linux/fs/xfs/libxfs/xfs_alloc.h

284 lines
9.7 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef __XFS_ALLOC_H__
#define __XFS_ALLOC_H__
struct xfs_buf;
struct xfs_btree_cur;
struct xfs_mount;
struct xfs_perag;
struct xfs_trans;
extern struct workqueue_struct *xfs_alloc_wq;
unsigned int xfs_agfl_size(struct xfs_mount *mp);
/*
* Flags for xfs_alloc_fix_freelist.
*/
xfs: don't block in busy flushing when freeing extents If the current transaction holds a busy extent and we are trying to allocate a new extent to fix up the free list, we can deadlock if the AG is entirely empty except for the busy extent held by the transaction. This can occur at runtime processing an XEFI with multiple extents in this path: __schedule+0x22f at ffffffff81f75e8f schedule+0x46 at ffffffff81f76366 xfs_extent_busy_flush+0x69 at ffffffff81477d99 xfs_alloc_ag_vextent_size+0x16a at ffffffff8141711a xfs_alloc_ag_vextent+0x19b at ffffffff81417edb xfs_alloc_fix_freelist+0x22f at ffffffff8141896f xfs_free_extent_fix_freelist+0x6a at ffffffff8141939a __xfs_free_extent+0x99 at ffffffff81419499 xfs_trans_free_extent+0x3e at ffffffff814a6fee xfs_extent_free_finish_item+0x24 at ffffffff814a70d4 xfs_defer_finish_noroll+0x1f7 at ffffffff81441407 xfs_defer_finish+0x11 at ffffffff814417e1 xfs_itruncate_extents_flags+0x13d at ffffffff8148b7dd xfs_inactive_truncate+0xb9 at ffffffff8148bb89 xfs_inactive+0x227 at ffffffff8148c4f7 xfs_fs_destroy_inode+0xb8 at ffffffff81496898 destroy_inode+0x3b at ffffffff8127d2ab do_unlinkat+0x1d1 at ffffffff81270df1 do_syscall_64+0x40 at ffffffff81f6b5f0 entry_SYSCALL_64_after_hwframe+0x44 at ffffffff8200007c This can also happen in log recovery when processing an EFI with multiple extents through this path: context_switch() kernel/sched/core.c:3881 __schedule() kernel/sched/core.c:5111 schedule() kernel/sched/core.c:5186 xfs_extent_busy_flush() fs/xfs/xfs_extent_busy.c:598 xfs_alloc_ag_vextent_size() fs/xfs/libxfs/xfs_alloc.c:1641 xfs_alloc_ag_vextent() fs/xfs/libxfs/xfs_alloc.c:828 xfs_alloc_fix_freelist() fs/xfs/libxfs/xfs_alloc.c:2362 xfs_free_extent_fix_freelist() fs/xfs/libxfs/xfs_alloc.c:3029 __xfs_free_extent() fs/xfs/libxfs/xfs_alloc.c:3067 xfs_trans_free_extent() fs/xfs/xfs_extfree_item.c:370 xfs_efi_recover() fs/xfs/xfs_extfree_item.c:626 xlog_recover_process_efi() fs/xfs/xfs_log_recover.c:4605 xlog_recover_process_intents() fs/xfs/xfs_log_recover.c:4893 xlog_recover_finish() fs/xfs/xfs_log_recover.c:5824 xfs_log_mount_finish() fs/xfs/xfs_log.c:764 xfs_mountfs() fs/xfs/xfs_mount.c:978 xfs_fs_fill_super() fs/xfs/xfs_super.c:1908 mount_bdev() fs/super.c:1417 xfs_fs_mount() fs/xfs/xfs_super.c:1985 legacy_get_tree() fs/fs_context.c:647 vfs_get_tree() fs/super.c:1547 do_new_mount() fs/namespace.c:2843 do_mount() fs/namespace.c:3163 ksys_mount() fs/namespace.c:3372 __do_sys_mount() fs/namespace.c:3386 __se_sys_mount() fs/namespace.c:3383 __x64_sys_mount() fs/namespace.c:3383 do_syscall_64() arch/x86/entry/common.c:296 entry_SYSCALL_64() arch/x86/entry/entry_64.S:180 To avoid this deadlock, we should not block in xfs_extent_busy_flush() if we hold a busy extent in the current transaction. Now that the EFI processing code can handle requeuing a partially completed EFI, we can detect this situation in xfs_extent_busy_flush() and return -EAGAIN rather than going to sleep forever. The -EAGAIN get propagated back out to the xfs_trans_free_extent() context, where the EFD is populated and the transaction is rolled, thereby moving the busy extents into the CIL. At this point, we can retry the extent free operation again with a clean transaction. If we hit the same "all free extents are busy" situation when trying to fix up the free list, we can safely call xfs_extent_busy_flush() and wait for the busy extents to resolve and wake us. At this point, the allocation search can make progress again and we can fix up the free list. This deadlock was first reported by Chandan in mid-2021, but I couldn't make myself understood during review, and didn't have time to fix it myself. It was reported again in March 2023, and again I have found myself unable to explain the complexities of the solution needed during review. As such, I don't have hours more time to waste trying to get the fix written the way it needs to be written, so I'm just doing it myself. This patchset is largely based on Wengang Wang's last patch, but with all the unnecessary stuff removed, split up into multiple patches and cleaned up somewhat. Reported-by: Chandan Babu R <chandanrlinux@gmail.com> Reported-by: Wengang Wang <wen.gang.wang@oracle.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2023-06-28 18:04:33 +00:00
#define XFS_ALLOC_FLAG_TRYLOCK (1U << 0) /* use trylock for buffer locking */
#define XFS_ALLOC_FLAG_FREEING (1U << 1) /* indicate caller is freeing extents*/
#define XFS_ALLOC_FLAG_NORMAP (1U << 2) /* don't modify the rmapbt */
#define XFS_ALLOC_FLAG_NOSHRINK (1U << 3) /* don't shrink the freelist */
#define XFS_ALLOC_FLAG_CHECK (1U << 4) /* test only, don't modify args */
#define XFS_ALLOC_FLAG_TRYFLUSH (1U << 5) /* don't wait in busy extent flush */
/*
* Argument structure for xfs_alloc routines.
* This is turned into a structure to avoid having 20 arguments passed
* down several levels of the stack.
*/
typedef struct xfs_alloc_arg {
struct xfs_trans *tp; /* transaction pointer */
struct xfs_mount *mp; /* file system mount point */
struct xfs_buf *agbp; /* buffer for a.g. freelist header */
struct xfs_perag *pag; /* per-ag struct for this agno */
xfs_fsblock_t fsbno; /* file system block number */
xfs_agnumber_t agno; /* allocation group number */
xfs_agblock_t agbno; /* allocation group-relative block # */
xfs_extlen_t minlen; /* minimum size of extent */
xfs_extlen_t maxlen; /* maximum size of extent */
xfs_extlen_t mod; /* mod value for extent size */
xfs_extlen_t prod; /* prod value for extent size */
xfs_extlen_t minleft; /* min blocks must be left after us */
xfs_extlen_t total; /* total blocks needed in xaction */
xfs_extlen_t alignment; /* align answer to multiple of this */
xfs_extlen_t minalignslop; /* slop for minlen+alignment calcs */
xfs: support min/max agbno args in block allocator The block allocator supports various arguments to tweak block allocation behavior and set allocation requirements. The sparse inode chunk feature introduces a new requirement not supported by the current arguments. Sparse inode allocations must convert or merge into an inode record that describes a fixed length chunk (64 inodes x inodesize). Full inode chunk allocations by definition always result in valid inode records. Sparse chunk allocations are smaller and the associated records can refer to blocks not owned by the inode chunk. This model can result in invalid inode records in certain cases. For example, if a sparse allocation occurs near the start of an AG, the aligned inode record for that chunk might refer to agbno 0. If an allocation occurs towards the end of the AG and the AG size is not aligned, the inode record could refer to blocks beyond the end of the AG. While neither of these scenarios directly result in corruption, they both insert invalid inode records and at minimum cause repair to complain, are unlikely to merge into full chunks over time and set land mines for other areas of code. To guarantee sparse inode chunk allocation creates valid inode records, support the ability to specify an agbno range limit for XFS_ALLOCTYPE_NEAR_BNO block allocations. The min/max agbno's are specified in the allocation arguments and limit the block allocation algorithms to that range. The starting 'agbno' hint is clamped to the range if the specified agbno is out of range. If no sufficient extent is available within the range, the allocation fails. For backwards compatibility, the min/max fields can be initialized to 0 to disable range limiting (e.g., equivalent to min=0,max=agsize). Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-05-28 22:53:00 +00:00
xfs_agblock_t min_agbno; /* set an agbno range for NEAR allocs */
xfs_agblock_t max_agbno; /* ... */
xfs_extlen_t len; /* output: actual size of extent */
xfs: remote attribute blocks aren't really userdata When adding a new remote attribute, we write the attribute to the new extent before the allocation transaction is committed. This means we cannot reuse busy extents as that violates crash consistency semantics. Hence we currently treat remote attribute extent allocation like userdata because it has the same overwrite ordering constraints as userdata. Unfortunately, this also allows the allocator to incorrectly apply extent size hints to the remote attribute extent allocation. This results in interesting failures, such as transaction block reservation overruns and in-memory inode attribute fork corruption. To fix this, we need to separate the busy extent reuse configuration from the userdata configuration. This changes the definition of XFS_BMAPI_METADATA slightly - it now means that allocation is metadata and reuse of busy extents is acceptible due to the metadata ordering semantics of the journal. If this flag is not set, it means the allocation is that has unordered data writeback, and hence busy extent reuse is not allowed. It no longer implies the allocation is for user data, just that the data write will not be strictly ordered. This matches the semantics for both user data and remote attribute block allocation. As such, This patch changes the "userdata" field to a "datatype" field, and adds a "no busy reuse" flag to the field. When we detect an unordered data extent allocation, we immediately set the no reuse flag. We then set the "user data" flags based on the inode fork we are allocating the extent to. Hence we only set userdata flags on data fork allocations now and consider attribute fork remote extents to be an unordered metadata extent. The result is that remote attribute extents now have the expected allocation semantics, and the data fork allocation behaviour is completely unchanged. It should be noted that there may be other ways to fix this (e.g. use ordered metadata buffers for the remote attribute extent data write) but they are more invasive and difficult to validate both from a design and implementation POV. Hence this patch takes the simple, obvious route to fixing the problem... Reported-and-tested-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-09-25 22:21:28 +00:00
int datatype; /* mask defining data type treatment */
char wasdel; /* set if allocation was prev delayed */
char wasfromfl; /* set if allocation is from freelist */
xfs: add owner field to extent allocation and freeing For the rmap btree to work, we have to feed the extent owner information to the the allocation and freeing functions. This information is what will end up in the rmap btree that tracks allocated extents. While we technically don't need the owner information when freeing extents, passing it allows us to validate that the extent we are removing from the rmap btree actually belonged to the owner we expected it to belong to. We also define a special set of owner values for internal metadata that would otherwise have no owner. This allows us to tell the difference between metadata owned by different per-ag btrees, as well as static fs metadata (e.g. AG headers) and internal journal blocks. There are also a couple of special cases we need to take care of - during EFI recovery, we don't actually know who the original owner was, so we need to pass a wildcard to indicate that we aren't checking the owner for validity. We also need special handling in growfs, as we "free" the space in the last AG when extending it, but because it's new space it has no actual owner... While touching the xfs_bmap_add_free() function, re-order the parameters to put the struct xfs_mount first. Extend the owner field to include both the owner type and some sort of index within the owner. The index field will be used to support reverse mappings when reflink is enabled. When we're freeing extents from an EFI, we don't have the owner information available (rmap updates have their own redo items). xfs_free_extent therefore doesn't need to do an rmap update. Make sure that the log replay code signals this correctly. This is based upon a patch originally from Dave Chinner. It has been extended to add more owner information with the intent of helping recovery operations when things go wrong (e.g. offset of user data block in a file). [dchinner: de-shout the xfs_rmap_*_owner helpers] [darrick: minor style fixes suggested by Christoph Hellwig] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-08-03 01:33:42 +00:00
struct xfs_owner_info oinfo; /* owner of blocks being allocated */
xfs: set up per-AG free space reservations One unfortunate quirk of the reference count and reverse mapping btrees -- they can expand in size when blocks are written to *other* allocation groups if, say, one large extent becomes a lot of tiny extents. Since we don't want to start throwing errors in the middle of CoWing, we need to reserve some blocks to handle future expansion. The transaction block reservation counters aren't sufficient here because we have to have a reserve of blocks in every AG, not just somewhere in the filesystem. Therefore, create two per-AG block reservation pools. One feeds the AGFL so that rmapbt expansion always succeeds, and the other feeds all other metadata so that refcountbt expansion never fails. Use the count of how many reserved blocks we need to have on hand to create a virtual reservation in the AG. Through selective clamping of the maximum length of allocation requests and of the length of the longest free extent, we can make it look like there's less free space in the AG unless the reservation owner is asking for blocks. In other words, play some accounting tricks in-core to make sure that we always have blocks available. On the plus side, there's nothing to clean up if we crash, which is contrast to the strategy that the rough draft used (actually removing extents from the freespace btrees). Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-09-19 00:30:52 +00:00
enum xfs_ag_resv_type resv; /* block reservation to use */
#ifdef DEBUG
bool alloc_minlen_only; /* allocate exact minlen extent */
#endif
} xfs_alloc_arg_t;
/*
xfs: remote attribute blocks aren't really userdata When adding a new remote attribute, we write the attribute to the new extent before the allocation transaction is committed. This means we cannot reuse busy extents as that violates crash consistency semantics. Hence we currently treat remote attribute extent allocation like userdata because it has the same overwrite ordering constraints as userdata. Unfortunately, this also allows the allocator to incorrectly apply extent size hints to the remote attribute extent allocation. This results in interesting failures, such as transaction block reservation overruns and in-memory inode attribute fork corruption. To fix this, we need to separate the busy extent reuse configuration from the userdata configuration. This changes the definition of XFS_BMAPI_METADATA slightly - it now means that allocation is metadata and reuse of busy extents is acceptible due to the metadata ordering semantics of the journal. If this flag is not set, it means the allocation is that has unordered data writeback, and hence busy extent reuse is not allowed. It no longer implies the allocation is for user data, just that the data write will not be strictly ordered. This matches the semantics for both user data and remote attribute block allocation. As such, This patch changes the "userdata" field to a "datatype" field, and adds a "no busy reuse" flag to the field. When we detect an unordered data extent allocation, we immediately set the no reuse flag. We then set the "user data" flags based on the inode fork we are allocating the extent to. Hence we only set userdata flags on data fork allocations now and consider attribute fork remote extents to be an unordered metadata extent. The result is that remote attribute extents now have the expected allocation semantics, and the data fork allocation behaviour is completely unchanged. It should be noted that there may be other ways to fix this (e.g. use ordered metadata buffers for the remote attribute extent data write) but they are more invasive and difficult to validate both from a design and implementation POV. Hence this patch takes the simple, obvious route to fixing the problem... Reported-and-tested-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-09-25 22:21:28 +00:00
* Defines for datatype
*/
#define XFS_ALLOC_USERDATA (1 << 0)/* allocation is for user data*/
#define XFS_ALLOC_INITIAL_USER_DATA (1 << 1)/* special case start of file */
#define XFS_ALLOC_NOBUSY (1 << 2)/* Busy extents not allowed */
xfs: remote attribute blocks aren't really userdata When adding a new remote attribute, we write the attribute to the new extent before the allocation transaction is committed. This means we cannot reuse busy extents as that violates crash consistency semantics. Hence we currently treat remote attribute extent allocation like userdata because it has the same overwrite ordering constraints as userdata. Unfortunately, this also allows the allocator to incorrectly apply extent size hints to the remote attribute extent allocation. This results in interesting failures, such as transaction block reservation overruns and in-memory inode attribute fork corruption. To fix this, we need to separate the busy extent reuse configuration from the userdata configuration. This changes the definition of XFS_BMAPI_METADATA slightly - it now means that allocation is metadata and reuse of busy extents is acceptible due to the metadata ordering semantics of the journal. If this flag is not set, it means the allocation is that has unordered data writeback, and hence busy extent reuse is not allowed. It no longer implies the allocation is for user data, just that the data write will not be strictly ordered. This matches the semantics for both user data and remote attribute block allocation. As such, This patch changes the "userdata" field to a "datatype" field, and adds a "no busy reuse" flag to the field. When we detect an unordered data extent allocation, we immediately set the no reuse flag. We then set the "user data" flags based on the inode fork we are allocating the extent to. Hence we only set userdata flags on data fork allocations now and consider attribute fork remote extents to be an unordered metadata extent. The result is that remote attribute extents now have the expected allocation semantics, and the data fork allocation behaviour is completely unchanged. It should be noted that there may be other ways to fix this (e.g. use ordered metadata buffers for the remote attribute extent data write) but they are more invasive and difficult to validate both from a design and implementation POV. Hence this patch takes the simple, obvious route to fixing the problem... Reported-and-tested-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-09-25 22:21:28 +00:00
/* freespace limit calculations */
unsigned int xfs_alloc_set_aside(struct xfs_mount *mp);
unsigned int xfs_alloc_ag_max_usable(struct xfs_mount *mp);
xfs_extlen_t xfs_alloc_longest_free_extent(struct xfs_perag *pag,
xfs_extlen_t need, xfs_extlen_t reserved);
unsigned int xfs_alloc_min_freelist(struct xfs_mount *mp,
struct xfs_perag *pag);
int xfs_alloc_get_freelist(struct xfs_perag *pag, struct xfs_trans *tp,
struct xfs_buf *agfbp, xfs_agblock_t *bnop, int btreeblk);
int xfs_alloc_put_freelist(struct xfs_perag *pag, struct xfs_trans *tp,
struct xfs_buf *agfbp, struct xfs_buf *agflbp,
xfs_agblock_t bno, int btreeblk);
xfs: avoid redundant AGFL buffer invalidation Currently AGFL blocks can be filled from the following three sources: - allocbt free blocks, as in xfs_allocbt_free_block(); - rmapbt free blocks, as in xfs_rmapbt_free_block(); - refilled from freespace btrees, as in xfs_alloc_fix_freelist(). Originally, allocbt free blocks would be marked as stale only when they put back in the general free space pool as Dave mentioned on IRC, "we don't stale AGF metadata btree blocks when they are returned to the AGFL .. but once they get put back in the general free space pool, we have to make sure the buffers are marked stale as the next user of those blocks might be user data...." However, after commit ca250b1b3d71 ("xfs: invalidate allocbt blocks moved to the free list") and commit edfd9dd54921 ("xfs: move buffer invalidation to xfs_btree_free_block"), even allocbt / bmapbt free blocks will be invalidated immediately since they may fail to pass V5 format validation on writeback even writeback to free space would be safe. IOWs, IMHO currently there is actually no difference of free blocks between AGFL freespace pool and the general free space pool. So let's avoid extra redundant AGFL buffer invalidation, since otherwise we're currently facing unnecessary xfs_log_force() due to xfs_trans_binval() again on buffers already marked as stale before as below: [ 333.507469] Call Trace: [ 333.507862] xfs_buf_find+0x371/0x6a0 <- xfs_buf_lock [ 333.508451] xfs_buf_get_map+0x3f/0x230 [ 333.509062] xfs_trans_get_buf_map+0x11a/0x280 [ 333.509751] xfs_free_agfl_block+0xa1/0xd0 [ 333.510403] xfs_agfl_free_finish_item+0x16e/0x1d0 [ 333.511157] xfs_defer_finish_noroll+0x1ef/0x5c0 [ 333.511871] xfs_defer_finish+0xc/0xa0 [ 333.512471] xfs_itruncate_extents_flags+0x18a/0x5e0 [ 333.513253] xfs_inactive_truncate+0xb8/0x130 [ 333.513930] xfs_inactive+0x223/0x270 xfs_log_force() will take tens of milliseconds with AGF buffer locked. It becomes an unnecessary long latency especially on our PMEM devices with FSDAX enabled and fsops like xfs_reflink_find_shared() at the same time are stuck due to the same AGF lock. Removing the double invalidation on the AGFL blocks does not make this issue go away, but this patch fixes for our workloads in reality and it should also work by the code analysis. Note that I'm not sure I need to remove another redundant one in xfs_alloc_ag_vextent_small() since it's unrelated to our workloads. Also fstests are passed with this patch. Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
2024-05-28 04:12:39 +00:00
int xfs_free_ag_extent(struct xfs_trans *tp, struct xfs_buf *agbp,
xfs_agnumber_t agno, xfs_agblock_t bno,
xfs_extlen_t len, const struct xfs_owner_info *oinfo,
enum xfs_ag_resv_type type);
/*
* Compute and fill in value of m_alloc_maxlevels.
*/
void
xfs_alloc_compute_maxlevels(
struct xfs_mount *mp); /* file system mount structure */
/*
* Log the given fields from the agf structure.
*/
void
xfs_alloc_log_agf(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_buf *bp, /* buffer for a.g. freelist header */
uint32_t fields);/* mask of fields to be logged (XFS_AGF_...) */
/*
* Allocate an extent anywhere in the specific AG given. If there is no
* space matching the requirements in that AG, then the allocation will fail.
*/
int xfs_alloc_vextent_this_ag(struct xfs_alloc_arg *args, xfs_agnumber_t agno);
/*
* Allocate an extent as close to the target as possible. If there are not
* viable candidates in the AG, then fail the allocation.
*/
int xfs_alloc_vextent_near_bno(struct xfs_alloc_arg *args,
xfs_fsblock_t target);
/*
* Allocate an extent exactly at the target given. If this is not possible
* then the allocation fails.
*/
int xfs_alloc_vextent_exact_bno(struct xfs_alloc_arg *args,
xfs_fsblock_t target);
/*
* Best effort full filesystem allocation scan.
*
* Locality aware allocation will be attempted in the initial AG, but on failure
* non-localised attempts will be made. The AGs are constrained by previous
* allocations in the current transaction. Two passes will be made - the first
* non-blocking, the second blocking.
*/
int xfs_alloc_vextent_start_ag(struct xfs_alloc_arg *args,
xfs_fsblock_t target);
/*
* Iterate from the AG indicated from args->fsbno through to the end of the
* filesystem attempting blocking allocation. This is for use in last
* resort allocation attempts when everything else has failed.
*/
int xfs_alloc_vextent_first_ag(struct xfs_alloc_arg *args,
xfs_fsblock_t target);
/*
* Free an extent.
*/
int /* error */
__xfs_free_extent(
xfs: add owner field to extent allocation and freeing For the rmap btree to work, we have to feed the extent owner information to the the allocation and freeing functions. This information is what will end up in the rmap btree that tracks allocated extents. While we technically don't need the owner information when freeing extents, passing it allows us to validate that the extent we are removing from the rmap btree actually belonged to the owner we expected it to belong to. We also define a special set of owner values for internal metadata that would otherwise have no owner. This allows us to tell the difference between metadata owned by different per-ag btrees, as well as static fs metadata (e.g. AG headers) and internal journal blocks. There are also a couple of special cases we need to take care of - during EFI recovery, we don't actually know who the original owner was, so we need to pass a wildcard to indicate that we aren't checking the owner for validity. We also need special handling in growfs, as we "free" the space in the last AG when extending it, but because it's new space it has no actual owner... While touching the xfs_bmap_add_free() function, re-order the parameters to put the struct xfs_mount first. Extend the owner field to include both the owner type and some sort of index within the owner. The index field will be used to support reverse mappings when reflink is enabled. When we're freeing extents from an EFI, we don't have the owner information available (rmap updates have their own redo items). xfs_free_extent therefore doesn't need to do an rmap update. Make sure that the log replay code signals this correctly. This is based upon a patch originally from Dave Chinner. It has been extended to add more owner information with the intent of helping recovery operations when things go wrong (e.g. offset of user data block in a file). [dchinner: de-shout the xfs_rmap_*_owner helpers] [darrick: minor style fixes suggested by Christoph Hellwig] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-08-03 01:33:42 +00:00
struct xfs_trans *tp, /* transaction pointer */
struct xfs_perag *pag,
xfs_agblock_t agbno,
xfs: add owner field to extent allocation and freeing For the rmap btree to work, we have to feed the extent owner information to the the allocation and freeing functions. This information is what will end up in the rmap btree that tracks allocated extents. While we technically don't need the owner information when freeing extents, passing it allows us to validate that the extent we are removing from the rmap btree actually belonged to the owner we expected it to belong to. We also define a special set of owner values for internal metadata that would otherwise have no owner. This allows us to tell the difference between metadata owned by different per-ag btrees, as well as static fs metadata (e.g. AG headers) and internal journal blocks. There are also a couple of special cases we need to take care of - during EFI recovery, we don't actually know who the original owner was, so we need to pass a wildcard to indicate that we aren't checking the owner for validity. We also need special handling in growfs, as we "free" the space in the last AG when extending it, but because it's new space it has no actual owner... While touching the xfs_bmap_add_free() function, re-order the parameters to put the struct xfs_mount first. Extend the owner field to include both the owner type and some sort of index within the owner. The index field will be used to support reverse mappings when reflink is enabled. When we're freeing extents from an EFI, we don't have the owner information available (rmap updates have their own redo items). xfs_free_extent therefore doesn't need to do an rmap update. Make sure that the log replay code signals this correctly. This is based upon a patch originally from Dave Chinner. It has been extended to add more owner information with the intent of helping recovery operations when things go wrong (e.g. offset of user data block in a file). [dchinner: de-shout the xfs_rmap_*_owner helpers] [darrick: minor style fixes suggested by Christoph Hellwig] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-08-03 01:33:42 +00:00
xfs_extlen_t len, /* length of extent */
const struct xfs_owner_info *oinfo, /* extent owner */
enum xfs_ag_resv_type type, /* block reservation type */
bool skip_discard);
static inline int
xfs_free_extent(
struct xfs_trans *tp,
struct xfs_perag *pag,
xfs_agblock_t agbno,
xfs_extlen_t len,
const struct xfs_owner_info *oinfo,
enum xfs_ag_resv_type type)
{
return __xfs_free_extent(tp, pag, agbno, len, oinfo, type, false);
}
int /* error */
xfs_alloc_lookup_le(
struct xfs_btree_cur *cur, /* btree cursor */
xfs_agblock_t bno, /* starting block of extent */
xfs_extlen_t len, /* length of extent */
int *stat); /* success/failure */
xfs: fix fstrim offset calculations xfs_ioc_fstrim() doesn't treat the incoming offset and length correctly. It treats them as a filesystem block address, rather than a disk address. This is wrong because the range passed in is a linear representation, while the filesystem block address notation is a sparse representation. Hence we cannot convert the range direct to filesystem block units and then use that for calculating the range to trim. While this sounds dangerous, the problem is limited to calculating what AGs need to be trimmed. The code that calcuates the actual ranges to trim gets the right result (i.e. only ever discards free space), even though it uses the wrong ranges to limit what is trimmed. Hence this is not a bug that endangers user data. Fix this by treating the range as a disk address range and use the appropriate functions to convert the range into the desired formats for calculations. Further, fix the first free extent lookup (the longest) to actually find the largest free extent. Currently this lookup uses a <= lookup, which results in finding the extent to the left of the largest because we can never get an exact match on the largest extent. This is due to the fact that while we know it's size, we don't know it's location and so the exact match fails and we move one record to the left to get the next largest extent. Instead, use a >= search so that the lookup returns the largest extent regardless of the fact we don't get an exact match on it. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-03-22 05:15:12 +00:00
int /* error */
xfs_alloc_lookup_ge(
struct xfs_btree_cur *cur, /* btree cursor */
xfs_agblock_t bno, /* starting block of extent */
xfs_extlen_t len, /* length of extent */
int *stat); /* success/failure */
int /* error */
xfs_alloc_get_rec(
struct xfs_btree_cur *cur, /* btree cursor */
xfs_agblock_t *bno, /* output: starting block of extent */
xfs_extlen_t *len, /* output: length of extent */
int *stat); /* output: success/failure */
union xfs_btree_rec;
void xfs_alloc_btrec_to_irec(const union xfs_btree_rec *rec,
struct xfs_alloc_rec_incore *irec);
xfs_failaddr_t xfs_alloc_check_irec(struct xfs_perag *pag,
const struct xfs_alloc_rec_incore *irec);
int xfs_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags,
struct xfs_buf **agfbpp);
int xfs_alloc_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags,
struct xfs_buf **agfbpp);
int xfs_alloc_read_agfl(struct xfs_perag *pag, struct xfs_trans *tp,
struct xfs_buf **bpp);
int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, uint32_t alloc_flags);
int xfs_free_extent_fix_freelist(struct xfs_trans *tp, struct xfs_perag *pag,
struct xfs_buf **agbp);
xfs_extlen_t xfs_prealloc_blocks(struct xfs_mount *mp);
typedef int (*xfs_alloc_query_range_fn)(
struct xfs_btree_cur *cur,
const struct xfs_alloc_rec_incore *rec,
void *priv);
int xfs_alloc_query_range(struct xfs_btree_cur *cur,
const struct xfs_alloc_rec_incore *low_rec,
const struct xfs_alloc_rec_incore *high_rec,
xfs_alloc_query_range_fn fn, void *priv);
int xfs_alloc_query_all(struct xfs_btree_cur *cur, xfs_alloc_query_range_fn fn,
void *priv);
int xfs_alloc_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno,
xfs_extlen_t len, enum xbtree_recpacking *outcome);
typedef int (*xfs_agfl_walk_fn)(struct xfs_mount *mp, xfs_agblock_t bno,
void *priv);
int xfs_agfl_walk(struct xfs_mount *mp, struct xfs_agf *agf,
struct xfs_buf *agflbp, xfs_agfl_walk_fn walk_fn, void *priv);
static inline __be32 *
xfs_buf_to_agfl_bno(
struct xfs_buf *bp)
{
if (xfs_has_crc(bp->b_mount))
return bp->b_addr + sizeof(struct xfs_agfl);
return bp->b_addr;
}
int xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
xfs_filblks_t len, const struct xfs_owner_info *oinfo,
enum xfs_ag_resv_type type, unsigned int free_flags);
/* Don't issue a discard for the blocks freed. */
#define XFS_FREE_EXTENT_SKIP_DISCARD (1U << 0)
#define XFS_FREE_EXTENT_ALL_FLAGS (XFS_FREE_EXTENT_SKIP_DISCARD)
/*
* List of extents to be free "later".
* The list is kept sorted on xbf_startblock.
*/
struct xfs_extent_free_item {
struct list_head xefi_list;
uint64_t xefi_owner;
xfs_fsblock_t xefi_startblock;/* starting fs block number */
xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
struct xfs_perag *xefi_pag;
unsigned int xefi_flags;
xfs: use deferred frees for btree block freeing Btrees that aren't freespace management trees use the normal extent allocation and freeing routines for their blocks. Hence when a btree block is freed, a direct call to xfs_free_extent() is made and the extent is immediately freed. This puts the entire free space management btrees under this path, so we are stacking btrees on btrees in the call stack. The inobt, finobt and refcount btrees all do this. However, the bmap btree does not do this - it calls xfs_free_extent_later() to defer the extent free operation via an XEFI and hence it gets processed in deferred operation processing during the commit of the primary transaction (i.e. via intent chaining). We need to change xfs_free_extent() to behave in a non-blocking manner so that we can avoid deadlocks with busy extents near ENOSPC in transactions that free multiple extents. Inserting or removing a record from a btree can cause a multi-level tree merge operation and that will free multiple blocks from the btree in a single transaction. i.e. we can call xfs_free_extent() multiple times, and hence the btree manipulation transaction is vulnerable to this busy extent deadlock vector. To fix this, convert all the remaining callers of xfs_free_extent() to use xfs_free_extent_later() to queue XEFIs and hence defer processing of the extent frees to a context that can be safely restarted if a deadlock condition is detected. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Chandan Babu R <chandan.babu@oracle.com>
2023-06-28 18:04:32 +00:00
enum xfs_ag_resv_type xefi_agresv;
};
#define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */
#define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */
#define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */
#define XFS_EFI_CANCELLED (1U << 3) /* dont actually free the space */
struct xfs_alloc_autoreap {
struct xfs_defer_pending *dfp;
};
int xfs_alloc_schedule_autoreap(const struct xfs_alloc_arg *args,
unsigned int free_flags, struct xfs_alloc_autoreap *aarp);
void xfs_alloc_cancel_autoreap(struct xfs_trans *tp,
struct xfs_alloc_autoreap *aarp);
void xfs_alloc_commit_autoreap(struct xfs_trans *tp,
struct xfs_alloc_autoreap *aarp);
extern struct kmem_cache *xfs_extfree_item_cache;
int __init xfs_extfree_intent_init_cache(void);
void xfs_extfree_intent_destroy_cache(void);
xfs_failaddr_t xfs_validate_ag_length(struct xfs_buf *bp, uint32_t seqno,
uint32_t length);
#endif /* __XFS_ALLOC_H__ */