diff options
author | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-07-18 10:32:00 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-07-18 10:32:00 -0700 |
commit | d756d10e246a01515d07f8161181b8a14afba7cc (patch) | |
tree | de7336f2b4b596881468bf65cb2f2f88cedcde86 /fs/ext4/extents.c | |
parent | cdf4a6482dd4c739f8c1132c5a9356912911fec5 (diff) | |
parent | e9f410b1c035b6e63f0b4c3d6cfe4298d6a04492 (diff) |
Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: extent macros cleanup
Fix compilation with EXT_DEBUG, also fix leXX_to_cpu conversions.
ext4: remove extra IS_RDONLY() check
ext4: Use is_power_of_2()
Use zero_user_page() in ext4 where possible
ext4: Remove 65000 subdirectory limit
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields
ext4: Add nanosecond timestamps
jbd2: Move jbd2-debug file to debugfs
jbd2: Fix CONFIG_JBD_DEBUG ifdef to be CONFIG_JBD2_DEBUG
ext4: Set the journal JBD2_FEATURE_INCOMPAT_64BIT on large devices
ext4: Make extents code sanely handle on-disk corruption
ext4: copy i_flags to inode flags on write
ext4: Enable extents by default
Change on-disk format to support 2^15 uninitialized extents
write support for preallocated blocks
fallocate support in ext4
sys_fallocate() implementation on i386, x86_64 and powerpc
Diffstat (limited to 'fs/ext4/extents.c')
-rw-r--r-- | fs/ext4/extents.c | 682 |
1 files changed, 548 insertions, 134 deletions
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index b9ce2412907..750c46f7d89 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -39,6 +39,7 @@ #include <linux/quotaops.h> #include <linux/string.h> #include <linux/slab.h> +#include <linux/falloc.h> #include <linux/ext4_fs_extents.h> #include <asm/uaccess.h> @@ -91,36 +92,6 @@ static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb) ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); } -static int ext4_ext_check_header(const char *function, struct inode *inode, - struct ext4_extent_header *eh) -{ - const char *error_msg = NULL; - - if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) { - error_msg = "invalid magic"; - goto corrupted; - } - if (unlikely(eh->eh_max == 0)) { - error_msg = "invalid eh_max"; - goto corrupted; - } - if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) { - error_msg = "invalid eh_entries"; - goto corrupted; - } - return 0; - -corrupted: - ext4_error(inode->i_sb, function, - "bad header in inode #%lu: %s - magic %x, " - "entries %u, max %u, depth %u", - inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic), - le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), - le16_to_cpu(eh->eh_depth)); - - return -EIO; -} - static handle_t *ext4_ext_journal_restart(handle_t *handle, int needed) { int err; @@ -269,6 +240,70 @@ static int ext4_ext_space_root_idx(struct inode *inode) return size; } +static int +ext4_ext_max_entries(struct inode *inode, int depth) +{ + int max; + + if (depth == ext_depth(inode)) { + if (depth == 0) + max = ext4_ext_space_root(inode); + else + max = ext4_ext_space_root_idx(inode); + } else { + if (depth == 0) + max = ext4_ext_space_block(inode); + else + max = ext4_ext_space_block_idx(inode); + } + + return max; +} + +static int __ext4_ext_check_header(const char *function, struct inode *inode, + struct ext4_extent_header *eh, + int depth) +{ + const char *error_msg; + int max = 0; + + if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) { + error_msg = "invalid magic"; + goto corrupted; + } + if (unlikely(le16_to_cpu(eh->eh_depth) != depth)) { + error_msg = "unexpected eh_depth"; + goto corrupted; + } + if (unlikely(eh->eh_max == 0)) { + error_msg = "invalid eh_max"; + goto corrupted; + } + max = ext4_ext_max_entries(inode, depth); + if (unlikely(le16_to_cpu(eh->eh_max) > max)) { + error_msg = "too large eh_max"; + goto corrupted; + } + if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) { + error_msg = "invalid eh_entries"; + goto corrupted; + } + return 0; + +corrupted: + ext4_error(inode->i_sb, function, + "bad header in inode #%lu: %s - magic %x, " + "entries %u, max %u(%u), depth %u(%u)", + inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic), + le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), + max, le16_to_cpu(eh->eh_depth), depth); + + return -EIO; +} + +#define ext4_ext_check_header(inode, eh, depth) \ + __ext4_ext_check_header(__FUNCTION__, inode, eh, depth) + #ifdef EXT_DEBUG static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) { @@ -282,7 +317,7 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) } else if (path->p_ext) { ext_debug(" %d:%d:%llu ", le32_to_cpu(path->p_ext->ee_block), - le16_to_cpu(path->p_ext->ee_len), + ext4_ext_get_actual_len(path->p_ext), ext_pblock(path->p_ext)); } else ext_debug(" []"); @@ -305,7 +340,7 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { ext_debug("%d:%d:%llu ", le32_to_cpu(ex->ee_block), - le16_to_cpu(ex->ee_len), ext_pblock(ex)); + ext4_ext_get_actual_len(ex), ext_pblock(ex)); } ext_debug("\n"); } @@ -329,6 +364,7 @@ static void ext4_ext_drop_refs(struct ext4_ext_path *path) /* * ext4_ext_binsearch_idx: * binary search for the closest index of the given block + * the header must be checked before calling this */ static void ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int block) @@ -336,27 +372,25 @@ ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int bloc struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent_idx *r, *l, *m; - BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC); - BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max)); - BUG_ON(le16_to_cpu(eh->eh_entries) <= 0); ext_debug("binsearch for %d(idx): ", block); l = EXT_FIRST_INDEX(eh) + 1; - r = EXT_FIRST_INDEX(eh) + le16_to_cpu(eh->eh_entries) - 1; + r = EXT_LAST_INDEX(eh); while (l <= r) { m = l + (r - l) / 2; if (block < le32_to_cpu(m->ei_block)) r = m - 1; else l = m + 1; - ext_debug("%p(%u):%p(%u):%p(%u) ", l, l->ei_block, - m, m->ei_block, r, r->ei_block); + ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block), + m, le32_to_cpu(m->ei_block), + r, le32_to_cpu(r->ei_block)); } path->p_idx = l - 1; ext_debug(" -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block), - idx_block(path->p_idx)); + idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH { @@ -388,6 +422,7 @@ ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int bloc /* * ext4_ext_binsearch: * binary search for closest extent of the given block + * the header must be checked before calling this */ static void ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block) @@ -395,9 +430,6 @@ ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block) struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent *r, *l, *m; - BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC); - BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max)); - if (eh->eh_entries == 0) { /* * this leaf is empty: @@ -409,7 +441,7 @@ ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block) ext_debug("binsearch for %d: ", block); l = EXT_FIRST_EXTENT(eh) + 1; - r = EXT_FIRST_EXTENT(eh) + le16_to_cpu(eh->eh_entries) - 1; + r = EXT_LAST_EXTENT(eh); while (l <= r) { m = l + (r - l) / 2; @@ -417,15 +449,16 @@ ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block) r = m - 1; else l = m + 1; - ext_debug("%p(%u):%p(%u):%p(%u) ", l, l->ee_block, - m, m->ee_block, r, r->ee_block); + ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block), + m, le32_to_cpu(m->ee_block), + r, le32_to_cpu(r->ee_block)); } path->p_ext = l - 1; ext_debug(" -> %d:%llu:%d ", le32_to_cpu(path->p_ext->ee_block), ext_pblock(path->p_ext), - le16_to_cpu(path->p_ext->ee_len)); + ext4_ext_get_actual_len(path->p_ext)); #ifdef CHECK_BINSEARCH { @@ -468,11 +501,10 @@ ext4_ext_find_extent(struct inode *inode, int block, struct ext4_ext_path *path) short int depth, i, ppos = 0, alloc = 0; eh = ext_inode_hdr(inode); - BUG_ON(eh == NULL); - if (ext4_ext_check_header(__FUNCTION__, inode, eh)) + depth = ext_depth(inode); + if (ext4_ext_check_header(inode, eh, depth)) return ERR_PTR(-EIO); - i = depth = ext_depth(inode); /* account possible depth increase */ if (!path) { @@ -484,10 +516,12 @@ ext4_ext_find_extent(struct inode *inode, int block, struct ext4_ext_path *path) } path[0].p_hdr = eh; + i = depth; /* walk through the tree */ while (i) { ext_debug("depth %d: num %d, max %d\n", ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); + ext4_ext_binsearch_idx(inode, path + ppos, block); path[ppos].p_block = idx_pblock(path[ppos].p_idx); path[ppos].p_depth = i; @@ -504,7 +538,7 @@ ext4_ext_find_extent(struct inode *inode, int block, struct ext4_ext_path *path) path[ppos].p_hdr = eh; i--; - if (ext4_ext_check_header(__FUNCTION__, inode, eh)) + if (ext4_ext_check_header(inode, eh, i)) goto err; } @@ -513,9 +547,6 @@ ext4_ext_find_extent(struct inode *inode, int block, struct ext4_ext_path *path) path[ppos].p_ext = NULL; path[ppos].p_idx = NULL; - if (ext4_ext_check_header(__FUNCTION__, inode, eh)) - goto err; - /* find extent */ ext4_ext_binsearch(inode, path + ppos, block); @@ -553,7 +584,7 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, if (curp->p_idx != EXT_LAST_INDEX(curp->p_hdr)) { len = (len - 1) * sizeof(struct ext4_extent_idx); len = len < 0 ? 0 : len; - ext_debug("insert new index %d after: %d. " + ext_debug("insert new index %d after: %llu. " "move %d from 0x%p to 0x%p\n", logical, ptr, len, (curp->p_idx + 1), (curp->p_idx + 2)); @@ -564,7 +595,7 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, /* insert before */ len = len * sizeof(struct ext4_extent_idx); len = len < 0 ? 0 : len; - ext_debug("insert new index %d before: %d. " + ext_debug("insert new index %d before: %llu. " "move %d from 0x%p to 0x%p\n", logical, ptr, len, curp->p_idx, (curp->p_idx + 1)); @@ -686,7 +717,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, ext_debug("move %d:%llu:%d in new leaf %llu\n", le32_to_cpu(path[depth].p_ext->ee_block), ext_pblock(path[depth].p_ext), - le16_to_cpu(path[depth].p_ext->ee_len), + ext4_ext_get_actual_len(path[depth].p_ext), newblock); /*memmove(ex++, path[depth].p_ext++, sizeof(struct ext4_extent)); @@ -764,7 +795,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, BUG_ON(EXT_MAX_INDEX(path[i].p_hdr) != EXT_LAST_INDEX(path[i].p_hdr)); while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) { - ext_debug("%d: move %d:%d in new index %llu\n", i, + ext_debug("%d: move %d:%llu in new index %llu\n", i, le32_to_cpu(path[i].p_idx->ei_block), idx_pblock(path[i].p_idx), newblock); @@ -893,8 +924,13 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode)); curp->p_hdr->eh_entries = cpu_to_le16(1); curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr); - /* FIXME: it works, but actually path[0] can be index */ - curp->p_idx->ei_block = EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block; + + if (path[0].p_hdr->eh_depth) + curp->p_idx->ei_block = + EXT_FIRST_INDEX(path[0].p_hdr)->ei_block; + else + curp->p_idx->ei_block = + EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block; ext4_idx_store_pblock(curp->p_idx, newblock); neh = ext_inode_hdr(inode); @@ -1106,7 +1142,24 @@ static int ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, struct ext4_extent *ex2) { - if (le32_to_cpu(ex1->ee_block) + le16_to_cpu(ex1->ee_len) != + unsigned short ext1_ee_len, ext2_ee_len, max_len; + + /* + * Make sure that either both extents are uninitialized, or + * both are _not_. + */ + if (ext4_ext_is_uninitialized(ex1) ^ ext4_ext_is_uninitialized(ex2)) + return 0; + + if (ext4_ext_is_uninitialized(ex1)) + max_len = EXT_UNINIT_MAX_LEN; + else + max_len = EXT_INIT_MAX_LEN; + + ext1_ee_len = ext4_ext_get_actual_len(ex1); + ext2_ee_len = ext4_ext_get_actual_len(ex2); + + if (le32_to_cpu(ex1->ee_block) + ext1_ee_len != le32_to_cpu(ex2->ee_block)) return 0; @@ -1115,19 +1168,66 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, * as an RO_COMPAT feature, refuse to merge to extents if * this can result in the top bit of ee_len being set. */ - if (le16_to_cpu(ex1->ee_len) + le16_to_cpu(ex2->ee_len) > EXT_MAX_LEN) + if (ext1_ee_len + ext2_ee_len > max_len) return 0; #ifdef AGGRESSIVE_TEST if (le16_to_cpu(ex1->ee_len) >= 4) return 0; #endif - if (ext_pblock(ex1) + le16_to_cpu(ex1->ee_len) == ext_pblock(ex2)) + if (ext_pblock(ex1) + ext1_ee_len == ext_pblock(ex2)) return 1; return 0; } /* + * This function tries to merge the "ex" extent to the next extent in the tree. + * It always tries to merge towards right. If you want to merge towards + * left, pass "ex - 1" as argument instead of "ex". + * Returns 0 if the extents (ex and ex+1) were _not_ merged and returns + * 1 if they got merged. + */ +int ext4_ext_try_to_merge(struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *ex) +{ + struct ext4_extent_header *eh; + unsigned int depth, len; + int merge_done = 0; + int uninitialized = 0; + + depth = ext_depth(inode); + BUG_ON(path[depth].p_hdr == NULL); + eh = path[depth].p_hdr; + + while (ex < EXT_LAST_EXTENT(eh)) { + if (!ext4_can_extents_be_merged(inode, ex, ex + 1)) + break; + /* merge with next extent! */ + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + + ext4_ext_get_actual_len(ex + 1)); + if (uninitialized) + ext4_ext_mark_uninitialized(ex); + + if (ex + 1 < EXT_LAST_EXTENT(eh)) { + len = (EXT_LAST_EXTENT(eh) - ex - 1) + * sizeof(struct ext4_extent); + memmove(ex + 1, ex + 2, len); + } + eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries) - 1); + merge_done = 1; + WARN_ON(eh->eh_entries == 0); + if (!eh->eh_entries) + ext4_error(inode->i_sb, "ext4_ext_try_to_merge", + "inode#%lu, eh->eh_entries = 0!", inode->i_ino); + } + + return merge_done; +} + +/* * check if a portion of the "newext" extent overlaps with an * existing extent. * @@ -1144,7 +1244,7 @@ unsigned int ext4_ext_check_overlap(struct inode *inode, unsigned int ret = 0; b1 = le32_to_cpu(newext->ee_block); - len1 = le16_to_cpu(newext->ee_len); + len1 = ext4_ext_get_actual_len(newext); depth = ext_depth(inode); if (!path[depth].p_ext) goto out; @@ -1191,8 +1291,9 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, struct ext4_extent *nearex; /* nearest extent */ struct ext4_ext_path *npath = NULL; int depth, len, err, next; + unsigned uninitialized = 0; - BUG_ON(newext->ee_len == 0); + BUG_ON(ext4_ext_get_actual_len(newext) == 0); depth = ext_depth(inode); ex = path[depth].p_ext; BUG_ON(path[depth].p_hdr == NULL); @@ -1200,14 +1301,24 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, /* try to insert block into found extent and return */ if (ex && ext4_can_extents_be_merged(inode, ex, newext)) { ext_debug("append %d block to %d:%d (from %llu)\n", - le16_to_cpu(newext->ee_len), + ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), - le16_to_cpu(ex->ee_len), ext_pblock(ex)); + ext4_ext_get_actual_len(ex), ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; - ex->ee_len = cpu_to_le16(le16_to_cpu(ex->ee_len) - + le16_to_cpu(newext->ee_len)); + + /* + * ext4_can_extents_be_merged should have checked that either + * both extents are uninitialized, or both aren't. Thus we + * need to check only one of them here. + */ + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + + ext4_ext_get_actual_len(newext)); + if (uninitialized) + ext4_ext_mark_uninitialized(ex); eh = path[depth].p_hdr; nearex = ex; goto merge; @@ -1263,7 +1374,7 @@ has_space: ext_debug("first extent in the leaf: %d:%llu:%d\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), - le16_to_cpu(newext->ee_len)); + ext4_ext_get_actual_len(newext)); path[depth].p_ext = EXT_FIRST_EXTENT(eh); } else if (le32_to_cpu(newext->ee_block) > le32_to_cpu(nearex->ee_block)) { @@ -1276,7 +1387,7 @@ has_space: "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), - le16_to_cpu(newext->ee_len), + ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); memmove(nearex + 2, nearex + 1, len); } @@ -1289,7 +1400,7 @@ has_space: "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), - le16_to_cpu(newext->ee_len), + ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); memmove(nearex + 1, nearex, len); path[depth].p_ext = nearex; @@ -1304,20 +1415,7 @@ has_space: merge: /* try to merge extents to the right */ - while (nearex < EXT_LAST_EXTENT(eh)) { - if (!ext4_can_extents_be_merged(inode, nearex, nearex + 1)) - break; - /* merge with next extent! */ - nearex->ee_len = cpu_to_le16(le16_to_cpu(nearex->ee_len) - + le16_to_cpu(nearex[1].ee_len)); - if (nearex + 1 < EXT_LAST_EXTENT(eh)) { - len = (EXT_LAST_EXTENT(eh) - nearex - 1) - * sizeof(struct ext4_extent); - memmove(nearex + 1, nearex + 2, len); - } - eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)-1); - BUG_ON(eh->eh_entries == 0); - } + ext4_ext_try_to_merge(inode, path, nearex); /* try to merge extents to the left */ @@ -1379,8 +1477,8 @@ int ext4_ext_walk_space(struct inode *inode, unsigned long block, end = le32_to_cpu(ex->ee_block); if (block + num < end) end = block + num; - } else if (block >= - le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len)) { + } else if (block >= le32_to_cpu(ex->ee_block) + + ext4_ext_get_actual_len(ex)) { /* need to allocate space after found extent */ start = block; end = block + num; @@ -1392,7 +1490,8 @@ int ext4_ext_walk_space(struct inode *inode, unsigned long block, * by found extent */ start = block; - end = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len); + end = le32_to_cpu(ex->ee_block) + + ext4_ext_get_actual_len(ex); if (block + num < end) end = block + num; exists = 1; @@ -1408,7 +1507,7 @@ int ext4_ext_walk_space(struct inode *inode, unsigned long block, cbex.ec_type = EXT4_EXT_CACHE_GAP; } else { cbex.ec_block = le32_to_cpu(ex->ee_block); - cbex.ec_len = le16_to_cpu(ex->ee_len); + cbex.ec_len = ext4_ext_get_actual_len(ex); cbex.ec_start = ext_pblock(ex); cbex.ec_type = EXT4_EXT_CACHE_EXTENT; } @@ -1481,15 +1580,15 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, ext_debug("cache gap(before): %lu [%lu:%lu]", (unsigned long) block, (unsigned long) le32_to_cpu(ex->ee_block), - (unsigned long) le16_to_cpu(ex->ee_len)); + (unsigned long) ext4_ext_get_actual_len(ex)); } else if (block >= le32_to_cpu(ex->ee_block) - + le16_to_cpu(ex->ee_len)) { + + ext4_ext_get_actual_len(ex)) { lblock = le32_to_cpu(ex->ee_block) - + le16_to_cpu(ex->ee_len); + + ext4_ext_get_actual_len(ex); len = ext4_ext_next_allocated_block(path); ext_debug("cache gap(after): [%lu:%lu] %lu", (unsigned long) le32_to_cpu(ex->ee_block), - (unsigned long) le16_to_cpu(ex->ee_len), + (unsigned long) ext4_ext_get_actual_len(ex), (unsigned long) block); BUG_ON(len == lblock); len = len - lblock; @@ -1619,12 +1718,12 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, unsigned long from, unsigned long to) { struct buffer_head *bh; + unsigned short ee_len = ext4_ext_get_actual_len(ex); int i; #ifdef EXTENTS_STATS { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - unsigned short ee_len = le16_to_cpu(ex->ee_len); spin_lock(&sbi->s_ext_stats_lock); sbi->s_ext_blocks += ee_len; sbi->s_ext_extents++; @@ -1638,12 +1737,12 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, } #endif if (from >= le32_to_cpu(ex->ee_block) - && to == le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) { + && to == le32_to_cpu(ex->ee_block) + ee_len - 1) { /* tail removal */ unsigned long num; ext4_fsblk_t start; - num = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - from; - start = ext_pblock(ex) + le16_to_cpu(ex->ee_len) - num; + num = le32_to_cpu(ex->ee_block) + ee_len - from; + start = ext_pblock(ex) + ee_len - num; ext_debug("free last %lu blocks starting %llu\n", num, start); for (i = 0; i < num; i++) { bh = sb_find_get_block(inode->i_sb, start + i); @@ -1651,12 +1750,12 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, } ext4_free_blocks(handle, inode, start, num); } else if (from == le32_to_cpu(ex->ee_block) - && to <= le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) { + && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) { printk("strange request: removal %lu-%lu from %u:%u\n", - from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len)); + from, to, le32_to_cpu(ex->ee_block), ee_len); } else { printk("strange request: removal(2) %lu-%lu from %u:%u\n", - from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len)); + from, to, le32_to_cpu(ex->ee_block), ee_len); } return 0; } @@ -1671,21 +1770,23 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, unsigned a, b, block, num; unsigned long ex_ee_block; unsigned short ex_ee_len; + unsigned uninitialized = 0; struct ext4_extent *ex; + /* the header must be checked already in ext4_ext_remove_space() */ ext_debug("truncate since %lu in leaf\n", start); if (!path[depth].p_hdr) path[depth].p_hdr = ext_block_hdr(path[depth].p_bh); eh = path[depth].p_hdr; BUG_ON(eh == NULL); - BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max)); - BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC); /* find where to start removing */ ex = EXT_LAST_EXTENT(eh); ex_ee_block = le32_to_cpu(ex->ee_block); - ex_ee_len = le16_to_cpu(ex->ee_len); + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + ex_ee_len = ext4_ext_get_actual_len(ex); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { @@ -1753,6 +1854,12 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ex->ee_block = cpu_to_le32(block); ex->ee_len = cpu_to_le16(num); + /* + * Do not mark uninitialized if all the blocks in the + * extent have been removed. + */ + if (uninitialized && num) + ext4_ext_mark_uninitialized(ex); err = ext4_ext_dirty(handle, inode, path + depth); if (err) @@ -1762,7 +1869,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ext_pblock(ex)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); - ex_ee_len = le16_to_cpu(ex->ee_len); + ex_ee_len = ext4_ext_get_actual_len(ex); } if (correct_index && eh->eh_entries) @@ -1825,7 +1932,7 @@ int ext4_ext_remove_space(struct inode *inode, unsigned long start) return -ENOMEM; } path[0].p_hdr = ext_inode_hdr(inode); - if (ext4_ext_check_header(__FUNCTION__, inode, path[0].p_hdr)) { + if (ext4_ext_check_header(inode, path[0].p_hdr, depth)) { err = -EIO; goto out; } @@ -1846,17 +1953,8 @@ int ext4_ext_remove_space(struct inode *inode, unsigned long start) if (!path[i].p_hdr) { ext_debug("initialize header\n"); path[i].p_hdr = ext_block_hdr(path[i].p_bh); - if (ext4_ext_check_header(__FUNCTION__, inode, - path[i].p_hdr)) { - err = -EIO; - goto out; - } } - BUG_ON(le16_to_cpu(path[i].p_hdr->eh_entries) - > le16_to_cpu(path[i].p_hdr->eh_max)); - BUG_ON(path[i].p_hdr->eh_magic != EXT4_EXT_MAGIC); - if (!path[i].p_idx) { /* this level hasn't been touched yet */ path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr); @@ -1873,17 +1971,27 @@ int ext4_ext_remove_space(struct inode *inode, unsigned long start) i, EXT_FIRST_INDEX(path[i].p_hdr), path[i].p_idx); if (ext4_ext_more_to_rm(path + i)) { + struct buffer_head *bh; /* go to the next level */ ext_debug("move to level %d (block %llu)\n", i + 1, idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); - path[i+1].p_bh = - sb_bread(sb, idx_pblock(path[i].p_idx)); - if (!path[i+1].p_bh) { + bh = sb_bread(sb, idx_pblock(path[i].p_idx)); + if (!bh) { /* should we reset i_size? */ err = -EIO; break; } + if (WARN_ON(i + 1 > depth)) { + err = -EIO; + break; + } + if (ext4_ext_check_header(inode, ext_block_hdr(bh), + depth - i - 1)) { + err = -EIO; + break; + } + path[i + 1].p_bh = bh; /* save actual number of indexes since this * number is changed at the next iteration */ @@ -1977,15 +2085,158 @@ void ext4_ext_release(struct super_block *sb) #endif } +/* + * This function is called by ext4_ext_get_blocks() if someone tries to write + * to an uninitialized extent. It may result in splitting the uninitialized + * extent into multiple extents (upto three - one initialized and two + * uninitialized). + * There are three possibilities: + * a> There is no split required: Entire extent should be initialized + * b> Splits in two extents: Write is happening at either end of the extent + * c> Splits in three extents: Somone is writing in middle of the extent + */ +int ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path, + ext4_fsblk_t iblock, + unsigned long max_blocks) +{ + struct ext4_extent *ex, newex; + struct ext4_extent *ex1 = NULL; + struct ext4_extent *ex2 = NULL; + struct ext4_extent *ex3 = NULL; + struct ext4_extent_header *eh; + unsigned int allocated, ee_block, ee_len, depth; + ext4_fsblk_t newblock; + int err = 0; + int ret = 0; + + depth = ext_depth(inode); + eh = path[depth].p_hdr; + ex = path[depth].p_ext; + ee_block = le32_to_cpu(ex->ee_block); + ee_len = ext4_ext_get_actual_len(ex); + allocated = ee_len - (iblock - ee_block); + newblock = iblock - ee_block + ext_pblock(ex); + ex2 = ex; + + /* ex1: ee_block to iblock - 1 : uninitialized */ + if (iblock > ee_block) { + ex1 = ex; + ex1->ee_len = cpu_to_le16(iblock - ee_block); + ext4_ext_mark_uninitialized(ex1); + ex2 = &newex; + } + /* + * for sanity, update the length of the ex2 extent before + * we insert ex3, if ex1 is NULL. This is to avoid temporary + * overlap of blocks. + */ + if (!ex1 && allocated > max_blocks) + ex2->ee_len = cpu_to_le16(max_blocks); + /* ex3: to ee_block + ee_len : uninitialised */ + if (allocated > max_blocks) { + unsigned int newdepth; + ex3 = &newex; + ex3->ee_block = cpu_to_le32(iblock + max_blocks); + ext4_ext_store_pblock(ex3, newblock + max_blocks); + ex3->ee_len = cpu_to_le16(allocated - max_blocks); + ext4_ext_mark_uninitialized(ex3); + err = ext4_ext_insert_extent(handle, inode, path, ex3); + if (err) + goto out; + /* + * The depth, and hence eh & ex might change + * as part of the insert above. + */ + newdepth = ext_depth(inode); + if (newdepth != depth) { + depth = newdepth; + path = ext4_ext_find_extent(inode, iblock, NULL); + if (IS_ERR(path)) { + err = PTR_ERR(path); + path = NULL; + goto out; + } + eh = path[depth].p_hdr; + ex = path[depth].p_ext; + if (ex2 != &newex) + ex2 = ex; + } + allocated = max_blocks; + } + /* + * If there was a change of depth as part of the + * insertion of ex3 above, we need to update the length + * of the ex1 extent again here + */ + if (ex1 && ex1 != ex) { + ex1 = ex; + ex1->ee_len = cpu_to_le16(iblock - ee_block); + ext4_ext_mark_uninitialized(ex1); + ex2 = &newex; + } + /* ex2: iblock to iblock + maxblocks-1 : initialised */ + ex2->ee_block = cpu_to_le32(iblock); + ex2->ee_start = cpu_to_le32(newblock); + ext4_ext_store_pblock(ex2, newblock); + ex2->ee_len = cpu_to_le16(allocated); + if (ex2 != ex) + goto insert; + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; + /* + * New (initialized) extent starts from the first block + * in the current extent. i.e., ex2 == ex + * We have to see if it can be merged with the extent + * on the left. + */ + if (ex2 > EXT_FIRST_EXTENT(eh)) { + /* + * To merge left, pass "ex2 - 1" to try_to_merge(), + * since it merges towards right _only_. + */ + ret = ext4_ext_try_to_merge(inode, path, ex2 - 1); + if (ret) { + err = ext4_ext_correct_indexes(handle, inode, path); + if (err) + goto out; + depth = ext_depth(inode); + ex2--; + } + } + /* + * Try to Merge towards right. This might be required + * only when the whole extent is being written to. + * i.e. ex2 == ex and ex3 == NULL. + */ + if (!ex3) { + ret = ext4_ext_try_to_merge(inode, path, ex2); + if (ret) { + err = ext4_ext_correct_indexes(handle, inode, path); + if (err) + goto out; + } + } + /* Mark modified extent as dirty */ + err = ext4_ext_dirty(handle, inode, path + depth); + goto out; +insert: + err = ext4_ext_insert_extent(handle, inode, path, &newex); +out: + return err ? err : allocated; +} + int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t iblock, unsigned long max_blocks, struct buffer_head *bh_result, int create, int extend_disksize) { struct ext4_ext_path *path = NULL; + struct ext4_extent_header *eh; struct ext4_extent newex, *ex; ext4_fsblk_t goal, newblock; - int err = 0, depth; + int err = 0, depth, ret; unsigned long allocated = 0; __clear_bit(BH_New, &bh_result->b_state); @@ -1998,8 +2249,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, if (goal) { if (goal == EXT4_EXT_CACHE_GAP) { if (!create) { - /* block isn't allocated yet and - * user doesn't want to allocate it */ + /* + * block isn't allocated yet and + * user doesn't want to allocate it + */ goto out2; } /* we should allocate requested block */ @@ -2033,21 +2286,19 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * this is why assert can't be put in ext4_ext_find_extent() */ BUG_ON(path[depth].p_ext == NULL && depth != 0); + eh = path[depth].p_hdr; ex = path[depth].p_ext; if (ex) { unsigned long ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext_pblock(ex); - unsigned short ee_len = le16_to_cpu(ex->ee_len); + unsigned short ee_len; /* - * Allow future support for preallocated extents to be added - * as an RO_COMPAT feature: * Uninitialized extents are treated as holes, except that - * we avoid (fail) allocating new blocks during a write. + * we split out initialized portions during a write. */ - if (ee_len > EXT_MAX_LEN) - goto out2; + ee_len = ext4_ext_get_actual_len(ex); /* if found extent covers block, simply return it */ if (iblock >= ee_block && iblock < ee_block + ee_len) { newblock = iblock - ee_block + ee_start; @@ -2055,9 +2306,27 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, allocated = ee_len - (iblock - ee_block); ext_debug("%d fit into %lu:%d -> %llu\n", (int) iblock, ee_block, ee_len, newblock); - ext4_ext_put_in_cache(inode, ee_block, ee_len, - ee_start, EXT4_EXT_CACHE_EXTENT); - goto out; + + /* Do not put uninitialized extent in the cache */ + if (!ext4_ext_is_uninitialized(ex)) { + ext4_ext_put_in_cache(inode, ee_block, + ee_len, ee_start, + EXT4_EXT_CACHE_EXTENT); + goto out; + } + if (create == EXT4_CREATE_UNINITIALIZED_EXT) + goto out; + if (!create) + goto out2; + + ret = ext4_ext_convert_to_initialized(handle, inode, + path, iblock, + max_blocks); + if (ret <= 0) + goto out2; + else + allocated = ret; + goto outnew; } } @@ -2066,8 +2335,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * we couldn't try to create block if create flag is zero */ if (!create) { - /* put just found gap into cache to speed up - * subsequent requests */ + /* + * put just found gap into cache to speed up + * subsequent requests + */ ext4_ext_put_gap_in_cache(inode, path, iblock); goto out2; } @@ -2081,6 +2352,19 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, /* allocate new block */ goal = ext4_ext_find_goal(inode, path, iblock); + /* + * See if request is beyond maximum number of blocks we can have in + * a single extent. For an initialized extent this limit is + * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is + * EXT_UNINIT_MAX_LEN. + */ + if (max_blocks > EXT_INIT_MAX_LEN && + create != EXT4_CREATE_UNINITIALIZED_EXT) + max_blocks = EXT_INIT_MAX_LEN; + else if (max_blocks > EXT_UNINIT_MAX_LEN && + create == EXT4_CREATE_UNINITIALIZED_EXT) + max_blocks = EXT_UNINIT_MAX_LEN; + /* Check if we can really insert (iblock)::(iblock+max_blocks) extent */ newex.ee_block = cpu_to_le32(iblock); newex.ee_len = cpu_to_le16(max_blocks); @@ -2098,6 +2382,8 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, /* try to insert new extent into found leaf and return */ ext4_ext_store_pblock(&newex, newblock); newex.ee_len = cpu_to_le16(allocated); + if (create == EXT4_CREATE_UNINITIALIZED_EXT) /* Mark uninitialized */ + ext4_ext_mark_uninitialized(&newex); err = ext4_ext_insert_extent(handle, inode, path, &newex); if (err) { /* free data blocks we just allocated */ @@ -2111,10 +2397,13 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, /* previous routine could use block we allocated */ newblock = ext_pblock(&newex); +outnew: __set_bit(BH_New, &bh_result->b_state); - ext4_ext_put_in_cache(inode, iblock, allocated, newblock, - EXT4_EXT_CACHE_EXTENT); + /* Cache only when it is _not_ an uninitialized extent */ + if (create != EXT4_CREATE_UNINITIALIZED_EXT) + ext4_ext_put_in_cache(inode, iblock, allocated, newblock, + EXT4_EXT_CACHE_EXTENT); out: if (allocated > max_blocks) allocated = max_blocks; @@ -2178,7 +2467,8 @@ void ext4_ext_truncate(struct inode * inode, struct page *page) err = ext4_ext_remove_space(inode, last_block); /* In a multi-transaction truncate, we only make the final - * transaction synchronous. */ + * transaction synchronous. + */ if (IS_SYNC(inode)) handle->h_sync = 1; @@ -2217,3 +2507,127 @@ int ext4_ext_writepage_trans_blocks(struct inode *inode, int num) return needed; } + +/* + * preallocate space for a file. This implements ext4's fallocate inode + * operation, which gets called from sys_fallocate system call. + * For block-mapped files, posix_fallocate should fall back to the method + * of writing zeroes to the required new blocks (the same behavior which is + * expected for file systems which do not support fallocate() system call). + */ +long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len) +{ + handle_t *handle; + ext4_fsblk_t block, max_blocks; + ext4_fsblk_t nblocks = 0; + int ret = 0; + int ret2 = 0; + int retries = 0; + struct buffer_head map_bh; + unsigned int credits, blkbits = inode->i_blkbits; + + /* + * currently supporting (pre)allocate mode for extent-based + * files _only_ + */ + if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) + return -EOPNOTSUPP; + + /* preallocation to directories is currently not supported */ + if (S_ISDIR(inode->i_mode)) + return -ENODEV; + + block = offset >> blkbits; + max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) + - block; + + /* + * credits to insert 1 extent into extent tree + buffers to be able to + * modify 1 super block, 1 block bitmap and 1 group descriptor. + */ + credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3; +retry: + while (ret >= 0 && ret < max_blocks) { + block = block + ret; + max_blocks = max_blocks - ret; + handle = ext4_journal_start(inode, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + break; + } + + ret = ext4_ext_get_blocks(handle, inode, block, + max_blocks, &map_bh, + EXT4_CREATE_UNINITIALIZED_EXT, 0); + WARN_ON(!ret); + if (!ret) { + ext4_error(inode->i_sb, "ext4_fallocate", + "ext4_ext_get_blocks returned 0! inode#%lu" + ", block=%llu, max_blocks=%llu", + inode->i_ino, block, max_blocks); + ret = -EIO; + ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_journal_stop(handle); + break; + } + if (ret > 0) { + /* check wrap through sign-bit/zero here */ + if ((block + ret) < 0 || (block + ret) < block) { + ret = -EIO; + ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_journal_stop(handle); + break; + } + if (buffer_new(&map_bh) && ((block + ret) > + (EXT4_BLOCK_ALIGN(i_size_read(inode), blkbits) + >> blkbits))) + nblocks = nblocks + ret; + } + + /* Update ctime if new blocks get allocated */ + if (nblocks) { + struct timespec now; + + now = current_fs_time(inode->i_sb); + if (!timespec_equal(&inode->i_ctime, &now)) + inode->i_ctime = now; + } + + ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_journal_stop(handle); + if (ret2) + break; + } + + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + + /* + * Time to update the file size. + * Update only when preallocation was requested beyond the file size. + */ + if (!(mode & FALLOC_FL_KEEP_SIZE) && + (offset + len) > i_size_read(inode)) { + if (ret > 0) { + /* + * if no error, we assume preallocation succeeded + * completely + */ + mutex_lock(&inode->i_mutex); + i_size_write(inode, offset + len); + EXT4_I(inode)->i_disksize = i_size_read(inode); + mutex_unlock(&inode->i_mutex); + } else if (ret < 0 && nblocks) { + /* Handle partial allocation scenario */ + loff_t newsize; + + mutex_lock(&inode->i_mutex); + newsize = (nblocks << blkbits) + i_size_read(inode); + i_size_write(inode, EXT4_BLOCK_ALIGN(newsize, blkbits)); + EXT4_I(inode)->i_disksize = i_size_read(inode); + mutex_unlock(&inode->i_mutex); + } + } + + return ret > 0 ? ret2 : ret; +} |