From b4de0e9be963b95c46c4a5426e94059923d236d6 Mon Sep 17 00:00:00 2001 From: John Garry Date: Mon, 3 Mar 2025 17:11:10 +0000 Subject: iomap: Rename IOMAP_ATOMIC -> IOMAP_ATOMIC_HW In future xfs will support a SW-based atomic write, so rename IOMAP_ATOMIC -> IOMAP_ATOMIC_HW to be clear which mode is being used. Also relocate setting of IOMAP_ATOMIC_HW to the write path in __iomap_dio_rw(), to be clear that this flag is only relevant to writes. Reviewed-by: "Darrick J. Wong" Signed-off-by: John Garry Link: https://lore.kernel.org/r/20250303171120.2837067-3-john.g.garry@oracle.com Signed-off-by: Christian Brauner --- Documentation/filesystems/iomap/operations.rst | 4 ++-- fs/ext4/inode.c | 2 +- fs/iomap/direct-io.c | 18 +++++++++--------- fs/iomap/trace.h | 2 +- include/linux/iomap.h | 2 +- 5 files changed, 14 insertions(+), 14 deletions(-) diff --git a/Documentation/filesystems/iomap/operations.rst b/Documentation/filesystems/iomap/operations.rst index d1535109587a..0b9d7be23bce 100644 --- a/Documentation/filesystems/iomap/operations.rst +++ b/Documentation/filesystems/iomap/operations.rst @@ -514,8 +514,8 @@ IOMAP_WRITE`` with any combination of the following enhancements: if the mapping is unwritten and the filesystem cannot handle zeroing the unaligned regions without exposing stale contents. - * ``IOMAP_ATOMIC``: This write is being issued with torn-write - protection. + * ``IOMAP_ATOMIC_HW``: This write is being issued with torn-write + protection based on HW-offload support. Only a single bio can be created for the write, and the write must not be split into multiple I/O requests, i.e. flag REQ_ATOMIC must be set. diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7c54ae5fcbd4..ba2f1e3db7c7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3467,7 +3467,7 @@ static inline bool ext4_want_directio_fallback(unsigned flags, ssize_t written) return false; /* atomic writes are all-or-nothing */ - if (flags & IOMAP_ATOMIC) + if (flags & IOMAP_ATOMIC_HW) return false; /* can only try again if we wrote nothing */ diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index e1e32e2bb0bf..c696ce980796 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -317,7 +317,7 @@ static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, * clearing the WRITE_THROUGH flag in the dio request. */ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio, - const struct iomap *iomap, bool use_fua, bool atomic) + const struct iomap *iomap, bool use_fua, bool atomic_hw) { blk_opf_t opflags = REQ_SYNC | REQ_IDLE; @@ -329,7 +329,7 @@ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio, opflags |= REQ_FUA; else dio->flags &= ~IOMAP_DIO_WRITE_THROUGH; - if (atomic) + if (atomic_hw) opflags |= REQ_ATOMIC; return opflags; @@ -340,8 +340,8 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) const struct iomap *iomap = &iter->iomap; struct inode *inode = iter->inode; unsigned int fs_block_size = i_blocksize(inode), pad; + bool atomic_hw = iter->flags & IOMAP_ATOMIC_HW; const loff_t length = iomap_length(iter); - bool atomic = iter->flags & IOMAP_ATOMIC; loff_t pos = iter->pos; blk_opf_t bio_opf; struct bio *bio; @@ -351,7 +351,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) u64 copied = 0; size_t orig_count; - if (atomic && length != fs_block_size) + if (atomic_hw && length != fs_block_size) return -EINVAL; if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) || @@ -428,7 +428,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) goto out; } - bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic); + bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic_hw); nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS); do { @@ -461,7 +461,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) } n = bio->bi_iter.bi_size; - if (WARN_ON_ONCE(atomic && n != length)) { + if (WARN_ON_ONCE(atomic_hw && n != length)) { /* * This bio should have covered the complete length, * which it doesn't, so error. We may need to zero out @@ -652,9 +652,6 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (iocb->ki_flags & IOCB_NOWAIT) iomi.flags |= IOMAP_NOWAIT; - if (iocb->ki_flags & IOCB_ATOMIC) - iomi.flags |= IOMAP_ATOMIC; - if (iov_iter_rw(iter) == READ) { /* reads can always complete inline */ dio->flags |= IOMAP_DIO_INLINE_COMP; @@ -689,6 +686,9 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, iomi.flags |= IOMAP_OVERWRITE_ONLY; } + if (iocb->ki_flags & IOCB_ATOMIC) + iomi.flags |= IOMAP_ATOMIC_HW; + /* for data sync or sync, we need sync completion processing */ if (iocb_is_dsync(iocb)) { dio->flags |= IOMAP_DIO_NEED_SYNC; diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index 9eab2c8ac3c5..69af89044ebd 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -99,7 +99,7 @@ DEFINE_RANGE_EVENT(iomap_dio_rw_queued); { IOMAP_FAULT, "FAULT" }, \ { IOMAP_DIRECT, "DIRECT" }, \ { IOMAP_NOWAIT, "NOWAIT" }, \ - { IOMAP_ATOMIC, "ATOMIC" } + { IOMAP_ATOMIC_HW, "ATOMIC_HW" } #define IOMAP_F_FLAGS_STRINGS \ { IOMAP_F_NEW, "NEW" }, \ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index ea29388b2fba..87cd7079aaf3 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -189,7 +189,7 @@ struct iomap_folio_ops { #else #define IOMAP_DAX 0 #endif /* CONFIG_FS_DAX */ -#define IOMAP_ATOMIC (1 << 9) +#define IOMAP_ATOMIC_HW (1 << 9) #define IOMAP_DONTCACHE (1 << 10) struct iomap_ops { -- cgit v1.2.3 From 794ca29dcc924cd3f16d12b6fba61074c992b8fd Mon Sep 17 00:00:00 2001 From: John Garry Date: Mon, 3 Mar 2025 17:11:13 +0000 Subject: iomap: Support SW-based atomic writes Currently atomic write support requires dedicated HW support. This imposes a restriction on the filesystem that disk blocks need to be aligned and contiguously mapped to FS blocks to issue atomic writes. XFS has no method to guarantee FS block alignment for regular, non-RT files. As such, atomic writes are currently limited to 1x FS block there. To deal with the scenario that we are issuing an atomic write over misaligned or discontiguous data blocks - and raise the atomic write size limit - support a SW-based software emulated atomic write mode. For XFS, this SW-based atomic writes would use CoW support to issue emulated untorn writes. It is the responsibility of the FS to detect discontiguous atomic writes and switch to IOMAP_DIO_ATOMIC_SW mode and retry the write. Indeed, SW-based atomic writes could be used always when the mounted bdev does not support HW offload, but this strategy is not initially expected to be used. Reviewed-by: "Darrick J. Wong" Signed-off-by: John Garry Link: https://lore.kernel.org/r/20250303171120.2837067-6-john.g.garry@oracle.com Signed-off-by: Christian Brauner --- Documentation/filesystems/iomap/operations.rst | 16 ++++++++++++++-- fs/iomap/direct-io.c | 4 +++- include/linux/iomap.h | 8 +++++++- 3 files changed, 24 insertions(+), 4 deletions(-) diff --git a/Documentation/filesystems/iomap/operations.rst b/Documentation/filesystems/iomap/operations.rst index 0b9d7be23bce..b08a79d11d9f 100644 --- a/Documentation/filesystems/iomap/operations.rst +++ b/Documentation/filesystems/iomap/operations.rst @@ -526,8 +526,20 @@ IOMAP_WRITE`` with any combination of the following enhancements: conversion or copy on write), all updates for the entire file range must be committed atomically as well. Only one space mapping is allowed per untorn write. - Untorn writes must be aligned to, and must not be longer than, a - single file block. + Untorn writes may be longer than a single file block. In all cases, + the mapping start disk block must have at least the same alignment as + the write offset. + + * ``IOMAP_ATOMIC_SW``: This write is being issued with torn-write + protection via a software mechanism provided by the filesystem. + All the disk block alignment and single bio restrictions which apply + to IOMAP_ATOMIC_HW do not apply here. + SW-based untorn writes would typically be used as a fallback when + HW-based untorn writes may not be issued, e.g. the range of the write + covers multiple extents, meaning that it is not possible to issue + a single bio. + All filesystem metadata updates for the entire file range must be + committed atomically as well. Callers commonly hold ``i_rwsem`` in shared or exclusive mode before calling this function. diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index c696ce980796..c594f2cf3ab4 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -686,7 +686,9 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, iomi.flags |= IOMAP_OVERWRITE_ONLY; } - if (iocb->ki_flags & IOCB_ATOMIC) + if (dio_flags & IOMAP_DIO_ATOMIC_SW) + iomi.flags |= IOMAP_ATOMIC_SW; + else if (iocb->ki_flags & IOCB_ATOMIC) iomi.flags |= IOMAP_ATOMIC_HW; /* for data sync or sync, we need sync completion processing */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 87cd7079aaf3..9cd93530013c 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -189,8 +189,9 @@ struct iomap_folio_ops { #else #define IOMAP_DAX 0 #endif /* CONFIG_FS_DAX */ -#define IOMAP_ATOMIC_HW (1 << 9) +#define IOMAP_ATOMIC_HW (1 << 9) /* HW-based torn-write protection */ #define IOMAP_DONTCACHE (1 << 10) +#define IOMAP_ATOMIC_SW (1 << 11)/* SW-based torn-write protection */ struct iomap_ops { /* @@ -502,6 +503,11 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_PARTIAL (1 << 2) +/* + * Use software-based torn-write protection. + */ +#define IOMAP_DIO_ATOMIC_SW (1 << 3) + ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); -- cgit v1.2.3 From 786e3080cbe916f6a4c0987124d4f930c1814a97 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Mon, 3 Mar 2025 17:11:14 +0000 Subject: iomap: Lift blocksize restriction on atomic writes Filesystems like ext4 can submit writes in multiples of blocksizes. But we still can't allow the writes to be split. Hence let's check if the iomap_length() is same as iter->len or not. It is the role of the FS to ensure that a single mapping may be created for an atomic write. The FS will also continue to check size and alignment legality. Signed-off-by: "Ritesh Harjani (IBM)" jpg: Tweak commit message Reviewed-by: "Darrick J. Wong" Signed-off-by: John Garry Link: https://lore.kernel.org/r/20250303171120.2837067-7-john.g.garry@oracle.com Signed-off-by: Christian Brauner --- fs/iomap/direct-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index c594f2cf3ab4..5299f70428ef 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -351,7 +351,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) u64 copied = 0; size_t orig_count; - if (atomic_hw && length != fs_block_size) + if (atomic_hw && length != iter->len) return -EINVAL; if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) || -- cgit v1.2.3 From 5d138b6fb4da63b46981bca744f8f262d2524281 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 3 Mar 2025 18:02:32 +0000 Subject: xfs: Use abs_diff instead of XFS_ABSDIFF We have a central definition for this function since 2023, used by a number of different parts of the kernel. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Carlos Maiolino Reviewed-by: Eric Sandeen Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_alloc.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 3d33e17f2e5c..7839efe050bf 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -33,8 +33,6 @@ struct kmem_cache *xfs_extfree_item_cache; struct workqueue_struct *xfs_alloc_wq; -#define XFS_ABSDIFF(a,b) (((a) <= (b)) ? ((b) - (a)) : ((a) - (b))) - #define XFSA_FIXUP_BNO_OK 1 #define XFSA_FIXUP_CNT_OK 2 @@ -410,8 +408,8 @@ xfs_alloc_compute_diff( if (newbno1 != NULLAGBLOCK && newbno2 != NULLAGBLOCK) { if (newlen1 < newlen2 || (newlen1 == newlen2 && - XFS_ABSDIFF(newbno1, wantbno) > - XFS_ABSDIFF(newbno2, wantbno))) + abs_diff(newbno1, wantbno) > + abs_diff(newbno2, wantbno))) newbno1 = newbno2; } else if (newbno2 != NULLAGBLOCK) newbno1 = newbno2; @@ -427,7 +425,7 @@ xfs_alloc_compute_diff( } else newbno1 = freeend - wantlen; *newbnop = newbno1; - return newbno1 == NULLAGBLOCK ? 0 : XFS_ABSDIFF(newbno1, wantbno); + return newbno1 == NULLAGBLOCK ? 0 : abs_diff(newbno1, wantbno); } /* -- cgit v1.2.3 From 69659e46b7588d2fd5e4644dec9e61127bbfd5f3 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 10 Mar 2025 14:19:04 +0100 Subject: xfs: unmapped buffer item size straddling mismatch We never log large contiguous regions of unmapped buffers, so this bug is never triggered by the current code. However, the slowpath for formatting buffer straddling regions is broken. That is, the size and shape of the log vector calculated across a straddle does not match how the formatting code formats a straddle. This results in a log vector with an uninitialised iovec and this causes a crash when xlog_write_full() goes to copy the iovec into the journal. Whilst touching this code, don't bother checking mapped or single folio buffers for discontiguous regions because they don't have them. This significantly reduces the overhead of this check when logging large buffers as calling xfs_buf_offset() is not free and it occurs a *lot* in those cases. Fixes: 929f8b0deb83 ("xfs: optimise xfs_buf_item_size/format for contiguous regions") Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf_item.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 47549cfa61cd..0ee6fa9efd18 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -57,6 +57,10 @@ xfs_buf_log_format_size( (blfp->blf_map_size * sizeof(blfp->blf_data_map[0])); } +/* + * We only have to worry about discontiguous buffer range straddling on unmapped + * buffers. Everything else will have a contiguous data region we can copy from. + */ static inline bool xfs_buf_item_straddle( struct xfs_buf *bp, @@ -66,6 +70,9 @@ xfs_buf_item_straddle( { void *first, *last; + if (bp->b_page_count == 1 || !(bp->b_flags & XBF_UNMAPPED)) + return false; + first = xfs_buf_offset(bp, offset + (first_bit << XFS_BLF_SHIFT)); last = xfs_buf_offset(bp, offset + ((first_bit + nbits) << XFS_BLF_SHIFT)); @@ -133,11 +140,13 @@ xfs_buf_item_size_segment( return; slow_scan: - /* Count the first bit we jumped out of the above loop from */ - (*nvecs)++; - *nbytes += XFS_BLF_CHUNK; + ASSERT(bp->b_addr == NULL); last_bit = first_bit; + nbits = 1; while (last_bit != -1) { + + *nbytes += XFS_BLF_CHUNK; + /* * This takes the bit number to start looking from and * returns the next set bit from there. It returns -1 @@ -152,6 +161,8 @@ slow_scan: * else keep scanning the current set of bits. */ if (next_bit == -1) { + if (first_bit != last_bit) + (*nvecs)++; break; } else if (next_bit != last_bit + 1 || xfs_buf_item_straddle(bp, offset, first_bit, nbits)) { @@ -163,7 +174,6 @@ slow_scan: last_bit++; nbits++; } - *nbytes += XFS_BLF_CHUNK; } } -- cgit v1.2.3 From f2a3717a74c2cf01e29ea3aba355e171eb0d5f5f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:05 +0100 Subject: xfs: add a fast path to xfs_buf_zero when b_addr is set No need to walk the page list if bp->b_addr is valid. That also means b_offset doesn't need to be taken into account in the unmapped loop as b_offset is only set for kmem backed buffers which are always mapped. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 5d560e9073f4..ba0bdff3ad57 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1633,13 +1633,18 @@ xfs_buf_zero( { size_t bend; + if (bp->b_addr) { + memset(bp->b_addr + boff, 0, bsize); + return; + } + bend = boff + bsize; while (boff < bend) { struct page *page; int page_index, page_offset, csize; - page_index = (boff + bp->b_offset) >> PAGE_SHIFT; - page_offset = (boff + bp->b_offset) & ~PAGE_MASK; + page_index = boff >> PAGE_SHIFT; + page_offset = boff & ~PAGE_MASK; page = bp->b_pages[page_index]; csize = min_t(size_t, PAGE_SIZE - page_offset, BBTOB(bp->b_length) - boff); -- cgit v1.2.3 From 51e10993153adc14e8caf2a13d6defc8403dfb4c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:06 +0100 Subject: xfs: remove xfs_buf.b_offset b_offset is only set for slab backed buffers and always set to offset_in_page(bp->b_addr), which can be done just as easily in the only user of b_offset. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 3 +-- fs/xfs/xfs_buf.h | 2 -- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index ba0bdff3ad57..972ea34ecfd4 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -278,7 +278,6 @@ xfs_buf_alloc_kmem( bp->b_addr = NULL; return -ENOMEM; } - bp->b_offset = offset_in_page(bp->b_addr); bp->b_pages = bp->b_page_array; bp->b_pages[0] = kmem_to_page(bp->b_addr); bp->b_page_count = 1; @@ -1474,7 +1473,7 @@ xfs_buf_submit_bio( if (bp->b_flags & _XBF_KMEM) { __bio_add_page(bio, virt_to_page(bp->b_addr), size, - bp->b_offset); + offset_in_page(bp->b_addr)); } else { for (p = 0; p < bp->b_page_count; p++) __bio_add_page(bio, bp->b_pages[p], PAGE_SIZE, 0); diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 80e06eecaf56..c92a328252cc 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -194,8 +194,6 @@ struct xfs_buf { int b_map_count; atomic_t b_pin_count; /* pin count */ unsigned int b_page_count; /* size of page array */ - unsigned int b_offset; /* page offset of b_addr, - only for _XBF_KMEM buffers */ int b_error; /* error code on I/O */ void (*b_iodone)(struct xfs_buf *bp); -- cgit v1.2.3 From 48a325a4eec3251c2ead7ad7dad304bbdc1460a0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:07 +0100 Subject: xfs: remove xfs_buf_is_vmapped No need to look at the page count if we can simply call is_vmalloc_addr on bp->b_addr. This prepares for eventualy removing the b_page_count field. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 972ea34ecfd4..58eaf5a13c12 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -55,20 +55,6 @@ static inline bool xfs_buf_is_uncached(struct xfs_buf *bp) return bp->b_rhash_key == XFS_BUF_DADDR_NULL; } -static inline int -xfs_buf_is_vmapped( - struct xfs_buf *bp) -{ - /* - * Return true if the buffer is vmapped. - * - * b_addr is null if the buffer is not mapped, but the code is clever - * enough to know it doesn't have to map a single page, so the check has - * to be both for b_addr and bp->b_page_count > 1. - */ - return bp->b_addr && bp->b_page_count > 1; -} - static inline int xfs_buf_vmap_len( struct xfs_buf *bp) @@ -212,7 +198,7 @@ xfs_buf_free_pages( ASSERT(bp->b_flags & _XBF_PAGES); - if (xfs_buf_is_vmapped(bp)) + if (is_vmalloc_addr(bp->b_addr)) vm_unmap_ram(bp->b_addr, bp->b_page_count); for (i = 0; i < bp->b_page_count; i++) { @@ -1298,7 +1284,7 @@ __xfs_buf_ioend( trace_xfs_buf_iodone(bp, _RET_IP_); if (bp->b_flags & XBF_READ) { - if (!bp->b_error && xfs_buf_is_vmapped(bp)) + if (!bp->b_error && bp->b_addr && is_vmalloc_addr(bp->b_addr)) invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); if (!bp->b_error && bp->b_ops) @@ -1479,7 +1465,7 @@ xfs_buf_submit_bio( __bio_add_page(bio, bp->b_pages[p], PAGE_SIZE, 0); bio->bi_iter.bi_size = size; /* limit to the actual size used */ - if (xfs_buf_is_vmapped(bp)) + if (bp->b_addr && is_vmalloc_addr(bp->b_addr)) flush_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); } -- cgit v1.2.3 From 50a524e0ef9be0e862207fc822ab4b7dcb0c4310 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:08 +0100 Subject: xfs: refactor backing memory allocations for buffers Lift handling of shmem and slab backed buffers into xfs_buf_alloc_pages and rename the result to xfs_buf_alloc_backing_mem. This shares more code and ensures uncached buffers can also use slab, which slightly reduces the memory usage of growfs on 512 byte sector size file systems, but more importantly means the allocation invariants are the same for cached and uncached buffers. Document these new invariants with a big fat comment mostly stolen from a patch by Dave Chinner. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 55 ++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 36 insertions(+), 19 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 58eaf5a13c12..18ec1c1fbca1 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -271,19 +271,49 @@ xfs_buf_alloc_kmem( return 0; } +/* + * Allocate backing memory for a buffer. + * + * For tmpfs-backed buffers used by in-memory btrees this directly maps the + * tmpfs page cache folios. + * + * For real file system buffers there are two different kinds backing memory: + * + * The first type backs the buffer by a kmalloc allocation. This is done for + * less than PAGE_SIZE allocations to avoid wasting memory. + * + * The second type of buffer is the multi-page buffer. These are always made + * up of single pages so that they can be fed to vmap_ram() to return a + * contiguous memory region we can access the data through, or mark it as + * XBF_UNMAPPED and access the data directly through individual page_address() + * calls. + */ static int -xfs_buf_alloc_pages( +xfs_buf_alloc_backing_mem( struct xfs_buf *bp, xfs_buf_flags_t flags) { + size_t size = BBTOB(bp->b_length); gfp_t gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOWARN; long filled = 0; + if (xfs_buftarg_is_mem(bp->b_target)) + return xmbuf_map_page(bp); + + /* + * For buffers that fit entirely within a single page, first attempt to + * allocate the memory from the heap to minimise memory usage. If we + * can't get heap memory for these small buffers, we fall back to using + * the page allocator. + */ + if (size < PAGE_SIZE && xfs_buf_alloc_kmem(new_bp, flags) == 0) + return 0; + if (flags & XBF_READ_AHEAD) gfp_mask |= __GFP_NORETRY; /* Make sure that we have a page list */ - bp->b_page_count = DIV_ROUND_UP(BBTOB(bp->b_length), PAGE_SIZE); + bp->b_page_count = DIV_ROUND_UP(size, PAGE_SIZE); if (bp->b_page_count <= XB_PAGES) { bp->b_pages = bp->b_page_array; } else { @@ -564,18 +594,7 @@ xfs_buf_find_insert( if (error) goto out_drop_pag; - if (xfs_buftarg_is_mem(new_bp->b_target)) { - error = xmbuf_map_page(new_bp); - } else if (BBTOB(new_bp->b_length) >= PAGE_SIZE || - xfs_buf_alloc_kmem(new_bp, flags) < 0) { - /* - * For buffers that fit entirely within a single page, first - * attempt to allocate the memory from the heap to minimise - * memory usage. If we can't get heap memory for these small - * buffers, we fall back to using the page allocator. - */ - error = xfs_buf_alloc_pages(new_bp, flags); - } + error = xfs_buf_alloc_backing_mem(new_bp, flags); if (error) goto out_free_buf; @@ -939,14 +958,12 @@ xfs_buf_get_uncached( if (error) return error; - if (xfs_buftarg_is_mem(bp->b_target)) - error = xmbuf_map_page(bp); - else - error = xfs_buf_alloc_pages(bp, flags); + error = xfs_buf_alloc_backing_mem(bp, flags); if (error) goto fail_free_buf; - error = _xfs_buf_map_pages(bp, 0); + if (!bp->b_addr) + error = _xfs_buf_map_pages(bp, 0); if (unlikely(error)) { xfs_warn(target->bt_mount, "%s: failed to map pages", __func__); -- cgit v1.2.3 From 4ef39828318220f11050984fb8dbc372c9c03960 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:09 +0100 Subject: xfs: remove the kmalloc to page allocator fallback Since commit 59bb47985c1d ("mm, sl[aou]b: guarantee natural alignment for kmalloc(power-of-two)", kmalloc and friends guarantee that power of two sized allocations are naturally aligned. Limit our use of kmalloc for buffers to these power of two sizes and remove the fallback to the page allocator for this case, but keep a check in addition to trusting the slab allocator to get the alignment right. Also refactor the kmalloc path to reuse various calculations for the size and gfp flags. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 48 ++++++++++++++++++++++++------------------------ 1 file changed, 24 insertions(+), 24 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 18ec1c1fbca1..acf19b5221bf 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -243,23 +243,23 @@ xfs_buf_free( static int xfs_buf_alloc_kmem( - struct xfs_buf *bp, - xfs_buf_flags_t flags) + struct xfs_buf *bp, + size_t size, + gfp_t gfp_mask) { - gfp_t gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL; - size_t size = BBTOB(bp->b_length); - - /* Assure zeroed buffer for non-read cases. */ - if (!(flags & XBF_READ)) - gfp_mask |= __GFP_ZERO; + ASSERT(is_power_of_2(size)); + ASSERT(size < PAGE_SIZE); - bp->b_addr = kmalloc(size, gfp_mask); + bp->b_addr = kmalloc(size, gfp_mask | __GFP_NOFAIL); if (!bp->b_addr) return -ENOMEM; - if (((unsigned long)(bp->b_addr + size - 1) & PAGE_MASK) != - ((unsigned long)bp->b_addr & PAGE_MASK)) { - /* b_addr spans two pages - use alloc_page instead */ + /* + * Slab guarantees that we get back naturally aligned allocations for + * power of two sizes. Keep this check as the canary in the coal mine + * if anything changes in slab. + */ + if (WARN_ON_ONCE(!IS_ALIGNED((unsigned long)bp->b_addr, size))) { kfree(bp->b_addr); bp->b_addr = NULL; return -ENOMEM; @@ -300,18 +300,22 @@ xfs_buf_alloc_backing_mem( if (xfs_buftarg_is_mem(bp->b_target)) return xmbuf_map_page(bp); - /* - * For buffers that fit entirely within a single page, first attempt to - * allocate the memory from the heap to minimise memory usage. If we - * can't get heap memory for these small buffers, we fall back to using - * the page allocator. - */ - if (size < PAGE_SIZE && xfs_buf_alloc_kmem(new_bp, flags) == 0) - return 0; + /* Assure zeroed buffer for non-read cases. */ + if (!(flags & XBF_READ)) + gfp_mask |= __GFP_ZERO; if (flags & XBF_READ_AHEAD) gfp_mask |= __GFP_NORETRY; + /* + * For buffers smaller than PAGE_SIZE use a kmalloc allocation if that + * is properly aligned. The slab allocator now guarantees an aligned + * allocation for all power of two sizes, which matches most of the + * smaller than PAGE_SIZE buffers used by XFS. + */ + if (size < PAGE_SIZE && is_power_of_2(size)) + return xfs_buf_alloc_kmem(bp, size, gfp_mask); + /* Make sure that we have a page list */ bp->b_page_count = DIV_ROUND_UP(size, PAGE_SIZE); if (bp->b_page_count <= XB_PAGES) { @@ -324,10 +328,6 @@ xfs_buf_alloc_backing_mem( } bp->b_flags |= _XBF_PAGES; - /* Assure zeroed buffer for non-read cases. */ - if (!(flags & XBF_READ)) - gfp_mask |= __GFP_ZERO; - /* * Bulk filling of pages can take multiple calls. Not filling the entire * array is not an allocation failure, so don't back off if we get at -- cgit v1.2.3 From 94c78cfa3bd1858eec3c462aedeb7f297d38d768 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:10 +0100 Subject: xfs: convert buffer cache to use high order folios Now that we have the buffer cache using the folio API, we can extend the use of folios to allocate high order folios for multi-page buffers rather than an array of single pages that are then vmapped into a contiguous range. This creates a new type of single folio buffers that can have arbitrary order in addition to the existing multi-folio buffers made up of many single page folios that get vmapped. The single folio is for now stashed into the existing b_pages array, but that will go away entirely later in the series and remove the temporary page vs folio typing issues that only work because the two structures currently can be used largely interchangeable. The code that allocates buffers will optimistically attempt a high order folio allocation as a fast path if the buffer size is a power of two and thus fits into a folio. If this high order allocation fails, then we fall back to the existing multi-folio allocation code. This now forms the slow allocation path, and hopefully will be largely unused in normal conditions except for buffers with size that are not a power of two like larger remote xattrs. This should improve performance of large buffer operations (e.g. large directory block sizes) as we should now mostly avoid the expense of vmapping large buffers (and the vmap lock contention that can occur) as well as avoid the runtime pressure that frequently accessing kernel vmapped pages put on the TLBs. Based on a patch from Dave Chinner , but mutilated beyond recognition. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 50 insertions(+), 6 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index acf19b5221bf..a831e8c755cb 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -203,9 +203,9 @@ xfs_buf_free_pages( for (i = 0; i < bp->b_page_count; i++) { if (bp->b_pages[i]) - __free_page(bp->b_pages[i]); + folio_put(page_folio(bp->b_pages[i])); } - mm_account_reclaimed_pages(bp->b_page_count); + mm_account_reclaimed_pages(howmany(BBTOB(bp->b_length), PAGE_SIZE)); if (bp->b_pages != bp->b_page_array) kfree(bp->b_pages); @@ -277,12 +277,17 @@ xfs_buf_alloc_kmem( * For tmpfs-backed buffers used by in-memory btrees this directly maps the * tmpfs page cache folios. * - * For real file system buffers there are two different kinds backing memory: + * For real file system buffers there are three different kinds backing memory: * * The first type backs the buffer by a kmalloc allocation. This is done for * less than PAGE_SIZE allocations to avoid wasting memory. * - * The second type of buffer is the multi-page buffer. These are always made + * The second type is a single folio buffer - this may be a high order folio or + * just a single page sized folio, but either way they get treated the same way + * by the rest of the code - the buffer memory spans a single contiguous memory + * region that we don't have to map and unmap to access the data directly. + * + * The third type of buffer is the multi-page buffer. These are always made * up of single pages so that they can be fed to vmap_ram() to return a * contiguous memory region we can access the data through, or mark it as * XBF_UNMAPPED and access the data directly through individual page_address() @@ -295,6 +300,7 @@ xfs_buf_alloc_backing_mem( { size_t size = BBTOB(bp->b_length); gfp_t gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOWARN; + struct folio *folio; long filled = 0; if (xfs_buftarg_is_mem(bp->b_target)) @@ -316,7 +322,45 @@ xfs_buf_alloc_backing_mem( if (size < PAGE_SIZE && is_power_of_2(size)) return xfs_buf_alloc_kmem(bp, size, gfp_mask); - /* Make sure that we have a page list */ + /* + * Don't bother with the retry loop for single PAGE allocations: vmalloc + * won't do any better. + */ + if (size <= PAGE_SIZE) + gfp_mask |= __GFP_NOFAIL; + + /* + * Optimistically attempt a single high order folio allocation for + * larger than PAGE_SIZE buffers. + * + * Allocating a high order folio makes the assumption that buffers are a + * power-of-2 size, matching the power-of-2 folios sizes available. + * + * The exception here are user xattr data buffers, which can be arbitrarily + * sized up to 64kB plus structure metadata, skip straight to the vmalloc + * path for them instead of wasting memory here. + */ + if (size > PAGE_SIZE) { + if (!is_power_of_2(size)) + goto fallback; + gfp_mask &= ~__GFP_DIRECT_RECLAIM; + gfp_mask |= __GFP_NORETRY; + } + folio = folio_alloc(gfp_mask, get_order(size)); + if (!folio) { + if (size <= PAGE_SIZE) + return -ENOMEM; + goto fallback; + } + bp->b_addr = folio_address(folio); + bp->b_page_array[0] = &folio->page; + bp->b_pages = bp->b_page_array; + bp->b_page_count = 1; + bp->b_flags |= _XBF_PAGES; + return 0; + +fallback: + /* Fall back to allocating an array of single page folios. */ bp->b_page_count = DIV_ROUND_UP(size, PAGE_SIZE); if (bp->b_page_count <= XB_PAGES) { bp->b_pages = bp->b_page_array; @@ -1474,7 +1518,7 @@ xfs_buf_submit_bio( bio->bi_private = bp; bio->bi_end_io = xfs_buf_bio_end_io; - if (bp->b_flags & _XBF_KMEM) { + if (bp->b_page_count == 1) { __bio_add_page(bio, virt_to_page(bp->b_addr), size, offset_in_page(bp->b_addr)); } else { -- cgit v1.2.3 From a2f790b28512c22f7cf4f420a99e1b008e7098fe Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:11 +0100 Subject: xfs: kill XBF_UNMAPPED Unmapped buffer access is a pain, so kill it. The switch to large folios means we rarely pay a vmap penalty for large buffers, so this functionality is largely unnecessary now. Signed-off-by: Christoph Hellwig Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_ialloc.c | 2 +- fs/xfs/libxfs/xfs_inode_buf.c | 2 +- fs/xfs/scrub/inode_repair.c | 3 +-- fs/xfs/xfs_buf.c | 58 +++---------------------------------------- fs/xfs/xfs_buf.h | 16 ++++++++---- fs/xfs/xfs_buf_item.c | 2 +- fs/xfs/xfs_buf_item_recover.c | 8 +----- fs/xfs/xfs_inode.c | 3 +-- 8 files changed, 21 insertions(+), 73 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 57513ba19d6a..0c47b5c6ca7d 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -364,7 +364,7 @@ xfs_ialloc_inode_init( (j * M_IGEO(mp)->blocks_per_cluster)); error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize * M_IGEO(mp)->blocks_per_cluster, - XBF_UNMAPPED, &fbuf); + 0, &fbuf); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 992e6d337709..aa13fc00afd7 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -137,7 +137,7 @@ xfs_imap_to_bp( int error; error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno, - imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops); + imap->im_len, 0, bpp, &xfs_inode_buf_ops); if (xfs_metadata_is_sick(error)) xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno), XFS_SICK_AG_INODES); diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 4299063ffe87..a90a011c7e5f 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -1560,8 +1560,7 @@ xrep_dinode_core( /* Read the inode cluster buffer. */ error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp, - ri->imap.im_blkno, ri->imap.im_len, XBF_UNMAPPED, &bp, - NULL); + ri->imap.im_blkno, ri->imap.im_len, 0, &bp, NULL); if (error) return error; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index a831e8c755cb..b5ec7d83210f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -145,7 +145,7 @@ _xfs_buf_alloc( * We don't want certain flags to appear in b_flags unless they are * specifically set by later operations on the buffer. */ - flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD); + flags &= ~(XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD); /* * A new buffer is held and locked by the owner. This ensures that the @@ -289,9 +289,7 @@ xfs_buf_alloc_kmem( * * The third type of buffer is the multi-page buffer. These are always made * up of single pages so that they can be fed to vmap_ram() to return a - * contiguous memory region we can access the data through, or mark it as - * XBF_UNMAPPED and access the data directly through individual page_address() - * calls. + * contiguous memory region we can access the data through. */ static int xfs_buf_alloc_backing_mem( @@ -413,8 +411,6 @@ _xfs_buf_map_pages( if (bp->b_page_count == 1) { /* A single page buffer is always mappable */ bp->b_addr = page_address(bp->b_pages[0]); - } else if (flags & XBF_UNMAPPED) { - bp->b_addr = NULL; } else { int retried = 0; unsigned nofs_flag; @@ -1345,7 +1341,7 @@ __xfs_buf_ioend( trace_xfs_buf_iodone(bp, _RET_IP_); if (bp->b_flags & XBF_READ) { - if (!bp->b_error && bp->b_addr && is_vmalloc_addr(bp->b_addr)) + if (!bp->b_error && is_vmalloc_addr(bp->b_addr)) invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); if (!bp->b_error && bp->b_ops) @@ -1526,7 +1522,7 @@ xfs_buf_submit_bio( __bio_add_page(bio, bp->b_pages[p], PAGE_SIZE, 0); bio->bi_iter.bi_size = size; /* limit to the actual size used */ - if (bp->b_addr && is_vmalloc_addr(bp->b_addr)) + if (is_vmalloc_addr(bp->b_addr)) flush_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); } @@ -1657,52 +1653,6 @@ xfs_buf_submit( xfs_buf_submit_bio(bp); } -void * -xfs_buf_offset( - struct xfs_buf *bp, - size_t offset) -{ - struct page *page; - - if (bp->b_addr) - return bp->b_addr + offset; - - page = bp->b_pages[offset >> PAGE_SHIFT]; - return page_address(page) + (offset & (PAGE_SIZE-1)); -} - -void -xfs_buf_zero( - struct xfs_buf *bp, - size_t boff, - size_t bsize) -{ - size_t bend; - - if (bp->b_addr) { - memset(bp->b_addr + boff, 0, bsize); - return; - } - - bend = boff + bsize; - while (boff < bend) { - struct page *page; - int page_index, page_offset, csize; - - page_index = boff >> PAGE_SHIFT; - page_offset = boff & ~PAGE_MASK; - page = bp->b_pages[page_index]; - csize = min_t(size_t, PAGE_SIZE - page_offset, - BBTOB(bp->b_length) - boff); - - ASSERT((csize + page_offset) <= PAGE_SIZE); - - memset(page_address(page) + page_offset, 0, csize); - - boff += csize; - } -} - /* * Log a message about and stale a buffer that a caller has decided is corrupt. * diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index c92a328252cc..8db522f19b0c 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -48,7 +48,6 @@ struct xfs_buf; #define XBF_LIVESCAN (1u << 28) #define XBF_INCORE (1u << 29)/* lookup only, return if found in cache */ #define XBF_TRYLOCK (1u << 30)/* lock requested, but do not wait */ -#define XBF_UNMAPPED (1u << 31)/* do not map the buffer */ typedef unsigned int xfs_buf_flags_t; @@ -68,8 +67,7 @@ typedef unsigned int xfs_buf_flags_t; /* The following interface flags should never be set */ \ { XBF_LIVESCAN, "LIVESCAN" }, \ { XBF_INCORE, "INCORE" }, \ - { XBF_TRYLOCK, "TRYLOCK" }, \ - { XBF_UNMAPPED, "UNMAPPED" } + { XBF_TRYLOCK, "TRYLOCK" } /* * Internal state flags. @@ -313,12 +311,20 @@ extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error, #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address) extern void xfs_buf_ioerror_alert(struct xfs_buf *bp, xfs_failaddr_t fa); void xfs_buf_ioend_fail(struct xfs_buf *); -void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize); void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa); #define xfs_buf_mark_corrupt(bp) __xfs_buf_mark_corrupt((bp), __this_address) /* Buffer Utility Routines */ -extern void *xfs_buf_offset(struct xfs_buf *, size_t); +static inline void *xfs_buf_offset(struct xfs_buf *bp, size_t offset) +{ + return bp->b_addr + offset; +} + +static inline void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize) +{ + memset(bp->b_addr + boff, 0, bsize); +} + extern void xfs_buf_stale(struct xfs_buf *bp); /* Delayed Write Buffer Routines */ diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 0ee6fa9efd18..41f0bc9aa5f4 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -70,7 +70,7 @@ xfs_buf_item_straddle( { void *first, *last; - if (bp->b_page_count == 1 || !(bp->b_flags & XBF_UNMAPPED)) + if (bp->b_page_count == 1) return false; first = xfs_buf_offset(bp, offset + (first_bit << XFS_BLF_SHIFT)); diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index 05a2f6927c12..d4c5cef5bc43 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -1006,7 +1006,6 @@ xlog_recover_buf_commit_pass2( struct xfs_mount *mp = log->l_mp; struct xfs_buf *bp; int error; - uint buf_flags; xfs_lsn_t lsn; /* @@ -1025,13 +1024,8 @@ xlog_recover_buf_commit_pass2( } trace_xfs_log_recover_buf_recover(log, buf_f); - - buf_flags = 0; - if (buf_f->blf_flags & XFS_BLF_INODE_BUF) - buf_flags |= XBF_UNMAPPED; - error = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len, - buf_flags, &bp, NULL); + 0, &bp, NULL); if (error) return error; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 7ded570e0191..ce6b8ffbaa2c 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1721,8 +1721,7 @@ xfs_ifree_cluster( * to mark all the active inodes on the buffer stale. */ error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, - mp->m_bsize * igeo->blocks_per_cluster, - XBF_UNMAPPED, &bp); + mp->m_bsize * igeo->blocks_per_cluster, 0, &bp); if (error) return error; -- cgit v1.2.3 From fd87851680edcb931b2ec4caf23b4abbea126fc3 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 10 Mar 2025 14:19:12 +0100 Subject: xfs: buffer items don't straddle pages anymore Unmapped buffers don't exist anymore, so the page straddling detection and slow path code can go away now. Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf_item.c | 124 -------------------------------------------------- 1 file changed, 124 deletions(-) diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 41f0bc9aa5f4..19eb0b7a3e58 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -57,31 +57,6 @@ xfs_buf_log_format_size( (blfp->blf_map_size * sizeof(blfp->blf_data_map[0])); } -/* - * We only have to worry about discontiguous buffer range straddling on unmapped - * buffers. Everything else will have a contiguous data region we can copy from. - */ -static inline bool -xfs_buf_item_straddle( - struct xfs_buf *bp, - uint offset, - int first_bit, - int nbits) -{ - void *first, *last; - - if (bp->b_page_count == 1) - return false; - - first = xfs_buf_offset(bp, offset + (first_bit << XFS_BLF_SHIFT)); - last = xfs_buf_offset(bp, - offset + ((first_bit + nbits) << XFS_BLF_SHIFT)); - - if (last - first != nbits * XFS_BLF_CHUNK) - return true; - return false; -} - /* * Return the number of log iovecs and space needed to log the given buf log * item segment. @@ -98,11 +73,8 @@ xfs_buf_item_size_segment( int *nvecs, int *nbytes) { - struct xfs_buf *bp = bip->bli_buf; int first_bit; int nbits; - int next_bit; - int last_bit; first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0); if (first_bit == -1) @@ -115,15 +87,6 @@ xfs_buf_item_size_segment( nbits = xfs_contig_bits(blfp->blf_data_map, blfp->blf_map_size, first_bit); ASSERT(nbits > 0); - - /* - * Straddling a page is rare because we don't log contiguous - * chunks of unmapped buffers anywhere. - */ - if (nbits > 1 && - xfs_buf_item_straddle(bp, offset, first_bit, nbits)) - goto slow_scan; - (*nvecs)++; *nbytes += nbits * XFS_BLF_CHUNK; @@ -138,43 +101,6 @@ xfs_buf_item_size_segment( } while (first_bit != -1); return; - -slow_scan: - ASSERT(bp->b_addr == NULL); - last_bit = first_bit; - nbits = 1; - while (last_bit != -1) { - - *nbytes += XFS_BLF_CHUNK; - - /* - * This takes the bit number to start looking from and - * returns the next set bit from there. It returns -1 - * if there are no more bits set or the start bit is - * beyond the end of the bitmap. - */ - next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, - last_bit + 1); - /* - * If we run out of bits, leave the loop, - * else if we find a new set of bits bump the number of vecs, - * else keep scanning the current set of bits. - */ - if (next_bit == -1) { - if (first_bit != last_bit) - (*nvecs)++; - break; - } else if (next_bit != last_bit + 1 || - xfs_buf_item_straddle(bp, offset, first_bit, nbits)) { - last_bit = next_bit; - first_bit = next_bit; - (*nvecs)++; - nbits = 1; - } else { - last_bit++; - nbits++; - } - } } /* @@ -287,8 +213,6 @@ xfs_buf_item_format_segment( struct xfs_buf *bp = bip->bli_buf; uint base_size; int first_bit; - int last_bit; - int next_bit; uint nbits; /* copy the flags across from the base format item */ @@ -333,15 +257,6 @@ xfs_buf_item_format_segment( nbits = xfs_contig_bits(blfp->blf_data_map, blfp->blf_map_size, first_bit); ASSERT(nbits > 0); - - /* - * Straddling a page is rare because we don't log contiguous - * chunks of unmapped buffers anywhere. - */ - if (nbits > 1 && - xfs_buf_item_straddle(bp, offset, first_bit, nbits)) - goto slow_scan; - xfs_buf_item_copy_iovec(lv, vecp, bp, offset, first_bit, nbits); blfp->blf_size++; @@ -357,45 +272,6 @@ xfs_buf_item_format_segment( } while (first_bit != -1); return; - -slow_scan: - ASSERT(bp->b_addr == NULL); - last_bit = first_bit; - nbits = 1; - for (;;) { - /* - * This takes the bit number to start looking from and - * returns the next set bit from there. It returns -1 - * if there are no more bits set or the start bit is - * beyond the end of the bitmap. - */ - next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, - (uint)last_bit + 1); - /* - * If we run out of bits fill in the last iovec and get out of - * the loop. Else if we start a new set of bits then fill in - * the iovec for the series we were looking at and start - * counting the bits in the new one. Else we're still in the - * same set of bits so just keep counting and scanning. - */ - if (next_bit == -1) { - xfs_buf_item_copy_iovec(lv, vecp, bp, offset, - first_bit, nbits); - blfp->blf_size++; - break; - } else if (next_bit != last_bit + 1 || - xfs_buf_item_straddle(bp, offset, first_bit, nbits)) { - xfs_buf_item_copy_iovec(lv, vecp, bp, offset, - first_bit, nbits); - blfp->blf_size++; - first_bit = next_bit; - last_bit = next_bit; - nbits = 1; - } else { - last_bit++; - nbits++; - } - } } /* -- cgit v1.2.3 From e2874632a6213b4687e53cd7d837c642c805c903 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:13 +0100 Subject: xfs: use vmalloc instead of vm_map_area for buffer backing memory The fallback buffer allocation path currently open codes a suboptimal version of vmalloc to allocate pages that are then mapped into vmalloc space. Switch to using vmalloc instead, which uses all the optimizations in the common vmalloc code, and removes the need to track the backing pages in the xfs_buf structure. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 212 +++++++++++++-------------------------------------- fs/xfs/xfs_buf.h | 7 -- fs/xfs/xfs_buf_mem.c | 11 +-- 3 files changed, 53 insertions(+), 177 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index b5ec7d83210f..4aaa588330e4 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -55,13 +55,6 @@ static inline bool xfs_buf_is_uncached(struct xfs_buf *bp) return bp->b_rhash_key == XFS_BUF_DADDR_NULL; } -static inline int -xfs_buf_vmap_len( - struct xfs_buf *bp) -{ - return (bp->b_page_count * PAGE_SIZE); -} - /* * When we mark a buffer stale, we remove the buffer from the LRU and clear the * b_lru_ref count so that the buffer is freed immediately when the buffer @@ -190,29 +183,6 @@ _xfs_buf_alloc( return 0; } -static void -xfs_buf_free_pages( - struct xfs_buf *bp) -{ - uint i; - - ASSERT(bp->b_flags & _XBF_PAGES); - - if (is_vmalloc_addr(bp->b_addr)) - vm_unmap_ram(bp->b_addr, bp->b_page_count); - - for (i = 0; i < bp->b_page_count; i++) { - if (bp->b_pages[i]) - folio_put(page_folio(bp->b_pages[i])); - } - mm_account_reclaimed_pages(howmany(BBTOB(bp->b_length), PAGE_SIZE)); - - if (bp->b_pages != bp->b_page_array) - kfree(bp->b_pages); - bp->b_pages = NULL; - bp->b_flags &= ~_XBF_PAGES; -} - static void xfs_buf_free_callback( struct callback_head *cb) @@ -227,16 +197,23 @@ static void xfs_buf_free( struct xfs_buf *bp) { + unsigned int size = BBTOB(bp->b_length); + trace_xfs_buf_free(bp, _RET_IP_); ASSERT(list_empty(&bp->b_lru)); + if (!xfs_buftarg_is_mem(bp->b_target) && size >= PAGE_SIZE) + mm_account_reclaimed_pages(howmany(size, PAGE_SHIFT)); + if (xfs_buftarg_is_mem(bp->b_target)) xmbuf_unmap_page(bp); - else if (bp->b_flags & _XBF_PAGES) - xfs_buf_free_pages(bp); + else if (is_vmalloc_addr(bp->b_addr)) + vfree(bp->b_addr); else if (bp->b_flags & _XBF_KMEM) kfree(bp->b_addr); + else + folio_put(virt_to_folio(bp->b_addr)); call_rcu(&bp->b_rcu, xfs_buf_free_callback); } @@ -264,9 +241,6 @@ xfs_buf_alloc_kmem( bp->b_addr = NULL; return -ENOMEM; } - bp->b_pages = bp->b_page_array; - bp->b_pages[0] = kmem_to_page(bp->b_addr); - bp->b_page_count = 1; bp->b_flags |= _XBF_KMEM; return 0; } @@ -287,9 +261,9 @@ xfs_buf_alloc_kmem( * by the rest of the code - the buffer memory spans a single contiguous memory * region that we don't have to map and unmap to access the data directly. * - * The third type of buffer is the multi-page buffer. These are always made - * up of single pages so that they can be fed to vmap_ram() to return a - * contiguous memory region we can access the data through. + * The third type of buffer is the vmalloc()d buffer. This provides the buffer + * with the required contiguous memory region but backed by discontiguous + * physical pages. */ static int xfs_buf_alloc_backing_mem( @@ -299,7 +273,6 @@ xfs_buf_alloc_backing_mem( size_t size = BBTOB(bp->b_length); gfp_t gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOWARN; struct folio *folio; - long filled = 0; if (xfs_buftarg_is_mem(bp->b_target)) return xmbuf_map_page(bp); @@ -351,98 +324,18 @@ xfs_buf_alloc_backing_mem( goto fallback; } bp->b_addr = folio_address(folio); - bp->b_page_array[0] = &folio->page; - bp->b_pages = bp->b_page_array; - bp->b_page_count = 1; - bp->b_flags |= _XBF_PAGES; return 0; fallback: - /* Fall back to allocating an array of single page folios. */ - bp->b_page_count = DIV_ROUND_UP(size, PAGE_SIZE); - if (bp->b_page_count <= XB_PAGES) { - bp->b_pages = bp->b_page_array; - } else { - bp->b_pages = kzalloc(sizeof(struct page *) * bp->b_page_count, - gfp_mask); - if (!bp->b_pages) - return -ENOMEM; - } - bp->b_flags |= _XBF_PAGES; - - /* - * Bulk filling of pages can take multiple calls. Not filling the entire - * array is not an allocation failure, so don't back off if we get at - * least one extra page. - */ for (;;) { - long last = filled; - - filled = alloc_pages_bulk(gfp_mask, bp->b_page_count, - bp->b_pages); - if (filled == bp->b_page_count) { - XFS_STATS_INC(bp->b_mount, xb_page_found); + bp->b_addr = __vmalloc(size, gfp_mask); + if (bp->b_addr) break; - } - - if (filled != last) - continue; - - if (flags & XBF_READ_AHEAD) { - xfs_buf_free_pages(bp); + if (flags & XBF_READ_AHEAD) return -ENOMEM; - } - XFS_STATS_INC(bp->b_mount, xb_page_retries); memalloc_retry_wait(gfp_mask); } - return 0; -} - -/* - * Map buffer into kernel address-space if necessary. - */ -STATIC int -_xfs_buf_map_pages( - struct xfs_buf *bp, - xfs_buf_flags_t flags) -{ - ASSERT(bp->b_flags & _XBF_PAGES); - if (bp->b_page_count == 1) { - /* A single page buffer is always mappable */ - bp->b_addr = page_address(bp->b_pages[0]); - } else { - int retried = 0; - unsigned nofs_flag; - - /* - * vm_map_ram() will allocate auxiliary structures (e.g. - * pagetables) with GFP_KERNEL, yet we often under a scoped nofs - * context here. Mixing GFP_KERNEL with GFP_NOFS allocations - * from the same call site that can be run from both above and - * below memory reclaim causes lockdep false positives. Hence we - * always need to force this allocation to nofs context because - * we can't pass __GFP_NOLOCKDEP down to auxillary structures to - * prevent false positive lockdep reports. - * - * XXX(dgc): I think dquot reclaim is the only place we can get - * to this function from memory reclaim context now. If we fix - * that like we've fixed inode reclaim to avoid writeback from - * reclaim, this nofs wrapping can go away. - */ - nofs_flag = memalloc_nofs_save(); - do { - bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, - -1); - if (bp->b_addr) - break; - vm_unmap_aliases(); - } while (retried++ <= 1); - memalloc_nofs_restore(nofs_flag); - - if (!bp->b_addr) - return -ENOMEM; - } return 0; } @@ -562,7 +455,7 @@ xfs_buf_find_lock( return -ENOENT; } ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0); - bp->b_flags &= _XBF_KMEM | _XBF_PAGES; + bp->b_flags &= _XBF_KMEM; bp->b_ops = NULL; } return 0; @@ -748,18 +641,6 @@ xfs_buf_get_map( xfs_perag_put(pag); } - /* We do not hold a perag reference anymore. */ - if (!bp->b_addr) { - error = _xfs_buf_map_pages(bp, flags); - if (unlikely(error)) { - xfs_warn_ratelimited(btp->bt_mount, - "%s: failed to map %u pages", __func__, - bp->b_page_count); - xfs_buf_relse(bp); - return error; - } - } - /* * Clear b_error if this is a lookup from a caller that doesn't expect * valid data to be found in the buffer. @@ -1002,14 +883,6 @@ xfs_buf_get_uncached( if (error) goto fail_free_buf; - if (!bp->b_addr) - error = _xfs_buf_map_pages(bp, 0); - if (unlikely(error)) { - xfs_warn(target->bt_mount, - "%s: failed to map pages", __func__); - goto fail_free_buf; - } - trace_xfs_buf_get_uncached(bp, _RET_IP_); *bpp = bp; return 0; @@ -1343,7 +1216,7 @@ __xfs_buf_ioend( if (bp->b_flags & XBF_READ) { if (!bp->b_error && is_vmalloc_addr(bp->b_addr)) invalidate_kernel_vmap_range(bp->b_addr, - xfs_buf_vmap_len(bp)); + roundup(BBTOB(bp->b_length), PAGE_SIZE)); if (!bp->b_error && bp->b_ops) bp->b_ops->verify_read(bp); if (!bp->b_error) @@ -1504,29 +1377,48 @@ static void xfs_buf_submit_bio( struct xfs_buf *bp) { - unsigned int size = BBTOB(bp->b_length); - unsigned int map = 0, p; + unsigned int map = 0; struct blk_plug plug; struct bio *bio; - bio = bio_alloc(bp->b_target->bt_bdev, bp->b_page_count, - xfs_buf_bio_op(bp), GFP_NOIO); - bio->bi_private = bp; - bio->bi_end_io = xfs_buf_bio_end_io; + if (is_vmalloc_addr(bp->b_addr)) { + unsigned int size = BBTOB(bp->b_length); + unsigned int alloc_size = roundup(size, PAGE_SIZE); + void *data = bp->b_addr; - if (bp->b_page_count == 1) { - __bio_add_page(bio, virt_to_page(bp->b_addr), size, - offset_in_page(bp->b_addr)); - } else { - for (p = 0; p < bp->b_page_count; p++) - __bio_add_page(bio, bp->b_pages[p], PAGE_SIZE, 0); - bio->bi_iter.bi_size = size; /* limit to the actual size used */ + bio = bio_alloc(bp->b_target->bt_bdev, alloc_size >> PAGE_SHIFT, + xfs_buf_bio_op(bp), GFP_NOIO); + + do { + unsigned int len = min(size, PAGE_SIZE); - if (is_vmalloc_addr(bp->b_addr)) - flush_kernel_vmap_range(bp->b_addr, - xfs_buf_vmap_len(bp)); + ASSERT(offset_in_page(data) == 0); + __bio_add_page(bio, vmalloc_to_page(data), len, 0); + data += len; + size -= len; + } while (size); + + flush_kernel_vmap_range(bp->b_addr, alloc_size); + } else { + /* + * Single folio or slab allocation. Must be contiguous and thus + * only a single bvec is needed. + * + * This uses the page based bio add helper for now as that is + * the lowest common denominator between folios and slab + * allocations. To be replaced with a better block layer + * helper soon (hopefully). + */ + bio = bio_alloc(bp->b_target->bt_bdev, 1, xfs_buf_bio_op(bp), + GFP_NOIO); + __bio_add_page(bio, virt_to_page(bp->b_addr), + BBTOB(bp->b_length), + offset_in_page(bp->b_addr)); } + bio->bi_private = bp; + bio->bi_end_io = xfs_buf_bio_end_io; + /* * If there is more than one map segment, split out a new bio for each * map except of the last one. The last map is handled by the diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 8db522f19b0c..db43bdc17f55 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -36,7 +36,6 @@ struct xfs_buf; #define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */ /* flags used only internally */ -#define _XBF_PAGES (1u << 20)/* backed by refcounted pages */ #define _XBF_KMEM (1u << 21)/* backed by heap memory */ #define _XBF_DELWRI_Q (1u << 22)/* buffer on a delwri queue */ @@ -61,7 +60,6 @@ typedef unsigned int xfs_buf_flags_t; { XBF_STALE, "STALE" }, \ { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ - { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ /* The following interface flags should never be set */ \ @@ -122,8 +120,6 @@ struct xfs_buftarg { struct xfs_buf_cache bt_cache[]; }; -#define XB_PAGES 2 - struct xfs_buf_map { xfs_daddr_t bm_bn; /* block number for I/O */ int bm_len; /* size of I/O */ @@ -185,13 +181,10 @@ struct xfs_buf { struct xfs_buf_log_item *b_log_item; struct list_head b_li_list; /* Log items list head */ struct xfs_trans *b_transp; - struct page **b_pages; /* array of page pointers */ - struct page *b_page_array[XB_PAGES]; /* inline pages */ struct xfs_buf_map *b_maps; /* compound buffer map */ struct xfs_buf_map __b_map; /* inline compound buffer map */ int b_map_count; atomic_t b_pin_count; /* pin count */ - unsigned int b_page_count; /* size of page array */ int b_error; /* error code on I/O */ void (*b_iodone)(struct xfs_buf *bp); diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c index 5b64a2b3b113..b207754d2ee0 100644 --- a/fs/xfs/xfs_buf_mem.c +++ b/fs/xfs/xfs_buf_mem.c @@ -169,9 +169,6 @@ xmbuf_map_page( unlock_page(page); bp->b_addr = page_address(page); - bp->b_pages = bp->b_page_array; - bp->b_pages[0] = page; - bp->b_page_count = 1; return 0; } @@ -180,16 +177,10 @@ void xmbuf_unmap_page( struct xfs_buf *bp) { - struct page *page = bp->b_pages[0]; - ASSERT(xfs_buftarg_is_mem(bp->b_target)); - put_page(page); - + put_page(virt_to_page(bp->b_addr)); bp->b_addr = NULL; - bp->b_pages[0] = NULL; - bp->b_pages = NULL; - bp->b_page_count = 0; } /* Is this a valid daddr within the buftarg? */ -- cgit v1.2.3 From e614a00117bc2d46219c66a287ddde0f0a04517c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:14 +0100 Subject: xfs: cleanup mapping tmpfs folios into the buffer cache Directly assign b_addr based on the tmpfs folios without a detour through pages, reuse the folio_put path used for non-tmpfs buffers and replace all references to pages in comments with folios. Partially based on a patch from Dave Chinner . Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 6 ++---- fs/xfs/xfs_buf_mem.c | 34 ++++++++++------------------------ fs/xfs/xfs_buf_mem.h | 6 ++---- 3 files changed, 14 insertions(+), 32 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 4aaa588330e4..a7430fcd8301 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -206,9 +206,7 @@ xfs_buf_free( if (!xfs_buftarg_is_mem(bp->b_target) && size >= PAGE_SIZE) mm_account_reclaimed_pages(howmany(size, PAGE_SHIFT)); - if (xfs_buftarg_is_mem(bp->b_target)) - xmbuf_unmap_page(bp); - else if (is_vmalloc_addr(bp->b_addr)) + if (is_vmalloc_addr(bp->b_addr)) vfree(bp->b_addr); else if (bp->b_flags & _XBF_KMEM) kfree(bp->b_addr); @@ -275,7 +273,7 @@ xfs_buf_alloc_backing_mem( struct folio *folio; if (xfs_buftarg_is_mem(bp->b_target)) - return xmbuf_map_page(bp); + return xmbuf_map_backing_mem(bp); /* Assure zeroed buffer for non-read cases. */ if (!(flags & XBF_READ)) diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c index b207754d2ee0..b4ffd80b7cb6 100644 --- a/fs/xfs/xfs_buf_mem.c +++ b/fs/xfs/xfs_buf_mem.c @@ -74,7 +74,7 @@ xmbuf_alloc( /* * We don't want to bother with kmapping data during repair, so don't - * allow highmem pages to back this mapping. + * allow highmem folios to back this mapping. */ mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL); @@ -127,14 +127,13 @@ xmbuf_free( kfree(btp); } -/* Directly map a shmem page into the buffer cache. */ +/* Directly map a shmem folio into the buffer cache. */ int -xmbuf_map_page( +xmbuf_map_backing_mem( struct xfs_buf *bp) { struct inode *inode = file_inode(bp->b_target->bt_file); struct folio *folio = NULL; - struct page *page; loff_t pos = BBTOB(xfs_buf_daddr(bp)); int error; @@ -159,30 +158,17 @@ xmbuf_map_page( return -EIO; } - page = folio_file_page(folio, pos >> PAGE_SHIFT); - /* - * Mark the page dirty so that it won't be reclaimed once we drop the - * (potentially last) reference in xmbuf_unmap_page. + * Mark the folio dirty so that it won't be reclaimed once we drop the + * (potentially last) reference in xfs_buf_free. */ - set_page_dirty(page); - unlock_page(page); + folio_set_dirty(folio); + folio_unlock(folio); - bp->b_addr = page_address(page); + bp->b_addr = folio_address(folio); return 0; } -/* Unmap a shmem page that was mapped into the buffer cache. */ -void -xmbuf_unmap_page( - struct xfs_buf *bp) -{ - ASSERT(xfs_buftarg_is_mem(bp->b_target)); - - put_page(virt_to_page(bp->b_addr)); - bp->b_addr = NULL; -} - /* Is this a valid daddr within the buftarg? */ bool xmbuf_verify_daddr( @@ -196,7 +182,7 @@ xmbuf_verify_daddr( return daddr < (inode->i_sb->s_maxbytes >> BBSHIFT); } -/* Discard the page backing this buffer. */ +/* Discard the folio backing this buffer. */ static void xmbuf_stale( struct xfs_buf *bp) @@ -211,7 +197,7 @@ xmbuf_stale( } /* - * Finalize a buffer -- discard the backing page if it's stale, or run the + * Finalize a buffer -- discard the backing folio if it's stale, or run the * write verifier to detect problems. */ int diff --git a/fs/xfs/xfs_buf_mem.h b/fs/xfs/xfs_buf_mem.h index eed4a7b63232..67d525cc1513 100644 --- a/fs/xfs/xfs_buf_mem.h +++ b/fs/xfs/xfs_buf_mem.h @@ -19,16 +19,14 @@ int xmbuf_alloc(struct xfs_mount *mp, const char *descr, struct xfs_buftarg **btpp); void xmbuf_free(struct xfs_buftarg *btp); -int xmbuf_map_page(struct xfs_buf *bp); -void xmbuf_unmap_page(struct xfs_buf *bp); bool xmbuf_verify_daddr(struct xfs_buftarg *btp, xfs_daddr_t daddr); void xmbuf_trans_bdetach(struct xfs_trans *tp, struct xfs_buf *bp); int xmbuf_finalize(struct xfs_buf *bp); #else # define xfs_buftarg_is_mem(...) (false) -# define xmbuf_map_page(...) (-ENOMEM) -# define xmbuf_unmap_page(...) ((void)0) # define xmbuf_verify_daddr(...) (false) #endif /* CONFIG_XFS_MEMORY_BUFS */ +int xmbuf_map_backing_mem(struct xfs_buf *bp); + #endif /* __XFS_BUF_MEM_H__ */ -- cgit v1.2.3 From 89ce287c83c91f5d222809b82e597426587a862d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Mar 2025 14:19:15 +0100 Subject: xfs: trace what memory backs a buffer Add three trace points for the different backing memory allocators for buffers. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/xfs_buf.c | 4 ++++ fs/xfs/xfs_trace.h | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index a7430fcd8301..106ee81fa56f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -240,6 +240,7 @@ xfs_buf_alloc_kmem( return -ENOMEM; } bp->b_flags |= _XBF_KMEM; + trace_xfs_buf_backing_kmem(bp, _RET_IP_); return 0; } @@ -319,9 +320,11 @@ xfs_buf_alloc_backing_mem( if (!folio) { if (size <= PAGE_SIZE) return -ENOMEM; + trace_xfs_buf_backing_fallback(bp, _RET_IP_); goto fallback; } bp->b_addr = folio_address(folio); + trace_xfs_buf_backing_folio(bp, _RET_IP_); return 0; fallback: @@ -335,6 +338,7 @@ fallback: memalloc_retry_wait(gfp_mask); } + trace_xfs_buf_backing_vmalloc(bp, _RET_IP_); return 0; } diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 83f894c07866..e56ba1963160 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -692,6 +692,10 @@ DEFINE_BUF_EVENT(xfs_buf_iodone_async); DEFINE_BUF_EVENT(xfs_buf_error_relse); DEFINE_BUF_EVENT(xfs_buf_drain_buftarg); DEFINE_BUF_EVENT(xfs_trans_read_buf_shut); +DEFINE_BUF_EVENT(xfs_buf_backing_folio); +DEFINE_BUF_EVENT(xfs_buf_backing_kmem); +DEFINE_BUF_EVENT(xfs_buf_backing_vmalloc); +DEFINE_BUF_EVENT(xfs_buf_backing_fallback); /* not really buffer traces, but the buf provides useful information */ DEFINE_BUF_EVENT(xfs_btree_corrupt); -- cgit v1.2.3