use folios and vmalloc for buffer cache backing memory
Hi all,
this is another spin on converting the XFS buffer cache to use folios and generally simplify the memory allocation in it. It is based on Dave's last folio series (which itself had pulled in bits from my earlier vmalloc series).
It converts the backing memory allocation for all large buffers that are power of two sized to large folios, converts > PAGE_SIZE but not power of two allocations to vmalloc instead of vm_map_ram and generally cleans up a lot of code around the memory allocation and reduces the size of the xfs_buf structure by removing the embedded pages array and pages pointer.
I've benchmarked it using buffer heavy workloads, most notable fs_mark run on null_blk without any fsync or O_SYNC to stress the buffer memory allocator. The performance results are disappointingly boring
unfortunately: for 4k directory block I see no significant change (although the variance for both loads is very high to start with), and for 64k directory block I see a minimal 1-2% gain that is barely about the variance. So based on the performance results alone I would not propose this series, but I think it actually cleans the code up very nicely.
Diffstat:
libxfs/xfs_ialloc.c | 2 libxfs/xfs_inode_buf.c | 2 scrub/inode_repair.c | 3 xfs_buf.c | 371 +++++++++++++++++-------------------------------- xfs_buf.h | 25 +-- xfs_buf_item.c | 114 --------------- xfs_buf_item_recover.c | 8 - xfs_buf_mem.c | 43 +---- xfs_buf_mem.h | 6 xfs_inode.c | 3 xfs_trace.h | 4 11 files changed, 164 insertions(+), 417 deletions(-)
PATCH 1/12 xfs: unmapped buffer item size straddling mismatch
From: Dave Chinner <[email protected]>
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.
--- fs/xfs/xfs_buf_item.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-)
fs/xfs/xfs_buf_item.c +14 -4
@@ -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 @@ xfs_buf_item_size_segment(* 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 @@ xfs_buf_item_size_segment( last_bit++; nbits++; } - *nbytes +=XFS_BLF_CHUNK ; } }
Signature · 1 line
2.45.2
PATCH 2/12 xfs: add a fast path to xfs_buf_zero when b_addr is set
In reply to Christoph HellwigNo 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.
--- fs/xfs/xfs_buf.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
fs/xfs/xfs_buf.c +7 -2
@@ -1688,13 +1688,18 @@ 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);
Signature · 1 line
2.45.2
Re: [PATCH 02/12] xfs: add a fast path to xfs_buf_zero when b_addr is set
Quoted 5 lines · Christoph Hellwig
No need to walk the page list if
bp->b_addris valid. That also meansb_offsetdoesn't need to be taken into account in the unmapped loop asb_offsetis only set for kmem backed buffers which are always mapped.Signed-off-by Christoph Hellwig <[email protected]>
That's much clearer!
--D
Quoted 33 lines
--- fs/xfs/xfs_buf.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)fs/xfs/xfs_buf.c +7
-2@@ -1688,13 +1688,18 @@ 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);Signature · 1 line
2.45.2
PATCH 3/12 xfs: remove xfs_buf.b_offset
In reply to Christoph Hellwigb_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.
--- fs/xfs/xfs_buf.c | 3 +-- fs/xfs/xfs_buf.h | 2 -- 2 files changed, 1 insertion(+), 4 deletions(-)
fs/xfs/xfs_buf.c +1 -2
@@ -336,7 +336,6 @@ 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 ;
@@ -1528,7 +1527,7 @@ 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 );
fs/xfs/xfs_buf.h +0 -2
@@ -197,8 +197,6 @@ 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);
Signature · 1 line
2.45.2
Re: [PATCH 03/12] xfs: remove xfs_buf.b_offset
Quoted 5 lines · Christoph Hellwig
b_offsetis only set for slab backed buffers and always set tooffset_in_page(bp->b_addr), which can be done just as easily in the only user ofb_offset.Signed-off-by Christoph Hellwig <[email protected]>
Wooo space savings!
--D
Quoted 43 lines
--- fs/xfs/xfs_buf.c | 3 +-- fs/xfs/xfs_buf.h | 2 -- 2 files changed, 1 insertion(+), 4 deletions(-)fs/xfs/xfs_buf.c +1
-2@@ -336,7 +336,6 @@ 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 ;@@ -1528,7 +1527,7 @@ 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 );fs/xfs/xfs_buf.h +0
-2@@ -197,8 +197,6 @@ 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);Signature · 1 line
2.45.2
PATCH 4/12 xfs: remove xfs_buf_is_vmapped
In reply to Christoph HellwigNo 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.
--- fs/xfs/xfs_buf.c | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-)
fs/xfs/xfs_buf.c +3 -17
@@ -60,20 +60,6 @@ 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)
@@ -270,7 +256,7 @@ 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++) {
@@ -1361,7 +1347,7 @@ 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)
@@ -1533,7 +1519,7 @@ 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)); }
Signature · 1 line
2.45.2
Re: [PATCH 04/12] xfs: remove xfs_buf_is_vmapped
Quoted 5 lines · Christoph Hellwig
No need to look at the page count if we can simply call
is_vmalloc_addronbp->b_addr. This prepares for eventualy removing theb_page_countfield.Signed-off-by Christoph Hellwig <[email protected]>
Yeah, that's more direct.
--D
Quoted 60 lines
--- fs/xfs/xfs_buf.c | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-)fs/xfs/xfs_buf.c +3
-17@@ -60,20 +60,6 @@ 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)@@ -270,7 +256,7 @@ 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++) {@@ -1361,7 +1347,7 @@ 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)@@ -1533,7 +1519,7 @@ 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)); }Signature · 1 line
2.45.2
PATCH 5/12 xfs: refactor backing memory allocations for buffers
In reply to Christoph HellwigLift 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.
--- fs/xfs/xfs_buf.c | 55 +++++++++++++++++++++++++++++++----------------- 1 file changed, 36 insertions(+), 19 deletions(-)
fs/xfs/xfs_buf.c +36 -19
@@ -329,19 +329,49 @@ 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 {
@@ -622,18 +652,7 @@ 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;
@@ -995,14 +1014,12 @@ 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__);
Signature · 1 line
2.45.2
Re: [PATCH 05/12] xfs: refactor backing memory allocations for buffers
Quoted 9 lines · Christoph Hellwig
Lift handling of shmem and slab backed buffers into
xfs_buf_alloc_pagesand rename the result toxfs_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 <[email protected]>
That's a nice refactoring. I'd wondered about get_buf_uncached not going for slab memory when I was writing the xmbuf code, but didn't want to overcomplicate that patchset and then forgot about it :/
--D
Quoted 102 lines
--- fs/xfs/xfs_buf.c | 55 +++++++++++++++++++++++++++++++----------------- 1 file changed, 36 insertions(+), 19 deletions(-)fs/xfs/xfs_buf.c +36
-19@@ -329,19 +329,49 @@ 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 {@@ -622,18 +652,7 @@ 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;@@ -995,14 +1014,12 @@ 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__);Signature · 1 line
2.45.2
PATCH 6/12 xfs: remove the kmalloc to page allocator fallback
In reply to Christoph HellwigSince 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.
--- fs/xfs/xfs_buf.c | 49 ++++++++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 24 deletions(-)
fs/xfs/xfs_buf.c +25 -24
@@ -301,23 +301,24 @@ 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 (!IS_ALIGNED ((unsigned long )bp->b_addr, size)) { +ASSERT (IS_ALIGNED ((unsigned long )bp->b_addr, size));kfree (bp->b_addr); bp->b_addr =NULL ;return -ENOMEM ;
@@ -358,18 +359,22 @@ 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, we matches must 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 ) {
@@ -382,10 +387,6 @@ 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
Signature · 1 line
2.45.2
Re: [PATCH 06/12] xfs: remove the kmalloc to page allocator fallback
Quoted 43 lines · Christoph Hellwig
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 <[email protected]>--- fs/xfs/xfs_buf.c | 49 ++++++++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 24 deletions(-)fs/xfs/xfs_buf.c +6
-9@@ -301,23 +301,24 @@ 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 ;
fs/xfs/xfs_buf.c xfs_buf_free( · line 321
Quoted 10 lines
fs/xfs/xfs_buf.c +7
-3-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 (!IS_ALIGNED ((unsigned long )bp->b_addr, size)) { +ASSERT (IS_ALIGNED ((unsigned long )bp->b_addr, size));
Depending on the level of paranoia about "outside" subsystems, should this be a regular xfs_err so we can catch these kinds of things on production kernels?
Quoted 16 lines
fs/xfs/xfs_buf.c +1
-8kfree (bp->b_addr); bp->b_addr =NULL ;return -ENOMEM ;@@ -358,18 +359,22 @@ 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. */
fs/xfs/xfs_buf.c xfs_buf_alloc_backing_mem( · line 372
Quoted 10 lines
fs/xfs/xfs_buf.c +6
-0+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, we matches must of the smaller
"...which matches most of the smaller than PAGE_SIZE buffers..."
--D
Quoted 23 lines
fs/xfs/xfs_buf.c +5
-4+* 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 ) {@@ -382,10 +387,6 @@ 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 Signature · 1 line
2.45.2
Re: [PATCH 06/12] xfs: remove the kmalloc to page allocator fallback
Quoted 6 lines · Darrick J. Wong
fs/xfs/xfs_buf.c xfs_buf_free( · line 321
Quoted 2 lines
fs/xfs/xfs_buf.c +2
-0+if (!IS_ALIGNED ((unsigned long )bp->b_addr, size)) { +ASSERT (IS_ALIGNED ((unsigned long )bp->b_addr, size));Depending on the level of paranoia about "outside" subsystems, should this be a regular
xfs_errso we can catch these kinds of things on production kernels?
I'll switch to WARN_ON_ONCE.
PATCH 7/12 xfs: convert buffer cache to use high order folios
In reply to Christoph HellwigNow 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 <[email protected]>, but mutilated beyond recognition.
--- fs/xfs/xfs_buf.c | 58 +++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 52 insertions(+), 6 deletions(-)
fs/xfs/xfs_buf.c +52 -6
@@ -261,9 +261,10 @@ 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 ( +DIV_ROUND_UP (BBTOB (bp->b_length),PAGE_SIZE ));if (bp->b_pages != bp->b_page_array)kfree (bp->b_pages);
@@ -336,12 +337,17 @@ 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()
@@ -354,6 +360,7 @@ 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))
@@ -375,7 +382,46 @@ 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 */ +/* Assure zeroed buffer for non-read cases. */ +if (!(flags &XBF_READ )) + gfp_mask |= __GFP_ZERO; + +/* +* Don't bother with the retry loop for single PAGE allocations, there +* is litte changes this can be better than the VM version. +*/ +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 && !is_power_of_2 (size)) + goto fallback; + 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;
@@ -1529,7 +1575,7 @@ 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 {
Signature · 1 line
2.45.2
Re: [PATCH 07/12] xfs: convert buffer cache to use high order folios
Quoted 40 lines · Christoph Hellwig
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_pagesarray, 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 <[email protected]>, but mutilated beyond recognition.
Signed-off-by Christoph Hellwig <[email protected]>--- fs/xfs/xfs_buf.c | 58 +++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 52 insertions(+), 6 deletions(-)fs/xfs/xfs_buf.c +0
-0
fs/xfs/xfs_buf.c xfs_buf_free_pages( · line 267
Quoted 9 lines
fs/xfs/xfs_buf.c +3
-2@@ -261,9 +261,10 @@ 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 ( +DIV_ROUND_UP (BBTOB (bp->b_length),PAGE_SIZE ));
Why do we round the number of bytes in the buffer up to base page size?
Don't we want howmany(BBTOB(bp->b_length), PAGE_SIZE) here?
Oh wait, howmany *is* DIV_ROUND_UP. Never mind...
Quoted 31 lines
fs/xfs/xfs_buf.c +8
-2if (bp->b_pages != bp->b_page_array)kfree (bp->b_pages);@@ -336,12 +337,17 @@ 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() @@ -354,6 +360,7 @@ 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))
fs/xfs/xfs_buf.c xfs_buf_alloc_backing_mem( · line 387
Quoted 7 lines
fs/xfs/xfs_buf.c +3
-1@@ -375,7 +382,46 @@ 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 */ +/* Assure zeroed buffer for non-read cases. */ +if (!(flags &XBF_READ )) + gfp_mask |= __GFP_ZERO;
Didn't this get added ten lines up in "xfs: remove the kmalloc to page allocator fallback"?
fs/xfs/xfs_buf.c xfs_buf_alloc_backing_mem( · line 391
Quoted 4 lines
fs/xfs/xfs_buf.c +4
-0+ +/* +* Don't bother with the retry loop for single PAGE allocations, there +* is litte changes this can be better than the VM version.
Er... I don't understand the second half of this sentence; is this what you're trying to communicate?:
"Don't bother with the retry loop for single-page allocations; vmalloc won't do any better."
Quoted 5 lines
fs/xfs/xfs_buf.c +5
-0+*/ +if (size <=PAGE_SIZE ) + gfp_mask |= __GFP_NOFAIL; + +/*
fs/xfs/xfs_buf.c xfs_buf_alloc_backing_mem( · line 406
Quoted 10 lines
fs/xfs/xfs_buf.c +10
-0+* 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.
Nit: "...path for them instead of wasting memory here."
--D
Quoted 34 lines
fs/xfs/xfs_buf.c +19
-1+*/ +if (size >PAGE_SIZE && !is_power_of_2 (size)) + goto fallback; + 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;@@ -1529,7 +1575,7 @@ 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 {Signature · 1 line
2.45.2
Re: [PATCH 07/12] xfs: convert buffer cache to use high order folios
Quoted 9 lines · Darrick J. Wong
fs/xfs/xfs_buf.c xfs_buf_free_pages( · line 267
Quoted 3 lines
fs/xfs/xfs_buf.c +2
-1-mm_account_reclaimed_pages (bp->b_page_count); +mm_account_reclaimed_pages ( +DIV_ROUND_UP (BBTOB (bp->b_length),PAGE_SIZE ));Why do we round the number of bytes in the buffer up to base page size?
Don't we want
howmany(BBTOB(bp->b_length), PAGE_SIZE)here?Oh wait, howmany *is*
DIV_ROUND_UP. Never mind...
I'll use howmany for consistency with the rest of the XFS code.
Quoted 7 lines
fs/xfs/xfs_buf.c xfs_buf_alloc_backing_mem( · line 387
Quoted 4 lines
fs/xfs/xfs_buf.c +3
-1-/* Make sure that we have a page list */ +/* Assure zeroed buffer for non-read cases. */ +if (!(flags &XBF_READ )) + gfp_mask |= __GFP_ZERO;Didn't this get added ten lines up in "xfs: remove the kmalloc to page allocator fallback"?
Yes. Looks like I didn't finish my refatoring to not duplicate this properly.
PATCH 8/12 xfs: kill XBF_UNMAPPED
In reply to Christoph HellwigUnmapped 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.
--- 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(-)
fs/xfs/libxfs/xfs_ialloc.c +1 -1
@@ -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;
fs/xfs/libxfs/xfs_inode_buf.c +1 -1
@@ -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 );
fs/xfs/scrub/inode_repair.c +1 -2
@@ -1558,8 +1558,7 @@ 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;
fs/xfs/xfs_buf.c +4 -54
94 lines not on this page · raw message
fs/xfs/xfs_buf.h +11 -5
@@ -49,7 +49,6 @@ 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 ;
@@ -70,8 +69,7 @@ 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.
@@ -316,12 +314,20 @@ 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 */
fs/xfs/xfs_buf_item.c +1 -1
@@ -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 ));
fs/xfs/xfs_buf_item_recover.c +1 -7
@@ -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;
fs/xfs/xfs_inode.c +1 -2
@@ -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;
Signature · 1 line
2.45.2
PATCH 9/12 xfs: buffer items don't straddle pages anymore
In reply to Christoph HellwigFrom: Dave Chinner <[email protected]>
Unmapped buffers don't exist anymore, so the page straddling detection and slow path code can go away now.
--- fs/xfs/xfs_buf_item.c | 124 ------------------------------------------ 1 file changed, 124 deletions(-)
fs/xfs/xfs_buf_item.c +0 -124
@@ -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++; - } - } }/*
Signature · 1 line
2.45.2
PATCH 10/12 xfs: use vmalloc instead of vm_map_area for buffer backing memory
In reply to Christoph HellwigThe 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.
--- fs/xfs/xfs_buf.c | 209 ++++++++++--------------------------------- fs/xfs/xfs_buf.h | 7 -- fs/xfs/xfs_buf_mem.c | 11 +-- 3 files changed, 49 insertions(+), 178 deletions(-)
fs/xfs/xfs_buf.c +48 -161
@@ -60,13 +60,6 @@ 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 ); -} -/* * Bump the I/O in flight count on the buftarg if we haven't yet done so for * this buffer. The count is incremented once per buffer (per hold cycle)
@@ -248,30 +241,6 @@ _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 ( -DIV_ROUND_UP (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)
@@ -286,16 +255,23 @@ static voidxfs_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 (DIV_ROUND_UP (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); }
@@ -324,9 +300,6 @@ 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 ; }
@@ -347,9 +320,9 @@ 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(
@@ -359,7 +332,6 @@ 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);
@@ -412,98 +384,18 @@ 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 ; }
@@ -623,7 +515,7 @@ 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 ;
@@ -809,18 +701,6 @@ 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.
@@ -1061,14 +941,6 @@ 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 ;
@@ -1409,7 +1281,8 @@ 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)); +DIV_ROUND_UP (BBTOB (bp->b_length), +PAGE_SIZE ));if (!bp->b_error && bp->b_ops) bp->b_ops->verify_read (bp);if (!bp->b_error)
@@ -1561,29 +1434,43 @@ static voidxfs_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 =DIV_ROUND_UP (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, size >>PAGE_SHIFT , +xfs_buf_bio_op (bp),GFP_NOIO ); + +do { +unsigned int len =min (size,PAGE_SIZE ); + +ASSERT (offset_in_page (data) ==0 ); +__bio_add_page (bio,vmalloc_to_page (data), len,0 ); + data += len; + size -= len; + }while (size); -if (is_vmalloc_addr (bp->b_addr)) -flush_kernel_vmap_range (bp->b_addr, -xfs_buf_vmap_len (bp)); +flush_kernel_vmap_range (bp->b_addr, alloc_size); + }else { +/* +* Single folio or slab allocation. Must be contigous and thus +* only a single bvec is needed. +*/ + 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
fs/xfs/xfs_buf.h +0 -7
@@ -37,7 +37,6 @@ 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 */
@@ -63,7 +62,6 @@ 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 */ \
@@ -125,8 +123,6 @@ 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 */
@@ -188,13 +184,10 @@ 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);
fs/xfs/xfs_buf_mem.c +1 -10
@@ -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 @@ voidxmbuf_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? */
Signature · 1 line
2.45.2
Re: [PATCH 10/12] xfs: use vmalloc instead of vm_map_area for buffer backing memory
Quoted 17 lines · Christoph Hellwig
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_bufstructure.Signed-off-by Christoph Hellwig <[email protected]>--- fs/xfs/xfs_buf.c | 209 ++++++++++--------------------------------- fs/xfs/xfs_buf.h | 7 -- fs/xfs/xfs_buf_mem.c | 11 +-- 3 files changed, 49 insertions(+), 178 deletions(-)fs/xfs/xfs_buf.c +0
-0
<snip>
Quoted 75 lines
fs/xfs/xfs_buf.c +3
-59@@ -412,98 +384,18 @@ 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
fs/xfs/xfs_buf.c xfs_buf_alloc_backing_mem( · line 492
Quoted 10 lines
fs/xfs/xfs_buf.c +0
-10-* 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.
Heh, I should've got rid of this comment when I added the code pinning dquot buffers to the dquot log item at transaction commit/quotacheck dirty time.
Quoted 18 lines
fs/xfs/xfs_buf.c +0
-14-*/ - 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 ; }
fs/xfs/xfs_buf.c xfs_buf_ioend( · line 1285
Quoted 6 lines
fs/xfs/xfs_buf.c +2
-1@@ -1409,7 +1281,8 @@ 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)); +DIV_ROUND_UP (BBTOB (bp->b_length), +PAGE_SIZE ));
The second argument to invalidate_kernel_vmap_range is the number of bytes, right? Isn't this BBTOB() without the DIV_ROUND_UP? Or do you actually want roundup(BBTOB(b_length), PAGE_SIZE) here?
Quoted 20 lines
fs/xfs/xfs_buf.c +4
-6if (!bp->b_error && bp->b_ops) bp->b_ops->verify_read (bp);if (!bp->b_error)@@ -1561,29 +1434,43 @@ static voidxfs_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 =DIV_ROUND_UP (size,PAGE_SIZE );
fs/xfs/xfs_buf.c static void · line 1446
Quoted 10 lines
fs/xfs/xfs_buf.c +2
-7+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, size >> PAGE_SHIFT,
Is the second argument (size >> PAGE_SHIFT) supposed to be the number of pages that we're going to __bio_add_page to the bio?
In which case, shouldn't it be alloc_size ?
Quoted 5 lines
fs/xfs/xfs_buf.c +5
-0+ xfs_buf_bio_op(bp), GFP_NOIO); + + do { + unsigned int len = min(size, PAGE_SIZE); +
fs/xfs/xfs_buf.c static void · line 1458
Quoted 10 lines
fs/xfs/xfs_buf.c +6
-3+ASSERT (offset_in_page (data) ==0 ); +__bio_add_page (bio,vmalloc_to_page (data), len,0 ); + data += len; + size -= len; + }while (size); -if (is_vmalloc_addr (bp->b_addr)) -flush_kernel_vmap_range (bp->b_addr, -xfs_buf_vmap_len (bp)); +flush_kernel_vmap_range (bp->b_addr, alloc_size);
...and this one is roundup(size, PAGE_SIZE) isn't it?
fs/xfs/xfs_buf.c static void · line 1461
Quoted 3 lines
fs/xfs/xfs_buf.c +3
-0+ }else { +/* +* Single folio or slab allocation. Must be contigous and thus
s/contigous/contiguous/
--D
Quoted 94 lines
fs/xfs/xfs_buf.c +10
-0+* only a single bvec is needed. +*/ + 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 fs/xfs/xfs_buf.h +0
-7@@ -37,7 +37,6 @@ 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 */ @@ -63,7 +62,6 @@ 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 */ \@@ -125,8 +123,6 @@ 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 */ @@ -188,13 +184,10 @@ 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);fs/xfs/xfs_buf_mem.c +1
-10@@ -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 @@ voidxmbuf_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? */ Signature · 1 line
2.45.2
Re: [PATCH 10/12] xfs: use vmalloc instead of vm_map_area for buffer backing memory
Quoted 8 lines · Darrick J. Wong
fs/xfs/xfs_buf.c xfs_buf_ioend( · line 1285
Quoted 5 lines
fs/xfs/xfs_buf.c +2
-1if (!bp->b_error &&is_vmalloc_addr (bp->b_addr))invalidate_kernel_vmap_range (bp->b_addr, -xfs_buf_vmap_len (bp)); +DIV_ROUND_UP (BBTOB (bp->b_length), +PAGE_SIZE ));The second argument to
invalidate_kernel_vmap_rangeis the number of bytes, right?
Yes.
Quoted 2 lines
Isn't this
BBTOB()without theDIV_ROUND_UP? Or do you actually wantroundup(BBTOB(b_length), PAGE_SIZE)here?
Yes.
Quoted 11 lines
fs/xfs/xfs_buf.c static void · line 1446
Quoted 8 lines
fs/xfs/xfs_buf.c +1
-7-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, size >> PAGE_SHIFT,Is the second argument (size >>
PAGE_SHIFT) supposed to be the number of pages that we're going to__bio_add_pageto the bio?
Yes.
Quoted 1 line
In which case, shouldn't it be
alloc_size?
Yes.
Quoted 8 lines
fs/xfs/xfs_buf.c static void · line 1458
Quoted 6 lines
fs/xfs/xfs_buf.c +2
-3+ }while (size); -if (is_vmalloc_addr (bp->b_addr)) -flush_kernel_vmap_range (bp->b_addr, -xfs_buf_vmap_len (bp)); +flush_kernel_vmap_range (bp->b_addr, alloc_size);...and this one is
roundup(size, PAGE_SIZE)isn't it?
Yes.
PATCH 11/12 xfs: cleanup mapping tmpfs folios into the buffer cache
In reply to Christoph HellwigDirectly 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 <[email protected]>.
--- 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(-)
fs/xfs/xfs_buf.c +2 -4
@@ -264,9 +264,7 @@ xfs_buf_free(if (!xfs_buftarg_is_mem (bp->b_target) && size >=PAGE_SIZE )mm_account_reclaimed_pages (DIV_ROUND_UP (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);
@@ -334,7 +332,7 @@ 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 ))
fs/xfs/xfs_buf_mem.c +10 -24
@@ -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
fs/xfs/xfs_buf_mem.h +2 -4
@@ -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__ */
Signature · 1 line
2.45.2
Re: [PATCH 11/12] xfs: cleanup mapping tmpfs folios into the buffer cache
Quoted 13 lines · Christoph Hellwig
Directly assign
b_addrbased on the tmpfs folios without a detour through pages, reuse thefolio_putpath used for non-tmpfs buffers and replace all references to pages in comments with folios.Partially based on a patch from Dave Chinner <[email protected]>.
Signed-off-by Christoph Hellwig <[email protected]>--- 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(-)
<snip>
Quoted 11 lines
fs/xfs/xfs_buf_mem.h +0
-2@@ -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);
fs/xfs/xfs_buf_mem.h int xmbuf_alloc(struct xfs_mount *mp, const char *descr, · line 30
Quoted 10 lines
fs/xfs/xfs_buf_mem.h +1
-2void 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);
Does this actually work if CONFIG_XFS_MEMORY_BUFS=n ? I guess the compiler will see:
if (false) return xmbuf_map_backing_mem(bp);
and optimize it out, right? But these subtleties make my eyes twitch.
--D
Quoted 6 lines
fs/xfs/xfs_buf_mem.h +1
-0+#endif /* __XFS_BUF_MEM_H__ */ Signature · 1 line
2.45.2
Re: [PATCH 11/12] xfs: cleanup mapping tmpfs folios into the buffer cache
Quoted 9 lines · Darrick J. Wong
Quoted 1 line
+int
xmbuf_map_backing_mem(struct xfs_buf *bp);Does this actually work if
CONFIG_XFS_MEMORY_BUFS=n? I guess the compiler will see:if (false) return xmbuf_map_backing_mem(bp);and optimize it out, right?
Exactly.
PATCH 12/12 xfs: trace what memory backs a buffer
In reply to Christoph HellwigAdd three trace points for the different backing memory allocators for buffers.
--- fs/xfs/xfs_buf.c | 4 ++++ fs/xfs/xfs_trace.h | 4 ++++ 2 files changed, 8 insertions(+)
fs/xfs/xfs_buf.c +4 -0
@@ -299,6 +299,7 @@ xfs_buf_alloc_kmem(return -ENOMEM ; } bp->b_flags |= _XBF_KMEM; +trace_xfs_buf_backing_kmem (bp, _RET_IP_);return 0 ; }
@@ -379,9 +380,11 @@ 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:
@@ -395,6 +398,7 @@ xfs_buf_alloc_backing_mem(memalloc_retry_wait (gfp_mask); } +trace_xfs_buf_backing_vmalloc (bp, _RET_IP_);return 0 ; }
fs/xfs/xfs_trace.h +4 -0
@@ -545,6 +545,10 @@ 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);
Signature · 1 line
2.45.2
Re: [PATCH 12/12] xfs: trace what memory backs a buffer
Quoted 4 lines · Christoph Hellwig
Add three trace points for the different backing memory allocators for buffers.
Signed-off-by Christoph Hellwig <[email protected]>
--D
Quoted 56 lines
--- fs/xfs/xfs_buf.c | 4 ++++ fs/xfs/xfs_trace.h | 4 ++++ 2 files changed, 8 insertions(+)fs/xfs/xfs_buf.c +4
-0@@ -299,6 +299,7 @@ xfs_buf_alloc_kmem(return -ENOMEM ; } bp->b_flags |= _XBF_KMEM; +trace_xfs_buf_backing_kmem (bp, _RET_IP_);return 0 ; }@@ -379,9 +380,11 @@ 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:@@ -395,6 +398,7 @@ xfs_buf_alloc_backing_mem(memalloc_retry_wait (gfp_mask); } +trace_xfs_buf_backing_vmalloc (bp, _RET_IP_);return 0 ; }fs/xfs/xfs_trace.h +4
-0@@ -545,6 +545,10 @@ 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);Signature · 1 line
2.45.2