linux-stable/drivers/firmware/efi/efi-pstore.c

259 lines
6.2 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0+
#include <linux/efi.h>
#include <linux/module.h>
#include <linux/pstore.h>
#include <linux/slab.h>
#include <linux/ucs2_string.h>
MODULE_IMPORT_NS(EFIVAR);
#define DUMP_NAME_LEN 66
#define EFIVARS_DATA_SIZE_MAX 1024
static bool efivars_pstore_disable =
IS_ENABLED(CONFIG_EFI_VARS_PSTORE_DEFAULT_DISABLE);
module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644);
#define PSTORE_EFI_ATTRIBUTES \
(EFI_VARIABLE_NON_VOLATILE | \
EFI_VARIABLE_BOOTSERVICE_ACCESS | \
EFI_VARIABLE_RUNTIME_ACCESS)
static int efi_pstore_open(struct pstore_info *psi)
{
int err;
err = efivar_lock();
if (err)
return err;
psi->data = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL);
if (!psi->data)
return -ENOMEM;
return 0;
}
static int efi_pstore_close(struct pstore_info *psi)
{
efivar_unlock();
kfree(psi->data);
return 0;
}
static inline u64 generic_id(u64 timestamp, unsigned int part, int count)
{
return (timestamp * 100 + part) * 1000 + count;
}
static int efi_pstore_read_func(struct pstore_record *record,
efi_char16_t *varname)
{
unsigned long wlen, size = EFIVARS_DATA_SIZE_MAX;
char name[DUMP_NAME_LEN], data_type;
efi_status_t status;
int cnt;
unsigned int part;
u64 time;
ucs2_as_utf8(name, varname, DUMP_NAME_LEN);
if (sscanf(name, "dump-type%u-%u-%d-%llu-%c",
&record->type, &part, &cnt, &time, &data_type) == 5) {
record->id = generic_id(time, part, cnt);
record->part = part;
record->count = cnt;
record->time.tv_sec = time;
record->time.tv_nsec = 0;
if (data_type == 'C')
record->compressed = true;
else
record->compressed = false;
record->ecc_notice_size = 0;
} else if (sscanf(name, "dump-type%u-%u-%d-%llu",
&record->type, &part, &cnt, &time) == 4) {
record->id = generic_id(time, part, cnt);
record->part = part;
record->count = cnt;
record->time.tv_sec = time;
record->time.tv_nsec = 0;
record->compressed = false;
record->ecc_notice_size = 0;
} else if (sscanf(name, "dump-type%u-%u-%llu",
&record->type, &part, &time) == 3) {
/*
* Check if an old format,
* which doesn't support holding
* multiple logs, remains.
*/
record->id = generic_id(time, part, 0);
record->part = part;
record->count = 0;
record->time.tv_sec = time;
record->time.tv_nsec = 0;
record->compressed = false;
record->ecc_notice_size = 0;
} else
return 0;
record->buf = kmalloc(size, GFP_KERNEL);
if (!record->buf)
return -ENOMEM;
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: Seiji Aguchi <seiji.aguchi@hds.com> Tested-by: Madper Xie <cxie@redhat.com> Cc: stable@kernel.org Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-10-30 19:27:26 +00:00
status = efivar_get_variable(varname, &LINUX_EFI_CRASH_GUID, NULL,
&size, record->buf);
if (status != EFI_SUCCESS) {
kfree(record->buf);
return -EIO;
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: Seiji Aguchi <seiji.aguchi@hds.com> Tested-by: Madper Xie <cxie@redhat.com> Cc: stable@kernel.org Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-10-30 19:27:26 +00:00
}
/*
* Store the name of the variable in the pstore_record priv field, so
* we can reuse it later if we need to delete the EFI variable from the
* variable store.
*/
wlen = (ucs2_strnlen(varname, DUMP_NAME_LEN) + 1) * sizeof(efi_char16_t);
record->priv = kmemdup(varname, wlen, GFP_KERNEL);
if (!record->priv) {
kfree(record->buf);
return -ENOMEM;
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: Seiji Aguchi <seiji.aguchi@hds.com> Tested-by: Madper Xie <cxie@redhat.com> Cc: stable@kernel.org Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-10-30 19:27:26 +00:00
}
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: Seiji Aguchi <seiji.aguchi@hds.com> Tested-by: Madper Xie <cxie@redhat.com> Cc: stable@kernel.org Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-10-30 19:27:26 +00:00
return size;
}
static ssize_t efi_pstore_read(struct pstore_record *record)
{
efi_char16_t *varname = record->psi->data;
efi_guid_t guid = LINUX_EFI_CRASH_GUID;
unsigned long varname_size;
efi_status_t status;
for (;;) {
varname_size = EFIVARS_DATA_SIZE_MAX;
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: Seiji Aguchi <seiji.aguchi@hds.com> Tested-by: Madper Xie <cxie@redhat.com> Cc: stable@kernel.org Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-10-30 19:27:26 +00:00
/*
* If this is the first read() call in the pstore enumeration,
* varname will be the empty string, and the GetNextVariable()
* runtime service call will return the first EFI variable in
* its own enumeration order, ignoring the guid argument.
*
* Subsequent calls to GetNextVariable() must pass the name and
* guid values returned by the previous call, which is why we
* store varname in record->psi->data. Given that we only
* enumerate variables with the efi-pstore GUID, there is no
* need to record the guid return value.
*/
status = efivar_get_next_variable(&varname_size, varname, &guid);
if (status == EFI_NOT_FOUND)
return 0;
if (status != EFI_SUCCESS)
return -EIO;
/* skip variables that don't concern us */
if (efi_guidcmp(guid, LINUX_EFI_CRASH_GUID))
continue;
return efi_pstore_read_func(record, varname);
}
}
static int efi_pstore_write(struct pstore_record *record)
{
char name[DUMP_NAME_LEN];
efi_char16_t efi_name[DUMP_NAME_LEN];
efi_status_t status;
int i;
record->id = generic_id(record->time.tv_sec, record->part,
record->count);
/* Since we copy the entire length of name, make sure it is wiped. */
memset(name, 0, sizeof(name));
snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lld-%c",
record->type, record->part, record->count,
(long long)record->time.tv_sec,
record->compressed ? 'C' : 'D');
for (i = 0; i < DUMP_NAME_LEN; i++)
efi_name[i] = name[i];
if (efivar_trylock())
return -EBUSY;
status = efivar_set_variable_locked(efi_name, &LINUX_EFI_CRASH_GUID,
PSTORE_EFI_ATTRIBUTES,
record->size, record->psi->buf,
true);
efivar_unlock();
return status == EFI_SUCCESS ? 0 : -EIO;
};
static int efi_pstore_erase(struct pstore_record *record)
{
efi_status_t status;
status = efivar_set_variable(record->priv, &LINUX_EFI_CRASH_GUID,
PSTORE_EFI_ATTRIBUTES, 0, NULL);
if (status != EFI_SUCCESS && status != EFI_NOT_FOUND)
return -EIO;
return 0;
}
static struct pstore_info efi_pstore_info = {
.owner = THIS_MODULE,
.name = "efi",
.flags = PSTORE_FLAGS_DMESG,
.open = efi_pstore_open,
.close = efi_pstore_close,
.read = efi_pstore_read,
.write = efi_pstore_write,
.erase = efi_pstore_erase,
};
static __init int efivars_pstore_init(void)
{
if (!efivar_supports_writes())
return 0;
if (efivars_pstore_disable)
return 0;
efi_pstore_info.buf = kmalloc(4096, GFP_KERNEL);
if (!efi_pstore_info.buf)
return -ENOMEM;
efi_pstore_info.bufsize = 1024;
if (pstore_register(&efi_pstore_info)) {
kfree(efi_pstore_info.buf);
efi_pstore_info.buf = NULL;
efi_pstore_info.bufsize = 0;
}
return 0;
}
static __exit void efivars_pstore_exit(void)
{
if (!efi_pstore_info.bufsize)
return;
pstore_unregister(&efi_pstore_info);
kfree(efi_pstore_info.buf);
efi_pstore_info.buf = NULL;
efi_pstore_info.bufsize = 0;
}
module_init(efivars_pstore_init);
module_exit(efivars_pstore_exit);
MODULE_DESCRIPTION("EFI variable backend for pstore");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:efivars");