Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-09-20 23:13:00 +00:00
Code Issues Packages Projects Releases Wiki Activity
97e993830a
linux/fs/xfs/xfs_rmap_item.c
Darrick J. Wong 3c919b0910 xfs: reserve less log space when recovering log intent items 
Wengang Wang reports that a customer's system was running a number of
truncate operations on a filesystem with a very small log.  Contention
on the reserve heads lead to other threads stalling on smaller updates
(e.g.  mtime updates) long enough to result in the node being rebooted
on account of the lack of responsivenes.  The node failed to recover
because log recovery of an EFI became stuck waiting for a grant of
reserve space.  From Wengang's report:

"For the file deletion, log bytes are reserved basing on
xfs_mount->tr_itruncate which is:

    tr_logres = 175488,
    tr_logcount = 2,
    tr_logflags = XFS_TRANS_PERM_LOG_RES,

"You see it's a permanent log reservation with two log operations (two
transactions in rolling mode).  After calculation (xlog_calc_unit_res()
adds space for various log headers), the final log space needed per
transaction changes from  175488 to 180208 bytes.  So the total log
space needed is 360416 bytes (180208 * 2).  [That quantity] of log space
(360416 bytes) needs to be reserved for both run time inode removing
(xfs_inactive_truncate()) and EFI recover (xfs_efi_item_recover())."

In other words, runtime pre-reserves 360K of space in anticipation of
running a chain of two transactions in which each transaction gets a
180K reservation.

Now that we've allocated the transaction, we delete the bmap mapping,
log an EFI to free the space, and roll the transaction as part of
finishing the deferops chain.  Rolling creates a new xfs_trans which
shares its ticket with the old transaction.  Next, xfs_trans_roll calls
__xfs_trans_commit with regrant == true, which calls xlog_cil_commit
with the same regrant parameter.

xlog_cil_commit calls xfs_log_ticket_regrant, which decrements t_cnt and
subtracts t_curr_res from the reservation and write heads.

If the filesystem is fresh and the first transaction only used (say)
20K, then t_curr_res will be 160K, and we give that much reservation
back to the reservation head.  Or if the file is really fragmented and
the first transaction actually uses 170K, then t_curr_res will be 10K,
and that's what we give back to the reservation.

Having done that, we're now headed into the second transaction with an
EFI and 180K of reservation.  Other threads apparently consumed all the
reservation for smaller transactions, such as timestamp updates.

Now let's say the first transaction gets written to disk and we crash
without ever completing the second transaction.  Now we remount the fs,
log recovery finds the unfinished EFI, and calls xfs_efi_recover to
finish the EFI.  However, xfs_efi_recover starts a new tr_itruncate
tranasction, which asks for 360K log reservation.  This is a lot more
than the 180K that we had reserved at the time of the crash.  If the
first EFI to be recovered is also pinning the tail of the log, we will
be unable to free any space in the log, and recovery livelocks.

Wengang confirmed this:

"Now we have the second transaction which has 180208 log bytes reserved
too. The second transaction is supposed to process intents including
extent freeing.  With my hacking patch, I blocked the extent freeing 5
hours. So in that 5 hours, 180208 (NOT 360416) log bytes are reserved.

"With my test case, other transactions (update timestamps) then happen.
As my hacking patch pins the journal tail, those timestamp-updating
transactions finally use up (almost) all the left available log space
(in memory in on disk).  And finally the on disk (and in memory)
available log space goes down near to 180208 bytes.  Those 180208 bytes
are reserved by [the] second (extent-free) transaction [in the chain]."

Wengang and I noticed that EFI recovery starts a transaction, completes
one step of the chain, and commits the transaction without completing
any other steps of the chain.  Those subsequent steps are completed by
xlog_finish_defer_ops, which allocates yet another transaction to
finish the rest of the chain.  That transaction gets the same tr_logres
as the head transaction, but with tr_logcount = 1 to force regranting
with every roll to avoid livelocks.

In other words, we already figured this out in commit 929b92f640
("xfs: xfs_defer_capture should absorb remaining transaction
reservation"), but should have applied that logic to each intent item's
recovery function.  For Wengang's case, the xfs_trans_alloc call in the
EFI recovery function should only be asking for a single transaction's
worth of log reservation -- 180K, not 360K.

Quoting Wengang again:

"With log recovery, during EFI recovery, we use tr_itruncate again to
reserve two transactions that needs 360416 log bytes.  Reserving 360416
bytes fails [stalls] because we now only have about 180208 available.

"Actually during the EFI recover, we only need one transaction to free
the extents just like the 2nd transaction at RUNTIME.  So it only needs
to reserve 180208 rather than 360416 bytes.  We have (a bit) more than
180208 available log bytes on disk, so [if we decrease the reservation
to 180K] the reservation goes and the recovery [finishes].  That is to
say: we can fix the log recover part to fix the issue. We can introduce
a new xfs_trans_res xfs_mount->tr_ext_free

{
  tr_logres = 175488,
  tr_logcount = 0,
  tr_logflags = 0,
}

"and use tr_ext_free instead of tr_itruncate in EFI recover."

However, I don't think it quite makes sense to create an entirely new
transaction reservation type to handle single-stepping during log
recovery.  Instead, we should copy the transaction reservation
information in the xfs_mount, change tr_logcount to 1, and pass that
into xfs_trans_alloc.  We know this won't risk changing the min log size
computation since we always ask for a fraction of the reservation for
all known transaction types.

This looks like it's been lurking in the codebase since commit
3d3c8b5222, which changed the xfs_trans_reserve call in
xlog_recover_process_efi to use the tr_logcount in tr_itruncate.
That changed the EFI recovery transaction from making a
non-XFS_TRANS_PERM_LOG_RES request for one transaction's worth of log
space to a XFS_TRANS_PERM_LOG_RES request for two transactions worth.

Fixes: 3d3c8b5222 ("xfs: refactor xfs_trans_reserve() interface")
Complements: 929b92f640 ("xfs: xfs_defer_capture should absorb remaining transaction reservation")
Suggested-by: Wengang Wang <wen.gang.wang@oracle.com>
Cc: Srikanth C S <srikanth.c.s@oracle.com>
[djwong: apply the same transformation to all log intent recovery]
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
2023-09-12 10:31:07 -07:00

750 lines
20 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0+
/*
* Copyright (C) 2016 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <darrick.wong@oracle.com>
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_shared.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_rmap_item.h"
#include "xfs_log.h"
#include "xfs_rmap.h"
#include "xfs_error.h"
#include "xfs_log_priv.h"
#include "xfs_log_recover.h"
#include "xfs_ag.h"
struct kmem_cache *xfs_rui_cache;
struct kmem_cache *xfs_rud_cache;
static const struct xfs_item_ops xfs_rui_item_ops;
static inline struct xfs_rui_log_item *RUI_ITEM(struct xfs_log_item *lip)
{
return container_of(lip, struct xfs_rui_log_item, rui_item);
}
STATIC void
xfs_rui_item_free(
struct xfs_rui_log_item *ruip)
{
kmem_free(ruip->rui_item.li_lv_shadow);
if (ruip->rui_format.rui_nextents > XFS_RUI_MAX_FAST_EXTENTS)
kmem_free(ruip);
else
kmem_cache_free(xfs_rui_cache, ruip);
}
/*
* Freeing the RUI requires that we remove it from the AIL if it has already
* been placed there. However, the RUI may not yet have been placed in the AIL
* when called by xfs_rui_release() from RUD processing due to the ordering of
* committed vs unpin operations in bulk insert operations. Hence the reference
* count to ensure only the last caller frees the RUI.
*/
STATIC void
xfs_rui_release(
struct xfs_rui_log_item *ruip)
{
ASSERT(atomic_read(&ruip->rui_refcount) > 0);
if (!atomic_dec_and_test(&ruip->rui_refcount))
return;
xfs_trans_ail_delete(&ruip->rui_item, 0);
xfs_rui_item_free(ruip);
}
STATIC void
xfs_rui_item_size(
struct xfs_log_item *lip,
int *nvecs,
int *nbytes)
{
struct xfs_rui_log_item *ruip = RUI_ITEM(lip);
*nvecs += 1;
*nbytes += xfs_rui_log_format_sizeof(ruip->rui_format.rui_nextents);
}
/*
* This is called to fill in the vector of log iovecs for the
* given rui log item. We use only 1 iovec, and we point that
* at the rui_log_format structure embedded in the rui item.
* It is at this point that we assert that all of the extent
* slots in the rui item have been filled.
*/
STATIC void
xfs_rui_item_format(
struct xfs_log_item *lip,
struct xfs_log_vec *lv)
{
struct xfs_rui_log_item *ruip = RUI_ITEM(lip);
struct xfs_log_iovec *vecp = NULL;
ASSERT(atomic_read(&ruip->rui_next_extent) ==
ruip->rui_format.rui_nextents);
ruip->rui_format.rui_type = XFS_LI_RUI;
ruip->rui_format.rui_size = 1;
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUI_FORMAT, &ruip->rui_format,
xfs_rui_log_format_sizeof(ruip->rui_format.rui_nextents));
}
/*
* The unpin operation is the last place an RUI is manipulated in the log. It is
* either inserted in the AIL or aborted in the event of a log I/O error. In
* either case, the RUI transaction has been successfully committed to make it
* this far. Therefore, we expect whoever committed the RUI to either construct
* and commit the RUD or drop the RUD's reference in the event of error. Simply
* drop the log's RUI reference now that the log is done with it.
*/
STATIC void
xfs_rui_item_unpin(
struct xfs_log_item *lip,
int remove)
{
struct xfs_rui_log_item *ruip = RUI_ITEM(lip);
xfs_rui_release(ruip);
}
/*
* The RUI has been either committed or aborted if the transaction has been
* cancelled. If the transaction was cancelled, an RUD isn't going to be
* constructed and thus we free the RUI here directly.
*/
STATIC void
xfs_rui_item_release(
struct xfs_log_item *lip)
{
xfs_rui_release(RUI_ITEM(lip));
}
/*
* Allocate and initialize an rui item with the given number of extents.
*/
STATIC struct xfs_rui_log_item *
xfs_rui_init(
struct xfs_mount *mp,
uint nextents)
{
struct xfs_rui_log_item *ruip;
ASSERT(nextents > 0);
if (nextents > XFS_RUI_MAX_FAST_EXTENTS)
ruip = kmem_zalloc(xfs_rui_log_item_sizeof(nextents), 0);
else
ruip = kmem_cache_zalloc(xfs_rui_cache,
GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops);
ruip->rui_format.rui_nextents = nextents;
ruip->rui_format.rui_id = (uintptr_t)(void *)ruip;
atomic_set(&ruip->rui_next_extent, 0);
atomic_set(&ruip->rui_refcount, 2);
return ruip;
}
static inline struct xfs_rud_log_item *RUD_ITEM(struct xfs_log_item *lip)
{
return container_of(lip, struct xfs_rud_log_item, rud_item);
}
STATIC void
xfs_rud_item_size(
struct xfs_log_item *lip,
int *nvecs,
int *nbytes)
{
*nvecs += 1;
*nbytes += sizeof(struct xfs_rud_log_format);
}
/*
* This is called to fill in the vector of log iovecs for the
* given rud log item. We use only 1 iovec, and we point that
* at the rud_log_format structure embedded in the rud item.
* It is at this point that we assert that all of the extent
* slots in the rud item have been filled.
*/
STATIC void
xfs_rud_item_format(
struct xfs_log_item *lip,
struct xfs_log_vec *lv)
{
struct xfs_rud_log_item *rudp = RUD_ITEM(lip);
struct xfs_log_iovec *vecp = NULL;
rudp->rud_format.rud_type = XFS_LI_RUD;
rudp->rud_format.rud_size = 1;
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUD_FORMAT, &rudp->rud_format,
sizeof(struct xfs_rud_log_format));
}
/*
* The RUD is either committed or aborted if the transaction is cancelled. If
* the transaction is cancelled, drop our reference to the RUI and free the
* RUD.
*/
STATIC void
xfs_rud_item_release(
struct xfs_log_item *lip)
{
struct xfs_rud_log_item *rudp = RUD_ITEM(lip);
xfs_rui_release(rudp->rud_ruip);
kmem_free(rudp->rud_item.li_lv_shadow);
kmem_cache_free(xfs_rud_cache, rudp);
}
static struct xfs_log_item *
xfs_rud_item_intent(
struct xfs_log_item *lip)
{
return &RUD_ITEM(lip)->rud_ruip->rui_item;
}
static const struct xfs_item_ops xfs_rud_item_ops = {
.flags = XFS_ITEM_RELEASE_WHEN_COMMITTED |
XFS_ITEM_INTENT_DONE,
.iop_size = xfs_rud_item_size,
.iop_format = xfs_rud_item_format,
.iop_release = xfs_rud_item_release,
.iop_intent = xfs_rud_item_intent,
};
static struct xfs_rud_log_item *
xfs_trans_get_rud(
struct xfs_trans *tp,
struct xfs_rui_log_item *ruip)
{
struct xfs_rud_log_item *rudp;
rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
&xfs_rud_item_ops);
rudp->rud_ruip = ruip;
rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id;
xfs_trans_add_item(tp, &rudp->rud_item);
return rudp;
}
/* Set the map extent flags for this reverse mapping. */
static void
xfs_trans_set_rmap_flags(
struct xfs_map_extent *map,
enum xfs_rmap_intent_type type,
int whichfork,
xfs_exntst_t state)
{
map->me_flags = 0;
if (state == XFS_EXT_UNWRITTEN)
map->me_flags |= XFS_RMAP_EXTENT_UNWRITTEN;
if (whichfork == XFS_ATTR_FORK)
map->me_flags |= XFS_RMAP_EXTENT_ATTR_FORK;
switch (type) {
case XFS_RMAP_MAP:
map->me_flags |= XFS_RMAP_EXTENT_MAP;
break;
case XFS_RMAP_MAP_SHARED:
map->me_flags |= XFS_RMAP_EXTENT_MAP_SHARED;
break;
case XFS_RMAP_UNMAP:
map->me_flags |= XFS_RMAP_EXTENT_UNMAP;
break;
case XFS_RMAP_UNMAP_SHARED:
map->me_flags |= XFS_RMAP_EXTENT_UNMAP_SHARED;
break;
case XFS_RMAP_CONVERT:
map->me_flags |= XFS_RMAP_EXTENT_CONVERT;
break;
case XFS_RMAP_CONVERT_SHARED:
map->me_flags |= XFS_RMAP_EXTENT_CONVERT_SHARED;
break;
case XFS_RMAP_ALLOC:
map->me_flags |= XFS_RMAP_EXTENT_ALLOC;
break;
case XFS_RMAP_FREE:
map->me_flags |= XFS_RMAP_EXTENT_FREE;
break;
default:
ASSERT(0);
}
}
/*
* Finish an rmap update and log it to the RUD. Note that the transaction is
* marked dirty regardless of whether the rmap update succeeds or fails to
* support the RUI/RUD lifecycle rules.
*/
static int
xfs_trans_log_finish_rmap_update(
struct xfs_trans *tp,
struct xfs_rud_log_item *rudp,
struct xfs_rmap_intent *ri,
struct xfs_btree_cur **pcur)
{
int error;
error = xfs_rmap_finish_one(tp, ri, pcur);
/*
* Mark the transaction dirty, even on error. This ensures the
* transaction is aborted, which:
*
* 1.) releases the RUI and frees the RUD
* 2.) shuts down the filesystem
*/
tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
return error;
}
/* Sort rmap intents by AG. */
static int
xfs_rmap_update_diff_items(
void *priv,
const struct list_head *a,
const struct list_head *b)
{
struct xfs_rmap_intent *ra;
struct xfs_rmap_intent *rb;
ra = container_of(a, struct xfs_rmap_intent, ri_list);
rb = container_of(b, struct xfs_rmap_intent, ri_list);
return ra->ri_pag->pag_agno - rb->ri_pag->pag_agno;
}
/* Log rmap updates in the intent item. */
STATIC void
xfs_rmap_update_log_item(
struct xfs_trans *tp,
struct xfs_rui_log_item *ruip,
struct xfs_rmap_intent *ri)
{
uint next_extent;
struct xfs_map_extent *map;
tp->t_flags |= XFS_TRANS_DIRTY;
set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
/*
* atomic_inc_return gives us the value after the increment;
* we want to use it as an array index so we need to subtract 1 from
* it.
*/
next_extent = atomic_inc_return(&ruip->rui_next_extent) - 1;
ASSERT(next_extent < ruip->rui_format.rui_nextents);
map = &ruip->rui_format.rui_extents[next_extent];
map->me_owner = ri->ri_owner;
map->me_startblock = ri->ri_bmap.br_startblock;
map->me_startoff = ri->ri_bmap.br_startoff;
map->me_len = ri->ri_bmap.br_blockcount;
xfs_trans_set_rmap_flags(map, ri->ri_type, ri->ri_whichfork,
ri->ri_bmap.br_state);
}
static struct xfs_log_item *
xfs_rmap_update_create_intent(
struct xfs_trans *tp,
struct list_head *items,
unsigned int count,
bool sort)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_rui_log_item *ruip = xfs_rui_init(mp, count);
struct xfs_rmap_intent *ri;
ASSERT(count > 0);
xfs_trans_add_item(tp, &ruip->rui_item);
if (sort)
list_sort(mp, items, xfs_rmap_update_diff_items);
list_for_each_entry(ri, items, ri_list)
xfs_rmap_update_log_item(tp, ruip, ri);
return &ruip->rui_item;
}
/* Get an RUD so we can process all the deferred rmap updates. */
static struct xfs_log_item *
xfs_rmap_update_create_done(
struct xfs_trans *tp,
struct xfs_log_item *intent,
unsigned int count)
{
return &xfs_trans_get_rud(tp, RUI_ITEM(intent))->rud_item;
}
/* Take a passive ref to the AG containing the space we're rmapping. */
void
xfs_rmap_update_get_group(
struct xfs_mount *mp,
struct xfs_rmap_intent *ri)
{
xfs_agnumber_t agno;
agno = XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock);
ri->ri_pag = xfs_perag_intent_get(mp, agno);
}
/* Release a passive AG ref after finishing rmapping work. */
static inline void
xfs_rmap_update_put_group(
struct xfs_rmap_intent *ri)
{
xfs_perag_intent_put(ri->ri_pag);
}
/* Process a deferred rmap update. */
STATIC int
xfs_rmap_update_finish_item(
struct xfs_trans *tp,
struct xfs_log_item *done,
struct list_head *item,
struct xfs_btree_cur **state)
{
struct xfs_rmap_intent *ri;
int error;
ri = container_of(item, struct xfs_rmap_intent, ri_list);
error = xfs_trans_log_finish_rmap_update(tp, RUD_ITEM(done), ri,
state);
xfs_rmap_update_put_group(ri);
kmem_cache_free(xfs_rmap_intent_cache, ri);
return error;
}
/* Abort all pending RUIs. */
STATIC void
xfs_rmap_update_abort_intent(
struct xfs_log_item *intent)
{
xfs_rui_release(RUI_ITEM(intent));
}
/* Cancel a deferred rmap update. */
STATIC void
xfs_rmap_update_cancel_item(
struct list_head *item)
{
struct xfs_rmap_intent *ri;
ri = container_of(item, struct xfs_rmap_intent, ri_list);
xfs_rmap_update_put_group(ri);
kmem_cache_free(xfs_rmap_intent_cache, ri);
}
const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
.max_items = XFS_RUI_MAX_FAST_EXTENTS,
.create_intent = xfs_rmap_update_create_intent,
.abort_intent = xfs_rmap_update_abort_intent,
.create_done = xfs_rmap_update_create_done,
.finish_item = xfs_rmap_update_finish_item,
.finish_cleanup = xfs_rmap_finish_one_cleanup,
.cancel_item = xfs_rmap_update_cancel_item,
};
/* Is this recovered RUI ok? */
static inline bool
xfs_rui_validate_map(
struct xfs_mount *mp,
struct xfs_map_extent *map)
{
if (!xfs_has_rmapbt(mp))
return false;
if (map->me_flags & ~XFS_RMAP_EXTENT_FLAGS)
return false;
switch (map->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
case XFS_RMAP_EXTENT_MAP:
case XFS_RMAP_EXTENT_MAP_SHARED:
case XFS_RMAP_EXTENT_UNMAP:
case XFS_RMAP_EXTENT_UNMAP_SHARED:
case XFS_RMAP_EXTENT_CONVERT:
case XFS_RMAP_EXTENT_CONVERT_SHARED:
case XFS_RMAP_EXTENT_ALLOC:
case XFS_RMAP_EXTENT_FREE:
break;
default:
return false;
}
if (!XFS_RMAP_NON_INODE_OWNER(map->me_owner) &&
!xfs_verify_ino(mp, map->me_owner))
return false;
if (!xfs_verify_fileext(mp, map->me_startoff, map->me_len))
return false;
return xfs_verify_fsbext(mp, map->me_startblock, map->me_len);
}
/*
* Process an rmap update intent item that was recovered from the log.
* We need to update the rmapbt.
*/
STATIC int
xfs_rui_item_recover(
struct xfs_log_item *lip,
struct list_head *capture_list)
{
struct xfs_trans_res resv;
struct xfs_rui_log_item *ruip = RUI_ITEM(lip);
struct xfs_rud_log_item *rudp;
struct xfs_trans *tp;
struct xfs_btree_cur *rcur = NULL;
struct xfs_mount *mp = lip->li_log->l_mp;
int i;
int error = 0;
/*
* First check the validity of the extents described by the
* RUI. If any are bad, then assume that all are bad and
* just toss the RUI.
*/
for (i = 0; i < ruip->rui_format.rui_nextents; i++) {
if (!xfs_rui_validate_map(mp,
&ruip->rui_format.rui_extents[i])) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
&ruip->rui_format,
sizeof(ruip->rui_format));
return -EFSCORRUPTED;
}
}
resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
error = xfs_trans_alloc(mp, &resv, mp->m_rmap_maxlevels, 0,
XFS_TRANS_RESERVE, &tp);
if (error)
return error;
rudp = xfs_trans_get_rud(tp, ruip);
for (i = 0; i < ruip->rui_format.rui_nextents; i++) {
struct xfs_rmap_intent fake = { };
struct xfs_map_extent *map;
map = &ruip->rui_format.rui_extents[i];
switch (map->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
case XFS_RMAP_EXTENT_MAP:
fake.ri_type = XFS_RMAP_MAP;
break;
case XFS_RMAP_EXTENT_MAP_SHARED:
fake.ri_type = XFS_RMAP_MAP_SHARED;
break;
case XFS_RMAP_EXTENT_UNMAP:
fake.ri_type = XFS_RMAP_UNMAP;
break;
case XFS_RMAP_EXTENT_UNMAP_SHARED:
fake.ri_type = XFS_RMAP_UNMAP_SHARED;
break;
case XFS_RMAP_EXTENT_CONVERT:
fake.ri_type = XFS_RMAP_CONVERT;
break;
case XFS_RMAP_EXTENT_CONVERT_SHARED:
fake.ri_type = XFS_RMAP_CONVERT_SHARED;
break;
case XFS_RMAP_EXTENT_ALLOC:
fake.ri_type = XFS_RMAP_ALLOC;
break;
case XFS_RMAP_EXTENT_FREE:
fake.ri_type = XFS_RMAP_FREE;
break;
default:
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
&ruip->rui_format,
sizeof(ruip->rui_format));
error = -EFSCORRUPTED;
goto abort_error;
}
fake.ri_owner = map->me_owner;
fake.ri_whichfork = (map->me_flags & XFS_RMAP_EXTENT_ATTR_FORK) ?
XFS_ATTR_FORK : XFS_DATA_FORK;
fake.ri_bmap.br_startblock = map->me_startblock;
fake.ri_bmap.br_startoff = map->me_startoff;
fake.ri_bmap.br_blockcount = map->me_len;
fake.ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ?
XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
xfs_rmap_update_get_group(mp, &fake);
error = xfs_trans_log_finish_rmap_update(tp, rudp, &fake,
&rcur);
if (error == -EFSCORRUPTED)
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
map, sizeof(*map));
xfs_rmap_update_put_group(&fake);
if (error)
goto abort_error;
}
xfs_rmap_finish_one_cleanup(tp, rcur, error);
return xfs_defer_ops_capture_and_commit(tp, capture_list);
abort_error:
xfs_rmap_finish_one_cleanup(tp, rcur, error);
xfs_trans_cancel(tp);
return error;
}
STATIC bool
xfs_rui_item_match(
struct xfs_log_item *lip,
uint64_t intent_id)
{
return RUI_ITEM(lip)->rui_format.rui_id == intent_id;
}
/* Relog an intent item to push the log tail forward. */
static struct xfs_log_item *
xfs_rui_item_relog(
struct xfs_log_item *intent,
struct xfs_trans *tp)
{
struct xfs_rud_log_item *rudp;
struct xfs_rui_log_item *ruip;
struct xfs_map_extent *map;
unsigned int count;
count = RUI_ITEM(intent)->rui_format.rui_nextents;
map = RUI_ITEM(intent)->rui_format.rui_extents;
tp->t_flags |= XFS_TRANS_DIRTY;
rudp = xfs_trans_get_rud(tp, RUI_ITEM(intent));
set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
ruip = xfs_rui_init(tp->t_mountp, count);
memcpy(ruip->rui_format.rui_extents, map, count * sizeof(*map));
atomic_set(&ruip->rui_next_extent, count);
xfs_trans_add_item(tp, &ruip->rui_item);
set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
return &ruip->rui_item;
}
static const struct xfs_item_ops xfs_rui_item_ops = {
.flags = XFS_ITEM_INTENT,
.iop_size = xfs_rui_item_size,
.iop_format = xfs_rui_item_format,
.iop_unpin = xfs_rui_item_unpin,
.iop_release = xfs_rui_item_release,
.iop_recover = xfs_rui_item_recover,
.iop_match = xfs_rui_item_match,
.iop_relog = xfs_rui_item_relog,
};
static inline void
xfs_rui_copy_format(
struct xfs_rui_log_format *dst,
const struct xfs_rui_log_format *src)
{
unsigned int i;
memcpy(dst, src, offsetof(struct xfs_rui_log_format, rui_extents));
for (i = 0; i < src->rui_nextents; i++)
memcpy(&dst->rui_extents[i], &src->rui_extents[i],
sizeof(struct xfs_map_extent));
}
/*
* This routine is called to create an in-core extent rmap update
* item from the rui format structure which was logged on disk.
* It allocates an in-core rui, copies the extents from the format
* structure into it, and adds the rui to the AIL with the given
* LSN.
*/
STATIC int
xlog_recover_rui_commit_pass2(
struct xlog *log,
struct list_head *buffer_list,
struct xlog_recover_item *item,
xfs_lsn_t lsn)
{
struct xfs_mount *mp = log->l_mp;
struct xfs_rui_log_item *ruip;
struct xfs_rui_log_format *rui_formatp;
size_t len;
rui_formatp = item->ri_buf[0].i_addr;
if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
if (item->ri_buf[0].i_len != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
/*
* Insert the intent into the AIL directly and drop one reference so
* that finishing or canceling the work will drop the other.
*/
xfs_trans_ail_insert(log->l_ailp, &ruip->rui_item, lsn);
xfs_rui_release(ruip);
return 0;
}
const struct xlog_recover_item_ops xlog_rui_item_ops = {
.item_type = XFS_LI_RUI,
.commit_pass2 = xlog_recover_rui_commit_pass2,
};
/*
* This routine is called when an RUD format structure is found in a committed
* transaction in the log. Its purpose is to cancel the corresponding RUI if it
* was still in the log. To do this it searches the AIL for the RUI with an id
* equal to that in the RUD format structure. If we find it we drop the RUD
* reference, which removes the RUI from the AIL and frees it.
*/
STATIC int
xlog_recover_rud_commit_pass2(
struct xlog *log,
struct list_head *buffer_list,
struct xlog_recover_item *item,
xfs_lsn_t lsn)
{
struct xfs_rud_log_format *rud_formatp;
rud_formatp = item->ri_buf[0].i_addr;
if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
rud_formatp, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
xlog_recover_release_intent(log, XFS_LI_RUI, rud_formatp->rud_rui_id);
return 0;
}
const struct xlog_recover_item_ops xlog_rud_item_ops = {
.item_type = XFS_LI_RUD,
.commit_pass2 = xlog_recover_rud_commit_pass2,
};
Reference in New Issue View Git Blame Copy Permalink