From e47e2e0ba9103df7b3d25356421e6832c4d0e7be Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 19 Feb 2024 07:27:21 +0100 Subject: xfs: remove the xfile_pread/pwrite APIs All current and pending xfile users use the xfile_obj_load and xfile_obj_store API, so make those the actual implementation. Signed-off-by: Christoph Hellwig Reviewed-by: "Darrick J. Wong" Signed-off-by: Chandan Babu R --- .../filesystems/xfs/xfs-online-fsck-design.rst | 23 ++++++++-------------- 1 file changed, 8 insertions(+), 15 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/xfs/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst index 352516feef6ff..216c99ce511f7 100644 --- a/Documentation/filesystems/xfs/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst @@ -1915,19 +1915,13 @@ four of those five higher level data structures. The fifth use case is discussed in the :ref:`realtime summary ` case study. -The most general storage interface supported by the xfile enables the reading -and writing of arbitrary quantities of data at arbitrary offsets in the xfile. -This capability is provided by ``xfile_pread`` and ``xfile_pwrite`` functions, -which behave similarly to their userspace counterparts. XFS is very record-based, which suggests that the ability to load and store complete records is important. -To support these cases, a pair of ``xfile_obj_load`` and ``xfile_obj_store`` -functions are provided to read and persist objects into an xfile. -They are internally the same as pread and pwrite, except that they treat any -error as an out of memory error. -For online repair, squashing error conditions in this manner is an acceptable -behavior because the only reaction is to abort the operation back to userspace. -All five xfile usecases can be serviced by these four functions. +To support these cases, a pair of ``xfile_load`` and ``xfile_store`` +functions are provided to read and persist objects into an xfile that treat any +error as an out of memory error. For online repair, squashing error conditions +in this manner is an acceptable behavior because the only reaction is to abort +the operation back to userspace. However, no discussion of file access idioms is complete without answering the question, "But what about mmap?" @@ -1939,10 +1933,9 @@ tmpfs can only push a pagecache folio to the swap cache if the folio is neither pinned nor locked, which means the xfile must not pin too many folios. Short term direct access to xfile contents is done by locking the pagecache -folio and mapping it into kernel address space. -Programmatic access (e.g. pread and pwrite) uses this mechanism. -Folio locks are not supposed to be held for long periods of time, so long -term direct access to xfile contents is done by bumping the folio refcount, +folio and mapping it into kernel address space. Object load and store uses this +mechanism. Folio locks are not supposed to be held for long periods of time, so +long term direct access to xfile contents is done by bumping the folio refcount, mapping it into kernel address space, and dropping the folio lock. These long term users *must* be responsive to memory reclaim by hooking into the shrinker infrastructure to know when to release folios. -- cgit 1.2.3-korg From e5a2f47cff812c01018652f11d5e861e2a6b462b Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 19 Feb 2024 07:27:30 +0100 Subject: xfs: remove xfile_{get,put}_page These functions aren't used anymore, so get rid of them. Signed-off-by: "Darrick J. Wong" Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Chandan Babu R --- .../filesystems/xfs/xfs-online-fsck-design.rst | 2 +- fs/xfs/scrub/trace.h | 2 - fs/xfs/scrub/xfile.c | 104 --------------------- fs/xfs/scrub/xfile.h | 20 ---- 4 files changed, 1 insertion(+), 127 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/xfs/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst index 216c99ce511f7..d03480266e9b1 100644 --- a/Documentation/filesystems/xfs/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst @@ -1940,7 +1940,7 @@ mapping it into kernel address space, and dropping the folio lock. These long term users *must* be responsive to memory reclaim by hooking into the shrinker infrastructure to know when to release folios. -The ``xfile_get_page`` and ``xfile_put_page`` functions are provided to +The ``xfile_get_folio`` and ``xfile_put_folio`` functions are provided to retrieve the (locked) folio that backs part of an xfile and to release it. The only code to use these folio lease functions are the xfarray :ref:`sorting` algorithms and the :ref:`in-memory diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 3a1a827828dcb..ae6b2385a8cbe 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -906,8 +906,6 @@ DEFINE_EVENT(xfile_class, name, \ DEFINE_XFILE_EVENT(xfile_load); DEFINE_XFILE_EVENT(xfile_store); DEFINE_XFILE_EVENT(xfile_seek_data); -DEFINE_XFILE_EVENT(xfile_get_page); -DEFINE_XFILE_EVENT(xfile_put_page); DEFINE_XFILE_EVENT(xfile_get_folio); DEFINE_XFILE_EVENT(xfile_put_folio); diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c index 0cab9d529365b..8cdd863db5850 100644 --- a/fs/xfs/scrub/xfile.c +++ b/fs/xfs/scrub/xfile.c @@ -237,110 +237,6 @@ xfile_seek_data( return ret; } -/* - * Grab the (locked) page for a memory object. The object cannot span a page - * boundary. Returns 0 (and a locked page) if successful, -ENOTBLK if we - * cannot grab the page, or the usual negative errno. - */ -int -xfile_get_page( - struct xfile *xf, - loff_t pos, - unsigned int len, - struct xfile_page *xfpage) -{ - struct inode *inode = file_inode(xf->file); - struct address_space *mapping = inode->i_mapping; - const struct address_space_operations *aops = mapping->a_ops; - struct page *page = NULL; - void *fsdata = NULL; - loff_t key = round_down(pos, PAGE_SIZE); - unsigned int pflags; - int error; - - if (inode->i_sb->s_maxbytes - pos < len) - return -ENOMEM; - if (len > PAGE_SIZE - offset_in_page(pos)) - return -ENOTBLK; - - trace_xfile_get_page(xf, pos, len); - - pflags = memalloc_nofs_save(); - - /* - * We call write_begin directly here to avoid all the freezer - * protection lock-taking that happens in the normal path. shmem - * doesn't support fs freeze, but lockdep doesn't know that and will - * trip over that. - */ - error = aops->write_begin(NULL, mapping, key, PAGE_SIZE, &page, - &fsdata); - if (error) - goto out_pflags; - - /* We got the page, so make sure we push out EOF. */ - if (i_size_read(inode) < pos + len) - i_size_write(inode, pos + len); - - /* - * If the page isn't up to date, fill it with zeroes before we hand it - * to the caller and make sure the backing store will hold on to them. - */ - if (!PageUptodate(page)) { - memset(page_address(page), 0, PAGE_SIZE); - SetPageUptodate(page); - } - - /* - * Mark each page dirty so that the contents are written to some - * backing store when we drop this buffer, and take an extra reference - * to prevent the xfile page from being swapped or removed from the - * page cache by reclaim if the caller unlocks the page. - */ - set_page_dirty(page); - get_page(page); - - xfpage->page = page; - xfpage->fsdata = fsdata; - xfpage->pos = key; -out_pflags: - memalloc_nofs_restore(pflags); - return error; -} - -/* - * Release the (locked) page for a memory object. Returns 0 or a negative - * errno. - */ -int -xfile_put_page( - struct xfile *xf, - struct xfile_page *xfpage) -{ - struct inode *inode = file_inode(xf->file); - struct address_space *mapping = inode->i_mapping; - const struct address_space_operations *aops = mapping->a_ops; - unsigned int pflags; - int ret; - - trace_xfile_put_page(xf, xfpage->pos, PAGE_SIZE); - - /* Give back the reference that we took in xfile_get_page. */ - put_page(xfpage->page); - - pflags = memalloc_nofs_save(); - ret = aops->write_end(NULL, mapping, xfpage->pos, PAGE_SIZE, PAGE_SIZE, - xfpage->page, xfpage->fsdata); - memalloc_nofs_restore(pflags); - memset(xfpage, 0, sizeof(struct xfile_page)); - - if (ret < 0) - return ret; - if (ret != PAGE_SIZE) - return -EIO; - return 0; -} - /* * Grab the (locked) folio for a memory object. The object cannot span a folio * boundary. Returns the locked folio if successful, NULL if there was no diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h index afb75e9fbaf26..76d78dba7e347 100644 --- a/fs/xfs/scrub/xfile.h +++ b/fs/xfs/scrub/xfile.h @@ -6,22 +6,6 @@ #ifndef __XFS_SCRUB_XFILE_H__ #define __XFS_SCRUB_XFILE_H__ -struct xfile_page { - struct page *page; - void *fsdata; - loff_t pos; -}; - -static inline bool xfile_page_cached(const struct xfile_page *xfpage) -{ - return xfpage->page != NULL; -} - -static inline pgoff_t xfile_page_index(const struct xfile_page *xfpage) -{ - return xfpage->page->index; -} - struct xfile { struct file *file; }; @@ -35,10 +19,6 @@ int xfile_store(struct xfile *xf, const void *buf, size_t count, loff_t xfile_seek_data(struct xfile *xf, loff_t pos); -int xfile_get_page(struct xfile *xf, loff_t offset, unsigned int len, - struct xfile_page *xbuf); -int xfile_put_page(struct xfile *xf, struct xfile_page *xbuf); - #define XFILE_MAX_FOLIO_SIZE (PAGE_SIZE << MAX_PAGECACHE_ORDER) #define XFILE_ALLOC (1 << 0) /* allocate folio if not present */ -- cgit 1.2.3-korg From a095686a2383526d7315197e2419d84ee8470217 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 22 Feb 2024 12:43:35 -0800 Subject: xfs: support in-memory btrees Adapt the generic btree cursor code to be able to create a btree whose buffers come from a (presumably in-memory) buftarg with a header block that's specific to in-memory btrees. We'll connect this to other parts of online scrub in the next patches. Note that in-memory btrees always have a block size matching the system memory page size for efficiency reasons. There are also a few things we need to do to finalize a btree update; that's covered in the next patch. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- .../filesystems/xfs/xfs-online-fsck-design.rst | 5 +- fs/xfs/Kconfig | 4 + fs/xfs/Makefile | 1 + fs/xfs/libxfs/xfs_btree.c | 256 ++++++++++++++++++--- fs/xfs/libxfs/xfs_btree.h | 7 + fs/xfs/libxfs/xfs_btree_mem.c | 228 ++++++++++++++++++ fs/xfs/libxfs/xfs_btree_mem.h | 72 ++++++ fs/xfs/scrub/scrub.c | 5 + fs/xfs/scrub/scrub.h | 3 + fs/xfs/xfs_buf_mem.c | 13 ++ fs/xfs/xfs_buf_mem.h | 2 + fs/xfs/xfs_health.c | 3 + fs/xfs/xfs_trace.c | 1 + fs/xfs/xfs_trace.h | 117 +++++++++- 14 files changed, 675 insertions(+), 42 deletions(-) create mode 100644 fs/xfs/libxfs/xfs_btree_mem.c create mode 100644 fs/xfs/libxfs/xfs_btree_mem.h (limited to 'Documentation') diff --git a/Documentation/filesystems/xfs/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst index d03480266e9b1..6333697ba3e82 100644 --- a/Documentation/filesystems/xfs/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs/xfs-online-fsck-design.rst @@ -2270,13 +2270,12 @@ follows: pointing to the xfile. 3. Pass the buffer cache target, buffer ops, and other information to - ``xfbtree_create`` to write an initial tree header and root block to the - xfile. + ``xfbtree_init`` to initialize the passed in ``struct xfbtree`` and write an + initial root block to the xfile. Each btree type should define a wrapper that passes necessary arguments to the creation function. For example, rmap btrees define ``xfs_rmapbt_mem_create`` to take care of all the necessary details for callers. - A ``struct xfbtree`` object will be returned. 4. Pass the xfbtree object to the btree cursor creation function for the btree type. diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 7017ea0fb4cd3..d41edd30388b7 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -131,6 +131,9 @@ config XFS_LIVE_HOOKS config XFS_MEMORY_BUFS bool +config XFS_BTREE_IN_MEM + bool + config XFS_ONLINE_SCRUB bool "XFS online metadata check support" default n @@ -173,6 +176,7 @@ config XFS_ONLINE_REPAIR bool "XFS online metadata repair support" default n depends on XFS_FS && XFS_ONLINE_SCRUB + select XFS_BTREE_IN_MEM help If you say Y here you will be able to repair metadata on a mounted XFS filesystem. This feature is intended to reduce diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 045874235b82b..9a6574da8de5b 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -138,6 +138,7 @@ endif xfs-$(CONFIG_XFS_DRAIN_INTENTS) += xfs_drain.o xfs-$(CONFIG_XFS_LIVE_HOOKS) += xfs_hooks.o xfs-$(CONFIG_XFS_MEMORY_BUFS) += xfs_buf_mem.o +xfs-$(CONFIG_XFS_BTREE_IN_MEM) += libxfs/xfs_btree_mem.o # online scrub/repair ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index aa60a46b8eecc..d29547572a688 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -28,6 +28,8 @@ #include "xfs_rmap_btree.h" #include "xfs_refcount_btree.h" #include "xfs_health.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" /* * Btree magic numbers. @@ -75,6 +77,25 @@ xfs_btree_check_fsblock_siblings( return NULL; } +static inline xfs_failaddr_t +xfs_btree_check_memblock_siblings( + struct xfs_buftarg *btp, + xfbno_t bno, + __be64 dsibling) +{ + xfbno_t sibling; + + if (dsibling == cpu_to_be64(NULLFSBLOCK)) + return NULL; + + sibling = be64_to_cpu(dsibling); + if (sibling == bno) + return __this_address; + if (!xmbuf_verify_daddr(btp, xfbno_to_daddr(sibling))) + return __this_address; + return NULL; +} + static inline xfs_failaddr_t xfs_btree_check_agblock_siblings( struct xfs_perag *pag, @@ -164,6 +185,34 @@ __xfs_btree_check_fsblock( return fa; } +/* + * Check an in-memory btree block header. Return the address of the failing + * check, or NULL if everything is ok. + */ +static xfs_failaddr_t +__xfs_btree_check_memblock( + struct xfs_btree_cur *cur, + struct xfs_btree_block *block, + int level, + struct xfs_buf *bp) +{ + struct xfs_buftarg *btp = cur->bc_mem.xfbtree->target; + xfs_failaddr_t fa; + xfbno_t bno; + + fa = __xfs_btree_check_lblock_hdr(cur, block, level, bp); + if (fa) + return fa; + + bno = xfs_daddr_to_xfbno(xfs_buf_daddr(bp)); + fa = xfs_btree_check_memblock_siblings(btp, bno, + block->bb_u.l.bb_leftsib); + if (!fa) + fa = xfs_btree_check_memblock_siblings(btp, bno, + block->bb_u.l.bb_rightsib); + return fa; +} + /* * Check a short btree block header. Return the address of the failing check, * or NULL if everything is ok. @@ -216,9 +265,17 @@ __xfs_btree_check_block( int level, struct xfs_buf *bp) { - if (cur->bc_ops->type == XFS_BTREE_TYPE_AG) + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_MEM: + return __xfs_btree_check_memblock(cur, block, level, bp); + case XFS_BTREE_TYPE_AG: return __xfs_btree_check_agblock(cur, block, level, bp); - return __xfs_btree_check_fsblock(cur, block, level, bp); + case XFS_BTREE_TYPE_INODE: + return __xfs_btree_check_fsblock(cur, block, level, bp); + default: + ASSERT(0); + return __this_address; + } } static inline unsigned int xfs_btree_block_errtag(struct xfs_btree_cur *cur) @@ -262,14 +319,22 @@ __xfs_btree_check_ptr( if (level <= 0) return -EFSCORRUPTED; - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_MEM: + if (!xfbtree_verify_bno(cur->bc_mem.xfbtree, + be64_to_cpu((&ptr->l)[index]))) + return -EFSCORRUPTED; + break; + case XFS_BTREE_TYPE_INODE: if (!xfs_verify_fsbno(cur->bc_mp, be64_to_cpu((&ptr->l)[index]))) return -EFSCORRUPTED; - } else { + break; + case XFS_BTREE_TYPE_AG: if (!xfs_verify_agbno(cur->bc_ag.pag, be32_to_cpu((&ptr->s)[index]))) return -EFSCORRUPTED; + break; } return 0; @@ -290,17 +355,26 @@ xfs_btree_check_ptr( error = __xfs_btree_check_ptr(cur, ptr, index, level); if (error) { - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_MEM: + xfs_err(cur->bc_mp, +"In-memory: Corrupt %sbt flags 0x%x pointer at level %d index %d fa %pS.", + cur->bc_ops->name, cur->bc_flags, level, index, + __this_address); + break; + case XFS_BTREE_TYPE_INODE: xfs_err(cur->bc_mp, "Inode %llu fork %d: Corrupt %sbt pointer at level %d index %d.", cur->bc_ino.ip->i_ino, cur->bc_ino.whichfork, cur->bc_ops->name, level, index); - } else { + break; + case XFS_BTREE_TYPE_AG: xfs_err(cur->bc_mp, "AG %u: Corrupt %sbt pointer at level %d index %d.", cur->bc_ag.pag->pag_agno, cur->bc_ops->name, level, index); + break; } xfs_btree_mark_sick(cur); } @@ -457,11 +531,35 @@ xfs_btree_del_cursor( case XFS_BTREE_TYPE_INODE: /* nothing to do */ break; + case XFS_BTREE_TYPE_MEM: + if (cur->bc_mem.pag) + xfs_perag_put(cur->bc_mem.pag); + break; } kmem_cache_free(cur->bc_cache, cur); } +/* Return the buffer target for this btree's buffer. */ +static inline struct xfs_buftarg * +xfs_btree_buftarg( + struct xfs_btree_cur *cur) +{ + if (cur->bc_ops->type == XFS_BTREE_TYPE_MEM) + return cur->bc_mem.xfbtree->target; + return cur->bc_mp->m_ddev_targp; +} + +/* Return the block size (in units of 512b sectors) for this btree. */ +static inline unsigned int +xfs_btree_bbsize( + struct xfs_btree_cur *cur) +{ + if (cur->bc_ops->type == XFS_BTREE_TYPE_MEM) + return XFBNO_BBSIZE; + return cur->bc_mp->m_bsize; +} + /* * Duplicate the btree cursor. * Allocate a new one, copy the record, re-get the buffers. @@ -505,10 +603,11 @@ xfs_btree_dup_cursor( new->bc_levels[i].ra = cur->bc_levels[i].ra; bp = cur->bc_levels[i].bp; if (bp) { - error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, - xfs_buf_daddr(bp), mp->m_bsize, - 0, &bp, - cur->bc_ops->buf_ops); + error = xfs_trans_read_buf(mp, tp, + xfs_btree_buftarg(cur), + xfs_buf_daddr(bp), + xfs_btree_bbsize(cur), 0, &bp, + cur->bc_ops->buf_ops); if (xfs_metadata_is_sick(error)) xfs_btree_mark_sick(new); if (error) { @@ -885,6 +984,32 @@ xfs_btree_readahead_fsblock( return rval; } +STATIC int +xfs_btree_readahead_memblock( + struct xfs_btree_cur *cur, + int lr, + struct xfs_btree_block *block) +{ + struct xfs_buftarg *btp = cur->bc_mem.xfbtree->target; + xfbno_t left = be64_to_cpu(block->bb_u.l.bb_leftsib); + xfbno_t right = be64_to_cpu(block->bb_u.l.bb_rightsib); + int rval = 0; + + if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) { + xfs_buf_readahead(btp, xfbno_to_daddr(left), XFBNO_BBSIZE, + cur->bc_ops->buf_ops); + rval++; + } + + if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLFSBLOCK) { + xfs_buf_readahead(btp, xfbno_to_daddr(right), XFBNO_BBSIZE, + cur->bc_ops->buf_ops); + rval++; + } + + return rval; +} + STATIC int xfs_btree_readahead_agblock( struct xfs_btree_cur *cur, @@ -939,9 +1064,17 @@ xfs_btree_readahead( cur->bc_levels[lev].ra |= lr; block = XFS_BUF_TO_BLOCK(cur->bc_levels[lev].bp); - if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_AG: + return xfs_btree_readahead_agblock(cur, lr, block); + case XFS_BTREE_TYPE_INODE: return xfs_btree_readahead_fsblock(cur, lr, block); - return xfs_btree_readahead_agblock(cur, lr, block); + case XFS_BTREE_TYPE_MEM: + return xfs_btree_readahead_memblock(cur, lr, block); + default: + ASSERT(0); + return 0; + } } STATIC int @@ -950,23 +1083,24 @@ xfs_btree_ptr_to_daddr( const union xfs_btree_ptr *ptr, xfs_daddr_t *daddr) { - xfs_fsblock_t fsbno; - xfs_agblock_t agbno; int error; error = xfs_btree_check_ptr(cur, ptr, 0, 1); if (error) return error; - if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { - fsbno = be64_to_cpu(ptr->l); - *daddr = XFS_FSB_TO_DADDR(cur->bc_mp, fsbno); - } else { - agbno = be32_to_cpu(ptr->s); + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_AG: *daddr = XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_ag.pag->pag_agno, - agbno); + be32_to_cpu(ptr->s)); + break; + case XFS_BTREE_TYPE_INODE: + *daddr = XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l)); + break; + case XFS_BTREE_TYPE_MEM: + *daddr = xfbno_to_daddr(be64_to_cpu(ptr->l)); + break; } - return 0; } @@ -986,8 +1120,9 @@ xfs_btree_readahead_ptr( if (xfs_btree_ptr_to_daddr(cur, ptr, &daddr)) return; - xfs_buf_readahead(cur->bc_mp->m_ddev_targp, daddr, - cur->bc_mp->m_bsize * count, cur->bc_ops->buf_ops); + xfs_buf_readahead(xfs_btree_buftarg(cur), daddr, + xfs_btree_bbsize(cur) * count, + cur->bc_ops->buf_ops); } /* @@ -1172,9 +1307,17 @@ static inline __u64 xfs_btree_owner( struct xfs_btree_cur *cur) { - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_MEM: + return cur->bc_mem.xfbtree->owner; + case XFS_BTREE_TYPE_INODE: return cur->bc_ino.ip->i_ino; - return cur->bc_ag.pag->pag_agno; + case XFS_BTREE_TYPE_AG: + return cur->bc_ag.pag->pag_agno; + default: + ASSERT(0); + return 0; + } } void @@ -1218,12 +1361,18 @@ xfs_btree_buf_to_ptr( struct xfs_buf *bp, union xfs_btree_ptr *ptr) { - if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) - ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp, - xfs_buf_daddr(bp))); - else { + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_AG: ptr->s = cpu_to_be32(xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp))); + break; + case XFS_BTREE_TYPE_INODE: + ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp, + xfs_buf_daddr(bp))); + break; + case XFS_BTREE_TYPE_MEM: + ptr->l = cpu_to_be64(xfs_daddr_to_xfbno(xfs_buf_daddr(bp))); + break; } } @@ -1242,15 +1391,14 @@ xfs_btree_get_buf_block( struct xfs_btree_block **block, struct xfs_buf **bpp) { - struct xfs_mount *mp = cur->bc_mp; - xfs_daddr_t d; - int error; + xfs_daddr_t d; + int error; error = xfs_btree_ptr_to_daddr(cur, ptr, &d); if (error) return error; - error = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d, mp->m_bsize, - 0, bpp); + error = xfs_trans_get_buf(cur->bc_tp, xfs_btree_buftarg(cur), d, + xfs_btree_bbsize(cur), 0, bpp); if (error) return error; @@ -1281,9 +1429,9 @@ xfs_btree_read_buf_block( error = xfs_btree_ptr_to_daddr(cur, ptr, &d); if (error) return error; - error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d, - mp->m_bsize, flags, bpp, - cur->bc_ops->buf_ops); + error = xfs_trans_read_buf(mp, cur->bc_tp, xfs_btree_buftarg(cur), d, + xfs_btree_bbsize(cur), flags, bpp, + cur->bc_ops->buf_ops); if (xfs_metadata_is_sick(error)) xfs_btree_mark_sick(cur); if (error) @@ -4582,6 +4730,8 @@ xfs_btree_fsblock_verify( xfs_fsblock_t fsb; xfs_failaddr_t fa; + ASSERT(!xfs_buftarg_is_mem(bp->b_target)); + /* numrecs verification */ if (be16_to_cpu(block->bb_numrecs) > max_recs) return __this_address; @@ -4596,6 +4746,36 @@ xfs_btree_fsblock_verify( return fa; } +/* Verify an in-memory btree block. */ +xfs_failaddr_t +xfs_btree_memblock_verify( + struct xfs_buf *bp, + unsigned int max_recs) +{ + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); + struct xfs_buftarg *btp = bp->b_target; + xfs_failaddr_t fa; + xfbno_t bno; + + ASSERT(xfs_buftarg_is_mem(bp->b_target)); + + /* numrecs verification */ + if (be16_to_cpu(block->bb_numrecs) > max_recs) + return __this_address; + + /* sibling pointer verification */ + bno = xfs_daddr_to_xfbno(xfs_buf_daddr(bp)); + fa = xfs_btree_check_memblock_siblings(btp, bno, + block->bb_u.l.bb_leftsib); + if (fa) + return fa; + fa = xfs_btree_check_memblock_siblings(btp, bno, + block->bb_u.l.bb_rightsib); + if (fa) + return fa; + + return NULL; +} /** * xfs_btree_agblock_v5hdr_verify() -- verify the v5 fields of a short-format * btree block @@ -4637,6 +4817,8 @@ xfs_btree_agblock_verify( xfs_agblock_t agbno; xfs_failaddr_t fa; + ASSERT(!xfs_buftarg_is_mem(bp->b_target)); + /* numrecs verification */ if (be16_to_cpu(block->bb_numrecs) > max_recs) return __this_address; diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index bacd67cc8cedb..f93374278aa1b 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -112,6 +112,7 @@ static inline enum xbtree_key_contig xbtree_key_contig(uint64_t x, uint64_t y) enum xfs_btree_type { XFS_BTREE_TYPE_AG, XFS_BTREE_TYPE_INODE, + XFS_BTREE_TYPE_MEM, }; struct xfs_btree_ops { @@ -281,6 +282,10 @@ struct xfs_btree_cur struct xfs_buf *agbp; struct xbtree_afakeroot *afake; /* for staging cursor */ } bc_ag; + struct { + struct xfbtree *xfbtree; + struct xfs_perag *pag; + } bc_mem; }; /* per-format private data */ @@ -455,6 +460,8 @@ xfs_failaddr_t xfs_btree_fsblock_v5hdr_verify(struct xfs_buf *bp, uint64_t owner); xfs_failaddr_t xfs_btree_fsblock_verify(struct xfs_buf *bp, unsigned int max_recs); +xfs_failaddr_t xfs_btree_memblock_verify(struct xfs_buf *bp, + unsigned int max_recs); unsigned int xfs_btree_compute_maxlevels(const unsigned int *limits, unsigned long long records); diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c new file mode 100644 index 0000000000000..cb156e9363a5d --- /dev/null +++ b/fs/xfs/libxfs/xfs_btree_mem.c @@ -0,0 +1,228 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_trans.h" +#include "xfs_btree.h" +#include "xfs_error.h" +#include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" +#include "xfs_ag.h" +#include "xfs_buf_item.h" +#include "xfs_trace.h" + +/* Set the root of an in-memory btree. */ +void +xfbtree_set_root( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *ptr, + int inc) +{ + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + cur->bc_mem.xfbtree->root = *ptr; + cur->bc_mem.xfbtree->nlevels += inc; +} + +/* Initialize a pointer from the in-memory btree header. */ +void +xfbtree_init_ptr_from_cur( + struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr) +{ + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + *ptr = cur->bc_mem.xfbtree->root; +} + +/* Duplicate an in-memory btree cursor. */ +struct xfs_btree_cur * +xfbtree_dup_cursor( + struct xfs_btree_cur *cur) +{ + struct xfs_btree_cur *ncur; + + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + ncur = xfs_btree_alloc_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ops, + cur->bc_maxlevels, cur->bc_cache); + ncur->bc_flags = cur->bc_flags; + ncur->bc_nlevels = cur->bc_nlevels; + ncur->bc_mem.xfbtree = cur->bc_mem.xfbtree; + + if (cur->bc_mem.pag) + ncur->bc_mem.pag = xfs_perag_hold(cur->bc_mem.pag); + + return ncur; +} + +/* Close the btree xfile and release all resources. */ +void +xfbtree_destroy( + struct xfbtree *xfbt) +{ + xfs_buftarg_drain(xfbt->target); +} + +/* Compute the number of bytes available for records. */ +static inline unsigned int +xfbtree_rec_bytes( + struct xfs_mount *mp, + const struct xfs_btree_ops *ops) +{ + return XMBUF_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; +} + +/* Initialize an empty leaf block as the btree root. */ +STATIC int +xfbtree_init_leaf_block( + struct xfs_mount *mp, + struct xfbtree *xfbt, + const struct xfs_btree_ops *ops) +{ + struct xfs_buf *bp; + xfbno_t bno = xfbt->highest_bno++; + int error; + + error = xfs_buf_get(xfbt->target, xfbno_to_daddr(bno), XFBNO_BBSIZE, + &bp); + if (error) + return error; + + trace_xfbtree_create_root_buf(xfbt, bp); + + bp->b_ops = ops->buf_ops; + xfs_btree_init_buf(mp, bp, ops, 0, 0, xfbt->owner); + xfs_buf_relse(bp); + + xfbt->root.l = cpu_to_be64(bno); + return 0; +} + +/* + * Create an in-memory btree root that can be used with the given xmbuf. + * Callers must set xfbt->owner. + */ +int +xfbtree_init( + struct xfs_mount *mp, + struct xfbtree *xfbt, + struct xfs_buftarg *btp, + const struct xfs_btree_ops *ops) +{ + unsigned int blocklen = xfbtree_rec_bytes(mp, ops); + unsigned int keyptr_len; + int error; + + /* Requires a long-format CRC-format btree */ + if (!xfs_has_crc(mp)) { + ASSERT(xfs_has_crc(mp)); + return -EINVAL; + } + if (ops->ptr_len != XFS_BTREE_LONG_PTR_LEN) { + ASSERT(ops->ptr_len == XFS_BTREE_LONG_PTR_LEN); + return -EINVAL; + } + + memset(xfbt, 0, sizeof(*xfbt)); + xfbt->target = btp; + + /* Set up min/maxrecs for this btree. */ + keyptr_len = ops->key_len + sizeof(__be64); + xfbt->maxrecs[0] = blocklen / ops->rec_len; + xfbt->maxrecs[1] = blocklen / keyptr_len; + xfbt->minrecs[0] = xfbt->maxrecs[0] / 2; + xfbt->minrecs[1] = xfbt->maxrecs[1] / 2; + xfbt->highest_bno = 0; + xfbt->nlevels = 1; + + /* Initialize the empty btree. */ + error = xfbtree_init_leaf_block(mp, xfbt, ops); + if (error) + goto err_freesp; + + trace_xfbtree_init(mp, xfbt, ops); + + return 0; + +err_freesp: + xfs_buftarg_drain(xfbt->target); + return error; +} + +/* Allocate a block to our in-memory btree. */ +int +xfbtree_alloc_block( + struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, + union xfs_btree_ptr *new, + int *stat) +{ + struct xfbtree *xfbt = cur->bc_mem.xfbtree; + xfbno_t bno = xfbt->highest_bno++; + + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + trace_xfbtree_alloc_block(xfbt, cur, bno); + + /* Fail if the block address exceeds the maximum for the buftarg. */ + if (!xfbtree_verify_bno(xfbt, bno)) { + ASSERT(xfbtree_verify_bno(xfbt, bno)); + *stat = 0; + return 0; + } + + new->l = cpu_to_be64(bno); + *stat = 1; + return 0; +} + +/* Free a block from our in-memory btree. */ +int +xfbtree_free_block( + struct xfs_btree_cur *cur, + struct xfs_buf *bp) +{ + struct xfbtree *xfbt = cur->bc_mem.xfbtree; + xfs_daddr_t daddr = xfs_buf_daddr(bp); + xfbno_t bno = xfs_daddr_to_xfbno(daddr); + + ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM); + + trace_xfbtree_free_block(xfbt, cur, bno); + + if (bno + 1 == xfbt->highest_bno) + xfbt->highest_bno--; + + return 0; +} + +/* Return the minimum number of records for a btree block. */ +int +xfbtree_get_minrecs( + struct xfs_btree_cur *cur, + int level) +{ + struct xfbtree *xfbt = cur->bc_mem.xfbtree; + + return xfbt->minrecs[level != 0]; +} + +/* Return the maximum number of records for a btree block. */ +int +xfbtree_get_maxrecs( + struct xfs_btree_cur *cur, + int level) +{ + struct xfbtree *xfbt = cur->bc_mem.xfbtree; + + return xfbt->maxrecs[level != 0]; +} diff --git a/fs/xfs/libxfs/xfs_btree_mem.h b/fs/xfs/libxfs/xfs_btree_mem.h new file mode 100644 index 0000000000000..ecc2ceac3ed4f --- /dev/null +++ b/fs/xfs/libxfs/xfs_btree_mem.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021-2024 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#ifndef __XFS_BTREE_MEM_H__ +#define __XFS_BTREE_MEM_H__ + +typedef uint64_t xfbno_t; + +#define XFBNO_BLOCKSIZE (XMBUF_BLOCKSIZE) +#define XFBNO_BBSHIFT (XMBUF_BLOCKSHIFT - BBSHIFT) +#define XFBNO_BBSIZE (XFBNO_BLOCKSIZE >> BBSHIFT) + +static inline xfs_daddr_t xfbno_to_daddr(xfbno_t blkno) +{ + return blkno << XFBNO_BBSHIFT; +} + +static inline xfbno_t xfs_daddr_to_xfbno(xfs_daddr_t daddr) +{ + return daddr >> XFBNO_BBSHIFT; +} + +struct xfbtree { + /* buffer cache target for this in-memory btree */ + struct xfs_buftarg *target; + + /* Highest block number that has been written to. */ + xfbno_t highest_bno; + + /* Owner of this btree. */ + unsigned long long owner; + + /* Btree header */ + union xfs_btree_ptr root; + unsigned int nlevels; + + /* Minimum and maximum records per block. */ + unsigned int maxrecs[2]; + unsigned int minrecs[2]; +}; + +#ifdef CONFIG_XFS_BTREE_IN_MEM +static inline bool xfbtree_verify_bno(struct xfbtree *xfbt, xfbno_t bno) +{ + return xmbuf_verify_daddr(xfbt->target, xfbno_to_daddr(bno)); +} + +void xfbtree_set_root(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *ptr, int inc); +void xfbtree_init_ptr_from_cur(struct xfs_btree_cur *cur, + union xfs_btree_ptr *ptr); +struct xfs_btree_cur *xfbtree_dup_cursor(struct xfs_btree_cur *cur); + +int xfbtree_get_minrecs(struct xfs_btree_cur *cur, int level); +int xfbtree_get_maxrecs(struct xfs_btree_cur *cur, int level); + +int xfbtree_alloc_block(struct xfs_btree_cur *cur, + const union xfs_btree_ptr *start, union xfs_btree_ptr *ptr, + int *stat); +int xfbtree_free_block(struct xfs_btree_cur *cur, struct xfs_buf *bp); + +/* Callers must set xfbt->target and xfbt->owner before calling this */ +int xfbtree_init(struct xfs_mount *mp, struct xfbtree *xfbt, + struct xfs_buftarg *btp, const struct xfs_btree_ops *ops); +void xfbtree_destroy(struct xfbtree *xfbt); +#else +# define xfbtree_verify_bno(...) (false) +#endif /* CONFIG_XFS_BTREE_IN_MEM */ + +#endif /* __XFS_BTREE_MEM_H__ */ diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index aeac9cae4ad4c..6828e72824fb5 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -15,6 +15,7 @@ #include "xfs_quota.h" #include "xfs_qm.h" #include "xfs_scrub.h" +#include "xfs_buf_mem.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -190,6 +191,10 @@ xchk_teardown( sc->flags &= ~XCHK_HAVE_FREEZE_PROT; mnt_drop_write_file(sc->file); } + if (sc->xmbtp) { + xmbuf_free(sc->xmbtp); + sc->xmbtp = NULL; + } if (sc->xfile) { xfile_destroy(sc->xfile); sc->xfile = NULL; diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index f99a3c21d02ea..1247284c17a09 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -99,6 +99,9 @@ struct xfs_scrub { /* xfile used by the scrubbers; freed at teardown. */ struct xfile *xfile; + /* buffer target for in-memory btrees; also freed at teardown. */ + struct xfs_buftarg *xmbtp; + /* Lock flags for @ip. */ uint ilock_flags; diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c index be71ba1a3d7b0..73caa2ea8b18f 100644 --- a/fs/xfs/xfs_buf_mem.c +++ b/fs/xfs/xfs_buf_mem.c @@ -187,3 +187,16 @@ xmbuf_unmap_page( bp->b_pages = NULL; bp->b_page_count = 0; } + +/* Is this a valid daddr within the buftarg? */ +bool +xmbuf_verify_daddr( + struct xfs_buftarg *btp, + xfs_daddr_t daddr) +{ + struct inode *inode = file_inode(btp->bt_file); + + ASSERT(xfs_buftarg_is_mem(btp)); + + return daddr < (inode->i_sb->s_maxbytes >> BBSHIFT); +} diff --git a/fs/xfs/xfs_buf_mem.h b/fs/xfs/xfs_buf_mem.h index 945f4b610998f..dfb3029113ff7 100644 --- a/fs/xfs/xfs_buf_mem.h +++ b/fs/xfs/xfs_buf_mem.h @@ -21,10 +21,12 @@ 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); #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 */ #endif /* __XFS_BUF_MEM_H__ */ diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c index b28546b6fe34d..b39f959146bc1 100644 --- a/fs/xfs/xfs_health.c +++ b/fs/xfs/xfs_health.c @@ -527,6 +527,9 @@ xfs_btree_mark_sick( struct xfs_btree_cur *cur) { switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_MEM: + /* no health state tracking for ephemeral btrees */ + return; case XFS_BTREE_TYPE_AG: ASSERT(cur->bc_ops->sick_mask); xfs_ag_mark_sick(cur->bc_ag.pag, cur->bc_ops->sick_mask); diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index ae5be6b589f0e..3f253884fe5b1 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -37,6 +37,7 @@ #include #include "xfs_iomap.h" #include "xfs_buf_mem.h" +#include "xfs_btree_mem.h" /* * We include this last to have the helpers above available for the trace diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 14cb8752e3d3b..4971d650bd6b4 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -79,6 +79,8 @@ union xfs_btree_ptr; struct xfs_dqtrx; struct xfs_icwalk; struct xfs_perag; +struct xfbtree; +struct xfs_btree_ops; #define XFS_ATTR_FILTER_FLAGS \ { XFS_ATTR_ROOT, "ROOT" }, \ @@ -2499,12 +2501,19 @@ TRACE_EVENT(xfs_btree_alloc_block, ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; - if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { + switch (cur->bc_ops->type) { + case XFS_BTREE_TYPE_INODE: __entry->agno = 0; __entry->ino = cur->bc_ino.ip->i_ino; - } else { + break; + case XFS_BTREE_TYPE_AG: __entry->agno = cur->bc_ag.pag->pag_agno; __entry->ino = 0; + break; + case XFS_BTREE_TYPE_MEM: + __entry->agno = 0; + __entry->ino = 0; + break; } __assign_str(name, cur->bc_ops->name); __entry->error = error; @@ -4563,6 +4572,110 @@ TRACE_EVENT(xmbuf_free, ); #endif /* CONFIG_XFS_MEMORY_BUFS */ +#ifdef CONFIG_XFS_BTREE_IN_MEM +TRACE_EVENT(xfbtree_init, + TP_PROTO(struct xfs_mount *mp, struct xfbtree *xfbt, + const struct xfs_btree_ops *ops), + TP_ARGS(mp, xfbt, ops), + TP_STRUCT__entry( + __field(const void *, btree_ops) + __field(unsigned long, xfino) + __field(unsigned int, leaf_mxr) + __field(unsigned int, leaf_mnr) + __field(unsigned int, node_mxr) + __field(unsigned int, node_mnr) + __field(unsigned long long, owner) + ), + TP_fast_assign( + __entry->btree_ops = ops; + __entry->xfino = file_inode(xfbt->target->bt_file)->i_ino; + __entry->leaf_mxr = xfbt->maxrecs[0]; + __entry->node_mxr = xfbt->maxrecs[1]; + __entry->leaf_mnr = xfbt->minrecs[0]; + __entry->node_mnr = xfbt->minrecs[1]; + __entry->owner = xfbt->owner; + ), + TP_printk("xfino 0x%lx btree_ops %pS owner 0x%llx leaf_mxr %u leaf_mnr %u node_mxr %u node_mnr %u", + __entry->xfino, + __entry->btree_ops, + __entry->owner, + __entry->leaf_mxr, + __entry->leaf_mnr, + __entry->node_mxr, + __entry->node_mnr) +); + +DECLARE_EVENT_CLASS(xfbtree_buf_class, + TP_PROTO(struct xfbtree *xfbt, struct xfs_buf *bp), + TP_ARGS(xfbt, bp), + TP_STRUCT__entry( + __field(unsigned long, xfino) + __field(xfs_daddr_t, bno) + __field(int, nblks) + __field(int, hold) + __field(int, pincount) + __field(unsigned int, lockval) + __field(unsigned int, flags) + ), + TP_fast_assign( + __entry->xfino = file_inode(xfbt->target->bt_file)->i_ino; + __entry->bno = xfs_buf_daddr(bp); + __entry->nblks = bp->b_length; + __entry->hold = atomic_read(&bp->b_hold); + __entry->pincount = atomic_read(&bp->b_pin_count); + __entry->lockval = bp->b_sema.count; + __entry->flags = bp->b_flags; + ), + TP_printk("xfino 0x%lx daddr 0x%llx bbcount 0x%x hold %d pincount %d lock %d flags %s", + __entry->xfino, + (unsigned long long)__entry->bno, + __entry->nblks, + __entry->hold, + __entry->pincount, + __entry->lockval, + __print_flags(__entry->flags, "|", XFS_BUF_FLAGS)) +) + +#define DEFINE_XFBTREE_BUF_EVENT(name) \ +DEFINE_EVENT(xfbtree_buf_class, name, \ + TP_PROTO(struct xfbtree *xfbt, struct xfs_buf *bp), \ + TP_ARGS(xfbt, bp)) +DEFINE_XFBTREE_BUF_EVENT(xfbtree_create_root_buf); +DEFINE_XFBTREE_BUF_EVENT(xfbtree_trans_commit_buf); +DEFINE_XFBTREE_BUF_EVENT(xfbtree_trans_cancel_buf); + +DECLARE_EVENT_CLASS(xfbtree_freesp_class, + TP_PROTO(struct xfbtree *xfbt, struct xfs_btree_cur *cur, + xfs_fileoff_t fileoff), + TP_ARGS(xfbt, cur, fileoff), + TP_STRUCT__entry( + __field(unsigned long, xfino) + __string(btname, cur->bc_ops->name) + __field(int, nlevels) + __field(xfs_fileoff_t, fileoff) + ), + TP_fast_assign( + __entry->xfino = file_inode(xfbt->target->bt_file)->i_ino; + __assign_str(btname, cur->bc_ops->name); + __entry->nlevels = cur->bc_nlevels; + __entry->fileoff = fileoff; + ), + TP_printk("xfino 0x%lx %sbt nlevels %d fileoff 0x%llx", + __entry->xfino, + __get_str(btname), + __entry->nlevels, + (unsigned long long)__entry->fileoff) +) + +#define DEFINE_XFBTREE_FREESP_EVENT(name) \ +DEFINE_EVENT(xfbtree_freesp_class, name, \ + TP_PROTO(struct xfbtree *xfbt, struct xfs_btree_cur *cur, \ + xfs_fileoff_t fileoff), \ + TP_ARGS(xfbt, cur, fileoff)) +DEFINE_XFBTREE_FREESP_EVENT(xfbtree_alloc_block); +DEFINE_XFBTREE_FREESP_EVENT(xfbtree_free_block); +#endif /* CONFIG_XFS_BTREE_IN_MEM */ + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH -- cgit 1.2.3-korg