OpenCloudOS-Kernel/fs/xfs/libxfs/xfs_bmap.h

290 lines
9.8 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef __XFS_BMAP_H__
#define __XFS_BMAP_H__
struct getbmap;
struct xfs_bmbt_irec;
struct xfs_ifork;
struct xfs_inode;
struct xfs_mount;
struct xfs_trans;
extern kmem_zone_t *xfs_bmap_free_item_zone;
/*
* Argument structure for xfs_bmap_alloc.
*/
struct xfs_bmalloca {
xfs_fsblock_t *firstblock; /* i/o first block allocated */
struct xfs_defer_ops *dfops; /* bmap freelist */
struct xfs_trans *tp; /* transaction pointer */
struct xfs_inode *ip; /* incore inode pointer */
struct xfs_bmbt_irec prev; /* extent before the new one */
struct xfs_bmbt_irec got; /* extent after, or delayed */
xfs_fileoff_t offset; /* offset in file filling in */
xfs_extlen_t length; /* i/o length asked/allocated */
xfs_fsblock_t blkno; /* starting block of new extent */
struct xfs_btree_cur *cur; /* btree cursor */
struct xfs_iext_cursor icur; /* incore extent cursor */
int nallocs;/* number of extents alloc'd */
int logflags;/* flags for transaction logging */
xfs_extlen_t total; /* total blocks needed for xaction */
xfs_extlen_t minlen; /* minimum allocation size (blocks) */
xfs_extlen_t minleft; /* amount must be left after alloc */
bool eof; /* set if allocating past last extent */
bool wasdel; /* replacing a delayed allocation */
bool aeof; /* allocated space at eof */
bool conv; /* overwriting unwritten extents */
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>
2016-09-26 06:21:28 +08:00
int datatype;/* data type being allocated */
int flags;
};
/*
* List of extents to be free "later".
* The list is kept sorted on xbf_startblock.
*/
struct xfs_extent_free_item
{
xfs_fsblock_t xefi_startblock;/* starting fs block number */
xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
struct list_head xefi_list;
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 09:33:42 +08:00
struct xfs_owner_info xefi_oinfo; /* extent owner */
bool xefi_skip_discard;
};
#define XFS_BMAP_MAX_NMAP 4
/*
* Flags for xfs_bmapi_*
*/
#define XFS_BMAPI_ENTIRE 0x001 /* return entire extent, not trimmed */
#define XFS_BMAPI_METADATA 0x002 /* mapping metadata not user data */
#define XFS_BMAPI_ATTRFORK 0x004 /* use attribute fork not data */
#define XFS_BMAPI_PREALLOC 0x008 /* preallocation op: unwritten space */
#define XFS_BMAPI_CONTIG 0x020 /* must allocate only one extent */
/*
* unwritten extent conversion - this needs write cache flushing and no additional
* allocation alignments. When specified with XFS_BMAPI_PREALLOC it converts
* from written to unwritten, otherwise convert from unwritten to written.
*/
#define XFS_BMAPI_CONVERT 0x040
/*
* allocate zeroed extents - this requires all newly allocated user data extents
* to be initialised to zero. It will be ignored if XFS_BMAPI_METADATA is set.
* Use in conjunction with XFS_BMAPI_CONVERT to convert unwritten extents found
* during the allocation range to zeroed written extents.
*/
#define XFS_BMAPI_ZERO 0x080
/*
* Map the inode offset to the block given in ap->firstblock. Primarily
* used for reflink. The range must be in a hole, and this flag cannot be
* turned on with PREALLOC or CONVERT, and cannot be used on the attr fork.
*
* For bunmapi, this flag unmaps the range without adjusting quota, reducing
* refcount, or freeing the blocks.
*/
#define XFS_BMAPI_REMAP 0x100
/* Map something in the CoW fork. */
#define XFS_BMAPI_COWFORK 0x200
/* Only convert delalloc space, don't allocate entirely new extents */
#define XFS_BMAPI_DELALLOC 0x400
/* Only convert unwritten extents, don't allocate new blocks */
#define XFS_BMAPI_CONVERT_ONLY 0x800
/* Skip online discard of freed extents */
#define XFS_BMAPI_NODISCARD 0x1000
/* Do not update the rmap btree. Used for reconstructing bmbt from rmapbt. */
#define XFS_BMAPI_NORMAP 0x2000
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
#define XFS_BMAPI_FLAGS \
{ XFS_BMAPI_ENTIRE, "ENTIRE" }, \
{ XFS_BMAPI_METADATA, "METADATA" }, \
{ XFS_BMAPI_ATTRFORK, "ATTRFORK" }, \
{ XFS_BMAPI_PREALLOC, "PREALLOC" }, \
{ XFS_BMAPI_CONTIG, "CONTIG" }, \
{ XFS_BMAPI_CONVERT, "CONVERT" }, \
{ XFS_BMAPI_ZERO, "ZERO" }, \
{ XFS_BMAPI_REMAP, "REMAP" }, \
{ XFS_BMAPI_COWFORK, "COWFORK" }, \
{ XFS_BMAPI_DELALLOC, "DELALLOC" }, \
{ XFS_BMAPI_CONVERT_ONLY, "CONVERT_ONLY" }, \
{ XFS_BMAPI_NODISCARD, "NODISCARD" }, \
{ XFS_BMAPI_NORMAP, "NORMAP" }
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
static inline int xfs_bmapi_aflag(int w)
{
return (w == XFS_ATTR_FORK ? XFS_BMAPI_ATTRFORK :
(w == XFS_COW_FORK ? XFS_BMAPI_COWFORK : 0));
}
static inline int xfs_bmapi_whichfork(int bmapi_flags)
{
if (bmapi_flags & XFS_BMAPI_COWFORK)
return XFS_COW_FORK;
else if (bmapi_flags & XFS_BMAPI_ATTRFORK)
return XFS_ATTR_FORK;
return XFS_DATA_FORK;
}
/*
* Special values for xfs_bmbt_irec_t br_startblock field.
*/
#define DELAYSTARTBLOCK ((xfs_fsblock_t)-1LL)
#define HOLESTARTBLOCK ((xfs_fsblock_t)-2LL)
/*
* Flags for xfs_bmap_add_extent*.
*/
#define BMAP_LEFT_CONTIG (1 << 0)
#define BMAP_RIGHT_CONTIG (1 << 1)
#define BMAP_LEFT_FILLING (1 << 2)
#define BMAP_RIGHT_FILLING (1 << 3)
#define BMAP_LEFT_DELAY (1 << 4)
#define BMAP_RIGHT_DELAY (1 << 5)
#define BMAP_LEFT_VALID (1 << 6)
#define BMAP_RIGHT_VALID (1 << 7)
#define BMAP_ATTRFORK (1 << 8)
#define BMAP_COWFORK (1 << 9)
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
#define XFS_BMAP_EXT_FLAGS \
{ BMAP_LEFT_CONTIG, "LC" }, \
{ BMAP_RIGHT_CONTIG, "RC" }, \
{ BMAP_LEFT_FILLING, "LF" }, \
{ BMAP_RIGHT_FILLING, "RF" }, \
{ BMAP_ATTRFORK, "ATTR" }, \
{ BMAP_COWFORK, "COW" }
/*
* Return true if the extent is a real, allocated extent, or false if it is a
* delayed allocation, and unwritten extent or a hole.
*/
static inline bool xfs_bmap_is_real_extent(struct xfs_bmbt_irec *irec)
{
return irec->br_state != XFS_EXT_UNWRITTEN &&
irec->br_startblock != HOLESTARTBLOCK &&
irec->br_startblock != DELAYSTARTBLOCK &&
!isnullstartblock(irec->br_startblock);
}
void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
xfs_filblks_t len);
xfs: trim writepage mapping to within eof The writeback rework in commit fbcc02561359 ("xfs: Introduce writeback context for writepages") introduced a subtle change in behavior with regard to the block mapping used across the ->writepages() sequence. The previous xfs_cluster_write() code would only flush pages up to EOF at the time of the writepage, thus ensuring that any pages due to file-extending writes would be handled on a separate cycle and with a new, updated block mapping. The updated code establishes a block mapping in xfs_writepage_map() that could extend beyond EOF if the file has post-eof preallocation. Because we now use the generic writeback infrastructure and pass the cached mapping to each writepage call, there is no implicit EOF limit in place. If eofblocks trimming occurs during ->writepages(), any post-eof portion of the cached mapping becomes invalid. The eofblocks code has no means to serialize against writeback because there are no pages associated with post-eof blocks. Therefore if an eofblocks trim occurs and is followed by a file-extending buffered write, not only has the mapping become invalid, but we could end up writing a page to disk based on the invalid mapping. Consider the following sequence of events: - A buffered write creates a delalloc extent and post-eof speculative preallocation. - Writeback starts and on the first writepage cycle, the delalloc extent is converted to real blocks (including the post-eof blocks) and the mapping is cached. - The file is closed and xfs_release() trims post-eof blocks. The cached writeback mapping is now invalid. - Another buffered write appends the file with a delalloc extent. - The concurrent writeback cycle picks up the just written page because the writeback range end is LLONG_MAX. xfs_writepage_map() attributes it to the (now invalid) cached mapping and writes the data to an incorrect location on disk (and where the file offset is still backed by a delalloc extent). This problem is reproduced by xfstests test generic/464, which triggers racing writes, appends, open/closes and writeback requests. To address this problem, trim the mapping used during writeback to within EOF when the mapping is validated. This ensures the mapping is revalidated for any pages encountered beyond EOF as of the time the current mapping was cached or last validated. Reported-by: Eryu Guan <eguan@redhat.com> Diagnosed-by: Eryu Guan <eguan@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-10-14 00:47:46 +08:00
void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
void __xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
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 09:33:42 +08:00
xfs_fsblock_t bno, xfs_filblks_t len,
struct xfs_owner_info *oinfo, bool skip_discard);
void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
int xfs_bmap_last_before(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t *last_block, int whichfork);
int xfs_bmap_last_offset(struct xfs_inode *ip, xfs_fileoff_t *unused,
int whichfork);
int xfs_bmap_one_block(struct xfs_inode *ip, int whichfork);
int xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
xfs_filblks_t len, struct xfs_bmbt_irec *mval,
int *nmap, int flags);
int xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, int flags,
xfs_fsblock_t *firstblock, xfs_extlen_t total,
struct xfs_bmbt_irec *mval, int *nmap);
int __xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t *rlen, int flags,
xfs_extnum_t nexts, xfs_fsblock_t *firstblock);
int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, int flags,
xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
int *done);
int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
struct xfs_bmbt_irec *del);
void xfs_bmap_del_extent_cow(struct xfs_inode *ip,
struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
struct xfs_bmbt_irec *del);
uint xfs_default_attroffset(struct xfs_inode *ip);
int xfs_bmap_collapse_extents(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
bool *done, xfs_fsblock_t *firstblock,
struct xfs_defer_ops *dfops);
int xfs_bmap_can_insert_extents(struct xfs_inode *ip, xfs_fileoff_t off,
xfs_fileoff_t shift);
int xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock,
struct xfs_defer_ops *dfops);
int xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset);
int xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
xfs: track preallocation separately in xfs_bmapi_reserve_delalloc() Speculative preallocation is currently processed entirely by the callers of xfs_bmapi_reserve_delalloc(). The caller determines how much preallocation to include, adjusts the extent length and passes down the resulting request. While this works fine for post-eof speculative preallocation, it is not as reliable for COW fork preallocation. COW fork preallocation is implemented via the cowextszhint, which aligns the start offset as well as the length of the extent. Further, it is difficult for the caller to accurately identify when preallocation occurs because the returned extent could have been merged with neighboring extents in the fork. To simplify this situation and facilitate further COW fork preallocation enhancements, update xfs_bmapi_reserve_delalloc() to take a separate preallocation parameter to incorporate into the allocation request. The preallocation blocks value is tacked onto the end of the request and adjusted to accommodate neighboring extents and extent size limits. Since xfs_bmapi_reserve_delalloc() now knows precisely how much preallocation was included in the allocation, it can also tag the inodes appropriately to support preallocation reclaim. Note that xfs_bmapi_reserve_delalloc() callers are not yet updated to use the preallocation mechanism. This patch should not change behavior outside of correctly tagging reflink inodes when start offset preallocation occurs (which the caller does not handle correctly). Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-11-28 11:57:42 +08:00
xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,
struct xfs_bmbt_irec *got, struct xfs_iext_cursor *cur,
int eof);
static inline void
xfs_bmap_add_free(
struct xfs_mount *mp,
struct xfs_defer_ops *dfops,
xfs_fsblock_t bno,
xfs_filblks_t len,
struct xfs_owner_info *oinfo)
{
__xfs_bmap_add_free(mp, dfops, bno, len, oinfo, false);
}
enum xfs_bmap_intent_type {
XFS_BMAP_MAP = 1,
XFS_BMAP_UNMAP,
};
struct xfs_bmap_intent {
struct list_head bi_list;
enum xfs_bmap_intent_type bi_type;
struct xfs_inode *bi_owner;
int bi_whichfork;
struct xfs_bmbt_irec bi_bmap;
};
int xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops,
struct xfs_inode *ip, enum xfs_bmap_intent_type type,
int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
xfs_filblks_t *blockcount, xfs_exntst_t state);
int xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
int xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
static inline int xfs_bmap_fork_to_state(int whichfork)
{
switch (whichfork) {
case XFS_ATTR_FORK:
return BMAP_ATTRFORK;
case XFS_COW_FORK:
return BMAP_COWFORK;
default:
return 0;
}
}
xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
struct xfs_bmbt_irec *irec);
int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
struct xfs_defer_ops *dfops, int flags);
#endif /* __XFS_BMAP_H__ */