Commit e0d59733 authored by Seiji Aguchi's avatar Seiji Aguchi Committed by Matt Fleming

efivars, efi-pstore: Hold off deletion of sysfs entry until the scan is completed

Currently, when mounting pstore file system, a read callback of
efi_pstore driver runs mutiple times as below.

- In the first read callback, scan efivar_sysfs_list from head and pass
  a kmsg buffer of a entry to an upper pstore layer.
- In the second read callback, rescan efivar_sysfs_list from the entry
  and pass another kmsg buffer to it.
- Repeat the scan and pass until the end of efivar_sysfs_list.

In this process, an entry is read across the multiple read function
calls. To avoid race between the read and erasion, the whole process
above is protected by a spinlock, holding in open() and releasing in
close().

At the same time, kmemdup() is called to pass the buffer to pstore
filesystem during it. And then, it causes a following lockdep warning.

To make the dynamic memory allocation runnable without taking spinlock,
holding off a deletion of sysfs entry if it happens while scanning it
via efi_pstore, and deleting it after the scan is completed.

To implement it, this patch introduces two flags, scanning and deleting,
to efivar_entry.

On the code basis, it seems that all the scanning and deleting logic is
not needed because __efivars->lock are not dropped when reading from the
EFI variable store.

But, the scanning and deleting logic is still needed because an
efi-pstore and a pstore filesystem works as follows.

In case an entry(A) is found, the pointer is saved to psi->data.  And
efi_pstore_read() passes the entry(A) to a pstore filesystem by
releasing  __efivars->lock.

And then, the pstore filesystem calls efi_pstore_read() again and the
same entry(A), which is saved to psi->data, is used for resuming to scan
a sysfs-list.

So, to protect the entry(A), the logic is needed.

[    1.143710] ------------[ cut here ]------------
[    1.144058] WARNING: CPU: 1 PID: 1 at kernel/lockdep.c:2740 lockdep_trace_alloc+0x104/0x110()
[    1.144058] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))
[    1.144058] Modules linked in:
[    1.144058] CPU: 1 PID: 1 Comm: systemd Not tainted 3.11.0-rc5 #2
[    1.144058]  0000000000000009 ffff8800797e9ae0 ffffffff816614a5 ffff8800797e9b28
[    1.144058]  ffff8800797e9b18 ffffffff8105510d 0000000000000080 0000000000000046
[    1.144058]  00000000000000d0 00000000000003af ffffffff81ccd0c0 ffff8800797e9b78
[    1.144058] Call Trace:
[    1.144058]  [<ffffffff816614a5>] dump_stack+0x54/0x74
[    1.144058]  [<ffffffff8105510d>] warn_slowpath_common+0x7d/0xa0
[    1.144058]  [<ffffffff8105517c>] warn_slowpath_fmt+0x4c/0x50
[    1.144058]  [<ffffffff8131290f>] ? vsscanf+0x57f/0x7b0
[    1.144058]  [<ffffffff810bbd74>] lockdep_trace_alloc+0x104/0x110
[    1.144058]  [<ffffffff81192da0>] __kmalloc_track_caller+0x50/0x280
[    1.144058]  [<ffffffff815147bb>] ? efi_pstore_read_func.part.1+0x12b/0x170
[    1.144058]  [<ffffffff8115b260>] kmemdup+0x20/0x50
[    1.144058]  [<ffffffff815147bb>] efi_pstore_read_func.part.1+0x12b/0x170
[    1.144058]  [<ffffffff81514800>] ? efi_pstore_read_func.part.1+0x170/0x170
[    1.144058]  [<ffffffff815148b4>] efi_pstore_read_func+0xb4/0xe0
[    1.144058]  [<ffffffff81512b7b>] __efivar_entry_iter+0xfb/0x120
[    1.144058]  [<ffffffff8151428f>] efi_pstore_read+0x3f/0x50
[    1.144058]  [<ffffffff8128d7ba>] pstore_get_records+0x9a/0x150
[    1.158207]  [<ffffffff812af25c>] ? selinux_d_instantiate+0x1c/0x20
[    1.158207]  [<ffffffff8128ce30>] ? parse_options+0x80/0x80
[    1.158207]  [<ffffffff8128ced5>] pstore_fill_super+0xa5/0xc0
[    1.158207]  [<ffffffff811ae7d2>] mount_single+0xa2/0xd0
[    1.158207]  [<ffffffff8128ccf8>] pstore_mount+0x18/0x20
[    1.158207]  [<ffffffff811ae8b9>] mount_fs+0x39/0x1b0
[    1.158207]  [<ffffffff81160550>] ? __alloc_percpu+0x10/0x20
[    1.158207]  [<ffffffff811c9493>] vfs_kern_mount+0x63/0xf0
[    1.158207]  [<ffffffff811cbb0e>] do_mount+0x23e/0xa20
[    1.158207]  [<ffffffff8115b51b>] ? strndup_user+0x4b/0xf0
[    1.158207]  [<ffffffff811cc373>] SyS_mount+0x83/0xc0
[    1.158207]  [<ffffffff81673cc2>] system_call_fastpath+0x16/0x1b
[    1.158207] ---[ end trace 61981bc62de9f6f4 ]---
Signed-off-by: default avatarSeiji Aguchi <seiji.aguchi@hds.com>
Tested-by: default avatarMadper Xie <cxie@redhat.com>
Cc: stable@kernel.org
Signed-off-by: default avatarMatt Fleming <matt.fleming@intel.com>
parent 6ce4eac1
...@@ -18,14 +18,12 @@ module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644); ...@@ -18,14 +18,12 @@ module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644);
static int efi_pstore_open(struct pstore_info *psi) static int efi_pstore_open(struct pstore_info *psi)
{ {
efivar_entry_iter_begin();
psi->data = NULL; psi->data = NULL;
return 0; return 0;
} }
static int efi_pstore_close(struct pstore_info *psi) static int efi_pstore_close(struct pstore_info *psi)
{ {
efivar_entry_iter_end();
psi->data = NULL; psi->data = NULL;
return 0; return 0;
} }
...@@ -91,19 +89,125 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data) ...@@ -91,19 +89,125 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
__efivar_entry_get(entry, &entry->var.Attributes, __efivar_entry_get(entry, &entry->var.Attributes,
&entry->var.DataSize, entry->var.Data); &entry->var.DataSize, entry->var.Data);
size = entry->var.DataSize; size = entry->var.DataSize;
memcpy(*cb_data->buf, entry->var.Data,
(size_t)min_t(unsigned long, EFIVARS_DATA_SIZE_MAX, size));
*cb_data->buf = kmemdup(entry->var.Data, size, GFP_KERNEL);
if (*cb_data->buf == NULL)
return -ENOMEM;
return size; return size;
} }
/**
* efi_pstore_scan_sysfs_enter
* @entry: scanning entry
* @next: next entry
* @head: list head
*/
static void efi_pstore_scan_sysfs_enter(struct efivar_entry *pos,
struct efivar_entry *next,
struct list_head *head)
{
pos->scanning = true;
if (&next->list != head)
next->scanning = true;
}
/**
* __efi_pstore_scan_sysfs_exit
* @entry: deleting entry
* @turn_off_scanning: Check if a scanning flag should be turned off
*/
static inline void __efi_pstore_scan_sysfs_exit(struct efivar_entry *entry,
bool turn_off_scanning)
{
if (entry->deleting) {
list_del(&entry->list);
efivar_entry_iter_end();
efivar_unregister(entry);
efivar_entry_iter_begin();
} else if (turn_off_scanning)
entry->scanning = false;
}
/**
* efi_pstore_scan_sysfs_exit
* @pos: scanning entry
* @next: next entry
* @head: list head
* @stop: a flag checking if scanning will stop
*/
static void efi_pstore_scan_sysfs_exit(struct efivar_entry *pos,
struct efivar_entry *next,
struct list_head *head, bool stop)
{
__efi_pstore_scan_sysfs_exit(pos, true);
if (stop)
__efi_pstore_scan_sysfs_exit(next, &next->list != head);
}
/**
* efi_pstore_sysfs_entry_iter
*
* @data: function-specific data to pass to callback
* @pos: entry to begin iterating from
*
* You MUST call efivar_enter_iter_begin() before this function, and
* efivar_entry_iter_end() afterwards.
*
* It is possible to begin iteration from an arbitrary entry within
* the list by passing @pos. @pos is updated on return to point to
* the next entry of the last one passed to efi_pstore_read_func().
* To begin iterating from the beginning of the list @pos must be %NULL.
*/
static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
{
struct efivar_entry *entry, *n;
struct list_head *head = &efivar_sysfs_list;
int size = 0;
if (!*pos) {
list_for_each_entry_safe(entry, n, head, list) {
efi_pstore_scan_sysfs_enter(entry, n, head);
size = efi_pstore_read_func(entry, data);
efi_pstore_scan_sysfs_exit(entry, n, head, size < 0);
if (size)
break;
}
*pos = n;
return size;
}
list_for_each_entry_safe_from((*pos), n, head, list) {
efi_pstore_scan_sysfs_enter((*pos), n, head);
size = efi_pstore_read_func((*pos), data);
efi_pstore_scan_sysfs_exit((*pos), n, head, size < 0);
if (size)
break;
}
*pos = n;
return size;
}
/**
* efi_pstore_read
*
* This function returns a size of NVRAM entry logged via efi_pstore_write().
* The meaning and behavior of efi_pstore/pstore are as below.
*
* size > 0: Got data of an entry logged via efi_pstore_write() successfully,
* and pstore filesystem will continue reading subsequent entries.
* size == 0: Entry was not logged via efi_pstore_write(),
* and efi_pstore driver will continue reading subsequent entries.
* size < 0: Failed to get data of entry logging via efi_pstore_write(),
* and pstore will stop reading entry.
*/
static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
int *count, struct timespec *timespec, int *count, struct timespec *timespec,
char **buf, bool *compressed, char **buf, bool *compressed,
struct pstore_info *psi) struct pstore_info *psi)
{ {
struct pstore_read_data data; struct pstore_read_data data;
ssize_t size;
data.id = id; data.id = id;
data.type = type; data.type = type;
...@@ -112,8 +216,17 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, ...@@ -112,8 +216,17 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
data.compressed = compressed; data.compressed = compressed;
data.buf = buf; data.buf = buf;
return __efivar_entry_iter(efi_pstore_read_func, &efivar_sysfs_list, &data, *data.buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL);
(struct efivar_entry **)&psi->data); if (!*data.buf)
return -ENOMEM;
efivar_entry_iter_begin();
size = efi_pstore_sysfs_entry_iter(&data,
(struct efivar_entry **)&psi->data);
efivar_entry_iter_end();
if (size <= 0)
kfree(*data.buf);
return size;
} }
static int efi_pstore_write(enum pstore_type_id type, static int efi_pstore_write(enum pstore_type_id type,
...@@ -184,9 +297,17 @@ static int efi_pstore_erase_func(struct efivar_entry *entry, void *data) ...@@ -184,9 +297,17 @@ static int efi_pstore_erase_func(struct efivar_entry *entry, void *data)
return 0; return 0;
} }
if (entry->scanning) {
/*
* Skip deletion because this entry will be deleted
* after scanning is completed.
*/
entry->deleting = true;
} else
list_del(&entry->list);
/* found */ /* found */
__efivar_entry_delete(entry); __efivar_entry_delete(entry);
list_del(&entry->list);
return 1; return 1;
} }
...@@ -214,10 +335,12 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count, ...@@ -214,10 +335,12 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
efivar_entry_iter_begin(); efivar_entry_iter_begin();
found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list, &edata, &entry); found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list, &edata, &entry);
efivar_entry_iter_end();
if (found) if (found && !entry->scanning) {
efivar_entry_iter_end();
efivar_unregister(entry); efivar_unregister(entry);
} else
efivar_entry_iter_end();
return 0; return 0;
} }
......
...@@ -383,12 +383,16 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, ...@@ -383,12 +383,16 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj,
else if (__efivar_entry_delete(entry)) else if (__efivar_entry_delete(entry))
err = -EIO; err = -EIO;
efivar_entry_iter_end(); if (err) {
efivar_entry_iter_end();
if (err)
return err; return err;
}
efivar_unregister(entry); if (!entry->scanning) {
efivar_entry_iter_end();
efivar_unregister(entry);
} else
efivar_entry_iter_end();
/* It's dead Jim.... */ /* It's dead Jim.... */
return count; return count;
......
...@@ -683,8 +683,16 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, ...@@ -683,8 +683,16 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
if (!found) if (!found)
return NULL; return NULL;
if (remove) if (remove) {
list_del(&entry->list); if (entry->scanning) {
/*
* The entry will be deleted
* after scanning is completed.
*/
entry->deleting = true;
} else
list_del(&entry->list);
}
return entry; return entry;
} }
......
...@@ -801,6 +801,8 @@ struct efivar_entry { ...@@ -801,6 +801,8 @@ struct efivar_entry {
struct efi_variable var; struct efi_variable var;
struct list_head list; struct list_head list;
struct kobject kobj; struct kobject kobj;
bool scanning;
bool deleting;
}; };
...@@ -866,6 +868,8 @@ void efivar_run_worker(void); ...@@ -866,6 +868,8 @@ void efivar_run_worker(void);
#if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
int efivars_sysfs_init(void); int efivars_sysfs_init(void);
#define EFIVARS_DATA_SIZE_MAX 1024
#endif /* CONFIG_EFI_VARS */ #endif /* CONFIG_EFI_VARS */
#endif /* _LINUX_EFI_H */ #endif /* _LINUX_EFI_H */
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment