From 4f13f0a3fc6ad193e4d144a5e001b7b8f1fc4b7f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 20 Nov 2024 16:20:12 -0800 Subject: xfs: tidy up xfs_iroot_realloc Tidy up this function a bit before we start refactoring the memory handling and move the function to the bmbt code. Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_inode_fork.c | 83 ++++++++++++++++++++---------------------- 1 file changed, 40 insertions(+), 43 deletions(-) (limited to 'fs/xfs/libxfs/xfs_inode_fork.c') diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 1158ca48626b..7f865479c415 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -382,33 +382,32 @@ xfs_iformat_attr_fork( */ void xfs_iroot_realloc( - xfs_inode_t *ip, + struct xfs_inode *ip, int rec_diff, int whichfork) { struct xfs_mount *mp = ip->i_mount; - int cur_max; - struct xfs_ifork *ifp; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_block *new_broot; - int new_max; - size_t new_size; char *np; char *op; + size_t new_size; + short old_size = ifp->if_broot_bytes; + int cur_max; + int new_max; /* * Handle the degenerate case quietly. */ - if (rec_diff == 0) { + if (rec_diff == 0) return; - } - ifp = xfs_ifork_ptr(ip, whichfork); if (rec_diff > 0) { /* * If there wasn't any memory allocated before, just * allocate it now and get out. */ - if (ifp->if_broot_bytes == 0) { + if (old_size == 0) { new_size = xfs_bmap_broot_space_calc(mp, rec_diff); ifp->if_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); @@ -422,13 +421,13 @@ xfs_iroot_realloc( * location. The records don't change location because * they are kept butted up against the btree block header. */ - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false); + cur_max = xfs_bmbt_maxrecs(mp, old_size, false); new_max = cur_max + rec_diff; new_size = xfs_bmap_broot_space_calc(mp, new_max); ifp->if_broot = krealloc(ifp->if_broot, new_size, GFP_KERNEL | __GFP_NOFAIL); op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); + old_size); np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, (int)new_size); ifp->if_broot_bytes = (int)new_size; @@ -443,52 +442,50 @@ xfs_iroot_realloc( * if_broot buffer. It must already exist. If we go to zero * records, just get rid of the root and clear the status bit. */ - ASSERT((ifp->if_broot != NULL) && (ifp->if_broot_bytes > 0)); - cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false); + ASSERT(ifp->if_broot != NULL && old_size > 0); + cur_max = xfs_bmbt_maxrecs(mp, old_size, false); new_max = cur_max + rec_diff; ASSERT(new_max >= 0); if (new_max > 0) new_size = xfs_bmap_broot_space_calc(mp, new_max); else new_size = 0; - if (new_size > 0) { - new_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); - /* - * First copy over the btree block header. - */ - memcpy(new_broot, ifp->if_broot, - xfs_bmbt_block_len(ip->i_mount)); - } else { - new_broot = NULL; + if (new_size == 0) { + ifp->if_broot = NULL; + ifp->if_broot_bytes = 0; + return; } /* - * Only copy the keys and pointers if there are any. + * Shrink the btree root by allocating a smaller object and copying the + * fields from the old object to the new object. krealloc does nothing + * if we realloc downwards. */ - if (new_max > 0) { - /* - * First copy the keys. - */ - op = (char *)xfs_bmbt_key_addr(mp, ifp->if_broot, 1); - np = (char *)xfs_bmbt_key_addr(mp, new_broot, 1); - memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_key_t)); + new_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); + /* + * First copy over the btree block header. + */ + memcpy(new_broot, ifp->if_broot, xfs_bmbt_block_len(ip->i_mount)); + + /* + * First copy the keys. + */ + op = (char *)xfs_bmbt_key_addr(mp, ifp->if_broot, 1); + np = (char *)xfs_bmbt_key_addr(mp, new_broot, 1); + memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_key_t)); + + /* + * Then copy the pointers. + */ + op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, old_size); + np = (char *)xfs_bmap_broot_ptr_addr(mp, new_broot, 1, (int)new_size); + memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t)); - /* - * Then copy the pointers. - */ - op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - ifp->if_broot_bytes); - np = (char *)xfs_bmap_broot_ptr_addr(mp, new_broot, 1, - (int)new_size); - memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t)); - } kfree(ifp->if_broot); ifp->if_broot = new_broot; ifp->if_broot_bytes = (int)new_size; - if (ifp->if_broot) - ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - return; + ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, whichfork)); } -- cgit v1.2.3 From 6c1c55ac3c0512262817a088e805d99aad4c0867 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 20 Nov 2024 16:20:13 -0800 Subject: xfs: refactor the inode fork memory allocation functions Hoist the code that allocates, frees, and reallocates if_broot into a single xfs_iroot_krealloc function. Eventually we're going to push xfs_iroot_realloc into the btree ops structure to handle multiple inode-rooted btrees, but first let's separate out the bits that should stay in xfs_inode_fork.c. Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_inode_fork.c | 116 +++++++++++++++++++++++++++-------------- fs/xfs/libxfs/xfs_inode_fork.h | 5 ++ 2 files changed, 82 insertions(+), 39 deletions(-) (limited to 'fs/xfs/libxfs/xfs_inode_fork.c') diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 7f865479c415..294c3c555683 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -178,7 +178,7 @@ xfs_iformat_btree( struct xfs_mount *mp = ip->i_mount; xfs_bmdr_block_t *dfp; struct xfs_ifork *ifp; - /* REFERENCED */ + struct xfs_btree_block *broot; int nrecs; int size; int level; @@ -211,16 +211,13 @@ xfs_iformat_btree( return -EFSCORRUPTED; } - ifp->if_broot_bytes = size; - ifp->if_broot = kmalloc(size, - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); - ASSERT(ifp->if_broot != NULL); + broot = xfs_broot_alloc(ifp, size); /* * Copy and convert from the on-disk structure * to the in-memory structure. */ xfs_bmdr_to_bmbt(ip, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork), - ifp->if_broot, size); + broot, size); ifp->if_bytes = 0; ifp->if_data = NULL; @@ -362,6 +359,69 @@ xfs_iformat_attr_fork( return error; } +/* + * Allocate the if_broot component of an inode fork so that it is @new_size + * bytes in size, using __GFP_NOLOCKDEP like all the other code that + * initializes a broot during inode load. Returns if_broot. + */ +struct xfs_btree_block * +xfs_broot_alloc( + struct xfs_ifork *ifp, + size_t new_size) +{ + ASSERT(ifp->if_broot == NULL); + + ifp->if_broot = kmalloc(new_size, + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; +} + +/* + * Reallocate the if_broot component of an inode fork so that it is @new_size + * bytes in size. Returns if_broot. + */ +struct xfs_btree_block * +xfs_broot_realloc( + struct xfs_ifork *ifp, + size_t new_size) +{ + /* No size change? No action needed. */ + if (new_size == ifp->if_broot_bytes) + return ifp->if_broot; + + /* New size is zero, free it. */ + if (new_size == 0) { + ifp->if_broot_bytes = 0; + kfree(ifp->if_broot); + ifp->if_broot = NULL; + return NULL; + } + + /* + * Shrinking the iroot means we allocate a new smaller object and copy + * it. We don't trust krealloc not to nop on realloc-down. + */ + if (ifp->if_broot_bytes > 0 && ifp->if_broot_bytes > new_size) { + struct xfs_btree_block *old_broot = ifp->if_broot; + + ifp->if_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + memcpy(ifp->if_broot, old_broot, new_size); + kfree(old_broot); + return ifp->if_broot; + } + + /* + * Growing the iroot means we can krealloc. This may get us the same + * object. + */ + ifp->if_broot = krealloc(ifp->if_broot, new_size, + GFP_KERNEL | __GFP_NOFAIL); + ifp->if_broot_bytes = new_size; + return ifp->if_broot; +} + /* * Reallocate the space for if_broot based on the number of records * being added or deleted as indicated in rec_diff. Move the records @@ -388,7 +448,6 @@ xfs_iroot_realloc( { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); - struct xfs_btree_block *new_broot; char *np; char *op; size_t new_size; @@ -409,9 +468,7 @@ xfs_iroot_realloc( */ if (old_size == 0) { new_size = xfs_bmap_broot_space_calc(mp, rec_diff); - ifp->if_broot = kmalloc(new_size, - GFP_KERNEL | __GFP_NOFAIL); - ifp->if_broot_bytes = (int)new_size; + xfs_broot_realloc(ifp, new_size); return; } @@ -424,13 +481,12 @@ xfs_iroot_realloc( cur_max = xfs_bmbt_maxrecs(mp, old_size, false); new_max = cur_max + rec_diff; new_size = xfs_bmap_broot_space_calc(mp, new_max); - ifp->if_broot = krealloc(ifp->if_broot, new_size, - GFP_KERNEL | __GFP_NOFAIL); + + xfs_broot_realloc(ifp, new_size); op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, old_size); np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, (int)new_size); - ifp->if_broot_bytes = (int)new_size; ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= xfs_inode_fork_size(ip, whichfork)); memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t)); @@ -451,39 +507,21 @@ xfs_iroot_realloc( else new_size = 0; if (new_size == 0) { - ifp->if_broot = NULL; - ifp->if_broot_bytes = 0; + xfs_broot_realloc(ifp, 0); return; } /* - * Shrink the btree root by allocating a smaller object and copying the - * fields from the old object to the new object. krealloc does nothing - * if we realloc downwards. - */ - new_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL); - /* - * First copy over the btree block header. - */ - memcpy(new_broot, ifp->if_broot, xfs_bmbt_block_len(ip->i_mount)); - - /* - * First copy the keys. - */ - op = (char *)xfs_bmbt_key_addr(mp, ifp->if_broot, 1); - np = (char *)xfs_bmbt_key_addr(mp, new_broot, 1); - memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_key_t)); - - /* - * Then copy the pointers. + * Shrink the btree root by moving the bmbt pointers, since they are + * not butted up against the btree block header, then reallocating + * broot. */ op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, old_size); - np = (char *)xfs_bmap_broot_ptr_addr(mp, new_broot, 1, (int)new_size); - memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t)); + np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, + (int)new_size); + memmove(np, op, new_max * (uint)sizeof(xfs_fsblock_t)); - kfree(ifp->if_broot); - ifp->if_broot = new_broot; - ifp->if_broot_bytes = (int)new_size; + xfs_broot_realloc(ifp, new_size); ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= xfs_inode_fork_size(ip, whichfork)); } diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 2373d12fd474..e3c5c9121044 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -170,6 +170,11 @@ void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, void xfs_idestroy_fork(struct xfs_ifork *ifp); void * xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff, int whichfork); +struct xfs_btree_block *xfs_broot_alloc(struct xfs_ifork *ifp, + size_t new_size); +struct xfs_btree_block *xfs_broot_realloc(struct xfs_ifork *ifp, + size_t new_size); + void xfs_iroot_realloc(struct xfs_inode *, int, int); int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, -- cgit v1.2.3 From 6a92924275ecdd768c8105f8975b971300c5ba7d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 20 Nov 2024 16:20:14 -0800 Subject: xfs: make xfs_iroot_realloc take the new numrecs instead of deltas Change the calling signature of xfs_iroot_realloc to take the ifork and the new number of records in the btree block, not a diff against the current number. This will make the callsites easier to understand. Note that this function is misnamed because it is very specific to the single type of inode-rooted btree supported. This will be addressed in a subsequent patch. Return the new btree root to reduce the amount of code clutter. Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_bmap.c | 7 ++-- fs/xfs/libxfs/xfs_btree.c | 25 +++++-------- fs/xfs/libxfs/xfs_inode_fork.c | 83 +++++++++++++++++++----------------------- fs/xfs/libxfs/xfs_inode_fork.h | 3 +- 4 files changed, 51 insertions(+), 67 deletions(-) (limited to 'fs/xfs/libxfs/xfs_inode_fork.c') diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 5255f93bae31..8ab38f07cb78 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -615,7 +615,7 @@ xfs_bmap_btree_to_extents( xfs_trans_binval(tp, cbp); if (cur->bc_levels[0].bp == cbp) cur->bc_levels[0].bp = NULL; - xfs_iroot_realloc(ip, -1, whichfork); + xfs_iroot_realloc(ip, whichfork, 0); ASSERT(ifp->if_broot == NULL); ifp->if_format = XFS_DINODE_FMT_EXTENTS; *logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork); @@ -659,12 +659,11 @@ xfs_bmap_extents_to_btree( * Make space in the inode incore. This needs to be undone if we fail * to expand the root. */ - xfs_iroot_realloc(ip, 1, whichfork); + block = xfs_iroot_realloc(ip, whichfork, 1); /* * Fill in the root. */ - block = ifp->if_broot; xfs_bmbt_init_block(ip, block, NULL, 1, 1); /* * Need a cursor. Can't allocate until bb_level is filled in. @@ -746,7 +745,7 @@ xfs_bmap_extents_to_btree( out_unreserve_dquot: xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); out_root_realloc: - xfs_iroot_realloc(ip, -1, whichfork); + xfs_iroot_realloc(ip, whichfork, 0); ifp->if_format = XFS_DINODE_FMT_EXTENTS; ASSERT(ifp->if_broot == NULL); xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 68ee1c299c25..5714bec26c20 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -3161,9 +3161,7 @@ xfs_btree_new_iroot( xfs_btree_copy_ptrs(cur, pp, &nptr, 1); - xfs_iroot_realloc(cur->bc_ino.ip, - 1 - xfs_btree_get_numrecs(cblock), - cur->bc_ino.whichfork); + xfs_iroot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, 1); xfs_btree_setbuf(cur, level, cbp); @@ -3347,7 +3345,8 @@ xfs_btree_make_block_unfull( if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) { /* A root block that can be made bigger. */ - xfs_iroot_realloc(ip, 1, cur->bc_ino.whichfork); + xfs_iroot_realloc(ip, cur->bc_ino.whichfork, + numrecs + 1); *stat = 1; } else { /* A root block that needs replacing */ @@ -3705,9 +3704,7 @@ STATIC int xfs_btree_kill_iroot( struct xfs_btree_cur *cur) { - int whichfork = cur->bc_ino.whichfork; struct xfs_inode *ip = cur->bc_ino.ip; - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_block *block; struct xfs_btree_block *cblock; union xfs_btree_key *kp; @@ -3716,7 +3713,6 @@ xfs_btree_kill_iroot( union xfs_btree_ptr *cpp; struct xfs_buf *cbp; int level; - int index; int numrecs; int error; #ifdef DEBUG @@ -3762,14 +3758,10 @@ xfs_btree_kill_iroot( ASSERT(xfs_btree_ptr_is_null(cur, &ptr)); #endif - index = numrecs - cur->bc_ops->get_maxrecs(cur, level); - if (index) { - xfs_iroot_realloc(cur->bc_ino.ip, index, - cur->bc_ino.whichfork); - block = ifp->if_broot; - } + block = xfs_iroot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, + numrecs); - be16_add_cpu(&block->bb_numrecs, index); + block->bb_numrecs = be16_to_cpu(numrecs); ASSERT(block->bb_numrecs == cblock->bb_numrecs); kp = xfs_btree_key_addr(cur, 1, block); @@ -3949,10 +3941,11 @@ xfs_btree_delrec( /* * We're at the root level. First, shrink the root block in-memory. * Try to get rid of the next level down. If we can't then there's - * nothing left to do. + * nothing left to do. numrecs was decremented above. */ if (xfs_btree_at_iroot(cur, level)) { - xfs_iroot_realloc(cur->bc_ino.ip, -1, cur->bc_ino.whichfork); + xfs_iroot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, + numrecs); error = xfs_btree_kill_iroot(cur); if (error) diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 294c3c555683..53bfdf422ad8 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -423,12 +423,10 @@ xfs_broot_realloc( } /* - * Reallocate the space for if_broot based on the number of records - * being added or deleted as indicated in rec_diff. Move the records - * and pointers in if_broot to fit the new size. When shrinking this - * will eliminate holes between the records and pointers created by - * the caller. When growing this will create holes to be filled in - * by the caller. + * Reallocate the space for if_broot based on the number of records. Move the + * records and pointers in if_broot to fit the new size. When shrinking this + * will eliminate holes between the records and pointers created by the caller. + * When growing this will create holes to be filled in by the caller. * * The caller must not request to add more records than would fit in * the on-disk inode root. If the if_broot is currently NULL, then @@ -437,40 +435,47 @@ xfs_broot_realloc( * it can go to zero. * * ip -- the inode whose if_broot area is changing - * ext_diff -- the change in the number of records, positive or negative, - * requested for the if_broot array. + * whichfork -- which inode fork to change + * new_numrecs -- the new number of records requested for the if_broot array + * + * Returns the incore btree root block. */ -void +struct xfs_btree_block * xfs_iroot_realloc( struct xfs_inode *ip, - int rec_diff, - int whichfork) + int whichfork, + unsigned int new_numrecs) { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); char *np; char *op; - size_t new_size; - short old_size = ifp->if_broot_bytes; - int cur_max; - int new_max; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; /* - * Handle the degenerate case quietly. + * Block mapping btrees do not support storing zero records; if this + * happens, the fork is being changed to FMT_EXTENTS. Free the broot + * and get out. */ - if (rec_diff == 0) - return; + if (new_numrecs == 0) + return xfs_broot_realloc(ifp, 0); + + new_size = xfs_bmap_broot_space_calc(mp, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; - if (rec_diff > 0) { /* * If there wasn't any memory allocated before, just * allocate it now and get out. */ - if (old_size == 0) { - new_size = xfs_bmap_broot_space_calc(mp, rec_diff); - xfs_broot_realloc(ifp, new_size); - return; - } + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); /* * If there is already an existing if_broot, then we need @@ -478,10 +483,7 @@ xfs_iroot_realloc( * location. The records don't change location because * they are kept butted up against the btree block header. */ - cur_max = xfs_bmbt_maxrecs(mp, old_size, false); - new_max = cur_max + rec_diff; - new_size = xfs_bmap_broot_space_calc(mp, new_max); - + old_numrecs = xfs_bmbt_maxrecs(mp, old_size, false); xfs_broot_realloc(ifp, new_size); op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, old_size); @@ -489,27 +491,15 @@ xfs_iroot_realloc( (int)new_size); ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= xfs_inode_fork_size(ip, whichfork)); - memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t)); - return; + memmove(np, op, old_numrecs * (uint)sizeof(xfs_fsblock_t)); + return ifp->if_broot; } /* - * rec_diff is less than 0. In this case, we are shrinking the - * if_broot buffer. It must already exist. If we go to zero - * records, just get rid of the root and clear the status bit. + * We're reducing, but not totally eliminating, numrecs. In this case, + * we are shrinking the if_broot buffer, so it must already exist. */ - ASSERT(ifp->if_broot != NULL && old_size > 0); - cur_max = xfs_bmbt_maxrecs(mp, old_size, false); - new_max = cur_max + rec_diff; - ASSERT(new_max >= 0); - if (new_max > 0) - new_size = xfs_bmap_broot_space_calc(mp, new_max); - else - new_size = 0; - if (new_size == 0) { - xfs_broot_realloc(ifp, 0); - return; - } + ASSERT(ifp->if_broot != NULL && old_size > 0 && new_size > 0); /* * Shrink the btree root by moving the bmbt pointers, since they are @@ -519,11 +509,12 @@ xfs_iroot_realloc( op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, old_size); np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, (int)new_size); - memmove(np, op, new_max * (uint)sizeof(xfs_fsblock_t)); + memmove(np, op, new_numrecs * (uint)sizeof(xfs_fsblock_t)); xfs_broot_realloc(ifp, new_size); ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= xfs_inode_fork_size(ip, whichfork)); + return ifp->if_broot; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index e3c5c9121044..d05eb0bad864 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -175,7 +175,8 @@ struct xfs_btree_block *xfs_broot_alloc(struct xfs_ifork *ifp, struct xfs_btree_block *xfs_broot_realloc(struct xfs_ifork *ifp, size_t new_size); -void xfs_iroot_realloc(struct xfs_inode *, int, int); +struct xfs_btree_block *xfs_iroot_realloc(struct xfs_inode *ip, int whichfork, + unsigned int new_numrecs); int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, int); -- cgit v1.2.3 From eb9bff22311ca47ef4848bbdcf24dae06ae3f243 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 20 Nov 2024 16:20:15 -0800 Subject: xfs: make xfs_iroot_realloc a bmap btree function Move the inode fork btree root reallocation function part of the btree ops because it's now mostly bmbt-specific code. Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_bmap.c | 6 +-- fs/xfs/libxfs/xfs_bmap_btree.c | 104 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_bmap_btree.h | 3 ++ fs/xfs/libxfs/xfs_btree.c | 11 ++--- fs/xfs/libxfs/xfs_btree.h | 16 +++++++ fs/xfs/libxfs/xfs_inode_fork.c | 96 ------------------------------------- fs/xfs/libxfs/xfs_inode_fork.h | 2 - 7 files changed, 130 insertions(+), 108 deletions(-) (limited to 'fs/xfs/libxfs/xfs_inode_fork.c') diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 8ab38f07cb78..0842577755f7 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -615,7 +615,7 @@ xfs_bmap_btree_to_extents( xfs_trans_binval(tp, cbp); if (cur->bc_levels[0].bp == cbp) cur->bc_levels[0].bp = NULL; - xfs_iroot_realloc(ip, whichfork, 0); + xfs_bmap_broot_realloc(ip, whichfork, 0); ASSERT(ifp->if_broot == NULL); ifp->if_format = XFS_DINODE_FMT_EXTENTS; *logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork); @@ -659,7 +659,7 @@ xfs_bmap_extents_to_btree( * Make space in the inode incore. This needs to be undone if we fail * to expand the root. */ - block = xfs_iroot_realloc(ip, whichfork, 1); + block = xfs_bmap_broot_realloc(ip, whichfork, 1); /* * Fill in the root. @@ -745,7 +745,7 @@ xfs_bmap_extents_to_btree( out_unreserve_dquot: xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); out_root_realloc: - xfs_iroot_realloc(ip, whichfork, 0); + xfs_bmap_broot_realloc(ip, whichfork, 0); ifp->if_format = XFS_DINODE_FMT_EXTENTS; ASSERT(ifp->if_broot == NULL); xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 3464be771f95..22cf2059d54d 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -516,6 +516,109 @@ xfs_bmbt_keys_contiguous( be64_to_cpu(key2->bmbt.br_startoff)); } +/* + * Reallocate the space for if_broot based on the number of records. Move the + * records and pointers in if_broot to fit the new size. When shrinking this + * will eliminate holes between the records and pointers created by the caller. + * When growing this will create holes to be filled in by the caller. + * + * The caller must not request to add more records than would fit in the + * on-disk inode root. If the if_broot is currently NULL, then if we are + * adding records, one will be allocated. The caller must also not request + * that the number of records go below zero, although it can go to zero. + * + * ip -- the inode whose if_broot area is changing + * whichfork -- which inode fork to change + * new_numrecs -- the new number of records requested for the if_broot array + * + * Returns the incore btree root block. + */ +struct xfs_btree_block * +xfs_bmap_broot_realloc( + struct xfs_inode *ip, + int whichfork, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + char *np; + char *op; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + + /* + * Block mapping btrees do not support storing zero records; if this + * happens, the fork is being changed to FMT_EXTENTS. Free the broot + * and get out. + */ + if (new_numrecs == 0) + return xfs_broot_realloc(ifp, 0); + + new_size = xfs_bmap_broot_space_calc(mp, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just + * allocate it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need + * to realloc() it and shift the pointers to their new + * location. The records don't change location because + * they are kept butted up against the btree block header. + */ + old_numrecs = xfs_bmbt_maxrecs(mp, old_size, false); + xfs_broot_realloc(ifp, new_size); + op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, + old_size); + np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, + (int)new_size); + ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, whichfork)); + memmove(np, op, old_numrecs * (uint)sizeof(xfs_fsblock_t)); + return ifp->if_broot; + } + + /* + * We're reducing, but not totally eliminating, numrecs. In this case, + * we are shrinking the if_broot buffer, so it must already exist. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0 && new_size > 0); + + /* + * Shrink the btree root by moving the bmbt pointers, since they are + * not butted up against the btree block header, then reallocating + * broot. + */ + op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, old_size); + np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, + (int)new_size); + memmove(np, op, new_numrecs * (uint)sizeof(xfs_fsblock_t)); + + xfs_broot_realloc(ifp, new_size); + ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, whichfork)); + return ifp->if_broot; +} + +static struct xfs_btree_block * +xfs_bmbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + return xfs_bmap_broot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, + new_numrecs); +} + const struct xfs_btree_ops xfs_bmbt_ops = { .name = "bmap", .type = XFS_BTREE_TYPE_INODE, @@ -543,6 +646,7 @@ const struct xfs_btree_ops xfs_bmbt_ops = { .keys_inorder = xfs_bmbt_keys_inorder, .recs_inorder = xfs_bmbt_recs_inorder, .keys_contiguous = xfs_bmbt_keys_contiguous, + .broot_realloc = xfs_bmbt_broot_realloc, }; /* diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h index 49a3bae3f6ec..b238d559ab03 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.h +++ b/fs/xfs/libxfs/xfs_bmap_btree.h @@ -198,4 +198,7 @@ xfs_bmap_bmdr_space(struct xfs_btree_block *bb) return xfs_bmdr_space_calc(be16_to_cpu(bb->bb_numrecs)); } +struct xfs_btree_block *xfs_bmap_broot_realloc(struct xfs_inode *ip, + int whichfork, unsigned int new_numrecs); + #endif /* __XFS_BMAP_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 5714bec26c20..672746f7217c 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -3161,7 +3161,7 @@ xfs_btree_new_iroot( xfs_btree_copy_ptrs(cur, pp, &nptr, 1); - xfs_iroot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, 1); + cur->bc_ops->broot_realloc(cur, 1); xfs_btree_setbuf(cur, level, cbp); @@ -3345,8 +3345,7 @@ xfs_btree_make_block_unfull( if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) { /* A root block that can be made bigger. */ - xfs_iroot_realloc(ip, cur->bc_ino.whichfork, - numrecs + 1); + cur->bc_ops->broot_realloc(cur, numrecs + 1); *stat = 1; } else { /* A root block that needs replacing */ @@ -3758,8 +3757,7 @@ xfs_btree_kill_iroot( ASSERT(xfs_btree_ptr_is_null(cur, &ptr)); #endif - block = xfs_iroot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, - numrecs); + block = cur->bc_ops->broot_realloc(cur, numrecs); block->bb_numrecs = be16_to_cpu(numrecs); ASSERT(block->bb_numrecs == cblock->bb_numrecs); @@ -3944,8 +3942,7 @@ xfs_btree_delrec( * nothing left to do. numrecs was decremented above. */ if (xfs_btree_at_iroot(cur, level)) { - xfs_iroot_realloc(cur->bc_ino.ip, cur->bc_ino.whichfork, - numrecs); + cur->bc_ops->broot_realloc(cur, numrecs); error = xfs_btree_kill_iroot(cur); if (error) diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index c5bff273cae2..8380ae0a64dd 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -213,6 +213,22 @@ struct xfs_btree_ops { const union xfs_btree_key *key1, const union xfs_btree_key *key2, const union xfs_btree_key *mask); + + /* + * Reallocate the space for if_broot to fit the number of records. + * Move the records and pointers in if_broot to fit the new size. When + * shrinking this will eliminate holes between the records and pointers + * created by the caller. When growing this will create holes to be + * filled in by the caller. + * + * The caller must not request to add more records than would fit in + * the on-disk inode root. If the if_broot is currently NULL, then if + * we are adding records, one will be allocated. The caller must also + * not request that the number of records go below zero, although it + * can go to zero. + */ + struct xfs_btree_block *(*broot_realloc)(struct xfs_btree_cur *cur, + unsigned int new_numrecs); }; /* btree geometry flags */ diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 53bfdf422ad8..60853bac289a 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -422,102 +422,6 @@ xfs_broot_realloc( return ifp->if_broot; } -/* - * Reallocate the space for if_broot based on the number of records. Move the - * records and pointers in if_broot to fit the new size. When shrinking this - * will eliminate holes between the records and pointers created by the caller. - * When growing this will create holes to be filled in by the caller. - * - * The caller must not request to add more records than would fit in - * the on-disk inode root. If the if_broot is currently NULL, then - * if we are adding records, one will be allocated. The caller must also - * not request that the number of records go below zero, although - * it can go to zero. - * - * ip -- the inode whose if_broot area is changing - * whichfork -- which inode fork to change - * new_numrecs -- the new number of records requested for the if_broot array - * - * Returns the incore btree root block. - */ -struct xfs_btree_block * -xfs_iroot_realloc( - struct xfs_inode *ip, - int whichfork, - unsigned int new_numrecs) -{ - struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); - char *np; - char *op; - unsigned int new_size; - unsigned int old_size = ifp->if_broot_bytes; - - /* - * Block mapping btrees do not support storing zero records; if this - * happens, the fork is being changed to FMT_EXTENTS. Free the broot - * and get out. - */ - if (new_numrecs == 0) - return xfs_broot_realloc(ifp, 0); - - new_size = xfs_bmap_broot_space_calc(mp, new_numrecs); - - /* Handle the nop case quietly. */ - if (new_size == old_size) - return ifp->if_broot; - - if (new_size > old_size) { - unsigned int old_numrecs; - - /* - * If there wasn't any memory allocated before, just - * allocate it now and get out. - */ - if (old_size == 0) - return xfs_broot_realloc(ifp, new_size); - - /* - * If there is already an existing if_broot, then we need - * to realloc() it and shift the pointers to their new - * location. The records don't change location because - * they are kept butted up against the btree block header. - */ - old_numrecs = xfs_bmbt_maxrecs(mp, old_size, false); - xfs_broot_realloc(ifp, new_size); - op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - old_size); - np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - (int)new_size); - ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - memmove(np, op, old_numrecs * (uint)sizeof(xfs_fsblock_t)); - return ifp->if_broot; - } - - /* - * We're reducing, but not totally eliminating, numrecs. In this case, - * we are shrinking the if_broot buffer, so it must already exist. - */ - ASSERT(ifp->if_broot != NULL && old_size > 0 && new_size > 0); - - /* - * Shrink the btree root by moving the bmbt pointers, since they are - * not butted up against the btree block header, then reallocating - * broot. - */ - op = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, old_size); - np = (char *)xfs_bmap_broot_ptr_addr(mp, ifp->if_broot, 1, - (int)new_size); - memmove(np, op, new_numrecs * (uint)sizeof(xfs_fsblock_t)); - - xfs_broot_realloc(ifp, new_size); - ASSERT(xfs_bmap_bmdr_space(ifp->if_broot) <= - xfs_inode_fork_size(ip, whichfork)); - return ifp->if_broot; -} - - /* * This is called when the amount of space needed for if_data * is increased or decreased. The change in size is indicated by diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index d05eb0bad864..69ed0919d60b 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -175,8 +175,6 @@ struct xfs_btree_block *xfs_broot_alloc(struct xfs_ifork *ifp, struct xfs_btree_block *xfs_broot_realloc(struct xfs_ifork *ifp, size_t new_size); -struct xfs_btree_block *xfs_iroot_realloc(struct xfs_inode *ip, int whichfork, - unsigned int new_numrecs); int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, int); -- cgit v1.2.3 From 702c90f451622384d6c65897b619f647704b06a9 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 20 Nov 2024 16:20:27 -0800 Subject: xfs: support file data forks containing metadata btrees Create a new fork format type for metadata btrees. This fork type requires that the inode is in the metadata directory tree, and only applies to the data fork. The actual type of the metadata btree itself is determined by the di_metatype field. Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_format.h | 6 ++++-- fs/xfs/libxfs/xfs_inode_buf.c | 23 ++++++++++++++++++++--- fs/xfs/libxfs/xfs_inode_fork.c | 19 +++++++++++++++++++ fs/xfs/scrub/bmap.c | 1 + fs/xfs/scrub/bmap_repair.c | 1 + fs/xfs/scrub/inode.c | 4 ++++ fs/xfs/scrub/inode_repair.c | 36 ++++++++++++++++++++++++++++++++++++ fs/xfs/scrub/rmap_repair.c | 31 +++++++++++++++++++++---------- fs/xfs/xfs_inode.c | 19 ++++++++++++++++++- fs/xfs/xfs_inode_item.c | 2 ++ fs/xfs/xfs_inode_item_recover.c | 40 +++++++++++++++++++++++++++++++++++----- fs/xfs/xfs_trace.h | 1 + 12 files changed, 162 insertions(+), 21 deletions(-) (limited to 'fs/xfs/libxfs/xfs_inode_fork.c') diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 469fc7afa591..41ea4283c43c 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -997,7 +997,8 @@ enum xfs_dinode_fmt { XFS_DINODE_FMT_LOCAL, /* bulk data */ XFS_DINODE_FMT_EXTENTS, /* struct xfs_bmbt_rec */ XFS_DINODE_FMT_BTREE, /* struct xfs_bmdr_block */ - XFS_DINODE_FMT_UUID /* added long ago, but never used */ + XFS_DINODE_FMT_UUID, /* added long ago, but never used */ + XFS_DINODE_FMT_META_BTREE, /* metadata btree */ }; #define XFS_INODE_FORMAT_STR \ @@ -1005,7 +1006,8 @@ enum xfs_dinode_fmt { { XFS_DINODE_FMT_LOCAL, "local" }, \ { XFS_DINODE_FMT_EXTENTS, "extent" }, \ { XFS_DINODE_FMT_BTREE, "btree" }, \ - { XFS_DINODE_FMT_UUID, "uuid" } + { XFS_DINODE_FMT_UUID, "uuid" }, \ + { XFS_DINODE_FMT_META_BTREE, "meta_btree" } /* * Max values for extnum and aextnum. diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 424861fbf1bd..1648d72d6ed9 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -441,6 +441,16 @@ xfs_dinode_verify_fork( if (di_nextents > max_extents) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp)) + return __this_address; + if (!(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA))) + return __this_address; + switch (be16_to_cpu(dip->di_metatype)) { + default: + return __this_address; + } + break; default: return __this_address; } @@ -460,6 +470,10 @@ xfs_dinode_verify_forkoff( if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3)) return __this_address; break; + case XFS_DINODE_FMT_META_BTREE: + if (!xfs_has_metadir(mp) || !xfs_has_parent(mp)) + return __this_address; + fallthrough; case XFS_DINODE_FMT_LOCAL: /* fall through ... */ case XFS_DINODE_FMT_EXTENTS: /* fall through ... */ case XFS_DINODE_FMT_BTREE: @@ -637,9 +651,6 @@ xfs_dinode_verify( if (mode && nextents + naextents > nblocks) return __this_address; - if (nextents + naextents == 0 && nblocks != 0) - return __this_address; - if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents) return __this_address; @@ -743,6 +754,12 @@ xfs_dinode_verify( return fa; } + /* metadata inodes containing btrees always have zero extent count */ + if (XFS_DFORK_FORMAT(dip, XFS_DATA_FORK) != XFS_DINODE_FMT_META_BTREE) { + if (nextents + naextents == 0 && nblocks != 0) + return __this_address; + } + return NULL; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 60853bac289a..1a782339396d 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -267,6 +267,12 @@ xfs_iformat_data_fork( return xfs_iformat_extents(ip, dip, XFS_DATA_FORK); case XFS_DINODE_FMT_BTREE: return xfs_iformat_btree(ip, dip, XFS_DATA_FORK); + case XFS_DINODE_FMT_META_BTREE: + switch (ip->i_metatype) { + default: + break; + } + fallthrough; default: xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, sizeof(*dip), __this_address); @@ -601,6 +607,19 @@ xfs_iflush_fork( } break; + case XFS_DINODE_FMT_META_BTREE: + ASSERT(whichfork == XFS_DATA_FORK); + + if (!(iip->ili_fields & brootflag[whichfork])) + break; + + switch (ip->i_metatype) { + default: + ASSERT(0); + break; + } + break; + default: ASSERT(0); break; diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 7e00312225ed..0d7ad692822d 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -983,6 +983,7 @@ xchk_bmap( case XFS_DINODE_FMT_UUID: case XFS_DINODE_FMT_DEV: case XFS_DINODE_FMT_LOCAL: + case XFS_DINODE_FMT_META_BTREE: /* No mappings to check. */ if (whichfork == XFS_COW_FORK) xchk_fblock_set_corrupt(sc, whichfork, 0); diff --git a/fs/xfs/scrub/bmap_repair.c b/fs/xfs/scrub/bmap_repair.c index 7c4955482641..141d36f1da9a 100644 --- a/fs/xfs/scrub/bmap_repair.c +++ b/fs/xfs/scrub/bmap_repair.c @@ -731,6 +731,7 @@ xrep_bmap_check_inputs( case XFS_DINODE_FMT_DEV: case XFS_DINODE_FMT_LOCAL: case XFS_DINODE_FMT_UUID: + case XFS_DINODE_FMT_META_BTREE: return -ECANCELED; case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 25ee66e7649d..2e911f38deae 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -502,6 +502,10 @@ xchk_dinode( if (!S_ISREG(mode) && !S_ISDIR(mode)) xchk_ino_set_corrupt(sc, ino); break; + case XFS_DINODE_FMT_META_BTREE: + if (!S_ISREG(mode)) + xchk_ino_set_corrupt(sc, ino); + break; case XFS_DINODE_FMT_UUID: default: xchk_ino_set_corrupt(sc, ino); diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 5a58ddd27bd2..7faa27472b91 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -888,6 +888,25 @@ xrep_dinode_bad_bmbt_fork( return false; } +/* Check a metadata-btree fork. */ +STATIC bool +xrep_dinode_bad_metabt_fork( + struct xfs_scrub *sc, + struct xfs_dinode *dip, + unsigned int dfork_size, + int whichfork) +{ + if (whichfork != XFS_DATA_FORK) + return true; + + switch (be16_to_cpu(dip->di_metatype)) { + default: + return true; + } + + return false; +} + /* * Check the data fork for things that will fail the ifork verifiers or the * ifork formatters. @@ -968,6 +987,11 @@ xrep_dinode_check_dfork( XFS_DATA_FORK)) return true; break; + case XFS_DINODE_FMT_META_BTREE: + if (xrep_dinode_bad_metabt_fork(sc, dip, dfork_size, + XFS_DATA_FORK)) + return true; + break; default: return true; } @@ -1088,6 +1112,11 @@ xrep_dinode_check_afork( XFS_ATTR_FORK)) return true; break; + case XFS_DINODE_FMT_META_BTREE: + if (xrep_dinode_bad_metabt_fork(sc, dip, afork_size, + XFS_ATTR_FORK)) + return true; + break; default: return true; } @@ -1241,6 +1270,13 @@ xrep_dinode_ensure_forkoff( bmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK); dfork_min = xfs_bmap_broot_space(sc->mp, bmdr); break; + case XFS_DINODE_FMT_META_BTREE: + switch (be16_to_cpu(dip->di_metatype)) { + default: + dfork_min = 0; + break; + } + break; default: dfork_min = 0; break; diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c index a0a227d183d2..2a0b9e3d0fba 100644 --- a/fs/xfs/scrub/rmap_repair.c +++ b/fs/xfs/scrub/rmap_repair.c @@ -499,6 +499,14 @@ xrep_rmap_scan_iext( return xrep_rmap_stash_accumulated(rf); } +static int +xrep_rmap_scan_meta_btree( + struct xrep_rmap_ifork *rf, + struct xfs_inode *ip) +{ + return -EFSCORRUPTED; /* XXX placeholder */ +} + /* Find all the extents from a given AG in an inode fork. */ STATIC int xrep_rmap_scan_ifork( @@ -512,14 +520,14 @@ xrep_rmap_scan_ifork( .whichfork = whichfork, }; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); + bool mappings_done; int error = 0; if (!ifp) return 0; - if (ifp->if_format == XFS_DINODE_FMT_BTREE) { - bool mappings_done; - + switch (ifp->if_format) { + case XFS_DINODE_FMT_BTREE: /* * Scan the bmap btree for data device mappings. This includes * the btree blocks themselves, even if this is a realtime @@ -528,15 +536,18 @@ xrep_rmap_scan_ifork( error = xrep_rmap_scan_bmbt(&rf, ip, &mappings_done); if (error || mappings_done) return error; - } else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) { - return 0; + fallthrough; + case XFS_DINODE_FMT_EXTENTS: + /* Scan incore extent cache if this isn't a realtime file. */ + if (xfs_ifork_is_realtime(ip, whichfork)) + return 0; + + return xrep_rmap_scan_iext(&rf, ifp); + case XFS_DINODE_FMT_META_BTREE: + return xrep_rmap_scan_meta_btree(&rf, ip); } - /* Scan incore extent cache if this isn't a realtime file. */ - if (xfs_ifork_is_realtime(ip, whichfork)) - return 0; - - return xrep_rmap_scan_iext(&rf, ifp); + return 0; } /* diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c8ad2606f928..c95fe1b1de4e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2382,7 +2382,16 @@ xfs_iflush( __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip); goto flush_out; } - if (S_ISREG(VFS_I(ip)->i_mode)) { + if (ip->i_df.if_format == XFS_DINODE_FMT_META_BTREE) { + if (!S_ISREG(VFS_I(ip)->i_mode) || + !(ip->i_diflags2 & XFS_DIFLAG2_METADATA)) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: Bad %s meta btree inode %Lu, ptr "PTR_FMT, + __func__, xfs_metafile_type_str(ip->i_metatype), + ip->i_ino, ip); + goto flush_out; + } + } else if (S_ISREG(VFS_I(ip)->i_mode)) { if (XFS_TEST_ERROR( ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && ip->i_df.if_format != XFS_DINODE_FMT_BTREE, @@ -2422,6 +2431,14 @@ xfs_iflush( goto flush_out; } + if (xfs_inode_has_attr_fork(ip) && + ip->i_af.if_format == XFS_DINODE_FMT_META_BTREE) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: meta btree in inode %Lu attr fork, ptr "PTR_FMT, + __func__, ip->i_ino, ip); + goto flush_out; + } + /* * Inode item log recovery for v2 inodes are dependent on the flushiter * count for correct sequencing. We bump the flush iteration count so diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 912f0b1bc3cb..a174f64b8bb2 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -242,6 +242,7 @@ xfs_inode_item_data_fork_size( } break; case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: if ((iip->ili_fields & XFS_ILOG_DBROOT) && ip->i_df.if_broot_bytes > 0) { *nbytes += ip->i_df.if_broot_bytes; @@ -362,6 +363,7 @@ xfs_inode_item_format_data_fork( } break; case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: iip->ili_fields &= ~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV); diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index e70d2611456b..6e9b3bfc718c 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -266,6 +266,35 @@ xlog_dinode_verify_extent_counts( return 0; } +static inline int +xlog_recover_inode_dbroot( + struct xfs_mount *mp, + void *src, + unsigned int len, + struct xfs_dinode *dip) +{ + void *dfork = XFS_DFORK_DPTR(dip); + unsigned int dsize = XFS_DFORK_DSIZE(dip, mp); + + switch (dip->di_format) { + case XFS_DINODE_FMT_BTREE: + xfs_bmbt_to_bmdr(mp, src, len, dfork, dsize); + break; + case XFS_DINODE_FMT_META_BTREE: + switch (be16_to_cpu(dip->di_metatype)) { + default: + ASSERT(0); + return -EFSCORRUPTED; + } + break; + default: + ASSERT(0); + return -EFSCORRUPTED; + } + + return 0; +} + STATIC int xlog_recover_inode_commit_pass2( struct xlog *log, @@ -393,8 +422,9 @@ xlog_recover_inode_commit_pass2( if (unlikely(S_ISREG(ldip->di_mode))) { - if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) && - (ldip->di_format != XFS_DINODE_FMT_BTREE)) { + if (ldip->di_format != XFS_DINODE_FMT_EXTENTS && + ldip->di_format != XFS_DINODE_FMT_BTREE && + ldip->di_format != XFS_DINODE_FMT_META_BTREE) { XFS_CORRUPTION_ERROR( "Bad log dinode data fork format for regular file", XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip)); @@ -475,9 +505,9 @@ xlog_recover_inode_commit_pass2( break; case XFS_ILOG_DBROOT: - xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src, len, - (struct xfs_bmdr_block *)XFS_DFORK_DPTR(dip), - XFS_DFORK_DSIZE(dip, mp)); + error = xlog_recover_inode_dbroot(mp, src, len, dip); + if (error) + goto out_release; break; default: diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 8b7bb1f5ae3c..a098935163b7 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -2299,6 +2299,7 @@ TRACE_DEFINE_ENUM(XFS_DINODE_FMT_LOCAL); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_EXTENTS); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_BTREE); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_UUID); +TRACE_DEFINE_ENUM(XFS_DINODE_FMT_META_BTREE); DECLARE_EVENT_CLASS(xfs_swap_extent_class, TP_PROTO(struct xfs_inode *ip, int which), -- cgit v1.2.3 From 6b08901a6e8fcda555f3ad39abd73bb0dd37f231 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 20 Nov 2024 16:20:27 -0800 Subject: xfs: add realtime reverse map inode to metadata directory Add a metadir path to select the realtime rmap btree inode and load it at mount time. The rtrmapbt inode will have a unique extent format code, which means that we also have to update the inode validation and flush routines to look for it. Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_format.h | 4 +++- fs/xfs/libxfs/xfs_inode_buf.c | 9 +++++++++ fs/xfs/libxfs/xfs_inode_fork.c | 6 ++++++ fs/xfs/libxfs/xfs_rtgroup.c | 20 ++++++++++++++++++-- fs/xfs/libxfs/xfs_rtgroup.h | 8 ++++++++ fs/xfs/libxfs/xfs_rtrmap_btree.c | 6 +++--- 6 files changed, 47 insertions(+), 6 deletions(-) (limited to 'fs/xfs/libxfs/xfs_inode_fork.c') diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 41ea4283c43c..f32c9fda5a19 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -857,6 +857,7 @@ enum xfs_metafile_type { XFS_METAFILE_PRJQUOTA, /* project quota */ XFS_METAFILE_RTBITMAP, /* rt bitmap */ XFS_METAFILE_RTSUMMARY, /* rt summary */ + XFS_METAFILE_RTRMAP, /* rt rmap */ XFS_METAFILE_MAX } __packed; @@ -868,7 +869,8 @@ enum xfs_metafile_type { { XFS_METAFILE_GRPQUOTA, "grpquota" }, \ { XFS_METAFILE_PRJQUOTA, "prjquota" }, \ { XFS_METAFILE_RTBITMAP, "rtbitmap" }, \ - { XFS_METAFILE_RTSUMMARY, "rtsummary" } + { XFS_METAFILE_RTSUMMARY, "rtsummary" }, \ + { XFS_METAFILE_RTRMAP, "rtrmap" } /* * On-disk inode structure. diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 1648d72d6ed9..17cb91b89fca 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -447,6 +447,15 @@ xfs_dinode_verify_fork( if (!(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA))) return __this_address; switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use + * the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(mp)) + return __this_address; + break; default: return __this_address; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 1a782339396d..7c2b071a5838 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -269,6 +269,9 @@ xfs_iformat_data_fork( return xfs_iformat_btree(ip, dip, XFS_DATA_FORK); case XFS_DINODE_FMT_META_BTREE: switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + ASSERT(0); /* to be implemented later */ + return -EFSCORRUPTED; default: break; } @@ -614,6 +617,9 @@ xfs_iflush_fork( break; switch (ip->i_metatype) { + case XFS_METAFILE_RTRMAP: + ASSERT(0); /* to be implemented later */ + break; default: ASSERT(0); break; diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index 9e5fdc0dc55c..1b56c13b2827 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -315,6 +315,8 @@ struct xfs_rtginode_ops { unsigned int sick; /* rtgroup sickness flag */ + unsigned int fmt_mask; /* all valid data fork formats */ + /* Does the fs have this feature? */ bool (*enabled)(struct xfs_mount *mp); @@ -330,14 +332,29 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = { .name = "bitmap", .metafile_type = XFS_METAFILE_RTBITMAP, .sick = XFS_SICK_RG_BITMAP, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), .create = xfs_rtbitmap_create, }, [XFS_RTGI_SUMMARY] = { .name = "summary", .metafile_type = XFS_METAFILE_RTSUMMARY, .sick = XFS_SICK_RG_SUMMARY, + .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | + (1U << XFS_DINODE_FMT_BTREE), .create = xfs_rtsummary_create, }, + [XFS_RTGI_RMAP] = { + .name = "rmap", + .metafile_type = XFS_METAFILE_RTRMAP, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* + * growfs must create the rtrmap inodes before adding a + * realtime volume to the filesystem, so we cannot use the + * rtrmapbt predicate here. + */ + .enabled = xfs_has_rmapbt, + }, }; /* Return the shortname of this rtgroup inode. */ @@ -434,8 +451,7 @@ xfs_rtginode_load( return error; } - if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && - ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) { + if (XFS_IS_CORRUPT(mp, !((1U << ip->i_df.if_format) & ops->fmt_mask))) { xfs_irele(ip); xfs_rtginode_mark_sick(rtg, type); return -EFSCORRUPTED; diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index dc3ce660a013..5b61291d2669 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -14,6 +14,7 @@ struct xfs_trans; enum xfs_rtg_inodes { XFS_RTGI_BITMAP, /* allocation bitmap */ XFS_RTGI_SUMMARY, /* allocation summary */ + XFS_RTGI_RMAP, /* rmap btree inode */ XFS_RTGI_MAX, }; @@ -74,6 +75,11 @@ static inline struct xfs_inode *rtg_summary(const struct xfs_rtgroup *rtg) return rtg->rtg_inodes[XFS_RTGI_SUMMARY]; } +static inline struct xfs_inode *rtg_rmap(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_RMAP]; +} + /* Passive rtgroup references */ static inline struct xfs_rtgroup * xfs_rtgroup_get( @@ -284,6 +290,8 @@ int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type, bool init); void xfs_rtginode_irele(struct xfs_inode **ipp); +void xfs_rtginode_irele(struct xfs_inode **ipp); + static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno, enum xfs_rtg_inodes type) { diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c index 99d828bb5fe7..22aabf326b2c 100644 --- a/fs/xfs/libxfs/xfs_rtrmap_btree.c +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -18,6 +18,7 @@ #include "xfs_alloc.h" #include "xfs_btree.h" #include "xfs_btree_staging.h" +#include "xfs_metafile.h" #include "xfs_rmap.h" #include "xfs_rtrmap_btree.h" #include "xfs_trace.h" @@ -405,12 +406,10 @@ xfs_rtrmapbt_init_cursor( struct xfs_trans *tp, struct xfs_rtgroup *rtg) { - struct xfs_inode *ip = NULL; + struct xfs_inode *ip = rtg_rmap(rtg); struct xfs_mount *mp = rtg_mount(rtg); struct xfs_btree_cur *cur; - return NULL; /* XXX */ - xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_ops, @@ -439,6 +438,7 @@ xfs_rtrmapbt_commit_staged_btree( int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); /* * Free any resources hanging off the real fork, then shallow-copy the -- cgit v1.2.3 From f33659e8a114e2c17108227d30a2bdf398e39bdb Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 20 Nov 2024 16:20:29 -0800 Subject: xfs: wire up a new metafile type for the realtime rmap Plumb in the pieces we need to embed the root of the realtime rmap btree in an inode's data fork, complete with new metafile type and on-disk interpretation functions. Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_format.h | 8 ++ fs/xfs/libxfs/xfs_inode_fork.c | 6 +- fs/xfs/libxfs/xfs_ondisk.h | 1 + fs/xfs/libxfs/xfs_rtrmap_btree.c | 251 +++++++++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_rtrmap_btree.h | 112 +++++++++++++++++ fs/xfs/xfs_inode_item_recover.c | 4 + 6 files changed, 379 insertions(+), 3 deletions(-) (limited to 'fs/xfs/libxfs/xfs_inode_fork.c') diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index f32c9fda5a19..fba4e59aded4 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -1736,6 +1736,14 @@ typedef __be32 xfs_rmap_ptr_t; */ #define XFS_RTRMAP_CRC_MAGIC 0x4d415052 /* 'MAPR' */ +/* + * rtrmap root header, on-disk form only. + */ +struct xfs_rtrmap_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + /* inode-based btree pointer type */ typedef __be64 xfs_rtrmap_ptr_t; diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 7c2b071a5838..d9b3c182cb40 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -27,6 +27,7 @@ #include "xfs_errortag.h" #include "xfs_health.h" #include "xfs_symlink_remote.h" +#include "xfs_rtrmap_btree.h" struct kmem_cache *xfs_ifork_cache; @@ -270,8 +271,7 @@ xfs_iformat_data_fork( case XFS_DINODE_FMT_META_BTREE: switch (ip->i_metatype) { case XFS_METAFILE_RTRMAP: - ASSERT(0); /* to be implemented later */ - return -EFSCORRUPTED; + return xfs_iformat_rtrmap(ip, dip); default: break; } @@ -618,7 +618,7 @@ xfs_iflush_fork( switch (ip->i_metatype) { case XFS_METAFILE_RTRMAP: - ASSERT(0); /* to be implemented later */ + xfs_iflush_rtrmap(ip, dip); break; default: ASSERT(0); diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h index 2c50877a1a2f..07e2f5fb3a94 100644 --- a/fs/xfs/libxfs/xfs_ondisk.h +++ b/fs/xfs/libxfs/xfs_ondisk.h @@ -84,6 +84,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(union xfs_suminfo_raw, 4); XFS_CHECK_STRUCT_SIZE(struct xfs_rtbuf_blkinfo, 48); XFS_CHECK_STRUCT_SIZE(xfs_rtrmap_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrmap_root, 4); /* * m68k has problems with struct xfs_attr_leaf_name_remote, but we pad diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c index 066deadcaac9..af0df0c7e61e 100644 --- a/fs/xfs/libxfs/xfs_rtrmap_btree.c +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -77,6 +77,39 @@ xfs_rtrmapbt_get_maxrecs( return cur->bc_mp->m_rtrmap_mxr[level != 0]; } +/* Calculate number of records in the ondisk realtime rmap btree inode root. */ +unsigned int +xfs_rtrmapbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrmap_root); + + if (leaf) + return blocklen / sizeof(struct xfs_rmap_rec); + return blocklen / (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrmapbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork + * so that we can resize the in-memory buffer to match it. After a + * resize to the maximum size this function returns the same value + * as xfs_rtrmapbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrmapbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrmap_mxr[level != 0]; + return xfs_rtrmapbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + /* * Convert the ondisk record's offset field into the ondisk key's offset field. * Fork and bmbt are significant parts of the rmap record key, but written @@ -369,6 +402,87 @@ xfs_rtrmapbt_keys_contiguous( be32_to_cpu(key2->rmap.rm_startblock)); } +static inline void +xfs_rtrmapbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrmap_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrmapbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrmap_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrmapbt_maxrecs(mp, old_size, level == 0); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, broot, old_size, new_size, + old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrmapbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, + new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrmap_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + const struct xfs_btree_ops xfs_rtrmapbt_ops = { .name = "rtrmap", .type = XFS_BTREE_TYPE_INODE, @@ -388,6 +502,7 @@ const struct xfs_btree_ops xfs_rtrmapbt_ops = { .free_block = xfs_btree_free_metafile_block, .get_minrecs = xfs_rtrmapbt_get_minrecs, .get_maxrecs = xfs_rtrmapbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrmapbt_get_dmaxrecs, .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, @@ -398,6 +513,7 @@ const struct xfs_btree_ops xfs_rtrmapbt_ops = { .keys_inorder = xfs_rtrmapbt_keys_inorder, .recs_inorder = xfs_rtrmapbt_recs_inorder, .keys_contiguous = xfs_rtrmapbt_keys_contiguous, + .broot_realloc = xfs_rtrmapbt_broot_realloc, }; /* Allocate a new rt rmap btree cursor. */ @@ -581,3 +697,138 @@ xfs_rtrmapbt_calc_reserves( return max_t(xfs_filblks_t, blocks / 100, xfs_rtrmapbt_max_size(mp, blocks)); } + +/* Convert on-disk form of btree root to in-memory form. */ +STATIC void +xfs_rtrmapbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int rblocklen = xfs_rtrmap_broot_space(mp, dblock); + unsigned int numrecs; + unsigned int maxrecs; + + xfs_btree_init_block(mp, rblock, &xfs_rtrmapbt_ops, 0, 0, ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + numrecs = be16_to_cpu(dblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_droot_key_addr(dblock, 1); + tkp = xfs_rtrmap_key_addr(rblock, 1); + fpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_droot_rec_addr(dblock, 1); + trp = xfs_rtrmap_rec_addr(rblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reverse mapping btree root in from disk. */ +int +xfs_iformat_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrmap inodes before adding a realtime volume + * to the filesystem, so we cannot use the rtrmapbt predicate here. + */ + if (!xfs_has_rmapbt(ip->i_mount)) + return -EFSCORRUPTED; + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrmap_maxlevels || + xfs_rtrmap_droot_space_calc(level, numrecs) > dsize) + return -EFSCORRUPTED; + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrmap_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrmapbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* Convert in-memory form of btree root to on-disk form. */ +void +xfs_rtrmapbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + unsigned int rblocklen, + struct xfs_rtrmap_root *dblock, + unsigned int dblocklen) +{ + struct xfs_rmap_key *fkp; + __be64 *fpp; + struct xfs_rmap_key *tkp; + __be64 *tpp; + struct xfs_rmap_rec *frp; + struct xfs_rmap_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTRMAP_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + numrecs = be16_to_cpu(rblock->bb_numrecs); + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrmap_key_addr(rblock, 1); + tkp = xfs_rtrmap_droot_key_addr(dblock, 1); + fpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrmap_rec_addr(rblock, 1); + trp = xfs_rtrmap_droot_rec_addr(dblock, 1); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reverse mapping btree root out to disk. */ +void +xfs_iflush_rtrmap( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrmap_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrmapbt_to_disk(ip->i_mount, ifp->if_broot, ifp->if_broot_bytes, + dfp, XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.h b/fs/xfs/libxfs/xfs_rtrmap_btree.h index eaa2942297e2..e97695066920 100644 --- a/fs/xfs/libxfs/xfs_rtrmap_btree.h +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.h @@ -25,6 +25,7 @@ void xfs_rtrmapbt_commit_staged_btree(struct xfs_btree_cur *cur, unsigned int xfs_rtrmapbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, bool leaf); void xfs_rtrmapbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrmapbt_droot_maxrecs(unsigned int blocklen, bool leaf); /* * Addresses of records, keys, and pointers within an incore rtrmapbt block. @@ -81,4 +82,115 @@ void xfs_rtrmapbt_destroy_cur_cache(void); xfs_filblks_t xfs_rtrmapbt_calc_reserves(struct xfs_mount *mp); +/* Addresses of key, pointers, and records within an ondisk rtrmapbt block. */ + +static inline struct xfs_rmap_rec * +xfs_rtrmap_droot_rec_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_rmap_rec)); +} + +static inline struct xfs_rmap_key * +xfs_rtrmap_droot_key_addr( + struct xfs_rtrmap_root *block, + unsigned int index) +{ + return (struct xfs_rmap_key *) + ((char *)(block + 1) + + (index - 1) * 2 * sizeof(struct xfs_rmap_key)); +} + +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_droot_ptr_addr( + struct xfs_rtrmap_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrmap_ptr_t *) + ((char *)(block + 1) + + maxrecs * 2 * sizeof(struct xfs_rmap_key) + + (index - 1) * sizeof(xfs_rtrmap_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrmap_ptr_t * +xfs_rtrmap_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrmap_ptr_addr(bb, index, + xfs_rtrmapbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrmap_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTRMAP_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrmap_broot_space(struct xfs_mount *mp, struct xfs_rtrmap_root *bb) +{ + return xfs_rtrmap_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrmap_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrmap_root); + + if (level > 0) + return sz + nrecs * (2 * sizeof(struct xfs_rmap_key) + + sizeof(xfs_rtrmap_ptr_t)); + return sz + nrecs * sizeof(struct xfs_rmap_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrmap_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrmap_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrmapbt_to_disk(struct xfs_mount *mp, struct xfs_btree_block *rblock, + unsigned int rblocklen, struct xfs_rtrmap_root *dblock, + unsigned int dblocklen); +void xfs_iflush_rtrmap(struct xfs_inode *ip, struct xfs_dinode *dip); + #endif /* __XFS_RTRMAP_BTREE_H__ */ diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index 6e9b3bfc718c..5de1d3563b76 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -22,6 +22,7 @@ #include "xfs_log_recover.h" #include "xfs_icache.h" #include "xfs_bmap_btree.h" +#include "xfs_rtrmap_btree.h" STATIC void xlog_recover_inode_ra_pass2( @@ -282,6 +283,9 @@ xlog_recover_inode_dbroot( break; case XFS_DINODE_FMT_META_BTREE: switch (be16_to_cpu(dip->di_metatype)) { + case XFS_METAFILE_RTRMAP: + xfs_rtrmapbt_to_disk(mp, src, len, dfork, dsize); + return 0; default: ASSERT(0); return -EFSCORRUPTED; -- cgit v1.2.3 From eaed472c40527e526217aff3737816b44b08b363 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 20 Nov 2024 16:20:52 -0800 Subject: xfs: add realtime refcount btree inode to metadata directory Add a metadir path to select the realtime refcount btree inode and load it at mount time. The rtrefcountbt inode will have a unique extent format code, which means that we also have to update the inode validation and flush routines to look for it. Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_format.h | 4 +++- fs/xfs/libxfs/xfs_inode_buf.c | 5 +++++ fs/xfs/libxfs/xfs_inode_fork.c | 6 ++++++ fs/xfs/libxfs/xfs_rtgroup.c | 7 +++++++ fs/xfs/libxfs/xfs_rtgroup.h | 6 ++++++ fs/xfs/libxfs/xfs_rtrefcount_btree.c | 6 +++--- 6 files changed, 30 insertions(+), 4 deletions(-) (limited to 'fs/xfs/libxfs/xfs_inode_fork.c') diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 17f7c0d1aaa4..b6828f92c131 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -858,6 +858,7 @@ enum xfs_metafile_type { XFS_METAFILE_RTBITMAP, /* rt bitmap */ XFS_METAFILE_RTSUMMARY, /* rt summary */ XFS_METAFILE_RTRMAP, /* rt rmap */ + XFS_METAFILE_RTREFCOUNT, /* rt refcount */ XFS_METAFILE_MAX } __packed; @@ -870,7 +871,8 @@ enum xfs_metafile_type { { XFS_METAFILE_PRJQUOTA, "prjquota" }, \ { XFS_METAFILE_RTBITMAP, "rtbitmap" }, \ { XFS_METAFILE_RTSUMMARY, "rtsummary" }, \ - { XFS_METAFILE_RTRMAP, "rtrmap" } + { XFS_METAFILE_RTRMAP, "rtrmap" }, \ + { XFS_METAFILE_RTREFCOUNT, "rtrefcount" } /* * On-disk inode structure. diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 17cb91b89fca..65eec8f60376 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -456,6 +456,11 @@ xfs_dinode_verify_fork( if (!xfs_has_rmapbt(mp)) return __this_address; break; + case XFS_METAFILE_RTREFCOUNT: + /* same comment about growfs and rmap inodes applies */ + if (!xfs_has_reflink(mp)) + return __this_address; + break; default: return __this_address; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index d9b3c182cb40..0c4bc12401a1 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -272,6 +272,9 @@ xfs_iformat_data_fork( switch (ip->i_metatype) { case XFS_METAFILE_RTRMAP: return xfs_iformat_rtrmap(ip, dip); + case XFS_METAFILE_RTREFCOUNT: + ASSERT(0); /* to be implemented later */ + return -EFSCORRUPTED; default: break; } @@ -620,6 +623,9 @@ xfs_iflush_fork( case XFS_METAFILE_RTRMAP: xfs_iflush_rtrmap(ip, dip); break; + case XFS_METAFILE_RTREFCOUNT: + ASSERT(0); /* to be implemented later */ + break; default: ASSERT(0); break; diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index b7ed2d27d545..6aebe9f48490 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -367,6 +367,13 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = { .enabled = xfs_has_rmapbt, .create = xfs_rtrmapbt_create, }, + [XFS_RTGI_REFCOUNT] = { + .name = "refcount", + .metafile_type = XFS_METAFILE_RTREFCOUNT, + .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, + /* same comment about growfs and rmap inodes applies here */ + .enabled = xfs_has_reflink, + }, }; /* Return the shortname of this rtgroup inode. */ diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 733da7417c9c..385ea8e2f28b 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -15,6 +15,7 @@ enum xfs_rtg_inodes { XFS_RTGI_BITMAP, /* allocation bitmap */ XFS_RTGI_SUMMARY, /* allocation summary */ XFS_RTGI_RMAP, /* rmap btree inode */ + XFS_RTGI_REFCOUNT, /* refcount btree inode */ XFS_RTGI_MAX, }; @@ -80,6 +81,11 @@ static inline struct xfs_inode *rtg_rmap(const struct xfs_rtgroup *rtg) return rtg->rtg_inodes[XFS_RTGI_RMAP]; } +static inline struct xfs_inode *rtg_refcount(const struct xfs_rtgroup *rtg) +{ + return rtg->rtg_inodes[XFS_RTGI_REFCOUNT]; +} + /* Passive rtgroup references */ static inline struct xfs_rtgroup * xfs_rtgroup_get( diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c index e30af9415816..ebbeab112d14 100644 --- a/fs/xfs/libxfs/xfs_rtrefcount_btree.c +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c @@ -26,6 +26,7 @@ #include "xfs_extent_busy.h" #include "xfs_rtgroup.h" #include "xfs_rtbitmap.h" +#include "xfs_metafile.h" static struct kmem_cache *xfs_rtrefcountbt_cur_cache; @@ -281,12 +282,10 @@ xfs_rtrefcountbt_init_cursor( struct xfs_trans *tp, struct xfs_rtgroup *rtg) { - struct xfs_inode *ip = NULL; + struct xfs_inode *ip = rtg_refcount(rtg); struct xfs_mount *mp = rtg_mount(rtg); struct xfs_btree_cur *cur; - return NULL; /* XXX */ - xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrefcountbt_ops, @@ -316,6 +315,7 @@ xfs_rtrefcountbt_commit_staged_btree( int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; ASSERT(cur->bc_flags & XFS_BTREE_STAGING); + ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); /* * Free any resources hanging off the real fork, then shallow-copy the -- cgit v1.2.3 From f0415af60f482a2192065be8b334b409495ca8a3 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 20 Nov 2024 16:20:54 -0800 Subject: xfs: wire up a new metafile type for the realtime refcount Plumb in the pieces we need to embed the root of the realtime refcount btree in an inode's data fork, complete with metafile type and on-disk interpretation functions. Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_format.h | 8 ++ fs/xfs/libxfs/xfs_inode_fork.c | 6 +- fs/xfs/libxfs/xfs_ondisk.h | 1 + fs/xfs/libxfs/xfs_rtrefcount_btree.c | 264 +++++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_rtrefcount_btree.h | 112 +++++++++++++++ fs/xfs/xfs_inode_item_recover.c | 4 + 6 files changed, 392 insertions(+), 3 deletions(-) (limited to 'fs/xfs/libxfs/xfs_inode_fork.c') diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index b6828f92c131..b1007fb661ba 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -1805,6 +1805,14 @@ typedef __be32 xfs_refcount_ptr_t; */ #define XFS_RTREFC_CRC_MAGIC 0x52434e54 /* 'RCNT' */ +/* + * rt refcount root header, on-disk form only. + */ +struct xfs_rtrefcount_root { + __be16 bb_level; /* 0 is a leaf */ + __be16 bb_numrecs; /* current # of data records */ +}; + /* inode-rooted btree pointer type */ typedef __be64 xfs_rtrefcount_ptr_t; diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 0c4bc12401a1..4f99b90add55 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -28,6 +28,7 @@ #include "xfs_health.h" #include "xfs_symlink_remote.h" #include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" struct kmem_cache *xfs_ifork_cache; @@ -273,8 +274,7 @@ xfs_iformat_data_fork( case XFS_METAFILE_RTRMAP: return xfs_iformat_rtrmap(ip, dip); case XFS_METAFILE_RTREFCOUNT: - ASSERT(0); /* to be implemented later */ - return -EFSCORRUPTED; + return xfs_iformat_rtrefcount(ip, dip); default: break; } @@ -624,7 +624,7 @@ xfs_iflush_fork( xfs_iflush_rtrmap(ip, dip); break; case XFS_METAFILE_RTREFCOUNT: - ASSERT(0); /* to be implemented later */ + xfs_iflush_rtrefcount(ip, dip); break; default: ASSERT(0); diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h index efb035050c00..a85ecddaa48e 100644 --- a/fs/xfs/libxfs/xfs_ondisk.h +++ b/fs/xfs/libxfs/xfs_ondisk.h @@ -86,6 +86,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(xfs_rtrmap_ptr_t, 8); XFS_CHECK_STRUCT_SIZE(struct xfs_rtrmap_root, 4); XFS_CHECK_STRUCT_SIZE(xfs_rtrefcount_ptr_t, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtrefcount_root, 4); /* * m68k has problems with struct xfs_attr_leaf_name_remote, but we pad diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c index ff72ed09e75f..6a5bc7ea42fb 100644 --- a/fs/xfs/libxfs/xfs_rtrefcount_btree.c +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c @@ -77,6 +77,41 @@ xfs_rtrefcountbt_get_maxrecs( return cur->bc_mp->m_rtrefc_mxr[level != 0]; } +/* + * Calculate number of records in a realtime refcount btree inode root. + */ +unsigned int +xfs_rtrefcountbt_droot_maxrecs( + unsigned int blocklen, + bool leaf) +{ + blocklen -= sizeof(struct xfs_rtrefcount_root); + + if (leaf) + return blocklen / sizeof(struct xfs_refcount_rec); + return blocklen / (2 * sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Get the maximum records we could store in the on-disk format. + * + * For non-root nodes this is equivalent to xfs_rtrefcountbt_get_maxrecs, but + * for the root node this checks the available space in the dinode fork so that + * we can resize the in-memory buffer to match it. After a resize to the + * maximum size this function returns the same value as + * xfs_rtrefcountbt_get_maxrecs for the root node, too. + */ +STATIC int +xfs_rtrefcountbt_get_dmaxrecs( + struct xfs_btree_cur *cur, + int level) +{ + if (level != cur->bc_nlevels - 1) + return cur->bc_mp->m_rtrefc_mxr[level != 0]; + return xfs_rtrefcountbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); +} + STATIC void xfs_rtrefcountbt_init_key_from_rec( union xfs_btree_key *key, @@ -247,6 +282,87 @@ xfs_rtrefcountbt_keys_contiguous( be32_to_cpu(key2->refc.rc_startblock)); } +static inline void +xfs_rtrefcountbt_move_ptrs( + struct xfs_mount *mp, + struct xfs_btree_block *broot, + short old_size, + size_t new_size, + unsigned int numrecs) +{ + void *dptr; + void *sptr; + + sptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, old_size); + dptr = xfs_rtrefcount_broot_ptr_addr(mp, broot, 1, new_size); + memmove(dptr, sptr, numrecs * sizeof(xfs_rtrefcount_ptr_t)); +} + +static struct xfs_btree_block * +xfs_rtrefcountbt_broot_realloc( + struct xfs_btree_cur *cur, + unsigned int new_numrecs) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); + struct xfs_btree_block *broot; + unsigned int new_size; + unsigned int old_size = ifp->if_broot_bytes; + const unsigned int level = cur->bc_nlevels - 1; + + new_size = xfs_rtrefcount_broot_space_calc(mp, level, new_numrecs); + + /* Handle the nop case quietly. */ + if (new_size == old_size) + return ifp->if_broot; + + if (new_size > old_size) { + unsigned int old_numrecs; + + /* + * If there wasn't any memory allocated before, just allocate + * it now and get out. + */ + if (old_size == 0) + return xfs_broot_realloc(ifp, new_size); + + /* + * If there is already an existing if_broot, then we need to + * realloc it and possibly move the node block pointers because + * those are not butted up against the btree block header. + */ + old_numrecs = xfs_rtrefcountbt_maxrecs(mp, old_size, level); + broot = xfs_broot_realloc(ifp, new_size); + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, broot, old_size, + new_size, old_numrecs); + goto out_broot; + } + + /* + * We're reducing numrecs. If we're going all the way to zero, just + * free the block. + */ + ASSERT(ifp->if_broot != NULL && old_size > 0); + if (new_size == 0) + return xfs_broot_realloc(ifp, 0); + + /* + * Shrink the btree root by possibly moving the rtrmapbt pointers, + * since they are not butted up against the btree block header. Then + * reallocate broot. + */ + if (level > 0) + xfs_rtrefcountbt_move_ptrs(mp, ifp->if_broot, old_size, + new_size, new_numrecs); + broot = xfs_broot_realloc(ifp, new_size); + +out_broot: + ASSERT(xfs_rtrefcount_droot_space(broot) <= + xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); + return broot; +} + const struct xfs_btree_ops xfs_rtrefcountbt_ops = { .name = "rtrefcount", .type = XFS_BTREE_TYPE_INODE, @@ -264,6 +380,7 @@ const struct xfs_btree_ops xfs_rtrefcountbt_ops = { .free_block = xfs_btree_free_metafile_block, .get_minrecs = xfs_rtrefcountbt_get_minrecs, .get_maxrecs = xfs_rtrefcountbt_get_maxrecs, + .get_dmaxrecs = xfs_rtrefcountbt_get_dmaxrecs, .init_key_from_rec = xfs_rtrefcountbt_init_key_from_rec, .init_high_key_from_rec = xfs_rtrefcountbt_init_high_key_from_rec, .init_rec_from_cur = xfs_rtrefcountbt_init_rec_from_cur, @@ -274,6 +391,7 @@ const struct xfs_btree_ops xfs_rtrefcountbt_ops = { .keys_inorder = xfs_rtrefcountbt_keys_inorder, .recs_inorder = xfs_rtrefcountbt_recs_inorder, .keys_contiguous = xfs_rtrefcountbt_keys_contiguous, + .broot_realloc = xfs_rtrefcountbt_broot_realloc, }; /* Allocate a new rt refcount btree cursor. */ @@ -457,3 +575,149 @@ xfs_rtrefcountbt_calc_reserves( return xfs_rtrefcountbt_max_size(mp, mp->m_sb.sb_rgextents); } + +/* + * Convert on-disk form of btree root to in-memory form. + */ +STATIC void +xfs_rtrefcountbt_from_disk( + struct xfs_inode *ip, + struct xfs_rtrefcount_root *dblock, + int dblocklen, + struct xfs_btree_block *rblock) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int numrecs; + unsigned int maxrecs; + unsigned int rblocklen; + + rblocklen = xfs_rtrefcount_broot_space(mp, dblock); + + xfs_btree_init_block(mp, rblock, &xfs_rtrefcountbt_ops, 0, 0, + ip->i_ino); + + rblock->bb_level = dblock->bb_level; + rblock->bb_numrecs = dblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + tkp = xfs_rtrefcount_key_addr(rblock, 1); + fpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + tpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + trp = xfs_rtrefcount_rec_addr(rblock, 1); + numrecs = be16_to_cpu(dblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Load a realtime reference count btree root in from disk. */ +int +xfs_iformat_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + struct xfs_btree_block *broot; + unsigned int numrecs; + unsigned int level; + int dsize; + + /* + * growfs must create the rtrefcount inodes before adding a realtime + * volume to the filesystem, so we cannot use the rtrefcount predicate + * here. + */ + if (!xfs_has_reflink(ip->i_mount)) + return -EFSCORRUPTED; + + dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); + numrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); + + if (level > mp->m_rtrefc_maxlevels || + xfs_rtrefcount_droot_space_calc(level, numrecs) > dsize) + return -EFSCORRUPTED; + + broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), + xfs_rtrefcount_broot_space_calc(mp, level, numrecs)); + if (broot) + xfs_rtrefcountbt_from_disk(ip, dfp, dsize, broot); + return 0; +} + +/* + * Convert in-memory form of btree root to on-disk form. + */ +void +xfs_rtrefcountbt_to_disk( + struct xfs_mount *mp, + struct xfs_btree_block *rblock, + int rblocklen, + struct xfs_rtrefcount_root *dblock, + int dblocklen) +{ + struct xfs_refcount_key *fkp; + __be64 *fpp; + struct xfs_refcount_key *tkp; + __be64 *tpp; + struct xfs_refcount_rec *frp; + struct xfs_refcount_rec *trp; + unsigned int maxrecs; + unsigned int numrecs; + + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTREFC_CRC_MAGIC)); + ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); + ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); + + dblock->bb_level = rblock->bb_level; + dblock->bb_numrecs = rblock->bb_numrecs; + + if (be16_to_cpu(rblock->bb_level) > 0) { + maxrecs = xfs_rtrefcountbt_droot_maxrecs(dblocklen, false); + fkp = xfs_rtrefcount_key_addr(rblock, 1); + tkp = xfs_rtrefcount_droot_key_addr(dblock, 1); + fpp = xfs_rtrefcount_broot_ptr_addr(mp, rblock, 1, rblocklen); + tpp = xfs_rtrefcount_droot_ptr_addr(dblock, 1, maxrecs); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); + memcpy(tpp, fpp, sizeof(*fpp) * numrecs); + } else { + frp = xfs_rtrefcount_rec_addr(rblock, 1); + trp = xfs_rtrefcount_droot_rec_addr(dblock, 1); + numrecs = be16_to_cpu(rblock->bb_numrecs); + memcpy(trp, frp, sizeof(*frp) * numrecs); + } +} + +/* Flush a realtime reference count btree root out to disk. */ +void +xfs_iflush_rtrefcount( + struct xfs_inode *ip, + struct xfs_dinode *dip) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); + struct xfs_rtrefcount_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); + + ASSERT(ifp->if_broot != NULL); + ASSERT(ifp->if_broot_bytes > 0); + ASSERT(xfs_rtrefcount_droot_space(ifp->if_broot) <= + xfs_inode_fork_size(ip, XFS_DATA_FORK)); + xfs_rtrefcountbt_to_disk(ip->i_mount, ifp->if_broot, + ifp->if_broot_bytes, dfp, + XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); +} diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.h b/fs/xfs/libxfs/xfs_rtrefcount_btree.h index 3cd44590c930..e558a10c4744 100644 --- a/fs/xfs/libxfs/xfs_rtrefcount_btree.h +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.h @@ -25,6 +25,7 @@ void xfs_rtrefcountbt_commit_staged_btree(struct xfs_btree_cur *cur, unsigned int xfs_rtrefcountbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, bool leaf); void xfs_rtrefcountbt_compute_maxlevels(struct xfs_mount *mp); +unsigned int xfs_rtrefcountbt_droot_maxrecs(unsigned int blocklen, bool leaf); /* * Addresses of records, keys, and pointers within an incore rtrefcountbt block. @@ -71,4 +72,115 @@ xfs_filblks_t xfs_rtrefcountbt_calc_reserves(struct xfs_mount *mp); unsigned long long xfs_rtrefcountbt_calc_size(struct xfs_mount *mp, unsigned long long len); +/* Addresses of key, pointers, and records within an ondisk rtrefcount block. */ + +static inline struct xfs_refcount_rec * +xfs_rtrefcount_droot_rec_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_rec *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_rec)); +} + +static inline struct xfs_refcount_key * +xfs_rtrefcount_droot_key_addr( + struct xfs_rtrefcount_root *block, + unsigned int index) +{ + return (struct xfs_refcount_key *) + ((char *)(block + 1) + + (index - 1) * sizeof(struct xfs_refcount_key)); +} + +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_droot_ptr_addr( + struct xfs_rtrefcount_root *block, + unsigned int index, + unsigned int maxrecs) +{ + return (xfs_rtrefcount_ptr_t *) + ((char *)(block + 1) + + maxrecs * sizeof(struct xfs_refcount_key) + + (index - 1) * sizeof(xfs_rtrefcount_ptr_t)); +} + +/* + * Address of pointers within the incore btree root. + * + * These are to be used when we know the size of the block and + * we don't have a cursor. + */ +static inline xfs_rtrefcount_ptr_t * +xfs_rtrefcount_broot_ptr_addr( + struct xfs_mount *mp, + struct xfs_btree_block *bb, + unsigned int index, + unsigned int block_size) +{ + return xfs_rtrefcount_ptr_addr(bb, index, + xfs_rtrefcountbt_maxrecs(mp, block_size, false)); +} + +/* + * Compute the space required for the incore btree root containing the given + * number of records. + */ +static inline size_t +xfs_rtrefcount_broot_space_calc( + struct xfs_mount *mp, + unsigned int level, + unsigned int nrecs) +{ + size_t sz = XFS_RTREFCOUNT_BLOCK_LEN; + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the incore btree root given the ondisk + * btree root block. + */ +static inline size_t +xfs_rtrefcount_broot_space(struct xfs_mount *mp, struct xfs_rtrefcount_root *bb) +{ + return xfs_rtrefcount_broot_space_calc(mp, be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +/* Compute the space required for the ondisk root block. */ +static inline size_t +xfs_rtrefcount_droot_space_calc( + unsigned int level, + unsigned int nrecs) +{ + size_t sz = sizeof(struct xfs_rtrefcount_root); + + if (level > 0) + return sz + nrecs * (sizeof(struct xfs_refcount_key) + + sizeof(xfs_rtrefcount_ptr_t)); + return sz + nrecs * sizeof(struct xfs_refcount_rec); +} + +/* + * Compute the space required for the ondisk root block given an incore root + * block. + */ +static inline size_t +xfs_rtrefcount_droot_space(struct xfs_btree_block *bb) +{ + return xfs_rtrefcount_droot_space_calc(be16_to_cpu(bb->bb_level), + be16_to_cpu(bb->bb_numrecs)); +} + +int xfs_iformat_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); +void xfs_rtrefcountbt_to_disk(struct xfs_mount *mp, + struct xfs_btree_block *rblock, int rblocklen, + struct xfs_rtrefcount_root *dblock, int dblocklen); +void xfs_iflush_rtrefcount(struct xfs_inode *ip, struct xfs_dinode *dip); + #endif /* __XFS_RTREFCOUNT_BTREE_H__ */ diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index 5de1d3563b76..f3bfb814378c 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -23,6 +23,7 @@ #include "xfs_icache.h" #include "xfs_bmap_btree.h" #include "xfs_rtrmap_btree.h" +#include "xfs_rtrefcount_btree.h" STATIC void xlog_recover_inode_ra_pass2( @@ -286,6 +287,9 @@ xlog_recover_inode_dbroot( case XFS_METAFILE_RTRMAP: xfs_rtrmapbt_to_disk(mp, src, len, dfork, dsize); return 0; + case XFS_METAFILE_RTREFCOUNT: + xfs_rtrefcountbt_to_disk(mp, src, len, dfork, dsize); + return 0; default: ASSERT(0); return -EFSCORRUPTED; -- cgit v1.2.3