From e33c267ab70de4249d22d7eab1cc7d68a889bac2 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 31 May 2022 20:22:24 -0700 Subject: mm: shrinkers: provide shrinkers with names Currently shrinkers are anonymous objects. For debugging purposes they can be identified by count/scan function names, but it's not always useful: e.g. for superblock's shrinkers it's nice to have at least an idea of to which superblock the shrinker belongs. This commit adds names to shrinkers. register_shrinker() and prealloc_shrinker() functions are extended to take a format and arguments to master a name. In some cases it's not possible to determine a good name at the time when a shrinker is allocated. For such cases shrinker_debugfs_rename() is provided. The expected format is: -[:]- For some shrinkers an instance can be encoded as (MAJOR:MINOR) pair. After this change the shrinker debugfs directory looks like: $ cd /sys/kernel/debug/shrinker/ $ ls dquota-cache-16 sb-devpts-28 sb-proc-47 sb-tmpfs-42 mm-shadow-18 sb-devtmpfs-5 sb-proc-48 sb-tmpfs-43 mm-zspool:zram0-34 sb-hugetlbfs-17 sb-pstore-31 sb-tmpfs-44 rcu-kfree-0 sb-hugetlbfs-33 sb-rootfs-2 sb-tmpfs-49 sb-aio-20 sb-iomem-12 sb-securityfs-6 sb-tracefs-13 sb-anon_inodefs-15 sb-mqueue-21 sb-selinuxfs-22 sb-xfs:vda1-36 sb-bdev-3 sb-nsfs-4 sb-sockfs-8 sb-zsmalloc-19 sb-bpf-32 sb-pipefs-14 sb-sysfs-26 thp-deferred_split-10 sb-btrfs:vda2-24 sb-proc-25 sb-tmpfs-1 thp-zero-9 sb-cgroup2-30 sb-proc-39 sb-tmpfs-27 xfs-buf:vda1-37 sb-configfs-23 sb-proc-41 sb-tmpfs-29 xfs-inodegc:vda1-38 sb-dax-11 sb-proc-45 sb-tmpfs-35 sb-debugfs-7 sb-proc-46 sb-tmpfs-40 [roman.gushchin@linux.dev: fix build warnings] Link: https://lkml.kernel.org/r/Yr+ZTnLb9lJk6fJO@castle Reported-by: kernel test robot Link: https://lkml.kernel.org/r/20220601032227.4076670-4-roman.gushchin@linux.dev Signed-off-by: Roman Gushchin Cc: Christophe JAILLET Cc: Dave Chinner Cc: Hillf Danton Cc: Kent Overstreet Cc: Muchun Song Signed-off-by: Andrew Morton --- fs/xfs/xfs_buf.c | 3 ++- fs/xfs/xfs_icache.c | 2 +- fs/xfs/xfs_qm.c | 3 ++- 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index bf4e60871068..4aa9c9cf5b6e 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1986,7 +1986,8 @@ xfs_alloc_buftarg( btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan; btp->bt_shrinker.seeks = DEFAULT_SEEKS; btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE; - if (register_shrinker(&btp->bt_shrinker)) + if (register_shrinker(&btp->bt_shrinker, "xfs-buf:%s", + mp->m_super->s_id)) goto error_pcpu; return btp; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 5269354b1b69..a1941c8b8630 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -2201,5 +2201,5 @@ xfs_inodegc_register_shrinker( shrink->flags = SHRINKER_NONSLAB; shrink->batch = XFS_INODEGC_SHRINKER_BATCH; - return register_shrinker(shrink); + return register_shrinker(shrink, "xfs-inodegc:%s", mp->m_super->s_id); } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index abf08bbf34a9..c31d57453ceb 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -677,7 +677,8 @@ xfs_qm_init_quotainfo( qinf->qi_shrinker.seeks = DEFAULT_SEEKS; qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE; - error = register_shrinker(&qinf->qi_shrinker); + error = register_shrinker(&qinf->qi_shrinker, "xfs-qm:%s", + mp->m_super->s_id); if (error) goto out_free_inos; -- cgit v1.2.3 From 8012b866085523758780850087102421dbcce522 Mon Sep 17 00:00:00 2001 From: Shiyang Ruan Date: Fri, 3 Jun 2022 13:37:25 +0800 Subject: dax: introduce holder for dax_device Patch series "v14 fsdax-rmap + v11 fsdax-reflink", v2. The patchset fsdax-rmap is aimed to support shared pages tracking for fsdax. It moves owner tracking from dax_assocaite_entry() to pmem device driver, by introducing an interface ->memory_failure() for struct pagemap. This interface is called by memory_failure() in mm, and implemented by pmem device. Then call holder operations to find the filesystem which the corrupted data located in, and call filesystem handler to track files or metadata associated with this page. Finally we are able to try to fix the corrupted data in filesystem and do other necessary processing, such as killing processes who are using the files affected. The call trace is like this: memory_failure() |* fsdax case |------------ |pgmap->ops->memory_failure() => pmem_pgmap_memory_failure() | dax_holder_notify_failure() => | dax_device->holder_ops->notify_failure() => | - xfs_dax_notify_failure() | |* xfs_dax_notify_failure() | |-------------------------- | | xfs_rmap_query_range() | | xfs_dax_failure_fn() | | * corrupted on metadata | | try to recover data, call xfs_force_shutdown() | | * corrupted on file data | | try to recover data, call mf_dax_kill_procs() |* normal case |------------- |mf_generic_kill_procs() The patchset fsdax-reflink attempts to add CoW support for fsdax, and takes XFS, which has both reflink and fsdax features, as an example. One of the key mechanisms needed to be implemented in fsdax is CoW. Copy the data from srcmap before we actually write data to the destination iomap. And we just copy range in which data won't be changed. Another mechanism is range comparison. In page cache case, readpage() is used to load data on disk to page cache in order to be able to compare data. In fsdax case, readpage() does not work. So, we need another compare data with direct access support. With the two mechanisms implemented in fsdax, we are able to make reflink and fsdax work together in XFS. This patch (of 14): To easily track filesystem from a pmem device, we introduce a holder for dax_device structure, and also its operation. This holder is used to remember who is using this dax_device: - When it is the backend of a filesystem, the holder will be the instance of this filesystem. - When this pmem device is one of the targets in a mapped device, the holder will be this mapped device. In this case, the mapped device has its own dax_device and it will follow the first rule. So that we can finally track to the filesystem we needed. The holder and holder_ops will be set when filesystem is being mounted, or an target device is being activated. Link: https://lkml.kernel.org/r/20220603053738.1218681-1-ruansy.fnst@fujitsu.com Link: https://lkml.kernel.org/r/20220603053738.1218681-2-ruansy.fnst@fujitsu.com Signed-off-by: Shiyang Ruan Reviewed-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Cc: Dave Chinner Cc: Jane Chu Cc: Goldwyn Rodrigues Cc: Al Viro Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: Miaohe Lin Cc: Dan Williams Cc: Goldwyn Rodrigues Cc: Ritesh Harjani Signed-off-by: Andrew Morton --- fs/xfs/xfs_buf.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 4aa9c9cf5b6e..1ec2a7b6d44e 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1911,7 +1911,7 @@ xfs_free_buftarg( list_lru_destroy(&btp->bt_lru); blkdev_issue_flush(btp->bt_bdev); - fs_put_dax(btp->bt_daxdev); + fs_put_dax(btp->bt_daxdev, NULL); kmem_free(btp); } @@ -1964,7 +1964,8 @@ xfs_alloc_buftarg( btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; - btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off); + btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, NULL, + NULL); /* * Buffer IO error rate limiting. Limit it to no more than 10 messages -- cgit v1.2.3 From 6f643c57d57c56d4677bc05f1fca2ef3f249797c Mon Sep 17 00:00:00 2001 From: Shiyang Ruan Date: Fri, 3 Jun 2022 13:37:30 +0800 Subject: xfs: implement ->notify_failure() for XFS Introduce xfs_notify_failure.c to handle failure related works, such as implement ->notify_failure(), register/unregister dax holder in xfs, and so on. If the rmap feature of XFS enabled, we can query it to find files and metadata which are associated with the corrupt data. For now all we do is kill processes with that file mapped into their address spaces, but future patches could actually do something about corrupt metadata. After that, the memory failure needs to notify the processes who are using those files. Link: https://lkml.kernel.org/r/20220603053738.1218681-7-ruansy.fnst@fujitsu.com Signed-off-by: Shiyang Ruan Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Cc: Al Viro Cc: Dan Williams Cc: Dan Williams Cc: Dave Chinner Cc: Goldwyn Rodrigues Cc: Goldwyn Rodrigues Cc: Jane Chu Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Ritesh Harjani Signed-off-by: Andrew Morton --- fs/xfs/Makefile | 5 + fs/xfs/xfs_buf.c | 11 ++- fs/xfs/xfs_fsops.c | 3 + fs/xfs/xfs_mount.h | 1 + fs/xfs/xfs_notify_failure.c | 220 ++++++++++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_super.h | 1 + 6 files changed, 238 insertions(+), 3 deletions(-) create mode 100644 fs/xfs/xfs_notify_failure.c (limited to 'fs/xfs') diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index b056cfc6398e..805a0d0a88c1 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -129,6 +129,11 @@ xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o xfs-$(CONFIG_COMPAT) += xfs_ioctl32.o xfs-$(CONFIG_EXPORTFS_BLOCK_OPS) += xfs_pnfs.o +# notify failure +ifeq ($(CONFIG_MEMORY_FAILURE),y) +xfs-$(CONFIG_FS_DAX) += xfs_notify_failure.o +endif + # online scrub/repair ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 1ec2a7b6d44e..59c6b62fde57 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -5,6 +5,7 @@ */ #include "xfs.h" #include +#include #include "xfs_shared.h" #include "xfs_format.h" @@ -1911,7 +1912,7 @@ xfs_free_buftarg( list_lru_destroy(&btp->bt_lru); blkdev_issue_flush(btp->bt_bdev); - fs_put_dax(btp->bt_daxdev, NULL); + fs_put_dax(btp->bt_daxdev, btp->bt_mount); kmem_free(btp); } @@ -1958,14 +1959,18 @@ xfs_alloc_buftarg( struct block_device *bdev) { xfs_buftarg_t *btp; + const struct dax_holder_operations *ops = NULL; +#if defined(CONFIG_FS_DAX) && defined(CONFIG_MEMORY_FAILURE) + ops = &xfs_dax_holder_operations; +#endif btp = kmem_zalloc(sizeof(*btp), KM_NOFS); btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; - btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, NULL, - NULL); + btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, + mp, ops); /* * Buffer IO error rate limiting. Limit it to no more than 10 messages diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index d4a77c53f94b..0bc74a71a095 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -528,6 +528,9 @@ xfs_do_force_shutdown( } else if (flags & SHUTDOWN_CORRUPT_INCORE) { tag = XFS_PTAG_SHUTDOWN_CORRUPT; why = "Corruption of in-memory data"; + } else if (flags & SHUTDOWN_CORRUPT_ONDISK) { + tag = XFS_PTAG_SHUTDOWN_CORRUPT; + why = "Corruption of on-disk metadata"; } else { tag = XFS_PTAG_SHUTDOWN_IOERROR; why = "Metadata I/O Error"; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index ba5d42abf66e..32a67f78fdd1 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -454,6 +454,7 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, uint32_t flags, char *fname, #define SHUTDOWN_LOG_IO_ERROR (1u << 1) /* write attempt to the log failed */ #define SHUTDOWN_FORCE_UMOUNT (1u << 2) /* shutdown from a forced unmount */ #define SHUTDOWN_CORRUPT_INCORE (1u << 3) /* corrupt in-memory structures */ +#define SHUTDOWN_CORRUPT_ONDISK (1u << 4) /* corrupt metadata on device */ #define XFS_SHUTDOWN_STRINGS \ { SHUTDOWN_META_IO_ERROR, "metadata_io" }, \ diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c new file mode 100644 index 000000000000..aa8dc27c599c --- /dev/null +++ b/fs/xfs/xfs_notify_failure.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Fujitsu. All Rights Reserved. + */ + +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_alloc.h" +#include "xfs_bit.h" +#include "xfs_btree.h" +#include "xfs_inode.h" +#include "xfs_icache.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_trans.h" + +#include +#include + +struct failure_info { + xfs_agblock_t startblock; + xfs_extlen_t blockcount; + int mf_flags; +}; + +static pgoff_t +xfs_failure_pgoff( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rec, + const struct failure_info *notify) +{ + loff_t pos = XFS_FSB_TO_B(mp, rec->rm_offset); + + if (notify->startblock > rec->rm_startblock) + pos += XFS_FSB_TO_B(mp, + notify->startblock - rec->rm_startblock); + return pos >> PAGE_SHIFT; +} + +static unsigned long +xfs_failure_pgcnt( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rec, + const struct failure_info *notify) +{ + xfs_agblock_t end_rec; + xfs_agblock_t end_notify; + xfs_agblock_t start_cross; + xfs_agblock_t end_cross; + + start_cross = max(rec->rm_startblock, notify->startblock); + + end_rec = rec->rm_startblock + rec->rm_blockcount; + end_notify = notify->startblock + notify->blockcount; + end_cross = min(end_rec, end_notify); + + return XFS_FSB_TO_B(mp, end_cross - start_cross) >> PAGE_SHIFT; +} + +static int +xfs_dax_failure_fn( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *data) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_inode *ip; + struct failure_info *notify = data; + int error = 0; + + if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) || + (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + + /* Get files that incore, filter out others that are not in use. */ + error = xfs_iget(mp, cur->bc_tp, rec->rm_owner, XFS_IGET_INCORE, + 0, &ip); + /* Continue the rmap query if the inode isn't incore */ + if (error == -ENODATA) + return 0; + if (error) + return error; + + error = mf_dax_kill_procs(VFS_I(ip)->i_mapping, + xfs_failure_pgoff(mp, rec, notify), + xfs_failure_pgcnt(mp, rec, notify), + notify->mf_flags); + xfs_irele(ip); + return error; +} + +static int +xfs_dax_notify_ddev_failure( + struct xfs_mount *mp, + xfs_daddr_t daddr, + xfs_daddr_t bblen, + int mf_flags) +{ + struct xfs_trans *tp = NULL; + struct xfs_btree_cur *cur = NULL; + struct xfs_buf *agf_bp = NULL; + int error = 0; + xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr); + xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno); + xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen); + xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno); + + error = xfs_trans_alloc_empty(mp, &tp); + if (error) + return error; + + for (; agno <= end_agno; agno++) { + struct xfs_rmap_irec ri_low = { }; + struct xfs_rmap_irec ri_high; + struct failure_info notify; + struct xfs_agf *agf; + xfs_agblock_t agend; + + error = xfs_alloc_read_agf(mp, tp, agno, 0, &agf_bp); + if (error) + break; + + cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, agf_bp->b_pag); + + /* + * Set the rmap range from ri_low to ri_high, which represents + * a [start, end] where we looking for the files or metadata. + */ + memset(&ri_high, 0xFF, sizeof(ri_high)); + ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno); + if (agno == end_agno) + ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); + + agf = agf_bp->b_addr; + agend = min(be32_to_cpu(agf->agf_length), + ri_high.rm_startblock); + notify.startblock = ri_low.rm_startblock; + notify.blockcount = agend - ri_low.rm_startblock; + + error = xfs_rmap_query_range(cur, &ri_low, &ri_high, + xfs_dax_failure_fn, ¬ify); + xfs_btree_del_cursor(cur, error); + xfs_trans_brelse(tp, agf_bp); + if (error) + break; + + fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0); + } + + xfs_trans_cancel(tp); + return error; +} + +static int +xfs_dax_notify_failure( + struct dax_device *dax_dev, + u64 offset, + u64 len, + int mf_flags) +{ + struct xfs_mount *mp = dax_holder(dax_dev); + u64 ddev_start; + u64 ddev_end; + + if (!(mp->m_sb.sb_flags & SB_BORN)) { + xfs_warn(mp, "filesystem is not ready for notify_failure()!"); + return -EIO; + } + + if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) { + xfs_warn(mp, + "notify_failure() not supported on realtime device!"); + return -EOPNOTSUPP; + } + + if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev && + mp->m_logdev_targp != mp->m_ddev_targp) { + xfs_err(mp, "ondisk log corrupt, shutting down fs!"); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + + if (!xfs_has_rmapbt(mp)) { + xfs_warn(mp, "notify_failure() needs rmapbt enabled!"); + return -EOPNOTSUPP; + } + + ddev_start = mp->m_ddev_targp->bt_dax_part_off; + ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1; + + /* Ignore the range out of filesystem area */ + if (offset + len < ddev_start) + return -ENXIO; + if (offset > ddev_end) + return -ENXIO; + + /* Calculate the real range when it touches the boundary */ + if (offset > ddev_start) + offset -= ddev_start; + else { + len -= ddev_start - offset; + offset = 0; + } + if (offset + len > ddev_end) + len -= ddev_end - offset; + + return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len), + mf_flags); +} + +const struct dax_holder_operations xfs_dax_holder_operations = { + .notify_failure = xfs_dax_notify_failure, +}; diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 3cd5a51bace1..364e2c2648a8 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -92,6 +92,7 @@ extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *, extern const struct export_operations xfs_export_operations; extern const struct quotactl_ops xfs_quotactl_operations; +extern const struct dax_holder_operations xfs_dax_holder_operations; extern void xfs_reinit_percpu_counters(struct xfs_mount *mp); -- cgit v1.2.3 From 6f7db3894ae23eb5d40af4efb404aa0c072a68d2 Mon Sep 17 00:00:00 2001 From: Shiyang Ruan Date: Fri, 3 Jun 2022 13:37:36 +0800 Subject: fsdax: dedup file range to use a compare function With dax we cannot deal with readpage() etc. So, we create a dax comparison function which is similar with vfs_dedupe_file_range_compare(). And introduce dax_remap_file_range_prep() for filesystem use. Link: https://lkml.kernel.org/r/20220603053738.1218681-13-ruansy.fnst@fujitsu.com Signed-off-by: Goldwyn Rodrigues Signed-off-by: Shiyang Ruan Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Dan Williams Cc: Dan Williams Cc: Dave Chinner Cc: Goldwyn Rodrigues Cc: Jane Chu Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Ritesh Harjani Signed-off-by: Andrew Morton --- fs/xfs/xfs_reflink.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index e7a7c00d93be..cbaf36d21020 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1367,8 +1367,12 @@ xfs_reflink_remap_prep( if (IS_DAX(inode_in) || IS_DAX(inode_out)) goto out_unlock; - ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, - len, remap_flags); + if (!IS_DAX(inode_in)) + ret = generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags); + else + ret = dax_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, &xfs_read_iomap_ops); if (ret || *len == 0) goto out_unlock; -- cgit v1.2.3 From ea6c49b784f0998297fb206af81c28dfaf8bb343 Mon Sep 17 00:00:00 2001 From: Shiyang Ruan Date: Fri, 3 Jun 2022 13:37:37 +0800 Subject: xfs: support CoW in fsdax mode In fsdax mode, WRITE and ZERO on a shared extent need CoW performed. After that, new allocated extents needs to be remapped to the file. So, add a CoW identification in ->iomap_begin(), and implement ->iomap_end() to do the remapping work. [akpm@linux-foundation.org: make xfs_dax_fault() static] Link: https://lkml.kernel.org/r/20220603053738.1218681-14-ruansy.fnst@fujitsu.com Signed-off-by: Shiyang Ruan Reviewed-by: Darrick J. Wong Cc: Al Viro Cc: Christoph Hellwig Cc: Dan Williams Cc: Dan Williams Cc: Dave Chinner Cc: Goldwyn Rodrigues Cc: Goldwyn Rodrigues Cc: Jane Chu Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Ritesh Harjani Signed-off-by: Andrew Morton --- fs/xfs/xfs_file.c | 33 ++++++++++++++++++++++++++++----- fs/xfs/xfs_iomap.c | 30 +++++++++++++++++++++++++++++- fs/xfs/xfs_iomap.h | 1 + 3 files changed, 58 insertions(+), 6 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 5a171c0b244b..45d8e64188f3 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -25,6 +25,7 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" +#include #include #include #include @@ -669,7 +670,7 @@ xfs_file_dax_write( pos = iocb->ki_pos; trace_xfs_file_dax_write(iocb, from); - ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops); + ret = dax_iomap_rw(iocb, from, &xfs_dax_write_iomap_ops); if (ret > 0 && iocb->ki_pos > i_size_read(inode)) { i_size_write(inode, iocb->ki_pos); error = xfs_setfilesize(ip, pos, ret); @@ -1254,6 +1255,31 @@ xfs_file_llseek( return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); } +#ifdef CONFIG_FS_DAX +static int +xfs_dax_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size, + bool write_fault, + pfn_t *pfn) +{ + return dax_iomap_fault(vmf, pe_size, pfn, NULL, + (write_fault && !vmf->cow_page) ? + &xfs_dax_write_iomap_ops : + &xfs_read_iomap_ops); +} +#else +static int +xfs_dax_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size, + bool write_fault, + pfn_t *pfn) +{ + return 0; +} +#endif + /* * Locking for serialisation of IO during page faults. This results in a lock * ordering of: @@ -1285,10 +1311,7 @@ __xfs_filemap_fault( pfn_t pfn; xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, - (write_fault && !vmf->cow_page) ? - &xfs_direct_write_iomap_ops : - &xfs_read_iomap_ops); + ret = xfs_dax_fault(vmf, pe_size, write_fault, &pfn); if (ret & VM_FAULT_NEEDDSYNC) ret = dax_finish_sync_fault(vmf, pe_size, pfn); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 5a393259a3a3..4c07f5e718fb 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -773,7 +773,8 @@ xfs_direct_write_iomap_begin( /* may drop and re-acquire the ilock */ error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared, - &lockmode, flags & IOMAP_DIRECT); + &lockmode, + (flags & IOMAP_DIRECT) || IS_DAX(inode)); if (error) goto out_unlock; if (shared) @@ -867,6 +868,33 @@ const struct iomap_ops xfs_direct_write_iomap_ops = { .iomap_begin = xfs_direct_write_iomap_begin, }; +static int +xfs_dax_write_iomap_end( + struct inode *inode, + loff_t pos, + loff_t length, + ssize_t written, + unsigned flags, + struct iomap *iomap) +{ + struct xfs_inode *ip = XFS_I(inode); + + if (!xfs_is_cow_inode(ip)) + return 0; + + if (!written) { + xfs_reflink_cancel_cow_range(ip, pos, length, true); + return 0; + } + + return xfs_reflink_end_cow(ip, pos, written); +} + +const struct iomap_ops xfs_dax_write_iomap_ops = { + .iomap_begin = xfs_direct_write_iomap_begin, + .iomap_end = xfs_dax_write_iomap_end, +}; + static int xfs_buffered_write_iomap_begin( struct inode *inode, diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index e88dc162c785..c782e8c0479c 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -51,5 +51,6 @@ extern const struct iomap_ops xfs_direct_write_iomap_ops; extern const struct iomap_ops xfs_read_iomap_ops; extern const struct iomap_ops xfs_seek_iomap_ops; extern const struct iomap_ops xfs_xattr_iomap_ops; +extern const struct iomap_ops xfs_dax_write_iomap_ops; #endif /* __XFS_IOMAP_H__*/ -- cgit v1.2.3 From 13f9e267fdbba30820ce3999338b7d8fe7d6bf77 Mon Sep 17 00:00:00 2001 From: Shiyang Ruan Date: Fri, 3 Jun 2022 13:37:38 +0800 Subject: xfs: add dax dedupe support Introduce xfs_mmaplock_two_inodes_and_break_dax_layout() for dax files who are going to be deduped. After that, call compare range function only when files are both DAX or not. Link: https://lkml.kernel.org/r/20220603053738.1218681-15-ruansy.fnst@fujitsu.com Signed-off-by: Shiyang Ruan Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Dan Williams Cc: Dan Williams Cc: Dave Chinner Cc: Goldwyn Rodrigues Cc: Goldwyn Rodrigues Cc: Jane Chu Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Ritesh Harjani Signed-off-by: Andrew Morton --- fs/xfs/xfs_file.c | 2 +- fs/xfs/xfs_inode.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++++--- fs/xfs/xfs_inode.h | 1 + fs/xfs/xfs_reflink.c | 4 +-- 4 files changed, 69 insertions(+), 7 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 45d8e64188f3..92a3af1e4414 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -808,7 +808,7 @@ xfs_wait_dax_page( xfs_ilock(ip, XFS_MMAPLOCK_EXCL); } -static int +int xfs_break_dax_layouts( struct inode *inode, bool *retry) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 52d6f2c7d58b..6f251781ebd0 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3767,6 +3767,50 @@ retry: return 0; } +static int +xfs_mmaplock_two_inodes_and_break_dax_layout( + struct xfs_inode *ip1, + struct xfs_inode *ip2) +{ + int error; + bool retry; + struct page *page; + + if (ip1->i_ino > ip2->i_ino) + swap(ip1, ip2); + +again: + retry = false; + /* Lock the first inode */ + xfs_ilock(ip1, XFS_MMAPLOCK_EXCL); + error = xfs_break_dax_layouts(VFS_I(ip1), &retry); + if (error || retry) { + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + if (error == 0 && retry) + goto again; + return error; + } + + if (ip1 == ip2) + return 0; + + /* Nested lock the second inode */ + xfs_ilock(ip2, xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1)); + /* + * We cannot use xfs_break_dax_layouts() directly here because it may + * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable + * for this nested lock case. + */ + page = dax_layout_busy_page(VFS_I(ip2)->i_mapping); + if (page && page_ref_count(page) != 1) { + xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + goto again; + } + + return 0; +} + /* * Lock two inodes so that userspace cannot initiate I/O via file syscalls or * mmap activity. @@ -3781,8 +3825,19 @@ xfs_ilock2_io_mmap( ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2)); if (ret) return ret; - filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping, - VFS_I(ip2)->i_mapping); + + if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { + ret = xfs_mmaplock_two_inodes_and_break_dax_layout(ip1, ip2); + if (ret) { + inode_unlock(VFS_I(ip2)); + if (ip1 != ip2) + inode_unlock(VFS_I(ip1)); + return ret; + } + } else + filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping, + VFS_I(ip2)->i_mapping); + return 0; } @@ -3792,8 +3847,14 @@ xfs_iunlock2_io_mmap( struct xfs_inode *ip1, struct xfs_inode *ip2) { - filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping, - VFS_I(ip2)->i_mapping); + if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { + xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); + if (ip1 != ip2) + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + } else + filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping, + VFS_I(ip2)->i_mapping); + inode_unlock(VFS_I(ip2)); if (ip1 != ip2) inode_unlock(VFS_I(ip1)); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 7be6f8e705ab..8313cc83b6ee 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -467,6 +467,7 @@ xfs_itruncate_extents( } /* from xfs_file.c */ +int xfs_break_dax_layouts(struct inode *inode, bool *retry); int xfs_break_layouts(struct inode *inode, uint *iolock, enum layout_break_reason reason); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index cbaf36d21020..d07f06ff0f13 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1363,8 +1363,8 @@ xfs_reflink_remap_prep( if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) goto out_unlock; - /* Don't share DAX file data for now. */ - if (IS_DAX(inode_in) || IS_DAX(inode_out)) + /* Don't share DAX file data with non-DAX file. */ + if (IS_DAX(inode_in) != IS_DAX(inode_out)) goto out_unlock; if (!IS_DAX(inode_in)) -- cgit v1.2.3 From 35fcd75af3edf035638e632bb49607cc8fc3cdf4 Mon Sep 17 00:00:00 2001 From: Shiyang Ruan Date: Thu, 9 Jun 2022 22:34:35 +0800 Subject: xfs: fail dax mount if reflink is enabled on a partition Failure notification is not supported on partitions. So, when we mount a reflink enabled xfs on a partition with dax option, let it fail with -EINVAL code. Link: https://lkml.kernel.org/r/20220609143435.393724-1-ruansy.fnst@fujitsu.com Signed-off-by: Shiyang Ruan Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Cc: Dave Chinner Signed-off-by: Andrew Morton --- fs/xfs/xfs_super.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'fs/xfs') diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index ed18160e6181..c440e90fecef 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -350,8 +350,10 @@ xfs_setup_dax_always( goto disable_dax; } - if (xfs_has_reflink(mp)) { - xfs_alert(mp, "DAX and reflink cannot be used together!"); + if (xfs_has_reflink(mp) && + bdev_is_partition(mp->m_ddev_targp->bt_bdev)) { + xfs_alert(mp, + "DAX and reflink cannot work with multi-partitions!"); return -EINVAL; } -- cgit v1.2.3