + PRCM_HDMICLK_MGT));
- writel(PRCMU_DSI_LP_CLOCK_SETTING, (_PRCMU_BASE + PRCM_TVCLK_MGT));
- writel(PRCMU_DPI_CLOCK_SETTING, (_PRCMU_BASE + PRCM_LCDCLK_MGT));
+ writel(dsiclk, PRCM_HDMICLK_MGT);
+ writel(PRCMU_DSI_LP_CLOCK_SETTING, PRCM_TVCLK_MGT);
+ writel(PRCMU_DPI_CLOCK_SETTING, PRCM_LCDCLK_MGT);
/* Release the HW semaphore. */
- writel(0, (_PRCMU_BASE + PRCM_SEM));
+ writel(0, PRCM_SEM);
spin_unlock_irqrestore(&clk_mgt_lock, flags);
@@ -578,8 +617,8 @@
unsigned long flags;
spin_lock_irqsave(&gpiocr_lock, flags);
- reg = readl(_PRCMU_BASE + PRCM_GPIOCR);
- writel(reg | PRCM_GPIOCR_SPI2_SELECT, _PRCMU_BASE + PRCM_GPIOCR);
+ reg = readl(PRCM_GPIOCR);
+ writel(reg | PRCM_GPIOCR_SPI2_SELECT, PRCM_GPIOCR);
spin_unlock_irqrestore(&gpiocr_lock, flags);
}
@@ -592,8 +631,8 @@
unsigned long flags;
spin_lock_irqsave(&gpiocr_lock, flags);
- reg = readl(_PRCMU_BASE + PRCM_GPIOCR);
- writel(reg & ~PRCM_GPIOCR_SPI2_SELECT, _PRCMU_BASE + PRCM_GPIOCR);
+ reg = readl(PRCM_GPIOCR);
+ writel(reg & ~PRCM_GPIOCR_SPI2_SELECT, PRCM_GPIOCR);
spin_unlock_irqrestore(&gpiocr_lock, flags);
}
@@ -701,7 +740,7 @@
spin_lock_irqsave(&clkout_lock, flags);
- val = readl(_PRCMU_BASE + PRCM_CLKOCR);
+ val = readl(PRCM_CLKOCR);
if (val & div_mask) {
if (div) {
if ((val & mask) != bits) {
@@ -715,7 +754,7 @@
}
}
}
- writel((bits | (val & ~mask)), (_PRCMU_BASE + PRCM_CLKOCR));
+ writel((bits | (val & ~mask)), PRCM_CLKOCR);
requests[clkout] += (div ? 1 : -1);
unlock_and_return:
@@ -724,7 +763,7 @@
return r;
}
-int prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll)
+int db8500_prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll)
{
unsigned long flags;
@@ -732,7 +771,7 @@
spin_lock_irqsave(&mb0_transfer.lock, flags);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
cpu_relax();
writeb(MB0H_POWER_STATE_TRANS, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB0));
@@ -741,7 +780,7 @@
writeb((keep_ulp_clk ? 1 : 0),
(tcdm_base + PRCM_REQ_MB0_ULP_CLOCK_STATE));
writeb(0, (tcdm_base + PRCM_REQ_MB0_DO_NOT_WFI));
- writel(MBOX_BIT(0), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(0), PRCM_MBOX_CPU_SET);
spin_unlock_irqrestore(&mb0_transfer.lock, flags);
@@ -770,18 +809,18 @@
return;
for (i = 0; i < 2; i++) {
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
cpu_relax();
writel(dbb_events, (tcdm_base + PRCM_REQ_MB0_WAKEUP_8500));
writel(abb_events, (tcdm_base + PRCM_REQ_MB0_WAKEUP_4500));
writeb(header[i], (tcdm_base + PRCM_MBOX_HEADER_REQ_MB0));
- writel(MBOX_BIT(0), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(0), PRCM_MBOX_CPU_SET);
}
last_dbb_events = dbb_events;
last_abb_events = abb_events;
}
-void prcmu_enable_wakeups(u32 wakeups)
+void db8500_prcmu_enable_wakeups(u32 wakeups)
{
unsigned long flags;
u32 bits;
@@ -802,7 +841,7 @@
spin_unlock_irqrestore(&mb0_transfer.lock, flags);
}
-void prcmu_config_abb_event_readout(u32 abb_events)
+void db8500_prcmu_config_abb_event_readout(u32 abb_events)
{
unsigned long flags;
@@ -814,7 +853,7 @@
spin_unlock_irqrestore(&mb0_transfer.lock, flags);
}
-void prcmu_get_abb_event_buffer(void __iomem **buf)
+void db8500_prcmu_get_abb_event_buffer(void __iomem **buf)
{
if (readb(tcdm_base + PRCM_ACK_MB0_READ_POINTER) & 1)
*buf = (tcdm_base + PRCM_ACK_MB0_WAKEUP_1_4500);
@@ -823,13 +862,13 @@
}
/**
- * prcmu_set_arm_opp - set the appropriate ARM OPP
+ * db8500_prcmu_set_arm_opp - set the appropriate ARM OPP
* @opp: The new ARM operating point to which transition is to be made
* Returns: 0 on success, non-zero on failure
*
* This function sets the the operating point of the ARM.
*/
-int prcmu_set_arm_opp(u8 opp)
+int db8500_prcmu_set_arm_opp(u8 opp)
{
int r;
@@ -840,14 +879,14 @@
mutex_lock(&mb1_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
cpu_relax();
writeb(MB1H_ARM_APE_OPP, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
writeb(opp, (tcdm_base + PRCM_REQ_MB1_ARM_OPP));
writeb(APE_NO_CHANGE, (tcdm_base + PRCM_REQ_MB1_APE_OPP));
- writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(1), PRCM_MBOX_CPU_SET);
wait_for_completion(&mb1_transfer.work);
if ((mb1_transfer.ack.header != MB1H_ARM_APE_OPP) ||
@@ -860,11 +899,11 @@
}
/**
- * prcmu_get_arm_opp - get the current ARM OPP
+ * db8500_prcmu_get_arm_opp - get the current ARM OPP
*
* Returns: the current ARM OPP
*/
-int prcmu_get_arm_opp(void)
+int db8500_prcmu_get_arm_opp(void)
{
return readb(tcdm_base + PRCM_ACK_MB1_CURRENT_ARM_OPP);
}
@@ -876,7 +915,7 @@
*/
int prcmu_get_ddr_opp(void)
{
- return readb(_PRCMU_BASE + PRCM_DDR_SUBSYS_APE_MINBW);
+ return readb(PRCM_DDR_SUBSYS_APE_MINBW);
}
/**
@@ -892,7 +931,7 @@
return -EINVAL;
/* Changing the DDR OPP can hang the hardware pre-v21 */
if (cpu_is_u8500v20_or_later() && !cpu_is_u8500v20())
- writeb(opp, (_PRCMU_BASE + PRCM_DDR_SUBSYS_APE_MINBW));
+ writeb(opp, PRCM_DDR_SUBSYS_APE_MINBW);
return 0;
}
@@ -909,14 +948,14 @@
mutex_lock(&mb1_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
cpu_relax();
writeb(MB1H_ARM_APE_OPP, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
writeb(ARM_NO_CHANGE, (tcdm_base + PRCM_REQ_MB1_ARM_OPP));
writeb(opp, (tcdm_base + PRCM_REQ_MB1_APE_OPP));
- writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(1), PRCM_MBOX_CPU_SET);
wait_for_completion(&mb1_transfer.work);
if ((mb1_transfer.ack.header != MB1H_ARM_APE_OPP) ||
@@ -966,12 +1005,12 @@
header = MB1H_RELEASE_APE_OPP_100_VOLT;
}
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
cpu_relax();
writeb(header, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
- writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(1), PRCM_MBOX_CPU_SET);
wait_for_completion(&mb1_transfer.work);
if ((mb1_transfer.ack.header != header) ||
@@ -995,13 +1034,13 @@
mutex_lock(&mb1_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
cpu_relax();
writeb(MB1H_RELEASE_USB_WAKEUP,
(tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
- writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(1), PRCM_MBOX_CPU_SET);
wait_for_completion(&mb1_transfer.work);
if ((mb1_transfer.ack.header != MB1H_RELEASE_USB_WAKEUP) ||
@@ -1013,15 +1052,169 @@
return r;
}
+static int request_pll(u8 clock, bool enable)
+{
+ int r = 0;
+
+ if (clock == PRCMU_PLLSOC1)
+ clock = (enable ? PLL_SOC1_ON : PLL_SOC1_OFF);
+ else
+ return -EINVAL;
+
+ mutex_lock(&mb1_transfer.lock);
+
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+ cpu_relax();
+
+ writeb(MB1H_PLL_ON_OFF, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
+ writeb(clock, (tcdm_base + PRCM_REQ_MB1_PLL_ON_OFF));
+
+ writel(MBOX_BIT(1), PRCM_MBOX_CPU_SET);
+ wait_for_completion(&mb1_transfer.work);
+
+ if (mb1_transfer.ack.header != MB1H_PLL_ON_OFF)
+ r = -EIO;
+
+ mutex_unlock(&mb1_transfer.lock);
+
+ return r;
+}
+
/**
- * prcmu_set_epod - set the state of a EPOD (power domain)
+ * prcmu_set_hwacc - set the power state of a h/w accelerator
+ * @hwacc_dev: The hardware accelerator (enum hw_acc_dev).
+ * @state: The new power state (enum hw_acc_state).
+ *
+ * This function sets the power state of a hardware accelerator.
+ * This function should not be called from interrupt context.
+ *
+ * NOTE! Deprecated, to be removed when all users switched over to use the
+ * regulator framework API.
+ */
+int prcmu_set_hwacc(u16 hwacc_dev, u8 state)
+{
+ int r = 0;
+ bool ram_retention = false;
+ bool enable, enable_ret;
+
+ /* check argument */
+ BUG_ON(hwacc_dev >= NUM_HW_ACC);
+
+ /* get state of switches */
+ enable = hwacc_enabled[hwacc_dev];
+ enable_ret = hwacc_ret_enabled[hwacc_dev];
+
+ /* set flag if retention is possible */
+ switch (hwacc_dev) {
+ case HW_ACC_SVAMMDSP:
+ case HW_ACC_SIAMMDSP:
+ case HW_ACC_ESRAM1:
+ case HW_ACC_ESRAM2:
+ case HW_ACC_ESRAM3:
+ case HW_ACC_ESRAM4:
+ ram_retention = true;
+ break;
+ }
+
+ /* check argument */
+ BUG_ON(state > HW_ON);
+ BUG_ON(state == HW_OFF_RAMRET && !ram_retention);
+
+ /* modify enable flags */
+ switch (state) {
+ case HW_OFF:
+ enable_ret = false;
+ enable = false;
+ break;
+ case HW_ON:
+ enable = true;
+ break;
+ case HW_OFF_RAMRET:
+ enable_ret = true;
+ enable = false;
+ break;
+ }
+
+ /* get regulator (lazy) */
+ if (hwacc_regulator[hwacc_dev] == NULL) {
+ hwacc_regulator[hwacc_dev] = regulator_get(NULL,
+ hwacc_regulator_name[hwacc_dev]);
+ if (IS_ERR(hwacc_regulator[hwacc_dev])) {
+ pr_err("prcmu: failed to get supply %s\n",
+ hwacc_regulator_name[hwacc_dev]);
+ r = PTR_ERR(hwacc_regulator[hwacc_dev]);
+ goto out;
+ }
+ }
+
+ if (ram_retention) {
+ if (hwacc_ret_regulator[hwacc_dev] == NULL) {
+ hwacc_ret_regulator[hwacc_dev] = regulator_get(NULL,
+ hwacc_ret_regulator_name[hwacc_dev]);
+ if (IS_ERR(hwacc_ret_regulator[hwacc_dev])) {
+ pr_err("prcmu: failed to get supply %s\n",
+ hwacc_ret_regulator_name[hwacc_dev]);
+ r = PTR_ERR(hwacc_ret_regulator[hwacc_dev]);
+ goto out;
+ }
+ }
+ }
+
+ /* set regulators */
+ if (ram_retention) {
+ if (enable_ret && !hwacc_ret_enabled[hwacc_dev]) {
+ r = regulator_enable(hwacc_ret_regulator[hwacc_dev]);
+ if (r < 0) {
+ pr_err("prcmu_set_hwacc: ret enable failed\n");
+ goto out;
+ }
+ hwacc_ret_enabled[hwacc_dev] = true;
+ }
+ }
+
+ if (enable && !hwacc_enabled[hwacc_dev]) {
+ r = regulator_enable(hwacc_regulator[hwacc_dev]);
+ if (r < 0) {
+ pr_err("prcmu_set_hwacc: enable failed\n");
+ goto out;
+ }
+ hwacc_enabled[hwacc_dev] = true;
+ }
+
+ if (!enable && hwacc_enabled[hwacc_dev]) {
+ r = regulator_disable(hwacc_regulator[hwacc_dev]);
+ if (r < 0) {
+ pr_err("prcmu_set_hwacc: disable failed\n");
+ goto out;
+ }
+ hwacc_enabled[hwacc_dev] = false;
+ }
+
+ if (ram_retention) {
+ if (!enable_ret && hwacc_ret_enabled[hwacc_dev]) {
+ r = regulator_disable(hwacc_ret_regulator[hwacc_dev]);
+ if (r < 0) {
+ pr_err("prcmu_set_hwacc: ret disable failed\n");
+ goto out;
+ }
+ hwacc_ret_enabled[hwacc_dev] = false;
+ }
+ }
+
+out:
+ return r;
+}
+EXPORT_SYMBOL(prcmu_set_hwacc);
+
+/**
+ * db8500_prcmu_set_epod - set the state of a EPOD (power domain)
* @epod_id: The EPOD to set
* @epod_state: The new EPOD state
*
* This function sets the state of a EPOD (power domain). It may not be called
* from interrupt context.
*/
-int prcmu_set_epod(u16 epod_id, u8 epod_state)
+int db8500_prcmu_set_epod(u16 epod_id, u8 epod_state)
{
int r = 0;
bool ram_retention = false;
@@ -1048,7 +1241,7 @@
mutex_lock(&mb2_transfer.lock);
/* wait for mailbox */
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(2))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(2))
cpu_relax();
/* fill in mailbox */
@@ -1058,7 +1251,7 @@
writeb(MB2H_DPS, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB2));
- writel(MBOX_BIT(2), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(2), PRCM_MBOX_CPU_SET);
/*
* The current firmware version does not handle errors correctly,
@@ -1145,13 +1338,13 @@
spin_lock_irqsave(&mb3_transfer.lock, flags);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(3))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(3))
cpu_relax();
writeb((enable ? ON : OFF), (tcdm_base + PRCM_REQ_MB3_SYSCLK_MGT));
writeb(MB3H_SYSCLK, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB3));
- writel(MBOX_BIT(3), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(3), PRCM_MBOX_CPU_SET);
spin_unlock_irqrestore(&mb3_transfer.lock, flags);
@@ -1177,7 +1370,7 @@
if (!enable)
val |= PRCM_TCR_STOP_TIMERS;
- writel(val, (_PRCMU_BASE + PRCM_TCR));
+ writel(val, PRCM_TCR);
return 0;
}
@@ -1190,7 +1383,7 @@
spin_lock_irqsave(&clk_mgt_lock, flags);
/* Grab the HW semaphore. */
- while ((readl(_PRCMU_BASE + PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
+ while ((readl(PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
cpu_relax();
val = readl(_PRCMU_BASE + clk_mgt[clock].offset);
@@ -1203,34 +1396,61 @@
writel(val, (_PRCMU_BASE + clk_mgt[clock].offset));
/* Release the HW semaphore. */
- writel(0, (_PRCMU_BASE + PRCM_SEM));
+ writel(0, PRCM_SEM);
spin_unlock_irqrestore(&clk_mgt_lock, flags);
return 0;
}
+static int request_sga_clock(u8 clock, bool enable)
+{
+ u32 val;
+ int ret;
+
+ if (enable) {
+ val = readl(PRCM_CGATING_BYPASS);
+ writel(val | PRCM_CGATING_BYPASS_ICN2, PRCM_CGATING_BYPASS);
+ }
+
+ ret = request_reg_clock(clock, enable);
+
+ if (!ret && !enable) {
+ val = readl(PRCM_CGATING_BYPASS);
+ writel(val & ~PRCM_CGATING_BYPASS_ICN2, PRCM_CGATING_BYPASS);
+ }
+
+ return ret;
+}
+
/**
- * prcmu_request_clock() - Request for a clock to be enabled or disabled.
+ * db8500_prcmu_request_clock() - Request for a clock to be enabled or disabled.
* @clock: The clock for which the request is made.
* @enable: Whether the clock should be enabled (true) or disabled (false).
*
* This function should only be used by the clock implementation.
* Do not use it from any other place!
*/
-int prcmu_request_clock(u8 clock, bool enable)
+int db8500_prcmu_request_clock(u8 clock, bool enable)
{
+ switch(clock) {
+ case PRCMU_SGACLK:
+ return request_sga_clock(clock, enable);
+ case PRCMU_TIMCLK:
+ return request_timclk(enable);
+ case PRCMU_SYSCLK:
+ return request_sysclk(enable);
+ case PRCMU_PLLSOC1:
+ return request_pll(clock, enable);
+ default:
+ break;
+ }
if (clock < PRCMU_NUM_REG_CLOCKS)
return request_reg_clock(clock, enable);
- else if (clock == PRCMU_TIMCLK)
- return request_timclk(enable);
- else if (clock == PRCMU_SYSCLK)
- return request_sysclk(enable);
- else
- return -EINVAL;
+ return -EINVAL;
}
-int prcmu_config_esram0_deep_sleep(u8 state)
+int db8500_prcmu_config_esram0_deep_sleep(u8 state)
{
if ((state > ESRAM0_DEEP_SLEEP_STATE_RET) ||
(state < ESRAM0_DEEP_SLEEP_STATE_OFF))
@@ -1238,7 +1458,7 @@
mutex_lock(&mb4_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
cpu_relax();
writeb(MB4H_MEM_ST, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB4));
@@ -1248,7 +1468,7 @@
(tcdm_base + PRCM_REQ_MB4_DDR_ST_AP_DEEP_IDLE));
writeb(state, (tcdm_base + PRCM_REQ_MB4_ESRAM0_ST));
- writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(4), PRCM_MBOX_CPU_SET);
wait_for_completion(&mb4_transfer.work);
mutex_unlock(&mb4_transfer.lock);
@@ -1260,13 +1480,13 @@
{
mutex_lock(&mb4_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
cpu_relax();
writeb(threshold, (tcdm_base + PRCM_REQ_MB4_HOTDOG_THRESHOLD));
writeb(MB4H_HOTDOG, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB4));
- writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(4), PRCM_MBOX_CPU_SET);
wait_for_completion(&mb4_transfer.work);
mutex_unlock(&mb4_transfer.lock);
@@ -1278,7 +1498,7 @@
{
mutex_lock(&mb4_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
cpu_relax();
writeb(low, (tcdm_base + PRCM_REQ_MB4_HOTMON_LOW));
@@ -1287,7 +1507,7 @@
(tcdm_base + PRCM_REQ_MB4_HOTMON_CONFIG));
writeb(MB4H_HOTMON, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB4));
- writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(4), PRCM_MBOX_CPU_SET);
wait_for_completion(&mb4_transfer.work);
mutex_unlock(&mb4_transfer.lock);
@@ -1299,13 +1519,13 @@
{
mutex_lock(&mb4_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
cpu_relax();
writew(val, (tcdm_base + PRCM_REQ_MB4_HOT_PERIOD));
writeb(MB4H_HOT_PERIOD, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB4));
- writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(4), PRCM_MBOX_CPU_SET);
wait_for_completion(&mb4_transfer.work);
mutex_unlock(&mb4_transfer.lock);
@@ -1326,6 +1546,78 @@
return config_hot_period(0xFFFF);
}
+static int prcmu_a9wdog(u8 cmd, u8 d0, u8 d1, u8 d2, u8 d3)
+{
+
+ mutex_lock(&mb4_transfer.lock);
+
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
+ cpu_relax();
+
+ writeb(d0, (tcdm_base + PRCM_REQ_MB4_A9WDOG_0));
+ writeb(d1, (tcdm_base + PRCM_REQ_MB4_A9WDOG_1));
+ writeb(d2, (tcdm_base + PRCM_REQ_MB4_A9WDOG_2));
+ writeb(d3, (tcdm_base + PRCM_REQ_MB4_A9WDOG_3));
+
+ writeb(cmd, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB4));
+
+ writel(MBOX_BIT(4), PRCM_MBOX_CPU_SET);
+ wait_for_completion(&mb4_transfer.work);
+
+ mutex_unlock(&mb4_transfer.lock);
+
+ return 0;
+
+}
+
+int prcmu_config_a9wdog(u8 num, bool sleep_auto_off)
+{
+ BUG_ON(num == 0 || num > 0xf);
+ return prcmu_a9wdog(MB4H_A9WDOG_CONF, num, 0, 0,
+ sleep_auto_off ? A9WDOG_AUTO_OFF_EN :
+ A9WDOG_AUTO_OFF_DIS);
+}
+
+int prcmu_enable_a9wdog(u8 id)
+{
+ return prcmu_a9wdog(MB4H_A9WDOG_EN, id, 0, 0, 0);
+}
+
+int prcmu_disable_a9wdog(u8 id)
+{
+ return prcmu_a9wdog(MB4H_A9WDOG_DIS, id, 0, 0, 0);
+}
+
+int prcmu_kick_a9wdog(u8 id)
+{
+ return prcmu_a9wdog(MB4H_A9WDOG_KICK, id, 0, 0, 0);
+}
+
+/*
+ * timeout is 28 bit, in ms.
+ */
+#define MAX_WATCHDOG_TIMEOUT 131000
+int prcmu_load_a9wdog(u8 id, u32 timeout)
+{
+ if (timeout > MAX_WATCHDOG_TIMEOUT)
+ /*
+ * Due to calculation bug in prcmu fw, timeouts
+ * can't be bigger than 131 seconds.
+ */
+ return -EINVAL;
+
+ return prcmu_a9wdog(MB4H_A9WDOG_LOAD,
+ (id & A9WDOG_ID_MASK) |
+ /*
+ * Put the lowest 28 bits of timeout at
+ * offset 4. Four first bits are used for id.
+ */
+ (u8)((timeout << 4) & 0xf0),
+ (u8)((timeout >> 4) & 0xff),
+ (u8)((timeout >> 12) & 0xff),
+ (u8)((timeout >> 20) & 0xff));
+}
+
/**
* prcmu_set_clock_divider() - Configure the clock divider.
* @clock: The clock for which the request is made.
@@ -1345,7 +1637,7 @@
spin_lock_irqsave(&clk_mgt_lock, flags);
/* Grab the HW semaphore. */
- while ((readl(_PRCMU_BASE + PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
+ while ((readl(PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
cpu_relax();
val = readl(_PRCMU_BASE + clk_mgt[clock].offset);
@@ -1354,7 +1646,7 @@
writel(val, (_PRCMU_BASE + clk_mgt[clock].offset));
/* Release the HW semaphore. */
- writel(0, (_PRCMU_BASE + PRCM_SEM));
+ writel(0, PRCM_SEM);
spin_unlock_irqrestore(&clk_mgt_lock, flags);
@@ -1380,7 +1672,7 @@
mutex_lock(&mb5_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
cpu_relax();
writeb(PRCMU_I2C_READ(slave), (tcdm_base + PRCM_REQ_MB5_I2C_SLAVE_OP));
@@ -1388,7 +1680,7 @@
writeb(reg, (tcdm_base + PRCM_REQ_MB5_I2C_REG));
writeb(0, (tcdm_base + PRCM_REQ_MB5_I2C_VAL));
- writel(MBOX_BIT(5), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(5), PRCM_MBOX_CPU_SET);
if (!wait_for_completion_timeout(&mb5_transfer.work,
msecs_to_jiffies(20000))) {
@@ -1426,7 +1718,7 @@
mutex_lock(&mb5_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
cpu_relax();
writeb(PRCMU_I2C_WRITE(slave), (tcdm_base + PRCM_REQ_MB5_I2C_SLAVE_OP));
@@ -1434,7 +1726,7 @@
writeb(reg, (tcdm_base + PRCM_REQ_MB5_I2C_REG));
writeb(*value, (tcdm_base + PRCM_REQ_MB5_I2C_VAL));
- writel(MBOX_BIT(5), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(5), PRCM_MBOX_CPU_SET);
if (!wait_for_completion_timeout(&mb5_transfer.work,
msecs_to_jiffies(20000))) {
@@ -1456,21 +1748,44 @@
void prcmu_ac_wake_req(void)
{
u32 val;
+ u32 status;
mutex_lock(&mb0_transfer.ac_wake_lock);
- val = readl(_PRCMU_BASE + PRCM_HOSTACCESS_REQ);
+ val = readl(PRCM_HOSTACCESS_REQ);
if (val & PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ)
goto unlock_and_return;
atomic_set(&ac_wake_req_state, 1);
- writel((val | PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ),
- (_PRCMU_BASE + PRCM_HOSTACCESS_REQ));
+retry:
+ writel((val | PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ), PRCM_HOSTACCESS_REQ);
if (!wait_for_completion_timeout(&mb0_transfer.ac_wake_work,
- msecs_to_jiffies(20000))) {
- pr_err("prcmu: %s timed out (20 s) waiting for a reply.\n",
+ msecs_to_jiffies(5000))) {
+ pr_crit("prcmu: %s timed out (5 s) waiting for a reply.\n",
+ __func__);
+ goto unlock_and_return;
+ }
+
+ /*
+ * The modem can generate an AC_WAKE_ACK, and then still go to sleep.
+ * As a workaround, we wait, and then check that the modem is indeed
+ * awake (in terms of the value of the PRCM_MOD_AWAKE_STATUS
+ * register, which may not be the whole truth).
+ */
+ udelay(400);
+ status = (readl(PRCM_MOD_AWAKE_STATUS) & BITS(0, 2));
+ if (status != (PRCM_MOD_AWAKE_STATUS_PRCM_MOD_AAPD_AWAKE |
+ PRCM_MOD_AWAKE_STATUS_PRCM_MOD_COREPD_AWAKE)) {
+ pr_err("prcmu: %s received ack, but modem not awake (0x%X).\n",
+ __func__, status);
+ udelay(1200);
+ writel(val, PRCM_HOSTACCESS_REQ);
+ if (wait_for_completion_timeout(&mb0_transfer.ac_wake_work,
+ msecs_to_jiffies(5000)))
+ goto retry;
+ pr_crit("prcmu: %s timed out (5 s) waiting for AC_SLEEP_ACK.\n",
__func__);
}
@@ -1487,16 +1802,16 @@
mutex_lock(&mb0_transfer.ac_wake_lock);
- val = readl(_PRCMU_BASE + PRCM_HOSTACCESS_REQ);
+ val = readl(PRCM_HOSTACCESS_REQ);
if (!(val & PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ))
goto unlock_and_return;
writel((val & ~PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ),
- (_PRCMU_BASE + PRCM_HOSTACCESS_REQ));
+ PRCM_HOSTACCESS_REQ);
if (!wait_for_completion_timeout(&mb0_transfer.ac_wake_work,
- msecs_to_jiffies(20000))) {
- pr_err("prcmu: %s timed out (20 s) waiting for a reply.\n",
+ msecs_to_jiffies(5000))) {
+ pr_crit("prcmu: %s timed out (5 s) waiting for a reply.\n",
__func__);
}
@@ -1506,21 +1821,32 @@
mutex_unlock(&mb0_transfer.ac_wake_lock);
}
-bool prcmu_is_ac_wake_requested(void)
+bool db8500_prcmu_is_ac_wake_requested(void)
{
return (atomic_read(&ac_wake_req_state) != 0);
}
/**
- * prcmu_system_reset - System reset
+ * db8500_prcmu_system_reset - System reset
*
- * Saves the reset reason code and then sets the APE_SOFRST register which
+ * Saves the reset reason code and then sets the APE_SOFTRST register which
* fires interrupt to fw
*/
-void prcmu_system_reset(u16 reset_code)
+void db8500_prcmu_system_reset(u16 reset_code)
{
writew(reset_code, (tcdm_base + PRCM_SW_RST_REASON));
- writel(1, (_PRCMU_BASE + PRCM_APE_SOFTRST));
+ writel(1, PRCM_APE_SOFTRST);
+}
+
+/**
+ * db8500_prcmu_get_reset_code - Retrieve SW reset reason code
+ *
+ * Retrieves the reset reason code stored by prcmu_system_reset() before
+ * last restart.
+ */
+u16 db8500_prcmu_get_reset_code(void)
+{
+ return readw(tcdm_base + PRCM_SW_RST_REASON);
}
/**
@@ -1530,11 +1856,11 @@
{
mutex_lock(&mb1_transfer.lock);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
cpu_relax();
writeb(MB1H_RESET_MODEM, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
- writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(1), PRCM_MBOX_CPU_SET);
wait_for_completion(&mb1_transfer.work);
/*
@@ -1551,11 +1877,11 @@
spin_lock_irqsave(&mb0_transfer.lock, flags);
- while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
+ while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
cpu_relax();
writeb(MB0H_READ_WAKEUP_ACK, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB0));
- writel(MBOX_BIT(0), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+ writel(MBOX_BIT(0), PRCM_MBOX_CPU_SET);
spin_unlock_irqrestore(&mb0_transfer.lock, flags);
}
@@ -1600,7 +1926,7 @@
r = false;
break;
}
- writel(MBOX_BIT(0), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+ writel(MBOX_BIT(0), PRCM_ARM_IT1_CLR);
return r;
}
@@ -1613,7 +1939,7 @@
PRCM_ACK_MB1_CURRENT_APE_OPP);
mb1_transfer.ack.ape_voltage_status = readb(tcdm_base +
PRCM_ACK_MB1_APE_VOLTAGE_STATUS);
- writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+ writel(MBOX_BIT(1), PRCM_ARM_IT1_CLR);
complete(&mb1_transfer.work);
return false;
}
@@ -1621,14 +1947,14 @@
static bool read_mailbox_2(void)
{
mb2_transfer.ack.status = readb(tcdm_base + PRCM_ACK_MB2_DPS_STATUS);
- writel(MBOX_BIT(2), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+ writel(MBOX_BIT(2), PRCM_ARM_IT1_CLR);
complete(&mb2_transfer.work);
return false;
}
static bool read_mailbox_3(void)
{
- writel(MBOX_BIT(3), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+ writel(MBOX_BIT(3), PRCM_ARM_IT1_CLR);
return false;
}
@@ -1643,6 +1969,11 @@
case MB4H_HOTDOG:
case MB4H_HOTMON:
case MB4H_HOT_PERIOD:
+ case MB4H_A9WDOG_CONF:
+ case MB4H_A9WDOG_EN:
+ case MB4H_A9WDOG_DIS:
+ case MB4H_A9WDOG_LOAD:
+ case MB4H_A9WDOG_KICK:
break;
default:
print_unknown_header_warning(4, header);
@@ -1650,7 +1981,7 @@
break;
}
- writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+ writel(MBOX_BIT(4), PRCM_ARM_IT1_CLR);
if (do_complete)
complete(&mb4_transfer.work);
@@ -1662,20 +1993,20 @@
{
mb5_transfer.ack.status = readb(tcdm_base + PRCM_ACK_MB5_I2C_STATUS);
mb5_transfer.ack.value = readb(tcdm_base + PRCM_ACK_MB5_I2C_VAL);
- writel(MBOX_BIT(5), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+ writel(MBOX_BIT(5), PRCM_ARM_IT1_CLR);
complete(&mb5_transfer.work);
return false;
}
static bool read_mailbox_6(void)
{
- writel(MBOX_BIT(6), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+ writel(MBOX_BIT(6), PRCM_ARM_IT1_CLR);
return false;
}
static bool read_mailbox_7(void)
{
- writel(MBOX_BIT(7), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+ writel(MBOX_BIT(7), PRCM_ARM_IT1_CLR);
return false;
}
@@ -1696,7 +2027,7 @@
u8 n;
irqreturn_t r;
- bits = (readl(_PRCMU_BASE + PRCM_ARM_IT1_VAL) & ALL_MBOX_BITS);
+ bits = (readl(PRCM_ARM_IT1_VAL) & ALL_MBOX_BITS);
if (unlikely(!bits))
return IRQ_NONE;
@@ -1768,7 +2099,7 @@
.irq_unmask = prcmu_irq_unmask,
};
-void __init prcmu_early_init(void)
+void __init db8500_prcmu_early_init(void)
{
unsigned int i;
@@ -1826,6 +2157,16 @@
}
}
+static void __init db8500_prcmu_init_clkforce(void)
+{
+ u32 val;
+
+ val = readl(PRCM_A9PL_FORCE_CLKEN);
+ val &= ~(PRCM_A9PL_FORCE_CLKEN_PRCM_A9PL_FORCE_CLKEN |
+ PRCM_A9PL_FORCE_CLKEN_PRCM_A9AXI_FORCE_CLKEN);
+ writel(val, (PRCM_A9PL_FORCE_CLKEN));
+}
+
/*
* Power domain switches (ePODs) modeled as regulators for the DB8500 SoC
*/
@@ -1861,7 +2202,42 @@
static struct regulator_consumer_supply db8500_b2r2_mcde_consumers[] = {
REGULATOR_SUPPLY("vsupply", "b2r2.0"),
- REGULATOR_SUPPLY("vsupply", "mcde.0"),
+ REGULATOR_SUPPLY("vsupply", "mcde"),
+};
+
+/* SVA MMDSP regulator switch */
+static struct regulator_consumer_supply db8500_svammdsp_consumers[] = {
+ REGULATOR_SUPPLY("sva-mmdsp", "cm_control"),
+};
+
+/* SVA pipe regulator switch */
+static struct regulator_consumer_supply db8500_svapipe_consumers[] = {
+ REGULATOR_SUPPLY("sva-pipe", "cm_control"),
+};
+
+/* SIA MMDSP regulator switch */
+static struct regulator_consumer_supply db8500_siammdsp_consumers[] = {
+ REGULATOR_SUPPLY("sia-mmdsp", "cm_control"),
+};
+
+/* SIA pipe regulator switch */
+static struct regulator_consumer_supply db8500_siapipe_consumers[] = {
+ REGULATOR_SUPPLY("sia-pipe", "cm_control"),
+};
+
+static struct regulator_consumer_supply db8500_sga_consumers[] = {
+ REGULATOR_SUPPLY("v-mali", NULL),
+};
+
+/* ESRAM1 and 2 regulator switch */
+static struct regulator_consumer_supply db8500_esram12_consumers[] = {
+ REGULATOR_SUPPLY("esram12", "cm_control"),
+};
+
+/* ESRAM3 and 4 regulator switch */
+static struct regulator_consumer_supply db8500_esram34_consumers[] = {
+ REGULATOR_SUPPLY("v-esram34", "mcde"),
+ REGULATOR_SUPPLY("esram34", "cm_control"),
};
static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
@@ -1923,6 +2299,8 @@
.name = "db8500-sva-mmdsp",
.valid_ops_mask = REGULATOR_CHANGE_STATUS,
},
+ .consumer_supplies = db8500_svammdsp_consumers,
+ .num_consumer_supplies = ARRAY_SIZE(db8500_svammdsp_consumers),
},
[DB8500_REGULATOR_SWITCH_SVAMMDSPRET] = {
.constraints = {
@@ -1937,6 +2315,8 @@
.name = "db8500-sva-pipe",
.valid_ops_mask = REGULATOR_CHANGE_STATUS,
},
+ .consumer_supplies = db8500_svapipe_consumers,
+ .num_consumer_supplies = ARRAY_SIZE(db8500_svapipe_consumers),
},
[DB8500_REGULATOR_SWITCH_SIAMMDSP] = {
.supply_regulator = "db8500-vape",
@@ -1944,6 +2324,8 @@
.name = "db8500-sia-mmdsp",
.valid_ops_mask = REGULATOR_CHANGE_STATUS,
},
+ .consumer_supplies = db8500_siammdsp_consumers,
+ .num_consumer_supplies = ARRAY_SIZE(db8500_siammdsp_consumers),
},
[DB8500_REGULATOR_SWITCH_SIAMMDSPRET] = {
.constraints = {
@@ -1957,6 +2339,8 @@
.name = "db8500-sia-pipe",
.valid_ops_mask = REGULATOR_CHANGE_STATUS,
},
+ .consumer_supplies = db8500_siapipe_consumers,
+ .num_consumer_supplies = ARRAY_SIZE(db8500_siapipe_consumers),
},
[DB8500_REGULATOR_SWITCH_SGA] = {
.supply_regulator = "db8500-vape",
@@ -1964,6 +2348,9 @@
.name = "db8500-sga",
.valid_ops_mask = REGULATOR_CHANGE_STATUS,
},
+ .consumer_supplies = db8500_sga_consumers,
+ .num_consumer_supplies = ARRAY_SIZE(db8500_sga_consumers),
+
},
[DB8500_REGULATOR_SWITCH_B2R2_MCDE] = {
.supply_regulator = "db8500-vape",
@@ -1980,6 +2367,8 @@
.name = "db8500-esram12",
.valid_ops_mask = REGULATOR_CHANGE_STATUS,
},
+ .consumer_supplies = db8500_esram12_consumers,
+ .num_consumer_supplies = ARRAY_SIZE(db8500_esram12_consumers),
},
[DB8500_REGULATOR_SWITCH_ESRAM12RET] = {
.constraints = {
@@ -1993,6 +2382,8 @@
.name = "db8500-esram34",
.valid_ops_mask = REGULATOR_CHANGE_STATUS,
},
+ .consumer_supplies = db8500_esram34_consumers,
+ .num_consumer_supplies = ARRAY_SIZE(db8500_esram34_consumers),
},
[DB8500_REGULATOR_SWITCH_ESRAM34RET] = {
.constraints = {
@@ -2024,8 +2415,10 @@
if (ux500_is_svp())
return -ENODEV;
+ db8500_prcmu_init_clkforce();
+
/* Clean up the mailbox interrupts after pre-kernel code. */
- writel(ALL_MBOX_BITS, (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+ writel(ALL_MBOX_BITS, PRCM_ARM_IT1_CLR);
err = request_threaded_irq(IRQ_DB8500_PRCMU1, prcmu_irq_handler,
prcmu_irq_thread_fn, IRQF_NO_SUSPEND, "prcmu", NULL);
diff --git a/drivers/mfd/dbx500-prcmu-regs.h b/drivers/mfd/dbx500-prcmu-regs.h
new file mode 100644
index 0000000..ec22e9f
--- /dev/null
+++ b/drivers/mfd/dbx500-prcmu-regs.h
@@ -0,0 +1,204 @@
+/*
+ * Copyright (C) STMicroelectronics 2009
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * Author: Kumar Sanghvi <kumar.sanghvi@stericsson.com>
+ * Author: Sundar Iyer <sundar.iyer@stericsson.com>
+ *
+ * License Terms: GNU General Public License v2
+ *
+ * PRCM Unit registers
+ */
+
+#ifndef __DB8500_PRCMU_REGS_H
+#define __DB8500_PRCMU_REGS_H
+
+#include <mach/hardware.h>
+
+#define BITS(_start, _end) ((BIT(_end) - BIT(_start)) + BIT(_end))
+
+#define PRCM_SVACLK_MGT_OFF 0x008
+#define PRCM_SIACLK_MGT_OFF 0x00C
+#define PRCM_SGACLK_MGT_OFF 0x014
+#define PRCM_UARTCLK_MGT_OFF 0x018
+#define PRCM_MSP02CLK_MGT_OFF 0x01C
+#define PRCM_I2CCLK_MGT_OFF 0x020
+#define PRCM_SDMMCCLK_MGT_OFF 0x024
+#define PRCM_SLIMCLK_MGT_OFF 0x028
+#define PRCM_PER1CLK_MGT_OFF 0x02C
+#define PRCM_PER2CLK_MGT_OFF 0x030
+#define PRCM_PER3CLK_MGT_OFF 0x034
+#define PRCM_PER5CLK_MGT_OFF 0x038
+#define PRCM_PER6CLK_MGT_OFF 0x03C
+#define PRCM_PER7CLK_MGT_OFF 0x040
+#define PRCM_PWMCLK_MGT_OFF 0x044 /* for DB5500 */
+#define PRCM_IRDACLK_MGT_OFF 0x048 /* for DB5500 */
+#define PRCM_IRRCCLK_MGT_OFF 0x04C /* for DB5500 */
+#define PRCM_LCDCLK_MGT_OFF 0x044
+#define PRCM_BMLCLK_MGT_OFF 0x04C
+#define PRCM_HSITXCLK_MGT_OFF 0x050
+#define PRCM_HSIRXCLK_MGT_OFF 0x054
+#define PRCM_HDMICLK_MGT_OFF 0x058
+#define PRCM_APEATCLK_MGT_OFF 0x05C
+#define PRCM_APETRACECLK_MGT_OFF 0x060
+#define PRCM_MCDECLK_MGT_OFF 0x064
+#define PRCM_IPI2CCLK_MGT_OFF 0x068
+#define PRCM_DSIALTCLK_MGT_OFF 0x06C
+#define PRCM_DMACLK_MGT_OFF 0x074
+#define PRCM_B2R2CLK_MGT_OFF 0x078
+#define PRCM_TVCLK_MGT_OFF 0x07C
+#define PRCM_UNIPROCLK_MGT_OFF 0x278
+#define PRCM_SSPCLK_MGT_OFF 0x280
+#define PRCM_RNGCLK_MGT_OFF 0x284
+#define PRCM_UICCCLK_MGT_OFF 0x27C
+#define PRCM_MSP1CLK_MGT_OFF 0x288
+
+#define PRCM_ARM_PLLDIVPS (_PRCMU_BASE + 0x118)
+#define PRCM_ARM_PLLDIVPS_ARM_BRM_RATE 0x3f
+#define PRCM_ARM_PLLDIVPS_MAX_MASK 0xf
+
+#define PRCM_PLLARM_LOCKP (_PRCMU_BASE + 0x0a8)
+#define PRCM_PLLARM_LOCKP_PRCM_PLLARM_LOCKP3 0x2
+
+#define PRCM_ARM_CHGCLKREQ (_PRCMU_BASE + 0x114)
+#define PRCM_ARM_CHGCLKREQ_PRCM_ARM_CHGCLKREQ 0x1
+
+#define PRCM_PLLARM_ENABLE (_PRCMU_BASE + 0x98)
+#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_ENABLE 0x1
+#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_COUNTON 0x100
+
+#define PRCM_ARMCLKFIX_MGT (_PRCMU_BASE + 0x0)
+#define PRCM_A9PL_FORCE_CLKEN (_PRCMU_BASE + 0x19C)
+#define PRCM_A9_RESETN_CLR (_PRCMU_BASE + 0x1f4)
+#define PRCM_A9_RESETN_SET (_PRCMU_BASE + 0x1f0)
+#define PRCM_ARM_LS_CLAMP (_PRCMU_BASE + 0x30c)
+#define PRCM_SRAM_A9 (_PRCMU_BASE + 0x308)
+
+#define PRCM_A9PL_FORCE_CLKEN_PRCM_A9PL_FORCE_CLKEN BIT(0)
+#define PRCM_A9PL_FORCE_CLKEN_PRCM_A9AXI_FORCE_CLKEN BIT(1)
+
+/* ARM WFI Standby signal register */
+#define PRCM_ARM_WFI_STANDBY (_PRCMU_BASE + 0x130)
+#define PRCM_IOCR (_PRCMU_BASE + 0x310)
+#define PRCM_IOCR_IOFORCE 0x1
+
+/* CPU mailbox registers */
+#define PRCM_MBOX_CPU_VAL (_PRCMU_BASE + 0x0fc)
+#define PRCM_MBOX_CPU_SET (_PRCMU_BASE + 0x100)
+#define PRCM_MBOX_CPU_CLR (_PRCMU_BASE + 0x104)
+
+/* Dual A9 core interrupt management unit registers */
+#define PRCM_A9_MASK_REQ (_PRCMU_BASE + 0x328)
+#define PRCM_A9_MASK_REQ_PRCM_A9_MASK_REQ 0x1
+
+#define PRCM_A9_MASK_ACK (_PRCMU_BASE + 0x32c)
+#define PRCM_ARMITMSK31TO0 (_PRCMU_BASE + 0x11c)
+#define PRCM_ARMITMSK63TO32 (_PRCMU_BASE + 0x120)
+#define PRCM_ARMITMSK95TO64 (_PRCMU_BASE + 0x124)
+#define PRCM_ARMITMSK127TO96 (_PRCMU_BASE + 0x128)
+#define PRCM_POWER_STATE_VAL (_PRCMU_BASE + 0x25C)
+#define PRCM_ARMITVAL31TO0 (_PRCMU_BASE + 0x260)
+#define PRCM_ARMITVAL63TO32 (_PRCMU_BASE + 0x264)
+#define PRCM_ARMITVAL95TO64 (_PRCMU_BASE + 0x268)
+#define PRCM_ARMITVAL127TO96 (_PRCMU_BASE + 0x26C)
+
+#define PRCM_HOSTACCESS_REQ (_PRCMU_BASE + 0x334)
+#define PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ 0x1
+#define ARM_WAKEUP_MODEM 0x1
+
+#define PRCM_ARM_IT1_CLR (_PRCMU_BASE + 0x48C)
+#define PRCM_ARM_IT1_VAL (_PRCMU_BASE + 0x494)
+#define PRCM_HOLD_EVT (_PRCMU_BASE + 0x174)
+
+#define PRCM_MOD_AWAKE_STATUS (_PRCMU_BASE + 0x4A0)
+#define PRCM_MOD_AWAKE_STATUS_PRCM_MOD_COREPD_AWAKE BIT(0)
+#define PRCM_MOD_AWAKE_STATUS_PRCM_MOD_AAPD_AWAKE BIT(1)
+#define PRCM_MOD_AWAKE_STATUS_PRCM_MOD_VMODEM_OFF_ISO BIT(2)
+
+#define PRCM_ITSTATUS0 (_PRCMU_BASE + 0x148)
+#define PRCM_ITSTATUS1 (_PRCMU_BASE + 0x150)
+#define PRCM_ITSTATUS2 (_PRCMU_BASE + 0x158)
+#define PRCM_ITSTATUS3 (_PRCMU_BASE + 0x160)
+#define PRCM_ITSTATUS4 (_PRCMU_BASE + 0x168)
+#define PRCM_ITSTATUS5 (_PRCMU_BASE + 0x484)
+#define PRCM_ITCLEAR5 (_PRCMU_BASE + 0x488)
+#define PRCM_ARMIT_MASKXP70_IT (_PRCMU_BASE + 0x1018)
+
+/* System reset register */
+#define PRCM_APE_SOFTRST (_PRCMU_BASE + 0x228)
+
+/* Level shifter and clamp control registers */
+#define PRCM_MMIP_LS_CLAMP_SET (_PRCMU_BASE + 0x420)
+#define PRCM_MMIP_LS_CLAMP_CLR (_PRCMU_BASE + 0x424)
+
+/* PRCMU clock/PLL/reset registers */
+#define PRCM_PLLDSI_FREQ (_PRCMU_BASE + 0x500)
+#define PRCM_PLLDSI_ENABLE (_PRCMU_BASE + 0x504)
+#define PRCM_PLLDSI_LOCKP (_PRCMU_BASE + 0x508)
+#define PRCM_LCDCLK_MGT (_PRCMU_BASE + PRCM_LCDCLK_MGT_OFF)
+#define PRCM_MCDECLK_MGT (_PRCMU_BASE + PRCM_MCDECLK_MGT_OFF)
+#define PRCM_HDMICLK_MGT (_PRCMU_BASE + PRCM_HDMICLK_MGT_OFF)
+#define PRCM_TVCLK_MGT (_PRCMU_BASE + PRCM_TVCLK_MGT_OFF)
+#define PRCM_DSI_PLLOUT_SEL (_PRCMU_BASE + 0x530)
+#define PRCM_DSITVCLK_DIV (_PRCMU_BASE + 0x52C)
+#define PRCM_PLLDSI_LOCKP (_PRCMU_BASE + 0x508)
+#define PRCM_APE_RESETN_SET (_PRCMU_BASE + 0x1E4)
+#define PRCM_APE_RESETN_CLR (_PRCMU_BASE + 0x1E8)
+
+#define PRCM_CLKOCR (_PRCMU_BASE + 0x1CC)
+#define PRCM_CLKOCR_CLKOUT0_REF_CLK (1 << 0)
+#define PRCM_CLKOCR_CLKOUT0_MASK BITS(0, 13)
+#define PRCM_CLKOCR_CLKOUT1_REF_CLK (1 << 16)
+#define PRCM_CLKOCR_CLKOUT1_MASK BITS(16, 29)
+
+/* ePOD and memory power signal control registers */
+#define PRCM_EPOD_C_SET (_PRCMU_BASE + 0x410)
+#define PRCM_SRAM_LS_SLEEP (_PRCMU_BASE + 0x304)
+
+/* Debug power control unit registers */
+#define PRCM_POWER_STATE_SET (_PRCMU_BASE + 0x254)
+
+/* Miscellaneous unit registers */
+#define PRCM_DSI_SW_RESET (_PRCMU_BASE + 0x324)
+#define PRCM_GPIOCR (_PRCMU_BASE + 0x138)
+#define PRCM_GPIOCR_DBG_STM_MOD_CMD1 0x800
+#define PRCM_GPIOCR_DBG_UARTMOD_CMD0 0x1
+
+/* PRCMU HW semaphore */
+#define PRCM_SEM (_PRCMU_BASE + 0x400)
+#define PRCM_SEM_PRCM_SEM BIT(0)
+
+#define PRCM_TCR (_PRCMU_BASE + 0x1C8)
+#define PRCM_TCR_TENSEL_MASK BITS(0, 7)
+#define PRCM_TCR_STOP_TIMERS BIT(16)
+#define PRCM_TCR_DOZE_MODE BIT(17)
+
+#define PRCM_CLKOCR_CLKODIV0_SHIFT 0
+#define PRCM_CLKOCR_CLKODIV0_MASK BITS(0, 5)
+#define PRCM_CLKOCR_CLKOSEL0_SHIFT 6
+#define PRCM_CLKOCR_CLKOSEL0_MASK BITS(6, 8)
+#define PRCM_CLKOCR_CLKODIV1_SHIFT 16
+#define PRCM_CLKOCR_CLKODIV1_MASK BITS(16, 21)
+#define PRCM_CLKOCR_CLKOSEL1_SHIFT 22
+#define PRCM_CLKOCR_CLKOSEL1_MASK BITS(22, 24)
+#define PRCM_CLKOCR_CLK1TYPE BIT(28)
+
+#define PRCM_CLK_MGT_CLKPLLDIV_MASK BITS(0, 4)
+#define PRCM_CLK_MGT_CLKPLLSW_MASK BITS(5, 7)
+#define PRCM_CLK_MGT_CLKEN BIT(8)
+
+/* GPIOCR register */
+#define PRCM_GPIOCR_SPI2_SELECT BIT(23)
+
+#define PRCM_DDR_SUBSYS_APE_MINBW (_PRCMU_BASE + 0x438)
+#define PRCM_CGATING_BYPASS (_PRCMU_BASE + 0x134)
+#define PRCM_CGATING_BYPASS_ICN2 BIT(6)
+
+/* Miscellaneous unit registers */
+#define PRCM_RESOUTN_SET (_PRCMU_BASE + 0x214)
+#define PRCM_RESOUTN_CLR (_PRCMU_BASE + 0x218)
+
+/* System reset register */
+#define PRCM_APE_SOFTRST (_PRCMU_BASE + 0x228)
+
+#endif /* __DB8500_PRCMU_REGS_H */
diff --git a/drivers/mfd/intel_msic.c b/drivers/mfd/intel_msic.c
new file mode 100644
index 0000000..97c2776
--- /dev/null
+++ b/drivers/mfd/intel_msic.c
@@ -0,0 +1,502 @@
+/*
+ * Driver for Intel MSIC
+ *
+ * Copyright (C) 2011, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/gpio.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/intel_msic.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <asm/intel_scu_ipc.h>
+
+#define MSIC_VENDOR(id) ((id >> 6) & 3)
+#define MSIC_VERSION(id) (id & 0x3f)
+#define MSIC_MAJOR(id) ('A' + ((id >> 3) & 7))
+#define MSIC_MINOR(id) (id & 7)
+
+/*
+ * MSIC interrupt tree is readable from SRAM at INTEL_MSIC_IRQ_PHYS_BASE.
+ * Since IRQ block starts from address 0x002 we need to substract that from
+ * the actual IRQ status register address.
+ */
+#define MSIC_IRQ_STATUS(x) (INTEL_MSIC_IRQ_PHYS_BASE + ((x) - 2))
+#define MSIC_IRQ_STATUS_ACCDET MSIC_IRQ_STATUS(INTEL_MSIC_ACCDET)
+
+/*
+ * The SCU hardware has limitation of 16 bytes per read/write buffer on
+ * Medfield.
+ */
+#define SCU_IPC_RWBUF_LIMIT 16
+
+/**
+ * struct intel_msic - an MSIC MFD instance
+ * @pdev: pointer to the platform device
+ * @vendor: vendor ID
+ * @version: chip version
+ * @irq_base: base address of the mapped MSIC SRAM interrupt tree
+ */
+struct intel_msic {
+ struct platform_device *pdev;
+ unsigned vendor;
+ unsigned version;
+ void __iomem *irq_base;
+};
+
+static struct resource msic_touch_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct resource msic_adc_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct resource msic_battery_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct resource msic_gpio_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct resource msic_audio_resources[] = {
+ {
+ .name = "IRQ",
+ .flags = IORESOURCE_IRQ,
+ },
+ /*
+ * We will pass IRQ_BASE to the driver now but this can be removed
+ * when/if the driver starts to use intel_msic_irq_read().
+ */
+ {
+ .name = "IRQ_BASE",
+ .flags = IORESOURCE_MEM,
+ .start = MSIC_IRQ_STATUS_ACCDET,
+ .end = MSIC_IRQ_STATUS_ACCDET,
+ },
+};
+
+static struct resource msic_hdmi_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct resource msic_thermal_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct resource msic_power_btn_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct resource msic_ocd_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+/*
+ * Devices that are part of the MSIC and are available via firmware
+ * populated SFI DEVS table.
+ */
+static struct mfd_cell msic_devs[] = {
+ [INTEL_MSIC_BLOCK_TOUCH] = {
+ .name = "msic_touch",
+ .num_resources = ARRAY_SIZE(msic_touch_resources),
+ .resources = msic_touch_resources,
+ },
+ [INTEL_MSIC_BLOCK_ADC] = {
+ .name = "msic_adc",
+ .num_resources = ARRAY_SIZE(msic_adc_resources),
+ .resources = msic_adc_resources,
+ },
+ [INTEL_MSIC_BLOCK_BATTERY] = {
+ .name = "msic_battery",
+ .num_resources = ARRAY_SIZE(msic_battery_resources),
+ .resources = msic_battery_resources,
+ },
+ [INTEL_MSIC_BLOCK_GPIO] = {
+ .name = "msic_gpio",
+ .num_resources = ARRAY_SIZE(msic_gpio_resources),
+ .resources = msic_gpio_resources,
+ },
+ [INTEL_MSIC_BLOCK_AUDIO] = {
+ .name = "msic_audio",
+ .num_resources = ARRAY_SIZE(msic_audio_resources),
+ .resources = msic_audio_resources,
+ },
+ [INTEL_MSIC_BLOCK_HDMI] = {
+ .name = "msic_hdmi",
+ .num_resources = ARRAY_SIZE(msic_hdmi_resources),
+ .resources = msic_hdmi_resources,
+ },
+ [INTEL_MSIC_BLOCK_THERMAL] = {
+ .name = "msic_thermal",
+ .num_resources = ARRAY_SIZE(msic_thermal_resources),
+ .resources = msic_thermal_resources,
+ },
+ [INTEL_MSIC_BLOCK_POWER_BTN] = {
+ .name = "msic_power_btn",
+ .num_resources = ARRAY_SIZE(msic_power_btn_resources),
+ .resources = msic_power_btn_resources,
+ },
+ [INTEL_MSIC_BLOCK_OCD] = {
+ .name = "msic_ocd",
+ .num_resources = ARRAY_SIZE(msic_ocd_resources),
+ .resources = msic_ocd_resources,
+ },
+};
+
+/*
+ * Other MSIC related devices which are not directly available via SFI DEVS
+ * table. These can be pseudo devices, regulators etc. which are needed for
+ * different purposes.
+ *
+ * These devices appear only after the MSIC driver itself is initialized so
+ * we can guarantee that the SCU IPC interface is ready.
+ */
+static struct mfd_cell msic_other_devs[] = {
+ /* Audio codec in the MSIC */
+ {
+ .id = -1,
+ .name = "sn95031",
+ },
+};
+
+/**
+ * intel_msic_reg_read - read a single MSIC register
+ * @reg: register to read
+ * @val: register value is placed here
+ *
+ * Read a single register from MSIC. Returns %0 on success and negative
+ * errno in case of failure.
+ *
+ * Function may sleep.
+ */
+int intel_msic_reg_read(unsigned short reg, u8 *val)
+{
+ return intel_scu_ipc_ioread8(reg, val);
+}
+EXPORT_SYMBOL_GPL(intel_msic_reg_read);
+
+/**
+ * intel_msic_reg_write - write a single MSIC register
+ * @reg: register to write
+ * @val: value to write to that register
+ *
+ * Write a single MSIC register. Returns 0 on success and negative
+ * errno in case of failure.
+ *
+ * Function may sleep.
+ */
+int intel_msic_reg_write(unsigned short reg, u8 val)
+{
+ return intel_scu_ipc_iowrite8(reg, val);
+}
+EXPORT_SYMBOL_GPL(intel_msic_reg_write);
+
+/**
+ * intel_msic_reg_update - update a single MSIC register
+ * @reg: register to update
+ * @val: value to write to the register
+ * @mask: specifies which of the bits are updated (%0 = don't update,
+ * %1 = update)
+ *
+ * Perform an update to a register @reg. @mask is used to specify which
+ * bits are updated. Returns %0 in case of success and negative errno in
+ * case of failure.
+ *
+ * Function may sleep.
+ */
+int intel_msic_reg_update(unsigned short reg, u8 val, u8 mask)
+{
+ return intel_scu_ipc_update_register(reg, val, mask);
+}
+EXPORT_SYMBOL_GPL(intel_msic_reg_update);
+
+/**
+ * intel_msic_bulk_read - read an array of registers
+ * @reg: array of register addresses to read
+ * @buf: array where the read values are placed
+ * @count: number of registers to read
+ *
+ * Function reads @count registers from the MSIC using addresses passed in
+ * @reg. Read values are placed in @buf. Reads are performed atomically
+ * wrt. MSIC.
+ *
+ * Returns %0 in case of success and negative errno in case of failure.
+ *
+ * Function may sleep.
+ */
+int intel_msic_bulk_read(unsigned short *reg, u8 *buf, size_t count)
+{
+ if (WARN_ON(count > SCU_IPC_RWBUF_LIMIT))
+ return -EINVAL;
+
+ return intel_scu_ipc_readv(reg, buf, count);
+}
+EXPORT_SYMBOL_GPL(intel_msic_bulk_read);
+
+/**
+ * intel_msic_bulk_write - write an array of values to the MSIC registers
+ * @reg: array of registers to write
+ * @buf: values to write to each register
+ * @count: number of registers to write
+ *
+ * Function writes @count registers in @buf to MSIC. Writes are performed
+ * atomically wrt MSIC. Returns %0 in case of success and negative errno in
+ * case of failure.
+ *
+ * Function may sleep.
+ */
+int intel_msic_bulk_write(unsigned short *reg, u8 *buf, size_t count)
+{
+ if (WARN_ON(count > SCU_IPC_RWBUF_LIMIT))
+ return -EINVAL;
+
+ return intel_scu_ipc_writev(reg, buf, count);
+}
+EXPORT_SYMBOL_GPL(intel_msic_bulk_write);
+
+/**
+ * intel_msic_irq_read - read a register from an MSIC interrupt tree
+ * @msic: MSIC instance
+ * @reg: interrupt register (between %INTEL_MSIC_IRQLVL1 and
+ * %INTEL_MSIC_RESETIRQ2)
+ * @val: value of the register is placed here
+ *
+ * This function can be used by an MSIC subdevice interrupt handler to read
+ * a register value from the MSIC interrupt tree. In this way subdevice
+ * drivers don't have to map in the interrupt tree themselves but can just
+ * call this function instead.
+ *
+ * Function doesn't sleep and is callable from interrupt context.
+ *
+ * Returns %-EINVAL if @reg is outside of the allowed register region.
+ */
+int intel_msic_irq_read(struct intel_msic *msic, unsigned short reg, u8 *val)
+{
+ if (WARN_ON(reg < INTEL_MSIC_IRQLVL1 || reg > INTEL_MSIC_RESETIRQ2))
+ return -EINVAL;
+
+ *val = readb(msic->irq_base + (reg - INTEL_MSIC_IRQLVL1));
+ return 0;
+}
+EXPORT_SYMBOL_GPL(intel_msic_irq_read);
+
+static int __devinit intel_msic_init_devices(struct intel_msic *msic)
+{
+ struct platform_device *pdev = msic->pdev;
+ struct intel_msic_platform_data *pdata = pdev->dev.platform_data;
+ int ret, i;
+
+ if (pdata->gpio) {
+ struct mfd_cell *cell = &msic_devs[INTEL_MSIC_BLOCK_GPIO];
+
+ cell->platform_data = pdata->gpio;
+ cell->pdata_size = sizeof(*pdata->gpio);
+ }
+
+ if (pdata->ocd) {
+ unsigned gpio = pdata->ocd->gpio;
+
+ ret = gpio_request_one(gpio, GPIOF_IN, "ocd_gpio");
+ if (ret) {
+ dev_err(&pdev->dev, "failed to register OCD GPIO\n");
+ return ret;
+ }
+
+ ret = gpio_to_irq(gpio);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "no IRQ number for OCD GPIO\n");
+ gpio_free(gpio);
+ return ret;
+ }
+
+ /* Update the IRQ number for the OCD */
+ pdata->irq[INTEL_MSIC_BLOCK_OCD] = ret;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(msic_devs); i++) {
+ if (!pdata->irq[i])
+ continue;
+
+ ret = mfd_add_devices(&pdev->dev, -1, &msic_devs[i], 1, NULL,
+ pdata->irq[i]);
+ if (ret)
+ goto fail;
+ }
+
+ ret = mfd_add_devices(&pdev->dev, 0, msic_other_devs,
+ ARRAY_SIZE(msic_other_devs), NULL, 0);
+ if (ret)
+ goto fail;
+
+ return 0;
+
+fail:
+ mfd_remove_devices(&pdev->dev);
+ if (pdata->ocd)
+ gpio_free(pdata->ocd->gpio);
+
+ return ret;
+}
+
+static void __devexit intel_msic_remove_devices(struct intel_msic *msic)
+{
+ struct platform_device *pdev = msic->pdev;
+ struct intel_msic_platform_data *pdata = pdev->dev.platform_data;
+
+ mfd_remove_devices(&pdev->dev);
+
+ if (pdata->ocd)
+ gpio_free(pdata->ocd->gpio);
+}
+
+static int __devinit intel_msic_probe(struct platform_device *pdev)
+{
+ struct intel_msic_platform_data *pdata = pdev->dev.platform_data;
+ struct intel_msic *msic;
+ struct resource *res;
+ u8 id0, id1;
+ int ret;
+
+ if (!pdata) {
+ dev_err(&pdev->dev, "no platform data passed\n");
+ return -EINVAL;
+ }
+
+ /* First validate that we have an MSIC in place */
+ ret = intel_scu_ipc_ioread8(INTEL_MSIC_ID0, &id0);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to identify the MSIC chip (ID0)\n");
+ return -ENXIO;
+ }
+
+ ret = intel_scu_ipc_ioread8(INTEL_MSIC_ID1, &id1);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to identify the MSIC chip (ID1)\n");
+ return -ENXIO;
+ }
+
+ if (MSIC_VENDOR(id0) != MSIC_VENDOR(id1)) {
+ dev_err(&pdev->dev, "invalid vendor ID: %x, %x\n", id0, id1);
+ return -ENXIO;
+ }
+
+ msic = kzalloc(sizeof(*msic), GFP_KERNEL);
+ if (!msic)
+ return -ENOMEM;
+
+ msic->vendor = MSIC_VENDOR(id0);
+ msic->version = MSIC_VERSION(id0);
+ msic->pdev = pdev;
+
+ /*
+ * Map in the MSIC interrupt tree area in SRAM. This is exposed to
+ * the clients via intel_msic_irq_read().
+ */
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(&pdev->dev, "failed to get SRAM iomem resource\n");
+ ret = -ENODEV;
+ goto fail_free_msic;
+ }
+
+ res = request_mem_region(res->start, resource_size(res), pdev->name);
+ if (!res) {
+ ret = -EBUSY;
+ goto fail_free_msic;
+ }
+
+ msic->irq_base = ioremap_nocache(res->start, resource_size(res));
+ if (!msic->irq_base) {
+ dev_err(&pdev->dev, "failed to map SRAM memory\n");
+ ret = -ENOMEM;
+ goto fail_release_region;
+ }
+
+ platform_set_drvdata(pdev, msic);
+
+ ret = intel_msic_init_devices(msic);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to initialize MSIC devices\n");
+ goto fail_unmap_mem;
+ }
+
+ dev_info(&pdev->dev, "Intel MSIC version %c%d (vendor %#x)\n",
+ MSIC_MAJOR(msic->version), MSIC_MINOR(msic->version),
+ msic->vendor);
+
+ return 0;
+
+fail_unmap_mem:
+ iounmap(msic->irq_base);
+fail_release_region:
+ release_mem_region(res->start, resource_size(res));
+fail_free_msic:
+ kfree(msic);
+
+ return ret;
+}
+
+static int __devexit intel_msic_remove(struct platform_device *pdev)
+{
+ struct intel_msic *msic = platform_get_drvdata(pdev);
+ struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+ intel_msic_remove_devices(msic);
+ platform_set_drvdata(pdev, NULL);
+ iounmap(msic->irq_base);
+ release_mem_region(res->start, resource_size(res));
+ kfree(msic);
+
+ return 0;
+}
+
+static struct platform_driver intel_msic_driver = {
+ .probe = intel_msic_probe,
+ .remove = __devexit_p(intel_msic_remove),
+ .driver = {
+ .name = "intel_msic",
+ .owner = THIS_MODULE,
+ },
+};
+
+static int __init intel_msic_init(void)
+{
+ return platform_driver_register(&intel_msic_driver);
+}
+module_init(intel_msic_init);
+
+static void __exit intel_msic_exit(void)
+{
+ platform_driver_unregister(&intel_msic_driver);
+}
+module_exit(intel_msic_exit);
+
+MODULE_DESCRIPTION("Driver for Intel MSIC");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/jz4740-adc.c b/drivers/mfd/jz4740-adc.c
index 563654c..1e9ee53 100644
--- a/drivers/mfd/jz4740-adc.c
+++ b/drivers/mfd/jz4740-adc.c
@@ -328,7 +328,7 @@
return 0;
}
-struct platform_driver jz4740_adc_driver = {
+static struct platform_driver jz4740_adc_driver = {
.probe = jz4740_adc_probe,
.remove = __devexit_p(jz4740_adc_remove),
.driver = {
diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c
index f83103b..dc58750 100644
--- a/drivers/mfd/max8997.c
+++ b/drivers/mfd/max8997.c
@@ -23,6 +23,7 @@
#include <linux/slab.h>
#include <linux/i2c.h>
+#include <linux/interrupt.h>
#include <linux/pm_runtime.h>
#include <linux/mutex.h>
#include <linux/mfd/core.h>
@@ -142,7 +143,6 @@
max8997->irq_base = pdata->irq_base;
max8997->ono = pdata->ono;
- max8997->wakeup = pdata->wakeup;
mutex_init(&max8997->iolock);
@@ -169,6 +169,9 @@
if (ret < 0)
goto err_mfd;
+ /* MAX8997 has a power button input. */
+ device_init_wakeup(max8997->dev, pdata->wakeup);
+
return ret;
err_mfd:
@@ -398,7 +401,29 @@
return 0;
}
+static int max8997_suspend(struct device *dev)
+{
+ struct i2c_client *i2c = container_of(dev, struct i2c_client, dev);
+ struct max8997_dev *max8997 = i2c_get_clientdata(i2c);
+
+ if (device_may_wakeup(dev))
+ irq_set_irq_wake(max8997->irq, 1);
+ return 0;
+}
+
+static int max8997_resume(struct device *dev)
+{
+ struct i2c_client *i2c = container_of(dev, struct i2c_client, dev);
+ struct max8997_dev *max8997 = i2c_get_clientdata(i2c);
+
+ if (device_may_wakeup(dev))
+ irq_set_irq_wake(max8997->irq, 0);
+ return max8997_irq_resume(max8997);
+}
+
const struct dev_pm_ops max8997_pm = {
+ .suspend = max8997_suspend,
+ .resume = max8997_resume,
.freeze = max8997_freeze,
.restore = max8997_restore,
};
diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c
index 7e4d44b..e9619ac 100644
--- a/drivers/mfd/mc13xxx-core.c
+++ b/drivers/mfd/mc13xxx-core.c
@@ -26,20 +26,10 @@
irq_handler_t irqhandler[MC13XXX_NUM_IRQ];
void *irqdata[MC13XXX_NUM_IRQ];
-};
-
-struct mc13783 {
- struct mc13xxx mc13xxx;
int adcflags;
};
-struct mc13xxx *mc13783_to_mc13xxx(struct mc13783 *mc13783)
-{
- return &mc13783->mc13xxx;
-}
-EXPORT_SYMBOL(mc13783_to_mc13xxx);
-
#define MC13XXX_IRQSTAT0 0
#define MC13XXX_IRQSTAT0_ADCDONEI (1 << 0)
#define MC13XXX_IRQSTAT0_ADCBISDONEI (1 << 1)
@@ -136,14 +126,14 @@
#define MC13XXX_REVISION_FAB (0x03 << 11)
#define MC13XXX_REVISION_ICIDCODE (0x3f << 13)
-#define MC13783_ADC1 44
-#define MC13783_ADC1_ADEN (1 << 0)
-#define MC13783_ADC1_RAND (1 << 1)
-#define MC13783_ADC1_ADSEL (1 << 3)
-#define MC13783_ADC1_ASC (1 << 20)
-#define MC13783_ADC1_ADTRIGIGN (1 << 21)
+#define MC13XXX_ADC1 44
+#define MC13XXX_ADC1_ADEN (1 << 0)
+#define MC13XXX_ADC1_RAND (1 << 1)
+#define MC13XXX_ADC1_ADSEL (1 << 3)
+#define MC13XXX_ADC1_ASC (1 << 20)
+#define MC13XXX_ADC1_ADTRIGIGN (1 << 21)
-#define MC13783_ADC2 45
+#define MC13XXX_ADC2 45
#define MC13XXX_NUMREGS 0x3f
@@ -487,7 +477,7 @@
MC13XXX_ID_INVALID,
};
-const char *mc13xxx_chipname[] = {
+static const char *mc13xxx_chipname[] = {
[MC13XXX_ID_MC13783] = "mc13783",
[MC13XXX_ID_MC13892] = "mc13892",
};
@@ -558,8 +548,6 @@
return mc13xxx_chipname[devid->driver_data];
}
-#include <linux/mfd/mc13783.h>
-
int mc13xxx_get_flags(struct mc13xxx *mc13xxx)
{
struct mc13xxx_platform_data *pdata =
@@ -569,15 +557,15 @@
}
EXPORT_SYMBOL(mc13xxx_get_flags);
-#define MC13783_ADC1_CHAN0_SHIFT 5
-#define MC13783_ADC1_CHAN1_SHIFT 8
+#define MC13XXX_ADC1_CHAN0_SHIFT 5
+#define MC13XXX_ADC1_CHAN1_SHIFT 8
struct mc13xxx_adcdone_data {
struct mc13xxx *mc13xxx;
struct completion done;
};
-static irqreturn_t mc13783_handler_adcdone(int irq, void *data)
+static irqreturn_t mc13xxx_handler_adcdone(int irq, void *data)
{
struct mc13xxx_adcdone_data *adcdone_data = data;
@@ -588,12 +576,11 @@
return IRQ_HANDLED;
}
-#define MC13783_ADC_WORKING (1 << 0)
+#define MC13XXX_ADC_WORKING (1 << 0)
-int mc13783_adc_do_conversion(struct mc13783 *mc13783, unsigned int mode,
+int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode,
unsigned int channel, unsigned int *sample)
{
- struct mc13xxx *mc13xxx = &mc13783->mc13xxx;
u32 adc0, adc1, old_adc0;
int i, ret;
struct mc13xxx_adcdone_data adcdone_data = {
@@ -605,51 +592,51 @@
mc13xxx_lock(mc13xxx);
- if (mc13783->adcflags & MC13783_ADC_WORKING) {
+ if (mc13xxx->adcflags & MC13XXX_ADC_WORKING) {
ret = -EBUSY;
goto out;
}
- mc13783->adcflags |= MC13783_ADC_WORKING;
+ mc13xxx->adcflags |= MC13XXX_ADC_WORKING;
- mc13xxx_reg_read(mc13xxx, MC13783_ADC0, &old_adc0);
+ mc13xxx_reg_read(mc13xxx, MC13XXX_ADC0, &old_adc0);
- adc0 = MC13783_ADC0_ADINC1 | MC13783_ADC0_ADINC2;
- adc1 = MC13783_ADC1_ADEN | MC13783_ADC1_ADTRIGIGN | MC13783_ADC1_ASC;
+ adc0 = MC13XXX_ADC0_ADINC1 | MC13XXX_ADC0_ADINC2;
+ adc1 = MC13XXX_ADC1_ADEN | MC13XXX_ADC1_ADTRIGIGN | MC13XXX_ADC1_ASC;
if (channel > 7)
- adc1 |= MC13783_ADC1_ADSEL;
+ adc1 |= MC13XXX_ADC1_ADSEL;
switch (mode) {
- case MC13783_ADC_MODE_TS:
- adc0 |= MC13783_ADC0_ADREFEN | MC13783_ADC0_TSMOD0 |
- MC13783_ADC0_TSMOD1;
- adc1 |= 4 << MC13783_ADC1_CHAN1_SHIFT;
+ case MC13XXX_ADC_MODE_TS:
+ adc0 |= MC13XXX_ADC0_ADREFEN | MC13XXX_ADC0_TSMOD0 |
+ MC13XXX_ADC0_TSMOD1;
+ adc1 |= 4 << MC13XXX_ADC1_CHAN1_SHIFT;
break;
- case MC13783_ADC_MODE_SINGLE_CHAN:
- adc0 |= old_adc0 & MC13783_ADC0_TSMOD_MASK;
- adc1 |= (channel & 0x7) << MC13783_ADC1_CHAN0_SHIFT;
- adc1 |= MC13783_ADC1_RAND;
+ case MC13XXX_ADC_MODE_SINGLE_CHAN:
+ adc0 |= old_adc0 & MC13XXX_ADC0_TSMOD_MASK;
+ adc1 |= (channel & 0x7) << MC13XXX_ADC1_CHAN0_SHIFT;
+ adc1 |= MC13XXX_ADC1_RAND;
break;
- case MC13783_ADC_MODE_MULT_CHAN:
- adc0 |= old_adc0 & MC13783_ADC0_TSMOD_MASK;
- adc1 |= 4 << MC13783_ADC1_CHAN1_SHIFT;
+ case MC13XXX_ADC_MODE_MULT_CHAN:
+ adc0 |= old_adc0 & MC13XXX_ADC0_TSMOD_MASK;
+ adc1 |= 4 << MC13XXX_ADC1_CHAN1_SHIFT;
break;
default:
- mc13783_unlock(mc13783);
+ mc13xxx_unlock(mc13xxx);
return -EINVAL;
}
- dev_dbg(&mc13783->mc13xxx.spidev->dev, "%s: request irq\n", __func__);
- mc13xxx_irq_request(mc13xxx, MC13783_IRQ_ADCDONE,
- mc13783_handler_adcdone, __func__, &adcdone_data);
- mc13xxx_irq_ack(mc13xxx, MC13783_IRQ_ADCDONE);
+ dev_dbg(&mc13xxx->spidev->dev, "%s: request irq\n", __func__);
+ mc13xxx_irq_request(mc13xxx, MC13XXX_IRQ_ADCDONE,
+ mc13xxx_handler_adcdone, __func__, &adcdone_data);
+ mc13xxx_irq_ack(mc13xxx, MC13XXX_IRQ_ADCDONE);
- mc13xxx_reg_write(mc13xxx, MC13783_ADC0, adc0);
- mc13xxx_reg_write(mc13xxx, MC13783_ADC1, adc1);
+ mc13xxx_reg_write(mc13xxx, MC13XXX_ADC0, adc0);
+ mc13xxx_reg_write(mc13xxx, MC13XXX_ADC1, adc1);
mc13xxx_unlock(mc13xxx);
@@ -660,27 +647,27 @@
mc13xxx_lock(mc13xxx);
- mc13xxx_irq_free(mc13xxx, MC13783_IRQ_ADCDONE, &adcdone_data);
+ mc13xxx_irq_free(mc13xxx, MC13XXX_IRQ_ADCDONE, &adcdone_data);
if (ret > 0)
for (i = 0; i < 4; ++i) {
ret = mc13xxx_reg_read(mc13xxx,
- MC13783_ADC2, &sample[i]);
+ MC13XXX_ADC2, &sample[i]);
if (ret)
break;
}
- if (mode == MC13783_ADC_MODE_TS)
+ if (mode == MC13XXX_ADC_MODE_TS)
/* restore TSMOD */
- mc13xxx_reg_write(mc13xxx, MC13783_ADC0, old_adc0);
+ mc13xxx_reg_write(mc13xxx, MC13XXX_ADC0, old_adc0);
- mc13783->adcflags &= ~MC13783_ADC_WORKING;
+ mc13xxx->adcflags &= ~MC13XXX_ADC_WORKING;
out:
mc13xxx_unlock(mc13xxx);
return ret;
}
-EXPORT_SYMBOL_GPL(mc13783_adc_do_conversion);
+EXPORT_SYMBOL_GPL(mc13xxx_adc_do_conversion);
static int mc13xxx_add_subdevice_pdata(struct mc13xxx *mc13xxx,
const char *format, void *pdata, size_t pdata_size)
@@ -716,6 +703,11 @@
enum mc13xxx_id id;
int ret;
+ if (!pdata) {
+ dev_err(&spi->dev, "invalid platform data\n");
+ return -EINVAL;
+ }
+
mc13xxx = kzalloc(sizeof(*mc13xxx), GFP_KERNEL);
if (!mc13xxx)
return -ENOMEM;
@@ -763,10 +755,8 @@
if (pdata->flags & MC13XXX_USE_CODEC)
mc13xxx_add_subdevice(mc13xxx, "%s-codec");
- if (pdata->flags & MC13XXX_USE_REGULATOR) {
- mc13xxx_add_subdevice_pdata(mc13xxx, "%s-regulator",
- &pdata->regulators, sizeof(pdata->regulators));
- }
+ mc13xxx_add_subdevice_pdata(mc13xxx, "%s-regulator",
+ &pdata->regulators, sizeof(pdata->regulators));
if (pdata->flags & MC13XXX_USE_RTC)
mc13xxx_add_subdevice(mc13xxx, "%s-rtc");
@@ -774,10 +764,14 @@
if (pdata->flags & MC13XXX_USE_TOUCHSCREEN)
mc13xxx_add_subdevice(mc13xxx, "%s-ts");
- if (pdata->flags & MC13XXX_USE_LED)
+ if (pdata->leds)
mc13xxx_add_subdevice_pdata(mc13xxx, "%s-led",
pdata->leds, sizeof(*pdata->leds));
+ if (pdata->buttons)
+ mc13xxx_add_subdevice_pdata(mc13xxx, "%s-pwrbutton",
+ pdata->buttons, sizeof(*pdata->buttons));
+
return 0;
}
diff --git a/drivers/mfd/menelaus.c b/drivers/mfd/menelaus.c
index af5d9d0..cb4910a 100644
--- a/drivers/mfd/menelaus.c
+++ b/drivers/mfd/menelaus.c
@@ -1226,7 +1226,7 @@
menelaus_write_reg(MENELAUS_MCT_CTRL1, 0x73);
if (client->irq > 0) {
- err = request_irq(client->irq, menelaus_irq, IRQF_DISABLED,
+ err = request_irq(client->irq, menelaus_irq, 0,
DRIVER_NAME, menelaus);
if (err) {
dev_dbg(&client->dev, "can't get IRQ %d, err %d\n",
diff --git a/drivers/mfd/pcf50633-core.c b/drivers/mfd/pcf50633-core.c
index 57868416..ff1a7e7 100644
--- a/drivers/mfd/pcf50633-core.c
+++ b/drivers/mfd/pcf50633-core.c
@@ -23,45 +23,22 @@
#include <linux/i2c.h>
#include <linux/pm.h>
#include <linux/slab.h>
+#include <linux/regmap.h>
+#include <linux/err.h>
#include <linux/mfd/pcf50633/core.h>
-static int __pcf50633_read(struct pcf50633 *pcf, u8 reg, int num, u8 *data)
-{
- int ret;
-
- ret = i2c_smbus_read_i2c_block_data(pcf->i2c_client, reg,
- num, data);
- if (ret < 0)
- dev_err(pcf->dev, "Error reading %d regs at %d\n", num, reg);
-
- return ret;
-}
-
-static int __pcf50633_write(struct pcf50633 *pcf, u8 reg, int num, u8 *data)
-{
- int ret;
-
- ret = i2c_smbus_write_i2c_block_data(pcf->i2c_client, reg,
- num, data);
- if (ret < 0)
- dev_err(pcf->dev, "Error writing %d regs at %d\n", num, reg);
-
- return ret;
-
-}
-
/* Read a block of up to 32 regs */
int pcf50633_read_block(struct pcf50633 *pcf, u8 reg,
int nr_regs, u8 *data)
{
int ret;
- mutex_lock(&pcf->lock);
- ret = __pcf50633_read(pcf, reg, nr_regs, data);
- mutex_unlock(&pcf->lock);
+ ret = regmap_raw_read(pcf->regmap, reg, data, nr_regs);
+ if (ret != 0)
+ return ret;
- return ret;
+ return nr_regs;
}
EXPORT_SYMBOL_GPL(pcf50633_read_block);
@@ -71,21 +48,22 @@
{
int ret;
- mutex_lock(&pcf->lock);
- ret = __pcf50633_write(pcf, reg, nr_regs, data);
- mutex_unlock(&pcf->lock);
+ ret = regmap_raw_write(pcf->regmap, reg, data, nr_regs);
+ if (ret != 0)
+ return ret;
- return ret;
+ return nr_regs;
}
EXPORT_SYMBOL_GPL(pcf50633_write_block);
u8 pcf50633_reg_read(struct pcf50633 *pcf, u8 reg)
{
- u8 val;
+ unsigned int val;
+ int ret;
- mutex_lock(&pcf->lock);
- __pcf50633_read(pcf, reg, 1, &val);
- mutex_unlock(&pcf->lock);
+ ret = regmap_read(pcf->regmap, reg, &val);
+ if (ret < 0)
+ return -1;
return val;
}
@@ -93,56 +71,19 @@
int pcf50633_reg_write(struct pcf50633 *pcf, u8 reg, u8 val)
{
- int ret;
-
- mutex_lock(&pcf->lock);
- ret = __pcf50633_write(pcf, reg, 1, &val);
- mutex_unlock(&pcf->lock);
-
- return ret;
+ return regmap_write(pcf->regmap, reg, val);
}
EXPORT_SYMBOL_GPL(pcf50633_reg_write);
int pcf50633_reg_set_bit_mask(struct pcf50633 *pcf, u8 reg, u8 mask, u8 val)
{
- int ret;
- u8 tmp;
-
- val &= mask;
-
- mutex_lock(&pcf->lock);
- ret = __pcf50633_read(pcf, reg, 1, &tmp);
- if (ret < 0)
- goto out;
-
- tmp &= ~mask;
- tmp |= val;
- ret = __pcf50633_write(pcf, reg, 1, &tmp);
-
-out:
- mutex_unlock(&pcf->lock);
-
- return ret;
+ return regmap_update_bits(pcf->regmap, reg, mask, val);
}
EXPORT_SYMBOL_GPL(pcf50633_reg_set_bit_mask);
int pcf50633_reg_clear_bits(struct pcf50633 *pcf, u8 reg, u8 val)
{
- int ret;
- u8 tmp;
-
- mutex_lock(&pcf->lock);
- ret = __pcf50633_read(pcf, reg, 1, &tmp);
- if (ret < 0)
- goto out;
-
- tmp &= ~val;
- ret = __pcf50633_write(pcf, reg, 1, &tmp);
-
-out:
- mutex_unlock(&pcf->lock);
-
- return ret;
+ return regmap_update_bits(pcf->regmap, reg, val, 0);
}
EXPORT_SYMBOL_GPL(pcf50633_reg_clear_bits);
@@ -251,6 +192,11 @@
static SIMPLE_DEV_PM_OPS(pcf50633_pm, pcf50633_suspend, pcf50633_resume);
+static struct regmap_config pcf50633_regmap_config = {
+ .reg_bits = 8,
+ .val_bits = 8,
+};
+
static int __devinit pcf50633_probe(struct i2c_client *client,
const struct i2c_device_id *ids)
{
@@ -272,16 +218,23 @@
mutex_init(&pcf->lock);
+ pcf->regmap = regmap_init_i2c(client, &pcf50633_regmap_config);
+ if (IS_ERR(pcf->regmap)) {
+ ret = PTR_ERR(pcf->regmap);
+ dev_err(pcf->dev, "Failed to allocate register map: %d\n",
+ ret);
+ goto err_free;
+ }
+
i2c_set_clientdata(client, pcf);
pcf->dev = &client->dev;
- pcf->i2c_client = client;
version = pcf50633_reg_read(pcf, 0);
variant = pcf50633_reg_read(pcf, 1);
if (version < 0 || variant < 0) {
dev_err(pcf->dev, "Unable to probe pcf50633\n");
ret = -ENODEV;
- goto err_free;
+ goto err_regmap;
}
dev_info(pcf->dev, "Probed device version %d variant %d\n",
@@ -328,6 +281,8 @@
return 0;
+err_regmap:
+ regmap_exit(pcf->regmap);
err_free:
kfree(pcf);
@@ -351,6 +306,7 @@
for (i = 0; i < PCF50633_NUM_REGULATORS; i++)
platform_device_unregister(pcf->regulator_pdev[i]);
+ regmap_exit(pcf->regmap);
kfree(pcf);
return 0;
diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c
index c27e515..de97974 100644
--- a/drivers/mfd/tc3589x.c
+++ b/drivers/mfd/tc3589x.c
@@ -357,6 +357,7 @@
return 0;
}
+#ifdef CONFIG_PM
static int tc3589x_suspend(struct device *dev)
{
struct tc3589x *tc3589x = dev_get_drvdata(dev);
@@ -387,6 +388,7 @@
static const SIMPLE_DEV_PM_OPS(tc3589x_dev_pm_ops, tc3589x_suspend,
tc3589x_resume);
+#endif
static const struct i2c_device_id tc3589x_id[] = {
{ "tc3589x", 24 },
diff --git a/drivers/mfd/timberdale.c b/drivers/mfd/timberdale.c
index 696879e..02d6569 100644
--- a/drivers/mfd/timberdale.c
+++ b/drivers/mfd/timberdale.c
@@ -697,7 +697,7 @@
dev_err(&dev->dev, "The driver supports an older "
"version of the FPGA, please update the driver to "
"support %d.%d\n", priv->fw.major, priv->fw.minor);
- goto err_ioremap;
+ goto err_config;
}
if (priv->fw.major < TIMB_SUPPORTED_MAJOR ||
priv->fw.minor < TIMB_REQUIRED_MINOR) {
@@ -705,13 +705,13 @@
"please upgrade the FPGA to at least: %d.%d\n",
priv->fw.major, priv->fw.minor,
TIMB_SUPPORTED_MAJOR, TIMB_REQUIRED_MINOR);
- goto err_ioremap;
+ goto err_config;
}
msix_entries = kzalloc(TIMBERDALE_NR_IRQS * sizeof(*msix_entries),
GFP_KERNEL);
if (!msix_entries)
- goto err_ioremap;
+ goto err_config;
for (i = 0; i < TIMBERDALE_NR_IRQS; i++)
msix_entries[i].entry = i;
@@ -825,6 +825,8 @@
err_create_file:
pci_disable_msix(dev);
err_msix:
+ kfree(msix_entries);
+err_config:
iounmap(priv->ctl_membase);
err_ioremap:
release_mem_region(priv->ctl_mapbase, CHIPCTLSIZE);
@@ -833,7 +835,6 @@
err_start:
pci_disable_device(dev);
err_enable:
- kfree(msix_entries);
kfree(priv);
pci_set_drvdata(dev, NULL);
return -ENODEV;
diff --git a/drivers/mfd/tps65912-core.c b/drivers/mfd/tps65912-core.c
index 955bc00..5fec23a 100644
--- a/drivers/mfd/tps65912-core.c
+++ b/drivers/mfd/tps65912-core.c
@@ -131,9 +131,6 @@
if (init_data == NULL)
return -ENOMEM;
- init_data->irq = pmic_plat_data->irq;
- init_data->irq_base = pmic_plat_data->irq;
-
mutex_init(&tps65912->io_mutex);
dev_set_drvdata(tps65912->dev, tps65912);
@@ -153,10 +150,13 @@
if (ret < 0)
goto err;
+ init_data->irq = pmic_plat_data->irq;
+ init_data->irq_base = pmic_plat_data->irq;
ret = tps65912_irq_init(tps65912, init_data->irq, init_data);
if (ret < 0)
goto err;
+ kfree(init_data);
return ret;
err:
diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c
index 01ecfee..b8eef46 100644
--- a/drivers/mfd/twl-core.c
+++ b/drivers/mfd/twl-core.c
@@ -109,7 +109,7 @@
#define twl_has_watchdog() false
#endif
-#if defined(CONFIG_TWL4030_CODEC) || defined(CONFIG_TWL4030_CODEC_MODULE) ||\
+#if defined(CONFIG_MFD_TWL4030_AUDIO) || defined(CONFIG_MFD_TWL4030_AUDIO_MODULE) ||\
defined(CONFIG_TWL6040_CORE) || defined(CONFIG_TWL6040_CORE_MODULE)
#define twl_has_codec() true
#else
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index 8a7ee31..f062c8c 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -30,7 +30,6 @@
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
-#include <linux/kthread.h>
#include <linux/slab.h>
#include <linux/i2c/twl.h>
@@ -278,59 +277,6 @@
static unsigned twl4030_irq_base;
-static struct completion irq_event;
-
-/*
- * This thread processes interrupts reported by the Primary Interrupt Handler.
- */
-static int twl4030_irq_thread(void *data)
-{
- long irq = (long)data;
- static unsigned i2c_errors;
- static const unsigned max_i2c_errors = 100;
-
-
- current->flags |= PF_NOFREEZE;
-
- while (!kthread_should_stop()) {
- int ret;
- int module_irq;
- u8 pih_isr;
-
- /* Wait for IRQ, then read PIH irq status (also blocking) */
- wait_for_completion_interruptible(&irq_event);
-
- ret = twl_i2c_read_u8(TWL4030_MODULE_PIH, &pih_isr,
- REG_PIH_ISR_P1);
- if (ret) {
- pr_warning("twl4030: I2C error %d reading PIH ISR\n",
- ret);
- if (++i2c_errors >= max_i2c_errors) {
- printk(KERN_ERR "Maximum I2C error count"
- " exceeded. Terminating %s.\n",
- __func__);
- break;
- }
- complete(&irq_event);
- continue;
- }
-
- /* these handlers deal with the relevant SIH irq status */
- local_irq_disable();
- for (module_irq = twl4030_irq_base;
- pih_isr;
- pih_isr >>= 1, module_irq++) {
- if (pih_isr & 0x1)
- generic_handle_irq(module_irq);
- }
- local_irq_enable();
-
- enable_irq(irq);
- }
-
- return 0;
-}
-
/*
* handle_twl4030_pih() is the desc->handle method for the twl4030 interrupt.
* This is a chained interrupt, so there is no desc->action method for it.
@@ -342,9 +288,25 @@
*/
static irqreturn_t handle_twl4030_pih(int irq, void *devid)
{
- /* Acknowledge, clear *AND* mask the interrupt... */
- disable_irq_nosync(irq);
- complete(devid);
+ int module_irq;
+ irqreturn_t ret;
+ u8 pih_isr;
+
+ ret = twl_i2c_read_u8(TWL4030_MODULE_PIH, &pih_isr,
+ REG_PIH_ISR_P1);
+ if (ret) {
+ pr_warning("twl4030: I2C error %d reading PIH ISR\n", ret);
+ return IRQ_NONE;
+ }
+
+ /* these handlers deal with the relevant SIH irq status */
+ for (module_irq = twl4030_irq_base;
+ pih_isr;
+ pih_isr >>= 1, module_irq++) {
+ if (pih_isr & 0x1)
+ handle_nested_irq(module_irq);
+ }
+
return IRQ_HANDLED;
}
/*----------------------------------------------------------------------*/
@@ -460,114 +422,18 @@
/*----------------------------------------------------------------------*/
-static DEFINE_SPINLOCK(sih_agent_lock);
-
-static struct workqueue_struct *wq;
-
struct sih_agent {
int irq_base;
const struct sih *sih;
u32 imr;
bool imr_change_pending;
- struct work_struct mask_work;
u32 edge_change;
- struct work_struct edge_work;
+
+ struct mutex irq_lock;
};
-static void twl4030_sih_do_mask(struct work_struct *work)
-{
- struct sih_agent *agent;
- const struct sih *sih;
- union {
- u8 bytes[4];
- u32 word;
- } imr;
- int status;
-
- agent = container_of(work, struct sih_agent, mask_work);
-
- /* see what work we have */
- spin_lock_irq(&sih_agent_lock);
- if (agent->imr_change_pending) {
- sih = agent->sih;
- /* byte[0] gets overwritten as we write ... */
- imr.word = cpu_to_le32(agent->imr << 8);
- agent->imr_change_pending = false;
- } else
- sih = NULL;
- spin_unlock_irq(&sih_agent_lock);
- if (!sih)
- return;
-
- /* write the whole mask ... simpler than subsetting it */
- status = twl_i2c_write(sih->module, imr.bytes,
- sih->mask[irq_line].imr_offset, sih->bytes_ixr);
- if (status)
- pr_err("twl4030: %s, %s --> %d\n", __func__,
- "write", status);
-}
-
-static void twl4030_sih_do_edge(struct work_struct *work)
-{
- struct sih_agent *agent;
- const struct sih *sih;
- u8 bytes[6];
- u32 edge_change;
- int status;
-
- agent = container_of(work, struct sih_agent, edge_work);
-
- /* see what work we have */
- spin_lock_irq(&sih_agent_lock);
- edge_change = agent->edge_change;
- agent->edge_change = 0;
- sih = edge_change ? agent->sih : NULL;
- spin_unlock_irq(&sih_agent_lock);
- if (!sih)
- return;
-
- /* Read, reserving first byte for write scratch. Yes, this
- * could be cached for some speedup ... but be careful about
- * any processor on the other IRQ line, EDR registers are
- * shared.
- */
- status = twl_i2c_read(sih->module, bytes + 1,
- sih->edr_offset, sih->bytes_edr);
- if (status) {
- pr_err("twl4030: %s, %s --> %d\n", __func__,
- "read", status);
- return;
- }
-
- /* Modify only the bits we know must change */
- while (edge_change) {
- int i = fls(edge_change) - 1;
- struct irq_data *idata = irq_get_irq_data(i + agent->irq_base);
- int byte = 1 + (i >> 2);
- int off = (i & 0x3) * 2;
- unsigned int type;
-
- bytes[byte] &= ~(0x03 << off);
-
- type = irqd_get_trigger_type(idata);
- if (type & IRQ_TYPE_EDGE_RISING)
- bytes[byte] |= BIT(off + 1);
- if (type & IRQ_TYPE_EDGE_FALLING)
- bytes[byte] |= BIT(off + 0);
-
- edge_change &= ~BIT(i);
- }
-
- /* Write */
- status = twl_i2c_write(sih->module, bytes,
- sih->edr_offset, sih->bytes_edr);
- if (status)
- pr_err("twl4030: %s, %s --> %d\n", __func__,
- "write", status);
-}
-
/*----------------------------------------------------------------------*/
/*
@@ -579,50 +445,125 @@
static void twl4030_sih_mask(struct irq_data *data)
{
- struct sih_agent *sih = irq_data_get_irq_chip_data(data);
- unsigned long flags;
+ struct sih_agent *agent = irq_data_get_irq_chip_data(data);
- spin_lock_irqsave(&sih_agent_lock, flags);
- sih->imr |= BIT(data->irq - sih->irq_base);
- sih->imr_change_pending = true;
- queue_work(wq, &sih->mask_work);
- spin_unlock_irqrestore(&sih_agent_lock, flags);
+ agent->imr |= BIT(data->irq - agent->irq_base);
+ agent->imr_change_pending = true;
}
static void twl4030_sih_unmask(struct irq_data *data)
{
- struct sih_agent *sih = irq_data_get_irq_chip_data(data);
- unsigned long flags;
+ struct sih_agent *agent = irq_data_get_irq_chip_data(data);
- spin_lock_irqsave(&sih_agent_lock, flags);
- sih->imr &= ~BIT(data->irq - sih->irq_base);
- sih->imr_change_pending = true;
- queue_work(wq, &sih->mask_work);
- spin_unlock_irqrestore(&sih_agent_lock, flags);
+ agent->imr &= ~BIT(data->irq - agent->irq_base);
+ agent->imr_change_pending = true;
}
static int twl4030_sih_set_type(struct irq_data *data, unsigned trigger)
{
- struct sih_agent *sih = irq_data_get_irq_chip_data(data);
- unsigned long flags;
+ struct sih_agent *agent = irq_data_get_irq_chip_data(data);
if (trigger & ~(IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
return -EINVAL;
- spin_lock_irqsave(&sih_agent_lock, flags);
- if (irqd_get_trigger_type(data) != trigger) {
- sih->edge_change |= BIT(data->irq - sih->irq_base);
- queue_work(wq, &sih->edge_work);
- }
- spin_unlock_irqrestore(&sih_agent_lock, flags);
+ if (irqd_get_trigger_type(data) != trigger)
+ agent->edge_change |= BIT(data->irq - agent->irq_base);
+
return 0;
}
+static void twl4030_sih_bus_lock(struct irq_data *data)
+{
+ struct sih_agent *agent = irq_data_get_irq_chip_data(data);
+
+ mutex_lock(&agent->irq_lock);
+}
+
+static void twl4030_sih_bus_sync_unlock(struct irq_data *data)
+{
+ struct sih_agent *agent = irq_data_get_irq_chip_data(data);
+ const struct sih *sih = agent->sih;
+ int status;
+
+ if (agent->imr_change_pending) {
+ union {
+ u32 word;
+ u8 bytes[4];
+ } imr;
+
+ /* byte[0] gets overwriten as we write ... */
+ imr.word = cpu_to_le32(agent->imr << 8);
+ agent->imr_change_pending = false;
+
+ /* write the whole mask ... simpler than subsetting it */
+ status = twl_i2c_write(sih->module, imr.bytes,
+ sih->mask[irq_line].imr_offset,
+ sih->bytes_ixr);
+ if (status)
+ pr_err("twl4030: %s, %s --> %d\n", __func__,
+ "write", status);
+ }
+
+ if (agent->edge_change) {
+ u32 edge_change;
+ u8 bytes[6];
+
+ edge_change = agent->edge_change;
+ agent->edge_change = 0;
+
+ /*
+ * Read, reserving first byte for write scratch. Yes, this
+ * could be cached for some speedup ... but be careful about
+ * any processor on the other IRQ line, EDR registers are
+ * shared.
+ */
+ status = twl_i2c_read(sih->module, bytes + 1,
+ sih->edr_offset, sih->bytes_edr);
+ if (status) {
+ pr_err("twl4030: %s, %s --> %d\n", __func__,
+ "read", status);
+ return;
+ }
+
+ /* Modify only the bits we know must change */
+ while (edge_change) {
+ int i = fls(edge_change) - 1;
+ struct irq_data *idata;
+ int byte = 1 + (i >> 2);
+ int off = (i & 0x3) * 2;
+ unsigned int type;
+
+ idata = irq_get_irq_data(i + agent->irq_base);
+
+ bytes[byte] &= ~(0x03 << off);
+
+ type = irqd_get_trigger_type(idata);
+ if (type & IRQ_TYPE_EDGE_RISING)
+ bytes[byte] |= BIT(off + 1);
+ if (type & IRQ_TYPE_EDGE_FALLING)
+ bytes[byte] |= BIT(off + 0);
+
+ edge_change &= ~BIT(i);
+ }
+
+ /* Write */
+ status = twl_i2c_write(sih->module, bytes,
+ sih->edr_offset, sih->bytes_edr);
+ if (status)
+ pr_err("twl4030: %s, %s --> %d\n", __func__,
+ "write", status);
+ }
+
+ mutex_unlock(&agent->irq_lock);
+}
+
static struct irq_chip twl4030_sih_irq_chip = {
.name = "twl4030",
- .irq_mask = twl4030_sih_mask,
+ .irq_mask = twl4030_sih_mask,
.irq_unmask = twl4030_sih_unmask,
.irq_set_type = twl4030_sih_set_type,
+ .irq_bus_lock = twl4030_sih_bus_lock,
+ .irq_bus_sync_unlock = twl4030_sih_bus_sync_unlock,
};
/*----------------------------------------------------------------------*/
@@ -655,9 +596,7 @@
int isr;
/* reading ISR acks the IRQs, using clear-on-read mode */
- local_irq_enable();
isr = sih_read_isr(sih);
- local_irq_disable();
if (isr < 0) {
pr_err("twl4030: %s SIH, read ISR error %d\n",
@@ -672,7 +611,7 @@
isr &= ~BIT(irq);
if (irq < sih->bits)
- generic_handle_irq(agent->irq_base + irq);
+ handle_nested_irq(agent->irq_base + irq);
else
pr_err("twl4030: %s SIH, invalid ISR bit %d\n",
sih->name, irq);
@@ -718,15 +657,14 @@
agent->irq_base = irq_base;
agent->sih = sih;
agent->imr = ~0;
- INIT_WORK(&agent->mask_work, twl4030_sih_do_mask);
- INIT_WORK(&agent->edge_work, twl4030_sih_do_edge);
+ mutex_init(&agent->irq_lock);
for (i = 0; i < sih->bits; i++) {
irq = irq_base + i;
+ irq_set_chip_data(irq, agent);
irq_set_chip_and_handler(irq, &twl4030_sih_irq_chip,
handle_edge_irq);
- irq_set_chip_data(irq, agent);
activate_irq(irq);
}
@@ -758,7 +696,6 @@
int status;
int i;
- struct task_struct *task;
/*
* Mask and clear all TWL4030 interrupts since initially we do
@@ -768,12 +705,6 @@
if (status < 0)
return status;
- wq = create_singlethread_workqueue("twl4030-irqchip");
- if (!wq) {
- pr_err("twl4030: workqueue FAIL\n");
- return -ESRCH;
- }
-
twl4030_irq_base = irq_base;
/* install an irq handler for each of the SIH modules;
@@ -787,6 +718,7 @@
for (i = irq_base; i < irq_end; i++) {
irq_set_chip_and_handler(i, &twl4030_irq_chip,
handle_simple_irq);
+ irq_set_nested_thread(i, 1);
activate_irq(i);
}
twl4030_irq_next = i;
@@ -801,34 +733,22 @@
}
/* install an irq handler to demultiplex the TWL4030 interrupt */
-
-
- init_completion(&irq_event);
-
- status = request_irq(irq_num, handle_twl4030_pih, IRQF_DISABLED,
- "TWL4030-PIH", &irq_event);
+ status = request_threaded_irq(irq_num, NULL, handle_twl4030_pih, 0,
+ "TWL4030-PIH", NULL);
if (status < 0) {
pr_err("twl4030: could not claim irq%d: %d\n", irq_num, status);
goto fail_rqirq;
}
- task = kthread_run(twl4030_irq_thread, (void *)(long)irq_num,
- "twl4030-irq");
- if (IS_ERR(task)) {
- pr_err("twl4030: could not create irq %d thread!\n", irq_num);
- status = PTR_ERR(task);
- goto fail_kthread;
- }
return status;
-fail_kthread:
- free_irq(irq_num, &irq_event);
fail_rqirq:
/* clean up twl4030_sih_setup */
fail:
- for (i = irq_base; i < irq_end; i++)
+ for (i = irq_base; i < irq_end; i++) {
+ irq_set_nested_thread(i, 0);
irq_set_chip_and_handler(i, NULL, NULL);
- destroy_workqueue(wq);
- wq = NULL;
+ }
+
return status;
}
diff --git a/drivers/mfd/twl4030-madc.c b/drivers/mfd/twl4030-madc.c
index 7cbf2aa..834f824 100644
--- a/drivers/mfd/twl4030-madc.c
+++ b/drivers/mfd/twl4030-madc.c
@@ -740,6 +740,28 @@
TWL4030_BCI_BCICTL1);
goto err_i2c;
}
+
+ /* Check that MADC clock is on */
+ ret = twl_i2c_read_u8(TWL4030_MODULE_INTBR, ®val, TWL4030_REG_GPBR1);
+ if (ret) {
+ dev_err(&pdev->dev, "unable to read reg GPBR1 0x%X\n",
+ TWL4030_REG_GPBR1);
+ goto err_i2c;
+ }
+
+ /* If MADC clk is not on, turn it on */
+ if (!(regval & TWL4030_GPBR1_MADC_HFCLK_EN)) {
+ dev_info(&pdev->dev, "clk disabled, enabling\n");
+ regval |= TWL4030_GPBR1_MADC_HFCLK_EN;
+ ret = twl_i2c_write_u8(TWL4030_MODULE_INTBR, regval,
+ TWL4030_REG_GPBR1);
+ if (ret) {
+ dev_err(&pdev->dev, "unable to write reg GPBR1 0x%X\n",
+ TWL4030_REG_GPBR1);
+ goto err_i2c;
+ }
+ }
+
platform_set_drvdata(pdev, madc);
mutex_init(&madc->lock);
ret = request_threaded_irq(platform_get_irq(pdev, 0), NULL,
diff --git a/drivers/mfd/twl6030-irq.c b/drivers/mfd/twl6030-irq.c
index eb3b5f8..deec3ec 100644
--- a/drivers/mfd/twl6030-irq.c
+++ b/drivers/mfd/twl6030-irq.c
@@ -37,6 +37,7 @@
#include <linux/kthread.h>
#include <linux/i2c/twl.h>
#include <linux/platform_device.h>
+#include <linux/suspend.h>
#include "twl-core.h"
@@ -83,8 +84,48 @@
/*----------------------------------------------------------------------*/
static unsigned twl6030_irq_base;
+static int twl_irq;
+static bool twl_irq_wake_enabled;
static struct completion irq_event;
+static atomic_t twl6030_wakeirqs = ATOMIC_INIT(0);
+
+static int twl6030_irq_pm_notifier(struct notifier_block *notifier,
+ unsigned long pm_event, void *unused)
+{
+ int chained_wakeups;
+
+ switch (pm_event) {
+ case PM_SUSPEND_PREPARE:
+ chained_wakeups = atomic_read(&twl6030_wakeirqs);
+
+ if (chained_wakeups && !twl_irq_wake_enabled) {
+ if (enable_irq_wake(twl_irq))
+ pr_err("twl6030 IRQ wake enable failed\n");
+ else
+ twl_irq_wake_enabled = true;
+ } else if (!chained_wakeups && twl_irq_wake_enabled) {
+ disable_irq_wake(twl_irq);
+ twl_irq_wake_enabled = false;
+ }
+
+ disable_irq(twl_irq);
+ break;
+
+ case PM_POST_SUSPEND:
+ enable_irq(twl_irq);
+ break;
+
+ default:
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block twl6030_irq_pm_notifier_block = {
+ .notifier_call = twl6030_irq_pm_notifier,
+};
/*
* This thread processes interrupts reported by the Primary Interrupt Handler.
@@ -187,6 +228,16 @@
#endif
}
+int twl6030_irq_set_wake(struct irq_data *d, unsigned int on)
+{
+ if (on)
+ atomic_inc(&twl6030_wakeirqs);
+ else
+ atomic_dec(&twl6030_wakeirqs);
+
+ return 0;
+}
+
/*----------------------------------------------------------------------*/
static unsigned twl6030_irq_next;
@@ -318,10 +369,12 @@
twl6030_irq_chip = dummy_irq_chip;
twl6030_irq_chip.name = "twl6030";
twl6030_irq_chip.irq_set_type = NULL;
+ twl6030_irq_chip.irq_set_wake = twl6030_irq_set_wake;
for (i = irq_base; i < irq_end; i++) {
irq_set_chip_and_handler(i, &twl6030_irq_chip,
handle_simple_irq);
+ irq_set_chip_data(i, (void *)irq_num);
activate_irq(i);
}
@@ -331,6 +384,14 @@
/* install an irq handler to demultiplex the TWL6030 interrupt */
init_completion(&irq_event);
+
+ status = request_irq(irq_num, handle_twl6030_pih, 0,
+ "TWL6030-PIH", &irq_event);
+ if (status < 0) {
+ pr_err("twl6030: could not claim irq%d: %d\n", irq_num, status);
+ goto fail_irq;
+ }
+
task = kthread_run(twl6030_irq_thread, (void *)irq_num, "twl6030-irq");
if (IS_ERR(task)) {
pr_err("twl6030: could not create irq %d thread!\n", irq_num);
@@ -338,17 +399,14 @@
goto fail_kthread;
}
- status = request_irq(irq_num, handle_twl6030_pih, IRQF_DISABLED,
- "TWL6030-PIH", &irq_event);
- if (status < 0) {
- pr_err("twl6030: could not claim irq%d: %d\n", irq_num, status);
- goto fail_irq;
- }
+ twl_irq = irq_num;
+ register_pm_notifier(&twl6030_irq_pm_notifier_block);
return status;
-fail_irq:
- free_irq(irq_num, &irq_event);
fail_kthread:
+ free_irq(irq_num, &irq_event);
+
+fail_irq:
for (i = irq_base; i < irq_end; i++)
irq_set_chip_and_handler(i, NULL, NULL);
return status;
@@ -356,6 +414,7 @@
int twl6030_exit_irq(void)
{
+ unregister_pm_notifier(&twl6030_irq_pm_notifier_block);
if (twl6030_irq_base) {
pr_err("twl6030: can't yet clean up IRQs?\n");
diff --git a/drivers/mfd/wm831x-irq.c b/drivers/mfd/wm831x-irq.c
index ada1835..f4747a4 100644
--- a/drivers/mfd/wm831x-irq.c
+++ b/drivers/mfd/wm831x-irq.c
@@ -420,12 +420,19 @@
switch (type) {
case IRQ_TYPE_EDGE_BOTH:
wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_INT_MODE;
+ wm831x->gpio_level[irq] = false;
break;
case IRQ_TYPE_EDGE_RISING:
wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_POL;
+ wm831x->gpio_level[irq] = false;
break;
case IRQ_TYPE_EDGE_FALLING:
wm831x->gpio_update[irq] = 0x10000;
+ wm831x->gpio_level[irq] = false;
+ break;
+ case IRQ_TYPE_LEVEL_HIGH:
+ wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_POL;
+ wm831x->gpio_level[irq] = true;
break;
default:
return -EINVAL;
@@ -449,7 +456,7 @@
{
struct wm831x *wm831x = data;
unsigned int i;
- int primary, status_addr;
+ int primary, status_addr, ret;
int status_regs[WM831X_NUM_IRQ_REGS] = { 0 };
int read[WM831X_NUM_IRQ_REGS] = { 0 };
int *status;
@@ -507,6 +514,19 @@
if (*status & wm831x_irqs[i].mask)
handle_nested_irq(wm831x->irq_base + i);
+
+ /* Simulate an edge triggered IRQ by polling the input
+ * status. This is sucky but improves interoperability.
+ */
+ if (primary == WM831X_GP_INT &&
+ wm831x->gpio_level[i - WM831X_IRQ_GPIO_1]) {
+ ret = wm831x_reg_read(wm831x, WM831X_GPIO_LEVEL);
+ while (ret & 1 << (i - WM831X_IRQ_GPIO_1)) {
+ handle_nested_irq(wm831x->irq_base + i);
+ ret = wm831x_reg_read(wm831x,
+ WM831X_GPIO_LEVEL);
+ }
+ }
}
out:
@@ -596,8 +616,6 @@
"No interrupt specified - functionality limited\n");
}
-
-
/* Enable top level interrupts, we mask at secondary level */
wm831x_reg_write(wm831x, WM831X_SYSTEM_INTERRUPTS_MASK, 0);
diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index b03be1d..5d6ba13 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -217,6 +217,47 @@
return 0;
}
+ ret = wm8994_reg_read(wm8994, WM8994_POWER_MANAGEMENT_4);
+ if (ret < 0) {
+ dev_err(dev, "Failed to read power status: %d\n", ret);
+ } else if (ret & (WM8994_AIF2ADCL_ENA | WM8994_AIF2ADCR_ENA |
+ WM8994_AIF1ADC2L_ENA | WM8994_AIF1ADC2R_ENA |
+ WM8994_AIF1ADC1L_ENA | WM8994_AIF1ADC1R_ENA)) {
+ dev_dbg(dev, "CODEC still active, ignoring suspend\n");
+ return 0;
+ }
+
+ ret = wm8994_reg_read(wm8994, WM8994_POWER_MANAGEMENT_5);
+ if (ret < 0) {
+ dev_err(dev, "Failed to read power status: %d\n", ret);
+ } else if (ret & (WM8994_AIF2DACL_ENA | WM8994_AIF2DACR_ENA |
+ WM8994_AIF1DAC2L_ENA | WM8994_AIF1DAC2R_ENA |
+ WM8994_AIF1DAC1L_ENA | WM8994_AIF1DAC1R_ENA)) {
+ dev_dbg(dev, "CODEC still active, ignoring suspend\n");
+ return 0;
+ }
+
+ switch (wm8994->type) {
+ case WM8958:
+ ret = wm8994_reg_read(wm8994, WM8958_MIC_DETECT_1);
+ if (ret < 0) {
+ dev_err(dev, "Failed to read power status: %d\n", ret);
+ } else if (ret & WM8958_MICD_ENA) {
+ dev_dbg(dev, "CODEC still active, ignoring suspend\n");
+ return 0;
+ }
+ break;
+ default:
+ break;
+ }
+
+ /* Disable LDO pulldowns while the device is suspended if we
+ * don't know that something will be driving them. */
+ if (!wm8994->ldo_ena_always_driven)
+ wm8994_set_bits(wm8994, WM8994_PULL_CONTROL_2,
+ WM8994_LDO1ENA_PD | WM8994_LDO2ENA_PD,
+ WM8994_LDO1ENA_PD | WM8994_LDO2ENA_PD);
+
/* GPIO configuration state is saved here since we may be configuring
* the GPIO alternate functions even if we're not using the gpiolib
* driver for them.
@@ -286,6 +327,11 @@
if (ret < 0)
dev_err(dev, "Failed to restore GPIO registers: %d\n", ret);
+ /* Disable LDO pulldowns while the device is active */
+ wm8994_set_bits(wm8994, WM8994_PULL_CONTROL_2,
+ WM8994_LDO1ENA_PD | WM8994_LDO2ENA_PD,
+ 0);
+
wm8994->suspended = false;
return 0;
@@ -467,8 +513,15 @@
pdata->gpio_defaults[i]);
}
}
+
+ wm8994->ldo_ena_always_driven = pdata->ldo_ena_always_driven;
}
+ /* Disable LDO pulldowns while the device is active */
+ wm8994_set_bits(wm8994, WM8994_PULL_CONTROL_2,
+ WM8994_LDO1ENA_PD | WM8994_LDO2ENA_PD,
+ 0);
+
/* In some system designs where the regulators are not in use,
* we can achieve a small reduction in leakage currents by
* floating LDO outputs. This bit makes no difference if the
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index 053d36c..cd41d40 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -151,7 +151,7 @@
struct vmballoon_stats {
unsigned int timer;
- /* allocation statustics */
+ /* allocation statistics */
unsigned int alloc;
unsigned int alloc_fail;
unsigned int sleep_alloc;
@@ -412,6 +412,7 @@
gfp_t flags;
unsigned int hv_status;
bool locked = false;
+ flags = can_sleep ? VMW_PAGE_ALLOC_CANSLEEP : VMW_PAGE_ALLOC_NOSLEEP;
do {
if (!can_sleep)
@@ -419,7 +420,6 @@
else
STATS_INC(b->stats.sleep_alloc);
- flags = can_sleep ? VMW_PAGE_ALLOC_CANSLEEP : VMW_PAGE_ALLOC_NOSLEEP;
page = alloc_page(flags);
if (!page) {
if (!can_sleep)
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 87d5067..cf444b0 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -263,7 +263,7 @@
config MMC_AU1X
tristate "Alchemy AU1XX0 MMC Card Interface support"
- depends on SOC_AU1200
+ depends on MIPS_ALCHEMY
help
This selects the AMD Alchemy(R) Multimedia card interface.
If you have a Alchemy platform with a MMC slot, say Y or M here.
diff --git a/drivers/mmc/host/au1xmmc.c b/drivers/mmc/host/au1xmmc.c
index 707bc7d..5d3b9ae 100644
--- a/drivers/mmc/host/au1xmmc.c
+++ b/drivers/mmc/host/au1xmmc.c
@@ -64,11 +64,8 @@
#define AU1XMMC_DESCRIPTOR_COUNT 1
/* max DMA seg size: 64KB on Au1100, 4MB on Au1200 */
-#ifdef CONFIG_SOC_AU1100
-#define AU1XMMC_DESCRIPTOR_SIZE 0x0000ffff
-#else /* Au1200 */
-#define AU1XMMC_DESCRIPTOR_SIZE 0x003fffff
-#endif
+#define AU1100_MMC_DESCRIPTOR_SIZE 0x0000ffff
+#define AU1200_MMC_DESCRIPTOR_SIZE 0x003fffff
#define AU1XMMC_OCR (MMC_VDD_27_28 | MMC_VDD_28_29 | MMC_VDD_29_30 | \
MMC_VDD_30_31 | MMC_VDD_31_32 | MMC_VDD_32_33 | \
@@ -127,6 +124,7 @@
#define HOST_F_XMIT 0x0001
#define HOST_F_RECV 0x0002
#define HOST_F_DMA 0x0010
+#define HOST_F_DBDMA 0x0020
#define HOST_F_ACTIVE 0x0100
#define HOST_F_STOP 0x1000
@@ -151,6 +149,16 @@
#define DMA_CHANNEL(h) \
(((h)->flags & HOST_F_XMIT) ? (h)->tx_chan : (h)->rx_chan)
+static inline int has_dbdma(void)
+{
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1200:
+ return 1;
+ default:
+ return 0;
+ }
+}
+
static inline void IRQ_ON(struct au1xmmc_host *host, u32 mask)
{
u32 val = au_readl(HOST_CONFIG(host));
@@ -353,14 +361,12 @@
data->bytes_xfered = 0;
if (!data->error) {
- if (host->flags & HOST_F_DMA) {
-#ifdef CONFIG_SOC_AU1200 /* DBDMA */
+ if (host->flags & (HOST_F_DMA | HOST_F_DBDMA)) {
u32 chan = DMA_CHANNEL(host);
chan_tab_t *c = *((chan_tab_t **)chan);
au1x_dma_chan_t *cp = c->chan_ptr;
data->bytes_xfered = cp->ddma_bytecnt;
-#endif
} else
data->bytes_xfered =
(data->blocks * data->blksz) - host->pio.len;
@@ -570,11 +576,10 @@
host->status = HOST_S_DATA;
- if (host->flags & HOST_F_DMA) {
-#ifdef CONFIG_SOC_AU1200 /* DBDMA */
+ if ((host->flags & (HOST_F_DMA | HOST_F_DBDMA))) {
u32 channel = DMA_CHANNEL(host);
- /* Start the DMA as soon as the buffer gets something in it */
+ /* Start the DBDMA as soon as the buffer gets something in it */
if (host->flags & HOST_F_RECV) {
u32 mask = SD_STATUS_DB | SD_STATUS_NE;
@@ -584,7 +589,6 @@
}
au1xxx_dbdma_start(channel);
-#endif
}
}
@@ -633,8 +637,7 @@
au_writel(data->blksz - 1, HOST_BLKSIZE(host));
- if (host->flags & HOST_F_DMA) {
-#ifdef CONFIG_SOC_AU1200 /* DBDMA */
+ if (host->flags & (HOST_F_DMA | HOST_F_DBDMA)) {
int i;
u32 channel = DMA_CHANNEL(host);
@@ -663,7 +666,6 @@
datalen -= len;
}
-#endif
} else {
host->pio.index = 0;
host->pio.offset = 0;
@@ -838,7 +840,6 @@
return IRQ_HANDLED;
}
-#ifdef CONFIG_SOC_AU1200
/* 8bit memory DMA device */
static dbdev_tab_t au1xmmc_mem_dbdev = {
.dev_id = DSCR_CMD0_ALWAYS,
@@ -905,7 +906,7 @@
au1xxx_dbdma_ring_alloc(host->rx_chan, AU1XMMC_DESCRIPTOR_COUNT);
/* DBDMA is good to go */
- host->flags |= HOST_F_DMA;
+ host->flags |= HOST_F_DMA | HOST_F_DBDMA;
return 0;
}
@@ -918,7 +919,6 @@
au1xxx_dbdma_chan_free(host->rx_chan);
}
}
-#endif
static void au1xmmc_enable_sdio_irq(struct mmc_host *mmc, int en)
{
@@ -997,8 +997,16 @@
mmc->f_min = 450000;
mmc->f_max = 24000000;
- mmc->max_seg_size = AU1XMMC_DESCRIPTOR_SIZE;
- mmc->max_segs = AU1XMMC_DESCRIPTOR_COUNT;
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1100:
+ mmc->max_seg_size = AU1100_MMC_DESCRIPTOR_SIZE;
+ mmc->max_segs = AU1XMMC_DESCRIPTOR_COUNT;
+ break;
+ case ALCHEMY_CPU_AU1200:
+ mmc->max_seg_size = AU1200_MMC_DESCRIPTOR_SIZE;
+ mmc->max_segs = AU1XMMC_DESCRIPTOR_COUNT;
+ break;
+ }
mmc->max_blk_size = 2048;
mmc->max_blk_count = 512;
@@ -1028,11 +1036,11 @@
tasklet_init(&host->finish_task, au1xmmc_tasklet_finish,
(unsigned long)host);
-#ifdef CONFIG_SOC_AU1200
- ret = au1xmmc_dbdma_init(host);
- if (ret)
- pr_info(DRIVER_NAME ": DBDMA init failed; using PIO\n");
-#endif
+ if (has_dbdma()) {
+ ret = au1xmmc_dbdma_init(host);
+ if (ret)
+ pr_info(DRIVER_NAME ": DBDMA init failed; using PIO\n");
+ }
#ifdef CONFIG_LEDS_CLASS
if (host->platdata && host->platdata->led) {
@@ -1073,9 +1081,8 @@
au_writel(0, HOST_CONFIG2(host));
au_sync();
-#ifdef CONFIG_SOC_AU1200
- au1xmmc_dbdma_shutdown(host);
-#endif
+ if (host->flags & HOST_F_DBDMA)
+ au1xmmc_dbdma_shutdown(host);
tasklet_kill(&host->data_task);
tasklet_kill(&host->finish_task);
@@ -1120,9 +1127,9 @@
tasklet_kill(&host->data_task);
tasklet_kill(&host->finish_task);
-#ifdef CONFIG_SOC_AU1200
- au1xmmc_dbdma_shutdown(host);
-#endif
+ if (host->flags & HOST_F_DBDMA)
+ au1xmmc_dbdma_shutdown(host);
+
au1xmmc_set_power(host, 0);
free_irq(host->irq, host);
@@ -1181,24 +1188,23 @@
static int __init au1xmmc_init(void)
{
-#ifdef CONFIG_SOC_AU1200
- /* DSCR_CMD0_ALWAYS has a stride of 32 bits, we need a stride
- * of 8 bits. And since devices are shared, we need to create
- * our own to avoid freaking out other devices.
- */
- memid = au1xxx_ddma_add_device(&au1xmmc_mem_dbdev);
- if (!memid)
- pr_err("au1xmmc: cannot add memory dbdma dev\n");
-#endif
+ if (has_dbdma()) {
+ /* DSCR_CMD0_ALWAYS has a stride of 32 bits, we need a stride
+ * of 8 bits. And since devices are shared, we need to create
+ * our own to avoid freaking out other devices.
+ */
+ memid = au1xxx_ddma_add_device(&au1xmmc_mem_dbdev);
+ if (!memid)
+ pr_err("au1xmmc: cannot add memory dbdma\n");
+ }
return platform_driver_register(&au1xmmc_driver);
}
static void __exit au1xmmc_exit(void)
{
-#ifdef CONFIG_SOC_AU1200
- if (memid)
+ if (has_dbdma() && memid)
au1xxx_ddma_del_device(memid);
-#endif
+
platform_driver_unregister(&au1xmmc_driver);
}
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index e8ff123..101cd31 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -1270,7 +1270,7 @@
}
} else {
if (!host->protect_card) {
- pr_info"%s: cover is open, "
+ pr_info("%s: cover is open, "
"card is now inaccessible\n",
mmc_hostname(host->mmc));
host->protect_card = 1;
diff --git a/drivers/mtd/maps/lantiq-flash.c b/drivers/mtd/maps/lantiq-flash.c
index a90cabd..7e50896 100644
--- a/drivers/mtd/maps/lantiq-flash.c
+++ b/drivers/mtd/maps/lantiq-flash.c
@@ -182,7 +182,7 @@
parts = ltq_mtd_data->parts;
}
- err = add_mtd_partitions(ltq_mtd->mtd, parts, nr_parts);
+ err = mtd_device_register(ltq_mtd->mtd, parts, nr_parts);
if (err) {
dev_err(&pdev->dev, "failed to add partitions\n");
goto err_destroy;
@@ -208,7 +208,7 @@
if (ltq_mtd) {
if (ltq_mtd->mtd) {
- del_mtd_partitions(ltq_mtd->mtd);
+ mtd_device_unregister(ltq_mtd->mtd);
map_destroy(ltq_mtd->mtd);
}
if (ltq_mtd->map->virt)
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index f1af222..61086ea 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -1144,7 +1144,7 @@
if (mtd_ino) {
/* Destroy the inode if it exists */
- mtd_ino->i_nlink = 0;
+ clear_nlink(mtd_ino);
iput(mtd_ino);
}
}
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 4c34252..dbfa0f7 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -138,7 +138,7 @@
config MTD_NAND_AU1550
tristate "Au1550/1200 NAND support"
- depends on SOC_AU1200 || SOC_AU1550
+ depends on MIPS_ALCHEMY
help
This enables the driver for the NAND flash controller on the
AMD/Alchemy 1550 SOC.
diff --git a/drivers/mtd/nand/au1550nd.c b/drivers/mtd/nand/au1550nd.c
index e7767ee..fa5736b 100644
--- a/drivers/mtd/nand/au1550nd.c
+++ b/drivers/mtd/nand/au1550nd.c
@@ -19,7 +19,11 @@
#include <linux/mtd/partitions.h>
#include <asm/io.h>
-#include <asm/mach-au1x00/au1xxx.h>
+#ifdef CONFIG_MIPS_PB1550
+#include <asm/mach-pb1x00/pb1550.h>
+#elif defined(CONFIG_MIPS_DB1550)
+#include <asm/mach-db1x00/db1x00.h>
+#endif
#include <asm/mach-db1x00/bcsr.h>
/*
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c34cc1e..b2b9109 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -550,7 +550,7 @@
/*
* Get link speed and duplex from the slave's base driver
* using ethtool. If for some reason the call fails or the
- * values are invalid, fake speed and duplex to 100/Full
+ * values are invalid, set speed and duplex to -1,
* and return error.
*/
static int bond_update_speed_duplex(struct slave *slave)
@@ -560,9 +560,8 @@
u32 slave_speed;
int res;
- /* Fake speed and duplex */
- slave->speed = SPEED_100;
- slave->duplex = DUPLEX_FULL;
+ slave->speed = -1;
+ slave->duplex = -1;
res = __ethtool_get_settings(slave_dev, &ecmd);
if (res < 0)
@@ -1751,16 +1750,7 @@
new_slave->link = BOND_LINK_DOWN;
}
- if (bond_update_speed_duplex(new_slave) &&
- (new_slave->link != BOND_LINK_DOWN)) {
- pr_warning("%s: Warning: failed to get speed and duplex from %s, assumed to be 100Mb/sec and Full.\n",
- bond_dev->name, new_slave->dev->name);
-
- if (bond->params.mode == BOND_MODE_8023AD) {
- pr_warning("%s: Warning: Operation of 802.3ad mode requires ETHTOOL support in base driver for proper aggregator selection.\n",
- bond_dev->name);
- }
- }
+ bond_update_speed_duplex(new_slave);
if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
/* if there is a primary slave, remember it */
@@ -3220,6 +3210,7 @@
{
struct net_device *bond_dev = slave_dev->master;
struct bonding *bond = netdev_priv(bond_dev);
+ struct slave *slave = NULL;
switch (event) {
case NETDEV_UNREGISTER:
@@ -3230,20 +3221,16 @@
bond_release(bond_dev, slave_dev);
}
break;
+ case NETDEV_UP:
case NETDEV_CHANGE:
- if (bond->params.mode == BOND_MODE_8023AD || bond_is_lb(bond)) {
- struct slave *slave;
+ slave = bond_get_slave_by_dev(bond, slave_dev);
+ if (slave) {
+ u32 old_speed = slave->speed;
+ u8 old_duplex = slave->duplex;
- slave = bond_get_slave_by_dev(bond, slave_dev);
- if (slave) {
- u32 old_speed = slave->speed;
- u8 old_duplex = slave->duplex;
+ bond_update_speed_duplex(slave);
- bond_update_speed_duplex(slave);
-
- if (bond_is_lb(bond))
- break;
-
+ if (bond->params.mode == BOND_MODE_8023AD) {
if (old_speed != slave->speed)
bond_3ad_adapter_speed_changed(slave);
if (old_duplex != slave->duplex)
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index 95de93b..d2ff52e 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -157,8 +157,16 @@
seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name);
seq_printf(seq, "MII Status: %s\n",
(slave->link == BOND_LINK_UP) ? "up" : "down");
- seq_printf(seq, "Speed: %d Mbps\n", slave->speed);
- seq_printf(seq, "Duplex: %s\n", slave->duplex ? "full" : "half");
+ if (slave->speed == -1)
+ seq_printf(seq, "Speed: %s\n", "Unknown");
+ else
+ seq_printf(seq, "Speed: %d Mbps\n", slave->speed);
+
+ if (slave->duplex == -1)
+ seq_printf(seq, "Duplex: %s\n", "Unknown");
+ else
+ seq_printf(seq, "Duplex: %s\n", slave->duplex ? "full" : "half");
+
seq_printf(seq, "Link Failure Count: %u\n",
slave->link_failure_count);
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 6dff5a0..597f4d4 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -159,6 +159,7 @@
will be called s6gmac.
source "drivers/net/ethernet/seeq/Kconfig"
+source "drivers/net/ethernet/silan/Kconfig"
source "drivers/net/ethernet/sis/Kconfig"
source "drivers/net/ethernet/sfc/Kconfig"
source "drivers/net/ethernet/sgi/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index c53ad3a..be5dde0 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -58,6 +58,7 @@
obj-$(CONFIG_NET_VENDOR_RDC) += rdc/
obj-$(CONFIG_S6GMAC) += s6gmac.o
obj-$(CONFIG_NET_VENDOR_SEEQ) += seeq/
+obj-$(CONFIG_NET_VENDOR_SILAN) += silan/
obj-$(CONFIG_NET_VENDOR_SIS) += sis/
obj-$(CONFIG_SFC) += sfc/
obj-$(CONFIG_NET_VENDOR_SGI) += sgi/
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index 8238667..4865ff1 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -541,19 +541,17 @@
* these are not descriptors sitting in memory.
*/
static void
-au1000_setup_hw_rings(struct au1000_private *aup, u32 rx_base, u32 tx_base)
+au1000_setup_hw_rings(struct au1000_private *aup, void __iomem *tx_base)
{
int i;
for (i = 0; i < NUM_RX_DMA; i++) {
- aup->rx_dma_ring[i] =
- (struct rx_dma *)
- (rx_base + sizeof(struct rx_dma)*i);
+ aup->rx_dma_ring[i] = (struct rx_dma *)
+ (tx_base + 0x100 + sizeof(struct rx_dma) * i);
}
for (i = 0; i < NUM_TX_DMA; i++) {
- aup->tx_dma_ring[i] =
- (struct tx_dma *)
- (tx_base + sizeof(struct tx_dma)*i);
+ aup->tx_dma_ring[i] = (struct tx_dma *)
+ (tx_base + sizeof(struct tx_dma) * i);
}
}
@@ -1026,7 +1024,7 @@
struct net_device *dev = NULL;
struct db_dest *pDB, *pDBfree;
int irq, i, err = 0;
- struct resource *base, *macen;
+ struct resource *base, *macen, *macdma;
base = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!base) {
@@ -1049,6 +1047,13 @@
goto out;
}
+ macdma = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+ if (!macdma) {
+ dev_err(&pdev->dev, "failed to retrieve MACDMA registers\n");
+ err = -ENODEV;
+ goto out;
+ }
+
if (!request_mem_region(base->start, resource_size(base),
pdev->name)) {
dev_err(&pdev->dev, "failed to request memory region for base registers\n");
@@ -1063,6 +1068,13 @@
goto err_request;
}
+ if (!request_mem_region(macdma->start, resource_size(macdma),
+ pdev->name)) {
+ dev_err(&pdev->dev, "failed to request MACDMA memory region\n");
+ err = -ENXIO;
+ goto err_macdma;
+ }
+
dev = alloc_etherdev(sizeof(struct au1000_private));
if (!dev) {
dev_err(&pdev->dev, "alloc_etherdev failed\n");
@@ -1109,10 +1121,14 @@
}
aup->mac_id = pdev->id;
- if (pdev->id == 0)
- au1000_setup_hw_rings(aup, MAC0_RX_DMA_ADDR, MAC0_TX_DMA_ADDR);
- else if (pdev->id == 1)
- au1000_setup_hw_rings(aup, MAC1_RX_DMA_ADDR, MAC1_TX_DMA_ADDR);
+ aup->macdma = ioremap_nocache(macdma->start, resource_size(macdma));
+ if (!aup->macdma) {
+ dev_err(&pdev->dev, "failed to ioremap MACDMA registers\n");
+ err = -ENXIO;
+ goto err_remap3;
+ }
+
+ au1000_setup_hw_rings(aup, aup->macdma);
/* set a random MAC now in case platform_data doesn't provide one */
random_ether_addr(dev->dev_addr);
@@ -1252,6 +1268,8 @@
err_mdiobus_reg:
mdiobus_free(aup->mii_bus);
err_mdiobus_alloc:
+ iounmap(aup->macdma);
+err_remap3:
iounmap(aup->enable);
err_remap2:
iounmap(aup->mac);
@@ -1261,6 +1279,8 @@
err_vaddr:
free_netdev(dev);
err_alloc:
+ release_mem_region(macdma->start, resource_size(macdma));
+err_macdma:
release_mem_region(macen->start, resource_size(macen));
err_request:
release_mem_region(base->start, resource_size(base));
@@ -1293,9 +1313,13 @@
(NUM_TX_BUFFS + NUM_RX_BUFFS),
(void *)aup->vaddr, aup->dma_addr);
+ iounmap(aup->macdma);
iounmap(aup->mac);
iounmap(aup->enable);
+ base = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+ release_mem_region(base->start, resource_size(base));
+
base = platform_get_resource(pdev, IORESOURCE_MEM, 0);
release_mem_region(base->start, resource_size(base));
diff --git a/drivers/net/ethernet/amd/au1000_eth.h b/drivers/net/ethernet/amd/au1000_eth.h
index 6229c77..4b7f7ad 100644
--- a/drivers/net/ethernet/amd/au1000_eth.h
+++ b/drivers/net/ethernet/amd/au1000_eth.h
@@ -124,7 +124,7 @@
*/
struct mac_reg *mac; /* mac registers */
u32 *enable; /* address of MAC Enable Register */
-
+ void __iomem *macdma; /* base of MAC DMA port */
u32 vaddr; /* virtual address of rx/tx buffers */
dma_addr_t dma_addr; /* dma address of rx/tx buffers */
diff --git a/drivers/net/ethernet/apple/Kconfig b/drivers/net/ethernet/apple/Kconfig
index a759d54..1375e2d 100644
--- a/drivers/net/ethernet/apple/Kconfig
+++ b/drivers/net/ethernet/apple/Kconfig
@@ -52,18 +52,6 @@
To compile this driver as a module, choose M here: the module
will be called bmac.
-config MAC89x0
- tristate "Macintosh CS89x0 based ethernet cards"
- depends on MAC
- ---help---
- Support for CS89x0 chipset based Ethernet cards. If you have a
- Nubus or LC-PDS network (Ethernet) card of this type, say Y and
- read the Ethernet-HOWTO, available from
- <http://www.tldp.org/docs.html#howto>.
-
- To compile this driver as a module, choose M here. This module will
- be called mac89x0.
-
config MACMACE
bool "Macintosh (AV) onboard MACE ethernet"
depends on MAC
diff --git a/drivers/net/ethernet/apple/Makefile b/drivers/net/ethernet/apple/Makefile
index 0d3a591..86eaa17 100644
--- a/drivers/net/ethernet/apple/Makefile
+++ b/drivers/net/ethernet/apple/Makefile
@@ -4,5 +4,4 @@
obj-$(CONFIG_MACE) += mace.o
obj-$(CONFIG_BMAC) += bmac.o
-obj-$(CONFIG_MAC89x0) += mac89x0.o
obj-$(CONFIG_MACMACE) += macmace.o
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index 6cbb81c..1f8648f 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -6,7 +6,7 @@
bool "Cirrus devices"
default y
depends on ISA || EISA || MACH_IXDP2351 || ARCH_IXDP2X01 \
- || MACH_MX31ADS || MACH_QQ2440 || (ARM && ARCH_EP93XX)
+ || MACH_MX31ADS || MACH_QQ2440 || (ARM && ARCH_EP93XX) || MAC
---help---
If you have a network (Ethernet) card belonging to this class, say Y
and read the Ethernet-HOWTO, available from
@@ -47,4 +47,16 @@
This is a driver for the ethernet hardware included in EP93xx CPUs.
Say Y if you are building a kernel for EP93xx based devices.
+config MAC89x0
+ tristate "Macintosh CS89x0 based ethernet cards"
+ depends on MAC
+ ---help---
+ Support for CS89x0 chipset based Ethernet cards. If you have a
+ Nubus or LC-PDS network (Ethernet) card of this type, say Y and
+ read the Ethernet-HOWTO, available from
+ <http://www.tldp.org/docs.html#howto>.
+
+ To compile this driver as a module, choose M here. This module will
+ be called mac89x0.
+
endif # NET_VENDOR_CIRRUS
diff --git a/drivers/net/ethernet/cirrus/Makefile b/drivers/net/ethernet/cirrus/Makefile
index 14bd77e..ca245e2 100644
--- a/drivers/net/ethernet/cirrus/Makefile
+++ b/drivers/net/ethernet/cirrus/Makefile
@@ -4,3 +4,4 @@
obj-$(CONFIG_CS89x0) += cs89x0.o
obj-$(CONFIG_EP93XX_ETH) += ep93xx_eth.o
+obj-$(CONFIG_MAC89x0) += mac89x0.o
diff --git a/drivers/net/ethernet/apple/mac89x0.c b/drivers/net/ethernet/cirrus/mac89x0.c
similarity index 100%
rename from drivers/net/ethernet/apple/mac89x0.c
rename to drivers/net/ethernet/cirrus/mac89x0.c
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 824b8e6..2c7b366 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -318,8 +318,7 @@
if (msecs > 4000) {
dev_err(&adapter->pdev->dev, "mbox poll timed out\n");
- if (!lancer_chip(adapter))
- be_detect_dump_ue(adapter);
+ be_detect_dump_ue(adapter);
return -1;
}
@@ -1540,7 +1539,14 @@
req->if_flags_mask = req->if_flags =
cpu_to_le32(BE_IF_FLAGS_MULTICAST);
- req->mcast_num = cpu_to_le16(netdev_mc_count(adapter->netdev));
+
+ /* Reset mcast promisc mode if already set by setting mask
+ * and not setting flags field
+ */
+ req->if_flags_mask |=
+ cpu_to_le32(BE_IF_FLAGS_MCAST_PROMISCUOUS);
+
+ req->mcast_num = cpu_to_le32(netdev_mc_count(adapter->netdev));
netdev_for_each_mc_addr(ha, adapter->netdev)
memcpy(req->mcast_mac[i++].byte, ha->addr, ETH_ALEN);
}
diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h
index fbc8a91..f2c89e3 100644
--- a/drivers/net/ethernet/emulex/benet/be_hw.h
+++ b/drivers/net/ethernet/emulex/benet/be_hw.h
@@ -48,6 +48,8 @@
/* Lancer SLIPORT_CONTROL SLIPORT_STATUS registers */
#define SLIPORT_STATUS_OFFSET 0x404
#define SLIPORT_CONTROL_OFFSET 0x408
+#define SLIPORT_ERROR1_OFFSET 0x40C
+#define SLIPORT_ERROR2_OFFSET 0x410
#define SLIPORT_STATUS_ERR_MASK 0x80000000
#define SLIPORT_STATUS_RN_MASK 0x01000000
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 2180497..e0aed18 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1905,6 +1905,8 @@
be_rx_stats_update(rxo, rxcp);
}
+ be_cq_notify(adapter, rx_cq->id, false, work_done);
+
/* Refill the queue */
if (work_done && atomic_read(&rxo->q.used) < RX_FRAGS_REFILL_WM)
be_post_rx_frags(rxo, GFP_ATOMIC);
@@ -1912,10 +1914,8 @@
/* All consumed */
if (work_done < budget) {
napi_complete(napi);
- be_cq_notify(adapter, rx_cq->id, true, work_done);
- } else {
- /* More to be consumed; continue with interrupts disabled */
- be_cq_notify(adapter, rx_cq->id, false, work_done);
+ /* Arm CQ */
+ be_cq_notify(adapter, rx_cq->id, true, 0);
}
return work_done;
}
@@ -1977,42 +1977,62 @@
void be_detect_dump_ue(struct be_adapter *adapter)
{
- u32 ue_status_lo, ue_status_hi, ue_status_lo_mask, ue_status_hi_mask;
+ u32 ue_lo = 0, ue_hi = 0, ue_lo_mask = 0, ue_hi_mask = 0;
+ u32 sliport_status = 0, sliport_err1 = 0, sliport_err2 = 0;
u32 i;
- pci_read_config_dword(adapter->pdev,
- PCICFG_UE_STATUS_LOW, &ue_status_lo);
- pci_read_config_dword(adapter->pdev,
- PCICFG_UE_STATUS_HIGH, &ue_status_hi);
- pci_read_config_dword(adapter->pdev,
- PCICFG_UE_STATUS_LOW_MASK, &ue_status_lo_mask);
- pci_read_config_dword(adapter->pdev,
- PCICFG_UE_STATUS_HI_MASK, &ue_status_hi_mask);
+ if (lancer_chip(adapter)) {
+ sliport_status = ioread32(adapter->db + SLIPORT_STATUS_OFFSET);
+ if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
+ sliport_err1 = ioread32(adapter->db +
+ SLIPORT_ERROR1_OFFSET);
+ sliport_err2 = ioread32(adapter->db +
+ SLIPORT_ERROR2_OFFSET);
+ }
+ } else {
+ pci_read_config_dword(adapter->pdev,
+ PCICFG_UE_STATUS_LOW, &ue_lo);
+ pci_read_config_dword(adapter->pdev,
+ PCICFG_UE_STATUS_HIGH, &ue_hi);
+ pci_read_config_dword(adapter->pdev,
+ PCICFG_UE_STATUS_LOW_MASK, &ue_lo_mask);
+ pci_read_config_dword(adapter->pdev,
+ PCICFG_UE_STATUS_HI_MASK, &ue_hi_mask);
- ue_status_lo = (ue_status_lo & (~ue_status_lo_mask));
- ue_status_hi = (ue_status_hi & (~ue_status_hi_mask));
+ ue_lo = (ue_lo & (~ue_lo_mask));
+ ue_hi = (ue_hi & (~ue_hi_mask));
+ }
- if (ue_status_lo || ue_status_hi) {
+ if (ue_lo || ue_hi ||
+ sliport_status & SLIPORT_STATUS_ERR_MASK) {
adapter->ue_detected = true;
adapter->eeh_err = true;
dev_err(&adapter->pdev->dev, "UE Detected!!\n");
}
- if (ue_status_lo) {
- for (i = 0; ue_status_lo; ue_status_lo >>= 1, i++) {
- if (ue_status_lo & 1)
+ if (ue_lo) {
+ for (i = 0; ue_lo; ue_lo >>= 1, i++) {
+ if (ue_lo & 1)
dev_err(&adapter->pdev->dev,
"UE: %s bit set\n", ue_status_low_desc[i]);
}
}
- if (ue_status_hi) {
- for (i = 0; ue_status_hi; ue_status_hi >>= 1, i++) {
- if (ue_status_hi & 1)
+ if (ue_hi) {
+ for (i = 0; ue_hi; ue_hi >>= 1, i++) {
+ if (ue_hi & 1)
dev_err(&adapter->pdev->dev,
"UE: %s bit set\n", ue_status_hi_desc[i]);
}
}
+ if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
+ dev_err(&adapter->pdev->dev,
+ "sliport status 0x%x\n", sliport_status);
+ dev_err(&adapter->pdev->dev,
+ "sliport error1 0x%x\n", sliport_err1);
+ dev_err(&adapter->pdev->dev,
+ "sliport error2 0x%x\n", sliport_err2);
+ }
}
static void be_worker(struct work_struct *work)
@@ -2022,7 +2042,7 @@
struct be_rx_obj *rxo;
int i;
- if (!adapter->ue_detected && !lancer_chip(adapter))
+ if (!adapter->ue_detected)
be_detect_dump_ue(adapter);
/* when interrupts are not yet enabled, just reap any pending
diff --git a/drivers/net/ethernet/i825xx/3c505.c b/drivers/net/ethernet/i825xx/3c505.c
index 40e1a17..ba82a26 100644
--- a/drivers/net/ethernet/i825xx/3c505.c
+++ b/drivers/net/ethernet/i825xx/3c505.c
@@ -126,15 +126,13 @@
*
*********************************************************/
-#define filename __FILE__
-
#define timeout_msg "*** timeout at %s:%s (line %d) ***\n"
#define TIMEOUT_MSG(lineno) \
- pr_notice(timeout_msg, filename, __func__, (lineno))
+ pr_notice(timeout_msg, __FILE__, __func__, (lineno))
#define invalid_pcb_msg "*** invalid pcb length %d at %s:%s (line %d) ***\n"
#define INVALID_PCB_MSG(len) \
- pr_notice(invalid_pcb_msg, (len), filename, __func__, __LINE__)
+ pr_notice(invalid_pcb_msg, (len), __FILE__, __func__, __LINE__)
#define search_msg "%s: Looking for 3c505 adapter at address %#x..."
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index ae17cd1..5a2fdf7 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -2810,6 +2810,10 @@
e100_get_defaults(nic);
+ /* D100 MAC doesn't allow rx of vlan packets with normal MTU */
+ if (nic->mac < mac_82558_D101_A4)
+ netdev->features |= NETIF_F_VLAN_CHALLENGED;
+
/* locks must be initialized before calling hw_reset */
spin_lock_init(&nic->cb_lock);
spin_lock_init(&nic->cmd_lock);
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 6a17c62..e2a80a2 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -866,8 +866,7 @@
if (test_and_set_bit(__E1000_ACCESS_SHARED_RESOURCE,
&hw->adapter->state)) {
- WARN(1, "e1000e: %s: contention for Phy access\n",
- hw->adapter->netdev->name);
+ e_dbg("contention for Phy access\n");
return -E1000_ERR_PHY;
}
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 7edf31e..b17d7c2 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -1687,7 +1687,7 @@
if (ret_val)
goto out;
- is_cm = !(phy_data & I347AT4_PCDC_CABLE_LENGTH_UNIT);
+ is_cm = !(phy_data2 & I347AT4_PCDC_CABLE_LENGTH_UNIT);
/* Populate the phy structure with cable length in meters */
phy->min_cable_length = phy_data / (is_cm ? 100 : 1);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 834f044..f1365fe 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -3344,7 +3344,7 @@
static s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, u32 *buffer,
u32 length)
{
- u32 hicr, i;
+ u32 hicr, i, bi;
u32 hdr_size = sizeof(struct ixgbe_hic_hdr);
u8 buf_len, dword_len;
@@ -3398,9 +3398,9 @@
dword_len = hdr_size >> 2;
/* first pull in the header so we know the buffer length */
- for (i = 0; i < dword_len; i++) {
- buffer[i] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, i);
- le32_to_cpus(&buffer[i]);
+ for (bi = 0; bi < dword_len; bi++) {
+ buffer[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi);
+ le32_to_cpus(&buffer[bi]);
}
/* If there is any thing in data position pull it in */
@@ -3414,12 +3414,14 @@
goto out;
}
- /* Calculate length in DWORDs, add one for odd lengths */
- dword_len = (buf_len + 1) >> 2;
+ /* Calculate length in DWORDs, add 3 for odd lengths */
+ dword_len = (buf_len + 3) >> 2;
- /* Pull in the rest of the buffer (i is where we left off)*/
- for (; i < buf_len; i++)
- buffer[i] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, i);
+ /* Pull in the rest of the buffer (bi is where we left off)*/
+ for (; bi <= dword_len; bi++) {
+ buffer[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi);
+ le32_to_cpus(&buffer[bi]);
+ }
out:
return ret_val;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index 3631d63..33b93ff 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -561,11 +561,12 @@
struct ixgbe_adapter *adapter = netdev_priv(dev);
struct ieee_ets *my_ets = adapter->ixgbe_ieee_ets;
+ ets->ets_cap = adapter->dcb_cfg.num_tcs.pg_tcs;
+
/* No IEEE PFC settings available */
if (!my_ets)
- return -EINVAL;
+ return 0;
- ets->ets_cap = adapter->dcb_cfg.num_tcs.pg_tcs;
ets->cbs = my_ets->cbs;
memcpy(ets->tc_tx_bw, my_ets->tc_tx_bw, sizeof(ets->tc_tx_bw));
memcpy(ets->tc_rx_bw, my_ets->tc_rx_bw, sizeof(ets->tc_rx_bw));
@@ -621,11 +622,12 @@
struct ieee_pfc *my_pfc = adapter->ixgbe_ieee_pfc;
int i;
+ pfc->pfc_cap = adapter->dcb_cfg.num_tcs.pfc_tcs;
+
/* No IEEE PFC settings available */
if (!my_pfc)
- return -EINVAL;
+ return 0;
- pfc->pfc_cap = adapter->dcb_cfg.num_tcs.pfc_tcs;
pfc->pfc_en = my_pfc->pfc_en;
pfc->mbc = my_pfc->mbc;
pfc->delay = my_pfc->delay;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 09b8e88..8ef92d1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3345,34 +3345,25 @@
hw->mac.ops.set_vfta(&adapter->hw, 0, 0, true);
+#ifdef IXGBE_FCOE
+ if (adapter->netdev->features & NETIF_F_FCOE_MTU)
+ max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE);
+#endif
+
/* reconfigure the hardware */
if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE) {
-#ifdef IXGBE_FCOE
- if (adapter->netdev->features & NETIF_F_FCOE_MTU)
- max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE);
-#endif
ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame,
DCB_TX_CONFIG);
ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame,
DCB_RX_CONFIG);
ixgbe_dcb_hw_config(hw, &adapter->dcb_cfg);
- } else {
- struct net_device *dev = adapter->netdev;
-
- if (adapter->ixgbe_ieee_ets) {
- struct ieee_ets *ets = adapter->ixgbe_ieee_ets;
- int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
-
- ixgbe_dcb_hw_ets(&adapter->hw, ets, max_frame);
- }
-
- if (adapter->ixgbe_ieee_pfc) {
- struct ieee_pfc *pfc = adapter->ixgbe_ieee_pfc;
- u8 *prio_tc = adapter->ixgbe_ieee_ets->prio_tc;
-
- ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc->pfc_en,
- prio_tc);
- }
+ } else if (adapter->ixgbe_ieee_ets && adapter->ixgbe_ieee_pfc) {
+ ixgbe_dcb_hw_ets(&adapter->hw,
+ adapter->ixgbe_ieee_ets,
+ max_frame);
+ ixgbe_dcb_hw_pfc_config(&adapter->hw,
+ adapter->ixgbe_ieee_pfc->pfc_en,
+ adapter->ixgbe_ieee_ets->prio_tc);
}
/* Enable RSS Hash per TC */
@@ -6125,7 +6116,6 @@
autoneg = hw->phy.autoneg_advertised;
if ((!autoneg) && (hw->mac.ops.get_link_capabilities))
hw->mac.ops.get_link_capabilities(hw, &autoneg, &negotiation);
- hw->mac.autotry_restart = false;
if (hw->mac.ops.setup_link)
hw->mac.ops.setup_link(hw, autoneg, negotiation, true);
@@ -7589,13 +7579,6 @@
goto err_eeprom;
}
- /* power down the optics for multispeed fiber and 82599 SFP+ fiber */
- if (hw->mac.ops.disable_tx_laser &&
- ((hw->phy.multispeed_fiber) ||
- ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) &&
- (hw->mac.type == ixgbe_mac_82599EB))))
- hw->mac.ops.disable_tx_laser(hw);
-
setup_timer(&adapter->service_timer, &ixgbe_service_timer,
(unsigned long) adapter);
@@ -7693,6 +7676,13 @@
if (err)
goto err_register;
+ /* power down the optics for multispeed fiber and 82599 SFP+ fiber */
+ if (hw->mac.ops.disable_tx_laser &&
+ ((hw->phy.multispeed_fiber) ||
+ ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) &&
+ (hw->mac.type == ixgbe_mac_82599EB))))
+ hw->mac.ops.disable_tx_laser(hw);
+
/* carrier off reporting is important to ethtool even BEFORE open */
netif_carrier_off(netdev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
index 5a7e1eb..4a5d889 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
@@ -42,10 +42,12 @@
int ixgbe_ndo_get_vf_config(struct net_device *netdev,
int vf, struct ifla_vf_info *ivi);
void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter);
+#ifdef CONFIG_PCI_IOV
void ixgbe_disable_sriov(struct ixgbe_adapter *adapter);
void ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
const struct ixgbe_info *ii);
int ixgbe_check_vf_assignment(struct ixgbe_adapter *adapter);
+#endif
#endif /* _IXGBE_SRIOV_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 5e92cc2..4c8e199 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -54,7 +54,7 @@
static const char ixgbevf_driver_string[] =
"Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver";
-#define DRV_VERSION "2.1.0-k"
+#define DRV_VERSION "2.2.0-k"
const char ixgbevf_driver_version[] = DRV_VERSION;
static char ixgbevf_copyright[] =
"Copyright (c) 2009 - 2010 Intel Corporation.";
diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 84083ec..0578859 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -115,16 +115,4 @@
To compile this driver as a module, choose M here: the module
will be called r8169. This is recommended.
-config SC92031
- tristate "Silan SC92031 PCI Fast Ethernet Adapter driver (EXPERIMENTAL)"
- depends on PCI && EXPERIMENTAL
- select CRC32
- ---help---
- This is a driver for the Fast Ethernet PCI network cards based on
- the Silan SC92031 chip (sometimes also called Rsltek 8139D). If you
- have one of these, say Y here.
-
- To compile this driver as a module, choose M here: the module
- will be called sc92031. This is recommended.
-
endif # NET_VENDOR_REALTEK
diff --git a/drivers/net/ethernet/realtek/Makefile b/drivers/net/ethernet/realtek/Makefile
index e48cfb6..71b1da3 100644
--- a/drivers/net/ethernet/realtek/Makefile
+++ b/drivers/net/ethernet/realtek/Makefile
@@ -6,4 +6,3 @@
obj-$(CONFIG_8139TOO) += 8139too.o
obj-$(CONFIG_ATP) += atp.o
obj-$(CONFIG_R8169) += r8169.o
-obj-$(CONFIG_SC92031) += sc92031.o
diff --git a/drivers/net/ethernet/silan/Kconfig b/drivers/net/ethernet/silan/Kconfig
new file mode 100644
index 0000000..ae1ce17
--- /dev/null
+++ b/drivers/net/ethernet/silan/Kconfig
@@ -0,0 +1,33 @@
+#
+# Silan device configuration
+#
+
+config NET_VENDOR_SILAN
+ bool "Silan devices"
+ default y
+ depends on PCI && EXPERIMENTAL
+ ---help---
+ If you have a network (Ethernet) card belonging to this class, say Y
+ and read the Ethernet-HOWTO, available from
+ <http://www.tldp.org/docs.html#howto>.
+
+ Note that the answer to this question doesn't directly affect the
+ kernel: saying N will just cause the configurator to skip all
+ the questions about Silan devices. If you say Y, you will be asked for
+ your specific card in the following questions.
+
+if NET_VENDOR_SILAN
+
+config SC92031
+ tristate "Silan SC92031 PCI Fast Ethernet Adapter driver (EXPERIMENTAL)"
+ depends on PCI && EXPERIMENTAL
+ select CRC32
+ ---help---
+ This is a driver for the Fast Ethernet PCI network cards based on
+ the Silan SC92031 chip (sometimes also called Rsltek 8139D). If you
+ have one of these, say Y here.
+
+ To compile this driver as a module, choose M here: the module
+ will be called sc92031. This is recommended.
+
+endif # NET_VENDOR_SILAN
diff --git a/drivers/net/ethernet/silan/Makefile b/drivers/net/ethernet/silan/Makefile
new file mode 100644
index 0000000..4ad3523
--- /dev/null
+++ b/drivers/net/ethernet/silan/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Silan network device drivers.
+#
+
+obj-$(CONFIG_SC92031) += sc92031.o
diff --git a/drivers/net/ethernet/realtek/sc92031.c b/drivers/net/ethernet/silan/sc92031.c
similarity index 100%
rename from drivers/net/ethernet/realtek/sc92031.c
rename to drivers/net/ethernet/silan/sc92031.c
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 4d1658e..caf3659 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -716,8 +716,8 @@
cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
cur_p->phys = dma_map_single(ndev->dev.parent,
skb_frag_address(frag),
- frag_size(frag), DMA_TO_DEVICE);
- cur_p->len = frag_size(frag);
+ skb_frag_size(frag), DMA_TO_DEVICE);
+ cur_p->len = skb_frag_size(frag);
cur_p->app0 = 0;
frag++;
}
diff --git a/drivers/net/irda/Kconfig b/drivers/net/irda/Kconfig
index a40fab4..d423d18 100644
--- a/drivers/net/irda/Kconfig
+++ b/drivers/net/irda/Kconfig
@@ -314,7 +314,7 @@
config AU1000_FIR
tristate "Alchemy Au1000 SIR/FIR"
- depends on SOC_AU1000 && IRDA
+ depends on IRDA && MIPS_ALCHEMY
config SMC_IRCC_FIR
tristate "SMSC IrCC (EXPERIMENTAL)"
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index 3bb1311..7145714 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -88,8 +88,8 @@
#define dev_rionet_capable(dev) \
is_rionet_capable(dev->src_ops, dev->dst_ops)
-#define RIONET_MAC_MATCH(x) (*(u32 *)x == 0x00010001)
-#define RIONET_GET_DESTID(x) (*(u16 *)(x + 4))
+#define RIONET_MAC_MATCH(x) (!memcmp((x), "\00\01\00\01", 4))
+#define RIONET_GET_DESTID(x) ((*((u8 *)x + 4) << 8) | *((u8 *)x + 5))
static int rionet_rx_clean(struct net_device *ndev)
{
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 91039ab..6ee8410 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -925,12 +925,10 @@
{
u16 v;
- if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS))
- return;
-
- vi->vdev->config->get(vi->vdev,
+ if (virtio_config_val(vi->vdev, VIRTIO_NET_F_STATUS,
offsetof(struct virtio_net_config, status),
- &v, sizeof(v));
+ &v) < 0)
+ return;
/* Ignore unknown (future) status bits */
v &= VIRTIO_NET_S_LINK_UP;
@@ -1006,11 +1004,9 @@
}
/* Configuration may specify what MAC to use. Otherwise random. */
- if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) {
- vdev->config->get(vdev,
+ if (virtio_config_val_len(vdev, VIRTIO_NET_F_MAC,
offsetof(struct virtio_net_config, mac),
- dev->dev_addr, dev->addr_len);
- } else
+ dev->dev_addr, dev->addr_len) < 0)
random_ether_addr(dev->dev_addr);
/* Set up our device-specific information */
diff --git a/drivers/net/wireless/ath/Kconfig b/drivers/net/wireless/ath/Kconfig
index 0735488..0960224 100644
--- a/drivers/net/wireless/ath/Kconfig
+++ b/drivers/net/wireless/ath/Kconfig
@@ -1,6 +1,6 @@
menuconfig ATH_COMMON
tristate "Atheros Wireless Cards"
- depends on CFG80211
+ depends on CFG80211 && (!UML || BROKEN)
---help---
This will enable the support for the Atheros wireless drivers.
ath5k, ath9k, ath9k_htc and ar9170 drivers share some common code, this option
diff --git a/drivers/net/wireless/rtlwifi/Kconfig b/drivers/net/wireless/rtlwifi/Kconfig
index 45e1476..d6c42e6 100644
--- a/drivers/net/wireless/rtlwifi/Kconfig
+++ b/drivers/net/wireless/rtlwifi/Kconfig
@@ -12,7 +12,7 @@
config RTL8192SE
tristate "Realtek RTL8192SE/RTL8191SE PCIe Wireless Network Adapter"
- depends on MAC80211 && EXPERIMENTAL
+ depends on MAC80211 && EXPERIMENTAL && PCI
select FW_LOADER
select RTLWIFI
---help---
@@ -23,7 +23,7 @@
config RTL8192DE
tristate "Realtek RTL8192DE/RTL8188DE PCIe Wireless Network Adapter"
- depends on MAC80211 && EXPERIMENTAL
+ depends on MAC80211 && EXPERIMENTAL && PCI
select FW_LOADER
select RTLWIFI
---help---
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 57de051..9f88641 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -70,6 +70,7 @@
config BATTERY_DS2780
tristate "DS2780 battery driver"
+ depends on HAS_IOMEM
select W1
select W1_SLAVE_DS2780
help
diff --git a/drivers/power/ds2780_battery.c b/drivers/power/ds2780_battery.c
index 1fefe82..91a783d 100644
--- a/drivers/power/ds2780_battery.c
+++ b/drivers/power/ds2780_battery.c
@@ -39,6 +39,7 @@
struct device *dev;
struct power_supply bat;
struct device *w1_dev;
+ struct task_struct *mutex_holder;
};
enum current_types {
@@ -49,8 +50,8 @@
static const char model[] = "DS2780";
static const char manufacturer[] = "Maxim/Dallas";
-static inline struct ds2780_device_info *to_ds2780_device_info(
- struct power_supply *psy)
+static inline struct ds2780_device_info *
+to_ds2780_device_info(struct power_supply *psy)
{
return container_of(psy, struct ds2780_device_info, bat);
}
@@ -60,17 +61,28 @@
return dev_get_drvdata(dev);
}
-static inline int ds2780_read8(struct device *dev, u8 *val, int addr)
+static inline int ds2780_battery_io(struct ds2780_device_info *dev_info,
+ char *buf, int addr, size_t count, int io)
{
- return w1_ds2780_io(dev, val, addr, sizeof(u8), 0);
+ if (dev_info->mutex_holder == current)
+ return w1_ds2780_io_nolock(dev_info->w1_dev, buf, addr, count, io);
+ else
+ return w1_ds2780_io(dev_info->w1_dev, buf, addr, count, io);
}
-static int ds2780_read16(struct device *dev, s16 *val, int addr)
+static inline int ds2780_read8(struct ds2780_device_info *dev_info, u8 *val,
+ int addr)
+{
+ return ds2780_battery_io(dev_info, val, addr, sizeof(u8), 0);
+}
+
+static int ds2780_read16(struct ds2780_device_info *dev_info, s16 *val,
+ int addr)
{
int ret;
u8 raw[2];
- ret = w1_ds2780_io(dev, raw, addr, sizeof(u8) * 2, 0);
+ ret = ds2780_battery_io(dev_info, raw, addr, sizeof(raw), 0);
if (ret < 0)
return ret;
@@ -79,16 +91,16 @@
return 0;
}
-static inline int ds2780_read_block(struct device *dev, u8 *val, int addr,
- size_t count)
+static inline int ds2780_read_block(struct ds2780_device_info *dev_info,
+ u8 *val, int addr, size_t count)
{
- return w1_ds2780_io(dev, val, addr, count, 0);
+ return ds2780_battery_io(dev_info, val, addr, count, 0);
}
-static inline int ds2780_write(struct device *dev, u8 *val, int addr,
- size_t count)
+static inline int ds2780_write(struct ds2780_device_info *dev_info, u8 *val,
+ int addr, size_t count)
{
- return w1_ds2780_io(dev, val, addr, count, 1);
+ return ds2780_battery_io(dev_info, val, addr, count, 1);
}
static inline int ds2780_store_eeprom(struct device *dev, int addr)
@@ -122,7 +134,7 @@
{
int ret;
- ret = ds2780_write(dev_info->w1_dev, &conductance,
+ ret = ds2780_write(dev_info, &conductance,
DS2780_RSNSP_REG, sizeof(u8));
if (ret < 0)
return ret;
@@ -134,7 +146,7 @@
static int ds2780_get_rsgain_register(struct ds2780_device_info *dev_info,
u16 *rsgain)
{
- return ds2780_read16(dev_info->w1_dev, rsgain, DS2780_RSGAIN_MSB_REG);
+ return ds2780_read16(dev_info, rsgain, DS2780_RSGAIN_MSB_REG);
}
/* Set RSGAIN value from 0 to 1.999 in steps of 0.001 */
@@ -144,8 +156,8 @@
int ret;
u8 raw[] = {rsgain >> 8, rsgain & 0xFF};
- ret = ds2780_write(dev_info->w1_dev, raw,
- DS2780_RSGAIN_MSB_REG, sizeof(u8) * 2);
+ ret = ds2780_write(dev_info, raw,
+ DS2780_RSGAIN_MSB_REG, sizeof(raw));
if (ret < 0)
return ret;
@@ -167,7 +179,7 @@
* Bits 2 - 0 of the voltage value are in bits 7 - 5 of the
* voltage LSB register
*/
- ret = ds2780_read16(dev_info->w1_dev, &voltage_raw,
+ ret = ds2780_read16(dev_info, &voltage_raw,
DS2780_VOLT_MSB_REG);
if (ret < 0)
return ret;
@@ -196,7 +208,7 @@
* Bits 2 - 0 of the temperature value are in bits 7 - 5 of the
* temperature LSB register
*/
- ret = ds2780_read16(dev_info->w1_dev, &temperature_raw,
+ ret = ds2780_read16(dev_info, &temperature_raw,
DS2780_TEMP_MSB_REG);
if (ret < 0)
return ret;
@@ -222,13 +234,13 @@
* The units of measurement for current are dependent on the value of
* the sense resistor.
*/
- ret = ds2780_read8(dev_info->w1_dev, &sense_res_raw, DS2780_RSNSP_REG);
+ ret = ds2780_read8(dev_info, &sense_res_raw, DS2780_RSNSP_REG);
if (ret < 0)
return ret;
if (sense_res_raw == 0) {
dev_err(dev_info->dev, "sense resistor value is 0\n");
- return -ENXIO;
+ return -EINVAL;
}
sense_res = 1000 / sense_res_raw;
@@ -248,7 +260,7 @@
* Bits 7 - 0 of the current value are in bits 7 - 0 of the current
* LSB register
*/
- ret = ds2780_read16(dev_info->w1_dev, ¤t_raw, reg_msb);
+ ret = ds2780_read16(dev_info, ¤t_raw, reg_msb);
if (ret < 0)
return ret;
@@ -267,7 +279,7 @@
* The units of measurement for accumulated current are dependent on
* the value of the sense resistor.
*/
- ret = ds2780_read8(dev_info->w1_dev, &sense_res_raw, DS2780_RSNSP_REG);
+ ret = ds2780_read8(dev_info, &sense_res_raw, DS2780_RSNSP_REG);
if (ret < 0)
return ret;
@@ -285,7 +297,7 @@
* Bits 7 - 0 of the ACR value are in bits 7 - 0 of the ACR
* LSB register
*/
- ret = ds2780_read16(dev_info->w1_dev, ¤t_raw, DS2780_ACR_MSB_REG);
+ ret = ds2780_read16(dev_info, ¤t_raw, DS2780_ACR_MSB_REG);
if (ret < 0)
return ret;
@@ -299,7 +311,7 @@
int ret;
u8 raw;
- ret = ds2780_read8(dev_info->w1_dev, &raw, DS2780_RARC_REG);
+ ret = ds2780_read8(dev_info, &raw, DS2780_RARC_REG);
if (ret < 0)
return ret;
@@ -345,7 +357,7 @@
* Bits 7 - 0 of the RAAC value are in bits 7 - 0 of the RAAC
* LSB register
*/
- ret = ds2780_read16(dev_info->w1_dev, &charge_raw, DS2780_RAAC_MSB_REG);
+ ret = ds2780_read16(dev_info, &charge_raw, DS2780_RAAC_MSB_REG);
if (ret < 0)
return ret;
@@ -356,7 +368,7 @@
static int ds2780_get_control_register(struct ds2780_device_info *dev_info,
u8 *control_reg)
{
- return ds2780_read8(dev_info->w1_dev, control_reg, DS2780_CONTROL_REG);
+ return ds2780_read8(dev_info, control_reg, DS2780_CONTROL_REG);
}
static int ds2780_set_control_register(struct ds2780_device_info *dev_info,
@@ -364,7 +376,7 @@
{
int ret;
- ret = ds2780_write(dev_info->w1_dev, &control_reg,
+ ret = ds2780_write(dev_info, &control_reg,
DS2780_CONTROL_REG, sizeof(u8));
if (ret < 0)
return ret;
@@ -503,7 +515,7 @@
struct power_supply *psy = to_power_supply(dev);
struct ds2780_device_info *dev_info = to_ds2780_device_info(psy);
- ret = ds2780_read8(dev_info->w1_dev, &sense_resistor, DS2780_RSNSP_REG);
+ ret = ds2780_read8(dev_info, &sense_resistor, DS2780_RSNSP_REG);
if (ret < 0)
return ret;
@@ -584,7 +596,7 @@
struct power_supply *psy = to_power_supply(dev);
struct ds2780_device_info *dev_info = to_ds2780_device_info(psy);
- ret = ds2780_read8(dev_info->w1_dev, &sfr, DS2780_SFR_REG);
+ ret = ds2780_read8(dev_info, &sfr, DS2780_SFR_REG);
if (ret < 0)
return ret;
@@ -611,7 +623,7 @@
return -EINVAL;
}
- ret = ds2780_write(dev_info->w1_dev, &new_setting,
+ ret = ds2780_write(dev_info, &new_setting,
DS2780_SFR_REG, sizeof(u8));
if (ret < 0)
return ret;
@@ -632,7 +644,7 @@
DS2780_EEPROM_BLOCK1_END -
DS2780_EEPROM_BLOCK1_START + 1 - off);
- return ds2780_read_block(dev_info->w1_dev, buf,
+ return ds2780_read_block(dev_info, buf,
DS2780_EEPROM_BLOCK1_START + off, count);
}
@@ -650,7 +662,7 @@
DS2780_EEPROM_BLOCK1_END -
DS2780_EEPROM_BLOCK1_START + 1 - off);
- ret = ds2780_write(dev_info->w1_dev, buf,
+ ret = ds2780_write(dev_info, buf,
DS2780_EEPROM_BLOCK1_START + off, count);
if (ret < 0)
return ret;
@@ -685,9 +697,8 @@
DS2780_EEPROM_BLOCK0_END -
DS2780_EEPROM_BLOCK0_START + 1 - off);
- return ds2780_read_block(dev_info->w1_dev, buf,
+ return ds2780_read_block(dev_info, buf,
DS2780_EEPROM_BLOCK0_START + off, count);
-
}
static ssize_t ds2780_write_user_eeprom_bin(struct file *filp,
@@ -704,7 +715,7 @@
DS2780_EEPROM_BLOCK0_END -
DS2780_EEPROM_BLOCK0_START + 1 - off);
- ret = ds2780_write(dev_info->w1_dev, buf,
+ ret = ds2780_write(dev_info, buf,
DS2780_EEPROM_BLOCK0_START + off, count);
if (ret < 0)
return ret;
@@ -768,6 +779,7 @@
dev_info->bat.properties = ds2780_battery_props;
dev_info->bat.num_properties = ARRAY_SIZE(ds2780_battery_props);
dev_info->bat.get_property = ds2780_battery_get_property;
+ dev_info->mutex_holder = current;
ret = power_supply_register(&pdev->dev, &dev_info->bat);
if (ret) {
@@ -797,6 +809,8 @@
goto fail_remove_bin_file;
}
+ dev_info->mutex_holder = NULL;
+
return 0;
fail_remove_bin_file:
@@ -816,6 +830,8 @@
{
struct ds2780_device_info *dev_info = platform_get_drvdata(pdev);
+ dev_info->mutex_holder = current;
+
/* remove attributes */
sysfs_remove_group(&dev_info->bat.dev->kobj, &ds2780_attr_group);
diff --git a/drivers/pps/clients/Kconfig b/drivers/pps/clients/Kconfig
index 8520a7f..445197d 100644
--- a/drivers/pps/clients/Kconfig
+++ b/drivers/pps/clients/Kconfig
@@ -29,4 +29,13 @@
If you say yes here you get support for a PPS source connected
with the interrupt pin of your parallel port.
+config PPS_CLIENT_GPIO
+ tristate "PPS client using GPIO"
+ depends on PPS && GENERIC_HARDIRQS
+ help
+ If you say yes here you get support for a PPS source using
+ GPIO. To be useful you must also register a platform device
+ specifying the GPIO pin and other options, usually in your board
+ setup.
+
endif
diff --git a/drivers/pps/clients/Makefile b/drivers/pps/clients/Makefile
index 4feb7e9..a461d15 100644
--- a/drivers/pps/clients/Makefile
+++ b/drivers/pps/clients/Makefile
@@ -5,5 +5,6 @@
obj-$(CONFIG_PPS_CLIENT_KTIMER) += pps-ktimer.o
obj-$(CONFIG_PPS_CLIENT_LDISC) += pps-ldisc.o
obj-$(CONFIG_PPS_CLIENT_PARPORT) += pps_parport.o
+obj-$(CONFIG_PPS_CLIENT_GPIO) += pps-gpio.o
ccflags-$(CONFIG_PPS_DEBUG) := -DDEBUG
diff --git a/drivers/pps/clients/pps-gpio.c b/drivers/pps/clients/pps-gpio.c
new file mode 100644
index 0000000..6550555
--- /dev/null
+++ b/drivers/pps/clients/pps-gpio.c
@@ -0,0 +1,227 @@
+/*
+ * pps-gpio.c -- PPS client driver using GPIO
+ *
+ *
+ * Copyright (C) 2010 Ricardo Martins <rasm@fe.up.pt>
+ * Copyright (C) 2011 James Nuss <jamesnuss@nanometrics.ca>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#define PPS_GPIO_NAME "pps-gpio"
+#define pr_fmt(fmt) PPS_GPIO_NAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/pps_kernel.h>
+#include <linux/pps-gpio.h>
+#include <linux/gpio.h>
+#include <linux/list.h>
+
+/* Info for each registered platform device */
+struct pps_gpio_device_data {
+ int irq; /* IRQ used as PPS source */
+ struct pps_device *pps; /* PPS source device */
+ struct pps_source_info info; /* PPS source information */
+ const struct pps_gpio_platform_data *pdata;
+};
+
+/*
+ * Report the PPS event
+ */
+
+static irqreturn_t pps_gpio_irq_handler(int irq, void *data)
+{
+ const struct pps_gpio_device_data *info;
+ struct pps_event_time ts;
+ int rising_edge;
+
+ /* Get the time stamp first */
+ pps_get_ts(&ts);
+
+ info = data;
+
+ rising_edge = gpio_get_value(info->pdata->gpio_pin);
+ if ((rising_edge && !info->pdata->assert_falling_edge) ||
+ (!rising_edge && info->pdata->assert_falling_edge))
+ pps_event(info->pps, &ts, PPS_CAPTUREASSERT, NULL);
+ else if (info->pdata->capture_clear &&
+ ((rising_edge && info->pdata->assert_falling_edge) ||
+ (!rising_edge && !info->pdata->assert_falling_edge)))
+ pps_event(info->pps, &ts, PPS_CAPTURECLEAR, NULL);
+
+ return IRQ_HANDLED;
+}
+
+static int pps_gpio_setup(struct platform_device *pdev)
+{
+ int ret;
+ const struct pps_gpio_platform_data *pdata = pdev->dev.platform_data;
+
+ ret = gpio_request(pdata->gpio_pin, pdata->gpio_label);
+ if (ret) {
+ pr_warning("failed to request GPIO %u\n", pdata->gpio_pin);
+ return -EINVAL;
+ }
+
+ ret = gpio_direction_input(pdata->gpio_pin);
+ if (ret) {
+ pr_warning("failed to set pin direction\n");
+ gpio_free(pdata->gpio_pin);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static unsigned long
+get_irqf_trigger_flags(const struct pps_gpio_platform_data *pdata)
+{
+ unsigned long flags = pdata->assert_falling_edge ?
+ IRQF_TRIGGER_FALLING : IRQF_TRIGGER_RISING;
+
+ if (pdata->capture_clear) {
+ flags |= ((flags & IRQF_TRIGGER_RISING) ?
+ IRQF_TRIGGER_FALLING : IRQF_TRIGGER_RISING);
+ }
+
+ return flags;
+}
+
+static int pps_gpio_probe(struct platform_device *pdev)
+{
+ struct pps_gpio_device_data *data;
+ int irq;
+ int ret;
+ int err;
+ int pps_default_params;
+ const struct pps_gpio_platform_data *pdata = pdev->dev.platform_data;
+
+
+ /* GPIO setup */
+ ret = pps_gpio_setup(pdev);
+ if (ret)
+ return -EINVAL;
+
+ /* IRQ setup */
+ irq = gpio_to_irq(pdata->gpio_pin);
+ if (irq < 0) {
+ pr_err("failed to map GPIO to IRQ: %d\n", irq);
+ err = -EINVAL;
+ goto return_error;
+ }
+
+ /* allocate space for device info */
+ data = kzalloc(sizeof(struct pps_gpio_device_data), GFP_KERNEL);
+ if (data == NULL) {
+ err = -ENOMEM;
+ goto return_error;
+ }
+
+ /* initialize PPS specific parts of the bookkeeping data structure. */
+ data->info.mode = PPS_CAPTUREASSERT | PPS_OFFSETASSERT |
+ PPS_ECHOASSERT | PPS_CANWAIT | PPS_TSFMT_TSPEC;
+ if (pdata->capture_clear)
+ data->info.mode |= PPS_CAPTURECLEAR | PPS_OFFSETCLEAR |
+ PPS_ECHOCLEAR;
+ data->info.owner = THIS_MODULE;
+ snprintf(data->info.name, PPS_MAX_NAME_LEN - 1, "%s.%d",
+ pdev->name, pdev->id);
+
+ /* register PPS source */
+ pps_default_params = PPS_CAPTUREASSERT | PPS_OFFSETASSERT;
+ if (pdata->capture_clear)
+ pps_default_params |= PPS_CAPTURECLEAR | PPS_OFFSETCLEAR;
+ data->pps = pps_register_source(&data->info, pps_default_params);
+ if (data->pps == NULL) {
+ kfree(data);
+ pr_err("failed to register IRQ %d as PPS source\n", irq);
+ err = -EINVAL;
+ goto return_error;
+ }
+
+ data->irq = irq;
+ data->pdata = pdata;
+
+ /* register IRQ interrupt handler */
+ ret = request_irq(irq, pps_gpio_irq_handler,
+ get_irqf_trigger_flags(pdata), data->info.name, data);
+ if (ret) {
+ pps_unregister_source(data->pps);
+ kfree(data);
+ pr_err("failed to acquire IRQ %d\n", irq);
+ err = -EINVAL;
+ goto return_error;
+ }
+
+ platform_set_drvdata(pdev, data);
+ dev_info(data->pps->dev, "Registered IRQ %d as PPS source\n", irq);
+
+ return 0;
+
+return_error:
+ gpio_free(pdata->gpio_pin);
+ return err;
+}
+
+static int pps_gpio_remove(struct platform_device *pdev)
+{
+ struct pps_gpio_device_data *data = platform_get_drvdata(pdev);
+ const struct pps_gpio_platform_data *pdata = data->pdata;
+
+ platform_set_drvdata(pdev, NULL);
+ free_irq(data->irq, data);
+ gpio_free(pdata->gpio_pin);
+ pps_unregister_source(data->pps);
+ pr_info("removed IRQ %d as PPS source\n", data->irq);
+ kfree(data);
+ return 0;
+}
+
+static struct platform_driver pps_gpio_driver = {
+ .probe = pps_gpio_probe,
+ .remove = __devexit_p(pps_gpio_remove),
+ .driver = {
+ .name = PPS_GPIO_NAME,
+ .owner = THIS_MODULE
+ },
+};
+
+static int __init pps_gpio_init(void)
+{
+ int ret = platform_driver_register(&pps_gpio_driver);
+ if (ret < 0)
+ pr_err("failed to register platform driver\n");
+ return ret;
+}
+
+static void __exit pps_gpio_exit(void)
+{
+ platform_driver_unregister(&pps_gpio_driver);
+ pr_debug("unregistered platform driver\n");
+}
+
+module_init(pps_gpio_init);
+module_exit(pps_gpio_exit);
+
+MODULE_AUTHOR("Ricardo Martins <rasm@fe.up.pt>");
+MODULE_AUTHOR("James Nuss <jamesnuss@nanometrics.ca>");
+MODULE_DESCRIPTION("Use GPIO pin as PPS source");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0.0");
diff --git a/drivers/pps/clients/pps-ktimer.c b/drivers/pps/clients/pps-ktimer.c
index 82583b0..436b4e4 100644
--- a/drivers/pps/clients/pps-ktimer.c
+++ b/drivers/pps/clients/pps-ktimer.c
@@ -52,17 +52,6 @@
}
/*
- * The echo function
- */
-
-static void pps_ktimer_echo(struct pps_device *pps, int event, void *data)
-{
- dev_info(pps->dev, "echo %s %s\n",
- event & PPS_CAPTUREASSERT ? "assert" : "",
- event & PPS_CAPTURECLEAR ? "clear" : "");
-}
-
-/*
* The PPS info struct
*/
@@ -72,7 +61,6 @@
.mode = PPS_CAPTUREASSERT | PPS_OFFSETASSERT |
PPS_ECHOASSERT |
PPS_CANWAIT | PPS_TSFMT_TSPEC,
- .echo = pps_ktimer_echo,
.owner = THIS_MODULE,
};
diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c
index c571d6d..e1b4705 100644
--- a/drivers/pps/clients/pps_parport.c
+++ b/drivers/pps/clients/pps_parport.c
@@ -133,14 +133,6 @@
return;
}
-/* the PPS echo function */
-static void pps_echo(struct pps_device *pps, int event, void *data)
-{
- dev_info(pps->dev, "echo %s %s\n",
- event & PPS_CAPTUREASSERT ? "assert" : "",
- event & PPS_CAPTURECLEAR ? "clear" : "");
-}
-
static void parport_attach(struct parport *port)
{
struct pps_client_pp *device;
@@ -151,7 +143,6 @@
PPS_OFFSETASSERT | PPS_OFFSETCLEAR | \
PPS_ECHOASSERT | PPS_ECHOCLEAR | \
PPS_CANWAIT | PPS_TSFMT_TSPEC,
- .echo = pps_echo,
.owner = THIS_MODULE,
.dev = NULL
};
diff --git a/drivers/pps/kapi.c b/drivers/pps/kapi.c
index a4e8eb9..f197e8e 100644
--- a/drivers/pps/kapi.c
+++ b/drivers/pps/kapi.c
@@ -52,6 +52,14 @@
ts->sec += offset->sec;
}
+static void pps_echo_client_default(struct pps_device *pps, int event,
+ void *data)
+{
+ dev_info(pps->dev, "echo %s %s\n",
+ event & PPS_CAPTUREASSERT ? "assert" : "",
+ event & PPS_CAPTURECLEAR ? "clear" : "");
+}
+
/*
* Exported functions
*/
@@ -80,13 +88,6 @@
err = -EINVAL;
goto pps_register_source_exit;
}
- if ((info->mode & (PPS_ECHOASSERT | PPS_ECHOCLEAR)) != 0 &&
- info->echo == NULL) {
- pr_err("%s: echo function is not defined\n",
- info->name);
- err = -EINVAL;
- goto pps_register_source_exit;
- }
if ((info->mode & (PPS_TSFMT_TSPEC | PPS_TSFMT_NTPFP)) == 0) {
pr_err("%s: unspecified time format\n",
info->name);
@@ -108,6 +109,11 @@
pps->params.mode = default_params;
pps->info = *info;
+ /* check for default echo function */
+ if ((pps->info.mode & (PPS_ECHOASSERT | PPS_ECHOCLEAR)) &&
+ pps->info.echo == NULL)
+ pps->info.echo = pps_echo_client_default;
+
init_waitqueue_head(&pps->queue);
spin_lock_init(&pps->lock);
diff --git a/drivers/rapidio/Kconfig b/drivers/rapidio/Kconfig
index 070211a..bc87192 100644
--- a/drivers/rapidio/Kconfig
+++ b/drivers/rapidio/Kconfig
@@ -1,6 +1,8 @@
#
# RapidIO configuration
#
+source "drivers/rapidio/devices/Kconfig"
+
config RAPIDIO_DISC_TIMEOUT
int "Discovery timeout duration (seconds)"
depends on RAPIDIO
@@ -20,8 +22,6 @@
ports for Input/Output direction to allow other traffic
than Maintenance transfers.
-source "drivers/rapidio/switches/Kconfig"
-
config RAPIDIO_DEBUG
bool "RapidIO subsystem debug messages"
depends on RAPIDIO
@@ -32,3 +32,5 @@
going on.
If you are unsure about this, say N here.
+
+source "drivers/rapidio/switches/Kconfig"
diff --git a/drivers/rapidio/Makefile b/drivers/rapidio/Makefile
index 89b8eca..ec3fb81 100644
--- a/drivers/rapidio/Makefile
+++ b/drivers/rapidio/Makefile
@@ -4,5 +4,6 @@
obj-y += rio.o rio-access.o rio-driver.o rio-scan.o rio-sysfs.o
obj-$(CONFIG_RAPIDIO) += switches/
+obj-$(CONFIG_RAPIDIO) += devices/
subdir-ccflags-$(CONFIG_RAPIDIO_DEBUG) := -DDEBUG
diff --git a/drivers/rapidio/devices/Kconfig b/drivers/rapidio/devices/Kconfig
new file mode 100644
index 0000000..12a9d7f
--- /dev/null
+++ b/drivers/rapidio/devices/Kconfig
@@ -0,0 +1,10 @@
+#
+# RapidIO master port configuration
+#
+
+config RAPIDIO_TSI721
+ bool "IDT Tsi721 PCI Express SRIO Controller support"
+ depends on RAPIDIO && PCIEPORTBUS
+ default "n"
+ ---help---
+ Include support for IDT Tsi721 PCI Express Serial RapidIO controller.
diff --git a/drivers/rapidio/devices/Makefile b/drivers/rapidio/devices/Makefile
new file mode 100644
index 0000000..3b7b4e2
--- /dev/null
+++ b/drivers/rapidio/devices/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for RapidIO devices
+#
+
+obj-$(CONFIG_RAPIDIO_TSI721) += tsi721.o
diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c
new file mode 100644
index 0000000..5225930
--- /dev/null
+++ b/drivers/rapidio/devices/tsi721.c
@@ -0,0 +1,2360 @@
+/*
+ * RapidIO mport driver for Tsi721 PCIExpress-to-SRIO bridge
+ *
+ * Copyright 2011 Integrated Device Technology, Inc.
+ * Alexandre Bounine <alexandre.bounine@idt.com>
+ * Chul Kim <chul.kim@idt.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ */
+
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/rio.h>
+#include <linux/rio_drv.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/kfifo.h>
+#include <linux/delay.h>
+
+#include "tsi721.h"
+
+#define DEBUG_PW /* Inbound Port-Write debugging */
+
+static void tsi721_omsg_handler(struct tsi721_device *priv, int ch);
+static void tsi721_imsg_handler(struct tsi721_device *priv, int ch);
+
+/**
+ * tsi721_lcread - read from local SREP config space
+ * @mport: RapidIO master port info
+ * @index: ID of RapdiIO interface
+ * @offset: Offset into configuration space
+ * @len: Length (in bytes) of the maintenance transaction
+ * @data: Value to be read into
+ *
+ * Generates a local SREP space read. Returns %0 on
+ * success or %-EINVAL on failure.
+ */
+static int tsi721_lcread(struct rio_mport *mport, int index, u32 offset,
+ int len, u32 *data)
+{
+ struct tsi721_device *priv = mport->priv;
+
+ if (len != sizeof(u32))
+ return -EINVAL; /* only 32-bit access is supported */
+
+ *data = ioread32(priv->regs + offset);
+
+ return 0;
+}
+
+/**
+ * tsi721_lcwrite - write into local SREP config space
+ * @mport: RapidIO master port info
+ * @index: ID of RapdiIO interface
+ * @offset: Offset into configuration space
+ * @len: Length (in bytes) of the maintenance transaction
+ * @data: Value to be written
+ *
+ * Generates a local write into SREP configuration space. Returns %0 on
+ * success or %-EINVAL on failure.
+ */
+static int tsi721_lcwrite(struct rio_mport *mport, int index, u32 offset,
+ int len, u32 data)
+{
+ struct tsi721_device *priv = mport->priv;
+
+ if (len != sizeof(u32))
+ return -EINVAL; /* only 32-bit access is supported */
+
+ iowrite32(data, priv->regs + offset);
+
+ return 0;
+}
+
+/**
+ * tsi721_maint_dma - Helper function to generate RapidIO maintenance
+ * transactions using designated Tsi721 DMA channel.
+ * @priv: pointer to tsi721 private data
+ * @sys_size: RapdiIO transport system size
+ * @destid: Destination ID of transaction
+ * @hopcount: Number of hops to target device
+ * @offset: Offset into configuration space
+ * @len: Length (in bytes) of the maintenance transaction
+ * @data: Location to be read from or write into
+ * @do_wr: Operation flag (1 == MAINT_WR)
+ *
+ * Generates a RapidIO maintenance transaction (Read or Write).
+ * Returns %0 on success and %-EINVAL or %-EFAULT on failure.
+ */
+static int tsi721_maint_dma(struct tsi721_device *priv, u32 sys_size,
+ u16 destid, u8 hopcount, u32 offset, int len,
+ u32 *data, int do_wr)
+{
+ struct tsi721_dma_desc *bd_ptr;
+ u32 rd_count, swr_ptr, ch_stat;
+ int i, err = 0;
+ u32 op = do_wr ? MAINT_WR : MAINT_RD;
+
+ if (offset > (RIO_MAINT_SPACE_SZ - len) || (len != sizeof(u32)))
+ return -EINVAL;
+
+ bd_ptr = priv->bdma[TSI721_DMACH_MAINT].bd_base;
+
+ rd_count = ioread32(
+ priv->regs + TSI721_DMAC_DRDCNT(TSI721_DMACH_MAINT));
+
+ /* Initialize DMA descriptor */
+ bd_ptr[0].type_id = cpu_to_le32((DTYPE2 << 29) | (op << 19) | destid);
+ bd_ptr[0].bcount = cpu_to_le32((sys_size << 26) | 0x04);
+ bd_ptr[0].raddr_lo = cpu_to_le32((hopcount << 24) | offset);
+ bd_ptr[0].raddr_hi = 0;
+ if (do_wr)
+ bd_ptr[0].data[0] = cpu_to_be32p(data);
+ else
+ bd_ptr[0].data[0] = 0xffffffff;
+
+ mb();
+
+ /* Start DMA operation */
+ iowrite32(rd_count + 2,
+ priv->regs + TSI721_DMAC_DWRCNT(TSI721_DMACH_MAINT));
+ ioread32(priv->regs + TSI721_DMAC_DWRCNT(TSI721_DMACH_MAINT));
+ i = 0;
+
+ /* Wait until DMA transfer is finished */
+ while ((ch_stat = ioread32(priv->regs +
+ TSI721_DMAC_STS(TSI721_DMACH_MAINT))) & TSI721_DMAC_STS_RUN) {
+ udelay(1);
+ if (++i >= 5000000) {
+ dev_dbg(&priv->pdev->dev,
+ "%s : DMA[%d] read timeout ch_status=%x\n",
+ __func__, TSI721_DMACH_MAINT, ch_stat);
+ if (!do_wr)
+ *data = 0xffffffff;
+ err = -EIO;
+ goto err_out;
+ }
+ }
+
+ if (ch_stat & TSI721_DMAC_STS_ABORT) {
+ /* If DMA operation aborted due to error,
+ * reinitialize DMA channel
+ */
+ dev_dbg(&priv->pdev->dev, "%s : DMA ABORT ch_stat=%x\n",
+ __func__, ch_stat);
+ dev_dbg(&priv->pdev->dev, "OP=%d : destid=%x hc=%x off=%x\n",
+ do_wr ? MAINT_WR : MAINT_RD, destid, hopcount, offset);
+ iowrite32(TSI721_DMAC_INT_ALL,
+ priv->regs + TSI721_DMAC_INT(TSI721_DMACH_MAINT));
+ iowrite32(TSI721_DMAC_CTL_INIT,
+ priv->regs + TSI721_DMAC_CTL(TSI721_DMACH_MAINT));
+ udelay(10);
+ iowrite32(0, priv->regs +
+ TSI721_DMAC_DWRCNT(TSI721_DMACH_MAINT));
+ udelay(1);
+ if (!do_wr)
+ *data = 0xffffffff;
+ err = -EIO;
+ goto err_out;
+ }
+
+ if (!do_wr)
+ *data = be32_to_cpu(bd_ptr[0].data[0]);
+
+ /*
+ * Update descriptor status FIFO RD pointer.
+ * NOTE: Skipping check and clear FIFO entries because we are waiting
+ * for transfer to be completed.
+ */
+ swr_ptr = ioread32(priv->regs + TSI721_DMAC_DSWP(TSI721_DMACH_MAINT));
+ iowrite32(swr_ptr, priv->regs + TSI721_DMAC_DSRP(TSI721_DMACH_MAINT));
+err_out:
+
+ return err;
+}
+
+/**
+ * tsi721_cread_dma - Generate a RapidIO maintenance read transaction
+ * using Tsi721 BDMA engine.
+ * @mport: RapidIO master port control structure
+ * @index: ID of RapdiIO interface
+ * @destid: Destination ID of transaction
+ * @hopcount: Number of hops to target device
+ * @offset: Offset into configuration space
+ * @len: Length (in bytes) of the maintenance transaction
+ * @val: Location to be read into
+ *
+ * Generates a RapidIO maintenance read transaction.
+ * Returns %0 on success and %-EINVAL or %-EFAULT on failure.
+ */
+static int tsi721_cread_dma(struct rio_mport *mport, int index, u16 destid,
+ u8 hopcount, u32 offset, int len, u32 *data)
+{
+ struct tsi721_device *priv = mport->priv;
+
+ return tsi721_maint_dma(priv, mport->sys_size, destid, hopcount,
+ offset, len, data, 0);
+}
+
+/**
+ * tsi721_cwrite_dma - Generate a RapidIO maintenance write transaction
+ * using Tsi721 BDMA engine
+ * @mport: RapidIO master port control structure
+ * @index: ID of RapdiIO interface
+ * @destid: Destination ID of transaction
+ * @hopcount: Number of hops to target device
+ * @offset: Offset into configuration space
+ * @len: Length (in bytes) of the maintenance transaction
+ * @val: Value to be written
+ *
+ * Generates a RapidIO maintenance write transaction.
+ * Returns %0 on success and %-EINVAL or %-EFAULT on failure.
+ */
+static int tsi721_cwrite_dma(struct rio_mport *mport, int index, u16 destid,
+ u8 hopcount, u32 offset, int len, u32 data)
+{
+ struct tsi721_device *priv = mport->priv;
+ u32 temp = data;
+
+ return tsi721_maint_dma(priv, mport->sys_size, destid, hopcount,
+ offset, len, &temp, 1);
+}
+
+/**
+ * tsi721_pw_handler - Tsi721 inbound port-write interrupt handler
+ * @mport: RapidIO master port structure
+ *
+ * Handles inbound port-write interrupts. Copies PW message from an internal
+ * buffer into PW message FIFO and schedules deferred routine to process
+ * queued messages.
+ */
+static int
+tsi721_pw_handler(struct rio_mport *mport)
+{
+ struct tsi721_device *priv = mport->priv;
+ u32 pw_stat;
+ u32 pw_buf[TSI721_RIO_PW_MSG_SIZE/sizeof(u32)];
+
+
+ pw_stat = ioread32(priv->regs + TSI721_RIO_PW_RX_STAT);
+
+ if (pw_stat & TSI721_RIO_PW_RX_STAT_PW_VAL) {
+ pw_buf[0] = ioread32(priv->regs + TSI721_RIO_PW_RX_CAPT(0));
+ pw_buf[1] = ioread32(priv->regs + TSI721_RIO_PW_RX_CAPT(1));
+ pw_buf[2] = ioread32(priv->regs + TSI721_RIO_PW_RX_CAPT(2));
+ pw_buf[3] = ioread32(priv->regs + TSI721_RIO_PW_RX_CAPT(3));
+
+ /* Queue PW message (if there is room in FIFO),
+ * otherwise discard it.
+ */
+ spin_lock(&priv->pw_fifo_lock);
+ if (kfifo_avail(&priv->pw_fifo) >= TSI721_RIO_PW_MSG_SIZE)
+ kfifo_in(&priv->pw_fifo, pw_buf,
+ TSI721_RIO_PW_MSG_SIZE);
+ else
+ priv->pw_discard_count++;
+ spin_unlock(&priv->pw_fifo_lock);
+ }
+
+ /* Clear pending PW interrupts */
+ iowrite32(TSI721_RIO_PW_RX_STAT_PW_DISC | TSI721_RIO_PW_RX_STAT_PW_VAL,
+ priv->regs + TSI721_RIO_PW_RX_STAT);
+
+ schedule_work(&priv->pw_work);
+
+ return 0;
+}
+
+static void tsi721_pw_dpc(struct work_struct *work)
+{
+ struct tsi721_device *priv = container_of(work, struct tsi721_device,
+ pw_work);
+ u32 msg_buffer[RIO_PW_MSG_SIZE/sizeof(u32)]; /* Use full size PW message
+ buffer for RIO layer */
+
+ /*
+ * Process port-write messages
+ */
+ while (kfifo_out_spinlocked(&priv->pw_fifo, (unsigned char *)msg_buffer,
+ TSI721_RIO_PW_MSG_SIZE, &priv->pw_fifo_lock)) {
+ /* Process one message */
+#ifdef DEBUG_PW
+ {
+ u32 i;
+ pr_debug("%s : Port-Write Message:", __func__);
+ for (i = 0; i < RIO_PW_MSG_SIZE/sizeof(u32); ) {
+ pr_debug("0x%02x: %08x %08x %08x %08x", i*4,
+ msg_buffer[i], msg_buffer[i + 1],
+ msg_buffer[i + 2], msg_buffer[i + 3]);
+ i += 4;
+ }
+ pr_debug("\n");
+ }
+#endif
+ /* Pass the port-write message to RIO core for processing */
+ rio_inb_pwrite_handler((union rio_pw_msg *)msg_buffer);
+ }
+}
+
+/**
+ * tsi721_pw_enable - enable/disable port-write interface init
+ * @mport: Master port implementing the port write unit
+ * @enable: 1=enable; 0=disable port-write message handling
+ */
+static int tsi721_pw_enable(struct rio_mport *mport, int enable)
+{
+ struct tsi721_device *priv = mport->priv;
+ u32 rval;
+
+ rval = ioread32(priv->regs + TSI721_RIO_EM_INT_ENABLE);
+
+ if (enable)
+ rval |= TSI721_RIO_EM_INT_ENABLE_PW_RX;
+ else
+ rval &= ~TSI721_RIO_EM_INT_ENABLE_PW_RX;
+
+ /* Clear pending PW interrupts */
+ iowrite32(TSI721_RIO_PW_RX_STAT_PW_DISC | TSI721_RIO_PW_RX_STAT_PW_VAL,
+ priv->regs + TSI721_RIO_PW_RX_STAT);
+ /* Update enable bits */
+ iowrite32(rval, priv->regs + TSI721_RIO_EM_INT_ENABLE);
+
+ return 0;
+}
+
+/**
+ * tsi721_dsend - Send a RapidIO doorbell
+ * @mport: RapidIO master port info
+ * @index: ID of RapidIO interface
+ * @destid: Destination ID of target device
+ * @data: 16-bit info field of RapidIO doorbell
+ *
+ * Sends a RapidIO doorbell message. Always returns %0.
+ */
+static int tsi721_dsend(struct rio_mport *mport, int index,
+ u16 destid, u16 data)
+{
+ struct tsi721_device *priv = mport->priv;
+ u32 offset;
+
+ offset = (((mport->sys_size) ? RIO_TT_CODE_16 : RIO_TT_CODE_8) << 18) |
+ (destid << 2);
+
+ dev_dbg(&priv->pdev->dev,
+ "Send Doorbell 0x%04x to destID 0x%x\n", data, destid);
+ iowrite16be(data, priv->odb_base + offset);
+
+ return 0;
+}
+
+/**
+ * tsi721_dbell_handler - Tsi721 doorbell interrupt handler
+ * @mport: RapidIO master port structure
+ *
+ * Handles inbound doorbell interrupts. Copies doorbell entry from an internal
+ * buffer into DB message FIFO and schedules deferred routine to process
+ * queued DBs.
+ */
+static int
+tsi721_dbell_handler(struct rio_mport *mport)
+{
+ struct tsi721_device *priv = mport->priv;
+ u32 regval;
+
+ /* Disable IDB interrupts */
+ regval = ioread32(priv->regs + TSI721_SR_CHINTE(IDB_QUEUE));
+ regval &= ~TSI721_SR_CHINT_IDBQRCV;
+ iowrite32(regval,
+ priv->regs + TSI721_SR_CHINTE(IDB_QUEUE));
+
+ schedule_work(&priv->idb_work);
+
+ return 0;
+}
+
+static void tsi721_db_dpc(struct work_struct *work)
+{
+ struct tsi721_device *priv = container_of(work, struct tsi721_device,
+ idb_work);
+ struct rio_mport *mport;
+ struct rio_dbell *dbell;
+ int found = 0;
+ u32 wr_ptr, rd_ptr;
+ u64 *idb_entry;
+ u32 regval;
+ union {
+ u64 msg;
+ u8 bytes[8];
+ } idb;
+
+ /*
+ * Process queued inbound doorbells
+ */
+ mport = priv->mport;
+
+ wr_ptr = ioread32(priv->regs + TSI721_IDQ_WP(IDB_QUEUE));
+ rd_ptr = ioread32(priv->regs + TSI721_IDQ_RP(IDB_QUEUE));
+
+ while (wr_ptr != rd_ptr) {
+ idb_entry = (u64 *)(priv->idb_base +
+ (TSI721_IDB_ENTRY_SIZE * rd_ptr));
+ rd_ptr++;
+ idb.msg = *idb_entry;
+ *idb_entry = 0;
+
+ /* Process one doorbell */
+ list_for_each_entry(dbell, &mport->dbells, node) {
+ if ((dbell->res->start <= DBELL_INF(idb.bytes)) &&
+ (dbell->res->end >= DBELL_INF(idb.bytes))) {
+ found = 1;
+ break;
+ }
+ }
+
+ if (found) {
+ dbell->dinb(mport, dbell->dev_id, DBELL_SID(idb.bytes),
+ DBELL_TID(idb.bytes), DBELL_INF(idb.bytes));
+ } else {
+ dev_dbg(&priv->pdev->dev,
+ "spurious inb doorbell, sid %2.2x tid %2.2x"
+ " info %4.4x\n", DBELL_SID(idb.bytes),
+ DBELL_TID(idb.bytes), DBELL_INF(idb.bytes));
+ }
+ }
+
+ iowrite32(rd_ptr & (IDB_QSIZE - 1),
+ priv->regs + TSI721_IDQ_RP(IDB_QUEUE));
+
+ /* Re-enable IDB interrupts */
+ regval = ioread32(priv->regs + TSI721_SR_CHINTE(IDB_QUEUE));
+ regval |= TSI721_SR_CHINT_IDBQRCV;
+ iowrite32(regval,
+ priv->regs + TSI721_SR_CHINTE(IDB_QUEUE));
+}
+
+/**
+ * tsi721_irqhandler - Tsi721 interrupt handler
+ * @irq: Linux interrupt number
+ * @ptr: Pointer to interrupt-specific data (mport structure)
+ *
+ * Handles Tsi721 interrupts signaled using MSI and INTA. Checks reported
+ * interrupt events and calls an event-specific handler(s).
+ */
+static irqreturn_t tsi721_irqhandler(int irq, void *ptr)
+{
+ struct rio_mport *mport = (struct rio_mport *)ptr;
+ struct tsi721_device *priv = mport->priv;
+ u32 dev_int;
+ u32 dev_ch_int;
+ u32 intval;
+ u32 ch_inte;
+
+ dev_int = ioread32(priv->regs + TSI721_DEV_INT);
+ if (!dev_int)
+ return IRQ_NONE;
+
+ dev_ch_int = ioread32(priv->regs + TSI721_DEV_CHAN_INT);
+
+ if (dev_int & TSI721_DEV_INT_SR2PC_CH) {
+ /* Service SR2PC Channel interrupts */
+ if (dev_ch_int & TSI721_INT_SR2PC_CHAN(IDB_QUEUE)) {
+ /* Service Inbound Doorbell interrupt */
+ intval = ioread32(priv->regs +
+ TSI721_SR_CHINT(IDB_QUEUE));
+ if (intval & TSI721_SR_CHINT_IDBQRCV)
+ tsi721_dbell_handler(mport);
+ else
+ dev_info(&priv->pdev->dev,
+ "Unsupported SR_CH_INT %x\n", intval);
+
+ /* Clear interrupts */
+ iowrite32(intval,
+ priv->regs + TSI721_SR_CHINT(IDB_QUEUE));
+ ioread32(priv->regs + TSI721_SR_CHINT(IDB_QUEUE));
+ }
+ }
+
+ if (dev_int & TSI721_DEV_INT_SMSG_CH) {
+ int ch;
+
+ /*
+ * Service channel interrupts from Messaging Engine
+ */
+
+ if (dev_ch_int & TSI721_INT_IMSG_CHAN_M) { /* Inbound Msg */
+ /* Disable signaled OB MSG Channel interrupts */
+ ch_inte = ioread32(priv->regs + TSI721_DEV_CHAN_INTE);
+ ch_inte &= ~(dev_ch_int & TSI721_INT_IMSG_CHAN_M);
+ iowrite32(ch_inte, priv->regs + TSI721_DEV_CHAN_INTE);
+
+ /*
+ * Process Inbound Message interrupt for each MBOX
+ */
+ for (ch = 4; ch < RIO_MAX_MBOX + 4; ch++) {
+ if (!(dev_ch_int & TSI721_INT_IMSG_CHAN(ch)))
+ continue;
+ tsi721_imsg_handler(priv, ch);
+ }
+ }
+
+ if (dev_ch_int & TSI721_INT_OMSG_CHAN_M) { /* Outbound Msg */
+ /* Disable signaled OB MSG Channel interrupts */
+ ch_inte = ioread32(priv->regs + TSI721_DEV_CHAN_INTE);
+ ch_inte &= ~(dev_ch_int & TSI721_INT_OMSG_CHAN_M);
+ iowrite32(ch_inte, priv->regs + TSI721_DEV_CHAN_INTE);
+
+ /*
+ * Process Outbound Message interrupts for each MBOX
+ */
+
+ for (ch = 0; ch < RIO_MAX_MBOX; ch++) {
+ if (!(dev_ch_int & TSI721_INT_OMSG_CHAN(ch)))
+ continue;
+ tsi721_omsg_handler(priv, ch);
+ }
+ }
+ }
+
+ if (dev_int & TSI721_DEV_INT_SRIO) {
+ /* Service SRIO MAC interrupts */
+ intval = ioread32(priv->regs + TSI721_RIO_EM_INT_STAT);
+ if (intval & TSI721_RIO_EM_INT_STAT_PW_RX)
+ tsi721_pw_handler(mport);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void tsi721_interrupts_init(struct tsi721_device *priv)
+{
+ u32 intr;
+
+ /* Enable IDB interrupts */
+ iowrite32(TSI721_SR_CHINT_ALL,
+ priv->regs + TSI721_SR_CHINT(IDB_QUEUE));
+ iowrite32(TSI721_SR_CHINT_IDBQRCV,
+ priv->regs + TSI721_SR_CHINTE(IDB_QUEUE));
+ iowrite32(TSI721_INT_SR2PC_CHAN(IDB_QUEUE),
+ priv->regs + TSI721_DEV_CHAN_INTE);
+
+ /* Enable SRIO MAC interrupts */
+ iowrite32(TSI721_RIO_EM_DEV_INT_EN_INT,
+ priv->regs + TSI721_RIO_EM_DEV_INT_EN);
+
+ if (priv->flags & TSI721_USING_MSIX)
+ intr = TSI721_DEV_INT_SRIO;
+ else
+ intr = TSI721_DEV_INT_SR2PC_CH | TSI721_DEV_INT_SRIO |
+ TSI721_DEV_INT_SMSG_CH;
+
+ iowrite32(intr, priv->regs + TSI721_DEV_INTE);
+ ioread32(priv->regs + TSI721_DEV_INTE);
+}
+
+#ifdef CONFIG_PCI_MSI
+/**
+ * tsi721_omsg_msix - MSI-X interrupt handler for outbound messaging
+ * @irq: Linux interrupt number
+ * @ptr: Pointer to interrupt-specific data (mport structure)
+ *
+ * Handles outbound messaging interrupts signaled using MSI-X.
+ */
+static irqreturn_t tsi721_omsg_msix(int irq, void *ptr)
+{
+ struct tsi721_device *priv = ((struct rio_mport *)ptr)->priv;
+ int mbox;
+
+ mbox = (irq - priv->msix[TSI721_VECT_OMB0_DONE].vector) % RIO_MAX_MBOX;
+ tsi721_omsg_handler(priv, mbox);
+ return IRQ_HANDLED;
+}
+
+/**
+ * tsi721_imsg_msix - MSI-X interrupt handler for inbound messaging
+ * @irq: Linux interrupt number
+ * @ptr: Pointer to interrupt-specific data (mport structure)
+ *
+ * Handles inbound messaging interrupts signaled using MSI-X.
+ */
+static irqreturn_t tsi721_imsg_msix(int irq, void *ptr)
+{
+ struct tsi721_device *priv = ((struct rio_mport *)ptr)->priv;
+ int mbox;
+
+ mbox = (irq - priv->msix[TSI721_VECT_IMB0_RCV].vector) % RIO_MAX_MBOX;
+ tsi721_imsg_handler(priv, mbox + 4);
+ return IRQ_HANDLED;
+}
+
+/**
+ * tsi721_srio_msix - Tsi721 MSI-X SRIO MAC interrupt handler
+ * @irq: Linux interrupt number
+ * @ptr: Pointer to interrupt-specific data (mport structure)
+ *
+ * Handles Tsi721 interrupts from SRIO MAC.
+ */
+static irqreturn_t tsi721_srio_msix(int irq, void *ptr)
+{
+ struct tsi721_device *priv = ((struct rio_mport *)ptr)->priv;
+ u32 srio_int;
+
+ /* Service SRIO MAC interrupts */
+ srio_int = ioread32(priv->regs + TSI721_RIO_EM_INT_STAT);
+ if (srio_int & TSI721_RIO_EM_INT_STAT_PW_RX)
+ tsi721_pw_handler((struct rio_mport *)ptr);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * tsi721_sr2pc_ch_msix - Tsi721 MSI-X SR2PC Channel interrupt handler
+ * @irq: Linux interrupt number
+ * @ptr: Pointer to interrupt-specific data (mport structure)
+ *
+ * Handles Tsi721 interrupts from SR2PC Channel.
+ * NOTE: At this moment services only one SR2PC channel associated with inbound
+ * doorbells.
+ */
+static irqreturn_t tsi721_sr2pc_ch_msix(int irq, void *ptr)
+{
+ struct tsi721_device *priv = ((struct rio_mport *)ptr)->priv;
+ u32 sr_ch_int;
+
+ /* Service Inbound DB interrupt from SR2PC channel */
+ sr_ch_int = ioread32(priv->regs + TSI721_SR_CHINT(IDB_QUEUE));
+ if (sr_ch_int & TSI721_SR_CHINT_IDBQRCV)
+ tsi721_dbell_handler((struct rio_mport *)ptr);
+
+ /* Clear interrupts */
+ iowrite32(sr_ch_int, priv->regs + TSI721_SR_CHINT(IDB_QUEUE));
+ /* Read back to ensure that interrupt was cleared */
+ sr_ch_int = ioread32(priv->regs + TSI721_SR_CHINT(IDB_QUEUE));
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * tsi721_request_msix - register interrupt service for MSI-X mode.
+ * @mport: RapidIO master port structure
+ *
+ * Registers MSI-X interrupt service routines for interrupts that are active
+ * immediately after mport initialization. Messaging interrupt service routines
+ * should be registered during corresponding open requests.
+ */
+static int tsi721_request_msix(struct rio_mport *mport)
+{
+ struct tsi721_device *priv = mport->priv;
+ int err = 0;
+
+ err = request_irq(priv->msix[TSI721_VECT_IDB].vector,
+ tsi721_sr2pc_ch_msix, 0,
+ priv->msix[TSI721_VECT_IDB].irq_name, (void *)mport);
+ if (err)
+ goto out;
+
+ err = request_irq(priv->msix[TSI721_VECT_PWRX].vector,
+ tsi721_srio_msix, 0,
+ priv->msix[TSI721_VECT_PWRX].irq_name, (void *)mport);
+ if (err)
+ free_irq(
+ priv->msix[TSI721_VECT_IDB].vector,
+ (void *)mport);
+out:
+ return err;
+}
+
+/**
+ * tsi721_enable_msix - Attempts to enable MSI-X support for Tsi721.
+ * @priv: pointer to tsi721 private data
+ *
+ * Configures MSI-X support for Tsi721. Supports only an exact number
+ * of requested vectors.
+ */
+static int tsi721_enable_msix(struct tsi721_device *priv)
+{
+ struct msix_entry entries[TSI721_VECT_MAX];
+ int err;
+ int i;
+
+ entries[TSI721_VECT_IDB].entry = TSI721_MSIX_SR2PC_IDBQ_RCV(IDB_QUEUE);
+ entries[TSI721_VECT_PWRX].entry = TSI721_MSIX_SRIO_MAC_INT;
+
+ /*
+ * Initialize MSI-X entries for Messaging Engine:
+ * this driver supports four RIO mailboxes (inbound and outbound)
+ * NOTE: Inbound message MBOX 0...4 use IB channels 4...7. Therefore
+ * offset +4 is added to IB MBOX number.
+ */
+ for (i = 0; i < RIO_MAX_MBOX; i++) {
+ entries[TSI721_VECT_IMB0_RCV + i].entry =
+ TSI721_MSIX_IMSG_DQ_RCV(i + 4);
+ entries[TSI721_VECT_IMB0_INT + i].entry =
+ TSI721_MSIX_IMSG_INT(i + 4);
+ entries[TSI721_VECT_OMB0_DONE + i].entry =
+ TSI721_MSIX_OMSG_DONE(i);
+ entries[TSI721_VECT_OMB0_INT + i].entry =
+ TSI721_MSIX_OMSG_INT(i);
+ }
+
+ err = pci_enable_msix(priv->pdev, entries, ARRAY_SIZE(entries));
+ if (err) {
+ if (err > 0)
+ dev_info(&priv->pdev->dev,
+ "Only %d MSI-X vectors available, "
+ "not using MSI-X\n", err);
+ return err;
+ }
+
+ /*
+ * Copy MSI-X vector information into tsi721 private structure
+ */
+ priv->msix[TSI721_VECT_IDB].vector = entries[TSI721_VECT_IDB].vector;
+ snprintf(priv->msix[TSI721_VECT_IDB].irq_name, IRQ_DEVICE_NAME_MAX,
+ DRV_NAME "-idb@pci:%s", pci_name(priv->pdev));
+ priv->msix[TSI721_VECT_PWRX].vector = entries[TSI721_VECT_PWRX].vector;
+ snprintf(priv->msix[TSI721_VECT_PWRX].irq_name, IRQ_DEVICE_NAME_MAX,
+ DRV_NAME "-pwrx@pci:%s", pci_name(priv->pdev));
+
+ for (i = 0; i < RIO_MAX_MBOX; i++) {
+ priv->msix[TSI721_VECT_IMB0_RCV + i].vector =
+ entries[TSI721_VECT_IMB0_RCV + i].vector;
+ snprintf(priv->msix[TSI721_VECT_IMB0_RCV + i].irq_name,
+ IRQ_DEVICE_NAME_MAX, DRV_NAME "-imbr%d@pci:%s",
+ i, pci_name(priv->pdev));
+
+ priv->msix[TSI721_VECT_IMB0_INT + i].vector =
+ entries[TSI721_VECT_IMB0_INT + i].vector;
+ snprintf(priv->msix[TSI721_VECT_IMB0_INT + i].irq_name,
+ IRQ_DEVICE_NAME_MAX, DRV_NAME "-imbi%d@pci:%s",
+ i, pci_name(priv->pdev));
+
+ priv->msix[TSI721_VECT_OMB0_DONE + i].vector =
+ entries[TSI721_VECT_OMB0_DONE + i].vector;
+ snprintf(priv->msix[TSI721_VECT_OMB0_DONE + i].irq_name,
+ IRQ_DEVICE_NAME_MAX, DRV_NAME "-ombd%d@pci:%s",
+ i, pci_name(priv->pdev));
+
+ priv->msix[TSI721_VECT_OMB0_INT + i].vector =
+ entries[TSI721_VECT_OMB0_INT + i].vector;
+ snprintf(priv->msix[TSI721_VECT_OMB0_INT + i].irq_name,
+ IRQ_DEVICE_NAME_MAX, DRV_NAME "-ombi%d@pci:%s",
+ i, pci_name(priv->pdev));
+ }
+
+ return 0;
+}
+#endif /* CONFIG_PCI_MSI */
+
+static int tsi721_request_irq(struct rio_mport *mport)
+{
+ struct tsi721_device *priv = mport->priv;
+ int err;
+
+#ifdef CONFIG_PCI_MSI
+ if (priv->flags & TSI721_USING_MSIX)
+ err = tsi721_request_msix(mport);
+ else
+#endif
+ err = request_irq(priv->pdev->irq, tsi721_irqhandler,
+ (priv->flags & TSI721_USING_MSI) ? 0 : IRQF_SHARED,
+ DRV_NAME, (void *)mport);
+
+ if (err)
+ dev_err(&priv->pdev->dev,
+ "Unable to allocate interrupt, Error: %d\n", err);
+
+ return err;
+}
+
+/**
+ * tsi721_init_pc2sr_mapping - initializes outbound (PCIe->SRIO)
+ * translation regions.
+ * @priv: pointer to tsi721 private data
+ *
+ * Disables SREP translation regions.
+ */
+static void tsi721_init_pc2sr_mapping(struct tsi721_device *priv)
+{
+ int i;
+
+ /* Disable all PC2SR translation windows */
+ for (i = 0; i < TSI721_OBWIN_NUM; i++)
+ iowrite32(0, priv->regs + TSI721_OBWINLB(i));
+}
+
+/**
+ * tsi721_init_sr2pc_mapping - initializes inbound (SRIO->PCIe)
+ * translation regions.
+ * @priv: pointer to tsi721 private data
+ *
+ * Disables inbound windows.
+ */
+static void tsi721_init_sr2pc_mapping(struct tsi721_device *priv)
+{
+ int i;
+
+ /* Disable all SR2PC inbound windows */
+ for (i = 0; i < TSI721_IBWIN_NUM; i++)
+ iowrite32(0, priv->regs + TSI721_IBWINLB(i));
+}
+
+/**
+ * tsi721_port_write_init - Inbound port write interface init
+ * @priv: pointer to tsi721 private data
+ *
+ * Initializes inbound port write handler.
+ * Returns %0 on success or %-ENOMEM on failure.
+ */
+static int tsi721_port_write_init(struct tsi721_device *priv)
+{
+ priv->pw_discard_count = 0;
+ INIT_WORK(&priv->pw_work, tsi721_pw_dpc);
+ spin_lock_init(&priv->pw_fifo_lock);
+ if (kfifo_alloc(&priv->pw_fifo,
+ TSI721_RIO_PW_MSG_SIZE * 32, GFP_KERNEL)) {
+ dev_err(&priv->pdev->dev, "PW FIFO allocation failed\n");
+ return -ENOMEM;
+ }
+
+ /* Use reliable port-write capture mode */
+ iowrite32(TSI721_RIO_PW_CTL_PWC_REL, priv->regs + TSI721_RIO_PW_CTL);
+ return 0;
+}
+
+static int tsi721_doorbell_init(struct tsi721_device *priv)
+{
+ /* Outbound Doorbells do not require any setup.
+ * Tsi721 uses dedicated PCI BAR1 to generate doorbells.
+ * That BAR1 was mapped during the probe routine.
+ */
+
+ /* Initialize Inbound Doorbell processing DPC and queue */
+ priv->db_discard_count = 0;
+ INIT_WORK(&priv->idb_work, tsi721_db_dpc);
+
+ /* Allocate buffer for inbound doorbells queue */
+ priv->idb_base = dma_alloc_coherent(&priv->pdev->dev,
+ IDB_QSIZE * TSI721_IDB_ENTRY_SIZE,
+ &priv->idb_dma, GFP_KERNEL);
+ if (!priv->idb_base)
+ return -ENOMEM;
+
+ memset(priv->idb_base, 0, IDB_QSIZE * TSI721_IDB_ENTRY_SIZE);
+
+ dev_dbg(&priv->pdev->dev, "Allocated IDB buffer @ %p (phys = %llx)\n",
+ priv->idb_base, (unsigned long long)priv->idb_dma);
+
+ iowrite32(TSI721_IDQ_SIZE_VAL(IDB_QSIZE),
+ priv->regs + TSI721_IDQ_SIZE(IDB_QUEUE));
+ iowrite32(((u64)priv->idb_dma >> 32),
+ priv->regs + TSI721_IDQ_BASEU(IDB_QUEUE));
+ iowrite32(((u64)priv->idb_dma & TSI721_IDQ_BASEL_ADDR),
+ priv->regs + TSI721_IDQ_BASEL(IDB_QUEUE));
+ /* Enable accepting all inbound doorbells */
+ iowrite32(0, priv->regs + TSI721_IDQ_MASK(IDB_QUEUE));
+
+ iowrite32(TSI721_IDQ_INIT, priv->regs + TSI721_IDQ_CTL(IDB_QUEUE));
+
+ iowrite32(0, priv->regs + TSI721_IDQ_RP(IDB_QUEUE));
+
+ return 0;
+}
+
+static void tsi721_doorbell_free(struct tsi721_device *priv)
+{
+ if (priv->idb_base == NULL)
+ return;
+
+ /* Free buffer allocated for inbound doorbell queue */
+ dma_free_coherent(&priv->pdev->dev, IDB_QSIZE * TSI721_IDB_ENTRY_SIZE,
+ priv->idb_base, priv->idb_dma);
+ priv->idb_base = NULL;
+}
+
+static int tsi721_bdma_ch_init(struct tsi721_device *priv, int chnum)
+{
+ struct tsi721_dma_desc *bd_ptr;
+ u64 *sts_ptr;
+ dma_addr_t bd_phys, sts_phys;
+ int sts_size;
+ int bd_num = priv->bdma[chnum].bd_num;
+
+ dev_dbg(&priv->pdev->dev, "Init Block DMA Engine, CH%d\n", chnum);
+
+ /*
+ * Initialize DMA channel for maintenance requests
+ */
+
+ /* Allocate space for DMA descriptors */
+ bd_ptr = dma_alloc_coherent(&priv->pdev->dev,
+ bd_num * sizeof(struct tsi721_dma_desc),
+ &bd_phys, GFP_KERNEL);
+ if (!bd_ptr)
+ return -ENOMEM;
+
+ priv->bdma[chnum].bd_phys = bd_phys;
+ priv->bdma[chnum].bd_base = bd_ptr;
+
+ memset(bd_ptr, 0, bd_num * sizeof(struct tsi721_dma_desc));
+
+ dev_dbg(&priv->pdev->dev, "DMA descriptors @ %p (phys = %llx)\n",
+ bd_ptr, (unsigned long long)bd_phys);
+
+ /* Allocate space for descriptor status FIFO */
+ sts_size = (bd_num >= TSI721_DMA_MINSTSSZ) ?
+ bd_num : TSI721_DMA_MINSTSSZ;
+ sts_size = roundup_pow_of_two(sts_size);
+ sts_ptr = dma_alloc_coherent(&priv->pdev->dev,
+ sts_size * sizeof(struct tsi721_dma_sts),
+ &sts_phys, GFP_KERNEL);
+ if (!sts_ptr) {
+ /* Free space allocated for DMA descriptors */
+ dma_free_coherent(&priv->pdev->dev,
+ bd_num * sizeof(struct tsi721_dma_desc),
+ bd_ptr, bd_phys);
+ priv->bdma[chnum].bd_base = NULL;
+ return -ENOMEM;
+ }
+
+ priv->bdma[chnum].sts_phys = sts_phys;
+ priv->bdma[chnum].sts_base = sts_ptr;
+ priv->bdma[chnum].sts_size = sts_size;
+
+ memset(sts_ptr, 0, sts_size);
+
+ dev_dbg(&priv->pdev->dev,
+ "desc status FIFO @ %p (phys = %llx) size=0x%x\n",
+ sts_ptr, (unsigned long long)sts_phys, sts_size);
+
+ /* Initialize DMA descriptors ring */
+ bd_ptr[bd_num - 1].type_id = cpu_to_le32(DTYPE3 << 29);
+ bd_ptr[bd_num - 1].next_lo = cpu_to_le32((u64)bd_phys &
+ TSI721_DMAC_DPTRL_MASK);
+ bd_ptr[bd_num - 1].next_hi = cpu_to_le32((u64)bd_phys >> 32);
+
+ /* Setup DMA descriptor pointers */
+ iowrite32(((u64)bd_phys >> 32),
+ priv->regs + TSI721_DMAC_DPTRH(chnum));
+ iowrite32(((u64)bd_phys & TSI721_DMAC_DPTRL_MASK),
+ priv->regs + TSI721_DMAC_DPTRL(chnum));
+
+ /* Setup descriptor status FIFO */
+ iowrite32(((u64)sts_phys >> 32),
+ priv->regs + TSI721_DMAC_DSBH(chnum));
+ iowrite32(((u64)sts_phys & TSI721_DMAC_DSBL_MASK),
+ priv->regs + TSI721_DMAC_DSBL(chnum));
+ iowrite32(TSI721_DMAC_DSSZ_SIZE(sts_size),
+ priv->regs + TSI721_DMAC_DSSZ(chnum));
+
+ /* Clear interrupt bits */
+ iowrite32(TSI721_DMAC_INT_ALL,
+ priv->regs + TSI721_DMAC_INT(chnum));
+
+ ioread32(priv->regs + TSI721_DMAC_INT(chnum));
+
+ /* Toggle DMA channel initialization */
+ iowrite32(TSI721_DMAC_CTL_INIT, priv->regs + TSI721_DMAC_CTL(chnum));
+ ioread32(priv->regs + TSI721_DMAC_CTL(chnum));
+ udelay(10);
+
+ return 0;
+}
+
+static int tsi721_bdma_ch_free(struct tsi721_device *priv, int chnum)
+{
+ u32 ch_stat;
+
+ if (priv->bdma[chnum].bd_base == NULL)
+ return 0;
+
+ /* Check if DMA channel still running */
+ ch_stat = ioread32(priv->regs + TSI721_DMAC_STS(chnum));
+ if (ch_stat & TSI721_DMAC_STS_RUN)
+ return -EFAULT;
+
+ /* Put DMA channel into init state */
+ iowrite32(TSI721_DMAC_CTL_INIT,
+ priv->regs + TSI721_DMAC_CTL(chnum));
+
+ /* Free space allocated for DMA descriptors */
+ dma_free_coherent(&priv->pdev->dev,
+ priv->bdma[chnum].bd_num * sizeof(struct tsi721_dma_desc),
+ priv->bdma[chnum].bd_base, priv->bdma[chnum].bd_phys);
+ priv->bdma[chnum].bd_base = NULL;
+
+ /* Free space allocated for status FIFO */
+ dma_free_coherent(&priv->pdev->dev,
+ priv->bdma[chnum].sts_size * sizeof(struct tsi721_dma_sts),
+ priv->bdma[chnum].sts_base, priv->bdma[chnum].sts_phys);
+ priv->bdma[chnum].sts_base = NULL;
+ return 0;
+}
+
+static int tsi721_bdma_init(struct tsi721_device *priv)
+{
+ /* Initialize BDMA channel allocated for RapidIO maintenance read/write
+ * request generation
+ */
+ priv->bdma[TSI721_DMACH_MAINT].bd_num = 2;
+ if (tsi721_bdma_ch_init(priv, TSI721_DMACH_MAINT)) {
+ dev_err(&priv->pdev->dev, "Unable to initialize maintenance DMA"
+ " channel %d, aborting\n", TSI721_DMACH_MAINT);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void tsi721_bdma_free(struct tsi721_device *priv)
+{
+ tsi721_bdma_ch_free(priv, TSI721_DMACH_MAINT);
+}
+
+/* Enable Inbound Messaging Interrupts */
+static void
+tsi721_imsg_interrupt_enable(struct tsi721_device *priv, int ch,
+ u32 inte_mask)
+{
+ u32 rval;
+
+ if (!inte_mask)
+ return;
+
+ /* Clear pending Inbound Messaging interrupts */
+ iowrite32(inte_mask, priv->regs + TSI721_IBDMAC_INT(ch));
+
+ /* Enable Inbound Messaging interrupts */
+ rval = ioread32(priv->regs + TSI721_IBDMAC_INTE(ch));
+ iowrite32(rval | inte_mask, priv->regs + TSI721_IBDMAC_INTE(ch));
+
+ if (priv->flags & TSI721_USING_MSIX)
+ return; /* Finished if we are in MSI-X mode */
+
+ /*
+ * For MSI and INTA interrupt signalling we need to enable next levels
+ */
+
+ /* Enable Device Channel Interrupt */
+ rval = ioread32(priv->regs + TSI721_DEV_CHAN_INTE);
+ iowrite32(rval | TSI721_INT_IMSG_CHAN(ch),
+ priv->regs + TSI721_DEV_CHAN_INTE);
+}
+
+/* Disable Inbound Messaging Interrupts */
+static void
+tsi721_imsg_interrupt_disable(struct tsi721_device *priv, int ch,
+ u32 inte_mask)
+{
+ u32 rval;
+
+ if (!inte_mask)
+ return;
+
+ /* Clear pending Inbound Messaging interrupts */
+ iowrite32(inte_mask, priv->regs + TSI721_IBDMAC_INT(ch));
+
+ /* Disable Inbound Messaging interrupts */
+ rval = ioread32(priv->regs + TSI721_IBDMAC_INTE(ch));
+ rval &= ~inte_mask;
+ iowrite32(rval, priv->regs + TSI721_IBDMAC_INTE(ch));
+
+ if (priv->flags & TSI721_USING_MSIX)
+ return; /* Finished if we are in MSI-X mode */
+
+ /*
+ * For MSI and INTA interrupt signalling we need to disable next levels
+ */
+
+ /* Disable Device Channel Interrupt */
+ rval = ioread32(priv->regs + TSI721_DEV_CHAN_INTE);
+ rval &= ~TSI721_INT_IMSG_CHAN(ch);
+ iowrite32(rval, priv->regs + TSI721_DEV_CHAN_INTE);
+}
+
+/* Enable Outbound Messaging interrupts */
+static void
+tsi721_omsg_interrupt_enable(struct tsi721_device *priv, int ch,
+ u32 inte_mask)
+{
+ u32 rval;
+
+ if (!inte_mask)
+ return;
+
+ /* Clear pending Outbound Messaging interrupts */
+ iowrite32(inte_mask, priv->regs + TSI721_OBDMAC_INT(ch));
+
+ /* Enable Outbound Messaging channel interrupts */
+ rval = ioread32(priv->regs + TSI721_OBDMAC_INTE(ch));
+ iowrite32(rval | inte_mask, priv->regs + TSI721_OBDMAC_INTE(ch));
+
+ if (priv->flags & TSI721_USING_MSIX)
+ return; /* Finished if we are in MSI-X mode */
+
+ /*
+ * For MSI and INTA interrupt signalling we need to enable next levels
+ */
+
+ /* Enable Device Channel Interrupt */
+ rval = ioread32(priv->regs + TSI721_DEV_CHAN_INTE);
+ iowrite32(rval | TSI721_INT_OMSG_CHAN(ch),
+ priv->regs + TSI721_DEV_CHAN_INTE);
+}
+
+/* Disable Outbound Messaging interrupts */
+static void
+tsi721_omsg_interrupt_disable(struct tsi721_device *priv, int ch,
+ u32 inte_mask)
+{
+ u32 rval;
+
+ if (!inte_mask)
+ return;
+
+ /* Clear pending Outbound Messaging interrupts */
+ iowrite32(inte_mask, priv->regs + TSI721_OBDMAC_INT(ch));
+
+ /* Disable Outbound Messaging interrupts */
+ rval = ioread32(priv->regs + TSI721_OBDMAC_INTE(ch));
+ rval &= ~inte_mask;
+ iowrite32(rval, priv->regs + TSI721_OBDMAC_INTE(ch));
+
+ if (priv->flags & TSI721_USING_MSIX)
+ return; /* Finished if we are in MSI-X mode */
+
+ /*
+ * For MSI and INTA interrupt signalling we need to disable next levels
+ */
+
+ /* Disable Device Channel Interrupt */
+ rval = ioread32(priv->regs + TSI721_DEV_CHAN_INTE);
+ rval &= ~TSI721_INT_OMSG_CHAN(ch);
+ iowrite32(rval, priv->regs + TSI721_DEV_CHAN_INTE);
+}
+
+/**
+ * tsi721_add_outb_message - Add message to the Tsi721 outbound message queue
+ * @mport: Master port with outbound message queue
+ * @rdev: Target of outbound message
+ * @mbox: Outbound mailbox
+ * @buffer: Message to add to outbound queue
+ * @len: Length of message
+ */
+static int
+tsi721_add_outb_message(struct rio_mport *mport, struct rio_dev *rdev, int mbox,
+ void *buffer, size_t len)
+{
+ struct tsi721_device *priv = mport->priv;
+ struct tsi721_omsg_desc *desc;
+ u32 tx_slot;
+
+ if (!priv->omsg_init[mbox] ||
+ len > TSI721_MSG_MAX_SIZE || len < 8)
+ return -EINVAL;
+
+ tx_slot = priv->omsg_ring[mbox].tx_slot;
+
+ /* Copy copy message into transfer buffer */
+ memcpy(priv->omsg_ring[mbox].omq_base[tx_slot], buffer, len);
+
+ if (len & 0x7)
+ len += 8;
+
+ /* Build descriptor associated with buffer */
+ desc = priv->omsg_ring[mbox].omd_base;
+ desc[tx_slot].type_id = cpu_to_le32((DTYPE4 << 29) | rdev->destid);
+ if (tx_slot % 4 == 0)
+ desc[tx_slot].type_id |= cpu_to_le32(TSI721_OMD_IOF);
+
+ desc[tx_slot].msg_info =
+ cpu_to_le32((mport->sys_size << 26) | (mbox << 22) |
+ (0xe << 12) | (len & 0xff8));
+ desc[tx_slot].bufptr_lo =
+ cpu_to_le32((u64)priv->omsg_ring[mbox].omq_phys[tx_slot] &
+ 0xffffffff);
+ desc[tx_slot].bufptr_hi =
+ cpu_to_le32((u64)priv->omsg_ring[mbox].omq_phys[tx_slot] >> 32);
+
+ priv->omsg_ring[mbox].wr_count++;
+
+ /* Go to next descriptor */
+ if (++priv->omsg_ring[mbox].tx_slot == priv->omsg_ring[mbox].size) {
+ priv->omsg_ring[mbox].tx_slot = 0;
+ /* Move through the ring link descriptor at the end */
+ priv->omsg_ring[mbox].wr_count++;
+ }
+
+ mb();
+
+ /* Set new write count value */
+ iowrite32(priv->omsg_ring[mbox].wr_count,
+ priv->regs + TSI721_OBDMAC_DWRCNT(mbox));
+ ioread32(priv->regs + TSI721_OBDMAC_DWRCNT(mbox));
+
+ return 0;
+}
+
+/**
+ * tsi721_omsg_handler - Outbound Message Interrupt Handler
+ * @priv: pointer to tsi721 private data
+ * @ch: number of OB MSG channel to service
+ *
+ * Services channel interrupts from outbound messaging engine.
+ */
+static void tsi721_omsg_handler(struct tsi721_device *priv, int ch)
+{
+ u32 omsg_int;
+
+ spin_lock(&priv->omsg_ring[ch].lock);
+
+ omsg_int = ioread32(priv->regs + TSI721_OBDMAC_INT(ch));
+
+ if (omsg_int & TSI721_OBDMAC_INT_ST_FULL)
+ dev_info(&priv->pdev->dev,
+ "OB MBOX%d: Status FIFO is full\n", ch);
+
+ if (omsg_int & (TSI721_OBDMAC_INT_DONE | TSI721_OBDMAC_INT_IOF_DONE)) {
+ u32 srd_ptr;
+ u64 *sts_ptr, last_ptr = 0, prev_ptr = 0;
+ int i, j;
+ u32 tx_slot;
+
+ /*
+ * Find last successfully processed descriptor
+ */
+
+ /* Check and clear descriptor status FIFO entries */
+ srd_ptr = priv->omsg_ring[ch].sts_rdptr;
+ sts_ptr = priv->omsg_ring[ch].sts_base;
+ j = srd_ptr * 8;
+ while (sts_ptr[j]) {
+ for (i = 0; i < 8 && sts_ptr[j]; i++, j++) {
+ prev_ptr = last_ptr;
+ last_ptr = le64_to_cpu(sts_ptr[j]);
+ sts_ptr[j] = 0;
+ }
+
+ ++srd_ptr;
+ srd_ptr %= priv->omsg_ring[ch].sts_size;
+ j = srd_ptr * 8;
+ }
+
+ if (last_ptr == 0)
+ goto no_sts_update;
+
+ priv->omsg_ring[ch].sts_rdptr = srd_ptr;
+ iowrite32(srd_ptr, priv->regs + TSI721_OBDMAC_DSRP(ch));
+
+ if (!priv->mport->outb_msg[ch].mcback)
+ goto no_sts_update;
+
+ /* Inform upper layer about transfer completion */
+
+ tx_slot = (last_ptr - (u64)priv->omsg_ring[ch].omd_phys)/
+ sizeof(struct tsi721_omsg_desc);
+
+ /*
+ * Check if this is a Link Descriptor (LD).
+ * If yes, ignore LD and use descriptor processed
+ * before LD.
+ */
+ if (tx_slot == priv->omsg_ring[ch].size) {
+ if (prev_ptr)
+ tx_slot = (prev_ptr -
+ (u64)priv->omsg_ring[ch].omd_phys)/
+ sizeof(struct tsi721_omsg_desc);
+ else
+ goto no_sts_update;
+ }
+
+ /* Move slot index to the next message to be sent */
+ ++tx_slot;
+ if (tx_slot == priv->omsg_ring[ch].size)
+ tx_slot = 0;
+ BUG_ON(tx_slot >= priv->omsg_ring[ch].size);
+ priv->mport->outb_msg[ch].mcback(priv->mport,
+ priv->omsg_ring[ch].dev_id, ch,
+ tx_slot);
+ }
+
+no_sts_update:
+
+ if (omsg_int & TSI721_OBDMAC_INT_ERROR) {
+ /*
+ * Outbound message operation aborted due to error,
+ * reinitialize OB MSG channel
+ */
+
+ dev_dbg(&priv->pdev->dev, "OB MSG ABORT ch_stat=%x\n",
+ ioread32(priv->regs + TSI721_OBDMAC_STS(ch)));
+
+ iowrite32(TSI721_OBDMAC_INT_ERROR,
+ priv->regs + TSI721_OBDMAC_INT(ch));
+ iowrite32(TSI721_OBDMAC_CTL_INIT,
+ priv->regs + TSI721_OBDMAC_CTL(ch));
+ ioread32(priv->regs + TSI721_OBDMAC_CTL(ch));
+
+ /* Inform upper level to clear all pending tx slots */
+ if (priv->mport->outb_msg[ch].mcback)
+ priv->mport->outb_msg[ch].mcback(priv->mport,
+ priv->omsg_ring[ch].dev_id, ch,
+ priv->omsg_ring[ch].tx_slot);
+ /* Synch tx_slot tracking */
+ iowrite32(priv->omsg_ring[ch].tx_slot,
+ priv->regs + TSI721_OBDMAC_DRDCNT(ch));
+ ioread32(priv->regs + TSI721_OBDMAC_DRDCNT(ch));
+ priv->omsg_ring[ch].wr_count = priv->omsg_ring[ch].tx_slot;
+ priv->omsg_ring[ch].sts_rdptr = 0;
+ }
+
+ /* Clear channel interrupts */
+ iowrite32(omsg_int, priv->regs + TSI721_OBDMAC_INT(ch));
+
+ if (!(priv->flags & TSI721_USING_MSIX)) {
+ u32 ch_inte;
+
+ /* Re-enable channel interrupts */
+ ch_inte = ioread32(priv->regs + TSI721_DEV_CHAN_INTE);
+ ch_inte |= TSI721_INT_OMSG_CHAN(ch);
+ iowrite32(ch_inte, priv->regs + TSI721_DEV_CHAN_INTE);
+ }
+
+ spin_unlock(&priv->omsg_ring[ch].lock);
+}
+
+/**
+ * tsi721_open_outb_mbox - Initialize Tsi721 outbound mailbox
+ * @mport: Master port implementing Outbound Messaging Engine
+ * @dev_id: Device specific pointer to pass on event
+ * @mbox: Mailbox to open
+ * @entries: Number of entries in the outbound mailbox ring
+ */
+static int tsi721_open_outb_mbox(struct rio_mport *mport, void *dev_id,
+ int mbox, int entries)
+{
+ struct tsi721_device *priv = mport->priv;
+ struct tsi721_omsg_desc *bd_ptr;
+ int i, rc = 0;
+
+ if ((entries < TSI721_OMSGD_MIN_RING_SIZE) ||
+ (entries > (TSI721_OMSGD_RING_SIZE)) ||
+ (!is_power_of_2(entries)) || mbox >= RIO_MAX_MBOX) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ priv->omsg_ring[mbox].dev_id = dev_id;
+ priv->omsg_ring[mbox].size = entries;
+ priv->omsg_ring[mbox].sts_rdptr = 0;
+ spin_lock_init(&priv->omsg_ring[mbox].lock);
+
+ /* Outbound Msg Buffer allocation based on
+ the number of maximum descriptor entries */
+ for (i = 0; i < entries; i++) {
+ priv->omsg_ring[mbox].omq_base[i] =
+ dma_alloc_coherent(
+ &priv->pdev->dev, TSI721_MSG_BUFFER_SIZE,
+ &priv->omsg_ring[mbox].omq_phys[i],
+ GFP_KERNEL);
+ if (priv->omsg_ring[mbox].omq_base[i] == NULL) {
+ dev_dbg(&priv->pdev->dev,
+ "Unable to allocate OB MSG data buffer for"
+ " MBOX%d\n", mbox);
+ rc = -ENOMEM;
+ goto out_buf;
+ }
+ }
+
+ /* Outbound message descriptor allocation */
+ priv->omsg_ring[mbox].omd_base = dma_alloc_coherent(
+ &priv->pdev->dev,
+ (entries + 1) * sizeof(struct tsi721_omsg_desc),
+ &priv->omsg_ring[mbox].omd_phys, GFP_KERNEL);
+ if (priv->omsg_ring[mbox].omd_base == NULL) {
+ dev_dbg(&priv->pdev->dev,
+ "Unable to allocate OB MSG descriptor memory "
+ "for MBOX%d\n", mbox);
+ rc = -ENOMEM;
+ goto out_buf;
+ }
+
+ priv->omsg_ring[mbox].tx_slot = 0;
+
+ /* Outbound message descriptor status FIFO allocation */
+ priv->omsg_ring[mbox].sts_size = roundup_pow_of_two(entries + 1);
+ priv->omsg_ring[mbox].sts_base = dma_alloc_coherent(&priv->pdev->dev,
+ priv->omsg_ring[mbox].sts_size *
+ sizeof(struct tsi721_dma_sts),
+ &priv->omsg_ring[mbox].sts_phys, GFP_KERNEL);
+ if (priv->omsg_ring[mbox].sts_base == NULL) {
+ dev_dbg(&priv->pdev->dev,
+ "Unable to allocate OB MSG descriptor status FIFO "
+ "for MBOX%d\n", mbox);
+ rc = -ENOMEM;
+ goto out_desc;
+ }
+
+ memset(priv->omsg_ring[mbox].sts_base, 0,
+ entries * sizeof(struct tsi721_dma_sts));
+
+ /*
+ * Configure Outbound Messaging Engine
+ */
+
+ /* Setup Outbound Message descriptor pointer */
+ iowrite32(((u64)priv->omsg_ring[mbox].omd_phys >> 32),
+ priv->regs + TSI721_OBDMAC_DPTRH(mbox));
+ iowrite32(((u64)priv->omsg_ring[mbox].omd_phys &
+ TSI721_OBDMAC_DPTRL_MASK),
+ priv->regs + TSI721_OBDMAC_DPTRL(mbox));
+
+ /* Setup Outbound Message descriptor status FIFO */
+ iowrite32(((u64)priv->omsg_ring[mbox].sts_phys >> 32),
+ priv->regs + TSI721_OBDMAC_DSBH(mbox));
+ iowrite32(((u64)priv->omsg_ring[mbox].sts_phys &
+ TSI721_OBDMAC_DSBL_MASK),
+ priv->regs + TSI721_OBDMAC_DSBL(mbox));
+ iowrite32(TSI721_DMAC_DSSZ_SIZE(priv->omsg_ring[mbox].sts_size),
+ priv->regs + (u32)TSI721_OBDMAC_DSSZ(mbox));
+
+ /* Enable interrupts */
+
+#ifdef CONFIG_PCI_MSI
+ if (priv->flags & TSI721_USING_MSIX) {
+ /* Request interrupt service if we are in MSI-X mode */
+ rc = request_irq(
+ priv->msix[TSI721_VECT_OMB0_DONE + mbox].vector,
+ tsi721_omsg_msix, 0,
+ priv->msix[TSI721_VECT_OMB0_DONE + mbox].irq_name,
+ (void *)mport);
+
+ if (rc) {
+ dev_dbg(&priv->pdev->dev,
+ "Unable to allocate MSI-X interrupt for "
+ "OBOX%d-DONE\n", mbox);
+ goto out_stat;
+ }
+
+ rc = request_irq(priv->msix[TSI721_VECT_OMB0_INT + mbox].vector,
+ tsi721_omsg_msix, 0,
+ priv->msix[TSI721_VECT_OMB0_INT + mbox].irq_name,
+ (void *)mport);
+
+ if (rc) {
+ dev_dbg(&priv->pdev->dev,
+ "Unable to allocate MSI-X interrupt for "
+ "MBOX%d-INT\n", mbox);
+ free_irq(
+ priv->msix[TSI721_VECT_OMB0_DONE + mbox].vector,
+ (void *)mport);
+ goto out_stat;
+ }
+ }
+#endif /* CONFIG_PCI_MSI */
+
+ tsi721_omsg_interrupt_enable(priv, mbox, TSI721_OBDMAC_INT_ALL);
+
+ /* Initialize Outbound Message descriptors ring */
+ bd_ptr = priv->omsg_ring[mbox].omd_base;
+ bd_ptr[entries].type_id = cpu_to_le32(DTYPE5 << 29);
+ bd_ptr[entries].msg_info = 0;
+ bd_ptr[entries].next_lo =
+ cpu_to_le32((u64)priv->omsg_ring[mbox].omd_phys &
+ TSI721_OBDMAC_DPTRL_MASK);
+ bd_ptr[entries].next_hi =
+ cpu_to_le32((u64)priv->omsg_ring[mbox].omd_phys >> 32);
+ priv->omsg_ring[mbox].wr_count = 0;
+ mb();
+
+ /* Initialize Outbound Message engine */
+ iowrite32(TSI721_OBDMAC_CTL_INIT, priv->regs + TSI721_OBDMAC_CTL(mbox));
+ ioread32(priv->regs + TSI721_OBDMAC_DWRCNT(mbox));
+ udelay(10);
+
+ priv->omsg_init[mbox] = 1;
+
+ return 0;
+
+#ifdef CONFIG_PCI_MSI
+out_stat:
+ dma_free_coherent(&priv->pdev->dev,
+ priv->omsg_ring[mbox].sts_size * sizeof(struct tsi721_dma_sts),
+ priv->omsg_ring[mbox].sts_base,
+ priv->omsg_ring[mbox].sts_phys);
+
+ priv->omsg_ring[mbox].sts_base = NULL;
+#endif /* CONFIG_PCI_MSI */
+
+out_desc:
+ dma_free_coherent(&priv->pdev->dev,
+ (entries + 1) * sizeof(struct tsi721_omsg_desc),
+ priv->omsg_ring[mbox].omd_base,
+ priv->omsg_ring[mbox].omd_phys);
+
+ priv->omsg_ring[mbox].omd_base = NULL;
+
+out_buf:
+ for (i = 0; i < priv->omsg_ring[mbox].size; i++) {
+ if (priv->omsg_ring[mbox].omq_base[i]) {
+ dma_free_coherent(&priv->pdev->dev,
+ TSI721_MSG_BUFFER_SIZE,
+ priv->omsg_ring[mbox].omq_base[i],
+ priv->omsg_ring[mbox].omq_phys[i]);
+
+ priv->omsg_ring[mbox].omq_base[i] = NULL;
+ }
+ }
+
+out:
+ return rc;
+}
+
+/**
+ * tsi721_close_outb_mbox - Close Tsi721 outbound mailbox
+ * @mport: Master port implementing the outbound message unit
+ * @mbox: Mailbox to close
+ */
+static void tsi721_close_outb_mbox(struct rio_mport *mport, int mbox)
+{
+ struct tsi721_device *priv = mport->priv;
+ u32 i;
+
+ if (!priv->omsg_init[mbox])
+ return;
+ priv->omsg_init[mbox] = 0;
+
+ /* Disable Interrupts */
+
+ tsi721_omsg_interrupt_disable(priv, mbox, TSI721_OBDMAC_INT_ALL);
+
+#ifdef CONFIG_PCI_MSI
+ if (priv->flags & TSI721_USING_MSIX) {
+ free_irq(priv->msix[TSI721_VECT_OMB0_DONE + mbox].vector,
+ (void *)mport);
+ free_irq(priv->msix[TSI721_VECT_OMB0_INT + mbox].vector,
+ (void *)mport);
+ }
+#endif /* CONFIG_PCI_MSI */
+
+ /* Free OMSG Descriptor Status FIFO */
+ dma_free_coherent(&priv->pdev->dev,
+ priv->omsg_ring[mbox].sts_size * sizeof(struct tsi721_dma_sts),
+ priv->omsg_ring[mbox].sts_base,
+ priv->omsg_ring[mbox].sts_phys);
+
+ priv->omsg_ring[mbox].sts_base = NULL;
+
+ /* Free OMSG descriptors */
+ dma_free_coherent(&priv->pdev->dev,
+ (priv->omsg_ring[mbox].size + 1) *
+ sizeof(struct tsi721_omsg_desc),
+ priv->omsg_ring[mbox].omd_base,
+ priv->omsg_ring[mbox].omd_phys);
+
+ priv->omsg_ring[mbox].omd_base = NULL;
+
+ /* Free message buffers */
+ for (i = 0; i < priv->omsg_ring[mbox].size; i++) {
+ if (priv->omsg_ring[mbox].omq_base[i]) {
+ dma_free_coherent(&priv->pdev->dev,
+ TSI721_MSG_BUFFER_SIZE,
+ priv->omsg_ring[mbox].omq_base[i],
+ priv->omsg_ring[mbox].omq_phys[i]);
+
+ priv->omsg_ring[mbox].omq_base[i] = NULL;
+ }
+ }
+}
+
+/**
+ * tsi721_imsg_handler - Inbound Message Interrupt Handler
+ * @priv: pointer to tsi721 private data
+ * @ch: inbound message channel number to service
+ *
+ * Services channel interrupts from inbound messaging engine.
+ */
+static void tsi721_imsg_handler(struct tsi721_device *priv, int ch)
+{
+ u32 mbox = ch - 4;
+ u32 imsg_int;
+
+ spin_lock(&priv->imsg_ring[mbox].lock);
+
+ imsg_int = ioread32(priv->regs + TSI721_IBDMAC_INT(ch));
+
+ if (imsg_int & TSI721_IBDMAC_INT_SRTO)
+ dev_info(&priv->pdev->dev, "IB MBOX%d SRIO timeout\n",
+ mbox);
+
+ if (imsg_int & TSI721_IBDMAC_INT_PC_ERROR)
+ dev_info(&priv->pdev->dev, "IB MBOX%d PCIe error\n",
+ mbox);
+
+ if (imsg_int & TSI721_IBDMAC_INT_FQ_LOW)
+ dev_info(&priv->pdev->dev,
+ "IB MBOX%d IB free queue low\n", mbox);
+
+ /* Clear IB channel interrupts */
+ iowrite32(imsg_int, priv->regs + TSI721_IBDMAC_INT(ch));
+
+ /* If an IB Msg is received notify the upper layer */
+ if (imsg_int & TSI721_IBDMAC_INT_DQ_RCV &&
+ priv->mport->inb_msg[mbox].mcback)
+ priv->mport->inb_msg[mbox].mcback(priv->mport,
+ priv->imsg_ring[mbox].dev_id, mbox, -1);
+
+ if (!(priv->flags & TSI721_USING_MSIX)) {
+ u32 ch_inte;
+
+ /* Re-enable channel interrupts */
+ ch_inte = ioread32(priv->regs + TSI721_DEV_CHAN_INTE);
+ ch_inte |= TSI721_INT_IMSG_CHAN(ch);
+ iowrite32(ch_inte, priv->regs + TSI721_DEV_CHAN_INTE);
+ }
+
+ spin_unlock(&priv->imsg_ring[mbox].lock);
+}
+
+/**
+ * tsi721_open_inb_mbox - Initialize Tsi721 inbound mailbox
+ * @mport: Master port implementing the Inbound Messaging Engine
+ * @dev_id: Device specific pointer to pass on event
+ * @mbox: Mailbox to open
+ * @entries: Number of entries in the inbound mailbox ring
+ */
+static int tsi721_open_inb_mbox(struct rio_mport *mport, void *dev_id,
+ int mbox, int entries)
+{
+ struct tsi721_device *priv = mport->priv;
+ int ch = mbox + 4;
+ int i;
+ u64 *free_ptr;
+ int rc = 0;
+
+ if ((entries < TSI721_IMSGD_MIN_RING_SIZE) ||
+ (entries > TSI721_IMSGD_RING_SIZE) ||
+ (!is_power_of_2(entries)) || mbox >= RIO_MAX_MBOX) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ /* Initialize IB Messaging Ring */
+ priv->imsg_ring[mbox].dev_id = dev_id;
+ priv->imsg_ring[mbox].size = entries;
+ priv->imsg_ring[mbox].rx_slot = 0;
+ priv->imsg_ring[mbox].desc_rdptr = 0;
+ priv->imsg_ring[mbox].fq_wrptr = 0;
+ for (i = 0; i < priv->imsg_ring[mbox].size; i++)
+ priv->imsg_ring[mbox].imq_base[i] = NULL;
+ spin_lock_init(&priv->imsg_ring[mbox].lock);
+
+ /* Allocate buffers for incoming messages */
+ priv->imsg_ring[mbox].buf_base =
+ dma_alloc_coherent(&priv->pdev->dev,
+ entries * TSI721_MSG_BUFFER_SIZE,
+ &priv->imsg_ring[mbox].buf_phys,
+ GFP_KERNEL);
+
+ if (priv->imsg_ring[mbox].buf_base == NULL) {
+ dev_err(&priv->pdev->dev,
+ "Failed to allocate buffers for IB MBOX%d\n", mbox);
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ /* Allocate memory for circular free list */
+ priv->imsg_ring[mbox].imfq_base =
+ dma_alloc_coherent(&priv->pdev->dev,
+ entries * 8,
+ &priv->imsg_ring[mbox].imfq_phys,
+ GFP_KERNEL);
+
+ if (priv->imsg_ring[mbox].imfq_base == NULL) {
+ dev_err(&priv->pdev->dev,
+ "Failed to allocate free queue for IB MBOX%d\n", mbox);
+ rc = -ENOMEM;
+ goto out_buf;
+ }
+
+ /* Allocate memory for Inbound message descriptors */
+ priv->imsg_ring[mbox].imd_base =
+ dma_alloc_coherent(&priv->pdev->dev,
+ entries * sizeof(struct tsi721_imsg_desc),
+ &priv->imsg_ring[mbox].imd_phys, GFP_KERNEL);
+
+ if (priv->imsg_ring[mbox].imd_base == NULL) {
+ dev_err(&priv->pdev->dev,
+ "Failed to allocate descriptor memory for IB MBOX%d\n",
+ mbox);
+ rc = -ENOMEM;
+ goto out_dma;
+ }
+
+ /* Fill free buffer pointer list */
+ free_ptr = priv->imsg_ring[mbox].imfq_base;
+ for (i = 0; i < entries; i++)
+ free_ptr[i] = cpu_to_le64(
+ (u64)(priv->imsg_ring[mbox].buf_phys) +
+ i * 0x1000);
+
+ mb();
+
+ /*
+ * For mapping of inbound SRIO Messages into appropriate queues we need
+ * to set Inbound Device ID register in the messaging engine. We do it
+ * once when first inbound mailbox is requested.
+ */
+ if (!(priv->flags & TSI721_IMSGID_SET)) {
+ iowrite32((u32)priv->mport->host_deviceid,
+ priv->regs + TSI721_IB_DEVID);
+ priv->flags |= TSI721_IMSGID_SET;
+ }
+
+ /*
+ * Configure Inbound Messaging channel (ch = mbox + 4)
+ */
+
+ /* Setup Inbound Message free queue */
+ iowrite32(((u64)priv->imsg_ring[mbox].imfq_phys >> 32),
+ priv->regs + TSI721_IBDMAC_FQBH(ch));
+ iowrite32(((u64)priv->imsg_ring[mbox].imfq_phys &
+ TSI721_IBDMAC_FQBL_MASK),
+ priv->regs+TSI721_IBDMAC_FQBL(ch));
+ iowrite32(TSI721_DMAC_DSSZ_SIZE(entries),
+ priv->regs + TSI721_IBDMAC_FQSZ(ch));
+
+ /* Setup Inbound Message descriptor queue */
+ iowrite32(((u64)priv->imsg_ring[mbox].imd_phys >> 32),
+ priv->regs + TSI721_IBDMAC_DQBH(ch));
+ iowrite32(((u32)priv->imsg_ring[mbox].imd_phys &
+ (u32)TSI721_IBDMAC_DQBL_MASK),
+ priv->regs+TSI721_IBDMAC_DQBL(ch));
+ iowrite32(TSI721_DMAC_DSSZ_SIZE(entries),
+ priv->regs + TSI721_IBDMAC_DQSZ(ch));
+
+ /* Enable interrupts */
+
+#ifdef CONFIG_PCI_MSI
+ if (priv->flags & TSI721_USING_MSIX) {
+ /* Request interrupt service if we are in MSI-X mode */
+ rc = request_irq(priv->msix[TSI721_VECT_IMB0_RCV + mbox].vector,
+ tsi721_imsg_msix, 0,
+ priv->msix[TSI721_VECT_IMB0_RCV + mbox].irq_name,
+ (void *)mport);
+
+ if (rc) {
+ dev_dbg(&priv->pdev->dev,
+ "Unable to allocate MSI-X interrupt for "
+ "IBOX%d-DONE\n", mbox);
+ goto out_desc;
+ }
+
+ rc = request_irq(priv->msix[TSI721_VECT_IMB0_INT + mbox].vector,
+ tsi721_imsg_msix, 0,
+ priv->msix[TSI721_VECT_IMB0_INT + mbox].irq_name,
+ (void *)mport);
+
+ if (rc) {
+ dev_dbg(&priv->pdev->dev,
+ "Unable to allocate MSI-X interrupt for "
+ "IBOX%d-INT\n", mbox);
+ free_irq(
+ priv->msix[TSI721_VECT_IMB0_RCV + mbox].vector,
+ (void *)mport);
+ goto out_desc;
+ }
+ }
+#endif /* CONFIG_PCI_MSI */
+
+ tsi721_imsg_interrupt_enable(priv, ch, TSI721_IBDMAC_INT_ALL);
+
+ /* Initialize Inbound Message Engine */
+ iowrite32(TSI721_IBDMAC_CTL_INIT, priv->regs + TSI721_IBDMAC_CTL(ch));
+ ioread32(priv->regs + TSI721_IBDMAC_CTL(ch));
+ udelay(10);
+ priv->imsg_ring[mbox].fq_wrptr = entries - 1;
+ iowrite32(entries - 1, priv->regs + TSI721_IBDMAC_FQWP(ch));
+
+ priv->imsg_init[mbox] = 1;
+ return 0;
+
+#ifdef CONFIG_PCI_MSI
+out_desc:
+ dma_free_coherent(&priv->pdev->dev,
+ priv->imsg_ring[mbox].size * sizeof(struct tsi721_imsg_desc),
+ priv->imsg_ring[mbox].imd_base,
+ priv->imsg_ring[mbox].imd_phys);
+
+ priv->imsg_ring[mbox].imd_base = NULL;
+#endif /* CONFIG_PCI_MSI */
+
+out_dma:
+ dma_free_coherent(&priv->pdev->dev,
+ priv->imsg_ring[mbox].size * 8,
+ priv->imsg_ring[mbox].imfq_base,
+ priv->imsg_ring[mbox].imfq_phys);
+
+ priv->imsg_ring[mbox].imfq_base = NULL;
+
+out_buf:
+ dma_free_coherent(&priv->pdev->dev,
+ priv->imsg_ring[mbox].size * TSI721_MSG_BUFFER_SIZE,
+ priv->imsg_ring[mbox].buf_base,
+ priv->imsg_ring[mbox].buf_phys);
+
+ priv->imsg_ring[mbox].buf_base = NULL;
+
+out:
+ return rc;
+}
+
+/**
+ * tsi721_close_inb_mbox - Shut down Tsi721 inbound mailbox
+ * @mport: Master port implementing the Inbound Messaging Engine
+ * @mbox: Mailbox to close
+ */
+static void tsi721_close_inb_mbox(struct rio_mport *mport, int mbox)
+{
+ struct tsi721_device *priv = mport->priv;
+ u32 rx_slot;
+ int ch = mbox + 4;
+
+ if (!priv->imsg_init[mbox]) /* mbox isn't initialized yet */
+ return;
+ priv->imsg_init[mbox] = 0;
+
+ /* Disable Inbound Messaging Engine */
+
+ /* Disable Interrupts */
+ tsi721_imsg_interrupt_disable(priv, ch, TSI721_OBDMAC_INT_MASK);
+
+#ifdef CONFIG_PCI_MSI
+ if (priv->flags & TSI721_USING_MSIX) {
+ free_irq(priv->msix[TSI721_VECT_IMB0_RCV + mbox].vector,
+ (void *)mport);
+ free_irq(priv->msix[TSI721_VECT_IMB0_INT + mbox].vector,
+ (void *)mport);
+ }
+#endif /* CONFIG_PCI_MSI */
+
+ /* Clear Inbound Buffer Queue */
+ for (rx_slot = 0; rx_slot < priv->imsg_ring[mbox].size; rx_slot++)
+ priv->imsg_ring[mbox].imq_base[rx_slot] = NULL;
+
+ /* Free memory allocated for message buffers */
+ dma_free_coherent(&priv->pdev->dev,
+ priv->imsg_ring[mbox].size * TSI721_MSG_BUFFER_SIZE,
+ priv->imsg_ring[mbox].buf_base,
+ priv->imsg_ring[mbox].buf_phys);
+
+ priv->imsg_ring[mbox].buf_base = NULL;
+
+ /* Free memory allocated for free pointr list */
+ dma_free_coherent(&priv->pdev->dev,
+ priv->imsg_ring[mbox].size * 8,
+ priv->imsg_ring[mbox].imfq_base,
+ priv->imsg_ring[mbox].imfq_phys);
+
+ priv->imsg_ring[mbox].imfq_base = NULL;
+
+ /* Free memory allocated for RX descriptors */
+ dma_free_coherent(&priv->pdev->dev,
+ priv->imsg_ring[mbox].size * sizeof(struct tsi721_imsg_desc),
+ priv->imsg_ring[mbox].imd_base,
+ priv->imsg_ring[mbox].imd_phys);
+
+ priv->imsg_ring[mbox].imd_base = NULL;
+}
+
+/**
+ * tsi721_add_inb_buffer - Add buffer to the Tsi721 inbound message queue
+ * @mport: Master port implementing the Inbound Messaging Engine
+ * @mbox: Inbound mailbox number
+ * @buf: Buffer to add to inbound queue
+ */
+static int tsi721_add_inb_buffer(struct rio_mport *mport, int mbox, void *buf)
+{
+ struct tsi721_device *priv = mport->priv;
+ u32 rx_slot;
+ int rc = 0;
+
+ rx_slot = priv->imsg_ring[mbox].rx_slot;
+ if (priv->imsg_ring[mbox].imq_base[rx_slot]) {
+ dev_err(&priv->pdev->dev,
+ "Error adding inbound buffer %d, buffer exists\n",
+ rx_slot);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ priv->imsg_ring[mbox].imq_base[rx_slot] = buf;
+
+ if (++priv->imsg_ring[mbox].rx_slot == priv->imsg_ring[mbox].size)
+ priv->imsg_ring[mbox].rx_slot = 0;
+
+out:
+ return rc;
+}
+
+/**
+ * tsi721_get_inb_message - Fetch inbound message from the Tsi721 MSG Queue
+ * @mport: Master port implementing the Inbound Messaging Engine
+ * @mbox: Inbound mailbox number
+ *
+ * Returns pointer to the message on success or NULL on failure.
+ */
+static void *tsi721_get_inb_message(struct rio_mport *mport, int mbox)
+{
+ struct tsi721_device *priv = mport->priv;
+ struct tsi721_imsg_desc *desc;
+ u32 rx_slot;
+ void *rx_virt = NULL;
+ u64 rx_phys;
+ void *buf = NULL;
+ u64 *free_ptr;
+ int ch = mbox + 4;
+ int msg_size;
+
+ if (!priv->imsg_init[mbox])
+ return NULL;
+
+ desc = priv->imsg_ring[mbox].imd_base;
+ desc += priv->imsg_ring[mbox].desc_rdptr;
+
+ if (!(le32_to_cpu(desc->msg_info) & TSI721_IMD_HO))
+ goto out;
+
+ rx_slot = priv->imsg_ring[mbox].rx_slot;
+ while (priv->imsg_ring[mbox].imq_base[rx_slot] == NULL) {
+ if (++rx_slot == priv->imsg_ring[mbox].size)
+ rx_slot = 0;
+ }
+
+ rx_phys = ((u64)le32_to_cpu(desc->bufptr_hi) << 32) |
+ le32_to_cpu(desc->bufptr_lo);
+
+ rx_virt = priv->imsg_ring[mbox].buf_base +
+ (rx_phys - (u64)priv->imsg_ring[mbox].buf_phys);
+
+ buf = priv->imsg_ring[mbox].imq_base[rx_slot];
+ msg_size = le32_to_cpu(desc->msg_info) & TSI721_IMD_BCOUNT;
+ if (msg_size == 0)
+ msg_size = RIO_MAX_MSG_SIZE;
+
+ memcpy(buf, rx_virt, msg_size);
+ priv->imsg_ring[mbox].imq_base[rx_slot] = NULL;
+
+ desc->msg_info &= cpu_to_le32(~TSI721_IMD_HO);
+ if (++priv->imsg_ring[mbox].desc_rdptr == priv->imsg_ring[mbox].size)
+ priv->imsg_ring[mbox].desc_rdptr = 0;
+
+ iowrite32(priv->imsg_ring[mbox].desc_rdptr,
+ priv->regs + TSI721_IBDMAC_DQRP(ch));
+
+ /* Return free buffer into the pointer list */
+ free_ptr = priv->imsg_ring[mbox].imfq_base;
+ free_ptr[priv->imsg_ring[mbox].fq_wrptr] = cpu_to_le64(rx_phys);
+
+ if (++priv->imsg_ring[mbox].fq_wrptr == priv->imsg_ring[mbox].size)
+ priv->imsg_ring[mbox].fq_wrptr = 0;
+
+ iowrite32(priv->imsg_ring[mbox].fq_wrptr,
+ priv->regs + TSI721_IBDMAC_FQWP(ch));
+out:
+ return buf;
+}
+
+/**
+ * tsi721_messages_init - Initialization of Messaging Engine
+ * @priv: pointer to tsi721 private data
+ *
+ * Configures Tsi721 messaging engine.
+ */
+static int tsi721_messages_init(struct tsi721_device *priv)
+{
+ int ch;
+
+ iowrite32(0, priv->regs + TSI721_SMSG_ECC_LOG);
+ iowrite32(0, priv->regs + TSI721_RETRY_GEN_CNT);
+ iowrite32(0, priv->regs + TSI721_RETRY_RX_CNT);
+
+ /* Set SRIO Message Request/Response Timeout */
+ iowrite32(TSI721_RQRPTO_VAL, priv->regs + TSI721_RQRPTO);
+
+ /* Initialize Inbound Messaging Engine Registers */
+ for (ch = 0; ch < TSI721_IMSG_CHNUM; ch++) {
+ /* Clear interrupt bits */
+ iowrite32(TSI721_IBDMAC_INT_MASK,
+ priv->regs + TSI721_IBDMAC_INT(ch));
+ /* Clear Status */
+ iowrite32(0, priv->regs + TSI721_IBDMAC_STS(ch));
+
+ iowrite32(TSI721_SMSG_ECC_COR_LOG_MASK,
+ priv->regs + TSI721_SMSG_ECC_COR_LOG(ch));
+ iowrite32(TSI721_SMSG_ECC_NCOR_MASK,
+ priv->regs + TSI721_SMSG_ECC_NCOR(ch));
+ }
+
+ return 0;
+}
+
+/**
+ * tsi721_disable_ints - disables all device interrupts
+ * @priv: pointer to tsi721 private data
+ */
+static void tsi721_disable_ints(struct tsi721_device *priv)
+{
+ int ch;
+
+ /* Disable all device level interrupts */
+ iowrite32(0, priv->regs + TSI721_DEV_INTE);
+
+ /* Disable all Device Channel interrupts */
+ iowrite32(0, priv->regs + TSI721_DEV_CHAN_INTE);
+
+ /* Disable all Inbound Msg Channel interrupts */
+ for (ch = 0; ch < TSI721_IMSG_CHNUM; ch++)
+ iowrite32(0, priv->regs + TSI721_IBDMAC_INTE(ch));
+
+ /* Disable all Outbound Msg Channel interrupts */
+ for (ch = 0; ch < TSI721_OMSG_CHNUM; ch++)
+ iowrite32(0, priv->regs + TSI721_OBDMAC_INTE(ch));
+
+ /* Disable all general messaging interrupts */
+ iowrite32(0, priv->regs + TSI721_SMSG_INTE);
+
+ /* Disable all BDMA Channel interrupts */
+ for (ch = 0; ch < TSI721_DMA_MAXCH; ch++)
+ iowrite32(0, priv->regs + TSI721_DMAC_INTE(ch));
+
+ /* Disable all general BDMA interrupts */
+ iowrite32(0, priv->regs + TSI721_BDMA_INTE);
+
+ /* Disable all SRIO Channel interrupts */
+ for (ch = 0; ch < TSI721_SRIO_MAXCH; ch++)
+ iowrite32(0, priv->regs + TSI721_SR_CHINTE(ch));
+
+ /* Disable all general SR2PC interrupts */
+ iowrite32(0, priv->regs + TSI721_SR2PC_GEN_INTE);
+
+ /* Disable all PC2SR interrupts */
+ iowrite32(0, priv->regs + TSI721_PC2SR_INTE);
+
+ /* Disable all I2C interrupts */
+ iowrite32(0, priv->regs + TSI721_I2C_INT_ENABLE);
+
+ /* Disable SRIO MAC interrupts */
+ iowrite32(0, priv->regs + TSI721_RIO_EM_INT_ENABLE);
+ iowrite32(0, priv->regs + TSI721_RIO_EM_DEV_INT_EN);
+}
+
+/**
+ * tsi721_setup_mport - Setup Tsi721 as RapidIO subsystem master port
+ * @priv: pointer to tsi721 private data
+ *
+ * Configures Tsi721 as RapidIO master port.
+ */
+static int __devinit tsi721_setup_mport(struct tsi721_device *priv)
+{
+ struct pci_dev *pdev = priv->pdev;
+ int err = 0;
+ struct rio_ops *ops;
+
+ struct rio_mport *mport;
+
+ ops = kzalloc(sizeof(struct rio_ops), GFP_KERNEL);
+ if (!ops) {
+ dev_dbg(&pdev->dev, "Unable to allocate memory for rio_ops\n");
+ return -ENOMEM;
+ }
+
+ ops->lcread = tsi721_lcread;
+ ops->lcwrite = tsi721_lcwrite;
+ ops->cread = tsi721_cread_dma;
+ ops->cwrite = tsi721_cwrite_dma;
+ ops->dsend = tsi721_dsend;
+ ops->open_inb_mbox = tsi721_open_inb_mbox;
+ ops->close_inb_mbox = tsi721_close_inb_mbox;
+ ops->open_outb_mbox = tsi721_open_outb_mbox;
+ ops->close_outb_mbox = tsi721_close_outb_mbox;
+ ops->add_outb_message = tsi721_add_outb_message;
+ ops->add_inb_buffer = tsi721_add_inb_buffer;
+ ops->get_inb_message = tsi721_get_inb_message;
+
+ mport = kzalloc(sizeof(struct rio_mport), GFP_KERNEL);
+ if (!mport) {
+ kfree(ops);
+ dev_dbg(&pdev->dev, "Unable to allocate memory for mport\n");
+ return -ENOMEM;
+ }
+
+ mport->ops = ops;
+ mport->index = 0;
+ mport->sys_size = 0; /* small system */
+ mport->phy_type = RIO_PHY_SERIAL;
+ mport->priv = (void *)priv;
+ mport->phys_efptr = 0x100;
+
+ INIT_LIST_HEAD(&mport->dbells);
+
+ rio_init_dbell_res(&mport->riores[RIO_DOORBELL_RESOURCE], 0, 0xffff);
+ rio_init_mbox_res(&mport->riores[RIO_INB_MBOX_RESOURCE], 0, 0);
+ rio_init_mbox_res(&mport->riores[RIO_OUTB_MBOX_RESOURCE], 0, 0);
+ strcpy(mport->name, "Tsi721 mport");
+
+ /* Hook up interrupt handler */
+
+#ifdef CONFIG_PCI_MSI
+ if (!tsi721_enable_msix(priv))
+ priv->flags |= TSI721_USING_MSIX;
+ else if (!pci_enable_msi(pdev))
+ priv->flags |= TSI721_USING_MSI;
+ else
+ dev_info(&pdev->dev,
+ "MSI/MSI-X is not available. Using legacy INTx.\n");
+#endif /* CONFIG_PCI_MSI */
+
+ err = tsi721_request_irq(mport);
+
+ if (!err) {
+ tsi721_interrupts_init(priv);
+ ops->pwenable = tsi721_pw_enable;
+ } else
+ dev_err(&pdev->dev, "Unable to get assigned PCI IRQ "
+ "vector %02X err=0x%x\n", pdev->irq, err);
+
+ /* Enable SRIO link */
+ iowrite32(ioread32(priv->regs + TSI721_DEVCTL) |
+ TSI721_DEVCTL_SRBOOT_CMPL,
+ priv->regs + TSI721_DEVCTL);
+
+ rio_register_mport(mport);
+ priv->mport = mport;
+
+ if (mport->host_deviceid >= 0)
+ iowrite32(RIO_PORT_GEN_HOST | RIO_PORT_GEN_MASTER |
+ RIO_PORT_GEN_DISCOVERED,
+ priv->regs + (0x100 + RIO_PORT_GEN_CTL_CSR));
+ else
+ iowrite32(0, priv->regs + (0x100 + RIO_PORT_GEN_CTL_CSR));
+
+ return 0;
+}
+
+static int __devinit tsi721_probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ struct tsi721_device *priv;
+ int i;
+ int err;
+ u32 regval;
+
+ priv = kzalloc(sizeof(struct tsi721_device), GFP_KERNEL);
+ if (priv == NULL) {
+ dev_err(&pdev->dev, "Failed to allocate memory for device\n");
+ err = -ENOMEM;
+ goto err_exit;
+ }
+
+ err = pci_enable_device(pdev);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to enable PCI device\n");
+ goto err_clean;
+ }
+
+ priv->pdev = pdev;
+
+#ifdef DEBUG
+ for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
+ dev_dbg(&pdev->dev, "res[%d] @ 0x%llx (0x%lx, 0x%lx)\n",
+ i, (unsigned long long)pci_resource_start(pdev, i),
+ (unsigned long)pci_resource_len(pdev, i),
+ pci_resource_flags(pdev, i));
+ }
+#endif
+ /*
+ * Verify BAR configuration
+ */
+
+ /* BAR_0 (registers) must be 512KB+ in 32-bit address space */
+ if (!(pci_resource_flags(pdev, BAR_0) & IORESOURCE_MEM) ||
+ pci_resource_flags(pdev, BAR_0) & IORESOURCE_MEM_64 ||
+ pci_resource_len(pdev, BAR_0) < TSI721_REG_SPACE_SIZE) {
+ dev_err(&pdev->dev,
+ "Missing or misconfigured CSR BAR0, aborting.\n");
+ err = -ENODEV;
+ goto err_disable_pdev;
+ }
+
+ /* BAR_1 (outbound doorbells) must be 16MB+ in 32-bit address space */
+ if (!(pci_resource_flags(pdev, BAR_1) & IORESOURCE_MEM) ||
+ pci_resource_flags(pdev, BAR_1) & IORESOURCE_MEM_64 ||
+ pci_resource_len(pdev, BAR_1) < TSI721_DB_WIN_SIZE) {
+ dev_err(&pdev->dev,
+ "Missing or misconfigured Doorbell BAR1, aborting.\n");
+ err = -ENODEV;
+ goto err_disable_pdev;
+ }
+
+ /*
+ * BAR_2 and BAR_4 (outbound translation) must be in 64-bit PCIe address
+ * space.
+ * NOTE: BAR_2 and BAR_4 are not used by this version of driver.
+ * It may be a good idea to keep them disabled using HW configuration
+ * to save PCI memory space.
+ */
+ if ((pci_resource_flags(pdev, BAR_2) & IORESOURCE_MEM) &&
+ (pci_resource_flags(pdev, BAR_2) & IORESOURCE_MEM_64)) {
+ dev_info(&pdev->dev, "Outbound BAR2 is not used but enabled.\n");
+ }
+
+ if ((pci_resource_flags(pdev, BAR_4) & IORESOURCE_MEM) &&
+ (pci_resource_flags(pdev, BAR_4) & IORESOURCE_MEM_64)) {
+ dev_info(&pdev->dev, "Outbound BAR4 is not used but enabled.\n");
+ }
+
+ err = pci_request_regions(pdev, DRV_NAME);
+ if (err) {
+ dev_err(&pdev->dev, "Cannot obtain PCI resources, "
+ "aborting.\n");
+ goto err_disable_pdev;
+ }
+
+ pci_set_master(pdev);
+
+ priv->regs = pci_ioremap_bar(pdev, BAR_0);
+ if (!priv->regs) {
+ dev_err(&pdev->dev,
+ "Unable to map device registers space, aborting\n");
+ err = -ENOMEM;
+ goto err_free_res;
+ }
+
+ priv->odb_base = pci_ioremap_bar(pdev, BAR_1);
+ if (!priv->odb_base) {
+ dev_err(&pdev->dev,
+ "Unable to map outbound doorbells space, aborting\n");
+ err = -ENOMEM;
+ goto err_unmap_bars;
+ }
+
+ /* Configure DMA attributes. */
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+ dev_info(&pdev->dev, "Unable to set DMA mask\n");
+ goto err_unmap_bars;
+ }
+
+ if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)))
+ dev_info(&pdev->dev, "Unable to set consistent DMA mask\n");
+ } else {
+ err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+ if (err)
+ dev_info(&pdev->dev, "Unable to set consistent DMA mask\n");
+ }
+
+ /* Clear "no snoop" and "relaxed ordering" bits. */
+ pci_read_config_dword(pdev, 0x40 + PCI_EXP_DEVCTL, ®val);
+ regval &= ~(PCI_EXP_DEVCTL_RELAX_EN | PCI_EXP_DEVCTL_NOSNOOP_EN);
+ pci_write_config_dword(pdev, 0x40 + PCI_EXP_DEVCTL, regval);
+
+ /*
+ * FIXUP: correct offsets of MSI-X tables in the MSI-X Capability Block
+ */
+ pci_write_config_dword(pdev, TSI721_PCIECFG_EPCTL, 0x01);
+ pci_write_config_dword(pdev, TSI721_PCIECFG_MSIXTBL,
+ TSI721_MSIXTBL_OFFSET);
+ pci_write_config_dword(pdev, TSI721_PCIECFG_MSIXPBA,
+ TSI721_MSIXPBA_OFFSET);
+ pci_write_config_dword(pdev, TSI721_PCIECFG_EPCTL, 0);
+ /* End of FIXUP */
+
+ tsi721_disable_ints(priv);
+
+ tsi721_init_pc2sr_mapping(priv);
+ tsi721_init_sr2pc_mapping(priv);
+
+ if (tsi721_bdma_init(priv)) {
+ dev_err(&pdev->dev, "BDMA initialization failed, aborting\n");
+ err = -ENOMEM;
+ goto err_unmap_bars;
+ }
+
+ err = tsi721_doorbell_init(priv);
+ if (err)
+ goto err_free_bdma;
+
+ tsi721_port_write_init(priv);
+
+ err = tsi721_messages_init(priv);
+ if (err)
+ goto err_free_consistent;
+
+ err = tsi721_setup_mport(priv);
+ if (err)
+ goto err_free_consistent;
+
+ return 0;
+
+err_free_consistent:
+ tsi721_doorbell_free(priv);
+err_free_bdma:
+ tsi721_bdma_free(priv);
+err_unmap_bars:
+ if (priv->regs)
+ iounmap(priv->regs);
+ if (priv->odb_base)
+ iounmap(priv->odb_base);
+err_free_res:
+ pci_release_regions(pdev);
+ pci_clear_master(pdev);
+err_disable_pdev:
+ pci_disable_device(pdev);
+err_clean:
+ kfree(priv);
+err_exit:
+ return err;
+}
+
+static DEFINE_PCI_DEVICE_TABLE(tsi721_pci_tbl) = {
+ { PCI_DEVICE(PCI_VENDOR_ID_IDT, PCI_DEVICE_ID_TSI721) },
+ { 0, } /* terminate list */
+};
+
+MODULE_DEVICE_TABLE(pci, tsi721_pci_tbl);
+
+static struct pci_driver tsi721_driver = {
+ .name = "tsi721",
+ .id_table = tsi721_pci_tbl,
+ .probe = tsi721_probe,
+};
+
+static int __init tsi721_init(void)
+{
+ return pci_register_driver(&tsi721_driver);
+}
+
+static void __exit tsi721_exit(void)
+{
+ pci_unregister_driver(&tsi721_driver);
+}
+
+device_initcall(tsi721_init);
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
new file mode 100644
index 0000000..58be4de
--- /dev/null
+++ b/drivers/rapidio/devices/tsi721.h
@@ -0,0 +1,766 @@
+/*
+ * Tsi721 PCIExpress-to-SRIO bridge definitions
+ *
+ * Copyright 2011, Integrated Device Technology, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ */
+
+#ifndef __TSI721_H
+#define __TSI721_H
+
+#define DRV_NAME "tsi721"
+
+#define DEFAULT_HOPCOUNT 0xff
+#define DEFAULT_DESTID 0xff
+
+/* PCI device ID */
+#define PCI_DEVICE_ID_TSI721 0x80ab
+
+#define BAR_0 0
+#define BAR_1 1
+#define BAR_2 2
+#define BAR_4 4
+
+#define TSI721_PC2SR_BARS 2
+#define TSI721_PC2SR_WINS 8
+#define TSI721_PC2SR_ZONES 8
+#define TSI721_MAINT_WIN 0 /* Window for outbound maintenance requests */
+#define IDB_QUEUE 0 /* Inbound Doorbell Queue to use */
+#define IDB_QSIZE 512 /* Inbound Doorbell Queue size */
+
+/* Memory space sizes */
+#define TSI721_REG_SPACE_SIZE (512 * 1024) /* 512K */
+#define TSI721_DB_WIN_SIZE (16 * 1024 * 1024) /* 16MB */
+
+#define RIO_TT_CODE_8 0x00000000
+#define RIO_TT_CODE_16 0x00000001
+
+#define TSI721_DMA_MAXCH 8
+#define TSI721_DMA_MINSTSSZ 32
+#define TSI721_DMA_STSBLKSZ 8
+
+#define TSI721_SRIO_MAXCH 8
+
+#define DBELL_SID(buf) (((u8)buf[2] << 8) | (u8)buf[3])
+#define DBELL_TID(buf) (((u8)buf[4] << 8) | (u8)buf[5])
+#define DBELL_INF(buf) (((u8)buf[0] << 8) | (u8)buf[1])
+
+#define TSI721_RIO_PW_MSG_SIZE 16 /* Tsi721 saves only 16 bytes of PW msg */
+
+/* Register definitions */
+
+/*
+ * Registers in PCIe configuration space
+ */
+
+#define TSI721_PCIECFG_MSIXTBL 0x0a4
+#define TSI721_MSIXTBL_OFFSET 0x2c000
+#define TSI721_PCIECFG_MSIXPBA 0x0a8
+#define TSI721_MSIXPBA_OFFSET 0x2a000
+#define TSI721_PCIECFG_EPCTL 0x400
+
+/*
+ * Event Management Registers
+ */
+
+#define TSI721_RIO_EM_INT_STAT 0x10910
+#define TSI721_RIO_EM_INT_STAT_PW_RX 0x00010000
+
+#define TSI721_RIO_EM_INT_ENABLE 0x10914
+#define TSI721_RIO_EM_INT_ENABLE_PW_RX 0x00010000
+
+#define TSI721_RIO_EM_DEV_INT_EN 0x10930
+#define TSI721_RIO_EM_DEV_INT_EN_INT 0x00000001
+
+/*
+ * Port-Write Block Registers
+ */
+
+#define TSI721_RIO_PW_CTL 0x10a04
+#define TSI721_RIO_PW_CTL_PW_TIMER 0xf0000000
+#define TSI721_RIO_PW_CTL_PWT_DIS (0 << 28)
+#define TSI721_RIO_PW_CTL_PWT_103 (1 << 28)
+#define TSI721_RIO_PW_CTL_PWT_205 (1 << 29)
+#define TSI721_RIO_PW_CTL_PWT_410 (1 << 30)
+#define TSI721_RIO_PW_CTL_PWT_820 (1 << 31)
+#define TSI721_RIO_PW_CTL_PWC_MODE 0x01000000
+#define TSI721_RIO_PW_CTL_PWC_CONT 0x00000000
+#define TSI721_RIO_PW_CTL_PWC_REL 0x01000000
+
+#define TSI721_RIO_PW_RX_STAT 0x10a10
+#define TSI721_RIO_PW_RX_STAT_WR_SIZE 0x0000f000
+#define TSI_RIO_PW_RX_STAT_WDPTR 0x00000100
+#define TSI721_RIO_PW_RX_STAT_PW_SHORT 0x00000008
+#define TSI721_RIO_PW_RX_STAT_PW_TRUNC 0x00000004
+#define TSI721_RIO_PW_RX_STAT_PW_DISC 0x00000002
+#define TSI721_RIO_PW_RX_STAT_PW_VAL 0x00000001
+
+#define TSI721_RIO_PW_RX_CAPT(x) (0x10a20 + (x)*4)
+
+/*
+ * Inbound Doorbells
+ */
+
+#define TSI721_IDB_ENTRY_SIZE 64
+
+#define TSI721_IDQ_CTL(x) (0x20000 + (x) * 1000)
+#define TSI721_IDQ_SUSPEND 0x00000002
+#define TSI721_IDQ_INIT 0x00000001
+
+#define TSI721_IDQ_STS(x) (0x20004 + (x) * 1000)
+#define TSI721_IDQ_RUN 0x00200000
+
+#define TSI721_IDQ_MASK(x) (0x20008 + (x) * 1000)
+#define TSI721_IDQ_MASK_MASK 0xffff0000
+#define TSI721_IDQ_MASK_PATT 0x0000ffff
+
+#define TSI721_IDQ_RP(x) (0x2000c + (x) * 1000)
+#define TSI721_IDQ_RP_PTR 0x0007ffff
+
+#define TSI721_IDQ_WP(x) (0x20010 + (x) * 1000)
+#define TSI721_IDQ_WP_PTR 0x0007ffff
+
+#define TSI721_IDQ_BASEL(x) (0x20014 + (x) * 1000)
+#define TSI721_IDQ_BASEL_ADDR 0xffffffc0
+#define TSI721_IDQ_BASEU(x) (0x20018 + (x) * 1000)
+#define TSI721_IDQ_SIZE(x) (0x2001c + (x) * 1000)
+#define TSI721_IDQ_SIZE_VAL(size) (__fls(size) - 4)
+#define TSI721_IDQ_SIZE_MIN 512
+#define TSI721_IDQ_SIZE_MAX (512 * 1024)
+
+#define TSI721_SR_CHINT(x) (0x20040 + (x) * 1000)
+#define TSI721_SR_CHINTE(x) (0x20044 + (x) * 1000)
+#define TSI721_SR_CHINTSET(x) (0x20048 + (x) * 1000)
+#define TSI721_SR_CHINT_ODBOK 0x00000020
+#define TSI721_SR_CHINT_IDBQRCV 0x00000010
+#define TSI721_SR_CHINT_SUSP 0x00000008
+#define TSI721_SR_CHINT_ODBTO 0x00000004
+#define TSI721_SR_CHINT_ODBRTRY 0x00000002
+#define TSI721_SR_CHINT_ODBERR 0x00000001
+#define TSI721_SR_CHINT_ALL 0x0000003f
+
+#define TSI721_IBWIN_NUM 8
+
+#define TSI721_IBWINLB(x) (0x29000 + (x) * 20)
+#define TSI721_IBWINLB_BA 0xfffff000
+#define TSI721_IBWINLB_WEN 0x00000001
+
+#define TSI721_SR2PC_GEN_INTE 0x29800
+#define TSI721_SR2PC_PWE 0x29804
+#define TSI721_SR2PC_GEN_INT 0x29808
+
+#define TSI721_DEV_INTE 0x29840
+#define TSI721_DEV_INT 0x29844
+#define TSI721_DEV_INTSET 0x29848
+#define TSI721_DEV_INT_SMSG_CH 0x00000800
+#define TSI721_DEV_INT_SMSG_NCH 0x00000400
+#define TSI721_DEV_INT_SR2PC_CH 0x00000200
+#define TSI721_DEV_INT_SRIO 0x00000020
+
+#define TSI721_DEV_CHAN_INTE 0x2984c
+#define TSI721_DEV_CHAN_INT 0x29850
+
+#define TSI721_INT_SR2PC_CHAN_M 0xff000000
+#define TSI721_INT_SR2PC_CHAN(x) (1 << (24 + (x)))
+#define TSI721_INT_IMSG_CHAN_M 0x00ff0000
+#define TSI721_INT_IMSG_CHAN(x) (1 << (16 + (x)))
+#define TSI721_INT_OMSG_CHAN_M 0x0000ff00
+#define TSI721_INT_OMSG_CHAN(x) (1 << (8 + (x)))
+
+/*
+ * PC2SR block registers
+ */
+#define TSI721_OBWIN_NUM TSI721_PC2SR_WINS
+
+#define TSI721_OBWINLB(x) (0x40000 + (x) * 20)
+#define TSI721_OBWINLB_BA 0xffff8000
+#define TSI721_OBWINLB_WEN 0x00000001
+
+#define TSI721_OBWINUB(x) (0x40004 + (x) * 20)
+
+#define TSI721_OBWINSZ(x) (0x40008 + (x) * 20)
+#define TSI721_OBWINSZ_SIZE 0x00001f00
+#define TSI721_OBWIN_SIZE(size) (__fls(size) - 15)
+
+#define TSI721_ZONE_SEL 0x41300
+#define TSI721_ZONE_SEL_RD_WRB 0x00020000
+#define TSI721_ZONE_SEL_GO 0x00010000
+#define TSI721_ZONE_SEL_WIN 0x00000038
+#define TSI721_ZONE_SEL_ZONE 0x00000007
+
+#define TSI721_LUT_DATA0 0x41304
+#define TSI721_LUT_DATA0_ADD 0xfffff000
+#define TSI721_LUT_DATA0_RDTYPE 0x00000f00
+#define TSI721_LUT_DATA0_NREAD 0x00000100
+#define TSI721_LUT_DATA0_MNTRD 0x00000200
+#define TSI721_LUT_DATA0_RDCRF 0x00000020
+#define TSI721_LUT_DATA0_WRCRF 0x00000010
+#define TSI721_LUT_DATA0_WRTYPE 0x0000000f
+#define TSI721_LUT_DATA0_NWR 0x00000001
+#define TSI721_LUT_DATA0_MNTWR 0x00000002
+#define TSI721_LUT_DATA0_NWR_R 0x00000004
+
+#define TSI721_LUT_DATA1 0x41308
+
+#define TSI721_LUT_DATA2 0x4130c
+#define TSI721_LUT_DATA2_HC 0xff000000
+#define TSI721_LUT_DATA2_ADD65 0x000c0000
+#define TSI721_LUT_DATA2_TT 0x00030000
+#define TSI721_LUT_DATA2_DSTID 0x0000ffff
+
+#define TSI721_PC2SR_INTE 0x41310
+
+#define TSI721_DEVCTL 0x48004
+#define TSI721_DEVCTL_SRBOOT_CMPL 0x00000004
+
+#define TSI721_I2C_INT_ENABLE 0x49120
+
+/*
+ * Block DMA Engine Registers
+ * x = 0..7
+ */
+
+#define TSI721_DMAC_DWRCNT(x) (0x51000 + (x) * 0x1000)
+#define TSI721_DMAC_DRDCNT(x) (0x51004 + (x) * 0x1000)
+
+#define TSI721_DMAC_CTL(x) (0x51008 + (x) * 0x1000)
+#define TSI721_DMAC_CTL_SUSP 0x00000002
+#define TSI721_DMAC_CTL_INIT 0x00000001
+
+#define TSI721_DMAC_INT(x) (0x5100c + (x) * 0x1000)
+#define TSI721_DMAC_INT_STFULL 0x00000010
+#define TSI721_DMAC_INT_DONE 0x00000008
+#define TSI721_DMAC_INT_SUSP 0x00000004
+#define TSI721_DMAC_INT_ERR 0x00000002
+#define TSI721_DMAC_INT_IOFDONE 0x00000001
+#define TSI721_DMAC_INT_ALL 0x0000001f
+
+#define TSI721_DMAC_INTSET(x) (0x51010 + (x) * 0x1000)
+
+#define TSI721_DMAC_STS(x) (0x51014 + (x) * 0x1000)
+#define TSI721_DMAC_STS_ABORT 0x00400000
+#define TSI721_DMAC_STS_RUN 0x00200000
+#define TSI721_DMAC_STS_CS 0x001f0000
+
+#define TSI721_DMAC_INTE(x) (0x51018 + (x) * 0x1000)
+
+#define TSI721_DMAC_DPTRL(x) (0x51024 + (x) * 0x1000)
+#define TSI721_DMAC_DPTRL_MASK 0xffffffe0
+
+#define TSI721_DMAC_DPTRH(x) (0x51028 + (x) * 0x1000)
+
+#define TSI721_DMAC_DSBL(x) (0x5102c + (x) * 0x1000)
+#define TSI721_DMAC_DSBL_MASK 0xffffffc0
+
+#define TSI721_DMAC_DSBH(x) (0x51030 + (x) * 0x1000)
+
+#define TSI721_DMAC_DSSZ(x) (0x51034 + (x) * 0x1000)
+#define TSI721_DMAC_DSSZ_SIZE_M 0x0000000f
+#define TSI721_DMAC_DSSZ_SIZE(size) (__fls(size) - 4)
+
+
+#define TSI721_DMAC_DSRP(x) (0x51038 + (x) * 0x1000)
+#define TSI721_DMAC_DSRP_MASK 0x0007ffff
+
+#define TSI721_DMAC_DSWP(x) (0x5103c + (x) * 0x1000)
+#define TSI721_DMAC_DSWP_MASK 0x0007ffff
+
+#define TSI721_BDMA_INTE 0x5f000
+
+/*
+ * Messaging definitions
+ */
+#define TSI721_MSG_BUFFER_SIZE RIO_MAX_MSG_SIZE
+#define TSI721_MSG_MAX_SIZE RIO_MAX_MSG_SIZE
+#define TSI721_IMSG_MAXCH 8
+#define TSI721_IMSG_CHNUM TSI721_IMSG_MAXCH
+#define TSI721_IMSGD_MIN_RING_SIZE 32
+#define TSI721_IMSGD_RING_SIZE 512
+
+#define TSI721_OMSG_CHNUM 4 /* One channel per MBOX */
+#define TSI721_OMSGD_MIN_RING_SIZE 32
+#define TSI721_OMSGD_RING_SIZE 512
+
+/*
+ * Outbound Messaging Engine Registers
+ * x = 0..7
+ */
+
+#define TSI721_OBDMAC_DWRCNT(x) (0x61000 + (x) * 0x1000)
+
+#define TSI721_OBDMAC_DRDCNT(x) (0x61004 + (x) * 0x1000)
+
+#define TSI721_OBDMAC_CTL(x) (0x61008 + (x) * 0x1000)
+#define TSI721_OBDMAC_CTL_MASK 0x00000007
+#define TSI721_OBDMAC_CTL_RETRY_THR 0x00000004
+#define TSI721_OBDMAC_CTL_SUSPEND 0x00000002
+#define TSI721_OBDMAC_CTL_INIT 0x00000001
+
+#define TSI721_OBDMAC_INT(x) (0x6100c + (x) * 0x1000)
+#define TSI721_OBDMAC_INTSET(x) (0x61010 + (x) * 0x1000)
+#define TSI721_OBDMAC_INTE(x) (0x61018 + (x) * 0x1000)
+#define TSI721_OBDMAC_INT_MASK 0x0000001F
+#define TSI721_OBDMAC_INT_ST_FULL 0x00000010
+#define TSI721_OBDMAC_INT_DONE 0x00000008
+#define TSI721_OBDMAC_INT_SUSPENDED 0x00000004
+#define TSI721_OBDMAC_INT_ERROR 0x00000002
+#define TSI721_OBDMAC_INT_IOF_DONE 0x00000001
+#define TSI721_OBDMAC_INT_ALL TSI721_OBDMAC_INT_MASK
+
+#define TSI721_OBDMAC_STS(x) (0x61014 + (x) * 0x1000)
+#define TSI721_OBDMAC_STS_MASK 0x007f0000
+#define TSI721_OBDMAC_STS_ABORT 0x00400000
+#define TSI721_OBDMAC_STS_RUN 0x00200000
+#define TSI721_OBDMAC_STS_CS 0x001f0000
+
+#define TSI721_OBDMAC_PWE(x) (0x6101c + (x) * 0x1000)
+#define TSI721_OBDMAC_PWE_MASK 0x00000002
+#define TSI721_OBDMAC_PWE_ERROR_EN 0x00000002
+
+#define TSI721_OBDMAC_DPTRL(x) (0x61020 + (x) * 0x1000)
+#define TSI721_OBDMAC_DPTRL_MASK 0xfffffff0
+
+#define TSI721_OBDMAC_DPTRH(x) (0x61024 + (x) * 0x1000)
+#define TSI721_OBDMAC_DPTRH_MASK 0xffffffff
+
+#define TSI721_OBDMAC_DSBL(x) (0x61040 + (x) * 0x1000)
+#define TSI721_OBDMAC_DSBL_MASK 0xffffffc0
+
+#define TSI721_OBDMAC_DSBH(x) (0x61044 + (x) * 0x1000)
+#define TSI721_OBDMAC_DSBH_MASK 0xffffffff
+
+#define TSI721_OBDMAC_DSSZ(x) (0x61048 + (x) * 0x1000)
+#define TSI721_OBDMAC_DSSZ_MASK 0x0000000f
+
+#define TSI721_OBDMAC_DSRP(x) (0x6104c + (x) * 0x1000)
+#define TSI721_OBDMAC_DSRP_MASK 0x0007ffff
+
+#define TSI721_OBDMAC_DSWP(x) (0x61050 + (x) * 0x1000)
+#define TSI721_OBDMAC_DSWP_MASK 0x0007ffff
+
+#define TSI721_RQRPTO 0x60010
+#define TSI721_RQRPTO_MASK 0x00ffffff
+#define TSI721_RQRPTO_VAL 400 /* Response TO value */
+
+/*
+ * Inbound Messaging Engine Registers
+ * x = 0..7
+ */
+
+#define TSI721_IB_DEVID_GLOBAL 0xffff
+#define TSI721_IBDMAC_FQBL(x) (0x61200 + (x) * 0x1000)
+#define TSI721_IBDMAC_FQBL_MASK 0xffffffc0
+
+#define TSI721_IBDMAC_FQBH(x) (0x61204 + (x) * 0x1000)
+#define TSI721_IBDMAC_FQBH_MASK 0xffffffff
+
+#define TSI721_IBDMAC_FQSZ_ENTRY_INX TSI721_IMSGD_RING_SIZE
+#define TSI721_IBDMAC_FQSZ(x) (0x61208 + (x) * 0x1000)
+#define TSI721_IBDMAC_FQSZ_MASK 0x0000000f
+
+#define TSI721_IBDMAC_FQRP(x) (0x6120c + (x) * 0x1000)
+#define TSI721_IBDMAC_FQRP_MASK 0x0007ffff
+
+#define TSI721_IBDMAC_FQWP(x) (0x61210 + (x) * 0x1000)
+#define TSI721_IBDMAC_FQWP_MASK 0x0007ffff
+
+#define TSI721_IBDMAC_FQTH(x) (0x61214 + (x) * 0x1000)
+#define TSI721_IBDMAC_FQTH_MASK 0x0007ffff
+
+#define TSI721_IB_DEVID 0x60020
+#define TSI721_IB_DEVID_MASK 0x0000ffff
+
+#define TSI721_IBDMAC_CTL(x) (0x61240 + (x) * 0x1000)
+#define TSI721_IBDMAC_CTL_MASK 0x00000003
+#define TSI721_IBDMAC_CTL_SUSPEND 0x00000002
+#define TSI721_IBDMAC_CTL_INIT 0x00000001
+
+#define TSI721_IBDMAC_STS(x) (0x61244 + (x) * 0x1000)
+#define TSI721_IBDMAC_STS_MASK 0x007f0000
+#define TSI721_IBSMAC_STS_ABORT 0x00400000
+#define TSI721_IBSMAC_STS_RUN 0x00200000
+#define TSI721_IBSMAC_STS_CS 0x001f0000
+
+#define TSI721_IBDMAC_INT(x) (0x61248 + (x) * 0x1000)
+#define TSI721_IBDMAC_INTSET(x) (0x6124c + (x) * 0x1000)
+#define TSI721_IBDMAC_INTE(x) (0x61250 + (x) * 0x1000)
+#define TSI721_IBDMAC_INT_MASK 0x0000100f
+#define TSI721_IBDMAC_INT_SRTO 0x00001000
+#define TSI721_IBDMAC_INT_SUSPENDED 0x00000008
+#define TSI721_IBDMAC_INT_PC_ERROR 0x00000004
+#define TSI721_IBDMAC_INT_FQ_LOW 0x00000002
+#define TSI721_IBDMAC_INT_DQ_RCV 0x00000001
+#define TSI721_IBDMAC_INT_ALL TSI721_IBDMAC_INT_MASK
+
+#define TSI721_IBDMAC_PWE(x) (0x61254 + (x) * 0x1000)
+#define TSI721_IBDMAC_PWE_MASK 0x00001700
+#define TSI721_IBDMAC_PWE_SRTO 0x00001000
+#define TSI721_IBDMAC_PWE_ILL_FMT 0x00000400
+#define TSI721_IBDMAC_PWE_ILL_DEC 0x00000200
+#define TSI721_IBDMAC_PWE_IMP_SP 0x00000100
+
+#define TSI721_IBDMAC_DQBL(x) (0x61300 + (x) * 0x1000)
+#define TSI721_IBDMAC_DQBL_MASK 0xffffffc0
+#define TSI721_IBDMAC_DQBL_ADDR 0xffffffc0
+
+#define TSI721_IBDMAC_DQBH(x) (0x61304 + (x) * 0x1000)
+#define TSI721_IBDMAC_DQBH_MASK 0xffffffff
+
+#define TSI721_IBDMAC_DQRP(x) (0x61308 + (x) * 0x1000)
+#define TSI721_IBDMAC_DQRP_MASK 0x0007ffff
+
+#define TSI721_IBDMAC_DQWR(x) (0x6130c + (x) * 0x1000)
+#define TSI721_IBDMAC_DQWR_MASK 0x0007ffff
+
+#define TSI721_IBDMAC_DQSZ(x) (0x61314 + (x) * 0x1000)
+#define TSI721_IBDMAC_DQSZ_MASK 0x0000000f
+
+/*
+ * Messaging Engine Interrupts
+ */
+
+#define TSI721_SMSG_PWE 0x6a004
+
+#define TSI721_SMSG_INTE 0x6a000
+#define TSI721_SMSG_INT 0x6a008
+#define TSI721_SMSG_INTSET 0x6a010
+#define TSI721_SMSG_INT_MASK 0x0086ffff
+#define TSI721_SMSG_INT_UNS_RSP 0x00800000
+#define TSI721_SMSG_INT_ECC_NCOR 0x00040000
+#define TSI721_SMSG_INT_ECC_COR 0x00020000
+#define TSI721_SMSG_INT_ECC_NCOR_CH 0x0000ff00
+#define TSI721_SMSG_INT_ECC_COR_CH 0x000000ff
+
+#define TSI721_SMSG_ECC_LOG 0x6a014
+#define TSI721_SMSG_ECC_LOG_MASK 0x00070007
+#define TSI721_SMSG_ECC_LOG_ECC_NCOR_M 0x00070000
+#define TSI721_SMSG_ECC_LOG_ECC_COR_M 0x00000007
+
+#define TSI721_RETRY_GEN_CNT 0x6a100
+#define TSI721_RETRY_GEN_CNT_MASK 0xffffffff
+
+#define TSI721_RETRY_RX_CNT 0x6a104
+#define TSI721_RETRY_RX_CNT_MASK 0xffffffff
+
+#define TSI721_SMSG_ECC_COR_LOG(x) (0x6a300 + (x) * 4)
+#define TSI721_SMSG_ECC_COR_LOG_MASK 0x000000ff
+
+#define TSI721_SMSG_ECC_NCOR(x) (0x6a340 + (x) * 4)
+#define TSI721_SMSG_ECC_NCOR_MASK 0x000000ff
+
+/*
+ * Block DMA Descriptors
+ */
+
+struct tsi721_dma_desc {
+ __le32 type_id;
+
+#define TSI721_DMAD_DEVID 0x0000ffff
+#define TSI721_DMAD_CRF 0x00010000
+#define TSI721_DMAD_PRIO 0x00060000
+#define TSI721_DMAD_RTYPE 0x00780000
+#define TSI721_DMAD_IOF 0x08000000
+#define TSI721_DMAD_DTYPE 0xe0000000
+
+ __le32 bcount;
+
+#define TSI721_DMAD_BCOUNT1 0x03ffffff /* if DTYPE == 1 */
+#define TSI721_DMAD_BCOUNT2 0x0000000f /* if DTYPE == 2 */
+#define TSI721_DMAD_TT 0x0c000000
+#define TSI721_DMAD_RADDR0 0xc0000000
+
+ union {
+ __le32 raddr_lo; /* if DTYPE == (1 || 2) */
+ __le32 next_lo; /* if DTYPE == 3 */
+ };
+
+#define TSI721_DMAD_CFGOFF 0x00ffffff
+#define TSI721_DMAD_HOPCNT 0xff000000
+
+ union {
+ __le32 raddr_hi; /* if DTYPE == (1 || 2) */
+ __le32 next_hi; /* if DTYPE == 3 */
+ };
+
+ union {
+ struct { /* if DTYPE == 1 */
+ __le32 bufptr_lo;
+ __le32 bufptr_hi;
+ __le32 s_dist;
+ __le32 s_size;
+ } t1;
+ __le32 data[4]; /* if DTYPE == 2 */
+ u32 reserved[4]; /* if DTYPE == 3 */
+ };
+} __aligned(32);
+
+/*
+ * Inbound Messaging Descriptor
+ */
+struct tsi721_imsg_desc {
+ __le32 type_id;
+
+#define TSI721_IMD_DEVID 0x0000ffff
+#define TSI721_IMD_CRF 0x00010000
+#define TSI721_IMD_PRIO 0x00060000
+#define TSI721_IMD_TT 0x00180000
+#define TSI721_IMD_DTYPE 0xe0000000
+
+ __le32 msg_info;
+
+#define TSI721_IMD_BCOUNT 0x00000ff8
+#define TSI721_IMD_SSIZE 0x0000f000
+#define TSI721_IMD_LETER 0x00030000
+#define TSI721_IMD_XMBOX 0x003c0000
+#define TSI721_IMD_MBOX 0x00c00000
+#define TSI721_IMD_CS 0x78000000
+#define TSI721_IMD_HO 0x80000000
+
+ __le32 bufptr_lo;
+ __le32 bufptr_hi;
+ u32 reserved[12];
+
+} __aligned(64);
+
+/*
+ * Outbound Messaging Descriptor
+ */
+struct tsi721_omsg_desc {
+ __le32 type_id;
+
+#define TSI721_OMD_DEVID 0x0000ffff
+#define TSI721_OMD_CRF 0x00010000
+#define TSI721_OMD_PRIO 0x00060000
+#define TSI721_OMD_IOF 0x08000000
+#define TSI721_OMD_DTYPE 0xe0000000
+#define TSI721_OMD_RSRVD 0x17f80000
+
+ __le32 msg_info;
+
+#define TSI721_OMD_BCOUNT 0x00000ff8
+#define TSI721_OMD_SSIZE 0x0000f000
+#define TSI721_OMD_LETER 0x00030000
+#define TSI721_OMD_XMBOX 0x003c0000
+#define TSI721_OMD_MBOX 0x00c00000
+#define TSI721_OMD_TT 0x0c000000
+
+ union {
+ __le32 bufptr_lo; /* if DTYPE == 4 */
+ __le32 next_lo; /* if DTYPE == 5 */
+ };
+
+ union {
+ __le32 bufptr_hi; /* if DTYPE == 4 */
+ __le32 next_hi; /* if DTYPE == 5 */
+ };
+
+} __aligned(16);
+
+struct tsi721_dma_sts {
+ __le64 desc_sts[8];
+} __aligned(64);
+
+struct tsi721_desc_sts_fifo {
+ union {
+ __le64 da64;
+ struct {
+ __le32 lo;
+ __le32 hi;
+ } da32;
+ } stat[8];
+} __aligned(64);
+
+/* Descriptor types for BDMA and Messaging blocks */
+enum dma_dtype {
+ DTYPE1 = 1, /* Data Transfer DMA Descriptor */
+ DTYPE2 = 2, /* Immediate Data Transfer DMA Descriptor */
+ DTYPE3 = 3, /* Block Pointer DMA Descriptor */
+ DTYPE4 = 4, /* Outbound Msg DMA Descriptor */
+ DTYPE5 = 5, /* OB Messaging Block Pointer Descriptor */
+ DTYPE6 = 6 /* Inbound Messaging Descriptor */
+};
+
+enum dma_rtype {
+ NREAD = 0,
+ LAST_NWRITE_R = 1,
+ ALL_NWRITE = 2,
+ ALL_NWRITE_R = 3,
+ MAINT_RD = 4,
+ MAINT_WR = 5
+};
+
+/*
+ * mport Driver Definitions
+ */
+#define TSI721_DMA_CHNUM TSI721_DMA_MAXCH
+
+#define TSI721_DMACH_MAINT 0 /* DMA channel for maint requests */
+#define TSI721_DMACH_MAINT_NBD 32 /* Number of BDs for maint requests */
+
+#define MSG_DMA_ENTRY_INX_TO_SIZE(x) ((0x10 << (x)) & 0xFFFF0)
+
+enum tsi721_smsg_int_flag {
+ SMSG_INT_NONE = 0x00000000,
+ SMSG_INT_ECC_COR_CH = 0x000000ff,
+ SMSG_INT_ECC_NCOR_CH = 0x0000ff00,
+ SMSG_INT_ECC_COR = 0x00020000,
+ SMSG_INT_ECC_NCOR = 0x00040000,
+ SMSG_INT_UNS_RSP = 0x00800000,
+ SMSG_INT_ALL = 0x0006ffff
+};
+
+/* Structures */
+
+struct tsi721_bdma_chan {
+ int bd_num; /* number of buffer descriptors */
+ void *bd_base; /* start of DMA descriptors */
+ dma_addr_t bd_phys;
+ void *sts_base; /* start of DMA BD status FIFO */
+ dma_addr_t sts_phys;
+ int sts_size;
+};
+
+struct tsi721_imsg_ring {
+ u32 size;
+ /* VA/PA of data buffers for incoming messages */
+ void *buf_base;
+ dma_addr_t buf_phys;
+ /* VA/PA of circular free buffer list */
+ void *imfq_base;
+ dma_addr_t imfq_phys;
+ /* VA/PA of Inbound message descriptors */
+ void *imd_base;
+ dma_addr_t imd_phys;
+ /* Inbound Queue buffer pointers */
+ void *imq_base[TSI721_IMSGD_RING_SIZE];
+
+ u32 rx_slot;
+ void *dev_id;
+ u32 fq_wrptr;
+ u32 desc_rdptr;
+ spinlock_t lock;
+};
+
+struct tsi721_omsg_ring {
+ u32 size;
+ /* VA/PA of OB Msg descriptors */
+ void *omd_base;
+ dma_addr_t omd_phys;
+ /* VA/PA of OB Msg data buffers */
+ void *omq_base[TSI721_OMSGD_RING_SIZE];
+ dma_addr_t omq_phys[TSI721_OMSGD_RING_SIZE];
+ /* VA/PA of OB Msg descriptor status FIFO */
+ void *sts_base;
+ dma_addr_t sts_phys;
+ u32 sts_size; /* # of allocated status entries */
+ u32 sts_rdptr;
+
+ u32 tx_slot;
+ void *dev_id;
+ u32 wr_count;
+ spinlock_t lock;
+};
+
+enum tsi721_flags {
+ TSI721_USING_MSI = (1 << 0),
+ TSI721_USING_MSIX = (1 << 1),
+ TSI721_IMSGID_SET = (1 << 2),
+};
+
+#ifdef CONFIG_PCI_MSI
+/*
+ * MSI-X Table Entries (0 ... 69)
+ */
+#define TSI721_MSIX_DMACH_DONE(x) (0 + (x))
+#define TSI721_MSIX_DMACH_INT(x) (8 + (x))
+#define TSI721_MSIX_BDMA_INT 16
+#define TSI721_MSIX_OMSG_DONE(x) (17 + (x))
+#define TSI721_MSIX_OMSG_INT(x) (25 + (x))
+#define TSI721_MSIX_IMSG_DQ_RCV(x) (33 + (x))
+#define TSI721_MSIX_IMSG_INT(x) (41 + (x))
+#define TSI721_MSIX_MSG_INT 49
+#define TSI721_MSIX_SR2PC_IDBQ_RCV(x) (50 + (x))
+#define TSI721_MSIX_SR2PC_CH_INT(x) (58 + (x))
+#define TSI721_MSIX_SR2PC_INT 66
+#define TSI721_MSIX_PC2SR_INT 67
+#define TSI721_MSIX_SRIO_MAC_INT 68
+#define TSI721_MSIX_I2C_INT 69
+
+/* MSI-X vector and init table entry indexes */
+enum tsi721_msix_vect {
+ TSI721_VECT_IDB,
+ TSI721_VECT_PWRX, /* PW_RX is part of SRIO MAC Interrupt reporting */
+ TSI721_VECT_OMB0_DONE,
+ TSI721_VECT_OMB1_DONE,
+ TSI721_VECT_OMB2_DONE,
+ TSI721_VECT_OMB3_DONE,
+ TSI721_VECT_OMB0_INT,
+ TSI721_VECT_OMB1_INT,
+ TSI721_VECT_OMB2_INT,
+ TSI721_VECT_OMB3_INT,
+ TSI721_VECT_IMB0_RCV,
+ TSI721_VECT_IMB1_RCV,
+ TSI721_VECT_IMB2_RCV,
+ TSI721_VECT_IMB3_RCV,
+ TSI721_VECT_IMB0_INT,
+ TSI721_VECT_IMB1_INT,
+ TSI721_VECT_IMB2_INT,
+ TSI721_VECT_IMB3_INT,
+ TSI721_VECT_MAX
+};
+
+#define IRQ_DEVICE_NAME_MAX 64
+
+struct msix_irq {
+ u16 vector;
+ char irq_name[IRQ_DEVICE_NAME_MAX];
+};
+#endif /* CONFIG_PCI_MSI */
+
+struct tsi721_device {
+ struct pci_dev *pdev;
+ struct rio_mport *mport;
+ u32 flags;
+ void __iomem *regs;
+#ifdef CONFIG_PCI_MSI
+ struct msix_irq msix[TSI721_VECT_MAX];
+#endif
+ /* Doorbells */
+ void __iomem *odb_base;
+ void *idb_base;
+ dma_addr_t idb_dma;
+ struct work_struct idb_work;
+ u32 db_discard_count;
+
+ /* Inbound Port-Write */
+ struct work_struct pw_work;
+ struct kfifo pw_fifo;
+ spinlock_t pw_fifo_lock;
+ u32 pw_discard_count;
+
+ /* BDMA Engine */
+ struct tsi721_bdma_chan bdma[TSI721_DMA_CHNUM];
+
+ /* Inbound Messaging */
+ int imsg_init[TSI721_IMSG_CHNUM];
+ struct tsi721_imsg_ring imsg_ring[TSI721_IMSG_CHNUM];
+
+ /* Outbound Messaging */
+ int omsg_init[TSI721_OMSG_CHNUM];
+ struct tsi721_omsg_ring omsg_ring[TSI721_OMSG_CHNUM];
+};
+
+#endif
diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index ebe77dd..2bebd79 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -516,7 +516,7 @@
return rdev;
cleanup:
- if (rio_is_switch(rdev))
+ if (rswitch)
kfree(rswitch->route_table);
kfree(rdev);
@@ -923,7 +923,7 @@
* rio_enum_complete- Tests if enumeration of a network is complete
* @port: Master port to send transaction
*
- * Tests the Component Tag CSR for non-zero value (enumeration
+ * Tests the PGCCSR discovered bit for non-zero value (enumeration
* complete flag). Return %1 if enumeration is complete or %0 if
* enumeration is incomplete.
*/
@@ -933,7 +933,7 @@
rio_local_read_config_32(port, port->phys_efptr + RIO_PORT_GEN_CTL_CSR,
®val);
- return (regval & RIO_PORT_GEN_MASTER) ? 1 : 0;
+ return (regval & RIO_PORT_GEN_DISCOVERED) ? 1 : 0;
}
/**
diff --git a/drivers/regulator/db8500-prcmu.c b/drivers/regulator/db8500-prcmu.c
index 2bb8f45..2d014a1 100644
--- a/drivers/regulator/db8500-prcmu.c
+++ b/drivers/regulator/db8500-prcmu.c
@@ -13,7 +13,7 @@
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/platform_device.h>
-#include <linux/mfd/db8500-prcmu.h>
+#include <linux/mfd/dbx500-prcmu.h>
#include <linux/regulator/driver.h>
#include <linux/regulator/machine.h>
#include <linux/regulator/db8500-prcmu.h>
diff --git a/drivers/regulator/mc13783-regulator.c b/drivers/regulator/mc13783-regulator.c
index 730f43a..cb2841f 100644
--- a/drivers/regulator/mc13783-regulator.c
+++ b/drivers/regulator/mc13783-regulator.c
@@ -336,9 +336,9 @@
{
struct mc13xxx_regulator_priv *priv;
struct mc13xxx *mc13783 = dev_get_drvdata(pdev->dev.parent);
- struct mc13783_regulator_platform_data *pdata =
+ struct mc13xxx_regulator_platform_data *pdata =
dev_get_platdata(&pdev->dev);
- struct mc13783_regulator_init_data *init_data;
+ struct mc13xxx_regulator_init_data *init_data;
int i, ret;
dev_dbg(&pdev->dev, "%s id %d\n", __func__, pdev->id);
@@ -381,7 +381,7 @@
static int __devexit mc13783_regulator_remove(struct platform_device *pdev)
{
struct mc13xxx_regulator_priv *priv = platform_get_drvdata(pdev);
- struct mc13783_regulator_platform_data *pdata =
+ struct mc13xxx_regulator_platform_data *pdata =
dev_get_platdata(&pdev->dev);
int i;
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 5a538fc..53eb4e5 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -8,7 +8,7 @@
menuconfig RTC_CLASS
bool "Real Time Clock"
default n
- depends on !S390
+ depends on !S390 && !UML
select RTC_LIB
help
Generic RTC class support. If you say yes here, you will
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index 01a7df5..e8326f2 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -21,16 +21,13 @@
#include "rtc-core.h"
-static DEFINE_IDR(rtc_idr);
-static DEFINE_MUTEX(idr_lock);
+static DEFINE_IDA(rtc_ida);
struct class *rtc_class;
static void rtc_device_release(struct device *dev)
{
struct rtc_device *rtc = to_rtc_device(dev);
- mutex_lock(&idr_lock);
- idr_remove(&rtc_idr, rtc->id);
- mutex_unlock(&idr_lock);
+ ida_simple_remove(&rtc_ida, rtc->id);
kfree(rtc);
}
@@ -146,25 +143,16 @@
struct rtc_wkalrm alrm;
int id, err;
- if (idr_pre_get(&rtc_idr, GFP_KERNEL) == 0) {
- err = -ENOMEM;
+ id = ida_simple_get(&rtc_ida, 0, 0, GFP_KERNEL);
+ if (id < 0) {
+ err = id;
goto exit;
}
-
- mutex_lock(&idr_lock);
- err = idr_get_new(&rtc_idr, NULL, &id);
- mutex_unlock(&idr_lock);
-
- if (err < 0)
- goto exit;
-
- id = id & MAX_ID_MASK;
-
rtc = kzalloc(sizeof(struct rtc_device), GFP_KERNEL);
if (rtc == NULL) {
err = -ENOMEM;
- goto exit_idr;
+ goto exit_ida;
}
rtc->id = id;
@@ -222,10 +210,8 @@
exit_kfree:
kfree(rtc);
-exit_idr:
- mutex_lock(&idr_lock);
- idr_remove(&rtc_idr, id);
- mutex_unlock(&idr_lock);
+exit_ida:
+ ida_simple_remove(&rtc_ida, id);
exit:
dev_err(dev, "rtc core: unable to register %s, err = %d\n",
@@ -276,7 +262,7 @@
{
rtc_dev_exit();
class_destroy(rtc_class);
- idr_destroy(&rtc_idr);
+ ida_destroy(&rtc_ida);
}
subsys_initcall(rtc_init);
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index b2005b4..62b0763 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -34,6 +34,7 @@
ds_1388,
ds_3231,
m41t00,
+ mcp7941x,
rx_8025,
// rs5c372 too? different address...
};
@@ -43,6 +44,7 @@
#define DS1307_REG_SECS 0x00 /* 00-59 */
# define DS1307_BIT_CH 0x80
# define DS1340_BIT_nEOSC 0x80
+# define MCP7941X_BIT_ST 0x80
#define DS1307_REG_MIN 0x01 /* 00-59 */
#define DS1307_REG_HOUR 0x02 /* 00-23, or 1-12{am,pm} */
# define DS1307_BIT_12HR 0x40 /* in REG_HOUR */
@@ -50,6 +52,7 @@
# define DS1340_BIT_CENTURY_EN 0x80 /* in REG_HOUR */
# define DS1340_BIT_CENTURY 0x40 /* in REG_HOUR */
#define DS1307_REG_WDAY 0x03 /* 01-07 */
+# define MCP7941X_BIT_VBATEN 0x08
#define DS1307_REG_MDAY 0x04 /* 01-31 */
#define DS1307_REG_MONTH 0x05 /* 01-12 */
# define DS1337_BIT_CENTURY 0x80 /* in REG_MONTH */
@@ -137,6 +140,8 @@
},
[m41t00] = {
},
+[mcp7941x] = {
+},
[rx_8025] = {
}, };
@@ -149,6 +154,7 @@
{ "ds1340", ds_1340 },
{ "ds3231", ds_3231 },
{ "m41t00", m41t00 },
+ { "mcp7941x", mcp7941x },
{ "pt7c4338", ds_1307 },
{ "rx8025", rx_8025 },
{ }
@@ -365,6 +371,10 @@
buf[DS1307_REG_HOUR] |= DS1340_BIT_CENTURY_EN
| DS1340_BIT_CENTURY;
break;
+ case mcp7941x:
+ buf[DS1307_REG_SECS] |= MCP7941X_BIT_ST;
+ buf[DS1307_REG_WDAY] |= MCP7941X_BIT_VBATEN;
+ break;
default:
break;
}
@@ -809,6 +819,23 @@
dev_warn(&client->dev, "SET TIME!\n");
}
break;
+ case mcp7941x:
+ /* make sure that the backup battery is enabled */
+ if (!(ds1307->regs[DS1307_REG_WDAY] & MCP7941X_BIT_VBATEN)) {
+ i2c_smbus_write_byte_data(client, DS1307_REG_WDAY,
+ ds1307->regs[DS1307_REG_WDAY]
+ | MCP7941X_BIT_VBATEN);
+ }
+
+ /* clock halted? turn it on, so clock can tick. */
+ if (!(tmp & MCP7941X_BIT_ST)) {
+ i2c_smbus_write_byte_data(client, DS1307_REG_SECS,
+ MCP7941X_BIT_ST);
+ dev_warn(&client->dev, "SET TIME!\n");
+ goto read_rtc;
+ }
+
+ break;
case rx_8025:
case ds_1337:
case ds_1339:
diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c
index a1a278b..9d0c3b4 100644
--- a/drivers/rtc/rtc-mc13xxx.c
+++ b/drivers/rtc/rtc-mc13xxx.c
@@ -309,7 +309,7 @@
return IRQ_HANDLED;
}
-static int __devinit mc13xxx_rtc_probe(struct platform_device *pdev)
+static int __init mc13xxx_rtc_probe(struct platform_device *pdev)
{
int ret;
struct mc13xxx_rtc *priv;
@@ -378,7 +378,7 @@
return ret;
}
-static int __devexit mc13xxx_rtc_remove(struct platform_device *pdev)
+static int __exit mc13xxx_rtc_remove(struct platform_device *pdev)
{
struct mc13xxx_rtc *priv = platform_get_drvdata(pdev);
@@ -410,7 +410,7 @@
static struct platform_driver mc13xxx_rtc_driver = {
.id_table = mc13xxx_rtc_idtable,
- .remove = __devexit_p(mc13xxx_rtc_remove),
+ .remove = __exit_p(mc13xxx_rtc_remove),
.driver = {
.name = DRIVER_NAME,
.owner = THIS_MODULE,
diff --git a/drivers/sh/intc/chip.c b/drivers/sh/intc/chip.c
index 33b2ed4..e0ada37 100644
--- a/drivers/sh/intc/chip.c
+++ b/drivers/sh/intc/chip.c
@@ -202,11 +202,16 @@
if (!value)
return -EINVAL;
+ value &= ~SENSE_VALID_FLAG;
+
ihp = intc_find_irq(d->sense, d->nr_sense, irq);
if (ihp) {
+ /* PINT has 2-bit sense registers, should fail on EDGE_BOTH */
+ if (value >= (1 << _INTC_WIDTH(ihp->handle)))
+ return -EINVAL;
+
addr = INTC_REG(d, _INTC_ADDR_E(ihp->handle), 0);
- intc_reg_fns[_INTC_FN(ihp->handle)](addr, ihp->handle,
- value & ~SENSE_VALID_FLAG);
+ intc_reg_fns[_INTC_FN(ihp->handle)](addr, ihp->handle, value);
}
return 0;
diff --git a/drivers/sh/intc/userimask.c b/drivers/sh/intc/userimask.c
index e32304b..56bf933 100644
--- a/drivers/sh/intc/userimask.c
+++ b/drivers/sh/intc/userimask.c
@@ -13,6 +13,7 @@
#include <linux/sysdev.h>
#include <linux/init.h>
#include <linux/io.h>
+#include <linux/stat.h>
#include <asm/sizes.h>
#include "internals.h"
diff --git a/drivers/sh/pfc.c b/drivers/sh/pfc.c
index 75934e3..e67fe17 100644
--- a/drivers/sh/pfc.c
+++ b/drivers/sh/pfc.c
@@ -217,7 +217,7 @@
if (!r_width)
break;
- for (n = 0; n < (r_width / f_width) * 1 << f_width; n++) {
+ for (n = 0; n < (r_width / f_width) * (1 << f_width); n++) {
if (config_reg->enum_ids[n] == enum_id) {
*crp = config_reg;
*indexp = n;
@@ -577,6 +577,32 @@
sh_gpio_set_value(chip_to_pinmux(chip), offset, value);
}
+static int sh_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
+{
+ struct pinmux_info *gpioc = chip_to_pinmux(chip);
+ pinmux_enum_t enum_id;
+ pinmux_enum_t *enum_ids;
+ int i, k, pos;
+
+ pos = 0;
+ enum_id = 0;
+ while (1) {
+ pos = get_gpio_enum_id(gpioc, offset, pos, &enum_id);
+ if (pos <= 0 || !enum_id)
+ break;
+
+ for (i = 0; i < gpioc->gpio_irq_size; i++) {
+ enum_ids = gpioc->gpio_irq[i].enum_ids;
+ for (k = 0; enum_ids[k]; k++) {
+ if (enum_ids[k] == enum_id)
+ return gpioc->gpio_irq[i].irq;
+ }
+ }
+ }
+
+ return -ENOSYS;
+}
+
int register_pinmux(struct pinmux_info *pip)
{
struct gpio_chip *chip = &pip->chip;
@@ -592,6 +618,7 @@
chip->get = sh_gpio_get;
chip->direction_output = sh_gpio_direction_output;
chip->set = sh_gpio_set;
+ chip->to_irq = sh_gpio_to_irq;
WARN_ON(pip->first_gpio != 0); /* needs testing */
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 52e2900..a1fd73d 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -88,7 +88,7 @@
config SPI_AU1550
tristate "Au1550/Au12x0 SPI Controller"
- depends on (SOC_AU1550 || SOC_AU1200) && EXPERIMENTAL
+ depends on MIPS_ALCHEMY && EXPERIMENTAL
select SPI_BITBANG
help
If you say yes to this option, support will be included for the
diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c
index f3c6060..7a19555 100644
--- a/drivers/staging/pohmelfs/inode.c
+++ b/drivers/staging/pohmelfs/inode.c
@@ -1197,7 +1197,7 @@
void pohmelfs_fill_inode(struct inode *inode, struct netfs_inode_info *info)
{
inode->i_mode = info->mode;
- inode->i_nlink = info->nlink;
+ set_nlink(inode, info->nlink);
inode->i_uid = info->uid;
inode->i_gid = info->gid;
inode->i_blocks = info->blocks;
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 8816f53..b3d1741 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -1,6 +1,6 @@
config VT
bool "Virtual terminal" if EXPERT
- depends on !S390
+ depends on !S390 && !UML
select INPUT
default y
---help---
diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index 4ac2750..791f11b 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -62,7 +62,6 @@
boolean
default y if FSL_SOC
default y if PPC_MPC512x
- default y if SOC_AU1200
default y if ARCH_IXP4XX
default y if ARCH_W90X900
default y if ARCH_AT91SAM9G45
diff --git a/drivers/usb/host/Makefile b/drivers/usb/host/Makefile
index ed48a5d..7ca290f 100644
--- a/drivers/usb/host/Makefile
+++ b/drivers/usb/host/Makefile
@@ -36,3 +36,4 @@
obj-$(CONFIG_USB_IMX21_HCD) += imx21-hcd.o
obj-$(CONFIG_USB_FSL_MPH_DR_OF) += fsl-mph-dr-of.o
obj-$(CONFIG_USB_OCTEON2_COMMON) += octeon2-common.o
+obj-$(CONFIG_MIPS_ALCHEMY) += alchemy-common.o
diff --git a/drivers/usb/host/alchemy-common.c b/drivers/usb/host/alchemy-common.c
new file mode 100644
index 0000000..b4192c9
--- /dev/null
+++ b/drivers/usb/host/alchemy-common.c
@@ -0,0 +1,337 @@
+/*
+ * USB block power/access management abstraction.
+ *
+ * Au1000+: The OHCI block control register is at the far end of the OHCI memory
+ * area. Au1550 has OHCI on different base address. No need to handle
+ * UDC here.
+ * Au1200: one register to control access and clocks to O/EHCI, UDC and OTG
+ * as well as the PHY for EHCI and UDC.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/syscore_ops.h>
+#include <asm/mach-au1x00/au1000.h>
+
+/* control register offsets */
+#define AU1000_OHCICFG 0x7fffc
+#define AU1550_OHCICFG 0x07ffc
+#define AU1200_USBCFG 0x04
+
+/* Au1000 USB block config bits */
+#define USBHEN_RD (1 << 4) /* OHCI reset-done indicator */
+#define USBHEN_CE (1 << 3) /* OHCI block clock enable */
+#define USBHEN_E (1 << 2) /* OHCI block enable */
+#define USBHEN_C (1 << 1) /* OHCI block coherency bit */
+#define USBHEN_BE (1 << 0) /* OHCI Big-Endian */
+
+/* Au1200 USB config bits */
+#define USBCFG_PFEN (1 << 31) /* prefetch enable (undoc) */
+#define USBCFG_RDCOMB (1 << 30) /* read combining (undoc) */
+#define USBCFG_UNKNOWN (5 << 20) /* unknown, leave this way */
+#define USBCFG_SSD (1 << 23) /* serial short detect en */
+#define USBCFG_PPE (1 << 19) /* HS PHY PLL */
+#define USBCFG_UCE (1 << 18) /* UDC clock enable */
+#define USBCFG_ECE (1 << 17) /* EHCI clock enable */
+#define USBCFG_OCE (1 << 16) /* OHCI clock enable */
+#define USBCFG_FLA(x) (((x) & 0x3f) << 8)
+#define USBCFG_UCAM (1 << 7) /* coherent access (undoc) */
+#define USBCFG_GME (1 << 6) /* OTG mem access */
+#define USBCFG_DBE (1 << 5) /* UDC busmaster enable */
+#define USBCFG_DME (1 << 4) /* UDC mem enable */
+#define USBCFG_EBE (1 << 3) /* EHCI busmaster enable */
+#define USBCFG_EME (1 << 2) /* EHCI mem enable */
+#define USBCFG_OBE (1 << 1) /* OHCI busmaster enable */
+#define USBCFG_OME (1 << 0) /* OHCI mem enable */
+#define USBCFG_INIT_AU1200 (USBCFG_PFEN | USBCFG_RDCOMB | USBCFG_UNKNOWN |\
+ USBCFG_SSD | USBCFG_FLA(0x20) | USBCFG_UCAM | \
+ USBCFG_GME | USBCFG_DBE | USBCFG_DME | \
+ USBCFG_EBE | USBCFG_EME | USBCFG_OBE | \
+ USBCFG_OME)
+
+
+static DEFINE_SPINLOCK(alchemy_usb_lock);
+
+
+static inline void __au1200_ohci_control(void __iomem *base, int enable)
+{
+ unsigned long r = __raw_readl(base + AU1200_USBCFG);
+ if (enable) {
+ __raw_writel(r | USBCFG_OCE, base + AU1200_USBCFG);
+ wmb();
+ udelay(2000);
+ } else {
+ __raw_writel(r & ~USBCFG_OCE, base + AU1200_USBCFG);
+ wmb();
+ udelay(1000);
+ }
+}
+
+static inline void __au1200_ehci_control(void __iomem *base, int enable)
+{
+ unsigned long r = __raw_readl(base + AU1200_USBCFG);
+ if (enable) {
+ __raw_writel(r | USBCFG_ECE | USBCFG_PPE, base + AU1200_USBCFG);
+ wmb();
+ udelay(1000);
+ } else {
+ if (!(r & USBCFG_UCE)) /* UDC also off? */
+ r &= ~USBCFG_PPE; /* yes: disable HS PHY PLL */
+ __raw_writel(r & ~USBCFG_ECE, base + AU1200_USBCFG);
+ wmb();
+ udelay(1000);
+ }
+}
+
+static inline void __au1200_udc_control(void __iomem *base, int enable)
+{
+ unsigned long r = __raw_readl(base + AU1200_USBCFG);
+ if (enable) {
+ __raw_writel(r | USBCFG_UCE | USBCFG_PPE, base + AU1200_USBCFG);
+ wmb();
+ } else {
+ if (!(r & USBCFG_ECE)) /* EHCI also off? */
+ r &= ~USBCFG_PPE; /* yes: disable HS PHY PLL */
+ __raw_writel(r & ~USBCFG_UCE, base + AU1200_USBCFG);
+ wmb();
+ }
+}
+
+static inline int au1200_coherency_bug(void)
+{
+#if defined(CONFIG_DMA_COHERENT)
+ /* Au1200 AB USB does not support coherent memory */
+ if (!(read_c0_prid() & 0xff)) {
+ printk(KERN_INFO "Au1200 USB: this is chip revision AB !!\n");
+ printk(KERN_INFO "Au1200 USB: update your board or re-configure"
+ " the kernel\n");
+ return -ENODEV;
+ }
+#endif
+ return 0;
+}
+
+static inline int au1200_usb_control(int block, int enable)
+{
+ void __iomem *base =
+ (void __iomem *)KSEG1ADDR(AU1200_USB_CTL_PHYS_ADDR);
+ int ret = 0;
+
+ switch (block) {
+ case ALCHEMY_USB_OHCI0:
+ ret = au1200_coherency_bug();
+ if (ret && enable)
+ goto out;
+ __au1200_ohci_control(base, enable);
+ break;
+ case ALCHEMY_USB_UDC0:
+ __au1200_udc_control(base, enable);
+ break;
+ case ALCHEMY_USB_EHCI0:
+ ret = au1200_coherency_bug();
+ if (ret && enable)
+ goto out;
+ __au1200_ehci_control(base, enable);
+ break;
+ default:
+ ret = -ENODEV;
+ }
+out:
+ return ret;
+}
+
+
+/* initialize USB block(s) to a known working state */
+static inline void au1200_usb_init(void)
+{
+ void __iomem *base =
+ (void __iomem *)KSEG1ADDR(AU1200_USB_CTL_PHYS_ADDR);
+ __raw_writel(USBCFG_INIT_AU1200, base + AU1200_USBCFG);
+ wmb();
+ udelay(1000);
+}
+
+static inline void au1000_usb_init(unsigned long rb, int reg)
+{
+ void __iomem *base = (void __iomem *)KSEG1ADDR(rb + reg);
+ unsigned long r = __raw_readl(base);
+
+#if defined(__BIG_ENDIAN)
+ r |= USBHEN_BE;
+#endif
+ r |= USBHEN_C;
+
+ __raw_writel(r, base);
+ wmb();
+ udelay(1000);
+}
+
+
+static inline void __au1xx0_ohci_control(int enable, unsigned long rb, int creg)
+{
+ void __iomem *base = (void __iomem *)KSEG1ADDR(rb);
+ unsigned long r = __raw_readl(base + creg);
+
+ if (enable) {
+ __raw_writel(r | USBHEN_CE, base + creg);
+ wmb();
+ udelay(1000);
+ __raw_writel(r | USBHEN_CE | USBHEN_E, base + creg);
+ wmb();
+ udelay(1000);
+
+ /* wait for reset complete (read reg twice: au1500 erratum) */
+ while (__raw_readl(base + creg),
+ !(__raw_readl(base + creg) & USBHEN_RD))
+ udelay(1000);
+ } else {
+ __raw_writel(r & ~(USBHEN_CE | USBHEN_E), base + creg);
+ wmb();
+ }
+}
+
+static inline int au1000_usb_control(int block, int enable, unsigned long rb,
+ int creg)
+{
+ int ret = 0;
+
+ switch (block) {
+ case ALCHEMY_USB_OHCI0:
+ __au1xx0_ohci_control(enable, rb, creg);
+ break;
+ default:
+ ret = -ENODEV;
+ }
+ return ret;
+}
+
+/*
+ * alchemy_usb_control - control Alchemy on-chip USB blocks
+ * @block: USB block to target
+ * @enable: set 1 to enable a block, 0 to disable
+ */
+int alchemy_usb_control(int block, int enable)
+{
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&alchemy_usb_lock, flags);
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1000:
+ case ALCHEMY_CPU_AU1500:
+ case ALCHEMY_CPU_AU1100:
+ ret = au1000_usb_control(block, enable,
+ AU1000_USB_OHCI_PHYS_ADDR, AU1000_OHCICFG);
+ break;
+ case ALCHEMY_CPU_AU1550:
+ ret = au1000_usb_control(block, enable,
+ AU1550_USB_OHCI_PHYS_ADDR, AU1550_OHCICFG);
+ break;
+ case ALCHEMY_CPU_AU1200:
+ ret = au1200_usb_control(block, enable);
+ break;
+ default:
+ ret = -ENODEV;
+ }
+ spin_unlock_irqrestore(&alchemy_usb_lock, flags);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(alchemy_usb_control);
+
+
+static unsigned long alchemy_usb_pmdata[2];
+
+static void au1000_usb_pm(unsigned long br, int creg, int susp)
+{
+ void __iomem *base = (void __iomem *)KSEG1ADDR(br);
+
+ if (susp) {
+ alchemy_usb_pmdata[0] = __raw_readl(base + creg);
+ /* There appears to be some undocumented reset register.... */
+ __raw_writel(0, base + 0x04);
+ wmb();
+ __raw_writel(0, base + creg);
+ wmb();
+ } else {
+ __raw_writel(alchemy_usb_pmdata[0], base + creg);
+ wmb();
+ }
+}
+
+static void au1200_usb_pm(int susp)
+{
+ void __iomem *base =
+ (void __iomem *)KSEG1ADDR(AU1200_USB_OTG_PHYS_ADDR);
+ if (susp) {
+ /* save OTG_CAP/MUX registers which indicate port routing */
+ /* FIXME: write an OTG driver to do that */
+ alchemy_usb_pmdata[0] = __raw_readl(base + 0x00);
+ alchemy_usb_pmdata[1] = __raw_readl(base + 0x04);
+ } else {
+ /* restore access to all MMIO areas */
+ au1200_usb_init();
+
+ /* restore OTG_CAP/MUX registers */
+ __raw_writel(alchemy_usb_pmdata[0], base + 0x00);
+ __raw_writel(alchemy_usb_pmdata[1], base + 0x04);
+ wmb();
+ }
+}
+
+static void alchemy_usb_pm(int susp)
+{
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1000:
+ case ALCHEMY_CPU_AU1500:
+ case ALCHEMY_CPU_AU1100:
+ au1000_usb_pm(AU1000_USB_OHCI_PHYS_ADDR, AU1000_OHCICFG, susp);
+ break;
+ case ALCHEMY_CPU_AU1550:
+ au1000_usb_pm(AU1550_USB_OHCI_PHYS_ADDR, AU1550_OHCICFG, susp);
+ break;
+ case ALCHEMY_CPU_AU1200:
+ au1200_usb_pm(susp);
+ break;
+ }
+}
+
+static int alchemy_usb_suspend(void)
+{
+ alchemy_usb_pm(1);
+ return 0;
+}
+
+static void alchemy_usb_resume(void)
+{
+ alchemy_usb_pm(0);
+}
+
+static struct syscore_ops alchemy_usb_pm_ops = {
+ .suspend = alchemy_usb_suspend,
+ .resume = alchemy_usb_resume,
+};
+
+static int __init alchemy_usb_init(void)
+{
+ switch (alchemy_get_cputype()) {
+ case ALCHEMY_CPU_AU1000:
+ case ALCHEMY_CPU_AU1500:
+ case ALCHEMY_CPU_AU1100:
+ au1000_usb_init(AU1000_USB_OHCI_PHYS_ADDR, AU1000_OHCICFG);
+ break;
+ case ALCHEMY_CPU_AU1550:
+ au1000_usb_init(AU1550_USB_OHCI_PHYS_ADDR, AU1550_OHCICFG);
+ break;
+ case ALCHEMY_CPU_AU1200:
+ au1200_usb_init();
+ break;
+ }
+
+ register_syscore_ops(&alchemy_usb_pm_ops);
+
+ return 0;
+}
+arch_initcall(alchemy_usb_init);
diff --git a/drivers/usb/host/ehci-au1xxx.c b/drivers/usb/host/ehci-au1xxx.c
index 65719e8..18bafa9 100644
--- a/drivers/usb/host/ehci-au1xxx.c
+++ b/drivers/usb/host/ehci-au1xxx.c
@@ -14,61 +14,9 @@
#include <linux/platform_device.h>
#include <asm/mach-au1x00/au1000.h>
-#define USB_HOST_CONFIG (USB_MSR_BASE + USB_MSR_MCFG)
-#define USB_MCFG_PFEN (1<<31)
-#define USB_MCFG_RDCOMB (1<<30)
-#define USB_MCFG_SSDEN (1<<23)
-#define USB_MCFG_PHYPLLEN (1<<19)
-#define USB_MCFG_UCECLKEN (1<<18)
-#define USB_MCFG_EHCCLKEN (1<<17)
-#ifdef CONFIG_DMA_COHERENT
-#define USB_MCFG_UCAM (1<<7)
-#else
-#define USB_MCFG_UCAM (0)
-#endif
-#define USB_MCFG_EBMEN (1<<3)
-#define USB_MCFG_EMEMEN (1<<2)
-
-#define USBH_ENABLE_CE (USB_MCFG_PHYPLLEN | USB_MCFG_EHCCLKEN)
-#define USBH_ENABLE_INIT (USB_MCFG_PFEN | USB_MCFG_RDCOMB | \
- USBH_ENABLE_CE | USB_MCFG_SSDEN | \
- USB_MCFG_UCAM | USB_MCFG_EBMEN | \
- USB_MCFG_EMEMEN)
-
-#define USBH_DISABLE (USB_MCFG_EBMEN | USB_MCFG_EMEMEN)
extern int usb_disabled(void);
-static void au1xxx_start_ehc(void)
-{
- /* enable clock to EHCI block and HS PHY PLL*/
- au_writel(au_readl(USB_HOST_CONFIG) | USBH_ENABLE_CE, USB_HOST_CONFIG);
- au_sync();
- udelay(1000);
-
- /* enable EHCI mmio */
- au_writel(au_readl(USB_HOST_CONFIG) | USBH_ENABLE_INIT, USB_HOST_CONFIG);
- au_sync();
- udelay(1000);
-}
-
-static void au1xxx_stop_ehc(void)
-{
- unsigned long c;
-
- /* Disable mem */
- au_writel(au_readl(USB_HOST_CONFIG) & ~USBH_DISABLE, USB_HOST_CONFIG);
- au_sync();
- udelay(1000);
-
- /* Disable EHC clock. If the HS PHY is unused disable it too. */
- c = au_readl(USB_HOST_CONFIG) & ~USB_MCFG_EHCCLKEN;
- if (!(c & USB_MCFG_UCECLKEN)) /* UDC disabled? */
- c &= ~USB_MCFG_PHYPLLEN; /* yes: disable HS PHY PLL */
- au_writel(c, USB_HOST_CONFIG);
- au_sync();
-}
-
static int au1xxx_ehci_setup(struct usb_hcd *hcd)
{
struct ehci_hcd *ehci = hcd_to_ehci(hcd);
@@ -136,16 +84,6 @@
if (usb_disabled())
return -ENODEV;
-#if defined(CONFIG_SOC_AU1200) && defined(CONFIG_DMA_COHERENT)
- /* Au1200 AB USB does not support coherent memory */
- if (!(read_c0_prid() & 0xff)) {
- printk(KERN_INFO "%s: this is chip revision AB!\n", pdev->name);
- printk(KERN_INFO "%s: update your board or re-configure"
- " the kernel\n", pdev->name);
- return -ENODEV;
- }
-#endif
-
if (pdev->resource[1].flags != IORESOURCE_IRQ) {
pr_debug("resource[1] is not IORESOURCE_IRQ");
return -ENOMEM;
@@ -171,7 +109,11 @@
goto err2;
}
- au1xxx_start_ehc();
+ if (alchemy_usb_control(ALCHEMY_USB_EHCI0, 1)) {
+ printk(KERN_INFO "%s: controller init failed!\n", pdev->name);
+ ret = -ENODEV;
+ goto err3;
+ }
ehci = hcd_to_ehci(hcd);
ehci->caps = hcd->regs;
@@ -187,7 +129,8 @@
return ret;
}
- au1xxx_stop_ehc();
+ alchemy_usb_control(ALCHEMY_USB_EHCI0, 0);
+err3:
iounmap(hcd->regs);
err2:
release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
@@ -201,10 +144,10 @@
struct usb_hcd *hcd = platform_get_drvdata(pdev);
usb_remove_hcd(hcd);
+ alchemy_usb_control(ALCHEMY_USB_EHCI0, 0);
iounmap(hcd->regs);
release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
usb_put_hcd(hcd);
- au1xxx_stop_ehc();
platform_set_drvdata(pdev, NULL);
return 0;
@@ -236,7 +179,7 @@
// could save FLADJ in case of Vaux power loss
// ... we'd only use it to handle clock skew
- au1xxx_stop_ehc();
+ alchemy_usb_control(ALCHEMY_USB_EHCI0, 0);
return rc;
}
@@ -246,7 +189,7 @@
struct usb_hcd *hcd = dev_get_drvdata(dev);
struct ehci_hcd *ehci = hcd_to_ehci(hcd);
- au1xxx_start_ehc();
+ alchemy_usb_control(ALCHEMY_USB_EHCI0, 1);
// maybe restore FLADJ
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 59e8161..3ff9f82 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -1224,7 +1224,7 @@
#define PLATFORM_DRIVER ehci_hcd_sh_driver
#endif
-#ifdef CONFIG_SOC_AU1200
+#ifdef CONFIG_MIPS_ALCHEMY
#include "ehci-au1xxx.c"
#define PLATFORM_DRIVER ehci_hcd_au1xxx_driver
#endif
diff --git a/drivers/usb/host/ohci-au1xxx.c b/drivers/usb/host/ohci-au1xxx.c
index 6b7bc50..9b66df8 100644
--- a/drivers/usb/host/ohci-au1xxx.c
+++ b/drivers/usb/host/ohci-au1xxx.c
@@ -23,92 +23,9 @@
#include <asm/mach-au1x00/au1000.h>
-#ifndef CONFIG_SOC_AU1200
-
-#define USBH_ENABLE_BE (1<<0)
-#define USBH_ENABLE_C (1<<1)
-#define USBH_ENABLE_E (1<<2)
-#define USBH_ENABLE_CE (1<<3)
-#define USBH_ENABLE_RD (1<<4)
-
-#ifdef __LITTLE_ENDIAN
-#define USBH_ENABLE_INIT (USBH_ENABLE_CE | USBH_ENABLE_E | USBH_ENABLE_C)
-#elif defined(__BIG_ENDIAN)
-#define USBH_ENABLE_INIT (USBH_ENABLE_CE | USBH_ENABLE_E | USBH_ENABLE_C | \
- USBH_ENABLE_BE)
-#else
-#error not byte order defined
-#endif
-
-#else /* Au1200 */
-
-#define USB_HOST_CONFIG (USB_MSR_BASE + USB_MSR_MCFG)
-#define USB_MCFG_PFEN (1<<31)
-#define USB_MCFG_RDCOMB (1<<30)
-#define USB_MCFG_SSDEN (1<<23)
-#define USB_MCFG_OHCCLKEN (1<<16)
-#ifdef CONFIG_DMA_COHERENT
-#define USB_MCFG_UCAM (1<<7)
-#else
-#define USB_MCFG_UCAM (0)
-#endif
-#define USB_MCFG_OBMEN (1<<1)
-#define USB_MCFG_OMEMEN (1<<0)
-
-#define USBH_ENABLE_CE USB_MCFG_OHCCLKEN
-
-#define USBH_ENABLE_INIT (USB_MCFG_PFEN | USB_MCFG_RDCOMB | \
- USBH_ENABLE_CE | USB_MCFG_SSDEN | \
- USB_MCFG_UCAM | \
- USB_MCFG_OBMEN | USB_MCFG_OMEMEN)
-
-#define USBH_DISABLE (USB_MCFG_OBMEN | USB_MCFG_OMEMEN)
-
-#endif /* Au1200 */
extern int usb_disabled(void);
-static void au1xxx_start_ohc(void)
-{
- /* enable host controller */
-#ifndef CONFIG_SOC_AU1200
- au_writel(USBH_ENABLE_CE, USB_HOST_CONFIG);
- au_sync();
- udelay(1000);
-
- au_writel(au_readl(USB_HOST_CONFIG) | USBH_ENABLE_INIT, USB_HOST_CONFIG);
- au_sync();
- udelay(1000);
-
- /* wait for reset complete (read register twice; see au1500 errata) */
- while (au_readl(USB_HOST_CONFIG),
- !(au_readl(USB_HOST_CONFIG) & USBH_ENABLE_RD))
- udelay(1000);
-
-#else /* Au1200 */
- au_writel(au_readl(USB_HOST_CONFIG) | USBH_ENABLE_CE, USB_HOST_CONFIG);
- au_sync();
- udelay(1000);
-
- au_writel(au_readl(USB_HOST_CONFIG) | USBH_ENABLE_INIT, USB_HOST_CONFIG);
- au_sync();
- udelay(2000);
-#endif /* Au1200 */
-}
-
-static void au1xxx_stop_ohc(void)
-{
-#ifdef CONFIG_SOC_AU1200
- /* Disable mem */
- au_writel(au_readl(USB_HOST_CONFIG) & ~USBH_DISABLE, USB_HOST_CONFIG);
- au_sync();
- udelay(1000);
-#endif
- /* Disable clock */
- au_writel(au_readl(USB_HOST_CONFIG) & ~USBH_ENABLE_CE, USB_HOST_CONFIG);
- au_sync();
-}
-
static int __devinit ohci_au1xxx_start(struct usb_hcd *hcd)
{
struct ohci_hcd *ohci = hcd_to_ohci(hcd);
@@ -178,17 +95,6 @@
if (usb_disabled())
return -ENODEV;
-#if defined(CONFIG_SOC_AU1200) && defined(CONFIG_DMA_COHERENT)
- /* Au1200 AB USB does not support coherent memory */
- if (!(read_c0_prid() & 0xff)) {
- printk(KERN_INFO "%s: this is chip revision AB !!\n",
- pdev->name);
- printk(KERN_INFO "%s: update your board or re-configure "
- "the kernel\n", pdev->name);
- return -ENODEV;
- }
-#endif
-
if (pdev->resource[1].flags != IORESOURCE_IRQ) {
pr_debug("resource[1] is not IORESOURCE_IRQ\n");
return -ENOMEM;
@@ -214,7 +120,12 @@
goto err2;
}
- au1xxx_start_ohc();
+ if (alchemy_usb_control(ALCHEMY_USB_OHCI0, 1)) {
+ printk(KERN_INFO "%s: controller init failed!\n", pdev->name);
+ ret = -ENODEV;
+ goto err3;
+ }
+
ohci_hcd_init(hcd_to_ohci(hcd));
ret = usb_add_hcd(hcd, pdev->resource[1].start,
@@ -224,7 +135,8 @@
return ret;
}
- au1xxx_stop_ohc();
+ alchemy_usb_control(ALCHEMY_USB_OHCI0, 0);
+err3:
iounmap(hcd->regs);
err2:
release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
@@ -238,7 +150,7 @@
struct usb_hcd *hcd = platform_get_drvdata(pdev);
usb_remove_hcd(hcd);
- au1xxx_stop_ohc();
+ alchemy_usb_control(ALCHEMY_USB_OHCI0, 0);
iounmap(hcd->regs);
release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
usb_put_hcd(hcd);
@@ -275,7 +187,7 @@
clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
- au1xxx_stop_ohc();
+ alchemy_usb_control(ALCHEMY_USB_OHCI0, 0);
bail:
spin_unlock_irqrestore(&ohci->lock, flags);
@@ -286,7 +198,7 @@
{
struct usb_hcd *hcd = dev_get_drvdata(dev);
- au1xxx_start_ohc();
+ alchemy_usb_control(ALCHEMY_USB_OHCI0, 1);
set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
ohci_finish_controller_resume(hcd);
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 8165c55..d83e967 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -1753,7 +1753,7 @@
config FB_AU1100
bool "Au1100 LCD Driver"
- depends on (FB = y) && MIPS && SOC_AU1100
+ depends on (FB = y) && MIPS_ALCHEMY
select FB_CFB_FILLRECT
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
@@ -1764,7 +1764,7 @@
config FB_AU1200
bool "Au1200 LCD Driver"
- depends on (FB = y) && MIPS && SOC_AU1200
+ depends on (FB = y) && MIPS_ALCHEMY
select FB_SYS_FILLRECT
select FB_SYS_COPYAREA
select FB_SYS_IMAGEBLIT
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 57e493b..816ed08 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -35,4 +35,15 @@
If unsure, say M.
+ config VIRTIO_MMIO
+ tristate "Platform bus driver for memory mapped virtio devices (EXPERIMENTAL)"
+ depends on EXPERIMENTAL
+ select VIRTIO
+ select VIRTIO_RING
+ ---help---
+ This drivers provides support for memory mapped virtio
+ platform device driver.
+
+ If unsure, say N.
+
endmenu
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 6738c44..5a4c63c 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,4 +1,5 @@
obj-$(CONFIG_VIRTIO) += virtio.o
obj-$(CONFIG_VIRTIO_RING) += virtio_ring.o
+obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
new file mode 100644
index 0000000..acc5e43
--- /dev/null
+++ b/drivers/virtio/virtio_mmio.c
@@ -0,0 +1,479 @@
+/*
+ * Virtio memory mapped device driver
+ *
+ * Copyright 2011, ARM Ltd.
+ *
+ * This module allows virtio devices to be used over a virtual, memory mapped
+ * platform device.
+ *
+ * Registers layout (all 32-bit wide):
+ *
+ * offset d. name description
+ * ------ -- ---------------- -----------------
+ *
+ * 0x000 R MagicValue Magic value "virt"
+ * 0x004 R Version Device version (current max. 1)
+ * 0x008 R DeviceID Virtio device ID
+ * 0x00c R VendorID Virtio vendor ID
+ *
+ * 0x010 R HostFeatures Features supported by the host
+ * 0x014 W HostFeaturesSel Set of host features to access via HostFeatures
+ *
+ * 0x020 W GuestFeatures Features activated by the guest
+ * 0x024 W GuestFeaturesSel Set of activated features to set via GuestFeatures
+ * 0x028 W GuestPageSize Size of guest's memory page in bytes
+ *
+ * 0x030 W QueueSel Queue selector
+ * 0x034 R QueueNumMax Maximum size of the currently selected queue
+ * 0x038 W QueueNum Queue size for the currently selected queue
+ * 0x03c W QueueAlign Used Ring alignment for the current queue
+ * 0x040 RW QueuePFN PFN for the currently selected queue
+ *
+ * 0x050 W QueueNotify Queue notifier
+ * 0x060 R InterruptStatus Interrupt status register
+ * 0x060 W InterruptACK Interrupt acknowledge register
+ * 0x070 RW Status Device status register
+ *
+ * 0x100+ RW Device-specific configuration space
+ *
+ * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include <linux/highmem.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_mmio.h>
+#include <linux/virtio_ring.h>
+
+
+
+/* The alignment to use between consumer and producer parts of vring.
+ * Currently hardcoded to the page size. */
+#define VIRTIO_MMIO_VRING_ALIGN PAGE_SIZE
+
+
+
+#define to_virtio_mmio_device(_plat_dev) \
+ container_of(_plat_dev, struct virtio_mmio_device, vdev)
+
+struct virtio_mmio_device {
+ struct virtio_device vdev;
+ struct platform_device *pdev;
+
+ void __iomem *base;
+ unsigned long version;
+
+ /* a list of queues so we can dispatch IRQs */
+ spinlock_t lock;
+ struct list_head virtqueues;
+};
+
+struct virtio_mmio_vq_info {
+ /* the actual virtqueue */
+ struct virtqueue *vq;
+
+ /* the number of entries in the queue */
+ unsigned int num;
+
+ /* the index of the queue */
+ int queue_index;
+
+ /* the virtual address of the ring queue */
+ void *queue;
+
+ /* the list node for the virtqueues list */
+ struct list_head node;
+};
+
+
+
+/* Configuration interface */
+
+static u32 vm_get_features(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+ /* TODO: Features > 32 bits */
+ writel(0, vm_dev->base + VIRTIO_MMIO_HOST_FEATURES_SEL);
+
+ return readl(vm_dev->base + VIRTIO_MMIO_HOST_FEATURES);
+}
+
+static void vm_finalize_features(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ int i;
+
+ /* Give virtio_ring a chance to accept features. */
+ vring_transport_features(vdev);
+
+ for (i = 0; i < ARRAY_SIZE(vdev->features); i++) {
+ writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SET);
+ writel(vdev->features[i],
+ vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
+ }
+}
+
+static void vm_get(struct virtio_device *vdev, unsigned offset,
+ void *buf, unsigned len)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ ptr[i] = readb(vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static void vm_set(struct virtio_device *vdev, unsigned offset,
+ const void *buf, unsigned len)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ const u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ writeb(ptr[i], vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static u8 vm_get_status(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+ return readl(vm_dev->base + VIRTIO_MMIO_STATUS) & 0xff;
+}
+
+static void vm_set_status(struct virtio_device *vdev, u8 status)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+ /* We should never be setting status to 0. */
+ BUG_ON(status == 0);
+
+ writel(status, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+static void vm_reset(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+ /* 0 status means a reset. */
+ writel(0, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+
+
+/* Transport interface */
+
+/* the notify function used when creating a virt queue */
+static void vm_notify(struct virtqueue *vq)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+ struct virtio_mmio_vq_info *info = vq->priv;
+
+ /* We write the queue's selector into the notification register to
+ * signal the other end */
+ writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+}
+
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vm_interrupt(int irq, void *opaque)
+{
+ struct virtio_mmio_device *vm_dev = opaque;
+ struct virtio_mmio_vq_info *info;
+ struct virtio_driver *vdrv = container_of(vm_dev->vdev.dev.driver,
+ struct virtio_driver, driver);
+ unsigned long status;
+ unsigned long flags;
+ irqreturn_t ret = IRQ_NONE;
+
+ /* Read and acknowledge interrupts */
+ status = readl(vm_dev->base + VIRTIO_MMIO_INTERRUPT_STATUS);
+ writel(status, vm_dev->base + VIRTIO_MMIO_INTERRUPT_ACK);
+
+ if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)
+ && vdrv && vdrv->config_changed) {
+ vdrv->config_changed(&vm_dev->vdev);
+ ret = IRQ_HANDLED;
+ }
+
+ if (likely(status & VIRTIO_MMIO_INT_VRING)) {
+ spin_lock_irqsave(&vm_dev->lock, flags);
+ list_for_each_entry(info, &vm_dev->virtqueues, node)
+ ret |= vring_interrupt(irq, info->vq);
+ spin_unlock_irqrestore(&vm_dev->lock, flags);
+ }
+
+ return ret;
+}
+
+
+
+static void vm_del_vq(struct virtqueue *vq)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+ struct virtio_mmio_vq_info *info = vq->priv;
+ unsigned long flags, size;
+
+ spin_lock_irqsave(&vm_dev->lock, flags);
+ list_del(&info->node);
+ spin_unlock_irqrestore(&vm_dev->lock, flags);
+
+ vring_del_virtqueue(vq);
+
+ /* Select and deactivate the queue */
+ writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+ writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+
+ size = PAGE_ALIGN(vring_size(info->num, VIRTIO_MMIO_VRING_ALIGN));
+ free_pages_exact(info->queue, size);
+ kfree(info);
+}
+
+static void vm_del_vqs(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ struct virtqueue *vq, *n;
+
+ list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+ vm_del_vq(vq);
+
+ free_irq(platform_get_irq(vm_dev->pdev, 0), vm_dev);
+}
+
+
+
+static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
+ void (*callback)(struct virtqueue *vq),
+ const char *name)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ struct virtio_mmio_vq_info *info;
+ struct virtqueue *vq;
+ unsigned long flags, size;
+ int err;
+
+ /* Select the queue we're interested in */
+ writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+
+ /* Queue shouldn't already be set up. */
+ if (readl(vm_dev->base + VIRTIO_MMIO_QUEUE_PFN)) {
+ err = -ENOENT;
+ goto error_available;
+ }
+
+ /* Allocate and fill out our active queue description */
+ info = kmalloc(sizeof(*info), GFP_KERNEL);
+ if (!info) {
+ err = -ENOMEM;
+ goto error_kmalloc;
+ }
+ info->queue_index = index;
+
+ /* Allocate pages for the queue - start with a queue as big as
+ * possible (limited by maximum size allowed by device), drop down
+ * to a minimal size, just big enough to fit descriptor table
+ * and two rings (which makes it "alignment_size * 2")
+ */
+ info->num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX);
+ while (1) {
+ size = PAGE_ALIGN(vring_size(info->num,
+ VIRTIO_MMIO_VRING_ALIGN));
+ /* Already smallest possible allocation? */
+ if (size <= VIRTIO_MMIO_VRING_ALIGN * 2) {
+ err = -ENOMEM;
+ goto error_alloc_pages;
+ }
+
+ info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+ if (info->queue)
+ break;
+
+ info->num /= 2;
+ }
+
+ /* Activate the queue */
+ writel(info->num, vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
+ writel(VIRTIO_MMIO_VRING_ALIGN,
+ vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
+ writel(virt_to_phys(info->queue) >> PAGE_SHIFT,
+ vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+
+ /* Create the vring */
+ vq = vring_new_virtqueue(info->num, VIRTIO_MMIO_VRING_ALIGN,
+ vdev, info->queue, vm_notify, callback, name);
+ if (!vq) {
+ err = -ENOMEM;
+ goto error_new_virtqueue;
+ }
+
+ vq->priv = info;
+ info->vq = vq;
+
+ spin_lock_irqsave(&vm_dev->lock, flags);
+ list_add(&info->node, &vm_dev->virtqueues);
+ spin_unlock_irqrestore(&vm_dev->lock, flags);
+
+ return vq;
+
+error_new_virtqueue:
+ writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+ free_pages_exact(info->queue, size);
+error_alloc_pages:
+ kfree(info);
+error_kmalloc:
+error_available:
+ return ERR_PTR(err);
+}
+
+static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char *names[])
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
+ int i, err;
+
+ err = request_irq(irq, vm_interrupt, IRQF_SHARED,
+ dev_name(&vdev->dev), vm_dev);
+ if (err)
+ return err;
+
+ for (i = 0; i < nvqs; ++i) {
+ vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i]);
+ if (IS_ERR(vqs[i])) {
+ vm_del_vqs(vdev);
+ return PTR_ERR(vqs[i]);
+ }
+ }
+
+ return 0;
+}
+
+
+
+static struct virtio_config_ops virtio_mmio_config_ops = {
+ .get = vm_get,
+ .set = vm_set,
+ .get_status = vm_get_status,
+ .set_status = vm_set_status,
+ .reset = vm_reset,
+ .find_vqs = vm_find_vqs,
+ .del_vqs = vm_del_vqs,
+ .get_features = vm_get_features,
+ .finalize_features = vm_finalize_features,
+};
+
+
+
+/* Platform device */
+
+static int __devinit virtio_mmio_probe(struct platform_device *pdev)
+{
+ struct virtio_mmio_device *vm_dev;
+ struct resource *mem;
+ unsigned long magic;
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!mem)
+ return -EINVAL;
+
+ if (!devm_request_mem_region(&pdev->dev, mem->start,
+ resource_size(mem), pdev->name))
+ return -EBUSY;
+
+ vm_dev = devm_kzalloc(&pdev->dev, sizeof(*vm_dev), GFP_KERNEL);
+ if (!vm_dev)
+ return -ENOMEM;
+
+ vm_dev->vdev.dev.parent = &pdev->dev;
+ vm_dev->vdev.config = &virtio_mmio_config_ops;
+ vm_dev->pdev = pdev;
+ INIT_LIST_HEAD(&vm_dev->virtqueues);
+ spin_lock_init(&vm_dev->lock);
+
+ vm_dev->base = devm_ioremap(&pdev->dev, mem->start, resource_size(mem));
+ if (vm_dev->base == NULL)
+ return -EFAULT;
+
+ /* Check magic value */
+ magic = readl(vm_dev->base + VIRTIO_MMIO_MAGIC_VALUE);
+ if (memcmp(&magic, "virt", 4) != 0) {
+ dev_warn(&pdev->dev, "Wrong magic value 0x%08lx!\n", magic);
+ return -ENODEV;
+ }
+
+ /* Check device version */
+ vm_dev->version = readl(vm_dev->base + VIRTIO_MMIO_VERSION);
+ if (vm_dev->version != 1) {
+ dev_err(&pdev->dev, "Version %ld not supported!\n",
+ vm_dev->version);
+ return -ENXIO;
+ }
+
+ vm_dev->vdev.id.device = readl(vm_dev->base + VIRTIO_MMIO_DEVICE_ID);
+ vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID);
+
+ writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+
+ platform_set_drvdata(pdev, vm_dev);
+
+ return register_virtio_device(&vm_dev->vdev);
+}
+
+static int __devexit virtio_mmio_remove(struct platform_device *pdev)
+{
+ struct virtio_mmio_device *vm_dev = platform_get_drvdata(pdev);
+
+ unregister_virtio_device(&vm_dev->vdev);
+
+ return 0;
+}
+
+
+
+/* Platform driver */
+
+static struct of_device_id virtio_mmio_match[] = {
+ { .compatible = "virtio,mmio", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, virtio_mmio_match);
+
+static struct platform_driver virtio_mmio_driver = {
+ .probe = virtio_mmio_probe,
+ .remove = __devexit_p(virtio_mmio_remove),
+ .driver = {
+ .name = "virtio-mmio",
+ .owner = THIS_MODULE,
+ .of_match_table = virtio_mmio_match,
+ },
+};
+
+static int __init virtio_mmio_init(void)
+{
+ return platform_driver_register(&virtio_mmio_driver);
+}
+
+static void __exit virtio_mmio_exit(void)
+{
+ platform_driver_unregister(&virtio_mmio_driver);
+}
+
+module_init(virtio_mmio_init);
+module_exit(virtio_mmio_exit);
+
+MODULE_AUTHOR("Pawel Moll <pawel.moll@arm.com>");
+MODULE_DESCRIPTION("Platform bus driver for memory mapped virtio devices");
+MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 4bcc8b8..79a31e5 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -415,9 +415,13 @@
}
}
- spin_lock_irqsave(&vp_dev->lock, flags);
- list_add(&info->node, &vp_dev->virtqueues);
- spin_unlock_irqrestore(&vp_dev->lock, flags);
+ if (callback) {
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_add(&info->node, &vp_dev->virtqueues);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+ } else {
+ INIT_LIST_HEAD(&info->node);
+ }
return vq;
diff --git a/drivers/w1/slaves/w1_ds2760.c b/drivers/w1/slaves/w1_ds2760.c
index 483d451..5754c9a 100644
--- a/drivers/w1/slaves/w1_ds2760.c
+++ b/drivers/w1/slaves/w1_ds2760.c
@@ -114,43 +114,7 @@
.read = w1_ds2760_read_bin,
};
-static DEFINE_IDR(bat_idr);
-static DEFINE_MUTEX(bat_idr_lock);
-
-static int new_bat_id(void)
-{
- int ret;
-
- while (1) {
- int id;
-
- ret = idr_pre_get(&bat_idr, GFP_KERNEL);
- if (ret == 0)
- return -ENOMEM;
-
- mutex_lock(&bat_idr_lock);
- ret = idr_get_new(&bat_idr, NULL, &id);
- mutex_unlock(&bat_idr_lock);
-
- if (ret == 0) {
- ret = id & MAX_ID_MASK;
- break;
- } else if (ret == -EAGAIN) {
- continue;
- } else {
- break;
- }
- }
-
- return ret;
-}
-
-static void release_bat_id(int id)
-{
- mutex_lock(&bat_idr_lock);
- idr_remove(&bat_idr, id);
- mutex_unlock(&bat_idr_lock);
-}
+static DEFINE_IDA(bat_ida);
static int w1_ds2760_add_slave(struct w1_slave *sl)
{
@@ -158,7 +122,7 @@
int id;
struct platform_device *pdev;
- id = new_bat_id();
+ id = ida_simple_get(&bat_ida, 0, 0, GFP_KERNEL);
if (id < 0) {
ret = id;
goto noid;
@@ -187,7 +151,7 @@
pdev_add_failed:
platform_device_unregister(pdev);
pdev_alloc_failed:
- release_bat_id(id);
+ ida_simple_remove(&bat_ida, id);
noid:
success:
return ret;
@@ -199,7 +163,7 @@
int id = pdev->id;
platform_device_unregister(pdev);
- release_bat_id(id);
+ ida_simple_remove(&bat_ida, id);
sysfs_remove_bin_file(&sl->dev.kobj, &w1_ds2760_bin_attr);
}
@@ -217,14 +181,14 @@
{
printk(KERN_INFO "1-Wire driver for the DS2760 battery monitor "
" chip - (c) 2004-2005, Szabolcs Gyurko\n");
- idr_init(&bat_idr);
+ ida_init(&bat_ida);
return w1_register_family(&w1_ds2760_family);
}
static void __exit w1_ds2760_exit(void)
{
w1_unregister_family(&w1_ds2760_family);
- idr_destroy(&bat_idr);
+ ida_destroy(&bat_ida);
}
EXPORT_SYMBOL(w1_ds2760_read);
diff --git a/drivers/w1/slaves/w1_ds2780.c b/drivers/w1/slaves/w1_ds2780.c
index 274c8f3..39f78c0 100644
--- a/drivers/w1/slaves/w1_ds2780.c
+++ b/drivers/w1/slaves/w1_ds2780.c
@@ -26,20 +26,14 @@
#include "../w1_family.h"
#include "w1_ds2780.h"
-int w1_ds2780_io(struct device *dev, char *buf, int addr, size_t count,
- int io)
+static int w1_ds2780_do_io(struct device *dev, char *buf, int addr,
+ size_t count, int io)
{
struct w1_slave *sl = container_of(dev, struct w1_slave, dev);
- if (!dev)
- return -ENODEV;
+ if (addr > DS2780_DATA_SIZE || addr < 0)
+ return 0;
- mutex_lock(&sl->master->mutex);
-
- if (addr > DS2780_DATA_SIZE || addr < 0) {
- count = 0;
- goto out;
- }
count = min_t(int, count, DS2780_DATA_SIZE - addr);
if (w1_reset_select_slave(sl) == 0) {
@@ -47,7 +41,6 @@
w1_write_8(sl->master, W1_DS2780_WRITE_DATA);
w1_write_8(sl->master, addr);
w1_write_block(sl->master, buf, count);
- /* XXX w1_write_block returns void, not n_written */
} else {
w1_write_8(sl->master, W1_DS2780_READ_DATA);
w1_write_8(sl->master, addr);
@@ -55,13 +48,42 @@
}
}
-out:
- mutex_unlock(&sl->master->mutex);
-
return count;
}
+
+int w1_ds2780_io(struct device *dev, char *buf, int addr, size_t count,
+ int io)
+{
+ struct w1_slave *sl = container_of(dev, struct w1_slave, dev);
+ int ret;
+
+ if (!dev)
+ return -ENODEV;
+
+ mutex_lock(&sl->master->mutex);
+
+ ret = w1_ds2780_do_io(dev, buf, addr, count, io);
+
+ mutex_unlock(&sl->master->mutex);
+
+ return ret;
+}
EXPORT_SYMBOL(w1_ds2780_io);
+int w1_ds2780_io_nolock(struct device *dev, char *buf, int addr, size_t count,
+ int io)
+{
+ int ret;
+
+ if (!dev)
+ return -ENODEV;
+
+ ret = w1_ds2780_do_io(dev, buf, addr, count, io);
+
+ return ret;
+}
+EXPORT_SYMBOL(w1_ds2780_io_nolock);
+
int w1_ds2780_eeprom_cmd(struct device *dev, int addr, int cmd)
{
struct w1_slave *sl = container_of(dev, struct w1_slave, dev);
@@ -99,43 +121,7 @@
.read = w1_ds2780_read_bin,
};
-static DEFINE_IDR(bat_idr);
-static DEFINE_MUTEX(bat_idr_lock);
-
-static int new_bat_id(void)
-{
- int ret;
-
- while (1) {
- int id;
-
- ret = idr_pre_get(&bat_idr, GFP_KERNEL);
- if (ret == 0)
- return -ENOMEM;
-
- mutex_lock(&bat_idr_lock);
- ret = idr_get_new(&bat_idr, NULL, &id);
- mutex_unlock(&bat_idr_lock);
-
- if (ret == 0) {
- ret = id & MAX_ID_MASK;
- break;
- } else if (ret == -EAGAIN) {
- continue;
- } else {
- break;
- }
- }
-
- return ret;
-}
-
-static void release_bat_id(int id)
-{
- mutex_lock(&bat_idr_lock);
- idr_remove(&bat_idr, id);
- mutex_unlock(&bat_idr_lock);
-}
+static DEFINE_IDA(bat_ida);
static int w1_ds2780_add_slave(struct w1_slave *sl)
{
@@ -143,7 +129,7 @@
int id;
struct platform_device *pdev;
- id = new_bat_id();
+ id = ida_simple_get(&bat_ida, 0, 0, GFP_KERNEL);
if (id < 0) {
ret = id;
goto noid;
@@ -172,7 +158,7 @@
pdev_add_failed:
platform_device_unregister(pdev);
pdev_alloc_failed:
- release_bat_id(id);
+ ida_simple_remove(&bat_ida, id);
noid:
return ret;
}
@@ -183,7 +169,7 @@
int id = pdev->id;
platform_device_unregister(pdev);
- release_bat_id(id);
+ ida_simple_remove(&bat_ida, id);
sysfs_remove_bin_file(&sl->dev.kobj, &w1_ds2780_bin_attr);
}
@@ -199,14 +185,14 @@
static int __init w1_ds2780_init(void)
{
- idr_init(&bat_idr);
+ ida_init(&bat_ida);
return w1_register_family(&w1_ds2780_family);
}
static void __exit w1_ds2780_exit(void)
{
w1_unregister_family(&w1_ds2780_family);
- idr_destroy(&bat_idr);
+ ida_destroy(&bat_ida);
}
module_init(w1_ds2780_init);
diff --git a/drivers/w1/slaves/w1_ds2780.h b/drivers/w1/slaves/w1_ds2780.h
index a1fba79..7373793 100644
--- a/drivers/w1/slaves/w1_ds2780.h
+++ b/drivers/w1/slaves/w1_ds2780.h
@@ -124,6 +124,8 @@
extern int w1_ds2780_io(struct device *dev, char *buf, int addr, size_t count,
int io);
+extern int w1_ds2780_io_nolock(struct device *dev, char *buf, int addr,
+ size_t count, int io);
extern int w1_ds2780_eeprom_cmd(struct device *dev, int addr, int cmd);
#endif /* !_W1_DS2780_H */
diff --git a/drivers/w1/w1_int.c b/drivers/w1/w1_int.c
index d220bce..f79e62e 100644
--- a/drivers/w1/w1_int.c
+++ b/drivers/w1/w1_int.c
@@ -78,6 +78,7 @@
memcpy(&dev->dev, device, sizeof(struct device));
dev_set_name(&dev->dev, "w1_bus_master%u", dev->id);
snprintf(dev->name, sizeof(dev->name), "w1_bus_master%u", dev->id);
+ dev->dev.init_name = dev->name;
dev->driver = driver;
diff --git a/drivers/w1/w1_io.c b/drivers/w1/w1_io.c
index 765b37b..3135b2c 100644
--- a/drivers/w1/w1_io.c
+++ b/drivers/w1/w1_io.c
@@ -158,13 +158,18 @@
static u8 w1_read_bit(struct w1_master *dev)
{
int result;
+ unsigned long flags;
+ /* sample timing is critical here */
+ local_irq_save(flags);
dev->bus_master->write_bit(dev->bus_master->data, 0);
w1_delay(6);
dev->bus_master->write_bit(dev->bus_master->data, 1);
w1_delay(9);
result = dev->bus_master->read_bit(dev->bus_master->data);
+ local_irq_restore(flags);
+
w1_delay(55);
return result & 0x1;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 86b0735..64c6752 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -726,7 +726,7 @@
config SBC7240_WDT
tristate "SBC Nano 7240 Watchdog Timer"
- depends on X86_32
+ depends on X86_32 && !UML
---help---
This is the driver for the hardware watchdog found on the IEI
single board computers EPIC Nano 7240 (and likely others). This
@@ -1174,6 +1174,10 @@
by Xen 4.0 and newer. The watchdog timeout period is normally one
minute but can be changed with a boot-time parameter.
+config UML_WATCHDOG
+ tristate "UML watchdog"
+ depends on UML
+
#
# ISA-based Watchdog Cards
#
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index b5a1076..879ed88 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1138,7 +1138,7 @@
struct v9fs_session_info *v9ses = sb->s_fs_info;
struct v9fs_inode *v9inode = V9FS_I(inode);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_atime.tv_sec = stat->atime;
inode->i_mtime.tv_sec = stat->mtime;
@@ -1164,7 +1164,7 @@
/* HARDLINKCOUNT %u */
sscanf(ext, "%13s %u", tag_name, &i_nlink);
if (!strncmp(tag_name, "HARDLINKCOUNT", 13))
- inode->i_nlink = i_nlink;
+ set_nlink(inode, i_nlink);
}
}
mode = stat->mode & S_IALLUGO;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index aded79f..0b5745e 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -606,7 +606,7 @@
inode->i_ctime.tv_nsec = stat->st_ctime_nsec;
inode->i_uid = stat->st_uid;
inode->i_gid = stat->st_gid;
- inode->i_nlink = stat->st_nlink;
+ set_nlink(inode, stat->st_nlink);
mode = stat->st_mode & S_IALLUGO;
mode |= inode->i_mode & ~S_IALLUGO;
@@ -632,7 +632,7 @@
if (stat->st_result_mask & P9_STATS_GID)
inode->i_gid = stat->st_gid;
if (stat->st_result_mask & P9_STATS_NLINK)
- inode->i_nlink = stat->st_nlink;
+ set_nlink(inode, stat->st_nlink);
if (stat->st_result_mask & P9_STATS_MODE) {
inode->i_mode = stat->st_mode;
if ((S_ISBLK(inode->i_mode)) ||
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index d5250c5..1dab6a1 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -247,7 +247,7 @@
inode->i_gid = ADFS_SB(sb)->s_gid;
inode->i_ino = obj->file_id;
inode->i_size = obj->size;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_blocks = (inode->i_size + sb->s_blocksize - 1) >>
sb->s_blocksize_bits;
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 3a4557e..de37ec8 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -215,7 +215,7 @@
break;
default:
if (!AFFS_TAIL(sb, bh)->link_chain)
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
affs_free_block(sb, link_ino);
goto done;
@@ -316,7 +316,7 @@
if (inode->i_nlink > 1)
retval = affs_remove_link(dentry);
else
- inode->i_nlink = 0;
+ clear_nlink(inode);
affs_unlock_link(inode);
inode->i_ctime = CURRENT_TIME_SEC;
mark_inode_dirty(inode);
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 5d82890..88a4b0b 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -54,7 +54,7 @@
prot = be32_to_cpu(tail->protect);
inode->i_size = 0;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_mode = 0;
AFFS_I(inode)->i_extcnt = 1;
AFFS_I(inode)->i_ext_last = ~1;
@@ -137,7 +137,7 @@
sbi->s_hashsize + 1;
}
if (tail->link_chain)
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_mapping->a_ops = (sbi->s_flags & SF_OFS) ? &affs_aops_ofs : &affs_aops;
inode->i_op = &affs_file_inode_operations;
inode->i_fop = &affs_file_operations;
@@ -304,7 +304,7 @@
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
inode->i_ino = block;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
atomic_set(&AFFS_I(inode)->i_opencnt, 0);
AFFS_I(inode)->i_blkcnt = 0;
@@ -387,7 +387,7 @@
AFFS_TAIL(sb, inode_bh)->link_chain = cpu_to_be32(block);
affs_adjust_checksum(inode_bh, block - be32_to_cpu(chain));
mark_buffer_dirty_inode(inode_bh, inode);
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
ihold(inode);
}
affs_fix_checksum(sb, bh);
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index e3e9efc..780a11d 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -277,7 +277,7 @@
inode->i_mapping->a_ops = (AFFS_SB(sb)->s_flags & SF_OFS) ? &affs_aops_ofs : &affs_aops;
error = affs_add_entry(dir, inode, dentry, ST_FILE);
if (error) {
- inode->i_nlink = 0;
+ clear_nlink(inode);
iput(inode);
return error;
}
@@ -305,7 +305,7 @@
error = affs_add_entry(dir, inode, dentry, ST_USERDIR);
if (error) {
- inode->i_nlink = 0;
+ clear_nlink(inode);
mark_inode_dirty(inode);
iput(inode);
return error;
@@ -392,7 +392,7 @@
return 0;
err:
- inode->i_nlink = 0;
+ clear_nlink(inode);
mark_inode_dirty(inode);
iput(inode);
return error;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 346e328..2f213d1 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -90,7 +90,7 @@
vnode->vfs_inode.i_uid = status->owner;
vnode->vfs_inode.i_gid = status->group;
vnode->vfs_inode.i_generation = vnode->fid.unique;
- vnode->vfs_inode.i_nlink = status->nlink;
+ set_nlink(&vnode->vfs_inode, status->nlink);
mode = vnode->vfs_inode.i_mode;
mode &= ~S_IALLUGO;
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 0fdab6e..d890ae3 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -67,7 +67,7 @@
fscache_attr_changed(vnode->cache);
#endif
- inode->i_nlink = vnode->status.nlink;
+ set_nlink(inode, vnode->status.nlink);
inode->i_uid = vnode->status.owner;
inode->i_gid = 0;
inode->i_size = vnode->status.size;
@@ -174,7 +174,7 @@
inode->i_size = 0;
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
inode->i_op = &afs_autocell_inode_operations;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_uid = 0;
inode->i_gid = 0;
inode->i_ctime.tv_sec = get_seconds();
diff --git a/fs/aio.c b/fs/aio.c
index 632b235..78c514c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -440,8 +440,6 @@
static struct kiocb *__aio_get_req(struct kioctx *ctx)
{
struct kiocb *req = NULL;
- struct aio_ring *ring;
- int okay = 0;
req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL);
if (unlikely(!req))
@@ -459,39 +457,114 @@
INIT_LIST_HEAD(&req->ki_run_list);
req->ki_eventfd = NULL;
- /* Check if the completion queue has enough free space to
- * accept an event from this io.
- */
- spin_lock_irq(&ctx->ctx_lock);
- ring = kmap_atomic(ctx->ring_info.ring_pages[0], KM_USER0);
- if (ctx->reqs_active < aio_ring_avail(&ctx->ring_info, ring)) {
- list_add(&req->ki_list, &ctx->active_reqs);
- ctx->reqs_active++;
- okay = 1;
- }
- kunmap_atomic(ring, KM_USER0);
- spin_unlock_irq(&ctx->ctx_lock);
-
- if (!okay) {
- kmem_cache_free(kiocb_cachep, req);
- req = NULL;
- }
-
return req;
}
-static inline struct kiocb *aio_get_req(struct kioctx *ctx)
+/*
+ * struct kiocb's are allocated in batches to reduce the number of
+ * times the ctx lock is acquired and released.
+ */
+#define KIOCB_BATCH_SIZE 32L
+struct kiocb_batch {
+ struct list_head head;
+ long count; /* number of requests left to allocate */
+};
+
+static void kiocb_batch_init(struct kiocb_batch *batch, long total)
+{
+ INIT_LIST_HEAD(&batch->head);
+ batch->count = total;
+}
+
+static void kiocb_batch_free(struct kiocb_batch *batch)
+{
+ struct kiocb *req, *n;
+
+ list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
+ list_del(&req->ki_batch);
+ kmem_cache_free(kiocb_cachep, req);
+ }
+}
+
+/*
+ * Allocate a batch of kiocbs. This avoids taking and dropping the
+ * context lock a lot during setup.
+ */
+static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch)
+{
+ unsigned short allocated, to_alloc;
+ long avail;
+ bool called_fput = false;
+ struct kiocb *req, *n;
+ struct aio_ring *ring;
+
+ to_alloc = min(batch->count, KIOCB_BATCH_SIZE);
+ for (allocated = 0; allocated < to_alloc; allocated++) {
+ req = __aio_get_req(ctx);
+ if (!req)
+ /* allocation failed, go with what we've got */
+ break;
+ list_add(&req->ki_batch, &batch->head);
+ }
+
+ if (allocated == 0)
+ goto out;
+
+retry:
+ spin_lock_irq(&ctx->ctx_lock);
+ ring = kmap_atomic(ctx->ring_info.ring_pages[0]);
+
+ avail = aio_ring_avail(&ctx->ring_info, ring) - ctx->reqs_active;
+ BUG_ON(avail < 0);
+ if (avail == 0 && !called_fput) {
+ /*
+ * Handle a potential starvation case. It is possible that
+ * we hold the last reference on a struct file, causing us
+ * to delay the final fput to non-irq context. In this case,
+ * ctx->reqs_active is artificially high. Calling the fput
+ * routine here may free up a slot in the event completion
+ * ring, allowing this allocation to succeed.
+ */
+ kunmap_atomic(ring);
+ spin_unlock_irq(&ctx->ctx_lock);
+ aio_fput_routine(NULL);
+ called_fput = true;
+ goto retry;
+ }
+
+ if (avail < allocated) {
+ /* Trim back the number of requests. */
+ list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
+ list_del(&req->ki_batch);
+ kmem_cache_free(kiocb_cachep, req);
+ if (--allocated <= avail)
+ break;
+ }
+ }
+
+ batch->count -= allocated;
+ list_for_each_entry(req, &batch->head, ki_batch) {
+ list_add(&req->ki_list, &ctx->active_reqs);
+ ctx->reqs_active++;
+ }
+
+ kunmap_atomic(ring);
+ spin_unlock_irq(&ctx->ctx_lock);
+
+out:
+ return allocated;
+}
+
+static inline struct kiocb *aio_get_req(struct kioctx *ctx,
+ struct kiocb_batch *batch)
{
struct kiocb *req;
- /* Handle a potential starvation case -- should be exceedingly rare as
- * requests will be stuck on fput_head only if the aio_fput_routine is
- * delayed and the requests were the last user of the struct file.
- */
- req = __aio_get_req(ctx);
- if (unlikely(NULL == req)) {
- aio_fput_routine(NULL);
- req = __aio_get_req(ctx);
- }
+
+ if (list_empty(&batch->head))
+ if (kiocb_batch_refill(ctx, batch) == 0)
+ return NULL;
+ req = list_first_entry(&batch->head, struct kiocb, ki_batch);
+ list_del(&req->ki_batch);
return req;
}
@@ -1515,7 +1588,8 @@
}
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
- struct iocb *iocb, bool compat)
+ struct iocb *iocb, struct kiocb_batch *batch,
+ bool compat)
{
struct kiocb *req;
struct file *file;
@@ -1541,7 +1615,7 @@
if (unlikely(!file))
return -EBADF;
- req = aio_get_req(ctx); /* returns with 2 references to req */
+ req = aio_get_req(ctx, batch); /* returns with 2 references to req */
if (unlikely(!req)) {
fput(file);
return -EAGAIN;
@@ -1621,8 +1695,9 @@
{
struct kioctx *ctx;
long ret = 0;
- int i;
+ int i = 0;
struct blk_plug plug;
+ struct kiocb_batch batch;
if (unlikely(nr < 0))
return -EINVAL;
@@ -1639,6 +1714,8 @@
return -EINVAL;
}
+ kiocb_batch_init(&batch, nr);
+
blk_start_plug(&plug);
/*
@@ -1659,12 +1736,13 @@
break;
}
- ret = io_submit_one(ctx, user_iocb, &tmp, compat);
+ ret = io_submit_one(ctx, user_iocb, &tmp, &batch, compat);
if (ret)
break;
}
blk_finish_plug(&plug);
+ kiocb_batch_free(&batch);
put_ioctx(ctx);
return i ? i : ret;
}
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 180fa24..8179f1a 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -342,7 +342,7 @@
inode->i_ino = get_next_ino();
if (S_ISDIR(mode)) {
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_op = &autofs4_dir_inode_operations;
inode->i_fop = &autofs4_dir_operations;
} else if (S_ISLNK(mode)) {
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 720d885..8342ca6 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -357,7 +357,7 @@
inode->i_gid = befs_sb->mount_opts.use_gid ?
befs_sb->mount_opts.gid : (gid_t) fs32_to_cpu(sb, raw_inode->gid);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
/*
* BEFS's time is 64 bits, but current VFS is 32 bits...
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index b14cebf..9cc0740 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -199,7 +199,7 @@
printf("unlinking non-existent file %s:%lu (nlink=%d)\n",
inode->i_sb->s_id, inode->i_ino,
inode->i_nlink);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
de->ino = 0;
mark_buffer_dirty_inode(bh, dir);
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index a8e37f8..697af5b 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -78,7 +78,7 @@
BFS_I(inode)->i_dsk_ino = le16_to_cpu(di->i_ino);
inode->i_uid = le32_to_cpu(di->i_uid);
inode->i_gid = le32_to_cpu(di->i_gid);
- inode->i_nlink = le32_to_cpu(di->i_nlink);
+ set_nlink(inode, le32_to_cpu(di->i_nlink));
inode->i_size = BFS_FILESIZE(di);
inode->i_blocks = BFS_FILEBLOCKS(di);
inode->i_atime.tv_sec = le32_to_cpu(di->i_atime);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index dd0fdfc..21ac5ee 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -795,7 +795,16 @@
* might try to exec. This is because the brk will
* follow the loader, and is not movable. */
#if defined(CONFIG_X86) || defined(CONFIG_ARM)
- load_bias = 0;
+ /* Memory randomization might have been switched off
+ * in runtime via sysctl.
+ * If that is the case, retain the original non-zero
+ * load_bias value in order to establish proper
+ * non-randomized mappings.
+ */
+ if (current->flags & PF_RANDOMIZE)
+ load_bias = 0;
+ else
+ load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
#else
load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
#endif
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index ba1a1ae..1e9edbd 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -521,7 +521,7 @@
write_unlock(&entries_lock);
if (dentry) {
- dentry->d_inode->i_nlink--;
+ drop_nlink(dentry->d_inode);
d_drop(dentry);
dput(dentry);
simple_release_fs(&bm_mnt, &entry_count);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index b52c672..ae4d9cd 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1641,7 +1641,7 @@
inode->i_gid = btrfs_stack_inode_gid(inode_item);
btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item));
inode->i_mode = btrfs_stack_inode_mode(inode_item);
- inode->i_nlink = btrfs_stack_inode_nlink(inode_item);
+ set_nlink(inode, btrfs_stack_inode_nlink(inode_item));
inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item));
BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item);
BTRFS_I(inode)->sequence = btrfs_stack_inode_sequence(inode_item);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 07b3ac6..07ea918 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1705,7 +1705,7 @@
sb->s_bdi = &fs_info->bdi;
fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
- fs_info->btree_inode->i_nlink = 1;
+ set_nlink(fs_info->btree_inode, 1);
/*
* we set the i_size on the btree inode to the max possible int.
* the real end of the address space is determined by all of
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b2d004a..75686a6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2534,7 +2534,7 @@
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
inode->i_mode = btrfs_inode_mode(leaf, inode_item);
- inode->i_nlink = btrfs_inode_nlink(leaf, inode_item);
+ set_nlink(inode, btrfs_inode_nlink(leaf, inode_item));
inode->i_uid = btrfs_inode_uid(leaf, inode_item);
inode->i_gid = btrfs_inode_gid(leaf, inode_item);
btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
@@ -6728,7 +6728,7 @@
inode->i_op = &btrfs_dir_inode_operations;
inode->i_fop = &btrfs_dir_file_operations;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
btrfs_i_size_write(inode, 0);
err = btrfs_update_inode(trans, new_root, inode);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 786639f..0618aa3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1030,7 +1030,7 @@
}
btrfs_release_path(path);
if (nlink != inode->i_nlink) {
- inode->i_nlink = nlink;
+ set_nlink(inode, nlink);
btrfs_update_inode(trans, root, inode);
}
BTRFS_I(inode)->index_cnt = (u64)-1;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b8731bf..15b21e3 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2363,7 +2363,7 @@
}
if ((issued & CEPH_CAP_LINK_EXCL) == 0)
- inode->i_nlink = le32_to_cpu(grant->nlink);
+ set_nlink(inode, le32_to_cpu(grant->nlink));
if ((issued & CEPH_CAP_XATTR_EXCL) == 0 && grant->xattr_len) {
int len = le32_to_cpu(grant->xattr_len);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 5dde7d51..1616a0d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -618,7 +618,7 @@
}
if ((issued & CEPH_CAP_LINK_EXCL) == 0)
- inode->i_nlink = le32_to_cpu(info->nlink);
+ set_nlink(inode, le32_to_cpu(info->nlink));
/* be careful with mtime, atime, size */
ceph_decode_timespec(&atime, &info->atime);
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 2cfb695..5d9b9ac 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -204,7 +204,7 @@
}
/* first calculate 24 bytes ntlm response and then 16 byte session key */
-int setup_ntlm_response(struct cifs_ses *ses)
+int setup_ntlm_response(struct cifs_ses *ses, const struct nls_table *nls_cp)
{
int rc = 0;
unsigned int temp_len = CIFS_SESS_KEY_SIZE + CIFS_AUTH_RESP_SIZE;
@@ -221,14 +221,14 @@
ses->auth_key.len = temp_len;
rc = SMBNTencrypt(ses->password, ses->server->cryptkey,
- ses->auth_key.response + CIFS_SESS_KEY_SIZE);
+ ses->auth_key.response + CIFS_SESS_KEY_SIZE, nls_cp);
if (rc) {
cFYI(1, "%s Can't generate NTLM response, error: %d",
__func__, rc);
return rc;
}
- rc = E_md4hash(ses->password, temp_key);
+ rc = E_md4hash(ses->password, temp_key, nls_cp);
if (rc) {
cFYI(1, "%s Can't generate NT hash, error: %d", __func__, rc);
return rc;
@@ -404,7 +404,7 @@
}
/* calculate md4 hash of password */
- E_md4hash(ses->password, nt_hash);
+ E_md4hash(ses->password, nt_hash, nls_cp);
rc = crypto_shash_setkey(ses->server->secmech.hmacmd5, nt_hash,
CIFS_NTHASH_SIZE);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index d9dbaf8..30ff560 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -125,5 +125,5 @@
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "1.75"
+#define CIFS_VERSION "1.76"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index ef4f631..6f4e243 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -395,8 +395,9 @@
extern int cifs_verify_signature(struct kvec *iov, unsigned int nr_iov,
struct TCP_Server_Info *server,
__u32 expected_sequence_number);
-extern int SMBNTencrypt(unsigned char *, unsigned char *, unsigned char *);
-extern int setup_ntlm_response(struct cifs_ses *);
+extern int SMBNTencrypt(unsigned char *, unsigned char *, unsigned char *,
+ const struct nls_table *);
+extern int setup_ntlm_response(struct cifs_ses *, const struct nls_table *);
extern int setup_ntlmv2_rsp(struct cifs_ses *, const struct nls_table *);
extern int cifs_crypto_shash_allocate(struct TCP_Server_Info *);
extern void cifs_crypto_shash_release(struct TCP_Server_Info *);
@@ -448,7 +449,8 @@
const unsigned char *path,
struct cifs_sb_info *cifs_sb, int xid);
extern int mdfour(unsigned char *, unsigned char *, int);
-extern int E_md4hash(const unsigned char *passwd, unsigned char *p16);
+extern int E_md4hash(const unsigned char *passwd, unsigned char *p16,
+ const struct nls_table *codepage);
extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8,
unsigned char *p24);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d545a95..c0458c5 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3452,7 +3452,7 @@
else
#endif /* CIFS_WEAK_PW_HASH */
rc = SMBNTencrypt(tcon->password, ses->server->cryptkey,
- bcc_ptr);
+ bcc_ptr, nls_codepage);
bcc_ptr += CIFS_AUTH_RESP_SIZE;
if (ses->capabilities & CAP_UNICODE) {
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index ea096ce..c1f063c 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -778,7 +778,6 @@
else {
mutex_lock(&cinode->lock_mutex);
list_del_init(&lock->blist);
- mutex_unlock(&cinode->lock_mutex);
}
}
@@ -794,6 +793,9 @@
struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode);
unsigned char saved_type = flock->fl_type;
+ if ((flock->fl_flags & FL_POSIX) == 0)
+ return 1;
+
mutex_lock(&cinode->lock_mutex);
posix_test_lock(file, flock);
@@ -810,12 +812,15 @@
cifs_posix_lock_set(struct file *file, struct file_lock *flock)
{
struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode);
- int rc;
+ int rc = 1;
+
+ if ((flock->fl_flags & FL_POSIX) == 0)
+ return rc;
mutex_lock(&cinode->lock_mutex);
if (!cinode->can_cache_brlcks) {
mutex_unlock(&cinode->lock_mutex);
- return 1;
+ return rc;
}
rc = posix_lock_file_wait(file, flock);
mutex_unlock(&cinode->lock_mutex);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 2c50bd2..e851d5b 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -132,7 +132,7 @@
inode->i_mtime = fattr->cf_mtime;
inode->i_ctime = fattr->cf_ctime;
inode->i_rdev = fattr->cf_rdev;
- inode->i_nlink = fattr->cf_nlink;
+ set_nlink(inode, fattr->cf_nlink);
inode->i_uid = fattr->cf_uid;
inode->i_gid = fattr->cf_gid;
@@ -905,7 +905,7 @@
if (rc && tcon->ipc) {
cFYI(1, "ipc connection - fake read inode");
inode->i_mode |= S_IFDIR;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_op = &cifs_ipc_inode_ops;
inode->i_fop = &simple_dir_operations;
inode->i_uid = cifs_sb->mnt_uid;
@@ -1367,7 +1367,7 @@
/* setting nlink not necessary except in cases where we
* failed to get it from the server or was set bogus */
if ((direntry->d_inode) && (direntry->d_inode->i_nlink < 2))
- direntry->d_inode->i_nlink = 2;
+ set_nlink(direntry->d_inode, 2);
mode &= ~current_umask();
/* must turn on setgid bit if parent dir has it */
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 8693b5d..6b0e064 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -433,7 +433,7 @@
if (old_file->d_inode) {
cifsInode = CIFS_I(old_file->d_inode);
if (rc == 0) {
- old_file->d_inode->i_nlink++;
+ inc_nlink(old_file->d_inode);
/* BB should we make this contingent on superblock flag NOATIME? */
/* old_file->d_inode->i_ctime = CURRENT_TIME;*/
/* parent dir timestamps will update from srv
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index c7d80e2..4ec3ee9 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -683,7 +683,7 @@
cpu_to_le16(CIFS_AUTH_RESP_SIZE);
/* calculate ntlm response and session key */
- rc = setup_ntlm_response(ses);
+ rc = setup_ntlm_response(ses, nls_cp);
if (rc) {
cERROR(1, "Error %d during NTLM authentication", rc);
goto ssetup_exit;
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index ac1221d..7cacba1 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -199,75 +199,36 @@
return rc;
}
-/* Routines for Windows NT MD4 Hash functions. */
-static int
-_my_wcslen(__u16 *str)
-{
- int len = 0;
- while (*str++ != 0)
- len++;
- return len;
-}
-
-/*
- * Convert a string into an NT UNICODE string.
- * Note that regardless of processor type
- * this must be in intel (little-endian)
- * format.
- */
-
-static int
-_my_mbstowcs(__u16 *dst, const unsigned char *src, int len)
-{ /* BB not a very good conversion routine - change/fix */
- int i;
- __u16 val;
-
- for (i = 0; i < len; i++) {
- val = *src;
- SSVAL(dst, 0, val);
- dst++;
- src++;
- if (val == 0)
- break;
- }
- return i;
-}
-
/*
* Creates the MD4 Hash of the users password in NT UNICODE.
*/
int
-E_md4hash(const unsigned char *passwd, unsigned char *p16)
+E_md4hash(const unsigned char *passwd, unsigned char *p16,
+ const struct nls_table *codepage)
{
int rc;
int len;
__u16 wpwd[129];
/* Password cannot be longer than 128 characters */
- if (passwd) {
- len = strlen((char *) passwd);
- if (len > 128)
- len = 128;
-
- /* Password must be converted to NT unicode */
- _my_mbstowcs(wpwd, passwd, len);
- } else
+ if (passwd) /* Password must be converted to NT unicode */
+ len = cifs_strtoUCS(wpwd, passwd, 128, codepage);
+ else {
len = 0;
+ *wpwd = 0; /* Ensure string is null terminated */
+ }
- wpwd[len] = 0; /* Ensure string is null terminated */
- /* Calculate length in bytes */
- len = _my_wcslen(wpwd) * sizeof(__u16);
-
- rc = mdfour(p16, (unsigned char *) wpwd, len);
- memset(wpwd, 0, 129 * 2);
+ rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__u16));
+ memset(wpwd, 0, 129 * sizeof(__u16));
return rc;
}
/* Does the NT MD4 hash then des encryption. */
int
-SMBNTencrypt(unsigned char *passwd, unsigned char *c8, unsigned char *p24)
+SMBNTencrypt(unsigned char *passwd, unsigned char *c8, unsigned char *p24,
+ const struct nls_table *codepage)
{
int rc;
unsigned char p16[16], p21[21];
@@ -275,7 +236,7 @@
memset(p16, '\0', 16);
memset(p21, '\0', 21);
- rc = E_md4hash(passwd, p16);
+ rc = E_md4hash(passwd, p16, codepage);
if (rc) {
cFYI(1, "%s Can't generate NT hash, error: %d", __func__, rc);
return rc;
diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c
index 2bdbcc1..854ace7 100644
--- a/fs/coda/coda_linux.c
+++ b/fs/coda/coda_linux.c
@@ -104,7 +104,7 @@
if (attr->va_gid != -1)
inode->i_gid = (gid_t) attr->va_gid;
if (attr->va_nlink != -1)
- inode->i_nlink = attr->va_nlink;
+ set_nlink(inode, attr->va_nlink);
if (attr->va_size != -1)
inode->i_size = attr->va_size;
if (attr->va_size != -1)
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 0239433..28e7e13 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -340,7 +340,7 @@
if (!error) {
/* VFS may delete the child */
if (de->d_inode)
- de->d_inode->i_nlink = 0;
+ clear_nlink(de->d_inode);
/* fix the link count of the parent */
coda_dir_drop_nlink(dir);
diff --git a/fs/dcache.c b/fs/dcache.c
index a88948b..274f13e 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -225,7 +225,7 @@
}
/*
- * dentry_lru_(add|del|move_tail) must be called with d_lock held.
+ * dentry_lru_(add|del|prune|move_tail) must be called with d_lock held.
*/
static void dentry_lru_add(struct dentry *dentry)
{
@@ -245,6 +245,9 @@
dentry_stat.nr_unused--;
}
+/*
+ * Remove a dentry with references from the LRU.
+ */
static void dentry_lru_del(struct dentry *dentry)
{
if (!list_empty(&dentry->d_lru)) {
@@ -254,6 +257,23 @@
}
}
+/*
+ * Remove a dentry that is unreferenced and about to be pruned
+ * (unhashed and destroyed) from the LRU, and inform the file system.
+ * This wrapper should be called _prior_ to unhashing a victim dentry.
+ */
+static void dentry_lru_prune(struct dentry *dentry)
+{
+ if (!list_empty(&dentry->d_lru)) {
+ if (dentry->d_flags & DCACHE_OP_PRUNE)
+ dentry->d_op->d_prune(dentry);
+
+ spin_lock(&dcache_lru_lock);
+ __dentry_lru_del(dentry);
+ spin_unlock(&dcache_lru_lock);
+ }
+}
+
static void dentry_lru_move_tail(struct dentry *dentry)
{
spin_lock(&dcache_lru_lock);
@@ -403,8 +423,12 @@
if (ref)
dentry->d_count--;
- /* if dentry was on the d_lru list delete it from there */
- dentry_lru_del(dentry);
+ /*
+ * if dentry was on the d_lru list delete it from there.
+ * inform the fs via d_prune that this dentry is about to be
+ * unhashed and destroyed.
+ */
+ dentry_lru_prune(dentry);
/* if it was on the hash then remove it */
__d_drop(dentry);
return d_kill(dentry, parent);
@@ -854,8 +878,12 @@
do {
struct inode *inode;
- /* detach from the system */
- dentry_lru_del(dentry);
+ /*
+ * remove the dentry from the lru, and inform
+ * the fs that this dentry is about to be
+ * unhashed and destroyed.
+ */
+ dentry_lru_prune(dentry);
__d_shrink(dentry);
if (dentry->d_count != 0) {
@@ -1283,6 +1311,8 @@
dentry->d_flags |= DCACHE_OP_REVALIDATE;
if (op->d_delete)
dentry->d_flags |= DCACHE_OP_DELETE;
+ if (op->d_prune)
+ dentry->d_flags |= DCACHE_OP_PRUNE;
}
EXPORT_SYMBOL(d_set_d_op);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 2f27e57..d5d5297 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -307,7 +307,7 @@
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR;
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
s->s_root = d_alloc_root(inode);
if (s->s_root)
@@ -549,7 +549,7 @@
dentry = d_find_alias(inode);
- inode->i_nlink--;
+ drop_nlink(inode);
d_delete(dentry);
dput(dentry); /* d_alloc_name() in devpts_pty_new() */
dput(dentry); /* d_find_alias above */
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 11f8582..a36d327 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -474,8 +474,8 @@
goto out_lock;
fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
- old_dentry->d_inode->i_nlink =
- ecryptfs_inode_to_lower(old_dentry->d_inode)->i_nlink;
+ set_nlink(old_dentry->d_inode,
+ ecryptfs_inode_to_lower(old_dentry->d_inode)->i_nlink);
i_size_write(new_dentry->d_inode, file_size_save);
out_lock:
unlock_dir(lower_dir_dentry);
@@ -499,8 +499,8 @@
goto out_unlock;
}
fsstack_copy_attr_times(dir, lower_dir_inode);
- dentry->d_inode->i_nlink =
- ecryptfs_inode_to_lower(dentry->d_inode)->i_nlink;
+ set_nlink(dentry->d_inode,
+ ecryptfs_inode_to_lower(dentry->d_inode)->i_nlink);
dentry->d_inode->i_ctime = dir->i_ctime;
d_drop(dentry);
out_unlock:
@@ -565,7 +565,7 @@
goto out;
fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
- dir->i_nlink = lower_dir_dentry->d_inode->i_nlink;
+ set_nlink(dir, lower_dir_dentry->d_inode->i_nlink);
out:
unlock_dir(lower_dir_dentry);
if (!dentry->d_inode)
@@ -588,7 +588,7 @@
if (!rc && dentry->d_inode)
clear_nlink(dentry->d_inode);
fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
- dir->i_nlink = lower_dir_dentry->d_inode->i_nlink;
+ set_nlink(dir, lower_dir_dentry->d_inode->i_nlink);
unlock_dir(lower_dir_dentry);
if (!rc)
d_drop(dentry);
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
index 9c13412..bc84f36 100644
--- a/fs/efs/inode.c
+++ b/fs/efs/inode.c
@@ -96,7 +96,7 @@
efs_inode = (struct efs_dinode *) (bh->b_data + offset);
inode->i_mode = be16_to_cpu(efs_inode->di_mode);
- inode->i_nlink = be16_to_cpu(efs_inode->di_nlink);
+ set_nlink(inode, be16_to_cpu(efs_inode->di_nlink));
inode->i_uid = (uid_t)be16_to_cpu(efs_inode->di_uid);
inode->i_gid = (gid_t)be16_to_cpu(efs_inode->di_gid);
inode->i_size = be32_to_cpu(efs_inode->di_size);
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 3e5f3a6..f6dbf77 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1165,7 +1165,7 @@
inode->i_mode = le16_to_cpu(fcb.i_mode);
inode->i_uid = le32_to_cpu(fcb.i_uid);
inode->i_gid = le32_to_cpu(fcb.i_gid);
- inode->i_nlink = le16_to_cpu(fcb.i_links_count);
+ set_nlink(inode, le16_to_cpu(fcb.i_links_count));
inode->i_ctime.tv_sec = (signed)le32_to_cpu(fcb.i_ctime);
inode->i_atime.tv_sec = (signed)le32_to_cpu(fcb.i_atime);
inode->i_mtime.tv_sec = (signed)le32_to_cpu(fcb.i_mtime);
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 8f44cef..a8cbe1b 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -421,7 +421,7 @@
void ext2_init_block_alloc_info(struct inode *inode)
{
struct ext2_inode_info *ei = EXT2_I(inode);
- struct ext2_block_alloc_info *block_i = ei->i_block_alloc_info;
+ struct ext2_block_alloc_info *block_i;
struct super_block *sb = inode->i_sb;
block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index ee9ed31..c4e81df 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -601,7 +601,7 @@
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
return ERR_PTR(err);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index a8a58f6..91a6945 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1321,7 +1321,7 @@
inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
- inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+ set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
inode->i_size = le32_to_cpu(raw_inode->i_size);
inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 1dd62ed..bd8ac16 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -327,10 +327,10 @@
if (ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count))
return ERR_PTR(-ESTALE);
- /* iget isn't really right if the inode is currently unallocated!!
- * ext2_read_inode currently does appropriate checks, but
- * it might be "neater" to call ext2_get_inode first and check
- * if the inode is valid.....
+ /*
+ * ext2_iget isn't quite right if the inode is currently unallocated!
+ * However ext2_iget currently does appropriate checks to handle stale
+ * inodes so everything is OK.
*/
inode = ext2_iget(sb, ino);
if (IS_ERR(inode))
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 6386d76..a203892 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -427,7 +427,7 @@
void ext3_init_block_alloc_info(struct inode *inode)
{
struct ext3_inode_info *ei = EXT3_I(inode);
- struct ext3_block_alloc_info *block_i = ei->i_block_alloc_info;
+ struct ext3_block_alloc_info *block_i;
struct super_block *sb = inode->i_sb;
block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
@@ -1440,14 +1440,14 @@
*
* Check if filesystem has at least 1 free block available for allocation.
*/
-static int ext3_has_free_blocks(struct ext3_sb_info *sbi)
+static int ext3_has_free_blocks(struct ext3_sb_info *sbi, int use_reservation)
{
ext3_fsblk_t free_blocks, root_blocks;
free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
- sbi->s_resuid != current_fsuid() &&
+ !use_reservation && sbi->s_resuid != current_fsuid() &&
(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
return 0;
}
@@ -1468,7 +1468,7 @@
*/
int ext3_should_retry_alloc(struct super_block *sb, int *retries)
{
- if (!ext3_has_free_blocks(EXT3_SB(sb)) || (*retries)++ > 3)
+ if (!ext3_has_free_blocks(EXT3_SB(sb), 0) || (*retries)++ > 3)
return 0;
jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
@@ -1546,7 +1546,7 @@
if (block_i && ((windowsz = block_i->rsv_window_node.rsv_goal_size) > 0))
my_rsv = &block_i->rsv_window_node;
- if (!ext3_has_free_blocks(sbi)) {
+ if (!ext3_has_free_blocks(sbi, IS_NOQUOTA(inode))) {
*errp = -ENOSPC;
goto out;
}
@@ -1924,9 +1924,10 @@
* reaches any used block. Then issue a TRIM command on this extent and free
* the extent in the block bitmap. This is done until whole group is scanned.
*/
-ext3_grpblk_t ext3_trim_all_free(struct super_block *sb, unsigned int group,
- ext3_grpblk_t start, ext3_grpblk_t max,
- ext3_grpblk_t minblocks)
+static ext3_grpblk_t ext3_trim_all_free(struct super_block *sb,
+ unsigned int group,
+ ext3_grpblk_t start, ext3_grpblk_t max,
+ ext3_grpblk_t minblocks)
{
handle_t *handle;
ext3_grpblk_t next, free_blocks, bit, freed, count = 0;
diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c
index d494c55..1860ed3 100644
--- a/fs/ext3/fsync.c
+++ b/fs/ext3/fsync.c
@@ -61,13 +61,6 @@
if (ret)
goto out;
- /*
- * Taking the mutex here just to keep consistent with how fsync was
- * called previously, however it looks like we don't need to take
- * i_mutex at all.
- */
- mutex_lock(&inode->i_mutex);
-
J_ASSERT(ext3_journal_current_handle() == NULL);
/*
@@ -85,7 +78,6 @@
* safe in-journal, which is all fsync() needs to ensure.
*/
if (ext3_should_journal_data(inode)) {
- mutex_unlock(&inode->i_mutex);
ret = ext3_force_commit(inode->i_sb);
goto out;
}
@@ -108,8 +100,6 @@
*/
if (needs_barrier)
blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
-
- mutex_unlock(&inode->i_mutex);
out:
trace_ext3_sync_file_exit(inode, ret);
return ret;
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index bf09cbf..5c866e0 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -178,42 +178,6 @@
}
/*
- * There are two policies for allocating an inode. If the new inode is
- * a directory, then a forward search is made for a block group with both
- * free space and a low directory-to-inode ratio; if that fails, then of
- * the groups with above-average free space, that group with the fewest
- * directories already is chosen.
- *
- * For other inodes, search forward from the parent directory\'s block
- * group to find a free inode.
- */
-static int find_group_dir(struct super_block *sb, struct inode *parent)
-{
- int ngroups = EXT3_SB(sb)->s_groups_count;
- unsigned int freei, avefreei;
- struct ext3_group_desc *desc, *best_desc = NULL;
- int group, best_group = -1;
-
- freei = percpu_counter_read_positive(&EXT3_SB(sb)->s_freeinodes_counter);
- avefreei = freei / ngroups;
-
- for (group = 0; group < ngroups; group++) {
- desc = ext3_get_group_desc (sb, group, NULL);
- if (!desc || !desc->bg_free_inodes_count)
- continue;
- if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
- continue;
- if (!best_desc ||
- (le16_to_cpu(desc->bg_free_blocks_count) >
- le16_to_cpu(best_desc->bg_free_blocks_count))) {
- best_group = group;
- best_desc = desc;
- }
- }
- return best_group;
-}
-
-/*
* Orlov's allocator for directories.
*
* We always try to spread first-level directories.
@@ -436,12 +400,9 @@
sbi = EXT3_SB(sb);
es = sbi->s_es;
- if (S_ISDIR(mode)) {
- if (test_opt (sb, OLDALLOC))
- group = find_group_dir(sb, dir);
- else
- group = find_group_orlov(sb, dir);
- } else
+ if (S_ISDIR(mode))
+ group = find_group_orlov(sb, dir);
+ else
group = find_group_other(sb, dir);
err = -ENOSPC;
@@ -621,7 +582,7 @@
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
brelse(bitmap_bh);
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 12661e1..85fe655 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -2899,7 +2899,7 @@
inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
- inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+ set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
inode->i_size = le32_to_cpu(raw_inode->i_size);
inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index c7f4394..ba1b54e 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -150,30 +150,6 @@
mnt_drop_write(filp->f_path.mnt);
return err;
}
-#ifdef CONFIG_JBD_DEBUG
- case EXT3_IOC_WAIT_FOR_READONLY:
- /*
- * This is racy - by the time we're woken up and running,
- * the superblock could be released. And the module could
- * have been unloaded. So sue me.
- *
- * Returns 1 if it slept, else zero.
- */
- {
- struct super_block *sb = inode->i_sb;
- DECLARE_WAITQUEUE(wait, current);
- int ret = 0;
-
- set_current_state(TASK_INTERRUPTIBLE);
- add_wait_queue(&EXT3_SB(sb)->ro_wait_queue, &wait);
- if (timer_pending(&EXT3_SB(sb)->turn_ro_timer)) {
- schedule();
- ret = 1;
- }
- remove_wait_queue(&EXT3_SB(sb)->ro_wait_queue, &wait);
- return ret;
- }
-#endif
case EXT3_IOC_GETRSVSZ:
if (test_opt(inode->i_sb, RESERVATION)
&& S_ISREG(inode->i_mode)
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 0629e09..642dc6d 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1821,7 +1821,7 @@
de->name_len = 2;
strcpy (de->name, "..");
ext3_set_de_type(dir->i_sb, de, S_IFDIR);
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
BUFFER_TRACE(dir_block, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, dir_block);
if (err)
@@ -1833,7 +1833,7 @@
if (err) {
out_clear_inode:
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
ext3_mark_inode_dirty(handle, inode);
iput (inode);
@@ -2170,7 +2170,7 @@
ext3_warning (inode->i_sb, "ext3_unlink",
"Deleting nonexistent file (%lu), %d",
inode->i_ino, inode->i_nlink);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
retval = ext3_delete_entry(handle, dir, de, bh);
if (retval)
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 7beb69a..922d289 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -652,8 +652,6 @@
seq_puts(seq, ",nouid32");
if (test_opt(sb, DEBUG))
seq_puts(seq, ",debug");
- if (test_opt(sb, OLDALLOC))
- seq_puts(seq, ",oldalloc");
#ifdef CONFIG_EXT3_FS_XATTR
if (test_opt(sb, XATTR_USER))
seq_puts(seq, ",user_xattr");
@@ -1049,10 +1047,12 @@
set_opt (sbi->s_mount_opt, DEBUG);
break;
case Opt_oldalloc:
- set_opt (sbi->s_mount_opt, OLDALLOC);
+ ext3_msg(sb, KERN_WARNING,
+ "Ignoring deprecated oldalloc option");
break;
case Opt_orlov:
- clear_opt (sbi->s_mount_opt, OLDALLOC);
+ ext3_msg(sb, KERN_WARNING,
+ "Ignoring deprecated orlov option");
break;
#ifdef CONFIG_EXT3_FS_XATTR
case Opt_user_xattr:
@@ -2669,13 +2669,13 @@
/*
* If we have an unprocessed orphan list hanging
* around from a previously readonly bdev mount,
- * require a full umount/remount for now.
+ * require a full umount & mount for now.
*/
if (es->s_last_orphan) {
ext3_msg(sb, KERN_WARNING, "warning: couldn't "
"remount RDWR because of unprocessed "
"orphan inode list. Please "
- "umount/remount instead.");
+ "umount & mount instead.");
err = -EINVAL;
goto restore_opts;
}
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f8224ad..f6dba45 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -28,7 +28,8 @@
*/
/*
- * Calculate the block group number and offset, given a block number
+ * Calculate the block group number and offset into the block/cluster
+ * allocation bitmap, given a block number
*/
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
@@ -37,7 +38,8 @@
ext4_grpblk_t offset;
blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
- offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb));
+ offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)) >>
+ EXT4_SB(sb)->s_cluster_bits;
if (offsetp)
*offsetp = offset;
if (blockgrpp)
@@ -55,131 +57,170 @@
return 0;
}
-static int ext4_group_used_meta_blocks(struct super_block *sb,
+/* Return the number of clusters used for file system metadata; this
+ * represents the overhead needed by the file system.
+ */
+unsigned ext4_num_overhead_clusters(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
+{
+ unsigned num_clusters;
+ int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
+ ext4_fsblk_t start = ext4_group_first_block_no(sb, block_group);
+ ext4_fsblk_t itbl_blk;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ /* This is the number of clusters used by the superblock,
+ * block group descriptors, and reserved block group
+ * descriptor blocks */
+ num_clusters = ext4_num_base_meta_clusters(sb, block_group);
+
+ /*
+ * For the allocation bitmaps and inode table, we first need
+ * to check to see if the block is in the block group. If it
+ * is, then check to see if the cluster is already accounted
+ * for in the clusters used for the base metadata cluster, or
+ * if we can increment the base metadata cluster to include
+ * that block. Otherwise, we will have to track the cluster
+ * used for the allocation bitmap or inode table explicitly.
+ * Normally all of these blocks are contiguous, so the special
+ * case handling shouldn't be necessary except for *very*
+ * unusual file system layouts.
+ */
+ if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) {
+ block_cluster = EXT4_B2C(sbi, (start -
+ ext4_block_bitmap(sb, gdp)));
+ if (block_cluster < num_clusters)
+ block_cluster = -1;
+ else if (block_cluster == num_clusters) {
+ num_clusters++;
+ block_cluster = -1;
+ }
+ }
+
+ if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) {
+ inode_cluster = EXT4_B2C(sbi,
+ start - ext4_inode_bitmap(sb, gdp));
+ if (inode_cluster < num_clusters)
+ inode_cluster = -1;
+ else if (inode_cluster == num_clusters) {
+ num_clusters++;
+ inode_cluster = -1;
+ }
+ }
+
+ itbl_blk = ext4_inode_table(sb, gdp);
+ for (i = 0; i < sbi->s_itb_per_group; i++) {
+ if (ext4_block_in_group(sb, itbl_blk + i, block_group)) {
+ c = EXT4_B2C(sbi, start - itbl_blk + i);
+ if ((c < num_clusters) || (c == inode_cluster) ||
+ (c == block_cluster) || (c == itbl_cluster))
+ continue;
+ if (c == num_clusters) {
+ num_clusters++;
+ continue;
+ }
+ num_clusters++;
+ itbl_cluster = c;
+ }
+ }
+
+ if (block_cluster != -1)
+ num_clusters++;
+ if (inode_cluster != -1)
+ num_clusters++;
+
+ return num_clusters;
+}
+
+static unsigned int num_clusters_in_group(struct super_block *sb,
+ ext4_group_t block_group)
+{
+ unsigned int blocks;
+
+ if (block_group == ext4_get_groups_count(sb) - 1) {
+ /*
+ * Even though mke2fs always initializes the first and
+ * last group, just in case some other tool was used,
+ * we need to make sure we calculate the right free
+ * blocks.
+ */
+ blocks = ext4_blocks_count(EXT4_SB(sb)->s_es) -
+ ext4_group_first_block_no(sb, block_group);
+ } else
+ blocks = EXT4_BLOCKS_PER_GROUP(sb);
+ return EXT4_NUM_B2C(EXT4_SB(sb), blocks);
+}
+
+/* Initializes an uninitialized block bitmap */
+void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
+{
+ unsigned int bit, bit_max;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_fsblk_t start, tmp;
+ int flex_bg = 0;
+
+ J_ASSERT_BH(bh, buffer_locked(bh));
+
+ /* If checksum is bad mark all blocks used to prevent allocation
+ * essentially implementing a per-group read-only flag. */
+ if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
+ ext4_error(sb, "Checksum bad for group %u", block_group);
+ ext4_free_group_clusters_set(sb, gdp, 0);
+ ext4_free_inodes_set(sb, gdp, 0);
+ ext4_itable_unused_set(sb, gdp, 0);
+ memset(bh->b_data, 0xff, sb->s_blocksize);
+ return;
+ }
+ memset(bh->b_data, 0, sb->s_blocksize);
+
+ bit_max = ext4_num_base_meta_clusters(sb, block_group);
+ for (bit = 0; bit < bit_max; bit++)
+ ext4_set_bit(bit, bh->b_data);
+
+ start = ext4_group_first_block_no(sb, block_group);
+
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+ flex_bg = 1;
+
+ /* Set bits for block and inode bitmaps, and inode table */
+ tmp = ext4_block_bitmap(sb, gdp);
+ if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
+
+ tmp = ext4_inode_bitmap(sb, gdp);
+ if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
+
+ tmp = ext4_inode_table(sb, gdp);
+ for (; tmp < ext4_inode_table(sb, gdp) +
+ sbi->s_itb_per_group; tmp++) {
+ if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
+ }
+
+ /*
+ * Also if the number of blocks within the group is less than
+ * the blocksize * 8 ( which is the size of bitmap ), set rest
+ * of the block bitmap to 1
+ */
+ ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group),
+ sb->s_blocksize * 8, bh->b_data);
+}
+
+/* Return the number of free blocks in a block group. It is used when
+ * the block bitmap is uninitialized, so we can't just count the bits
+ * in the bitmap. */
+unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp)
{
- ext4_fsblk_t tmp;
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- /* block bitmap, inode bitmap, and inode table blocks */
- int used_blocks = sbi->s_itb_per_group + 2;
-
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
- if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp),
- block_group))
- used_blocks--;
-
- if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp),
- block_group))
- used_blocks--;
-
- tmp = ext4_inode_table(sb, gdp);
- for (; tmp < ext4_inode_table(sb, gdp) +
- sbi->s_itb_per_group; tmp++) {
- if (!ext4_block_in_group(sb, tmp, block_group))
- used_blocks -= 1;
- }
- }
- return used_blocks;
+ return num_clusters_in_group(sb, block_group) -
+ ext4_num_overhead_clusters(sb, block_group, gdp);
}
-/* Initializes an uninitialized block bitmap if given, and returns the
- * number of blocks free in the group. */
-unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
- ext4_group_t block_group, struct ext4_group_desc *gdp)
-{
- int bit, bit_max;
- ext4_group_t ngroups = ext4_get_groups_count(sb);
- unsigned free_blocks, group_blocks;
- struct ext4_sb_info *sbi = EXT4_SB(sb);
-
- if (bh) {
- J_ASSERT_BH(bh, buffer_locked(bh));
-
- /* If checksum is bad mark all blocks used to prevent allocation
- * essentially implementing a per-group read-only flag. */
- if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
- ext4_error(sb, "Checksum bad for group %u",
- block_group);
- ext4_free_blks_set(sb, gdp, 0);
- ext4_free_inodes_set(sb, gdp, 0);
- ext4_itable_unused_set(sb, gdp, 0);
- memset(bh->b_data, 0xff, sb->s_blocksize);
- return 0;
- }
- memset(bh->b_data, 0, sb->s_blocksize);
- }
-
- /* Check for superblock and gdt backups in this group */
- bit_max = ext4_bg_has_super(sb, block_group);
-
- if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
- block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
- sbi->s_desc_per_block) {
- if (bit_max) {
- bit_max += ext4_bg_num_gdb(sb, block_group);
- bit_max +=
- le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
- }
- } else { /* For META_BG_BLOCK_GROUPS */
- bit_max += ext4_bg_num_gdb(sb, block_group);
- }
-
- if (block_group == ngroups - 1) {
- /*
- * Even though mke2fs always initialize first and last group
- * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
- * to make sure we calculate the right free blocks
- */
- group_blocks = ext4_blocks_count(sbi->s_es) -
- ext4_group_first_block_no(sb, ngroups - 1);
- } else {
- group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
- }
-
- free_blocks = group_blocks - bit_max;
-
- if (bh) {
- ext4_fsblk_t start, tmp;
- int flex_bg = 0;
-
- for (bit = 0; bit < bit_max; bit++)
- ext4_set_bit(bit, bh->b_data);
-
- start = ext4_group_first_block_no(sb, block_group);
-
- if (EXT4_HAS_INCOMPAT_FEATURE(sb,
- EXT4_FEATURE_INCOMPAT_FLEX_BG))
- flex_bg = 1;
-
- /* Set bits for block and inode bitmaps, and inode table */
- tmp = ext4_block_bitmap(sb, gdp);
- if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
- ext4_set_bit(tmp - start, bh->b_data);
-
- tmp = ext4_inode_bitmap(sb, gdp);
- if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
- ext4_set_bit(tmp - start, bh->b_data);
-
- tmp = ext4_inode_table(sb, gdp);
- for (; tmp < ext4_inode_table(sb, gdp) +
- sbi->s_itb_per_group; tmp++) {
- if (!flex_bg ||
- ext4_block_in_group(sb, tmp, block_group))
- ext4_set_bit(tmp - start, bh->b_data);
- }
- /*
- * Also if the number of blocks within the group is
- * less than the blocksize * 8 ( which is the size
- * of bitmap ), set rest of the block bitmap to 1
- */
- ext4_mark_bitmap_end(group_blocks, sb->s_blocksize * 8,
- bh->b_data);
- }
- return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
-}
-
-
/*
* The free blocks are managed by bitmaps. A file system contains several
* blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap
@@ -362,53 +403,54 @@
}
/**
- * ext4_has_free_blocks()
+ * ext4_has_free_clusters()
* @sbi: in-core super block structure.
- * @nblocks: number of needed blocks
+ * @nclusters: number of needed blocks
+ * @flags: flags from ext4_mb_new_blocks()
*
- * Check if filesystem has nblocks free & available for allocation.
+ * Check if filesystem has nclusters free & available for allocation.
* On success return 1, return 0 on failure.
*/
-static int ext4_has_free_blocks(struct ext4_sb_info *sbi,
- s64 nblocks, unsigned int flags)
+static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
+ s64 nclusters, unsigned int flags)
{
- s64 free_blocks, dirty_blocks, root_blocks;
- struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
- struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
+ s64 free_clusters, dirty_clusters, root_clusters;
+ struct percpu_counter *fcc = &sbi->s_freeclusters_counter;
+ struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter;
- free_blocks = percpu_counter_read_positive(fbc);
- dirty_blocks = percpu_counter_read_positive(dbc);
- root_blocks = ext4_r_blocks_count(sbi->s_es);
+ free_clusters = percpu_counter_read_positive(fcc);
+ dirty_clusters = percpu_counter_read_positive(dcc);
+ root_clusters = EXT4_B2C(sbi, ext4_r_blocks_count(sbi->s_es));
- if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
- EXT4_FREEBLOCKS_WATERMARK) {
- free_blocks = percpu_counter_sum_positive(fbc);
- dirty_blocks = percpu_counter_sum_positive(dbc);
+ if (free_clusters - (nclusters + root_clusters + dirty_clusters) <
+ EXT4_FREECLUSTERS_WATERMARK) {
+ free_clusters = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc));
+ dirty_clusters = percpu_counter_sum_positive(dcc);
}
- /* Check whether we have space after
- * accounting for current dirty blocks & root reserved blocks.
+ /* Check whether we have space after accounting for current
+ * dirty clusters & root reserved clusters.
*/
- if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks))
+ if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters))
return 1;
- /* Hm, nope. Are (enough) root reserved blocks available? */
+ /* Hm, nope. Are (enough) root reserved clusters available? */
if (sbi->s_resuid == current_fsuid() ||
((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
capable(CAP_SYS_RESOURCE) ||
(flags & EXT4_MB_USE_ROOT_BLOCKS)) {
- if (free_blocks >= (nblocks + dirty_blocks))
+ if (free_clusters >= (nclusters + dirty_clusters))
return 1;
}
return 0;
}
-int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
- s64 nblocks, unsigned int flags)
+int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
+ s64 nclusters, unsigned int flags)
{
- if (ext4_has_free_blocks(sbi, nblocks, flags)) {
- percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks);
+ if (ext4_has_free_clusters(sbi, nclusters, flags)) {
+ percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters);
return 0;
} else
return -ENOSPC;
@@ -428,7 +470,7 @@
*/
int ext4_should_retry_alloc(struct super_block *sb, int *retries)
{
- if (!ext4_has_free_blocks(EXT4_SB(sb), 1, 0) ||
+ if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
(*retries)++ > 3 ||
!EXT4_SB(sb)->s_journal)
return 0;
@@ -444,7 +486,7 @@
* @handle: handle to this transaction
* @inode: file inode
* @goal: given target block(filesystem wide)
- * @count: pointer to total number of blocks needed
+ * @count: pointer to total number of clusters needed
* @errp: error code
*
* Return 1st allocated block number on success, *count stores total account
@@ -476,18 +518,19 @@
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- dquot_alloc_block_nofail(inode, ar.len);
+ dquot_alloc_block_nofail(inode,
+ EXT4_C2B(EXT4_SB(inode->i_sb), ar.len));
}
return ret;
}
/**
- * ext4_count_free_blocks() -- count filesystem free blocks
+ * ext4_count_free_clusters() -- count filesystem free clusters
* @sb: superblock
*
- * Adds up the number of free blocks from each block group.
+ * Adds up the number of free clusters from each block group.
*/
-ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
+ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
{
ext4_fsblk_t desc_count;
struct ext4_group_desc *gdp;
@@ -508,7 +551,7 @@
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += ext4_free_blks_count(sb, gdp);
+ desc_count += ext4_free_group_clusters(sb, gdp);
brelse(bitmap_bh);
bitmap_bh = ext4_read_block_bitmap(sb, i);
if (bitmap_bh == NULL)
@@ -516,12 +559,13 @@
x = ext4_count_free(bitmap_bh, sb->s_blocksize);
printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
- i, ext4_free_blks_count(sb, gdp), x);
+ i, ext4_free_group_clusters(sb, gdp), x);
bitmap_count += x;
}
brelse(bitmap_bh);
- printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu"
- ", computed = %llu, %llu\n", ext4_free_blocks_count(es),
+ printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
+ ", computed = %llu, %llu\n",
+ EXT4_B2C(sbi, ext4_free_blocks_count(es)),
desc_count, bitmap_count);
return bitmap_count;
#else
@@ -530,7 +574,7 @@
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += ext4_free_blks_count(sb, gdp);
+ desc_count += ext4_free_group_clusters(sb, gdp);
}
return desc_count;
@@ -620,6 +664,31 @@
}
+/*
+ * This function returns the number of file system metadata clusters at
+ * the beginning of a block group, including the reserved gdt blocks.
+ */
+unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+ ext4_group_t block_group)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ unsigned num;
+
+ /* Check for superblock and gdt backups in this group */
+ num = ext4_bg_has_super(sb, block_group);
+
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
+ block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
+ sbi->s_desc_per_block) {
+ if (num) {
+ num += ext4_bg_num_gdb(sb, block_group);
+ num += le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+ }
+ } else { /* For META_BG_BLOCK_GROUPS */
+ num += ext4_bg_num_gdb(sb, block_group);
+ }
+ return EXT4_NUM_B2C(sbi, num);
+}
/**
* ext4_inode_to_goal_block - return a hint for block allocation
* @inode: inode for block allocation
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index cec3145..5b0e26a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -144,9 +144,17 @@
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
#define EXT4_MAP_UNINIT (1 << BH_Uninit)
+/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
+ * ext4_map_blocks wants to know whether or not the underlying cluster has
+ * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
+ * the requested mapping was from previously mapped (or delayed allocated)
+ * cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster
+ * should never appear on buffer_head's state flags.
+ */
+#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
- EXT4_MAP_UNINIT)
+ EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
@@ -239,8 +247,11 @@
# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
#endif
#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof(__u32))
+#define EXT4_CLUSTER_SIZE(s) (EXT4_BLOCK_SIZE(s) << \
+ EXT4_SB(s)->s_cluster_bits)
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits)
+# define EXT4_CLUSTER_BITS(s) (EXT4_SB(s)->s_cluster_bits)
#else
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10)
#endif
@@ -258,6 +269,14 @@
#endif
#define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits)))
+/* Translate a block number to a cluster number */
+#define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits)
+/* Translate a cluster number to a block number */
+#define EXT4_C2B(sbi, cluster) ((cluster) << (sbi)->s_cluster_bits)
+/* Translate # of blks to # of clusters */
+#define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \
+ (sbi)->s_cluster_bits)
+
/*
* Structure of a blocks group descriptor
*/
@@ -289,7 +308,7 @@
struct flex_groups {
atomic_t free_inodes;
- atomic_t free_blocks;
+ atomic_t free_clusters;
atomic_t used_dirs;
};
@@ -306,6 +325,7 @@
#define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size)
#ifdef __KERNEL__
# define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group)
+# define EXT4_CLUSTERS_PER_GROUP(s) (EXT4_SB(s)->s_clusters_per_group)
# define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block)
# define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group)
# define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits)
@@ -358,8 +378,7 @@
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
- EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\
- EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
+ EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
@@ -520,6 +539,8 @@
#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 0x0020
/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040
+ /* Request will not result in inode size update (user for fallocate) */
+#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080
/*
* Flags used by ext4_free_blocks
@@ -528,6 +549,13 @@
#define EXT4_FREE_BLOCKS_FORGET 0x0002
#define EXT4_FREE_BLOCKS_VALIDATED 0x0004
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008
+#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010
+#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020
+
+/*
+ * Flags used by ext4_discard_partial_page_buffers
+ */
+#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED 0x0001
/*
* ioctl commands
@@ -538,9 +566,6 @@
#define EXT4_IOC_SETVERSION _IOW('f', 4, long)
#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION
#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION
-#ifdef CONFIG_JBD2_DEBUG
-#define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long)
-#endif
#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long)
#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long)
#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long)
@@ -563,9 +588,6 @@
#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int)
#define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input)
-#ifdef CONFIG_JBD2_DEBUG
-#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int)
-#endif
#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
#endif
@@ -837,6 +859,7 @@
ext4_group_t i_last_alloc_group;
/* allocation reservation info for delalloc */
+ /* In case of bigalloc, these refer to clusters rather than blocks */
unsigned int i_reserved_data_blocks;
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
@@ -886,7 +909,6 @@
/*
* Mount flags
*/
-#define EXT4_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */
#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */
#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */
#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
@@ -918,6 +940,9 @@
#define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */
#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */
+#define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly
+ specified delalloc */
+
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
#define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \
@@ -968,9 +993,9 @@
/*10*/ __le32 s_free_inodes_count; /* Free inodes count */
__le32 s_first_data_block; /* First Data Block */
__le32 s_log_block_size; /* Block size */
- __le32 s_obso_log_frag_size; /* Obsoleted fragment size */
+ __le32 s_log_cluster_size; /* Allocation cluster size */
/*20*/ __le32 s_blocks_per_group; /* # Blocks per group */
- __le32 s_obso_frags_per_group; /* Obsoleted fragments per group */
+ __le32 s_clusters_per_group; /* # Clusters per group */
__le32 s_inodes_per_group; /* # Inodes per group */
__le32 s_mtime; /* Mount time */
/*30*/ __le32 s_wtime; /* Write time */
@@ -1066,7 +1091,10 @@
__u8 s_last_error_func[32]; /* function where the error happened */
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
__u8 s_mount_opts[64];
- __le32 s_reserved[112]; /* Padding to the end of the block */
+ __le32 s_usr_quota_inum; /* inode for tracking user quota */
+ __le32 s_grp_quota_inum; /* inode for tracking group quota */
+ __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
+ __le32 s_reserved[109]; /* Padding to the end of the block */
};
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
@@ -1086,6 +1114,7 @@
unsigned long s_desc_size; /* Size of a group descriptor in bytes */
unsigned long s_inodes_per_block;/* Number of inodes per block */
unsigned long s_blocks_per_group;/* Number of blocks in a group */
+ unsigned long s_clusters_per_group; /* Number of clusters in a group */
unsigned long s_inodes_per_group;/* Number of inodes in a group */
unsigned long s_itb_per_group; /* Number of inode table blocks per group */
unsigned long s_gdb_count; /* Number of group descriptor blocks */
@@ -1094,6 +1123,8 @@
ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
unsigned long s_overhead_last; /* Last calculated overhead */
unsigned long s_blocks_last; /* Last seen block count */
+ unsigned int s_cluster_ratio; /* Number of blocks per cluster */
+ unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
@@ -1117,10 +1148,10 @@
u32 s_hash_seed[4];
int s_def_hash_version;
int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
- struct percpu_counter s_freeblocks_counter;
+ struct percpu_counter s_freeclusters_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
- struct percpu_counter s_dirtyblocks_counter;
+ struct percpu_counter s_dirtyclusters_counter;
struct blockgroup_lock *s_blockgroup_lock;
struct proc_dir_entry *s_proc;
struct kobject s_kobj;
@@ -1136,10 +1167,6 @@
u32 s_max_batch_time;
u32 s_min_batch_time;
struct block_device *journal_bdev;
-#ifdef CONFIG_JBD2_DEBUG
- struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */
- wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */
-#endif
#ifdef CONFIG_QUOTA
char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
int s_jquota_fmt; /* Format of quota to use */
@@ -1248,6 +1275,15 @@
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
+static inline void ext4_set_io_unwritten_flag(struct inode *inode,
+ struct ext4_io_end *io_end)
+{
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ }
+}
+
/*
* Inode dynamic state flags
*/
@@ -1360,6 +1396,7 @@
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
#define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100
+#define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200
#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001
#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002
@@ -1402,7 +1439,8 @@
EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
- EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
+ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC)
/*
* Default values for user and/or group using reserved blocks
@@ -1735,9 +1773,9 @@
unsigned int flags,
unsigned long *count,
int *errp);
-extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
- s64 nblocks, unsigned int flags);
-extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
+extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
+ s64 nclusters, unsigned int flags);
+extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
extern void ext4_check_blocks_bitmap(struct super_block *);
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
ext4_group_t block_group,
@@ -1745,12 +1783,18 @@
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
ext4_group_t block_group);
-extern unsigned ext4_init_block_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
-#define ext4_free_blocks_after_init(sb, group, desc) \
- ext4_init_block_bitmap(sb, NULL, group, desc)
+extern void ext4_init_block_bitmap(struct super_block *sb,
+ struct buffer_head *bh,
+ ext4_group_t group,
+ struct ext4_group_desc *desc);
+extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp);
+extern unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+ ext4_group_t block_group);
+extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
/* dir.c */
@@ -1776,7 +1820,8 @@
/* ialloc.c */
extern struct inode *ext4_new_inode(handle_t *, struct inode *, int,
- const struct qstr *qstr, __u32 goal);
+ const struct qstr *qstr, __u32 goal,
+ uid_t *owner);
extern void ext4_free_inode(handle_t *, struct inode *);
extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
extern unsigned long ext4_count_free_inodes(struct super_block *);
@@ -1839,6 +1884,12 @@
struct address_space *mapping, loff_t from);
extern int ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length);
+extern int ext4_discard_partial_page_buffers(handle_t *handle,
+ struct address_space *mapping, loff_t from,
+ loff_t length, int flags);
+extern int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+ struct inode *inode, struct page *page, loff_t from,
+ loff_t length, int flags);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
@@ -1927,8 +1978,8 @@
struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg);
-extern __u32 ext4_free_blks_count(struct super_block *sb,
- struct ext4_group_desc *bg);
+extern __u32 ext4_free_group_clusters(struct super_block *sb,
+ struct ext4_group_desc *bg);
extern __u32 ext4_free_inodes_count(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_used_dirs_count(struct super_block *sb,
@@ -1941,8 +1992,9 @@
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
-extern void ext4_free_blks_set(struct super_block *sb,
- struct ext4_group_desc *bg, __u32 count);
+extern void ext4_free_group_clusters_set(struct super_block *sb,
+ struct ext4_group_desc *bg,
+ __u32 count);
extern void ext4_free_inodes_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count);
extern void ext4_used_dirs_set(struct super_block *sb,
@@ -2051,13 +2103,13 @@
} while (0)
#ifdef CONFIG_SMP
-/* Each CPU can accumulate percpu_counter_batch blocks in their local
- * counters. So we need to make sure we have free blocks more
+/* Each CPU can accumulate percpu_counter_batch clusters in their local
+ * counters. So we need to make sure we have free clusters more
* than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times.
*/
-#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
+#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
#else
-#define EXT4_FREEBLOCKS_WATERMARK 0
+#define EXT4_FREECLUSTERS_WATERMARK 0
#endif
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
@@ -2243,10 +2295,19 @@
enum ext4_state_bits {
BH_Uninit /* blocks are allocated but uninitialized on disk */
= BH_JBDPrivateStart,
+ BH_AllocFromCluster, /* allocated blocks were part of already
+ * allocated cluster. Note that this flag will
+ * never, ever appear in a buffer_head's state
+ * flag. See EXT4_MAP_FROM_CLUSTER to see where
+ * this is used. */
+ BH_Da_Mapped, /* Delayed allocated block that now has a mapping. This
+ * flag is set when ext4_map_blocks is called on a
+ * delayed allocated block to get its real mapping. */
};
BUFFER_FNS(Uninit, uninit)
TAS_BUFFER_FNS(Uninit, uninit)
+BUFFER_FNS(Da_Mapped, da_mapped)
/*
* Add new method to test wether block and inode bitmaps are properly
@@ -2282,4 +2343,6 @@
#endif /* __KERNEL__ */
+#include "ext4_extents.h"
+
#endif /* _EXT4_H */
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 095c36f..a52db3a 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -290,5 +290,7 @@
struct ext4_ext_path *);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
+extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
+ int search_hint_reverse);
#endif /* _EXT4_EXTENTS */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index f5240aa..aca1790 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -109,9 +109,11 @@
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, line, __func__,
- bh, handle, err);
+ if (err) {
+ /* Errors can only happen if there is a bug */
+ handle->h_err = err;
+ __ext4_journal_stop(where, line, handle);
+ }
} else {
if (inode)
mark_buffer_dirty_inode(bh, inode);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 57cf568..61fa9e1 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -42,7 +42,6 @@
#include <asm/uaccess.h>
#include <linux/fiemap.h>
#include "ext4_jbd2.h"
-#include "ext4_extents.h"
#include <trace/events/ext4.h>
@@ -96,13 +95,17 @@
* - ENOMEM
* - EIO
*/
-static int ext4_ext_dirty(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path)
+#define ext4_ext_dirty(handle, inode, path) \
+ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
+static int __ext4_ext_dirty(const char *where, unsigned int line,
+ handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
{
int err;
if (path->p_bh) {
/* path points to block */
- err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
+ err = __ext4_handle_dirty_metadata(where, line, handle,
+ inode, path->p_bh);
} else {
/* path points to leaf/index in inode body */
err = ext4_mark_inode_dirty(handle, inode);
@@ -114,11 +117,9 @@
struct ext4_ext_path *path,
ext4_lblk_t block)
{
- int depth;
-
if (path) {
+ int depth = path->p_depth;
struct ext4_extent *ex;
- depth = path->p_depth;
/*
* Try to predict block placement assuming that we are
@@ -180,12 +181,10 @@
size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 6)
- size = 6;
+ if (!check && size > 6)
+ size = 6;
#endif
- }
return size;
}
@@ -195,12 +194,10 @@
size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent_idx);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 5)
- size = 5;
+ if (!check && size > 5)
+ size = 5;
#endif
- }
return size;
}
@@ -211,12 +208,10 @@
size = sizeof(EXT4_I(inode)->i_data);
size -= sizeof(struct ext4_extent_header);
size /= sizeof(struct ext4_extent);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 3)
- size = 3;
+ if (!check && size > 3)
+ size = 3;
#endif
- }
return size;
}
@@ -227,12 +222,10 @@
size = sizeof(EXT4_I(inode)->i_data);
size -= sizeof(struct ext4_extent_header);
size /= sizeof(struct ext4_extent_idx);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 4)
- size = 4;
+ if (!check && size > 4)
+ size = 4;
#endif
- }
return size;
}
@@ -244,7 +237,7 @@
int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
{
struct ext4_inode_info *ei = EXT4_I(inode);
- int idxs, num = 0;
+ int idxs;
idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent_idx));
@@ -259,6 +252,8 @@
*/
if (ei->i_da_metadata_calc_len &&
ei->i_da_metadata_calc_last_lblock+1 == lblock) {
+ int num = 0;
+
if ((ei->i_da_metadata_calc_len % idxs) == 0)
num++;
if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
@@ -321,8 +316,6 @@
struct ext4_extent_header *eh,
int depth)
{
- struct ext4_extent *ext;
- struct ext4_extent_idx *ext_idx;
unsigned short entries;
if (eh->eh_entries == 0)
return 1;
@@ -331,7 +324,7 @@
if (depth == 0) {
/* leaf entries */
- ext = EXT_FIRST_EXTENT(eh);
+ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
while (entries) {
if (!ext4_valid_extent(inode, ext))
return 0;
@@ -339,7 +332,7 @@
entries--;
}
} else {
- ext_idx = EXT_FIRST_INDEX(eh);
+ struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
while (entries) {
if (!ext4_valid_extent_idx(inode, ext_idx))
return 0;
@@ -751,31 +744,30 @@
return -EIO;
}
- len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
/* insert after */
- if (curp->p_idx != EXT_LAST_INDEX(curp->p_hdr)) {
- len = (len - 1) * sizeof(struct ext4_extent_idx);
- len = len < 0 ? 0 : len;
- ext_debug("insert new index %d after: %llu. "
- "move %d from 0x%p to 0x%p\n",
- logical, ptr, len,
- (curp->p_idx + 1), (curp->p_idx + 2));
- memmove(curp->p_idx + 2, curp->p_idx + 1, len);
- }
+ ext_debug("insert new index %d after: %llu\n", logical, ptr);
ix = curp->p_idx + 1;
} else {
/* insert before */
- len = len * sizeof(struct ext4_extent_idx);
- len = len < 0 ? 0 : len;
- ext_debug("insert new index %d before: %llu. "
- "move %d from 0x%p to 0x%p\n",
- logical, ptr, len,
- curp->p_idx, (curp->p_idx + 1));
- memmove(curp->p_idx + 1, curp->p_idx, len);
+ ext_debug("insert new index %d before: %llu\n", logical, ptr);
ix = curp->p_idx;
}
+ len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1;
+ BUG_ON(len < 0);
+ if (len > 0) {
+ ext_debug("insert new index %d: "
+ "move %d indices from 0x%p to 0x%p\n",
+ logical, len, ix, ix + 1);
+ memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx));
+ }
+
+ if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) {
+ EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!");
+ return -EIO;
+ }
+
ix->ei_block = cpu_to_le32(logical);
ext4_idx_store_pblock(ix, ptr);
le16_add_cpu(&curp->p_hdr->eh_entries, 1);
@@ -1042,16 +1034,14 @@
*/
static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
unsigned int flags,
- struct ext4_ext_path *path,
struct ext4_extent *newext)
{
- struct ext4_ext_path *curp = path;
struct ext4_extent_header *neh;
struct buffer_head *bh;
ext4_fsblk_t newblock;
int err = 0;
- newblock = ext4_ext_new_meta_block(handle, inode, path,
+ newblock = ext4_ext_new_meta_block(handle, inode, NULL,
newext, &err, flags);
if (newblock == 0)
return err;
@@ -1071,7 +1061,8 @@
}
/* move top-level index/leaf into new block */
- memmove(bh->b_data, curp->p_hdr, sizeof(EXT4_I(inode)->i_data));
+ memmove(bh->b_data, EXT4_I(inode)->i_data,
+ sizeof(EXT4_I(inode)->i_data));
/* set size of new block */
neh = ext_block_hdr(bh);
@@ -1089,32 +1080,23 @@
if (err)
goto out;
- /* create index in new top-level index: num,max,pointer */
- err = ext4_ext_get_access(handle, inode, curp);
- if (err)
- goto out;
-
- curp->p_hdr->eh_magic = EXT4_EXT_MAGIC;
- curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
- curp->p_hdr->eh_entries = cpu_to_le16(1);
- curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr);
-
- if (path[0].p_hdr->eh_depth)
- curp->p_idx->ei_block =
- EXT_FIRST_INDEX(path[0].p_hdr)->ei_block;
- else
- curp->p_idx->ei_block =
- EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block;
- ext4_idx_store_pblock(curp->p_idx, newblock);
-
+ /* Update top-level index: num,max,pointer */
neh = ext_inode_hdr(inode);
+ neh->eh_entries = cpu_to_le16(1);
+ ext4_idx_store_pblock(EXT_FIRST_INDEX(neh), newblock);
+ if (neh->eh_depth == 0) {
+ /* Root extent block becomes index block */
+ neh->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
+ EXT_FIRST_INDEX(neh)->ei_block =
+ EXT_FIRST_EXTENT(neh)->ee_block;
+ }
ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n",
le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max),
le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
- neh->eh_depth = cpu_to_le16(path->p_depth + 1);
- err = ext4_ext_dirty(handle, inode, curp);
+ neh->eh_depth = cpu_to_le16(neh->eh_depth + 1);
+ ext4_mark_inode_dirty(handle, inode);
out:
brelse(bh);
@@ -1162,8 +1144,7 @@
err = PTR_ERR(path);
} else {
/* tree is full, time to grow in depth */
- err = ext4_ext_grow_indepth(handle, inode, flags,
- path, newext);
+ err = ext4_ext_grow_indepth(handle, inode, flags, newext);
if (err)
goto out;
@@ -1235,9 +1216,9 @@
if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
EXT4_ERROR_INODE(inode,
"ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!",
- ix != NULL ? ix->ei_block : 0,
+ ix != NULL ? le32_to_cpu(ix->ei_block) : 0,
EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ?
- EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block : 0,
+ le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0,
depth);
return -EIO;
}
@@ -1260,13 +1241,14 @@
/*
* search the closest allocated block to the right for *logical
* and returns it at @logical + it's physical address at @phys
- * if *logical is the smallest allocated block, the function
+ * if *logical is the largest allocated block, the function
* returns 0 at @phys
* return value contains 0 (success) or error code
*/
static int ext4_ext_search_right(struct inode *inode,
struct ext4_ext_path *path,
- ext4_lblk_t *logical, ext4_fsblk_t *phys)
+ ext4_lblk_t *logical, ext4_fsblk_t *phys,
+ struct ext4_extent **ret_ex)
{
struct buffer_head *bh = NULL;
struct ext4_extent_header *eh;
@@ -1308,9 +1290,7 @@
return -EIO;
}
}
- *logical = le32_to_cpu(ex->ee_block);
- *phys = ext4_ext_pblock(ex);
- return 0;
+ goto found_extent;
}
if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
@@ -1323,9 +1303,7 @@
if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
/* next allocated block in this leaf */
ex++;
- *logical = le32_to_cpu(ex->ee_block);
- *phys = ext4_ext_pblock(ex);
- return 0;
+ goto found_extent;
}
/* go up and search for index to the right */
@@ -1368,9 +1346,12 @@
return -EIO;
}
ex = EXT_FIRST_EXTENT(eh);
+found_extent:
*logical = le32_to_cpu(ex->ee_block);
*phys = ext4_ext_pblock(ex);
- put_bh(bh);
+ *ret_ex = ex;
+ if (bh)
+ put_bh(bh);
return 0;
}
@@ -1395,7 +1376,8 @@
while (depth >= 0) {
if (depth == path->p_depth) {
/* leaf */
- if (path[depth].p_ext !=
+ if (path[depth].p_ext &&
+ path[depth].p_ext !=
EXT_LAST_EXTENT(path[depth].p_hdr))
return le32_to_cpu(path[depth].p_ext[1].ee_block);
} else {
@@ -1623,7 +1605,8 @@
* such that there will be no overlap, and then returns 1.
* If there is no overlap found, it returns 0.
*/
-static unsigned int ext4_ext_check_overlap(struct inode *inode,
+static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
+ struct inode *inode,
struct ext4_extent *newext,
struct ext4_ext_path *path)
{
@@ -1637,6 +1620,7 @@
if (!path[depth].p_ext)
goto out;
b2 = le32_to_cpu(path[depth].p_ext->ee_block);
+ b2 &= ~(sbi->s_cluster_ratio - 1);
/*
* get the next allocated block if the extent in the path
@@ -1646,6 +1630,7 @@
b2 = ext4_ext_next_allocated_block(path);
if (b2 == EXT_MAX_BLOCKS)
goto out;
+ b2 &= ~(sbi->s_cluster_ratio - 1);
}
/* check for wrap through zero on extent logical start block*/
@@ -1697,7 +1682,7 @@
/* try to insert block into found extent and return */
if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
&& ext4_can_extents_be_merged(inode, ex, newext)) {
- ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
+ ext_debug("append [%d]%d block to %u:[%d]%d (from %llu)\n",
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
@@ -1735,7 +1720,7 @@
if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block))
next = ext4_ext_next_leaf_block(path);
if (next != EXT_MAX_BLOCKS) {
- ext_debug("next leaf block - %d\n", next);
+ ext_debug("next leaf block - %u\n", next);
BUG_ON(npath != NULL);
npath = ext4_ext_find_extent(inode, next, NULL);
if (IS_ERR(npath))
@@ -1773,46 +1758,51 @@
if (!nearex) {
/* there is no extent in this leaf, create first one */
- ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n",
+ ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext));
- path[depth].p_ext = EXT_FIRST_EXTENT(eh);
- } else if (le32_to_cpu(newext->ee_block)
+ nearex = EXT_FIRST_EXTENT(eh);
+ } else {
+ if (le32_to_cpu(newext->ee_block)
> le32_to_cpu(nearex->ee_block)) {
-/* BUG_ON(newext->ee_block == nearex->ee_block); */
- if (nearex != EXT_LAST_EXTENT(eh)) {
- len = EXT_MAX_EXTENT(eh) - nearex;
- len = (len - 1) * sizeof(struct ext4_extent);
- len = len < 0 ? 0 : len;
- ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, "
- "move %d from 0x%p to 0x%p\n",
+ /* Insert after */
+ ext_debug("insert %u:%llu:[%d]%d before: "
+ "nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext),
- nearex, len, nearex + 1, nearex + 2);
- memmove(nearex + 2, nearex + 1, len);
+ nearex);
+ nearex++;
+ } else {
+ /* Insert before */
+ BUG_ON(newext->ee_block == nearex->ee_block);
+ ext_debug("insert %u:%llu:[%d]%d after: "
+ "nearest %p\n",
+ le32_to_cpu(newext->ee_block),
+ ext4_ext_pblock(newext),
+ ext4_ext_is_uninitialized(newext),
+ ext4_ext_get_actual_len(newext),
+ nearex);
}
- path[depth].p_ext = nearex + 1;
- } else {
- BUG_ON(newext->ee_block == nearex->ee_block);
- len = (EXT_MAX_EXTENT(eh) - nearex) * sizeof(struct ext4_extent);
- len = len < 0 ? 0 : len;
- ext_debug("insert %d:%llu:[%d]%d before: nearest 0x%p, "
- "move %d from 0x%p to 0x%p\n",
- le32_to_cpu(newext->ee_block),
- ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
- ext4_ext_get_actual_len(newext),
- nearex, len, nearex, nearex + 1);
- memmove(nearex + 1, nearex, len);
- path[depth].p_ext = nearex;
+ len = EXT_LAST_EXTENT(eh) - nearex + 1;
+ if (len > 0) {
+ ext_debug("insert %u:%llu:[%d]%d: "
+ "move %d extents from 0x%p to 0x%p\n",
+ le32_to_cpu(newext->ee_block),
+ ext4_ext_pblock(newext),
+ ext4_ext_is_uninitialized(newext),
+ ext4_ext_get_actual_len(newext),
+ len, nearex, nearex + 1);
+ memmove(nearex + 1, nearex,
+ len * sizeof(struct ext4_extent));
+ }
}
le16_add_cpu(&eh->eh_entries, 1);
- nearex = path[depth].p_ext;
+ path[depth].p_ext = nearex;
nearex->ee_block = newext->ee_block;
ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext));
nearex->ee_len = newext->ee_len;
@@ -1962,6 +1952,7 @@
struct ext4_ext_cache *cex;
BUG_ON(len == 0);
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+ trace_ext4_ext_put_in_cache(inode, block, len, start);
cex = &EXT4_I(inode)->i_cached_extent;
cex->ec_block = block;
cex->ec_len = len;
@@ -2063,6 +2054,7 @@
sbi->extent_cache_misses++;
else
sbi->extent_cache_hits++;
+ trace_ext4_ext_in_cache(inode, block, ret);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
return ret;
}
@@ -2130,6 +2122,8 @@
if (err)
return err;
ext_debug("index is empty, remove it, free block %llu\n", leaf);
+ trace_ext4_ext_rm_idx(inode, leaf);
+
ext4_free_blocks(handle, inode, NULL, leaf, 1,
EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
return err;
@@ -2158,7 +2152,7 @@
* need to account for leaf block credit
*
* bitmaps and block group descriptor blocks
- * and other metadat blocks still need to be
+ * and other metadata blocks still need to be
* accounted.
*/
/* 1 bitmap, 1 block group descriptor */
@@ -2195,14 +2189,40 @@
}
static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
- struct ext4_extent *ex,
- ext4_lblk_t from, ext4_lblk_t to)
+ struct ext4_extent *ex,
+ ext4_fsblk_t *partial_cluster,
+ ext4_lblk_t from, ext4_lblk_t to)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned short ee_len = ext4_ext_get_actual_len(ex);
+ ext4_fsblk_t pblk;
int flags = EXT4_FREE_BLOCKS_FORGET;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
flags |= EXT4_FREE_BLOCKS_METADATA;
+ /*
+ * For bigalloc file systems, we never free a partial cluster
+ * at the beginning of the extent. Instead, we make a note
+ * that we tried freeing the cluster, and check to see if we
+ * need to free it on a subsequent call to ext4_remove_blocks,
+ * or at the end of the ext4_truncate() operation.
+ */
+ flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER;
+
+ trace_ext4_remove_blocks(inode, ex, from, to, *partial_cluster);
+ /*
+ * If we have a partial cluster, and it's different from the
+ * cluster of the last block, we need to explicitly free the
+ * partial cluster here.
+ */
+ pblk = ext4_ext_pblock(ex) + ee_len - 1;
+ if (*partial_cluster && (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(sbi, *partial_cluster),
+ sbi->s_cluster_ratio, flags);
+ *partial_cluster = 0;
+ }
+
#ifdef EXTENTS_STATS
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -2222,12 +2242,24 @@
&& to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* tail removal */
ext4_lblk_t num;
- ext4_fsblk_t start;
num = le32_to_cpu(ex->ee_block) + ee_len - from;
- start = ext4_ext_pblock(ex) + ee_len - num;
- ext_debug("free last %u blocks starting %llu\n", num, start);
- ext4_free_blocks(handle, inode, NULL, start, num, flags);
+ pblk = ext4_ext_pblock(ex) + ee_len - num;
+ ext_debug("free last %u blocks starting %llu\n", num, pblk);
+ ext4_free_blocks(handle, inode, NULL, pblk, num, flags);
+ /*
+ * If the block range to be freed didn't start at the
+ * beginning of a cluster, and we removed the entire
+ * extent, save the partial cluster here, since we
+ * might need to delete if we determine that the
+ * truncate operation has removed all of the blocks in
+ * the cluster.
+ */
+ if (pblk & (sbi->s_cluster_ratio - 1) &&
+ (ee_len == num))
+ *partial_cluster = EXT4_B2C(sbi, pblk);
+ else
+ *partial_cluster = 0;
} else if (from == le32_to_cpu(ex->ee_block)
&& to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* head removal */
@@ -2238,7 +2270,7 @@
start = ext4_ext_pblock(ex);
ext_debug("free first %u blocks starting %llu\n", num, start);
- ext4_free_blocks(handle, inode, 0, start, num, flags);
+ ext4_free_blocks(handle, inode, NULL, start, num, flags);
} else {
printk(KERN_INFO "strange request: removal(2) "
@@ -2262,19 +2294,19 @@
*/
static int
ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path, ext4_lblk_t start,
- ext4_lblk_t end)
+ struct ext4_ext_path *path, ext4_fsblk_t *partial_cluster,
+ ext4_lblk_t start, ext4_lblk_t end)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int err = 0, correct_index = 0;
int depth = ext_depth(inode), credits;
struct ext4_extent_header *eh;
- ext4_lblk_t a, b, block;
+ ext4_lblk_t a, b;
unsigned num;
ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
unsigned uninitialized = 0;
struct ext4_extent *ex;
- struct ext4_map_blocks map;
/* the header must be checked already in ext4_ext_remove_space() */
ext_debug("truncate since %u in leaf\n", start);
@@ -2291,6 +2323,8 @@
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
+ trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
+
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
@@ -2315,86 +2349,18 @@
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
continue;
- } else if (a != ex_ee_block &&
- b != ex_ee_block + ex_ee_len - 1) {
- /*
- * If this is a truncate, then this condition should
- * never happen because at least one of the end points
- * needs to be on the edge of the extent.
- */
- if (end == EXT_MAX_BLOCKS - 1) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- block = 0;
- num = 0;
- err = -EIO;
- goto out;
- }
- /*
- * else this is a hole punch, so the extent needs to
- * be split since neither edge of the hole is on the
- * extent edge
- */
- else{
- map.m_pblk = ext4_ext_pblock(ex);
- map.m_lblk = ex_ee_block;
- map.m_len = b - ex_ee_block;
-
- err = ext4_split_extent(handle,
- inode, path, &map, 0,
- EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
- EXT4_GET_BLOCKS_PRE_IO);
-
- if (err < 0)
- goto out;
-
- ex_ee_len = ext4_ext_get_actual_len(ex);
-
- b = ex_ee_block+ex_ee_len - 1 < end ?
- ex_ee_block+ex_ee_len - 1 : end;
-
- /* Then remove tail of this extent */
- block = ex_ee_block;
- num = a - block;
- }
+ } else if (b != ex_ee_block + ex_ee_len - 1) {
+ EXT4_ERROR_INODE(inode," bad truncate %u:%u\n",
+ start, end);
+ err = -EIO;
+ goto out;
} else if (a != ex_ee_block) {
/* remove tail of the extent */
- block = ex_ee_block;
- num = a - block;
- } else if (b != ex_ee_block + ex_ee_len - 1) {
- /* remove head of the extent */
- block = b;
- num = ex_ee_block + ex_ee_len - b;
-
- /*
- * If this is a truncate, this condition
- * should never happen
- */
- if (end == EXT_MAX_BLOCKS - 1) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- err = -EIO;
- goto out;
- }
+ num = a - ex_ee_block;
} else {
/* remove whole extent: excellent! */
- block = ex_ee_block;
num = 0;
- if (a != ex_ee_block) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- err = -EIO;
- goto out;
- }
-
- if (b != ex_ee_block + ex_ee_len - 1) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- err = -EIO;
- goto out;
- }
}
-
/*
* 3 for leaf, sb, and inode plus 2 (bmap and group
* descriptor) for each block group; assume two block
@@ -2416,23 +2382,15 @@
if (err)
goto out;
- err = ext4_remove_blocks(handle, inode, ex, a, b);
+ err = ext4_remove_blocks(handle, inode, ex, partial_cluster,
+ a, b);
if (err)
goto out;
- if (num == 0) {
+ if (num == 0)
/* this extent is removed; mark slot entirely unused */
ext4_ext_store_pblock(ex, 0);
- } else if (block != ex_ee_block) {
- /*
- * If this was a head removal, then we need to update
- * the physical block since it is now at a different
- * location
- */
- ext4_ext_store_pblock(ex, ext4_ext_pblock(ex) + (b-a));
- }
- ex->ee_block = cpu_to_le32(block);
ex->ee_len = cpu_to_le16(num);
/*
* Do not mark uninitialized if all the blocks in the
@@ -2440,11 +2398,6 @@
*/
if (uninitialized && num)
ext4_ext_mark_uninitialized(ex);
-
- err = ext4_ext_dirty(handle, inode, path + depth);
- if (err)
- goto out;
-
/*
* If the extent was completely released,
* we need to remove it from the leaf
@@ -2464,9 +2417,14 @@
sizeof(struct ext4_extent));
}
le16_add_cpu(&eh->eh_entries, -1);
- }
+ } else
+ *partial_cluster = 0;
- ext_debug("new extent: %u:%u:%llu\n", block, num,
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ ext_debug("new extent: %u:%u:%llu\n", ex_ee_block, num,
ext4_ext_pblock(ex));
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
@@ -2476,6 +2434,25 @@
if (correct_index && eh->eh_entries)
err = ext4_ext_correct_indexes(handle, inode, path);
+ /*
+ * If there is still a entry in the leaf node, check to see if
+ * it references the partial cluster. This is the only place
+ * where it could; if it doesn't, we can free the cluster.
+ */
+ if (*partial_cluster && ex >= EXT_FIRST_EXTENT(eh) &&
+ (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
+ *partial_cluster)) {
+ int flags = EXT4_FREE_BLOCKS_FORGET;
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
+
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(sbi, *partial_cluster),
+ sbi->s_cluster_ratio, flags);
+ *partial_cluster = 0;
+ }
+
/* if this leaf is free, then we should
* remove it from index block above */
if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
@@ -2511,6 +2488,7 @@
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
struct ext4_ext_path *path;
+ ext4_fsblk_t partial_cluster = 0;
handle_t *handle;
int i, err;
@@ -2524,6 +2502,8 @@
again:
ext4_ext_invalidate_cache(inode);
+ trace_ext4_ext_remove_space(inode, start, depth);
+
/*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
@@ -2546,7 +2526,8 @@
if (i == depth) {
/* this is leaf block */
err = ext4_ext_rm_leaf(handle, inode, path,
- start, EXT_MAX_BLOCKS - 1);
+ &partial_cluster, start,
+ EXT_MAX_BLOCKS - 1);
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
path[i].p_bh = NULL;
@@ -2618,6 +2599,24 @@
}
}
+ trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster,
+ path->p_hdr->eh_entries);
+
+ /* If we still have something in the partial cluster and we have removed
+ * even the first extent, then we should free the blocks in the partial
+ * cluster as well. */
+ if (partial_cluster && path->p_hdr->eh_entries == 0) {
+ int flags = EXT4_FREE_BLOCKS_FORGET;
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
+
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(EXT4_SB(sb), partial_cluster),
+ EXT4_SB(sb)->s_cluster_ratio, flags);
+ partial_cluster = 0;
+ }
+
/* TODO: flexible tree reduction should be here */
if (path->p_hdr->eh_entries == 0) {
/*
@@ -2909,17 +2908,29 @@
* a> There is no split required: Entire extent should be initialized
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
+ *
+ * Pre-conditions:
+ * - The extent pointed to by 'path' is uninitialized.
+ * - The extent pointed to by 'path' contains a superset
+ * of the logical span [map->m_lblk, map->m_lblk + map->m_len).
+ *
+ * Post-conditions on success:
+ * - the returned value is the number of blocks beyond map->l_lblk
+ * that are allocated and initialized.
+ * It is guaranteed to be >= map->m_len.
*/
static int ext4_ext_convert_to_initialized(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path *path)
{
+ struct ext4_extent_header *eh;
struct ext4_map_blocks split_map;
struct ext4_extent zero_ex;
struct ext4_extent *ex;
ext4_lblk_t ee_block, eof_block;
- unsigned int allocated, ee_len, depth;
+ unsigned int ee_len, depth;
+ int allocated;
int err = 0;
int split_flag = 0;
@@ -2933,11 +2944,93 @@
eof_block = map->m_lblk + map->m_len;
depth = ext_depth(inode);
+ eh = path[depth].p_hdr;
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (map->m_lblk - ee_block);
+ trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
+
+ /* Pre-conditions */
+ BUG_ON(!ext4_ext_is_uninitialized(ex));
+ BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
+ BUG_ON(map->m_lblk + map->m_len > ee_block + ee_len);
+
+ /*
+ * Attempt to transfer newly initialized blocks from the currently
+ * uninitialized extent to its left neighbor. This is much cheaper
+ * than an insertion followed by a merge as those involve costly
+ * memmove() calls. This is the common case in steady state for
+ * workloads doing fallocate(FALLOC_FL_KEEP_SIZE) followed by append
+ * writes.
+ *
+ * Limitations of the current logic:
+ * - L1: we only deal with writes at the start of the extent.
+ * The approach could be extended to writes at the end
+ * of the extent but this scenario was deemed less common.
+ * - L2: we do not deal with writes covering the whole extent.
+ * This would require removing the extent if the transfer
+ * is possible.
+ * - L3: we only attempt to merge with an extent stored in the
+ * same extent tree node.
+ */
+ if ((map->m_lblk == ee_block) && /*L1*/
+ (map->m_len < ee_len) && /*L2*/
+ (ex > EXT_FIRST_EXTENT(eh))) { /*L3*/
+ struct ext4_extent *prev_ex;
+ ext4_lblk_t prev_lblk;
+ ext4_fsblk_t prev_pblk, ee_pblk;
+ unsigned int prev_len, write_len;
+
+ prev_ex = ex - 1;
+ prev_lblk = le32_to_cpu(prev_ex->ee_block);
+ prev_len = ext4_ext_get_actual_len(prev_ex);
+ prev_pblk = ext4_ext_pblock(prev_ex);
+ ee_pblk = ext4_ext_pblock(ex);
+ write_len = map->m_len;
+
+ /*
+ * A transfer of blocks from 'ex' to 'prev_ex' is allowed
+ * upon those conditions:
+ * - C1: prev_ex is initialized,
+ * - C2: prev_ex is logically abutting ex,
+ * - C3: prev_ex is physically abutting ex,
+ * - C4: prev_ex can receive the additional blocks without
+ * overflowing the (initialized) length limit.
+ */
+ if ((!ext4_ext_is_uninitialized(prev_ex)) && /*C1*/
+ ((prev_lblk + prev_len) == ee_block) && /*C2*/
+ ((prev_pblk + prev_len) == ee_pblk) && /*C3*/
+ (prev_len < (EXT_INIT_MAX_LEN - write_len))) { /*C4*/
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ trace_ext4_ext_convert_to_initialized_fastpath(inode,
+ map, ex, prev_ex);
+
+ /* Shift the start of ex by 'write_len' blocks */
+ ex->ee_block = cpu_to_le32(ee_block + write_len);
+ ext4_ext_store_pblock(ex, ee_pblk + write_len);
+ ex->ee_len = cpu_to_le16(ee_len - write_len);
+ ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+
+ /* Extend prev_ex by 'write_len' blocks */
+ prev_ex->ee_len = cpu_to_le16(prev_len + write_len);
+
+ /* Mark the block containing both extents as dirty */
+ ext4_ext_dirty(handle, inode, path + depth);
+
+ /* Update path to point to the right extent */
+ path[depth].p_ext = prev_ex;
+
+ /* Result: number of initialized blocks past m_lblk */
+ allocated = write_len;
+ goto out;
+ }
+ }
+
WARN_ON(map->m_lblk < ee_block);
/*
* It is safe to convert extent to initialized via explicit
@@ -3165,6 +3258,192 @@
return ext4_mark_inode_dirty(handle, inode);
}
+/**
+ * ext4_find_delalloc_range: find delayed allocated block in the given range.
+ *
+ * Goes through the buffer heads in the range [lblk_start, lblk_end] and returns
+ * whether there are any buffers marked for delayed allocation. It returns '1'
+ * on the first delalloc'ed buffer head found. If no buffer head in the given
+ * range is marked for delalloc, it returns 0.
+ * lblk_start should always be <= lblk_end.
+ * search_hint_reverse is to indicate that searching in reverse from lblk_end to
+ * lblk_start might be more efficient (i.e., we will likely hit the delalloc'ed
+ * block sooner). This is useful when blocks are truncated sequentially from
+ * lblk_start towards lblk_end.
+ */
+static int ext4_find_delalloc_range(struct inode *inode,
+ ext4_lblk_t lblk_start,
+ ext4_lblk_t lblk_end,
+ int search_hint_reverse)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct buffer_head *head, *bh = NULL;
+ struct page *page;
+ ext4_lblk_t i, pg_lblk;
+ pgoff_t index;
+
+ /* reverse search wont work if fs block size is less than page size */
+ if (inode->i_blkbits < PAGE_CACHE_SHIFT)
+ search_hint_reverse = 0;
+
+ if (search_hint_reverse)
+ i = lblk_end;
+ else
+ i = lblk_start;
+
+ index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ while ((i >= lblk_start) && (i <= lblk_end)) {
+ page = find_get_page(mapping, index);
+ if (!page)
+ goto nextpage;
+
+ if (!page_has_buffers(page))
+ goto nextpage;
+
+ head = page_buffers(page);
+ if (!head)
+ goto nextpage;
+
+ bh = head;
+ pg_lblk = index << (PAGE_CACHE_SHIFT -
+ inode->i_blkbits);
+ do {
+ if (unlikely(pg_lblk < lblk_start)) {
+ /*
+ * This is possible when fs block size is less
+ * than page size and our cluster starts/ends in
+ * middle of the page. So we need to skip the
+ * initial few blocks till we reach the 'lblk'
+ */
+ pg_lblk++;
+ continue;
+ }
+
+ /* Check if the buffer is delayed allocated and that it
+ * is not yet mapped. (when da-buffers are mapped during
+ * their writeout, their da_mapped bit is set.)
+ */
+ if (buffer_delay(bh) && !buffer_da_mapped(bh)) {
+ page_cache_release(page);
+ trace_ext4_find_delalloc_range(inode,
+ lblk_start, lblk_end,
+ search_hint_reverse,
+ 1, i);
+ return 1;
+ }
+ if (search_hint_reverse)
+ i--;
+ else
+ i++;
+ } while ((i >= lblk_start) && (i <= lblk_end) &&
+ ((bh = bh->b_this_page) != head));
+nextpage:
+ if (page)
+ page_cache_release(page);
+ /*
+ * Move to next page. 'i' will be the first lblk in the next
+ * page.
+ */
+ if (search_hint_reverse)
+ index--;
+ else
+ index++;
+ i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ }
+
+ trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end,
+ search_hint_reverse, 0, 0);
+ return 0;
+}
+
+int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
+ int search_hint_reverse)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ ext4_lblk_t lblk_start, lblk_end;
+ lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+ lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
+
+ return ext4_find_delalloc_range(inode, lblk_start, lblk_end,
+ search_hint_reverse);
+}
+
+/**
+ * Determines how many complete clusters (out of those specified by the 'map')
+ * are under delalloc and were reserved quota for.
+ * This function is called when we are writing out the blocks that were
+ * originally written with their allocation delayed, but then the space was
+ * allocated using fallocate() before the delayed allocation could be resolved.
+ * The cases to look for are:
+ * ('=' indicated delayed allocated blocks
+ * '-' indicates non-delayed allocated blocks)
+ * (a) partial clusters towards beginning and/or end outside of allocated range
+ * are not delalloc'ed.
+ * Ex:
+ * |----c---=|====c====|====c====|===-c----|
+ * |++++++ allocated ++++++|
+ * ==> 4 complete clusters in above example
+ *
+ * (b) partial cluster (outside of allocated range) towards either end is
+ * marked for delayed allocation. In this case, we will exclude that
+ * cluster.
+ * Ex:
+ * |----====c========|========c========|
+ * |++++++ allocated ++++++|
+ * ==> 1 complete clusters in above example
+ *
+ * Ex:
+ * |================c================|
+ * |++++++ allocated ++++++|
+ * ==> 0 complete clusters in above example
+ *
+ * The ext4_da_update_reserve_space will be called only if we
+ * determine here that there were some "entire" clusters that span
+ * this 'allocated' range.
+ * In the non-bigalloc case, this function will just end up returning num_blks
+ * without ever calling ext4_find_delalloc_range.
+ */
+static unsigned int
+get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
+ unsigned int num_blks)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ ext4_lblk_t alloc_cluster_start, alloc_cluster_end;
+ ext4_lblk_t lblk_from, lblk_to, c_offset;
+ unsigned int allocated_clusters = 0;
+
+ alloc_cluster_start = EXT4_B2C(sbi, lblk_start);
+ alloc_cluster_end = EXT4_B2C(sbi, lblk_start + num_blks - 1);
+
+ /* max possible clusters for this allocation */
+ allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1;
+
+ trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
+
+ /* Check towards left side */
+ c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+ if (c_offset) {
+ lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+ lblk_to = lblk_from + c_offset - 1;
+
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ allocated_clusters--;
+ }
+
+ /* Now check towards right. */
+ c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+ if (allocated_clusters && c_offset) {
+ lblk_from = lblk_start + num_blks;
+ lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
+
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ allocated_clusters--;
+ }
+
+ return allocated_clusters;
+}
+
static int
ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
@@ -3181,6 +3460,9 @@
flags, allocated);
ext4_ext_show_leaf(inode, path);
+ trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated,
+ newblock);
+
/* get_block() before submit the IO, split the extent */
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
ret = ext4_split_unwritten_extents(handle, inode, map,
@@ -3190,10 +3472,9 @@
* that this IO needs to conversion to written when IO is
* completed
*/
- if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
- io->flag = EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
- } else
+ if (io)
+ ext4_set_io_unwritten_flag(inode, io);
+ else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
if (ext4_should_dioread_nolock(inode))
map->m_flags |= EXT4_MAP_UNINIT;
@@ -3234,14 +3515,8 @@
/* buffered write, writepage time, convert*/
ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
- if (ret >= 0) {
+ if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
- err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
- map->m_len);
- if (err < 0)
- goto out2;
- }
-
out:
if (ret <= 0) {
err = ret;
@@ -3270,11 +3545,24 @@
* But fallocate would have already updated quota and block
* count for this offset. So cancel these reservation
*/
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- ext4_da_update_reserve_space(inode, allocated, 0);
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+ unsigned int reserved_clusters;
+ reserved_clusters = get_reserved_cluster_alloc(inode,
+ map->m_lblk, map->m_len);
+ if (reserved_clusters)
+ ext4_da_update_reserve_space(inode,
+ reserved_clusters,
+ 0);
+ }
map_out:
map->m_flags |= EXT4_MAP_MAPPED;
+ if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) {
+ err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
+ map->m_len);
+ if (err < 0)
+ goto out2;
+ }
out1:
if (allocated > map->m_len)
allocated = map->m_len;
@@ -3290,6 +3578,111 @@
}
/*
+ * get_implied_cluster_alloc - check to see if the requested
+ * allocation (in the map structure) overlaps with a cluster already
+ * allocated in an extent.
+ * @sb The filesystem superblock structure
+ * @map The requested lblk->pblk mapping
+ * @ex The extent structure which might contain an implied
+ * cluster allocation
+ *
+ * This function is called by ext4_ext_map_blocks() after we failed to
+ * find blocks that were already in the inode's extent tree. Hence,
+ * we know that the beginning of the requested region cannot overlap
+ * the extent from the inode's extent tree. There are three cases we
+ * want to catch. The first is this case:
+ *
+ * |--- cluster # N--|
+ * |--- extent ---| |---- requested region ---|
+ * |==========|
+ *
+ * The second case that we need to test for is this one:
+ *
+ * |--------- cluster # N ----------------|
+ * |--- requested region --| |------- extent ----|
+ * |=======================|
+ *
+ * The third case is when the requested region lies between two extents
+ * within the same cluster:
+ * |------------- cluster # N-------------|
+ * |----- ex -----| |---- ex_right ----|
+ * |------ requested region ------|
+ * |================|
+ *
+ * In each of the above cases, we need to set the map->m_pblk and
+ * map->m_len so it corresponds to the return the extent labelled as
+ * "|====|" from cluster #N, since it is already in use for data in
+ * cluster EXT4_B2C(sbi, map->m_lblk). We will then return 1 to
+ * signal to ext4_ext_map_blocks() that map->m_pblk should be treated
+ * as a new "allocated" block region. Otherwise, we will return 0 and
+ * ext4_ext_map_blocks() will then allocate one or more new clusters
+ * by calling ext4_mb_new_blocks().
+ */
+static int get_implied_cluster_alloc(struct super_block *sb,
+ struct ext4_map_blocks *map,
+ struct ext4_extent *ex,
+ struct ext4_ext_path *path)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+ ext4_lblk_t ex_cluster_start, ex_cluster_end;
+ ext4_lblk_t rr_cluster_start, rr_cluster_end;
+ ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
+ ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
+ unsigned short ee_len = ext4_ext_get_actual_len(ex);
+
+ /* The extent passed in that we are trying to match */
+ ex_cluster_start = EXT4_B2C(sbi, ee_block);
+ ex_cluster_end = EXT4_B2C(sbi, ee_block + ee_len - 1);
+
+ /* The requested region passed into ext4_map_blocks() */
+ rr_cluster_start = EXT4_B2C(sbi, map->m_lblk);
+ rr_cluster_end = EXT4_B2C(sbi, map->m_lblk + map->m_len - 1);
+
+ if ((rr_cluster_start == ex_cluster_end) ||
+ (rr_cluster_start == ex_cluster_start)) {
+ if (rr_cluster_start == ex_cluster_end)
+ ee_start += ee_len - 1;
+ map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
+ c_offset;
+ map->m_len = min(map->m_len,
+ (unsigned) sbi->s_cluster_ratio - c_offset);
+ /*
+ * Check for and handle this case:
+ *
+ * |--------- cluster # N-------------|
+ * |------- extent ----|
+ * |--- requested region ---|
+ * |===========|
+ */
+
+ if (map->m_lblk < ee_block)
+ map->m_len = min(map->m_len, ee_block - map->m_lblk);
+
+ /*
+ * Check for the case where there is already another allocated
+ * block to the right of 'ex' but before the end of the cluster.
+ *
+ * |------------- cluster # N-------------|
+ * |----- ex -----| |---- ex_right ----|
+ * |------ requested region ------|
+ * |================|
+ */
+ if (map->m_lblk > ee_block) {
+ ext4_lblk_t next = ext4_ext_next_allocated_block(path);
+ map->m_len = min(map->m_len, next - map->m_lblk);
+ }
+
+ trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1);
+ return 1;
+ }
+
+ trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0);
+ return 0;
+}
+
+
+/*
* Block allocation/map/preallocation routine for extents based files
*
*
@@ -3311,15 +3704,17 @@
struct ext4_map_blocks *map, int flags)
{
struct ext4_ext_path *path = NULL;
- struct ext4_extent newex, *ex;
+ struct ext4_extent newex, *ex, *ex2;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_fsblk_t newblock = 0;
- int err = 0, depth, ret;
- unsigned int allocated = 0;
+ int free_on_err = 0, err = 0, depth, ret;
+ unsigned int allocated = 0, offset = 0;
+ unsigned int allocated_clusters = 0;
unsigned int punched_out = 0;
unsigned int result = 0;
struct ext4_allocation_request ar;
ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
- struct ext4_map_blocks punch_map;
+ ext4_lblk_t cluster_offset;
ext_debug("blocks %u/%u requested for inode %lu\n",
map->m_lblk, map->m_len, inode->i_ino);
@@ -3329,6 +3724,10 @@
if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) &&
ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
if (!newex.ee_start_lo && !newex.ee_start_hi) {
+ if ((sbi->s_cluster_ratio > 1) &&
+ ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
/*
* block isn't allocated yet and
@@ -3339,6 +3738,8 @@
/* we should allocate requested block */
} else {
/* block is already allocated */
+ if (sbi->s_cluster_ratio > 1)
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
newblock = map->m_lblk
- le32_to_cpu(newex.ee_block)
+ ext4_ext_pblock(&newex);
@@ -3384,8 +3785,14 @@
* we split out initialized portions during a write.
*/
ee_len = ext4_ext_get_actual_len(ex);
+
+ trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len);
+
/* if found extent covers block, simply return it */
if (in_range(map->m_lblk, ee_block, ee_len)) {
+ struct ext4_map_blocks punch_map;
+ ext4_fsblk_t partial_cluster = 0;
+
newblock = map->m_lblk - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (map->m_lblk - ee_block);
@@ -3469,7 +3876,8 @@
ext4_ext_invalidate_cache(inode);
err = ext4_ext_rm_leaf(handle, inode, path,
- map->m_lblk, map->m_lblk + punched_out);
+ &partial_cluster, map->m_lblk,
+ map->m_lblk + punched_out);
if (!err && path->p_hdr->eh_entries == 0) {
/*
@@ -3492,6 +3900,10 @@
}
}
+ if ((sbi->s_cluster_ratio > 1) &&
+ ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+
/*
* requested block isn't allocated yet;
* we couldn't try to create block if create flag is zero
@@ -3504,9 +3916,25 @@
ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
goto out2;
}
+
/*
* Okay, we need to do block allocation.
*/
+ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
+ newex.ee_block = cpu_to_le32(map->m_lblk);
+ cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+
+ /*
+ * If we are doing bigalloc, check to see if the extent returned
+ * by ext4_ext_find_extent() implies a cluster we can use.
+ */
+ if (cluster_offset && ex &&
+ get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
+ ar.len = allocated = map->m_len;
+ newblock = map->m_pblk;
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+ goto got_allocated_blocks;
+ }
/* find neighbour allocated blocks */
ar.lleft = map->m_lblk;
@@ -3514,10 +3942,21 @@
if (err)
goto out2;
ar.lright = map->m_lblk;
- err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
+ ex2 = NULL;
+ err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2);
if (err)
goto out2;
+ /* Check if the extent after searching to the right implies a
+ * cluster we can use. */
+ if ((sbi->s_cluster_ratio > 1) && ex2 &&
+ get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
+ ar.len = allocated = map->m_len;
+ newblock = map->m_pblk;
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+ goto got_allocated_blocks;
+ }
+
/*
* See if request is beyond maximum number of blocks we can have in
* a single extent. For an initialized extent this limit is
@@ -3532,9 +3971,8 @@
map->m_len = EXT_UNINIT_MAX_LEN;
/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
- newex.ee_block = cpu_to_le32(map->m_lblk);
newex.ee_len = cpu_to_le16(map->m_len);
- err = ext4_ext_check_overlap(inode, &newex, path);
+ err = ext4_ext_check_overlap(sbi, inode, &newex, path);
if (err)
allocated = ext4_ext_get_actual_len(&newex);
else
@@ -3544,7 +3982,18 @@
ar.inode = inode;
ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk);
ar.logical = map->m_lblk;
- ar.len = allocated;
+ /*
+ * We calculate the offset from the beginning of the cluster
+ * for the logical block number, since when we allocate a
+ * physical cluster, the physical block should start at the
+ * same offset from the beginning of the cluster. This is
+ * needed so that future calls to get_implied_cluster_alloc()
+ * work correctly.
+ */
+ offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+ ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
+ ar.goal -= offset;
+ ar.logical -= offset;
if (S_ISREG(inode->i_mode))
ar.flags = EXT4_MB_HINT_DATA;
else
@@ -3557,9 +4006,15 @@
goto out2;
ext_debug("allocate new block: goal %llu, found %llu/%u\n",
ar.goal, newblock, allocated);
+ free_on_err = 1;
+ allocated_clusters = ar.len;
+ ar.len = EXT4_C2B(sbi, ar.len) - offset;
+ if (ar.len > allocated)
+ ar.len = allocated;
+got_allocated_blocks:
/* try to insert new extent into found leaf and return */
- ext4_ext_store_pblock(&newex, newblock);
+ ext4_ext_store_pblock(&newex, newblock + offset);
newex.ee_len = cpu_to_le16(ar.len);
/* Mark uninitialized */
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
@@ -3572,10 +4027,9 @@
* that we need to perform conversion when IO is done.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
- if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
- io->flag = EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
- } else
+ if (io)
+ ext4_set_io_unwritten_flag(inode, io);
+ else
ext4_set_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN);
}
@@ -3583,11 +4037,14 @@
map->m_flags |= EXT4_MAP_UNINIT;
}
- err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len);
+ err = 0;
+ if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0)
+ err = check_eofblocks_fl(handle, inode, map->m_lblk,
+ path, ar.len);
if (!err)
err = ext4_ext_insert_extent(handle, inode, path,
&newex, flags);
- if (err) {
+ if (err && free_on_err) {
int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
/* free data blocks we just allocated */
@@ -3610,8 +4067,82 @@
* Update reserved blocks/metadata blocks after successful
* block allocation which had been deferred till now.
*/
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- ext4_da_update_reserve_space(inode, allocated, 1);
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+ unsigned int reserved_clusters;
+ /*
+ * Check how many clusters we had reserved this allocated range
+ */
+ reserved_clusters = get_reserved_cluster_alloc(inode,
+ map->m_lblk, allocated);
+ if (map->m_flags & EXT4_MAP_FROM_CLUSTER) {
+ if (reserved_clusters) {
+ /*
+ * We have clusters reserved for this range.
+ * But since we are not doing actual allocation
+ * and are simply using blocks from previously
+ * allocated cluster, we should release the
+ * reservation and not claim quota.
+ */
+ ext4_da_update_reserve_space(inode,
+ reserved_clusters, 0);
+ }
+ } else {
+ BUG_ON(allocated_clusters < reserved_clusters);
+ /* We will claim quota for all newly allocated blocks.*/
+ ext4_da_update_reserve_space(inode, allocated_clusters,
+ 1);
+ if (reserved_clusters < allocated_clusters) {
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int reservation = allocated_clusters -
+ reserved_clusters;
+ /*
+ * It seems we claimed few clusters outside of
+ * the range of this allocation. We should give
+ * it back to the reservation pool. This can
+ * happen in the following case:
+ *
+ * * Suppose s_cluster_ratio is 4 (i.e., each
+ * cluster has 4 blocks. Thus, the clusters
+ * are [0-3],[4-7],[8-11]...
+ * * First comes delayed allocation write for
+ * logical blocks 10 & 11. Since there were no
+ * previous delayed allocated blocks in the
+ * range [8-11], we would reserve 1 cluster
+ * for this write.
+ * * Next comes write for logical blocks 3 to 8.
+ * In this case, we will reserve 2 clusters
+ * (for [0-3] and [4-7]; and not for [8-11] as
+ * that range has a delayed allocated blocks.
+ * Thus total reserved clusters now becomes 3.
+ * * Now, during the delayed allocation writeout
+ * time, we will first write blocks [3-8] and
+ * allocate 3 clusters for writing these
+ * blocks. Also, we would claim all these
+ * three clusters above.
+ * * Now when we come here to writeout the
+ * blocks [10-11], we would expect to claim
+ * the reservation of 1 cluster we had made
+ * (and we would claim it since there are no
+ * more delayed allocated blocks in the range
+ * [8-11]. But our reserved cluster count had
+ * already gone to 0.
+ *
+ * Thus, at the step 4 above when we determine
+ * that there are still some unwritten delayed
+ * allocated blocks outside of our current
+ * block range, we should increment the
+ * reserved clusters count so that when the
+ * remaining blocks finally gets written, we
+ * could claim them.
+ */
+ dquot_reserve_block(inode,
+ EXT4_C2B(sbi, reservation));
+ spin_lock(&ei->i_block_reservation_lock);
+ ei->i_reserved_data_blocks += reservation;
+ spin_unlock(&ei->i_block_reservation_lock);
+ }
+ }
+ }
/*
* Cache the extent and update transaction to commit on fdatasync only
@@ -3634,12 +4165,12 @@
ext4_ext_drop_refs(path);
kfree(path);
}
- trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
- newblock, map->m_len, err ? err : allocated);
-
result = (flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) ?
punched_out : allocated;
+ trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
+ newblock, map->m_len, err ? err : result);
+
return err ? err : result;
}
@@ -3649,6 +4180,7 @@
struct super_block *sb = inode->i_sb;
ext4_lblk_t last_block;
handle_t *handle;
+ loff_t page_len;
int err = 0;
/*
@@ -3665,8 +4197,16 @@
if (IS_ERR(handle))
return;
- if (inode->i_size & (sb->s_blocksize - 1))
- ext4_block_truncate_page(handle, mapping, inode->i_size);
+ if (inode->i_size % PAGE_CACHE_SIZE != 0) {
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0);
+
+ if (err)
+ goto out_stop;
+ }
if (ext4_orphan_add(handle, inode))
goto out_stop;
@@ -3760,6 +4300,7 @@
int ret = 0;
int ret2 = 0;
int retries = 0;
+ int flags;
struct ext4_map_blocks map;
unsigned int credits, blkbits = inode->i_blkbits;
@@ -3796,6 +4337,16 @@
trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
return ret;
}
+ flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
+ if (mode & FALLOC_FL_KEEP_SIZE)
+ flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+ /*
+ * Don't normalize the request if it can fit in one extent so
+ * that it doesn't get unnecessarily split into multiple
+ * extents.
+ */
+ if (len <= EXT_UNINIT_MAX_LEN << blkbits)
+ flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
retry:
while (ret >= 0 && ret < max_blocks) {
map.m_lblk = map.m_lblk + ret;
@@ -3805,9 +4356,7 @@
ret = PTR_ERR(handle);
break;
}
- ret = ext4_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
- EXT4_GET_BLOCKS_NO_NORMALIZE);
+ ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret <= 0) {
#ifdef EXT4FS_DEBUG
WARN_ON(ret <= 0);
@@ -4102,7 +4651,6 @@
return EXT_BREAK;
return EXT_CONTINUE;
}
-
/* fiemap flags we can handle specified here */
#define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
@@ -4162,17 +4710,28 @@
struct address_space *mapping = inode->i_mapping;
struct ext4_map_blocks map;
handle_t *handle;
- loff_t first_block_offset, last_block_offset, block_len;
- loff_t first_page, last_page, first_page_offset, last_page_offset;
+ loff_t first_page, last_page, page_len;
+ loff_t first_page_offset, last_page_offset;
int ret, credits, blocks_released, err = 0;
+ /* No need to punch hole beyond i_size */
+ if (offset >= inode->i_size)
+ return 0;
+
+ /*
+ * If the hole extends beyond i_size, set the hole
+ * to end after the page that contains i_size
+ */
+ if (offset + length > inode->i_size) {
+ length = inode->i_size +
+ PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
+ offset;
+ }
+
first_block = (offset + sb->s_blocksize - 1) >>
EXT4_BLOCK_SIZE_BITS(sb);
last_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
- first_block_offset = first_block << EXT4_BLOCK_SIZE_BITS(sb);
- last_block_offset = last_block << EXT4_BLOCK_SIZE_BITS(sb);
-
first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
last_page = (offset + length) >> PAGE_CACHE_SHIFT;
@@ -4185,11 +4744,10 @@
*/
if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
err = filemap_write_and_wait_range(mapping,
- first_page_offset == 0 ? 0 : first_page_offset-1,
- last_page_offset);
+ offset, offset + length - 1);
- if (err)
- return err;
+ if (err)
+ return err;
}
/* Now release the pages */
@@ -4211,24 +4769,64 @@
goto out;
/*
- * Now we need to zero out the un block aligned data.
- * If the file is smaller than a block, just
- * zero out the middle
+ * Now we need to zero out the non-page-aligned data in the
+ * pages at the start and tail of the hole, and unmap the buffer
+ * heads for the block aligned regions of the page that were
+ * completely zeroed.
*/
- if (first_block > last_block)
- ext4_block_zero_page_range(handle, mapping, offset, length);
- else {
- /* zero out the head of the hole before the first block */
- block_len = first_block_offset - offset;
- if (block_len > 0)
- ext4_block_zero_page_range(handle, mapping,
- offset, block_len);
+ if (first_page > last_page) {
+ /*
+ * If the file space being truncated is contained within a page
+ * just zero out and unmap the middle of that page
+ */
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, offset, length, 0);
- /* zero out the tail of the hole after the last block */
- block_len = offset + length - last_block_offset;
- if (block_len > 0) {
- ext4_block_zero_page_range(handle, mapping,
- last_block_offset, block_len);
+ if (err)
+ goto out;
+ } else {
+ /*
+ * zero out and unmap the partial page that contains
+ * the start of the hole
+ */
+ page_len = first_page_offset - offset;
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle, mapping,
+ offset, page_len, 0);
+ if (err)
+ goto out;
+ }
+
+ /*
+ * zero out and unmap the partial page that contains
+ * the end of the hole
+ */
+ page_len = offset + length - last_page_offset;
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle, mapping,
+ last_page_offset, page_len, 0);
+ if (err)
+ goto out;
+ }
+ }
+
+
+ /*
+ * If i_size is contained in the last page, we need to
+ * unmap and zero the partial page after i_size
+ */
+ if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
+ inode->i_size % PAGE_CACHE_SIZE != 0) {
+
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0);
+
+ if (err)
+ goto out;
}
}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index b9548f4..cb70f18 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -181,8 +181,8 @@
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
- memcpy(sbi->s_es->s_last_mounted, cp,
- sizeof(sbi->s_es->s_last_mounted));
+ strlcpy(sbi->s_es->s_last_mounted, cp,
+ sizeof(sbi->s_es->s_last_mounted));
ext4_mark_super_dirty(sb);
}
}
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 036f78f..00a2cb7 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -75,7 +75,7 @@
* to written.
* The function return the number of pending IOs on success.
*/
-extern int ext4_flush_completed_IO(struct inode *inode)
+int ext4_flush_completed_IO(struct inode *inode)
{
ext4_io_end_t *io;
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -83,14 +83,12 @@
int ret = 0;
int ret2 = 0;
- if (list_empty(&ei->i_completed_io_list))
- return ret;
-
dump_completed_IO(inode);
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
while (!list_empty(&ei->i_completed_io_list)){
io = list_entry(ei->i_completed_io_list.next,
ext4_io_end_t, list);
+ list_del_init(&io->list);
/*
* Calling ext4_end_io_nolock() to convert completed
* IO to written.
@@ -107,11 +105,9 @@
*/
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
ret = ext4_end_io_nolock(io);
- spin_lock_irqsave(&ei->i_completed_io_lock, flags);
if (ret < 0)
ret2 = ret;
- else
- list_del_init(&io->list);
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
}
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
return (ret2 < 0) ? ret2 : 0;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 9c63f27..00beb4f 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -78,7 +78,7 @@
* allocation, essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, "Checksum bad for group %u", block_group);
- ext4_free_blks_set(sb, gdp, 0);
+ ext4_free_group_clusters_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
memset(bh->b_data, 0xff, sb->s_blocksize);
@@ -293,121 +293,9 @@
ext4_std_error(sb, fatal);
}
-/*
- * There are two policies for allocating an inode. If the new inode is
- * a directory, then a forward search is made for a block group with both
- * free space and a low directory-to-inode ratio; if that fails, then of
- * the groups with above-average free space, that group with the fewest
- * directories already is chosen.
- *
- * For other inodes, search forward from the parent directory\'s block
- * group to find a free inode.
- */
-static int find_group_dir(struct super_block *sb, struct inode *parent,
- ext4_group_t *best_group)
-{
- ext4_group_t ngroups = ext4_get_groups_count(sb);
- unsigned int freei, avefreei;
- struct ext4_group_desc *desc, *best_desc = NULL;
- ext4_group_t group;
- int ret = -1;
-
- freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
- avefreei = freei / ngroups;
-
- for (group = 0; group < ngroups; group++) {
- desc = ext4_get_group_desc(sb, group, NULL);
- if (!desc || !ext4_free_inodes_count(sb, desc))
- continue;
- if (ext4_free_inodes_count(sb, desc) < avefreei)
- continue;
- if (!best_desc ||
- (ext4_free_blks_count(sb, desc) >
- ext4_free_blks_count(sb, best_desc))) {
- *best_group = group;
- best_desc = desc;
- ret = 0;
- }
- }
- return ret;
-}
-
-#define free_block_ratio 10
-
-static int find_group_flex(struct super_block *sb, struct inode *parent,
- ext4_group_t *best_group)
-{
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_group_desc *desc;
- struct flex_groups *flex_group = sbi->s_flex_groups;
- ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
- ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
- ext4_group_t ngroups = ext4_get_groups_count(sb);
- int flex_size = ext4_flex_bg_size(sbi);
- ext4_group_t best_flex = parent_fbg_group;
- int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
- int flexbg_free_blocks;
- int flex_freeb_ratio;
- ext4_group_t n_fbg_groups;
- ext4_group_t i;
-
- n_fbg_groups = (ngroups + flex_size - 1) >>
- sbi->s_log_groups_per_flex;
-
-find_close_to_parent:
- flexbg_free_blocks = atomic_read(&flex_group[best_flex].free_blocks);
- flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
- if (atomic_read(&flex_group[best_flex].free_inodes) &&
- flex_freeb_ratio > free_block_ratio)
- goto found_flexbg;
-
- if (best_flex && best_flex == parent_fbg_group) {
- best_flex--;
- goto find_close_to_parent;
- }
-
- for (i = 0; i < n_fbg_groups; i++) {
- if (i == parent_fbg_group || i == parent_fbg_group - 1)
- continue;
-
- flexbg_free_blocks = atomic_read(&flex_group[i].free_blocks);
- flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
-
- if (flex_freeb_ratio > free_block_ratio &&
- (atomic_read(&flex_group[i].free_inodes))) {
- best_flex = i;
- goto found_flexbg;
- }
-
- if ((atomic_read(&flex_group[best_flex].free_inodes) == 0) ||
- ((atomic_read(&flex_group[i].free_blocks) >
- atomic_read(&flex_group[best_flex].free_blocks)) &&
- atomic_read(&flex_group[i].free_inodes)))
- best_flex = i;
- }
-
- if (!atomic_read(&flex_group[best_flex].free_inodes) ||
- !atomic_read(&flex_group[best_flex].free_blocks))
- return -1;
-
-found_flexbg:
- for (i = best_flex * flex_size; i < ngroups &&
- i < (best_flex + 1) * flex_size; i++) {
- desc = ext4_get_group_desc(sb, i, NULL);
- if (ext4_free_inodes_count(sb, desc)) {
- *best_group = i;
- goto out;
- }
- }
-
- return -1;
-out:
- return 0;
-}
-
struct orlov_stats {
__u32 free_inodes;
- __u32 free_blocks;
+ __u32 free_clusters;
__u32 used_dirs;
};
@@ -424,7 +312,7 @@
if (flex_size > 1) {
stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
- stats->free_blocks = atomic_read(&flex_group[g].free_blocks);
+ stats->free_clusters = atomic_read(&flex_group[g].free_clusters);
stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
return;
}
@@ -432,11 +320,11 @@
desc = ext4_get_group_desc(sb, g, NULL);
if (desc) {
stats->free_inodes = ext4_free_inodes_count(sb, desc);
- stats->free_blocks = ext4_free_blks_count(sb, desc);
+ stats->free_clusters = ext4_free_group_clusters(sb, desc);
stats->used_dirs = ext4_used_dirs_count(sb, desc);
} else {
stats->free_inodes = 0;
- stats->free_blocks = 0;
+ stats->free_clusters = 0;
stats->used_dirs = 0;
}
}
@@ -471,10 +359,10 @@
ext4_group_t real_ngroups = ext4_get_groups_count(sb);
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
- ext4_fsblk_t freeb, avefreeb;
+ ext4_fsblk_t freeb, avefreec;
unsigned int ndirs;
int max_dirs, min_inodes;
- ext4_grpblk_t min_blocks;
+ ext4_grpblk_t min_clusters;
ext4_group_t i, grp, g, ngroups;
struct ext4_group_desc *desc;
struct orlov_stats stats;
@@ -490,9 +378,10 @@
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
avefreei = freei / ngroups;
- freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
- avefreeb = freeb;
- do_div(avefreeb, ngroups);
+ freeb = EXT4_C2B(sbi,
+ percpu_counter_read_positive(&sbi->s_freeclusters_counter));
+ avefreec = freeb;
+ do_div(avefreec, ngroups);
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if (S_ISDIR(mode) &&
@@ -518,7 +407,7 @@
continue;
if (stats.free_inodes < avefreei)
continue;
- if (stats.free_blocks < avefreeb)
+ if (stats.free_clusters < avefreec)
continue;
grp = g;
ret = 0;
@@ -556,7 +445,7 @@
min_inodes = avefreei - inodes_per_group*flex_size / 4;
if (min_inodes < 1)
min_inodes = 1;
- min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb)*flex_size / 4;
+ min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4;
/*
* Start looking in the flex group where we last allocated an
@@ -575,7 +464,7 @@
continue;
if (stats.free_inodes < min_inodes)
continue;
- if (stats.free_blocks < min_blocks)
+ if (stats.free_clusters < min_clusters)
continue;
goto found_flex_bg;
}
@@ -659,7 +548,7 @@
*group = parent_group;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && ext4_free_inodes_count(sb, desc) &&
- ext4_free_blks_count(sb, desc))
+ ext4_free_group_clusters(sb, desc))
return 0;
/*
@@ -683,7 +572,7 @@
*group -= ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && ext4_free_inodes_count(sb, desc) &&
- ext4_free_blks_count(sb, desc))
+ ext4_free_group_clusters(sb, desc))
return 0;
}
@@ -802,7 +691,7 @@
* group to find a free inode.
*/
struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
- const struct qstr *qstr, __u32 goal)
+ const struct qstr *qstr, __u32 goal, uid_t *owner)
{
struct super_block *sb;
struct buffer_head *inode_bitmap_bh = NULL;
@@ -816,8 +705,6 @@
int ret2, err = 0;
struct inode *ret;
ext4_group_t i;
- int free = 0;
- static int once = 1;
ext4_group_t flex_group;
/* Cannot create files in a deleted directory */
@@ -843,26 +730,9 @@
goto got_group;
}
- if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
- ret2 = find_group_flex(sb, dir, &group);
- if (ret2 == -1) {
- ret2 = find_group_other(sb, dir, &group, mode);
- if (ret2 == 0 && once) {
- once = 0;
- printk(KERN_NOTICE "ext4: find_group_flex "
- "failed, fallback succeeded dir %lu\n",
- dir->i_ino);
- }
- }
- goto got_group;
- }
-
- if (S_ISDIR(mode)) {
- if (test_opt(sb, OLDALLOC))
- ret2 = find_group_dir(sb, dir, &group);
- else
- ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
- } else
+ if (S_ISDIR(mode))
+ ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
+ else
ret2 = find_group_other(sb, dir, &group, mode);
got_group:
@@ -950,26 +820,21 @@
goto fail;
}
- free = 0;
- ext4_lock_group(sb, group);
+ BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
+ err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh);
+ brelse(block_bitmap_bh);
+
/* recheck and clear flag under lock if we still need to */
+ ext4_lock_group(sb, group);
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
- free = ext4_free_blocks_after_init(sb, group, gdp);
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
- ext4_free_blks_set(sb, gdp, free);
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_clusters_after_init(sb, group, gdp));
gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
gdp);
}
ext4_unlock_group(sb, group);
- /* Don't need to dirty bitmap block if we didn't change it */
- if (free) {
- BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
- err = ext4_handle_dirty_metadata(handle,
- NULL, block_bitmap_bh);
- }
-
- brelse(block_bitmap_bh);
if (err)
goto fail;
}
@@ -987,8 +852,11 @@
flex_group = ext4_flex_group(sbi, group);
atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
}
-
- if (test_opt(sb, GRPID)) {
+ if (owner) {
+ inode->i_mode = mode;
+ inode->i_uid = owner[0];
+ inode->i_gid = owner[1];
+ } else if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = dir->i_gid;
@@ -1005,11 +873,7 @@
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
- /*
- * Don't inherit extent flag from directory, amongst others. We set
- * extent flag on newly created directory and file only if -o extent
- * mount option is specified
- */
+ /* Don't inherit extent flag from directory, amongst others. */
ei->i_flags =
ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED);
ei->i_file_acl = 0;
@@ -1084,7 +948,7 @@
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
brelse(inode_bitmap_bh);
@@ -1235,7 +1099,7 @@
* inode allocation from the current group, so we take alloc_sem lock, to
* block ext4_claim_inode until we are finished.
*/
-extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
+int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
int barrier)
{
struct ext4_group_info *grp = ext4_get_group_info(sb, group);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 0962642..3cfc73f 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -699,6 +699,13 @@
/*
* Okay, we need to do block allocation.
*/
+ if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+ EXT4_ERROR_INODE(inode, "Can't allocate blocks for "
+ "non-extent mapped inodes with bigalloc");
+ return -ENOSPC;
+ }
+
goal = ext4_find_goal(inode, map->m_lblk, partial);
/* the number of blocks need to allocate for [d,t]indirect blocks */
@@ -1343,7 +1350,9 @@
__le32 nr = 0;
int n = 0;
ext4_lblk_t last_block, max_block;
+ loff_t page_len;
unsigned blocksize = inode->i_sb->s_blocksize;
+ int err;
handle = start_transaction(inode);
if (IS_ERR(handle))
@@ -1354,9 +1363,16 @@
max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
- if (inode->i_size & (blocksize - 1))
- if (ext4_block_truncate_page(handle, mapping, inode->i_size))
+ if (inode->i_size % PAGE_CACHE_SIZE != 0) {
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0);
+
+ if (err)
goto out_stop;
+ }
if (last_block != max_block) {
n = ext4_block_to_path(inode, last_block, offsets, NULL);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0defe0b..cc5a6da 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -42,7 +42,6 @@
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
-#include "ext4_extents.h"
#include "truncate.h"
#include <trace/events/ext4.h>
@@ -268,7 +267,7 @@
struct ext4_inode_info *ei = EXT4_I(inode);
spin_lock(&ei->i_block_reservation_lock);
- trace_ext4_da_update_reserve_space(inode, used);
+ trace_ext4_da_update_reserve_space(inode, used, quota_claim);
if (unlikely(used > ei->i_reserved_data_blocks)) {
ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
"with only %d reserved data blocks\n",
@@ -281,7 +280,7 @@
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
used + ei->i_allocated_meta_blocks);
ei->i_allocated_meta_blocks = 0;
@@ -291,7 +290,7 @@
* only when we have written all of the delayed
* allocation blocks.
*/
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
@@ -300,14 +299,14 @@
/* Update quota subsystem for data blocks */
if (quota_claim)
- dquot_claim_block(inode, used);
+ dquot_claim_block(inode, EXT4_C2B(sbi, used));
else {
/*
* We did fallocate with an offset that is already delayed
* allocated. So on delayed allocated writeback we should
* not re-claim the quota for fallocated blocks.
*/
- dquot_release_reservation_block(inode, used);
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
}
/*
@@ -399,6 +398,49 @@
}
/*
+ * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map.
+ */
+static void set_buffers_da_mapped(struct inode *inode,
+ struct ext4_map_blocks *map)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct pagevec pvec;
+ int i, nr_pages;
+ pgoff_t index, end;
+
+ index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (map->m_lblk + map->m_len - 1) >>
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ pagevec_init(&pvec, 0);
+ while (index <= end) {
+ nr_pages = pagevec_lookup(&pvec, mapping, index,
+ min(end - index + 1,
+ (pgoff_t)PAGEVEC_SIZE));
+ if (nr_pages == 0)
+ break;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ struct buffer_head *bh, *head;
+
+ if (unlikely(page->mapping != mapping) ||
+ !PageDirty(page))
+ break;
+
+ if (page_has_buffers(page)) {
+ bh = head = page_buffers(page);
+ do {
+ set_buffer_da_mapped(bh);
+ bh = bh->b_this_page;
+ } while (bh != head);
+ }
+ index++;
+ }
+ pagevec_release(&pvec);
+ }
+}
+
+/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
@@ -416,7 +458,7 @@
* the buffer head is mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
- * that casem, buffer head is unmapped
+ * that case, buffer head is unmapped
*
* It returns the error in case of allocation failure.
*/
@@ -435,9 +477,11 @@
*/
down_read((&EXT4_I(inode)->i_data_sem));
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
- retval = ext4_ext_map_blocks(handle, inode, map, 0);
+ retval = ext4_ext_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
} else {
- retval = ext4_ind_map_blocks(handle, inode, map, 0);
+ retval = ext4_ind_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
}
up_read((&EXT4_I(inode)->i_data_sem));
@@ -455,7 +499,7 @@
* Returns if the blocks have already allocated
*
* Note that if blocks have been preallocated
- * ext4_ext_get_block() returns th create = 0
+ * ext4_ext_get_block() returns the create = 0
* with buffer head unmapped.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
@@ -517,9 +561,17 @@
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
+ /* If we have successfully mapped the delayed allocated blocks,
+ * set the BH_Da_Mapped bit on them. Its important to do this
+ * under the protection of i_data_sem.
+ */
+ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
+ set_buffers_da_mapped(inode, map);
+ }
+
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int ret = check_block_validity(inode, map);
@@ -909,7 +961,11 @@
ext4_orphan_add(handle, inode);
if (ret2 < 0)
ret = ret2;
+ } else {
+ unlock_page(page);
+ page_cache_release(page);
}
+
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
@@ -1037,14 +1093,14 @@
}
/*
- * Reserve a single block located at lblock
+ * Reserve a single cluster located at lblock
*/
static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
{
int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
- unsigned long md_needed;
+ unsigned int md_needed;
int ret;
/*
@@ -1054,7 +1110,8 @@
*/
repeat:
spin_lock(&ei->i_block_reservation_lock);
- md_needed = ext4_calc_metadata_amount(inode, lblock);
+ md_needed = EXT4_NUM_B2C(sbi,
+ ext4_calc_metadata_amount(inode, lblock));
trace_ext4_da_reserve_space(inode, md_needed);
spin_unlock(&ei->i_block_reservation_lock);
@@ -1063,15 +1120,15 @@
* us from metadata over-estimation, though we may go over by
* a small amount in the end. Here we just reserve for data.
*/
- ret = dquot_reserve_block(inode, 1);
+ ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
if (ret)
return ret;
/*
* We do still charge estimated metadata to the sb though;
* we cannot afford to run out of free blocks.
*/
- if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) {
- dquot_release_reservation_block(inode, 1);
+ if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) {
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
@@ -1118,19 +1175,21 @@
* We can release all of the reserved metadata blocks
* only when we have written all of the delayed
* allocation blocks.
+ * Note that in case of bigalloc, i_reserved_meta_blocks,
+ * i_reserved_data_blocks, etc. refer to number of clusters.
*/
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
}
/* update fs dirty data blocks counter */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- dquot_release_reservation_block(inode, to_free);
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
}
static void ext4_da_page_release_reservation(struct page *page,
@@ -1139,6 +1198,9 @@
int to_release = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
+ struct inode *inode = page->mapping->host;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ int num_clusters;
head = page_buffers(page);
bh = head;
@@ -1148,10 +1210,24 @@
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
clear_buffer_delay(bh);
+ clear_buffer_da_mapped(bh);
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
- ext4_da_release_space(page->mapping->host, to_release);
+
+ /* If we have released all the blocks belonging to a cluster, then we
+ * need to release the reserved space for that cluster. */
+ num_clusters = EXT4_NUM_B2C(sbi, to_release);
+ while (num_clusters > 0) {
+ ext4_fsblk_t lblk;
+ lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) +
+ ((num_clusters - 1) << sbi->s_cluster_bits);
+ if (sbi->s_cluster_ratio == 1 ||
+ !ext4_find_delalloc_cluster(inode, lblk, 1))
+ ext4_da_release_space(inode, 1);
+
+ num_clusters--;
+ }
}
/*
@@ -1253,6 +1329,8 @@
clear_buffer_delay(bh);
bh->b_blocknr = pblock;
}
+ if (buffer_da_mapped(bh))
+ clear_buffer_da_mapped(bh);
if (buffer_unwritten(bh) ||
buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
@@ -1346,12 +1424,15 @@
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
printk(KERN_CRIT "Total free blocks count %lld\n",
- ext4_count_free_blocks(inode->i_sb));
+ EXT4_C2B(EXT4_SB(inode->i_sb),
+ ext4_count_free_clusters(inode->i_sb)));
printk(KERN_CRIT "Free/Dirty block details\n");
printk(KERN_CRIT "free_blocks=%lld\n",
- (long long) percpu_counter_sum(&sbi->s_freeblocks_counter));
+ (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ percpu_counter_sum(&sbi->s_freeclusters_counter)));
printk(KERN_CRIT "dirty_blocks=%lld\n",
- (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
printk(KERN_CRIT "Block reservation details\n");
printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
EXT4_I(inode)->i_reserved_data_blocks);
@@ -1430,8 +1511,7 @@
if (err == -EAGAIN)
goto submit_io;
- if (err == -ENOSPC &&
- ext4_count_free_blocks(sb)) {
+ if (err == -ENOSPC && ext4_count_free_clusters(sb)) {
mpd->retval = err;
goto submit_io;
}
@@ -1471,13 +1551,15 @@
for (i = 0; i < map.m_len; i++)
unmap_underlying_metadata(bdev, map.m_pblk + i);
- }
- if (ext4_should_order_data(mpd->inode)) {
- err = ext4_jbd2_file_inode(handle, mpd->inode);
- if (err)
- /* This only happens if the journal is aborted */
- return;
+ if (ext4_should_order_data(mpd->inode)) {
+ err = ext4_jbd2_file_inode(handle, mpd->inode);
+ if (err) {
+ /* Only if the journal is aborted */
+ mpd->retval = err;
+ goto submit_io;
+ }
+ }
}
/*
@@ -1584,6 +1666,66 @@
}
/*
+ * This function is grabs code from the very beginning of
+ * ext4_map_blocks, but assumes that the caller is from delayed write
+ * time. This function looks up the requested blocks and sets the
+ * buffer delay bit under the protection of i_data_sem.
+ */
+static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
+ struct ext4_map_blocks *map,
+ struct buffer_head *bh)
+{
+ int retval;
+ sector_t invalid_block = ~((sector_t) 0xffff);
+
+ if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
+ invalid_block = ~0;
+
+ map->m_flags = 0;
+ ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
+ "logical block %lu\n", inode->i_ino, map->m_len,
+ (unsigned long) map->m_lblk);
+ /*
+ * Try to see if we can get the block without requesting a new
+ * file system block.
+ */
+ down_read((&EXT4_I(inode)->i_data_sem));
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ retval = ext4_ext_map_blocks(NULL, inode, map, 0);
+ else
+ retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+
+ if (retval == 0) {
+ /*
+ * XXX: __block_prepare_write() unmaps passed block,
+ * is it OK?
+ */
+ /* If the block was allocated from previously allocated cluster,
+ * then we dont need to reserve it again. */
+ if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
+ retval = ext4_da_reserve_space(inode, iblock);
+ if (retval)
+ /* not enough space to reserve */
+ goto out_unlock;
+ }
+
+ /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
+ * and it should not appear on the bh->b_state.
+ */
+ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
+
+ map_bh(bh, inode->i_sb, invalid_block);
+ set_buffer_new(bh);
+ set_buffer_delay(bh);
+ }
+
+out_unlock:
+ up_read((&EXT4_I(inode)->i_data_sem));
+
+ return retval;
+}
+
+/*
* This is a special get_blocks_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
* reserve space for a single block.
@@ -1600,10 +1742,6 @@
{
struct ext4_map_blocks map;
int ret = 0;
- sector_t invalid_block = ~((sector_t) 0xffff);
-
- if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
- invalid_block = ~0;
BUG_ON(create == 0);
BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
@@ -1616,25 +1754,9 @@
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
+ ret = ext4_da_map_blocks(inode, iblock, &map, bh);
+ if (ret <= 0)
return ret;
- if (ret == 0) {
- if (buffer_delay(bh))
- return 0; /* Not sure this could or should happen */
- /*
- * XXX: __block_write_begin() unmaps passed block, is it OK?
- */
- ret = ext4_da_reserve_space(inode, iblock);
- if (ret)
- /* not enough space to reserve */
- return ret;
-
- map_bh(bh, inode->i_sb, invalid_block);
- set_buffer_new(bh);
- set_buffer_delay(bh);
- return 0;
- }
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
@@ -2050,6 +2172,7 @@
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
pgoff_t done_index = 0;
pgoff_t end;
+ struct blk_plug plug;
trace_ext4_da_writepages(inode, wbc);
@@ -2128,6 +2251,7 @@
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
+ blk_start_plug(&plug);
while (!ret && wbc->nr_to_write > 0) {
/*
@@ -2178,11 +2302,12 @@
ret = 0;
} else if (ret == MPAGE_DA_EXTENT_TAIL) {
/*
- * got one extent now try with
- * rest of the pages
+ * Got one extent now try with rest of the pages.
+ * If mpd.retval is set -EIO, journal is aborted.
+ * So we don't need to write any more.
*/
pages_written += mpd.pages_written;
- ret = 0;
+ ret = mpd.retval;
io_done = 1;
} else if (wbc->nr_to_write)
/*
@@ -2192,6 +2317,7 @@
*/
break;
}
+ blk_finish_plug(&plug);
if (!io_done && !cycled) {
cycled = 1;
index = 0;
@@ -2230,10 +2356,11 @@
* Delalloc need an accurate free block accounting. So switch
* to non delalloc when we are near to error range.
*/
- free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
- dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+ free_blocks = EXT4_C2B(sbi,
+ percpu_counter_read_positive(&sbi->s_freeclusters_counter));
+ dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
if (2 * free_blocks < 3 * dirty_blocks ||
- free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+ free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
/*
* free block count is less than 150% of dirty blocks
* or free blocks is less than watermark
@@ -2259,6 +2386,7 @@
pgoff_t index;
struct inode *inode = mapping->host;
handle_t *handle;
+ loff_t page_len;
index = pos >> PAGE_CACHE_SHIFT;
@@ -2305,6 +2433,13 @@
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
+ } else {
+ page_len = pos & (PAGE_CACHE_SIZE - 1);
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers_no_lock(handle,
+ inode, page, pos - page_len, page_len,
+ EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+ }
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -2347,6 +2482,7 @@
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
+ loff_t page_len;
if (write_mode == FALL_BACK_TO_NONDELALLOC) {
if (ext4_should_order_data(inode)) {
@@ -2395,6 +2531,16 @@
}
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
+
+ page_len = PAGE_CACHE_SIZE -
+ ((pos + copied - 1) & (PAGE_CACHE_SIZE - 1));
+
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers_no_lock(handle,
+ inode, page, pos + copied - 1, page_len,
+ EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+ }
+
copied = ret2;
if (ret2 < 0)
ret = ret2;
@@ -2689,10 +2835,7 @@
* but being more careful is always safe for the future change.
*/
inode = io_end->inode;
- if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
- io_end->flag |= EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
- }
+ ext4_set_io_unwritten_flag(inode, io_end);
/* Add the io_end to per-inode completed io list*/
spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
@@ -2858,6 +3001,12 @@
struct inode *inode = file->f_mapping->host;
ssize_t ret;
+ /*
+ * If we are doing data journalling we don't support O_DIRECT
+ */
+ if (ext4_should_journal_data(inode))
+ return 0;
+
trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
@@ -2927,6 +3076,7 @@
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
@@ -2963,6 +3113,227 @@
inode->i_mapping->a_ops = &ext4_journalled_aops;
}
+
+/*
+ * ext4_discard_partial_page_buffers()
+ * Wrapper function for ext4_discard_partial_page_buffers_no_lock.
+ * This function finds and locks the page containing the offset
+ * "from" and passes it to ext4_discard_partial_page_buffers_no_lock.
+ * Calling functions that already have the page locked should call
+ * ext4_discard_partial_page_buffers_no_lock directly.
+ */
+int ext4_discard_partial_page_buffers(handle_t *handle,
+ struct address_space *mapping, loff_t from,
+ loff_t length, int flags)
+{
+ struct inode *inode = mapping->host;
+ struct page *page;
+ int err = 0;
+
+ page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
+ mapping_gfp_mask(mapping) & ~__GFP_FS);
+ if (!page)
+ return -ENOMEM;
+
+ err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page,
+ from, length, flags);
+
+ unlock_page(page);
+ page_cache_release(page);
+ return err;
+}
+
+/*
+ * ext4_discard_partial_page_buffers_no_lock()
+ * Zeros a page range of length 'length' starting from offset 'from'.
+ * Buffer heads that correspond to the block aligned regions of the
+ * zeroed range will be unmapped. Unblock aligned regions
+ * will have the corresponding buffer head mapped if needed so that
+ * that region of the page can be updated with the partial zero out.
+ *
+ * This function assumes that the page has already been locked. The
+ * The range to be discarded must be contained with in the given page.
+ * If the specified range exceeds the end of the page it will be shortened
+ * to the end of the page that corresponds to 'from'. This function is
+ * appropriate for updating a page and it buffer heads to be unmapped and
+ * zeroed for blocks that have been either released, or are going to be
+ * released.
+ *
+ * handle: The journal handle
+ * inode: The files inode
+ * page: A locked page that contains the offset "from"
+ * from: The starting byte offset (from the begining of the file)
+ * to begin discarding
+ * len: The length of bytes to discard
+ * flags: Optional flags that may be used:
+ *
+ * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED
+ * Only zero the regions of the page whose buffer heads
+ * have already been unmapped. This flag is appropriate
+ * for updateing the contents of a page whose blocks may
+ * have already been released, and we only want to zero
+ * out the regions that correspond to those released blocks.
+ *
+ * Returns zero on sucess or negative on failure.
+ */
+int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+ struct inode *inode, struct page *page, loff_t from,
+ loff_t length, int flags)
+{
+ ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
+ unsigned int offset = from & (PAGE_CACHE_SIZE-1);
+ unsigned int blocksize, max, pos;
+ ext4_lblk_t iblock;
+ struct buffer_head *bh;
+ int err = 0;
+
+ blocksize = inode->i_sb->s_blocksize;
+ max = PAGE_CACHE_SIZE - offset;
+
+ if (index != page->index)
+ return -EINVAL;
+
+ /*
+ * correct length if it does not fall between
+ * 'from' and the end of the page
+ */
+ if (length > max || length < 0)
+ length = max;
+
+ iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+
+ if (!page_has_buffers(page)) {
+ /*
+ * If the range to be discarded covers a partial block
+ * we need to get the page buffers. This is because
+ * partial blocks cannot be released and the page needs
+ * to be updated with the contents of the block before
+ * we write the zeros on top of it.
+ */
+ if ((from & (blocksize - 1)) ||
+ ((from + length) & (blocksize - 1))) {
+ create_empty_buffers(page, blocksize, 0);
+ } else {
+ /*
+ * If there are no partial blocks,
+ * there is nothing to update,
+ * so we can return now
+ */
+ return 0;
+ }
+ }
+
+ /* Find the buffer that contains "offset" */
+ bh = page_buffers(page);
+ pos = blocksize;
+ while (offset >= pos) {
+ bh = bh->b_this_page;
+ iblock++;
+ pos += blocksize;
+ }
+
+ pos = offset;
+ while (pos < offset + length) {
+ unsigned int end_of_block, range_to_discard;
+
+ err = 0;
+
+ /* The length of space left to zero and unmap */
+ range_to_discard = offset + length - pos;
+
+ /* The length of space until the end of the block */
+ end_of_block = blocksize - (pos & (blocksize-1));
+
+ /*
+ * Do not unmap or zero past end of block
+ * for this buffer head
+ */
+ if (range_to_discard > end_of_block)
+ range_to_discard = end_of_block;
+
+
+ /*
+ * Skip this buffer head if we are only zeroing unampped
+ * regions of the page
+ */
+ if (flags & EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED &&
+ buffer_mapped(bh))
+ goto next;
+
+ /* If the range is block aligned, unmap */
+ if (range_to_discard == blocksize) {
+ clear_buffer_dirty(bh);
+ bh->b_bdev = NULL;
+ clear_buffer_mapped(bh);
+ clear_buffer_req(bh);
+ clear_buffer_new(bh);
+ clear_buffer_delay(bh);
+ clear_buffer_unwritten(bh);
+ clear_buffer_uptodate(bh);
+ zero_user(page, pos, range_to_discard);
+ BUFFER_TRACE(bh, "Buffer discarded");
+ goto next;
+ }
+
+ /*
+ * If this block is not completely contained in the range
+ * to be discarded, then it is not going to be released. Because
+ * we need to keep this block, we need to make sure this part
+ * of the page is uptodate before we modify it by writeing
+ * partial zeros on it.
+ */
+ if (!buffer_mapped(bh)) {
+ /*
+ * Buffer head must be mapped before we can read
+ * from the block
+ */
+ BUFFER_TRACE(bh, "unmapped");
+ ext4_get_block(inode, iblock, bh, 0);
+ /* unmapped? It's a hole - nothing to do */
+ if (!buffer_mapped(bh)) {
+ BUFFER_TRACE(bh, "still unmapped");
+ goto next;
+ }
+ }
+
+ /* Ok, it's mapped. Make sure it's up-to-date */
+ if (PageUptodate(page))
+ set_buffer_uptodate(bh);
+
+ if (!buffer_uptodate(bh)) {
+ err = -EIO;
+ ll_rw_block(READ, 1, &bh);
+ wait_on_buffer(bh);
+ /* Uhhuh. Read error. Complain and punt.*/
+ if (!buffer_uptodate(bh))
+ goto next;
+ }
+
+ if (ext4_should_journal_data(inode)) {
+ BUFFER_TRACE(bh, "get write access");
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err)
+ goto next;
+ }
+
+ zero_user(page, pos, range_to_discard);
+
+ err = 0;
+ if (ext4_should_journal_data(inode)) {
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+ } else
+ mark_buffer_dirty(bh);
+
+ BUFFER_TRACE(bh, "Partial buffer zeroed");
+next:
+ bh = bh->b_this_page;
+ iblock++;
+ pos += range_to_discard;
+ }
+
+ return err;
+}
+
/*
* ext4_block_truncate_page() zeroes out a mapping from file offset `from'
* up to the end of the block which corresponds to `from'.
@@ -3005,7 +3376,7 @@
page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
mapping_gfp_mask(mapping) & ~__GFP_FS);
if (!page)
- return -EINVAL;
+ return -ENOMEM;
blocksize = inode->i_sb->s_blocksize;
max = blocksize - (offset & (blocksize - 1));
@@ -3074,11 +3445,8 @@
err = 0;
if (ext4_should_journal_data(inode)) {
err = ext4_handle_dirty_metadata(handle, inode, bh);
- } else {
- if (ext4_should_order_data(inode) && EXT4_I(inode)->jinode)
- err = ext4_jbd2_file_inode(handle, inode);
+ } else
mark_buffer_dirty(bh);
- }
unlock:
unlock_page(page);
@@ -3119,6 +3487,11 @@
return -ENOTSUPP;
}
+ if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
+ /* TODO: Add support for bigalloc file systems */
+ return -ENOTSUPP;
+ }
+
return ext4_ext_punch_hole(file, offset, length);
}
@@ -3418,7 +3791,7 @@
inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
- inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+ set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
ei->i_dir_start_lookup = 0;
@@ -4420,6 +4793,7 @@
PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
unlock_page(page);
ret = VM_FAULT_SIGBUS;
+ ext4_journal_stop(handle);
goto out;
}
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index f18bfe3..a567968 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -21,6 +21,7 @@
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = filp->f_dentry->d_inode;
+ struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
@@ -173,33 +174,8 @@
mnt_drop_write(filp->f_path.mnt);
return err;
}
-#ifdef CONFIG_JBD2_DEBUG
- case EXT4_IOC_WAIT_FOR_READONLY:
- /*
- * This is racy - by the time we're woken up and running,
- * the superblock could be released. And the module could
- * have been unloaded. So sue me.
- *
- * Returns 1 if it slept, else zero.
- */
- {
- struct super_block *sb = inode->i_sb;
- DECLARE_WAITQUEUE(wait, current);
- int ret = 0;
-
- set_current_state(TASK_INTERRUPTIBLE);
- add_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
- if (timer_pending(&EXT4_SB(sb)->turn_ro_timer)) {
- schedule();
- ret = 1;
- }
- remove_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
- return ret;
- }
-#endif
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
- struct super_block *sb = inode->i_sb;
int err, err2=0;
err = ext4_resize_begin(sb);
@@ -209,6 +185,13 @@
if (get_user(n_blocks_count, (__u32 __user *)arg))
return -EFAULT;
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+ ext4_msg(sb, KERN_ERR,
+ "Online resizing not supported with bigalloc");
+ return -EOPNOTSUPP;
+ }
+
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
@@ -250,6 +233,13 @@
goto mext_out;
}
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+ ext4_msg(sb, KERN_ERR,
+ "Online defrag not supported with bigalloc");
+ return -EOPNOTSUPP;
+ }
+
err = mnt_want_write(filp->f_path.mnt);
if (err)
goto mext_out;
@@ -270,7 +260,6 @@
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
- struct super_block *sb = inode->i_sb;
int err, err2=0;
err = ext4_resize_begin(sb);
@@ -281,6 +270,13 @@
sizeof(input)))
return -EFAULT;
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+ ext4_msg(sb, KERN_ERR,
+ "Online resizing not supported with bigalloc");
+ return -EOPNOTSUPP;
+ }
+
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
@@ -337,7 +333,6 @@
case FITRIM:
{
- struct super_block *sb = inode->i_sb;
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
@@ -348,7 +343,14 @@
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
- if (copy_from_user(&range, (struct fstrim_range *)arg,
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+ ext4_msg(sb, KERN_ERR,
+ "FITRIM not supported with bigalloc");
+ return -EOPNOTSUPP;
+ }
+
+ if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
@@ -358,7 +360,7 @@
if (ret < 0)
return ret;
- if (copy_to_user((struct fstrim_range *)arg, &range,
+ if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
@@ -396,11 +398,6 @@
case EXT4_IOC32_SETVERSION_OLD:
cmd = EXT4_IOC_SETVERSION_OLD;
break;
-#ifdef CONFIG_JBD2_DEBUG
- case EXT4_IOC32_WAIT_FOR_READONLY:
- cmd = EXT4_IOC_WAIT_FOR_READONLY;
- break;
-#endif
case EXT4_IOC32_GETRSVSZ:
cmd = EXT4_IOC_GETRSVSZ;
break;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 17a5a57..e2d8be8 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -70,8 +70,8 @@
*
* pa_lstart -> the logical start block for this prealloc space
* pa_pstart -> the physical start block for this prealloc space
- * pa_len -> length for this prealloc space
- * pa_free -> free space available in this prealloc space
+ * pa_len -> length for this prealloc space (in clusters)
+ * pa_free -> free space available in this prealloc space (in clusters)
*
* The inode preallocation space is used looking at the _logical_ start
* block. If only the logical file block falls within the range of prealloc
@@ -126,7 +126,8 @@
* list. In case of inode preallocation we follow a list of heuristics
* based on file size. This can be found in ext4_mb_normalize_request. If
* we are doing a group prealloc we try to normalize the request to
- * sbi->s_mb_group_prealloc. Default value of s_mb_group_prealloc is
+ * sbi->s_mb_group_prealloc. The default value of s_mb_group_prealloc is
+ * dependent on the cluster size; for non-bigalloc file systems, it is
* 512 blocks. This can be tuned via
* /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in
* terms of number of blocks. If we have mounted the file system with -O
@@ -459,7 +460,7 @@
ext4_fsblk_t blocknr;
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
- blocknr += first + i;
+ blocknr += EXT4_C2B(EXT4_SB(sb), first + i);
ext4_grp_locked_error(sb, e4b->bd_group,
inode ? inode->i_ino : 0,
blocknr,
@@ -580,7 +581,7 @@
continue;
}
- /* both bits in buddy2 must be 0 */
+ /* both bits in buddy2 must be 1 */
MB_CHECK_ASSERT(mb_test_bit(i << 1, buddy2));
MB_CHECK_ASSERT(mb_test_bit((i << 1) + 1, buddy2));
@@ -653,7 +654,7 @@
ext4_grpblk_t chunk;
unsigned short border;
- BUG_ON(len > EXT4_BLOCKS_PER_GROUP(sb));
+ BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb));
border = 2 << sb->s_blocksize_bits;
@@ -705,7 +706,7 @@
void *buddy, void *bitmap, ext4_group_t group)
{
struct ext4_group_info *grp = ext4_get_group_info(sb, group);
- ext4_grpblk_t max = EXT4_BLOCKS_PER_GROUP(sb);
+ ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb);
ext4_grpblk_t i = 0;
ext4_grpblk_t first;
ext4_grpblk_t len;
@@ -734,7 +735,7 @@
if (free != grp->bb_free) {
ext4_grp_locked_error(sb, group, 0, 0,
- "%u blocks in bitmap, %u in gd",
+ "%u clusters in bitmap, %u in gd",
free, grp->bb_free);
/*
* If we intent to continue, we consider group descritor
@@ -1339,7 +1340,7 @@
ext4_fsblk_t blocknr;
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
- blocknr += block;
+ blocknr += EXT4_C2B(EXT4_SB(sb), block);
ext4_grp_locked_error(sb, e4b->bd_group,
inode ? inode->i_ino : 0,
blocknr,
@@ -1390,7 +1391,6 @@
{
int next = block;
int max;
- int ord;
void *buddy;
assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
@@ -1432,9 +1432,8 @@
if (mb_test_bit(next, EXT4_MB_BITMAP(e4b)))
break;
- ord = mb_find_order_for_block(e4b, next);
+ order = mb_find_order_for_block(e4b, next);
- order = ord;
block = next >> order;
ex->fe_len += 1 << order;
}
@@ -1624,8 +1623,8 @@
struct ext4_free_extent *gex = &ac->ac_g_ex;
BUG_ON(ex->fe_len <= 0);
- BUG_ON(ex->fe_len > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
- BUG_ON(ex->fe_start >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+ BUG_ON(ex->fe_len > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+ BUG_ON(ex->fe_start >= EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
BUG_ON(ac->ac_status != AC_STATUS_CONTINUE);
ac->ac_found++;
@@ -1823,15 +1822,15 @@
while (free && ac->ac_status == AC_STATUS_CONTINUE) {
i = mb_find_next_zero_bit(bitmap,
- EXT4_BLOCKS_PER_GROUP(sb), i);
- if (i >= EXT4_BLOCKS_PER_GROUP(sb)) {
+ EXT4_CLUSTERS_PER_GROUP(sb), i);
+ if (i >= EXT4_CLUSTERS_PER_GROUP(sb)) {
/*
* IF we have corrupt bitmap, we won't find any
* free blocks even though group info says we
* we have free blocks
*/
ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
- "%d free blocks as per "
+ "%d free clusters as per "
"group info. But bitmap says 0",
free);
break;
@@ -1841,7 +1840,7 @@
BUG_ON(ex.fe_len <= 0);
if (free < ex.fe_len) {
ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
- "%d free blocks as per "
+ "%d free clusters as per "
"group info. But got %d blocks",
free, ex.fe_len);
/*
@@ -1887,7 +1886,7 @@
do_div(a, sbi->s_stripe);
i = (a * sbi->s_stripe) - first_group_block;
- while (i < EXT4_BLOCKS_PER_GROUP(sb)) {
+ while (i < EXT4_CLUSTERS_PER_GROUP(sb)) {
if (!mb_test_bit(i, bitmap)) {
max = mb_find_extent(e4b, 0, i, sbi->s_stripe, &ex);
if (max >= sbi->s_stripe) {
@@ -2252,10 +2251,10 @@
*/
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
meta_group_info[i]->bb_free =
- ext4_free_blocks_after_init(sb, group, desc);
+ ext4_free_clusters_after_init(sb, group, desc);
} else {
meta_group_info[i]->bb_free =
- ext4_free_blks_count(sb, desc);
+ ext4_free_group_clusters(sb, desc);
}
INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
@@ -2473,7 +2472,20 @@
sbi->s_mb_stats = MB_DEFAULT_STATS;
sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD;
sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS;
- sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
+ /*
+ * The default group preallocation is 512, which for 4k block
+ * sizes translates to 2 megabytes. However for bigalloc file
+ * systems, this is probably too big (i.e, if the cluster size
+ * is 1 megabyte, then group preallocation size becomes half a
+ * gigabyte!). As a default, we will keep a two megabyte
+ * group pralloc size for cluster sizes up to 64k, and after
+ * that, we will force a minimum group preallocation size of
+ * 32 clusters. This translates to 8 megs when the cluster
+ * size is 256k, and 32 megs when the cluster size is 1 meg,
+ * which seems reasonable as a default.
+ */
+ sbi->s_mb_group_prealloc = max(MB_DEFAULT_GROUP_PREALLOC >>
+ sbi->s_cluster_bits, 32);
/*
* If there is a s_stripe > 1, then we set the s_mb_group_prealloc
* to the lowest multiple of s_stripe which is bigger than
@@ -2490,7 +2502,7 @@
sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
if (sbi->s_locality_groups == NULL) {
ret = -ENOMEM;
- goto out;
+ goto out_free_groupinfo_slab;
}
for_each_possible_cpu(i) {
struct ext4_locality_group *lg;
@@ -2503,9 +2515,8 @@
/* init file for buddy data */
ret = ext4_mb_init_backend(sb);
- if (ret != 0) {
- goto out;
- }
+ if (ret != 0)
+ goto out_free_locality_groups;
if (sbi->s_proc)
proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
@@ -2513,11 +2524,19 @@
if (sbi->s_journal)
sbi->s_journal->j_commit_callback = release_blocks_on_commit;
+
+ return 0;
+
+out_free_locality_groups:
+ free_percpu(sbi->s_locality_groups);
+ sbi->s_locality_groups = NULL;
+out_free_groupinfo_slab:
+ ext4_groupinfo_destroy_slabs();
out:
- if (ret) {
- kfree(sbi->s_mb_offsets);
- kfree(sbi->s_mb_maxs);
- }
+ kfree(sbi->s_mb_offsets);
+ sbi->s_mb_offsets = NULL;
+ kfree(sbi->s_mb_maxs);
+ sbi->s_mb_maxs = NULL;
return ret;
}
@@ -2602,11 +2621,13 @@
}
static inline int ext4_issue_discard(struct super_block *sb,
- ext4_group_t block_group, ext4_grpblk_t block, int count)
+ ext4_group_t block_group, ext4_grpblk_t cluster, int count)
{
ext4_fsblk_t discard_block;
- discard_block = block + ext4_group_first_block_no(sb, block_group);
+ discard_block = (EXT4_C2B(EXT4_SB(sb), cluster) +
+ ext4_group_first_block_no(sb, block_group));
+ count = EXT4_C2B(EXT4_SB(sb), count);
trace_ext4_discard_blocks(sb,
(unsigned long long) discard_block, count);
return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
@@ -2633,7 +2654,7 @@
if (test_opt(sb, DISCARD))
ext4_issue_discard(sb, entry->group,
- entry->start_blk, entry->count);
+ entry->start_cluster, entry->count);
err = ext4_mb_load_buddy(sb, entry->group, &e4b);
/* we expect to find existing buddy because it's pinned */
@@ -2646,7 +2667,7 @@
ext4_lock_group(sb, entry->group);
/* Take it out of per group rb tree */
rb_erase(&entry->node, &(db->bb_free_root));
- mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count);
+ mb_free_blocks(NULL, &e4b, entry->start_cluster, entry->count);
/*
* Clear the trimmed flag for the group so that the next
@@ -2752,7 +2773,7 @@
*/
static noinline_for_stack int
ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
- handle_t *handle, unsigned int reserv_blks)
+ handle_t *handle, unsigned int reserv_clstrs)
{
struct buffer_head *bitmap_bh = NULL;
struct ext4_group_desc *gdp;
@@ -2783,7 +2804,7 @@
goto out_err;
ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
- ext4_free_blks_count(sb, gdp));
+ ext4_free_group_clusters(sb, gdp));
err = ext4_journal_get_write_access(handle, gdp_bh);
if (err)
@@ -2791,7 +2812,7 @@
block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
- len = ac->ac_b_ex.fe_len;
+ len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
if (!ext4_data_block_valid(sbi, block, len)) {
ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
"fs metadata\n", block, block+len);
@@ -2823,28 +2844,29 @@
ac->ac_b_ex.fe_len);
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
- ext4_free_blks_set(sb, gdp,
- ext4_free_blocks_after_init(sb,
- ac->ac_b_ex.fe_group, gdp));
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_clusters_after_init(sb,
+ ac->ac_b_ex.fe_group, gdp));
}
- len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len;
- ext4_free_blks_set(sb, gdp, len);
+ len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len;
+ ext4_free_group_clusters_set(sb, gdp, len);
gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
- percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
+ percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len);
/*
* Now reduce the dirty block count also. Should not go negative
*/
if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
/* release all the reserved blocks if non delalloc */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
+ reserv_clstrs);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi,
ac->ac_b_ex.fe_group);
atomic_sub(ac->ac_b_ex.fe_len,
- &sbi->s_flex_groups[flex_group].free_blocks);
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -2886,6 +2908,7 @@
ext4_mb_normalize_request(struct ext4_allocation_context *ac,
struct ext4_allocation_request *ar)
{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
int bsbits, max;
ext4_lblk_t end;
loff_t size, orig_size, start_off;
@@ -2916,7 +2939,7 @@
/* first, let's learn actual file size
* given current request is allocated */
- size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
+ size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
size = size << bsbits;
if (size < i_size_read(ac->ac_inode))
size = i_size_read(ac->ac_inode);
@@ -2988,7 +3011,8 @@
continue;
}
- pa_end = pa->pa_lstart + pa->pa_len;
+ pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
+ pa->pa_len);
/* PA must not overlap original request */
BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end ||
@@ -3018,9 +3042,11 @@
rcu_read_lock();
list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
ext4_lblk_t pa_end;
+
spin_lock(&pa->pa_lock);
if (pa->pa_deleted == 0) {
- pa_end = pa->pa_lstart + pa->pa_len;
+ pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
+ pa->pa_len);
BUG_ON(!(start >= pa_end || end <= pa->pa_lstart));
}
spin_unlock(&pa->pa_lock);
@@ -3036,14 +3062,14 @@
}
BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
start > ac->ac_o_ex.fe_logical);
- BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+ BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
/* now prepare goal request */
/* XXX: is it better to align blocks WRT to logical
* placement or satisfy big request as is */
ac->ac_g_ex.fe_logical = start;
- ac->ac_g_ex.fe_len = size;
+ ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size);
/* define goal start in order to merge */
if (ar->pright && (ar->lright == (start + size))) {
@@ -3112,14 +3138,16 @@
static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
struct ext4_prealloc_space *pa)
{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
ext4_fsblk_t start;
ext4_fsblk_t end;
int len;
/* found preallocated blocks, use them */
start = pa->pa_pstart + (ac->ac_o_ex.fe_logical - pa->pa_lstart);
- end = min(pa->pa_pstart + pa->pa_len, start + ac->ac_o_ex.fe_len);
- len = end - start;
+ end = min(pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len),
+ start + EXT4_C2B(sbi, ac->ac_o_ex.fe_len));
+ len = EXT4_NUM_B2C(sbi, end - start);
ext4_get_group_no_and_offset(ac->ac_sb, start, &ac->ac_b_ex.fe_group,
&ac->ac_b_ex.fe_start);
ac->ac_b_ex.fe_len = len;
@@ -3127,7 +3155,7 @@
ac->ac_pa = pa;
BUG_ON(start < pa->pa_pstart);
- BUG_ON(start + len > pa->pa_pstart + pa->pa_len);
+ BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len));
BUG_ON(pa->pa_free < len);
pa->pa_free -= len;
@@ -3193,6 +3221,7 @@
static noinline_for_stack int
ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
int order, i;
struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
struct ext4_locality_group *lg;
@@ -3210,12 +3239,14 @@
/* all fields in this condition don't change,
* so we can skip locking for them */
if (ac->ac_o_ex.fe_logical < pa->pa_lstart ||
- ac->ac_o_ex.fe_logical >= pa->pa_lstart + pa->pa_len)
+ ac->ac_o_ex.fe_logical >= (pa->pa_lstart +
+ EXT4_C2B(sbi, pa->pa_len)))
continue;
/* non-extent files can't have physical blocks past 2^32 */
if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
- pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS)
+ (pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len) >
+ EXT4_MAX_BLOCK_FILE_PHYS))
continue;
/* found preallocated blocks, use them */
@@ -3291,7 +3322,7 @@
while (n) {
entry = rb_entry(n, struct ext4_free_data, node);
- ext4_set_bits(bitmap, entry->start_blk, entry->count);
+ ext4_set_bits(bitmap, entry->start_cluster, entry->count);
n = rb_next(n);
}
return;
@@ -3312,7 +3343,6 @@
ext4_group_t groupnr;
ext4_grpblk_t start;
int preallocated = 0;
- int count = 0;
int len;
/* all form of preallocation discards first load group,
@@ -3335,7 +3365,6 @@
BUG_ON(groupnr != group);
ext4_set_bits(bitmap, start, len);
preallocated += len;
- count++;
}
mb_debug(1, "prellocated %u for group %u\n", preallocated, group);
}
@@ -3412,6 +3441,7 @@
ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
{
struct super_block *sb = ac->ac_sb;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_prealloc_space *pa;
struct ext4_group_info *grp;
struct ext4_inode_info *ei;
@@ -3443,16 +3473,18 @@
winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical;
/* also, we should cover whole original request */
- wins = ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len;
+ wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len);
/* the smallest one defines real window */
win = min(winl, wins);
- offs = ac->ac_o_ex.fe_logical % ac->ac_b_ex.fe_len;
+ offs = ac->ac_o_ex.fe_logical %
+ EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
if (offs && offs < win)
win = offs;
- ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical - win;
+ ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
+ EXT4_B2C(sbi, win);
BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
}
@@ -3477,7 +3509,7 @@
trace_ext4_mb_new_inode_pa(ac, pa);
ext4_mb_use_inode_pa(ac, pa);
- atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
+ atomic_add(pa->pa_free, &sbi->s_mb_preallocated);
ei = EXT4_I(ac->ac_inode);
grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group);
@@ -3592,7 +3624,7 @@
BUG_ON(pa->pa_deleted == 0);
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
- grp_blk_start = pa->pa_pstart - bit;
+ grp_blk_start = pa->pa_pstart - EXT4_C2B(sbi, bit);
BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
end = bit + pa->pa_len;
@@ -3607,7 +3639,8 @@
free += next - bit;
trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit);
- trace_ext4_mb_release_inode_pa(pa, grp_blk_start + bit,
+ trace_ext4_mb_release_inode_pa(pa, (grp_blk_start +
+ EXT4_C2B(sbi, bit)),
next - bit);
mb_free_blocks(pa->pa_inode, e4b, bit, next - bit);
bit = next + 1;
@@ -3690,7 +3723,7 @@
}
if (needed == 0)
- needed = EXT4_BLOCKS_PER_GROUP(sb) + 1;
+ needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1;
INIT_LIST_HEAD(&list);
repeat:
@@ -3958,7 +3991,7 @@
if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
return;
- size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len;
+ size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
>> bsbits;
@@ -3969,6 +4002,11 @@
return;
}
+ if (sbi->s_mb_group_prealloc <= 0) {
+ ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
+ return;
+ }
+
/* don't use group allocation for large files */
size = max(size, isize);
if (size > sbi->s_mb_stream_request) {
@@ -4007,8 +4045,8 @@
len = ar->len;
/* just a dirty hack to filter too big requests */
- if (len >= EXT4_BLOCKS_PER_GROUP(sb) - 10)
- len = EXT4_BLOCKS_PER_GROUP(sb) - 10;
+ if (len >= EXT4_CLUSTERS_PER_GROUP(sb) - 10)
+ len = EXT4_CLUSTERS_PER_GROUP(sb) - 10;
/* start searching from the goal */
goal = ar->goal;
@@ -4019,18 +4057,15 @@
/* set up allocation goals */
memset(ac, 0, sizeof(struct ext4_allocation_context));
- ac->ac_b_ex.fe_logical = ar->logical;
+ ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
ac->ac_status = AC_STATUS_CONTINUE;
ac->ac_sb = sb;
ac->ac_inode = ar->inode;
- ac->ac_o_ex.fe_logical = ar->logical;
+ ac->ac_o_ex.fe_logical = ac->ac_b_ex.fe_logical;
ac->ac_o_ex.fe_group = group;
ac->ac_o_ex.fe_start = block;
ac->ac_o_ex.fe_len = len;
- ac->ac_g_ex.fe_logical = ar->logical;
- ac->ac_g_ex.fe_group = group;
- ac->ac_g_ex.fe_start = block;
- ac->ac_g_ex.fe_len = len;
+ ac->ac_g_ex = ac->ac_o_ex;
ac->ac_flags = ar->flags;
/* we have to define context: we'll we work with a file or
@@ -4182,13 +4217,14 @@
*/
static int ext4_mb_release_context(struct ext4_allocation_context *ac)
{
+ struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
struct ext4_prealloc_space *pa = ac->ac_pa;
if (pa) {
if (pa->pa_type == MB_GROUP_PA) {
/* see comment in ext4_mb_use_group_pa() */
spin_lock(&pa->pa_lock);
- pa->pa_pstart += ac->ac_b_ex.fe_len;
- pa->pa_lstart += ac->ac_b_ex.fe_len;
+ pa->pa_pstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
+ pa->pa_lstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
pa->pa_free -= ac->ac_b_ex.fe_len;
pa->pa_len -= ac->ac_b_ex.fe_len;
spin_unlock(&pa->pa_lock);
@@ -4249,13 +4285,17 @@
struct super_block *sb;
ext4_fsblk_t block = 0;
unsigned int inquota = 0;
- unsigned int reserv_blks = 0;
+ unsigned int reserv_clstrs = 0;
sb = ar->inode->i_sb;
sbi = EXT4_SB(sb);
trace_ext4_request_blocks(ar);
+ /* Allow to use superuser reservation for quota file */
+ if (IS_NOQUOTA(ar->inode))
+ ar->flags |= EXT4_MB_USE_ROOT_BLOCKS;
+
/*
* For delayed allocation, we could skip the ENOSPC and
* EDQUOT check, as blocks and quotas have been already
@@ -4269,7 +4309,7 @@
* and verify allocation doesn't exceed the quota limits.
*/
while (ar->len &&
- ext4_claim_free_blocks(sbi, ar->len, ar->flags)) {
+ ext4_claim_free_clusters(sbi, ar->len, ar->flags)) {
/* let others to free the space */
yield();
@@ -4279,12 +4319,14 @@
*errp = -ENOSPC;
return 0;
}
- reserv_blks = ar->len;
+ reserv_clstrs = ar->len;
if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) {
- dquot_alloc_block_nofail(ar->inode, ar->len);
+ dquot_alloc_block_nofail(ar->inode,
+ EXT4_C2B(sbi, ar->len));
} else {
while (ar->len &&
- dquot_alloc_block(ar->inode, ar->len)) {
+ dquot_alloc_block(ar->inode,
+ EXT4_C2B(sbi, ar->len))) {
ar->flags |= EXT4_MB_HINT_NOPREALLOC;
ar->len--;
@@ -4328,7 +4370,7 @@
ext4_mb_new_preallocation(ac);
}
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
- *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
+ *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
if (*errp == -EAGAIN) {
/*
* drop the reference that we took
@@ -4364,13 +4406,13 @@
if (ac)
kmem_cache_free(ext4_ac_cachep, ac);
if (inquota && ar->len < inquota)
- dquot_free_block(ar->inode, inquota - ar->len);
+ dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len));
if (!ar->len) {
if (!ext4_test_inode_state(ar->inode,
EXT4_STATE_DELALLOC_RESERVED))
/* release all the reserved blocks if non delalloc */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
- reserv_blks);
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
+ reserv_clstrs);
}
trace_ext4_allocate_blocks(ar, (unsigned long long)block);
@@ -4388,7 +4430,7 @@
{
if ((entry1->t_tid == entry2->t_tid) &&
(entry1->group == entry2->group) &&
- ((entry1->start_blk + entry1->count) == entry2->start_blk))
+ ((entry1->start_cluster + entry1->count) == entry2->start_cluster))
return 1;
return 0;
}
@@ -4398,7 +4440,7 @@
struct ext4_free_data *new_entry)
{
ext4_group_t group = e4b->bd_group;
- ext4_grpblk_t block;
+ ext4_grpblk_t cluster;
struct ext4_free_data *entry;
struct ext4_group_info *db = e4b->bd_info;
struct super_block *sb = e4b->bd_sb;
@@ -4411,7 +4453,7 @@
BUG_ON(e4b->bd_buddy_page == NULL);
new_node = &new_entry->node;
- block = new_entry->start_blk;
+ cluster = new_entry->start_cluster;
if (!*n) {
/* first free block exent. We need to
@@ -4425,13 +4467,14 @@
while (*n) {
parent = *n;
entry = rb_entry(parent, struct ext4_free_data, node);
- if (block < entry->start_blk)
+ if (cluster < entry->start_cluster)
n = &(*n)->rb_left;
- else if (block >= (entry->start_blk + entry->count))
+ else if (cluster >= (entry->start_cluster + entry->count))
n = &(*n)->rb_right;
else {
ext4_grp_locked_error(sb, group, 0,
- ext4_group_first_block_no(sb, group) + block,
+ ext4_group_first_block_no(sb, group) +
+ EXT4_C2B(sbi, cluster),
"Block already on to-be-freed list");
return 0;
}
@@ -4445,7 +4488,7 @@
if (node) {
entry = rb_entry(node, struct ext4_free_data, node);
if (can_merge(entry, new_entry)) {
- new_entry->start_blk = entry->start_blk;
+ new_entry->start_cluster = entry->start_cluster;
new_entry->count += entry->count;
rb_erase(node, &(db->bb_free_root));
spin_lock(&sbi->s_md_lock);
@@ -4496,6 +4539,7 @@
ext4_group_t block_group;
struct ext4_sb_info *sbi;
struct ext4_buddy e4b;
+ unsigned int count_clusters;
int err = 0;
int ret;
@@ -4544,6 +4588,38 @@
if (!ext4_should_writeback_data(inode))
flags |= EXT4_FREE_BLOCKS_METADATA;
+ /*
+ * If the extent to be freed does not begin on a cluster
+ * boundary, we need to deal with partial clusters at the
+ * beginning and end of the extent. Normally we will free
+ * blocks at the beginning or the end unless we are explicitly
+ * requested to avoid doing so.
+ */
+ overflow = block & (sbi->s_cluster_ratio - 1);
+ if (overflow) {
+ if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
+ overflow = sbi->s_cluster_ratio - overflow;
+ block += overflow;
+ if (count > overflow)
+ count -= overflow;
+ else
+ return;
+ } else {
+ block -= overflow;
+ count += overflow;
+ }
+ }
+ overflow = count & (sbi->s_cluster_ratio - 1);
+ if (overflow) {
+ if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
+ if (count > overflow)
+ count -= overflow;
+ else
+ return;
+ } else
+ count += sbi->s_cluster_ratio - overflow;
+ }
+
do_more:
overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
@@ -4552,10 +4628,12 @@
* Check to see if we are freeing blocks across a group
* boundary.
*/
- if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
- overflow = bit + count - EXT4_BLOCKS_PER_GROUP(sb);
+ if (EXT4_C2B(sbi, bit) + count > EXT4_BLOCKS_PER_GROUP(sb)) {
+ overflow = EXT4_C2B(sbi, bit) + count -
+ EXT4_BLOCKS_PER_GROUP(sb);
count -= overflow;
}
+ count_clusters = EXT4_B2C(sbi, count);
bitmap_bh = ext4_read_block_bitmap(sb, block_group);
if (!bitmap_bh) {
err = -EIO;
@@ -4570,9 +4648,9 @@
if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
in_range(block, ext4_inode_table(sb, gdp),
- EXT4_SB(sb)->s_itb_per_group) ||
+ EXT4_SB(sb)->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, gdp),
- EXT4_SB(sb)->s_itb_per_group)) {
+ EXT4_SB(sb)->s_itb_per_group)) {
ext4_error(sb, "Freeing blocks in system zone - "
"Block = %llu, count = %lu", block, count);
@@ -4597,11 +4675,11 @@
#ifdef AGGRESSIVE_CHECK
{
int i;
- for (i = 0; i < count; i++)
+ for (i = 0; i < count_clusters; i++)
BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data));
}
#endif
- trace_ext4_mballoc_free(sb, inode, block_group, bit, count);
+ trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
err = ext4_mb_load_buddy(sb, block_group, &e4b);
if (err)
@@ -4618,13 +4696,13 @@
err = -ENOMEM;
goto error_return;
}
- new_entry->start_blk = bit;
+ new_entry->start_cluster = bit;
new_entry->group = block_group;
- new_entry->count = count;
+ new_entry->count = count_clusters;
new_entry->t_tid = handle->h_transaction->t_tid;
ext4_lock_group(sb, block_group);
- mb_clear_bits(bitmap_bh->b_data, bit, count);
+ mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
ext4_mb_free_metadata(handle, &e4b, new_entry);
} else {
/* need to update group_info->bb_free and bitmap
@@ -4632,25 +4710,29 @@
* them with group lock_held
*/
ext4_lock_group(sb, block_group);
- mb_clear_bits(bitmap_bh->b_data, bit, count);
- mb_free_blocks(inode, &e4b, bit, count);
+ mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
+ mb_free_blocks(inode, &e4b, bit, count_clusters);
}
- ret = ext4_free_blks_count(sb, gdp) + count;
- ext4_free_blks_set(sb, gdp, ret);
+ ret = ext4_free_group_clusters(sb, gdp) + count_clusters;
+ ext4_free_group_clusters_set(sb, gdp, ret);
gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
ext4_unlock_group(sb, block_group);
- percpu_counter_add(&sbi->s_freeblocks_counter, count);
+ percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic_add(count, &sbi->s_flex_groups[flex_group].free_blocks);
+ atomic_add(count_clusters,
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
ext4_mb_unload_buddy(&e4b);
freed += count;
+ if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+ dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
+
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -4669,8 +4751,6 @@
}
ext4_mark_super_dirty(sb);
error_return:
- if (freed && !(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
- dquot_free_block(inode, freed);
brelse(bitmap_bh);
ext4_std_error(sb, err);
return;
@@ -4778,16 +4858,17 @@
ext4_lock_group(sb, block_group);
mb_clear_bits(bitmap_bh->b_data, bit, count);
mb_free_blocks(NULL, &e4b, bit, count);
- blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
- ext4_free_blks_set(sb, desc, blk_free_count);
+ blk_free_count = blocks_freed + ext4_free_group_clusters(sb, desc);
+ ext4_free_group_clusters_set(sb, desc, blk_free_count);
desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
ext4_unlock_group(sb, block_group);
- percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
+ percpu_counter_add(&sbi->s_freeclusters_counter,
+ EXT4_B2C(sbi, blocks_freed));
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic_add(blocks_freed,
- &sbi->s_flex_groups[flex_group].free_blocks);
+ atomic_add(EXT4_B2C(sbi, blocks_freed),
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
ext4_mb_unload_buddy(&e4b);
@@ -4948,7 +5029,7 @@
struct ext4_group_info *grp;
ext4_group_t first_group, last_group;
ext4_group_t group, ngroups = ext4_get_groups_count(sb);
- ext4_grpblk_t cnt = 0, first_block, last_block;
+ ext4_grpblk_t cnt = 0, first_cluster, last_cluster;
uint64_t start, len, minlen, trimmed = 0;
ext4_fsblk_t first_data_blk =
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
@@ -4958,7 +5039,7 @@
len = range->len >> sb->s_blocksize_bits;
minlen = range->minlen >> sb->s_blocksize_bits;
- if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
+ if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)))
return -EINVAL;
if (start + len <= first_data_blk)
goto out;
@@ -4969,11 +5050,11 @@
/* Determine first and last group to examine based on start and len */
ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start,
- &first_group, &first_block);
+ &first_group, &first_cluster);
ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) (start + len),
- &last_group, &last_block);
+ &last_group, &last_cluster);
last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
- last_block = EXT4_BLOCKS_PER_GROUP(sb);
+ last_cluster = EXT4_CLUSTERS_PER_GROUP(sb);
if (first_group > last_group)
return -EINVAL;
@@ -4993,20 +5074,20 @@
* change it for the last group in which case start +
* len < EXT4_BLOCKS_PER_GROUP(sb).
*/
- if (first_block + len < EXT4_BLOCKS_PER_GROUP(sb))
- last_block = first_block + len;
- len -= last_block - first_block;
+ if (first_cluster + len < EXT4_CLUSTERS_PER_GROUP(sb))
+ last_cluster = first_cluster + len;
+ len -= last_cluster - first_cluster;
if (grp->bb_free >= minlen) {
- cnt = ext4_trim_all_free(sb, group, first_block,
- last_block, minlen);
+ cnt = ext4_trim_all_free(sb, group, first_cluster,
+ last_cluster, minlen);
if (cnt < 0) {
ret = cnt;
break;
}
}
trimmed += cnt;
- first_block = 0;
+ first_cluster = 0;
}
range->len = trimmed * sb->s_blocksize;
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 9d4a636..47705f3 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -106,7 +106,7 @@
ext4_group_t group;
/* free block extent */
- ext4_grpblk_t start_blk;
+ ext4_grpblk_t start_cluster;
ext4_grpblk_t count;
/* transaction which freed this extent */
@@ -139,9 +139,9 @@
struct ext4_free_extent {
ext4_lblk_t fe_logical;
- ext4_grpblk_t fe_start;
+ ext4_grpblk_t fe_start; /* In cluster units */
ext4_group_t fe_group;
- ext4_grpblk_t fe_len;
+ ext4_grpblk_t fe_len; /* In cluster units */
};
/*
@@ -175,7 +175,7 @@
/* the best found extent */
struct ext4_free_extent ac_b_ex;
- /* copy of the bext found extent taken before preallocation efforts */
+ /* copy of the best found extent taken before preallocation efforts */
struct ext4_free_extent ac_f_ex;
/* number of iterations done. we have to track to limit searching */
@@ -216,6 +216,7 @@
static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
struct ext4_free_extent *fex)
{
- return ext4_group_first_block_no(sb, fex->fe_group) + fex->fe_start;
+ return ext4_group_first_block_no(sb, fex->fe_group) +
+ (fex->fe_start << EXT4_SB(sb)->s_cluster_bits);
}
#endif
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b57b98f..16ac228 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -15,19 +15,18 @@
#include <linux/module.h>
#include <linux/slab.h>
#include "ext4_jbd2.h"
-#include "ext4_extents.h"
/*
* The contiguous blocks details which can be
* represented by a single extent
*/
-struct list_blocks_struct {
- ext4_lblk_t first_block, last_block;
+struct migrate_struct {
+ ext4_lblk_t first_block, last_block, curr_block;
ext4_fsblk_t first_pblock, last_pblock;
};
static int finish_range(handle_t *handle, struct inode *inode,
- struct list_blocks_struct *lb)
+ struct migrate_struct *lb)
{
int retval = 0, needed;
@@ -87,8 +86,7 @@
}
static int update_extent_range(handle_t *handle, struct inode *inode,
- ext4_fsblk_t pblock, ext4_lblk_t blk_num,
- struct list_blocks_struct *lb)
+ ext4_fsblk_t pblock, struct migrate_struct *lb)
{
int retval;
/*
@@ -96,9 +94,10 @@
*/
if (lb->first_pblock &&
(lb->last_pblock+1 == pblock) &&
- (lb->last_block+1 == blk_num)) {
+ (lb->last_block+1 == lb->curr_block)) {
lb->last_pblock = pblock;
- lb->last_block = blk_num;
+ lb->last_block = lb->curr_block;
+ lb->curr_block++;
return 0;
}
/*
@@ -106,64 +105,49 @@
*/
retval = finish_range(handle, inode, lb);
lb->first_pblock = lb->last_pblock = pblock;
- lb->first_block = lb->last_block = blk_num;
-
+ lb->first_block = lb->last_block = lb->curr_block;
+ lb->curr_block++;
return retval;
}
static int update_ind_extent_range(handle_t *handle, struct inode *inode,
- ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
- struct list_blocks_struct *lb)
+ ext4_fsblk_t pblock,
+ struct migrate_struct *lb)
{
struct buffer_head *bh;
__le32 *i_data;
int i, retval = 0;
- ext4_lblk_t blk_count = *blk_nump;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
- if (!pblock) {
- /* Only update the file block number */
- *blk_nump += max_entries;
- return 0;
- }
-
bh = sb_bread(inode->i_sb, pblock);
if (!bh)
return -EIO;
i_data = (__le32 *)bh->b_data;
- for (i = 0; i < max_entries; i++, blk_count++) {
+ for (i = 0; i < max_entries; i++) {
if (i_data[i]) {
retval = update_extent_range(handle, inode,
- le32_to_cpu(i_data[i]),
- blk_count, lb);
+ le32_to_cpu(i_data[i]), lb);
if (retval)
break;
+ } else {
+ lb->curr_block++;
}
}
-
- /* Update the file block number */
- *blk_nump = blk_count;
put_bh(bh);
return retval;
}
static int update_dind_extent_range(handle_t *handle, struct inode *inode,
- ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
- struct list_blocks_struct *lb)
+ ext4_fsblk_t pblock,
+ struct migrate_struct *lb)
{
struct buffer_head *bh;
__le32 *i_data;
int i, retval = 0;
- ext4_lblk_t blk_count = *blk_nump;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
- if (!pblock) {
- /* Only update the file block number */
- *blk_nump += max_entries * max_entries;
- return 0;
- }
bh = sb_bread(inode->i_sb, pblock);
if (!bh)
return -EIO;
@@ -172,38 +156,28 @@
for (i = 0; i < max_entries; i++) {
if (i_data[i]) {
retval = update_ind_extent_range(handle, inode,
- le32_to_cpu(i_data[i]),
- &blk_count, lb);
+ le32_to_cpu(i_data[i]), lb);
if (retval)
break;
} else {
/* Only update the file block number */
- blk_count += max_entries;
+ lb->curr_block += max_entries;
}
}
-
- /* Update the file block number */
- *blk_nump = blk_count;
put_bh(bh);
return retval;
}
static int update_tind_extent_range(handle_t *handle, struct inode *inode,
- ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
- struct list_blocks_struct *lb)
+ ext4_fsblk_t pblock,
+ struct migrate_struct *lb)
{
struct buffer_head *bh;
__le32 *i_data;
int i, retval = 0;
- ext4_lblk_t blk_count = *blk_nump;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
- if (!pblock) {
- /* Only update the file block number */
- *blk_nump += max_entries * max_entries * max_entries;
- return 0;
- }
bh = sb_bread(inode->i_sb, pblock);
if (!bh)
return -EIO;
@@ -212,16 +186,14 @@
for (i = 0; i < max_entries; i++) {
if (i_data[i]) {
retval = update_dind_extent_range(handle, inode,
- le32_to_cpu(i_data[i]),
- &blk_count, lb);
+ le32_to_cpu(i_data[i]), lb);
if (retval)
break;
- } else
+ } else {
/* Only update the file block number */
- blk_count += max_entries * max_entries;
+ lb->curr_block += max_entries * max_entries;
+ }
}
- /* Update the file block number */
- *blk_nump = blk_count;
put_bh(bh);
return retval;
@@ -462,12 +434,12 @@
handle_t *handle;
int retval = 0, i;
__le32 *i_data;
- ext4_lblk_t blk_count = 0;
struct ext4_inode_info *ei;
struct inode *tmp_inode = NULL;
- struct list_blocks_struct lb;
+ struct migrate_struct lb;
unsigned long max_entries;
__u32 goal;
+ uid_t owner[2];
/*
* If the filesystem does not support extents, or the inode
@@ -495,10 +467,12 @@
}
goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
+ owner[0] = inode->i_uid;
+ owner[1] = inode->i_gid;
tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
- S_IFREG, NULL, goal);
+ S_IFREG, NULL, goal, owner);
if (IS_ERR(tmp_inode)) {
- retval = -ENOMEM;
+ retval = PTR_ERR(inode);
ext4_journal_stop(handle);
return retval;
}
@@ -507,7 +481,7 @@
* Set the i_nlink to zero so it will be deleted later
* when we drop inode reference.
*/
- tmp_inode->i_nlink = 0;
+ clear_nlink(tmp_inode);
ext4_ext_tree_init(handle, tmp_inode);
ext4_orphan_add(handle, tmp_inode);
@@ -551,35 +525,32 @@
/* 32 bit block address 4 bytes */
max_entries = inode->i_sb->s_blocksize >> 2;
- for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) {
+ for (i = 0; i < EXT4_NDIR_BLOCKS; i++) {
if (i_data[i]) {
retval = update_extent_range(handle, tmp_inode,
- le32_to_cpu(i_data[i]),
- blk_count, &lb);
+ le32_to_cpu(i_data[i]), &lb);
if (retval)
goto err_out;
- }
+ } else
+ lb.curr_block++;
}
if (i_data[EXT4_IND_BLOCK]) {
retval = update_ind_extent_range(handle, tmp_inode,
- le32_to_cpu(i_data[EXT4_IND_BLOCK]),
- &blk_count, &lb);
+ le32_to_cpu(i_data[EXT4_IND_BLOCK]), &lb);
if (retval)
goto err_out;
} else
- blk_count += max_entries;
+ lb.curr_block += max_entries;
if (i_data[EXT4_DIND_BLOCK]) {
retval = update_dind_extent_range(handle, tmp_inode,
- le32_to_cpu(i_data[EXT4_DIND_BLOCK]),
- &blk_count, &lb);
+ le32_to_cpu(i_data[EXT4_DIND_BLOCK]), &lb);
if (retval)
goto err_out;
} else
- blk_count += max_entries * max_entries;
+ lb.curr_block += max_entries * max_entries;
if (i_data[EXT4_TIND_BLOCK]) {
retval = update_tind_extent_range(handle, tmp_inode,
- le32_to_cpu(i_data[EXT4_TIND_BLOCK]),
- &blk_count, &lb);
+ le32_to_cpu(i_data[EXT4_TIND_BLOCK]), &lb);
if (retval)
goto err_out;
}
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 9bdef3f..7ea4ba4 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -109,7 +109,7 @@
mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
bdevname(bh->b_bdev, mmp->mmp_bdevname);
- memcpy(mmp->mmp_nodename, init_utsname()->sysname,
+ memcpy(mmp->mmp_nodename, init_utsname()->nodename,
sizeof(mmp->mmp_nodename));
while (!kthread_should_stop()) {
@@ -125,8 +125,9 @@
* Don't spew too many error messages. Print one every
* (s_mmp_update_interval * 60) seconds.
*/
- if (retval && (failed_writes % 60) == 0) {
- ext4_error(sb, "Error writing to MMP block");
+ if (retval) {
+ if ((failed_writes % 60) == 0)
+ ext4_error(sb, "Error writing to MMP block");
failed_writes++;
}
@@ -295,7 +296,8 @@
/*
* write a new random sequence number.
*/
- mmp->mmp_seq = seq = cpu_to_le32(mmp_new_seq());
+ seq = mmp_new_seq();
+ mmp->mmp_seq = cpu_to_le32(seq);
retval = write_mmp_block(bh);
if (retval)
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index f57455a..c5826c6 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -17,7 +17,6 @@
#include <linux/quotaops.h>
#include <linux/slab.h>
#include "ext4_jbd2.h"
-#include "ext4_extents.h"
#include "ext4.h"
/**
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1c924fa..aa4c782 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1586,7 +1586,7 @@
dxtrace(dx_show_index("node", frames[1].entries));
dxtrace(dx_show_index("node",
((struct dx_node *) bh2->b_data)->entries));
- err = ext4_handle_dirty_metadata(handle, inode, bh2);
+ err = ext4_handle_dirty_metadata(handle, dir, bh2);
if (err)
goto journal_error;
brelse (bh2);
@@ -1612,7 +1612,7 @@
if (err)
goto journal_error;
}
- err = ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
+ err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh);
if (err) {
ext4_std_error(inode->i_sb, err);
goto cleanup;
@@ -1694,7 +1694,7 @@
if (is_dx(inode) && inode->i_nlink > 1) {
/* limit is 16-bit i_links_count */
if (inode->i_nlink >= EXT4_LINK_MAX || inode->i_nlink == 2) {
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
EXT4_SET_RO_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_RO_COMPAT_DIR_NLINK);
}
@@ -1707,9 +1707,8 @@
*/
static void ext4_dec_count(handle_t *handle, struct inode *inode)
{
- drop_nlink(inode);
- if (S_ISDIR(inode->i_mode) && inode->i_nlink == 0)
- inc_nlink(inode);
+ if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
+ drop_nlink(inode);
}
@@ -1756,7 +1755,7 @@
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
- inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
+ inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
inode->i_op = &ext4_file_inode_operations;
@@ -1792,7 +1791,7 @@
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
- inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
+ inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
@@ -1832,7 +1831,7 @@
ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFDIR | mode,
- &dentry->d_name, 0);
+ &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
@@ -1861,9 +1860,9 @@
de->name_len = 2;
strcpy(de->name, "..");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, dir, dir_block);
+ err = ext4_handle_dirty_metadata(handle, inode, dir_block);
if (err)
goto out_clear_inode;
err = ext4_mark_inode_dirty(handle, inode);
@@ -2214,7 +2213,7 @@
ext4_warning(inode->i_sb,
"Deleting nonexistent file (%lu), %d",
inode->i_ino, inode->i_nlink);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
@@ -2279,7 +2278,7 @@
ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO,
- &dentry->d_name, 0);
+ &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
@@ -2530,7 +2529,7 @@
PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
cpu_to_le32(new_dir->i_ino);
BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
- retval = ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
+ retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh);
if (retval) {
ext4_std_error(old_dir->i_sb, retval);
goto end_rename;
@@ -2539,7 +2538,7 @@
if (new_inode) {
/* checked empty_dir above, can't have another parent,
* ext4_dec_count() won't work for many-linked dirs */
- new_inode->i_nlink = 0;
+ clear_nlink(new_inode);
} else {
ext4_inc_count(handle, new_dir);
ext4_update_dx_flag(new_dir);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 92f38ee..7ce1d0b 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -70,7 +70,6 @@
void ext4_free_io_end(ext4_io_end_t *io)
{
int i;
- wait_queue_head_t *wq;
BUG_ON(!io);
if (io->page)
@@ -78,56 +77,43 @@
for (i = 0; i < io->num_io_pages; i++)
put_io_page(io->pages[i]);
io->num_io_pages = 0;
- wq = ext4_ioend_wq(io->inode);
- if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
- waitqueue_active(wq))
- wake_up_all(wq);
+ if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count))
+ wake_up_all(ext4_ioend_wq(io->inode));
kmem_cache_free(io_end_cachep, io);
}
/*
* check a range of space and convert unwritten extents to written.
+ *
+ * Called with inode->i_mutex; we depend on this when we manipulate
+ * io->flag, since we could otherwise race with ext4_flush_completed_IO()
*/
int ext4_end_io_nolock(ext4_io_end_t *io)
{
struct inode *inode = io->inode;
loff_t offset = io->offset;
ssize_t size = io->size;
- wait_queue_head_t *wq;
int ret = 0;
ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
"list->prev 0x%p\n",
io, inode->i_ino, io->list.next, io->list.prev);
- if (list_empty(&io->list))
- return ret;
-
- if (!(io->flag & EXT4_IO_END_UNWRITTEN))
- return ret;
-
ret = ext4_convert_unwritten_extents(inode, offset, size);
if (ret < 0) {
- printk(KERN_EMERG "%s: failed to convert unwritten "
- "extents to written extents, error is %d "
- "io is still on inode %lu aio dio list\n",
- __func__, ret, inode->i_ino);
- return ret;
+ ext4_msg(inode->i_sb, KERN_EMERG,
+ "failed to convert unwritten extents to written "
+ "extents -- potential data loss! "
+ "(inode %lu, offset %llu, size %zd, error %d)",
+ inode->i_ino, offset, size, ret);
}
if (io->iocb)
aio_complete(io->iocb, io->result, 0);
- /* clear the DIO AIO unwritten flag */
- if (io->flag & EXT4_IO_END_UNWRITTEN) {
- io->flag &= ~EXT4_IO_END_UNWRITTEN;
- /* Wake up anyone waiting on unwritten extent conversion */
- wq = ext4_ioend_wq(io->inode);
- if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) &&
- waitqueue_active(wq)) {
- wake_up_all(wq);
- }
- }
+ /* Wake up anyone waiting on unwritten extent conversion */
+ if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten))
+ wake_up_all(ext4_ioend_wq(io->inode));
return ret;
}
@@ -140,9 +126,15 @@
struct inode *inode = io->inode;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned long flags;
- int ret;
+
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ if (list_empty(&io->list)) {
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+ goto free;
+ }
if (!mutex_trylock(&inode->i_mutex)) {
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
/*
* Requeue the work instead of waiting so that the work
* items queued after this can be processed.
@@ -159,17 +151,11 @@
io->flag |= EXT4_IO_END_QUEUED;
return;
}
- ret = ext4_end_io_nolock(io);
- if (ret < 0) {
- mutex_unlock(&inode->i_mutex);
- return;
- }
-
- spin_lock_irqsave(&ei->i_completed_io_lock, flags);
- if (!list_empty(&io->list))
- list_del_init(&io->list);
+ list_del_init(&io->list);
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+ (void) ext4_end_io_nolock(io);
mutex_unlock(&inode->i_mutex);
+free:
ext4_free_io_end(io);
}
@@ -350,10 +336,8 @@
if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
(io_end->pages[io_end->num_io_pages-1] != io_page))
goto submit_and_retry;
- if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
- io_end->flag |= EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
- }
+ if (buffer_uninit(bh))
+ ext4_set_io_unwritten_flag(inode, io_end);
io->io_end->size += bh->b_size;
io->io_next_block++;
ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 707d3f1..996780a 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -875,7 +875,7 @@
ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
- ext4_free_blks_set(sb, gdp, input->free_blocks_count);
+ ext4_free_group_clusters_set(sb, gdp, input->free_blocks_count);
ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
gdp->bg_flags = cpu_to_le16(EXT4_BG_INODE_ZEROED);
gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
@@ -937,8 +937,8 @@
input->reserved_blocks);
/* Update the free space counts */
- percpu_counter_add(&sbi->s_freeblocks_counter,
- input->free_blocks_count);
+ percpu_counter_add(&sbi->s_freeclusters_counter,
+ EXT4_B2C(sbi, input->free_blocks_count));
percpu_counter_add(&sbi->s_freeinodes_counter,
EXT4_INODES_PER_GROUP(sb));
@@ -946,8 +946,8 @@
sbi->s_log_groups_per_flex) {
ext4_group_t flex_group;
flex_group = ext4_flex_group(sbi, input->group);
- atomic_add(input->free_blocks_count,
- &sbi->s_flex_groups[flex_group].free_blocks);
+ atomic_add(EXT4_B2C(sbi, input->free_blocks_count),
+ &sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(EXT4_INODES_PER_GROUP(sb),
&sbi->s_flex_groups[flex_group].free_inodes);
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 44d0c8d..9953d80 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -45,6 +45,7 @@
#include <linux/freezer.h>
#include "ext4.h"
+#include "ext4_extents.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
@@ -163,8 +164,8 @@
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}
-__u32 ext4_free_blks_count(struct super_block *sb,
- struct ext4_group_desc *bg)
+__u32 ext4_free_group_clusters(struct super_block *sb,
+ struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_free_blocks_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
@@ -219,8 +220,8 @@
bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
}
-void ext4_free_blks_set(struct super_block *sb,
- struct ext4_group_desc *bg, __u32 count)
+void ext4_free_group_clusters_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
{
bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
@@ -414,6 +415,22 @@
ext4_commit_super(sb, 1);
}
+/*
+ * The del_gendisk() function uninitializes the disk-specific data
+ * structures, including the bdi structure, without telling anyone
+ * else. Once this happens, any attempt to call mark_buffer_dirty()
+ * (for example, by ext4_commit_super), will cause a kernel OOPS.
+ * This is a kludge to prevent these oops until we can put in a proper
+ * hook in del_gendisk() to inform the VFS and file system layers.
+ */
+static int block_device_ejected(struct super_block *sb)
+{
+ struct inode *bd_inode = sb->s_bdev->bd_inode;
+ struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info;
+
+ return bdi->dev == NULL;
+}
+
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
@@ -821,10 +838,10 @@
brelse(sbi->s_group_desc[i]);
ext4_kvfree(sbi->s_group_desc);
ext4_kvfree(sbi->s_flex_groups);
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+ percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
@@ -1057,8 +1074,6 @@
seq_puts(seq, ",nouid32");
if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG))
seq_puts(seq, ",debug");
- if (test_opt(sb, OLDALLOC))
- seq_puts(seq, ",oldalloc");
#ifdef CONFIG_EXT4_FS_XATTR
if (test_opt(sb, XATTR_USER))
seq_puts(seq, ",user_xattr");
@@ -1567,10 +1582,12 @@
set_opt(sb, DEBUG);
break;
case Opt_oldalloc:
- set_opt(sb, OLDALLOC);
+ ext4_msg(sb, KERN_WARNING,
+ "Ignoring deprecated oldalloc option");
break;
case Opt_orlov:
- clear_opt(sb, OLDALLOC);
+ ext4_msg(sb, KERN_WARNING,
+ "Ignoring deprecated orlov option");
break;
#ifdef CONFIG_EXT4_FS_XATTR
case Opt_user_xattr:
@@ -1801,6 +1818,7 @@
break;
case Opt_nodelalloc:
clear_opt(sb, DELALLOC);
+ clear_opt2(sb, EXPLICIT_DELALLOC);
break;
case Opt_mblk_io_submit:
set_opt(sb, MBLK_IO_SUBMIT);
@@ -1817,6 +1835,7 @@
break;
case Opt_delalloc:
set_opt(sb, DELALLOC);
+ set_opt2(sb, EXPLICIT_DELALLOC);
break;
case Opt_block_validity:
set_opt(sb, BLOCK_VALIDITY);
@@ -1935,7 +1954,7 @@
res = MS_RDONLY;
}
if (read_only)
- return res;
+ goto done;
if (!(sbi->s_mount_state & EXT4_VALID_FS))
ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
"running e2fsck is recommended");
@@ -1966,6 +1985,7 @@
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
+done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
"bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
@@ -2015,8 +2035,8 @@
flex_group = ext4_flex_group(sbi, i);
atomic_add(ext4_free_inodes_count(sb, gdp),
&sbi->s_flex_groups[flex_group].free_inodes);
- atomic_add(ext4_free_blks_count(sb, gdp),
- &sbi->s_flex_groups[flex_group].free_blocks);
+ atomic_add(ext4_free_group_clusters(sb, gdp),
+ &sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(ext4_used_dirs_count(sb, gdp),
&sbi->s_flex_groups[flex_group].used_dirs);
}
@@ -2134,7 +2154,8 @@
if (NULL != first_not_zeroed)
*first_not_zeroed = grp;
- ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
+ ext4_free_blocks_count_set(sbi->s_es,
+ EXT4_C2B(sbi, ext4_count_free_clusters(sb)));
sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
return 1;
}
@@ -2454,7 +2475,8 @@
char *buf)
{
return snprintf(buf, PAGE_SIZE, "%llu\n",
- (s64) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ (s64) EXT4_C2B(sbi,
+ percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
}
static ssize_t session_write_kbytes_show(struct ext4_attr *a,
@@ -2682,6 +2704,13 @@
return 0;
}
}
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC) &&
+ !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+ ext4_msg(sb, KERN_ERR,
+ "Can't support bigalloc feature without "
+ "extents feature\n");
+ return 0;
+ }
return 1;
}
@@ -3087,10 +3116,10 @@
char *cp;
const char *descr;
int ret = -ENOMEM;
- int blocksize;
+ int blocksize, clustersize;
unsigned int db_count;
unsigned int i;
- int needs_recovery, has_huge_files;
+ int needs_recovery, has_huge_files, has_bigalloc;
__u64 blocks_count;
int err;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
@@ -3224,6 +3253,33 @@
&journal_ioprio, NULL, 0))
goto failed_mount;
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
+ "with data=journal disables delayed "
+ "allocation and O_DIRECT support!\n");
+ if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ goto failed_mount;
+ }
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ goto failed_mount;
+ }
+ if (test_opt(sb, DELALLOC))
+ clear_opt(sb, DELALLOC);
+ }
+
+ blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ if (blocksize < PAGE_SIZE) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "dioread_nolock if block size != PAGE_SIZE");
+ goto failed_mount;
+ }
+ }
+
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
@@ -3265,8 +3321,6 @@
if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
goto failed_mount;
- blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
-
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
blocksize > EXT4_MAX_BLOCK_SIZE) {
ext4_msg(sb, KERN_ERR,
@@ -3369,12 +3423,53 @@
sb->s_dirt = 1;
}
- if (sbi->s_blocks_per_group > blocksize * 8) {
- ext4_msg(sb, KERN_ERR,
- "#blocks per group too big: %lu",
- sbi->s_blocks_per_group);
- goto failed_mount;
+ /* Handle clustersize */
+ clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size);
+ has_bigalloc = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC);
+ if (has_bigalloc) {
+ if (clustersize < blocksize) {
+ ext4_msg(sb, KERN_ERR,
+ "cluster size (%d) smaller than "
+ "block size (%d)", clustersize, blocksize);
+ goto failed_mount;
+ }
+ sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
+ le32_to_cpu(es->s_log_block_size);
+ sbi->s_clusters_per_group =
+ le32_to_cpu(es->s_clusters_per_group);
+ if (sbi->s_clusters_per_group > blocksize * 8) {
+ ext4_msg(sb, KERN_ERR,
+ "#clusters per group too big: %lu",
+ sbi->s_clusters_per_group);
+ goto failed_mount;
+ }
+ if (sbi->s_blocks_per_group !=
+ (sbi->s_clusters_per_group * (clustersize / blocksize))) {
+ ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and "
+ "clusters per group (%lu) inconsistent",
+ sbi->s_blocks_per_group,
+ sbi->s_clusters_per_group);
+ goto failed_mount;
+ }
+ } else {
+ if (clustersize != blocksize) {
+ ext4_warning(sb, "fragment/cluster size (%d) != "
+ "block size (%d)", clustersize,
+ blocksize);
+ clustersize = blocksize;
+ }
+ if (sbi->s_blocks_per_group > blocksize * 8) {
+ ext4_msg(sb, KERN_ERR,
+ "#blocks per group too big: %lu",
+ sbi->s_blocks_per_group);
+ goto failed_mount;
+ }
+ sbi->s_clusters_per_group = sbi->s_blocks_per_group;
+ sbi->s_cluster_bits = 0;
}
+ sbi->s_cluster_ratio = clustersize / blocksize;
+
if (sbi->s_inodes_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR,
"#inodes per group too big: %lu",
@@ -3446,10 +3541,8 @@
goto failed_mount;
}
-#ifdef CONFIG_PROC_FS
if (ext4_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
-#endif
bgl_lock_init(sbi->s_blockgroup_lock);
@@ -3483,8 +3576,8 @@
sbi->s_err_report.function = print_daily_error_info;
sbi->s_err_report.data = (unsigned long) sb;
- err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(sb));
+ err = percpu_counter_init(&sbi->s_freeclusters_counter,
+ ext4_count_free_clusters(sb));
if (!err) {
err = percpu_counter_init(&sbi->s_freeinodes_counter,
ext4_count_free_inodes(sb));
@@ -3494,7 +3587,7 @@
ext4_count_dirs(sb));
}
if (!err) {
- err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
}
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
@@ -3609,13 +3702,13 @@
* The journal may have updated the bg summary counts, so we
* need to update the global counters.
*/
- percpu_counter_set(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(sb));
+ percpu_counter_set(&sbi->s_freeclusters_counter,
+ ext4_count_free_clusters(sb));
percpu_counter_set(&sbi->s_freeinodes_counter,
ext4_count_free_inodes(sb));
percpu_counter_set(&sbi->s_dirs_counter,
ext4_count_dirs(sb));
- percpu_counter_set(&sbi->s_dirtyblocks_counter, 0);
+ percpu_counter_set(&sbi->s_dirtyclusters_counter, 0);
no_journal:
/*
@@ -3679,25 +3772,6 @@
"available");
}
- if (test_opt(sb, DELALLOC) &&
- (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) {
- ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
- "requested data journaling mode");
- clear_opt(sb, DELALLOC);
- }
- if (test_opt(sb, DIOREAD_NOLOCK)) {
- if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
- ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
- "option - requested data journaling mode");
- clear_opt(sb, DIOREAD_NOLOCK);
- }
- if (sb->s_blocksize < PAGE_SIZE) {
- ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
- "option - block size is too small");
- clear_opt(sb, DIOREAD_NOLOCK);
- }
- }
-
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
@@ -3710,22 +3784,19 @@
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
err);
- goto failed_mount4;
+ goto failed_mount5;
}
err = ext4_register_li_request(sb, first_not_zeroed);
if (err)
- goto failed_mount4;
+ goto failed_mount6;
sbi->s_kobj.kset = ext4_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
"%s", sb->s_id);
- if (err) {
- ext4_mb_release(sb);
- ext4_ext_release(sb);
- goto failed_mount4;
- };
+ if (err)
+ goto failed_mount7;
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
@@ -3759,13 +3830,19 @@
ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
goto failed_mount;
+failed_mount7:
+ ext4_unregister_li_request(sb);
+failed_mount6:
+ ext4_ext_release(sb);
+failed_mount5:
+ ext4_mb_release(sb);
+ ext4_release_system_zone(sb);
failed_mount4:
iput(root);
sb->s_root = NULL;
ext4_msg(sb, KERN_ERR, "mount failed");
destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
failed_mount_wq:
- ext4_release_system_zone(sb);
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
@@ -3774,10 +3851,10 @@
del_timer(&sbi->s_err_report);
if (sbi->s_flex_groups)
ext4_kvfree(sbi->s_flex_groups);
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+ percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
@@ -4064,7 +4141,7 @@
struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
int error = 0;
- if (!sbh)
+ if (!sbh || block_device_ejected(sb))
return error;
if (buffer_write_io_error(sbh)) {
/*
@@ -4100,8 +4177,9 @@
else
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
- ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeblocks_counter));
+ ext4_free_blocks_count_set(es,
+ EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
+ &EXT4_SB(sb)->s_freeclusters_counter)));
es->s_free_inodes_count =
cpu_to_le32(percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeinodes_counter));
@@ -4506,16 +4584,34 @@
return err;
}
+/*
+ * Note: calculating the overhead so we can be compatible with
+ * historical BSD practice is quite difficult in the face of
+ * clusters/bigalloc. This is because multiple metadata blocks from
+ * different block group can end up in the same allocation cluster.
+ * Calculating the exact overhead in the face of clustered allocation
+ * requires either O(all block bitmaps) in memory or O(number of block
+ * groups**2) in time. We will still calculate the superblock for
+ * older file systems --- and if we come across with a bigalloc file
+ * system with zero in s_overhead_clusters the estimate will be close to
+ * correct especially for very large cluster sizes --- but for newer
+ * file systems, it's better to calculate this figure once at mkfs
+ * time, and store it in the superblock. If the superblock value is
+ * present (even for non-bigalloc file systems), we will use it.
+ */
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
+ struct ext4_group_desc *gdp;
u64 fsid;
s64 bfree;
if (test_opt(sb, MINIX_DF)) {
sbi->s_overhead_last = 0;
+ } else if (es->s_overhead_clusters) {
+ sbi->s_overhead_last = le32_to_cpu(es->s_overhead_clusters);
} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
ext4_fsblk_t overhead = 0;
@@ -4530,24 +4626,16 @@
* All of the blocks before first_data_block are
* overhead
*/
- overhead = le32_to_cpu(es->s_first_data_block);
+ overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block));
/*
- * Add the overhead attributed to the superblock and
- * block group descriptors. If the sparse superblocks
- * feature is turned on, then not all groups have this.
+ * Add the overhead found in each block group
*/
for (i = 0; i < ngroups; i++) {
- overhead += ext4_bg_has_super(sb, i) +
- ext4_bg_num_gdb(sb, i);
+ gdp = ext4_get_group_desc(sb, i, NULL);
+ overhead += ext4_num_overhead_clusters(sb, i, gdp);
cond_resched();
}
-
- /*
- * Every block group has an inode bitmap, a block
- * bitmap, and an inode table.
- */
- overhead += ngroups * (2 + sbi->s_itb_per_group);
sbi->s_overhead_last = overhead;
smp_wmb();
sbi->s_blocks_last = ext4_blocks_count(es);
@@ -4555,11 +4643,12 @@
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
- buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
- bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
- percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
+ buf->f_blocks = (ext4_blocks_count(es) -
+ EXT4_C2B(sbi, sbi->s_overhead_last));
+ bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
+ percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
/* prevent underflow in case that few free space is available */
- buf->f_bfree = max_t(s64, bfree, 0);
+ buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0));
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
buf->f_bavail = 0;
@@ -4980,13 +5069,11 @@
return err;
err = ext4_init_system_zone();
if (err)
- goto out7;
+ goto out6;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
- goto out6;
- ext4_proc_root = proc_mkdir("fs/ext4", NULL);
- if (!ext4_proc_root)
goto out5;
+ ext4_proc_root = proc_mkdir("fs/ext4", NULL);
err = ext4_init_feat_adverts();
if (err)
@@ -5022,12 +5109,12 @@
out3:
ext4_exit_feat_adverts();
out4:
- remove_proc_entry("fs/ext4", NULL);
-out5:
+ if (ext4_proc_root)
+ remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
-out6:
+out5:
ext4_exit_system_zone();
-out7:
+out6:
ext4_exit_pageio();
return err;
}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c757adc..93a00d8 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -820,8 +820,14 @@
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+ /*
+ * take i_data_sem because we will test
+ * i_delalloc_reserved_flag in ext4_mb_new_blocks
+ */
+ down_read((&EXT4_I(inode)->i_data_sem));
block = ext4_new_meta_blocks(handle, inode, goal, 0,
NULL, &error);
+ up_read((&EXT4_I(inode)->i_data_sem));
if (error)
goto cleanup;
@@ -985,11 +991,7 @@
no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
- error = ext4_get_inode_loc(inode, &is.iloc);
- if (error)
- goto cleanup;
-
- error = ext4_journal_get_write_access(handle, is.iloc.bh);
+ error = ext4_reserve_inode_write(handle, inode, &is.iloc);
if (error)
goto cleanup;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 1726d73..808cac7 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -379,7 +379,7 @@
return error;
MSDOS_I(inode)->mmu_private = inode->i_size;
- inode->i_nlink = fat_subdirs(inode);
+ set_nlink(inode, fat_subdirs(inode));
} else { /* not a directory */
inode->i_generation |= 1;
inode->i_mode = fat_make_mode(sbi, de->attr,
@@ -1233,7 +1233,7 @@
fat_save_attrs(inode, ATTR_DIR);
inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = 0;
inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = 0;
- inode->i_nlink = fat_subdirs(inode)+2;
+ set_nlink(inode, fat_subdirs(inode)+2);
return 0;
}
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 66e83b8..216b419 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -387,7 +387,7 @@
/* the directory was completed, just return a error */
goto out;
}
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_mtime = inode->i_atime = inode->i_ctime = ts;
/* timestamp is already written, so mark_inode_dirty() is unneeded. */
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index bb3f29c..a87a656 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -900,7 +900,7 @@
goto out;
}
inode->i_version++;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_mtime = inode->i_atime = inode->i_ctime = ts;
/* timestamp is already written, so mark_inode_dirty() is unneeded. */
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index 1a43114..7b2af5a 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -227,7 +227,7 @@
ip->i_uid = (uid_t)vip->vii_uid;
ip->i_gid = (gid_t)vip->vii_gid;
- ip->i_nlink = vip->vii_nlink;
+ set_nlink(ip, vip->vii_nlink);
ip->i_size = vip->vii_size;
ip->i_atime.tv_sec = vip->vii_atime;
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 85542a7..42593c5 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -231,7 +231,7 @@
if (iop)
inode->i_op = iop;
inode->i_fop = fop;
- inode->i_nlink = nlink;
+ set_nlink(inode, nlink);
inode->i_private = fc;
d_add(dentry, inode);
return dentry;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index add96f6..3e6d727 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -151,7 +151,7 @@
inode->i_ino = attr->ino;
inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
- inode->i_nlink = attr->nlink;
+ set_nlink(inode, attr->nlink);
inode->i_uid = attr->uid;
inode->i_gid = attr->gid;
inode->i_blocks = attr->blocks;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 78418b4..1656df7 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -299,7 +299,7 @@
if (nlink == 0)
clear_nlink(inode);
else
- inode->i_nlink = nlink;
+ set_nlink(inode, nlink);
}
}
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 3ebc437..1cbdeea 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -46,11 +46,26 @@
case HFS_EXT_CNID:
hfs_inode_read_fork(tree->inode, mdb->drXTExtRec, mdb->drXTFlSize,
mdb->drXTFlSize, be32_to_cpu(mdb->drXTClpSiz));
+ if (HFS_I(tree->inode)->alloc_blocks >
+ HFS_I(tree->inode)->first_blocks) {
+ printk(KERN_ERR "hfs: invalid btree extent records\n");
+ unlock_new_inode(tree->inode);
+ goto free_inode;
+ }
+
tree->inode->i_mapping->a_ops = &hfs_btree_aops;
break;
case HFS_CAT_CNID:
hfs_inode_read_fork(tree->inode, mdb->drCTExtRec, mdb->drCTFlSize,
mdb->drCTFlSize, be32_to_cpu(mdb->drCTClpSiz));
+
+ if (!HFS_I(tree->inode)->first_blocks) {
+ printk(KERN_ERR "hfs: invalid btree extent records "
+ "(0 size).\n");
+ unlock_new_inode(tree->inode);
+ goto free_inode;
+ }
+
tree->inode->i_mapping->a_ops = &hfs_btree_aops;
break;
default:
@@ -59,11 +74,6 @@
}
unlock_new_inode(tree->inode);
- if (!HFS_I(tree->inode)->first_blocks) {
- printk(KERN_ERR "hfs: invalid btree extent records (0 size).\n");
- goto free_inode;
- }
-
mapping = tree->inode->i_mapping;
page = read_mapping_page(mapping, 0, NULL);
if (IS_ERR(page))
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index b4d70b1..bce4eef 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -198,7 +198,7 @@
res = hfs_cat_create(inode->i_ino, dir, &dentry->d_name, inode);
if (res) {
- inode->i_nlink = 0;
+ clear_nlink(inode);
hfs_delete_inode(inode);
iput(inode);
return res;
@@ -227,7 +227,7 @@
res = hfs_cat_create(inode->i_ino, dir, &dentry->d_name, inode);
if (res) {
- inode->i_nlink = 0;
+ clear_nlink(inode);
hfs_delete_inode(inode);
iput(inode);
return res;
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 96a1b62..a1a9fdc 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -183,7 +183,7 @@
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
HFS_I(inode)->flags = 0;
HFS_I(inode)->rsrc_inode = NULL;
@@ -313,7 +313,7 @@
/* Initialize the inode */
inode->i_uid = hsb->s_uid;
inode->i_gid = hsb->s_gid;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
if (idata->key)
HFS_I(inode)->cat_key = *idata->key;
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 25b2443..4536cd3 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -415,7 +415,7 @@
goto out;
out_err:
- inode->i_nlink = 0;
+ clear_nlink(inode);
hfsplus_delete_inode(inode);
iput(inode);
out:
@@ -440,7 +440,7 @@
res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
if (res) {
- inode->i_nlink = 0;
+ clear_nlink(inode);
hfsplus_delete_inode(inode);
iput(inode);
goto out;
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 4cc1e3a..40e1413 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -391,7 +391,7 @@
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
hip = HFSPLUS_I(inode);
@@ -512,7 +512,7 @@
hfs_bnode_read(fd->bnode, &entry, fd->entryoffset,
sizeof(struct hfsplus_cat_folder));
hfsplus_get_perms(inode, &folder->permissions, 1);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_size = 2 + be32_to_cpu(folder->valence);
inode->i_atime = hfsp_mt2ut(folder->access_date);
inode->i_mtime = hfsp_mt2ut(folder->content_mod_date);
@@ -532,11 +532,11 @@
hfsplus_inode_read_fork(inode, HFSPLUS_IS_RSRC(inode) ?
&file->rsrc_fork : &file->data_fork);
hfsplus_get_perms(inode, &file->permissions, 0);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
if (S_ISREG(inode->i_mode)) {
if (file->permissions.dev)
- inode->i_nlink =
- be32_to_cpu(file->permissions.dev);
+ set_nlink(inode,
+ be32_to_cpu(file->permissions.dev));
inode->i_op = &hfsplus_file_inode_operations;
inode->i_fop = &hfsplus_file_operations;
inode->i_mapping->a_ops = &hfsplus_aops;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 0d22afd..2f72da5 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -541,7 +541,7 @@
ino->i_ino = st.ino;
ino->i_mode = st.mode;
- ino->i_nlink = st.nlink;
+ set_nlink(ino, st.nlink);
ino->i_uid = st.uid;
ino->i_gid = st.gid;
ino->i_atime = st.atime;
diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c
index d51a983..dd7bc38 100644
--- a/fs/hostfs/hostfs_user.c
+++ b/fs/hostfs/hostfs_user.c
@@ -16,7 +16,6 @@
#include <sys/vfs.h>
#include "hostfs.h"
#include "os.h"
-#include "user.h"
#include <utime.h>
static void stat64_to_hostfs(const struct stat64 *buf, struct hostfs_stat *p)
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 96a8ed9..2fa0089 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -247,7 +247,7 @@
result->i_mode &= ~0111;
result->i_op = &hpfs_file_iops;
result->i_fop = &hpfs_file_ops;
- result->i_nlink = 1;
+ set_nlink(result, 1);
}
unlock_new_inode(result);
}
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 338cd83..3b2cec2 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -53,7 +53,7 @@
i->i_mode &= ~0111;
i->i_op = &hpfs_file_iops;
i->i_fop = &hpfs_file_ops;
- i->i_nlink = 0;*/
+ clear_nlink(i);*/
make_bad_inode(i);
return;
}
@@ -77,7 +77,7 @@
i->i_mode = S_IFLNK | 0777;
i->i_op = &page_symlink_inode_operations;
i->i_data.a_ops = &hpfs_symlink_aops;
- i->i_nlink = 1;
+ set_nlink(i, 1);
i->i_size = ea_size;
i->i_blocks = 1;
brelse(bh);
@@ -101,7 +101,7 @@
}
if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) {
brelse(bh);
- i->i_nlink = 1;
+ set_nlink(i, 1);
i->i_size = 0;
i->i_blocks = 1;
init_special_inode(i, mode,
@@ -125,13 +125,13 @@
hpfs_count_dnodes(i->i_sb, hpfs_inode->i_dno, &n_dnodes, &n_subdirs, NULL);
i->i_blocks = 4 * n_dnodes;
i->i_size = 2048 * n_dnodes;
- i->i_nlink = 2 + n_subdirs;
+ set_nlink(i, 2 + n_subdirs);
} else {
i->i_mode |= S_IFREG;
if (!hpfs_inode->i_ea_mode) i->i_mode &= ~0111;
i->i_op = &hpfs_file_iops;
i->i_fop = &hpfs_file_ops;
- i->i_nlink = 1;
+ set_nlink(i, 1);
i->i_size = le32_to_cpu(fnode->file_size);
i->i_blocks = ((i->i_size + 511) >> 9) + 1;
i->i_data.a_ops = &hpfs_aops;
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 2df69e2..ea91fcb 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -56,7 +56,7 @@
result->i_fop = &hpfs_dir_ops;
result->i_blocks = 4;
result->i_size = 2048;
- result->i_nlink = 2;
+ set_nlink(result, 2);
if (dee.read_only)
result->i_mode &= ~0222;
@@ -150,7 +150,7 @@
result->i_mode &= ~0111;
result->i_op = &hpfs_file_iops;
result->i_fop = &hpfs_file_ops;
- result->i_nlink = 1;
+ set_nlink(result, 1);
hpfs_i(result)->i_parent_dir = dir->i_ino;
result->i_ctime.tv_sec = result->i_mtime.tv_sec = result->i_atime.tv_sec = local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date));
result->i_ctime.tv_nsec = 0;
@@ -242,7 +242,7 @@
hpfs_i(result)->i_ea_size = 0;
result->i_uid = current_fsuid();
result->i_gid = current_fsgid();
- result->i_nlink = 1;
+ set_nlink(result, 1);
result->i_size = 0;
result->i_blocks = 1;
init_special_inode(result, mode, rdev);
@@ -318,7 +318,7 @@
result->i_uid = current_fsuid();
result->i_gid = current_fsgid();
result->i_blocks = 1;
- result->i_nlink = 1;
+ set_nlink(result, 1);
result->i_size = strlen(symlink);
result->i_op = &page_symlink_inode_operations;
result->i_data.a_ops = &hpfs_symlink_aops;
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index 970ea98..f590b11 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -702,7 +702,7 @@
inode->i_ctime = proc_ino->i_ctime;
inode->i_ino = proc_ino->i_ino;
inode->i_mode = proc_ino->i_mode;
- inode->i_nlink = proc_ino->i_nlink;
+ set_nlink(inode, proc_ino->i_nlink);
inode->i_size = proc_ino->i_size;
inode->i_blocks = proc_ino->i_blocks;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ec88953..0be5a78 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -970,7 +970,7 @@
d_instantiate(path.dentry, inode);
inode->i_size = size;
- inode->i_nlink = 0;
+ clear_nlink(inode);
error = -ENFILE;
file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
diff --git a/fs/inode.c b/fs/inode.c
index ecbb68d..ee4e66b 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -142,7 +142,7 @@
atomic_set(&inode->i_count, 1);
inode->i_op = &empty_iops;
inode->i_fop = &empty_fops;
- inode->i_nlink = 1;
+ inode->__i_nlink = 1;
inode->i_opflags = 0;
inode->i_uid = 0;
inode->i_gid = 0;
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index a5d0367..f950059 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -20,6 +20,7 @@
#include <linux/statfs.h>
#include <linux/cdrom.h>
#include <linux/parser.h>
+#include <linux/mpage.h>
#include "isofs.h"
#include "zisofs.h"
@@ -1148,7 +1149,13 @@
static int isofs_readpage(struct file *file, struct page *page)
{
- return block_read_full_page(page,isofs_get_block);
+ return mpage_readpage(page, isofs_get_block);
+}
+
+static int isofs_readpages(struct file *file, struct address_space *mapping,
+ struct list_head *pages, unsigned nr_pages)
+{
+ return mpage_readpages(mapping, pages, nr_pages, isofs_get_block);
}
static sector_t _isofs_bmap(struct address_space *mapping, sector_t block)
@@ -1158,6 +1165,7 @@
static const struct address_space_operations isofs_aops = {
.readpage = isofs_readpage,
+ .readpages = isofs_readpages,
.bmap = _isofs_bmap
};
@@ -1319,7 +1327,7 @@
inode->i_mode = S_IFDIR | sbi->s_dmode;
else
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
- inode->i_nlink = 1; /*
+ set_nlink(inode, 1); /*
* Set to 1. We know there are 2, but
* the find utility tries to optimize
* if it is 2, and it screws up. It is
@@ -1337,7 +1345,7 @@
*/
inode->i_mode = S_IFREG | S_IRUGO | S_IXUGO;
}
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
inode->i_uid = sbi->s_uid;
inode->i_gid = sbi->s_gid;
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index 1fbc7de..70e79d0 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -363,7 +363,7 @@
break;
case SIG('P', 'X'):
inode->i_mode = isonum_733(rr->u.PX.mode);
- inode->i_nlink = isonum_733(rr->u.PX.n_links);
+ set_nlink(inode, isonum_733(rr->u.PX.n_links));
inode->i_uid = isonum_733(rr->u.PX.uid);
inode->i_gid = isonum_733(rr->u.PX.gid);
break;
@@ -496,7 +496,7 @@
goto out;
}
inode->i_mode = reloc->i_mode;
- inode->i_nlink = reloc->i_nlink;
+ set_nlink(inode, reloc->i_nlink);
inode->i_uid = reloc->i_uid;
inode->i_gid = reloc->i_gid;
inode->i_rdev = reloc->i_rdev;
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index 9fe061f..fea8dd6 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -1135,6 +1135,14 @@
goto out;
}
+ if (be32_to_cpu(sb->s_first) == 0 ||
+ be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+ printk(KERN_WARNING
+ "JBD: Invalid start block of journal: %u\n",
+ be32_to_cpu(sb->s_first));
+ goto out;
+ }
+
return 0;
out:
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index eef6979..68d704d 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -352,7 +352,7 @@
J_ASSERT(commit_transaction->t_state == T_RUNNING);
trace_jbd2_start_commit(journal, commit_transaction);
- jbd_debug(1, "JBD: starting commit of transaction %d\n",
+ jbd_debug(1, "JBD2: starting commit of transaction %d\n",
commit_transaction->t_tid);
write_lock(&journal->j_state_lock);
@@ -427,7 +427,7 @@
__jbd2_journal_clean_checkpoint_list(journal);
spin_unlock(&journal->j_list_lock);
- jbd_debug (3, "JBD: commit phase 1\n");
+ jbd_debug(3, "JBD2: commit phase 1\n");
/*
* Switch to a new revoke table.
@@ -447,7 +447,7 @@
wake_up(&journal->j_wait_transaction_locked);
write_unlock(&journal->j_state_lock);
- jbd_debug (3, "JBD: commit phase 2\n");
+ jbd_debug(3, "JBD2: commit phase 2\n");
/*
* Now start flushing things to disk, in the order they appear
@@ -462,7 +462,7 @@
WRITE_SYNC);
blk_finish_plug(&plug);
- jbd_debug(3, "JBD: commit phase 2\n");
+ jbd_debug(3, "JBD2: commit phase 2\n");
/*
* Way to go: we have now written out all of the data for a
@@ -522,7 +522,7 @@
J_ASSERT (bufs == 0);
- jbd_debug(4, "JBD: get descriptor\n");
+ jbd_debug(4, "JBD2: get descriptor\n");
descriptor = jbd2_journal_get_descriptor_buffer(journal);
if (!descriptor) {
@@ -531,7 +531,7 @@
}
bh = jh2bh(descriptor);
- jbd_debug(4, "JBD: got buffer %llu (%p)\n",
+ jbd_debug(4, "JBD2: got buffer %llu (%p)\n",
(unsigned long long)bh->b_blocknr, bh->b_data);
header = (journal_header_t *)&bh->b_data[0];
header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
@@ -625,7 +625,7 @@
commit_transaction->t_buffers == NULL ||
space_left < tag_bytes + 16) {
- jbd_debug(4, "JBD: Submit %d IOs\n", bufs);
+ jbd_debug(4, "JBD2: Submit %d IOs\n", bufs);
/* Write an end-of-descriptor marker before
submitting the IOs. "tag" still points to
@@ -707,7 +707,7 @@
so we incur less scheduling load.
*/
- jbd_debug(3, "JBD: commit phase 3\n");
+ jbd_debug(3, "JBD2: commit phase 3\n");
/*
* akpm: these are BJ_IO, and j_list_lock is not needed.
@@ -771,7 +771,7 @@
J_ASSERT (commit_transaction->t_shadow_list == NULL);
- jbd_debug(3, "JBD: commit phase 4\n");
+ jbd_debug(3, "JBD2: commit phase 4\n");
/* Here we wait for the revoke record and descriptor record buffers */
wait_for_ctlbuf:
@@ -801,7 +801,7 @@
if (err)
jbd2_journal_abort(journal, err);
- jbd_debug(3, "JBD: commit phase 5\n");
+ jbd_debug(3, "JBD2: commit phase 5\n");
write_lock(&journal->j_state_lock);
J_ASSERT(commit_transaction->t_state == T_COMMIT_DFLUSH);
commit_transaction->t_state = T_COMMIT_JFLUSH;
@@ -830,7 +830,7 @@
transaction can be removed from any checkpoint list it was on
before. */
- jbd_debug(3, "JBD: commit phase 6\n");
+ jbd_debug(3, "JBD2: commit phase 6\n");
J_ASSERT(list_empty(&commit_transaction->t_inode_list));
J_ASSERT(commit_transaction->t_buffers == NULL);
@@ -964,7 +964,7 @@
/* Done with this transaction! */
- jbd_debug(3, "JBD: commit phase 7\n");
+ jbd_debug(3, "JBD2: commit phase 7\n");
J_ASSERT(commit_transaction->t_state == T_COMMIT_JFLUSH);
@@ -1039,7 +1039,7 @@
journal->j_commit_callback(journal, commit_transaction);
trace_jbd2_end_commit(journal, commit_transaction);
- jbd_debug(1, "JBD: commit %d complete, head %d\n",
+ jbd_debug(1, "JBD2: commit %d complete, head %d\n",
journal->j_commit_sequence, journal->j_tail_sequence);
if (to_free)
kfree(commit_transaction);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index f24df13..0fa0123 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -491,7 +491,7 @@
*/
journal->j_commit_request = target;
- jbd_debug(1, "JBD: requesting commit %d/%d\n",
+ jbd_debug(1, "JBD2: requesting commit %d/%d\n",
journal->j_commit_request,
journal->j_commit_sequence);
wake_up(&journal->j_wait_commit);
@@ -500,7 +500,7 @@
/* This should never happen, but if it does, preserve
the evidence before kjournald goes into a loop and
increments j_commit_sequence beyond all recognition. */
- WARN_ONCE(1, "jbd: bad log_start_commit: %u %u %u %u\n",
+ WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n",
journal->j_commit_request,
journal->j_commit_sequence,
target, journal->j_running_transaction ?
@@ -645,7 +645,7 @@
}
#endif
while (tid_gt(tid, journal->j_commit_sequence)) {
- jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n",
+ jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n",
tid, journal->j_commit_sequence);
wake_up(&journal->j_wait_commit);
read_unlock(&journal->j_state_lock);
@@ -1093,7 +1093,7 @@
first = be32_to_cpu(sb->s_first);
last = be32_to_cpu(sb->s_maxlen);
if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) {
- printk(KERN_ERR "JBD: Journal too short (blocks %llu-%llu).\n",
+ printk(KERN_ERR "JBD2: Journal too short (blocks %llu-%llu).\n",
first, last);
journal_fail_superblock(journal);
return -EINVAL;
@@ -1139,7 +1139,7 @@
*/
if (sb->s_start == 0 && journal->j_tail_sequence ==
journal->j_transaction_sequence) {
- jbd_debug(1,"JBD: Skipping superblock update on recovered sb "
+ jbd_debug(1, "JBD2: Skipping superblock update on recovered sb "
"(start %ld, seq %d, errno %d)\n",
journal->j_tail, journal->j_tail_sequence,
journal->j_errno);
@@ -1163,7 +1163,7 @@
}
read_lock(&journal->j_state_lock);
- jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n",
+ jbd_debug(1, "JBD2: updating superblock (start %ld, seq %d, errno %d)\n",
journal->j_tail, journal->j_tail_sequence, journal->j_errno);
sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
@@ -1216,8 +1216,8 @@
ll_rw_block(READ, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
- printk (KERN_ERR
- "JBD: IO error reading journal superblock\n");
+ printk(KERN_ERR
+ "JBD2: IO error reading journal superblock\n");
goto out;
}
}
@@ -1228,7 +1228,7 @@
if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) ||
sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) {
- printk(KERN_WARNING "JBD: no valid journal superblock found\n");
+ printk(KERN_WARNING "JBD2: no valid journal superblock found\n");
goto out;
}
@@ -1240,14 +1240,22 @@
journal->j_format_version = 2;
break;
default:
- printk(KERN_WARNING "JBD: unrecognised superblock format ID\n");
+ printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n");
goto out;
}
if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
- printk (KERN_WARNING "JBD: journal file too short\n");
+ printk(KERN_WARNING "JBD2: journal file too short\n");
+ goto out;
+ }
+
+ if (be32_to_cpu(sb->s_first) == 0 ||
+ be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+ printk(KERN_WARNING
+ "JBD2: Invalid start block of journal: %u\n",
+ be32_to_cpu(sb->s_first));
goto out;
}
@@ -1310,8 +1318,8 @@
~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) ||
(sb->s_feature_incompat &
~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) {
- printk (KERN_WARNING
- "JBD: Unrecognised features on journal\n");
+ printk(KERN_WARNING
+ "JBD2: Unrecognised features on journal\n");
return -EINVAL;
}
}
@@ -1346,7 +1354,7 @@
return 0;
recovery_error:
- printk (KERN_WARNING "JBD: recovery failed\n");
+ printk(KERN_WARNING "JBD2: recovery failed\n");
return -EIO;
}
@@ -1577,7 +1585,7 @@
struct buffer_head *bh;
printk(KERN_WARNING
- "JBD: Converting superblock from version 1 to 2.\n");
+ "JBD2: Converting superblock from version 1 to 2.\n");
/* Pre-initialise new fields to zero */
offset = ((char *) &(sb->s_feature_compat)) - ((char *) sb);
@@ -1694,7 +1702,7 @@
if (!journal->j_tail)
goto no_recovery;
- printk (KERN_WARNING "JBD: %s recovery information on journal\n",
+ printk(KERN_WARNING "JBD2: %s recovery information on journal\n",
write ? "Clearing" : "Ignoring");
err = jbd2_journal_skip_recovery(journal);
@@ -2020,7 +2028,7 @@
retval = 0;
if (!jbd2_journal_head_cache) {
retval = -ENOMEM;
- printk(KERN_EMERG "JBD: no memory for journal_head cache\n");
+ printk(KERN_EMERG "JBD2: no memory for journal_head cache\n");
}
return retval;
}
@@ -2383,7 +2391,7 @@
#ifdef CONFIG_JBD2_DEBUG
int n = atomic_read(&nr_journal_heads);
if (n)
- printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n);
+ printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n);
#endif
jbd2_remove_debugfs_entry();
jbd2_remove_jbd_stats_proc_entry();
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 1cad869..da6d7ba 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -89,7 +89,7 @@
err = jbd2_journal_bmap(journal, next, &blocknr);
if (err) {
- printk (KERN_ERR "JBD: bad block at offset %u\n",
+ printk(KERN_ERR "JBD2: bad block at offset %u\n",
next);
goto failed;
}
@@ -138,14 +138,14 @@
*bhp = NULL;
if (offset >= journal->j_maxlen) {
- printk(KERN_ERR "JBD: corrupted journal superblock\n");
+ printk(KERN_ERR "JBD2: corrupted journal superblock\n");
return -EIO;
}
err = jbd2_journal_bmap(journal, offset, &blocknr);
if (err) {
- printk (KERN_ERR "JBD: bad block at offset %u\n",
+ printk(KERN_ERR "JBD2: bad block at offset %u\n",
offset);
return err;
}
@@ -163,7 +163,7 @@
}
if (!buffer_uptodate(bh)) {
- printk (KERN_ERR "JBD: Failed to read block at offset %u\n",
+ printk(KERN_ERR "JBD2: Failed to read block at offset %u\n",
offset);
brelse(bh);
return -EIO;
@@ -251,10 +251,10 @@
if (!err)
err = do_one_pass(journal, &info, PASS_REPLAY);
- jbd_debug(1, "JBD: recovery, exit status %d, "
+ jbd_debug(1, "JBD2: recovery, exit status %d, "
"recovered transactions %u to %u\n",
err, info.start_transaction, info.end_transaction);
- jbd_debug(1, "JBD: Replayed %d and revoked %d/%d blocks\n",
+ jbd_debug(1, "JBD2: Replayed %d and revoked %d/%d blocks\n",
info.nr_replays, info.nr_revoke_hits, info.nr_revokes);
/* Restart the log at the next transaction ID, thus invalidating
@@ -293,14 +293,14 @@
err = do_one_pass(journal, &info, PASS_SCAN);
if (err) {
- printk(KERN_ERR "JBD: error %d scanning journal\n", err);
+ printk(KERN_ERR "JBD2: error %d scanning journal\n", err);
++journal->j_transaction_sequence;
} else {
#ifdef CONFIG_JBD2_DEBUG
int dropped = info.end_transaction -
be32_to_cpu(journal->j_superblock->s_sequence);
jbd_debug(1,
- "JBD: ignoring %d transaction%s from the journal.\n",
+ "JBD2: ignoring %d transaction%s from the journal.\n",
dropped, (dropped == 1) ? "" : "s");
#endif
journal->j_transaction_sequence = ++info.end_transaction;
@@ -338,7 +338,7 @@
wrap(journal, *next_log_block);
err = jread(&obh, journal, io_block);
if (err) {
- printk(KERN_ERR "JBD: IO error %d recovering block "
+ printk(KERN_ERR "JBD2: IO error %d recovering block "
"%lu in log\n", err, io_block);
return 1;
} else {
@@ -411,7 +411,7 @@
* either the next descriptor block or the final commit
* record. */
- jbd_debug(3, "JBD: checking block %ld\n", next_log_block);
+ jbd_debug(3, "JBD2: checking block %ld\n", next_log_block);
err = jread(&bh, journal, next_log_block);
if (err)
goto failed;
@@ -491,8 +491,8 @@
/* Recover what we can, but
* report failure at the end. */
success = err;
- printk (KERN_ERR
- "JBD: IO error %d recovering "
+ printk(KERN_ERR
+ "JBD2: IO error %d recovering "
"block %ld in log\n",
err, io_block);
} else {
@@ -520,7 +520,7 @@
journal->j_blocksize);
if (nbh == NULL) {
printk(KERN_ERR
- "JBD: Out of memory "
+ "JBD2: Out of memory "
"during recovery.\n");
err = -ENOMEM;
brelse(bh);
@@ -689,7 +689,7 @@
/* It's really bad news if different passes end up at
* different places (but possible due to IO errors). */
if (info->end_transaction != next_commit_ID) {
- printk (KERN_ERR "JBD: recovery pass %d ended at "
+ printk(KERN_ERR "JBD2: recovery pass %d ended at "
"transaction %u, expected %u\n",
pass, next_commit_ID, info->end_transaction);
if (!success)
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 2d71094..a0e41a4 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -27,6 +27,7 @@
#include <linux/highmem.h>
#include <linux/hrtimer.h>
#include <linux/backing-dev.h>
+#include <linux/bug.h>
#include <linux/module.h>
static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
@@ -115,7 +116,7 @@
*/
static int start_this_handle(journal_t *journal, handle_t *handle,
- int gfp_mask)
+ gfp_t gfp_mask)
{
transaction_t *transaction, *new_transaction = NULL;
tid_t tid;
@@ -124,7 +125,7 @@
unsigned long ts = jiffies;
if (nblocks > journal->j_max_transaction_buffers) {
- printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
+ printk(KERN_ERR "JBD2: %s wants too many credits (%d > %d)\n",
current->comm, nblocks,
journal->j_max_transaction_buffers);
return -ENOSPC;
@@ -320,7 +321,7 @@
* Return a pointer to a newly allocated handle, or an ERR_PTR() value
* on failure.
*/
-handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int gfp_mask)
+handle_t *jbd2__journal_start(journal_t *journal, int nblocks, gfp_t gfp_mask)
{
handle_t *handle = journal_current_handle();
int err;
@@ -443,7 +444,7 @@
* transaction capabable of guaranteeing the requested number of
* credits.
*/
-int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
+int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
@@ -563,7 +564,7 @@
char b[BDEVNAME_SIZE];
printk(KERN_WARNING
- "JBD: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). "
+ "JBD2: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). "
"There's a risk of filesystem corruption in case of system "
"crash.\n",
bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr);
@@ -1049,6 +1050,10 @@
* mark dirty metadata which needs to be journaled as part of the current
* transaction.
*
+ * The buffer must have previously had jbd2_journal_get_write_access()
+ * called so that it has a valid journal_head attached to the buffer
+ * head.
+ *
* The buffer is placed on the transaction's metadata list and is marked
* as belonging to the transaction.
*
@@ -1065,11 +1070,16 @@
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
struct journal_head *jh = bh2jh(bh);
+ int ret = 0;
jbd_debug(5, "journal_head %p\n", jh);
JBUFFER_TRACE(jh, "entry");
if (is_handle_aborted(handle))
goto out;
+ if (!buffer_jbd(bh)) {
+ ret = -EUCLEAN;
+ goto out;
+ }
jbd_lock_bh_state(bh);
@@ -1093,8 +1103,20 @@
*/
if (jh->b_transaction == transaction && jh->b_jlist == BJ_Metadata) {
JBUFFER_TRACE(jh, "fastpath");
- J_ASSERT_JH(jh, jh->b_transaction ==
- journal->j_running_transaction);
+ if (unlikely(jh->b_transaction !=
+ journal->j_running_transaction)) {
+ printk(KERN_EMERG "JBD: %s: "
+ "jh->b_transaction (%llu, %p, %u) != "
+ "journal->j_running_transaction (%p, %u)",
+ journal->j_devname,
+ (unsigned long long) bh->b_blocknr,
+ jh->b_transaction,
+ jh->b_transaction ? jh->b_transaction->t_tid : 0,
+ journal->j_running_transaction,
+ journal->j_running_transaction ?
+ journal->j_running_transaction->t_tid : 0);
+ ret = -EINVAL;
+ }
goto out_unlock_bh;
}
@@ -1108,9 +1130,32 @@
*/
if (jh->b_transaction != transaction) {
JBUFFER_TRACE(jh, "already on other transaction");
- J_ASSERT_JH(jh, jh->b_transaction ==
- journal->j_committing_transaction);
- J_ASSERT_JH(jh, jh->b_next_transaction == transaction);
+ if (unlikely(jh->b_transaction !=
+ journal->j_committing_transaction)) {
+ printk(KERN_EMERG "JBD: %s: "
+ "jh->b_transaction (%llu, %p, %u) != "
+ "journal->j_committing_transaction (%p, %u)",
+ journal->j_devname,
+ (unsigned long long) bh->b_blocknr,
+ jh->b_transaction,
+ jh->b_transaction ? jh->b_transaction->t_tid : 0,
+ journal->j_committing_transaction,
+ journal->j_committing_transaction ?
+ journal->j_committing_transaction->t_tid : 0);
+ ret = -EINVAL;
+ }
+ if (unlikely(jh->b_next_transaction != transaction)) {
+ printk(KERN_EMERG "JBD: %s: "
+ "jh->b_next_transaction (%llu, %p, %u) != "
+ "transaction (%p, %u)",
+ journal->j_devname,
+ (unsigned long long) bh->b_blocknr,
+ jh->b_next_transaction,
+ jh->b_next_transaction ?
+ jh->b_next_transaction->t_tid : 0,
+ transaction, transaction->t_tid);
+ ret = -EINVAL;
+ }
/* And this case is illegal: we can't reuse another
* transaction's data buffer, ever. */
goto out_unlock_bh;
@@ -1127,7 +1172,8 @@
jbd_unlock_bh_state(bh);
out:
JBUFFER_TRACE(jh, "exit");
- return 0;
+ WARN_ON(ret); /* All errors are bugs, so dump the stack */
+ return ret;
}
/*
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 9659b7c..be6169b 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -245,7 +245,7 @@
ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name,
dentry->d_name.len, dead_f, now);
if (dead_f->inocache)
- dentry->d_inode->i_nlink = dead_f->inocache->pino_nlink;
+ set_nlink(dentry->d_inode, dead_f->inocache->pino_nlink);
if (!ret)
dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
return ret;
@@ -278,7 +278,7 @@
if (!ret) {
mutex_lock(&f->sem);
- old_dentry->d_inode->i_nlink = ++f->inocache->pino_nlink;
+ set_nlink(old_dentry->d_inode, ++f->inocache->pino_nlink);
mutex_unlock(&f->sem);
d_instantiate(dentry, old_dentry->d_inode);
dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
@@ -497,7 +497,7 @@
f = JFFS2_INODE_INFO(inode);
/* Directories get nlink 2 at start */
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
/* but ic->pino_nlink is the parent ino# */
f->inocache->pino_nlink = dir_i->i_ino;
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index bbcb975..7286e44 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -278,7 +278,7 @@
inode->i_mtime = ITIME(je32_to_cpu(latest_node.mtime));
inode->i_ctime = ITIME(je32_to_cpu(latest_node.ctime));
- inode->i_nlink = f->inocache->pino_nlink;
+ set_nlink(inode, f->inocache->pino_nlink);
inode->i_blocks = (inode->i_size + 511) >> 9;
@@ -291,7 +291,7 @@
case S_IFDIR:
{
struct jffs2_full_dirent *fd;
- inode->i_nlink = 2; /* parent and '.' */
+ set_nlink(inode, 2); /* parent and '.' */
for (fd=f->dents; fd; fd = fd->next) {
if (fd->type == DT_DIR && fd->ino)
@@ -453,7 +453,7 @@
iput(inode);
return ERR_PTR(ret);
}
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_ino = je32_to_cpu(ri->ino);
inode->i_mode = jemode_to_cpu(ri->mode);
inode->i_gid = je16_to_cpu(ri->gid);
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index b78b2f9..1b6f15f 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -457,7 +457,7 @@
/* read the page of fixed disk inode (AIT) in raw mode */
mp = read_metapage(ip, address << sbi->l2nbperpage, PSIZE, 1);
if (mp == NULL) {
- ip->i_nlink = 1; /* Don't want iput() deleting it */
+ set_nlink(ip, 1); /* Don't want iput() deleting it */
iput(ip);
return (NULL);
}
@@ -469,7 +469,7 @@
/* copy on-disk inode to in-memory inode */
if ((copy_from_dinode(dp, ip)) != 0) {
/* handle bad return by returning NULL for ip */
- ip->i_nlink = 1; /* Don't want iput() deleting it */
+ set_nlink(ip, 1); /* Don't want iput() deleting it */
iput(ip);
/* release the page */
release_metapage(mp);
@@ -3076,7 +3076,7 @@
ip->i_mode |= 0001;
}
}
- ip->i_nlink = le32_to_cpu(dip->di_nlink);
+ set_nlink(ip, le32_to_cpu(dip->di_nlink));
jfs_ip->saved_uid = le32_to_cpu(dip->di_uid);
if (sbi->uid == -1)
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index 2686531..c1a3e60 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -157,7 +157,7 @@
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
fail_unlock:
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
fail_put:
iput(inode);
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index e17545e..a112ad9 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -172,7 +172,7 @@
mutex_unlock(&JFS_IP(dip)->commit_mutex);
if (rc) {
free_ea_wmap(ip);
- ip->i_nlink = 0;
+ clear_nlink(ip);
unlock_new_inode(ip);
iput(ip);
} else {
@@ -292,7 +292,7 @@
goto out3;
}
- ip->i_nlink = 2; /* for '.' */
+ set_nlink(ip, 2); /* for '.' */
ip->i_op = &jfs_dir_inode_operations;
ip->i_fop = &jfs_dir_operations;
@@ -311,7 +311,7 @@
mutex_unlock(&JFS_IP(dip)->commit_mutex);
if (rc) {
free_ea_wmap(ip);
- ip->i_nlink = 0;
+ clear_nlink(ip);
unlock_new_inode(ip);
iput(ip);
} else {
@@ -844,7 +844,7 @@
rc = txCommit(tid, 2, &iplist[0], 0);
if (rc) {
- ip->i_nlink--; /* never instantiated */
+ drop_nlink(ip); /* never instantiated */
iput(ip);
} else
d_instantiate(dentry, ip);
@@ -1048,7 +1048,7 @@
mutex_unlock(&JFS_IP(dip)->commit_mutex);
if (rc) {
free_ea_wmap(ip);
- ip->i_nlink = 0;
+ clear_nlink(ip);
unlock_new_inode(ip);
iput(ip);
} else {
@@ -1433,7 +1433,7 @@
mutex_unlock(&JFS_IP(dir)->commit_mutex);
if (rc) {
free_ea_wmap(ip);
- ip->i_nlink = 0;
+ clear_nlink(ip);
unlock_new_inode(ip);
iput(ip);
} else {
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 06c8a67..a44eff0 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -485,7 +485,6 @@
goto out_unload;
}
inode->i_ino = 0;
- inode->i_nlink = 1;
inode->i_size = sb->s_bdev->bd_inode->i_size;
inode->i_mapping->a_ops = &jfs_metapage_aops;
insert_inode_hash(inode);
diff --git a/fs/libfs.c b/fs/libfs.c
index c18e9a1..f6d411e 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -490,7 +490,7 @@
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
root = d_alloc_root(inode);
if (!root) {
iput(inode);
@@ -510,8 +510,10 @@
if (!dentry)
goto out;
inode = new_inode(s);
- if (!inode)
+ if (!inode) {
+ dput(dentry);
goto out;
+ }
inode->i_mode = S_IFREG | files->mode;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_fop = files->ops;
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index b3ff3d8..b7d7f67 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -197,7 +197,7 @@
{
int ret;
- inode->i_nlink--;
+ drop_nlink(inode);
ret = write_inode(inode);
LOGFS_BUG_ON(ret, inode->i_sb);
return ret;
@@ -433,7 +433,7 @@
ta = kzalloc(sizeof(*ta), GFP_KERNEL);
if (!ta) {
- inode->i_nlink--;
+ drop_nlink(inode);
iput(inode);
return -ENOMEM;
}
@@ -456,7 +456,7 @@
abort_transaction(inode, ta);
li->li_flags |= LOGFS_IF_STILLBORN;
/* FIXME: truncate symlink */
- inode->i_nlink--;
+ drop_nlink(inode);
iput(inode);
goto out;
}
@@ -563,7 +563,7 @@
inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
ihold(inode);
- inode->i_nlink++;
+ inc_nlink(inode);
mark_inode_dirty_sync(inode);
return __logfs_create(dir, dentry, inode, NULL, 0);
diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c
index edfea7a..7e441ad 100644
--- a/fs/logfs/inode.c
+++ b/fs/logfs/inode.c
@@ -93,7 +93,7 @@
/* inode->i_nlink == 0 can be true when called from
* block validator */
/* set i_nlink to 0 to prevent caching */
- inode->i_nlink = 0;
+ clear_nlink(inode);
logfs_inode(inode)->li_flags |= LOGFS_IF_ZOMBIE;
iget_failed(inode);
if (!err)
@@ -199,7 +199,6 @@
inode->i_blocks = 0;
inode->i_ctime = CURRENT_TIME;
inode->i_mtime = CURRENT_TIME;
- inode->i_nlink = 1;
li->li_refcount = 1;
INIT_LIST_HEAD(&li->li_freeing_list);
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index d8d0938..2ac4217 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -126,7 +126,7 @@
inode->i_atime = be64_to_timespec(di->di_atime);
inode->i_ctime = be64_to_timespec(di->di_ctime);
inode->i_mtime = be64_to_timespec(di->di_mtime);
- inode->i_nlink = be32_to_cpu(di->di_refcount);
+ set_nlink(inode, be32_to_cpu(di->di_refcount));
inode->i_generation = be32_to_cpu(di->di_generation);
switch (inode->i_mode & S_IFMT) {
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index e7d23e2..64cdcd6 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -446,7 +446,7 @@
inode->i_mode = raw_inode->i_mode;
inode->i_uid = (uid_t)raw_inode->i_uid;
inode->i_gid = (gid_t)raw_inode->i_gid;
- inode->i_nlink = raw_inode->i_nlinks;
+ set_nlink(inode, raw_inode->i_nlinks);
inode->i_size = raw_inode->i_size;
inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = raw_inode->i_time;
inode->i_mtime.tv_nsec = 0;
@@ -479,7 +479,7 @@
inode->i_mode = raw_inode->i_mode;
inode->i_uid = (uid_t)raw_inode->i_uid;
inode->i_gid = (gid_t)raw_inode->i_gid;
- inode->i_nlink = raw_inode->i_nlinks;
+ set_nlink(inode, raw_inode->i_nlinks);
inode->i_size = raw_inode->i_size;
inode->i_mtime.tv_sec = raw_inode->i_mtime;
inode->i_atime.tv_sec = raw_inode->i_atime;
diff --git a/fs/namei.c b/fs/namei.c
index 7657be4..ac6d214 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -137,7 +137,7 @@
return retval;
}
-static char *getname_flags(const char __user * filename, int flags)
+static char *getname_flags(const char __user *filename, int flags, int *empty)
{
char *tmp, *result;
@@ -148,6 +148,8 @@
result = tmp;
if (retval < 0) {
+ if (retval == -ENOENT && empty)
+ *empty = 1;
if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
__putname(tmp);
result = ERR_PTR(retval);
@@ -160,7 +162,7 @@
char *getname(const char __user * filename)
{
- return getname_flags(filename, 0);
+ return getname_flags(filename, 0, 0);
}
#ifdef CONFIG_AUDITSYSCALL
@@ -1798,11 +1800,11 @@
return __lookup_hash(&this, base, NULL);
}
-int user_path_at(int dfd, const char __user *name, unsigned flags,
- struct path *path)
+int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
+ struct path *path, int *empty)
{
struct nameidata nd;
- char *tmp = getname_flags(name, flags);
+ char *tmp = getname_flags(name, flags, empty);
int err = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
@@ -1816,6 +1818,12 @@
return err;
}
+int user_path_at(int dfd, const char __user *name, unsigned flags,
+ struct path *path)
+{
+ return user_path_at_empty(dfd, name, flags, path, 0);
+}
+
static int user_path_parent(int dfd, const char __user *path,
struct nameidata *nd, char **name)
{
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 202f370..5b5fa33 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -228,7 +228,7 @@
DDPRINTK("ncp_read_inode: inode->i_mode = %u\n", inode->i_mode);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_uid = server->m.uid;
inode->i_gid = server->m.gid;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 4dc6d07..c07a55a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -320,7 +320,7 @@
memset(&inode->i_ctime, 0, sizeof(inode->i_ctime));
inode->i_version = 0;
inode->i_size = 0;
- inode->i_nlink = 0;
+ clear_nlink(inode);
inode->i_uid = -2;
inode->i_gid = -2;
inode->i_blocks = 0;
@@ -355,7 +355,7 @@
| NFS_INO_INVALID_DATA
| NFS_INO_REVAL_PAGECACHE;
if (fattr->valid & NFS_ATTR_FATTR_NLINK)
- inode->i_nlink = fattr->nlink;
+ set_nlink(inode, fattr->nlink);
else if (nfs_server_capable(inode, NFS_CAP_NLINK))
nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
if (fattr->valid & NFS_ATTR_FATTR_OWNER)
@@ -1361,7 +1361,7 @@
invalid |= NFS_INO_INVALID_ATTR;
if (S_ISDIR(inode->i_mode))
invalid |= NFS_INO_INVALID_DATA;
- inode->i_nlink = fattr->nlink;
+ set_nlink(inode, fattr->nlink);
}
} else if (server->caps & NFS_CAP_NLINK)
invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 66d095d..b6fa792 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -655,7 +655,7 @@
default:
return nfserr_bad_xdr;
}
- w &= !NFS4_SHARE_ACCESS_MASK;
+ w &= ~NFS4_SHARE_ACCESS_MASK;
if (!w)
return nfs_ok;
if (!argp->minorversion)
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 666628b..b50ffb7 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -354,7 +354,7 @@
failed_acl:
failed_bmap:
- inode->i_nlink = 0;
+ clear_nlink(inode);
iput(inode); /* raw_inode will be deleted through
generic_delete_inode() */
goto failed;
@@ -396,7 +396,7 @@
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
inode->i_uid = (uid_t)le32_to_cpu(raw_inode->i_uid);
inode->i_gid = (gid_t)le32_to_cpu(raw_inode->i_gid);
- inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+ set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
inode->i_size = le64_to_cpu(raw_inode->i_size);
inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index a314199..768982d 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -289,7 +289,7 @@
nilfs_warning(inode->i_sb, __func__,
"deleting nonexistent file (%lu), %d\n",
inode->i_ino, inode->i_nlink);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
err = nilfs_delete_entry(de, page);
if (err)
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 1371487..97e2dac 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -612,7 +612,7 @@
* might be tricky due to vfs interactions. Need to think about this
* some more when implementing the unlink command.
*/
- vi->i_nlink = le16_to_cpu(m->link_count);
+ set_nlink(vi, le16_to_cpu(m->link_count));
/*
* FIXME: Reparse points can have the directory bit set even though
* they would be S_IFLNK. Need to deal with this further below when we
@@ -634,7 +634,7 @@
vi->i_mode &= ~vol->dmask;
/* Things break without this kludge! */
if (vi->i_nlink > 1)
- vi->i_nlink = 1;
+ set_nlink(vi, 1);
} else {
vi->i_mode |= S_IFREG;
/* Apply the file permissions mask set in the mount options. */
@@ -1242,7 +1242,7 @@
vi->i_version = base_vi->i_version;
vi->i_uid = base_vi->i_uid;
vi->i_gid = base_vi->i_gid;
- vi->i_nlink = base_vi->i_nlink;
+ set_nlink(vi, base_vi->i_nlink);
vi->i_mtime = base_vi->i_mtime;
vi->i_ctime = base_vi->i_ctime;
vi->i_atime = base_vi->i_atime;
@@ -1508,7 +1508,7 @@
vi->i_version = base_vi->i_version;
vi->i_uid = base_vi->i_uid;
vi->i_gid = base_vi->i_gid;
- vi->i_nlink = base_vi->i_nlink;
+ set_nlink(vi, base_vi->i_nlink);
vi->i_mtime = base_vi->i_mtime;
vi->i_ctime = base_vi->i_ctime;
vi->i_atime = base_vi->i_atime;
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 8582e3f..e2878b5 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -2292,7 +2292,7 @@
ocfs2_journal_dirty(handle, di_bh);
i_size_write(inode, size);
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_blocks = ocfs2_inode_sector_count(inode);
ret = ocfs2_mark_inode_dirty(handle, inode, di_bh);
@@ -2354,7 +2354,7 @@
ocfs2_journal_dirty(handle, new_bh);
i_size_write(inode, inode->i_sb->s_blocksize);
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_blocks = ocfs2_inode_sector_count(inode);
status = ocfs2_mark_inode_dirty(handle, inode, fe_bh);
if (status < 0) {
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 7642d7c..e1ed5e5 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2092,7 +2092,7 @@
inode->i_uid = be32_to_cpu(lvb->lvb_iuid);
inode->i_gid = be32_to_cpu(lvb->lvb_igid);
inode->i_mode = be16_to_cpu(lvb->lvb_imode);
- inode->i_nlink = be16_to_cpu(lvb->lvb_inlink);
+ set_nlink(inode, be16_to_cpu(lvb->lvb_inlink));
ocfs2_unpack_timespec(&inode->i_atime,
be64_to_cpu(lvb->lvb_iatime_packed));
ocfs2_unpack_timespec(&inode->i_mtime,
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index b4c8bb6..a22d2c0 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -291,7 +291,7 @@
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)le64_to_cpu(fe->i_blkno));
- inode->i_nlink = ocfs2_read_links_count(fe);
+ set_nlink(inode, ocfs2_read_links_count(fe));
trace_ocfs2_populate_inode(OCFS2_I(inode)->ip_blkno,
le32_to_cpu(fe->i_flags));
@@ -1290,7 +1290,7 @@
OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features);
ocfs2_set_inode_flags(inode);
i_size_write(inode, le64_to_cpu(fe->i_size));
- inode->i_nlink = ocfs2_read_links_count(fe);
+ set_nlink(inode, ocfs2_read_links_count(fe));
inode->i_uid = le32_to_cpu(fe->i_uid);
inode->i_gid = le32_to_cpu(fe->i_gid);
inode->i_mode = le16_to_cpu(fe->i_mode);
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 53aa41e..a8b2bfe 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -199,9 +199,7 @@
* these are used by the support functions here and in
* callers. */
if (S_ISDIR(mode))
- inode->i_nlink = 2;
- else
- inode->i_nlink = 1;
+ set_nlink(inode, 2);
inode_init_owner(inode, dir, mode);
dquot_initialize(inode);
return inode;
@@ -1379,7 +1377,7 @@
}
if (new_inode) {
- new_inode->i_nlink--;
+ drop_nlink(new_inode);
new_inode->i_ctime = CURRENT_TIME;
}
old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME;
@@ -1387,9 +1385,9 @@
if (update_dot_dot) {
status = ocfs2_update_entry(old_inode, handle,
&old_inode_dot_dot_res, new_dir);
- old_dir->i_nlink--;
+ drop_nlink(old_dir);
if (new_inode) {
- new_inode->i_nlink--;
+ drop_nlink(new_inode);
} else {
inc_nlink(new_dir);
mark_inode_dirty(new_dir);
@@ -2018,7 +2016,7 @@
orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data;
if (S_ISDIR(inode->i_mode))
ocfs2_add_links_count(orphan_fe, 1);
- orphan_dir_inode->i_nlink = ocfs2_read_links_count(orphan_fe);
+ set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe));
ocfs2_journal_dirty(handle, orphan_dir_bh);
status = __ocfs2_add_entry(handle, orphan_dir_inode, name,
@@ -2116,7 +2114,7 @@
orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data;
if (S_ISDIR(inode->i_mode))
ocfs2_add_links_count(orphan_fe, -1);
- orphan_dir_inode->i_nlink = ocfs2_read_links_count(orphan_fe);
+ set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe));
ocfs2_journal_dirty(handle, orphan_dir_bh);
leave:
@@ -2282,7 +2280,7 @@
goto leave;
}
- inode->i_nlink = 0;
+ clear_nlink(inode);
/* do the real work now. */
status = __ocfs2_mknod_locked(dir, inode,
0, &new_di_bh, parent_di_bh, handle,
@@ -2437,7 +2435,7 @@
di = (struct ocfs2_dinode *)di_bh->b_data;
le32_add_cpu(&di->i_flags, -OCFS2_ORPHANED_FL);
di->i_orphaned_slot = 0;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
ocfs2_set_links_count(di, inode->i_nlink);
ocfs2_journal_dirty(handle, di_bh);
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index a2a5bff..e4e0ff7 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -242,7 +242,7 @@
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
inode->i_op = &openprom_inode_operations;
inode->i_fop = &openprom_operations;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
break;
case op_inode_prop:
if (!strcmp(dp->name, "options") && (len == 17) &&
@@ -251,7 +251,7 @@
else
inode->i_mode = S_IFREG | S_IRUGO;
inode->i_fop = &openpromfs_prop_ops;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_size = ent_oi->u.prop->length;
break;
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 8f0087e..2db1bd3 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1652,12 +1652,46 @@
return error;
}
+static int proc_pid_fd_link_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ struct inode *inode = dentry->d_inode;
+ struct task_struct *task = get_proc_task(inode);
+ int rc;
+
+ if (task == NULL)
+ return -ESRCH;
+
+ rc = -EACCES;
+ if (lock_trace(task))
+ goto out_task;
+
+ generic_fillattr(inode, stat);
+ unlock_trace(task);
+ rc = 0;
+out_task:
+ put_task_struct(task);
+ return rc;
+}
+
static const struct inode_operations proc_pid_link_inode_operations = {
.readlink = proc_pid_readlink,
.follow_link = proc_pid_follow_link,
.setattr = proc_setattr,
};
+static const struct inode_operations proc_fdinfo_link_inode_operations = {
+ .setattr = proc_setattr,
+ .getattr = proc_pid_fd_link_getattr,
+};
+
+static const struct inode_operations proc_fd_link_inode_operations = {
+ .readlink = proc_pid_readlink,
+ .follow_link = proc_pid_follow_link,
+ .setattr = proc_setattr,
+ .getattr = proc_pid_fd_link_getattr,
+};
+
/* building an inode */
@@ -1889,49 +1923,61 @@
static int proc_fd_info(struct inode *inode, struct path *path, char *info)
{
- struct task_struct *task = get_proc_task(inode);
- struct files_struct *files = NULL;
+ struct task_struct *task;
+ struct files_struct *files;
struct file *file;
int fd = proc_fd(inode);
+ int rc;
- if (task) {
- files = get_files_struct(task);
- put_task_struct(task);
- }
- if (files) {
- /*
- * We are not taking a ref to the file structure, so we must
- * hold ->file_lock.
- */
- spin_lock(&files->file_lock);
- file = fcheck_files(files, fd);
- if (file) {
- unsigned int f_flags;
- struct fdtable *fdt;
+ task = get_proc_task(inode);
+ if (!task)
+ return -ENOENT;
- fdt = files_fdtable(files);
- f_flags = file->f_flags & ~O_CLOEXEC;
- if (FD_ISSET(fd, fdt->close_on_exec))
- f_flags |= O_CLOEXEC;
+ rc = -EACCES;
+ if (lock_trace(task))
+ goto out_task;
- if (path) {
- *path = file->f_path;
- path_get(&file->f_path);
- }
- if (info)
- snprintf(info, PROC_FDINFO_MAX,
- "pos:\t%lli\n"
- "flags:\t0%o\n",
- (long long) file->f_pos,
- f_flags);
- spin_unlock(&files->file_lock);
- put_files_struct(files);
- return 0;
+ rc = -ENOENT;
+ files = get_files_struct(task);
+ if (files == NULL)
+ goto out_unlock;
+
+ /*
+ * We are not taking a ref to the file structure, so we must
+ * hold ->file_lock.
+ */
+ spin_lock(&files->file_lock);
+ file = fcheck_files(files, fd);
+ if (file) {
+ unsigned int f_flags;
+ struct fdtable *fdt;
+
+ fdt = files_fdtable(files);
+ f_flags = file->f_flags & ~O_CLOEXEC;
+ if (FD_ISSET(fd, fdt->close_on_exec))
+ f_flags |= O_CLOEXEC;
+
+ if (path) {
+ *path = file->f_path;
+ path_get(&file->f_path);
}
- spin_unlock(&files->file_lock);
- put_files_struct(files);
- }
- return -ENOENT;
+ if (info)
+ snprintf(info, PROC_FDINFO_MAX,
+ "pos:\t%lli\n"
+ "flags:\t0%o\n",
+ (long long) file->f_pos,
+ f_flags);
+ rc = 0;
+ } else
+ rc = -ENOENT;
+ spin_unlock(&files->file_lock);
+ put_files_struct(files);
+
+out_unlock:
+ unlock_trace(task);
+out_task:
+ put_task_struct(task);
+ return rc;
}
static int proc_fd_link(struct inode *inode, struct path *path)
@@ -2026,7 +2072,7 @@
spin_unlock(&files->file_lock);
put_files_struct(files);
- inode->i_op = &proc_pid_link_inode_operations;
+ inode->i_op = &proc_fd_link_inode_operations;
inode->i_size = 64;
ei->op.proc_get_link = proc_fd_link;
d_set_d_op(dentry, &tid_fd_dentry_operations);
@@ -2058,7 +2104,12 @@
if (fd == ~0U)
goto out;
+ result = ERR_PTR(-EACCES);
+ if (lock_trace(task))
+ goto out;
+
result = instantiate(dir, dentry, task, &fd);
+ unlock_trace(task);
out:
put_task_struct(task);
out_no_task:
@@ -2078,23 +2129,28 @@
retval = -ENOENT;
if (!p)
goto out_no_task;
+
+ retval = -EACCES;
+ if (lock_trace(p))
+ goto out;
+
retval = 0;
fd = filp->f_pos;
switch (fd) {
case 0:
if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
- goto out;
+ goto out_unlock;
filp->f_pos++;
case 1:
ino = parent_ino(dentry);
if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
- goto out;
+ goto out_unlock;
filp->f_pos++;
default:
files = get_files_struct(p);
if (!files)
- goto out;
+ goto out_unlock;
rcu_read_lock();
for (fd = filp->f_pos-2;
fd < files_fdtable(files)->max_fds;
@@ -2118,6 +2174,9 @@
rcu_read_unlock();
put_files_struct(files);
}
+
+out_unlock:
+ unlock_trace(p);
out:
put_task_struct(p);
out_no_task:
@@ -2195,6 +2254,7 @@
ei->fd = fd;
inode->i_mode = S_IFREG | S_IRUSR;
inode->i_fop = &proc_fdinfo_file_operations;
+ inode->i_op = &proc_fdinfo_link_inode_operations;
d_set_d_op(dentry, &tid_fd_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
@@ -2248,7 +2308,7 @@
ei = PROC_I(inode);
inode->i_mode = p->mode;
if (S_ISDIR(inode->i_mode))
- inode->i_nlink = 2; /* Use getattr to fix if necessary */
+ set_nlink(inode, 2); /* Use getattr to fix if necessary */
if (p->iop)
inode->i_op = p->iop;
if (p->fop)
@@ -2642,7 +2702,7 @@
inode->i_mode = p->mode;
if (S_ISDIR(inode->i_mode))
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
if (S_ISLNK(inode->i_mode))
inode->i_size = 64;
if (p->iop)
@@ -2981,8 +3041,8 @@
inode->i_fop = &proc_tgid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff,
- ARRAY_SIZE(tgid_base_stuff));
+ set_nlink(inode, 2 + pid_entry_count_dirs(tgid_base_stuff,
+ ARRAY_SIZE(tgid_base_stuff)));
d_set_d_op(dentry, &pid_dentry_operations);
@@ -3233,8 +3293,8 @@
inode->i_fop = &proc_tid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff,
- ARRAY_SIZE(tid_base_stuff));
+ set_nlink(inode, 2 + pid_entry_count_dirs(tid_base_stuff,
+ ARRAY_SIZE(tid_base_stuff)));
d_set_d_op(dentry, &pid_dentry_operations);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 9d99131..10090d9 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -283,7 +283,7 @@
struct inode *inode = dentry->d_inode;
struct proc_dir_entry *de = PROC_I(inode)->pde;
if (de && de->nlink)
- inode->i_nlink = de->nlink;
+ set_nlink(inode, de->nlink);
generic_fillattr(inode, stat);
return 0;
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 7ed72d6..7737c54 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -445,7 +445,7 @@
if (de->size)
inode->i_size = de->size;
if (de->nlink)
- inode->i_nlink = de->nlink;
+ set_nlink(inode, de->nlink);
if (de->proc_iops)
inode->i_op = de->proc_iops;
if (de->proc_fops) {
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 1a77dbe..a6b6217 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -3,6 +3,7 @@
*/
#include <linux/init.h>
#include <linux/sysctl.h>
+#include <linux/poll.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/namei.h>
@@ -14,6 +15,15 @@
static const struct file_operations proc_sys_dir_file_operations;
static const struct inode_operations proc_sys_dir_operations;
+void proc_sys_poll_notify(struct ctl_table_poll *poll)
+{
+ if (!poll)
+ return;
+
+ atomic_inc(&poll->event);
+ wake_up_interruptible(&poll->wait);
+}
+
static struct inode *proc_sys_make_inode(struct super_block *sb,
struct ctl_table_header *head, struct ctl_table *table)
{
@@ -39,7 +49,7 @@
inode->i_fop = &proc_sys_file_operations;
} else {
inode->i_mode |= S_IFDIR;
- inode->i_nlink = 0;
+ clear_nlink(inode);
inode->i_op = &proc_sys_dir_operations;
inode->i_fop = &proc_sys_dir_file_operations;
}
@@ -176,6 +186,39 @@
return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
}
+static int proc_sys_open(struct inode *inode, struct file *filp)
+{
+ struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+
+ if (table->poll)
+ filp->private_data = proc_sys_poll_event(table->poll);
+
+ return 0;
+}
+
+static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
+{
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+ unsigned long event = (unsigned long)filp->private_data;
+ unsigned int ret = DEFAULT_POLLMASK;
+
+ if (!table->proc_handler)
+ goto out;
+
+ if (!table->poll)
+ goto out;
+
+ poll_wait(filp, &table->poll->wait, wait);
+
+ if (event != atomic_read(&table->poll->event)) {
+ filp->private_data = proc_sys_poll_event(table->poll);
+ ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI;
+ }
+
+out:
+ return ret;
+}
static int proc_sys_fill_cache(struct file *filp, void *dirent,
filldir_t filldir,
@@ -364,12 +407,15 @@
}
static const struct file_operations proc_sys_file_operations = {
+ .open = proc_sys_open,
+ .poll = proc_sys_poll,
.read = proc_sys_read,
.write = proc_sys_write,
.llseek = default_llseek,
};
static const struct file_operations proc_sys_dir_file_operations = {
+ .read = generic_read_dir,
.readdir = proc_sys_readdir,
.llseek = generic_file_llseek,
};
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 2b06466..3bdd214 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -379,7 +379,7 @@
inode->i_mode = le16_to_cpu(raw_inode->di_mode);
inode->i_uid = (uid_t)le16_to_cpu(raw_inode->di_uid);
inode->i_gid = (gid_t)le16_to_cpu(raw_inode->di_gid);
- inode->i_nlink = le16_to_cpu(raw_inode->di_nlink);
+ set_nlink(inode, le16_to_cpu(raw_inode->di_nlink));
inode->i_size = le32_to_cpu(raw_inode->di_size);
inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->di_mtime);
inode->i_mtime.tv_nsec = 0;
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 10b6be3..aae0edb 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -363,12 +363,15 @@
}
sb = quotactl_block(special);
- if (IS_ERR(sb))
- return PTR_ERR(sb);
+ if (IS_ERR(sb)) {
+ ret = PTR_ERR(sb);
+ goto out;
+ }
ret = do_quotactl(sb, type, cmds, id, addr, pathp);
drop_super(sb);
+out:
if (pathp && !IS_ERR(pathp))
path_put(pathp);
return ret;
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index eacb166..462ceb3 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -23,7 +23,6 @@
* caches is sufficient.
*/
-#include <linux/module.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
@@ -288,14 +287,7 @@
{
return register_filesystem(&ramfs_fs_type);
}
-
-static void __exit exit_ramfs_fs(void)
-{
- unregister_filesystem(&ramfs_fs_type);
-}
-
module_init(init_ramfs_fs)
-module_exit(exit_ramfs_fs)
int __init init_rootfs(void)
{
@@ -311,5 +303,3 @@
return err;
}
-
-MODULE_LICENSE("GPL");
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 9b0d4b7..950f13a 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1154,7 +1154,7 @@
set_inode_item_key_version(inode, KEY_FORMAT_3_5);
set_inode_sd_version(inode, STAT_DATA_V1);
inode->i_mode = sd_v1_mode(sd);
- inode->i_nlink = sd_v1_nlink(sd);
+ set_nlink(inode, sd_v1_nlink(sd));
inode->i_uid = sd_v1_uid(sd);
inode->i_gid = sd_v1_gid(sd);
inode->i_size = sd_v1_size(sd);
@@ -1199,7 +1199,7 @@
struct stat_data *sd = (struct stat_data *)B_I_PITEM(bh, ih);
inode->i_mode = sd_v2_mode(sd);
- inode->i_nlink = sd_v2_nlink(sd);
+ set_nlink(inode, sd_v2_nlink(sd));
inode->i_uid = sd_v2_uid(sd);
inode->i_size = sd_v2_size(sd);
inode->i_gid = sd_v2_gid(sd);
@@ -1444,7 +1444,7 @@
/* a stale NFS handle can trigger this without it being an error */
pathrelse(&path_to_sd);
reiserfs_make_bad_inode(inode);
- inode->i_nlink = 0;
+ clear_nlink(inode);
return;
}
@@ -1832,7 +1832,7 @@
#endif
/* fill stat data */
- inode->i_nlink = (S_ISDIR(mode) ? 2 : 1);
+ set_nlink(inode, (S_ISDIR(mode) ? 2 : 1));
/* uid and gid must already be set by the caller for quota init */
@@ -1987,7 +1987,7 @@
make_bad_inode(inode);
out_inserted_sd:
- inode->i_nlink = 0;
+ clear_nlink(inode);
th->t_trans_id = 0; /* so the caller can't use this handle later */
unlock_new_inode(inode); /* OK to do even if we hadn't locked it */
iput(inode);
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index ef39232..80058e8 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -19,7 +19,7 @@
#include <linux/reiserfs_xattr.h>
#include <linux/quotaops.h>
-#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { inc_nlink(i); if (i->i_nlink >= REISERFS_LINK_MAX) i->i_nlink=1; }
+#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { inc_nlink(i); if (i->i_nlink >= REISERFS_LINK_MAX) set_nlink(i, 1); }
#define DEC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) drop_nlink(i);
// directory item contains array of entry headers. This performs
@@ -622,7 +622,7 @@
dentry->d_name.len, inode, 1 /*visible */ );
if (retval) {
int err;
- inode->i_nlink--;
+ drop_nlink(inode);
reiserfs_update_sd(&th, inode);
err = journal_end(&th, dir->i_sb, jbegin_count);
if (err)
@@ -702,7 +702,7 @@
dentry->d_name.len, inode, 1 /*visible */ );
if (retval) {
int err;
- inode->i_nlink--;
+ drop_nlink(inode);
reiserfs_update_sd(&th, inode);
err = journal_end(&th, dir->i_sb, jbegin_count);
if (err)
@@ -787,7 +787,7 @@
dentry->d_name.len, inode, 1 /*visible */ );
if (retval) {
int err;
- inode->i_nlink = 0;
+ clear_nlink(inode);
DEC_DIR_INODE_NLINK(dir);
reiserfs_update_sd(&th, inode);
err = journal_end(&th, dir->i_sb, jbegin_count);
@@ -964,7 +964,7 @@
reiserfs_warning(inode->i_sb, "reiserfs-7042",
"deleting nonexistent file (%lu), %d",
inode->i_ino, inode->i_nlink);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
drop_nlink(inode);
@@ -1086,7 +1086,7 @@
dentry->d_name.len, inode, 1 /*visible */ );
if (retval) {
int err;
- inode->i_nlink--;
+ drop_nlink(inode);
reiserfs_update_sd(&th, inode);
err = journal_end(&th, parent_dir->i_sb, jbegin_count);
if (err)
@@ -1129,7 +1129,7 @@
retval = journal_begin(&th, dir->i_sb, jbegin_count);
if (retval) {
- inode->i_nlink--;
+ drop_nlink(inode);
reiserfs_write_unlock(dir->i_sb);
return retval;
}
@@ -1144,7 +1144,7 @@
if (retval) {
int err;
- inode->i_nlink--;
+ drop_nlink(inode);
err = journal_end(&th, dir->i_sb, jbegin_count);
reiserfs_write_unlock(dir->i_sb);
return err ? err : retval;
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 2305e31..8b4089f 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -337,7 +337,7 @@
inode->i_metasize = (ROMFH_SIZE + nlen + 1 + ROMFH_PAD) & ROMFH_MASK;
inode->i_dataoffset = pos + inode->i_metasize;
- i->i_nlink = 1; /* Hard to decide.. */
+ set_nlink(i, 1); /* Hard to decide.. */
i->i_size = be32_to_cpu(ri.size);
i->i_mtime.tv_sec = i->i_atime.tv_sec = i->i_ctime.tv_sec = 0;
i->i_mtime.tv_nsec = i->i_atime.tv_nsec = i->i_ctime.tv_nsec = 0;
diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c
index 04bebca..fd7b3b3 100644
--- a/fs/squashfs/inode.c
+++ b/fs/squashfs/inode.c
@@ -159,7 +159,7 @@
frag_offset = 0;
}
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_size = le32_to_cpu(sqsh_ino->file_size);
inode->i_fop = &generic_ro_fops;
inode->i_mode |= S_IFREG;
@@ -203,7 +203,7 @@
}
xattr_id = le32_to_cpu(sqsh_ino->xattr);
- inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
inode->i_size = le64_to_cpu(sqsh_ino->file_size);
inode->i_op = &squashfs_inode_ops;
inode->i_fop = &generic_ro_fops;
@@ -232,7 +232,7 @@
if (err < 0)
goto failed_read;
- inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
inode->i_size = le16_to_cpu(sqsh_ino->file_size);
inode->i_op = &squashfs_dir_inode_ops;
inode->i_fop = &squashfs_dir_ops;
@@ -257,7 +257,7 @@
goto failed_read;
xattr_id = le32_to_cpu(sqsh_ino->xattr);
- inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
inode->i_size = le32_to_cpu(sqsh_ino->file_size);
inode->i_op = &squashfs_dir_inode_ops;
inode->i_fop = &squashfs_dir_ops;
@@ -284,7 +284,7 @@
if (err < 0)
goto failed_read;
- inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
inode->i_size = le32_to_cpu(sqsh_ino->symlink_size);
inode->i_op = &squashfs_symlink_inode_ops;
inode->i_data.a_ops = &squashfs_symlink_aops;
@@ -325,7 +325,7 @@
inode->i_mode |= S_IFCHR;
else
inode->i_mode |= S_IFBLK;
- inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
rdev = le32_to_cpu(sqsh_ino->rdev);
init_special_inode(inode, inode->i_mode, new_decode_dev(rdev));
@@ -349,7 +349,7 @@
inode->i_mode |= S_IFBLK;
xattr_id = le32_to_cpu(sqsh_ino->xattr);
inode->i_op = &squashfs_inode_ops;
- inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
rdev = le32_to_cpu(sqsh_ino->rdev);
init_special_inode(inode, inode->i_mode, new_decode_dev(rdev));
@@ -370,7 +370,7 @@
inode->i_mode |= S_IFIFO;
else
inode->i_mode |= S_IFSOCK;
- inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
init_special_inode(inode, inode->i_mode, 0);
break;
}
@@ -389,7 +389,7 @@
inode->i_mode |= S_IFSOCK;
xattr_id = le32_to_cpu(sqsh_ino->xattr);
inode->i_op = &squashfs_inode_ops;
- inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
init_special_inode(inode, inode->i_mode, 0);
break;
}
diff --git a/fs/stack.c b/fs/stack.c
index b4f2ab4..9c11519 100644
--- a/fs/stack.c
+++ b/fs/stack.c
@@ -71,6 +71,6 @@
dest->i_ctime = src->i_ctime;
dest->i_blkbits = src->i_blkbits;
dest->i_flags = src->i_flags;
- dest->i_nlink = src->i_nlink;
+ set_nlink(dest, src->i_nlink);
}
EXPORT_SYMBOL_GPL(fsstack_copy_attr_all);
diff --git a/fs/stat.c b/fs/stat.c
index 78a3aa8..8806b89 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -294,15 +294,16 @@
{
struct path path;
int error;
+ int empty = 0;
if (bufsiz <= 0)
return -EINVAL;
- error = user_path_at(dfd, pathname, LOOKUP_EMPTY, &path);
+ error = user_path_at_empty(dfd, pathname, LOOKUP_EMPTY, &path, &empty);
if (!error) {
struct inode *inode = path.dentry->d_inode;
- error = -EINVAL;
+ error = empty ? -ENOENT : -EINVAL;
if (inode->i_op->readlink) {
error = security_inode_readlink(path.dentry);
if (!error) {
diff --git a/fs/super.c b/fs/super.c
index 32a81f3..afd0f1a 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -727,8 +727,13 @@
if (sb->s_op->remount_fs) {
retval = sb->s_op->remount_fs(sb, &flags, data);
- if (retval)
- return retval;
+ if (retval) {
+ if (!force)
+ return retval;
+ /* If forced remount, go ahead despite any errors */
+ WARN(1, "forced remount of a %s fs returned %i\n",
+ sb->s_type->name, retval);
+ }
}
sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index e23f288..c81b22f 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -218,7 +218,7 @@
}
if (sysfs_type(sd) == SYSFS_DIR)
- inode->i_nlink = sd->s_dir.subdirs + 2;
+ set_nlink(inode, sd->s_dir.subdirs + 2);
}
int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 0630eb9..25ffb3e 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -219,7 +219,7 @@
inode->i_mode = fs16_to_cpu(sbi, raw_inode->i_mode);
inode->i_uid = (uid_t)fs16_to_cpu(sbi, raw_inode->i_uid);
inode->i_gid = (gid_t)fs16_to_cpu(sbi, raw_inode->i_gid);
- inode->i_nlink = fs16_to_cpu(sbi, raw_inode->i_nlink);
+ set_nlink(inode, fs16_to_cpu(sbi, raw_inode->i_nlink));
inode->i_size = fs32_to_cpu(sbi, raw_inode->i_size);
inode->i_atime.tv_sec = fs32_to_cpu(sbi, raw_inode->i_atime);
inode->i_mtime.tv_sec = fs32_to_cpu(sbi, raw_inode->i_mtime);
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index b281212..20403dc 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -129,7 +129,7 @@
goto out_ino;
inode->i_flags |= (S_NOCMTIME | S_NOATIME);
- inode->i_nlink = le32_to_cpu(ino->nlink);
+ set_nlink(inode, le32_to_cpu(ino->nlink));
inode->i_uid = le32_to_cpu(ino->uid);
inode->i_gid = le32_to_cpu(ino->gid);
inode->i_atime.tv_sec = (int64_t)le64_to_cpu(ino->atime_sec);
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 16f19f5..bf18f7a 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -558,10 +558,10 @@
}
ubifs_assert(inode->i_nlink == 1);
- inode->i_nlink = 0;
+ clear_nlink(inode);
err = remove_xattr(c, host, inode, &nm);
if (err)
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
/* If @i_nlink is 0, 'iput()' will delete the inode */
iput(inode);
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index 95518a9..987585b 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -59,8 +59,8 @@
int nr_groups = bitmap->s_nr_groups;
if (block_group >= nr_groups) {
- udf_debug("block_group (%d) > nr_groups (%d)\n", block_group,
- nr_groups);
+ udf_debug("block_group (%d) > nr_groups (%d)\n",
+ block_group, nr_groups);
}
if (bitmap->s_block_bitmap[block_group]) {
@@ -126,8 +126,9 @@
if (bloc->logicalBlockNum + count < count ||
(bloc->logicalBlockNum + count) > partmap->s_partition_len) {
udf_debug("%d < %d || %d + %d > %d\n",
- bloc->logicalBlockNum, 0, bloc->logicalBlockNum,
- count, partmap->s_partition_len);
+ bloc->logicalBlockNum, 0,
+ bloc->logicalBlockNum, count,
+ partmap->s_partition_len);
goto error_return;
}
@@ -155,7 +156,7 @@
if (udf_set_bit(bit + i, bh->b_data)) {
udf_debug("bit %ld already set\n", bit + i);
udf_debug("byte=%2x\n",
- ((char *)bh->b_data)[(bit + i) >> 3]);
+ ((char *)bh->b_data)[(bit + i) >> 3]);
}
}
udf_add_free_space(sb, sbi->s_partition, count);
@@ -369,7 +370,8 @@
if (bloc->logicalBlockNum + count < count ||
(bloc->logicalBlockNum + count) > partmap->s_partition_len) {
udf_debug("%d < %d || %d + %d > %d\n",
- bloc->logicalBlockNum, 0, bloc->logicalBlockNum, count,
+ bloc->logicalBlockNum, 0,
+ bloc->logicalBlockNum, count,
partmap->s_partition_len);
goto error_return;
}
diff --git a/fs/udf/directory.c b/fs/udf/directory.c
index 2ffdb67..3e44f57 100644
--- a/fs/udf/directory.c
+++ b/fs/udf/directory.c
@@ -162,8 +162,8 @@
int padlen;
if ((!buffer) || (!offset)) {
- udf_debug("invalidparms\n, buffer=%p, offset=%p\n", buffer,
- offset);
+ udf_debug("invalidparms, buffer=%p, offset=%p\n",
+ buffer, offset);
return NULL;
}
@@ -201,7 +201,7 @@
struct short_ad *sa;
if ((!ptr) || (!offset)) {
- printk(KERN_ERR "udf: udf_get_fileshortad() invalidparms\n");
+ pr_err("%s: invalidparms\n", __func__);
return NULL;
}
@@ -223,7 +223,7 @@
struct long_ad *la;
if ((!ptr) || (!offset)) {
- printk(KERN_ERR "udf: udf_get_filelongad() invalidparms\n");
+ pr_err("%s: invalidparms\n", __func__);
return NULL;
}
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 1d1358e..4fd1d80 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -37,6 +37,7 @@
#include <linux/writeback.h>
#include <linux/slab.h>
#include <linux/crc-itu-t.h>
+#include <linux/mpage.h>
#include "udf_i.h"
#include "udf_sb.h"
@@ -83,12 +84,10 @@
end_writeback(inode);
if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB &&
inode->i_size != iinfo->i_lenExtents) {
- printk(KERN_WARNING "UDF-fs (%s): Inode %lu (mode %o) has "
- "inode size %llu different from extent length %llu. "
- "Filesystem need not be standards compliant.\n",
- inode->i_sb->s_id, inode->i_ino, inode->i_mode,
- (unsigned long long)inode->i_size,
- (unsigned long long)iinfo->i_lenExtents);
+ udf_warn(inode->i_sb, "Inode %lu (mode %o) has inode size %llu different from extent length %llu. Filesystem need not be standards compliant.\n",
+ inode->i_ino, inode->i_mode,
+ (unsigned long long)inode->i_size,
+ (unsigned long long)iinfo->i_lenExtents);
}
kfree(iinfo->i_ext.i_data);
iinfo->i_ext.i_data = NULL;
@@ -104,7 +103,13 @@
static int udf_readpage(struct file *file, struct page *page)
{
- return block_read_full_page(page, udf_get_block);
+ return mpage_readpage(page, udf_get_block);
+}
+
+static int udf_readpages(struct file *file, struct address_space *mapping,
+ struct list_head *pages, unsigned nr_pages)
+{
+ return mpage_readpages(mapping, pages, nr_pages, udf_get_block);
}
static int udf_write_begin(struct file *file, struct address_space *mapping,
@@ -139,6 +144,7 @@
const struct address_space_operations udf_aops = {
.readpage = udf_readpage,
+ .readpages = udf_readpages,
.writepage = udf_writepage,
.write_begin = udf_write_begin,
.write_end = generic_write_end,
@@ -1169,16 +1175,15 @@
*/
bh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 0, &ident);
if (!bh) {
- printk(KERN_ERR "udf: udf_read_inode(ino %ld) failed !bh\n",
- inode->i_ino);
+ udf_err(inode->i_sb, "(ino %ld) failed !bh\n", inode->i_ino);
make_bad_inode(inode);
return;
}
if (ident != TAG_IDENT_FE && ident != TAG_IDENT_EFE &&
ident != TAG_IDENT_USE) {
- printk(KERN_ERR "udf: udf_read_inode(ino %ld) "
- "failed ident=%d\n", inode->i_ino, ident);
+ udf_err(inode->i_sb, "(ino %ld) failed ident=%d\n",
+ inode->i_ino, ident);
brelse(bh);
make_bad_inode(inode);
return;
@@ -1218,8 +1223,8 @@
}
brelse(ibh);
} else if (fe->icbTag.strategyType != cpu_to_le16(4)) {
- printk(KERN_ERR "udf: unsupported strategy type: %d\n",
- le16_to_cpu(fe->icbTag.strategyType));
+ udf_err(inode->i_sb, "unsupported strategy type: %d\n",
+ le16_to_cpu(fe->icbTag.strategyType));
brelse(bh);
make_bad_inode(inode);
return;
@@ -1236,6 +1241,7 @@
int offset;
struct udf_sb_info *sbi = UDF_SB(inode->i_sb);
struct udf_inode_info *iinfo = UDF_I(inode);
+ unsigned int link_count;
fe = (struct fileEntry *)bh->b_data;
efe = (struct extendedFileEntry *)bh->b_data;
@@ -1318,9 +1324,10 @@
inode->i_mode &= ~sbi->s_umask;
read_unlock(&sbi->s_cred_lock);
- inode->i_nlink = le16_to_cpu(fe->fileLinkCount);
- if (!inode->i_nlink)
- inode->i_nlink = 1;
+ link_count = le16_to_cpu(fe->fileLinkCount);
+ if (!link_count)
+ link_count = 1;
+ set_nlink(inode, link_count);
inode->i_size = le64_to_cpu(fe->informationLength);
iinfo->i_lenExtents = inode->i_size;
@@ -1413,9 +1420,8 @@
udf_debug("METADATA BITMAP FILE-----\n");
break;
default:
- printk(KERN_ERR "udf: udf_fill_inode(ino %ld) failed unknown "
- "file type=%d\n", inode->i_ino,
- fe->icbTag.fileType);
+ udf_err(inode->i_sb, "(ino %ld) failed unknown file type=%d\n",
+ inode->i_ino, fe->icbTag.fileType);
make_bad_inode(inode);
return;
}
@@ -1438,8 +1444,8 @@
iinfo->i_ext.i_data = kmalloc(size, GFP_KERNEL);
if (!iinfo->i_ext.i_data) {
- printk(KERN_ERR "udf:udf_alloc_i_data (ino %ld) "
- "no free memory\n", inode->i_ino);
+ udf_err(inode->i_sb, "(ino %ld) no free memory\n",
+ inode->i_ino);
return -ENOMEM;
}
@@ -1689,9 +1695,8 @@
if (do_sync) {
sync_dirty_buffer(bh);
if (buffer_write_io_error(bh)) {
- printk(KERN_WARNING "IO error syncing udf inode "
- "[%s:%08lx]\n", inode->i_sb->s_id,
- inode->i_ino);
+ udf_warn(inode->i_sb, "IO error syncing udf inode [%08lx]\n",
+ inode->i_ino);
err = -EIO;
}
}
@@ -1982,8 +1987,7 @@
*elen = le32_to_cpu(lad->extLength) & UDF_EXTENT_LENGTH_MASK;
break;
default:
- udf_debug("alloc_type = %d unsupported\n",
- iinfo->i_alloc_type);
+ udf_debug("alloc_type = %d unsupported\n", iinfo->i_alloc_type);
return -1;
}
diff --git a/fs/udf/lowlevel.c b/fs/udf/lowlevel.c
index 43e24a3..6583fe9 100644
--- a/fs/udf/lowlevel.c
+++ b/fs/udf/lowlevel.c
@@ -38,7 +38,7 @@
if (i == 0) {
udf_debug("XA disk: %s, vol_desc_start=%d\n",
- (ms_info.xa_flag ? "yes" : "no"), ms_info.addr.lba);
+ ms_info.xa_flag ? "yes" : "no", ms_info.addr.lba);
if (ms_info.xa_flag) /* necessary for a valid ms_info.addr */
vol_desc_start = ms_info.addr.lba;
} else {
diff --git a/fs/udf/misc.c b/fs/udf/misc.c
index 9215700..c175b4d 100644
--- a/fs/udf/misc.c
+++ b/fs/udf/misc.c
@@ -204,6 +204,7 @@
{
struct tag *tag_p;
struct buffer_head *bh = NULL;
+ u8 checksum;
/* Read the block */
if (block == 0xFFFFFFFF)
@@ -211,8 +212,8 @@
bh = udf_tread(sb, block);
if (!bh) {
- udf_debug("block=%d, location=%d: read failed\n",
- block, location);
+ udf_err(sb, "read failed, block=%u, location=%d\n",
+ block, location);
return NULL;
}
@@ -227,16 +228,18 @@
}
/* Verify the tag checksum */
- if (udf_tag_checksum(tag_p) != tag_p->tagChecksum) {
- printk(KERN_ERR "udf: tag checksum failed block %d\n", block);
+ checksum = udf_tag_checksum(tag_p);
+ if (checksum != tag_p->tagChecksum) {
+ udf_err(sb, "tag checksum failed, block %u: 0x%02x != 0x%02x\n",
+ block, checksum, tag_p->tagChecksum);
goto error_out;
}
/* Verify the tag version */
if (tag_p->descVersion != cpu_to_le16(0x0002U) &&
tag_p->descVersion != cpu_to_le16(0x0003U)) {
- udf_debug("tag version 0x%04x != 0x0002 || 0x0003 block %d\n",
- le16_to_cpu(tag_p->descVersion), block);
+ udf_err(sb, "tag version 0x%04x != 0x0002 || 0x0003, block %u\n",
+ le16_to_cpu(tag_p->descVersion), block);
goto error_out;
}
@@ -248,8 +251,8 @@
return bh;
udf_debug("Crc failure block %d: crc = %d, crclen = %d\n", block,
- le16_to_cpu(tag_p->descCRC), le16_to_cpu(tag_p->descCRCLength));
-
+ le16_to_cpu(tag_p->descCRC),
+ le16_to_cpu(tag_p->descCRCLength));
error_out:
brelse(bh);
return NULL;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index f1dce84..4639e13 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -577,8 +577,7 @@
fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err);
if (!fi) {
- inode->i_nlink--;
- mark_inode_dirty(inode);
+ inode_dec_link_count(inode);
iput(inode);
return err;
}
@@ -618,8 +617,7 @@
init_special_inode(inode, mode, rdev);
fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err);
if (!fi) {
- inode->i_nlink--;
- mark_inode_dirty(inode);
+ inode_dec_link_count(inode);
iput(inode);
return err;
}
@@ -665,12 +663,11 @@
inode->i_fop = &udf_dir_operations;
fi = udf_add_entry(inode, NULL, &fibh, &cfi, &err);
if (!fi) {
- inode->i_nlink--;
- mark_inode_dirty(inode);
+ inode_dec_link_count(inode);
iput(inode);
goto out;
}
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize);
cfi.icb.extLocation = cpu_to_lelb(dinfo->i_location);
*(__le32 *)((struct allocDescImpUse *)cfi.icb.impUse)->impUse =
@@ -683,7 +680,7 @@
fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err);
if (!fi) {
- inode->i_nlink = 0;
+ clear_nlink(inode);
mark_inode_dirty(inode);
iput(inode);
goto out;
@@ -799,9 +796,8 @@
if (retval)
goto end_rmdir;
if (inode->i_nlink != 2)
- udf_warning(inode->i_sb, "udf_rmdir",
- "empty directory has nlink != 2 (%d)",
- inode->i_nlink);
+ udf_warn(inode->i_sb, "empty directory has nlink != 2 (%d)\n",
+ inode->i_nlink);
clear_nlink(inode);
inode->i_size = 0;
inode_dec_link_count(dir);
@@ -840,7 +836,7 @@
if (!inode->i_nlink) {
udf_debug("Deleting nonexistent file (%lu), %d\n",
inode->i_ino, inode->i_nlink);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
retval = udf_delete_entry(dir, fi, &fibh, &cfi);
if (retval)
diff --git a/fs/udf/partition.c b/fs/udf/partition.c
index a71090e..d6caf01 100644
--- a/fs/udf/partition.c
+++ b/fs/udf/partition.c
@@ -33,8 +33,8 @@
struct udf_sb_info *sbi = UDF_SB(sb);
struct udf_part_map *map;
if (partition >= sbi->s_partitions) {
- udf_debug("block=%d, partition=%d, offset=%d: "
- "invalid partition\n", block, partition, offset);
+ udf_debug("block=%d, partition=%d, offset=%d: invalid partition\n",
+ block, partition, offset);
return 0xFFFFFFFF;
}
map = &sbi->s_partmaps[partition];
@@ -60,8 +60,8 @@
vdata = &map->s_type_specific.s_virtual;
if (block > vdata->s_num_entries) {
- udf_debug("Trying to access block beyond end of VAT "
- "(%d max %d)\n", block, vdata->s_num_entries);
+ udf_debug("Trying to access block beyond end of VAT (%d max %d)\n",
+ block, vdata->s_num_entries);
return 0xFFFFFFFF;
}
@@ -321,9 +321,14 @@
/* We shouldn't mount such media... */
BUG_ON(!inode);
retblk = udf_try_read_meta(inode, block, partition, offset);
- if (retblk == 0xFFFFFFFF) {
- udf_warning(sb, __func__, "error reading from METADATA, "
- "trying to read from MIRROR");
+ if (retblk == 0xFFFFFFFF && mdata->s_metadata_fe) {
+ udf_warn(sb, "error reading from METADATA, trying to read from MIRROR\n");
+ if (!(mdata->s_flags & MF_MIRROR_FE_LOADED)) {
+ mdata->s_mirror_fe = udf_find_metadata_inode_efe(sb,
+ mdata->s_mirror_file_loc, map->s_partition_num);
+ mdata->s_flags |= MF_MIRROR_FE_LOADED;
+ }
+
inode = mdata->s_mirror_fe;
if (!inode)
return 0xFFFFFFFF;
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 7b27b06..e185253 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -75,8 +75,6 @@
#define UDF_DEFAULT_BLOCKSIZE 2048
-static char error_buf[1024];
-
/* These are the "meat" - everything else is stuffing */
static int udf_fill_super(struct super_block *, void *, int);
static void udf_put_super(struct super_block *);
@@ -92,8 +90,6 @@
static unsigned int udf_count_free(struct super_block *);
static int udf_statfs(struct dentry *, struct kstatfs *);
static int udf_show_options(struct seq_file *, struct vfsmount *);
-static void udf_error(struct super_block *sb, const char *function,
- const char *fmt, ...);
struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct udf_sb_info *sbi)
{
@@ -244,9 +240,8 @@
sbi->s_partmaps = kcalloc(count, sizeof(struct udf_part_map),
GFP_KERNEL);
if (!sbi->s_partmaps) {
- udf_error(sb, __func__,
- "Unable to allocate space for %d partition maps",
- count);
+ udf_err(sb, "Unable to allocate space for %d partition maps\n",
+ count);
sbi->s_partitions = 0;
return -ENOMEM;
}
@@ -550,8 +545,7 @@
uopt->dmode = option & 0777;
break;
default:
- printk(KERN_ERR "udf: bad mount option \"%s\" "
- "or missing value\n", p);
+ pr_err("bad mount option \"%s\" or missing value\n", p);
return 0;
}
}
@@ -645,20 +639,16 @@
udf_debug("ISO9660 Boot Record found\n");
break;
case 1:
- udf_debug("ISO9660 Primary Volume Descriptor "
- "found\n");
+ udf_debug("ISO9660 Primary Volume Descriptor found\n");
break;
case 2:
- udf_debug("ISO9660 Supplementary Volume "
- "Descriptor found\n");
+ udf_debug("ISO9660 Supplementary Volume Descriptor found\n");
break;
case 3:
- udf_debug("ISO9660 Volume Partition Descriptor "
- "found\n");
+ udf_debug("ISO9660 Volume Partition Descriptor found\n");
break;
case 255:
- udf_debug("ISO9660 Volume Descriptor Set "
- "Terminator found\n");
+ udf_debug("ISO9660 Volume Descriptor Set Terminator found\n");
break;
default:
udf_debug("ISO9660 VRS (%u) found\n",
@@ -809,8 +799,7 @@
pvoldesc->recordingDateAndTime)) {
#ifdef UDFFS_DEBUG
struct timestamp *ts = &pvoldesc->recordingDateAndTime;
- udf_debug("recording time %04u/%02u/%02u"
- " %02u:%02u (%x)\n",
+ udf_debug("recording time %04u/%02u/%02u %02u:%02u (%x)\n",
le16_to_cpu(ts->year), ts->month, ts->day, ts->hour,
ts->minute, le16_to_cpu(ts->typeAndTimezone));
#endif
@@ -821,7 +810,7 @@
strncpy(UDF_SB(sb)->s_volume_ident, outstr->u_name,
outstr->u_len > 31 ? 31 : outstr->u_len);
udf_debug("volIdent[] = '%s'\n",
- UDF_SB(sb)->s_volume_ident);
+ UDF_SB(sb)->s_volume_ident);
}
if (!udf_build_ustr(instr, pvoldesc->volSetIdent, 128))
@@ -837,64 +826,57 @@
return ret;
}
+struct inode *udf_find_metadata_inode_efe(struct super_block *sb,
+ u32 meta_file_loc, u32 partition_num)
+{
+ struct kernel_lb_addr addr;
+ struct inode *metadata_fe;
+
+ addr.logicalBlockNum = meta_file_loc;
+ addr.partitionReferenceNum = partition_num;
+
+ metadata_fe = udf_iget(sb, &addr);
+
+ if (metadata_fe == NULL)
+ udf_warn(sb, "metadata inode efe not found\n");
+ else if (UDF_I(metadata_fe)->i_alloc_type != ICBTAG_FLAG_AD_SHORT) {
+ udf_warn(sb, "metadata inode efe does not have short allocation descriptors!\n");
+ iput(metadata_fe);
+ metadata_fe = NULL;
+ }
+
+ return metadata_fe;
+}
+
static int udf_load_metadata_files(struct super_block *sb, int partition)
{
struct udf_sb_info *sbi = UDF_SB(sb);
struct udf_part_map *map;
struct udf_meta_data *mdata;
struct kernel_lb_addr addr;
- int fe_error = 0;
map = &sbi->s_partmaps[partition];
mdata = &map->s_type_specific.s_metadata;
/* metadata address */
- addr.logicalBlockNum = mdata->s_meta_file_loc;
- addr.partitionReferenceNum = map->s_partition_num;
-
udf_debug("Metadata file location: block = %d part = %d\n",
- addr.logicalBlockNum, addr.partitionReferenceNum);
+ mdata->s_meta_file_loc, map->s_partition_num);
- mdata->s_metadata_fe = udf_iget(sb, &addr);
+ mdata->s_metadata_fe = udf_find_metadata_inode_efe(sb,
+ mdata->s_meta_file_loc, map->s_partition_num);
if (mdata->s_metadata_fe == NULL) {
- udf_warning(sb, __func__, "metadata inode efe not found, "
- "will try mirror inode.");
- fe_error = 1;
- } else if (UDF_I(mdata->s_metadata_fe)->i_alloc_type !=
- ICBTAG_FLAG_AD_SHORT) {
- udf_warning(sb, __func__, "metadata inode efe does not have "
- "short allocation descriptors!");
- fe_error = 1;
- iput(mdata->s_metadata_fe);
- mdata->s_metadata_fe = NULL;
- }
+ /* mirror file entry */
+ udf_debug("Mirror metadata file location: block = %d part = %d\n",
+ mdata->s_mirror_file_loc, map->s_partition_num);
- /* mirror file entry */
- addr.logicalBlockNum = mdata->s_mirror_file_loc;
- addr.partitionReferenceNum = map->s_partition_num;
+ mdata->s_mirror_fe = udf_find_metadata_inode_efe(sb,
+ mdata->s_mirror_file_loc, map->s_partition_num);
- udf_debug("Mirror metadata file location: block = %d part = %d\n",
- addr.logicalBlockNum, addr.partitionReferenceNum);
-
- mdata->s_mirror_fe = udf_iget(sb, &addr);
-
- if (mdata->s_mirror_fe == NULL) {
- if (fe_error) {
- udf_error(sb, __func__, "mirror inode efe not found "
- "and metadata inode is missing too, exiting...");
+ if (mdata->s_mirror_fe == NULL) {
+ udf_err(sb, "Both metadata and mirror metadata inode efe can not found\n");
goto error_exit;
- } else
- udf_warning(sb, __func__, "mirror inode efe not found,"
- " but metadata inode is OK");
- } else if (UDF_I(mdata->s_mirror_fe)->i_alloc_type !=
- ICBTAG_FLAG_AD_SHORT) {
- udf_warning(sb, __func__, "mirror inode efe does not have "
- "short allocation descriptors!");
- iput(mdata->s_mirror_fe);
- mdata->s_mirror_fe = NULL;
- if (fe_error)
- goto error_exit;
+ }
}
/*
@@ -907,18 +889,15 @@
addr.partitionReferenceNum = map->s_partition_num;
udf_debug("Bitmap file location: block = %d part = %d\n",
- addr.logicalBlockNum, addr.partitionReferenceNum);
+ addr.logicalBlockNum, addr.partitionReferenceNum);
mdata->s_bitmap_fe = udf_iget(sb, &addr);
if (mdata->s_bitmap_fe == NULL) {
if (sb->s_flags & MS_RDONLY)
- udf_warning(sb, __func__, "bitmap inode efe "
- "not found but it's ok since the disc"
- " is mounted read-only");
+ udf_warn(sb, "bitmap inode efe not found but it's ok since the disc is mounted read-only\n");
else {
- udf_error(sb, __func__, "bitmap inode efe not "
- "found and attempted read-write mount");
+ udf_err(sb, "bitmap inode efe not found and attempted read-write mount\n");
goto error_exit;
}
}
@@ -971,9 +950,8 @@
bitmap = vzalloc(size); /* TODO: get rid of vzalloc */
if (bitmap == NULL) {
- udf_error(sb, __func__,
- "Unable to allocate space for bitmap "
- "and %d buffer_head pointers", nr_groups);
+ udf_err(sb, "Unable to allocate space for bitmap and %d buffer_head pointers\n",
+ nr_groups);
return NULL;
}
@@ -1003,10 +981,9 @@
if (p->accessType == cpu_to_le32(PD_ACCESS_TYPE_OVERWRITABLE))
map->s_partition_flags |= UDF_PART_FLAG_OVERWRITABLE;
- udf_debug("Partition (%d type %x) starts at physical %d, "
- "block length %d\n", p_index,
- map->s_partition_type, map->s_partition_root,
- map->s_partition_len);
+ udf_debug("Partition (%d type %x) starts at physical %d, block length %d\n",
+ p_index, map->s_partition_type,
+ map->s_partition_root, map->s_partition_len);
if (strcmp(p->partitionContents.ident, PD_PARTITION_CONTENTS_NSR02) &&
strcmp(p->partitionContents.ident, PD_PARTITION_CONTENTS_NSR03))
@@ -1023,12 +1000,12 @@
map->s_uspace.s_table = udf_iget(sb, &loc);
if (!map->s_uspace.s_table) {
udf_debug("cannot load unallocSpaceTable (part %d)\n",
- p_index);
+ p_index);
return 1;
}
map->s_partition_flags |= UDF_PART_FLAG_UNALLOC_TABLE;
udf_debug("unallocSpaceTable (part %d) @ %ld\n",
- p_index, map->s_uspace.s_table->i_ino);
+ p_index, map->s_uspace.s_table->i_ino);
}
if (phd->unallocSpaceBitmap.extLength) {
@@ -1041,8 +1018,8 @@
bitmap->s_extPosition = le32_to_cpu(
phd->unallocSpaceBitmap.extPosition);
map->s_partition_flags |= UDF_PART_FLAG_UNALLOC_BITMAP;
- udf_debug("unallocSpaceBitmap (part %d) @ %d\n", p_index,
- bitmap->s_extPosition);
+ udf_debug("unallocSpaceBitmap (part %d) @ %d\n",
+ p_index, bitmap->s_extPosition);
}
if (phd->partitionIntegrityTable.extLength)
@@ -1058,13 +1035,13 @@
map->s_fspace.s_table = udf_iget(sb, &loc);
if (!map->s_fspace.s_table) {
udf_debug("cannot load freedSpaceTable (part %d)\n",
- p_index);
+ p_index);
return 1;
}
map->s_partition_flags |= UDF_PART_FLAG_FREED_TABLE;
udf_debug("freedSpaceTable (part %d) @ %ld\n",
- p_index, map->s_fspace.s_table->i_ino);
+ p_index, map->s_fspace.s_table->i_ino);
}
if (phd->freedSpaceBitmap.extLength) {
@@ -1077,8 +1054,8 @@
bitmap->s_extPosition = le32_to_cpu(
phd->freedSpaceBitmap.extPosition);
map->s_partition_flags |= UDF_PART_FLAG_FREED_BITMAP;
- udf_debug("freedSpaceBitmap (part %d) @ %d\n", p_index,
- bitmap->s_extPosition);
+ udf_debug("freedSpaceBitmap (part %d) @ %d\n",
+ p_index, bitmap->s_extPosition);
}
return 0;
}
@@ -1118,11 +1095,9 @@
udf_find_vat_block(sb, p_index, type1_index, sbi->s_last_block);
if (!sbi->s_vat_inode &&
sbi->s_last_block != blocks - 1) {
- printk(KERN_NOTICE "UDF-fs: Failed to read VAT inode from the"
- " last recorded block (%lu), retrying with the last "
- "block of the device (%lu).\n",
- (unsigned long)sbi->s_last_block,
- (unsigned long)blocks - 1);
+ pr_notice("Failed to read VAT inode from the last recorded block (%lu), retrying with the last block of the device (%lu).\n",
+ (unsigned long)sbi->s_last_block,
+ (unsigned long)blocks - 1);
udf_find_vat_block(sb, p_index, type1_index, blocks - 1);
}
if (!sbi->s_vat_inode)
@@ -1220,8 +1195,8 @@
if (map->s_partition_type == UDF_METADATA_MAP25) {
ret = udf_load_metadata_files(sb, i);
if (ret) {
- printk(KERN_ERR "UDF-fs: error loading MetaData "
- "partition map %d\n", i);
+ udf_err(sb, "error loading MetaData partition map %d\n",
+ i);
goto out_bh;
}
} else {
@@ -1234,9 +1209,7 @@
* overwrite blocks instead of relocating them).
*/
sb->s_flags |= MS_RDONLY;
- printk(KERN_NOTICE "UDF-fs: Filesystem marked read-only "
- "because writing to pseudooverwrite partition is "
- "not implemented.\n");
+ pr_notice("Filesystem marked read-only because writing to pseudooverwrite partition is not implemented\n");
}
out_bh:
/* In case loading failed, we handle cleanup in udf_fill_super */
@@ -1344,9 +1317,8 @@
struct metadataPartitionMap *mdm =
(struct metadataPartitionMap *)
&(lvd->partitionMaps[offset]);
- udf_debug("Parsing Logical vol part %d "
- "type %d id=%s\n", i, type,
- UDF_ID_METADATA);
+ udf_debug("Parsing Logical vol part %d type %d id=%s\n",
+ i, type, UDF_ID_METADATA);
map->s_partition_type = UDF_METADATA_MAP25;
map->s_partition_func = udf_get_pblock_meta25;
@@ -1361,25 +1333,24 @@
le32_to_cpu(mdm->allocUnitSize);
mdata->s_align_unit_size =
le16_to_cpu(mdm->alignUnitSize);
- mdata->s_dup_md_flag =
- mdm->flags & 0x01;
+ if (mdm->flags & 0x01)
+ mdata->s_flags |= MF_DUPLICATE_MD;
udf_debug("Metadata Ident suffix=0x%x\n",
- (le16_to_cpu(
- ((__le16 *)
- mdm->partIdent.identSuffix)[0])));
+ le16_to_cpu(*(__le16 *)
+ mdm->partIdent.identSuffix));
udf_debug("Metadata part num=%d\n",
- le16_to_cpu(mdm->partitionNum));
+ le16_to_cpu(mdm->partitionNum));
udf_debug("Metadata part alloc unit size=%d\n",
- le32_to_cpu(mdm->allocUnitSize));
+ le32_to_cpu(mdm->allocUnitSize));
udf_debug("Metadata file loc=%d\n",
- le32_to_cpu(mdm->metadataFileLoc));
+ le32_to_cpu(mdm->metadataFileLoc));
udf_debug("Mirror file loc=%d\n",
- le32_to_cpu(mdm->metadataMirrorFileLoc));
+ le32_to_cpu(mdm->metadataMirrorFileLoc));
udf_debug("Bitmap file loc=%d\n",
- le32_to_cpu(mdm->metadataBitmapFileLoc));
- udf_debug("Duplicate Flag: %d %d\n",
- mdata->s_dup_md_flag, mdm->flags);
+ le32_to_cpu(mdm->metadataBitmapFileLoc));
+ udf_debug("Flags: %d %d\n",
+ mdata->s_flags, mdm->flags);
} else {
udf_debug("Unknown ident: %s\n",
upm2->partIdent.ident);
@@ -1389,16 +1360,15 @@
map->s_partition_num = le16_to_cpu(upm2->partitionNum);
}
udf_debug("Partition (%d:%d) type %d on volume %d\n",
- i, map->s_partition_num, type,
- map->s_volumeseqnum);
+ i, map->s_partition_num, type, map->s_volumeseqnum);
}
if (fileset) {
struct long_ad *la = (struct long_ad *)&(lvd->logicalVolContentsUse[0]);
*fileset = lelb_to_cpu(la->extLocation);
- udf_debug("FileSet found in LogicalVolDesc at block=%d, "
- "partition=%d\n", fileset->logicalBlockNum,
+ udf_debug("FileSet found in LogicalVolDesc at block=%d, partition=%d\n",
+ fileset->logicalBlockNum,
fileset->partitionReferenceNum);
}
if (lvd->integritySeqExt.extLength)
@@ -1478,9 +1448,9 @@
bh = udf_read_tagged(sb, block, block, &ident);
if (!bh) {
- printk(KERN_ERR "udf: Block %Lu of volume descriptor "
- "sequence is corrupted or we could not read "
- "it.\n", (unsigned long long)block);
+ udf_err(sb,
+ "Block %llu of volume descriptor sequence is corrupted or we could not read it\n",
+ (unsigned long long)block);
return 1;
}
@@ -1553,7 +1523,7 @@
* in a suitable order
*/
if (!vds[VDS_POS_PRIMARY_VOL_DESC].block) {
- printk(KERN_ERR "udf: Primary Volume Descriptor not found!\n");
+ udf_err(sb, "Primary Volume Descriptor not found!\n");
return 1;
}
if (udf_load_pvoldesc(sb, vds[VDS_POS_PRIMARY_VOL_DESC].block))
@@ -1740,7 +1710,7 @@
if (!sb_set_blocksize(sb, uopt->blocksize)) {
if (!silent)
- printk(KERN_WARNING "UDF-fs: Bad block size\n");
+ udf_warn(sb, "Bad block size\n");
return 0;
}
sbi->s_last_block = uopt->lastblock;
@@ -1749,12 +1719,11 @@
nsr_off = udf_check_vsd(sb);
if (!nsr_off) {
if (!silent)
- printk(KERN_WARNING "UDF-fs: No VRS found\n");
+ udf_warn(sb, "No VRS found\n");
return 0;
}
if (nsr_off == -1)
- udf_debug("Failed to read byte 32768. Assuming open "
- "disc. Skipping validity check\n");
+ udf_debug("Failed to read byte 32768. Assuming open disc. Skipping validity check\n");
if (!sbi->s_last_block)
sbi->s_last_block = udf_get_last_block(sb);
} else {
@@ -1765,7 +1734,7 @@
sbi->s_anchor = uopt->anchor;
if (!udf_find_anchor(sb, fileset)) {
if (!silent)
- printk(KERN_WARNING "UDF-fs: No anchor found\n");
+ udf_warn(sb, "No anchor found\n");
return 0;
}
return 1;
@@ -1937,8 +1906,7 @@
if (uopt.flags & (1 << UDF_FLAG_UTF8) &&
uopt.flags & (1 << UDF_FLAG_NLS_MAP)) {
- udf_error(sb, "udf_read_super",
- "utf8 cannot be combined with iocharset\n");
+ udf_err(sb, "utf8 cannot be combined with iocharset\n");
goto error_out;
}
#ifdef CONFIG_UDF_NLS
@@ -1987,15 +1955,14 @@
ret = udf_load_vrs(sb, &uopt, silent, &fileset);
if (!ret && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
if (!silent)
- printk(KERN_NOTICE
- "UDF-fs: Rescanning with blocksize "
- "%d\n", UDF_DEFAULT_BLOCKSIZE);
+ pr_notice("Rescanning with blocksize %d\n",
+ UDF_DEFAULT_BLOCKSIZE);
uopt.blocksize = UDF_DEFAULT_BLOCKSIZE;
ret = udf_load_vrs(sb, &uopt, silent, &fileset);
}
}
if (!ret) {
- printk(KERN_WARNING "UDF-fs: No partition found (1)\n");
+ udf_warn(sb, "No partition found (1)\n");
goto error_out;
}
@@ -2010,10 +1977,9 @@
le16_to_cpu(lvidiu->maxUDFWriteRev); */
if (minUDFReadRev > UDF_MAX_READ_VERSION) {
- printk(KERN_ERR "UDF-fs: minUDFReadRev=%x "
- "(max is %x)\n",
- le16_to_cpu(lvidiu->minUDFReadRev),
- UDF_MAX_READ_VERSION);
+ udf_err(sb, "minUDFReadRev=%x (max is %x)\n",
+ le16_to_cpu(lvidiu->minUDFReadRev),
+ UDF_MAX_READ_VERSION);
goto error_out;
} else if (minUDFWriteRev > UDF_MAX_WRITE_VERSION)
sb->s_flags |= MS_RDONLY;
@@ -2027,28 +1993,27 @@
}
if (!sbi->s_partitions) {
- printk(KERN_WARNING "UDF-fs: No partition found (2)\n");
+ udf_warn(sb, "No partition found (2)\n");
goto error_out;
}
if (sbi->s_partmaps[sbi->s_partition].s_partition_flags &
UDF_PART_FLAG_READ_ONLY) {
- printk(KERN_NOTICE "UDF-fs: Partition marked readonly; "
- "forcing readonly mount\n");
+ pr_notice("Partition marked readonly; forcing readonly mount\n");
sb->s_flags |= MS_RDONLY;
}
if (udf_find_fileset(sb, &fileset, &rootdir)) {
- printk(KERN_WARNING "UDF-fs: No fileset found\n");
+ udf_warn(sb, "No fileset found\n");
goto error_out;
}
if (!silent) {
struct timestamp ts;
udf_time_to_disk_stamp(&ts, sbi->s_record_time);
- udf_info("UDF: Mounting volume '%s', "
- "timestamp %04u/%02u/%02u %02u:%02u (%x)\n",
- sbi->s_volume_ident, le16_to_cpu(ts.year), ts.month, ts.day,
+ udf_info("Mounting volume '%s', timestamp %04u/%02u/%02u %02u:%02u (%x)\n",
+ sbi->s_volume_ident,
+ le16_to_cpu(ts.year), ts.month, ts.day,
ts.hour, ts.minute, le16_to_cpu(ts.typeAndTimezone));
}
if (!(sb->s_flags & MS_RDONLY))
@@ -2059,8 +2024,7 @@
/* perhaps it's not extensible enough, but for now ... */
inode = udf_iget(sb, &rootdir);
if (!inode) {
- printk(KERN_ERR "UDF-fs: Error in udf_iget, block=%d, "
- "partition=%d\n",
+ udf_err(sb, "Error in udf_iget, block=%d, partition=%d\n",
rootdir.logicalBlockNum, rootdir.partitionReferenceNum);
goto error_out;
}
@@ -2068,7 +2032,7 @@
/* Allocate a dentry for the root inode */
sb->s_root = d_alloc_root(inode);
if (!sb->s_root) {
- printk(KERN_ERR "UDF-fs: Couldn't allocate root dentry\n");
+ udf_err(sb, "Couldn't allocate root dentry\n");
iput(inode);
goto error_out;
}
@@ -2096,32 +2060,40 @@
return -EINVAL;
}
-static void udf_error(struct super_block *sb, const char *function,
- const char *fmt, ...)
+void _udf_err(struct super_block *sb, const char *function,
+ const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
- if (!(sb->s_flags & MS_RDONLY)) {
- /* mark sb error */
+ /* mark sb error */
+ if (!(sb->s_flags & MS_RDONLY))
sb->s_dirt = 1;
- }
+
va_start(args, fmt);
- vsnprintf(error_buf, sizeof(error_buf), fmt, args);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
+
+ pr_err("error (device %s): %s: %pV", sb->s_id, function, &vaf);
+
va_end(args);
- printk(KERN_CRIT "UDF-fs error (device %s): %s: %s\n",
- sb->s_id, function, error_buf);
}
-void udf_warning(struct super_block *sb, const char *function,
- const char *fmt, ...)
+void _udf_warn(struct super_block *sb, const char *function,
+ const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
va_start(args, fmt);
- vsnprintf(error_buf, sizeof(error_buf), fmt, args);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
+
+ pr_warn("warning (device %s): %s: %pV", sb->s_id, function, &vaf);
+
va_end(args);
- printk(KERN_WARNING "UDF-fs warning (device %s): %s: %s\n",
- sb->s_id, function, error_buf);
}
static void udf_put_super(struct super_block *sb)
@@ -2213,11 +2185,11 @@
bh = udf_read_ptagged(sb, &loc, 0, &ident);
if (!bh) {
- printk(KERN_ERR "udf: udf_count_free failed\n");
+ udf_err(sb, "udf_count_free failed\n");
goto out;
} else if (ident != TAG_IDENT_SBD) {
brelse(bh);
- printk(KERN_ERR "udf: udf_count_free failed\n");
+ udf_err(sb, "udf_count_free failed\n");
goto out;
}
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index 8424308..4b98fee 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -95,23 +95,21 @@
lbcount += elen;
if (lbcount > inode->i_size) {
if (lbcount - inode->i_size >= inode->i_sb->s_blocksize)
- printk(KERN_WARNING
- "udf_truncate_tail_extent(): Too long "
- "extent after EOF in inode %u: i_size: "
- "%Ld lbcount: %Ld extent %u+%u\n",
- (unsigned)inode->i_ino,
- (long long)inode->i_size,
- (long long)lbcount,
- (unsigned)eloc.logicalBlockNum,
- (unsigned)elen);
+ udf_warn(inode->i_sb,
+ "Too long extent after EOF in inode %u: i_size: %lld lbcount: %lld extent %u+%u\n",
+ (unsigned)inode->i_ino,
+ (long long)inode->i_size,
+ (long long)lbcount,
+ (unsigned)eloc.logicalBlockNum,
+ (unsigned)elen);
nelen = elen - (lbcount - inode->i_size);
epos.offset -= adsize;
extent_trunc(inode, &epos, &eloc, etype, elen, nelen);
epos.offset += adsize;
if (udf_next_aext(inode, &epos, &eloc, &elen, 1) != -1)
- printk(KERN_ERR "udf_truncate_tail_extent(): "
- "Extent after EOF in inode %u.\n",
- (unsigned)inode->i_ino);
+ udf_err(inode->i_sb,
+ "Extent after EOF in inode %u\n",
+ (unsigned)inode->i_ino);
break;
}
}
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 4858c19..5142a82 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -54,13 +54,16 @@
#pragma pack(1) /* XXX(hch): Why? This file just defines in-core structures */
+#define MF_DUPLICATE_MD 0x01
+#define MF_MIRROR_FE_LOADED 0x02
+
struct udf_meta_data {
__u32 s_meta_file_loc;
__u32 s_mirror_file_loc;
__u32 s_bitmap_file_loc;
__u32 s_alloc_unit_size;
__u16 s_align_unit_size;
- __u8 s_dup_md_flag;
+ int s_flags;
struct inode *s_metadata_fe;
struct inode *s_mirror_fe;
struct inode *s_bitmap_fe;
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index dc8a8dc..f34e6fc 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -1,6 +1,8 @@
#ifndef __UDF_DECL_H
#define __UDF_DECL_H
+#define pr_fmt(fmt) "UDF-fs: " fmt
+
#include "ecma_167.h"
#include "osta_udf.h"
@@ -16,23 +18,30 @@
#define UDF_PREALLOCATE
#define UDF_DEFAULT_PREALLOC_BLOCKS 8
+extern __printf(3, 4) void _udf_err(struct super_block *sb,
+ const char *function, const char *fmt, ...);
+#define udf_err(sb, fmt, ...) \
+ _udf_err(sb, __func__, fmt, ##__VA_ARGS__)
+
+extern __printf(3, 4) void _udf_warn(struct super_block *sb,
+ const char *function, const char *fmt, ...);
+#define udf_warn(sb, fmt, ...) \
+ _udf_warn(sb, __func__, fmt, ##__VA_ARGS__)
+
+#define udf_info(fmt, ...) \
+ pr_info("INFO " fmt, ##__VA_ARGS__)
+
#undef UDFFS_DEBUG
#ifdef UDFFS_DEBUG
-#define udf_debug(f, a...) \
-do { \
- printk(KERN_DEBUG "UDF-fs DEBUG %s:%d:%s: ", \
- __FILE__, __LINE__, __func__); \
- printk(f, ##a); \
-} while (0)
+#define udf_debug(fmt, ...) \
+ printk(KERN_DEBUG pr_fmt("%s:%d:%s: " fmt), \
+ __FILE__, __LINE__, __func__, ##__VA_ARGS__)
#else
-#define udf_debug(f, a...) /**/
+#define udf_debug(fmt, ...) \
+ no_printk(fmt, ##__VA_ARGS__)
#endif
-#define udf_info(f, a...) \
- printk(KERN_INFO "UDF-fs INFO " f, ##a);
-
-
#define udf_fixed_to_variable(x) ( ( ( (x) >> 5 ) * 39 ) + ( (x) & 0x0000001F ) )
#define udf_variable_to_fixed(x) ( ( ( (x) / 39 ) << 5 ) + ( (x) % 39 ) )
@@ -112,8 +121,6 @@
/* super.c */
-extern __printf(3, 4) void udf_warning(struct super_block *, const char *,
- const char *, ...);
static inline void udf_updated_lvid(struct super_block *sb)
{
struct buffer_head *bh = UDF_SB(sb)->s_lvid_bh;
@@ -126,6 +133,8 @@
UDF_SB(sb)->s_lvid_dirty = 1;
}
extern u64 lvid_get_unique_id(struct super_block *sb);
+struct inode *udf_find_metadata_inode_efe(struct super_block *sb,
+ u32 meta_file_loc, u32 partition_num);
/* namei.c */
extern int udf_write_fi(struct inode *inode, struct fileIdentDesc *,
diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c
index b8c828c..1f11483 100644
--- a/fs/udf/udftime.c
+++ b/fs/udf/udftime.c
@@ -34,9 +34,10 @@
* http://www.boulder.nist.gov/timefreq/pubs/bulletin/leapsecond.htm
*/
+#include "udfdecl.h"
+
#include <linux/types.h>
#include <linux/kernel.h>
-#include "udfdecl.h"
#define EPOCH_YEAR 1970
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index d03a90b..44b815e 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -114,7 +114,7 @@
cmp_id = ocu_i->u_cmpID;
if (cmp_id != 8 && cmp_id != 16) {
memset(utf_o, 0, sizeof(struct ustr));
- printk(KERN_ERR "udf: unknown compression code (%d) stri=%s\n",
+ pr_err("unknown compression code (%d) stri=%s\n",
cmp_id, ocu_i->u_name);
return 0;
}
@@ -242,7 +242,7 @@
if (utf_cnt) {
error_out:
ocu[++u_len] = '?';
- printk(KERN_DEBUG "udf: bad UTF-8 character\n");
+ printk(KERN_DEBUG pr_fmt("bad UTF-8 character\n"));
}
ocu[length - 1] = (uint8_t)u_len + 1;
@@ -267,7 +267,7 @@
cmp_id = ocu_i->u_cmpID;
if (cmp_id != 8 && cmp_id != 16) {
memset(utf_o, 0, sizeof(struct ustr));
- printk(KERN_ERR "udf: unknown compression code (%d) stri=%s\n",
+ pr_err("unknown compression code (%d) stri=%s\n",
cmp_id, ocu_i->u_name);
return 0;
}
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index 2eabf04..78a4c70 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -341,7 +341,7 @@
fail_remove_inode:
unlock_super(sb);
- inode->i_nlink = 0;
+ clear_nlink(inode);
iput(inode);
UFSD("EXIT (FAILED): err %d\n", err);
return ERR_PTR(err);
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index b4d791a..879b134 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -589,7 +589,7 @@
* Copy data to the in-core inode.
*/
inode->i_mode = mode = fs16_to_cpu(sb, ufs_inode->ui_mode);
- inode->i_nlink = fs16_to_cpu(sb, ufs_inode->ui_nlink);
+ set_nlink(inode, fs16_to_cpu(sb, ufs_inode->ui_nlink));
if (inode->i_nlink == 0) {
ufs_error (sb, "ufs_read_inode", "inode %lu has zero nlink\n", inode->i_ino);
return -1;
@@ -637,7 +637,7 @@
* Copy data to the in-core inode.
*/
inode->i_mode = mode = fs16_to_cpu(sb, ufs2_inode->ui_mode);
- inode->i_nlink = fs16_to_cpu(sb, ufs2_inode->ui_nlink);
+ set_nlink(inode, fs16_to_cpu(sb, ufs2_inode->ui_nlink));
if (inode->i_nlink == 0) {
ufs_error (sb, "ufs_read_inode", "inode %lu has zero nlink\n", inode->i_ino);
return -1;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 9ba2a07..23ce927 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1153,7 +1153,7 @@
hlist_add_fake(&inode->i_hash);
inode->i_mode = ip->i_d.di_mode;
- inode->i_nlink = ip->i_d.di_nlink;
+ set_nlink(inode, ip->i_d.di_nlink);
inode->i_uid = ip->i_d.di_uid;
inode->i_gid = ip->i_d.di_gid;
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 2dcb72b..2314ad8 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -117,6 +117,7 @@
struct list_head ki_list; /* the aio core uses this
* for cancellation */
+ struct list_head ki_batch; /* batch allocation */
/*
* If the aio_resfd field of the userspace iocb is not zero,
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index da7e4bc..1b7f9d5 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -516,7 +516,7 @@
struct list_head sibling;
/* used when use_id == true */
struct idr idr;
- spinlock_t id_lock;
+ rwlock_t id_lock;
/* should be defined only by modular subsystems */
struct module *module;
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 62157c0..4df9261 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -165,6 +165,7 @@
unsigned int, const char *, const struct qstr *);
int (*d_delete)(const struct dentry *);
void (*d_release)(struct dentry *);
+ void (*d_prune)(struct dentry *);
void (*d_iput)(struct dentry *, struct inode *);
char *(*d_dname)(struct dentry *, char *, int);
struct vfsmount *(*d_automount)(struct path *);
@@ -184,8 +185,9 @@
#define DCACHE_OP_COMPARE 0x0002
#define DCACHE_OP_REVALIDATE 0x0004
#define DCACHE_OP_DELETE 0x0008
+#define DCACHE_OP_PRUNE 0x0010
-#define DCACHE_DISCONNECTED 0x0010
+#define DCACHE_DISCONNECTED 0x0020
/* This dentry is possibly not currently connected to the dcache tree, in
* which case its parent will either be itself, or will have this flag as
* well. nfsd will not use a dentry with this bit set, but will first
@@ -196,8 +198,8 @@
* dentry into place and return that dentry rather than the passed one,
* typically using d_splice_alias. */
-#define DCACHE_REFERENCED 0x0020 /* Recently used, don't discard. */
-#define DCACHE_RCUACCESS 0x0040 /* Entry has ever been RCU-visible */
+#define DCACHE_REFERENCED 0x0040 /* Recently used, don't discard. */
+#define DCACHE_RCUACCESS 0x0080 /* Entry has ever been RCU-visible */
#define DCACHE_CANT_MOUNT 0x0100
#define DCACHE_GENOCIDE 0x0200
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 99e3e50..98f34b8 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -10,6 +10,7 @@
#include <linux/bio.h>
#include <linux/blkdev.h>
+#include <linux/ratelimit.h>
struct dm_dev;
struct dm_target;
@@ -127,10 +128,6 @@
* Information about a target type
*/
-/*
- * Target features
- */
-
struct target_type {
uint64_t features;
const char *name;
@@ -159,6 +156,30 @@
struct list_head list;
};
+/*
+ * Target features
+ */
+
+/*
+ * Any table that contains an instance of this target must have only one.
+ */
+#define DM_TARGET_SINGLETON 0x00000001
+#define dm_target_needs_singleton(type) ((type)->features & DM_TARGET_SINGLETON)
+
+/*
+ * Indicates that a target does not support read-only devices.
+ */
+#define DM_TARGET_ALWAYS_WRITEABLE 0x00000002
+#define dm_target_always_writeable(type) \
+ ((type)->features & DM_TARGET_ALWAYS_WRITEABLE)
+
+/*
+ * Any device that contains a table with an instance of this target may never
+ * have tables containing any different target type.
+ */
+#define DM_TARGET_IMMUTABLE 0x00000004
+#define dm_target_is_immutable(type) ((type)->features & DM_TARGET_IMMUTABLE)
+
struct dm_target {
struct dm_table *table;
struct target_type *type;
@@ -375,6 +396,14 @@
*---------------------------------------------------------------*/
#define DM_NAME "device-mapper"
+#ifdef CONFIG_PRINTK
+extern struct ratelimit_state dm_ratelimit_state;
+
+#define dm_ratelimit() __ratelimit(&dm_ratelimit_state)
+#else
+#define dm_ratelimit() 0
+#endif
+
#define DMCRIT(f, arg...) \
printk(KERN_CRIT DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
@@ -382,7 +411,7 @@
printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
#define DMERR_LIMIT(f, arg...) \
do { \
- if (printk_ratelimit()) \
+ if (dm_ratelimit()) \
printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " \
f "\n", ## arg); \
} while (0)
@@ -391,7 +420,7 @@
printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
#define DMWARN_LIMIT(f, arg...) \
do { \
- if (printk_ratelimit()) \
+ if (dm_ratelimit()) \
printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " \
f "\n", ## arg); \
} while (0)
@@ -400,7 +429,7 @@
printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
#define DMINFO_LIMIT(f, arg...) \
do { \
- if (printk_ratelimit()) \
+ if (dm_ratelimit()) \
printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f \
"\n", ## arg); \
} while (0)
@@ -410,7 +439,7 @@
printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX " DEBUG: " f "\n", ## arg)
# define DMDEBUG_LIMIT(f, arg...) \
do { \
- if (printk_ratelimit()) \
+ if (dm_ratelimit()) \
printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX ": " f \
"\n", ## arg); \
} while (0)
diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h
index 0cb8eff..75fd557 100644
--- a/include/linux/dm-ioctl.h
+++ b/include/linux/dm-ioctl.h
@@ -267,9 +267,9 @@
#define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
#define DM_VERSION_MAJOR 4
-#define DM_VERSION_MINOR 21
+#define DM_VERSION_MINOR 22
#define DM_VERSION_PATCHLEVEL 0
-#define DM_VERSION_EXTRA "-ioctl (2011-07-06)"
+#define DM_VERSION_EXTRA "-ioctl (2011-10-19)"
/* Status bits */
#define DM_READONLY_FLAG (1 << 0) /* In/Out */
diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h
index 5e54458..47d9d37 100644
--- a/include/linux/dm-kcopyd.h
+++ b/include/linux/dm-kcopyd.h
@@ -57,5 +57,9 @@
dm_kcopyd_notify_fn fn, void *context);
void dm_kcopyd_do_callback(void *job, int read_err, unsigned long write_err);
+int dm_kcopyd_zero(struct dm_kcopyd_client *kc,
+ unsigned num_dests, struct dm_io_region *dests,
+ unsigned flags, dm_kcopyd_notify_fn fn, void *context);
+
#endif /* __KERNEL__ */
#endif /* _LINUX_DM_KCOPYD_H */
diff --git a/include/linux/dm-log-userspace.h b/include/linux/dm-log-userspace.h
index eeace7d..0678c2a 100644
--- a/include/linux/dm-log-userspace.h
+++ b/include/linux/dm-log-userspace.h
@@ -52,15 +52,20 @@
* Payload-to-userspace:
* A single string containing all the argv arguments separated by ' 's
* Payload-to-kernel:
- * None. ('data_size' in the dm_ulog_request struct should be 0.)
+ * A NUL-terminated string that is the name of the device that is used
+ * as the backing store for the log data. 'dm_get_device' will be called
+ * on this device. ('dm_put_device' will be called on this device
+ * automatically after calling DM_ULOG_DTR.) If there is no device needed
+ * for log data, 'data_size' in the dm_ulog_request struct should be 0.
*
* The UUID contained in the dm_ulog_request structure is the reference that
* will be used by all request types to a specific log. The constructor must
- * record this assotiation with instance created.
+ * record this association with the instance created.
*
* When the request has been processed, user-space must return the
- * dm_ulog_request to the kernel - setting the 'error' field and
- * 'data_size' appropriately.
+ * dm_ulog_request to the kernel - setting the 'error' field, filling the
+ * data field with the log device if necessary, and setting 'data_size'
+ * appropriately.
*/
#define DM_ULOG_CTR 1
@@ -377,8 +382,11 @@
* dm_ulog_request or a change in the way requests are
* issued/handled. Changes are outlined here:
* version 1: Initial implementation
+ * version 2: DM_ULOG_CTR allowed to return a string containing a
+ * device name that is to be registered with DM via
+ * 'dm_get_device'.
*/
-#define DM_ULOG_REQUEST_VERSION 1
+#define DM_ULOG_REQUEST_VERSION 2
struct dm_ulog_request {
/*
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 347fdc3..be86ae1 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -1,6 +1,7 @@
#ifndef _LINUX_DMA_MAPPING_H
#define _LINUX_DMA_MAPPING_H
+#include <linux/string.h>
#include <linux/device.h>
#include <linux/err.h>
#include <linux/dma-attrs.h>
@@ -117,6 +118,15 @@
return -EIO;
}
+static inline void *dma_zalloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag)
+{
+ void *ret = dma_alloc_coherent(dev, size, dma_handle, flag);
+ if (ret)
+ memset(ret, 0, size);
+ return ret;
+}
+
#ifdef CONFIG_HAS_DMA
static inline int dma_get_cache_alignment(void)
{
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 4a73257..055b248 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -42,4 +42,354 @@
return;
}
+#define EDAC_MC_LABEL_LEN 31
+#define MC_PROC_NAME_MAX_LEN 7
+
+/* memory devices */
+enum dev_type {
+ DEV_UNKNOWN = 0,
+ DEV_X1,
+ DEV_X2,
+ DEV_X4,
+ DEV_X8,
+ DEV_X16,
+ DEV_X32, /* Do these parts exist? */
+ DEV_X64 /* Do these parts exist? */
+};
+
+#define DEV_FLAG_UNKNOWN BIT(DEV_UNKNOWN)
+#define DEV_FLAG_X1 BIT(DEV_X1)
+#define DEV_FLAG_X2 BIT(DEV_X2)
+#define DEV_FLAG_X4 BIT(DEV_X4)
+#define DEV_FLAG_X8 BIT(DEV_X8)
+#define DEV_FLAG_X16 BIT(DEV_X16)
+#define DEV_FLAG_X32 BIT(DEV_X32)
+#define DEV_FLAG_X64 BIT(DEV_X64)
+
+/* memory types */
+enum mem_type {
+ MEM_EMPTY = 0, /* Empty csrow */
+ MEM_RESERVED, /* Reserved csrow type */
+ MEM_UNKNOWN, /* Unknown csrow type */
+ MEM_FPM, /* Fast page mode */
+ MEM_EDO, /* Extended data out */
+ MEM_BEDO, /* Burst Extended data out */
+ MEM_SDR, /* Single data rate SDRAM */
+ MEM_RDR, /* Registered single data rate SDRAM */
+ MEM_DDR, /* Double data rate SDRAM */
+ MEM_RDDR, /* Registered Double data rate SDRAM */
+ MEM_RMBS, /* Rambus DRAM */
+ MEM_DDR2, /* DDR2 RAM */
+ MEM_FB_DDR2, /* fully buffered DDR2 */
+ MEM_RDDR2, /* Registered DDR2 RAM */
+ MEM_XDR, /* Rambus XDR */
+ MEM_DDR3, /* DDR3 RAM */
+ MEM_RDDR3, /* Registered DDR3 RAM */
+};
+
+#define MEM_FLAG_EMPTY BIT(MEM_EMPTY)
+#define MEM_FLAG_RESERVED BIT(MEM_RESERVED)
+#define MEM_FLAG_UNKNOWN BIT(MEM_UNKNOWN)
+#define MEM_FLAG_FPM BIT(MEM_FPM)
+#define MEM_FLAG_EDO BIT(MEM_EDO)
+#define MEM_FLAG_BEDO BIT(MEM_BEDO)
+#define MEM_FLAG_SDR BIT(MEM_SDR)
+#define MEM_FLAG_RDR BIT(MEM_RDR)
+#define MEM_FLAG_DDR BIT(MEM_DDR)
+#define MEM_FLAG_RDDR BIT(MEM_RDDR)
+#define MEM_FLAG_RMBS BIT(MEM_RMBS)
+#define MEM_FLAG_DDR2 BIT(MEM_DDR2)
+#define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2)
+#define MEM_FLAG_RDDR2 BIT(MEM_RDDR2)
+#define MEM_FLAG_XDR BIT(MEM_XDR)
+#define MEM_FLAG_DDR3 BIT(MEM_DDR3)
+#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3)
+
+/* chipset Error Detection and Correction capabilities and mode */
+enum edac_type {
+ EDAC_UNKNOWN = 0, /* Unknown if ECC is available */
+ EDAC_NONE, /* Doesn't support ECC */
+ EDAC_RESERVED, /* Reserved ECC type */
+ EDAC_PARITY, /* Detects parity errors */
+ EDAC_EC, /* Error Checking - no correction */
+ EDAC_SECDED, /* Single bit error correction, Double detection */
+ EDAC_S2ECD2ED, /* Chipkill x2 devices - do these exist? */
+ EDAC_S4ECD4ED, /* Chipkill x4 devices */
+ EDAC_S8ECD8ED, /* Chipkill x8 devices */
+ EDAC_S16ECD16ED, /* Chipkill x16 devices */
+};
+
+#define EDAC_FLAG_UNKNOWN BIT(EDAC_UNKNOWN)
+#define EDAC_FLAG_NONE BIT(EDAC_NONE)
+#define EDAC_FLAG_PARITY BIT(EDAC_PARITY)
+#define EDAC_FLAG_EC BIT(EDAC_EC)
+#define EDAC_FLAG_SECDED BIT(EDAC_SECDED)
+#define EDAC_FLAG_S2ECD2ED BIT(EDAC_S2ECD2ED)
+#define EDAC_FLAG_S4ECD4ED BIT(EDAC_S4ECD4ED)
+#define EDAC_FLAG_S8ECD8ED BIT(EDAC_S8ECD8ED)
+#define EDAC_FLAG_S16ECD16ED BIT(EDAC_S16ECD16ED)
+
+/* scrubbing capabilities */
+enum scrub_type {
+ SCRUB_UNKNOWN = 0, /* Unknown if scrubber is available */
+ SCRUB_NONE, /* No scrubber */
+ SCRUB_SW_PROG, /* SW progressive (sequential) scrubbing */
+ SCRUB_SW_SRC, /* Software scrub only errors */
+ SCRUB_SW_PROG_SRC, /* Progressive software scrub from an error */
+ SCRUB_SW_TUNABLE, /* Software scrub frequency is tunable */
+ SCRUB_HW_PROG, /* HW progressive (sequential) scrubbing */
+ SCRUB_HW_SRC, /* Hardware scrub only errors */
+ SCRUB_HW_PROG_SRC, /* Progressive hardware scrub from an error */
+ SCRUB_HW_TUNABLE /* Hardware scrub frequency is tunable */
+};
+
+#define SCRUB_FLAG_SW_PROG BIT(SCRUB_SW_PROG)
+#define SCRUB_FLAG_SW_SRC BIT(SCRUB_SW_SRC)
+#define SCRUB_FLAG_SW_PROG_SRC BIT(SCRUB_SW_PROG_SRC)
+#define SCRUB_FLAG_SW_TUN BIT(SCRUB_SW_SCRUB_TUNABLE)
+#define SCRUB_FLAG_HW_PROG BIT(SCRUB_HW_PROG)
+#define SCRUB_FLAG_HW_SRC BIT(SCRUB_HW_SRC)
+#define SCRUB_FLAG_HW_PROG_SRC BIT(SCRUB_HW_PROG_SRC)
+#define SCRUB_FLAG_HW_TUN BIT(SCRUB_HW_TUNABLE)
+
+/* FIXME - should have notify capabilities: NMI, LOG, PROC, etc */
+
+/* EDAC internal operation states */
+#define OP_ALLOC 0x100
+#define OP_RUNNING_POLL 0x201
+#define OP_RUNNING_INTERRUPT 0x202
+#define OP_RUNNING_POLL_INTR 0x203
+#define OP_OFFLINE 0x300
+
+/*
+ * There are several things to be aware of that aren't at all obvious:
+ *
+ *
+ * SOCKETS, SOCKET SETS, BANKS, ROWS, CHIP-SELECT ROWS, CHANNELS, etc..
+ *
+ * These are some of the many terms that are thrown about that don't always
+ * mean what people think they mean (Inconceivable!). In the interest of
+ * creating a common ground for discussion, terms and their definitions
+ * will be established.
+ *
+ * Memory devices: The individual chip on a memory stick. These devices
+ * commonly output 4 and 8 bits each. Grouping several
+ * of these in parallel provides 64 bits which is common
+ * for a memory stick.
+ *
+ * Memory Stick: A printed circuit board that aggregates multiple
+ * memory devices in parallel. This is the atomic
+ * memory component that is purchaseable by Joe consumer
+ * and loaded into a memory socket.
+ *
+ * Socket: A physical connector on the motherboard that accepts
+ * a single memory stick.
+ *
+ * Channel: Set of memory devices on a memory stick that must be
+ * grouped in parallel with one or more additional
+ * channels from other memory sticks. This parallel
+ * grouping of the output from multiple channels are
+ * necessary for the smallest granularity of memory access.
+ * Some memory controllers are capable of single channel -
+ * which means that memory sticks can be loaded
+ * individually. Other memory controllers are only
+ * capable of dual channel - which means that memory
+ * sticks must be loaded as pairs (see "socket set").
+ *
+ * Chip-select row: All of the memory devices that are selected together.
+ * for a single, minimum grain of memory access.
+ * This selects all of the parallel memory devices across
+ * all of the parallel channels. Common chip-select rows
+ * for single channel are 64 bits, for dual channel 128
+ * bits.
+ *
+ * Single-Ranked stick: A Single-ranked stick has 1 chip-select row of memory.
+ * Motherboards commonly drive two chip-select pins to
+ * a memory stick. A single-ranked stick, will occupy
+ * only one of those rows. The other will be unused.
+ *
+ * Double-Ranked stick: A double-ranked stick has two chip-select rows which
+ * access different sets of memory devices. The two
+ * rows cannot be accessed concurrently.
+ *
+ * Double-sided stick: DEPRECATED TERM, see Double-Ranked stick.
+ * A double-sided stick has two chip-select rows which
+ * access different sets of memory devices. The two
+ * rows cannot be accessed concurrently. "Double-sided"
+ * is irrespective of the memory devices being mounted
+ * on both sides of the memory stick.
+ *
+ * Socket set: All of the memory sticks that are required for
+ * a single memory access or all of the memory sticks
+ * spanned by a chip-select row. A single socket set
+ * has two chip-select rows and if double-sided sticks
+ * are used these will occupy those chip-select rows.
+ *
+ * Bank: This term is avoided because it is unclear when
+ * needing to distinguish between chip-select rows and
+ * socket sets.
+ *
+ * Controller pages:
+ *
+ * Physical pages:
+ *
+ * Virtual pages:
+ *
+ *
+ * STRUCTURE ORGANIZATION AND CHOICES
+ *
+ *
+ *
+ * PS - I enjoyed writing all that about as much as you enjoyed reading it.
+ */
+
+struct channel_info {
+ int chan_idx; /* channel index */
+ u32 ce_count; /* Correctable Errors for this CHANNEL */
+ char label[EDAC_MC_LABEL_LEN + 1]; /* DIMM label on motherboard */
+ struct csrow_info *csrow; /* the parent */
+};
+
+struct csrow_info {
+ unsigned long first_page; /* first page number in dimm */
+ unsigned long last_page; /* last page number in dimm */
+ unsigned long page_mask; /* used for interleaving -
+ * 0UL for non intlv
+ */
+ u32 nr_pages; /* number of pages in csrow */
+ u32 grain; /* granularity of reported error in bytes */
+ int csrow_idx; /* the chip-select row */
+ enum dev_type dtype; /* memory device type */
+ u32 ue_count; /* Uncorrectable Errors for this csrow */
+ u32 ce_count; /* Correctable Errors for this csrow */
+ enum mem_type mtype; /* memory csrow type */
+ enum edac_type edac_mode; /* EDAC mode for this csrow */
+ struct mem_ctl_info *mci; /* the parent */
+
+ struct kobject kobj; /* sysfs kobject for this csrow */
+
+ /* channel information for this csrow */
+ u32 nr_channels;
+ struct channel_info *channels;
+};
+
+struct mcidev_sysfs_group {
+ const char *name; /* group name */
+ const struct mcidev_sysfs_attribute *mcidev_attr; /* group attributes */
+};
+
+struct mcidev_sysfs_group_kobj {
+ struct list_head list; /* list for all instances within a mc */
+
+ struct kobject kobj; /* kobj for the group */
+
+ const struct mcidev_sysfs_group *grp; /* group description table */
+ struct mem_ctl_info *mci; /* the parent */
+};
+
+/* mcidev_sysfs_attribute structure
+ * used for driver sysfs attributes and in mem_ctl_info
+ * sysfs top level entries
+ */
+struct mcidev_sysfs_attribute {
+ /* It should use either attr or grp */
+ struct attribute attr;
+ const struct mcidev_sysfs_group *grp; /* Points to a group of attributes */
+
+ /* Ops for show/store values at the attribute - not used on group */
+ ssize_t (*show)(struct mem_ctl_info *,char *);
+ ssize_t (*store)(struct mem_ctl_info *, const char *,size_t);
+};
+
+/* MEMORY controller information structure
+ */
+struct mem_ctl_info {
+ struct list_head link; /* for global list of mem_ctl_info structs */
+
+ struct module *owner; /* Module owner of this control struct */
+
+ unsigned long mtype_cap; /* memory types supported by mc */
+ unsigned long edac_ctl_cap; /* Mem controller EDAC capabilities */
+ unsigned long edac_cap; /* configuration capabilities - this is
+ * closely related to edac_ctl_cap. The
+ * difference is that the controller may be
+ * capable of s4ecd4ed which would be listed
+ * in edac_ctl_cap, but if channels aren't
+ * capable of s4ecd4ed then the edac_cap would
+ * not have that capability.
+ */
+ unsigned long scrub_cap; /* chipset scrub capabilities */
+ enum scrub_type scrub_mode; /* current scrub mode */
+
+ /* Translates sdram memory scrub rate given in bytes/sec to the
+ internal representation and configures whatever else needs
+ to be configured.
+ */
+ int (*set_sdram_scrub_rate) (struct mem_ctl_info * mci, u32 bw);
+
+ /* Get the current sdram memory scrub rate from the internal
+ representation and converts it to the closest matching
+ bandwidth in bytes/sec.
+ */
+ int (*get_sdram_scrub_rate) (struct mem_ctl_info * mci);
+
+
+ /* pointer to edac checking routine */
+ void (*edac_check) (struct mem_ctl_info * mci);
+
+ /*
+ * Remaps memory pages: controller pages to physical pages.
+ * For most MC's, this will be NULL.
+ */
+ /* FIXME - why not send the phys page to begin with? */
+ unsigned long (*ctl_page_to_phys) (struct mem_ctl_info * mci,
+ unsigned long page);
+ int mc_idx;
+ int nr_csrows;
+ struct csrow_info *csrows;
+ /*
+ * FIXME - what about controllers on other busses? - IDs must be
+ * unique. dev pointer should be sufficiently unique, but
+ * BUS:SLOT.FUNC numbers may not be unique.
+ */
+ struct device *dev;
+ const char *mod_name;
+ const char *mod_ver;
+ const char *ctl_name;
+ const char *dev_name;
+ char proc_name[MC_PROC_NAME_MAX_LEN + 1];
+ void *pvt_info;
+ u32 ue_noinfo_count; /* Uncorrectable Errors w/o info */
+ u32 ce_noinfo_count; /* Correctable Errors w/o info */
+ u32 ue_count; /* Total Uncorrectable Errors for this MC */
+ u32 ce_count; /* Total Correctable Errors for this MC */
+ unsigned long start_time; /* mci load start time (in jiffies) */
+
+ struct completion complete;
+
+ /* edac sysfs device control */
+ struct kobject edac_mci_kobj;
+
+ /* list for all grp instances within a mc */
+ struct list_head grp_kobj_list;
+
+ /* Additional top controller level attributes, but specified
+ * by the low level driver.
+ *
+ * Set by the low level driver to provide attributes at the
+ * controller level, same level as 'ue_count' and 'ce_count' above.
+ * An array of structures, NULL terminated
+ *
+ * If attributes are desired, then set to array of attributes
+ * If no attributes are desired, leave NULL
+ */
+ const struct mcidev_sysfs_attribute *mc_driver_sysfs_attributes;
+
+ /* work struct for this MC */
+ struct delayed_work work;
+
+ /* the internal state of this controller instance */
+ int op_state;
+};
+
#endif
diff --git a/include/linux/edac_mce.h b/include/linux/edac_mce.h
deleted file mode 100644
index f974fc0..0000000
--- a/include/linux/edac_mce.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* Provides edac interface to mcelog events
- *
- * This file may be distributed under the terms of the
- * GNU General Public License version 2.
- *
- * Copyright (c) 2009 by:
- * Mauro Carvalho Chehab <mchehab@redhat.com>
- *
- * Red Hat Inc. http://www.redhat.com
- */
-
-#if defined(CONFIG_EDAC_MCE) || \
- (defined(CONFIG_EDAC_MCE_MODULE) && defined(MODULE))
-
-#include <asm/mce.h>
-#include <linux/list.h>
-
-struct edac_mce {
- struct list_head list;
-
- void *priv;
- int (*check_error)(void *priv, struct mce *mce);
-};
-
-int edac_mce_register(struct edac_mce *edac_mce);
-void edac_mce_unregister(struct edac_mce *edac_mce);
-int edac_mce_parse(struct mce *mce);
-
-#else
-#define edac_mce_parse(mce) (0)
-#endif
diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h
index 53792bf..ce1b719 100644
--- a/include/linux/ext2_fs.h
+++ b/include/linux/ext2_fs.h
@@ -197,8 +197,8 @@
/* Flags that should be inherited by new inodes from their parent. */
#define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\
- EXT2_SYNC_FL | EXT2_IMMUTABLE_FL | EXT2_APPEND_FL |\
- EXT2_NODUMP_FL | EXT2_NOATIME_FL | EXT2_COMPRBLK_FL|\
+ EXT2_SYNC_FL | EXT2_NODUMP_FL |\
+ EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\
EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\
EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL)
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 81965cc..dec9911 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -180,8 +180,8 @@
/* Flags that should be inherited by new inodes from their parent. */
#define EXT3_FL_INHERITED (EXT3_SECRM_FL | EXT3_UNRM_FL | EXT3_COMPR_FL |\
- EXT3_SYNC_FL | EXT3_IMMUTABLE_FL | EXT3_APPEND_FL |\
- EXT3_NODUMP_FL | EXT3_NOATIME_FL | EXT3_COMPRBLK_FL|\
+ EXT3_SYNC_FL | EXT3_NODUMP_FL |\
+ EXT3_NOATIME_FL | EXT3_COMPRBLK_FL |\
EXT3_NOCOMPR_FL | EXT3_JOURNAL_DATA_FL |\
EXT3_NOTAIL_FL | EXT3_DIRSYNC_FL)
@@ -381,7 +381,7 @@
* Mount flags
*/
#define EXT3_MOUNT_CHECK 0x00001 /* Do mount-time checks */
-#define EXT3_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */
+/* EXT3_MOUNT_OLDALLOC was there */
#define EXT3_MOUNT_GRPID 0x00004 /* Create files with directory's group */
#define EXT3_MOUNT_DEBUG 0x00008 /* Some debugging messages */
#define EXT3_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
diff --git a/include/linux/ext3_fs_sb.h b/include/linux/ext3_fs_sb.h
index 258088a..6436525 100644
--- a/include/linux/ext3_fs_sb.h
+++ b/include/linux/ext3_fs_sb.h
@@ -76,10 +76,6 @@
struct mutex s_resize_lock;
unsigned long s_commit_interval;
struct block_device *journal_bdev;
-#ifdef CONFIG_JBD_DEBUG
- struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */
- wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */
-#endif
#ifdef CONFIG_QUOTA
char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
int s_jquota_fmt; /* Format of quota to use */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7a049fd..0c4df26 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -768,14 +768,25 @@
/* Stat data, not accessed from path walking */
unsigned long i_ino;
- unsigned int i_nlink;
+ /*
+ * Filesystems may only read i_nlink directly. They shall use the
+ * following functions for modification:
+ *
+ * (set|clear|inc|drop)_nlink
+ * inode_(inc|dec)_link_count
+ */
+ union {
+ const unsigned int i_nlink;
+ unsigned int __i_nlink;
+ };
dev_t i_rdev;
- loff_t i_size;
struct timespec i_atime;
struct timespec i_mtime;
struct timespec i_ctime;
- unsigned int i_blkbits;
+ spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
+ unsigned short i_bytes;
blkcnt_t i_blocks;
+ loff_t i_size;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
@@ -783,7 +794,6 @@
/* Misc */
unsigned long i_state;
- spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
struct mutex i_mutex;
unsigned long dirtied_when; /* jiffies of first dirtying */
@@ -797,9 +807,10 @@
struct rcu_head i_rcu;
};
atomic_t i_count;
+ unsigned int i_blkbits;
u64 i_version;
- unsigned short i_bytes;
atomic_t i_dio_count;
+ atomic_t i_writecount;
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
struct file_lock *i_flock;
struct address_space i_data;
@@ -823,7 +834,6 @@
#ifdef CONFIG_IMA
atomic_t i_readcount; /* struct files open RO */
#endif
- atomic_t i_writecount;
void *i_private; /* fs or device private pointer */
};
@@ -1755,6 +1765,19 @@
}
/**
+ * set_nlink - directly set an inode's link count
+ * @inode: inode
+ * @nlink: new nlink (should be non-zero)
+ *
+ * This is a low-level filesystem helper to replace any
+ * direct filesystem manipulation of i_nlink.
+ */
+static inline void set_nlink(struct inode *inode, unsigned int nlink)
+{
+ inode->__i_nlink = nlink;
+}
+
+/**
* inc_nlink - directly increment an inode's link count
* @inode: inode
*
@@ -1764,7 +1787,7 @@
*/
static inline void inc_nlink(struct inode *inode)
{
- inode->i_nlink++;
+ inode->__i_nlink++;
}
static inline void inode_inc_link_count(struct inode *inode)
@@ -1786,7 +1809,7 @@
*/
static inline void drop_nlink(struct inode *inode)
{
- inode->i_nlink--;
+ inode->__i_nlink--;
}
/**
@@ -1799,7 +1822,7 @@
*/
static inline void clear_nlink(struct inode *inode)
{
- inode->i_nlink = 0;
+ inode->__i_nlink = 0;
}
static inline void inode_dec_link_count(struct inode *inode)
diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h
index 8390efc..08a2fee 100644
--- a/include/linux/hwspinlock.h
+++ b/include/linux/hwspinlock.h
@@ -20,17 +20,49 @@
#include <linux/err.h>
#include <linux/sched.h>
+#include <linux/device.h>
/* hwspinlock mode argument */
#define HWLOCK_IRQSTATE 0x01 /* Disable interrupts, save state */
#define HWLOCK_IRQ 0x02 /* Disable interrupts, don't save state */
struct hwspinlock;
+struct hwspinlock_device;
+struct hwspinlock_ops;
+
+/**
+ * struct hwspinlock_pdata - platform data for hwspinlock drivers
+ * @base_id: base id for this hwspinlock device
+ *
+ * hwspinlock devices provide system-wide hardware locks that are used
+ * by remote processors that have no other way to achieve synchronization.
+ *
+ * To achieve that, each physical lock must have a system-wide id number
+ * that is agreed upon, otherwise remote processors can't possibly assume
+ * they're using the same hardware lock.
+ *
+ * Usually boards have a single hwspinlock device, which provides several
+ * hwspinlocks, and in this case, they can be trivially numbered 0 to
+ * (num-of-locks - 1).
+ *
+ * In case boards have several hwspinlocks devices, a different base id
+ * should be used for each hwspinlock device (they can't all use 0 as
+ * a starting id!).
+ *
+ * This platform data structure should be used to provide the base id
+ * for each device (which is trivially 0 when only a single hwspinlock
+ * device exists). It can be shared between different platforms, hence
+ * its location.
+ */
+struct hwspinlock_pdata {
+ int base_id;
+};
#if defined(CONFIG_HWSPINLOCK) || defined(CONFIG_HWSPINLOCK_MODULE)
-int hwspin_lock_register(struct hwspinlock *lock);
-struct hwspinlock *hwspin_lock_unregister(unsigned int id);
+int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev,
+ const struct hwspinlock_ops *ops, int base_id, int num_locks);
+int hwspin_lock_unregister(struct hwspinlock_device *bank);
struct hwspinlock *hwspin_lock_request(void);
struct hwspinlock *hwspin_lock_request_specific(unsigned int id);
int hwspin_lock_free(struct hwspinlock *hwlock);
@@ -94,16 +126,6 @@
return 0;
}
-static inline int hwspin_lock_register(struct hwspinlock *hwlock)
-{
- return -ENODEV;
-}
-
-static inline struct hwspinlock *hwspin_lock_unregister(unsigned int id)
-{
- return NULL;
-}
-
#endif /* !CONFIG_HWSPINLOCK */
/**
diff --git a/include/linux/i2c/twl4030-madc.h b/include/linux/i2c/twl4030-madc.h
index 6427d29..530e11b 100644
--- a/include/linux/i2c/twl4030-madc.h
+++ b/include/linux/i2c/twl4030-madc.h
@@ -129,6 +129,10 @@
#define REG_BCICTL2 0x024
#define TWL4030_BCI_ITHSENS 0x007
+/* Register and bits for GPBR1 register */
+#define TWL4030_REG_GPBR1 0x0c
+#define TWL4030_GPBR1_MADC_HFCLK_EN (1 << 7)
+
struct twl4030_madc_user_parms {
int channel;
int average;
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index e6a5e34..c7acdde 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -244,6 +244,7 @@
#include <linux/fs.h>
#include <linux/sched.h>
+#include <linux/jbd_common.h>
#define J_ASSERT(assert) BUG_ON(!(assert))
@@ -270,69 +271,6 @@
#define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why)
#endif
-enum jbd_state_bits {
- BH_JBD /* Has an attached ext3 journal_head */
- = BH_PrivateStart,
- BH_JWrite, /* Being written to log (@@@ DEBUGGING) */
- BH_Freed, /* Has been freed (truncated) */
- BH_Revoked, /* Has been revoked from the log */
- BH_RevokeValid, /* Revoked flag is valid */
- BH_JBDDirty, /* Is dirty but journaled */
- BH_State, /* Pins most journal_head state */
- BH_JournalHead, /* Pins bh->b_private and jh->b_bh */
- BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */
-};
-
-BUFFER_FNS(JBD, jbd)
-BUFFER_FNS(JWrite, jwrite)
-BUFFER_FNS(JBDDirty, jbddirty)
-TAS_BUFFER_FNS(JBDDirty, jbddirty)
-BUFFER_FNS(Revoked, revoked)
-TAS_BUFFER_FNS(Revoked, revoked)
-BUFFER_FNS(RevokeValid, revokevalid)
-TAS_BUFFER_FNS(RevokeValid, revokevalid)
-BUFFER_FNS(Freed, freed)
-
-static inline struct buffer_head *jh2bh(struct journal_head *jh)
-{
- return jh->b_bh;
-}
-
-static inline struct journal_head *bh2jh(struct buffer_head *bh)
-{
- return bh->b_private;
-}
-
-static inline void jbd_lock_bh_state(struct buffer_head *bh)
-{
- bit_spin_lock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_trylock_bh_state(struct buffer_head *bh)
-{
- return bit_spin_trylock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
-{
- return bit_spin_is_locked(BH_State, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_state(struct buffer_head *bh)
-{
- bit_spin_unlock(BH_State, &bh->b_state);
-}
-
-static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
-{
- bit_spin_lock(BH_JournalHead, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
-{
- bit_spin_unlock(BH_JournalHead, &bh->b_state);
-}
-
struct jbd_revoke_table_s;
/**
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 38f307b..2092ea2 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -275,6 +275,7 @@
#include <linux/fs.h>
#include <linux/sched.h>
+#include <linux/jbd_common.h>
#define J_ASSERT(assert) BUG_ON(!(assert))
@@ -302,70 +303,6 @@
#define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why)
#endif
-enum jbd_state_bits {
- BH_JBD /* Has an attached ext3 journal_head */
- = BH_PrivateStart,
- BH_JWrite, /* Being written to log (@@@ DEBUGGING) */
- BH_Freed, /* Has been freed (truncated) */
- BH_Revoked, /* Has been revoked from the log */
- BH_RevokeValid, /* Revoked flag is valid */
- BH_JBDDirty, /* Is dirty but journaled */
- BH_State, /* Pins most journal_head state */
- BH_JournalHead, /* Pins bh->b_private and jh->b_bh */
- BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */
- BH_JBDPrivateStart, /* First bit available for private use by FS */
-};
-
-BUFFER_FNS(JBD, jbd)
-BUFFER_FNS(JWrite, jwrite)
-BUFFER_FNS(JBDDirty, jbddirty)
-TAS_BUFFER_FNS(JBDDirty, jbddirty)
-BUFFER_FNS(Revoked, revoked)
-TAS_BUFFER_FNS(Revoked, revoked)
-BUFFER_FNS(RevokeValid, revokevalid)
-TAS_BUFFER_FNS(RevokeValid, revokevalid)
-BUFFER_FNS(Freed, freed)
-
-static inline struct buffer_head *jh2bh(struct journal_head *jh)
-{
- return jh->b_bh;
-}
-
-static inline struct journal_head *bh2jh(struct buffer_head *bh)
-{
- return bh->b_private;
-}
-
-static inline void jbd_lock_bh_state(struct buffer_head *bh)
-{
- bit_spin_lock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_trylock_bh_state(struct buffer_head *bh)
-{
- return bit_spin_trylock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
-{
- return bit_spin_is_locked(BH_State, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_state(struct buffer_head *bh)
-{
- bit_spin_unlock(BH_State, &bh->b_state);
-}
-
-static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
-{
- bit_spin_lock(BH_JournalHead, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
-{
- bit_spin_unlock(BH_JournalHead, &bh->b_state);
-}
-
/* Flags in jbd_inode->i_flags */
#define __JI_COMMIT_RUNNING 0
/* Commit of the inode data in progress. We use this flag to protect us from
@@ -1106,9 +1043,9 @@
*/
extern handle_t *jbd2_journal_start(journal_t *, int nblocks);
-extern handle_t *jbd2__journal_start(journal_t *, int nblocks, int gfp_mask);
+extern handle_t *jbd2__journal_start(journal_t *, int nblocks, gfp_t gfp_mask);
extern int jbd2_journal_restart(handle_t *, int nblocks);
-extern int jbd2__journal_restart(handle_t *, int nblocks, int gfp_mask);
+extern int jbd2__journal_restart(handle_t *, int nblocks, gfp_t gfp_mask);
extern int jbd2_journal_extend (handle_t *, int nblocks);
extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
diff --git a/include/linux/jbd_common.h b/include/linux/jbd_common.h
new file mode 100644
index 0000000..6230f85
--- /dev/null
+++ b/include/linux/jbd_common.h
@@ -0,0 +1,68 @@
+#ifndef _LINUX_JBD_STATE_H
+#define _LINUX_JBD_STATE_H
+
+enum jbd_state_bits {
+ BH_JBD /* Has an attached ext3 journal_head */
+ = BH_PrivateStart,
+ BH_JWrite, /* Being written to log (@@@ DEBUGGING) */
+ BH_Freed, /* Has been freed (truncated) */
+ BH_Revoked, /* Has been revoked from the log */
+ BH_RevokeValid, /* Revoked flag is valid */
+ BH_JBDDirty, /* Is dirty but journaled */
+ BH_State, /* Pins most journal_head state */
+ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */
+ BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */
+ BH_JBDPrivateStart, /* First bit available for private use by FS */
+};
+
+BUFFER_FNS(JBD, jbd)
+BUFFER_FNS(JWrite, jwrite)
+BUFFER_FNS(JBDDirty, jbddirty)
+TAS_BUFFER_FNS(JBDDirty, jbddirty)
+BUFFER_FNS(Revoked, revoked)
+TAS_BUFFER_FNS(Revoked, revoked)
+BUFFER_FNS(RevokeValid, revokevalid)
+TAS_BUFFER_FNS(RevokeValid, revokevalid)
+BUFFER_FNS(Freed, freed)
+
+static inline struct buffer_head *jh2bh(struct journal_head *jh)
+{
+ return jh->b_bh;
+}
+
+static inline struct journal_head *bh2jh(struct buffer_head *bh)
+{
+ return bh->b_private;
+}
+
+static inline void jbd_lock_bh_state(struct buffer_head *bh)
+{
+ bit_spin_lock(BH_State, &bh->b_state);
+}
+
+static inline int jbd_trylock_bh_state(struct buffer_head *bh)
+{
+ return bit_spin_trylock(BH_State, &bh->b_state);
+}
+
+static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
+{
+ return bit_spin_is_locked(BH_State, &bh->b_state);
+}
+
+static inline void jbd_unlock_bh_state(struct buffer_head *bh)
+{
+ bit_spin_unlock(BH_State, &bh->b_state);
+}
+
+static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
+{
+ bit_spin_lock(BH_JournalHead, &bh->b_state);
+}
+
+static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
+{
+ bit_spin_unlock(BH_JournalHead, &bh->b_state);
+}
+
+#endif
diff --git a/include/linux/magic.h b/include/linux/magic.h
index 1e5df2a..2d4beab 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -30,11 +30,11 @@
#define ANON_INODE_FS_MAGIC 0x09041934
#define PSTOREFS_MAGIC 0x6165676C
-#define MINIX_SUPER_MAGIC 0x137F /* original minix fs */
-#define MINIX_SUPER_MAGIC2 0x138F /* minix fs, 30 char names */
-#define MINIX2_SUPER_MAGIC 0x2468 /* minix V2 fs */
-#define MINIX2_SUPER_MAGIC2 0x2478 /* minix V2 fs, 30 char names */
-#define MINIX3_SUPER_MAGIC 0x4d5a /* minix V3 fs */
+#define MINIX_SUPER_MAGIC 0x137F /* minix v1 fs, 14 char names */
+#define MINIX_SUPER_MAGIC2 0x138F /* minix v1 fs, 30 char names */
+#define MINIX2_SUPER_MAGIC 0x2468 /* minix v2 fs, 14 char names */
+#define MINIX2_SUPER_MAGIC2 0x2478 /* minix v2 fs, 30 char names */
+#define MINIX3_SUPER_MAGIC 0x4d5a /* minix v3 fs, 60 char names */
#define MSDOS_SUPER_MAGIC 0x4d44 /* MD */
#define NCP_SUPER_MAGIC 0x564c /* Guess, what 0x564c is :-) */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ac797fa..b87068a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -78,8 +78,8 @@
extern void mem_cgroup_uncharge_page(struct page *page);
extern void mem_cgroup_uncharge_cache_page(struct page *page);
-extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
-int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
+extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask);
+int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg);
extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
@@ -88,26 +88,28 @@
static inline
int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup *memcg;
rcu_read_lock();
- mem = mem_cgroup_from_task(rcu_dereference((mm)->owner));
+ memcg = mem_cgroup_from_task(rcu_dereference((mm)->owner));
rcu_read_unlock();
- return cgroup == mem;
+ return cgroup == memcg;
}
-extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem);
+extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
extern int
mem_cgroup_prepare_migration(struct page *page,
struct page *newpage, struct mem_cgroup **ptr, gfp_t gfp_mask);
-extern void mem_cgroup_end_migration(struct mem_cgroup *mem,
+extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
struct page *oldpage, struct page *newpage, bool migration_ok);
/*
* For memory reclaim.
*/
-int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg);
-int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg);
+int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg,
+ struct zone *zone);
+int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg,
+ struct zone *zone);
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg,
int nid, int zid, unsigned int lrumask);
@@ -148,7 +150,7 @@
unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
gfp_t gfp_mask,
unsigned long *total_scanned);
-u64 mem_cgroup_get_limit(struct mem_cgroup *mem);
+u64 mem_cgroup_get_limit(struct mem_cgroup *memcg);
void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -244,18 +246,20 @@
return NULL;
}
-static inline int mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *mem)
+static inline int mm_match_cgroup(struct mm_struct *mm,
+ struct mem_cgroup *memcg)
{
return 1;
}
static inline int task_in_mem_cgroup(struct task_struct *task,
- const struct mem_cgroup *mem)
+ const struct mem_cgroup *memcg)
{
return 1;
}
-static inline struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem)
+static inline struct cgroup_subsys_state
+ *mem_cgroup_css(struct mem_cgroup *memcg)
{
return NULL;
}
@@ -267,22 +271,22 @@
return 0;
}
-static inline void mem_cgroup_end_migration(struct mem_cgroup *mem,
+static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
struct page *oldpage, struct page *newpage, bool migration_ok)
{
}
-static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
+static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *memcg)
{
return 0;
}
-static inline void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
+static inline void mem_cgroup_note_reclaim_priority(struct mem_cgroup *memcg,
int priority)
{
}
-static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
+static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *memcg,
int priority)
{
}
@@ -293,13 +297,13 @@
}
static inline int
-mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
+mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone)
{
return 1;
}
static inline int
-mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
+mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, struct zone *zone)
{
return 1;
}
@@ -348,7 +352,7 @@
}
static inline
-u64 mem_cgroup_get_limit(struct mem_cgroup *mem)
+u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
{
return 0;
}
diff --git a/include/linux/mfd/ab5500/ab5500.h b/include/linux/mfd/ab5500/ab5500.h
new file mode 100644
index 0000000..a720051
--- /dev/null
+++ b/include/linux/mfd/ab5500/ab5500.h
@@ -0,0 +1,140 @@
+/*
+ * Copyright (C) ST-Ericsson 2011
+ *
+ * License Terms: GNU General Public License v2
+ */
+#ifndef MFD_AB5500_H
+#define MFD_AB5500_H
+
+#include <linux/device.h>
+
+enum ab5500_devid {
+ AB5500_DEVID_ADC,
+ AB5500_DEVID_LEDS,
+ AB5500_DEVID_POWER,
+ AB5500_DEVID_REGULATORS,
+ AB5500_DEVID_SIM,
+ AB5500_DEVID_RTC,
+ AB5500_DEVID_CHARGER,
+ AB5500_DEVID_FUELGAUGE,
+ AB5500_DEVID_VIBRATOR,
+ AB5500_DEVID_CODEC,
+ AB5500_DEVID_USB,
+ AB5500_DEVID_OTP,
+ AB5500_DEVID_VIDEO,
+ AB5500_DEVID_DBIECI,
+ AB5500_DEVID_ONSWA,
+ AB5500_NUM_DEVICES,
+};
+
+enum ab5500_banks {
+ AB5500_BANK_VIT_IO_I2C_CLK_TST_OTP = 0,
+ AB5500_BANK_VDDDIG_IO_I2C_CLK_TST = 1,
+ AB5500_BANK_VDENC = 2,
+ AB5500_BANK_SIM_USBSIM = 3,
+ AB5500_BANK_LED = 4,
+ AB5500_BANK_ADC = 5,
+ AB5500_BANK_RTC = 6,
+ AB5500_BANK_STARTUP = 7,
+ AB5500_BANK_DBI_ECI = 8,
+ AB5500_BANK_CHG = 9,
+ AB5500_BANK_FG_BATTCOM_ACC = 10,
+ AB5500_BANK_USB = 11,
+ AB5500_BANK_IT = 12,
+ AB5500_BANK_VIBRA = 13,
+ AB5500_BANK_AUDIO_HEADSETUSB = 14,
+ AB5500_NUM_BANKS = 15,
+};
+
+enum ab5500_banks_addr {
+ AB5500_ADDR_VIT_IO_I2C_CLK_TST_OTP = 0x4A,
+ AB5500_ADDR_VDDDIG_IO_I2C_CLK_TST = 0x4B,
+ AB5500_ADDR_VDENC = 0x06,
+ AB5500_ADDR_SIM_USBSIM = 0x04,
+ AB5500_ADDR_LED = 0x10,
+ AB5500_ADDR_ADC = 0x0A,
+ AB5500_ADDR_RTC = 0x0F,
+ AB5500_ADDR_STARTUP = 0x03,
+ AB5500_ADDR_DBI_ECI = 0x07,
+ AB5500_ADDR_CHG = 0x0B,
+ AB5500_ADDR_FG_BATTCOM_ACC = 0x0C,
+ AB5500_ADDR_USB = 0x05,
+ AB5500_ADDR_IT = 0x0E,
+ AB5500_ADDR_VIBRA = 0x02,
+ AB5500_ADDR_AUDIO_HEADSETUSB = 0x0D,
+};
+
+/*
+ * Interrupt register offsets
+ * Bank : 0x0E
+ */
+#define AB5500_IT_SOURCE0_REG 0x20
+#define AB5500_IT_SOURCE1_REG 0x21
+#define AB5500_IT_SOURCE2_REG 0x22
+#define AB5500_IT_SOURCE3_REG 0x23
+#define AB5500_IT_SOURCE4_REG 0x24
+#define AB5500_IT_SOURCE5_REG 0x25
+#define AB5500_IT_SOURCE6_REG 0x26
+#define AB5500_IT_SOURCE7_REG 0x27
+#define AB5500_IT_SOURCE8_REG 0x28
+#define AB5500_IT_SOURCE9_REG 0x29
+#define AB5500_IT_SOURCE10_REG 0x2A
+#define AB5500_IT_SOURCE11_REG 0x2B
+#define AB5500_IT_SOURCE12_REG 0x2C
+#define AB5500_IT_SOURCE13_REG 0x2D
+#define AB5500_IT_SOURCE14_REG 0x2E
+#define AB5500_IT_SOURCE15_REG 0x2F
+#define AB5500_IT_SOURCE16_REG 0x30
+#define AB5500_IT_SOURCE17_REG 0x31
+#define AB5500_IT_SOURCE18_REG 0x32
+#define AB5500_IT_SOURCE19_REG 0x33
+#define AB5500_IT_SOURCE20_REG 0x34
+#define AB5500_IT_SOURCE21_REG 0x35
+#define AB5500_IT_SOURCE22_REG 0x36
+#define AB5500_IT_SOURCE23_REG 0x37
+
+#define AB5500_NUM_IRQ_REGS 23
+
+/**
+ * struct ab5500
+ * @access_mutex: lock out concurrent accesses to the AB registers
+ * @dev: a pointer to the device struct for this chip driver
+ * @ab5500_irq: the analog baseband irq
+ * @irq_base: the platform configuration irq base for subdevices
+ * @chip_name: name of this chip variant
+ * @chip_id: 8 bit chip ID for this chip variant
+ * @irq_lock: a lock to protect the mask
+ * @abb_events: a local bit mask of the prcmu wakeup events
+ * @event_mask: a local copy of the mask event registers
+ * @last_event_mask: a copy of the last event_mask written to hardware
+ * @startup_events: a copy of the first reading of the event registers
+ * @startup_events_read: whether the first events have been read
+ */
+struct ab5500 {
+ struct mutex access_mutex;
+ struct device *dev;
+ unsigned int ab5500_irq;
+ unsigned int irq_base;
+ char chip_name[32];
+ u8 chip_id;
+ struct mutex irq_lock;
+ u32 abb_events;
+ u8 mask[AB5500_NUM_IRQ_REGS];
+ u8 oldmask[AB5500_NUM_IRQ_REGS];
+ u8 startup_events[AB5500_NUM_IRQ_REGS];
+ bool startup_events_read;
+#ifdef CONFIG_DEBUG_FS
+ unsigned int debug_bank;
+ unsigned int debug_address;
+#endif
+};
+
+struct ab5500_platform_data {
+ struct {unsigned int base; unsigned int count; } irq;
+ void *dev_data[AB5500_NUM_DEVICES];
+ struct abx500_init_settings *init_settings;
+ unsigned int init_settings_sz;
+ bool pm_power_off;
+};
+
+#endif /* MFD_AB5500_H */
diff --git a/include/linux/mfd/ab8500/gpadc.h b/include/linux/mfd/ab8500/gpadc.h
index 46b9540..2529667 100644
--- a/include/linux/mfd/ab8500/gpadc.h
+++ b/include/linux/mfd/ab8500/gpadc.h
@@ -27,6 +27,9 @@
struct ab8500_gpadc;
struct ab8500_gpadc *ab8500_gpadc_get(char *name);
-int ab8500_gpadc_convert(struct ab8500_gpadc *gpadc, u8 input);
+int ab8500_gpadc_convert(struct ab8500_gpadc *gpadc, u8 channel);
+int ab8500_gpadc_read_raw(struct ab8500_gpadc *gpadc, u8 channel);
+int ab8500_gpadc_ad_to_voltage(struct ab8500_gpadc *gpadc,
+ u8 channel, int ad_value);
#endif /* _AB8500_GPADC_H */
diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h
index 896b5e4..9970337 100644
--- a/include/linux/mfd/abx500.h
+++ b/include/linux/mfd/abx500.h
@@ -6,7 +6,7 @@
*
* ABX500 core access functions.
* The abx500 interface is used for the Analog Baseband chip
- * ab3100, ab3550, ab5500, and ab8500.
+ * ab3100, ab5500, and ab8500.
*
* Author: Mattias Wallin <mattias.wallin@stericsson.com>
* Author: Mattias Nilsson <mattias.i.nilsson@stericsson.com>
@@ -29,17 +29,16 @@
#define AB3100_P1G 0xc6
#define AB3100_R2A 0xc7
#define AB3100_R2B 0xc8
-#define AB3550_P1A 0x10
#define AB5500_1_0 0x20
-#define AB5500_2_0 0x21
-#define AB5500_2_1 0x22
+#define AB5500_1_1 0x21
+#define AB5500_2_0 0x24
/* AB8500 CIDs*/
-#define AB8500_CUTEARLY 0x00
#define AB8500_CUT1P0 0x10
#define AB8500_CUT1P1 0x11
#define AB8500_CUT2P0 0x20
#define AB8500_CUT3P0 0x30
+#define AB8500_CUT3P3 0x33
/*
* AB3100, EVENTA1, A2 and A3 event register flags
@@ -143,39 +142,6 @@
int ab3100_event_unregister(struct ab3100 *ab3100,
struct notifier_block *nb);
-/* AB3550, STR register flags */
-#define AB3550_STR_ONSWA (0x01)
-#define AB3550_STR_ONSWB (0x02)
-#define AB3550_STR_ONSWC (0x04)
-#define AB3550_STR_DCIO (0x08)
-#define AB3550_STR_BOOT_MODE (0x10)
-#define AB3550_STR_SIM_OFF (0x20)
-#define AB3550_STR_BATT_REMOVAL (0x40)
-#define AB3550_STR_VBUS (0x80)
-
-/* Interrupt mask registers */
-#define AB3550_IMR1 0x29
-#define AB3550_IMR2 0x2a
-#define AB3550_IMR3 0x2b
-#define AB3550_IMR4 0x2c
-#define AB3550_IMR5 0x2d
-
-enum ab3550_devid {
- AB3550_DEVID_ADC,
- AB3550_DEVID_DAC,
- AB3550_DEVID_LEDS,
- AB3550_DEVID_POWER,
- AB3550_DEVID_REGULATORS,
- AB3550_DEVID_SIM,
- AB3550_DEVID_UART,
- AB3550_DEVID_RTC,
- AB3550_DEVID_CHARGER,
- AB3550_DEVID_FUELGAUGE,
- AB3550_DEVID_VIBRATOR,
- AB3550_DEVID_CODEC,
- AB3550_NUM_DEVICES,
-};
-
/**
* struct abx500_init_setting
* Initial value of the registers for driver to use during setup.
@@ -186,18 +152,6 @@
u8 setting;
};
-/**
- * struct ab3550_platform_data
- * Data supplied to initialize board connections to the AB3550
- */
-struct ab3550_platform_data {
- struct {unsigned int base; unsigned int count; } irq;
- void *dev_data[AB3550_NUM_DEVICES];
- size_t dev_data_sz[AB3550_NUM_DEVICES];
- struct abx500_init_settings *init_settings;
- unsigned int init_settings_sz;
-};
-
int abx500_set_register_interruptible(struct device *dev, u8 bank, u8 reg,
u8 value);
int abx500_get_register_interruptible(struct device *dev, u8 bank, u8 reg,
diff --git a/include/linux/mfd/db5500-prcmu.h b/include/linux/mfd/db5500-prcmu.h
index f097798..9890687 100644
--- a/include/linux/mfd/db5500-prcmu.h
+++ b/include/linux/mfd/db5500-prcmu.h
@@ -5,21 +5,35 @@
*
* U5500 PRCMU API.
*/
-#ifndef __MACH_PRCMU_U5500_H
-#define __MACH_PRCMU_U5500_H
+#ifndef __MFD_DB5500_PRCMU_H
+#define __MFD_DB5500_PRCMU_H
-#ifdef CONFIG_UX500_SOC_DB5500
+#ifdef CONFIG_MFD_DB5500_PRCMU
void db5500_prcmu_early_init(void);
-
+int db5500_prcmu_set_epod(u16 epod_id, u8 epod_state);
+int db5500_prcmu_set_display_clocks(void);
+int db5500_prcmu_disable_dsipll(void);
+int db5500_prcmu_enable_dsipll(void);
int db5500_prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size);
int db5500_prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size);
+void db5500_prcmu_enable_wakeups(u32 wakeups);
+int db5500_prcmu_request_clock(u8 clock, bool enable);
+void db5500_prcmu_config_abb_event_readout(u32 abb_events);
+void db5500_prcmu_get_abb_event_buffer(void __iomem **buf);
+int prcmu_resetout(u8 resoutn, u8 state);
+int db5500_prcmu_set_power_state(u8 state, bool keep_ulp_clk,
+ bool keep_ap_pll);
+int db5500_prcmu_config_esram0_deep_sleep(u8 state);
+void db5500_prcmu_system_reset(u16 reset_code);
+u16 db5500_prcmu_get_reset_code(void);
+bool db5500_prcmu_is_ac_wake_requested(void);
+int db5500_prcmu_set_arm_opp(u8 opp);
+int db5500_prcmu_get_arm_opp(void);
#else /* !CONFIG_UX500_SOC_DB5500 */
-static inline void db5500_prcmu_early_init(void)
-{
-}
+static inline void db5500_prcmu_early_init(void) {}
static inline int db5500_prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
{
@@ -31,15 +45,75 @@
return -ENOSYS;
}
-#endif /* CONFIG_UX500_SOC_DB5500 */
-
-static inline int db5500_prcmu_config_abb_event_readout(u32 abb_events)
+static inline int db5500_prcmu_request_clock(u8 clock, bool enable)
{
-#ifdef CONFIG_MACH_U5500_SIMULATOR
return 0;
-#else
- return -1;
-#endif
}
-#endif /* __MACH_PRCMU_U5500_H */
+static inline int db5500_prcmu_set_display_clocks(void)
+{
+ return 0;
+}
+
+static inline int db5500_prcmu_disable_dsipll(void)
+{
+ return 0;
+}
+
+static inline int db5500_prcmu_enable_dsipll(void)
+{
+ return 0;
+}
+
+static inline int db5500_prcmu_config_esram0_deep_sleep(u8 state)
+{
+ return 0;
+}
+
+static inline void db5500_prcmu_enable_wakeups(u32 wakeups) {}
+
+static inline int prcmu_resetout(u8 resoutn, u8 state)
+{
+ return 0;
+}
+
+static inline int db5500_prcmu_set_epod(u16 epod_id, u8 epod_state)
+{
+ return 0;
+}
+
+static inline void db5500_prcmu_get_abb_event_buffer(void __iomem **buf) {}
+static inline void db5500_prcmu_config_abb_event_readout(u32 abb_events) {}
+
+static inline int db5500_prcmu_set_power_state(u8 state, bool keep_ulp_clk,
+ bool keep_ap_pll)
+{
+ return 0;
+}
+
+static inline void db5500_prcmu_system_reset(u16 reset_code) {}
+
+static inline u16 db5500_prcmu_get_reset_code(void)
+{
+ return 0;
+}
+
+static inline bool db5500_prcmu_is_ac_wake_requested(void)
+{
+ return 0;
+}
+
+static inline int db5500_prcmu_set_arm_opp(u8 opp)
+{
+ return 0;
+}
+
+static inline int db5500_prcmu_get_arm_opp(void)
+{
+ return 0;
+}
+
+
+#endif /* CONFIG_MFD_DB5500_PRCMU */
+
+#endif /* __MFD_DB5500_PRCMU_H */
diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h
index 917dbcab..60d27f7 100644
--- a/include/linux/mfd/db8500-prcmu.h
+++ b/include/linux/mfd/db8500-prcmu.h
@@ -11,7 +11,6 @@
#define __MFD_DB8500_PRCMU_H
#include <linux/interrupt.h>
-#include <linux/notifier.h>
/* This portion previously known as <mach/prcmu-fw-defs_v1.h> */
@@ -133,7 +132,7 @@
* @APEXECUTE_TO_APIDLE: Power state transition from ApExecute to ApIdle
*/
enum ap_pwrst_trans {
- NO_TRANSITION = 0x00,
+ PRCMU_AP_NO_CHANGE = 0x00,
APEXECUTE_TO_APSLEEP = 0x01,
APIDLE_TO_APSLEEP = 0x02, /* To be removed */
PRCMU_AP_SLEEP = 0x01,
@@ -146,54 +145,6 @@
};
/**
- * enum ddr_pwrst - DDR power states definition
- * @DDR_PWR_STATE_UNCHANGED: SDRAM and DDR controller state is unchanged
- * @DDR_PWR_STATE_ON:
- * @DDR_PWR_STATE_OFFLOWLAT:
- * @DDR_PWR_STATE_OFFHIGHLAT:
- */
-enum ddr_pwrst {
- DDR_PWR_STATE_UNCHANGED = 0x00,
- DDR_PWR_STATE_ON = 0x01,
- DDR_PWR_STATE_OFFLOWLAT = 0x02,
- DDR_PWR_STATE_OFFHIGHLAT = 0x03
-};
-
-/**
- * enum arm_opp - ARM OPP states definition
- * @ARM_OPP_INIT:
- * @ARM_NO_CHANGE: The ARM operating point is unchanged
- * @ARM_100_OPP: The new ARM operating point is arm100opp
- * @ARM_50_OPP: The new ARM operating point is arm50opp
- * @ARM_MAX_OPP: Operating point is "max" (more than 100)
- * @ARM_MAX_FREQ100OPP: Set max opp if available, else 100
- * @ARM_EXTCLK: The new ARM operating point is armExtClk
- */
-enum arm_opp {
- ARM_OPP_INIT = 0x00,
- ARM_NO_CHANGE = 0x01,
- ARM_100_OPP = 0x02,
- ARM_50_OPP = 0x03,
- ARM_MAX_OPP = 0x04,
- ARM_MAX_FREQ100OPP = 0x05,
- ARM_EXTCLK = 0x07
-};
-
-/**
- * enum ape_opp - APE OPP states definition
- * @APE_OPP_INIT:
- * @APE_NO_CHANGE: The APE operating point is unchanged
- * @APE_100_OPP: The new APE operating point is ape100opp
- * @APE_50_OPP: 50%
- */
-enum ape_opp {
- APE_OPP_INIT = 0x00,
- APE_NO_CHANGE = 0x01,
- APE_100_OPP = 0x02,
- APE_50_OPP = 0x03
-};
-
-/**
* enum hw_acc_state - State definition for hardware accelerator
* @HW_NO_CHANGE: The hardware accelerator state must remain unchanged
* @HW_OFF: The hardware accelerator must be switched off
@@ -469,26 +420,6 @@
/* End of file previously known as prcmu-fw-defs_v1.h */
-/* PRCMU Wakeup defines */
-enum prcmu_wakeup_index {
- PRCMU_WAKEUP_INDEX_RTC,
- PRCMU_WAKEUP_INDEX_RTT0,
- PRCMU_WAKEUP_INDEX_RTT1,
- PRCMU_WAKEUP_INDEX_HSI0,
- PRCMU_WAKEUP_INDEX_HSI1,
- PRCMU_WAKEUP_INDEX_USB,
- PRCMU_WAKEUP_INDEX_ABB,
- PRCMU_WAKEUP_INDEX_ABB_FIFO,
- PRCMU_WAKEUP_INDEX_ARM,
- NUM_PRCMU_WAKEUP_INDICES
-};
-#define PRCMU_WAKEUP(_name) (BIT(PRCMU_WAKEUP_INDEX_##_name))
-
-/* PRCMU QoS APE OPP class */
-#define PRCMU_QOS_APE_OPP 1
-#define PRCMU_QOS_DDR_OPP 2
-#define PRCMU_QOS_DEFAULT_VALUE -1
-
/**
* enum hw_acc_dev - enum for hw accelerators
* @HW_ACC_SVAMMDSP: for SVAMMDSP
@@ -527,64 +458,6 @@
};
/*
- * Ids for all EPODs (power domains)
- * - EPOD_ID_SVAMMDSP: power domain for SVA MMDSP
- * - EPOD_ID_SVAPIPE: power domain for SVA pipe
- * - EPOD_ID_SIAMMDSP: power domain for SIA MMDSP
- * - EPOD_ID_SIAPIPE: power domain for SIA pipe
- * - EPOD_ID_SGA: power domain for SGA
- * - EPOD_ID_B2R2_MCDE: power domain for B2R2 and MCDE
- * - EPOD_ID_ESRAM12: power domain for ESRAM 1 and 2
- * - EPOD_ID_ESRAM34: power domain for ESRAM 3 and 4
- * - NUM_EPOD_ID: number of power domains
- */
-#define EPOD_ID_SVAMMDSP 0
-#define EPOD_ID_SVAPIPE 1
-#define EPOD_ID_SIAMMDSP 2
-#define EPOD_ID_SIAPIPE 3
-#define EPOD_ID_SGA 4
-#define EPOD_ID_B2R2_MCDE 5
-#define EPOD_ID_ESRAM12 6
-#define EPOD_ID_ESRAM34 7
-#define NUM_EPOD_ID 8
-
-/*
- * state definition for EPOD (power domain)
- * - EPOD_STATE_NO_CHANGE: The EPOD should remain unchanged
- * - EPOD_STATE_OFF: The EPOD is switched off
- * - EPOD_STATE_RAMRET: The EPOD is switched off with its internal RAM in
- * retention
- * - EPOD_STATE_ON_CLK_OFF: The EPOD is switched on, clock is still off
- * - EPOD_STATE_ON: Same as above, but with clock enabled
- */
-#define EPOD_STATE_NO_CHANGE 0x00
-#define EPOD_STATE_OFF 0x01
-#define EPOD_STATE_RAMRET 0x02
-#define EPOD_STATE_ON_CLK_OFF 0x03
-#define EPOD_STATE_ON 0x04
-
-/*
- * CLKOUT sources
- */
-#define PRCMU_CLKSRC_CLK38M 0x00
-#define PRCMU_CLKSRC_ACLK 0x01
-#define PRCMU_CLKSRC_SYSCLK 0x02
-#define PRCMU_CLKSRC_LCDCLK 0x03
-#define PRCMU_CLKSRC_SDMMCCLK 0x04
-#define PRCMU_CLKSRC_TVCLK 0x05
-#define PRCMU_CLKSRC_TIMCLK 0x06
-#define PRCMU_CLKSRC_CLK009 0x07
-/* These are only valid for CLKOUT1: */
-#define PRCMU_CLKSRC_SIAMMDSPCLK 0x40
-#define PRCMU_CLKSRC_I2CCLK 0x41
-#define PRCMU_CLKSRC_MSP02CLK 0x42
-#define PRCMU_CLKSRC_ARMPLL_OBSCLK 0x43
-#define PRCMU_CLKSRC_HSIRXCLK 0x44
-#define PRCMU_CLKSRC_HSITXCLK 0x45
-#define PRCMU_CLKSRC_ARMCLKFIX 0x46
-#define PRCMU_CLKSRC_HDMICLK 0x47
-
-/*
* Definitions for autonomous power management configuration.
*/
@@ -620,88 +493,12 @@
u8 sva_policy;
};
-/**
- * enum ddr_opp - DDR OPP states definition
- * @DDR_100_OPP: The new DDR operating point is ddr100opp
- * @DDR_50_OPP: The new DDR operating point is ddr50opp
- * @DDR_25_OPP: The new DDR operating point is ddr25opp
- */
-enum ddr_opp {
- DDR_100_OPP = 0x00,
- DDR_50_OPP = 0x01,
- DDR_25_OPP = 0x02,
-};
-
-/*
- * Clock identifiers.
- */
-enum prcmu_clock {
- PRCMU_SGACLK,
- PRCMU_UARTCLK,
- PRCMU_MSP02CLK,
- PRCMU_MSP1CLK,
- PRCMU_I2CCLK,
- PRCMU_SDMMCCLK,
- PRCMU_SLIMCLK,
- PRCMU_PER1CLK,
- PRCMU_PER2CLK,
- PRCMU_PER3CLK,
- PRCMU_PER5CLK,
- PRCMU_PER6CLK,
- PRCMU_PER7CLK,
- PRCMU_LCDCLK,
- PRCMU_BMLCLK,
- PRCMU_HSITXCLK,
- PRCMU_HSIRXCLK,
- PRCMU_HDMICLK,
- PRCMU_APEATCLK,
- PRCMU_APETRACECLK,
- PRCMU_MCDECLK,
- PRCMU_IPI2CCLK,
- PRCMU_DSIALTCLK,
- PRCMU_DMACLK,
- PRCMU_B2R2CLK,
- PRCMU_TVCLK,
- PRCMU_SSPCLK,
- PRCMU_RNGCLK,
- PRCMU_UICCCLK,
- PRCMU_NUM_REG_CLOCKS,
- PRCMU_SYSCLK = PRCMU_NUM_REG_CLOCKS,
- PRCMU_TIMCLK,
-};
-
-/*
- * Definitions for controlling ESRAM0 in deep sleep.
- */
-#define ESRAM0_DEEP_SLEEP_STATE_OFF 1
-#define ESRAM0_DEEP_SLEEP_STATE_RET 2
-
-#ifdef CONFIG_MFD_DB8500_PRCMU
-void __init prcmu_early_init(void);
-int prcmu_set_display_clocks(void);
-int prcmu_disable_dsipll(void);
-int prcmu_enable_dsipll(void);
-#else
-static inline void __init prcmu_early_init(void) {}
-#endif
-
#ifdef CONFIG_MFD_DB8500_PRCMU
+void db8500_prcmu_early_init(void);
int prcmu_set_rc_a2p(enum romcode_write);
enum romcode_read prcmu_get_rc_p2a(void);
enum ap_pwrst prcmu_get_xp70_current_state(void);
-int prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll);
-
-void prcmu_enable_wakeups(u32 wakeups);
-static inline void prcmu_disable_wakeups(void)
-{
- prcmu_enable_wakeups(0);
-}
-
-void prcmu_config_abb_event_readout(u32 abb_events);
-void prcmu_get_abb_event_buffer(void __iomem **buf);
-int prcmu_set_arm_opp(u8 opp);
-int prcmu_get_arm_opp(void);
bool prcmu_has_arm_maxopp(void);
bool prcmu_is_u8400(void);
int prcmu_set_ape_opp(u8 opp);
@@ -710,19 +507,14 @@
int prcmu_release_usb_wakeup_state(void);
int prcmu_set_ddr_opp(u8 opp);
int prcmu_get_ddr_opp(void);
-unsigned long prcmu_qos_get_cpufreq_opp_delay(void);
-void prcmu_qos_set_cpufreq_opp_delay(unsigned long);
/* NOTE! Use regulator framework instead */
int prcmu_set_hwacc(u16 hw_acc_dev, u8 state);
-int prcmu_set_epod(u16 epod_id, u8 epod_state);
void prcmu_configure_auto_pm(struct prcmu_auto_pm_config *sleep,
struct prcmu_auto_pm_config *idle);
bool prcmu_is_auto_pm_enabled(void);
int prcmu_config_clkout(u8 clkout, u8 source, u8 div);
-int prcmu_request_clock(u8 clock, bool enable);
int prcmu_set_clock_divider(u8 clock, u8 divider);
-int prcmu_config_esram0_deep_sleep(u8 state);
int prcmu_config_hotdog(u8 threshold);
int prcmu_config_hotmon(u8 low, u8 high);
int prcmu_start_temp_sense(u16 cycles32k);
@@ -732,14 +524,36 @@
void prcmu_ac_wake_req(void);
void prcmu_ac_sleep_req(void);
-void prcmu_system_reset(u16 reset_code);
void prcmu_modem_reset(void);
-bool prcmu_is_ac_wake_requested(void);
void prcmu_enable_spi2(void);
void prcmu_disable_spi2(void);
+int prcmu_config_a9wdog(u8 num, bool sleep_auto_off);
+int prcmu_enable_a9wdog(u8 id);
+int prcmu_disable_a9wdog(u8 id);
+int prcmu_kick_a9wdog(u8 id);
+int prcmu_load_a9wdog(u8 id, u32 val);
+
+void db8500_prcmu_system_reset(u16 reset_code);
+int db8500_prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll);
+void db8500_prcmu_enable_wakeups(u32 wakeups);
+int db8500_prcmu_set_epod(u16 epod_id, u8 epod_state);
+int db8500_prcmu_request_clock(u8 clock, bool enable);
+int db8500_prcmu_set_display_clocks(void);
+int db8500_prcmu_disable_dsipll(void);
+int db8500_prcmu_enable_dsipll(void);
+void db8500_prcmu_config_abb_event_readout(u32 abb_events);
+void db8500_prcmu_get_abb_event_buffer(void __iomem **buf);
+int db8500_prcmu_config_esram0_deep_sleep(u8 state);
+u16 db8500_prcmu_get_reset_code(void);
+bool db8500_prcmu_is_ac_wake_requested(void);
+int db8500_prcmu_set_arm_opp(u8 opp);
+int db8500_prcmu_get_arm_opp(void);
+
#else /* !CONFIG_MFD_DB8500_PRCMU */
+static inline void db8500_prcmu_early_init(void) {}
+
static inline int prcmu_set_rc_a2p(enum romcode_write code)
{
return 0;
@@ -755,34 +569,12 @@
return AP_EXECUTE;
}
-static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk,
- bool keep_ap_pll)
-{
- return 0;
-}
-
-static inline void prcmu_enable_wakeups(u32 wakeups) {}
-
-static inline void prcmu_disable_wakeups(void) {}
-
-static inline void prcmu_config_abb_event_readout(u32 abb_events) {}
-
-static inline int prcmu_set_arm_opp(u8 opp)
-{
- return 0;
-}
-
-static inline int prcmu_get_arm_opp(void)
-{
- return ARM_100_OPP;
-}
-
-static bool prcmu_has_arm_maxopp(void)
+static inline bool prcmu_has_arm_maxopp(void)
{
return false;
}
-static bool prcmu_is_u8400(void)
+static inline bool prcmu_is_u8400(void)
{
return false;
}
@@ -817,13 +609,6 @@
return DDR_100_OPP;
}
-static inline unsigned long prcmu_qos_get_cpufreq_opp_delay(void)
-{
- return 0;
-}
-
-static inline void prcmu_qos_set_cpufreq_opp_delay(unsigned long n) {}
-
static inline int prcmu_set_hwacc(u16 hw_acc_dev, u8 state)
{
return 0;
@@ -844,21 +629,11 @@
return 0;
}
-static inline int prcmu_request_clock(u8 clock, bool enable)
-{
- return 0;
-}
-
static inline int prcmu_set_clock_divider(u8 clock, u8 divider)
{
return 0;
}
-int prcmu_config_esram0_deep_sleep(u8 state)
-{
- return 0;
-}
-
static inline int prcmu_config_hotdog(u8 threshold)
{
return 0;
@@ -893,32 +668,8 @@
static inline void prcmu_ac_sleep_req(void) {}
-static inline void prcmu_system_reset(u16 reset_code) {}
-
static inline void prcmu_modem_reset(void) {}
-static inline bool prcmu_is_ac_wake_requested(void)
-{
- return false;
-}
-
-#ifndef CONFIG_UX500_SOC_DB5500
-static inline int prcmu_set_display_clocks(void)
-{
- return 0;
-}
-
-static inline int prcmu_disable_dsipll(void)
-{
- return 0;
-}
-
-static inline int prcmu_enable_dsipll(void)
-{
- return 0;
-}
-#endif
-
static inline int prcmu_enable_spi2(void)
{
return 0;
@@ -929,50 +680,95 @@
return 0;
}
+static inline void db8500_prcmu_system_reset(u16 reset_code) {}
+
+static inline int db8500_prcmu_set_power_state(u8 state, bool keep_ulp_clk,
+ bool keep_ap_pll)
+{
+ return 0;
+}
+
+static inline void db8500_prcmu_enable_wakeups(u32 wakeups) {}
+
+static inline int db8500_prcmu_set_epod(u16 epod_id, u8 epod_state)
+{
+ return 0;
+}
+
+static inline int db8500_prcmu_request_clock(u8 clock, bool enable)
+{
+ return 0;
+}
+
+static inline int db8500_prcmu_set_display_clocks(void)
+{
+ return 0;
+}
+
+static inline int db8500_prcmu_disable_dsipll(void)
+{
+ return 0;
+}
+
+static inline int db8500_prcmu_enable_dsipll(void)
+{
+ return 0;
+}
+
+static inline int db8500_prcmu_config_esram0_deep_sleep(u8 state)
+{
+ return 0;
+}
+
+static inline void db8500_prcmu_config_abb_event_readout(u32 abb_events) {}
+
+static inline void db8500_prcmu_get_abb_event_buffer(void __iomem **buf) {}
+
+static inline u16 db8500_prcmu_get_reset_code(void)
+{
+ return 0;
+}
+
+static inline int prcmu_config_a9wdog(u8 num, bool sleep_auto_off)
+{
+ return 0;
+}
+
+static inline int prcmu_enable_a9wdog(u8 id)
+{
+ return 0;
+}
+
+static inline int prcmu_disable_a9wdog(u8 id)
+{
+ return 0;
+}
+
+static inline int prcmu_kick_a9wdog(u8 id)
+{
+ return 0;
+}
+
+static inline int prcmu_load_a9wdog(u8 id, u32 val)
+{
+ return 0;
+}
+
+static inline bool db8500_prcmu_is_ac_wake_requested(void)
+{
+ return 0;
+}
+
+static inline int db8500_prcmu_set_arm_opp(u8 opp)
+{
+ return 0;
+}
+
+static inline int db8500_prcmu_get_arm_opp(void)
+{
+ return 0;
+}
+
#endif /* !CONFIG_MFD_DB8500_PRCMU */
-#ifdef CONFIG_UX500_PRCMU_QOS_POWER
-int prcmu_qos_requirement(int pm_qos_class);
-int prcmu_qos_add_requirement(int pm_qos_class, char *name, s32 value);
-int prcmu_qos_update_requirement(int pm_qos_class, char *name, s32 new_value);
-void prcmu_qos_remove_requirement(int pm_qos_class, char *name);
-int prcmu_qos_add_notifier(int prcmu_qos_class,
- struct notifier_block *notifier);
-int prcmu_qos_remove_notifier(int prcmu_qos_class,
- struct notifier_block *notifier);
-#else
-static inline int prcmu_qos_requirement(int prcmu_qos_class)
-{
- return 0;
-}
-
-static inline int prcmu_qos_add_requirement(int prcmu_qos_class,
- char *name, s32 value)
-{
- return 0;
-}
-
-static inline int prcmu_qos_update_requirement(int prcmu_qos_class,
- char *name, s32 new_value)
-{
- return 0;
-}
-
-static inline void prcmu_qos_remove_requirement(int prcmu_qos_class, char *name)
-{
-}
-
-static inline int prcmu_qos_add_notifier(int prcmu_qos_class,
- struct notifier_block *notifier)
-{
- return 0;
-}
-static inline int prcmu_qos_remove_notifier(int prcmu_qos_class,
- struct notifier_block *notifier)
-{
- return 0;
-}
-
-#endif
-
#endif /* __MFD_DB8500_PRCMU_H */
diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h
new file mode 100644
index 0000000..bac942f
--- /dev/null
+++ b/include/linux/mfd/dbx500-prcmu.h
@@ -0,0 +1,549 @@
+/*
+ * Copyright (C) ST Ericsson SA 2011
+ *
+ * License Terms: GNU General Public License v2
+ *
+ * STE Ux500 PRCMU API
+ */
+#ifndef __MACH_PRCMU_H
+#define __MACH_PRCMU_H
+
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <asm/mach-types.h>
+
+/* PRCMU Wakeup defines */
+enum prcmu_wakeup_index {
+ PRCMU_WAKEUP_INDEX_RTC,
+ PRCMU_WAKEUP_INDEX_RTT0,
+ PRCMU_WAKEUP_INDEX_RTT1,
+ PRCMU_WAKEUP_INDEX_HSI0,
+ PRCMU_WAKEUP_INDEX_HSI1,
+ PRCMU_WAKEUP_INDEX_USB,
+ PRCMU_WAKEUP_INDEX_ABB,
+ PRCMU_WAKEUP_INDEX_ABB_FIFO,
+ PRCMU_WAKEUP_INDEX_ARM,
+ PRCMU_WAKEUP_INDEX_CD_IRQ,
+ NUM_PRCMU_WAKEUP_INDICES
+};
+#define PRCMU_WAKEUP(_name) (BIT(PRCMU_WAKEUP_INDEX_##_name))
+
+/* EPOD (power domain) IDs */
+
+/*
+ * DB8500 EPODs
+ * - EPOD_ID_SVAMMDSP: power domain for SVA MMDSP
+ * - EPOD_ID_SVAPIPE: power domain for SVA pipe
+ * - EPOD_ID_SIAMMDSP: power domain for SIA MMDSP
+ * - EPOD_ID_SIAPIPE: power domain for SIA pipe
+ * - EPOD_ID_SGA: power domain for SGA
+ * - EPOD_ID_B2R2_MCDE: power domain for B2R2 and MCDE
+ * - EPOD_ID_ESRAM12: power domain for ESRAM 1 and 2
+ * - EPOD_ID_ESRAM34: power domain for ESRAM 3 and 4
+ * - NUM_EPOD_ID: number of power domains
+ *
+ * TODO: These should be prefixed.
+ */
+#define EPOD_ID_SVAMMDSP 0
+#define EPOD_ID_SVAPIPE 1
+#define EPOD_ID_SIAMMDSP 2
+#define EPOD_ID_SIAPIPE 3
+#define EPOD_ID_SGA 4
+#define EPOD_ID_B2R2_MCDE 5
+#define EPOD_ID_ESRAM12 6
+#define EPOD_ID_ESRAM34 7
+#define NUM_EPOD_ID 8
+
+/*
+ * DB5500 EPODs
+ */
+#define DB5500_EPOD_ID_BASE 0x0100
+#define DB5500_EPOD_ID_SGA (DB5500_EPOD_ID_BASE + 0)
+#define DB5500_EPOD_ID_HVA (DB5500_EPOD_ID_BASE + 1)
+#define DB5500_EPOD_ID_SIA (DB5500_EPOD_ID_BASE + 2)
+#define DB5500_EPOD_ID_DISP (DB5500_EPOD_ID_BASE + 3)
+#define DB5500_EPOD_ID_ESRAM12 (DB5500_EPOD_ID_BASE + 6)
+#define DB5500_NUM_EPOD_ID 7
+
+/*
+ * state definition for EPOD (power domain)
+ * - EPOD_STATE_NO_CHANGE: The EPOD should remain unchanged
+ * - EPOD_STATE_OFF: The EPOD is switched off
+ * - EPOD_STATE_RAMRET: The EPOD is switched off with its internal RAM in
+ * retention
+ * - EPOD_STATE_ON_CLK_OFF: The EPOD is switched on, clock is still off
+ * - EPOD_STATE_ON: Same as above, but with clock enabled
+ */
+#define EPOD_STATE_NO_CHANGE 0x00
+#define EPOD_STATE_OFF 0x01
+#define EPOD_STATE_RAMRET 0x02
+#define EPOD_STATE_ON_CLK_OFF 0x03
+#define EPOD_STATE_ON 0x04
+
+/*
+ * CLKOUT sources
+ */
+#define PRCMU_CLKSRC_CLK38M 0x00
+#define PRCMU_CLKSRC_ACLK 0x01
+#define PRCMU_CLKSRC_SYSCLK 0x02
+#define PRCMU_CLKSRC_LCDCLK 0x03
+#define PRCMU_CLKSRC_SDMMCCLK 0x04
+#define PRCMU_CLKSRC_TVCLK 0x05
+#define PRCMU_CLKSRC_TIMCLK 0x06
+#define PRCMU_CLKSRC_CLK009 0x07
+/* These are only valid for CLKOUT1: */
+#define PRCMU_CLKSRC_SIAMMDSPCLK 0x40
+#define PRCMU_CLKSRC_I2CCLK 0x41
+#define PRCMU_CLKSRC_MSP02CLK 0x42
+#define PRCMU_CLKSRC_ARMPLL_OBSCLK 0x43
+#define PRCMU_CLKSRC_HSIRXCLK 0x44
+#define PRCMU_CLKSRC_HSITXCLK 0x45
+#define PRCMU_CLKSRC_ARMCLKFIX 0x46
+#define PRCMU_CLKSRC_HDMICLK 0x47
+
+/*
+ * Clock identifiers.
+ */
+enum prcmu_clock {
+ PRCMU_SGACLK,
+ PRCMU_UARTCLK,
+ PRCMU_MSP02CLK,
+ PRCMU_MSP1CLK,
+ PRCMU_I2CCLK,
+ PRCMU_SDMMCCLK,
+ PRCMU_SLIMCLK,
+ PRCMU_PER1CLK,
+ PRCMU_PER2CLK,
+ PRCMU_PER3CLK,
+ PRCMU_PER5CLK,
+ PRCMU_PER6CLK,
+ PRCMU_PER7CLK,
+ PRCMU_LCDCLK,
+ PRCMU_BMLCLK,
+ PRCMU_HSITXCLK,
+ PRCMU_HSIRXCLK,
+ PRCMU_HDMICLK,
+ PRCMU_APEATCLK,
+ PRCMU_APETRACECLK,
+ PRCMU_MCDECLK,
+ PRCMU_IPI2CCLK,
+ PRCMU_DSIALTCLK,
+ PRCMU_DMACLK,
+ PRCMU_B2R2CLK,
+ PRCMU_TVCLK,
+ PRCMU_SSPCLK,
+ PRCMU_RNGCLK,
+ PRCMU_UICCCLK,
+ PRCMU_PWMCLK,
+ PRCMU_IRDACLK,
+ PRCMU_IRRCCLK,
+ PRCMU_SIACLK,
+ PRCMU_SVACLK,
+ PRCMU_NUM_REG_CLOCKS,
+ PRCMU_SYSCLK = PRCMU_NUM_REG_CLOCKS,
+ PRCMU_TIMCLK,
+ PRCMU_PLLSOC0,
+ PRCMU_PLLSOC1,
+ PRCMU_PLLDDR,
+};
+
+/**
+ * enum ape_opp - APE OPP states definition
+ * @APE_OPP_INIT:
+ * @APE_NO_CHANGE: The APE operating point is unchanged
+ * @APE_100_OPP: The new APE operating point is ape100opp
+ * @APE_50_OPP: 50%
+ */
+enum ape_opp {
+ APE_OPP_INIT = 0x00,
+ APE_NO_CHANGE = 0x01,
+ APE_100_OPP = 0x02,
+ APE_50_OPP = 0x03
+};
+
+/**
+ * enum arm_opp - ARM OPP states definition
+ * @ARM_OPP_INIT:
+ * @ARM_NO_CHANGE: The ARM operating point is unchanged
+ * @ARM_100_OPP: The new ARM operating point is arm100opp
+ * @ARM_50_OPP: The new ARM operating point is arm50opp
+ * @ARM_MAX_OPP: Operating point is "max" (more than 100)
+ * @ARM_MAX_FREQ100OPP: Set max opp if available, else 100
+ * @ARM_EXTCLK: The new ARM operating point is armExtClk
+ */
+enum arm_opp {
+ ARM_OPP_INIT = 0x00,
+ ARM_NO_CHANGE = 0x01,
+ ARM_100_OPP = 0x02,
+ ARM_50_OPP = 0x03,
+ ARM_MAX_OPP = 0x04,
+ ARM_MAX_FREQ100OPP = 0x05,
+ ARM_EXTCLK = 0x07
+};
+
+/**
+ * enum ddr_opp - DDR OPP states definition
+ * @DDR_100_OPP: The new DDR operating point is ddr100opp
+ * @DDR_50_OPP: The new DDR operating point is ddr50opp
+ * @DDR_25_OPP: The new DDR operating point is ddr25opp
+ */
+enum ddr_opp {
+ DDR_100_OPP = 0x00,
+ DDR_50_OPP = 0x01,
+ DDR_25_OPP = 0x02,
+};
+
+/*
+ * Definitions for controlling ESRAM0 in deep sleep.
+ */
+#define ESRAM0_DEEP_SLEEP_STATE_OFF 1
+#define ESRAM0_DEEP_SLEEP_STATE_RET 2
+
+/**
+ * enum ddr_pwrst - DDR power states definition
+ * @DDR_PWR_STATE_UNCHANGED: SDRAM and DDR controller state is unchanged
+ * @DDR_PWR_STATE_ON:
+ * @DDR_PWR_STATE_OFFLOWLAT:
+ * @DDR_PWR_STATE_OFFHIGHLAT:
+ */
+enum ddr_pwrst {
+ DDR_PWR_STATE_UNCHANGED = 0x00,
+ DDR_PWR_STATE_ON = 0x01,
+ DDR_PWR_STATE_OFFLOWLAT = 0x02,
+ DDR_PWR_STATE_OFFHIGHLAT = 0x03
+};
+
+#include <linux/mfd/db8500-prcmu.h>
+#include <linux/mfd/db5500-prcmu.h>
+
+#if defined(CONFIG_UX500_SOC_DB8500) || defined(CONFIG_UX500_SOC_DB5500)
+
+static inline void __init prcmu_early_init(void)
+{
+ if (machine_is_u5500())
+ return db5500_prcmu_early_init();
+ else
+ return db8500_prcmu_early_init();
+}
+
+static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk,
+ bool keep_ap_pll)
+{
+ if (machine_is_u5500())
+ return db5500_prcmu_set_power_state(state, keep_ulp_clk,
+ keep_ap_pll);
+ else
+ return db8500_prcmu_set_power_state(state, keep_ulp_clk,
+ keep_ap_pll);
+}
+
+static inline int prcmu_set_epod(u16 epod_id, u8 epod_state)
+{
+ if (machine_is_u5500())
+ return -EINVAL;
+ else
+ return db8500_prcmu_set_epod(epod_id, epod_state);
+}
+
+static inline void prcmu_enable_wakeups(u32 wakeups)
+{
+ if (machine_is_u5500())
+ db5500_prcmu_enable_wakeups(wakeups);
+ else
+ db8500_prcmu_enable_wakeups(wakeups);
+}
+
+static inline void prcmu_disable_wakeups(void)
+{
+ prcmu_enable_wakeups(0);
+}
+
+static inline void prcmu_config_abb_event_readout(u32 abb_events)
+{
+ if (machine_is_u5500())
+ db5500_prcmu_config_abb_event_readout(abb_events);
+ else
+ db8500_prcmu_config_abb_event_readout(abb_events);
+}
+
+static inline void prcmu_get_abb_event_buffer(void __iomem **buf)
+{
+ if (machine_is_u5500())
+ db5500_prcmu_get_abb_event_buffer(buf);
+ else
+ db8500_prcmu_get_abb_event_buffer(buf);
+}
+
+int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size);
+int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size);
+
+int prcmu_config_clkout(u8 clkout, u8 source, u8 div);
+
+static inline int prcmu_request_clock(u8 clock, bool enable)
+{
+ if (machine_is_u5500())
+ return db5500_prcmu_request_clock(clock, enable);
+ else
+ return db8500_prcmu_request_clock(clock, enable);
+}
+
+int prcmu_set_ape_opp(u8 opp);
+int prcmu_get_ape_opp(void);
+int prcmu_set_ddr_opp(u8 opp);
+int prcmu_get_ddr_opp(void);
+
+static inline int prcmu_set_arm_opp(u8 opp)
+{
+ if (machine_is_u5500())
+ return -EINVAL;
+ else
+ return db8500_prcmu_set_arm_opp(opp);
+}
+
+static inline int prcmu_get_arm_opp(void)
+{
+ if (machine_is_u5500())
+ return -EINVAL;
+ else
+ return db8500_prcmu_get_arm_opp();
+}
+
+static inline void prcmu_system_reset(u16 reset_code)
+{
+ if (machine_is_u5500())
+ return db5500_prcmu_system_reset(reset_code);
+ else
+ return db8500_prcmu_system_reset(reset_code);
+}
+
+static inline u16 prcmu_get_reset_code(void)
+{
+ if (machine_is_u5500())
+ return db5500_prcmu_get_reset_code();
+ else
+ return db8500_prcmu_get_reset_code();
+}
+
+void prcmu_ac_wake_req(void);
+void prcmu_ac_sleep_req(void);
+void prcmu_modem_reset(void);
+static inline bool prcmu_is_ac_wake_requested(void)
+{
+ if (machine_is_u5500())
+ return db5500_prcmu_is_ac_wake_requested();
+ else
+ return db8500_prcmu_is_ac_wake_requested();
+}
+
+static inline int prcmu_set_display_clocks(void)
+{
+ if (machine_is_u5500())
+ return db5500_prcmu_set_display_clocks();
+ else
+ return db8500_prcmu_set_display_clocks();
+}
+
+static inline int prcmu_disable_dsipll(void)
+{
+ if (machine_is_u5500())
+ return db5500_prcmu_disable_dsipll();
+ else
+ return db8500_prcmu_disable_dsipll();
+}
+
+static inline int prcmu_enable_dsipll(void)
+{
+ if (machine_is_u5500())
+ return db5500_prcmu_enable_dsipll();
+ else
+ return db8500_prcmu_enable_dsipll();
+}
+
+static inline int prcmu_config_esram0_deep_sleep(u8 state)
+{
+ if (machine_is_u5500())
+ return -EINVAL;
+ else
+ return db8500_prcmu_config_esram0_deep_sleep(state);
+}
+#else
+
+static inline void __init prcmu_early_init(void) {}
+
+static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk,
+ bool keep_ap_pll)
+{
+ return 0;
+}
+
+static inline int prcmu_set_epod(u16 epod_id, u8 epod_state)
+{
+ return 0;
+}
+
+static inline void prcmu_enable_wakeups(u32 wakeups) {}
+
+static inline void prcmu_disable_wakeups(void) {}
+
+static inline int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
+{
+ return -ENOSYS;
+}
+
+static inline int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
+{
+ return -ENOSYS;
+}
+
+static inline int prcmu_config_clkout(u8 clkout, u8 source, u8 div)
+{
+ return 0;
+}
+
+static inline int prcmu_request_clock(u8 clock, bool enable)
+{
+ return 0;
+}
+
+static inline int prcmu_set_ape_opp(u8 opp)
+{
+ return 0;
+}
+
+static inline int prcmu_get_ape_opp(void)
+{
+ return APE_100_OPP;
+}
+
+static inline int prcmu_set_arm_opp(u8 opp)
+{
+ return 0;
+}
+
+static inline int prcmu_get_arm_opp(void)
+{
+ return ARM_100_OPP;
+}
+
+static inline int prcmu_set_ddr_opp(u8 opp)
+{
+ return 0;
+}
+
+static inline int prcmu_get_ddr_opp(void)
+{
+ return DDR_100_OPP;
+}
+
+static inline void prcmu_system_reset(u16 reset_code) {}
+
+static inline u16 prcmu_get_reset_code(void)
+{
+ return 0;
+}
+
+static inline void prcmu_ac_wake_req(void) {}
+
+static inline void prcmu_ac_sleep_req(void) {}
+
+static inline void prcmu_modem_reset(void) {}
+
+static inline bool prcmu_is_ac_wake_requested(void)
+{
+ return false;
+}
+
+static inline int prcmu_set_display_clocks(void)
+{
+ return 0;
+}
+
+static inline int prcmu_disable_dsipll(void)
+{
+ return 0;
+}
+
+static inline int prcmu_enable_dsipll(void)
+{
+ return 0;
+}
+
+static inline int prcmu_config_esram0_deep_sleep(u8 state)
+{
+ return 0;
+}
+
+static inline void prcmu_config_abb_event_readout(u32 abb_events) {}
+
+static inline void prcmu_get_abb_event_buffer(void __iomem **buf)
+{
+ *buf = NULL;
+}
+
+#endif
+
+/* PRCMU QoS APE OPP class */
+#define PRCMU_QOS_APE_OPP 1
+#define PRCMU_QOS_DDR_OPP 2
+#define PRCMU_QOS_DEFAULT_VALUE -1
+
+#ifdef CONFIG_UX500_PRCMU_QOS_POWER
+
+unsigned long prcmu_qos_get_cpufreq_opp_delay(void);
+void prcmu_qos_set_cpufreq_opp_delay(unsigned long);
+void prcmu_qos_force_opp(int, s32);
+int prcmu_qos_requirement(int pm_qos_class);
+int prcmu_qos_add_requirement(int pm_qos_class, char *name, s32 value);
+int prcmu_qos_update_requirement(int pm_qos_class, char *name, s32 new_value);
+void prcmu_qos_remove_requirement(int pm_qos_class, char *name);
+int prcmu_qos_add_notifier(int prcmu_qos_class,
+ struct notifier_block *notifier);
+int prcmu_qos_remove_notifier(int prcmu_qos_class,
+ struct notifier_block *notifier);
+
+#else
+
+static inline unsigned long prcmu_qos_get_cpufreq_opp_delay(void)
+{
+ return 0;
+}
+
+static inline void prcmu_qos_set_cpufreq_opp_delay(unsigned long n) {}
+
+static inline void prcmu_qos_force_opp(int prcmu_qos_class, s32 i) {}
+
+static inline int prcmu_qos_requirement(int prcmu_qos_class)
+{
+ return 0;
+}
+
+static inline int prcmu_qos_add_requirement(int prcmu_qos_class,
+ char *name, s32 value)
+{
+ return 0;
+}
+
+static inline int prcmu_qos_update_requirement(int prcmu_qos_class,
+ char *name, s32 new_value)
+{
+ return 0;
+}
+
+static inline void prcmu_qos_remove_requirement(int prcmu_qos_class, char *name)
+{
+}
+
+static inline int prcmu_qos_add_notifier(int prcmu_qos_class,
+ struct notifier_block *notifier)
+{
+ return 0;
+}
+static inline int prcmu_qos_remove_notifier(int prcmu_qos_class,
+ struct notifier_block *notifier)
+{
+ return 0;
+}
+
+#endif
+
+#endif /* __MACH_PRCMU_H */
diff --git a/include/linux/mfd/intel_msic.h b/include/linux/mfd/intel_msic.h
new file mode 100644
index 0000000..439a7a6
--- /dev/null
+++ b/include/linux/mfd/intel_msic.h
@@ -0,0 +1,456 @@
+/*
+ * include/linux/mfd/intel_msic.h - Core interface for Intel MSIC
+ *
+ * Copyright (C) 2011, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_MFD_INTEL_MSIC_H__
+#define __LINUX_MFD_INTEL_MSIC_H__
+
+/* ID */
+#define INTEL_MSIC_ID0 0x000 /* RO */
+#define INTEL_MSIC_ID1 0x001 /* RO */
+
+/* IRQ */
+#define INTEL_MSIC_IRQLVL1 0x002
+#define INTEL_MSIC_ADC1INT 0x003
+#define INTEL_MSIC_CCINT 0x004
+#define INTEL_MSIC_PWRSRCINT 0x005
+#define INTEL_MSIC_PWRSRCINT1 0x006
+#define INTEL_MSIC_CHRINT 0x007
+#define INTEL_MSIC_CHRINT1 0x008
+#define INTEL_MSIC_RTCIRQ 0x009
+#define INTEL_MSIC_GPIO0LVIRQ 0x00a
+#define INTEL_MSIC_GPIO1LVIRQ 0x00b
+#define INTEL_MSIC_GPIOHVIRQ 0x00c
+#define INTEL_MSIC_VRINT 0x00d
+#define INTEL_MSIC_OCAUDIO 0x00e
+#define INTEL_MSIC_ACCDET 0x00f
+#define INTEL_MSIC_RESETIRQ1 0x010
+#define INTEL_MSIC_RESETIRQ2 0x011
+#define INTEL_MSIC_MADC1INT 0x012
+#define INTEL_MSIC_MCCINT 0x013
+#define INTEL_MSIC_MPWRSRCINT 0x014
+#define INTEL_MSIC_MPWRSRCINT1 0x015
+#define INTEL_MSIC_MCHRINT 0x016
+#define INTEL_MSIC_MCHRINT1 0x017
+#define INTEL_MSIC_RTCIRQMASK 0x018
+#define INTEL_MSIC_GPIO0LVIRQMASK 0x019
+#define INTEL_MSIC_GPIO1LVIRQMASK 0x01a
+#define INTEL_MSIC_GPIOHVIRQMASK 0x01b
+#define INTEL_MSIC_VRINTMASK 0x01c
+#define INTEL_MSIC_OCAUDIOMASK 0x01d
+#define INTEL_MSIC_ACCDETMASK 0x01e
+#define INTEL_MSIC_RESETIRQ1MASK 0x01f
+#define INTEL_MSIC_RESETIRQ2MASK 0x020
+#define INTEL_MSIC_IRQLVL1MSK 0x021
+#define INTEL_MSIC_PBCONFIG 0x03e
+#define INTEL_MSIC_PBSTATUS 0x03f /* RO */
+
+/* GPIO */
+#define INTEL_MSIC_GPIO0LV7CTLO 0x040
+#define INTEL_MSIC_GPIO0LV6CTLO 0x041
+#define INTEL_MSIC_GPIO0LV5CTLO 0x042
+#define INTEL_MSIC_GPIO0LV4CTLO 0x043
+#define INTEL_MSIC_GPIO0LV3CTLO 0x044
+#define INTEL_MSIC_GPIO0LV2CTLO 0x045
+#define INTEL_MSIC_GPIO0LV1CTLO 0x046
+#define INTEL_MSIC_GPIO0LV0CTLO 0x047
+#define INTEL_MSIC_GPIO1LV7CTLOS 0x048
+#define INTEL_MSIC_GPIO1LV6CTLO 0x049
+#define INTEL_MSIC_GPIO1LV5CTLO 0x04a
+#define INTEL_MSIC_GPIO1LV4CTLO 0x04b
+#define INTEL_MSIC_GPIO1LV3CTLO 0x04c
+#define INTEL_MSIC_GPIO1LV2CTLO 0x04d
+#define INTEL_MSIC_GPIO1LV1CTLO 0x04e
+#define INTEL_MSIC_GPIO1LV0CTLO 0x04f
+#define INTEL_MSIC_GPIO0LV7CTLI 0x050
+#define INTEL_MSIC_GPIO0LV6CTLI 0x051
+#define INTEL_MSIC_GPIO0LV5CTLI 0x052
+#define INTEL_MSIC_GPIO0LV4CTLI 0x053
+#define INTEL_MSIC_GPIO0LV3CTLI 0x054
+#define INTEL_MSIC_GPIO0LV2CTLI 0x055
+#define INTEL_MSIC_GPIO0LV1CTLI 0x056
+#define INTEL_MSIC_GPIO0LV0CTLI 0x057
+#define INTEL_MSIC_GPIO1LV7CTLIS 0x058
+#define INTEL_MSIC_GPIO1LV6CTLI 0x059
+#define INTEL_MSIC_GPIO1LV5CTLI 0x05a
+#define INTEL_MSIC_GPIO1LV4CTLI 0x05b
+#define INTEL_MSIC_GPIO1LV3CTLI 0x05c
+#define INTEL_MSIC_GPIO1LV2CTLI 0x05d
+#define INTEL_MSIC_GPIO1LV1CTLI 0x05e
+#define INTEL_MSIC_GPIO1LV0CTLI 0x05f
+#define INTEL_MSIC_PWM0CLKDIV1 0x061
+#define INTEL_MSIC_PWM0CLKDIV0 0x062
+#define INTEL_MSIC_PWM1CLKDIV1 0x063
+#define INTEL_MSIC_PWM1CLKDIV0 0x064
+#define INTEL_MSIC_PWM2CLKDIV1 0x065
+#define INTEL_MSIC_PWM2CLKDIV0 0x066
+#define INTEL_MSIC_PWM0DUTYCYCLE 0x067
+#define INTEL_MSIC_PWM1DUTYCYCLE 0x068
+#define INTEL_MSIC_PWM2DUTYCYCLE 0x069
+#define INTEL_MSIC_GPIO0HV3CTLO 0x06d
+#define INTEL_MSIC_GPIO0HV2CTLO 0x06e
+#define INTEL_MSIC_GPIO0HV1CTLO 0x06f
+#define INTEL_MSIC_GPIO0HV0CTLO 0x070
+#define INTEL_MSIC_GPIO1HV3CTLO 0x071
+#define INTEL_MSIC_GPIO1HV2CTLO 0x072
+#define INTEL_MSIC_GPIO1HV1CTLO 0x073
+#define INTEL_MSIC_GPIO1HV0CTLO 0x074
+#define INTEL_MSIC_GPIO0HV3CTLI 0x075
+#define INTEL_MSIC_GPIO0HV2CTLI 0x076
+#define INTEL_MSIC_GPIO0HV1CTLI 0x077
+#define INTEL_MSIC_GPIO0HV0CTLI 0x078
+#define INTEL_MSIC_GPIO1HV3CTLI 0x079
+#define INTEL_MSIC_GPIO1HV2CTLI 0x07a
+#define INTEL_MSIC_GPIO1HV1CTLI 0x07b
+#define INTEL_MSIC_GPIO1HV0CTLI 0x07c
+
+/* SVID */
+#define INTEL_MSIC_SVIDCTRL0 0x080
+#define INTEL_MSIC_SVIDCTRL1 0x081
+#define INTEL_MSIC_SVIDCTRL2 0x082
+#define INTEL_MSIC_SVIDTXLASTPKT3 0x083 /* RO */
+#define INTEL_MSIC_SVIDTXLASTPKT2 0x084 /* RO */
+#define INTEL_MSIC_SVIDTXLASTPKT1 0x085 /* RO */
+#define INTEL_MSIC_SVIDTXLASTPKT0 0x086 /* RO */
+#define INTEL_MSIC_SVIDPKTOUTBYTE3 0x087
+#define INTEL_MSIC_SVIDPKTOUTBYTE2 0x088
+#define INTEL_MSIC_SVIDPKTOUTBYTE1 0x089
+#define INTEL_MSIC_SVIDPKTOUTBYTE0 0x08a
+#define INTEL_MSIC_SVIDRXVPDEBUG1 0x08b
+#define INTEL_MSIC_SVIDRXVPDEBUG0 0x08c
+#define INTEL_MSIC_SVIDRXLASTPKT3 0x08d /* RO */
+#define INTEL_MSIC_SVIDRXLASTPKT2 0x08e /* RO */
+#define INTEL_MSIC_SVIDRXLASTPKT1 0x08f /* RO */
+#define INTEL_MSIC_SVIDRXLASTPKT0 0x090 /* RO */
+#define INTEL_MSIC_SVIDRXCHKSTATUS3 0x091 /* RO */
+#define INTEL_MSIC_SVIDRXCHKSTATUS2 0x092 /* RO */
+#define INTEL_MSIC_SVIDRXCHKSTATUS1 0x093 /* RO */
+#define INTEL_MSIC_SVIDRXCHKSTATUS0 0x094 /* RO */
+
+/* VREG */
+#define INTEL_MSIC_VCCLATCH 0x0c0
+#define INTEL_MSIC_VNNLATCH 0x0c1
+#define INTEL_MSIC_VCCCNT 0x0c2
+#define INTEL_MSIC_SMPSRAMP 0x0c3
+#define INTEL_MSIC_VNNCNT 0x0c4
+#define INTEL_MSIC_VNNAONCNT 0x0c5
+#define INTEL_MSIC_VCC122AONCNT 0x0c6
+#define INTEL_MSIC_V180AONCNT 0x0c7
+#define INTEL_MSIC_V500CNT 0x0c8
+#define INTEL_MSIC_VIHFCNT 0x0c9
+#define INTEL_MSIC_LDORAMP1 0x0ca
+#define INTEL_MSIC_LDORAMP2 0x0cb
+#define INTEL_MSIC_VCC108AONCNT 0x0cc
+#define INTEL_MSIC_VCC108ASCNT 0x0cd
+#define INTEL_MSIC_VCC108CNT 0x0ce
+#define INTEL_MSIC_VCCA100ASCNT 0x0cf
+#define INTEL_MSIC_VCCA100CNT 0x0d0
+#define INTEL_MSIC_VCC180AONCNT 0x0d1
+#define INTEL_MSIC_VCC180CNT 0x0d2
+#define INTEL_MSIC_VCC330CNT 0x0d3
+#define INTEL_MSIC_VUSB330CNT 0x0d4
+#define INTEL_MSIC_VCCSDIOCNT 0x0d5
+#define INTEL_MSIC_VPROG1CNT 0x0d6
+#define INTEL_MSIC_VPROG2CNT 0x0d7
+#define INTEL_MSIC_VEMMCSCNT 0x0d8
+#define INTEL_MSIC_VEMMC1CNT 0x0d9
+#define INTEL_MSIC_VEMMC2CNT 0x0da
+#define INTEL_MSIC_VAUDACNT 0x0db
+#define INTEL_MSIC_VHSPCNT 0x0dc
+#define INTEL_MSIC_VHSNCNT 0x0dd
+#define INTEL_MSIC_VHDMICNT 0x0de
+#define INTEL_MSIC_VOTGCNT 0x0df
+#define INTEL_MSIC_V1P35CNT 0x0e0
+#define INTEL_MSIC_V330AONCNT 0x0e1
+
+/* RESET */
+#define INTEL_MSIC_CHIPCNTRL 0x100 /* WO */
+#define INTEL_MSIC_ERCONFIG 0x101
+
+/* BURST */
+#define INTEL_MSIC_BATCURRENTLIMIT12 0x102
+#define INTEL_MSIC_BATTIMELIMIT12 0x103
+#define INTEL_MSIC_BATTIMELIMIT3 0x104
+#define INTEL_MSIC_BATTIMEDB 0x105
+#define INTEL_MSIC_BRSTCONFIGOUTPUTS 0x106
+#define INTEL_MSIC_BRSTCONFIGACTIONS 0x107
+#define INTEL_MSIC_BURSTCONTROLSTATUS 0x108
+
+/* RTC */
+#define INTEL_MSIC_RTCB1 0x140 /* RO */
+#define INTEL_MSIC_RTCB2 0x141 /* RO */
+#define INTEL_MSIC_RTCB3 0x142 /* RO */
+#define INTEL_MSIC_RTCB4 0x143 /* RO */
+#define INTEL_MSIC_RTCOB1 0x144
+#define INTEL_MSIC_RTCOB2 0x145
+#define INTEL_MSIC_RTCOB3 0x146
+#define INTEL_MSIC_RTCOB4 0x147
+#define INTEL_MSIC_RTCAB1 0x148
+#define INTEL_MSIC_RTCAB2 0x149
+#define INTEL_MSIC_RTCAB3 0x14a
+#define INTEL_MSIC_RTCAB4 0x14b
+#define INTEL_MSIC_RTCWAB1 0x14c
+#define INTEL_MSIC_RTCWAB2 0x14d
+#define INTEL_MSIC_RTCWAB3 0x14e
+#define INTEL_MSIC_RTCWAB4 0x14f
+#define INTEL_MSIC_RTCSC1 0x150
+#define INTEL_MSIC_RTCSC2 0x151
+#define INTEL_MSIC_RTCSC3 0x152
+#define INTEL_MSIC_RTCSC4 0x153
+#define INTEL_MSIC_RTCSTATUS 0x154 /* RO */
+#define INTEL_MSIC_RTCCONFIG1 0x155
+#define INTEL_MSIC_RTCCONFIG2 0x156
+
+/* CHARGER */
+#define INTEL_MSIC_BDTIMER 0x180
+#define INTEL_MSIC_BATTRMV 0x181
+#define INTEL_MSIC_VBUSDET 0x182
+#define INTEL_MSIC_VBUSDET1 0x183
+#define INTEL_MSIC_ADPHVDET 0x184
+#define INTEL_MSIC_ADPLVDET 0x185
+#define INTEL_MSIC_ADPDETDBDM 0x186
+#define INTEL_MSIC_LOWBATTDET 0x187
+#define INTEL_MSIC_CHRCTRL 0x188
+#define INTEL_MSIC_CHRCVOLTAGE 0x189
+#define INTEL_MSIC_CHRCCURRENT 0x18a
+#define INTEL_MSIC_SPCHARGER 0x18b
+#define INTEL_MSIC_CHRTTIME 0x18c
+#define INTEL_MSIC_CHRCTRL1 0x18d
+#define INTEL_MSIC_PWRSRCLMT 0x18e
+#define INTEL_MSIC_CHRSTWDT 0x18f
+#define INTEL_MSIC_WDTWRITE 0x190 /* WO */
+#define INTEL_MSIC_CHRSAFELMT 0x191
+#define INTEL_MSIC_SPWRSRCINT 0x192 /* RO */
+#define INTEL_MSIC_SPWRSRCINT1 0x193 /* RO */
+#define INTEL_MSIC_CHRLEDPWM 0x194
+#define INTEL_MSIC_CHRLEDCTRL 0x195
+
+/* ADC */
+#define INTEL_MSIC_ADC1CNTL1 0x1c0
+#define INTEL_MSIC_ADC1CNTL2 0x1c1
+#define INTEL_MSIC_ADC1CNTL3 0x1c2
+#define INTEL_MSIC_ADC1OFFSETH 0x1c3 /* RO */
+#define INTEL_MSIC_ADC1OFFSETL 0x1c4 /* RO */
+#define INTEL_MSIC_ADC1ADDR0 0x1c5
+#define INTEL_MSIC_ADC1ADDR1 0x1c6
+#define INTEL_MSIC_ADC1ADDR2 0x1c7
+#define INTEL_MSIC_ADC1ADDR3 0x1c8
+#define INTEL_MSIC_ADC1ADDR4 0x1c9
+#define INTEL_MSIC_ADC1ADDR5 0x1ca
+#define INTEL_MSIC_ADC1ADDR6 0x1cb
+#define INTEL_MSIC_ADC1ADDR7 0x1cc
+#define INTEL_MSIC_ADC1ADDR8 0x1cd
+#define INTEL_MSIC_ADC1ADDR9 0x1ce
+#define INTEL_MSIC_ADC1ADDR10 0x1cf
+#define INTEL_MSIC_ADC1ADDR11 0x1d0
+#define INTEL_MSIC_ADC1ADDR12 0x1d1
+#define INTEL_MSIC_ADC1ADDR13 0x1d2
+#define INTEL_MSIC_ADC1ADDR14 0x1d3
+#define INTEL_MSIC_ADC1SNS0H 0x1d4 /* RO */
+#define INTEL_MSIC_ADC1SNS0L 0x1d5 /* RO */
+#define INTEL_MSIC_ADC1SNS1H 0x1d6 /* RO */
+#define INTEL_MSIC_ADC1SNS1L 0x1d7 /* RO */
+#define INTEL_MSIC_ADC1SNS2H 0x1d8 /* RO */
+#define INTEL_MSIC_ADC1SNS2L 0x1d9 /* RO */
+#define INTEL_MSIC_ADC1SNS3H 0x1da /* RO */
+#define INTEL_MSIC_ADC1SNS3L 0x1db /* RO */
+#define INTEL_MSIC_ADC1SNS4H 0x1dc /* RO */
+#define INTEL_MSIC_ADC1SNS4L 0x1dd /* RO */
+#define INTEL_MSIC_ADC1SNS5H 0x1de /* RO */
+#define INTEL_MSIC_ADC1SNS5L 0x1df /* RO */
+#define INTEL_MSIC_ADC1SNS6H 0x1e0 /* RO */
+#define INTEL_MSIC_ADC1SNS6L 0x1e1 /* RO */
+#define INTEL_MSIC_ADC1SNS7H 0x1e2 /* RO */
+#define INTEL_MSIC_ADC1SNS7L 0x1e3 /* RO */
+#define INTEL_MSIC_ADC1SNS8H 0x1e4 /* RO */
+#define INTEL_MSIC_ADC1SNS8L 0x1e5 /* RO */
+#define INTEL_MSIC_ADC1SNS9H 0x1e6 /* RO */
+#define INTEL_MSIC_ADC1SNS9L 0x1e7 /* RO */
+#define INTEL_MSIC_ADC1SNS10H 0x1e8 /* RO */
+#define INTEL_MSIC_ADC1SNS10L 0x1e9 /* RO */
+#define INTEL_MSIC_ADC1SNS11H 0x1ea /* RO */
+#define INTEL_MSIC_ADC1SNS11L 0x1eb /* RO */
+#define INTEL_MSIC_ADC1SNS12H 0x1ec /* RO */
+#define INTEL_MSIC_ADC1SNS12L 0x1ed /* RO */
+#define INTEL_MSIC_ADC1SNS13H 0x1ee /* RO */
+#define INTEL_MSIC_ADC1SNS13L 0x1ef /* RO */
+#define INTEL_MSIC_ADC1SNS14H 0x1f0 /* RO */
+#define INTEL_MSIC_ADC1SNS14L 0x1f1 /* RO */
+#define INTEL_MSIC_ADC1BV0H 0x1f2 /* RO */
+#define INTEL_MSIC_ADC1BV0L 0x1f3 /* RO */
+#define INTEL_MSIC_ADC1BV1H 0x1f4 /* RO */
+#define INTEL_MSIC_ADC1BV1L 0x1f5 /* RO */
+#define INTEL_MSIC_ADC1BV2H 0x1f6 /* RO */
+#define INTEL_MSIC_ADC1BV2L 0x1f7 /* RO */
+#define INTEL_MSIC_ADC1BV3H 0x1f8 /* RO */
+#define INTEL_MSIC_ADC1BV3L 0x1f9 /* RO */
+#define INTEL_MSIC_ADC1BI0H 0x1fa /* RO */
+#define INTEL_MSIC_ADC1BI0L 0x1fb /* RO */
+#define INTEL_MSIC_ADC1BI1H 0x1fc /* RO */
+#define INTEL_MSIC_ADC1BI1L 0x1fd /* RO */
+#define INTEL_MSIC_ADC1BI2H 0x1fe /* RO */
+#define INTEL_MSIC_ADC1BI2L 0x1ff /* RO */
+#define INTEL_MSIC_ADC1BI3H 0x200 /* RO */
+#define INTEL_MSIC_ADC1BI3L 0x201 /* RO */
+#define INTEL_MSIC_CCCNTL 0x202
+#define INTEL_MSIC_CCOFFSETH 0x203 /* RO */
+#define INTEL_MSIC_CCOFFSETL 0x204 /* RO */
+#define INTEL_MSIC_CCADCHA 0x205 /* RO */
+#define INTEL_MSIC_CCADCLA 0x206 /* RO */
+
+/* AUDIO */
+#define INTEL_MSIC_AUDPLLCTRL 0x240
+#define INTEL_MSIC_DMICBUF0123 0x241
+#define INTEL_MSIC_DMICBUF45 0x242
+#define INTEL_MSIC_DMICGPO 0x244
+#define INTEL_MSIC_DMICMUX 0x245
+#define INTEL_MSIC_DMICCLK 0x246
+#define INTEL_MSIC_MICBIAS 0x247
+#define INTEL_MSIC_ADCCONFIG 0x248
+#define INTEL_MSIC_MICAMP1 0x249
+#define INTEL_MSIC_MICAMP2 0x24a
+#define INTEL_MSIC_NOISEMUX 0x24b
+#define INTEL_MSIC_AUDIOMUX12 0x24c
+#define INTEL_MSIC_AUDIOMUX34 0x24d
+#define INTEL_MSIC_AUDIOSINC 0x24e
+#define INTEL_MSIC_AUDIOTXEN 0x24f
+#define INTEL_MSIC_HSEPRXCTRL 0x250
+#define INTEL_MSIC_IHFRXCTRL 0x251
+#define INTEL_MSIC_VOICETXVOL 0x252
+#define INTEL_MSIC_SIDETONEVOL 0x253
+#define INTEL_MSIC_MUSICSHARVOL 0x254
+#define INTEL_MSIC_VOICETXCTRL 0x255
+#define INTEL_MSIC_HSMIXER 0x256
+#define INTEL_MSIC_DACCONFIG 0x257
+#define INTEL_MSIC_SOFTMUTE 0x258
+#define INTEL_MSIC_HSLVOLCTRL 0x259
+#define INTEL_MSIC_HSRVOLCTRL 0x25a
+#define INTEL_MSIC_IHFLVOLCTRL 0x25b
+#define INTEL_MSIC_IHFRVOLCTRL 0x25c
+#define INTEL_MSIC_DRIVEREN 0x25d
+#define INTEL_MSIC_LINEOUTCTRL 0x25e
+#define INTEL_MSIC_VIB1CTRL1 0x25f
+#define INTEL_MSIC_VIB1CTRL2 0x260
+#define INTEL_MSIC_VIB1CTRL3 0x261
+#define INTEL_MSIC_VIB1SPIPCM_1 0x262
+#define INTEL_MSIC_VIB1SPIPCM_2 0x263
+#define INTEL_MSIC_VIB1CTRL5 0x264
+#define INTEL_MSIC_VIB2CTRL1 0x265
+#define INTEL_MSIC_VIB2CTRL2 0x266
+#define INTEL_MSIC_VIB2CTRL3 0x267
+#define INTEL_MSIC_VIB2SPIPCM_1 0x268
+#define INTEL_MSIC_VIB2SPIPCM_2 0x269
+#define INTEL_MSIC_VIB2CTRL5 0x26a
+#define INTEL_MSIC_BTNCTRL1 0x26b
+#define INTEL_MSIC_BTNCTRL2 0x26c
+#define INTEL_MSIC_PCM1TXSLOT01 0x26d
+#define INTEL_MSIC_PCM1TXSLOT23 0x26e
+#define INTEL_MSIC_PCM1TXSLOT45 0x26f
+#define INTEL_MSIC_PCM1RXSLOT0123 0x270
+#define INTEL_MSIC_PCM1RXSLOT045 0x271
+#define INTEL_MSIC_PCM2TXSLOT01 0x272
+#define INTEL_MSIC_PCM2TXSLOT23 0x273
+#define INTEL_MSIC_PCM2TXSLOT45 0x274
+#define INTEL_MSIC_PCM2RXSLOT01 0x275
+#define INTEL_MSIC_PCM2RXSLOT23 0x276
+#define INTEL_MSIC_PCM2RXSLOT45 0x277
+#define INTEL_MSIC_PCM1CTRL1 0x278
+#define INTEL_MSIC_PCM1CTRL2 0x279
+#define INTEL_MSIC_PCM1CTRL3 0x27a
+#define INTEL_MSIC_PCM2CTRL1 0x27b
+#define INTEL_MSIC_PCM2CTRL2 0x27c
+
+/* HDMI */
+#define INTEL_MSIC_HDMIPUEN 0x280
+#define INTEL_MSIC_HDMISTATUS 0x281 /* RO */
+
+/* Physical address of the start of the MSIC interrupt tree in SRAM */
+#define INTEL_MSIC_IRQ_PHYS_BASE 0xffff7fc0
+
+/**
+ * struct intel_msic_gpio_pdata - platform data for the MSIC GPIO driver
+ * @gpio_base: base number for the GPIOs
+ */
+struct intel_msic_gpio_pdata {
+ unsigned gpio_base;
+};
+
+/**
+ * struct intel_msic_ocd_pdata - platform data for the MSIC OCD driver
+ * @gpio: GPIO number used for OCD interrupts
+ *
+ * The MSIC MFD driver converts @gpio into an IRQ number and passes it to
+ * the OCD driver as %IORESOURCE_IRQ.
+ */
+struct intel_msic_ocd_pdata {
+ unsigned gpio;
+};
+
+/* MSIC embedded blocks (subdevices) */
+enum intel_msic_block {
+ INTEL_MSIC_BLOCK_TOUCH,
+ INTEL_MSIC_BLOCK_ADC,
+ INTEL_MSIC_BLOCK_BATTERY,
+ INTEL_MSIC_BLOCK_GPIO,
+ INTEL_MSIC_BLOCK_AUDIO,
+ INTEL_MSIC_BLOCK_HDMI,
+ INTEL_MSIC_BLOCK_THERMAL,
+ INTEL_MSIC_BLOCK_POWER_BTN,
+ INTEL_MSIC_BLOCK_OCD,
+
+ INTEL_MSIC_BLOCK_LAST,
+};
+
+/**
+ * struct intel_msic_platform_data - platform data for the MSIC driver
+ * @irq: array of interrupt numbers, one per device. If @irq is set to %0
+ * for a given block, the corresponding platform device is not
+ * created. For devices which don't have an interrupt, use %0xff
+ * (this is same as in SFI spec).
+ * @gpio: platform data for the MSIC GPIO driver
+ * @ocd: platform data for the MSIC OCD driver
+ *
+ * Once the MSIC driver is initialized, the register interface is ready to
+ * use. All the platform devices for subdevices are created after the
+ * register interface is ready so that we can guarantee its availability to
+ * the subdevice drivers.
+ *
+ * Interrupt numbers are passed to the subdevices via %IORESOURCE_IRQ
+ * resources of the created platform device.
+ */
+struct intel_msic_platform_data {
+ int irq[INTEL_MSIC_BLOCK_LAST];
+ struct intel_msic_gpio_pdata *gpio;
+ struct intel_msic_ocd_pdata *ocd;
+};
+
+struct intel_msic;
+
+extern int intel_msic_reg_read(unsigned short reg, u8 *val);
+extern int intel_msic_reg_write(unsigned short reg, u8 val);
+extern int intel_msic_reg_update(unsigned short reg, u8 val, u8 mask);
+extern int intel_msic_bulk_read(unsigned short *reg, u8 *buf, size_t count);
+extern int intel_msic_bulk_write(unsigned short *reg, u8 *buf, size_t count);
+
+/*
+ * pdev_to_intel_msic - gets an MSIC instance from the platform device
+ * @pdev: platform device pointer
+ *
+ * The client drivers need to have pointer to the MSIC instance if they
+ * want to call intel_msic_irq_read(). This macro can be used for
+ * convenience to get the MSIC pointer from @pdev where needed. This is
+ * _only_ valid for devices which are managed by the MSIC.
+ */
+#define pdev_to_intel_msic(pdev) (dev_get_drvdata(pdev->dev.parent))
+
+extern int intel_msic_irq_read(struct intel_msic *msic, unsigned short reg,
+ u8 *val);
+
+#endif /* __LINUX_MFD_INTEL_MSIC_H__ */
diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h
index 5ff2400..3f4deb6 100644
--- a/include/linux/mfd/max8997-private.h
+++ b/include/linux/mfd/max8997-private.h
@@ -326,7 +326,6 @@
int irq;
int ono;
int irq_base;
- bool wakeup;
struct mutex irqlock;
int irq_masks_cur[MAX8997_IRQ_GROUP_NR];
int irq_masks_cache[MAX8997_IRQ_GROUP_NR];
diff --git a/include/linux/mfd/mc13783.h b/include/linux/mfd/mc13783.h
index 7d0f3d6..a8eeda7 100644
--- a/include/linux/mfd/mc13783.h
+++ b/include/linux/mfd/mc13783.h
@@ -12,117 +12,6 @@
#include <linux/mfd/mc13xxx.h>
-struct mc13783;
-
-struct mc13xxx *mc13783_to_mc13xxx(struct mc13783 *mc13783);
-
-static inline void mc13783_lock(struct mc13783 *mc13783)
-{
- mc13xxx_lock(mc13783_to_mc13xxx(mc13783));
-}
-
-static inline void mc13783_unlock(struct mc13783 *mc13783)
-{
- mc13xxx_unlock(mc13783_to_mc13xxx(mc13783));
-}
-
-static inline int mc13783_reg_read(struct mc13783 *mc13783,
- unsigned int offset, u32 *val)
-{
- return mc13xxx_reg_read(mc13783_to_mc13xxx(mc13783), offset, val);
-}
-
-static inline int mc13783_reg_write(struct mc13783 *mc13783,
- unsigned int offset, u32 val)
-{
- return mc13xxx_reg_write(mc13783_to_mc13xxx(mc13783), offset, val);
-}
-
-static inline int mc13783_reg_rmw(struct mc13783 *mc13783,
- unsigned int offset, u32 mask, u32 val)
-{
- return mc13xxx_reg_rmw(mc13783_to_mc13xxx(mc13783), offset, mask, val);
-}
-
-static inline int mc13783_get_flags(struct mc13783 *mc13783)
-{
- return mc13xxx_get_flags(mc13783_to_mc13xxx(mc13783));
-}
-
-static inline int mc13783_irq_request(struct mc13783 *mc13783, int irq,
- irq_handler_t handler, const char *name, void *dev)
-{
- return mc13xxx_irq_request(mc13783_to_mc13xxx(mc13783), irq,
- handler, name, dev);
-}
-
-static inline int mc13783_irq_request_nounmask(struct mc13783 *mc13783, int irq,
- irq_handler_t handler, const char *name, void *dev)
-{
- return mc13xxx_irq_request_nounmask(mc13783_to_mc13xxx(mc13783), irq,
- handler, name, dev);
-}
-
-static inline int mc13783_irq_free(struct mc13783 *mc13783, int irq, void *dev)
-{
- return mc13xxx_irq_free(mc13783_to_mc13xxx(mc13783), irq, dev);
-}
-
-static inline int mc13783_irq_mask(struct mc13783 *mc13783, int irq)
-{
- return mc13xxx_irq_mask(mc13783_to_mc13xxx(mc13783), irq);
-}
-
-static inline int mc13783_irq_unmask(struct mc13783 *mc13783, int irq)
-{
- return mc13xxx_irq_unmask(mc13783_to_mc13xxx(mc13783), irq);
-}
-static inline int mc13783_irq_status(struct mc13783 *mc13783, int irq,
- int *enabled, int *pending)
-{
- return mc13xxx_irq_status(mc13783_to_mc13xxx(mc13783),
- irq, enabled, pending);
-}
-
-static inline int mc13783_irq_ack(struct mc13783 *mc13783, int irq)
-{
- return mc13xxx_irq_ack(mc13783_to_mc13xxx(mc13783), irq);
-}
-
-#define MC13783_ADC0 43
-#define MC13783_ADC0_ADREFEN (1 << 10)
-#define MC13783_ADC0_ADREFMODE (1 << 11)
-#define MC13783_ADC0_TSMOD0 (1 << 12)
-#define MC13783_ADC0_TSMOD1 (1 << 13)
-#define MC13783_ADC0_TSMOD2 (1 << 14)
-#define MC13783_ADC0_ADINC1 (1 << 16)
-#define MC13783_ADC0_ADINC2 (1 << 17)
-
-#define MC13783_ADC0_TSMOD_MASK (MC13783_ADC0_TSMOD0 | \
- MC13783_ADC0_TSMOD1 | \
- MC13783_ADC0_TSMOD2)
-
-#define mc13783_regulator_init_data mc13xxx_regulator_init_data
-#define mc13783_regulator_platform_data mc13xxx_regulator_platform_data
-#define mc13783_led_platform_data mc13xxx_led_platform_data
-#define mc13783_leds_platform_data mc13xxx_leds_platform_data
-
-#define mc13783_platform_data mc13xxx_platform_data
-#define MC13783_USE_TOUCHSCREEN MC13XXX_USE_TOUCHSCREEN
-#define MC13783_USE_CODEC MC13XXX_USE_CODEC
-#define MC13783_USE_ADC MC13XXX_USE_ADC
-#define MC13783_USE_RTC MC13XXX_USE_RTC
-#define MC13783_USE_REGULATOR MC13XXX_USE_REGULATOR
-#define MC13783_USE_LED MC13XXX_USE_LED
-
-#define MC13783_ADC_MODE_TS 1
-#define MC13783_ADC_MODE_SINGLE_CHAN 2
-#define MC13783_ADC_MODE_MULT_CHAN 3
-
-int mc13783_adc_do_conversion(struct mc13783 *mc13783, unsigned int mode,
- unsigned int channel, unsigned int *sample);
-
-
#define MC13783_REG_SW1A 0
#define MC13783_REG_SW1B 1
#define MC13783_REG_SW2A 2
diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h
index c064bea..3816c2f 100644
--- a/include/linux/mfd/mc13xxx.h
+++ b/include/linux/mfd/mc13xxx.h
@@ -37,6 +37,9 @@
int mc13xxx_get_flags(struct mc13xxx *mc13xxx);
+int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx,
+ unsigned int mode, unsigned int channel, unsigned int *sample);
+
#define MC13XXX_IRQ_ADCDONE 0
#define MC13XXX_IRQ_ADCBISDONE 1
#define MC13XXX_IRQ_TS 2
@@ -137,17 +140,48 @@
char tc3_period;
};
+struct mc13xxx_buttons_platform_data {
+#define MC13783_BUTTON_DBNC_0MS 0
+#define MC13783_BUTTON_DBNC_30MS 1
+#define MC13783_BUTTON_DBNC_150MS 2
+#define MC13783_BUTTON_DBNC_750MS 3
+#define MC13783_BUTTON_ENABLE (1 << 2)
+#define MC13783_BUTTON_POL_INVERT (1 << 3)
+#define MC13783_BUTTON_RESET_EN (1 << 4)
+ int b1on_flags;
+ unsigned short b1on_key;
+ int b2on_flags;
+ unsigned short b2on_key;
+ int b3on_flags;
+ unsigned short b3on_key;
+};
+
struct mc13xxx_platform_data {
#define MC13XXX_USE_TOUCHSCREEN (1 << 0)
#define MC13XXX_USE_CODEC (1 << 1)
#define MC13XXX_USE_ADC (1 << 2)
#define MC13XXX_USE_RTC (1 << 3)
-#define MC13XXX_USE_REGULATOR (1 << 4)
-#define MC13XXX_USE_LED (1 << 5)
unsigned int flags;
struct mc13xxx_regulator_platform_data regulators;
struct mc13xxx_leds_platform_data *leds;
+ struct mc13xxx_buttons_platform_data *buttons;
};
+#define MC13XXX_ADC_MODE_TS 1
+#define MC13XXX_ADC_MODE_SINGLE_CHAN 2
+#define MC13XXX_ADC_MODE_MULT_CHAN 3
+
+#define MC13XXX_ADC0 43
+#define MC13XXX_ADC0_ADREFEN (1 << 10)
+#define MC13XXX_ADC0_TSMOD0 (1 << 12)
+#define MC13XXX_ADC0_TSMOD1 (1 << 13)
+#define MC13XXX_ADC0_TSMOD2 (1 << 14)
+#define MC13XXX_ADC0_ADINC1 (1 << 16)
+#define MC13XXX_ADC0_ADINC2 (1 << 17)
+
+#define MC13XXX_ADC0_TSMOD_MASK (MC13XXX_ADC0_TSMOD0 | \
+ MC13XXX_ADC0_TSMOD1 | \
+ MC13XXX_ADC0_TSMOD2)
+
#endif /* ifndef __LINUX_MFD_MC13XXX_H */
diff --git a/include/linux/mfd/pcf50633/core.h b/include/linux/mfd/pcf50633/core.h
index 50d4a04..a808407 100644
--- a/include/linux/mfd/pcf50633/core.h
+++ b/include/linux/mfd/pcf50633/core.h
@@ -21,6 +21,7 @@
#include <linux/mfd/pcf50633/backlight.h>
struct pcf50633;
+struct regmap;
#define PCF50633_NUM_REGULATORS 11
@@ -134,7 +135,7 @@
struct pcf50633 {
struct device *dev;
- struct i2c_client *i2c_client;
+ struct regmap *regmap;
struct pcf50633_platform_data *pdata;
int irq;
diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h
index ed8fe0d..4b12118 100644
--- a/include/linux/mfd/wm831x/core.h
+++ b/include/linux/mfd/wm831x/core.h
@@ -382,6 +382,7 @@
/* Used by the interrupt controller code to post writes */
int gpio_update[WM831X_NUM_GPIO_REGS];
+ bool gpio_level[WM831X_NUM_GPIO_REGS];
struct mutex auxadc_lock;
struct list_head auxadc_pending;
diff --git a/include/linux/mfd/wm8994/core.h b/include/linux/mfd/wm8994/core.h
index 6268091..f44bdb7 100644
--- a/include/linux/mfd/wm8994/core.h
+++ b/include/linux/mfd/wm8994/core.h
@@ -59,6 +59,8 @@
struct device *dev;
struct regmap *regmap;
+ bool ldo_ena_always_driven;
+
int gpio_base;
int irq_base;
diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h
index 97cf4f2..ea32f30 100644
--- a/include/linux/mfd/wm8994/pdata.h
+++ b/include/linux/mfd/wm8994/pdata.h
@@ -167,6 +167,13 @@
/* WM8958 microphone bias configuration */
int micbias[2];
+
+ /* Disable the internal pull downs on the LDOs if they are
+ * always driven (eg, connected to an always on supply or
+ * GPIO that always drives an output. If they float power
+ * consumption will rise.
+ */
+ bool ldo_ena_always_driven;
};
#endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3b3e3b8..3dc3a8c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -356,36 +356,50 @@
return page;
}
+/*
+ * The atomic page->_mapcount, starts from -1: so that transitions
+ * both from it and to it can be tracked, using atomic_inc_and_test
+ * and atomic_add_negative(-1).
+ */
+static inline void reset_page_mapcount(struct page *page)
+{
+ atomic_set(&(page)->_mapcount, -1);
+}
+
+static inline int page_mapcount(struct page *page)
+{
+ return atomic_read(&(page)->_mapcount) + 1;
+}
+
static inline int page_count(struct page *page)
{
return atomic_read(&compound_head(page)->_count);
}
-static inline void get_page(struct page *page)
+static inline void get_huge_page_tail(struct page *page)
{
/*
- * Getting a normal page or the head of a compound page
- * requires to already have an elevated page->_count. Only if
- * we're getting a tail page, the elevated page->_count is
- * required only in the head page, so for tail pages the
- * bugcheck only verifies that the page->_count isn't
- * negative.
+ * __split_huge_page_refcount() cannot run
+ * from under us.
*/
- VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
- atomic_inc(&page->_count);
+ VM_BUG_ON(page_mapcount(page) < 0);
+ VM_BUG_ON(atomic_read(&page->_count) != 0);
+ atomic_inc(&page->_mapcount);
+}
+
+extern bool __get_page_tail(struct page *page);
+
+static inline void get_page(struct page *page)
+{
+ if (unlikely(PageTail(page)))
+ if (likely(__get_page_tail(page)))
+ return;
/*
- * Getting a tail page will elevate both the head and tail
- * page->_count(s).
+ * Getting a normal page or the head of a compound page
+ * requires to already have an elevated page->_count.
*/
- if (unlikely(PageTail(page))) {
- /*
- * This is safe only because
- * __split_huge_page_refcount can't run under
- * get_page().
- */
- VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
- atomic_inc(&page->first_page->_count);
- }
+ VM_BUG_ON(atomic_read(&page->_count) <= 0);
+ atomic_inc(&page->_count);
}
static inline struct page *virt_to_head_page(const void *x)
@@ -804,21 +818,6 @@
}
/*
- * The atomic page->_mapcount, like _count, starts from -1:
- * so that transitions both from it and to it can be tracked,
- * using atomic_inc_and_test and atomic_add_negative(-1).
- */
-static inline void reset_page_mapcount(struct page *page)
-{
- atomic_set(&(page)->_mapcount, -1);
-}
-
-static inline int page_mapcount(struct page *page)
-{
- return atomic_read(&(page)->_mapcount) + 1;
-}
-
-/*
* Return true if this page is mapped into pagetables.
*/
static inline int page_mapped(struct page *page)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3e01a19..5b42f1b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -62,10 +62,23 @@
struct {
union {
- atomic_t _mapcount; /* Count of ptes mapped in mms,
- * to show when page is mapped
- * & limit reverse map searches.
- */
+ /*
+ * Count of ptes mapped in
+ * mms, to show when page is
+ * mapped & limit reverse map
+ * searches.
+ *
+ * Used also for tail pages
+ * refcounting instead of
+ * _count. Tail pages cannot
+ * be mapped and keeping the
+ * tail page _count zero at
+ * all times guarantees
+ * get_page_unless_zero() will
+ * never succeed on tail
+ * pages.
+ */
+ atomic_t _mapcount;
struct {
unsigned inuse:16;
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 409328d..ffc0213 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -67,6 +67,7 @@
#define LOOKUP_EMPTY 0x4000
extern int user_path_at(int, const char __user *, unsigned, struct path *);
+extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
#define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
#define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path)
diff --git a/include/linux/netfilter_ipv4/Kbuild b/include/linux/netfilter_ipv4/Kbuild
index f9930c8..c3b4548 100644
--- a/include/linux/netfilter_ipv4/Kbuild
+++ b/include/linux/netfilter_ipv4/Kbuild
@@ -12,3 +12,4 @@
header-y += ipt_ecn.h
header-y += ipt_realm.h
header-y += ipt_ttl.h
+header-y += nf_nat.h
diff --git a/include/linux/netfilter_ipv4/nf_nat.h b/include/linux/netfilter_ipv4/nf_nat.h
new file mode 100644
index 0000000..7a861d0
--- /dev/null
+++ b/include/linux/netfilter_ipv4/nf_nat.h
@@ -0,0 +1,58 @@
+#ifndef _LINUX_NF_NAT_H
+#define _LINUX_NF_NAT_H
+
+#include <linux/types.h>
+
+#define IP_NAT_RANGE_MAP_IPS 1
+#define IP_NAT_RANGE_PROTO_SPECIFIED 2
+#define IP_NAT_RANGE_PROTO_RANDOM 4
+#define IP_NAT_RANGE_PERSISTENT 8
+
+/* The protocol-specific manipulable parts of the tuple. */
+union nf_conntrack_man_proto {
+ /* Add other protocols here. */
+ __be16 all;
+
+ struct {
+ __be16 port;
+ } tcp;
+ struct {
+ __be16 port;
+ } udp;
+ struct {
+ __be16 id;
+ } icmp;
+ struct {
+ __be16 port;
+ } dccp;
+ struct {
+ __be16 port;
+ } sctp;
+ struct {
+ __be16 key; /* GRE key is 32bit, PPtP only uses 16bit */
+ } gre;
+};
+
+/* Single range specification. */
+struct nf_nat_range {
+ /* Set to OR of flags above. */
+ unsigned int flags;
+
+ /* Inclusive: network order. */
+ __be32 min_ip, max_ip;
+
+ /* Inclusive: network order */
+ union nf_conntrack_man_proto min, max;
+};
+
+/* For backwards compat: don't use in modern code. */
+struct nf_nat_multi_range_compat {
+ unsigned int rangesize; /* Must be 1. */
+
+ /* hangs off end. */
+ struct nf_nat_range range[1];
+};
+
+#define nf_nat_multi_range nf_nat_multi_range_compat
+
+#endif
diff --git a/include/linux/pps-gpio.h b/include/linux/pps-gpio.h
new file mode 100644
index 0000000..0035abe
--- /dev/null
+++ b/include/linux/pps-gpio.h
@@ -0,0 +1,32 @@
+/*
+ * pps-gpio.h -- PPS client for GPIOs
+ *
+ *
+ * Copyright (C) 2011 James Nuss <jamesnuss@nanometrics.ca>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef _PPS_GPIO_H
+#define _PPS_GPIO_H
+
+struct pps_gpio_platform_data {
+ bool assert_falling_edge;
+ bool capture_clear;
+ unsigned int gpio_pin;
+ const char *gpio_label;
+};
+
+#endif
diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h
index 0cee015..b66d13d 100644
--- a/include/linux/rio_ids.h
+++ b/include/linux/rio_ids.h
@@ -39,5 +39,6 @@
#define RIO_DID_IDTCPS1616 0x0379
#define RIO_DID_IDTVPS1616 0x0377
#define RIO_DID_IDTSPS1616 0x0378
+#define RIO_DID_TSI721 0x80ab
#endif /* LINUX_RIO_IDS_H */
diff --git a/include/linux/sem.h b/include/linux/sem.h
index 1feb2de..10d6b22 100644
--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -83,13 +83,6 @@
struct task_struct;
-/* One semaphore structure for each semaphore in the system. */
-struct sem {
- int semval; /* current value */
- int sempid; /* pid of last operation */
- struct list_head sem_pending; /* pending single-sop operations */
-};
-
/* One sem_array data structure for each set of semaphores in the system. */
struct sem_array {
struct kern_ipc_perm ____cacheline_aligned_in_smp
@@ -103,51 +96,21 @@
int complex_count; /* pending complex operations */
};
-/* One queue for each sleeping process in the system. */
-struct sem_queue {
- struct list_head simple_list; /* queue of pending operations */
- struct list_head list; /* queue of pending operations */
- struct task_struct *sleeper; /* this process */
- struct sem_undo *undo; /* undo structure */
- int pid; /* process id of requesting process */
- int status; /* completion status of operation */
- struct sembuf *sops; /* array of pending operations */
- int nsops; /* number of operations */
- int alter; /* does the operation alter the array? */
-};
-
-/* Each task has a list of undo requests. They are executed automatically
- * when the process exits.
- */
-struct sem_undo {
- struct list_head list_proc; /* per-process list: all undos from one process. */
- /* rcu protected */
- struct rcu_head rcu; /* rcu struct for sem_undo() */
- struct sem_undo_list *ulp; /* sem_undo_list for the process */
- struct list_head list_id; /* per semaphore array list: all undos for one array */
- int semid; /* semaphore set identifier */
- short * semadj; /* array of adjustments, one per semaphore */
-};
-
-/* sem_undo_list controls shared access to the list of sem_undo structures
- * that may be shared among all a CLONE_SYSVSEM task group.
- */
-struct sem_undo_list {
- atomic_t refcnt;
- spinlock_t lock;
- struct list_head list_proc;
-};
+#ifdef CONFIG_SYSVIPC
struct sysv_sem {
struct sem_undo_list *undo_list;
};
-#ifdef CONFIG_SYSVIPC
-
extern int copy_semundo(unsigned long clone_flags, struct task_struct *tsk);
extern void exit_sem(struct task_struct *tsk);
#else
+
+struct sysv_sem {
+ /* empty */
+};
+
static inline int copy_semundo(unsigned long clone_flags, struct task_struct *tsk)
{
return 0;
diff --git a/include/linux/sh_pfc.h b/include/linux/sh_pfc.h
index 30cae70..bc8c920 100644
--- a/include/linux/sh_pfc.h
+++ b/include/linux/sh_pfc.h
@@ -61,6 +61,14 @@
.reg = r, .reg_width = r_width, \
.enum_ids = (pinmux_enum_t [r_width]) \
+struct pinmux_irq {
+ int irq;
+ pinmux_enum_t *enum_ids;
+};
+
+#define PINMUX_IRQ(irq_nr, ids...) \
+ { .irq = irq_nr, .enum_ids = (pinmux_enum_t []) { ids, 0 } } \
+
struct pinmux_range {
pinmux_enum_t begin;
pinmux_enum_t end;
@@ -87,7 +95,9 @@
pinmux_enum_t *gpio_data;
unsigned int gpio_data_size;
- unsigned long *gpio_in_use;
+ struct pinmux_irq *gpio_irq;
+ unsigned int gpio_irq_size;
+
struct gpio_chip chip;
};
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6a6b352..fe86488 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1806,12 +1806,12 @@
/**
* skb_frag_dma_map - maps a paged fragment via the DMA API
- * @device: the device to map the fragment to
+ * @dev: the device to map the fragment to
* @frag: the paged fragment to map
* @offset: the offset within the fragment (starting at the
* fragment's own offset)
* @size: the number of bytes to map
- * @direction: the direction of the mapping (%PCI_DMA_*)
+ * @dir: the direction of the mapping (%PCI_DMA_*)
*
* Maps the page associated with @frag to @device.
*/
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 9a1ec10..703cfa3 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -931,6 +931,7 @@
#ifdef __KERNEL__
#include <linux/list.h>
#include <linux/rcupdate.h>
+#include <linux/wait.h>
/* For the /proc/sys support */
struct ctl_table;
@@ -1011,6 +1012,26 @@
* cover common cases.
*/
+/* Support for userspace poll() to watch for changes */
+struct ctl_table_poll {
+ atomic_t event;
+ wait_queue_head_t wait;
+};
+
+static inline void *proc_sys_poll_event(struct ctl_table_poll *poll)
+{
+ return (void *)(unsigned long)atomic_read(&poll->event);
+}
+
+void proc_sys_poll_notify(struct ctl_table_poll *poll);
+
+#define __CTL_TABLE_POLL_INITIALIZER(name) { \
+ .event = ATOMIC_INIT(0), \
+ .wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait) }
+
+#define DEFINE_CTL_TABLE_POLL(name) \
+ struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name)
+
/* A sysctl table is an array of struct ctl_table: */
struct ctl_table
{
@@ -1021,6 +1042,7 @@
struct ctl_table *child;
struct ctl_table *parent; /* Automatically set */
proc_handler *proc_handler; /* Callback for text formatting */
+ struct ctl_table_poll *poll;
void *extra1;
void *extra2;
};
diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index 4e5b021..c714ed7 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -37,6 +37,14 @@
#include <linux/nsproxy.h>
#include <linux/err.h>
+enum uts_proc {
+ UTS_PROC_OSTYPE,
+ UTS_PROC_OSRELEASE,
+ UTS_PROC_VERSION,
+ UTS_PROC_HOSTNAME,
+ UTS_PROC_DOMAINNAME,
+};
+
struct user_namespace;
extern struct user_namespace init_user_ns;
@@ -80,6 +88,14 @@
}
#endif
+#ifdef CONFIG_PROC_SYSCTL
+extern void uts_proc_notify(enum uts_proc proc);
+#else
+static inline void uts_proc_notify(enum uts_proc proc)
+{
+}
+#endif
+
static inline struct new_utsname *utsname(void)
{
return ¤t->nsproxy->uts_ns->name;
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 851ebf1..4c069d8 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -131,10 +131,10 @@
* virtio_driver - operations for a virtio I/O driver
* @driver: underlying device driver (populate name and owner).
* @id_table: the ids serviced by this driver.
- * @feature_table: an array of feature numbers supported by this device.
+ * @feature_table: an array of feature numbers supported by this driver.
* @feature_table_size: number of entries in the feature table array.
* @probe: the function to call when a device is found. Returns 0 or -errno.
- * @remove: the function when a device is removed.
+ * @remove: the function to call when a device is removed.
* @config_changed: optional function to call when the device configuration
* changes; may be called in interrupt context.
*/
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 39c88c5..add4790 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -155,6 +155,9 @@
#define virtio_config_val(vdev, fbit, offset, v) \
virtio_config_buf((vdev), (fbit), (offset), (v), sizeof(*v))
+#define virtio_config_val_len(vdev, fbit, offset, v, len) \
+ virtio_config_buf((vdev), (fbit), (offset), (v), (len))
+
static inline int virtio_config_buf(struct virtio_device *vdev,
unsigned int fbit,
unsigned int offset,
diff --git a/include/linux/virtio_mmio.h b/include/linux/virtio_mmio.h
new file mode 100644
index 0000000..27c7ede
--- /dev/null
+++ b/include/linux/virtio_mmio.h
@@ -0,0 +1,111 @@
+/*
+ * Virtio platform device driver
+ *
+ * Copyright 2011, ARM Ltd.
+ *
+ * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_VIRTIO_MMIO_H
+#define _LINUX_VIRTIO_MMIO_H
+
+/*
+ * Control registers
+ */
+
+/* Magic value ("virt" string) - Read Only */
+#define VIRTIO_MMIO_MAGIC_VALUE 0x000
+
+/* Virtio device version - Read Only */
+#define VIRTIO_MMIO_VERSION 0x004
+
+/* Virtio device ID - Read Only */
+#define VIRTIO_MMIO_DEVICE_ID 0x008
+
+/* Virtio vendor ID - Read Only */
+#define VIRTIO_MMIO_VENDOR_ID 0x00c
+
+/* Bitmask of the features supported by the host
+ * (32 bits per set) - Read Only */
+#define VIRTIO_MMIO_HOST_FEATURES 0x010
+
+/* Host features set selector - Write Only */
+#define VIRTIO_MMIO_HOST_FEATURES_SEL 0x014
+
+/* Bitmask of features activated by the guest
+ * (32 bits per set) - Write Only */
+#define VIRTIO_MMIO_GUEST_FEATURES 0x020
+
+/* Activated features set selector - Write Only */
+#define VIRTIO_MMIO_GUEST_FEATURES_SET 0x024
+
+/* Guest's memory page size in bytes - Write Only */
+#define VIRTIO_MMIO_GUEST_PAGE_SIZE 0x028
+
+/* Queue selector - Write Only */
+#define VIRTIO_MMIO_QUEUE_SEL 0x030
+
+/* Maximum size of the currently selected queue - Read Only */
+#define VIRTIO_MMIO_QUEUE_NUM_MAX 0x034
+
+/* Queue size for the currently selected queue - Write Only */
+#define VIRTIO_MMIO_QUEUE_NUM 0x038
+
+/* Used Ring alignment for the currently selected queue - Write Only */
+#define VIRTIO_MMIO_QUEUE_ALIGN 0x03c
+
+/* Guest's PFN for the currently selected queue - Read Write */
+#define VIRTIO_MMIO_QUEUE_PFN 0x040
+
+/* Queue notifier - Write Only */
+#define VIRTIO_MMIO_QUEUE_NOTIFY 0x050
+
+/* Interrupt status - Read Only */
+#define VIRTIO_MMIO_INTERRUPT_STATUS 0x060
+
+/* Interrupt acknowledge - Write Only */
+#define VIRTIO_MMIO_INTERRUPT_ACK 0x064
+
+/* Device status register - Read Write */
+#define VIRTIO_MMIO_STATUS 0x070
+
+/* The config space is defined by each driver as
+ * the per-driver configuration space - Read Write */
+#define VIRTIO_MMIO_CONFIG 0x100
+
+
+
+/*
+ * Interrupt flags (re: interrupt status & acknowledge registers)
+ */
+
+#define VIRTIO_MMIO_INT_VRING (1 << 0)
+#define VIRTIO_MMIO_INT_CONFIG (1 << 1)
+
+#endif
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index 4a32cb6..36be0f6 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -135,13 +135,13 @@
vr->num = num;
vr->desc = p;
vr->avail = p + num*sizeof(struct vring_desc);
- vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + align-1)
- & ~(align - 1));
+ vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(__u16)
+ + align-1) & ~(align - 1));
}
static inline unsigned vring_size(unsigned int num, unsigned long align)
{
- return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (2 + num)
+ return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num)
+ align - 1) & ~(align - 1))
+ sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num;
}
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 8fa4430..05b08c9 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -425,9 +425,9 @@
const char *(*state_name)(int state);
- int (*state_transition)(struct ip_vs_conn *cp, int direction,
- const struct sk_buff *skb,
- struct ip_vs_proto_data *pd);
+ void (*state_transition)(struct ip_vs_conn *cp, int direction,
+ const struct sk_buff *skb,
+ struct ip_vs_proto_data *pd);
int (*register_app)(struct net *net, struct ip_vs_app *inc);
@@ -1378,7 +1378,7 @@
extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
int outin);
-extern int ip_vs_confirm_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp);
+extern int ip_vs_confirm_conntrack(struct sk_buff *skb);
extern void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct,
struct ip_vs_conn *cp, u_int8_t proto,
const __be16 port, int from_rs);
@@ -1396,8 +1396,7 @@
{
}
-static inline int ip_vs_confirm_conntrack(struct sk_buff *skb,
- struct ip_vs_conn *cp)
+static inline int ip_vs_confirm_conntrack(struct sk_buff *skb)
{
return NF_ACCEPT;
}
diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h
index 7ca6bdd..2f8fb77 100644
--- a/include/net/netfilter/nf_conntrack_tuple.h
+++ b/include/net/netfilter/nf_conntrack_tuple.h
@@ -12,6 +12,7 @@
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <linux/netfilter_ipv4/nf_nat.h>
#include <linux/list_nulls.h>
/* A `tuple' is a structure containing the information to uniquely
@@ -24,32 +25,6 @@
#define NF_CT_TUPLE_L3SIZE ARRAY_SIZE(((union nf_inet_addr *)NULL)->all)
-/* The protocol-specific manipulable parts of the tuple: always in
- network order! */
-union nf_conntrack_man_proto {
- /* Add other protocols here. */
- __be16 all;
-
- struct {
- __be16 port;
- } tcp;
- struct {
- __be16 port;
- } udp;
- struct {
- __be16 id;
- } icmp;
- struct {
- __be16 port;
- } dccp;
- struct {
- __be16 port;
- } sctp;
- struct {
- __be16 key; /* GRE key is 32bit, PPtP only uses 16bit */
- } gre;
-};
-
/* The manipulable part of the tuple. */
struct nf_conntrack_man {
union nf_inet_addr u3;
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index 0346b00..b8872df 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -1,6 +1,7 @@
#ifndef _NF_NAT_H
#define _NF_NAT_H
#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv4/nf_nat.h>
#include <net/netfilter/nf_conntrack_tuple.h>
#define NF_NAT_MAPPING_TYPE_MAX_NAMELEN 16
@@ -14,11 +15,6 @@
#define HOOK2MANIP(hooknum) ((hooknum) != NF_INET_POST_ROUTING && \
(hooknum) != NF_INET_LOCAL_IN)
-#define IP_NAT_RANGE_MAP_IPS 1
-#define IP_NAT_RANGE_PROTO_SPECIFIED 2
-#define IP_NAT_RANGE_PROTO_RANDOM 4
-#define IP_NAT_RANGE_PERSISTENT 8
-
/* NAT sequence number modifications */
struct nf_nat_seq {
/* position of the last TCP sequence number modification (if any) */
@@ -28,26 +24,6 @@
int16_t offset_before, offset_after;
};
-/* Single range specification. */
-struct nf_nat_range {
- /* Set to OR of flags above. */
- unsigned int flags;
-
- /* Inclusive: network order. */
- __be32 min_ip, max_ip;
-
- /* Inclusive: network order */
- union nf_conntrack_man_proto min, max;
-};
-
-/* For backwards compat: don't use in modern code. */
-struct nf_nat_multi_range_compat {
- unsigned int rangesize; /* Must be 1. */
-
- /* hangs off end. */
- struct nf_nat_range range[1];
-};
-
#include <linux/list.h>
#include <linux/netfilter/nf_conntrack_pptp.h>
#include <net/netfilter/nf_conntrack_extend.h>
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e147f42..bb18c4d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1403,11 +1403,13 @@
TCP_SEQ_STATE_TIME_WAIT,
};
+int tcp_seq_open(struct inode *inode, struct file *file);
+
struct tcp_seq_afinfo {
- char *name;
- sa_family_t family;
- struct file_operations seq_fops;
- struct seq_operations seq_ops;
+ char *name;
+ sa_family_t family;
+ const struct file_operations *seq_fops;
+ struct seq_operations seq_ops;
};
struct tcp_iter_state {
diff --git a/include/net/udp.h b/include/net/udp.h
index 67ea6fc..3b285f4 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -230,12 +230,14 @@
#endif
/* /proc */
+int udp_seq_open(struct inode *inode, struct file *file);
+
struct udp_seq_afinfo {
- char *name;
- sa_family_t family;
- struct udp_table *udp_table;
- struct file_operations seq_fops;
- struct seq_operations seq_ops;
+ char *name;
+ sa_family_t family;
+ struct udp_table *udp_table;
+ const struct file_operations *seq_fops;
+ struct seq_operations seq_ops;
};
struct udp_iter_state {
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index b50a547..748ff7c 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -9,9 +9,12 @@
struct ext4_allocation_context;
struct ext4_allocation_request;
+struct ext4_extent;
struct ext4_prealloc_space;
struct ext4_inode_info;
struct mpage_da_data;
+struct ext4_map_blocks;
+struct ext4_extent;
#define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode))
@@ -1032,9 +1035,9 @@
);
TRACE_EVENT(ext4_da_update_reserve_space,
- TP_PROTO(struct inode *inode, int used_blocks),
+ TP_PROTO(struct inode *inode, int used_blocks, int quota_claim),
- TP_ARGS(inode, used_blocks),
+ TP_ARGS(inode, used_blocks, quota_claim),
TP_STRUCT__entry(
__field( dev_t, dev )
@@ -1045,6 +1048,7 @@
__field( int, reserved_data_blocks )
__field( int, reserved_meta_blocks )
__field( int, allocated_meta_blocks )
+ __field( int, quota_claim )
),
TP_fast_assign(
@@ -1053,19 +1057,24 @@
__entry->mode = inode->i_mode;
__entry->i_blocks = inode->i_blocks;
__entry->used_blocks = used_blocks;
- __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
- __entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
- __entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks;
+ __entry->reserved_data_blocks =
+ EXT4_I(inode)->i_reserved_data_blocks;
+ __entry->reserved_meta_blocks =
+ EXT4_I(inode)->i_reserved_meta_blocks;
+ __entry->allocated_meta_blocks =
+ EXT4_I(inode)->i_allocated_meta_blocks;
+ __entry->quota_claim = quota_claim;
),
TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d "
"reserved_data_blocks %d reserved_meta_blocks %d "
- "allocated_meta_blocks %d",
+ "allocated_meta_blocks %d quota_claim %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long) __entry->ino,
__entry->mode, __entry->i_blocks,
__entry->used_blocks, __entry->reserved_data_blocks,
- __entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
+ __entry->reserved_meta_blocks, __entry->allocated_meta_blocks,
+ __entry->quota_claim)
);
TRACE_EVENT(ext4_da_reserve_space,
@@ -1386,6 +1395,87 @@
TP_ARGS(inode)
);
+/* 'ux' is the uninitialized extent. */
+TRACE_EVENT(ext4_ext_convert_to_initialized_enter,
+ TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
+ struct ext4_extent *ux),
+
+ TP_ARGS(inode, map, ux),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, m_lblk )
+ __field( unsigned, m_len )
+ __field( ext4_lblk_t, u_lblk )
+ __field( unsigned, u_len )
+ __field( ext4_fsblk_t, u_pblk )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->m_lblk = map->m_lblk;
+ __entry->m_len = map->m_len;
+ __entry->u_lblk = le32_to_cpu(ux->ee_block);
+ __entry->u_len = ext4_ext_get_actual_len(ux);
+ __entry->u_pblk = ext4_ext_pblock(ux);
+ ),
+
+ TP_printk("dev %d,%d ino %lu m_lblk %u m_len %u u_lblk %u u_len %u "
+ "u_pblk %llu",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ __entry->m_lblk, __entry->m_len,
+ __entry->u_lblk, __entry->u_len, __entry->u_pblk)
+);
+
+/*
+ * 'ux' is the uninitialized extent.
+ * 'ix' is the initialized extent to which blocks are transferred.
+ */
+TRACE_EVENT(ext4_ext_convert_to_initialized_fastpath,
+ TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
+ struct ext4_extent *ux, struct ext4_extent *ix),
+
+ TP_ARGS(inode, map, ux, ix),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, m_lblk )
+ __field( unsigned, m_len )
+ __field( ext4_lblk_t, u_lblk )
+ __field( unsigned, u_len )
+ __field( ext4_fsblk_t, u_pblk )
+ __field( ext4_lblk_t, i_lblk )
+ __field( unsigned, i_len )
+ __field( ext4_fsblk_t, i_pblk )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->m_lblk = map->m_lblk;
+ __entry->m_len = map->m_len;
+ __entry->u_lblk = le32_to_cpu(ux->ee_block);
+ __entry->u_len = ext4_ext_get_actual_len(ux);
+ __entry->u_pblk = ext4_ext_pblock(ux);
+ __entry->i_lblk = le32_to_cpu(ix->ee_block);
+ __entry->i_len = ext4_ext_get_actual_len(ix);
+ __entry->i_pblk = ext4_ext_pblock(ix);
+ ),
+
+ TP_printk("dev %d,%d ino %lu m_lblk %u m_len %u "
+ "u_lblk %u u_len %u u_pblk %llu "
+ "i_lblk %u i_len %u i_pblk %llu ",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ __entry->m_lblk, __entry->m_len,
+ __entry->u_lblk, __entry->u_len, __entry->u_pblk,
+ __entry->i_lblk, __entry->i_len, __entry->i_pblk)
+);
+
DECLARE_EVENT_CLASS(ext4__map_blocks_enter,
TP_PROTO(struct inode *inode, ext4_lblk_t lblk,
unsigned int len, unsigned int flags),
@@ -1589,6 +1679,382 @@
TP_ARGS(sb, group, start, len)
);
+TRACE_EVENT(ext4_ext_handle_uninitialized_extents,
+ TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
+ unsigned int allocated, ext4_fsblk_t newblock),
+
+ TP_ARGS(inode, map, allocated, newblock),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, lblk )
+ __field( ext4_fsblk_t, pblk )
+ __field( unsigned int, len )
+ __field( int, flags )
+ __field( unsigned int, allocated )
+ __field( ext4_fsblk_t, newblk )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->lblk = map->m_lblk;
+ __entry->pblk = map->m_pblk;
+ __entry->len = map->m_len;
+ __entry->flags = map->m_flags;
+ __entry->allocated = allocated;
+ __entry->newblk = newblock;
+ ),
+
+ TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %d"
+ "allocated %d newblock %llu",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->lblk, (unsigned long long) __entry->pblk,
+ __entry->len, __entry->flags,
+ (unsigned int) __entry->allocated,
+ (unsigned long long) __entry->newblk)
+);
+
+TRACE_EVENT(ext4_get_implied_cluster_alloc_exit,
+ TP_PROTO(struct super_block *sb, struct ext4_map_blocks *map, int ret),
+
+ TP_ARGS(sb, map, ret),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, lblk )
+ __field( ext4_fsblk_t, pblk )
+ __field( unsigned int, len )
+ __field( unsigned int, flags )
+ __field( int, ret )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->lblk = map->m_lblk;
+ __entry->pblk = map->m_pblk;
+ __entry->len = map->m_len;
+ __entry->flags = map->m_flags;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %u ret %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->lblk, (unsigned long long) __entry->pblk,
+ __entry->len, __entry->flags, __entry->ret)
+);
+
+TRACE_EVENT(ext4_ext_put_in_cache,
+ TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len,
+ ext4_fsblk_t start),
+
+ TP_ARGS(inode, lblk, len, start),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, lblk )
+ __field( unsigned int, len )
+ __field( ext4_fsblk_t, start )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->lblk = lblk;
+ __entry->len = len;
+ __entry->start = start;
+ ),
+
+ TP_printk("dev %d,%d ino %lu lblk %u len %u start %llu",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->lblk,
+ __entry->len,
+ (unsigned long long) __entry->start)
+);
+
+TRACE_EVENT(ext4_ext_in_cache,
+ TP_PROTO(struct inode *inode, ext4_lblk_t lblk, int ret),
+
+ TP_ARGS(inode, lblk, ret),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, lblk )
+ __field( int, ret )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->lblk = lblk;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev %d,%d ino %lu lblk %u ret %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->lblk,
+ __entry->ret)
+
+);
+
+TRACE_EVENT(ext4_find_delalloc_range,
+ TP_PROTO(struct inode *inode, ext4_lblk_t from, ext4_lblk_t to,
+ int reverse, int found, ext4_lblk_t found_blk),
+
+ TP_ARGS(inode, from, to, reverse, found, found_blk),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, from )
+ __field( ext4_lblk_t, to )
+ __field( int, reverse )
+ __field( int, found )
+ __field( ext4_lblk_t, found_blk )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->from = from;
+ __entry->to = to;
+ __entry->reverse = reverse;
+ __entry->found = found;
+ __entry->found_blk = found_blk;
+ ),
+
+ TP_printk("dev %d,%d ino %lu from %u to %u reverse %d found %d "
+ "(blk = %u)",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->from, (unsigned) __entry->to,
+ __entry->reverse, __entry->found,
+ (unsigned) __entry->found_blk)
+);
+
+TRACE_EVENT(ext4_get_reserved_cluster_alloc,
+ TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len),
+
+ TP_ARGS(inode, lblk, len),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, lblk )
+ __field( unsigned int, len )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->lblk = lblk;
+ __entry->len = len;
+ ),
+
+ TP_printk("dev %d,%d ino %lu lblk %u len %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->lblk,
+ __entry->len)
+);
+
+TRACE_EVENT(ext4_ext_show_extent,
+ TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
+ unsigned short len),
+
+ TP_ARGS(inode, lblk, pblk, len),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, lblk )
+ __field( ext4_fsblk_t, pblk )
+ __field( unsigned short, len )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->lblk = lblk;
+ __entry->pblk = pblk;
+ __entry->len = len;
+ ),
+
+ TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->lblk,
+ (unsigned long long) __entry->pblk,
+ (unsigned short) __entry->len)
+);
+
+TRACE_EVENT(ext4_remove_blocks,
+ TP_PROTO(struct inode *inode, struct ext4_extent *ex,
+ ext4_lblk_t from, ext4_fsblk_t to,
+ ext4_fsblk_t partial_cluster),
+
+ TP_ARGS(inode, ex, from, to, partial_cluster),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, ee_lblk )
+ __field( ext4_fsblk_t, ee_pblk )
+ __field( unsigned short, ee_len )
+ __field( ext4_lblk_t, from )
+ __field( ext4_lblk_t, to )
+ __field( ext4_fsblk_t, partial )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ee_lblk = cpu_to_le32(ex->ee_block);
+ __entry->ee_pblk = ext4_ext_pblock(ex);
+ __entry->ee_len = ext4_ext_get_actual_len(ex);
+ __entry->from = from;
+ __entry->to = to;
+ __entry->partial = partial_cluster;
+ ),
+
+ TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]"
+ "from %u to %u partial_cluster %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->ee_lblk,
+ (unsigned long long) __entry->ee_pblk,
+ (unsigned short) __entry->ee_len,
+ (unsigned) __entry->from,
+ (unsigned) __entry->to,
+ (unsigned) __entry->partial)
+);
+
+TRACE_EVENT(ext4_ext_rm_leaf,
+ TP_PROTO(struct inode *inode, ext4_lblk_t start,
+ struct ext4_extent *ex, ext4_fsblk_t partial_cluster),
+
+ TP_ARGS(inode, start, ex, partial_cluster),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, start )
+ __field( ext4_lblk_t, ee_lblk )
+ __field( ext4_fsblk_t, ee_pblk )
+ __field( short, ee_len )
+ __field( ext4_fsblk_t, partial )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->start = start;
+ __entry->ee_lblk = le32_to_cpu(ex->ee_block);
+ __entry->ee_pblk = ext4_ext_pblock(ex);
+ __entry->ee_len = ext4_ext_get_actual_len(ex);
+ __entry->partial = partial_cluster;
+ ),
+
+ TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]"
+ "partial_cluster %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->start,
+ (unsigned) __entry->ee_lblk,
+ (unsigned long long) __entry->ee_pblk,
+ (unsigned short) __entry->ee_len,
+ (unsigned) __entry->partial)
+);
+
+TRACE_EVENT(ext4_ext_rm_idx,
+ TP_PROTO(struct inode *inode, ext4_fsblk_t pblk),
+
+ TP_ARGS(inode, pblk),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_fsblk_t, pblk )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->pblk = pblk;
+ ),
+
+ TP_printk("dev %d,%d ino %lu index_pblk %llu",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned long long) __entry->pblk)
+);
+
+TRACE_EVENT(ext4_ext_remove_space,
+ TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth),
+
+ TP_ARGS(inode, start, depth),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, start )
+ __field( int, depth )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->start = start;
+ __entry->depth = depth;
+ ),
+
+ TP_printk("dev %d,%d ino %lu since %u depth %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->start,
+ __entry->depth)
+);
+
+TRACE_EVENT(ext4_ext_remove_space_done,
+ TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth,
+ ext4_lblk_t partial, unsigned short eh_entries),
+
+ TP_ARGS(inode, start, depth, partial, eh_entries),
+
+ TP_STRUCT__entry(
+ __field( ino_t, ino )
+ __field( dev_t, dev )
+ __field( ext4_lblk_t, start )
+ __field( int, depth )
+ __field( ext4_lblk_t, partial )
+ __field( unsigned short, eh_entries )
+ ),
+
+ TP_fast_assign(
+ __entry->ino = inode->i_ino;
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->start = start;
+ __entry->depth = depth;
+ __entry->partial = partial;
+ __entry->eh_entries = eh_entries;
+ ),
+
+ TP_printk("dev %d,%d ino %lu since %u depth %d partial %u "
+ "remaining_entries %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long) __entry->ino,
+ (unsigned) __entry->start,
+ __entry->depth,
+ (unsigned) __entry->partial,
+ (unsigned short) __entry->eh_entries)
+);
+
#endif /* _TRACE_EXT4_H */
/* This part must be outside protection */
diff --git a/init/Kconfig b/init/Kconfig
index 31ba0fd..43298f9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -947,7 +947,7 @@
config SYSCTL_SYSCALL
bool "Sysctl syscall support" if EXPERT
depends on PROC_SYSCTL
- default y
+ default n
select SYSCTL
---help---
sys_sysctl uses binary paths that have been found challenging
@@ -959,7 +959,7 @@
trying to save some space it is probably safe to disable this,
making your kernel marginally smaller.
- If unsure say Y here.
+ If unsure say N here.
config KALLSYMS
bool "Load all symbols for debugging/ksymoops" if EXPERT
diff --git a/init/do_mounts.c b/init/do_mounts.c
index c0851a8..0f6e1d9 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -28,7 +28,7 @@
int root_mountflags = MS_RDONLY | MS_SILENT;
static char * __initdata root_device_name;
static char __initdata saved_root_name[64];
-static int __initdata root_wait;
+static int root_wait;
dev_t ROOT_DEV;
@@ -85,12 +85,15 @@
/**
* devt_from_partuuid - looks up the dev_t of a partition by its UUID
- * @uuid: 36 byte char array containing a hex ascii UUID
+ * @uuid: min 36 byte char array containing a hex ascii UUID
*
* The function will return the first partition which contains a matching
* UUID value in its partition_meta_info struct. This does not search
* by filesystem UUIDs.
*
+ * If @uuid is followed by a "/PARTNROFF=%d", then the number will be
+ * extracted and used as an offset from the partition identified by the UUID.
+ *
* Returns the matching dev_t on success or 0 on failure.
*/
static dev_t devt_from_partuuid(char *uuid_str)
@@ -98,6 +101,28 @@
dev_t res = 0;
struct device *dev = NULL;
u8 uuid[16];
+ struct gendisk *disk;
+ struct hd_struct *part;
+ int offset = 0;
+
+ if (strlen(uuid_str) < 36)
+ goto done;
+
+ /* Check for optional partition number offset attributes. */
+ if (uuid_str[36]) {
+ char c = 0;
+ /* Explicitly fail on poor PARTUUID syntax. */
+ if (sscanf(&uuid_str[36],
+ "/PARTNROFF=%d%c", &offset, &c) != 1) {
+ printk(KERN_ERR "VFS: PARTUUID= is invalid.\n"
+ "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n");
+ if (root_wait)
+ printk(KERN_ERR
+ "Disabling rootwait; root= is invalid.\n");
+ root_wait = 0;
+ goto done;
+ }
+ }
/* Pack the requested UUID in the expected format. */
part_pack_uuid(uuid_str, uuid);
@@ -107,8 +132,21 @@
goto done;
res = dev->devt;
- put_device(dev);
+ /* Attempt to find the partition by offset. */
+ if (!offset)
+ goto no_offset;
+
+ res = 0;
+ disk = part_to_disk(dev_to_part(dev));
+ part = disk_get_part(disk, dev_to_part(dev)->partno + offset);
+ if (part) {
+ res = part_devt(part);
+ put_device(part_to_dev(part));
+ }
+
+no_offset:
+ put_device(dev);
done:
return res;
}
@@ -126,6 +164,8 @@
* used when disk name of partitioned disk ends on a digit.
* 6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
* unique id of a partition if the partition table provides it.
+ * 7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to
+ * a partition with a known unique id.
*
* If name doesn't have fall into the categories above, we return (0,0).
* block_class is used to check if something is a disk name. If the disk
@@ -143,8 +183,6 @@
#ifdef CONFIG_BLOCK
if (strncmp(name, "PARTUUID=", 9) == 0) {
name += 9;
- if (strlen(name) != 36)
- goto fail;
res = devt_from_partuuid(name);
if (!res)
goto fail;
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index fe9acb0..887629e 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -120,6 +120,20 @@
}
/*
+ * Read 512 bytes further to check if cramfs is padded
+ */
+ sys_lseek(fd, start_block * BLOCK_SIZE + 0x200, 0);
+ sys_read(fd, buf, size);
+
+ if (cramfsb->magic == CRAMFS_MAGIC) {
+ printk(KERN_NOTICE
+ "RAMDISK: cramfs filesystem found at block %d\n",
+ start_block);
+ nblocks = (cramfsb->size + BLOCK_SIZE - 1) >> BLOCK_SIZE_BITS;
+ goto done;
+ }
+
+ /*
* Read block 1 to test for minix and ext2 superblock
*/
sys_lseek(fd, (start_block+1) * BLOCK_SIZE, 0);
diff --git a/ipc/sem.c b/ipc/sem.c
index c8e00f8..5215a81 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -90,6 +90,52 @@
#include <asm/uaccess.h>
#include "util.h"
+/* One semaphore structure for each semaphore in the system. */
+struct sem {
+ int semval; /* current value */
+ int sempid; /* pid of last operation */
+ struct list_head sem_pending; /* pending single-sop operations */
+};
+
+/* One queue for each sleeping process in the system. */
+struct sem_queue {
+ struct list_head simple_list; /* queue of pending operations */
+ struct list_head list; /* queue of pending operations */
+ struct task_struct *sleeper; /* this process */
+ struct sem_undo *undo; /* undo structure */
+ int pid; /* process id of requesting process */
+ int status; /* completion status of operation */
+ struct sembuf *sops; /* array of pending operations */
+ int nsops; /* number of operations */
+ int alter; /* does *sops alter the array? */
+};
+
+/* Each task has a list of undo requests. They are executed automatically
+ * when the process exits.
+ */
+struct sem_undo {
+ struct list_head list_proc; /* per-process list: *
+ * all undos from one process
+ * rcu protected */
+ struct rcu_head rcu; /* rcu struct for sem_undo */
+ struct sem_undo_list *ulp; /* back ptr to sem_undo_list */
+ struct list_head list_id; /* per semaphore array list:
+ * all undos for one array */
+ int semid; /* semaphore set identifier */
+ short *semadj; /* array of adjustments */
+ /* one per semaphore */
+};
+
+/* sem_undo_list controls shared access to the list of sem_undo structures
+ * that may be shared among all a CLONE_SYSVSEM task group.
+ */
+struct sem_undo_list {
+ atomic_t refcnt;
+ spinlock_t lock;
+ struct list_head list_proc;
+};
+
+
#define sem_ids(ns) ((ns)->ids[IPC_SEM_IDS])
#define sem_unlock(sma) ipc_unlock(&(sma)->sem_perm)
@@ -1426,6 +1472,8 @@
queue.status = -EINTR;
queue.sleeper = current;
+
+sleep_again:
current->state = TASK_INTERRUPTIBLE;
sem_unlock(sma);
@@ -1460,7 +1508,6 @@
* Array removed? If yes, leave without sem_unlock().
*/
if (IS_ERR(sma)) {
- error = -EIDRM;
goto out_free;
}
@@ -1479,6 +1526,13 @@
*/
if (timeout && jiffies_left == 0)
error = -EAGAIN;
+
+ /*
+ * If the wakeup was spurious, just retry
+ */
+ if (error == -EINTR && !signal_pending(current))
+ goto sleep_again;
+
unlink_queue(sma, &queue);
out_unlock_free:
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 453100a..d9d5648 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2027,7 +2027,7 @@
goto out_free_group_list;
/* prevent changes to the threadgroup list while we take a snapshot. */
- rcu_read_lock();
+ read_lock(&tasklist_lock);
if (!thread_group_leader(leader)) {
/*
* a race with de_thread from another thread's exec() may strip
@@ -2036,7 +2036,7 @@
* throw this task away and try again (from cgroup_procs_write);
* this is "double-double-toil-and-trouble-check locking".
*/
- rcu_read_unlock();
+ read_unlock(&tasklist_lock);
retval = -EAGAIN;
goto out_free_group_list;
}
@@ -2057,7 +2057,7 @@
} while_each_thread(leader, tsk);
/* remember the number of threads in the array for later. */
group_size = i;
- rcu_read_unlock();
+ read_unlock(&tasklist_lock);
/*
* step 1: check that we can legitimately attach to the cgroup.
@@ -2135,14 +2135,17 @@
oldcgrp = task_cgroup_from_root(tsk, root);
if (cgrp == oldcgrp)
continue;
- /* attach each task to each subsystem */
- for_each_subsys(root, ss) {
- if (ss->attach_task)
- ss->attach_task(cgrp, tsk);
- }
/* if the thread is PF_EXITING, it can just get skipped. */
retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, true);
- BUG_ON(retval != 0 && retval != -ESRCH);
+ if (retval == 0) {
+ /* attach each task to each subsystem */
+ for_each_subsys(root, ss) {
+ if (ss->attach_task)
+ ss->attach_task(cgrp, tsk);
+ }
+ } else {
+ BUG_ON(retval != -ESRCH);
+ }
}
/* nothing is sensitive to fork() after this point. */
@@ -4880,9 +4883,9 @@
rcu_assign_pointer(id->css, NULL);
rcu_assign_pointer(css->id, NULL);
- spin_lock(&ss->id_lock);
+ write_lock(&ss->id_lock);
idr_remove(&ss->idr, id->id);
- spin_unlock(&ss->id_lock);
+ write_unlock(&ss->id_lock);
kfree_rcu(id, rcu_head);
}
EXPORT_SYMBOL_GPL(free_css_id);
@@ -4908,10 +4911,10 @@
error = -ENOMEM;
goto err_out;
}
- spin_lock(&ss->id_lock);
+ write_lock(&ss->id_lock);
/* Don't use 0. allocates an ID of 1-65535 */
error = idr_get_new_above(&ss->idr, newid, 1, &myid);
- spin_unlock(&ss->id_lock);
+ write_unlock(&ss->id_lock);
/* Returns error when there are no free spaces for new ID.*/
if (error) {
@@ -4926,9 +4929,9 @@
return newid;
remove_idr:
error = -ENOSPC;
- spin_lock(&ss->id_lock);
+ write_lock(&ss->id_lock);
idr_remove(&ss->idr, myid);
- spin_unlock(&ss->id_lock);
+ write_unlock(&ss->id_lock);
err_out:
kfree(newid);
return ERR_PTR(error);
@@ -4940,7 +4943,7 @@
{
struct css_id *newid;
- spin_lock_init(&ss->id_lock);
+ rwlock_init(&ss->id_lock);
idr_init(&ss->idr);
newid = get_new_cssid(ss, 0);
@@ -5035,9 +5038,9 @@
* scan next entry from bitmap(tree), tmpid is updated after
* idr_get_next().
*/
- spin_lock(&ss->id_lock);
+ read_lock(&ss->id_lock);
tmp = idr_get_next(&ss->idr, &tmpid);
- spin_unlock(&ss->id_lock);
+ read_unlock(&ss->id_lock);
if (!tmp)
break;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 10131fd..ed0ff44 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -949,6 +949,8 @@
static void cpuset_change_task_nodemask(struct task_struct *tsk,
nodemask_t *newmems)
{
+ bool masks_disjoint = !nodes_intersects(*newmems, tsk->mems_allowed);
+
repeat:
/*
* Allow tasks that have access to memory reserves because they have
@@ -963,7 +965,6 @@
nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
-
/*
* ensure checking ->mems_allowed_change_disable after setting all new
* allowed nodes.
@@ -980,9 +981,11 @@
/*
* Allocation of memory is very fast, we needn't sleep when waiting
- * for the read-side.
+ * for the read-side. No wait is necessary, however, if at least one
+ * node remains unchanged.
*/
- while (ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
+ while (masks_disjoint &&
+ ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
task_unlock(tsk);
if (!task_curr(tsk))
yield();
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 12a0287..e1253fa 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -29,7 +29,6 @@
#include <linux/hardirq.h>
#include <linux/rculist.h>
#include <linux/uaccess.h>
-#include <linux/suspend.h>
#include <linux/syscalls.h>
#include <linux/anon_inodes.h>
#include <linux/kernel_stat.h>
@@ -6853,7 +6852,7 @@
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
mutex_lock(&swhash->hlist_mutex);
- if (swhash->hlist_refcount > 0 && !swhash->swevent_hlist) {
+ if (swhash->hlist_refcount > 0) {
struct swevent_hlist *hlist;
hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
@@ -6942,14 +6941,7 @@
{
unsigned int cpu = (long)hcpu;
- /*
- * Ignore suspend/resume action, the perf_pm_notifier will
- * take care of that.
- */
- if (action & CPU_TASKS_FROZEN)
- return NOTIFY_OK;
-
- switch (action) {
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
case CPU_DOWN_FAILED:
@@ -6968,90 +6960,6 @@
return NOTIFY_OK;
}
-static void perf_pm_resume_cpu(void *unused)
-{
- struct perf_cpu_context *cpuctx;
- struct perf_event_context *ctx;
- struct pmu *pmu;
- int idx;
-
- idx = srcu_read_lock(&pmus_srcu);
- list_for_each_entry_rcu(pmu, &pmus, entry) {
- cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
- ctx = cpuctx->task_ctx;
-
- perf_ctx_lock(cpuctx, ctx);
- perf_pmu_disable(cpuctx->ctx.pmu);
-
- cpu_ctx_sched_out(cpuctx, EVENT_ALL);
- if (ctx)
- ctx_sched_out(ctx, cpuctx, EVENT_ALL);
-
- perf_pmu_enable(cpuctx->ctx.pmu);
- perf_ctx_unlock(cpuctx, ctx);
- }
- srcu_read_unlock(&pmus_srcu, idx);
-}
-
-static void perf_pm_suspend_cpu(void *unused)
-{
- struct perf_cpu_context *cpuctx;
- struct perf_event_context *ctx;
- struct pmu *pmu;
- int idx;
-
- idx = srcu_read_lock(&pmus_srcu);
- list_for_each_entry_rcu(pmu, &pmus, entry) {
- cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
- ctx = cpuctx->task_ctx;
-
- perf_ctx_lock(cpuctx, ctx);
- perf_pmu_disable(cpuctx->ctx.pmu);
-
- perf_event_sched_in(cpuctx, ctx, current);
-
- perf_pmu_enable(cpuctx->ctx.pmu);
- perf_ctx_unlock(cpuctx, ctx);
- }
- srcu_read_unlock(&pmus_srcu, idx);
-}
-
-static int perf_resume(void)
-{
- get_online_cpus();
- smp_call_function(perf_pm_resume_cpu, NULL, 1);
- put_online_cpus();
-
- return NOTIFY_OK;
-}
-
-static int perf_suspend(void)
-{
- get_online_cpus();
- smp_call_function(perf_pm_suspend_cpu, NULL, 1);
- put_online_cpus();
-
- return NOTIFY_OK;
-}
-
-static int perf_pm(struct notifier_block *self, unsigned long action, void *ptr)
-{
- switch (action) {
- case PM_POST_HIBERNATION:
- case PM_POST_SUSPEND:
- return perf_resume();
- case PM_HIBERNATION_PREPARE:
- case PM_SUSPEND_PREPARE:
- return perf_suspend();
- default:
- return NOTIFY_DONE;
- }
-}
-
-static struct notifier_block perf_pm_notifier = {
- .notifier_call = perf_pm,
-};
-
void __init perf_event_init(void)
{
int ret;
@@ -7066,7 +6974,6 @@
perf_tp_register();
perf_cpu_notifier(perf_cpu_notify);
register_reboot_notifier(&perf_reboot_notifier);
- register_pm_notifier(&perf_pm_notifier);
ret = init_hw_breakpoint();
WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
diff --git a/kernel/sys.c b/kernel/sys.c
index 5845950..d06c091 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1286,6 +1286,7 @@
memset(u->nodename + len, 0, sizeof(u->nodename) - len);
errno = 0;
}
+ uts_proc_notify(UTS_PROC_HOSTNAME);
up_write(&uts_sem);
return errno;
}
@@ -1336,6 +1337,7 @@
memset(u->domainname + len, 0, sizeof(u->domainname) - len);
errno = 0;
}
+ uts_proc_notify(UTS_PROC_DOMAINNAME);
up_write(&uts_sem);
return errno;
}
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index a2cd77e..3b0d48e 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -13,6 +13,7 @@
#include <linux/uts.h>
#include <linux/utsname.h>
#include <linux/sysctl.h>
+#include <linux/wait.h>
static void *get_uts(ctl_table *table, int write)
{
@@ -51,12 +52,19 @@
uts_table.data = get_uts(table, write);
r = proc_dostring(&uts_table,write,buffer,lenp, ppos);
put_uts(table, write, uts_table.data);
+
+ if (write)
+ proc_sys_poll_notify(table->poll);
+
return r;
}
#else
#define proc_do_uts_string NULL
#endif
+static DEFINE_CTL_TABLE_POLL(hostname_poll);
+static DEFINE_CTL_TABLE_POLL(domainname_poll);
+
static struct ctl_table uts_kern_table[] = {
{
.procname = "ostype",
@@ -85,6 +93,7 @@
.maxlen = sizeof(init_uts_ns.name.nodename),
.mode = 0644,
.proc_handler = proc_do_uts_string,
+ .poll = &hostname_poll,
},
{
.procname = "domainname",
@@ -92,6 +101,7 @@
.maxlen = sizeof(init_uts_ns.name.domainname),
.mode = 0644,
.proc_handler = proc_do_uts_string,
+ .poll = &domainname_poll,
},
{}
};
@@ -105,6 +115,19 @@
{}
};
+#ifdef CONFIG_PROC_SYSCTL
+/*
+ * Notify userspace about a change in a certain entry of uts_kern_table,
+ * identified by the parameter proc.
+ */
+void uts_proc_notify(enum uts_proc proc)
+{
+ struct ctl_table *table = &uts_kern_table[proc];
+
+ proc_sys_poll_notify(table->poll);
+}
+#endif
+
static int __init utsname_sysctl_init(void)
{
register_sysctl_table(uts_root_table);
diff --git a/lib/idr.c b/lib/idr.c
index bbf211a..ed055b2 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -944,6 +944,7 @@
{
int ret, id;
unsigned int max;
+ unsigned long flags;
BUG_ON((int)start < 0);
BUG_ON((int)end < 0);
@@ -959,7 +960,7 @@
if (!ida_pre_get(ida, gfp_mask))
return -ENOMEM;
- spin_lock(&simple_ida_lock);
+ spin_lock_irqsave(&simple_ida_lock, flags);
ret = ida_get_new_above(ida, start, &id);
if (!ret) {
if (id > max) {
@@ -969,7 +970,7 @@
ret = id;
}
}
- spin_unlock(&simple_ida_lock);
+ spin_unlock_irqrestore(&simple_ida_lock, flags);
if (unlikely(ret == -EAGAIN))
goto again;
@@ -985,10 +986,12 @@
*/
void ida_simple_remove(struct ida *ida, unsigned int id)
{
+ unsigned long flags;
+
BUG_ON((int)id < 0);
- spin_lock(&simple_ida_lock);
+ spin_lock_irqsave(&simple_ida_lock, flags);
ida_remove(ida, id);
- spin_unlock(&simple_ida_lock);
+ spin_unlock_irqrestore(&simple_ida_lock, flags);
}
EXPORT_SYMBOL(ida_simple_remove);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 860ec21..4298aba 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -990,7 +990,7 @@
page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
VM_BUG_ON(!PageCompound(page));
if (flags & FOLL_GET)
- get_page(page);
+ get_page_foll(page);
out:
return page;
@@ -1202,6 +1202,7 @@
unsigned long head_index = page->index;
struct zone *zone = page_zone(page);
int zonestat;
+ int tail_count = 0;
/* prevent PageLRU to go away from under us, and freeze lru stats */
spin_lock_irq(&zone->lru_lock);
@@ -1210,11 +1211,27 @@
for (i = 1; i < HPAGE_PMD_NR; i++) {
struct page *page_tail = page + i;
- /* tail_page->_count cannot change */
- atomic_sub(atomic_read(&page_tail->_count), &page->_count);
- BUG_ON(page_count(page) <= 0);
- atomic_add(page_mapcount(page) + 1, &page_tail->_count);
- BUG_ON(atomic_read(&page_tail->_count) <= 0);
+ /* tail_page->_mapcount cannot change */
+ BUG_ON(page_mapcount(page_tail) < 0);
+ tail_count += page_mapcount(page_tail);
+ /* check for overflow */
+ BUG_ON(tail_count < 0);
+ BUG_ON(atomic_read(&page_tail->_count) != 0);
+ /*
+ * tail_page->_count is zero and not changing from
+ * under us. But get_page_unless_zero() may be running
+ * from under us on the tail_page. If we used
+ * atomic_set() below instead of atomic_add(), we
+ * would then run atomic_set() concurrently with
+ * get_page_unless_zero(), and atomic_set() is
+ * implemented in C not using locked ops. spin_unlock
+ * on x86 sometime uses locked ops because of PPro
+ * errata 66, 92, so unless somebody can guarantee
+ * atomic_set() here would be safe on all archs (and
+ * not only on x86), it's safer to use atomic_add().
+ */
+ atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1,
+ &page_tail->_count);
/* after clearing PageTail the gup refcount can be released */
smp_mb();
@@ -1232,10 +1249,7 @@
(1L << PG_uptodate)));
page_tail->flags |= (1L << PG_dirty);
- /*
- * 1) clear PageTail before overwriting first_page
- * 2) clear PageTail before clearing PageHead for VM_BUG_ON
- */
+ /* clear PageTail before overwriting first_page */
smp_wmb();
/*
@@ -1252,7 +1266,6 @@
* status is achieved setting a reserved bit in the
* pmd, not by clearing the present bit.
*/
- BUG_ON(page_mapcount(page_tail));
page_tail->_mapcount = page->_mapcount;
BUG_ON(page_tail->mapping);
@@ -1269,6 +1282,8 @@
lru_add_page_tail(zone, page, page_tail);
}
+ atomic_sub(tail_count, &page->_count);
+ BUG_ON(atomic_read(&page->_count) <= 0);
__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
__mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR);
diff --git a/mm/internal.h b/mm/internal.h
index d071d38..2189af4 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -37,6 +37,52 @@
atomic_dec(&page->_count);
}
+static inline void __get_page_tail_foll(struct page *page,
+ bool get_page_head)
+{
+ /*
+ * If we're getting a tail page, the elevated page->_count is
+ * required only in the head page and we will elevate the head
+ * page->_count and tail page->_mapcount.
+ *
+ * We elevate page_tail->_mapcount for tail pages to force
+ * page_tail->_count to be zero at all times to avoid getting
+ * false positives from get_page_unless_zero() with
+ * speculative page access (like in
+ * page_cache_get_speculative()) on tail pages.
+ */
+ VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
+ VM_BUG_ON(atomic_read(&page->_count) != 0);
+ VM_BUG_ON(page_mapcount(page) < 0);
+ if (get_page_head)
+ atomic_inc(&page->first_page->_count);
+ atomic_inc(&page->_mapcount);
+}
+
+/*
+ * This is meant to be called as the FOLL_GET operation of
+ * follow_page() and it must be called while holding the proper PT
+ * lock while the pte (or pmd_trans_huge) is still mapping the page.
+ */
+static inline void get_page_foll(struct page *page)
+{
+ if (unlikely(PageTail(page)))
+ /*
+ * This is safe only because
+ * __split_huge_page_refcount() can't run under
+ * get_page_foll() because we hold the proper PT lock.
+ */
+ __get_page_tail_foll(page, true);
+ else {
+ /*
+ * Getting a normal page or the head of a compound page
+ * requires to already have an elevated page->_count.
+ */
+ VM_BUG_ON(atomic_read(&page->_count) <= 0);
+ atomic_inc(&page->_count);
+ }
+}
+
extern unsigned long highest_memmap_pfn;
/*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2d57555..7af1d5e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -201,8 +201,8 @@
struct eventfd_ctx *eventfd;
};
-static void mem_cgroup_threshold(struct mem_cgroup *mem);
-static void mem_cgroup_oom_notify(struct mem_cgroup *mem);
+static void mem_cgroup_threshold(struct mem_cgroup *memcg);
+static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
/*
* The memory controller data structure. The memory controller controls both
@@ -362,29 +362,29 @@
#define MEM_CGROUP_RECLAIM_SOFT_BIT 0x2
#define MEM_CGROUP_RECLAIM_SOFT (1 << MEM_CGROUP_RECLAIM_SOFT_BIT)
-static void mem_cgroup_get(struct mem_cgroup *mem);
-static void mem_cgroup_put(struct mem_cgroup *mem);
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
-static void drain_all_stock_async(struct mem_cgroup *mem);
+static void mem_cgroup_get(struct mem_cgroup *memcg);
+static void mem_cgroup_put(struct mem_cgroup *memcg);
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+static void drain_all_stock_async(struct mem_cgroup *memcg);
static struct mem_cgroup_per_zone *
-mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
+mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid)
{
- return &mem->info.nodeinfo[nid]->zoneinfo[zid];
+ return &memcg->info.nodeinfo[nid]->zoneinfo[zid];
}
-struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem)
+struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
{
- return &mem->css;
+ return &memcg->css;
}
static struct mem_cgroup_per_zone *
-page_cgroup_zoneinfo(struct mem_cgroup *mem, struct page *page)
+page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page)
{
int nid = page_to_nid(page);
int zid = page_zonenum(page);
- return mem_cgroup_zoneinfo(mem, nid, zid);
+ return mem_cgroup_zoneinfo(memcg, nid, zid);
}
static struct mem_cgroup_tree_per_zone *
@@ -403,7 +403,7 @@
}
static void
-__mem_cgroup_insert_exceeded(struct mem_cgroup *mem,
+__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg,
struct mem_cgroup_per_zone *mz,
struct mem_cgroup_tree_per_zone *mctz,
unsigned long long new_usage_in_excess)
@@ -437,7 +437,7 @@
}
static void
-__mem_cgroup_remove_exceeded(struct mem_cgroup *mem,
+__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
struct mem_cgroup_per_zone *mz,
struct mem_cgroup_tree_per_zone *mctz)
{
@@ -448,17 +448,17 @@
}
static void
-mem_cgroup_remove_exceeded(struct mem_cgroup *mem,
+mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
struct mem_cgroup_per_zone *mz,
struct mem_cgroup_tree_per_zone *mctz)
{
spin_lock(&mctz->lock);
- __mem_cgroup_remove_exceeded(mem, mz, mctz);
+ __mem_cgroup_remove_exceeded(memcg, mz, mctz);
spin_unlock(&mctz->lock);
}
-static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page)
+static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
{
unsigned long long excess;
struct mem_cgroup_per_zone *mz;
@@ -471,9 +471,9 @@
* Necessary to update all ancestors when hierarchy is used.
* because their event counter is not touched.
*/
- for (; mem; mem = parent_mem_cgroup(mem)) {
- mz = mem_cgroup_zoneinfo(mem, nid, zid);
- excess = res_counter_soft_limit_excess(&mem->res);
+ for (; memcg; memcg = parent_mem_cgroup(memcg)) {
+ mz = mem_cgroup_zoneinfo(memcg, nid, zid);
+ excess = res_counter_soft_limit_excess(&memcg->res);
/*
* We have to update the tree if mz is on RB-tree or
* mem is over its softlimit.
@@ -482,18 +482,18 @@
spin_lock(&mctz->lock);
/* if on-tree, remove it */
if (mz->on_tree)
- __mem_cgroup_remove_exceeded(mem, mz, mctz);
+ __mem_cgroup_remove_exceeded(memcg, mz, mctz);
/*
* Insert again. mz->usage_in_excess will be updated.
* If excess is 0, no tree ops.
*/
- __mem_cgroup_insert_exceeded(mem, mz, mctz, excess);
+ __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess);
spin_unlock(&mctz->lock);
}
}
}
-static void mem_cgroup_remove_from_trees(struct mem_cgroup *mem)
+static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
{
int node, zone;
struct mem_cgroup_per_zone *mz;
@@ -501,9 +501,9 @@
for_each_node_state(node, N_POSSIBLE) {
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
- mz = mem_cgroup_zoneinfo(mem, node, zone);
+ mz = mem_cgroup_zoneinfo(memcg, node, zone);
mctz = soft_limit_tree_node_zone(node, zone);
- mem_cgroup_remove_exceeded(mem, mz, mctz);
+ mem_cgroup_remove_exceeded(memcg, mz, mctz);
}
}
}
@@ -564,7 +564,7 @@
* common workload, threashold and synchonization as vmstat[] should be
* implemented.
*/
-static long mem_cgroup_read_stat(struct mem_cgroup *mem,
+static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
enum mem_cgroup_stat_index idx)
{
long val = 0;
@@ -572,81 +572,83 @@
get_online_cpus();
for_each_online_cpu(cpu)
- val += per_cpu(mem->stat->count[idx], cpu);
+ val += per_cpu(memcg->stat->count[idx], cpu);
#ifdef CONFIG_HOTPLUG_CPU
- spin_lock(&mem->pcp_counter_lock);
- val += mem->nocpu_base.count[idx];
- spin_unlock(&mem->pcp_counter_lock);
+ spin_lock(&memcg->pcp_counter_lock);
+ val += memcg->nocpu_base.count[idx];
+ spin_unlock(&memcg->pcp_counter_lock);
#endif
put_online_cpus();
return val;
}
-static void mem_cgroup_swap_statistics(struct mem_cgroup *mem,
+static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
bool charge)
{
int val = (charge) ? 1 : -1;
- this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_SWAPOUT], val);
+ this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAPOUT], val);
}
-void mem_cgroup_pgfault(struct mem_cgroup *mem, int val)
+void mem_cgroup_pgfault(struct mem_cgroup *memcg, int val)
{
- this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_PGFAULT], val);
+ this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT], val);
}
-void mem_cgroup_pgmajfault(struct mem_cgroup *mem, int val)
+void mem_cgroup_pgmajfault(struct mem_cgroup *memcg, int val)
{
- this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT], val);
+ this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT], val);
}
-static unsigned long mem_cgroup_read_events(struct mem_cgroup *mem,
+static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
enum mem_cgroup_events_index idx)
{
unsigned long val = 0;
int cpu;
for_each_online_cpu(cpu)
- val += per_cpu(mem->stat->events[idx], cpu);
+ val += per_cpu(memcg->stat->events[idx], cpu);
#ifdef CONFIG_HOTPLUG_CPU
- spin_lock(&mem->pcp_counter_lock);
- val += mem->nocpu_base.events[idx];
- spin_unlock(&mem->pcp_counter_lock);
+ spin_lock(&memcg->pcp_counter_lock);
+ val += memcg->nocpu_base.events[idx];
+ spin_unlock(&memcg->pcp_counter_lock);
#endif
return val;
}
-static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
+static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
bool file, int nr_pages)
{
preempt_disable();
if (file)
- __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages);
+ __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
+ nr_pages);
else
- __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], nr_pages);
+ __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
+ nr_pages);
/* pagein of a big page is an event. So, ignore page size */
if (nr_pages > 0)
- __this_cpu_inc(mem->stat->events[MEM_CGROUP_EVENTS_PGPGIN]);
+ __this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]);
else {
- __this_cpu_inc(mem->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]);
+ __this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]);
nr_pages = -nr_pages; /* for event */
}
- __this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_COUNT], nr_pages);
+ __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT], nr_pages);
preempt_enable();
}
unsigned long
-mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *mem, int nid, int zid,
+mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
unsigned int lru_mask)
{
struct mem_cgroup_per_zone *mz;
enum lru_list l;
unsigned long ret = 0;
- mz = mem_cgroup_zoneinfo(mem, nid, zid);
+ mz = mem_cgroup_zoneinfo(memcg, nid, zid);
for_each_lru(l) {
if (BIT(l) & lru_mask)
@@ -656,44 +658,45 @@
}
static unsigned long
-mem_cgroup_node_nr_lru_pages(struct mem_cgroup *mem,
+mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
int nid, unsigned int lru_mask)
{
u64 total = 0;
int zid;
for (zid = 0; zid < MAX_NR_ZONES; zid++)
- total += mem_cgroup_zone_nr_lru_pages(mem, nid, zid, lru_mask);
+ total += mem_cgroup_zone_nr_lru_pages(memcg,
+ nid, zid, lru_mask);
return total;
}
-static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *mem,
+static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg,
unsigned int lru_mask)
{
int nid;
u64 total = 0;
for_each_node_state(nid, N_HIGH_MEMORY)
- total += mem_cgroup_node_nr_lru_pages(mem, nid, lru_mask);
+ total += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask);
return total;
}
-static bool __memcg_event_check(struct mem_cgroup *mem, int target)
+static bool __memcg_event_check(struct mem_cgroup *memcg, int target)
{
unsigned long val, next;
- val = this_cpu_read(mem->stat->events[MEM_CGROUP_EVENTS_COUNT]);
- next = this_cpu_read(mem->stat->targets[target]);
+ val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
+ next = __this_cpu_read(memcg->stat->targets[target]);
/* from time_after() in jiffies.h */
return ((long)next - (long)val < 0);
}
-static void __mem_cgroup_target_update(struct mem_cgroup *mem, int target)
+static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target)
{
unsigned long val, next;
- val = this_cpu_read(mem->stat->events[MEM_CGROUP_EVENTS_COUNT]);
+ val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
switch (target) {
case MEM_CGROUP_TARGET_THRESH:
@@ -709,34 +712,36 @@
return;
}
- this_cpu_write(mem->stat->targets[target], next);
+ __this_cpu_write(memcg->stat->targets[target], next);
}
/*
* Check events in order.
*
*/
-static void memcg_check_events(struct mem_cgroup *mem, struct page *page)
+static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
{
+ preempt_disable();
/* threshold event is triggered in finer grain than soft limit */
- if (unlikely(__memcg_event_check(mem, MEM_CGROUP_TARGET_THRESH))) {
- mem_cgroup_threshold(mem);
- __mem_cgroup_target_update(mem, MEM_CGROUP_TARGET_THRESH);
- if (unlikely(__memcg_event_check(mem,
+ if (unlikely(__memcg_event_check(memcg, MEM_CGROUP_TARGET_THRESH))) {
+ mem_cgroup_threshold(memcg);
+ __mem_cgroup_target_update(memcg, MEM_CGROUP_TARGET_THRESH);
+ if (unlikely(__memcg_event_check(memcg,
MEM_CGROUP_TARGET_SOFTLIMIT))) {
- mem_cgroup_update_tree(mem, page);
- __mem_cgroup_target_update(mem,
+ mem_cgroup_update_tree(memcg, page);
+ __mem_cgroup_target_update(memcg,
MEM_CGROUP_TARGET_SOFTLIMIT);
}
#if MAX_NUMNODES > 1
- if (unlikely(__memcg_event_check(mem,
+ if (unlikely(__memcg_event_check(memcg,
MEM_CGROUP_TARGET_NUMAINFO))) {
- atomic_inc(&mem->numainfo_events);
- __mem_cgroup_target_update(mem,
+ atomic_inc(&memcg->numainfo_events);
+ __mem_cgroup_target_update(memcg,
MEM_CGROUP_TARGET_NUMAINFO);
}
#endif
}
+ preempt_enable();
}
static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
@@ -762,7 +767,7 @@
struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
{
- struct mem_cgroup *mem = NULL;
+ struct mem_cgroup *memcg = NULL;
if (!mm)
return NULL;
@@ -773,25 +778,25 @@
*/
rcu_read_lock();
do {
- mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
- if (unlikely(!mem))
+ memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ if (unlikely(!memcg))
break;
- } while (!css_tryget(&mem->css));
+ } while (!css_tryget(&memcg->css));
rcu_read_unlock();
- return mem;
+ return memcg;
}
/* The caller has to guarantee "mem" exists before calling this */
-static struct mem_cgroup *mem_cgroup_start_loop(struct mem_cgroup *mem)
+static struct mem_cgroup *mem_cgroup_start_loop(struct mem_cgroup *memcg)
{
struct cgroup_subsys_state *css;
int found;
- if (!mem) /* ROOT cgroup has the smallest ID */
+ if (!memcg) /* ROOT cgroup has the smallest ID */
return root_mem_cgroup; /*css_put/get against root is ignored*/
- if (!mem->use_hierarchy) {
- if (css_tryget(&mem->css))
- return mem;
+ if (!memcg->use_hierarchy) {
+ if (css_tryget(&memcg->css))
+ return memcg;
return NULL;
}
rcu_read_lock();
@@ -799,13 +804,13 @@
* searching a memory cgroup which has the smallest ID under given
* ROOT cgroup. (ID >= 1)
*/
- css = css_get_next(&mem_cgroup_subsys, 1, &mem->css, &found);
+ css = css_get_next(&mem_cgroup_subsys, 1, &memcg->css, &found);
if (css && css_tryget(css))
- mem = container_of(css, struct mem_cgroup, css);
+ memcg = container_of(css, struct mem_cgroup, css);
else
- mem = NULL;
+ memcg = NULL;
rcu_read_unlock();
- return mem;
+ return memcg;
}
static struct mem_cgroup *mem_cgroup_get_next(struct mem_cgroup *iter,
@@ -859,29 +864,29 @@
for_each_mem_cgroup_tree_cond(iter, NULL, true)
-static inline bool mem_cgroup_is_root(struct mem_cgroup *mem)
+static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
{
- return (mem == root_mem_cgroup);
+ return (memcg == root_mem_cgroup);
}
void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup *memcg;
if (!mm)
return;
rcu_read_lock();
- mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
- if (unlikely(!mem))
+ memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ if (unlikely(!memcg))
goto out;
switch (idx) {
case PGMAJFAULT:
- mem_cgroup_pgmajfault(mem, 1);
+ mem_cgroup_pgmajfault(memcg, 1);
break;
case PGFAULT:
- mem_cgroup_pgfault(mem, 1);
+ mem_cgroup_pgfault(memcg, 1);
break;
default:
BUG();
@@ -990,6 +995,16 @@
return;
pc = lookup_page_cgroup(page);
VM_BUG_ON(PageCgroupAcctLRU(pc));
+ /*
+ * putback: charge:
+ * SetPageLRU SetPageCgroupUsed
+ * smp_mb smp_mb
+ * PageCgroupUsed && add to memcg LRU PageLRU && add to memcg LRU
+ *
+ * Ensure that one of the two sides adds the page to the memcg
+ * LRU during a race.
+ */
+ smp_mb();
if (!PageCgroupUsed(pc))
return;
/* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
@@ -1041,7 +1056,16 @@
unsigned long flags;
struct zone *zone = page_zone(page);
struct page_cgroup *pc = lookup_page_cgroup(page);
-
+ /*
+ * putback: charge:
+ * SetPageLRU SetPageCgroupUsed
+ * smp_mb smp_mb
+ * PageCgroupUsed && add to memcg LRU PageLRU && add to memcg LRU
+ *
+ * Ensure that one of the two sides adds the page to the memcg
+ * LRU during a race.
+ */
+ smp_mb();
/* taking care of that the page is added to LRU while we commit it */
if (likely(!PageLRU(page)))
return;
@@ -1063,21 +1087,21 @@
}
/*
- * Checks whether given mem is same or in the root_mem's
+ * Checks whether given mem is same or in the root_mem_cgroup's
* hierarchy subtree
*/
-static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_mem,
- struct mem_cgroup *mem)
+static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
+ struct mem_cgroup *memcg)
{
- if (root_mem != mem) {
- return (root_mem->use_hierarchy &&
- css_is_ancestor(&mem->css, &root_mem->css));
+ if (root_memcg != memcg) {
+ return (root_memcg->use_hierarchy &&
+ css_is_ancestor(&memcg->css, &root_memcg->css));
}
return true;
}
-int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
+int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg)
{
int ret;
struct mem_cgroup *curr = NULL;
@@ -1091,25 +1115,29 @@
if (!curr)
return 0;
/*
- * We should check use_hierarchy of "mem" not "curr". Because checking
+ * We should check use_hierarchy of "memcg" not "curr". Because checking
* use_hierarchy of "curr" here make this function true if hierarchy is
- * enabled in "curr" and "curr" is a child of "mem" in *cgroup*
- * hierarchy(even if use_hierarchy is disabled in "mem").
+ * enabled in "curr" and "curr" is a child of "memcg" in *cgroup*
+ * hierarchy(even if use_hierarchy is disabled in "memcg").
*/
- ret = mem_cgroup_same_or_subtree(mem, curr);
+ ret = mem_cgroup_same_or_subtree(memcg, curr);
css_put(&curr->css);
return ret;
}
-static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages)
+int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone)
{
- unsigned long active;
- unsigned long inactive;
- unsigned long gb;
unsigned long inactive_ratio;
+ int nid = zone_to_nid(zone);
+ int zid = zone_idx(zone);
+ unsigned long inactive;
+ unsigned long active;
+ unsigned long gb;
- inactive = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_ANON));
- active = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_ANON));
+ inactive = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+ BIT(LRU_INACTIVE_ANON));
+ active = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+ BIT(LRU_ACTIVE_ANON));
gb = (inactive + active) >> (30 - PAGE_SHIFT);
if (gb)
@@ -1117,39 +1145,20 @@
else
inactive_ratio = 1;
- if (present_pages) {
- present_pages[0] = inactive;
- present_pages[1] = active;
- }
-
- return inactive_ratio;
+ return inactive * inactive_ratio < active;
}
-int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
+int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, struct zone *zone)
{
unsigned long active;
unsigned long inactive;
- unsigned long present_pages[2];
- unsigned long inactive_ratio;
+ int zid = zone_idx(zone);
+ int nid = zone_to_nid(zone);
- inactive_ratio = calc_inactive_ratio(memcg, present_pages);
-
- inactive = present_pages[0];
- active = present_pages[1];
-
- if (inactive * inactive_ratio < active)
- return 1;
-
- return 0;
-}
-
-int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
-{
- unsigned long active;
- unsigned long inactive;
-
- inactive = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_FILE));
- active = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_FILE));
+ inactive = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+ BIT(LRU_INACTIVE_FILE));
+ active = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
+ BIT(LRU_ACTIVE_FILE));
return (active > inactive);
}
@@ -1254,13 +1263,13 @@
* Returns the maximum amount of memory @mem can be charged with, in
* pages.
*/
-static unsigned long mem_cgroup_margin(struct mem_cgroup *mem)
+static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
{
unsigned long long margin;
- margin = res_counter_margin(&mem->res);
+ margin = res_counter_margin(&memcg->res);
if (do_swap_account)
- margin = min(margin, res_counter_margin(&mem->memsw));
+ margin = min(margin, res_counter_margin(&memcg->memsw));
return margin >> PAGE_SHIFT;
}
@@ -1275,33 +1284,33 @@
return memcg->swappiness;
}
-static void mem_cgroup_start_move(struct mem_cgroup *mem)
+static void mem_cgroup_start_move(struct mem_cgroup *memcg)
{
int cpu;
get_online_cpus();
- spin_lock(&mem->pcp_counter_lock);
+ spin_lock(&memcg->pcp_counter_lock);
for_each_online_cpu(cpu)
- per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
- mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1;
- spin_unlock(&mem->pcp_counter_lock);
+ per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
+ memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1;
+ spin_unlock(&memcg->pcp_counter_lock);
put_online_cpus();
synchronize_rcu();
}
-static void mem_cgroup_end_move(struct mem_cgroup *mem)
+static void mem_cgroup_end_move(struct mem_cgroup *memcg)
{
int cpu;
- if (!mem)
+ if (!memcg)
return;
get_online_cpus();
- spin_lock(&mem->pcp_counter_lock);
+ spin_lock(&memcg->pcp_counter_lock);
for_each_online_cpu(cpu)
- per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
- mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1;
- spin_unlock(&mem->pcp_counter_lock);
+ per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
+ memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1;
+ spin_unlock(&memcg->pcp_counter_lock);
put_online_cpus();
}
/*
@@ -1316,13 +1325,13 @@
* waiting at hith-memory prressure caused by "move".
*/
-static bool mem_cgroup_stealed(struct mem_cgroup *mem)
+static bool mem_cgroup_stealed(struct mem_cgroup *memcg)
{
VM_BUG_ON(!rcu_read_lock_held());
- return this_cpu_read(mem->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
+ return this_cpu_read(memcg->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
}
-static bool mem_cgroup_under_move(struct mem_cgroup *mem)
+static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
{
struct mem_cgroup *from;
struct mem_cgroup *to;
@@ -1337,17 +1346,17 @@
if (!from)
goto unlock;
- ret = mem_cgroup_same_or_subtree(mem, from)
- || mem_cgroup_same_or_subtree(mem, to);
+ ret = mem_cgroup_same_or_subtree(memcg, from)
+ || mem_cgroup_same_or_subtree(memcg, to);
unlock:
spin_unlock(&mc.lock);
return ret;
}
-static bool mem_cgroup_wait_acct_move(struct mem_cgroup *mem)
+static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg)
{
if (mc.moving_task && current != mc.moving_task) {
- if (mem_cgroup_under_move(mem)) {
+ if (mem_cgroup_under_move(memcg)) {
DEFINE_WAIT(wait);
prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE);
/* moving charge context might have finished. */
@@ -1431,12 +1440,12 @@
* This function returns the number of memcg under hierarchy tree. Returns
* 1(self count) if no children.
*/
-static int mem_cgroup_count_children(struct mem_cgroup *mem)
+static int mem_cgroup_count_children(struct mem_cgroup *memcg)
{
int num = 0;
struct mem_cgroup *iter;
- for_each_mem_cgroup_tree(iter, mem)
+ for_each_mem_cgroup_tree(iter, memcg)
num++;
return num;
}
@@ -1466,21 +1475,21 @@
* that to reclaim free pages from.
*/
static struct mem_cgroup *
-mem_cgroup_select_victim(struct mem_cgroup *root_mem)
+mem_cgroup_select_victim(struct mem_cgroup *root_memcg)
{
struct mem_cgroup *ret = NULL;
struct cgroup_subsys_state *css;
int nextid, found;
- if (!root_mem->use_hierarchy) {
- css_get(&root_mem->css);
- ret = root_mem;
+ if (!root_memcg->use_hierarchy) {
+ css_get(&root_memcg->css);
+ ret = root_memcg;
}
while (!ret) {
rcu_read_lock();
- nextid = root_mem->last_scanned_child + 1;
- css = css_get_next(&mem_cgroup_subsys, nextid, &root_mem->css,
+ nextid = root_memcg->last_scanned_child + 1;
+ css = css_get_next(&mem_cgroup_subsys, nextid, &root_memcg->css,
&found);
if (css && css_tryget(css))
ret = container_of(css, struct mem_cgroup, css);
@@ -1489,9 +1498,9 @@
/* Updates scanning parameter */
if (!css) {
/* this means start scan from ID:1 */
- root_mem->last_scanned_child = 0;
+ root_memcg->last_scanned_child = 0;
} else
- root_mem->last_scanned_child = found;
+ root_memcg->last_scanned_child = found;
}
return ret;
@@ -1507,14 +1516,14 @@
* reclaimable pages on a node. Returns true if there are any reclaimable
* pages in the node.
*/
-static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *mem,
+static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg,
int nid, bool noswap)
{
- if (mem_cgroup_node_nr_lru_pages(mem, nid, LRU_ALL_FILE))
+ if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_FILE))
return true;
if (noswap || !total_swap_pages)
return false;
- if (mem_cgroup_node_nr_lru_pages(mem, nid, LRU_ALL_ANON))
+ if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_ANON))
return true;
return false;
@@ -1527,29 +1536,29 @@
* nodes based on the zonelist. So update the list loosely once per 10 secs.
*
*/
-static void mem_cgroup_may_update_nodemask(struct mem_cgroup *mem)
+static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg)
{
int nid;
/*
* numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET
* pagein/pageout changes since the last update.
*/
- if (!atomic_read(&mem->numainfo_events))
+ if (!atomic_read(&memcg->numainfo_events))
return;
- if (atomic_inc_return(&mem->numainfo_updating) > 1)
+ if (atomic_inc_return(&memcg->numainfo_updating) > 1)
return;
/* make a nodemask where this memcg uses memory from */
- mem->scan_nodes = node_states[N_HIGH_MEMORY];
+ memcg->scan_nodes = node_states[N_HIGH_MEMORY];
for_each_node_mask(nid, node_states[N_HIGH_MEMORY]) {
- if (!test_mem_cgroup_node_reclaimable(mem, nid, false))
- node_clear(nid, mem->scan_nodes);
+ if (!test_mem_cgroup_node_reclaimable(memcg, nid, false))
+ node_clear(nid, memcg->scan_nodes);
}
- atomic_set(&mem->numainfo_events, 0);
- atomic_set(&mem->numainfo_updating, 0);
+ atomic_set(&memcg->numainfo_events, 0);
+ atomic_set(&memcg->numainfo_updating, 0);
}
/*
@@ -1564,16 +1573,16 @@
*
* Now, we use round-robin. Better algorithm is welcomed.
*/
-int mem_cgroup_select_victim_node(struct mem_cgroup *mem)
+int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
{
int node;
- mem_cgroup_may_update_nodemask(mem);
- node = mem->last_scanned_node;
+ mem_cgroup_may_update_nodemask(memcg);
+ node = memcg->last_scanned_node;
- node = next_node(node, mem->scan_nodes);
+ node = next_node(node, memcg->scan_nodes);
if (node == MAX_NUMNODES)
- node = first_node(mem->scan_nodes);
+ node = first_node(memcg->scan_nodes);
/*
* We call this when we hit limit, not when pages are added to LRU.
* No LRU may hold pages because all pages are UNEVICTABLE or
@@ -1583,7 +1592,7 @@
if (unlikely(node == MAX_NUMNODES))
node = numa_node_id();
- mem->last_scanned_node = node;
+ memcg->last_scanned_node = node;
return node;
}
@@ -1593,7 +1602,7 @@
* unused nodes. But scan_nodes is lazily updated and may not cotain
* enough new information. We need to do double check.
*/
-bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
+bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
{
int nid;
@@ -1601,12 +1610,12 @@
* quick check...making use of scan_node.
* We can skip unused nodes.
*/
- if (!nodes_empty(mem->scan_nodes)) {
- for (nid = first_node(mem->scan_nodes);
+ if (!nodes_empty(memcg->scan_nodes)) {
+ for (nid = first_node(memcg->scan_nodes);
nid < MAX_NUMNODES;
- nid = next_node(nid, mem->scan_nodes)) {
+ nid = next_node(nid, memcg->scan_nodes)) {
- if (test_mem_cgroup_node_reclaimable(mem, nid, noswap))
+ if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
return true;
}
}
@@ -1614,23 +1623,23 @@
* Check rest of nodes.
*/
for_each_node_state(nid, N_HIGH_MEMORY) {
- if (node_isset(nid, mem->scan_nodes))
+ if (node_isset(nid, memcg->scan_nodes))
continue;
- if (test_mem_cgroup_node_reclaimable(mem, nid, noswap))
+ if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
return true;
}
return false;
}
#else
-int mem_cgroup_select_victim_node(struct mem_cgroup *mem)
+int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
{
return 0;
}
-bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
+bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
{
- return test_mem_cgroup_node_reclaimable(mem, 0, noswap);
+ return test_mem_cgroup_node_reclaimable(memcg, 0, noswap);
}
#endif
@@ -1639,14 +1648,14 @@
* we reclaimed from, so that we don't end up penalizing one child extensively
* based on its position in the children list.
*
- * root_mem is the original ancestor that we've been reclaim from.
+ * root_memcg is the original ancestor that we've been reclaim from.
*
- * We give up and return to the caller when we visit root_mem twice.
+ * We give up and return to the caller when we visit root_memcg twice.
* (other groups can be removed while we're walking....)
*
* If shrink==true, for avoiding to free too much, this returns immedieately.
*/
-static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
+static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_memcg,
struct zone *zone,
gfp_t gfp_mask,
unsigned long reclaim_options,
@@ -1661,15 +1670,15 @@
unsigned long excess;
unsigned long nr_scanned;
- excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
+ excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;
/* If memsw_is_minimum==1, swap-out is of-no-use. */
- if (!check_soft && !shrink && root_mem->memsw_is_minimum)
+ if (!check_soft && !shrink && root_memcg->memsw_is_minimum)
noswap = true;
while (1) {
- victim = mem_cgroup_select_victim(root_mem);
- if (victim == root_mem) {
+ victim = mem_cgroup_select_victim(root_memcg);
+ if (victim == root_memcg) {
loop++;
/*
* We are not draining per cpu cached charges during
@@ -1678,7 +1687,7 @@
* charges will not give any.
*/
if (!check_soft && loop >= 1)
- drain_all_stock_async(root_mem);
+ drain_all_stock_async(root_memcg);
if (loop >= 2) {
/*
* If we have not been able to reclaim
@@ -1725,9 +1734,9 @@
return ret;
total += ret;
if (check_soft) {
- if (!res_counter_soft_limit_excess(&root_mem->res))
+ if (!res_counter_soft_limit_excess(&root_memcg->res))
return total;
- } else if (mem_cgroup_margin(root_mem))
+ } else if (mem_cgroup_margin(root_memcg))
return total;
}
return total;
@@ -1738,12 +1747,12 @@
* If someone is running, return false.
* Has to be called with memcg_oom_lock
*/
-static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
+static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter, *failed = NULL;
bool cond = true;
- for_each_mem_cgroup_tree_cond(iter, mem, cond) {
+ for_each_mem_cgroup_tree_cond(iter, memcg, cond) {
if (iter->oom_lock) {
/*
* this subtree of our hierarchy is already locked
@@ -1763,7 +1772,7 @@
* what we set up to the failing subtree
*/
cond = true;
- for_each_mem_cgroup_tree_cond(iter, mem, cond) {
+ for_each_mem_cgroup_tree_cond(iter, memcg, cond) {
if (iter == failed) {
cond = false;
continue;
@@ -1776,24 +1785,24 @@
/*
* Has to be called with memcg_oom_lock
*/
-static int mem_cgroup_oom_unlock(struct mem_cgroup *mem)
+static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter;
- for_each_mem_cgroup_tree(iter, mem)
+ for_each_mem_cgroup_tree(iter, memcg)
iter->oom_lock = false;
return 0;
}
-static void mem_cgroup_mark_under_oom(struct mem_cgroup *mem)
+static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter;
- for_each_mem_cgroup_tree(iter, mem)
+ for_each_mem_cgroup_tree(iter, memcg)
atomic_inc(&iter->under_oom);
}
-static void mem_cgroup_unmark_under_oom(struct mem_cgroup *mem)
+static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter;
@@ -1802,7 +1811,7 @@
* mem_cgroup_oom_lock() may not be called. We have to use
* atomic_add_unless() here.
*/
- for_each_mem_cgroup_tree(iter, mem)
+ for_each_mem_cgroup_tree(iter, memcg)
atomic_add_unless(&iter->under_oom, -1, 0);
}
@@ -1817,85 +1826,85 @@
static int memcg_oom_wake_function(wait_queue_t *wait,
unsigned mode, int sync, void *arg)
{
- struct mem_cgroup *wake_mem = (struct mem_cgroup *)arg,
- *oom_wait_mem;
+ struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg,
+ *oom_wait_memcg;
struct oom_wait_info *oom_wait_info;
oom_wait_info = container_of(wait, struct oom_wait_info, wait);
- oom_wait_mem = oom_wait_info->mem;
+ oom_wait_memcg = oom_wait_info->mem;
/*
* Both of oom_wait_info->mem and wake_mem are stable under us.
* Then we can use css_is_ancestor without taking care of RCU.
*/
- if (!mem_cgroup_same_or_subtree(oom_wait_mem, wake_mem)
- && !mem_cgroup_same_or_subtree(wake_mem, oom_wait_mem))
+ if (!mem_cgroup_same_or_subtree(oom_wait_memcg, wake_memcg)
+ && !mem_cgroup_same_or_subtree(wake_memcg, oom_wait_memcg))
return 0;
return autoremove_wake_function(wait, mode, sync, arg);
}
-static void memcg_wakeup_oom(struct mem_cgroup *mem)
+static void memcg_wakeup_oom(struct mem_cgroup *memcg)
{
- /* for filtering, pass "mem" as argument. */
- __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, mem);
+ /* for filtering, pass "memcg" as argument. */
+ __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}
-static void memcg_oom_recover(struct mem_cgroup *mem)
+static void memcg_oom_recover(struct mem_cgroup *memcg)
{
- if (mem && atomic_read(&mem->under_oom))
- memcg_wakeup_oom(mem);
+ if (memcg && atomic_read(&memcg->under_oom))
+ memcg_wakeup_oom(memcg);
}
/*
* try to call OOM killer. returns false if we should exit memory-reclaim loop.
*/
-bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask)
+bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask)
{
struct oom_wait_info owait;
bool locked, need_to_kill;
- owait.mem = mem;
+ owait.mem = memcg;
owait.wait.flags = 0;
owait.wait.func = memcg_oom_wake_function;
owait.wait.private = current;
INIT_LIST_HEAD(&owait.wait.task_list);
need_to_kill = true;
- mem_cgroup_mark_under_oom(mem);
+ mem_cgroup_mark_under_oom(memcg);
- /* At first, try to OOM lock hierarchy under mem.*/
+ /* At first, try to OOM lock hierarchy under memcg.*/
spin_lock(&memcg_oom_lock);
- locked = mem_cgroup_oom_lock(mem);
+ locked = mem_cgroup_oom_lock(memcg);
/*
* Even if signal_pending(), we can't quit charge() loop without
* accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL
* under OOM is always welcomed, use TASK_KILLABLE here.
*/
prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
- if (!locked || mem->oom_kill_disable)
+ if (!locked || memcg->oom_kill_disable)
need_to_kill = false;
if (locked)
- mem_cgroup_oom_notify(mem);
+ mem_cgroup_oom_notify(memcg);
spin_unlock(&memcg_oom_lock);
if (need_to_kill) {
finish_wait(&memcg_oom_waitq, &owait.wait);
- mem_cgroup_out_of_memory(mem, mask);
+ mem_cgroup_out_of_memory(memcg, mask);
} else {
schedule();
finish_wait(&memcg_oom_waitq, &owait.wait);
}
spin_lock(&memcg_oom_lock);
if (locked)
- mem_cgroup_oom_unlock(mem);
- memcg_wakeup_oom(mem);
+ mem_cgroup_oom_unlock(memcg);
+ memcg_wakeup_oom(memcg);
spin_unlock(&memcg_oom_lock);
- mem_cgroup_unmark_under_oom(mem);
+ mem_cgroup_unmark_under_oom(memcg);
if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
return false;
/* Give chance to dying process */
- schedule_timeout(1);
+ schedule_timeout_uninterruptible(1);
return true;
}
@@ -1926,7 +1935,7 @@
void mem_cgroup_update_page_stat(struct page *page,
enum mem_cgroup_page_stat_item idx, int val)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup *memcg;
struct page_cgroup *pc = lookup_page_cgroup(page);
bool need_unlock = false;
unsigned long uninitialized_var(flags);
@@ -1935,16 +1944,16 @@
return;
rcu_read_lock();
- mem = pc->mem_cgroup;
- if (unlikely(!mem || !PageCgroupUsed(pc)))
+ memcg = pc->mem_cgroup;
+ if (unlikely(!memcg || !PageCgroupUsed(pc)))
goto out;
/* pc->mem_cgroup is unstable ? */
- if (unlikely(mem_cgroup_stealed(mem)) || PageTransHuge(page)) {
+ if (unlikely(mem_cgroup_stealed(memcg)) || PageTransHuge(page)) {
/* take a lock against to access pc->mem_cgroup */
move_lock_page_cgroup(pc, &flags);
need_unlock = true;
- mem = pc->mem_cgroup;
- if (!mem || !PageCgroupUsed(pc))
+ memcg = pc->mem_cgroup;
+ if (!memcg || !PageCgroupUsed(pc))
goto out;
}
@@ -1960,7 +1969,7 @@
BUG();
}
- this_cpu_add(mem->stat->count[idx], val);
+ this_cpu_add(memcg->stat->count[idx], val);
out:
if (unlikely(need_unlock))
@@ -1991,13 +2000,13 @@
* cgroup which is not current target, returns false. This stock will be
* refilled.
*/
-static bool consume_stock(struct mem_cgroup *mem)
+static bool consume_stock(struct mem_cgroup *memcg)
{
struct memcg_stock_pcp *stock;
bool ret = true;
stock = &get_cpu_var(memcg_stock);
- if (mem == stock->cached && stock->nr_pages)
+ if (memcg == stock->cached && stock->nr_pages)
stock->nr_pages--;
else /* need to call res_counter_charge */
ret = false;
@@ -2038,24 +2047,24 @@
* Cache charges(val) which is from res_counter, to local per_cpu area.
* This will be consumed by consume_stock() function, later.
*/
-static void refill_stock(struct mem_cgroup *mem, unsigned int nr_pages)
+static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
- if (stock->cached != mem) { /* reset if necessary */
+ if (stock->cached != memcg) { /* reset if necessary */
drain_stock(stock);
- stock->cached = mem;
+ stock->cached = memcg;
}
stock->nr_pages += nr_pages;
put_cpu_var(memcg_stock);
}
/*
- * Drains all per-CPU charge caches for given root_mem resp. subtree
+ * Drains all per-CPU charge caches for given root_memcg resp. subtree
* of the hierarchy under it. sync flag says whether we should block
* until the work is done.
*/
-static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
+static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync)
{
int cpu, curcpu;
@@ -2064,12 +2073,12 @@
curcpu = get_cpu();
for_each_online_cpu(cpu) {
struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
- struct mem_cgroup *mem;
+ struct mem_cgroup *memcg;
- mem = stock->cached;
- if (!mem || !stock->nr_pages)
+ memcg = stock->cached;
+ if (!memcg || !stock->nr_pages)
continue;
- if (!mem_cgroup_same_or_subtree(root_mem, mem))
+ if (!mem_cgroup_same_or_subtree(root_memcg, memcg))
continue;
if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
if (cpu == curcpu)
@@ -2098,23 +2107,23 @@
* expects some charges will be back to res_counter later but cannot wait for
* it.
*/
-static void drain_all_stock_async(struct mem_cgroup *root_mem)
+static void drain_all_stock_async(struct mem_cgroup *root_memcg)
{
/*
* If someone calls draining, avoid adding more kworker runs.
*/
if (!mutex_trylock(&percpu_charge_mutex))
return;
- drain_all_stock(root_mem, false);
+ drain_all_stock(root_memcg, false);
mutex_unlock(&percpu_charge_mutex);
}
/* This is a synchronous drain interface. */
-static void drain_all_stock_sync(struct mem_cgroup *root_mem)
+static void drain_all_stock_sync(struct mem_cgroup *root_memcg)
{
/* called when force_empty is called */
mutex_lock(&percpu_charge_mutex);
- drain_all_stock(root_mem, true);
+ drain_all_stock(root_memcg, true);
mutex_unlock(&percpu_charge_mutex);
}
@@ -2122,35 +2131,35 @@
* This function drains percpu counter value from DEAD cpu and
* move it to local cpu. Note that this function can be preempted.
*/
-static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *mem, int cpu)
+static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu)
{
int i;
- spin_lock(&mem->pcp_counter_lock);
+ spin_lock(&memcg->pcp_counter_lock);
for (i = 0; i < MEM_CGROUP_STAT_DATA; i++) {
- long x = per_cpu(mem->stat->count[i], cpu);
+ long x = per_cpu(memcg->stat->count[i], cpu);
- per_cpu(mem->stat->count[i], cpu) = 0;
- mem->nocpu_base.count[i] += x;
+ per_cpu(memcg->stat->count[i], cpu) = 0;
+ memcg->nocpu_base.count[i] += x;
}
for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
- unsigned long x = per_cpu(mem->stat->events[i], cpu);
+ unsigned long x = per_cpu(memcg->stat->events[i], cpu);
- per_cpu(mem->stat->events[i], cpu) = 0;
- mem->nocpu_base.events[i] += x;
+ per_cpu(memcg->stat->events[i], cpu) = 0;
+ memcg->nocpu_base.events[i] += x;
}
/* need to clear ON_MOVE value, works as a kind of lock. */
- per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0;
- spin_unlock(&mem->pcp_counter_lock);
+ per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0;
+ spin_unlock(&memcg->pcp_counter_lock);
}
-static void synchronize_mem_cgroup_on_move(struct mem_cgroup *mem, int cpu)
+static void synchronize_mem_cgroup_on_move(struct mem_cgroup *memcg, int cpu)
{
int idx = MEM_CGROUP_ON_MOVE;
- spin_lock(&mem->pcp_counter_lock);
- per_cpu(mem->stat->count[idx], cpu) = mem->nocpu_base.count[idx];
- spin_unlock(&mem->pcp_counter_lock);
+ spin_lock(&memcg->pcp_counter_lock);
+ per_cpu(memcg->stat->count[idx], cpu) = memcg->nocpu_base.count[idx];
+ spin_unlock(&memcg->pcp_counter_lock);
}
static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
@@ -2188,7 +2197,7 @@
CHARGE_OOM_DIE, /* the current is killed because of OOM */
};
-static int mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask,
+static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
unsigned int nr_pages, bool oom_check)
{
unsigned long csize = nr_pages * PAGE_SIZE;
@@ -2197,16 +2206,16 @@
unsigned long flags = 0;
int ret;
- ret = res_counter_charge(&mem->res, csize, &fail_res);
+ ret = res_counter_charge(&memcg->res, csize, &fail_res);
if (likely(!ret)) {
if (!do_swap_account)
return CHARGE_OK;
- ret = res_counter_charge(&mem->memsw, csize, &fail_res);
+ ret = res_counter_charge(&memcg->memsw, csize, &fail_res);
if (likely(!ret))
return CHARGE_OK;
- res_counter_uncharge(&mem->res, csize);
+ res_counter_uncharge(&memcg->res, csize);
mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
flags |= MEM_CGROUP_RECLAIM_NOSWAP;
} else
@@ -2264,12 +2273,12 @@
static int __mem_cgroup_try_charge(struct mm_struct *mm,
gfp_t gfp_mask,
unsigned int nr_pages,
- struct mem_cgroup **memcg,
+ struct mem_cgroup **ptr,
bool oom)
{
unsigned int batch = max(CHARGE_BATCH, nr_pages);
int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
- struct mem_cgroup *mem = NULL;
+ struct mem_cgroup *memcg = NULL;
int ret;
/*
@@ -2287,17 +2296,17 @@
* thread group leader migrates. It's possible that mm is not
* set, if so charge the init_mm (happens for pagecache usage).
*/
- if (!*memcg && !mm)
+ if (!*ptr && !mm)
goto bypass;
again:
- if (*memcg) { /* css should be a valid one */
- mem = *memcg;
- VM_BUG_ON(css_is_removed(&mem->css));
- if (mem_cgroup_is_root(mem))
+ if (*ptr) { /* css should be a valid one */
+ memcg = *ptr;
+ VM_BUG_ON(css_is_removed(&memcg->css));
+ if (mem_cgroup_is_root(memcg))
goto done;
- if (nr_pages == 1 && consume_stock(mem))
+ if (nr_pages == 1 && consume_stock(memcg))
goto done;
- css_get(&mem->css);
+ css_get(&memcg->css);
} else {
struct task_struct *p;
@@ -2305,7 +2314,7 @@
p = rcu_dereference(mm->owner);
/*
* Because we don't have task_lock(), "p" can exit.
- * In that case, "mem" can point to root or p can be NULL with
+ * In that case, "memcg" can point to root or p can be NULL with
* race with swapoff. Then, we have small risk of mis-accouning.
* But such kind of mis-account by race always happens because
* we don't have cgroup_mutex(). It's overkill and we allo that
@@ -2313,12 +2322,12 @@
* (*) swapoff at el will charge against mm-struct not against
* task-struct. So, mm->owner can be NULL.
*/
- mem = mem_cgroup_from_task(p);
- if (!mem || mem_cgroup_is_root(mem)) {
+ memcg = mem_cgroup_from_task(p);
+ if (!memcg || mem_cgroup_is_root(memcg)) {
rcu_read_unlock();
goto done;
}
- if (nr_pages == 1 && consume_stock(mem)) {
+ if (nr_pages == 1 && consume_stock(memcg)) {
/*
* It seems dagerous to access memcg without css_get().
* But considering how consume_stok works, it's not
@@ -2331,7 +2340,7 @@
goto done;
}
/* after here, we may be blocked. we need to get refcnt */
- if (!css_tryget(&mem->css)) {
+ if (!css_tryget(&memcg->css)) {
rcu_read_unlock();
goto again;
}
@@ -2343,7 +2352,7 @@
/* If killed, bypass charge */
if (fatal_signal_pending(current)) {
- css_put(&mem->css);
+ css_put(&memcg->css);
goto bypass;
}
@@ -2353,43 +2362,43 @@
nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
}
- ret = mem_cgroup_do_charge(mem, gfp_mask, batch, oom_check);
+ ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, oom_check);
switch (ret) {
case CHARGE_OK:
break;
case CHARGE_RETRY: /* not in OOM situation but retry */
batch = nr_pages;
- css_put(&mem->css);
- mem = NULL;
+ css_put(&memcg->css);
+ memcg = NULL;
goto again;
case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */
- css_put(&mem->css);
+ css_put(&memcg->css);
goto nomem;
case CHARGE_NOMEM: /* OOM routine works */
if (!oom) {
- css_put(&mem->css);
+ css_put(&memcg->css);
goto nomem;
}
/* If oom, we never return -ENOMEM */
nr_oom_retries--;
break;
case CHARGE_OOM_DIE: /* Killed by OOM Killer */
- css_put(&mem->css);
+ css_put(&memcg->css);
goto bypass;
}
} while (ret != CHARGE_OK);
if (batch > nr_pages)
- refill_stock(mem, batch - nr_pages);
- css_put(&mem->css);
+ refill_stock(memcg, batch - nr_pages);
+ css_put(&memcg->css);
done:
- *memcg = mem;
+ *ptr = memcg;
return 0;
nomem:
- *memcg = NULL;
+ *ptr = NULL;
return -ENOMEM;
bypass:
- *memcg = NULL;
+ *ptr = NULL;
return 0;
}
@@ -2398,15 +2407,15 @@
* This function is for that and do uncharge, put css's refcnt.
* gotten by try_charge().
*/
-static void __mem_cgroup_cancel_charge(struct mem_cgroup *mem,
+static void __mem_cgroup_cancel_charge(struct mem_cgroup *memcg,
unsigned int nr_pages)
{
- if (!mem_cgroup_is_root(mem)) {
+ if (!mem_cgroup_is_root(memcg)) {
unsigned long bytes = nr_pages * PAGE_SIZE;
- res_counter_uncharge(&mem->res, bytes);
+ res_counter_uncharge(&memcg->res, bytes);
if (do_swap_account)
- res_counter_uncharge(&mem->memsw, bytes);
+ res_counter_uncharge(&memcg->memsw, bytes);
}
}
@@ -2431,7 +2440,7 @@
struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
{
- struct mem_cgroup *mem = NULL;
+ struct mem_cgroup *memcg = NULL;
struct page_cgroup *pc;
unsigned short id;
swp_entry_t ent;
@@ -2441,23 +2450,23 @@
pc = lookup_page_cgroup(page);
lock_page_cgroup(pc);
if (PageCgroupUsed(pc)) {
- mem = pc->mem_cgroup;
- if (mem && !css_tryget(&mem->css))
- mem = NULL;
+ memcg = pc->mem_cgroup;
+ if (memcg && !css_tryget(&memcg->css))
+ memcg = NULL;
} else if (PageSwapCache(page)) {
ent.val = page_private(page);
id = lookup_swap_cgroup(ent);
rcu_read_lock();
- mem = mem_cgroup_lookup(id);
- if (mem && !css_tryget(&mem->css))
- mem = NULL;
+ memcg = mem_cgroup_lookup(id);
+ if (memcg && !css_tryget(&memcg->css))
+ memcg = NULL;
rcu_read_unlock();
}
unlock_page_cgroup(pc);
- return mem;
+ return memcg;
}
-static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
+static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
struct page *page,
unsigned int nr_pages,
struct page_cgroup *pc,
@@ -2466,14 +2475,14 @@
lock_page_cgroup(pc);
if (unlikely(PageCgroupUsed(pc))) {
unlock_page_cgroup(pc);
- __mem_cgroup_cancel_charge(mem, nr_pages);
+ __mem_cgroup_cancel_charge(memcg, nr_pages);
return;
}
/*
* we don't need page_cgroup_lock about tail pages, becase they are not
* accessed by any other context at this point.
*/
- pc->mem_cgroup = mem;
+ pc->mem_cgroup = memcg;
/*
* We access a page_cgroup asynchronously without lock_page_cgroup().
* Especially when a page_cgroup is taken from a page, pc->mem_cgroup
@@ -2496,14 +2505,14 @@
break;
}
- mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), nr_pages);
+ mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages);
unlock_page_cgroup(pc);
/*
* "charge_statistics" updated event counter. Then, check it.
* Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
* if they exceeds softlimit.
*/
- memcg_check_events(mem, page);
+ memcg_check_events(memcg, page);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -2690,7 +2699,7 @@
static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask, enum charge_type ctype)
{
- struct mem_cgroup *mem = NULL;
+ struct mem_cgroup *memcg = NULL;
unsigned int nr_pages = 1;
struct page_cgroup *pc;
bool oom = true;
@@ -2709,11 +2718,11 @@
pc = lookup_page_cgroup(page);
BUG_ON(!pc); /* XXX: remove this and move pc lookup into commit */
- ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &mem, oom);
- if (ret || !mem)
+ ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom);
+ if (ret || !memcg)
return ret;
- __mem_cgroup_commit_charge(mem, page, nr_pages, pc, ctype);
+ __mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype);
return 0;
}
@@ -2742,7 +2751,7 @@
enum charge_type ctype);
static void
-__mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *mem,
+__mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *memcg,
enum charge_type ctype)
{
struct page_cgroup *pc = lookup_page_cgroup(page);
@@ -2752,7 +2761,7 @@
* LRU. Take care of it.
*/
mem_cgroup_lru_del_before_commit(page);
- __mem_cgroup_commit_charge(mem, page, 1, pc, ctype);
+ __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
mem_cgroup_lru_add_after_commit(page);
return;
}
@@ -2760,7 +2769,7 @@
int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask)
{
- struct mem_cgroup *mem = NULL;
+ struct mem_cgroup *memcg = NULL;
int ret;
if (mem_cgroup_disabled())
@@ -2772,8 +2781,8 @@
mm = &init_mm;
if (page_is_file_cache(page)) {
- ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, &mem, true);
- if (ret || !mem)
+ ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, &memcg, true);
+ if (ret || !memcg)
return ret;
/*
@@ -2781,15 +2790,15 @@
* put that would remove them from the LRU list, make
* sure that they get relinked properly.
*/
- __mem_cgroup_commit_charge_lrucare(page, mem,
+ __mem_cgroup_commit_charge_lrucare(page, memcg,
MEM_CGROUP_CHARGE_TYPE_CACHE);
return ret;
}
/* shmem */
if (PageSwapCache(page)) {
- ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
+ ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg);
if (!ret)
- __mem_cgroup_commit_charge_swapin(page, mem,
+ __mem_cgroup_commit_charge_swapin(page, memcg,
MEM_CGROUP_CHARGE_TYPE_SHMEM);
} else
ret = mem_cgroup_charge_common(page, mm, gfp_mask,
@@ -2808,7 +2817,7 @@
struct page *page,
gfp_t mask, struct mem_cgroup **ptr)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup *memcg;
int ret;
*ptr = NULL;
@@ -2826,12 +2835,12 @@
*/
if (!PageSwapCache(page))
goto charge_cur_mm;
- mem = try_get_mem_cgroup_from_page(page);
- if (!mem)
+ memcg = try_get_mem_cgroup_from_page(page);
+ if (!memcg)
goto charge_cur_mm;
- *ptr = mem;
+ *ptr = memcg;
ret = __mem_cgroup_try_charge(NULL, mask, 1, ptr, true);
- css_put(&mem->css);
+ css_put(&memcg->css);
return ret;
charge_cur_mm:
if (unlikely(!mm))
@@ -2891,16 +2900,16 @@
MEM_CGROUP_CHARGE_TYPE_MAPPED);
}
-void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
+void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg)
{
if (mem_cgroup_disabled())
return;
- if (!mem)
+ if (!memcg)
return;
- __mem_cgroup_cancel_charge(mem, 1);
+ __mem_cgroup_cancel_charge(memcg, 1);
}
-static void mem_cgroup_do_uncharge(struct mem_cgroup *mem,
+static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg,
unsigned int nr_pages,
const enum charge_type ctype)
{
@@ -2918,7 +2927,7 @@
* uncharges. Then, it's ok to ignore memcg's refcnt.
*/
if (!batch->memcg)
- batch->memcg = mem;
+ batch->memcg = memcg;
/*
* do_batch > 0 when unmapping pages or inode invalidate/truncate.
* In those cases, all pages freed continuously can be expected to be in
@@ -2938,7 +2947,7 @@
* merge a series of uncharges to an uncharge of res_counter.
* If not, we uncharge res_counter ony by one.
*/
- if (batch->memcg != mem)
+ if (batch->memcg != memcg)
goto direct_uncharge;
/* remember freed charge and uncharge it later */
batch->nr_pages++;
@@ -2946,11 +2955,11 @@
batch->memsw_nr_pages++;
return;
direct_uncharge:
- res_counter_uncharge(&mem->res, nr_pages * PAGE_SIZE);
+ res_counter_uncharge(&memcg->res, nr_pages * PAGE_SIZE);
if (uncharge_memsw)
- res_counter_uncharge(&mem->memsw, nr_pages * PAGE_SIZE);
- if (unlikely(batch->memcg != mem))
- memcg_oom_recover(mem);
+ res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE);
+ if (unlikely(batch->memcg != memcg))
+ memcg_oom_recover(memcg);
return;
}
@@ -2960,7 +2969,7 @@
static struct mem_cgroup *
__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
{
- struct mem_cgroup *mem = NULL;
+ struct mem_cgroup *memcg = NULL;
unsigned int nr_pages = 1;
struct page_cgroup *pc;
@@ -2983,7 +2992,7 @@
lock_page_cgroup(pc);
- mem = pc->mem_cgroup;
+ memcg = pc->mem_cgroup;
if (!PageCgroupUsed(pc))
goto unlock_out;
@@ -3006,7 +3015,7 @@
break;
}
- mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), -nr_pages);
+ mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -nr_pages);
ClearPageCgroupUsed(pc);
/*
@@ -3018,18 +3027,18 @@
unlock_page_cgroup(pc);
/*
- * even after unlock, we have mem->res.usage here and this memcg
+ * even after unlock, we have memcg->res.usage here and this memcg
* will never be freed.
*/
- memcg_check_events(mem, page);
+ memcg_check_events(memcg, page);
if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) {
- mem_cgroup_swap_statistics(mem, true);
- mem_cgroup_get(mem);
+ mem_cgroup_swap_statistics(memcg, true);
+ mem_cgroup_get(memcg);
}
- if (!mem_cgroup_is_root(mem))
- mem_cgroup_do_uncharge(mem, nr_pages, ctype);
+ if (!mem_cgroup_is_root(memcg))
+ mem_cgroup_do_uncharge(memcg, nr_pages, ctype);
- return mem;
+ return memcg;
unlock_out:
unlock_page_cgroup(pc);
@@ -3219,7 +3228,7 @@
int mem_cgroup_prepare_migration(struct page *page,
struct page *newpage, struct mem_cgroup **ptr, gfp_t gfp_mask)
{
- struct mem_cgroup *mem = NULL;
+ struct mem_cgroup *memcg = NULL;
struct page_cgroup *pc;
enum charge_type ctype;
int ret = 0;
@@ -3233,8 +3242,8 @@
pc = lookup_page_cgroup(page);
lock_page_cgroup(pc);
if (PageCgroupUsed(pc)) {
- mem = pc->mem_cgroup;
- css_get(&mem->css);
+ memcg = pc->mem_cgroup;
+ css_get(&memcg->css);
/*
* At migrating an anonymous page, its mapcount goes down
* to 0 and uncharge() will be called. But, even if it's fully
@@ -3272,12 +3281,12 @@
* If the page is not charged at this point,
* we return here.
*/
- if (!mem)
+ if (!memcg)
return 0;
- *ptr = mem;
+ *ptr = memcg;
ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, ptr, false);
- css_put(&mem->css);/* drop extra refcnt */
+ css_put(&memcg->css);/* drop extra refcnt */
if (ret || *ptr == NULL) {
if (PageAnon(page)) {
lock_page_cgroup(pc);
@@ -3303,21 +3312,21 @@
ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
else
ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
- __mem_cgroup_commit_charge(mem, page, 1, pc, ctype);
+ __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
return ret;
}
/* remove redundant charge if migration failed*/
-void mem_cgroup_end_migration(struct mem_cgroup *mem,
+void mem_cgroup_end_migration(struct mem_cgroup *memcg,
struct page *oldpage, struct page *newpage, bool migration_ok)
{
struct page *used, *unused;
struct page_cgroup *pc;
- if (!mem)
+ if (!memcg)
return;
/* blocks rmdir() */
- cgroup_exclude_rmdir(&mem->css);
+ cgroup_exclude_rmdir(&memcg->css);
if (!migration_ok) {
used = oldpage;
unused = newpage;
@@ -3353,7 +3362,7 @@
* So, rmdir()->pre_destroy() can be called while we do this charge.
* In that case, we need to call pre_destroy() again. check it here.
*/
- cgroup_release_and_wakeup_rmdir(&mem->css);
+ cgroup_release_and_wakeup_rmdir(&memcg->css);
}
#ifdef CONFIG_DEBUG_VM
@@ -3432,7 +3441,7 @@
/*
* Rather than hide all in some function, I do this in
* open coded manner. You see what this really does.
- * We have to guarantee mem->res.limit < mem->memsw.limit.
+ * We have to guarantee memcg->res.limit < memcg->memsw.limit.
*/
mutex_lock(&set_limit_mutex);
memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
@@ -3494,7 +3503,7 @@
/*
* Rather than hide all in some function, I do this in
* open coded manner. You see what this really does.
- * We have to guarantee mem->res.limit < mem->memsw.limit.
+ * We have to guarantee memcg->res.limit < memcg->memsw.limit.
*/
mutex_lock(&set_limit_mutex);
memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
@@ -3632,7 +3641,7 @@
* This routine traverse page_cgroup in given list and drop them all.
* *And* this routine doesn't reclaim page itself, just removes page_cgroup.
*/
-static int mem_cgroup_force_empty_list(struct mem_cgroup *mem,
+static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
int node, int zid, enum lru_list lru)
{
struct zone *zone;
@@ -3643,7 +3652,7 @@
int ret = 0;
zone = &NODE_DATA(node)->node_zones[zid];
- mz = mem_cgroup_zoneinfo(mem, node, zid);
+ mz = mem_cgroup_zoneinfo(memcg, node, zid);
list = &mz->lists[lru];
loop = MEM_CGROUP_ZSTAT(mz, lru);
@@ -3670,7 +3679,7 @@
page = lookup_cgroup_page(pc);
- ret = mem_cgroup_move_parent(page, pc, mem, GFP_KERNEL);
+ ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL);
if (ret == -ENOMEM)
break;
@@ -3691,14 +3700,14 @@
* make mem_cgroup's charge to be 0 if there is no task.
* This enables deleting this mem_cgroup.
*/
-static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all)
+static int mem_cgroup_force_empty(struct mem_cgroup *memcg, bool free_all)
{
int ret;
int node, zid, shrink;
int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
- struct cgroup *cgrp = mem->css.cgroup;
+ struct cgroup *cgrp = memcg->css.cgroup;
- css_get(&mem->css);
+ css_get(&memcg->css);
shrink = 0;
/* should free all ? */
@@ -3714,14 +3723,14 @@
goto out;
/* This is for making all *used* pages to be on LRU. */
lru_add_drain_all();
- drain_all_stock_sync(mem);
+ drain_all_stock_sync(memcg);
ret = 0;
- mem_cgroup_start_move(mem);
+ mem_cgroup_start_move(memcg);
for_each_node_state(node, N_HIGH_MEMORY) {
for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
enum lru_list l;
for_each_lru(l) {
- ret = mem_cgroup_force_empty_list(mem,
+ ret = mem_cgroup_force_empty_list(memcg,
node, zid, l);
if (ret)
break;
@@ -3730,16 +3739,16 @@
if (ret)
break;
}
- mem_cgroup_end_move(mem);
- memcg_oom_recover(mem);
+ mem_cgroup_end_move(memcg);
+ memcg_oom_recover(memcg);
/* it seems parent cgroup doesn't have enough mem */
if (ret == -ENOMEM)
goto try_to_free;
cond_resched();
/* "ret" should also be checked to ensure all lists are empty. */
- } while (mem->res.usage > 0 || ret);
+ } while (memcg->res.usage > 0 || ret);
out:
- css_put(&mem->css);
+ css_put(&memcg->css);
return ret;
try_to_free:
@@ -3752,14 +3761,14 @@
lru_add_drain_all();
/* try to free all pages in this cgroup */
shrink = 1;
- while (nr_retries && mem->res.usage > 0) {
+ while (nr_retries && memcg->res.usage > 0) {
int progress;
if (signal_pending(current)) {
ret = -EINTR;
goto out;
}
- progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
+ progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL,
false);
if (!progress) {
nr_retries--;
@@ -3788,12 +3797,12 @@
u64 val)
{
int retval = 0;
- struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
struct cgroup *parent = cont->parent;
- struct mem_cgroup *parent_mem = NULL;
+ struct mem_cgroup *parent_memcg = NULL;
if (parent)
- parent_mem = mem_cgroup_from_cont(parent);
+ parent_memcg = mem_cgroup_from_cont(parent);
cgroup_lock();
/*
@@ -3804,10 +3813,10 @@
* For the root cgroup, parent_mem is NULL, we allow value to be
* set if there are no children.
*/
- if ((!parent_mem || !parent_mem->use_hierarchy) &&
+ if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
(val == 1 || val == 0)) {
if (list_empty(&cont->children))
- mem->use_hierarchy = val;
+ memcg->use_hierarchy = val;
else
retval = -EBUSY;
} else
@@ -3818,14 +3827,14 @@
}
-static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *mem,
+static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg,
enum mem_cgroup_stat_index idx)
{
struct mem_cgroup *iter;
long val = 0;
/* Per-cpu values can be negative, use a signed accumulator */
- for_each_mem_cgroup_tree(iter, mem)
+ for_each_mem_cgroup_tree(iter, memcg)
val += mem_cgroup_read_stat(iter, idx);
if (val < 0) /* race ? */
@@ -3833,29 +3842,29 @@
return val;
}
-static inline u64 mem_cgroup_usage(struct mem_cgroup *mem, bool swap)
+static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
{
u64 val;
- if (!mem_cgroup_is_root(mem)) {
+ if (!mem_cgroup_is_root(memcg)) {
if (!swap)
- return res_counter_read_u64(&mem->res, RES_USAGE);
+ return res_counter_read_u64(&memcg->res, RES_USAGE);
else
- return res_counter_read_u64(&mem->memsw, RES_USAGE);
+ return res_counter_read_u64(&memcg->memsw, RES_USAGE);
}
- val = mem_cgroup_recursive_stat(mem, MEM_CGROUP_STAT_CACHE);
- val += mem_cgroup_recursive_stat(mem, MEM_CGROUP_STAT_RSS);
+ val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
+ val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
if (swap)
- val += mem_cgroup_recursive_stat(mem, MEM_CGROUP_STAT_SWAPOUT);
+ val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAPOUT);
return val << PAGE_SHIFT;
}
static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
u64 val;
int type, name;
@@ -3864,15 +3873,15 @@
switch (type) {
case _MEM:
if (name == RES_USAGE)
- val = mem_cgroup_usage(mem, false);
+ val = mem_cgroup_usage(memcg, false);
else
- val = res_counter_read_u64(&mem->res, name);
+ val = res_counter_read_u64(&memcg->res, name);
break;
case _MEMSWAP:
if (name == RES_USAGE)
- val = mem_cgroup_usage(mem, true);
+ val = mem_cgroup_usage(memcg, true);
else
- val = res_counter_read_u64(&mem->memsw, name);
+ val = res_counter_read_u64(&memcg->memsw, name);
break;
default:
BUG();
@@ -3960,24 +3969,24 @@
static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup *memcg;
int type, name;
- mem = mem_cgroup_from_cont(cont);
+ memcg = mem_cgroup_from_cont(cont);
type = MEMFILE_TYPE(event);
name = MEMFILE_ATTR(event);
switch (name) {
case RES_MAX_USAGE:
if (type == _MEM)
- res_counter_reset_max(&mem->res);
+ res_counter_reset_max(&memcg->res);
else
- res_counter_reset_max(&mem->memsw);
+ res_counter_reset_max(&memcg->memsw);
break;
case RES_FAILCNT:
if (type == _MEM)
- res_counter_reset_failcnt(&mem->res);
+ res_counter_reset_failcnt(&memcg->res);
else
- res_counter_reset_failcnt(&mem->memsw);
+ res_counter_reset_failcnt(&memcg->memsw);
break;
}
@@ -3994,7 +4003,7 @@
static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
struct cftype *cft, u64 val)
{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
if (val >= (1 << NR_MOVE_TYPE))
return -EINVAL;
@@ -4004,7 +4013,7 @@
* inconsistent.
*/
cgroup_lock();
- mem->move_charge_at_immigrate = val;
+ memcg->move_charge_at_immigrate = val;
cgroup_unlock();
return 0;
@@ -4061,49 +4070,49 @@
static void
-mem_cgroup_get_local_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
+mem_cgroup_get_local_stat(struct mem_cgroup *memcg, struct mcs_total_stat *s)
{
s64 val;
/* per cpu stat */
- val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE);
+ val = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_CACHE);
s->stat[MCS_CACHE] += val * PAGE_SIZE;
- val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS);
+ val = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_RSS);
s->stat[MCS_RSS] += val * PAGE_SIZE;
- val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_FILE_MAPPED);
+ val = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED);
s->stat[MCS_FILE_MAPPED] += val * PAGE_SIZE;
- val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGPGIN);
+ val = mem_cgroup_read_events(memcg, MEM_CGROUP_EVENTS_PGPGIN);
s->stat[MCS_PGPGIN] += val;
- val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGPGOUT);
+ val = mem_cgroup_read_events(memcg, MEM_CGROUP_EVENTS_PGPGOUT);
s->stat[MCS_PGPGOUT] += val;
if (do_swap_account) {
- val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_SWAPOUT);
+ val = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_SWAPOUT);
s->stat[MCS_SWAP] += val * PAGE_SIZE;
}
- val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGFAULT);
+ val = mem_cgroup_read_events(memcg, MEM_CGROUP_EVENTS_PGFAULT);
s->stat[MCS_PGFAULT] += val;
- val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGMAJFAULT);
+ val = mem_cgroup_read_events(memcg, MEM_CGROUP_EVENTS_PGMAJFAULT);
s->stat[MCS_PGMAJFAULT] += val;
/* per zone stat */
- val = mem_cgroup_nr_lru_pages(mem, BIT(LRU_INACTIVE_ANON));
+ val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_ANON));
s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE;
- val = mem_cgroup_nr_lru_pages(mem, BIT(LRU_ACTIVE_ANON));
+ val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_ANON));
s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE;
- val = mem_cgroup_nr_lru_pages(mem, BIT(LRU_INACTIVE_FILE));
+ val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_FILE));
s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE;
- val = mem_cgroup_nr_lru_pages(mem, BIT(LRU_ACTIVE_FILE));
+ val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_FILE));
s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE;
- val = mem_cgroup_nr_lru_pages(mem, BIT(LRU_UNEVICTABLE));
+ val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE));
s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE;
}
static void
-mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
+mem_cgroup_get_total_stat(struct mem_cgroup *memcg, struct mcs_total_stat *s)
{
struct mem_cgroup *iter;
- for_each_mem_cgroup_tree(iter, mem)
+ for_each_mem_cgroup_tree(iter, memcg)
mem_cgroup_get_local_stat(iter, s);
}
@@ -4189,8 +4198,6 @@
}
#ifdef CONFIG_DEBUG_VM
- cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
-
{
int nid, zid;
struct mem_cgroup_per_zone *mz;
@@ -4327,20 +4334,20 @@
return _a->threshold - _b->threshold;
}
-static int mem_cgroup_oom_notify_cb(struct mem_cgroup *mem)
+static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
{
struct mem_cgroup_eventfd_list *ev;
- list_for_each_entry(ev, &mem->oom_notify, list)
+ list_for_each_entry(ev, &memcg->oom_notify, list)
eventfd_signal(ev->eventfd, 1);
return 0;
}
-static void mem_cgroup_oom_notify(struct mem_cgroup *mem)
+static void mem_cgroup_oom_notify(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter;
- for_each_mem_cgroup_tree(iter, mem)
+ for_each_mem_cgroup_tree(iter, memcg)
mem_cgroup_oom_notify_cb(iter);
}
@@ -4530,7 +4537,7 @@
static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
struct cftype *cft, struct eventfd_ctx *eventfd)
{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
struct mem_cgroup_eventfd_list *ev, *tmp;
int type = MEMFILE_TYPE(cft->private);
@@ -4538,7 +4545,7 @@
spin_lock(&memcg_oom_lock);
- list_for_each_entry_safe(ev, tmp, &mem->oom_notify, list) {
+ list_for_each_entry_safe(ev, tmp, &memcg->oom_notify, list) {
if (ev->eventfd == eventfd) {
list_del(&ev->list);
kfree(ev);
@@ -4551,11 +4558,11 @@
static int mem_cgroup_oom_control_read(struct cgroup *cgrp,
struct cftype *cft, struct cgroup_map_cb *cb)
{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
- cb->fill(cb, "oom_kill_disable", mem->oom_kill_disable);
+ cb->fill(cb, "oom_kill_disable", memcg->oom_kill_disable);
- if (atomic_read(&mem->under_oom))
+ if (atomic_read(&memcg->under_oom))
cb->fill(cb, "under_oom", 1);
else
cb->fill(cb, "under_oom", 0);
@@ -4565,7 +4572,7 @@
static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
struct cftype *cft, u64 val)
{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
struct mem_cgroup *parent;
/* cannot set to root cgroup and only 0 and 1 are allowed */
@@ -4577,13 +4584,13 @@
cgroup_lock();
/* oom-kill-disable is a flag for subhierarchy. */
if ((parent->use_hierarchy) ||
- (mem->use_hierarchy && !list_empty(&cgrp->children))) {
+ (memcg->use_hierarchy && !list_empty(&cgrp->children))) {
cgroup_unlock();
return -EINVAL;
}
- mem->oom_kill_disable = val;
+ memcg->oom_kill_disable = val;
if (!val)
- memcg_oom_recover(mem);
+ memcg_oom_recover(memcg);
cgroup_unlock();
return 0;
}
@@ -4719,7 +4726,7 @@
}
#endif
-static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
+static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
{
struct mem_cgroup_per_node *pn;
struct mem_cgroup_per_zone *mz;
@@ -4739,21 +4746,21 @@
if (!pn)
return 1;
- mem->info.nodeinfo[node] = pn;
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
mz = &pn->zoneinfo[zone];
for_each_lru(l)
INIT_LIST_HEAD(&mz->lists[l]);
mz->usage_in_excess = 0;
mz->on_tree = false;
- mz->mem = mem;
+ mz->mem = memcg;
}
+ memcg->info.nodeinfo[node] = pn;
return 0;
}
-static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
+static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
{
- kfree(mem->info.nodeinfo[node]);
+ kfree(memcg->info.nodeinfo[node]);
}
static struct mem_cgroup *mem_cgroup_alloc(void)
@@ -4795,51 +4802,51 @@
* Removal of cgroup itself succeeds regardless of refs from swap.
*/
-static void __mem_cgroup_free(struct mem_cgroup *mem)
+static void __mem_cgroup_free(struct mem_cgroup *memcg)
{
int node;
- mem_cgroup_remove_from_trees(mem);
- free_css_id(&mem_cgroup_subsys, &mem->css);
+ mem_cgroup_remove_from_trees(memcg);
+ free_css_id(&mem_cgroup_subsys, &memcg->css);
for_each_node_state(node, N_POSSIBLE)
- free_mem_cgroup_per_zone_info(mem, node);
+ free_mem_cgroup_per_zone_info(memcg, node);
- free_percpu(mem->stat);
+ free_percpu(memcg->stat);
if (sizeof(struct mem_cgroup) < PAGE_SIZE)
- kfree(mem);
+ kfree(memcg);
else
- vfree(mem);
+ vfree(memcg);
}
-static void mem_cgroup_get(struct mem_cgroup *mem)
+static void mem_cgroup_get(struct mem_cgroup *memcg)
{
- atomic_inc(&mem->refcnt);
+ atomic_inc(&memcg->refcnt);
}
-static void __mem_cgroup_put(struct mem_cgroup *mem, int count)
+static void __mem_cgroup_put(struct mem_cgroup *memcg, int count)
{
- if (atomic_sub_and_test(count, &mem->refcnt)) {
- struct mem_cgroup *parent = parent_mem_cgroup(mem);
- __mem_cgroup_free(mem);
+ if (atomic_sub_and_test(count, &memcg->refcnt)) {
+ struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+ __mem_cgroup_free(memcg);
if (parent)
mem_cgroup_put(parent);
}
}
-static void mem_cgroup_put(struct mem_cgroup *mem)
+static void mem_cgroup_put(struct mem_cgroup *memcg)
{
- __mem_cgroup_put(mem, 1);
+ __mem_cgroup_put(memcg, 1);
}
/*
* Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
*/
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem)
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
{
- if (!mem->res.parent)
+ if (!memcg->res.parent)
return NULL;
- return mem_cgroup_from_res_counter(mem->res.parent, res);
+ return mem_cgroup_from_res_counter(memcg->res.parent, res);
}
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
@@ -4882,16 +4889,16 @@
static struct cgroup_subsys_state * __ref
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
- struct mem_cgroup *mem, *parent;
+ struct mem_cgroup *memcg, *parent;
long error = -ENOMEM;
int node;
- mem = mem_cgroup_alloc();
- if (!mem)
+ memcg = mem_cgroup_alloc();
+ if (!memcg)
return ERR_PTR(error);
for_each_node_state(node, N_POSSIBLE)
- if (alloc_mem_cgroup_per_zone_info(mem, node))
+ if (alloc_mem_cgroup_per_zone_info(memcg, node))
goto free_out;
/* root ? */
@@ -4899,7 +4906,7 @@
int cpu;
enable_swap_cgroup();
parent = NULL;
- root_mem_cgroup = mem;
+ root_mem_cgroup = memcg;
if (mem_cgroup_soft_limit_tree_init())
goto free_out;
for_each_possible_cpu(cpu) {
@@ -4910,13 +4917,13 @@
hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
} else {
parent = mem_cgroup_from_cont(cont->parent);
- mem->use_hierarchy = parent->use_hierarchy;
- mem->oom_kill_disable = parent->oom_kill_disable;
+ memcg->use_hierarchy = parent->use_hierarchy;
+ memcg->oom_kill_disable = parent->oom_kill_disable;
}
if (parent && parent->use_hierarchy) {
- res_counter_init(&mem->res, &parent->res);
- res_counter_init(&mem->memsw, &parent->memsw);
+ res_counter_init(&memcg->res, &parent->res);
+ res_counter_init(&memcg->memsw, &parent->memsw);
/*
* We increment refcnt of the parent to ensure that we can
* safely access it on res_counter_charge/uncharge.
@@ -4925,21 +4932,21 @@
*/
mem_cgroup_get(parent);
} else {
- res_counter_init(&mem->res, NULL);
- res_counter_init(&mem->memsw, NULL);
+ res_counter_init(&memcg->res, NULL);
+ res_counter_init(&memcg->memsw, NULL);
}
- mem->last_scanned_child = 0;
- mem->last_scanned_node = MAX_NUMNODES;
- INIT_LIST_HEAD(&mem->oom_notify);
+ memcg->last_scanned_child = 0;
+ memcg->last_scanned_node = MAX_NUMNODES;
+ INIT_LIST_HEAD(&memcg->oom_notify);
if (parent)
- mem->swappiness = mem_cgroup_swappiness(parent);
- atomic_set(&mem->refcnt, 1);
- mem->move_charge_at_immigrate = 0;
- mutex_init(&mem->thresholds_lock);
- return &mem->css;
+ memcg->swappiness = mem_cgroup_swappiness(parent);
+ atomic_set(&memcg->refcnt, 1);
+ memcg->move_charge_at_immigrate = 0;
+ mutex_init(&memcg->thresholds_lock);
+ return &memcg->css;
free_out:
- __mem_cgroup_free(mem);
+ __mem_cgroup_free(memcg);
root_mem_cgroup = NULL;
return ERR_PTR(error);
}
@@ -4947,17 +4954,17 @@
static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
struct cgroup *cont)
{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
- return mem_cgroup_force_empty(mem, false);
+ return mem_cgroup_force_empty(memcg, false);
}
static void mem_cgroup_destroy(struct cgroup_subsys *ss,
struct cgroup *cont)
{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
- mem_cgroup_put(mem);
+ mem_cgroup_put(memcg);
}
static int mem_cgroup_populate(struct cgroup_subsys *ss,
@@ -4980,9 +4987,9 @@
{
int ret = 0;
int batch_count = PRECHARGE_COUNT_AT_ONCE;
- struct mem_cgroup *mem = mc.to;
+ struct mem_cgroup *memcg = mc.to;
- if (mem_cgroup_is_root(mem)) {
+ if (mem_cgroup_is_root(memcg)) {
mc.precharge += count;
/* we don't need css_get for root */
return ret;
@@ -4991,16 +4998,16 @@
if (count > 1) {
struct res_counter *dummy;
/*
- * "mem" cannot be under rmdir() because we've already checked
+ * "memcg" cannot be under rmdir() because we've already checked
* by cgroup_lock_live_cgroup() that it is not removed and we
* are still under the same cgroup_mutex. So we can postpone
* css_get().
*/
- if (res_counter_charge(&mem->res, PAGE_SIZE * count, &dummy))
+ if (res_counter_charge(&memcg->res, PAGE_SIZE * count, &dummy))
goto one_by_one;
- if (do_swap_account && res_counter_charge(&mem->memsw,
+ if (do_swap_account && res_counter_charge(&memcg->memsw,
PAGE_SIZE * count, &dummy)) {
- res_counter_uncharge(&mem->res, PAGE_SIZE * count);
+ res_counter_uncharge(&memcg->res, PAGE_SIZE * count);
goto one_by_one;
}
mc.precharge += count;
@@ -5017,8 +5024,9 @@
batch_count = PRECHARGE_COUNT_AT_ONCE;
cond_resched();
}
- ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, 1, &mem, false);
- if (ret || !mem)
+ ret = __mem_cgroup_try_charge(NULL,
+ GFP_KERNEL, 1, &memcg, false);
+ if (ret || !memcg)
/* mem_cgroup_clear_mc() will do uncharge later */
return -ENOMEM;
mc.precharge++;
@@ -5292,13 +5300,13 @@
struct task_struct *p)
{
int ret = 0;
- struct mem_cgroup *mem = mem_cgroup_from_cont(cgroup);
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);
- if (mem->move_charge_at_immigrate) {
+ if (memcg->move_charge_at_immigrate) {
struct mm_struct *mm;
struct mem_cgroup *from = mem_cgroup_from_task(p);
- VM_BUG_ON(from == mem);
+ VM_BUG_ON(from == memcg);
mm = get_task_mm(p);
if (!mm)
@@ -5313,7 +5321,7 @@
mem_cgroup_start_move(from);
spin_lock(&mc.lock);
mc.from = from;
- mc.to = mem;
+ mc.to = memcg;
spin_unlock(&mc.lock);
/* We set mc.moving_task later */
diff --git a/mm/memory.c b/mm/memory.c
index a56e3ba..b2b8731 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1503,7 +1503,7 @@
}
if (flags & FOLL_GET)
- get_page(page);
+ get_page_foll(page);
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 6bdc67d..2d123f9 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -133,10 +133,13 @@
static void *__meminit alloc_page_cgroup(size_t size, int nid)
{
void *addr = NULL;
+ gfp_t flags = GFP_KERNEL | __GFP_NOWARN;
- addr = alloc_pages_exact_nid(nid, size, GFP_KERNEL | __GFP_NOWARN);
- if (addr)
+ addr = alloc_pages_exact_nid(nid, size, flags);
+ if (addr) {
+ kmemleak_alloc(addr, size, 1, flags);
return addr;
+ }
if (node_state(nid, N_HIGH_MEMORY))
addr = vmalloc_node(size, nid);
@@ -357,7 +360,7 @@
spinlock_t lock;
};
-struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
+static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
struct swap_cgroup {
unsigned short id;
diff --git a/mm/shmem.c b/mm/shmem.c
index fa4fa6c..45b9acb 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2503,7 +2503,7 @@
d_instantiate(path.dentry, inode);
inode->i_size = size;
- inode->i_nlink = 0; /* It is unlinked */
+ clear_nlink(inode); /* It is unlinked */
#ifndef CONFIG_MMU
error = ramfs_nommu_expand_for_mapping(inode, size);
if (error)
diff --git a/mm/swap.c b/mm/swap.c
index 3a442f1..87627f1 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -78,39 +78,22 @@
{
if (unlikely(PageTail(page))) {
/* __split_huge_page_refcount can run under us */
- struct page *page_head = page->first_page;
- smp_rmb();
- /*
- * If PageTail is still set after smp_rmb() we can be sure
- * that the page->first_page we read wasn't a dangling pointer.
- * See __split_huge_page_refcount() smp_wmb().
- */
- if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
+ struct page *page_head = compound_trans_head(page);
+
+ if (likely(page != page_head &&
+ get_page_unless_zero(page_head))) {
unsigned long flags;
/*
- * Verify that our page_head wasn't converted
- * to a a regular page before we got a
- * reference on it.
+ * page_head wasn't a dangling pointer but it
+ * may not be a head page anymore by the time
+ * we obtain the lock. That is ok as long as it
+ * can't be freed from under us.
*/
- if (unlikely(!PageHead(page_head))) {
- /* PageHead is cleared after PageTail */
- smp_rmb();
- VM_BUG_ON(PageTail(page));
- goto out_put_head;
- }
- /*
- * Only run compound_lock on a valid PageHead,
- * after having it pinned with
- * get_page_unless_zero() above.
- */
- smp_mb();
- /* page_head wasn't a dangling pointer */
flags = compound_lock_irqsave(page_head);
if (unlikely(!PageTail(page))) {
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
VM_BUG_ON(PageHead(page_head));
- out_put_head:
if (put_page_testzero(page_head))
__put_single_page(page_head);
out_put_single:
@@ -121,16 +104,17 @@
VM_BUG_ON(page_head != page->first_page);
/*
* We can release the refcount taken by
- * get_page_unless_zero now that
- * split_huge_page_refcount is blocked on the
- * compound_lock.
+ * get_page_unless_zero() now that
+ * __split_huge_page_refcount() is blocked on
+ * the compound_lock.
*/
if (put_page_testzero(page_head))
VM_BUG_ON(1);
/* __split_huge_page_refcount will wait now */
- VM_BUG_ON(atomic_read(&page->_count) <= 0);
- atomic_dec(&page->_count);
+ VM_BUG_ON(page_mapcount(page) <= 0);
+ atomic_dec(&page->_mapcount);
VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
+ VM_BUG_ON(atomic_read(&page->_count) != 0);
compound_unlock_irqrestore(page_head, flags);
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
@@ -160,6 +144,45 @@
}
EXPORT_SYMBOL(put_page);
+/*
+ * This function is exported but must not be called by anything other
+ * than get_page(). It implements the slow path of get_page().
+ */
+bool __get_page_tail(struct page *page)
+{
+ /*
+ * This takes care of get_page() if run on a tail page
+ * returned by one of the get_user_pages/follow_page variants.
+ * get_user_pages/follow_page itself doesn't need the compound
+ * lock because it runs __get_page_tail_foll() under the
+ * proper PT lock that already serializes against
+ * split_huge_page().
+ */
+ unsigned long flags;
+ bool got = false;
+ struct page *page_head = compound_trans_head(page);
+
+ if (likely(page != page_head && get_page_unless_zero(page_head))) {
+ /*
+ * page_head wasn't a dangling pointer but it
+ * may not be a head page anymore by the time
+ * we obtain the lock. That is ok as long as it
+ * can't be freed from under us.
+ */
+ flags = compound_lock_irqsave(page_head);
+ /* here __split_huge_page_refcount won't run anymore */
+ if (likely(PageTail(page))) {
+ __get_page_tail_foll(page, false);
+ got = true;
+ }
+ compound_unlock_irqrestore(page_head, flags);
+ if (unlikely(!got))
+ put_page(page_head);
+ }
+ return got;
+}
+EXPORT_SYMBOL(__get_page_tail);
+
/**
* put_pages_list() - release a list of pages
* @pages: list of pages threaded on page->lru
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a90c603..132d1dd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1767,7 +1767,7 @@
if (scanning_global_lru(sc))
low = inactive_anon_is_low_global(zone);
else
- low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
+ low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup, zone);
return low;
}
#else
@@ -1810,7 +1810,7 @@
if (scanning_global_lru(sc))
low = inactive_file_is_low_global(zone);
else
- low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup);
+ low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup, zone);
return low;
}
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index c8cf939..bc25286 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -470,10 +470,12 @@
{
struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
- if (change & IFF_ALLMULTI)
- dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1);
- if (change & IFF_PROMISC)
- dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1);
+ if (dev->flags & IFF_UP) {
+ if (change & IFF_ALLMULTI)
+ dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+ if (change & IFF_PROMISC)
+ dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1);
+ }
}
static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c
index bf2a333..5449294 100644
--- a/net/bridge/netfilter/ebt_ulog.c
+++ b/net/bridge/netfilter/ebt_ulog.c
@@ -102,16 +102,15 @@
unsigned int n;
n = max(size, nlbufsiz);
- skb = alloc_skb(n, GFP_ATOMIC);
+ skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN);
if (!skb) {
- pr_debug("cannot alloc whole buffer of size %ub!\n", n);
if (n > size) {
/* try to allocate only as much as we need for
* current packet */
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb)
- pr_debug("cannot even allocate "
- "buffer of size %ub\n", size);
+ pr_debug("cannot even allocate buffer of size %ub\n",
+ size);
}
}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 909ecb3..039d51e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -872,12 +872,8 @@
now = jiffies;
next = now + HZ;
- if (!(state & NUD_IN_TIMER)) {
-#ifndef CONFIG_SMP
- printk(KERN_WARNING "neigh: timer & !nud_in_timer\n");
-#endif
+ if (!(state & NUD_IN_TIMER))
goto out;
- }
if (state & NUD_REACHABLE) {
if (time_before_eq(now,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ca4db40..18a3ceb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -189,6 +189,7 @@
* aligned memory blocks, unless SLUB/SLAB debug is enabled.
* Both skb->head and skb_shared_info are cache line aligned.
*/
+ size = SKB_DATA_ALIGN(size);
size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
data = kmalloc_node_track_caller(size, gfp_mask, node);
if (!data)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 332639b..90a919a 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -433,6 +433,7 @@
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL;
put_and_exit:
+ bh_unlock_sock(newsk);
sock_put(newsk);
goto exit;
}
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index db8d22d..a639967 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -395,7 +395,6 @@
config = clusterip_config_init(cipinfo,
e->ip.dst.s_addr, dev);
if (!config) {
- pr_info("cannot allocate config\n");
dev_put(dev);
return -ENOMEM;
}
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 446e0f4..b550815 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -135,10 +135,8 @@
* due to slab allocator restrictions */
n = max(size, nlbufsiz);
- skb = alloc_skb(n, GFP_ATOMIC);
+ skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN);
if (!skb) {
- pr_debug("cannot alloc whole buffer %ub!\n", n);
-
if (n > size) {
/* try to allocate only as much as we need for
* current packet */
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index d1cb412..2133c30 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -400,11 +400,8 @@
*len = 0;
*octets = kmalloc(eoc - ctx->pointer, GFP_ATOMIC);
- if (*octets == NULL) {
- if (net_ratelimit())
- pr_notice("OOM in bsalg (%d)\n", __LINE__);
+ if (*octets == NULL)
return 0;
- }
ptr = *octets;
while (ctx->pointer < eoc) {
@@ -451,11 +448,8 @@
return 0;
*oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC);
- if (*oid == NULL) {
- if (net_ratelimit())
- pr_notice("OOM in bsalg (%d)\n", __LINE__);
+ if (*oid == NULL)
return 0;
- }
optr = *oid;
@@ -728,8 +722,6 @@
*obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC);
if (*obj == NULL) {
kfree(id);
- if (net_ratelimit())
- pr_notice("OOM in bsalg (%d)\n", __LINE__);
return 0;
}
(*obj)->syntax.l[0] = l;
@@ -744,8 +736,6 @@
if (*obj == NULL) {
kfree(p);
kfree(id);
- if (net_ratelimit())
- pr_notice("OOM in bsalg (%d)\n", __LINE__);
return 0;
}
memcpy((*obj)->syntax.c, p, len);
@@ -759,8 +749,6 @@
*obj = kmalloc(sizeof(struct snmp_object), GFP_ATOMIC);
if (*obj == NULL) {
kfree(id);
- if (net_ratelimit())
- pr_notice("OOM in bsalg (%d)\n", __LINE__);
return 0;
}
if (!asn1_null_decode(ctx, end)) {
@@ -780,8 +768,6 @@
if (*obj == NULL) {
kfree(lp);
kfree(id);
- if (net_ratelimit())
- pr_notice("OOM in bsalg (%d)\n", __LINE__);
return 0;
}
memcpy((*obj)->syntax.ul, lp, len);
@@ -801,8 +787,6 @@
if (*obj == NULL) {
kfree(p);
kfree(id);
- if (net_ratelimit())
- pr_notice("OOM in bsalg (%d)\n", __LINE__);
return 0;
}
memcpy((*obj)->syntax.uc, p, len);
@@ -819,8 +803,6 @@
*obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC);
if (*obj == NULL) {
kfree(id);
- if (net_ratelimit())
- pr_notice("OOM in bsalg (%d)\n", __LINE__);
return 0;
}
(*obj)->syntax.ul[0] = ul;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0ea10ee..a744315 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1510,6 +1510,7 @@
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL;
put_and_exit:
+ bh_unlock_sock(newsk);
sock_put(newsk);
goto exit;
}
@@ -2339,7 +2340,7 @@
}
}
-static int tcp_seq_open(struct inode *inode, struct file *file)
+int tcp_seq_open(struct inode *inode, struct file *file)
{
struct tcp_seq_afinfo *afinfo = PDE(inode)->data;
struct tcp_iter_state *s;
@@ -2355,23 +2356,19 @@
s->last_pos = 0;
return 0;
}
+EXPORT_SYMBOL(tcp_seq_open);
int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
{
int rc = 0;
struct proc_dir_entry *p;
- afinfo->seq_fops.open = tcp_seq_open;
- afinfo->seq_fops.read = seq_read;
- afinfo->seq_fops.llseek = seq_lseek;
- afinfo->seq_fops.release = seq_release_net;
-
afinfo->seq_ops.start = tcp_seq_start;
afinfo->seq_ops.next = tcp_seq_next;
afinfo->seq_ops.stop = tcp_seq_stop;
p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
- &afinfo->seq_fops, afinfo);
+ afinfo->seq_fops, afinfo);
if (!p)
rc = -ENOMEM;
return rc;
@@ -2520,12 +2517,18 @@
return 0;
}
+static const struct file_operations tcp_afinfo_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = tcp_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net
+};
+
static struct tcp_seq_afinfo tcp4_seq_afinfo = {
.name = "tcp",
.family = AF_INET,
- .seq_fops = {
- .owner = THIS_MODULE,
- },
+ .seq_fops = &tcp_afinfo_seq_fops,
.seq_ops = {
.show = tcp4_seq_show,
},
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ebaa96b..ab0966d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1397,6 +1397,8 @@
nf_reset(skb);
if (up->encap_type) {
+ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
+
/*
* This is an encapsulation socket so pass the skb to
* the socket's udp_encap_rcv() hook. Otherwise, just
@@ -1409,11 +1411,11 @@
*/
/* if we're overly short, let UDP handle it */
- if (skb->len > sizeof(struct udphdr) &&
- up->encap_rcv != NULL) {
+ encap_rcv = ACCESS_ONCE(up->encap_rcv);
+ if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) {
int ret;
- ret = (*up->encap_rcv)(sk, skb);
+ ret = encap_rcv(sk, skb);
if (ret <= 0) {
UDP_INC_STATS_BH(sock_net(sk),
UDP_MIB_INDATAGRAMS,
@@ -2037,7 +2039,7 @@
spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
}
-static int udp_seq_open(struct inode *inode, struct file *file)
+int udp_seq_open(struct inode *inode, struct file *file)
{
struct udp_seq_afinfo *afinfo = PDE(inode)->data;
struct udp_iter_state *s;
@@ -2053,6 +2055,7 @@
s->udp_table = afinfo->udp_table;
return err;
}
+EXPORT_SYMBOL(udp_seq_open);
/* ------------------------------------------------------------------------ */
int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo)
@@ -2060,17 +2063,12 @@
struct proc_dir_entry *p;
int rc = 0;
- afinfo->seq_fops.open = udp_seq_open;
- afinfo->seq_fops.read = seq_read;
- afinfo->seq_fops.llseek = seq_lseek;
- afinfo->seq_fops.release = seq_release_net;
-
afinfo->seq_ops.start = udp_seq_start;
afinfo->seq_ops.next = udp_seq_next;
afinfo->seq_ops.stop = udp_seq_stop;
p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
- &afinfo->seq_fops, afinfo);
+ afinfo->seq_fops, afinfo);
if (!p)
rc = -ENOMEM;
return rc;
@@ -2120,14 +2118,20 @@
return 0;
}
+static const struct file_operations udp_afinfo_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = udp_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net
+};
+
/* ------------------------------------------------------------------------ */
static struct udp_seq_afinfo udp4_seq_afinfo = {
.name = "udp",
.family = AF_INET,
.udp_table = &udp_table,
- .seq_fops = {
- .owner = THIS_MODULE,
- },
+ .seq_fops = &udp_afinfo_seq_fops,
.seq_ops = {
.show = udp4_seq_show,
},
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index aee9963..08383eb 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -71,13 +71,20 @@
};
#ifdef CONFIG_PROC_FS
+
+static const struct file_operations udplite_afinfo_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = udp_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net
+};
+
static struct udp_seq_afinfo udplite4_seq_afinfo = {
.name = "udplite",
.family = AF_INET,
.udp_table = &udplite_table,
- .seq_fops = {
- .owner = THIS_MODULE,
- },
+ .seq_fops = &udplite_afinfo_seq_fops,
.seq_ops = {
.show = udp4_seq_show,
},
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 30fcee4..8992cf6 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -100,9 +100,16 @@
.pinet6 = (struct ipv6_pinfo *) &fake_pinfo,
};
const void *sk = strict ? &fake_sk : NULL;
+ struct dst_entry *result;
+ int err;
- *dst = ip6_route_output(net, sk, &fl->u.ip6);
- return (*dst)->error;
+ result = ip6_route_output(net, sk, &fl->u.ip6);
+ err = result->error;
+ if (err)
+ dst_release(result);
+ else
+ *dst = result;
+ return err;
}
__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index e8762c7..38f00b0 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -182,7 +182,6 @@
return container_of(q, struct nf_ct_frag6_queue, q);
oom:
- pr_debug("Can't alloc new queue\n");
return NULL;
}
@@ -370,10 +369,10 @@
struct sk_buff *clone;
int i, plen = 0;
- if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL) {
- pr_debug("Can't alloc skb\n");
+ clone = alloc_skb(0, GFP_ATOMIC);
+ if (clone == NULL)
goto out_oom;
- }
+
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 10b2b31..36131d1 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2161,12 +2161,18 @@
return 0;
}
+static const struct file_operations tcp6_afinfo_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = tcp_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net
+};
+
static struct tcp_seq_afinfo tcp6_seq_afinfo = {
.name = "tcp6",
.family = AF_INET6,
- .seq_fops = {
- .owner = THIS_MODULE,
- },
+ .seq_fops = &tcp6_afinfo_seq_fops,
.seq_ops = {
.show = tcp6_seq_show,
},
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f4ca0a5..846f475 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1424,13 +1424,19 @@
return 0;
}
+static const struct file_operations udp6_afinfo_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = udp_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net
+};
+
static struct udp_seq_afinfo udp6_seq_afinfo = {
.name = "udp6",
.family = AF_INET6,
.udp_table = &udp_table,
- .seq_fops = {
- .owner = THIS_MODULE,
- },
+ .seq_fops = &udp6_afinfo_seq_fops,
.seq_ops = {
.show = udp6_seq_show,
},
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 986c4de..8889aa2 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -93,13 +93,20 @@
}
#ifdef CONFIG_PROC_FS
+
+static const struct file_operations udplite6_afinfo_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = udp_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net
+};
+
static struct udp_seq_afinfo udplite6_seq_afinfo = {
.name = "udplite6",
.family = AF_INET6,
.udp_table = &udplite_table,
- .seq_fops = {
- .owner = THIS_MODULE,
- },
+ .seq_fops = &udplite6_afinfo_seq_fops,
.seq_ops = {
.show = udp6_seq_show,
},
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 34b2dde..bf8d50c 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -397,6 +397,7 @@
* expect to send up next, dequeue it and any other
* in-sequence packets behind it.
*/
+start:
spin_lock_bh(&session->reorder_q.lock);
skb_queue_walk_safe(&session->reorder_q, skb, tmp) {
if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) {
@@ -433,7 +434,7 @@
*/
spin_unlock_bh(&session->reorder_q.lock);
l2tp_recv_dequeue_skb(session, skb);
- spin_lock_bh(&session->reorder_q.lock);
+ goto start;
}
out:
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 3346829..afca6c7 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -180,17 +180,16 @@
if (ret == 0)
ret = -EPERM;
} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
- ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
- verdict >> NF_VERDICT_QBITS);
- if (ret < 0) {
- if (ret == -ECANCELED)
+ int err = nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
+ verdict >> NF_VERDICT_QBITS);
+ if (err < 0) {
+ if (err == -ECANCELED)
goto next_hook;
- if (ret == -ESRCH &&
+ if (err == -ESRCH &&
(verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
goto next_hook;
kfree_skb(skb);
}
- ret = 0;
}
rcu_read_unlock();
return ret;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index d7e86ef..86137b5 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1699,10 +1699,8 @@
ip_set_list = kzalloc(sizeof(struct ip_set *) * ip_set_max,
GFP_KERNEL);
- if (!ip_set_list) {
- pr_err("ip_set: Unable to create ip_set_list\n");
+ if (!ip_set_list)
return -ENOMEM;
- }
ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
if (ret != 0) {
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 4f77bb1..093cc32 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -188,14 +188,13 @@
}
-static inline int
+static inline void
ip_vs_set_state(struct ip_vs_conn *cp, int direction,
const struct sk_buff *skb,
struct ip_vs_proto_data *pd)
{
- if (unlikely(!pd->pp->state_transition))
- return 0;
- return pd->pp->state_transition(cp, direction, skb, pd);
+ if (likely(pd->pp->state_transition))
+ pd->pp->state_transition(cp, direction, skb, pd);
}
static inline int
@@ -530,7 +529,7 @@
a cache_bypass connection entry */
ipvs = net_ipvs(net);
if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) {
- int ret, cs;
+ int ret;
struct ip_vs_conn *cp;
unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
iph.protocol == IPPROTO_UDP)?
@@ -557,7 +556,7 @@
ip_vs_in_stats(cp, skb);
/* set state */
- cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
+ ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
/* transmit the first SYN packet */
ret = cp->packet_xmit(skb, cp, pd->pp);
@@ -1490,7 +1489,7 @@
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
struct ip_vs_conn *cp;
- int ret, restart, pkts;
+ int ret, pkts;
struct netns_ipvs *ipvs;
/* Already marked as IPVS request or reply? */
@@ -1591,7 +1590,7 @@
}
ip_vs_in_stats(cp, skb);
- restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
+ ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
if (cp->packet_xmit)
ret = cp->packet_xmit(skb, cp, pp);
/* do not touch skb anymore */
@@ -1878,10 +1877,9 @@
struct netns_ipvs *ipvs;
ipvs = net_generic(net, ip_vs_net_id);
- if (ipvs == NULL) {
- pr_err("%s(): no memory.\n", __func__);
+ if (ipvs == NULL)
return -ENOMEM;
- }
+
/* Hold the beast until a service is registerd */
ipvs->enable = 0;
ipvs->net = net;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index e3be48b..008bf97 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -856,15 +856,12 @@
}
dest = kzalloc(sizeof(struct ip_vs_dest), GFP_KERNEL);
- if (dest == NULL) {
- pr_err("%s(): no memory.\n", __func__);
+ if (dest == NULL)
return -ENOMEM;
- }
+
dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
- if (!dest->stats.cpustats) {
- pr_err("%s() alloc_percpu failed\n", __func__);
+ if (!dest->stats.cpustats)
goto err_alloc;
- }
dest->af = svc->af;
dest->protocol = svc->protocol;
@@ -1168,10 +1165,8 @@
goto out_err;
}
svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
- if (!svc->stats.cpustats) {
- pr_err("%s() alloc_percpu failed\n", __func__);
+ if (!svc->stats.cpustats)
goto out_err;
- }
/* I'm the first user of the service */
atomic_set(&svc->usecnt, 0);
@@ -3326,10 +3321,8 @@
int ret = 0, cmd;
int need_full_svc = 0, need_full_dest = 0;
struct net *net;
- struct netns_ipvs *ipvs;
net = skb_sknet(skb);
- ipvs = net_ipvs(net);
cmd = info->genlhdr->cmd;
mutex_lock(&__ip_vs_mutex);
@@ -3421,10 +3414,8 @@
void *reply;
int ret, cmd, reply_cmd;
struct net *net;
- struct netns_ipvs *ipvs;
net = skb_sknet(skb);
- ipvs = net_ipvs(net);
cmd = info->genlhdr->cmd;
if (cmd == IPVS_CMD_GET_SERVICE)
@@ -3720,10 +3711,9 @@
/* procfs stats */
ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
- if (!ipvs->tot_stats.cpustats) {
- pr_err("%s(): alloc_percpu.\n", __func__);
+ if (!ipvs->tot_stats.cpustats)
return -ENOMEM;
- }
+
spin_lock_init(&ipvs->tot_stats.lock);
proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index 95fd0d1..1c269e5 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -150,10 +150,9 @@
/* allocate the DH table for this service */
tbl = kmalloc(sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE,
GFP_ATOMIC);
- if (tbl == NULL) {
- pr_err("%s(): no memory\n", __func__);
+ if (tbl == NULL)
return -ENOMEM;
- }
+
svc->sched_data = tbl;
IP_VS_DBG(6, "DH hash table (memory=%Zdbytes) allocated for "
"current service\n",
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 4490a32..538d74e 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -52,8 +52,9 @@
* List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper
* First port is set to the default port.
*/
+static unsigned int ports_count = 1;
static unsigned short ports[IP_VS_APP_MAX_PORTS] = {21, 0};
-module_param_array(ports, ushort, NULL, 0);
+module_param_array(ports, ushort, &ports_count, 0444);
MODULE_PARM_DESC(ports, "Ports to monitor for FTP control commands");
@@ -449,7 +450,7 @@
if (ret)
goto err_exit;
- for (i=0; i<IP_VS_APP_MAX_PORTS; i++) {
+ for (i = 0; i < ports_count; i++) {
if (!ports[i])
continue;
ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]);
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 87e40ea..0f16283 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -202,10 +202,8 @@
en = ip_vs_lblc_get(dest->af, tbl, daddr);
if (!en) {
en = kmalloc(sizeof(*en), GFP_ATOMIC);
- if (!en) {
- pr_err("%s(): no memory\n", __func__);
+ if (!en)
return NULL;
- }
en->af = dest->af;
ip_vs_addr_copy(dest->af, &en->addr, daddr);
@@ -345,10 +343,9 @@
* Allocate the ip_vs_lblc_table for this service
*/
tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC);
- if (tbl == NULL) {
- pr_err("%s(): no memory\n", __func__);
+ if (tbl == NULL)
return -ENOMEM;
- }
+
svc->sched_data = tbl;
IP_VS_DBG(6, "LBLC hash table (memory=%Zdbytes) allocated for "
"current service\n", sizeof(*tbl));
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 90f618a..eec797f 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -112,10 +112,8 @@
}
e = kmalloc(sizeof(*e), GFP_ATOMIC);
- if (e == NULL) {
- pr_err("%s(): no memory\n", __func__);
+ if (e == NULL)
return NULL;
- }
atomic_inc(&dest->refcnt);
e->dest = dest;
@@ -373,10 +371,8 @@
en = ip_vs_lblcr_get(dest->af, tbl, daddr);
if (!en) {
en = kmalloc(sizeof(*en), GFP_ATOMIC);
- if (!en) {
- pr_err("%s(): no memory\n", __func__);
+ if (!en)
return NULL;
- }
en->af = dest->af;
ip_vs_addr_copy(dest->af, &en->addr, daddr);
@@ -516,10 +512,9 @@
* Allocate the ip_vs_lblcr_table for this service
*/
tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC);
- if (tbl == NULL) {
- pr_err("%s(): no memory\n", __func__);
+ if (tbl == NULL)
return -ENOMEM;
- }
+
svc->sched_data = tbl;
IP_VS_DBG(6, "LBLCR hash table (memory=%Zdbytes) allocated for "
"current service\n", sizeof(*tbl));
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index f454c80..022e77e 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -127,7 +127,7 @@
nf_conntrack_alter_reply(ct, &new_tuple);
}
-int ip_vs_confirm_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp)
+int ip_vs_confirm_conntrack(struct sk_buff *skb)
{
return nf_conntrack_confirm(skb);
}
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 52d073c..8531293 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -74,10 +74,9 @@
struct ip_vs_proto_data *pd =
kzalloc(sizeof(struct ip_vs_proto_data), GFP_ATOMIC);
- if (!pd) {
- pr_err("%s(): no memory.\n", __func__);
+ if (!pd)
return -ENOMEM;
- }
+
pd->pp = pp; /* For speed issues */
pd->next = ipvs->proto_data_table[hash];
ipvs->proto_data_table[hash] = pd;
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index d12ed53..1fbf7a2 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -906,7 +906,7 @@
return "?";
}
-static inline int
+static inline void
set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
int direction, const struct sk_buff *skb)
{
@@ -924,7 +924,7 @@
sch = skb_header_pointer(skb, ihl + sizeof(sctp_sctphdr_t),
sizeof(_sctpch), &_sctpch);
if (sch == NULL)
- return 0;
+ return;
chunk_type = sch->type;
/*
@@ -993,21 +993,15 @@
cp->timeout = pd->timeout_table[cp->state = next_state];
else /* What to do ? */
cp->timeout = sctp_timeouts[cp->state = next_state];
-
- return 1;
}
-static int
+static void
sctp_state_transition(struct ip_vs_conn *cp, int direction,
const struct sk_buff *skb, struct ip_vs_proto_data *pd)
{
- int ret = 0;
-
spin_lock(&cp->lock);
- ret = set_sctp_state(pd, cp, direction, skb);
+ set_sctp_state(pd, cp, direction, skb);
spin_unlock(&cp->lock);
-
- return ret;
}
static inline __u16 sctp_app_hashkey(__be16 port)
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index c0cc341..ef8641f 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -546,7 +546,7 @@
/*
* Handle state transitions
*/
-static int
+static void
tcp_state_transition(struct ip_vs_conn *cp, int direction,
const struct sk_buff *skb,
struct ip_vs_proto_data *pd)
@@ -561,13 +561,11 @@
th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph);
if (th == NULL)
- return 0;
+ return;
spin_lock(&cp->lock);
set_tcp_state(pd, cp, direction, th);
spin_unlock(&cp->lock);
-
- return 1;
}
static inline __u16 tcp_app_hashkey(__be16 port)
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index f1282cb..f4b7262 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -454,18 +454,17 @@
return udp_state_name_table[state] ? udp_state_name_table[state] : "?";
}
-static int
+static void
udp_state_transition(struct ip_vs_conn *cp, int direction,
const struct sk_buff *skb,
struct ip_vs_proto_data *pd)
{
if (unlikely(!pd)) {
pr_err("UDP no ns data\n");
- return 0;
+ return;
}
cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL];
- return 1;
}
static void __udp_init(struct net *net, struct ip_vs_proto_data *pd)
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index b5e2556..33815f4 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -147,10 +147,9 @@
/* allocate the SH table for this service */
tbl = kmalloc(sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE,
GFP_ATOMIC);
- if (tbl == NULL) {
- pr_err("%s(): no memory\n", __func__);
+ if (tbl == NULL)
return -ENOMEM;
- }
+
svc->sched_data = tbl;
IP_VS_DBG(6, "SH hash table (memory=%Zdbytes) allocated for "
"current service\n",
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 1ef41f5..fd0d4e0 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -85,10 +85,9 @@
* Allocate the mark variable for WRR scheduling
*/
mark = kmalloc(sizeof(struct ip_vs_wrr_mark), GFP_ATOMIC);
- if (mark == NULL) {
- pr_err("%s(): no memory\n", __func__);
+ if (mark == NULL)
return -ENOMEM;
- }
+
mark->cl = &svc->destinations;
mark->cw = 0;
mark->mw = ip_vs_wrr_max_weight(svc);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index ee319a4..aa2d720 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -339,7 +339,7 @@
\
(skb)->ipvs_property = 1; \
if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \
- __ret = ip_vs_confirm_conntrack(skb, cp); \
+ __ret = ip_vs_confirm_conntrack(skb); \
if (__ret == NF_ACCEPT) { \
nf_reset(skb); \
skb_forward_csum(skb); \
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5acfaf5..7202b06 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -661,7 +661,6 @@
*/
ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp);
if (ct == NULL) {
- pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n");
atomic_dec(&net->ct.count);
return ERR_PTR(-ENOMEM);
}
@@ -749,10 +748,8 @@
ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
hash);
- if (IS_ERR(ct)) {
- pr_debug("Can't allocate conntrack.\n");
+ if (IS_ERR(ct))
return (struct nf_conntrack_tuple_hash *)ct;
- }
if (!l4proto->new(ct, skb, dataoff)) {
nf_conntrack_free(ct);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 2d8158a..66b2c54 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -307,17 +307,14 @@
n = max(inst_size, pkt_size);
skb = alloc_skb(n, GFP_ATOMIC);
if (!skb) {
- pr_notice("nfnetlink_log: can't alloc whole buffer (%u bytes)\n",
- inst_size);
-
if (n > pkt_size) {
/* try to allocate only as much as we need for current
* packet */
skb = alloc_skb(pkt_size, GFP_ATOMIC);
if (!skb)
- pr_err("nfnetlink_log: can't even alloc %u "
- "bytes\n", pkt_size);
+ pr_err("nfnetlink_log: can't even alloc %u bytes\n",
+ pkt_size);
}
}
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 3bdd443..f407ebc1 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -122,14 +122,12 @@
info->timer = kmalloc(sizeof(*info->timer), GFP_KERNEL);
if (!info->timer) {
- pr_debug("couldn't alloc timer\n");
ret = -ENOMEM;
goto out;
}
info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL);
if (!info->timer->attr.attr.name) {
- pr_debug("couldn't alloc attribute name\n");
ret = -ENOMEM;
goto out_free_timer;
}
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 9228ee0d..dfd52ba 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -176,10 +176,7 @@
ent = NULL;
} else
ent = kmem_cache_alloc(hashlimit_cachep, GFP_ATOMIC);
- if (!ent) {
- if (net_ratelimit())
- pr_err("cannot allocate dsthash_ent\n");
- } else {
+ if (ent) {
memcpy(&ent->dst, dst, sizeof(ent->dst));
spin_lock_init(&ent->lock);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 03bb45a..82a6f34 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -335,7 +335,7 @@
(((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \
((x)->kactive_blk_num+1) : 0)
-static inline struct packet_sock *pkt_sk(struct sock *sk)
+static struct packet_sock *pkt_sk(struct sock *sk)
{
return (struct packet_sock *)sk;
}
@@ -477,7 +477,7 @@
return h.raw;
}
-static inline void *packet_current_frame(struct packet_sock *po,
+static void *packet_current_frame(struct packet_sock *po,
struct packet_ring_buffer *rb,
int status)
{
@@ -715,7 +715,7 @@
spin_unlock(&po->sk.sk_receive_queue.lock);
}
-static inline void prb_flush_block(struct tpacket_kbdq_core *pkc1,
+static void prb_flush_block(struct tpacket_kbdq_core *pkc1,
struct tpacket_block_desc *pbd1, __u32 status)
{
/* Flush everything minus the block header */
@@ -793,7 +793,7 @@
pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1);
}
-static inline void prb_thaw_queue(struct tpacket_kbdq_core *pkc)
+static void prb_thaw_queue(struct tpacket_kbdq_core *pkc)
{
pkc->reset_pending_on_curr_blk = 0;
}
@@ -869,7 +869,7 @@
* case and __packet_lookup_frame_in_block will check if block-0
* is free and can now be re-used.
*/
-static inline void prb_freeze_queue(struct tpacket_kbdq_core *pkc,
+static void prb_freeze_queue(struct tpacket_kbdq_core *pkc,
struct packet_sock *po)
{
pkc->reset_pending_on_curr_blk = 1;
@@ -940,36 +940,36 @@
BUG();
}
-static inline int prb_curr_blk_in_use(struct tpacket_kbdq_core *pkc,
+static int prb_curr_blk_in_use(struct tpacket_kbdq_core *pkc,
struct tpacket_block_desc *pbd)
{
return TP_STATUS_USER & BLOCK_STATUS(pbd);
}
-static inline int prb_queue_frozen(struct tpacket_kbdq_core *pkc)
+static int prb_queue_frozen(struct tpacket_kbdq_core *pkc)
{
return pkc->reset_pending_on_curr_blk;
}
-static inline void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
+static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
{
struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb);
atomic_dec(&pkc->blk_fill_in_prog);
}
-static inline void prb_fill_rxhash(struct tpacket_kbdq_core *pkc,
+static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc,
struct tpacket3_hdr *ppd)
{
ppd->hv1.tp_rxhash = skb_get_rxhash(pkc->skb);
}
-static inline void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
+static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
struct tpacket3_hdr *ppd)
{
ppd->hv1.tp_rxhash = 0;
}
-static inline void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
+static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
struct tpacket3_hdr *ppd)
{
if (vlan_tx_tag_present(pkc->skb)) {
@@ -991,7 +991,7 @@
prb_clear_rxhash(pkc, ppd);
}
-static inline void prb_fill_curr_block(char *curr,
+static void prb_fill_curr_block(char *curr,
struct tpacket_kbdq_core *pkc,
struct tpacket_block_desc *pbd,
unsigned int len)
@@ -1071,7 +1071,7 @@
return NULL;
}
-static inline void *packet_current_rx_frame(struct packet_sock *po,
+static void *packet_current_rx_frame(struct packet_sock *po,
struct sk_buff *skb,
int status, unsigned int len)
{
@@ -1091,7 +1091,7 @@
}
}
-static inline void *prb_lookup_block(struct packet_sock *po,
+static void *prb_lookup_block(struct packet_sock *po,
struct packet_ring_buffer *rb,
unsigned int previous,
int status)
@@ -1104,7 +1104,7 @@
return pbd;
}
-static inline int prb_previous_blk_num(struct packet_ring_buffer *rb)
+static int prb_previous_blk_num(struct packet_ring_buffer *rb)
{
unsigned int prev;
if (rb->prb_bdqc.kactive_blk_num)
@@ -1115,7 +1115,7 @@
}
/* Assumes caller has held the rx_queue.lock */
-static inline void *__prb_previous_block(struct packet_sock *po,
+static void *__prb_previous_block(struct packet_sock *po,
struct packet_ring_buffer *rb,
int status)
{
@@ -1123,7 +1123,7 @@
return prb_lookup_block(po, rb, previous, status);
}
-static inline void *packet_previous_rx_frame(struct packet_sock *po,
+static void *packet_previous_rx_frame(struct packet_sock *po,
struct packet_ring_buffer *rb,
int status)
{
@@ -1133,7 +1133,7 @@
return __prb_previous_block(po, rb, status);
}
-static inline void packet_increment_rx_head(struct packet_sock *po,
+static void packet_increment_rx_head(struct packet_sock *po,
struct packet_ring_buffer *rb)
{
switch (po->tp_version) {
@@ -1148,7 +1148,7 @@
}
}
-static inline void *packet_previous_frame(struct packet_sock *po,
+static void *packet_previous_frame(struct packet_sock *po,
struct packet_ring_buffer *rb,
int status)
{
@@ -1156,7 +1156,7 @@
return packet_lookup_frame(po, rb, previous, status);
}
-static inline void packet_increment_head(struct packet_ring_buffer *buff)
+static void packet_increment_head(struct packet_ring_buffer *buff)
{
buff->head = buff->head != buff->frame_max ? buff->head+1 : 0;
}
@@ -1558,7 +1558,7 @@
return err;
}
-static inline unsigned int run_filter(const struct sk_buff *skb,
+static unsigned int run_filter(const struct sk_buff *skb,
const struct sock *sk,
unsigned int res)
{
@@ -2167,10 +2167,10 @@
return err;
}
-static inline struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
- size_t reserve, size_t len,
- size_t linear, int noblock,
- int *err)
+static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
+ size_t reserve, size_t len,
+ size_t linear, int noblock,
+ int *err)
{
struct sk_buff *skb;
@@ -3494,7 +3494,7 @@
kfree(pg_vec);
}
-static inline char *alloc_one_pg_vec_page(unsigned long order)
+static char *alloc_one_pg_vec_page(unsigned long order)
{
char *buffer = NULL;
gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP |
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 5f03e4e..3e16c6a 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1261,14 +1261,19 @@
struct x25_sock *x25 = x25_sk(sk);
struct sockaddr_x25 *sx25 = (struct sockaddr_x25 *)msg->msg_name;
size_t copied;
- int qbit, header_len = x25->neighbour->extended ?
- X25_EXT_MIN_LEN : X25_STD_MIN_LEN;
-
+ int qbit, header_len;
struct sk_buff *skb;
unsigned char *asmptr;
int rc = -ENOTCONN;
lock_sock(sk);
+
+ if (x25->neighbour == NULL)
+ goto out;
+
+ header_len = x25->neighbour->extended ?
+ X25_EXT_MIN_LEN : X25_STD_MIN_LEN;
+
/*
* This works for seqpacket too. The receiver has ordered the queue for
* us! We do one quick check first though
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 19c053b..4f554f2 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -9,7 +9,7 @@
select CRYPTO_HMAC
select CRYPTO_MD5
select CRYPTO_SHA1
- select TCG_TPM if !S390
+ select TCG_TPM if !S390 && !UML
select TCG_TIS if TCG_TPM
help
The Trusted Computing Group(TCG) runtime Integrity
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index 150911c..c47d3ce 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -966,6 +966,9 @@
return found;
}
+static struct tomoyo_domain_info *tomoyo_find_domain_by_qid
+(unsigned int serial);
+
/**
* tomoyo_select_domain - Parse select command.
*
@@ -999,6 +1002,8 @@
} else if (!strncmp(data, "domain=", 7)) {
if (tomoyo_domain_def(data + 7))
domain = tomoyo_find_domain(data + 7);
+ } else if (sscanf(data, "Q=%u", &pid) == 1) {
+ domain = tomoyo_find_domain_by_qid(pid);
} else
return false;
head->w.domain = domain;
@@ -1894,6 +1899,7 @@
/* Structure for query. */
struct tomoyo_query {
struct list_head list;
+ struct tomoyo_domain_info *domain;
char *query;
size_t query_len;
unsigned int serial;
@@ -2044,6 +2050,7 @@
goto out;
}
len = tomoyo_round2(entry.query_len);
+ entry.domain = r->domain;
spin_lock(&tomoyo_query_list_lock);
if (tomoyo_memory_quota[TOMOYO_MEMORY_QUERY] &&
tomoyo_memory_used[TOMOYO_MEMORY_QUERY] + len
@@ -2091,6 +2098,29 @@
}
/**
+ * tomoyo_find_domain_by_qid - Get domain by query id.
+ *
+ * @serial: Query ID assigned by tomoyo_supervisor().
+ *
+ * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise.
+ */
+static struct tomoyo_domain_info *tomoyo_find_domain_by_qid
+(unsigned int serial)
+{
+ struct tomoyo_query *ptr;
+ struct tomoyo_domain_info *domain = NULL;
+ spin_lock(&tomoyo_query_list_lock);
+ list_for_each_entry(ptr, &tomoyo_query_list, list) {
+ if (ptr->serial != serial || ptr->answer)
+ continue;
+ domain = ptr->domain;
+ break;
+ }
+ spin_unlock(&tomoyo_query_list_lock);
+ return domain;
+}
+
+/**
* tomoyo_poll_query - poll() for /sys/kernel/security/tomoyo/query.
*
* @file: Pointer to "struct file".
diff --git a/sound/Kconfig b/sound/Kconfig
index 1fef141..261a03c 100644
--- a/sound/Kconfig
+++ b/sound/Kconfig
@@ -59,7 +59,7 @@
source "sound/oss/dmasound/Kconfig"
-if !M68K
+if !M68K && !UML
menuconfig SND
tristate "Advanced Linux Sound Architecture"
diff --git a/sound/mips/Kconfig b/sound/mips/Kconfig
index 77dd0a1..d2f615a 100644
--- a/sound/mips/Kconfig
+++ b/sound/mips/Kconfig
@@ -24,7 +24,7 @@
config SND_AU1X00
tristate "Au1x00 AC97 Port Driver (DEPRECATED)"
- depends on SOC_AU1000 || SOC_AU1100 || SOC_AU1500
+ depends on MIPS_ALCHEMY
select SND_PCM
select SND_AC97_CODEC
help
diff --git a/sound/soc/au1x/Kconfig b/sound/soc/au1x/Kconfig
index 6d59254..e908a81 100644
--- a/sound/soc/au1x/Kconfig
+++ b/sound/soc/au1x/Kconfig
@@ -3,7 +3,7 @@
##
config SND_SOC_AU1XPSC
tristate "SoC Audio for Au1200/Au1250/Au1550"
- depends on SOC_AU1200 || SOC_AU1550
+ depends on MIPS_ALCHEMY
help
This option enables support for the Programmable Serial
Controllers in AC97 and I2S mode, and the Descriptor-Based DMA