Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw
* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw:
[GFS2] Fix GFS2's use of do_div() in its quota calculations
[GFS2] Remove unused declaration
[GFS2] Remove support for unused and pointless flag
[GFS2] Replace rgrp "recent list" with mru list
[GFS2] Allow local DF locks when holding a cached EX glock
[GFS2] Fix delayed demote race
[GFS2] don't call permission()
[GFS2] Fix module building
[GFS2] Glock documentation
[GFS2] Remove all_list from lock_dlm
[GFS2] Remove obsolete conversion deadlock avoidance code
[GFS2] Remove remote lock dropping code
[GFS2] kernel panic mounting volume
[GFS2] Revise readpage locking
[GFS2] Fix ordering of args for list_add
[GFS2] trivial sparse lock annotations
[GFS2] No lock_nolock
[GFS2] Fix ordering bug in lock_dlm
[GFS2] Clean up the glock core
diff --git a/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt
new file mode 100644
index 0000000..4dae9a3
--- /dev/null
+++ b/Documentation/filesystems/gfs2-glocks.txt
@@ -0,0 +1,114 @@
+ Glock internal locking rules
+ ------------------------------
+
+This documents the basic principles of the glock state machine
+internals. Each glock (struct gfs2_glock in fs/gfs2/incore.h)
+has two main (internal) locks:
+
+ 1. A spinlock (gl_spin) which protects the internal state such
+ as gl_state, gl_target and the list of holders (gl_holders)
+ 2. A non-blocking bit lock, GLF_LOCK, which is used to prevent other
+ threads from making calls to the DLM, etc. at the same time. If a
+ thread takes this lock, it must then call run_queue (usually via the
+ workqueue) when it releases it in order to ensure any pending tasks
+ are completed.
+
+The gl_holders list contains all the queued lock requests (not
+just the holders) associated with the glock. If there are any
+held locks, then they will be contiguous entries at the head
+of the list. Locks are granted in strictly the order that they
+are queued, except for those marked LM_FLAG_PRIORITY which are
+used only during recovery, and even then only for journal locks.
+
+There are three lock states that users of the glock layer can request,
+namely shared (SH), deferred (DF) and exclusive (EX). Those translate
+to the following DLM lock modes:
+
+Glock mode | DLM lock mode
+------------------------------
+ UN | IV/NL Unlocked (no DLM lock associated with glock) or NL
+ SH | PR (Protected read)
+ DF | CW (Concurrent write)
+ EX | EX (Exclusive)
+
+Thus DF is basically a shared mode which is incompatible with the "normal"
+shared lock mode, SH. In GFS2 the DF mode is used exclusively for direct I/O
+operations. The glocks are basically a lock plus some routines which deal
+with cache management. The following rules apply for the cache:
+
+Glock mode | Cache data | Cache Metadata | Dirty Data | Dirty Metadata
+--------------------------------------------------------------------------
+ UN | No | No | No | No
+ SH | Yes | Yes | No | No
+ DF | No | Yes | No | No
+ EX | Yes | Yes | Yes | Yes
+
+These rules are implemented using the various glock operations which
+are defined for each type of glock. Not all types of glocks use
+all the modes. Only inode glocks use the DF mode for example.
+
+Table of glock operations and per type constants:
+
+Field | Purpose
+----------------------------------------------------------------------------
+go_xmote_th | Called before remote state change (e.g. to sync dirty data)
+go_xmote_bh | Called after remote state change (e.g. to refill cache)
+go_inval | Called if remote state change requires invalidating the cache
+go_demote_ok | Returns boolean value of whether its ok to demote a glock
+ | (e.g. checks timeout, and that there is no cached data)
+go_lock | Called for the first local holder of a lock
+go_unlock | Called on the final local unlock of a lock
+go_dump | Called to print content of object for debugfs file, or on
+ | error to dump glock to the log.
+go_type; | The type of the glock, LM_TYPE_.....
+go_min_hold_time | The minimum hold time
+
+The minimum hold time for each lock is the time after a remote lock
+grant for which we ignore remote demote requests. This is in order to
+prevent a situation where locks are being bounced around the cluster
+from node to node with none of the nodes making any progress. This
+tends to show up most with shared mmaped files which are being written
+to by multiple nodes. By delaying the demotion in response to a
+remote callback, that gives the userspace program time to make
+some progress before the pages are unmapped.
+
+There is a plan to try and remove the go_lock and go_unlock callbacks
+if possible, in order to try and speed up the fast path though the locking.
+Also, eventually we hope to make the glock "EX" mode locally shared
+such that any local locking will be done with the i_mutex as required
+rather than via the glock.
+
+Locking rules for glock operations:
+
+Operation | GLF_LOCK bit lock held | gl_spin spinlock held
+-----------------------------------------------------------------
+go_xmote_th | Yes | No
+go_xmote_bh | Yes | No
+go_inval | Yes | No
+go_demote_ok | Sometimes | Yes
+go_lock | Yes | No
+go_unlock | Yes | No
+go_dump | Sometimes | Yes
+
+N.B. Operations must not drop either the bit lock or the spinlock
+if its held on entry. go_dump and do_demote_ok must never block.
+Note that go_dump will only be called if the glock's state
+indicates that it is caching uptodate data.
+
+Glock locking order within GFS2:
+
+ 1. i_mutex (if required)
+ 2. Rename glock (for rename only)
+ 3. Inode glock(s)
+ (Parents before children, inodes at "same level" with same parent in
+ lock number order)
+ 4. Rgrp glock(s) (for (de)allocation operations)
+ 5. Transaction glock (via gfs2_trans_begin) for non-read operations
+ 6. Page lock (always last, very important!)
+
+There are two glocks per inode. One deals with access to the inode
+itself (locking order as above), and the other, known as the iopen
+glock is used in conjunction with the i_nlink field in the inode to
+determine the lifetime of the inode in question. Locking of inodes
+is on a per-inode basis. Locking of rgrps is on a per rgrp basis.
+
diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig
index 7f7947e..ab2f57e 100644
--- a/fs/gfs2/Kconfig
+++ b/fs/gfs2/Kconfig
@@ -14,23 +14,11 @@
GFS is perfect consistency -- changes made to the filesystem on one
machine show up immediately on all other machines in the cluster.
- To use the GFS2 filesystem, you will need to enable one or more of
- the below locking modules. Documentation and utilities for GFS2 can
+ To use the GFS2 filesystem in a cluster, you will need to enable
+ the locking module below. Documentation and utilities for GFS2 can
be found here: http://sources.redhat.com/cluster
-config GFS2_FS_LOCKING_NOLOCK
- tristate "GFS2 \"nolock\" locking module"
- depends on GFS2_FS
- help
- Single node locking module for GFS2.
-
- Use this module if you want to use GFS2 on a single node without
- its clustering features. You can still take advantage of the
- large file support, and upgrade to running a full cluster later on
- if required.
-
- If you will only be using GFS2 in cluster mode, you do not need this
- module.
+ The "nolock" lock module is now built in to GFS2 by default.
config GFS2_FS_LOCKING_DLM
tristate "GFS2 DLM locking module"
diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
index e2350df..ec65851 100644
--- a/fs/gfs2/Makefile
+++ b/fs/gfs2/Makefile
@@ -5,6 +5,5 @@
ops_fstype.o ops_inode.o ops_super.o quota.o \
recovery.o rgrp.o super.o sys.o trans.o util.o
-obj-$(CONFIG_GFS2_FS_LOCKING_NOLOCK) += locking/nolock/
obj-$(CONFIG_GFS2_FS_LOCKING_DLM) += locking/dlm/
diff --git a/fs/gfs2/gfs2.h b/fs/gfs2/gfs2.h
index 3bb11c0..ef606e3 100644
--- a/fs/gfs2/gfs2.h
+++ b/fs/gfs2/gfs2.h
@@ -16,11 +16,6 @@
};
enum {
- NO_WAIT = 0,
- WAIT = 1,
-};
-
-enum {
NO_FORCE = 0,
FORCE = 1,
};
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index d636b3e..13391e5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -45,21 +45,19 @@
struct hlist_head hb_list;
};
-struct glock_iter {
- int hash; /* hash bucket index */
- struct gfs2_sbd *sdp; /* incore superblock */
- struct gfs2_glock *gl; /* current glock struct */
- struct seq_file *seq; /* sequence file for debugfs */
- char string[512]; /* scratch space */
+struct gfs2_glock_iter {
+ int hash; /* hash bucket index */
+ struct gfs2_sbd *sdp; /* incore superblock */
+ struct gfs2_glock *gl; /* current glock struct */
+ char string[512]; /* scratch space */
};
typedef void (*glock_examiner) (struct gfs2_glock * gl);
static int gfs2_dump_lockstate(struct gfs2_sbd *sdp);
-static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl);
-static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh);
-static void gfs2_glock_drop_th(struct gfs2_glock *gl);
-static void run_queue(struct gfs2_glock *gl);
+static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl);
+#define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { __dump_glock(NULL, gl); BUG(); } } while(0)
+static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target);
static DECLARE_RWSEM(gfs2_umount_flush_sem);
static struct dentry *gfs2_root;
@@ -123,33 +121,6 @@
#endif
/**
- * relaxed_state_ok - is a requested lock compatible with the current lock mode?
- * @actual: the current state of the lock
- * @requested: the lock state that was requested by the caller
- * @flags: the modifier flags passed in by the caller
- *
- * Returns: 1 if the locks are compatible, 0 otherwise
- */
-
-static inline int relaxed_state_ok(unsigned int actual, unsigned requested,
- int flags)
-{
- if (actual == requested)
- return 1;
-
- if (flags & GL_EXACT)
- return 0;
-
- if (actual == LM_ST_EXCLUSIVE && requested == LM_ST_SHARED)
- return 1;
-
- if (actual != LM_ST_UNLOCKED && (flags & LM_FLAG_ANY))
- return 1;
-
- return 0;
-}
-
-/**
* gl_hash() - Turn glock number into hash bucket number
* @lock: The glock number
*
@@ -182,7 +153,7 @@
struct gfs2_sbd *sdp = gl->gl_sbd;
struct inode *aspace = gl->gl_aspace;
- if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+ if (sdp->sd_lockstruct.ls_ops->lm_put_lock)
sdp->sd_lockstruct.ls_ops->lm_put_lock(gl->gl_lock);
if (aspace)
@@ -211,17 +182,14 @@
int gfs2_glock_put(struct gfs2_glock *gl)
{
int rv = 0;
- struct gfs2_sbd *sdp = gl->gl_sbd;
write_lock(gl_lock_addr(gl->gl_hash));
if (atomic_dec_and_test(&gl->gl_ref)) {
hlist_del(&gl->gl_list);
write_unlock(gl_lock_addr(gl->gl_hash));
- gfs2_assert(sdp, gl->gl_state == LM_ST_UNLOCKED);
- gfs2_assert(sdp, list_empty(&gl->gl_reclaim));
- gfs2_assert(sdp, list_empty(&gl->gl_holders));
- gfs2_assert(sdp, list_empty(&gl->gl_waiters1));
- gfs2_assert(sdp, list_empty(&gl->gl_waiters3));
+ GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_UNLOCKED);
+ GLOCK_BUG_ON(gl, !list_empty(&gl->gl_reclaim));
+ GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
glock_free(gl);
rv = 1;
goto out;
@@ -281,22 +249,401 @@
return gl;
}
-static void glock_work_func(struct work_struct *work)
+/**
+ * may_grant - check if its ok to grant a new lock
+ * @gl: The glock
+ * @gh: The lock request which we wish to grant
+ *
+ * Returns: true if its ok to grant the lock
+ */
+
+static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
{
- struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
+ const struct gfs2_holder *gh_head = list_entry(gl->gl_holders.next, const struct gfs2_holder, gh_list);
+ if ((gh->gh_state == LM_ST_EXCLUSIVE ||
+ gh_head->gh_state == LM_ST_EXCLUSIVE) && gh != gh_head)
+ return 0;
+ if (gl->gl_state == gh->gh_state)
+ return 1;
+ if (gh->gh_flags & GL_EXACT)
+ return 0;
+ if (gl->gl_state == LM_ST_EXCLUSIVE) {
+ if (gh->gh_state == LM_ST_SHARED && gh_head->gh_state == LM_ST_SHARED)
+ return 1;
+ if (gh->gh_state == LM_ST_DEFERRED && gh_head->gh_state == LM_ST_DEFERRED)
+ return 1;
+ }
+ if (gl->gl_state != LM_ST_UNLOCKED && (gh->gh_flags & LM_FLAG_ANY))
+ return 1;
+ return 0;
+}
+
+static void gfs2_holder_wake(struct gfs2_holder *gh)
+{
+ clear_bit(HIF_WAIT, &gh->gh_iflags);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&gh->gh_iflags, HIF_WAIT);
+}
+
+/**
+ * do_promote - promote as many requests as possible on the current queue
+ * @gl: The glock
+ *
+ * Returns: true if there is a blocked holder at the head of the list
+ */
+
+static int do_promote(struct gfs2_glock *gl)
+{
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ struct gfs2_holder *gh, *tmp;
+ int ret;
+
+restart:
+ list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
+ if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+ continue;
+ if (may_grant(gl, gh)) {
+ if (gh->gh_list.prev == &gl->gl_holders &&
+ glops->go_lock) {
+ spin_unlock(&gl->gl_spin);
+ /* FIXME: eliminate this eventually */
+ ret = glops->go_lock(gh);
+ spin_lock(&gl->gl_spin);
+ if (ret) {
+ gh->gh_error = ret;
+ list_del_init(&gh->gh_list);
+ gfs2_holder_wake(gh);
+ goto restart;
+ }
+ set_bit(HIF_HOLDER, &gh->gh_iflags);
+ gfs2_holder_wake(gh);
+ goto restart;
+ }
+ set_bit(HIF_HOLDER, &gh->gh_iflags);
+ gfs2_holder_wake(gh);
+ continue;
+ }
+ if (gh->gh_list.prev == &gl->gl_holders)
+ return 1;
+ break;
+ }
+ return 0;
+}
+
+/**
+ * do_error - Something unexpected has happened during a lock request
+ *
+ */
+
+static inline void do_error(struct gfs2_glock *gl, const int ret)
+{
+ struct gfs2_holder *gh, *tmp;
+
+ list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
+ if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+ continue;
+ if (ret & LM_OUT_ERROR)
+ gh->gh_error = -EIO;
+ else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
+ gh->gh_error = GLR_TRYFAILED;
+ else
+ continue;
+ list_del_init(&gh->gh_list);
+ gfs2_holder_wake(gh);
+ }
+}
+
+/**
+ * find_first_waiter - find the first gh that's waiting for the glock
+ * @gl: the glock
+ */
+
+static inline struct gfs2_holder *find_first_waiter(const struct gfs2_glock *gl)
+{
+ struct gfs2_holder *gh;
+
+ list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+ if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+ return gh;
+ }
+ return NULL;
+}
+
+/**
+ * state_change - record that the glock is now in a different state
+ * @gl: the glock
+ * @new_state the new state
+ *
+ */
+
+static void state_change(struct gfs2_glock *gl, unsigned int new_state)
+{
+ int held1, held2;
+
+ held1 = (gl->gl_state != LM_ST_UNLOCKED);
+ held2 = (new_state != LM_ST_UNLOCKED);
+
+ if (held1 != held2) {
+ if (held2)
+ gfs2_glock_hold(gl);
+ else
+ gfs2_glock_put(gl);
+ }
+
+ gl->gl_state = new_state;
+ gl->gl_tchange = jiffies;
+}
+
+static void gfs2_demote_wake(struct gfs2_glock *gl)
+{
+ gl->gl_demote_state = LM_ST_EXCLUSIVE;
+ clear_bit(GLF_DEMOTE, &gl->gl_flags);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
+}
+
+/**
+ * finish_xmote - The DLM has replied to one of our lock requests
+ * @gl: The glock
+ * @ret: The status from the DLM
+ *
+ */
+
+static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
+{
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ struct gfs2_holder *gh;
+ unsigned state = ret & LM_OUT_ST_MASK;
spin_lock(&gl->gl_spin);
- if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags))
- set_bit(GLF_DEMOTE, &gl->gl_flags);
- run_queue(gl);
+ state_change(gl, state);
+ gh = find_first_waiter(gl);
+
+ /* Demote to UN request arrived during demote to SH or DF */
+ if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags) &&
+ state != LM_ST_UNLOCKED && gl->gl_demote_state == LM_ST_UNLOCKED)
+ gl->gl_target = LM_ST_UNLOCKED;
+
+ /* Check for state != intended state */
+ if (unlikely(state != gl->gl_target)) {
+ if (gh && !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)) {
+ /* move to back of queue and try next entry */
+ if (ret & LM_OUT_CANCELED) {
+ if ((gh->gh_flags & LM_FLAG_PRIORITY) == 0)
+ list_move_tail(&gh->gh_list, &gl->gl_holders);
+ gh = find_first_waiter(gl);
+ gl->gl_target = gh->gh_state;
+ goto retry;
+ }
+ /* Some error or failed "try lock" - report it */
+ if ((ret & LM_OUT_ERROR) ||
+ (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) {
+ gl->gl_target = gl->gl_state;
+ do_error(gl, ret);
+ goto out;
+ }
+ }
+ switch(state) {
+ /* Unlocked due to conversion deadlock, try again */
+ case LM_ST_UNLOCKED:
+retry:
+ do_xmote(gl, gh, gl->gl_target);
+ break;
+ /* Conversion fails, unlock and try again */
+ case LM_ST_SHARED:
+ case LM_ST_DEFERRED:
+ do_xmote(gl, gh, LM_ST_UNLOCKED);
+ break;
+ default: /* Everything else */
+ printk(KERN_ERR "GFS2: wanted %u got %u\n", gl->gl_target, state);
+ GLOCK_BUG_ON(gl, 1);
+ }
+ spin_unlock(&gl->gl_spin);
+ gfs2_glock_put(gl);
+ return;
+ }
+
+ /* Fast path - we got what we asked for */
+ if (test_and_clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags))
+ gfs2_demote_wake(gl);
+ if (state != LM_ST_UNLOCKED) {
+ if (glops->go_xmote_bh) {
+ int rv;
+ spin_unlock(&gl->gl_spin);
+ rv = glops->go_xmote_bh(gl, gh);
+ if (rv == -EAGAIN)
+ return;
+ spin_lock(&gl->gl_spin);
+ if (rv) {
+ do_error(gl, rv);
+ goto out;
+ }
+ }
+ do_promote(gl);
+ }
+out:
+ clear_bit(GLF_LOCK, &gl->gl_flags);
spin_unlock(&gl->gl_spin);
gfs2_glock_put(gl);
}
+static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
+ unsigned int cur_state, unsigned int req_state,
+ unsigned int flags)
+{
+ int ret = LM_OUT_ERROR;
+
+ if (!sdp->sd_lockstruct.ls_ops->lm_lock)
+ return req_state == LM_ST_UNLOCKED ? 0 : req_state;
+
+ if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+ ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, cur_state,
+ req_state, flags);
+ return ret;
+}
+
+/**
+ * do_xmote - Calls the DLM to change the state of a lock
+ * @gl: The lock state
+ * @gh: The holder (only for promotes)
+ * @target: The target lock state
+ *
+ */
+
+static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target)
+{
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ unsigned int lck_flags = gh ? gh->gh_flags : 0;
+ int ret;
+
+ lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
+ LM_FLAG_PRIORITY);
+ BUG_ON(gl->gl_state == target);
+ BUG_ON(gl->gl_state == gl->gl_target);
+ if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) &&
+ glops->go_inval) {
+ set_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
+ do_error(gl, 0); /* Fail queued try locks */
+ }
+ spin_unlock(&gl->gl_spin);
+ if (glops->go_xmote_th)
+ glops->go_xmote_th(gl);
+ if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
+ glops->go_inval(gl, target == LM_ST_DEFERRED ? 0 : DIO_METADATA);
+ clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
+
+ gfs2_glock_hold(gl);
+ if (target != LM_ST_UNLOCKED && (gl->gl_state == LM_ST_SHARED ||
+ gl->gl_state == LM_ST_DEFERRED) &&
+ !(lck_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
+ lck_flags |= LM_FLAG_TRY_1CB;
+ ret = gfs2_lm_lock(sdp, gl->gl_lock, gl->gl_state, target, lck_flags);
+
+ if (!(ret & LM_OUT_ASYNC)) {
+ finish_xmote(gl, ret);
+ gfs2_glock_hold(gl);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
+ } else {
+ GLOCK_BUG_ON(gl, ret != LM_OUT_ASYNC);
+ }
+ spin_lock(&gl->gl_spin);
+}
+
+/**
+ * find_first_holder - find the first "holder" gh
+ * @gl: the glock
+ */
+
+static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
+{
+ struct gfs2_holder *gh;
+
+ if (!list_empty(&gl->gl_holders)) {
+ gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+ if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+ return gh;
+ }
+ return NULL;
+}
+
+/**
+ * run_queue - do all outstanding tasks related to a glock
+ * @gl: The glock in question
+ * @nonblock: True if we must not block in run_queue
+ *
+ */
+
+static void run_queue(struct gfs2_glock *gl, const int nonblock)
+{
+ struct gfs2_holder *gh = NULL;
+
+ if (test_and_set_bit(GLF_LOCK, &gl->gl_flags))
+ return;
+
+ GLOCK_BUG_ON(gl, test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags));
+
+ if (test_bit(GLF_DEMOTE, &gl->gl_flags) &&
+ gl->gl_demote_state != gl->gl_state) {
+ if (find_first_holder(gl))
+ goto out;
+ if (nonblock)
+ goto out_sched;
+ set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
+ GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE);
+ gl->gl_target = gl->gl_demote_state;
+ } else {
+ if (test_bit(GLF_DEMOTE, &gl->gl_flags))
+ gfs2_demote_wake(gl);
+ if (do_promote(gl) == 0)
+ goto out;
+ gh = find_first_waiter(gl);
+ gl->gl_target = gh->gh_state;
+ if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
+ do_error(gl, 0); /* Fail queued try locks */
+ }
+ do_xmote(gl, gh, gl->gl_target);
+ return;
+
+out_sched:
+ gfs2_glock_hold(gl);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
+out:
+ clear_bit(GLF_LOCK, &gl->gl_flags);
+}
+
+static void glock_work_func(struct work_struct *work)
+{
+ unsigned long delay = 0;
+ struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
+
+ if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+ finish_xmote(gl, gl->gl_reply);
+ spin_lock(&gl->gl_spin);
+ if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+ gl->gl_state != LM_ST_UNLOCKED &&
+ gl->gl_demote_state != LM_ST_EXCLUSIVE) {
+ unsigned long holdtime, now = jiffies;
+ holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
+ if (time_before(now, holdtime))
+ delay = holdtime - now;
+ set_bit(delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE, &gl->gl_flags);
+ }
+ run_queue(gl, 0);
+ spin_unlock(&gl->gl_spin);
+ if (!delay ||
+ queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+ gfs2_glock_put(gl);
+}
+
static int gfs2_lm_get_lock(struct gfs2_sbd *sdp, struct lm_lockname *name,
void **lockp)
{
int error = -EIO;
+ if (!sdp->sd_lockstruct.ls_ops->lm_get_lock)
+ return 0;
if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
error = sdp->sd_lockstruct.ls_ops->lm_get_lock(
sdp->sd_lockstruct.ls_lockspace, name, lockp);
@@ -342,12 +689,10 @@
gl->gl_name = name;
atomic_set(&gl->gl_ref, 1);
gl->gl_state = LM_ST_UNLOCKED;
+ gl->gl_target = LM_ST_UNLOCKED;
gl->gl_demote_state = LM_ST_EXCLUSIVE;
gl->gl_hash = hash;
- gl->gl_owner_pid = NULL;
- gl->gl_ip = 0;
gl->gl_ops = glops;
- gl->gl_req_gh = NULL;
gl->gl_stamp = jiffies;
gl->gl_tchange = jiffies;
gl->gl_object = NULL;
@@ -447,13 +792,6 @@
gh->gh_ip = 0;
}
-static void gfs2_holder_wake(struct gfs2_holder *gh)
-{
- clear_bit(HIF_WAIT, &gh->gh_iflags);
- smp_mb__after_clear_bit();
- wake_up_bit(&gh->gh_iflags, HIF_WAIT);
-}
-
static int just_schedule(void *word)
{
schedule();
@@ -466,14 +804,6 @@
wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE);
}
-static void gfs2_demote_wake(struct gfs2_glock *gl)
-{
- gl->gl_demote_state = LM_ST_EXCLUSIVE;
- clear_bit(GLF_DEMOTE, &gl->gl_flags);
- smp_mb__after_clear_bit();
- wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
-}
-
static void wait_on_demote(struct gfs2_glock *gl)
{
might_sleep();
@@ -481,217 +811,6 @@
}
/**
- * rq_mutex - process a mutex request in the queue
- * @gh: the glock holder
- *
- * Returns: 1 if the queue is blocked
- */
-
-static int rq_mutex(struct gfs2_holder *gh)
-{
- struct gfs2_glock *gl = gh->gh_gl;
-
- list_del_init(&gh->gh_list);
- /* gh->gh_error never examined. */
- set_bit(GLF_LOCK, &gl->gl_flags);
- clear_bit(HIF_WAIT, &gh->gh_iflags);
- smp_mb();
- wake_up_bit(&gh->gh_iflags, HIF_WAIT);
-
- return 1;
-}
-
-/**
- * rq_promote - process a promote request in the queue
- * @gh: the glock holder
- *
- * Acquire a new inter-node lock, or change a lock state to more restrictive.
- *
- * Returns: 1 if the queue is blocked
- */
-
-static int rq_promote(struct gfs2_holder *gh)
-{
- struct gfs2_glock *gl = gh->gh_gl;
-
- if (!relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
- if (list_empty(&gl->gl_holders)) {
- gl->gl_req_gh = gh;
- set_bit(GLF_LOCK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- gfs2_glock_xmote_th(gh->gh_gl, gh);
- spin_lock(&gl->gl_spin);
- }
- return 1;
- }
-
- if (list_empty(&gl->gl_holders)) {
- set_bit(HIF_FIRST, &gh->gh_iflags);
- set_bit(GLF_LOCK, &gl->gl_flags);
- } else {
- struct gfs2_holder *next_gh;
- if (gh->gh_state == LM_ST_EXCLUSIVE)
- return 1;
- next_gh = list_entry(gl->gl_holders.next, struct gfs2_holder,
- gh_list);
- if (next_gh->gh_state == LM_ST_EXCLUSIVE)
- return 1;
- }
-
- list_move_tail(&gh->gh_list, &gl->gl_holders);
- gh->gh_error = 0;
- set_bit(HIF_HOLDER, &gh->gh_iflags);
-
- gfs2_holder_wake(gh);
-
- return 0;
-}
-
-/**
- * rq_demote - process a demote request in the queue
- * @gh: the glock holder
- *
- * Returns: 1 if the queue is blocked
- */
-
-static int rq_demote(struct gfs2_glock *gl)
-{
- if (!list_empty(&gl->gl_holders))
- return 1;
-
- if (gl->gl_state == gl->gl_demote_state ||
- gl->gl_state == LM_ST_UNLOCKED) {
- gfs2_demote_wake(gl);
- return 0;
- }
-
- set_bit(GLF_LOCK, &gl->gl_flags);
- set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
-
- if (gl->gl_demote_state == LM_ST_UNLOCKED ||
- gl->gl_state != LM_ST_EXCLUSIVE) {
- spin_unlock(&gl->gl_spin);
- gfs2_glock_drop_th(gl);
- } else {
- spin_unlock(&gl->gl_spin);
- gfs2_glock_xmote_th(gl, NULL);
- }
-
- spin_lock(&gl->gl_spin);
- clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
-
- return 0;
-}
-
-/**
- * run_queue - process holder structures on a glock
- * @gl: the glock
- *
- */
-static void run_queue(struct gfs2_glock *gl)
-{
- struct gfs2_holder *gh;
- int blocked = 1;
-
- for (;;) {
- if (test_bit(GLF_LOCK, &gl->gl_flags))
- break;
-
- if (!list_empty(&gl->gl_waiters1)) {
- gh = list_entry(gl->gl_waiters1.next,
- struct gfs2_holder, gh_list);
- blocked = rq_mutex(gh);
- } else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
- blocked = rq_demote(gl);
- if (test_bit(GLF_WAITERS2, &gl->gl_flags) &&
- !blocked) {
- set_bit(GLF_DEMOTE, &gl->gl_flags);
- gl->gl_demote_state = LM_ST_UNLOCKED;
- }
- clear_bit(GLF_WAITERS2, &gl->gl_flags);
- } else if (!list_empty(&gl->gl_waiters3)) {
- gh = list_entry(gl->gl_waiters3.next,
- struct gfs2_holder, gh_list);
- blocked = rq_promote(gh);
- } else
- break;
-
- if (blocked)
- break;
- }
-}
-
-/**
- * gfs2_glmutex_lock - acquire a local lock on a glock
- * @gl: the glock
- *
- * Gives caller exclusive access to manipulate a glock structure.
- */
-
-static void gfs2_glmutex_lock(struct gfs2_glock *gl)
-{
- spin_lock(&gl->gl_spin);
- if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
- struct gfs2_holder gh;
-
- gfs2_holder_init(gl, 0, 0, &gh);
- set_bit(HIF_WAIT, &gh.gh_iflags);
- list_add_tail(&gh.gh_list, &gl->gl_waiters1);
- spin_unlock(&gl->gl_spin);
- wait_on_holder(&gh);
- gfs2_holder_uninit(&gh);
- } else {
- gl->gl_owner_pid = get_pid(task_pid(current));
- gl->gl_ip = (unsigned long)__builtin_return_address(0);
- spin_unlock(&gl->gl_spin);
- }
-}
-
-/**
- * gfs2_glmutex_trylock - try to acquire a local lock on a glock
- * @gl: the glock
- *
- * Returns: 1 if the glock is acquired
- */
-
-static int gfs2_glmutex_trylock(struct gfs2_glock *gl)
-{
- int acquired = 1;
-
- spin_lock(&gl->gl_spin);
- if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
- acquired = 0;
- } else {
- gl->gl_owner_pid = get_pid(task_pid(current));
- gl->gl_ip = (unsigned long)__builtin_return_address(0);
- }
- spin_unlock(&gl->gl_spin);
-
- return acquired;
-}
-
-/**
- * gfs2_glmutex_unlock - release a local lock on a glock
- * @gl: the glock
- *
- */
-
-static void gfs2_glmutex_unlock(struct gfs2_glock *gl)
-{
- struct pid *pid;
-
- spin_lock(&gl->gl_spin);
- clear_bit(GLF_LOCK, &gl->gl_flags);
- pid = gl->gl_owner_pid;
- gl->gl_owner_pid = NULL;
- gl->gl_ip = 0;
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
-
- put_pid(pid);
-}
-
-/**
* handle_callback - process a demote request
* @gl: the glock
* @state: the state the caller wants us to change to
@@ -705,398 +824,45 @@
{
int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
- spin_lock(&gl->gl_spin);
set_bit(bit, &gl->gl_flags);
if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
gl->gl_demote_state = state;
gl->gl_demote_time = jiffies;
if (remote && gl->gl_ops->go_type == LM_TYPE_IOPEN &&
- gl->gl_object) {
+ gl->gl_object)
gfs2_glock_schedule_for_reclaim(gl);
- spin_unlock(&gl->gl_spin);
- return;
- }
} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
gl->gl_demote_state != state) {
- if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags))
- set_bit(GLF_WAITERS2, &gl->gl_flags);
- else
- gl->gl_demote_state = LM_ST_UNLOCKED;
+ gl->gl_demote_state = LM_ST_UNLOCKED;
}
- spin_unlock(&gl->gl_spin);
}
/**
- * state_change - record that the glock is now in a different state
- * @gl: the glock
- * @new_state the new state
- *
- */
-
-static void state_change(struct gfs2_glock *gl, unsigned int new_state)
-{
- int held1, held2;
-
- held1 = (gl->gl_state != LM_ST_UNLOCKED);
- held2 = (new_state != LM_ST_UNLOCKED);
-
- if (held1 != held2) {
- if (held2)
- gfs2_glock_hold(gl);
- else
- gfs2_glock_put(gl);
- }
-
- gl->gl_state = new_state;
- gl->gl_tchange = jiffies;
-}
-
-/**
- * drop_bh - Called after a lock module unlock completes
- * @gl: the glock
- * @ret: the return status
- *
- * Doesn't wake up the process waiting on the struct gfs2_holder (if any)
- * Doesn't drop the reference on the glock the top half took out
- *
- */
-
-static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
-{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- struct gfs2_holder *gh = gl->gl_req_gh;
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
- gfs2_assert_warn(sdp, !ret);
-
- state_change(gl, LM_ST_UNLOCKED);
-
- if (test_and_clear_bit(GLF_CONV_DEADLK, &gl->gl_flags)) {
- spin_lock(&gl->gl_spin);
- gh->gh_error = 0;
- spin_unlock(&gl->gl_spin);
- gfs2_glock_xmote_th(gl, gl->gl_req_gh);
- gfs2_glock_put(gl);
- return;
- }
-
- spin_lock(&gl->gl_spin);
- gfs2_demote_wake(gl);
- clear_bit(GLF_LOCK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- gfs2_glock_put(gl);
-}
-
-/**
- * xmote_bh - Called after the lock module is done acquiring a lock
- * @gl: The glock in question
- * @ret: the int returned from the lock module
- *
- */
-
-static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
-{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- const struct gfs2_glock_operations *glops = gl->gl_ops;
- struct gfs2_holder *gh = gl->gl_req_gh;
- int op_done = 1;
-
- if (!gh && (ret & LM_OUT_ST_MASK) == LM_ST_UNLOCKED) {
- drop_bh(gl, ret);
- return;
- }
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
- gfs2_assert_warn(sdp, !(ret & LM_OUT_ASYNC));
-
- state_change(gl, ret & LM_OUT_ST_MASK);
-
- /* Deal with each possible exit condition */
-
- if (!gh) {
- gl->gl_stamp = jiffies;
- if (ret & LM_OUT_CANCELED) {
- op_done = 0;
- } else {
- spin_lock(&gl->gl_spin);
- if (gl->gl_state != gl->gl_demote_state) {
- spin_unlock(&gl->gl_spin);
- gfs2_glock_drop_th(gl);
- gfs2_glock_put(gl);
- return;
- }
- gfs2_demote_wake(gl);
- spin_unlock(&gl->gl_spin);
- }
- } else {
- spin_lock(&gl->gl_spin);
- if (ret & LM_OUT_CONV_DEADLK) {
- gh->gh_error = 0;
- set_bit(GLF_CONV_DEADLK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- gfs2_glock_drop_th(gl);
- gfs2_glock_put(gl);
- return;
- }
- list_del_init(&gh->gh_list);
- gh->gh_error = -EIO;
- if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
- goto out;
- gh->gh_error = GLR_CANCELED;
- if (ret & LM_OUT_CANCELED)
- goto out;
- if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
- list_add_tail(&gh->gh_list, &gl->gl_holders);
- gh->gh_error = 0;
- set_bit(HIF_HOLDER, &gh->gh_iflags);
- set_bit(HIF_FIRST, &gh->gh_iflags);
- op_done = 0;
- goto out;
- }
- gh->gh_error = GLR_TRYFAILED;
- if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
- goto out;
- gh->gh_error = -EINVAL;
- if (gfs2_assert_withdraw(sdp, 0) == -1)
- fs_err(sdp, "ret = 0x%.8X\n", ret);
-out:
- spin_unlock(&gl->gl_spin);
- }
-
- if (glops->go_xmote_bh)
- glops->go_xmote_bh(gl);
-
- if (op_done) {
- spin_lock(&gl->gl_spin);
- gl->gl_req_gh = NULL;
- clear_bit(GLF_LOCK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- }
-
- gfs2_glock_put(gl);
-
- if (gh)
- gfs2_holder_wake(gh);
-}
-
-static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
- unsigned int cur_state, unsigned int req_state,
- unsigned int flags)
-{
- int ret = 0;
- if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
- ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, cur_state,
- req_state, flags);
- return ret;
-}
-
-/**
- * gfs2_glock_xmote_th - Call into the lock module to acquire or change a glock
- * @gl: The glock in question
- * @state: the requested state
- * @flags: modifier flags to the lock call
- *
- */
-
-static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
-{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- int flags = gh ? gh->gh_flags : 0;
- unsigned state = gh ? gh->gh_state : gl->gl_demote_state;
- const struct gfs2_glock_operations *glops = gl->gl_ops;
- int lck_flags = flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB |
- LM_FLAG_NOEXP | LM_FLAG_ANY |
- LM_FLAG_PRIORITY);
- unsigned int lck_ret;
-
- if (glops->go_xmote_th)
- glops->go_xmote_th(gl);
- if (state == LM_ST_DEFERRED && glops->go_inval)
- glops->go_inval(gl, DIO_METADATA);
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
- gfs2_assert_warn(sdp, state != LM_ST_UNLOCKED);
- gfs2_assert_warn(sdp, state != gl->gl_state);
-
- gfs2_glock_hold(gl);
-
- lck_ret = gfs2_lm_lock(sdp, gl->gl_lock, gl->gl_state, state, lck_flags);
-
- if (gfs2_assert_withdraw(sdp, !(lck_ret & LM_OUT_ERROR)))
- return;
-
- if (lck_ret & LM_OUT_ASYNC)
- gfs2_assert_warn(sdp, lck_ret == LM_OUT_ASYNC);
- else
- xmote_bh(gl, lck_ret);
-}
-
-static unsigned int gfs2_lm_unlock(struct gfs2_sbd *sdp, void *lock,
- unsigned int cur_state)
-{
- int ret = 0;
- if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
- ret = sdp->sd_lockstruct.ls_ops->lm_unlock(lock, cur_state);
- return ret;
-}
-
-/**
- * gfs2_glock_drop_th - call into the lock module to unlock a lock
- * @gl: the glock
- *
- */
-
-static void gfs2_glock_drop_th(struct gfs2_glock *gl)
-{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- const struct gfs2_glock_operations *glops = gl->gl_ops;
- unsigned int ret;
-
- if (glops->go_xmote_th)
- glops->go_xmote_th(gl);
- if (glops->go_inval)
- glops->go_inval(gl, DIO_METADATA);
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
- gfs2_assert_warn(sdp, gl->gl_state != LM_ST_UNLOCKED);
-
- gfs2_glock_hold(gl);
-
- ret = gfs2_lm_unlock(sdp, gl->gl_lock, gl->gl_state);
-
- if (gfs2_assert_withdraw(sdp, !(ret & LM_OUT_ERROR)))
- return;
-
- if (!ret)
- drop_bh(gl, ret);
- else
- gfs2_assert_warn(sdp, ret == LM_OUT_ASYNC);
-}
-
-/**
- * do_cancels - cancel requests for locks stuck waiting on an expire flag
- * @gh: the LM_FLAG_PRIORITY holder waiting to acquire the lock
- *
- * Don't cancel GL_NOCANCEL requests.
- */
-
-static void do_cancels(struct gfs2_holder *gh)
-{
- struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_sbd *sdp = gl->gl_sbd;
-
- spin_lock(&gl->gl_spin);
-
- while (gl->gl_req_gh != gh &&
- !test_bit(HIF_HOLDER, &gh->gh_iflags) &&
- !list_empty(&gh->gh_list)) {
- if (!(gl->gl_req_gh && (gl->gl_req_gh->gh_flags & GL_NOCANCEL))) {
- spin_unlock(&gl->gl_spin);
- if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
- sdp->sd_lockstruct.ls_ops->lm_cancel(gl->gl_lock);
- msleep(100);
- spin_lock(&gl->gl_spin);
- } else {
- spin_unlock(&gl->gl_spin);
- msleep(100);
- spin_lock(&gl->gl_spin);
- }
- }
-
- spin_unlock(&gl->gl_spin);
-}
-
-/**
- * glock_wait_internal - wait on a glock acquisition
+ * gfs2_glock_wait - wait on a glock acquisition
* @gh: the glock holder
*
* Returns: 0 on success
*/
-static int glock_wait_internal(struct gfs2_holder *gh)
+int gfs2_glock_wait(struct gfs2_holder *gh)
{
- struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_sbd *sdp = gl->gl_sbd;
- const struct gfs2_glock_operations *glops = gl->gl_ops;
-
- if (test_bit(HIF_ABORTED, &gh->gh_iflags))
- return -EIO;
-
- if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
- spin_lock(&gl->gl_spin);
- if (gl->gl_req_gh != gh &&
- !test_bit(HIF_HOLDER, &gh->gh_iflags) &&
- !list_empty(&gh->gh_list)) {
- list_del_init(&gh->gh_list);
- gh->gh_error = GLR_TRYFAILED;
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
- return gh->gh_error;
- }
- spin_unlock(&gl->gl_spin);
- }
-
- if (gh->gh_flags & LM_FLAG_PRIORITY)
- do_cancels(gh);
-
wait_on_holder(gh);
- if (gh->gh_error)
- return gh->gh_error;
-
- gfs2_assert_withdraw(sdp, test_bit(HIF_HOLDER, &gh->gh_iflags));
- gfs2_assert_withdraw(sdp, relaxed_state_ok(gl->gl_state, gh->gh_state,
- gh->gh_flags));
-
- if (test_bit(HIF_FIRST, &gh->gh_iflags)) {
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
-
- if (glops->go_lock) {
- gh->gh_error = glops->go_lock(gh);
- if (gh->gh_error) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
- spin_unlock(&gl->gl_spin);
- }
- }
-
- spin_lock(&gl->gl_spin);
- gl->gl_req_gh = NULL;
- clear_bit(GLF_LOCK, &gl->gl_flags);
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
- }
-
return gh->gh_error;
}
-static inline struct gfs2_holder *
-find_holder_by_owner(struct list_head *head, struct pid *pid)
-{
- struct gfs2_holder *gh;
-
- list_for_each_entry(gh, head, gh_list) {
- if (gh->gh_owner_pid == pid)
- return gh;
- }
-
- return NULL;
-}
-
-static void print_dbg(struct glock_iter *gi, const char *fmt, ...)
+void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
- if (gi) {
+ if (seq) {
+ struct gfs2_glock_iter *gi = seq->private;
vsprintf(gi->string, fmt, args);
- seq_printf(gi->seq, gi->string);
- }
- else
+ seq_printf(seq, gi->string);
+ } else {
+ printk(KERN_ERR " ");
vprintk(fmt, args);
+ }
va_end(args);
}
@@ -1104,50 +870,76 @@
* add_to_queue - Add a holder to the wait queue (but look for recursion)
* @gh: the holder structure to add
*
+ * Eventually we should move the recursive locking trap to a
+ * debugging option or something like that. This is the fast
+ * path and needs to have the minimum number of distractions.
+ *
*/
-static void add_to_queue(struct gfs2_holder *gh)
+static inline void add_to_queue(struct gfs2_holder *gh)
{
struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_holder *existing;
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ struct list_head *insert_pt = NULL;
+ struct gfs2_holder *gh2;
+ int try_lock = 0;
BUG_ON(gh->gh_owner_pid == NULL);
if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
BUG();
- if (!(gh->gh_flags & GL_FLOCK)) {
- existing = find_holder_by_owner(&gl->gl_holders,
- gh->gh_owner_pid);
- if (existing) {
- print_symbol(KERN_WARNING "original: %s\n",
- existing->gh_ip);
- printk(KERN_INFO "pid : %d\n",
- pid_nr(existing->gh_owner_pid));
- printk(KERN_INFO "lock type : %d lock state : %d\n",
- existing->gh_gl->gl_name.ln_type,
- existing->gh_gl->gl_state);
- print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
- printk(KERN_INFO "pid : %d\n",
- pid_nr(gh->gh_owner_pid));
- printk(KERN_INFO "lock type : %d lock state : %d\n",
- gl->gl_name.ln_type, gl->gl_state);
- BUG();
- }
-
- existing = find_holder_by_owner(&gl->gl_waiters3,
- gh->gh_owner_pid);
- if (existing) {
- print_symbol(KERN_WARNING "original: %s\n",
- existing->gh_ip);
- print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
- BUG();
- }
+ if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
+ if (test_bit(GLF_LOCK, &gl->gl_flags))
+ try_lock = 1;
+ if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
+ goto fail;
}
- if (gh->gh_flags & LM_FLAG_PRIORITY)
- list_add(&gh->gh_list, &gl->gl_waiters3);
- else
- list_add_tail(&gh->gh_list, &gl->gl_waiters3);
+ list_for_each_entry(gh2, &gl->gl_holders, gh_list) {
+ if (unlikely(gh2->gh_owner_pid == gh->gh_owner_pid &&
+ (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK)))
+ goto trap_recursive;
+ if (try_lock &&
+ !(gh2->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) &&
+ !may_grant(gl, gh)) {
+fail:
+ gh->gh_error = GLR_TRYFAILED;
+ gfs2_holder_wake(gh);
+ return;
+ }
+ if (test_bit(HIF_HOLDER, &gh2->gh_iflags))
+ continue;
+ if (unlikely((gh->gh_flags & LM_FLAG_PRIORITY) && !insert_pt))
+ insert_pt = &gh2->gh_list;
+ }
+ if (likely(insert_pt == NULL)) {
+ list_add_tail(&gh->gh_list, &gl->gl_holders);
+ if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
+ goto do_cancel;
+ return;
+ }
+ list_add_tail(&gh->gh_list, insert_pt);
+do_cancel:
+ gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+ if (!(gh->gh_flags & LM_FLAG_PRIORITY)) {
+ spin_unlock(&gl->gl_spin);
+ if (sdp->sd_lockstruct.ls_ops->lm_cancel)
+ sdp->sd_lockstruct.ls_ops->lm_cancel(gl->gl_lock);
+ spin_lock(&gl->gl_spin);
+ }
+ return;
+
+trap_recursive:
+ print_symbol(KERN_ERR "original: %s\n", gh2->gh_ip);
+ printk(KERN_ERR "pid: %d\n", pid_nr(gh2->gh_owner_pid));
+ printk(KERN_ERR "lock type: %d req lock state : %d\n",
+ gh2->gh_gl->gl_name.ln_type, gh2->gh_state);
+ print_symbol(KERN_ERR "new: %s\n", gh->gh_ip);
+ printk(KERN_ERR "pid: %d\n", pid_nr(gh->gh_owner_pid));
+ printk(KERN_ERR "lock type: %d req lock state : %d\n",
+ gh->gh_gl->gl_name.ln_type, gh->gh_state);
+ __dump_glock(NULL, gl);
+ BUG();
}
/**
@@ -1165,24 +957,16 @@
struct gfs2_sbd *sdp = gl->gl_sbd;
int error = 0;
-restart:
- if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
- set_bit(HIF_ABORTED, &gh->gh_iflags);
+ if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
return -EIO;
- }
spin_lock(&gl->gl_spin);
add_to_queue(gh);
- run_queue(gl);
+ run_queue(gl, 1);
spin_unlock(&gl->gl_spin);
- if (!(gh->gh_flags & GL_ASYNC)) {
- error = glock_wait_internal(gh);
- if (error == GLR_CANCELED) {
- msleep(100);
- goto restart;
- }
- }
+ if (!(gh->gh_flags & GL_ASYNC))
+ error = gfs2_glock_wait(gh);
return error;
}
@@ -1196,48 +980,7 @@
int gfs2_glock_poll(struct gfs2_holder *gh)
{
- struct gfs2_glock *gl = gh->gh_gl;
- int ready = 0;
-
- spin_lock(&gl->gl_spin);
-
- if (test_bit(HIF_HOLDER, &gh->gh_iflags))
- ready = 1;
- else if (list_empty(&gh->gh_list)) {
- if (gh->gh_error == GLR_CANCELED) {
- spin_unlock(&gl->gl_spin);
- msleep(100);
- if (gfs2_glock_nq(gh))
- return 1;
- return 0;
- } else
- ready = 1;
- }
-
- spin_unlock(&gl->gl_spin);
-
- return ready;
-}
-
-/**
- * gfs2_glock_wait - wait for a lock acquisition that ended in a GLR_ASYNC
- * @gh: the holder structure
- *
- * Returns: 0, GLR_TRYFAILED, or errno on failure
- */
-
-int gfs2_glock_wait(struct gfs2_holder *gh)
-{
- int error;
-
- error = glock_wait_internal(gh);
- if (error == GLR_CANCELED) {
- msleep(100);
- gh->gh_flags &= ~GL_ASYNC;
- error = gfs2_glock_nq(gh);
- }
-
- return error;
+ return test_bit(HIF_WAIT, &gh->gh_iflags) ? 0 : 1;
}
/**
@@ -1251,26 +994,30 @@
struct gfs2_glock *gl = gh->gh_gl;
const struct gfs2_glock_operations *glops = gl->gl_ops;
unsigned delay = 0;
+ int fast_path = 0;
+ spin_lock(&gl->gl_spin);
if (gh->gh_flags & GL_NOCACHE)
handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
- gfs2_glmutex_lock(gl);
-
- spin_lock(&gl->gl_spin);
list_del_init(&gh->gh_list);
-
- if (list_empty(&gl->gl_holders)) {
+ if (find_first_holder(gl) == NULL) {
if (glops->go_unlock) {
+ GLOCK_BUG_ON(gl, test_and_set_bit(GLF_LOCK, &gl->gl_flags));
spin_unlock(&gl->gl_spin);
glops->go_unlock(gh);
spin_lock(&gl->gl_spin);
+ clear_bit(GLF_LOCK, &gl->gl_flags);
}
gl->gl_stamp = jiffies;
+ if (list_empty(&gl->gl_holders) &&
+ !test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+ !test_bit(GLF_DEMOTE, &gl->gl_flags))
+ fast_path = 1;
}
-
- clear_bit(GLF_LOCK, &gl->gl_flags);
spin_unlock(&gl->gl_spin);
+ if (likely(fast_path))
+ return;
gfs2_glock_hold(gl);
if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
@@ -1454,6 +1201,8 @@
static int gfs2_lm_hold_lvb(struct gfs2_sbd *sdp, void *lock, char **lvbp)
{
int error = -EIO;
+ if (!sdp->sd_lockstruct.ls_ops->lm_hold_lvb)
+ return 0;
if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
error = sdp->sd_lockstruct.ls_ops->lm_hold_lvb(lock, lvbp);
return error;
@@ -1469,20 +1218,14 @@
{
int error;
- gfs2_glmutex_lock(gl);
-
if (!atomic_read(&gl->gl_lvb_count)) {
error = gfs2_lm_hold_lvb(gl->gl_sbd, gl->gl_lock, &gl->gl_lvb);
- if (error) {
- gfs2_glmutex_unlock(gl);
+ if (error)
return error;
- }
gfs2_glock_hold(gl);
}
atomic_inc(&gl->gl_lvb_count);
- gfs2_glmutex_unlock(gl);
-
return 0;
}
@@ -1497,17 +1240,13 @@
struct gfs2_sbd *sdp = gl->gl_sbd;
gfs2_glock_hold(gl);
- gfs2_glmutex_lock(gl);
-
gfs2_assert(gl->gl_sbd, atomic_read(&gl->gl_lvb_count) > 0);
if (atomic_dec_and_test(&gl->gl_lvb_count)) {
- if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+ if (sdp->sd_lockstruct.ls_ops->lm_unhold_lvb)
sdp->sd_lockstruct.ls_ops->lm_unhold_lvb(gl->gl_lock, gl->gl_lvb);
gl->gl_lvb = NULL;
gfs2_glock_put(gl);
}
-
- gfs2_glmutex_unlock(gl);
gfs2_glock_put(gl);
}
@@ -1527,7 +1266,9 @@
if (time_before(now, holdtime))
delay = holdtime - now;
+ spin_lock(&gl->gl_spin);
handle_callback(gl, state, 1, delay);
+ spin_unlock(&gl->gl_spin);
if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
gfs2_glock_put(gl);
}
@@ -1568,7 +1309,8 @@
gl = gfs2_glock_find(sdp, &async->lc_name);
if (gfs2_assert_warn(sdp, gl))
return;
- xmote_bh(gl, async->lc_ret);
+ gl->gl_reply = async->lc_ret;
+ set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
gfs2_glock_put(gl);
up_read(&gfs2_umount_flush_sem);
@@ -1581,11 +1323,6 @@
wake_up_process(sdp->sd_recoverd_process);
return;
- case LM_CB_DROPLOCKS:
- gfs2_gl_hash_clear(sdp, NO_WAIT);
- gfs2_quota_scan(sdp);
- return;
-
default:
gfs2_assert_warn(sdp, 0);
return;
@@ -1646,6 +1383,7 @@
void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
{
struct gfs2_glock *gl;
+ int done_callback = 0;
spin_lock(&sdp->sd_reclaim_lock);
if (list_empty(&sdp->sd_reclaim_list)) {
@@ -1660,14 +1398,16 @@
atomic_dec(&sdp->sd_reclaim_count);
atomic_inc(&sdp->sd_reclaimed);
- if (gfs2_glmutex_trylock(gl)) {
- if (list_empty(&gl->gl_holders) &&
- gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
- handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
- gfs2_glmutex_unlock(gl);
+ spin_lock(&gl->gl_spin);
+ if (find_first_holder(gl) == NULL &&
+ gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl)) {
+ handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
+ done_callback = 1;
}
-
- gfs2_glock_put(gl);
+ spin_unlock(&gl->gl_spin);
+ if (!done_callback ||
+ queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
}
/**
@@ -1724,18 +1464,14 @@
{
if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object)
return;
+ if (test_bit(GLF_LOCK, &gl->gl_flags))
+ return;
- if (gfs2_glmutex_trylock(gl)) {
- if (list_empty(&gl->gl_holders) &&
- gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
- goto out_schedule;
- gfs2_glmutex_unlock(gl);
- }
- return;
-
-out_schedule:
- gfs2_glmutex_unlock(gl);
- gfs2_glock_schedule_for_reclaim(gl);
+ spin_lock(&gl->gl_spin);
+ if (find_first_holder(gl) == NULL &&
+ gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
+ gfs2_glock_schedule_for_reclaim(gl);
+ spin_unlock(&gl->gl_spin);
}
/**
@@ -1760,12 +1496,13 @@
spin_unlock(&sdp->sd_reclaim_lock);
}
- if (gfs2_glmutex_trylock(gl)) {
- if (list_empty(&gl->gl_holders) &&
- gl->gl_state != LM_ST_UNLOCKED)
- handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
- gfs2_glmutex_unlock(gl);
- }
+ spin_lock(&gl->gl_spin);
+ if (find_first_holder(gl) == NULL && gl->gl_state != LM_ST_UNLOCKED)
+ handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
+ spin_unlock(&gl->gl_spin);
+ gfs2_glock_hold(gl);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
}
/**
@@ -1773,11 +1510,10 @@
* @sdp: the filesystem
* @wait: wait until it's all gone
*
- * Called when unmounting the filesystem, or when inter-node lock manager
- * requests DROPLOCKS because it is running out of capacity.
+ * Called when unmounting the filesystem.
*/
-void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait)
+void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
{
unsigned long t;
unsigned int x;
@@ -1792,7 +1528,7 @@
cont = 1;
}
- if (!wait || !cont)
+ if (!cont)
break;
if (time_after_eq(jiffies,
@@ -1810,180 +1546,164 @@
}
}
-/*
- * Diagnostic routines to help debug distributed deadlock
- */
-
-static void gfs2_print_symbol(struct glock_iter *gi, const char *fmt,
- unsigned long address)
+static const char *state2str(unsigned state)
{
- char buffer[KSYM_SYMBOL_LEN];
+ switch(state) {
+ case LM_ST_UNLOCKED:
+ return "UN";
+ case LM_ST_SHARED:
+ return "SH";
+ case LM_ST_DEFERRED:
+ return "DF";
+ case LM_ST_EXCLUSIVE:
+ return "EX";
+ }
+ return "??";
+}
- sprint_symbol(buffer, address);
- print_dbg(gi, fmt, buffer);
+static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
+{
+ char *p = buf;
+ if (flags & LM_FLAG_TRY)
+ *p++ = 't';
+ if (flags & LM_FLAG_TRY_1CB)
+ *p++ = 'T';
+ if (flags & LM_FLAG_NOEXP)
+ *p++ = 'e';
+ if (flags & LM_FLAG_ANY)
+ *p++ = 'a';
+ if (flags & LM_FLAG_PRIORITY)
+ *p++ = 'p';
+ if (flags & GL_ASYNC)
+ *p++ = 'a';
+ if (flags & GL_EXACT)
+ *p++ = 'E';
+ if (flags & GL_ATIME)
+ *p++ = 'a';
+ if (flags & GL_NOCACHE)
+ *p++ = 'c';
+ if (test_bit(HIF_HOLDER, &iflags))
+ *p++ = 'H';
+ if (test_bit(HIF_WAIT, &iflags))
+ *p++ = 'W';
+ if (test_bit(HIF_FIRST, &iflags))
+ *p++ = 'F';
+ *p = 0;
+ return buf;
}
/**
* dump_holder - print information about a glock holder
- * @str: a string naming the type of holder
+ * @seq: the seq_file struct
* @gh: the glock holder
*
* Returns: 0 on success, -ENOBUFS when we run out of space
*/
-static int dump_holder(struct glock_iter *gi, char *str,
- struct gfs2_holder *gh)
+static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
{
- unsigned int x;
- struct task_struct *gh_owner;
+ struct task_struct *gh_owner = NULL;
+ char buffer[KSYM_SYMBOL_LEN];
+ char flags_buf[32];
- print_dbg(gi, " %s\n", str);
- if (gh->gh_owner_pid) {
- print_dbg(gi, " owner = %ld ",
- (long)pid_nr(gh->gh_owner_pid));
+ sprint_symbol(buffer, gh->gh_ip);
+ if (gh->gh_owner_pid)
gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
- if (gh_owner)
- print_dbg(gi, "(%s)\n", gh_owner->comm);
- else
- print_dbg(gi, "(ended)\n");
- } else
- print_dbg(gi, " owner = -1\n");
- print_dbg(gi, " gh_state = %u\n", gh->gh_state);
- print_dbg(gi, " gh_flags =");
- for (x = 0; x < 32; x++)
- if (gh->gh_flags & (1 << x))
- print_dbg(gi, " %u", x);
- print_dbg(gi, " \n");
- print_dbg(gi, " error = %d\n", gh->gh_error);
- print_dbg(gi, " gh_iflags =");
- for (x = 0; x < 32; x++)
- if (test_bit(x, &gh->gh_iflags))
- print_dbg(gi, " %u", x);
- print_dbg(gi, " \n");
- gfs2_print_symbol(gi, " initialized at: %s\n", gh->gh_ip);
-
+ gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %s\n",
+ state2str(gh->gh_state),
+ hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags),
+ gh->gh_error,
+ gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
+ gh_owner ? gh_owner->comm : "(ended)", buffer);
return 0;
}
-/**
- * dump_inode - print information about an inode
- * @ip: the inode
- *
- * Returns: 0 on success, -ENOBUFS when we run out of space
- */
-
-static int dump_inode(struct glock_iter *gi, struct gfs2_inode *ip)
+static const char *gflags2str(char *buf, const unsigned long *gflags)
{
- unsigned int x;
-
- print_dbg(gi, " Inode:\n");
- print_dbg(gi, " num = %llu/%llu\n",
- (unsigned long long)ip->i_no_formal_ino,
- (unsigned long long)ip->i_no_addr);
- print_dbg(gi, " type = %u\n", IF2DT(ip->i_inode.i_mode));
- print_dbg(gi, " i_flags =");
- for (x = 0; x < 32; x++)
- if (test_bit(x, &ip->i_flags))
- print_dbg(gi, " %u", x);
- print_dbg(gi, " \n");
- return 0;
+ char *p = buf;
+ if (test_bit(GLF_LOCK, gflags))
+ *p++ = 'l';
+ if (test_bit(GLF_STICKY, gflags))
+ *p++ = 's';
+ if (test_bit(GLF_DEMOTE, gflags))
+ *p++ = 'D';
+ if (test_bit(GLF_PENDING_DEMOTE, gflags))
+ *p++ = 'd';
+ if (test_bit(GLF_DEMOTE_IN_PROGRESS, gflags))
+ *p++ = 'p';
+ if (test_bit(GLF_DIRTY, gflags))
+ *p++ = 'y';
+ if (test_bit(GLF_LFLUSH, gflags))
+ *p++ = 'f';
+ if (test_bit(GLF_INVALIDATE_IN_PROGRESS, gflags))
+ *p++ = 'i';
+ if (test_bit(GLF_REPLY_PENDING, gflags))
+ *p++ = 'r';
+ *p = 0;
+ return buf;
}
/**
- * dump_glock - print information about a glock
+ * __dump_glock - print information about a glock
+ * @seq: The seq_file struct
* @gl: the glock
- * @count: where we are in the buffer
+ *
+ * The file format is as follows:
+ * One line per object, capital letters are used to indicate objects
+ * G = glock, I = Inode, R = rgrp, H = holder. Glocks are not indented,
+ * other objects are indented by a single space and follow the glock to
+ * which they are related. Fields are indicated by lower case letters
+ * followed by a colon and the field value, except for strings which are in
+ * [] so that its possible to see if they are composed of spaces for
+ * example. The field's are n = number (id of the object), f = flags,
+ * t = type, s = state, r = refcount, e = error, p = pid.
*
* Returns: 0 on success, -ENOBUFS when we run out of space
*/
-static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl)
+static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl)
{
- struct gfs2_holder *gh;
- unsigned int x;
- int error = -ENOBUFS;
- struct task_struct *gl_owner;
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ unsigned long long dtime;
+ const struct gfs2_holder *gh;
+ char gflags_buf[32];
+ int error = 0;
- spin_lock(&gl->gl_spin);
+ dtime = jiffies - gl->gl_demote_time;
+ dtime *= 1000000/HZ; /* demote time in uSec */
+ if (!test_bit(GLF_DEMOTE, &gl->gl_flags))
+ dtime = 0;
+ gfs2_print_dbg(seq, "G: s:%s n:%u/%llu f:%s t:%s d:%s/%llu l:%d a:%d r:%d\n",
+ state2str(gl->gl_state),
+ gl->gl_name.ln_type,
+ (unsigned long long)gl->gl_name.ln_number,
+ gflags2str(gflags_buf, &gl->gl_flags),
+ state2str(gl->gl_target),
+ state2str(gl->gl_demote_state), dtime,
+ atomic_read(&gl->gl_lvb_count),
+ atomic_read(&gl->gl_ail_count),
+ atomic_read(&gl->gl_ref));
- print_dbg(gi, "Glock 0x%p (%u, 0x%llx)\n", gl, gl->gl_name.ln_type,
- (unsigned long long)gl->gl_name.ln_number);
- print_dbg(gi, " gl_flags =");
- for (x = 0; x < 32; x++) {
- if (test_bit(x, &gl->gl_flags))
- print_dbg(gi, " %u", x);
- }
- if (!test_bit(GLF_LOCK, &gl->gl_flags))
- print_dbg(gi, " (unlocked)");
- print_dbg(gi, " \n");
- print_dbg(gi, " gl_ref = %d\n", atomic_read(&gl->gl_ref));
- print_dbg(gi, " gl_state = %u\n", gl->gl_state);
- if (gl->gl_owner_pid) {
- gl_owner = pid_task(gl->gl_owner_pid, PIDTYPE_PID);
- if (gl_owner)
- print_dbg(gi, " gl_owner = pid %d (%s)\n",
- pid_nr(gl->gl_owner_pid), gl_owner->comm);
- else
- print_dbg(gi, " gl_owner = %d (ended)\n",
- pid_nr(gl->gl_owner_pid));
- } else
- print_dbg(gi, " gl_owner = -1\n");
- print_dbg(gi, " gl_ip = %lu\n", gl->gl_ip);
- print_dbg(gi, " req_gh = %s\n", (gl->gl_req_gh) ? "yes" : "no");
- print_dbg(gi, " lvb_count = %d\n", atomic_read(&gl->gl_lvb_count));
- print_dbg(gi, " object = %s\n", (gl->gl_object) ? "yes" : "no");
- print_dbg(gi, " reclaim = %s\n",
- (list_empty(&gl->gl_reclaim)) ? "no" : "yes");
- if (gl->gl_aspace)
- print_dbg(gi, " aspace = 0x%p nrpages = %lu\n", gl->gl_aspace,
- gl->gl_aspace->i_mapping->nrpages);
- else
- print_dbg(gi, " aspace = no\n");
- print_dbg(gi, " ail = %d\n", atomic_read(&gl->gl_ail_count));
- if (gl->gl_req_gh) {
- error = dump_holder(gi, "Request", gl->gl_req_gh);
- if (error)
- goto out;
- }
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
- error = dump_holder(gi, "Holder", gh);
+ error = dump_holder(seq, gh);
if (error)
goto out;
}
- list_for_each_entry(gh, &gl->gl_waiters1, gh_list) {
- error = dump_holder(gi, "Waiter1", gh);
- if (error)
- goto out;
- }
- list_for_each_entry(gh, &gl->gl_waiters3, gh_list) {
- error = dump_holder(gi, "Waiter3", gh);
- if (error)
- goto out;
- }
- if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
- print_dbg(gi, " Demotion req to state %u (%llu uS ago)\n",
- gl->gl_demote_state, (unsigned long long)
- (jiffies - gl->gl_demote_time)*(1000000/HZ));
- }
- if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object) {
- if (!test_bit(GLF_LOCK, &gl->gl_flags) &&
- list_empty(&gl->gl_holders)) {
- error = dump_inode(gi, gl->gl_object);
- if (error)
- goto out;
- } else {
- error = -ENOBUFS;
- print_dbg(gi, " Inode: busy\n");
- }
- }
-
- error = 0;
-
+ if (gl->gl_state != LM_ST_UNLOCKED && glops->go_dump)
+ error = glops->go_dump(seq, gl);
out:
- spin_unlock(&gl->gl_spin);
return error;
}
+static int dump_glock(struct seq_file *seq, struct gfs2_glock *gl)
+{
+ int ret;
+ spin_lock(&gl->gl_spin);
+ ret = __dump_glock(seq, gl);
+ spin_unlock(&gl->gl_spin);
+ return ret;
+}
+
/**
* gfs2_dump_lockstate - print out the current lockstate
* @sdp: the filesystem
@@ -2086,7 +1806,7 @@
module_param(scand_secs, uint, S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(scand_secs, "The number of seconds between scand runs");
-static int gfs2_glock_iter_next(struct glock_iter *gi)
+static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
{
struct gfs2_glock *gl;
@@ -2104,7 +1824,7 @@
gfs2_glock_put(gl);
if (gl && gi->gl == NULL)
gi->hash++;
- while(gi->gl == NULL) {
+ while (gi->gl == NULL) {
if (gi->hash >= GFS2_GL_HASH_SIZE)
return 1;
read_lock(gl_lock_addr(gi->hash));
@@ -2122,58 +1842,34 @@
return 0;
}
-static void gfs2_glock_iter_free(struct glock_iter *gi)
+static void gfs2_glock_iter_free(struct gfs2_glock_iter *gi)
{
if (gi->gl)
gfs2_glock_put(gi->gl);
- kfree(gi);
-}
-
-static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
-{
- struct glock_iter *gi;
-
- gi = kmalloc(sizeof (*gi), GFP_KERNEL);
- if (!gi)
- return NULL;
-
- gi->sdp = sdp;
- gi->hash = 0;
- gi->seq = NULL;
gi->gl = NULL;
- memset(gi->string, 0, sizeof(gi->string));
-
- if (gfs2_glock_iter_next(gi)) {
- gfs2_glock_iter_free(gi);
- return NULL;
- }
-
- return gi;
}
-static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos)
+static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct glock_iter *gi;
+ struct gfs2_glock_iter *gi = seq->private;
loff_t n = *pos;
- gi = gfs2_glock_iter_init(file->private);
- if (!gi)
- return NULL;
+ gi->hash = 0;
- while(n--) {
+ do {
if (gfs2_glock_iter_next(gi)) {
gfs2_glock_iter_free(gi);
return NULL;
}
- }
+ } while (n--);
- return gi;
+ return gi->gl;
}
-static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
+static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr,
loff_t *pos)
{
- struct glock_iter *gi = iter_ptr;
+ struct gfs2_glock_iter *gi = seq->private;
(*pos)++;
@@ -2182,24 +1878,18 @@
return NULL;
}
- return gi;
+ return gi->gl;
}
-static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr)
+static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)
{
- struct glock_iter *gi = iter_ptr;
- if (gi)
- gfs2_glock_iter_free(gi);
+ struct gfs2_glock_iter *gi = seq->private;
+ gfs2_glock_iter_free(gi);
}
-static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)
+static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
{
- struct glock_iter *gi = iter_ptr;
-
- gi->seq = file;
- dump_glock(gi, gi->gl);
-
- return 0;
+ return dump_glock(seq, iter_ptr);
}
static const struct seq_operations gfs2_glock_seq_ops = {
@@ -2211,17 +1901,14 @@
static int gfs2_debugfs_open(struct inode *inode, struct file *file)
{
- struct seq_file *seq;
- int ret;
-
- ret = seq_open(file, &gfs2_glock_seq_ops);
- if (ret)
- return ret;
-
- seq = file->private_data;
- seq->private = inode->i_private;
-
- return 0;
+ int ret = seq_open_private(file, &gfs2_glock_seq_ops,
+ sizeof(struct gfs2_glock_iter));
+ if (ret == 0) {
+ struct seq_file *seq = file->private_data;
+ struct gfs2_glock_iter *gi = seq->private;
+ gi->sdp = inode->i_private;
+ }
+ return ret;
}
static const struct file_operations gfs2_debug_fops = {
@@ -2229,7 +1916,7 @@
.open = gfs2_debugfs_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release
+ .release = seq_release_private,
};
int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index cdad3e6..971d92a 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -26,11 +26,8 @@
#define GL_SKIP 0x00000100
#define GL_ATIME 0x00000200
#define GL_NOCACHE 0x00000400
-#define GL_FLOCK 0x00000800
-#define GL_NOCANCEL 0x00001000
#define GLR_TRYFAILED 13
-#define GLR_CANCELED 14
static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
{
@@ -41,6 +38,8 @@
spin_lock(&gl->gl_spin);
pid = task_pid(current);
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+ if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+ break;
if (gh->gh_owner_pid == pid)
goto out;
}
@@ -70,7 +69,7 @@
{
int ret;
spin_lock(&gl->gl_spin);
- ret = test_bit(GLF_DEMOTE, &gl->gl_flags) || !list_empty(&gl->gl_waiters3);
+ ret = test_bit(GLF_DEMOTE, &gl->gl_flags);
spin_unlock(&gl->gl_spin);
return ret;
}
@@ -98,6 +97,7 @@
int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
+void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
/**
* gfs2_glock_nq_init - intialize a holder and enqueue it on a glock
@@ -130,10 +130,9 @@
void gfs2_lvb_unhold(struct gfs2_glock *gl);
void gfs2_glock_cb(void *cb_data, unsigned int type, void *data);
-
void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl);
void gfs2_reclaim_glock(struct gfs2_sbd *sdp);
-void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait);
+void gfs2_gl_hash_clear(struct gfs2_sbd *sdp);
int __init gfs2_glock_init(void);
void gfs2_glock_exit(void);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 07d84d16..c6c318c 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -13,6 +13,7 @@
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>
+#include <linux/bio.h>
#include "gfs2.h"
#include "incore.h"
@@ -172,26 +173,6 @@
}
/**
- * inode_go_xmote_bh - After promoting/demoting a glock
- * @gl: the glock
- *
- */
-
-static void inode_go_xmote_bh(struct gfs2_glock *gl)
-{
- struct gfs2_holder *gh = gl->gl_req_gh;
- struct buffer_head *bh;
- int error;
-
- if (gl->gl_state != LM_ST_UNLOCKED &&
- (!gh || !(gh->gh_flags & GL_SKIP))) {
- error = gfs2_meta_read(gl, gl->gl_name.ln_number, 0, &bh);
- if (!error)
- brelse(bh);
- }
-}
-
-/**
* inode_go_inval - prepare a inode glock to be released
* @gl: the glock
* @flags:
@@ -267,6 +248,26 @@
}
/**
+ * inode_go_dump - print information about an inode
+ * @seq: The iterator
+ * @ip: the inode
+ *
+ * Returns: 0 on success, -ENOBUFS when we run out of space
+ */
+
+static int inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+ const struct gfs2_inode *ip = gl->gl_object;
+ if (ip == NULL)
+ return 0;
+ gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%08lx\n",
+ (unsigned long long)ip->i_no_formal_ino,
+ (unsigned long long)ip->i_no_addr,
+ IF2DT(ip->i_inode.i_mode), ip->i_flags);
+ return 0;
+}
+
+/**
* rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
* @gl: the glock
*
@@ -306,6 +307,22 @@
}
/**
+ * rgrp_go_dump - print out an rgrp
+ * @seq: The iterator
+ * @gl: The glock in question
+ *
+ */
+
+static int rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+ const struct gfs2_rgrpd *rgd = gl->gl_object;
+ if (rgd == NULL)
+ return 0;
+ gfs2_print_dbg(seq, " R: n:%llu\n", (unsigned long long)rgd->rd_addr);
+ return 0;
+}
+
+/**
* trans_go_sync - promote/demote the transaction glock
* @gl: the glock
* @state: the requested state
@@ -330,7 +347,7 @@
*
*/
-static void trans_go_xmote_bh(struct gfs2_glock *gl)
+static int trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
@@ -338,8 +355,7 @@
struct gfs2_log_header_host head;
int error;
- if (gl->gl_state != LM_ST_UNLOCKED &&
- test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+ if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
error = gfs2_find_jhead(sdp->sd_jdesc, &head);
@@ -354,6 +370,7 @@
gfs2_log_pointers_init(sdp, head.lh_blkno);
}
}
+ return 0;
}
/**
@@ -375,12 +392,12 @@
const struct gfs2_glock_operations gfs2_inode_glops = {
.go_xmote_th = inode_go_sync,
- .go_xmote_bh = inode_go_xmote_bh,
.go_inval = inode_go_inval,
.go_demote_ok = inode_go_demote_ok,
.go_lock = inode_go_lock,
+ .go_dump = inode_go_dump,
.go_type = LM_TYPE_INODE,
- .go_min_hold_time = HZ / 10,
+ .go_min_hold_time = HZ / 5,
};
const struct gfs2_glock_operations gfs2_rgrp_glops = {
@@ -389,8 +406,9 @@
.go_demote_ok = rgrp_go_demote_ok,
.go_lock = rgrp_go_lock,
.go_unlock = rgrp_go_unlock,
+ .go_dump = rgrp_go_dump,
.go_type = LM_TYPE_RGRP,
- .go_min_hold_time = HZ / 10,
+ .go_min_hold_time = HZ / 5,
};
const struct gfs2_glock_operations gfs2_trans_glops = {
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index eabe5ea..448697a 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -77,7 +77,6 @@
struct gfs2_rgrpd {
struct list_head rd_list; /* Link with superblock */
struct list_head rd_list_mru;
- struct list_head rd_recent; /* Recently used rgrps */
struct gfs2_glock *rd_gl; /* Glock for this rgrp */
u64 rd_addr; /* grp block disk address */
u64 rd_data0; /* first data location */
@@ -128,20 +127,20 @@
struct gfs2_glock_operations {
void (*go_xmote_th) (struct gfs2_glock *gl);
- void (*go_xmote_bh) (struct gfs2_glock *gl);
+ int (*go_xmote_bh) (struct gfs2_glock *gl, struct gfs2_holder *gh);
void (*go_inval) (struct gfs2_glock *gl, int flags);
int (*go_demote_ok) (struct gfs2_glock *gl);
int (*go_lock) (struct gfs2_holder *gh);
void (*go_unlock) (struct gfs2_holder *gh);
+ int (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl);
const int go_type;
const unsigned long go_min_hold_time;
};
enum {
/* States */
- HIF_HOLDER = 6,
+ HIF_HOLDER = 6, /* Set for gh that "holds" the glock */
HIF_FIRST = 7,
- HIF_ABORTED = 9,
HIF_WAIT = 10,
};
@@ -154,20 +153,20 @@
unsigned gh_flags;
int gh_error;
- unsigned long gh_iflags;
+ unsigned long gh_iflags; /* HIF_... */
unsigned long gh_ip;
};
enum {
- GLF_LOCK = 1,
- GLF_STICKY = 2,
- GLF_DEMOTE = 3,
- GLF_PENDING_DEMOTE = 4,
- GLF_DIRTY = 5,
- GLF_DEMOTE_IN_PROGRESS = 6,
- GLF_LFLUSH = 7,
- GLF_WAITERS2 = 8,
- GLF_CONV_DEADLK = 9,
+ GLF_LOCK = 1,
+ GLF_STICKY = 2,
+ GLF_DEMOTE = 3,
+ GLF_PENDING_DEMOTE = 4,
+ GLF_DEMOTE_IN_PROGRESS = 5,
+ GLF_DIRTY = 6,
+ GLF_LFLUSH = 7,
+ GLF_INVALIDATE_IN_PROGRESS = 8,
+ GLF_REPLY_PENDING = 9,
};
struct gfs2_glock {
@@ -179,19 +178,14 @@
spinlock_t gl_spin;
unsigned int gl_state;
+ unsigned int gl_target;
+ unsigned int gl_reply;
unsigned int gl_hash;
unsigned int gl_demote_state; /* state requested by remote node */
unsigned long gl_demote_time; /* time of first demote request */
- struct pid *gl_owner_pid;
- unsigned long gl_ip;
struct list_head gl_holders;
- struct list_head gl_waiters1; /* HIF_MUTEX */
- struct list_head gl_waiters3; /* HIF_PROMOTE */
const struct gfs2_glock_operations *gl_ops;
-
- struct gfs2_holder *gl_req_gh;
-
void *gl_lock;
char *gl_lvb;
atomic_t gl_lvb_count;
@@ -427,7 +421,6 @@
unsigned int gt_quota_quantum; /* Secs between syncs to quota file */
unsigned int gt_atime_quantum; /* Min secs between atime updates */
unsigned int gt_new_files_jdata;
- unsigned int gt_new_files_directio;
unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */
unsigned int gt_stall_secs; /* Detects trouble! */
unsigned int gt_complain_secs;
@@ -534,7 +527,6 @@
struct mutex sd_rindex_mutex;
struct list_head sd_rindex_list;
struct list_head sd_rindex_mru_list;
- struct list_head sd_rindex_recent_list;
struct gfs2_rgrpd *sd_rindex_forward;
unsigned int sd_rgrps;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 09453d0..6da0ab3 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -504,7 +504,7 @@
}
if (!is_root) {
- error = permission(dir, MAY_EXEC, NULL);
+ error = gfs2_permission(dir, MAY_EXEC);
if (error)
goto out;
}
@@ -667,7 +667,7 @@
{
int error;
- error = permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, NULL);
+ error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
@@ -789,13 +789,8 @@
if ((dip->i_di.di_flags & GFS2_DIF_INHERIT_JDATA) ||
gfs2_tune_get(sdp, gt_new_files_jdata))
di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
- if ((dip->i_di.di_flags & GFS2_DIF_INHERIT_DIRECTIO) ||
- gfs2_tune_get(sdp, gt_new_files_directio))
- di->di_flags |= cpu_to_be32(GFS2_DIF_DIRECTIO);
} else if (S_ISDIR(mode)) {
di->di_flags |= cpu_to_be32(dip->i_di.di_flags &
- GFS2_DIF_INHERIT_DIRECTIO);
- di->di_flags |= cpu_to_be32(dip->i_di.di_flags &
GFS2_DIF_INHERIT_JDATA);
}
@@ -1134,7 +1129,7 @@
if (IS_APPEND(&dip->i_inode))
return -EPERM;
- error = permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, NULL);
+ error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 580da45..6074c25 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -72,7 +72,6 @@
}
-void gfs2_inode_attr_in(struct gfs2_inode *ip);
void gfs2_set_iop(struct inode *inode);
struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type,
u64 no_addr, u64 no_formal_ino,
@@ -91,6 +90,7 @@
struct gfs2_inode *ip);
int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
const struct gfs2_inode *ip);
+int gfs2_permission(struct inode *inode, int mask);
int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to);
int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
int gfs2_glock_nq_atime(struct gfs2_holder *gh);
diff --git a/fs/gfs2/locking.c b/fs/gfs2/locking.c
index 663fee7..523243a 100644
--- a/fs/gfs2/locking.c
+++ b/fs/gfs2/locking.c
@@ -23,12 +23,54 @@
const struct lm_lockops *lw_ops;
};
+static int nolock_mount(char *table_name, char *host_data,
+ lm_callback_t cb, void *cb_data,
+ unsigned int min_lvb_size, int flags,
+ struct lm_lockstruct *lockstruct,
+ struct kobject *fskobj);
+
/* List of registered low-level locking protocols. A file system selects one
of them by name at mount time, e.g. lock_nolock, lock_dlm. */
+static const struct lm_lockops nolock_ops = {
+ .lm_proto_name = "lock_nolock",
+ .lm_mount = nolock_mount,
+};
+
+static struct lmh_wrapper nolock_proto = {
+ .lw_list = LIST_HEAD_INIT(nolock_proto.lw_list),
+ .lw_ops = &nolock_ops,
+};
+
static LIST_HEAD(lmh_list);
static DEFINE_MUTEX(lmh_lock);
+static int nolock_mount(char *table_name, char *host_data,
+ lm_callback_t cb, void *cb_data,
+ unsigned int min_lvb_size, int flags,
+ struct lm_lockstruct *lockstruct,
+ struct kobject *fskobj)
+{
+ char *c;
+ unsigned int jid;
+
+ c = strstr(host_data, "jid=");
+ if (!c)
+ jid = 0;
+ else {
+ c += 4;
+ sscanf(c, "%u", &jid);
+ }
+
+ lockstruct->ls_jid = jid;
+ lockstruct->ls_first = 1;
+ lockstruct->ls_lvb_size = min_lvb_size;
+ lockstruct->ls_ops = &nolock_ops;
+ lockstruct->ls_flags = LM_LSFLAG_LOCAL;
+
+ return 0;
+}
+
/**
* gfs2_register_lockproto - Register a low-level locking protocol
* @proto: the protocol definition
@@ -116,9 +158,13 @@
int try = 0;
int error, found;
+
retry:
mutex_lock(&lmh_lock);
+ if (list_empty(&nolock_proto.lw_list))
+ list_add(&nolock_proto.lw_list, &lmh_list);
+
found = 0;
list_for_each_entry(lw, &lmh_list, lw_list) {
if (!strcmp(lw->lw_ops->lm_proto_name, proto_name)) {
@@ -139,7 +185,8 @@
goto out;
}
- if (!try_module_get(lw->lw_ops->lm_owner)) {
+ if (lw->lw_ops->lm_owner &&
+ !try_module_get(lw->lw_ops->lm_owner)) {
try = 0;
mutex_unlock(&lmh_lock);
msleep(1000);
@@ -158,7 +205,8 @@
void gfs2_unmount_lockproto(struct lm_lockstruct *lockstruct)
{
mutex_lock(&lmh_lock);
- lockstruct->ls_ops->lm_unmount(lockstruct->ls_lockspace);
+ if (lockstruct->ls_ops->lm_unmount)
+ lockstruct->ls_ops->lm_unmount(lockstruct->ls_lockspace);
if (lockstruct->ls_ops->lm_owner)
module_put(lockstruct->ls_ops->lm_owner);
mutex_unlock(&lmh_lock);
diff --git a/fs/gfs2/locking/dlm/lock.c b/fs/gfs2/locking/dlm/lock.c
index cf7ea8a..2482c90 100644
--- a/fs/gfs2/locking/dlm/lock.c
+++ b/fs/gfs2/locking/dlm/lock.c
@@ -11,27 +11,287 @@
static char junk_lvb[GDLM_LVB_SIZE];
-static void queue_complete(struct gdlm_lock *lp)
+
+/* convert dlm lock-mode to gfs lock-state */
+
+static s16 gdlm_make_lmstate(s16 dlmmode)
+{
+ switch (dlmmode) {
+ case DLM_LOCK_IV:
+ case DLM_LOCK_NL:
+ return LM_ST_UNLOCKED;
+ case DLM_LOCK_EX:
+ return LM_ST_EXCLUSIVE;
+ case DLM_LOCK_CW:
+ return LM_ST_DEFERRED;
+ case DLM_LOCK_PR:
+ return LM_ST_SHARED;
+ }
+ gdlm_assert(0, "unknown DLM mode %d", dlmmode);
+ return -1;
+}
+
+/* A lock placed on this queue is re-submitted to DLM as soon as the lock_dlm
+ thread gets to it. */
+
+static void queue_submit(struct gdlm_lock *lp)
{
struct gdlm_ls *ls = lp->ls;
- clear_bit(LFL_ACTIVE, &lp->flags);
-
spin_lock(&ls->async_lock);
- list_add_tail(&lp->clist, &ls->complete);
+ list_add_tail(&lp->delay_list, &ls->submit);
spin_unlock(&ls->async_lock);
wake_up(&ls->thread_wait);
}
-static inline void gdlm_ast(void *astarg)
+static void wake_up_ast(struct gdlm_lock *lp)
{
- queue_complete(astarg);
+ clear_bit(LFL_AST_WAIT, &lp->flags);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&lp->flags, LFL_AST_WAIT);
}
-static inline void gdlm_bast(void *astarg, int mode)
+static void gdlm_delete_lp(struct gdlm_lock *lp)
+{
+ struct gdlm_ls *ls = lp->ls;
+
+ spin_lock(&ls->async_lock);
+ if (!list_empty(&lp->delay_list))
+ list_del_init(&lp->delay_list);
+ ls->all_locks_count--;
+ spin_unlock(&ls->async_lock);
+
+ kfree(lp);
+}
+
+static void gdlm_queue_delayed(struct gdlm_lock *lp)
+{
+ struct gdlm_ls *ls = lp->ls;
+
+ spin_lock(&ls->async_lock);
+ list_add_tail(&lp->delay_list, &ls->delayed);
+ spin_unlock(&ls->async_lock);
+}
+
+static void process_complete(struct gdlm_lock *lp)
+{
+ struct gdlm_ls *ls = lp->ls;
+ struct lm_async_cb acb;
+
+ memset(&acb, 0, sizeof(acb));
+
+ if (lp->lksb.sb_status == -DLM_ECANCEL) {
+ log_info("complete dlm cancel %x,%llx flags %lx",
+ lp->lockname.ln_type,
+ (unsigned long long)lp->lockname.ln_number,
+ lp->flags);
+
+ lp->req = lp->cur;
+ acb.lc_ret |= LM_OUT_CANCELED;
+ if (lp->cur == DLM_LOCK_IV)
+ lp->lksb.sb_lkid = 0;
+ goto out;
+ }
+
+ if (test_and_clear_bit(LFL_DLM_UNLOCK, &lp->flags)) {
+ if (lp->lksb.sb_status != -DLM_EUNLOCK) {
+ log_info("unlock sb_status %d %x,%llx flags %lx",
+ lp->lksb.sb_status, lp->lockname.ln_type,
+ (unsigned long long)lp->lockname.ln_number,
+ lp->flags);
+ return;
+ }
+
+ lp->cur = DLM_LOCK_IV;
+ lp->req = DLM_LOCK_IV;
+ lp->lksb.sb_lkid = 0;
+
+ if (test_and_clear_bit(LFL_UNLOCK_DELETE, &lp->flags)) {
+ gdlm_delete_lp(lp);
+ return;
+ }
+ goto out;
+ }
+
+ if (lp->lksb.sb_flags & DLM_SBF_VALNOTVALID)
+ memset(lp->lksb.sb_lvbptr, 0, GDLM_LVB_SIZE);
+
+ if (lp->lksb.sb_flags & DLM_SBF_ALTMODE) {
+ if (lp->req == DLM_LOCK_PR)
+ lp->req = DLM_LOCK_CW;
+ else if (lp->req == DLM_LOCK_CW)
+ lp->req = DLM_LOCK_PR;
+ }
+
+ /*
+ * A canceled lock request. The lock was just taken off the delayed
+ * list and was never even submitted to dlm.
+ */
+
+ if (test_and_clear_bit(LFL_CANCEL, &lp->flags)) {
+ log_info("complete internal cancel %x,%llx",
+ lp->lockname.ln_type,
+ (unsigned long long)lp->lockname.ln_number);
+ lp->req = lp->cur;
+ acb.lc_ret |= LM_OUT_CANCELED;
+ goto out;
+ }
+
+ /*
+ * An error occured.
+ */
+
+ if (lp->lksb.sb_status) {
+ /* a "normal" error */
+ if ((lp->lksb.sb_status == -EAGAIN) &&
+ (lp->lkf & DLM_LKF_NOQUEUE)) {
+ lp->req = lp->cur;
+ if (lp->cur == DLM_LOCK_IV)
+ lp->lksb.sb_lkid = 0;
+ goto out;
+ }
+
+ /* this could only happen with cancels I think */
+ log_info("ast sb_status %d %x,%llx flags %lx",
+ lp->lksb.sb_status, lp->lockname.ln_type,
+ (unsigned long long)lp->lockname.ln_number,
+ lp->flags);
+ return;
+ }
+
+ /*
+ * This is an AST for an EX->EX conversion for sync_lvb from GFS.
+ */
+
+ if (test_and_clear_bit(LFL_SYNC_LVB, &lp->flags)) {
+ wake_up_ast(lp);
+ return;
+ }
+
+ /*
+ * A lock has been demoted to NL because it initially completed during
+ * BLOCK_LOCKS. Now it must be requested in the originally requested
+ * mode.
+ */
+
+ if (test_and_clear_bit(LFL_REREQUEST, &lp->flags)) {
+ gdlm_assert(lp->req == DLM_LOCK_NL, "%x,%llx",
+ lp->lockname.ln_type,
+ (unsigned long long)lp->lockname.ln_number);
+ gdlm_assert(lp->prev_req > DLM_LOCK_NL, "%x,%llx",
+ lp->lockname.ln_type,
+ (unsigned long long)lp->lockname.ln_number);
+
+ lp->cur = DLM_LOCK_NL;
+ lp->req = lp->prev_req;
+ lp->prev_req = DLM_LOCK_IV;
+ lp->lkf &= ~DLM_LKF_CONVDEADLK;
+
+ set_bit(LFL_NOCACHE, &lp->flags);
+
+ if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
+ !test_bit(LFL_NOBLOCK, &lp->flags))
+ gdlm_queue_delayed(lp);
+ else
+ queue_submit(lp);
+ return;
+ }
+
+ /*
+ * A request is granted during dlm recovery. It may be granted
+ * because the locks of a failed node were cleared. In that case,
+ * there may be inconsistent data beneath this lock and we must wait
+ * for recovery to complete to use it. When gfs recovery is done this
+ * granted lock will be converted to NL and then reacquired in this
+ * granted state.
+ */
+
+ if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
+ !test_bit(LFL_NOBLOCK, &lp->flags) &&
+ lp->req != DLM_LOCK_NL) {
+
+ lp->cur = lp->req;
+ lp->prev_req = lp->req;
+ lp->req = DLM_LOCK_NL;
+ lp->lkf |= DLM_LKF_CONVERT;
+ lp->lkf &= ~DLM_LKF_CONVDEADLK;
+
+ log_debug("rereq %x,%llx id %x %d,%d",
+ lp->lockname.ln_type,
+ (unsigned long long)lp->lockname.ln_number,
+ lp->lksb.sb_lkid, lp->cur, lp->req);
+
+ set_bit(LFL_REREQUEST, &lp->flags);
+ queue_submit(lp);
+ return;
+ }
+
+ /*
+ * DLM demoted the lock to NL before it was granted so GFS must be
+ * told it cannot cache data for this lock.
+ */
+
+ if (lp->lksb.sb_flags & DLM_SBF_DEMOTED)
+ set_bit(LFL_NOCACHE, &lp->flags);
+
+out:
+ /*
+ * This is an internal lock_dlm lock
+ */
+
+ if (test_bit(LFL_INLOCK, &lp->flags)) {
+ clear_bit(LFL_NOBLOCK, &lp->flags);
+ lp->cur = lp->req;
+ wake_up_ast(lp);
+ return;
+ }
+
+ /*
+ * Normal completion of a lock request. Tell GFS it now has the lock.
+ */
+
+ clear_bit(LFL_NOBLOCK, &lp->flags);
+ lp->cur = lp->req;
+
+ acb.lc_name = lp->lockname;
+ acb.lc_ret |= gdlm_make_lmstate(lp->cur);
+
+ ls->fscb(ls->sdp, LM_CB_ASYNC, &acb);
+}
+
+static void gdlm_ast(void *astarg)
{
struct gdlm_lock *lp = astarg;
+ clear_bit(LFL_ACTIVE, &lp->flags);
+ process_complete(lp);
+}
+
+static void process_blocking(struct gdlm_lock *lp, int bast_mode)
+{
struct gdlm_ls *ls = lp->ls;
+ unsigned int cb = 0;
+
+ switch (gdlm_make_lmstate(bast_mode)) {
+ case LM_ST_EXCLUSIVE:
+ cb = LM_CB_NEED_E;
+ break;
+ case LM_ST_DEFERRED:
+ cb = LM_CB_NEED_D;
+ break;
+ case LM_ST_SHARED:
+ cb = LM_CB_NEED_S;
+ break;
+ default:
+ gdlm_assert(0, "unknown bast mode %u", bast_mode);
+ }
+
+ ls->fscb(ls->sdp, cb, &lp->lockname);
+}
+
+
+static void gdlm_bast(void *astarg, int mode)
+{
+ struct gdlm_lock *lp = astarg;
if (!mode) {
printk(KERN_INFO "lock_dlm: bast mode zero %x,%llx\n",
@@ -40,23 +300,7 @@
return;
}
- spin_lock(&ls->async_lock);
- if (!lp->bast_mode) {
- list_add_tail(&lp->blist, &ls->blocking);
- lp->bast_mode = mode;
- } else if (lp->bast_mode < mode)
- lp->bast_mode = mode;
- spin_unlock(&ls->async_lock);
- wake_up(&ls->thread_wait);
-}
-
-void gdlm_queue_delayed(struct gdlm_lock *lp)
-{
- struct gdlm_ls *ls = lp->ls;
-
- spin_lock(&ls->async_lock);
- list_add_tail(&lp->delay_list, &ls->delayed);
- spin_unlock(&ls->async_lock);
+ process_blocking(lp, mode);
}
/* convert gfs lock-state to dlm lock-mode */
@@ -77,24 +321,6 @@
return -1;
}
-/* convert dlm lock-mode to gfs lock-state */
-
-s16 gdlm_make_lmstate(s16 dlmmode)
-{
- switch (dlmmode) {
- case DLM_LOCK_IV:
- case DLM_LOCK_NL:
- return LM_ST_UNLOCKED;
- case DLM_LOCK_EX:
- return LM_ST_EXCLUSIVE;
- case DLM_LOCK_CW:
- return LM_ST_DEFERRED;
- case DLM_LOCK_PR:
- return LM_ST_SHARED;
- }
- gdlm_assert(0, "unknown DLM mode %d", dlmmode);
- return -1;
-}
/* verify agreement with GFS on the current lock state, NB: DLM_LOCK_NL and
DLM_LOCK_IV are both considered LM_ST_UNLOCKED by GFS. */
@@ -134,14 +360,6 @@
if (lp->lksb.sb_lkid != 0) {
lkf |= DLM_LKF_CONVERT;
-
- /* Conversion deadlock avoidance by DLM */
-
- if (!(lp->ls->fsflags & LM_MFLAG_CONV_NODROP) &&
- !test_bit(LFL_FORCE_PROMOTE, &lp->flags) &&
- !(lkf & DLM_LKF_NOQUEUE) &&
- cur > DLM_LOCK_NL && req > DLM_LOCK_NL && cur != req)
- lkf |= DLM_LKF_CONVDEADLK;
}
if (lp->lvb)
@@ -173,14 +391,9 @@
make_strname(name, &lp->strname);
lp->ls = ls;
lp->cur = DLM_LOCK_IV;
- lp->lvb = NULL;
- lp->hold_null = NULL;
- INIT_LIST_HEAD(&lp->clist);
- INIT_LIST_HEAD(&lp->blist);
INIT_LIST_HEAD(&lp->delay_list);
spin_lock(&ls->async_lock);
- list_add(&lp->all_list, &ls->all_locks);
ls->all_locks_count++;
spin_unlock(&ls->async_lock);
@@ -188,26 +401,6 @@
return 0;
}
-void gdlm_delete_lp(struct gdlm_lock *lp)
-{
- struct gdlm_ls *ls = lp->ls;
-
- spin_lock(&ls->async_lock);
- if (!list_empty(&lp->clist))
- list_del_init(&lp->clist);
- if (!list_empty(&lp->blist))
- list_del_init(&lp->blist);
- if (!list_empty(&lp->delay_list))
- list_del_init(&lp->delay_list);
- gdlm_assert(!list_empty(&lp->all_list), "%x,%llx", lp->lockname.ln_type,
- (unsigned long long)lp->lockname.ln_number);
- list_del_init(&lp->all_list);
- ls->all_locks_count--;
- spin_unlock(&ls->async_lock);
-
- kfree(lp);
-}
-
int gdlm_get_lock(void *lockspace, struct lm_lockname *name,
void **lockp)
{
@@ -261,7 +454,7 @@
if ((error == -EAGAIN) && (lp->lkf & DLM_LKF_NOQUEUE)) {
lp->lksb.sb_status = -EAGAIN;
- queue_complete(lp);
+ gdlm_ast(lp);
error = 0;
}
@@ -308,6 +501,12 @@
{
struct gdlm_lock *lp = lock;
+ if (req_state == LM_ST_UNLOCKED)
+ return gdlm_unlock(lock, cur_state);
+
+ if (req_state == LM_ST_UNLOCKED)
+ return gdlm_unlock(lock, cur_state);
+
clear_bit(LFL_DLM_CANCEL, &lp->flags);
if (flags & LM_FLAG_NOEXP)
set_bit(LFL_NOBLOCK, &lp->flags);
@@ -351,7 +550,7 @@
if (delay_list) {
set_bit(LFL_CANCEL, &lp->flags);
set_bit(LFL_ACTIVE, &lp->flags);
- queue_complete(lp);
+ gdlm_ast(lp);
return;
}
@@ -507,22 +706,3 @@
wake_up(&ls->thread_wait);
}
-int gdlm_release_all_locks(struct gdlm_ls *ls)
-{
- struct gdlm_lock *lp, *safe;
- int count = 0;
-
- spin_lock(&ls->async_lock);
- list_for_each_entry_safe(lp, safe, &ls->all_locks, all_list) {
- list_del_init(&lp->all_list);
-
- if (lp->lvb && lp->lvb != junk_lvb)
- kfree(lp->lvb);
- kfree(lp);
- count++;
- }
- spin_unlock(&ls->async_lock);
-
- return count;
-}
-
diff --git a/fs/gfs2/locking/dlm/lock_dlm.h b/fs/gfs2/locking/dlm/lock_dlm.h
index a243cf6..3c98e7c 100644
--- a/fs/gfs2/locking/dlm/lock_dlm.h
+++ b/fs/gfs2/locking/dlm/lock_dlm.h
@@ -72,19 +72,12 @@
int recover_jid_done;
int recover_jid_status;
spinlock_t async_lock;
- struct list_head complete;
- struct list_head blocking;
struct list_head delayed;
struct list_head submit;
- struct list_head all_locks;
u32 all_locks_count;
wait_queue_head_t wait_control;
- struct task_struct *thread1;
- struct task_struct *thread2;
+ struct task_struct *thread;
wait_queue_head_t thread_wait;
- unsigned long drop_time;
- int drop_locks_count;
- int drop_locks_period;
};
enum {
@@ -117,12 +110,7 @@
u32 lkf; /* dlm flags DLM_LKF_ */
unsigned long flags; /* lock_dlm flags LFL_ */
- int bast_mode; /* protected by async_lock */
-
- struct list_head clist; /* complete */
- struct list_head blist; /* blocking */
struct list_head delay_list; /* delayed */
- struct list_head all_list; /* all locks for the fs */
struct gdlm_lock *hold_null; /* NL lock for hold_lvb */
};
@@ -159,11 +147,7 @@
/* lock.c */
-s16 gdlm_make_lmstate(s16);
-void gdlm_queue_delayed(struct gdlm_lock *);
void gdlm_submit_delayed(struct gdlm_ls *);
-int gdlm_release_all_locks(struct gdlm_ls *);
-void gdlm_delete_lp(struct gdlm_lock *);
unsigned int gdlm_do_lock(struct gdlm_lock *);
int gdlm_get_lock(void *, struct lm_lockname *, void **);
diff --git a/fs/gfs2/locking/dlm/mount.c b/fs/gfs2/locking/dlm/mount.c
index 470bdf6..09d78c2 100644
--- a/fs/gfs2/locking/dlm/mount.c
+++ b/fs/gfs2/locking/dlm/mount.c
@@ -22,22 +22,14 @@
if (!ls)
return NULL;
- ls->drop_locks_count = GDLM_DROP_COUNT;
- ls->drop_locks_period = GDLM_DROP_PERIOD;
ls->fscb = cb;
ls->sdp = sdp;
ls->fsflags = flags;
spin_lock_init(&ls->async_lock);
- INIT_LIST_HEAD(&ls->complete);
- INIT_LIST_HEAD(&ls->blocking);
INIT_LIST_HEAD(&ls->delayed);
INIT_LIST_HEAD(&ls->submit);
- INIT_LIST_HEAD(&ls->all_locks);
init_waitqueue_head(&ls->thread_wait);
init_waitqueue_head(&ls->wait_control);
- ls->thread1 = NULL;
- ls->thread2 = NULL;
- ls->drop_time = jiffies;
ls->jid = -1;
strncpy(buf, table_name, 256);
@@ -180,7 +172,6 @@
static void gdlm_unmount(void *lockspace)
{
struct gdlm_ls *ls = lockspace;
- int rv;
log_debug("unmount flags %lx", ls->flags);
@@ -194,9 +185,7 @@
gdlm_kobject_release(ls);
dlm_release_lockspace(ls->dlm_lockspace, 2);
gdlm_release_threads(ls);
- rv = gdlm_release_all_locks(ls);
- if (rv)
- log_info("gdlm_unmount: %d stray locks freed", rv);
+ BUG_ON(ls->all_locks_count);
out:
kfree(ls);
}
@@ -232,7 +221,6 @@
dlm_release_lockspace(ls->dlm_lockspace, 2);
gdlm_release_threads(ls);
- gdlm_release_all_locks(ls);
gdlm_kobject_release(ls);
}
diff --git a/fs/gfs2/locking/dlm/sysfs.c b/fs/gfs2/locking/dlm/sysfs.c
index a4ff271..4ec571c 100644
--- a/fs/gfs2/locking/dlm/sysfs.c
+++ b/fs/gfs2/locking/dlm/sysfs.c
@@ -114,17 +114,6 @@
return sprintf(buf, "%d\n", ls->recover_jid_status);
}
-static ssize_t drop_count_show(struct gdlm_ls *ls, char *buf)
-{
- return sprintf(buf, "%d\n", ls->drop_locks_count);
-}
-
-static ssize_t drop_count_store(struct gdlm_ls *ls, const char *buf, size_t len)
-{
- ls->drop_locks_count = simple_strtol(buf, NULL, 0);
- return len;
-}
-
struct gdlm_attr {
struct attribute attr;
ssize_t (*show)(struct gdlm_ls *, char *);
@@ -144,7 +133,6 @@
GDLM_ATTR(recover, 0644, recover_show, recover_store);
GDLM_ATTR(recover_done, 0444, recover_done_show, NULL);
GDLM_ATTR(recover_status, 0444, recover_status_show, NULL);
-GDLM_ATTR(drop_count, 0644, drop_count_show, drop_count_store);
static struct attribute *gdlm_attrs[] = {
&gdlm_attr_proto_name.attr,
@@ -157,7 +145,6 @@
&gdlm_attr_recover.attr,
&gdlm_attr_recover_done.attr,
&gdlm_attr_recover_status.attr,
- &gdlm_attr_drop_count.attr,
NULL,
};
diff --git a/fs/gfs2/locking/dlm/thread.c b/fs/gfs2/locking/dlm/thread.c
index e53db6f..38823ef 100644
--- a/fs/gfs2/locking/dlm/thread.c
+++ b/fs/gfs2/locking/dlm/thread.c
@@ -9,367 +9,60 @@
#include "lock_dlm.h"
-/* A lock placed on this queue is re-submitted to DLM as soon as the lock_dlm
- thread gets to it. */
-
-static void queue_submit(struct gdlm_lock *lp)
-{
- struct gdlm_ls *ls = lp->ls;
-
- spin_lock(&ls->async_lock);
- list_add_tail(&lp->delay_list, &ls->submit);
- spin_unlock(&ls->async_lock);
- wake_up(&ls->thread_wait);
-}
-
-static void process_blocking(struct gdlm_lock *lp, int bast_mode)
-{
- struct gdlm_ls *ls = lp->ls;
- unsigned int cb = 0;
-
- switch (gdlm_make_lmstate(bast_mode)) {
- case LM_ST_EXCLUSIVE:
- cb = LM_CB_NEED_E;
- break;
- case LM_ST_DEFERRED:
- cb = LM_CB_NEED_D;
- break;
- case LM_ST_SHARED:
- cb = LM_CB_NEED_S;
- break;
- default:
- gdlm_assert(0, "unknown bast mode %u", lp->bast_mode);
- }
-
- ls->fscb(ls->sdp, cb, &lp->lockname);
-}
-
-static void wake_up_ast(struct gdlm_lock *lp)
-{
- clear_bit(LFL_AST_WAIT, &lp->flags);
- smp_mb__after_clear_bit();
- wake_up_bit(&lp->flags, LFL_AST_WAIT);
-}
-
-static void process_complete(struct gdlm_lock *lp)
-{
- struct gdlm_ls *ls = lp->ls;
- struct lm_async_cb acb;
- s16 prev_mode = lp->cur;
-
- memset(&acb, 0, sizeof(acb));
-
- if (lp->lksb.sb_status == -DLM_ECANCEL) {
- log_info("complete dlm cancel %x,%llx flags %lx",
- lp->lockname.ln_type,
- (unsigned long long)lp->lockname.ln_number,
- lp->flags);
-
- lp->req = lp->cur;
- acb.lc_ret |= LM_OUT_CANCELED;
- if (lp->cur == DLM_LOCK_IV)
- lp->lksb.sb_lkid = 0;
- goto out;
- }
-
- if (test_and_clear_bit(LFL_DLM_UNLOCK, &lp->flags)) {
- if (lp->lksb.sb_status != -DLM_EUNLOCK) {
- log_info("unlock sb_status %d %x,%llx flags %lx",
- lp->lksb.sb_status, lp->lockname.ln_type,
- (unsigned long long)lp->lockname.ln_number,
- lp->flags);
- return;
- }
-
- lp->cur = DLM_LOCK_IV;
- lp->req = DLM_LOCK_IV;
- lp->lksb.sb_lkid = 0;
-
- if (test_and_clear_bit(LFL_UNLOCK_DELETE, &lp->flags)) {
- gdlm_delete_lp(lp);
- return;
- }
- goto out;
- }
-
- if (lp->lksb.sb_flags & DLM_SBF_VALNOTVALID)
- memset(lp->lksb.sb_lvbptr, 0, GDLM_LVB_SIZE);
-
- if (lp->lksb.sb_flags & DLM_SBF_ALTMODE) {
- if (lp->req == DLM_LOCK_PR)
- lp->req = DLM_LOCK_CW;
- else if (lp->req == DLM_LOCK_CW)
- lp->req = DLM_LOCK_PR;
- }
-
- /*
- * A canceled lock request. The lock was just taken off the delayed
- * list and was never even submitted to dlm.
- */
-
- if (test_and_clear_bit(LFL_CANCEL, &lp->flags)) {
- log_info("complete internal cancel %x,%llx",
- lp->lockname.ln_type,
- (unsigned long long)lp->lockname.ln_number);
- lp->req = lp->cur;
- acb.lc_ret |= LM_OUT_CANCELED;
- goto out;
- }
-
- /*
- * An error occured.
- */
-
- if (lp->lksb.sb_status) {
- /* a "normal" error */
- if ((lp->lksb.sb_status == -EAGAIN) &&
- (lp->lkf & DLM_LKF_NOQUEUE)) {
- lp->req = lp->cur;
- if (lp->cur == DLM_LOCK_IV)
- lp->lksb.sb_lkid = 0;
- goto out;
- }
-
- /* this could only happen with cancels I think */
- log_info("ast sb_status %d %x,%llx flags %lx",
- lp->lksb.sb_status, lp->lockname.ln_type,
- (unsigned long long)lp->lockname.ln_number,
- lp->flags);
- if (lp->lksb.sb_status == -EDEADLOCK &&
- lp->ls->fsflags & LM_MFLAG_CONV_NODROP) {
- lp->req = lp->cur;
- acb.lc_ret |= LM_OUT_CONV_DEADLK;
- if (lp->cur == DLM_LOCK_IV)
- lp->lksb.sb_lkid = 0;
- goto out;
- } else
- return;
- }
-
- /*
- * This is an AST for an EX->EX conversion for sync_lvb from GFS.
- */
-
- if (test_and_clear_bit(LFL_SYNC_LVB, &lp->flags)) {
- wake_up_ast(lp);
- return;
- }
-
- /*
- * A lock has been demoted to NL because it initially completed during
- * BLOCK_LOCKS. Now it must be requested in the originally requested
- * mode.
- */
-
- if (test_and_clear_bit(LFL_REREQUEST, &lp->flags)) {
- gdlm_assert(lp->req == DLM_LOCK_NL, "%x,%llx",
- lp->lockname.ln_type,
- (unsigned long long)lp->lockname.ln_number);
- gdlm_assert(lp->prev_req > DLM_LOCK_NL, "%x,%llx",
- lp->lockname.ln_type,
- (unsigned long long)lp->lockname.ln_number);
-
- lp->cur = DLM_LOCK_NL;
- lp->req = lp->prev_req;
- lp->prev_req = DLM_LOCK_IV;
- lp->lkf &= ~DLM_LKF_CONVDEADLK;
-
- set_bit(LFL_NOCACHE, &lp->flags);
-
- if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
- !test_bit(LFL_NOBLOCK, &lp->flags))
- gdlm_queue_delayed(lp);
- else
- queue_submit(lp);
- return;
- }
-
- /*
- * A request is granted during dlm recovery. It may be granted
- * because the locks of a failed node were cleared. In that case,
- * there may be inconsistent data beneath this lock and we must wait
- * for recovery to complete to use it. When gfs recovery is done this
- * granted lock will be converted to NL and then reacquired in this
- * granted state.
- */
-
- if (test_bit(DFL_BLOCK_LOCKS, &ls->flags) &&
- !test_bit(LFL_NOBLOCK, &lp->flags) &&
- lp->req != DLM_LOCK_NL) {
-
- lp->cur = lp->req;
- lp->prev_req = lp->req;
- lp->req = DLM_LOCK_NL;
- lp->lkf |= DLM_LKF_CONVERT;
- lp->lkf &= ~DLM_LKF_CONVDEADLK;
-
- log_debug("rereq %x,%llx id %x %d,%d",
- lp->lockname.ln_type,
- (unsigned long long)lp->lockname.ln_number,
- lp->lksb.sb_lkid, lp->cur, lp->req);
-
- set_bit(LFL_REREQUEST, &lp->flags);
- queue_submit(lp);
- return;
- }
-
- /*
- * DLM demoted the lock to NL before it was granted so GFS must be
- * told it cannot cache data for this lock.
- */
-
- if (lp->lksb.sb_flags & DLM_SBF_DEMOTED)
- set_bit(LFL_NOCACHE, &lp->flags);
-
-out:
- /*
- * This is an internal lock_dlm lock
- */
-
- if (test_bit(LFL_INLOCK, &lp->flags)) {
- clear_bit(LFL_NOBLOCK, &lp->flags);
- lp->cur = lp->req;
- wake_up_ast(lp);
- return;
- }
-
- /*
- * Normal completion of a lock request. Tell GFS it now has the lock.
- */
-
- clear_bit(LFL_NOBLOCK, &lp->flags);
- lp->cur = lp->req;
-
- acb.lc_name = lp->lockname;
- acb.lc_ret |= gdlm_make_lmstate(lp->cur);
-
- if (!test_and_clear_bit(LFL_NOCACHE, &lp->flags) &&
- (lp->cur > DLM_LOCK_NL) && (prev_mode > DLM_LOCK_NL))
- acb.lc_ret |= LM_OUT_CACHEABLE;
-
- ls->fscb(ls->sdp, LM_CB_ASYNC, &acb);
-}
-
-static inline int no_work(struct gdlm_ls *ls, int blocking)
+static inline int no_work(struct gdlm_ls *ls)
{
int ret;
spin_lock(&ls->async_lock);
- ret = list_empty(&ls->complete) && list_empty(&ls->submit);
- if (ret && blocking)
- ret = list_empty(&ls->blocking);
+ ret = list_empty(&ls->submit);
spin_unlock(&ls->async_lock);
return ret;
}
-static inline int check_drop(struct gdlm_ls *ls)
-{
- if (!ls->drop_locks_count)
- return 0;
-
- if (time_after(jiffies, ls->drop_time + ls->drop_locks_period * HZ)) {
- ls->drop_time = jiffies;
- if (ls->all_locks_count >= ls->drop_locks_count)
- return 1;
- }
- return 0;
-}
-
-static int gdlm_thread(void *data, int blist)
+static int gdlm_thread(void *data)
{
struct gdlm_ls *ls = (struct gdlm_ls *) data;
struct gdlm_lock *lp = NULL;
- uint8_t complete, blocking, submit, drop;
-
- /* Only thread1 is allowed to do blocking callbacks since gfs
- may wait for a completion callback within a blocking cb. */
while (!kthread_should_stop()) {
wait_event_interruptible(ls->thread_wait,
- !no_work(ls, blist) || kthread_should_stop());
-
- complete = blocking = submit = drop = 0;
+ !no_work(ls) || kthread_should_stop());
spin_lock(&ls->async_lock);
- if (blist && !list_empty(&ls->blocking)) {
- lp = list_entry(ls->blocking.next, struct gdlm_lock,
- blist);
- list_del_init(&lp->blist);
- blocking = lp->bast_mode;
- lp->bast_mode = 0;
- } else if (!list_empty(&ls->complete)) {
- lp = list_entry(ls->complete.next, struct gdlm_lock,
- clist);
- list_del_init(&lp->clist);
- complete = 1;
- } else if (!list_empty(&ls->submit)) {
+ if (!list_empty(&ls->submit)) {
lp = list_entry(ls->submit.next, struct gdlm_lock,
delay_list);
list_del_init(&lp->delay_list);
- submit = 1;
- }
-
- drop = check_drop(ls);
- spin_unlock(&ls->async_lock);
-
- if (complete)
- process_complete(lp);
-
- else if (blocking)
- process_blocking(lp, blocking);
-
- else if (submit)
+ spin_unlock(&ls->async_lock);
gdlm_do_lock(lp);
-
- if (drop)
- ls->fscb(ls->sdp, LM_CB_DROPLOCKS, NULL);
-
- schedule();
+ spin_lock(&ls->async_lock);
+ }
+ spin_unlock(&ls->async_lock);
}
return 0;
}
-static int gdlm_thread1(void *data)
-{
- return gdlm_thread(data, 1);
-}
-
-static int gdlm_thread2(void *data)
-{
- return gdlm_thread(data, 0);
-}
-
int gdlm_init_threads(struct gdlm_ls *ls)
{
struct task_struct *p;
int error;
- p = kthread_run(gdlm_thread1, ls, "lock_dlm1");
+ p = kthread_run(gdlm_thread, ls, "lock_dlm");
error = IS_ERR(p);
if (error) {
- log_error("can't start lock_dlm1 thread %d", error);
+ log_error("can't start lock_dlm thread %d", error);
return error;
}
- ls->thread1 = p;
-
- p = kthread_run(gdlm_thread2, ls, "lock_dlm2");
- error = IS_ERR(p);
- if (error) {
- log_error("can't start lock_dlm2 thread %d", error);
- kthread_stop(ls->thread1);
- return error;
- }
- ls->thread2 = p;
+ ls->thread = p;
return 0;
}
void gdlm_release_threads(struct gdlm_ls *ls)
{
- kthread_stop(ls->thread1);
- kthread_stop(ls->thread2);
+ kthread_stop(ls->thread);
}
diff --git a/fs/gfs2/locking/nolock/Makefile b/fs/gfs2/locking/nolock/Makefile
deleted file mode 100644
index 35e9730..0000000
--- a/fs/gfs2/locking/nolock/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-obj-$(CONFIG_GFS2_FS_LOCKING_NOLOCK) += lock_nolock.o
-lock_nolock-y := main.o
-
diff --git a/fs/gfs2/locking/nolock/main.c b/fs/gfs2/locking/nolock/main.c
deleted file mode 100644
index 284a5ec..0000000
--- a/fs/gfs2/locking/nolock/main.c
+++ /dev/null
@@ -1,238 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
- * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/fs.h>
-#include <linux/lm_interface.h>
-
-struct nolock_lockspace {
- unsigned int nl_lvb_size;
-};
-
-static const struct lm_lockops nolock_ops;
-
-static int nolock_mount(char *table_name, char *host_data,
- lm_callback_t cb, void *cb_data,
- unsigned int min_lvb_size, int flags,
- struct lm_lockstruct *lockstruct,
- struct kobject *fskobj)
-{
- char *c;
- unsigned int jid;
- struct nolock_lockspace *nl;
-
- c = strstr(host_data, "jid=");
- if (!c)
- jid = 0;
- else {
- c += 4;
- sscanf(c, "%u", &jid);
- }
-
- nl = kzalloc(sizeof(struct nolock_lockspace), GFP_KERNEL);
- if (!nl)
- return -ENOMEM;
-
- nl->nl_lvb_size = min_lvb_size;
-
- lockstruct->ls_jid = jid;
- lockstruct->ls_first = 1;
- lockstruct->ls_lvb_size = min_lvb_size;
- lockstruct->ls_lockspace = nl;
- lockstruct->ls_ops = &nolock_ops;
- lockstruct->ls_flags = LM_LSFLAG_LOCAL;
-
- return 0;
-}
-
-static void nolock_others_may_mount(void *lockspace)
-{
-}
-
-static void nolock_unmount(void *lockspace)
-{
- struct nolock_lockspace *nl = lockspace;
- kfree(nl);
-}
-
-static void nolock_withdraw(void *lockspace)
-{
-}
-
-/**
- * nolock_get_lock - get a lm_lock_t given a descripton of the lock
- * @lockspace: the lockspace the lock lives in
- * @name: the name of the lock
- * @lockp: return the lm_lock_t here
- *
- * Returns: 0 on success, -EXXX on failure
- */
-
-static int nolock_get_lock(void *lockspace, struct lm_lockname *name,
- void **lockp)
-{
- *lockp = lockspace;
- return 0;
-}
-
-/**
- * nolock_put_lock - get rid of a lock structure
- * @lock: the lock to throw away
- *
- */
-
-static void nolock_put_lock(void *lock)
-{
-}
-
-/**
- * nolock_lock - acquire a lock
- * @lock: the lock to manipulate
- * @cur_state: the current state
- * @req_state: the requested state
- * @flags: modifier flags
- *
- * Returns: A bitmap of LM_OUT_*
- */
-
-static unsigned int nolock_lock(void *lock, unsigned int cur_state,
- unsigned int req_state, unsigned int flags)
-{
- return req_state | LM_OUT_CACHEABLE;
-}
-
-/**
- * nolock_unlock - unlock a lock
- * @lock: the lock to manipulate
- * @cur_state: the current state
- *
- * Returns: 0
- */
-
-static unsigned int nolock_unlock(void *lock, unsigned int cur_state)
-{
- return 0;
-}
-
-static void nolock_cancel(void *lock)
-{
-}
-
-/**
- * nolock_hold_lvb - hold on to a lock value block
- * @lock: the lock the LVB is associated with
- * @lvbp: return the lm_lvb_t here
- *
- * Returns: 0 on success, -EXXX on failure
- */
-
-static int nolock_hold_lvb(void *lock, char **lvbp)
-{
- struct nolock_lockspace *nl = lock;
- int error = 0;
-
- *lvbp = kzalloc(nl->nl_lvb_size, GFP_NOFS);
- if (!*lvbp)
- error = -ENOMEM;
-
- return error;
-}
-
-/**
- * nolock_unhold_lvb - release a LVB
- * @lock: the lock the LVB is associated with
- * @lvb: the lock value block
- *
- */
-
-static void nolock_unhold_lvb(void *lock, char *lvb)
-{
- kfree(lvb);
-}
-
-static int nolock_plock_get(void *lockspace, struct lm_lockname *name,
- struct file *file, struct file_lock *fl)
-{
- posix_test_lock(file, fl);
-
- return 0;
-}
-
-static int nolock_plock(void *lockspace, struct lm_lockname *name,
- struct file *file, int cmd, struct file_lock *fl)
-{
- int error;
- error = posix_lock_file_wait(file, fl);
- return error;
-}
-
-static int nolock_punlock(void *lockspace, struct lm_lockname *name,
- struct file *file, struct file_lock *fl)
-{
- int error;
- error = posix_lock_file_wait(file, fl);
- return error;
-}
-
-static void nolock_recovery_done(void *lockspace, unsigned int jid,
- unsigned int message)
-{
-}
-
-static const struct lm_lockops nolock_ops = {
- .lm_proto_name = "lock_nolock",
- .lm_mount = nolock_mount,
- .lm_others_may_mount = nolock_others_may_mount,
- .lm_unmount = nolock_unmount,
- .lm_withdraw = nolock_withdraw,
- .lm_get_lock = nolock_get_lock,
- .lm_put_lock = nolock_put_lock,
- .lm_lock = nolock_lock,
- .lm_unlock = nolock_unlock,
- .lm_cancel = nolock_cancel,
- .lm_hold_lvb = nolock_hold_lvb,
- .lm_unhold_lvb = nolock_unhold_lvb,
- .lm_plock_get = nolock_plock_get,
- .lm_plock = nolock_plock,
- .lm_punlock = nolock_punlock,
- .lm_recovery_done = nolock_recovery_done,
- .lm_owner = THIS_MODULE,
-};
-
-static int __init init_nolock(void)
-{
- int error;
-
- error = gfs2_register_lockproto(&nolock_ops);
- if (error) {
- printk(KERN_WARNING
- "lock_nolock: can't register protocol: %d\n", error);
- return error;
- }
-
- printk(KERN_INFO
- "Lock_Nolock (built %s %s) installed\n", __DATE__, __TIME__);
- return 0;
-}
-
-static void __exit exit_nolock(void)
-{
- gfs2_unregister_lockproto(&nolock_ops);
-}
-
-module_init(init_nolock);
-module_exit(exit_nolock);
-
-MODULE_DESCRIPTION("GFS Nolock Locking Module");
-MODULE_AUTHOR("Red Hat, Inc.");
-MODULE_LICENSE("GPL");
-
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 548264b..6c6af9f 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -87,6 +87,8 @@
*/
static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+__releases(&sdp->sd_log_lock)
+__acquires(&sdp->sd_log_lock)
{
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 7711528..7c64510 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -21,6 +21,7 @@
*/
static inline void gfs2_log_lock(struct gfs2_sbd *sdp)
+__acquires(&sdp->sd_log_lock)
{
spin_lock(&sdp->sd_log_lock);
}
@@ -32,6 +33,7 @@
*/
static inline void gfs2_log_unlock(struct gfs2_sbd *sdp)
+__releases(&sdp->sd_log_lock)
{
spin_unlock(&sdp->sd_log_lock);
}
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 053e2eb..bcc668d 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -40,8 +40,6 @@
INIT_HLIST_NODE(&gl->gl_list);
spin_lock_init(&gl->gl_spin);
INIT_LIST_HEAD(&gl->gl_holders);
- INIT_LIST_HEAD(&gl->gl_waiters1);
- INIT_LIST_HEAD(&gl->gl_waiters3);
gl->gl_lvb = NULL;
atomic_set(&gl->gl_lvb_count, 0);
INIT_LIST_HEAD(&gl->gl_reclaim);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 78d75f8..0985362 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -129,7 +129,7 @@
}
/**
- * getbuf - Get a buffer with a given address space
+ * gfs2_getbuf - Get a buffer with a given address space
* @gl: the glock
* @blkno: the block number (filesystem scope)
* @create: 1 if the buffer should be created
@@ -137,7 +137,7 @@
* Returns: the buffer
*/
-static struct buffer_head *getbuf(struct gfs2_glock *gl, u64 blkno, int create)
+struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
{
struct address_space *mapping = gl->gl_aspace->i_mapping;
struct gfs2_sbd *sdp = gl->gl_sbd;
@@ -205,7 +205,7 @@
struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
{
struct buffer_head *bh;
- bh = getbuf(gl, blkno, CREATE);
+ bh = gfs2_getbuf(gl, blkno, CREATE);
meta_prep_new(bh);
return bh;
}
@@ -223,7 +223,7 @@
int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
struct buffer_head **bhp)
{
- *bhp = getbuf(gl, blkno, CREATE);
+ *bhp = gfs2_getbuf(gl, blkno, CREATE);
if (!buffer_uptodate(*bhp)) {
ll_rw_block(READ_META, 1, bhp);
if (flags & DIO_WAIT) {
@@ -346,7 +346,7 @@
struct buffer_head *bh;
while (blen) {
- bh = getbuf(ip->i_gl, bstart, NO_CREATE);
+ bh = gfs2_getbuf(ip->i_gl, bstart, NO_CREATE);
if (bh) {
lock_buffer(bh);
gfs2_log_lock(sdp);
@@ -421,7 +421,7 @@
if (extlen > max_ra)
extlen = max_ra;
- first_bh = getbuf(gl, dblock, CREATE);
+ first_bh = gfs2_getbuf(gl, dblock, CREATE);
if (buffer_uptodate(first_bh))
goto out;
@@ -432,7 +432,7 @@
extlen--;
while (extlen) {
- bh = getbuf(gl, dblock, CREATE);
+ bh = gfs2_getbuf(gl, dblock, CREATE);
if (!buffer_uptodate(bh) && !buffer_locked(bh))
ll_rw_block(READA, 1, &bh);
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 73e3b1c..b1a5f36 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -47,6 +47,7 @@
int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno,
int flags, struct buffer_head **bhp);
int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
+struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create);
void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
int meta);
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index f55394e..e64a1b0 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -499,34 +499,34 @@
* @file: The file to read
* @page: The page of the file
*
- * This deals with the locking required. We use a trylock in order to
- * avoid the page lock / glock ordering problems returning AOP_TRUNCATED_PAGE
- * in the event that we are unable to get the lock.
+ * This deals with the locking required. We have to unlock and
+ * relock the page in order to get the locking in the right
+ * order.
*/
static int gfs2_readpage(struct file *file, struct page *page)
{
- struct gfs2_inode *ip = GFS2_I(page->mapping->host);
- struct gfs2_holder *gh;
+ struct address_space *mapping = page->mapping;
+ struct gfs2_inode *ip = GFS2_I(mapping->host);
+ struct gfs2_holder gh;
int error;
- gh = gfs2_glock_is_locked_by_me(ip->i_gl);
- if (!gh) {
- gh = kmalloc(sizeof(struct gfs2_holder), GFP_NOFS);
- if (!gh)
- return -ENOBUFS;
- gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, gh);
+ unlock_page(page);
+ gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
+ error = gfs2_glock_nq_atime(&gh);
+ if (unlikely(error))
+ goto out;
+ error = AOP_TRUNCATED_PAGE;
+ lock_page(page);
+ if (page->mapping == mapping && !PageUptodate(page))
+ error = __gfs2_readpage(file, page);
+ else
unlock_page(page);
- error = gfs2_glock_nq_atime(gh);
- if (likely(error != 0))
- goto out;
- return AOP_TRUNCATED_PAGE;
- }
- error = __gfs2_readpage(file, page);
- gfs2_glock_dq(gh);
+ gfs2_glock_dq(&gh);
out:
- gfs2_holder_uninit(gh);
- kfree(gh);
+ gfs2_holder_uninit(&gh);
+ if (error && error != AOP_TRUNCATED_PAGE)
+ lock_page(page);
return error;
}
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index 24dd594..e9a366d 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -15,6 +15,7 @@
#include <linux/uio.h>
#include <linux/blkdev.h>
#include <linux/mm.h>
+#include <linux/mount.h>
#include <linux/fs.h>
#include <linux/gfs2_ondisk.h>
#include <linux/ext2_fs.h>
@@ -133,7 +134,6 @@
[7] = GFS2_DIF_NOATIME,
[12] = GFS2_DIF_EXHASH,
[14] = GFS2_DIF_INHERIT_JDATA,
- [20] = GFS2_DIF_INHERIT_DIRECTIO,
};
static const u32 gfs2_to_fsflags[32] = {
@@ -142,7 +142,6 @@
[gfs2fl_AppendOnly] = FS_APPEND_FL,
[gfs2fl_NoAtime] = FS_NOATIME_FL,
[gfs2fl_ExHash] = FS_INDEX_FL,
- [gfs2fl_InheritDirectio] = FS_DIRECTIO_FL,
[gfs2fl_InheritJdata] = FS_JOURNAL_DATA_FL,
};
@@ -160,12 +159,8 @@
return error;
fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_di.di_flags);
- if (!S_ISDIR(inode->i_mode)) {
- if (ip->i_di.di_flags & GFS2_DIF_JDATA)
- fsflags |= FS_JOURNAL_DATA_FL;
- if (ip->i_di.di_flags & GFS2_DIF_DIRECTIO)
- fsflags |= FS_DIRECTIO_FL;
- }
+ if (!S_ISDIR(inode->i_mode) && ip->i_di.di_flags & GFS2_DIF_JDATA)
+ fsflags |= FS_JOURNAL_DATA_FL;
if (put_user(fsflags, ptr))
error = -EFAULT;
@@ -194,13 +189,11 @@
/* Flags that can be set by user space */
#define GFS2_FLAGS_USER_SET (GFS2_DIF_JDATA| \
- GFS2_DIF_DIRECTIO| \
GFS2_DIF_IMMUTABLE| \
GFS2_DIF_APPENDONLY| \
GFS2_DIF_NOATIME| \
GFS2_DIF_SYNC| \
GFS2_DIF_SYSTEM| \
- GFS2_DIF_INHERIT_DIRECTIO| \
GFS2_DIF_INHERIT_JDATA)
/**
@@ -220,10 +213,14 @@
int error;
u32 new_flags, flags;
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ error = mnt_want_write(filp->f_path.mnt);
if (error)
return error;
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ if (error)
+ goto out_drop_write;
+
flags = ip->i_di.di_flags;
new_flags = (flags & ~mask) | (reqflags & mask);
if ((new_flags ^ flags) == 0)
@@ -242,7 +239,7 @@
!capable(CAP_LINUX_IMMUTABLE))
goto out;
if (!IS_IMMUTABLE(inode)) {
- error = permission(inode, MAY_WRITE, NULL);
+ error = gfs2_permission(inode, MAY_WRITE);
if (error)
goto out;
}
@@ -272,6 +269,8 @@
gfs2_trans_end(sdp);
out:
gfs2_glock_dq_uninit(&gh);
+out_drop_write:
+ mnt_drop_write(filp->f_path.mnt);
return error;
}
@@ -285,8 +284,6 @@
if (!S_ISDIR(inode->i_mode)) {
if (gfsflags & GFS2_DIF_INHERIT_JDATA)
gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
- if (gfsflags & GFS2_DIF_INHERIT_DIRECTIO)
- gfsflags ^= (GFS2_DIF_DIRECTIO | GFS2_DIF_INHERIT_DIRECTIO);
return do_gfs2_set_flags(filp, gfsflags, ~0);
}
return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA);
@@ -487,11 +484,6 @@
goto fail_gunlock;
}
- /* Listen to the Direct I/O flag */
-
- if (ip->i_di.di_flags & GFS2_DIF_DIRECTIO)
- file->f_flags |= O_DIRECT;
-
gfs2_glock_dq_uninit(&i_gh);
}
@@ -669,8 +661,7 @@
int error = 0;
state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
- flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE
- | GL_FLOCK;
+ flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
mutex_lock(&fp->f_fl_mutex);
@@ -683,9 +674,8 @@
gfs2_glock_dq_wait(fl_gh);
gfs2_holder_reinit(state, flags, fl_gh);
} else {
- error = gfs2_glock_get(GFS2_SB(&ip->i_inode),
- ip->i_no_addr, &gfs2_flock_glops,
- CREATE, &gl);
+ error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
+ &gfs2_flock_glops, CREATE, &gl);
if (error)
goto out;
gfs2_holder_init(gl, state, flags, fl_gh);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index b2028c8..b4d1d64 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -64,7 +64,6 @@
mutex_init(&sdp->sd_rindex_mutex);
INIT_LIST_HEAD(&sdp->sd_rindex_list);
INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);
- INIT_LIST_HEAD(&sdp->sd_rindex_recent_list);
INIT_LIST_HEAD(&sdp->sd_jindex_list);
spin_lock_init(&sdp->sd_jindex_spin);
@@ -364,6 +363,8 @@
static void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp)
{
+ if (!sdp->sd_lockstruct.ls_ops->lm_others_may_mount)
+ return;
if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
sdp->sd_lockstruct.ls_ops->lm_others_may_mount(
sdp->sd_lockstruct.ls_lockspace);
@@ -741,8 +742,7 @@
goto out;
}
- if (gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_lockspace) ||
- gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_ops) ||
+ if (gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_ops) ||
gfs2_assert_warn(sdp, sdp->sd_lockstruct.ls_lvb_size >=
GFS2_MIN_LVB_SIZE)) {
gfs2_unmount_lockproto(&sdp->sd_lockstruct);
@@ -873,7 +873,7 @@
fail_locking:
init_locking(sdp, &mount_gh, UNDO);
fail_lm:
- gfs2_gl_hash_clear(sdp, WAIT);
+ gfs2_gl_hash_clear(sdp);
gfs2_lm_unmount(sdp);
while (invalidate_inodes(sb))
yield();
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 2686ad4..1e252df 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -163,7 +163,7 @@
if (error)
goto out;
- error = permission(dir, MAY_WRITE | MAY_EXEC, NULL);
+ error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
if (error)
goto out_gunlock;
@@ -669,7 +669,7 @@
}
}
} else {
- error = permission(ndir, MAY_WRITE | MAY_EXEC, NULL);
+ error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC);
if (error)
goto out_gunlock;
@@ -704,7 +704,7 @@
/* Check out the dir to be renamed */
if (dir_rename) {
- error = permission(odentry->d_inode, MAY_WRITE, NULL);
+ error = gfs2_permission(odentry->d_inode, MAY_WRITE);
if (error)
goto out_gunlock;
}
@@ -891,7 +891,7 @@
* Returns: errno
*/
-static int gfs2_permission(struct inode *inode, int mask, struct nameidata *nd)
+int gfs2_permission(struct inode *inode, int mask)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
@@ -905,13 +905,22 @@
unlock = 1;
}
- error = generic_permission(inode, mask, gfs2_check_acl);
+ if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
+ error = -EACCES;
+ else
+ error = generic_permission(inode, mask, gfs2_check_acl);
if (unlock)
gfs2_glock_dq_uninit(&i_gh);
return error;
}
+static int gfs2_iop_permission(struct inode *inode, int mask,
+ struct nameidata *nd)
+{
+ return gfs2_permission(inode, mask);
+}
+
static int setattr_size(struct inode *inode, struct iattr *attr)
{
struct gfs2_inode *ip = GFS2_I(inode);
@@ -1141,7 +1150,7 @@
}
const struct inode_operations gfs2_file_iops = {
- .permission = gfs2_permission,
+ .permission = gfs2_iop_permission,
.setattr = gfs2_setattr,
.getattr = gfs2_getattr,
.setxattr = gfs2_setxattr,
@@ -1160,7 +1169,7 @@
.rmdir = gfs2_rmdir,
.mknod = gfs2_mknod,
.rename = gfs2_rename,
- .permission = gfs2_permission,
+ .permission = gfs2_iop_permission,
.setattr = gfs2_setattr,
.getattr = gfs2_getattr,
.setxattr = gfs2_setxattr,
@@ -1172,7 +1181,7 @@
const struct inode_operations gfs2_symlink_iops = {
.readlink = gfs2_readlink,
.follow_link = gfs2_follow_link,
- .permission = gfs2_permission,
+ .permission = gfs2_iop_permission,
.setattr = gfs2_setattr,
.getattr = gfs2_getattr,
.setxattr = gfs2_setxattr,
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index 0b7cc92..f66ea0f 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -126,7 +126,7 @@
gfs2_clear_rgrpd(sdp);
gfs2_jindex_free(sdp);
/* Take apart glock structures and buffer lists */
- gfs2_gl_hash_clear(sdp, WAIT);
+ gfs2_gl_hash_clear(sdp);
/* Unmount the locking protocol */
gfs2_lm_unmount(sdp);
@@ -155,7 +155,7 @@
static int gfs2_sync_fs(struct super_block *sb, int wait)
{
sb->s_dirt = 0;
- if (wait)
+ if (wait && sb->s_fs_info)
gfs2_log_flush(sb->s_fs_info, NULL);
return 0;
}
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 56aaf91..3e073f5 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -904,7 +904,7 @@
do_sync = 0;
else {
value *= gfs2_jindex_size(sdp) * num;
- do_div(value, den);
+ value = div_s64(value, den);
value += (s64)be64_to_cpu(qd->qd_qb.qb_value);
if (value < (s64)be64_to_cpu(qd->qd_qb.qb_limit))
do_sync = 0;
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 2888e4b..d5e91f4 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -428,6 +428,9 @@
static void gfs2_lm_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
unsigned int message)
{
+ if (!sdp->sd_lockstruct.ls_ops->lm_recovery_done)
+ return;
+
if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
sdp->sd_lockstruct.ls_ops->lm_recovery_done(
sdp->sd_lockstruct.ls_lockspace, jid, message);
@@ -505,7 +508,7 @@
error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED,
LM_FLAG_NOEXP | LM_FLAG_PRIORITY |
- GL_NOCANCEL | GL_NOCACHE, &t_gh);
+ GL_NOCACHE, &t_gh);
if (error)
goto fail_gunlock_ji;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 3401628..2d90fb2 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -371,11 +371,6 @@
spin_lock(&sdp->sd_rindex_spin);
sdp->sd_rindex_forward = NULL;
- head = &sdp->sd_rindex_recent_list;
- while (!list_empty(head)) {
- rgd = list_entry(head->next, struct gfs2_rgrpd, rd_recent);
- list_del(&rgd->rd_recent);
- }
spin_unlock(&sdp->sd_rindex_spin);
head = &sdp->sd_rindex_list;
@@ -945,107 +940,30 @@
}
/**
- * recent_rgrp_first - get first RG from "recent" list
- * @sdp: The GFS2 superblock
- * @rglast: address of the rgrp used last
- *
- * Returns: The first rgrp in the recent list
- */
-
-static struct gfs2_rgrpd *recent_rgrp_first(struct gfs2_sbd *sdp,
- u64 rglast)
-{
- struct gfs2_rgrpd *rgd;
-
- spin_lock(&sdp->sd_rindex_spin);
-
- if (rglast) {
- list_for_each_entry(rgd, &sdp->sd_rindex_recent_list, rd_recent) {
- if (rgrp_contains_block(rgd, rglast))
- goto out;
- }
- }
- rgd = NULL;
- if (!list_empty(&sdp->sd_rindex_recent_list))
- rgd = list_entry(sdp->sd_rindex_recent_list.next,
- struct gfs2_rgrpd, rd_recent);
-out:
- spin_unlock(&sdp->sd_rindex_spin);
- return rgd;
-}
-
-/**
* recent_rgrp_next - get next RG from "recent" list
* @cur_rgd: current rgrp
- * @remove:
*
* Returns: The next rgrp in the recent list
*/
-static struct gfs2_rgrpd *recent_rgrp_next(struct gfs2_rgrpd *cur_rgd,
- int remove)
+static struct gfs2_rgrpd *recent_rgrp_next(struct gfs2_rgrpd *cur_rgd)
{
struct gfs2_sbd *sdp = cur_rgd->rd_sbd;
struct list_head *head;
struct gfs2_rgrpd *rgd;
spin_lock(&sdp->sd_rindex_spin);
-
- head = &sdp->sd_rindex_recent_list;
-
- list_for_each_entry(rgd, head, rd_recent) {
- if (rgd == cur_rgd) {
- if (cur_rgd->rd_recent.next != head)
- rgd = list_entry(cur_rgd->rd_recent.next,
- struct gfs2_rgrpd, rd_recent);
- else
- rgd = NULL;
-
- if (remove)
- list_del(&cur_rgd->rd_recent);
-
- goto out;
- }
+ head = &sdp->sd_rindex_mru_list;
+ if (unlikely(cur_rgd->rd_list_mru.next == head)) {
+ spin_unlock(&sdp->sd_rindex_spin);
+ return NULL;
}
-
- rgd = NULL;
- if (!list_empty(head))
- rgd = list_entry(head->next, struct gfs2_rgrpd, rd_recent);
-
-out:
+ rgd = list_entry(cur_rgd->rd_list_mru.next, struct gfs2_rgrpd, rd_list_mru);
spin_unlock(&sdp->sd_rindex_spin);
return rgd;
}
/**
- * recent_rgrp_add - add an RG to tail of "recent" list
- * @new_rgd: The rgrp to add
- *
- */
-
-static void recent_rgrp_add(struct gfs2_rgrpd *new_rgd)
-{
- struct gfs2_sbd *sdp = new_rgd->rd_sbd;
- struct gfs2_rgrpd *rgd;
- unsigned int count = 0;
- unsigned int max = sdp->sd_rgrps / gfs2_jindex_size(sdp);
-
- spin_lock(&sdp->sd_rindex_spin);
-
- list_for_each_entry(rgd, &sdp->sd_rindex_recent_list, rd_recent) {
- if (rgd == new_rgd)
- goto out;
-
- if (++count >= max)
- goto out;
- }
- list_add_tail(&new_rgd->rd_recent, &sdp->sd_rindex_recent_list);
-
-out:
- spin_unlock(&sdp->sd_rindex_spin);
-}
-
-/**
* forward_rgrp_get - get an rgrp to try next from full list
* @sdp: The GFS2 superblock
*
@@ -1112,9 +1030,7 @@
int loops = 0;
int error, rg_locked;
- /* Try recently successful rgrps */
-
- rgd = recent_rgrp_first(sdp, ip->i_goal);
+ rgd = gfs2_blk2rgrpd(sdp, ip->i_goal);
while (rgd) {
rg_locked = 0;
@@ -1136,11 +1052,9 @@
gfs2_glock_dq_uninit(&al->al_rgd_gh);
if (inode)
return inode;
- rgd = recent_rgrp_next(rgd, 1);
- break;
-
+ /* fall through */
case GLR_TRYFAILED:
- rgd = recent_rgrp_next(rgd, 0);
+ rgd = recent_rgrp_next(rgd);
break;
default:
@@ -1199,7 +1113,9 @@
out:
if (begin) {
- recent_rgrp_add(rgd);
+ spin_lock(&sdp->sd_rindex_spin);
+ list_move(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list);
+ spin_unlock(&sdp->sd_rindex_spin);
rgd = gfs2_rgrpd_get_next(rgd);
if (!rgd)
rgd = gfs2_rgrpd_get_first(sdp);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 7aeacbc..63a8a90 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -65,7 +65,6 @@
gt->gt_quota_quantum = 60;
gt->gt_atime_quantum = 3600;
gt->gt_new_files_jdata = 0;
- gt->gt_new_files_directio = 0;
gt->gt_max_readahead = 1 << 18;
gt->gt_stall_secs = 600;
gt->gt_complain_secs = 10;
@@ -941,8 +940,7 @@
}
error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_DEFERRED,
- LM_FLAG_PRIORITY | GL_NOCACHE,
- t_gh);
+ GL_NOCACHE, t_gh);
list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
error = gfs2_jdesc_check(jd);
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 9ab9fc8..7484655 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -110,18 +110,6 @@
return len;
}
-static ssize_t shrink_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
-{
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
-
- if (simple_strtol(buf, NULL, 0) != 1)
- return -EINVAL;
-
- gfs2_gl_hash_clear(sdp, NO_WAIT);
- return len;
-}
-
static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf,
size_t len)
{
@@ -175,7 +163,6 @@
GFS2_ATTR(id, 0444, id_show, NULL);
GFS2_ATTR(fsname, 0444, fsname_show, NULL);
GFS2_ATTR(freeze, 0644, freeze_show, freeze_store);
-GFS2_ATTR(shrink, 0200, NULL, shrink_store);
GFS2_ATTR(withdraw, 0644, withdraw_show, withdraw_store);
GFS2_ATTR(statfs_sync, 0200, NULL, statfs_sync_store);
GFS2_ATTR(quota_sync, 0200, NULL, quota_sync_store);
@@ -186,7 +173,6 @@
&gfs2_attr_id.attr,
&gfs2_attr_fsname.attr,
&gfs2_attr_freeze.attr,
- &gfs2_attr_shrink.attr,
&gfs2_attr_withdraw.attr,
&gfs2_attr_statfs_sync.attr,
&gfs2_attr_quota_sync.attr,
@@ -426,7 +412,6 @@
TUNE_ATTR(complain_secs, 0);
TUNE_ATTR(statfs_slow, 0);
TUNE_ATTR(new_files_jdata, 0);
-TUNE_ATTR(new_files_directio, 0);
TUNE_ATTR(quota_simul_sync, 1);
TUNE_ATTR(quota_cache_secs, 1);
TUNE_ATTR(stall_secs, 1);
@@ -455,7 +440,6 @@
&tune_attr_quotad_secs.attr,
&tune_attr_quota_scale.attr,
&tune_attr_new_files_jdata.attr,
- &tune_attr_new_files_directio.attr,
NULL,
};
diff --git a/include/linux/lm_interface.h b/include/linux/lm_interface.h
index f274997..2ed8fa1 100644
--- a/include/linux/lm_interface.h
+++ b/include/linux/lm_interface.h
@@ -122,11 +122,9 @@
*/
#define LM_OUT_ST_MASK 0x00000003
-#define LM_OUT_CACHEABLE 0x00000004
#define LM_OUT_CANCELED 0x00000008
#define LM_OUT_ASYNC 0x00000080
#define LM_OUT_ERROR 0x00000100
-#define LM_OUT_CONV_DEADLK 0x00000200
/*
* lm_callback_t types
@@ -138,9 +136,6 @@
* LM_CB_NEED_RECOVERY
* The given journal needs to be recovered.
*
- * LM_CB_DROPLOCKS
- * Reduce the number of cached locks.
- *
* LM_CB_ASYNC
* The given lock has been granted.
*/
@@ -149,7 +144,6 @@
#define LM_CB_NEED_D 258
#define LM_CB_NEED_S 259
#define LM_CB_NEED_RECOVERY 260
-#define LM_CB_DROPLOCKS 261
#define LM_CB_ASYNC 262
/*