Merge tag 'please-pull-pstore' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux
Pull pstore patches from Tony Luck:
"A few fixes to reduce places where pstore might hang a system in the
crash path. Plus a new mountpoint (/sys/fs/pstore ... makes more
sense then /dev/pstore)."
Fix up trivial conflict in drivers/firmware/efivars.c
* tag 'please-pull-pstore' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux:
pstore: Create a convenient mount point for pstore
efi_pstore: Introducing workqueue updating sysfs
efivars: Disable external interrupt while holding efivars->lock
efi_pstore: Avoid deadlock in non-blocking paths
pstore: Avoid deadlock in panic and emergency-restart path
diff --git a/Documentation/ABI/testing/pstore b/Documentation/ABI/testing/pstore
index ff1df4e..5fca9f5 100644
--- a/Documentation/ABI/testing/pstore
+++ b/Documentation/ABI/testing/pstore
@@ -1,4 +1,4 @@
-Where: /dev/pstore/...
+Where: /sys/fs/pstore/... (or /dev/pstore/...)
Date: March 2011
Kernel Version: 2.6.39
Contact: tony.luck@intel.com
@@ -11,9 +11,9 @@
of the console log is captured, but other interesting
data can also be saved.
- # mount -t pstore -o kmsg_bytes=8000 - /dev/pstore
+ # mount -t pstore -o kmsg_bytes=8000 - /sys/fs/pstore
- $ ls -l /dev/pstore
+ $ ls -l /sys/fs/pstore/
total 0
-r--r--r-- 1 root root 7896 Nov 30 15:38 dmesg-erst-1
@@ -27,9 +27,9 @@
the file will signal to the underlying persistent storage
device that it can reclaim the space for later re-use.
- $ rm /dev/pstore/dmesg-erst-1
+ $ rm /sys/fs/pstore/dmesg-erst-1
- The expectation is that all files in /dev/pstore
+ The expectation is that all files in /sys/fs/pstore/
will be saved elsewhere and erased from persistent store
soon after boot to free up space ready for the next
catastrophe.
diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index f5596db..fed08b6 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -158,6 +158,13 @@
efi_char16_t *variable_name,
efi_guid_t *vendor_guid);
+/*
+ * Prototype for workqueue functions updating sysfs entry
+ */
+
+static void efivar_update_sysfs_entries(struct work_struct *);
+static DECLARE_WORK(efivar_work, efivar_update_sysfs_entries);
+
/* Return the number of unicode characters in data */
static unsigned long
utf16_strnlen(efi_char16_t *s, size_t maxlength)
@@ -405,10 +412,11 @@
get_var_data(struct efivars *efivars, struct efi_variable *var)
{
efi_status_t status;
+ unsigned long flags;
- spin_lock(&efivars->lock);
+ spin_lock_irqsave(&efivars->lock, flags);
status = get_var_data_locked(efivars, var);
- spin_unlock(&efivars->lock);
+ spin_unlock_irqrestore(&efivars->lock, flags);
if (status != EFI_SUCCESS) {
printk(KERN_WARNING "efivars: get_variable() failed 0x%lx!\n",
@@ -537,14 +545,14 @@
return -EINVAL;
}
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
status = efivars->ops->set_variable(new_var->VariableName,
&new_var->VendorGuid,
new_var->Attributes,
new_var->DataSize,
new_var->Data);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
if (status != EFI_SUCCESS) {
printk(KERN_WARNING "efivars: set_variable() failed: status=%lx\n",
@@ -713,7 +721,7 @@
* amounts of memory. Pick a default size of 64K if
* QueryVariableInfo() isn't supported by the firmware.
*/
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
if (!efivars->ops->query_variable_info)
status = EFI_UNSUPPORTED;
@@ -723,7 +731,7 @@
&remaining_size, &max_size);
}
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
if (status != EFI_SUCCESS) {
if (status != EFI_UNSUPPORTED)
@@ -754,7 +762,7 @@
* set_variable call, and removal of the variable from the efivars
* list (in the case of an authenticated delete).
*/
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
status = efivars->ops->set_variable(var->var.VariableName,
&var->var.VendorGuid,
@@ -762,7 +770,7 @@
data);
if (status != EFI_SUCCESS) {
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
kfree(data);
return efi_status_to_err(status);
@@ -783,21 +791,21 @@
NULL);
if (status == EFI_BUFFER_TOO_SMALL) {
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
mutex_lock(&inode->i_mutex);
i_size_write(inode, newdatasize + sizeof(attributes));
mutex_unlock(&inode->i_mutex);
} else if (status == EFI_NOT_FOUND) {
list_del(&var->list);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
efivar_unregister(var);
drop_nlink(inode);
d_delete(file->f_dentry);
dput(file->f_dentry);
} else {
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
pr_warn("efivarfs: inconsistent EFI variable implementation? "
"status = %lx\n", status);
}
@@ -819,11 +827,11 @@
void *data;
ssize_t size = 0;
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
status = efivars->ops->get_variable(var->var.VariableName,
&var->var.VendorGuid,
&attributes, &datasize, NULL);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
if (status != EFI_BUFFER_TOO_SMALL)
return efi_status_to_err(status);
@@ -833,12 +841,12 @@
if (!data)
return -ENOMEM;
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
status = efivars->ops->get_variable(var->var.VariableName,
&var->var.VendorGuid,
&attributes, &datasize,
(data + sizeof(attributes)));
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
if (status != EFI_SUCCESS) {
size = efi_status_to_err(status);
@@ -966,9 +974,9 @@
goto out;
kobject_uevent(&var->kobj, KOBJ_ADD);
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
list_add(&var->list, &efivars->list);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
d_instantiate(dentry, inode);
dget(dentry);
out:
@@ -985,7 +993,7 @@
struct efivars *efivars = var->efivars;
efi_status_t status;
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
status = efivars->ops->set_variable(var->var.VariableName,
&var->var.VendorGuid,
@@ -993,14 +1001,14 @@
if (status == EFI_SUCCESS || status == EFI_NOT_FOUND) {
list_del(&var->list);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
efivar_unregister(var);
drop_nlink(dentry->d_inode);
dput(dentry);
return 0;
}
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
return -EINVAL;
};
@@ -1066,13 +1074,13 @@
/* copied by the above to local storage in the dentry. */
kfree(name);
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
efivars->ops->get_variable(entry->var.VariableName,
&entry->var.VendorGuid,
&entry->var.Attributes,
&size,
NULL);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
mutex_lock(&inode->i_mutex);
inode->i_private = entry;
@@ -1123,7 +1131,7 @@
{
struct efivars *efivars = psi->data;
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
efivars->walk_entry = list_first_entry(&efivars->list,
struct efivar_entry, list);
return 0;
@@ -1133,7 +1141,7 @@
{
struct efivars *efivars = psi->data;
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
return 0;
}
@@ -1209,8 +1217,18 @@
int i, ret = 0;
u64 storage_space, remaining_space, max_variable_size;
efi_status_t status = EFI_NOT_FOUND;
+ unsigned long flags;
- spin_lock(&efivars->lock);
+ if (pstore_cannot_block_path(reason)) {
+ /*
+ * If the lock is taken by another cpu in non-blocking path,
+ * this driver returns without entering firmware to avoid
+ * hanging up.
+ */
+ if (!spin_trylock_irqsave(&efivars->lock, flags))
+ return -EBUSY;
+ } else
+ spin_lock_irqsave(&efivars->lock, flags);
/*
* Check if there is a space enough to log.
@@ -1222,7 +1240,7 @@
&remaining_space,
&max_variable_size);
if (status || remaining_space < size + DUMP_NAME_LEN * 2) {
- spin_unlock(&efivars->lock);
+ spin_unlock_irqrestore(&efivars->lock, flags);
*id = part;
return -ENOSPC;
}
@@ -1236,13 +1254,10 @@
efivars->ops->set_variable(efi_name, &vendor, PSTORE_EFI_ATTRIBUTES,
size, psi->buf);
- spin_unlock(&efivars->lock);
+ spin_unlock_irqrestore(&efivars->lock, flags);
- if (size)
- ret = efivar_create_sysfs_entry(efivars,
- utf16_strsize(efi_name,
- DUMP_NAME_LEN * 2),
- efi_name, &vendor);
+ if (reason == KMSG_DUMP_OOPS)
+ schedule_work(&efivar_work);
*id = part;
return ret;
@@ -1263,7 +1278,7 @@
sprintf(name, "dump-type%u-%u-%d-%lu", type, (unsigned int)id, count,
time.tv_sec);
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
for (i = 0; i < DUMP_NAME_LEN; i++)
efi_name[i] = name[i];
@@ -1307,7 +1322,7 @@
if (found)
list_del(&found->list);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
if (found)
efivar_unregister(found);
@@ -1377,7 +1392,7 @@
return -EINVAL;
}
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
/*
* Does this variable already exist?
@@ -1395,7 +1410,7 @@
}
}
if (found) {
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
return -EINVAL;
}
@@ -1409,10 +1424,10 @@
if (status != EFI_SUCCESS) {
printk(KERN_WARNING "efivars: set_variable() failed: status=%lx\n",
status);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
return -EIO;
}
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
/* Create the entry in sysfs. Locking is not required here */
status = efivar_create_sysfs_entry(efivars,
@@ -1440,7 +1455,7 @@
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
/*
* Does this variable already exist?
@@ -1458,7 +1473,7 @@
}
}
if (!found) {
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
return -EINVAL;
}
/* force the Attributes/DataSize to 0 to ensure deletion */
@@ -1474,18 +1489,87 @@
if (status != EFI_SUCCESS) {
printk(KERN_WARNING "efivars: set_variable() failed: status=%lx\n",
status);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
return -EIO;
}
list_del(&search_efivar->list);
/* We need to release this lock before unregistering. */
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
efivar_unregister(search_efivar);
/* It's dead Jim.... */
return count;
}
+static bool variable_is_present(efi_char16_t *variable_name, efi_guid_t *vendor)
+{
+ struct efivar_entry *entry, *n;
+ struct efivars *efivars = &__efivars;
+ unsigned long strsize1, strsize2;
+ bool found = false;
+
+ strsize1 = utf16_strsize(variable_name, 1024);
+ list_for_each_entry_safe(entry, n, &efivars->list, list) {
+ strsize2 = utf16_strsize(entry->var.VariableName, 1024);
+ if (strsize1 == strsize2 &&
+ !memcmp(variable_name, &(entry->var.VariableName),
+ strsize2) &&
+ !efi_guidcmp(entry->var.VendorGuid,
+ *vendor)) {
+ found = true;
+ break;
+ }
+ }
+ return found;
+}
+
+static void efivar_update_sysfs_entries(struct work_struct *work)
+{
+ struct efivars *efivars = &__efivars;
+ efi_guid_t vendor;
+ efi_char16_t *variable_name;
+ unsigned long variable_name_size = 1024;
+ efi_status_t status = EFI_NOT_FOUND;
+ bool found;
+
+ /* Add new sysfs entries */
+ while (1) {
+ variable_name = kzalloc(variable_name_size, GFP_KERNEL);
+ if (!variable_name) {
+ pr_err("efivars: Memory allocation failed.\n");
+ return;
+ }
+
+ spin_lock_irq(&efivars->lock);
+ found = false;
+ while (1) {
+ variable_name_size = 1024;
+ status = efivars->ops->get_next_variable(
+ &variable_name_size,
+ variable_name,
+ &vendor);
+ if (status != EFI_SUCCESS) {
+ break;
+ } else {
+ if (!variable_is_present(variable_name,
+ &vendor)) {
+ found = true;
+ break;
+ }
+ }
+ }
+ spin_unlock_irq(&efivars->lock);
+
+ if (!found) {
+ kfree(variable_name);
+ break;
+ } else
+ efivar_create_sysfs_entry(efivars,
+ variable_name_size,
+ variable_name, &vendor);
+ }
+}
+
/*
* Let's not leave out systab information that snuck into
* the efivars driver
@@ -1594,9 +1678,9 @@
kfree(short_name);
short_name = NULL;
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
list_add(&new_efivar->list, &efivars->list);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
return 0;
}
@@ -1665,9 +1749,9 @@
struct efivar_entry *entry, *n;
list_for_each_entry_safe(entry, n, &efivars->list, list) {
- spin_lock(&efivars->lock);
+ spin_lock_irq(&efivars->lock);
list_del(&entry->list);
- spin_unlock(&efivars->lock);
+ spin_unlock_irq(&efivars->lock);
efivar_unregister(entry);
}
if (efivars->new_var)
@@ -1823,6 +1907,8 @@
static void __exit
efivars_exit(void)
{
+ cancel_work_sync(&efivar_work);
+
if (efi_enabled(EFI_RUNTIME_SERVICES)) {
unregister_efivars(&__efivars);
kobject_put(efi_kobj);
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 67de74c..e4bcb2c 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -418,9 +418,25 @@
.kill_sb = pstore_kill_sb,
};
+static struct kobject *pstore_kobj;
+
static int __init init_pstore_fs(void)
{
- return register_filesystem(&pstore_fs_type);
+ int err = 0;
+
+ /* Create a convenient mount point for people to access pstore */
+ pstore_kobj = kobject_create_and_add("pstore", fs_kobj);
+ if (!pstore_kobj) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ err = register_filesystem(&pstore_fs_type);
+ if (err < 0)
+ kobject_put(pstore_kobj);
+
+out:
+ return err;
}
module_init(init_pstore_fs)
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 5ea2e77..86d1038 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -96,6 +96,27 @@
}
}
+bool pstore_cannot_block_path(enum kmsg_dump_reason reason)
+{
+ /*
+ * In case of NMI path, pstore shouldn't be blocked
+ * regardless of reason.
+ */
+ if (in_nmi())
+ return true;
+
+ switch (reason) {
+ /* In panic case, other cpus are stopped by smp_send_stop(). */
+ case KMSG_DUMP_PANIC:
+ /* Emergency restart shouldn't be blocked by spin lock. */
+ case KMSG_DUMP_EMERG:
+ return true;
+ default:
+ return false;
+ }
+}
+EXPORT_SYMBOL_GPL(pstore_cannot_block_path);
+
/*
* callback from kmsg_dump. (s2,l2) has the most recently
* written bytes, older bytes are in (s1,l1). Save as much
@@ -114,10 +135,12 @@
why = get_reason_str(reason);
- if (in_nmi()) {
- is_locked = spin_trylock(&psinfo->buf_lock);
- if (!is_locked)
- pr_err("pstore dump routine blocked in NMI, may corrupt error record\n");
+ if (pstore_cannot_block_path(reason)) {
+ is_locked = spin_trylock_irqsave(&psinfo->buf_lock, flags);
+ if (!is_locked) {
+ pr_err("pstore dump routine blocked in %s path, may corrupt error record\n"
+ , in_nmi() ? "NMI" : why);
+ }
} else
spin_lock_irqsave(&psinfo->buf_lock, flags);
oopscount++;
@@ -143,9 +166,9 @@
total += hsize + len;
part++;
}
- if (in_nmi()) {
+ if (pstore_cannot_block_path(reason)) {
if (is_locked)
- spin_unlock(&psinfo->buf_lock);
+ spin_unlock_irqrestore(&psinfo->buf_lock, flags);
} else
spin_unlock_irqrestore(&psinfo->buf_lock, flags);
}
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 7a9498a..9bf2f1f 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -740,7 +740,8 @@
* 1) ->list - adds, removals, reads, writes
* 2) ops.[gs]et_variable() calls.
* It must not be held when creating sysfs entries or calling kmalloc.
- * ops.get_next_variable() is only called from register_efivars(),
+ * ops.get_next_variable() is only called from register_efivars()
+ * or efivar_update_sysfs_entries(),
* which is protected by the BKL, so that path is safe.
*/
spinlock_t lock;
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index 1788909..75d01760 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -68,12 +68,18 @@
#ifdef CONFIG_PSTORE
extern int pstore_register(struct pstore_info *);
+extern bool pstore_cannot_block_path(enum kmsg_dump_reason reason);
#else
static inline int
pstore_register(struct pstore_info *psi)
{
return -ENODEV;
}
+static inline bool
+pstore_cannot_block_path(enum kmsg_dump_reason reason)
+{
+ return false;
+}
#endif
#endif /*_LINUX_PSTORE_H*/