X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fext4%2Fialloc.c;h=1a0e183a2f048807e0a079de9ae65c671fc12e0d;hb=b10b8520903204c9a1e4ef4a6827c2f1569aae9b;hp=b47427a21f1c14f63564bd9d6e9f816a5c86c63b;hpb=3300beda523136f9f87821e4fba85c5c9e319645;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b47427a..1a0e183 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -23,11 +23,13 @@ #include #include #include + #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" -#include "group.h" + +#include /* * ialloc.c contains the inodes allocation and deallocation routines @@ -74,8 +76,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh, /* If checksum is bad mark all blocks and inodes use to prevent * allocation, essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { - ext4_error(sb, __func__, "Checksum bad for group %u", - block_group); + ext4_error(sb, "Checksum bad for group %u", block_group); ext4_free_blks_set(sb, gdp, 0); ext4_free_inodes_set(sb, gdp, 0); ext4_itable_unused_set(sb, gdp, 0); @@ -84,7 +85,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh, } memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8); - mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb), + mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); return EXT4_INODES_PER_GROUP(sb); @@ -109,30 +110,48 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) bitmap_blk = ext4_inode_bitmap(sb, desc); bh = sb_getblk(sb, bitmap_blk); if (unlikely(!bh)) { - ext4_error(sb, __func__, - "Cannot read inode bitmap - " + ext4_error(sb, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); return NULL; } - if (buffer_uptodate(bh) && - !(desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) + if (bitmap_uptodate(bh)) return bh; lock_buffer(bh); - spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group)); + if (bitmap_uptodate(bh)) { + unlock_buffer(bh); + return bh; + } + ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { ext4_init_inode_bitmap(sb, bh, block_group, desc); + set_bitmap_uptodate(bh); set_buffer_uptodate(bh); - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_unlock_group(sb, block_group); + unlock_buffer(bh); + return bh; + } + ext4_unlock_group(sb, block_group); + if (buffer_uptodate(bh)) { + /* + * if not uninit if bh is uptodate, + * bitmap is also uptodate + */ + set_bitmap_uptodate(bh); unlock_buffer(bh); return bh; } - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + /* + * submit the buffer_head for read. We can + * safely mark the bitmap as uptodate now. + * We do it here so the bitmap uptodate bit + * get set with buffer lock held. + */ + set_bitmap_uptodate(bh); if (bh_submit_read(bh) < 0) { put_bh(bh); - ext4_error(sb, __func__, - "Cannot read inode bitmap - " + ext4_error(sb, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); return NULL; @@ -168,8 +187,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) struct ext4_group_desc *gdp; struct ext4_super_block *es; struct ext4_sb_info *sbi; - int fatal = 0, err, count; - ext4_group_t flex_group; + int fatal = 0, err, count, cleared; if (atomic_read(&inode->i_count) > 1) { printk(KERN_ERR "ext4_free_inode: inode has count=%d\n", @@ -190,15 +208,16 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) ino = inode->i_ino; ext4_debug("freeing inode %lu\n", ino); + trace_ext4_free_inode(inode); /* * Note: we must free any quota before locking the superblock, * as writing the quota to disk may need the lock as well. */ - DQUOT_INIT(inode); + dquot_initialize(inode); ext4_xattr_delete_inode(handle, inode); - DQUOT_FREE_INODE(inode); - DQUOT_DROP(inode); + dquot_free_inode(inode); + dquot_drop(inode); is_directory = S_ISDIR(inode->i_mode); @@ -207,8 +226,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) es = EXT4_SB(sb)->s_es; if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { - ext4_error(sb, "ext4_free_inode", - "reserved or nonexistent inode %lu", ino); + ext4_error(sb, "reserved or nonexistent inode %lu", ino); goto error_return; } block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); @@ -223,10 +241,10 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) goto error_return; /* Ok, now we can actually update the inode bitmaps.. */ - if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group), - bit, bitmap_bh->b_data)) - ext4_error(sb, "ext4_free_inode", - "bit already cleared for inode %lu", ino); + cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group), + bit, bitmap_bh->b_data); + if (!cleared) + ext4_error(sb, "bit already cleared for inode %lu", ino); else { gdp = ext4_get_group_desc(sb, block_group, &bh2); @@ -235,25 +253,32 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) if (fatal) goto error_return; if (gdp) { - spin_lock(sb_bgl_lock(sbi, block_group)); + ext4_lock_group(sb, block_group); count = ext4_free_inodes_count(sb, gdp) + 1; ext4_free_inodes_set(sb, gdp, count); if (is_directory) { count = ext4_used_dirs_count(sb, gdp) - 1; ext4_used_dirs_set(sb, gdp, count); + if (sbi->s_log_groups_per_flex) { + ext4_group_t f; + + f = ext4_flex_group(sbi, block_group); + atomic_dec(&sbi->s_flex_groups[f].used_dirs); + } + } gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); - spin_unlock(sb_bgl_lock(sbi, block_group)); + ext4_unlock_group(sb, block_group); percpu_counter_inc(&sbi->s_freeinodes_counter); if (is_directory) percpu_counter_dec(&sbi->s_dirs_counter); if (sbi->s_log_groups_per_flex) { - flex_group = ext4_flex_group(sbi, block_group); - spin_lock(sb_bgl_lock(sbi, flex_group)); - sbi->s_flex_groups[flex_group].free_inodes++; - spin_unlock(sb_bgl_lock(sbi, flex_group)); + ext4_group_t f; + + f = ext4_flex_group(sbi, block_group); + atomic_inc(&sbi->s_flex_groups[f].free_inodes); } } BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata"); @@ -283,7 +308,7 @@ error_return: static int find_group_dir(struct super_block *sb, struct inode *parent, ext4_group_t *best_group) { - ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t ngroups = ext4_get_groups_count(sb); unsigned int freei, avefreei; struct ext4_group_desc *desc, *best_desc = NULL; ext4_group_t group; @@ -316,11 +341,10 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *desc; - struct buffer_head *bh; struct flex_groups *flex_group = sbi->s_flex_groups; ext4_group_t parent_group = EXT4_I(parent)->i_block_group; ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group); - ext4_group_t ngroups = sbi->s_groups_count; + ext4_group_t ngroups = ext4_get_groups_count(sb); int flex_size = ext4_flex_bg_size(sbi); ext4_group_t best_flex = parent_fbg_group; int blocks_per_flex = sbi->s_blocks_per_group * flex_size; @@ -329,13 +353,13 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, ext4_group_t n_fbg_groups; ext4_group_t i; - n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >> + n_fbg_groups = (ngroups + flex_size - 1) >> sbi->s_log_groups_per_flex; find_close_to_parent: - flexbg_free_blocks = flex_group[best_flex].free_blocks; + flexbg_free_blocks = atomic_read(&flex_group[best_flex].free_blocks); flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex; - if (flex_group[best_flex].free_inodes && + if (atomic_read(&flex_group[best_flex].free_inodes) && flex_freeb_ratio > free_block_ratio) goto found_flexbg; @@ -348,30 +372,30 @@ find_close_to_parent: if (i == parent_fbg_group || i == parent_fbg_group - 1) continue; - flexbg_free_blocks = flex_group[i].free_blocks; + flexbg_free_blocks = atomic_read(&flex_group[i].free_blocks); flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex; if (flex_freeb_ratio > free_block_ratio && - flex_group[i].free_inodes) { + (atomic_read(&flex_group[i].free_inodes))) { best_flex = i; goto found_flexbg; } - if (flex_group[best_flex].free_inodes == 0 || - (flex_group[i].free_blocks > - flex_group[best_flex].free_blocks && - flex_group[i].free_inodes)) + if ((atomic_read(&flex_group[best_flex].free_inodes) == 0) || + ((atomic_read(&flex_group[i].free_blocks) > + atomic_read(&flex_group[best_flex].free_blocks)) && + atomic_read(&flex_group[i].free_inodes))) best_flex = i; } - if (!flex_group[best_flex].free_inodes || - !flex_group[best_flex].free_blocks) + if (!atomic_read(&flex_group[best_flex].free_inodes) || + !atomic_read(&flex_group[best_flex].free_blocks)) return -1; found_flexbg: for (i = best_flex * flex_size; i < ngroups && i < (best_flex + 1) * flex_size; i++) { - desc = ext4_get_group_desc(sb, i, &bh); + desc = ext4_get_group_desc(sb, i, NULL); if (ext4_free_inodes_count(sb, desc)) { *best_group = i; goto out; @@ -383,6 +407,42 @@ out: return 0; } +struct orlov_stats { + __u32 free_inodes; + __u32 free_blocks; + __u32 used_dirs; +}; + +/* + * Helper function for Orlov's allocator; returns critical information + * for a particular block group or flex_bg. If flex_size is 1, then g + * is a block group number; otherwise it is flex_bg number. + */ +void get_orlov_stats(struct super_block *sb, ext4_group_t g, + int flex_size, struct orlov_stats *stats) +{ + struct ext4_group_desc *desc; + struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups; + + if (flex_size > 1) { + stats->free_inodes = atomic_read(&flex_group[g].free_inodes); + stats->free_blocks = atomic_read(&flex_group[g].free_blocks); + stats->used_dirs = atomic_read(&flex_group[g].used_dirs); + return; + } + + desc = ext4_get_group_desc(sb, g, NULL); + if (desc) { + stats->free_inodes = ext4_free_inodes_count(sb, desc); + stats->free_blocks = ext4_free_blks_count(sb, desc); + stats->used_dirs = ext4_used_dirs_count(sb, desc); + } else { + stats->free_inodes = 0; + stats->free_blocks = 0; + stats->used_dirs = 0; + } +} + /* * Orlov's allocator for directories. * @@ -398,35 +458,37 @@ out: * it has too many directories already (max_dirs) or * it has too few free inodes left (min_inodes) or * it has too few free blocks left (min_blocks) or - * it's already running too large debt (max_debt). * Parent's group is preferred, if it doesn't satisfy these * conditions we search cyclically through the rest. If none * of the groups look good we just look for a group with more * free inodes than average (starting at parent's group). - * - * Debt is incremented each time we allocate a directory and decremented - * when we allocate an inode, within 0--255. */ -#define INODE_COST 64 -#define BLOCK_COST 256 - static int find_group_orlov(struct super_block *sb, struct inode *parent, - ext4_group_t *group) + ext4_group_t *group, int mode, + const struct qstr *qstr) { ext4_group_t parent_group = EXT4_I(parent)->i_block_group; struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_super_block *es = sbi->s_es; - ext4_group_t ngroups = sbi->s_groups_count; + ext4_group_t real_ngroups = ext4_get_groups_count(sb); int inodes_per_group = EXT4_INODES_PER_GROUP(sb); unsigned int freei, avefreei; ext4_fsblk_t freeb, avefreeb; - ext4_fsblk_t blocks_per_dir; unsigned int ndirs; - int max_debt, max_dirs, min_inodes; + int max_dirs, min_inodes; ext4_grpblk_t min_blocks; - ext4_group_t i; + ext4_group_t i, grp, g, ngroups; struct ext4_group_desc *desc; + struct orlov_stats stats; + int flex_size = ext4_flex_bg_size(sbi); + struct dx_hash_info hinfo; + + ngroups = real_ngroups; + if (flex_size > 1) { + ngroups = (real_ngroups + flex_size - 1) >> + sbi->s_log_groups_per_flex; + parent_group >>= sbi->s_log_groups_per_flex; + } freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); avefreei = freei / ngroups; @@ -435,71 +497,104 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, do_div(avefreeb, ngroups); ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); - if ((parent == sb->s_root->d_inode) || - (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL)) { + if (S_ISDIR(mode) && + ((parent == sb->s_root->d_inode) || + (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL))) { int best_ndir = inodes_per_group; - ext4_group_t grp; int ret = -1; - get_random_bytes(&grp, sizeof(grp)); + if (qstr) { + hinfo.hash_version = DX_HASH_HALF_MD4; + hinfo.seed = sbi->s_hash_seed; + ext4fs_dirhash(qstr->name, qstr->len, &hinfo); + grp = hinfo.hash; + } else + get_random_bytes(&grp, sizeof(grp)); parent_group = (unsigned)grp % ngroups; for (i = 0; i < ngroups; i++) { - grp = (parent_group + i) % ngroups; - desc = ext4_get_group_desc(sb, grp, NULL); - if (!desc || !ext4_free_inodes_count(sb, desc)) + g = (parent_group + i) % ngroups; + get_orlov_stats(sb, g, flex_size, &stats); + if (!stats.free_inodes) continue; - if (ext4_used_dirs_count(sb, desc) >= best_ndir) + if (stats.used_dirs >= best_ndir) continue; - if (ext4_free_inodes_count(sb, desc) < avefreei) + if (stats.free_inodes < avefreei) continue; - if (ext4_free_blks_count(sb, desc) < avefreeb) + if (stats.free_blocks < avefreeb) continue; - *group = grp; + grp = g; ret = 0; - best_ndir = ext4_used_dirs_count(sb, desc); + best_ndir = stats.used_dirs; + } + if (ret) + goto fallback; + found_flex_bg: + if (flex_size == 1) { + *group = grp; + return 0; + } + + /* + * We pack inodes at the beginning of the flexgroup's + * inode tables. Block allocation decisions will do + * something similar, although regular files will + * start at 2nd block group of the flexgroup. See + * ext4_ext_find_goal() and ext4_find_near(). + */ + grp *= flex_size; + for (i = 0; i < flex_size; i++) { + if (grp+i >= real_ngroups) + break; + desc = ext4_get_group_desc(sb, grp+i, NULL); + if (desc && ext4_free_inodes_count(sb, desc)) { + *group = grp+i; + return 0; + } } - if (ret == 0) - return ret; goto fallback; } - blocks_per_dir = ext4_blocks_count(es) - freeb; - do_div(blocks_per_dir, ndirs); - max_dirs = ndirs / ngroups + inodes_per_group / 16; - min_inodes = avefreei - inodes_per_group / 4; - min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb) / 4; - - max_debt = EXT4_BLOCKS_PER_GROUP(sb); - max_debt /= max_t(int, blocks_per_dir, BLOCK_COST); - if (max_debt * INODE_COST > inodes_per_group) - max_debt = inodes_per_group / INODE_COST; - if (max_debt > 255) - max_debt = 255; - if (max_debt == 0) - max_debt = 1; + min_inodes = avefreei - inodes_per_group*flex_size / 4; + if (min_inodes < 1) + min_inodes = 1; + min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb)*flex_size / 4; + + /* + * Start looking in the flex group where we last allocated an + * inode for this parent directory + */ + if (EXT4_I(parent)->i_last_alloc_group != ~0) { + parent_group = EXT4_I(parent)->i_last_alloc_group; + if (flex_size > 1) + parent_group >>= sbi->s_log_groups_per_flex; + } for (i = 0; i < ngroups; i++) { - *group = (parent_group + i) % ngroups; - desc = ext4_get_group_desc(sb, *group, NULL); - if (!desc || !ext4_free_inodes_count(sb, desc)) - continue; - if (ext4_used_dirs_count(sb, desc) >= max_dirs) + grp = (parent_group + i) % ngroups; + get_orlov_stats(sb, grp, flex_size, &stats); + if (stats.used_dirs >= max_dirs) continue; - if (ext4_free_inodes_count(sb, desc) < min_inodes) + if (stats.free_inodes < min_inodes) continue; - if (ext4_free_blks_count(sb, desc) < min_blocks) + if (stats.free_blocks < min_blocks) continue; - return 0; + goto found_flex_bg; } fallback: + ngroups = real_ngroups; + avefreei = freei / ngroups; +fallback_retry: + parent_group = EXT4_I(parent)->i_block_group; for (i = 0; i < ngroups; i++) { - *group = (parent_group + i) % ngroups; - desc = ext4_get_group_desc(sb, *group, NULL); + grp = (parent_group + i) % ngroups; + desc = ext4_get_group_desc(sb, grp, NULL); if (desc && ext4_free_inodes_count(sb, desc) && - ext4_free_inodes_count(sb, desc) >= avefreei) + ext4_free_inodes_count(sb, desc) >= avefreei) { + *group = grp; return 0; + } } if (avefreei) { @@ -508,19 +603,57 @@ fallback: * filesystems the above test can fail to find any blockgroups */ avefreei = 0; - goto fallback; + goto fallback_retry; } return -1; } static int find_group_other(struct super_block *sb, struct inode *parent, - ext4_group_t *group) + ext4_group_t *group, int mode) { ext4_group_t parent_group = EXT4_I(parent)->i_block_group; - ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t i, last, ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; - ext4_group_t i; + int flex_size = ext4_flex_bg_size(EXT4_SB(sb)); + + /* + * Try to place the inode is the same flex group as its + * parent. If we can't find space, use the Orlov algorithm to + * find another flex group, and store that information in the + * parent directory's inode information so that use that flex + * group for future allocations. + */ + if (flex_size > 1) { + int retry = 0; + + try_again: + parent_group &= ~(flex_size-1); + last = parent_group + flex_size; + if (last > ngroups) + last = ngroups; + for (i = parent_group; i < last; i++) { + desc = ext4_get_group_desc(sb, i, NULL); + if (desc && ext4_free_inodes_count(sb, desc)) { + *group = i; + return 0; + } + } + if (!retry && EXT4_I(parent)->i_last_alloc_group != ~0) { + retry = 1; + parent_group = EXT4_I(parent)->i_last_alloc_group; + goto try_again; + } + /* + * If this didn't work, use the Orlov search algorithm + * to find a new flex group; we pass in the mode to + * avoid the topdir algorithms. + */ + *group = parent_group + flex_size; + if (*group > ngroups) + *group = 0; + return find_group_orlov(sb, parent, group, mode, 0); + } /* * Try to place the inode in its parent directory @@ -573,6 +706,83 @@ static int find_group_other(struct super_block *sb, struct inode *parent, } /* + * claim the inode from the inode bitmap. If the group + * is uninit we need to take the groups's ext4_group_lock + * and clear the uninit flag. The inode bitmap update + * and group desc uninit flag clear should be done + * after holding ext4_group_lock so that ext4_read_inode_bitmap + * doesn't race with the ext4_claim_inode + */ +static int ext4_claim_inode(struct super_block *sb, + struct buffer_head *inode_bitmap_bh, + unsigned long ino, ext4_group_t group, int mode) +{ + int free = 0, retval = 0, count; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); + + ext4_lock_group(sb, group); + if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) { + /* not a free inode */ + retval = 1; + goto err_ret; + } + ino++; + if ((group == 0 && ino < EXT4_FIRST_INO(sb)) || + ino > EXT4_INODES_PER_GROUP(sb)) { + ext4_unlock_group(sb, group); + ext4_error(sb, "reserved inode or inode > inodes count - " + "block_group = %u, inode=%lu", group, + ino + group * EXT4_INODES_PER_GROUP(sb)); + return 1; + } + /* If we didn't allocate from within the initialized part of the inode + * table then we need to initialize up to this inode. */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) { + + if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { + gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT); + /* When marking the block group with + * ~EXT4_BG_INODE_UNINIT we don't want to depend + * on the value of bg_itable_unused even though + * mke2fs could have initialized the same for us. + * Instead we calculated the value below + */ + + free = 0; + } else { + free = EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp); + } + + /* + * Check the relative inode number against the last used + * relative inode number in this group. if it is greater + * we need to update the bg_itable_unused count + * + */ + if (ino > free) + ext4_itable_unused_set(sb, gdp, + (EXT4_INODES_PER_GROUP(sb) - ino)); + } + count = ext4_free_inodes_count(sb, gdp) - 1; + ext4_free_inodes_set(sb, gdp, count); + if (S_ISDIR(mode)) { + count = ext4_used_dirs_count(sb, gdp) + 1; + ext4_used_dirs_set(sb, gdp, count); + if (sbi->s_log_groups_per_flex) { + ext4_group_t f = ext4_flex_group(sbi, group); + + atomic_inc(&sbi->s_flex_groups[f].used_dirs); + } + } + gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); +err_ret: + ext4_unlock_group(sb, group); + return retval; +} + +/* * There are two policies for allocating an inode. If the new inode is * a directory, then a forward search is made for a block group with both * free space and a low directory-to-inode ratio; if that fails, then of @@ -582,22 +792,23 @@ static int find_group_other(struct super_block *sb, struct inode *parent, * For other inodes, search forward from the parent directory's block * group to find a free inode. */ -struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) +struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode, + const struct qstr *qstr, __u32 goal) { struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; struct buffer_head *group_desc_bh; - ext4_group_t group = 0; + ext4_group_t ngroups, group = 0; unsigned long ino = 0; struct inode *inode; struct ext4_group_desc *gdp = NULL; - struct ext4_super_block *es; struct ext4_inode_info *ei; struct ext4_sb_info *sbi; - int ret2, err = 0, count; + int ret2, err = 0; struct inode *ret; ext4_group_t i; int free = 0; + static int once = 1; ext4_group_t flex_group; /* Cannot create files in a deleted directory */ @@ -605,16 +816,35 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) return ERR_PTR(-EPERM); sb = dir->i_sb; + ngroups = ext4_get_groups_count(sb); + trace_ext4_request_inode(dir, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT4_I(inode); - sbi = EXT4_SB(sb); - es = sbi->s_es; - if (sbi->s_log_groups_per_flex) { + if (!goal) + goal = sbi->s_inode_goal; + + if (goal && goal <= le32_to_cpu(sbi->s_es->s_inodes_count)) { + group = (goal - 1) / EXT4_INODES_PER_GROUP(sb); + ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb); + ret2 = 0; + goto got_group; + } + + if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) { ret2 = find_group_flex(sb, dir, &group); + if (ret2 == -1) { + ret2 = find_group_other(sb, dir, &group, mode); + if (ret2 == 0 && once) { + once = 0; + printk(KERN_NOTICE "ext4: find_group_flex " + "failed, fallback succeeded dir %lu\n", + dir->i_ino); + } + } goto got_group; } @@ -622,16 +852,17 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) if (test_opt(sb, OLDALLOC)) ret2 = find_group_dir(sb, dir, &group); else - ret2 = find_group_orlov(sb, dir, &group); + ret2 = find_group_orlov(sb, dir, &group, mode, qstr); } else - ret2 = find_group_other(sb, dir, &group); + ret2 = find_group_other(sb, dir, &group, mode); got_group: + EXT4_I(dir)->i_last_alloc_group = group; err = -ENOSPC; if (ret2 == -1) goto out; - for (i = 0; i < sbi->s_groups_count; i++) { + for (i = 0; i < ngroups; i++, ino = 0) { err = -EIO; gdp = ext4_get_group_desc(sb, group, &group_desc_bh); @@ -643,8 +874,6 @@ got_group: if (!inode_bitmap_bh) goto fail; - ino = 0; - repeat_in_this_group: ino = ext4_find_next_zero_bit((unsigned long *) inode_bitmap_bh->b_data, @@ -658,20 +887,28 @@ repeat_in_this_group: if (err) goto fail; - if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group), - ino, inode_bitmap_bh->b_data)) { + BUFFER_TRACE(group_desc_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, + group_desc_bh); + if (err) + goto fail; + if (!ext4_claim_inode(sb, inode_bitmap_bh, + ino, group, mode)) { /* we won it */ BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, - inode, + NULL, inode_bitmap_bh); if (err) goto fail; + /* zero bit is inode number 1*/ + ino++; goto got; } /* we lost it */ ext4_handle_release_buffer(handle, inode_bitmap_bh); + ext4_handle_release_buffer(handle, group_desc_bh); if (++ino < EXT4_INODES_PER_GROUP(sb)) goto repeat_in_this_group; @@ -684,29 +921,13 @@ repeat_in_this_group: * group descriptor metadata has not yet been updated. * So we just go onto the next blockgroup. */ - if (++group == sbi->s_groups_count) + if (++group == ngroups) group = 0; } err = -ENOSPC; goto out; got: - ino++; - if ((group == 0 && ino < EXT4_FIRST_INO(sb)) || - ino > EXT4_INODES_PER_GROUP(sb)) { - ext4_error(sb, __func__, - "reserved inode or inode > inodes count - " - "block_group = %u, inode=%lu", group, - ino + group * EXT4_INODES_PER_GROUP(sb)); - err = -EIO; - goto fail; - } - - BUFFER_TRACE(group_desc_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, group_desc_bh); - if (err) - goto fail; - /* We may have to initialize the block bitmap if it isn't already */ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { @@ -721,7 +942,7 @@ got: } free = 0; - spin_lock(sb_bgl_lock(sbi, group)); + ext4_lock_group(sb, group); /* recheck and clear flag under lock if we still need to */ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { free = ext4_free_blocks_after_init(sb, group, gdp); @@ -730,7 +951,7 @@ got: gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); } - spin_unlock(sb_bgl_lock(sbi, group)); + ext4_unlock_group(sb, group); /* Don't need to dirty bitmap block if we didn't change it */ if (free) { @@ -743,49 +964,10 @@ got: if (err) goto fail; } - - spin_lock(sb_bgl_lock(sbi, group)); - /* If we didn't allocate from within the initialized part of the inode - * table then we need to initialize up to this inode. */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) { - if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { - gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT); - - /* When marking the block group with - * ~EXT4_BG_INODE_UNINIT we don't want to depend - * on the value of bg_itable_unused even though - * mke2fs could have initialized the same for us. - * Instead we calculated the value below - */ - - free = 0; - } else { - free = EXT4_INODES_PER_GROUP(sb) - - ext4_itable_unused_count(sb, gdp); - } - - /* - * Check the relative inode number against the last used - * relative inode number in this group. if it is greater - * we need to update the bg_itable_unused count - * - */ - if (ino > free) - ext4_itable_unused_set(sb, gdp, - (EXT4_INODES_PER_GROUP(sb) - ino)); - } - - count = ext4_free_inodes_count(sb, gdp) - 1; - ext4_free_inodes_set(sb, gdp, count); - if (S_ISDIR(mode)) { - count = ext4_used_dirs_count(sb, gdp) + 1; - ext4_used_dirs_set(sb, gdp, count); - } - gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); - spin_unlock(sb_bgl_lock(sbi, group)); BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh); - if (err) goto fail; + if (err) + goto fail; percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) @@ -794,21 +976,15 @@ got: if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); - spin_lock(sb_bgl_lock(sbi, flex_group)); - sbi->s_flex_groups[flex_group].free_inodes--; - spin_unlock(sb_bgl_lock(sbi, flex_group)); + atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes); } - inode->i_uid = current_fsuid(); - if (test_opt(sb, GRPID)) + if (test_opt(sb, GRPID)) { + inode->i_mode = mode; + inode->i_uid = current_fsuid(); inode->i_gid = dir->i_gid; - else if (dir->i_mode & S_ISGID) { - inode->i_gid = dir->i_gid; - if (S_ISDIR(mode)) - mode |= S_ISGID; } else - inode->i_gid = current_fsgid(); - inode->i_mode = mode; + inode_init_owner(inode, dir, mode); inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); /* This is the optimal IO size (for stat), not the fs block size */ @@ -821,19 +997,16 @@ got: ei->i_disksize = 0; /* - * Don't inherit extent flag from directory. We set extent flag on - * newly created directory and file only if -o extent mount option is - * specified + * Don't inherit extent flag from directory, amongst others. We set + * extent flag on newly created directory and file only if -o extent + * mount option is specified */ - ei->i_flags = EXT4_I(dir)->i_flags & ~(EXT4_INDEX_FL|EXT4_EXTENTS_FL); - if (S_ISLNK(mode)) - ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL); - /* dirsync only applies to directories */ - if (!S_ISDIR(mode)) - ei->i_flags &= ~EXT4_DIRSYNC_FL; + ei->i_flags = + ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED); ei->i_file_acl = 0; ei->i_dtime = 0; ei->i_block_group = group; + ei->i_last_alloc_group = ~0; ext4_set_inode_flags(inode); if (IS_DIRSYNC(inode)) @@ -846,15 +1019,16 @@ got: inode->i_generation = sbi->s_next_generation++; spin_unlock(&sbi->s_next_gen_lock); - ei->i_state = EXT4_STATE_NEW; + ei->i_state_flags = 0; + ext4_set_inode_state(inode, EXT4_STATE_NEW); ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize; ret = inode; - if (DQUOT_ALLOC_INODE(inode)) { - err = -EDQUOT; + dquot_initialize(inode); + err = dquot_alloc_inode(inode); + if (err) goto fail_drop; - } err = ext4_init_acl(handle, inode, dir); if (err) @@ -864,7 +1038,7 @@ got: if (err) goto fail_free_drop; - if (test_opt(sb, EXTENTS)) { + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { /* set extent flag only for directory, file and normal symlink*/ if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) { EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL; @@ -879,6 +1053,7 @@ got: } ext4_debug("allocating inode %lu\n", inode->i_ino); + trace_ext4_allocate_inode(inode, dir, mode); goto really_out; fail: ext4_std_error(sb, err); @@ -890,10 +1065,10 @@ really_out: return ret; fail_free_drop: - DQUOT_FREE_INODE(inode); + dquot_free_inode(inode); fail_drop: - DQUOT_DROP(inode); + dquot_drop(inode); inode->i_flags |= S_NOQUOTA; inode->i_nlink = 0; unlock_new_inode(inode); @@ -914,8 +1089,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) /* Error cases - e2fsck has already cleaned up for us */ if (ino > max_ino) { - ext4_warning(sb, __func__, - "bad orphan ino %lu! e2fsck was run?", ino); + ext4_warning(sb, "bad orphan ino %lu! e2fsck was run?", ino); goto error; } @@ -923,8 +1097,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); if (!bitmap_bh) { - ext4_warning(sb, __func__, - "inode bitmap error for orphan %lu", ino); + ext4_warning(sb, "inode bitmap error for orphan %lu", ino); goto error; } @@ -956,8 +1129,7 @@ iget_failed: err = PTR_ERR(inode); inode = NULL; bad_orphan: - ext4_warning(sb, __func__, - "bad orphan inode %lu! e2fsck was run?", ino); + ext4_warning(sb, "bad orphan inode %lu! e2fsck was run?", ino); printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n", bit, (unsigned long long)bitmap_bh->b_blocknr, ext4_test_bit(bit, bitmap_bh->b_data)); @@ -983,7 +1155,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) { unsigned long desc_count; struct ext4_group_desc *gdp; - ext4_group_t i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); #ifdef EXT4FS_DEBUG struct ext4_super_block *es; unsigned long bitmap_count, x; @@ -993,7 +1165,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) desc_count = 0; bitmap_count = 0; gdp = NULL; - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; @@ -1005,7 +1177,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n", - i, ext4_free_inodes_count(sb, gdp), x); + (unsigned long) i, ext4_free_inodes_count(sb, gdp), x); bitmap_count += x; } brelse(bitmap_bh); @@ -1015,7 +1187,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) return desc_count; #else desc_count = 0; - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; @@ -1030,9 +1202,9 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) unsigned long ext4_count_dirs(struct super_block * sb) { unsigned long count = 0; - ext4_group_t i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue;