mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 17:30:02 +00:00
![Guo Xuenan](/assets/img/avatar_default.png)
xfs log io error will trigger xlog shut down, and end_io worker call xlog_state_shutdown_callbacks to unpin and release the buf log item. The race condition is that when there are some thread doing transaction commit and happened not to be intercepted by xlog_is_shutdown, then, these log item will be insert into CIL, when unpin and release these buf log item, UAF will occur. BTW, add delay before `xlog_cil_commit` can increase recurrence probability. The following call graph actually encountered this bad situation. fsstress io end worker kworker/0:1H-216 xlog_ioend_work ->xlog_force_shutdown ->xlog_state_shutdown_callbacks ->xlog_cil_process_committed ->xlog_cil_committed ->xfs_trans_committed_bulk ->xfs_trans_apply_sb_deltas ->li_ops->iop_unpin(lip, 1); ->xfs_trans_getsb ->_xfs_trans_bjoin ->xfs_buf_item_init ->if (bip) { return 0;} //relog ->xlog_cil_commit ->xlog_cil_insert_items //insert into CIL ->xfs_buf_ioend_fail(bp); ->xfs_buf_ioend ->xfs_buf_item_done ->xfs_buf_item_relse ->xfs_buf_item_free when cil push worker gather percpu cil and insert super block buf log item into ctx->log_items then uaf occurs. ================================================================== BUG: KASAN: use-after-free in xlog_cil_push_work+0x1c8f/0x22f0 Write of size 8 at addr ffff88801800f3f0 by task kworker/u4:4/105 CPU: 0 PID: 105 Comm: kworker/u4:4 Tainted: G W 6.1.0-rc1-00001-g274115149b42 #136 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Workqueue: xfs-cil/sda xlog_cil_push_work Call Trace: <TASK> dump_stack_lvl+0x4d/0x66 print_report+0x171/0x4a6 kasan_report+0xb3/0x130 xlog_cil_push_work+0x1c8f/0x22f0 process_one_work+0x6f9/0xf70 worker_thread+0x578/0xf30 kthread+0x28c/0x330 ret_from_fork+0x1f/0x30 </TASK> Allocated by task 2145: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 __kasan_slab_alloc+0x54/0x60 kmem_cache_alloc+0x14a/0x510 xfs_buf_item_init+0x160/0x6d0 _xfs_trans_bjoin+0x7f/0x2e0 xfs_trans_getsb+0xb6/0x3f0 xfs_trans_apply_sb_deltas+0x1f/0x8c0 __xfs_trans_commit+0xa25/0xe10 xfs_symlink+0xe23/0x1660 xfs_vn_symlink+0x157/0x280 vfs_symlink+0x491/0x790 do_symlinkat+0x128/0x220 __x64_sys_symlink+0x7a/0x90 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 216: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x40 __kasan_slab_free+0x105/0x1a0 kmem_cache_free+0xb6/0x460 xfs_buf_ioend+0x1e9/0x11f0 xfs_buf_item_unpin+0x3d6/0x840 xfs_trans_committed_bulk+0x4c2/0x7c0 xlog_cil_committed+0xab6/0xfb0 xlog_cil_process_committed+0x117/0x1e0 xlog_state_shutdown_callbacks+0x208/0x440 xlog_force_shutdown+0x1b3/0x3a0 xlog_ioend_work+0xef/0x1d0 process_one_work+0x6f9/0xf70 worker_thread+0x578/0xf30 kthread+0x28c/0x330 ret_from_fork+0x1f/0x30 The buggy address belongs to the object at ffff88801800f388 which belongs to the cache xfs_buf_item of size 272 The buggy address is located 104 bytes inside of 272-byte region [ffff88801800f388, ffff88801800f498) The buggy address belongs to the physical page: page:ffffea0000600380 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88801800f208 pfn:0x1800e head:ffffea0000600380 order:1 compound_mapcount:0 compound_pincount:0 flags: 0x1fffff80010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) raw: 001fffff80010200 ffffea0000699788 ffff88801319db50 ffff88800fb50640 raw: ffff88801800f208 000000000015000a 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88801800f280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88801800f300: fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88801800f380: fc fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88801800f400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88801800f480: fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Disabling lock debugging due to kernel taint Signed-off-by: Guo Xuenan <guoxuenan@huawei.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
1048 lines
29 KiB
C
1048 lines
29 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
|
|
* All Rights Reserved.
|
|
*/
|
|
#include "xfs.h"
|
|
#include "xfs_fs.h"
|
|
#include "xfs_shared.h"
|
|
#include "xfs_format.h"
|
|
#include "xfs_log_format.h"
|
|
#include "xfs_trans_resv.h"
|
|
#include "xfs_bit.h"
|
|
#include "xfs_mount.h"
|
|
#include "xfs_trans.h"
|
|
#include "xfs_trans_priv.h"
|
|
#include "xfs_buf_item.h"
|
|
#include "xfs_inode.h"
|
|
#include "xfs_inode_item.h"
|
|
#include "xfs_quota.h"
|
|
#include "xfs_dquot_item.h"
|
|
#include "xfs_dquot.h"
|
|
#include "xfs_trace.h"
|
|
#include "xfs_log.h"
|
|
#include "xfs_log_priv.h"
|
|
|
|
|
|
struct kmem_cache *xfs_buf_item_cache;
|
|
|
|
static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
|
|
{
|
|
return container_of(lip, struct xfs_buf_log_item, bli_item);
|
|
}
|
|
|
|
/* Is this log iovec plausibly large enough to contain the buffer log format? */
|
|
bool
|
|
xfs_buf_log_check_iovec(
|
|
struct xfs_log_iovec *iovec)
|
|
{
|
|
struct xfs_buf_log_format *blfp = iovec->i_addr;
|
|
char *bmp_end;
|
|
char *item_end;
|
|
|
|
if (offsetof(struct xfs_buf_log_format, blf_data_map) > iovec->i_len)
|
|
return false;
|
|
|
|
item_end = (char *)iovec->i_addr + iovec->i_len;
|
|
bmp_end = (char *)&blfp->blf_data_map[blfp->blf_map_size];
|
|
return bmp_end <= item_end;
|
|
}
|
|
|
|
static inline int
|
|
xfs_buf_log_format_size(
|
|
struct xfs_buf_log_format *blfp)
|
|
{
|
|
return offsetof(struct xfs_buf_log_format, blf_data_map) +
|
|
(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
|
|
}
|
|
|
|
static inline bool
|
|
xfs_buf_item_straddle(
|
|
struct xfs_buf *bp,
|
|
uint offset,
|
|
int first_bit,
|
|
int nbits)
|
|
{
|
|
void *first, *last;
|
|
|
|
first = xfs_buf_offset(bp, offset + (first_bit << XFS_BLF_SHIFT));
|
|
last = xfs_buf_offset(bp,
|
|
offset + ((first_bit + nbits) << XFS_BLF_SHIFT));
|
|
|
|
if (last - first != nbits * XFS_BLF_CHUNK)
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* Return the number of log iovecs and space needed to log the given buf log
|
|
* item segment.
|
|
*
|
|
* It calculates this as 1 iovec for the buf log format structure and 1 for each
|
|
* stretch of non-contiguous chunks to be logged. Contiguous chunks are logged
|
|
* in a single iovec.
|
|
*/
|
|
STATIC void
|
|
xfs_buf_item_size_segment(
|
|
struct xfs_buf_log_item *bip,
|
|
struct xfs_buf_log_format *blfp,
|
|
uint offset,
|
|
int *nvecs,
|
|
int *nbytes)
|
|
{
|
|
struct xfs_buf *bp = bip->bli_buf;
|
|
int first_bit;
|
|
int nbits;
|
|
int next_bit;
|
|
int last_bit;
|
|
|
|
first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
|
|
if (first_bit == -1)
|
|
return;
|
|
|
|
(*nvecs)++;
|
|
*nbytes += xfs_buf_log_format_size(blfp);
|
|
|
|
do {
|
|
nbits = xfs_contig_bits(blfp->blf_data_map,
|
|
blfp->blf_map_size, first_bit);
|
|
ASSERT(nbits > 0);
|
|
|
|
/*
|
|
* Straddling a page is rare because we don't log contiguous
|
|
* chunks of unmapped buffers anywhere.
|
|
*/
|
|
if (nbits > 1 &&
|
|
xfs_buf_item_straddle(bp, offset, first_bit, nbits))
|
|
goto slow_scan;
|
|
|
|
(*nvecs)++;
|
|
*nbytes += nbits * XFS_BLF_CHUNK;
|
|
|
|
/*
|
|
* This takes the bit number to start looking from and
|
|
* returns the next set bit from there. It returns -1
|
|
* if there are no more bits set or the start bit is
|
|
* beyond the end of the bitmap.
|
|
*/
|
|
first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
|
|
(uint)first_bit + nbits + 1);
|
|
} while (first_bit != -1);
|
|
|
|
return;
|
|
|
|
slow_scan:
|
|
/* Count the first bit we jumped out of the above loop from */
|
|
(*nvecs)++;
|
|
*nbytes += XFS_BLF_CHUNK;
|
|
last_bit = first_bit;
|
|
while (last_bit != -1) {
|
|
/*
|
|
* This takes the bit number to start looking from and
|
|
* returns the next set bit from there. It returns -1
|
|
* if there are no more bits set or the start bit is
|
|
* beyond the end of the bitmap.
|
|
*/
|
|
next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
|
|
last_bit + 1);
|
|
/*
|
|
* If we run out of bits, leave the loop,
|
|
* else if we find a new set of bits bump the number of vecs,
|
|
* else keep scanning the current set of bits.
|
|
*/
|
|
if (next_bit == -1) {
|
|
break;
|
|
} else if (next_bit != last_bit + 1 ||
|
|
xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
|
|
last_bit = next_bit;
|
|
first_bit = next_bit;
|
|
(*nvecs)++;
|
|
nbits = 1;
|
|
} else {
|
|
last_bit++;
|
|
nbits++;
|
|
}
|
|
*nbytes += XFS_BLF_CHUNK;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Return the number of log iovecs and space needed to log the given buf log
|
|
* item.
|
|
*
|
|
* Discontiguous buffers need a format structure per region that is being
|
|
* logged. This makes the changes in the buffer appear to log recovery as though
|
|
* they came from separate buffers, just like would occur if multiple buffers
|
|
* were used instead of a single discontiguous buffer. This enables
|
|
* discontiguous buffers to be in-memory constructs, completely transparent to
|
|
* what ends up on disk.
|
|
*
|
|
* If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
|
|
* format structures. If the item has previously been logged and has dirty
|
|
* regions, we do not relog them in stale buffers. This has the effect of
|
|
* reducing the size of the relogged item by the amount of dirty data tracked
|
|
* by the log item. This can result in the committing transaction reducing the
|
|
* amount of space being consumed by the CIL.
|
|
*/
|
|
STATIC void
|
|
xfs_buf_item_size(
|
|
struct xfs_log_item *lip,
|
|
int *nvecs,
|
|
int *nbytes)
|
|
{
|
|
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
|
|
struct xfs_buf *bp = bip->bli_buf;
|
|
int i;
|
|
int bytes;
|
|
uint offset = 0;
|
|
|
|
ASSERT(atomic_read(&bip->bli_refcount) > 0);
|
|
if (bip->bli_flags & XFS_BLI_STALE) {
|
|
/*
|
|
* The buffer is stale, so all we need to log is the buf log
|
|
* format structure with the cancel flag in it as we are never
|
|
* going to replay the changes tracked in the log item.
|
|
*/
|
|
trace_xfs_buf_item_size_stale(bip);
|
|
ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
|
|
*nvecs += bip->bli_format_count;
|
|
for (i = 0; i < bip->bli_format_count; i++) {
|
|
*nbytes += xfs_buf_log_format_size(&bip->bli_formats[i]);
|
|
}
|
|
return;
|
|
}
|
|
|
|
ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
|
|
|
|
if (bip->bli_flags & XFS_BLI_ORDERED) {
|
|
/*
|
|
* The buffer has been logged just to order it. It is not being
|
|
* included in the transaction commit, so no vectors are used at
|
|
* all.
|
|
*/
|
|
trace_xfs_buf_item_size_ordered(bip);
|
|
*nvecs = XFS_LOG_VEC_ORDERED;
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* The vector count is based on the number of buffer vectors we have
|
|
* dirty bits in. This will only be greater than one when we have a
|
|
* compound buffer with more than one segment dirty. Hence for compound
|
|
* buffers we need to track which segment the dirty bits correspond to,
|
|
* and when we move from one segment to the next increment the vector
|
|
* count for the extra buf log format structure that will need to be
|
|
* written.
|
|
*/
|
|
bytes = 0;
|
|
for (i = 0; i < bip->bli_format_count; i++) {
|
|
xfs_buf_item_size_segment(bip, &bip->bli_formats[i], offset,
|
|
nvecs, &bytes);
|
|
offset += BBTOB(bp->b_maps[i].bm_len);
|
|
}
|
|
|
|
/*
|
|
* Round up the buffer size required to minimise the number of memory
|
|
* allocations that need to be done as this item grows when relogged by
|
|
* repeated modifications.
|
|
*/
|
|
*nbytes = round_up(bytes, 512);
|
|
trace_xfs_buf_item_size(bip);
|
|
}
|
|
|
|
static inline void
|
|
xfs_buf_item_copy_iovec(
|
|
struct xfs_log_vec *lv,
|
|
struct xfs_log_iovec **vecp,
|
|
struct xfs_buf *bp,
|
|
uint offset,
|
|
int first_bit,
|
|
uint nbits)
|
|
{
|
|
offset += first_bit * XFS_BLF_CHUNK;
|
|
xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_BCHUNK,
|
|
xfs_buf_offset(bp, offset),
|
|
nbits * XFS_BLF_CHUNK);
|
|
}
|
|
|
|
static void
|
|
xfs_buf_item_format_segment(
|
|
struct xfs_buf_log_item *bip,
|
|
struct xfs_log_vec *lv,
|
|
struct xfs_log_iovec **vecp,
|
|
uint offset,
|
|
struct xfs_buf_log_format *blfp)
|
|
{
|
|
struct xfs_buf *bp = bip->bli_buf;
|
|
uint base_size;
|
|
int first_bit;
|
|
int last_bit;
|
|
int next_bit;
|
|
uint nbits;
|
|
|
|
/* copy the flags across from the base format item */
|
|
blfp->blf_flags = bip->__bli_format.blf_flags;
|
|
|
|
/*
|
|
* Base size is the actual size of the ondisk structure - it reflects
|
|
* the actual size of the dirty bitmap rather than the size of the in
|
|
* memory structure.
|
|
*/
|
|
base_size = xfs_buf_log_format_size(blfp);
|
|
|
|
first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
|
|
if (!(bip->bli_flags & XFS_BLI_STALE) && first_bit == -1) {
|
|
/*
|
|
* If the map is not be dirty in the transaction, mark
|
|
* the size as zero and do not advance the vector pointer.
|
|
*/
|
|
return;
|
|
}
|
|
|
|
blfp = xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_BFORMAT, blfp, base_size);
|
|
blfp->blf_size = 1;
|
|
|
|
if (bip->bli_flags & XFS_BLI_STALE) {
|
|
/*
|
|
* The buffer is stale, so all we need to log
|
|
* is the buf log format structure with the
|
|
* cancel flag in it.
|
|
*/
|
|
trace_xfs_buf_item_format_stale(bip);
|
|
ASSERT(blfp->blf_flags & XFS_BLF_CANCEL);
|
|
return;
|
|
}
|
|
|
|
|
|
/*
|
|
* Fill in an iovec for each set of contiguous chunks.
|
|
*/
|
|
do {
|
|
ASSERT(first_bit >= 0);
|
|
nbits = xfs_contig_bits(blfp->blf_data_map,
|
|
blfp->blf_map_size, first_bit);
|
|
ASSERT(nbits > 0);
|
|
|
|
/*
|
|
* Straddling a page is rare because we don't log contiguous
|
|
* chunks of unmapped buffers anywhere.
|
|
*/
|
|
if (nbits > 1 &&
|
|
xfs_buf_item_straddle(bp, offset, first_bit, nbits))
|
|
goto slow_scan;
|
|
|
|
xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
|
|
first_bit, nbits);
|
|
blfp->blf_size++;
|
|
|
|
/*
|
|
* This takes the bit number to start looking from and
|
|
* returns the next set bit from there. It returns -1
|
|
* if there are no more bits set or the start bit is
|
|
* beyond the end of the bitmap.
|
|
*/
|
|
first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
|
|
(uint)first_bit + nbits + 1);
|
|
} while (first_bit != -1);
|
|
|
|
return;
|
|
|
|
slow_scan:
|
|
ASSERT(bp->b_addr == NULL);
|
|
last_bit = first_bit;
|
|
nbits = 1;
|
|
for (;;) {
|
|
/*
|
|
* This takes the bit number to start looking from and
|
|
* returns the next set bit from there. It returns -1
|
|
* if there are no more bits set or the start bit is
|
|
* beyond the end of the bitmap.
|
|
*/
|
|
next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
|
|
(uint)last_bit + 1);
|
|
/*
|
|
* If we run out of bits fill in the last iovec and get out of
|
|
* the loop. Else if we start a new set of bits then fill in
|
|
* the iovec for the series we were looking at and start
|
|
* counting the bits in the new one. Else we're still in the
|
|
* same set of bits so just keep counting and scanning.
|
|
*/
|
|
if (next_bit == -1) {
|
|
xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
|
|
first_bit, nbits);
|
|
blfp->blf_size++;
|
|
break;
|
|
} else if (next_bit != last_bit + 1 ||
|
|
xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
|
|
xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
|
|
first_bit, nbits);
|
|
blfp->blf_size++;
|
|
first_bit = next_bit;
|
|
last_bit = next_bit;
|
|
nbits = 1;
|
|
} else {
|
|
last_bit++;
|
|
nbits++;
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* This is called to fill in the vector of log iovecs for the
|
|
* given log buf item. It fills the first entry with a buf log
|
|
* format structure, and the rest point to contiguous chunks
|
|
* within the buffer.
|
|
*/
|
|
STATIC void
|
|
xfs_buf_item_format(
|
|
struct xfs_log_item *lip,
|
|
struct xfs_log_vec *lv)
|
|
{
|
|
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
|
|
struct xfs_buf *bp = bip->bli_buf;
|
|
struct xfs_log_iovec *vecp = NULL;
|
|
uint offset = 0;
|
|
int i;
|
|
|
|
ASSERT(atomic_read(&bip->bli_refcount) > 0);
|
|
ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
|
|
(bip->bli_flags & XFS_BLI_STALE));
|
|
ASSERT((bip->bli_flags & XFS_BLI_STALE) ||
|
|
(xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF
|
|
&& xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF));
|
|
ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED) ||
|
|
(bip->bli_flags & XFS_BLI_STALE));
|
|
|
|
|
|
/*
|
|
* If it is an inode buffer, transfer the in-memory state to the
|
|
* format flags and clear the in-memory state.
|
|
*
|
|
* For buffer based inode allocation, we do not transfer
|
|
* this state if the inode buffer allocation has not yet been committed
|
|
* to the log as setting the XFS_BLI_INODE_BUF flag will prevent
|
|
* correct replay of the inode allocation.
|
|
*
|
|
* For icreate item based inode allocation, the buffers aren't written
|
|
* to the journal during allocation, and hence we should always tag the
|
|
* buffer as an inode buffer so that the correct unlinked list replay
|
|
* occurs during recovery.
|
|
*/
|
|
if (bip->bli_flags & XFS_BLI_INODE_BUF) {
|
|
if (xfs_has_v3inodes(lip->li_log->l_mp) ||
|
|
!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
|
|
xfs_log_item_in_current_chkpt(lip)))
|
|
bip->__bli_format.blf_flags |= XFS_BLF_INODE_BUF;
|
|
bip->bli_flags &= ~XFS_BLI_INODE_BUF;
|
|
}
|
|
|
|
for (i = 0; i < bip->bli_format_count; i++) {
|
|
xfs_buf_item_format_segment(bip, lv, &vecp, offset,
|
|
&bip->bli_formats[i]);
|
|
offset += BBTOB(bp->b_maps[i].bm_len);
|
|
}
|
|
|
|
/*
|
|
* Check to make sure everything is consistent.
|
|
*/
|
|
trace_xfs_buf_item_format(bip);
|
|
}
|
|
|
|
/*
|
|
* This is called to pin the buffer associated with the buf log item in memory
|
|
* so it cannot be written out.
|
|
*
|
|
* We also always take a reference to the buffer log item here so that the bli
|
|
* is held while the item is pinned in memory. This means that we can
|
|
* unconditionally drop the reference count a transaction holds when the
|
|
* transaction is completed.
|
|
*/
|
|
STATIC void
|
|
xfs_buf_item_pin(
|
|
struct xfs_log_item *lip)
|
|
{
|
|
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
|
|
|
|
ASSERT(atomic_read(&bip->bli_refcount) > 0);
|
|
ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
|
|
(bip->bli_flags & XFS_BLI_ORDERED) ||
|
|
(bip->bli_flags & XFS_BLI_STALE));
|
|
|
|
trace_xfs_buf_item_pin(bip);
|
|
|
|
atomic_inc(&bip->bli_refcount);
|
|
atomic_inc(&bip->bli_buf->b_pin_count);
|
|
}
|
|
|
|
/*
|
|
* This is called to unpin the buffer associated with the buf log item which
|
|
* was previously pinned with a call to xfs_buf_item_pin().
|
|
*/
|
|
STATIC void
|
|
xfs_buf_item_unpin(
|
|
struct xfs_log_item *lip,
|
|
int remove)
|
|
{
|
|
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
|
|
struct xfs_buf *bp = bip->bli_buf;
|
|
int stale = bip->bli_flags & XFS_BLI_STALE;
|
|
int freed;
|
|
|
|
ASSERT(bp->b_log_item == bip);
|
|
ASSERT(atomic_read(&bip->bli_refcount) > 0);
|
|
|
|
trace_xfs_buf_item_unpin(bip);
|
|
|
|
/*
|
|
* Drop the bli ref associated with the pin and grab the hold required
|
|
* for the I/O simulation failure in the abort case. We have to do this
|
|
* before the pin count drops because the AIL doesn't acquire a bli
|
|
* reference. Therefore if the refcount drops to zero, the bli could
|
|
* still be AIL resident and the buffer submitted for I/O (and freed on
|
|
* completion) at any point before we return. This can be removed once
|
|
* the AIL properly holds a reference on the bli.
|
|
*/
|
|
freed = atomic_dec_and_test(&bip->bli_refcount);
|
|
if (freed && !stale && remove)
|
|
xfs_buf_hold(bp);
|
|
if (atomic_dec_and_test(&bp->b_pin_count))
|
|
wake_up_all(&bp->b_waiters);
|
|
|
|
/* nothing to do but drop the pin count if the bli is active */
|
|
if (!freed)
|
|
return;
|
|
|
|
if (stale) {
|
|
ASSERT(bip->bli_flags & XFS_BLI_STALE);
|
|
ASSERT(xfs_buf_islocked(bp));
|
|
ASSERT(bp->b_flags & XBF_STALE);
|
|
ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
|
|
ASSERT(list_empty(&lip->li_trans));
|
|
ASSERT(!bp->b_transp);
|
|
|
|
trace_xfs_buf_item_unpin_stale(bip);
|
|
|
|
/*
|
|
* If we get called here because of an IO error, we may or may
|
|
* not have the item on the AIL. xfs_trans_ail_delete() will
|
|
* take care of that situation. xfs_trans_ail_delete() drops
|
|
* the AIL lock.
|
|
*/
|
|
if (bip->bli_flags & XFS_BLI_STALE_INODE) {
|
|
xfs_buf_item_done(bp);
|
|
xfs_buf_inode_iodone(bp);
|
|
ASSERT(list_empty(&bp->b_li_list));
|
|
} else {
|
|
xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR);
|
|
xfs_buf_item_relse(bp);
|
|
ASSERT(bp->b_log_item == NULL);
|
|
}
|
|
xfs_buf_relse(bp);
|
|
} else if (remove) {
|
|
/*
|
|
* The buffer must be locked and held by the caller to simulate
|
|
* an async I/O failure. We acquired the hold for this case
|
|
* before the buffer was unpinned.
|
|
*/
|
|
xfs_buf_lock(bp);
|
|
bp->b_flags |= XBF_ASYNC;
|
|
xfs_buf_ioend_fail(bp);
|
|
}
|
|
}
|
|
|
|
STATIC uint
|
|
xfs_buf_item_push(
|
|
struct xfs_log_item *lip,
|
|
struct list_head *buffer_list)
|
|
{
|
|
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
|
|
struct xfs_buf *bp = bip->bli_buf;
|
|
uint rval = XFS_ITEM_SUCCESS;
|
|
|
|
if (xfs_buf_ispinned(bp))
|
|
return XFS_ITEM_PINNED;
|
|
if (!xfs_buf_trylock(bp)) {
|
|
/*
|
|
* If we have just raced with a buffer being pinned and it has
|
|
* been marked stale, we could end up stalling until someone else
|
|
* issues a log force to unpin the stale buffer. Check for the
|
|
* race condition here so xfsaild recognizes the buffer is pinned
|
|
* and queues a log force to move it along.
|
|
*/
|
|
if (xfs_buf_ispinned(bp))
|
|
return XFS_ITEM_PINNED;
|
|
return XFS_ITEM_LOCKED;
|
|
}
|
|
|
|
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
|
|
|
|
trace_xfs_buf_item_push(bip);
|
|
|
|
/* has a previous flush failed due to IO errors? */
|
|
if (bp->b_flags & XBF_WRITE_FAIL) {
|
|
xfs_buf_alert_ratelimited(bp, "XFS: Failing async write",
|
|
"Failing async write on buffer block 0x%llx. Retrying async write.",
|
|
(long long)xfs_buf_daddr(bp));
|
|
}
|
|
|
|
if (!xfs_buf_delwri_queue(bp, buffer_list))
|
|
rval = XFS_ITEM_FLUSHING;
|
|
xfs_buf_unlock(bp);
|
|
return rval;
|
|
}
|
|
|
|
/*
|
|
* Drop the buffer log item refcount and take appropriate action. This helper
|
|
* determines whether the bli must be freed or not, since a decrement to zero
|
|
* does not necessarily mean the bli is unused.
|
|
*
|
|
* Return true if the bli is freed, false otherwise.
|
|
*/
|
|
bool
|
|
xfs_buf_item_put(
|
|
struct xfs_buf_log_item *bip)
|
|
{
|
|
struct xfs_log_item *lip = &bip->bli_item;
|
|
bool aborted;
|
|
bool dirty;
|
|
|
|
/* drop the bli ref and return if it wasn't the last one */
|
|
if (!atomic_dec_and_test(&bip->bli_refcount))
|
|
return false;
|
|
|
|
/*
|
|
* We dropped the last ref and must free the item if clean or aborted.
|
|
* If the bli is dirty and non-aborted, the buffer was clean in the
|
|
* transaction but still awaiting writeback from previous changes. In
|
|
* that case, the bli is freed on buffer writeback completion.
|
|
*/
|
|
aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags) ||
|
|
xlog_is_shutdown(lip->li_log);
|
|
dirty = bip->bli_flags & XFS_BLI_DIRTY;
|
|
if (dirty && !aborted)
|
|
return false;
|
|
|
|
/*
|
|
* The bli is aborted or clean. An aborted item may be in the AIL
|
|
* regardless of dirty state. For example, consider an aborted
|
|
* transaction that invalidated a dirty bli and cleared the dirty
|
|
* state.
|
|
*/
|
|
if (aborted)
|
|
xfs_trans_ail_delete(lip, 0);
|
|
xfs_buf_item_relse(bip->bli_buf);
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* Release the buffer associated with the buf log item. If there is no dirty
|
|
* logged data associated with the buffer recorded in the buf log item, then
|
|
* free the buf log item and remove the reference to it in the buffer.
|
|
*
|
|
* This call ignores the recursion count. It is only called when the buffer
|
|
* should REALLY be unlocked, regardless of the recursion count.
|
|
*
|
|
* We unconditionally drop the transaction's reference to the log item. If the
|
|
* item was logged, then another reference was taken when it was pinned, so we
|
|
* can safely drop the transaction reference now. This also allows us to avoid
|
|
* potential races with the unpin code freeing the bli by not referencing the
|
|
* bli after we've dropped the reference count.
|
|
*
|
|
* If the XFS_BLI_HOLD flag is set in the buf log item, then free the log item
|
|
* if necessary but do not unlock the buffer. This is for support of
|
|
* xfs_trans_bhold(). Make sure the XFS_BLI_HOLD field is cleared if we don't
|
|
* free the item.
|
|
*/
|
|
STATIC void
|
|
xfs_buf_item_release(
|
|
struct xfs_log_item *lip)
|
|
{
|
|
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
|
|
struct xfs_buf *bp = bip->bli_buf;
|
|
bool released;
|
|
bool hold = bip->bli_flags & XFS_BLI_HOLD;
|
|
bool stale = bip->bli_flags & XFS_BLI_STALE;
|
|
#if defined(DEBUG) || defined(XFS_WARN)
|
|
bool ordered = bip->bli_flags & XFS_BLI_ORDERED;
|
|
bool dirty = bip->bli_flags & XFS_BLI_DIRTY;
|
|
bool aborted = test_bit(XFS_LI_ABORTED,
|
|
&lip->li_flags);
|
|
#endif
|
|
|
|
trace_xfs_buf_item_release(bip);
|
|
|
|
/*
|
|
* The bli dirty state should match whether the blf has logged segments
|
|
* except for ordered buffers, where only the bli should be dirty.
|
|
*/
|
|
ASSERT((!ordered && dirty == xfs_buf_item_dirty_format(bip)) ||
|
|
(ordered && dirty && !xfs_buf_item_dirty_format(bip)));
|
|
ASSERT(!stale || (bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
|
|
|
|
/*
|
|
* Clear the buffer's association with this transaction and
|
|
* per-transaction state from the bli, which has been copied above.
|
|
*/
|
|
bp->b_transp = NULL;
|
|
bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
|
|
|
|
/*
|
|
* Unref the item and unlock the buffer unless held or stale. Stale
|
|
* buffers remain locked until final unpin unless the bli is freed by
|
|
* the unref call. The latter implies shutdown because buffer
|
|
* invalidation dirties the bli and transaction.
|
|
*/
|
|
released = xfs_buf_item_put(bip);
|
|
if (hold || (stale && !released))
|
|
return;
|
|
ASSERT(!stale || aborted);
|
|
xfs_buf_relse(bp);
|
|
}
|
|
|
|
STATIC void
|
|
xfs_buf_item_committing(
|
|
struct xfs_log_item *lip,
|
|
xfs_csn_t seq)
|
|
{
|
|
return xfs_buf_item_release(lip);
|
|
}
|
|
|
|
/*
|
|
* This is called to find out where the oldest active copy of the
|
|
* buf log item in the on disk log resides now that the last log
|
|
* write of it completed at the given lsn.
|
|
* We always re-log all the dirty data in a buffer, so usually the
|
|
* latest copy in the on disk log is the only one that matters. For
|
|
* those cases we simply return the given lsn.
|
|
*
|
|
* The one exception to this is for buffers full of newly allocated
|
|
* inodes. These buffers are only relogged with the XFS_BLI_INODE_BUF
|
|
* flag set, indicating that only the di_next_unlinked fields from the
|
|
* inodes in the buffers will be replayed during recovery. If the
|
|
* original newly allocated inode images have not yet been flushed
|
|
* when the buffer is so relogged, then we need to make sure that we
|
|
* keep the old images in the 'active' portion of the log. We do this
|
|
* by returning the original lsn of that transaction here rather than
|
|
* the current one.
|
|
*/
|
|
STATIC xfs_lsn_t
|
|
xfs_buf_item_committed(
|
|
struct xfs_log_item *lip,
|
|
xfs_lsn_t lsn)
|
|
{
|
|
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
|
|
|
|
trace_xfs_buf_item_committed(bip);
|
|
|
|
if ((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) && lip->li_lsn != 0)
|
|
return lip->li_lsn;
|
|
return lsn;
|
|
}
|
|
|
|
static const struct xfs_item_ops xfs_buf_item_ops = {
|
|
.iop_size = xfs_buf_item_size,
|
|
.iop_format = xfs_buf_item_format,
|
|
.iop_pin = xfs_buf_item_pin,
|
|
.iop_unpin = xfs_buf_item_unpin,
|
|
.iop_release = xfs_buf_item_release,
|
|
.iop_committing = xfs_buf_item_committing,
|
|
.iop_committed = xfs_buf_item_committed,
|
|
.iop_push = xfs_buf_item_push,
|
|
};
|
|
|
|
STATIC void
|
|
xfs_buf_item_get_format(
|
|
struct xfs_buf_log_item *bip,
|
|
int count)
|
|
{
|
|
ASSERT(bip->bli_formats == NULL);
|
|
bip->bli_format_count = count;
|
|
|
|
if (count == 1) {
|
|
bip->bli_formats = &bip->__bli_format;
|
|
return;
|
|
}
|
|
|
|
bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
|
|
0);
|
|
}
|
|
|
|
STATIC void
|
|
xfs_buf_item_free_format(
|
|
struct xfs_buf_log_item *bip)
|
|
{
|
|
if (bip->bli_formats != &bip->__bli_format) {
|
|
kmem_free(bip->bli_formats);
|
|
bip->bli_formats = NULL;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Allocate a new buf log item to go with the given buffer.
|
|
* Set the buffer's b_log_item field to point to the new
|
|
* buf log item.
|
|
*/
|
|
int
|
|
xfs_buf_item_init(
|
|
struct xfs_buf *bp,
|
|
struct xfs_mount *mp)
|
|
{
|
|
struct xfs_buf_log_item *bip = bp->b_log_item;
|
|
int chunks;
|
|
int map_size;
|
|
int i;
|
|
|
|
/*
|
|
* Check to see if there is already a buf log item for
|
|
* this buffer. If we do already have one, there is
|
|
* nothing to do here so return.
|
|
*/
|
|
ASSERT(bp->b_mount == mp);
|
|
if (bip) {
|
|
ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
|
|
ASSERT(!bp->b_transp);
|
|
ASSERT(bip->bli_buf == bp);
|
|
return 0;
|
|
}
|
|
|
|
bip = kmem_cache_zalloc(xfs_buf_item_cache, GFP_KERNEL | __GFP_NOFAIL);
|
|
xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
|
|
bip->bli_buf = bp;
|
|
|
|
/*
|
|
* chunks is the number of XFS_BLF_CHUNK size pieces the buffer
|
|
* can be divided into. Make sure not to truncate any pieces.
|
|
* map_size is the size of the bitmap needed to describe the
|
|
* chunks of the buffer.
|
|
*
|
|
* Discontiguous buffer support follows the layout of the underlying
|
|
* buffer. This makes the implementation as simple as possible.
|
|
*/
|
|
xfs_buf_item_get_format(bip, bp->b_map_count);
|
|
|
|
for (i = 0; i < bip->bli_format_count; i++) {
|
|
chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
|
|
XFS_BLF_CHUNK);
|
|
map_size = DIV_ROUND_UP(chunks, NBWORD);
|
|
|
|
if (map_size > XFS_BLF_DATAMAP_SIZE) {
|
|
kmem_cache_free(xfs_buf_item_cache, bip);
|
|
xfs_err(mp,
|
|
"buffer item dirty bitmap (%u uints) too small to reflect %u bytes!",
|
|
map_size,
|
|
BBTOB(bp->b_maps[i].bm_len));
|
|
return -EFSCORRUPTED;
|
|
}
|
|
|
|
bip->bli_formats[i].blf_type = XFS_LI_BUF;
|
|
bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
|
|
bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
|
|
bip->bli_formats[i].blf_map_size = map_size;
|
|
}
|
|
|
|
bp->b_log_item = bip;
|
|
xfs_buf_hold(bp);
|
|
return 0;
|
|
}
|
|
|
|
|
|
/*
|
|
* Mark bytes first through last inclusive as dirty in the buf
|
|
* item's bitmap.
|
|
*/
|
|
static void
|
|
xfs_buf_item_log_segment(
|
|
uint first,
|
|
uint last,
|
|
uint *map)
|
|
{
|
|
uint first_bit;
|
|
uint last_bit;
|
|
uint bits_to_set;
|
|
uint bits_set;
|
|
uint word_num;
|
|
uint *wordp;
|
|
uint bit;
|
|
uint end_bit;
|
|
uint mask;
|
|
|
|
ASSERT(first < XFS_BLF_DATAMAP_SIZE * XFS_BLF_CHUNK * NBWORD);
|
|
ASSERT(last < XFS_BLF_DATAMAP_SIZE * XFS_BLF_CHUNK * NBWORD);
|
|
|
|
/*
|
|
* Convert byte offsets to bit numbers.
|
|
*/
|
|
first_bit = first >> XFS_BLF_SHIFT;
|
|
last_bit = last >> XFS_BLF_SHIFT;
|
|
|
|
/*
|
|
* Calculate the total number of bits to be set.
|
|
*/
|
|
bits_to_set = last_bit - first_bit + 1;
|
|
|
|
/*
|
|
* Get a pointer to the first word in the bitmap
|
|
* to set a bit in.
|
|
*/
|
|
word_num = first_bit >> BIT_TO_WORD_SHIFT;
|
|
wordp = &map[word_num];
|
|
|
|
/*
|
|
* Calculate the starting bit in the first word.
|
|
*/
|
|
bit = first_bit & (uint)(NBWORD - 1);
|
|
|
|
/*
|
|
* First set any bits in the first word of our range.
|
|
* If it starts at bit 0 of the word, it will be
|
|
* set below rather than here. That is what the variable
|
|
* bit tells us. The variable bits_set tracks the number
|
|
* of bits that have been set so far. End_bit is the number
|
|
* of the last bit to be set in this word plus one.
|
|
*/
|
|
if (bit) {
|
|
end_bit = min(bit + bits_to_set, (uint)NBWORD);
|
|
mask = ((1U << (end_bit - bit)) - 1) << bit;
|
|
*wordp |= mask;
|
|
wordp++;
|
|
bits_set = end_bit - bit;
|
|
} else {
|
|
bits_set = 0;
|
|
}
|
|
|
|
/*
|
|
* Now set bits a whole word at a time that are between
|
|
* first_bit and last_bit.
|
|
*/
|
|
while ((bits_to_set - bits_set) >= NBWORD) {
|
|
*wordp = 0xffffffff;
|
|
bits_set += NBWORD;
|
|
wordp++;
|
|
}
|
|
|
|
/*
|
|
* Finally, set any bits left to be set in one last partial word.
|
|
*/
|
|
end_bit = bits_to_set - bits_set;
|
|
if (end_bit) {
|
|
mask = (1U << end_bit) - 1;
|
|
*wordp |= mask;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Mark bytes first through last inclusive as dirty in the buf
|
|
* item's bitmap.
|
|
*/
|
|
void
|
|
xfs_buf_item_log(
|
|
struct xfs_buf_log_item *bip,
|
|
uint first,
|
|
uint last)
|
|
{
|
|
int i;
|
|
uint start;
|
|
uint end;
|
|
struct xfs_buf *bp = bip->bli_buf;
|
|
|
|
/*
|
|
* walk each buffer segment and mark them dirty appropriately.
|
|
*/
|
|
start = 0;
|
|
for (i = 0; i < bip->bli_format_count; i++) {
|
|
if (start > last)
|
|
break;
|
|
end = start + BBTOB(bp->b_maps[i].bm_len) - 1;
|
|
|
|
/* skip to the map that includes the first byte to log */
|
|
if (first > end) {
|
|
start += BBTOB(bp->b_maps[i].bm_len);
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* Trim the range to this segment and mark it in the bitmap.
|
|
* Note that we must convert buffer offsets to segment relative
|
|
* offsets (e.g., the first byte of each segment is byte 0 of
|
|
* that segment).
|
|
*/
|
|
if (first < start)
|
|
first = start;
|
|
if (end > last)
|
|
end = last;
|
|
xfs_buf_item_log_segment(first - start, end - start,
|
|
&bip->bli_formats[i].blf_data_map[0]);
|
|
|
|
start += BBTOB(bp->b_maps[i].bm_len);
|
|
}
|
|
}
|
|
|
|
|
|
/*
|
|
* Return true if the buffer has any ranges logged/dirtied by a transaction,
|
|
* false otherwise.
|
|
*/
|
|
bool
|
|
xfs_buf_item_dirty_format(
|
|
struct xfs_buf_log_item *bip)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < bip->bli_format_count; i++) {
|
|
if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
|
|
bip->bli_formats[i].blf_map_size))
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
STATIC void
|
|
xfs_buf_item_free(
|
|
struct xfs_buf_log_item *bip)
|
|
{
|
|
xfs_buf_item_free_format(bip);
|
|
kmem_free(bip->bli_item.li_lv_shadow);
|
|
kmem_cache_free(xfs_buf_item_cache, bip);
|
|
}
|
|
|
|
/*
|
|
* xfs_buf_item_relse() is called when the buf log item is no longer needed.
|
|
*/
|
|
void
|
|
xfs_buf_item_relse(
|
|
struct xfs_buf *bp)
|
|
{
|
|
struct xfs_buf_log_item *bip = bp->b_log_item;
|
|
|
|
trace_xfs_buf_item_relse(bp, _RET_IP_);
|
|
ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
|
|
|
|
if (atomic_read(&bip->bli_refcount))
|
|
return;
|
|
bp->b_log_item = NULL;
|
|
xfs_buf_rele(bp);
|
|
xfs_buf_item_free(bip);
|
|
}
|
|
|
|
void
|
|
xfs_buf_item_done(
|
|
struct xfs_buf *bp)
|
|
{
|
|
/*
|
|
* If we are forcibly shutting down, this may well be off the AIL
|
|
* already. That's because we simulate the log-committed callbacks to
|
|
* unpin these buffers. Or we may never have put this item on AIL
|
|
* because of the transaction was aborted forcibly.
|
|
* xfs_trans_ail_delete() takes care of these.
|
|
*
|
|
* Either way, AIL is useless if we're forcing a shutdown.
|
|
*
|
|
* Note that log recovery writes might have buffer items that are not on
|
|
* the AIL even when the file system is not shut down.
|
|
*/
|
|
xfs_trans_ail_delete(&bp->b_log_item->bli_item,
|
|
(bp->b_flags & _XBF_LOGRECOVERY) ? 0 :
|
|
SHUTDOWN_CORRUPT_INCORE);
|
|
xfs_buf_item_relse(bp);
|
|
}
|