/* * linux/fs/ext3/ialloc.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * BSD ufs-inspired inode and directory allocation by * Stephen Tweedie (sct@redhat.com), 1993 * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/time.h>#include <linux/fs.h>#include <linux/jbd.h>#include <linux/ext3_fs.h>#include <linux/ext3_jbd.h>#include <linux/stat.h>#include <linux/string.h>#include <linux/quotaops.h>#include <linux/buffer_head.h>#include <linux/random.h>#include <linux/bitops.h>#include <trace/events/ext3.h> #include <asm/byteorder.h> #include "xattr.h"#include "acl.h" /* * ialloc.c contains the inodes allocation and deallocation routines */ /* * The free inodes are managed by bitmaps. A file system contains several * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap * block for inodes, N blocks for the inode table and data blocks. * * The file system contains group descriptors which are located after the * super block. Each descriptor contains the number of the bitmap block and * the free blocks count in the block. */ /* * Read the inode allocation bitmap for a given block_group, reading * into the specified slot in the superblock's bitmap cache. * * Return buffer_head of bitmap on success or NULL. */static struct buffer_head *read_inode_bitmap(struct super_block * sb, unsigned long block_group){ struct ext3_group_desc *desc; struct buffer_head *bh = NULL; desc = ext3_get_group_desc(sb, block_group, NULL); if (!desc) goto error_out; bh = sb_bread(sb, le32_to_cpu(desc->bg_inode_bitmap)); if (!bh) ext3_error(sb, "read_inode_bitmap", "Cannot read inode bitmap - " "block_group = %lu, inode_bitmap = %u", block_group, le32_to_cpu(desc->bg_inode_bitmap));error_out: return bh;} /* * NOTE! When we get the inode, we're the only people * that have access to it, and as such there are no * race conditions we have to worry about. The inode * is not on the hash-lists, and it cannot be reached * through the filesystem because the directory entry * has been deleted earlier. * * HOWEVER: we must make sure that we get no aliases, * which means that we have to call "clear_inode()" * _before_ we mark the inode not in use in the inode * bitmaps. Otherwise a newly created file might use * the same inode number (not actually the same pointer * though), and then we'd have two inodes sharing the * same inode number and space on the harddisk. */void ext3_free_inode (handle_t *handle, struct inode * inode){ struct super_block * sb = inode->i_sb; int is_directory; unsigned long ino; struct buffer_head *bitmap_bh = NULL; struct buffer_head *bh2; unsigned long block_group; unsigned long bit; struct ext3_group_desc * gdp; struct ext3_super_block * es; struct ext3_sb_info *sbi; int fatal = 0, err; if (atomic_read(&inode->i_count) > 1) { printk ("ext3_free_inode: inode has count=%d\n", atomic_read(&inode->i_count)); return; } if (inode->i_nlink) { printk ("ext3_free_inode: inode has nlink=%d\n", inode->i_nlink); return; } if (!sb) { printk("ext3_free_inode: inode on nonexistent device\n"); return; } sbi = EXT3_SB(sb); ino = inode->i_ino; ext3_debug ("freeing inode %lu\n", ino); trace_ext3_free_inode(inode); is_directory = S_ISDIR(inode->i_mode); es = EXT3_SB(sb)->s_es; if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { ext3_error (sb, "ext3_free_inode", "reserved or nonexistent inode %lu", ino); goto error_return; } block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT3_INODES_PER_GROUP(sb); bitmap_bh = read_inode_bitmap(sb, block_group); if (!bitmap_bh) goto error_return; BUFFER_TRACE(bitmap_bh, "get_write_access"); fatal = ext3_journal_get_write_access(handle, bitmap_bh); if (fatal) goto error_return; /* Ok, now we can actually update the inode bitmaps.. */ if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group), bit, bitmap_bh->b_data)) ext3_error (sb, "ext3_free_inode", "bit already cleared for inode %lu", ino); else { gdp = ext3_get_group_desc (sb, block_group, &bh2); BUFFER_TRACE(bh2, "get_write_access"); fatal = ext3_journal_get_write_access(handle, bh2); if (fatal) goto error_return; if (gdp) { spin_lock(sb_bgl_lock(sbi, block_group)); le16_add_cpu(&gdp->bg_free_inodes_count, 1); if (is_directory) le16_add_cpu(&gdp->bg_used_dirs_count, -1); spin_unlock(sb_bgl_lock(sbi, block_group)); percpu_counter_inc(&sbi->s_freeinodes_counter); if (is_directory) percpu_counter_dec(&sbi->s_dirs_counter); } BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, bh2); if (!fatal) fatal = err; } BUFFER_TRACE(bitmap_bh, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, bitmap_bh); if (!fatal) fatal = err; error_return: brelse(bitmap_bh); ext3_std_error(sb, fatal);} /* * Orlov's allocator for directories. * * We always try to spread first-level directories. * * If there are blockgroups with both free inodes and free blocks counts * not worse than average we return one with smallest directory count. * Otherwise we simply return a random group. * * For the rest rules look so: * * It's OK to put directory into a group unless * 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){ int parent_group = EXT3_I(parent)->i_block_group; struct ext3_sb_info *sbi = EXT3_SB(sb); struct ext3_super_block *es = sbi->s_es; int ngroups = sbi->s_groups_count; int inodes_per_group = EXT3_INODES_PER_GROUP(sb); unsigned int freei, avefreei; ext3_fsblk_t freeb, avefreeb; ext3_fsblk_t blocks_per_dir; unsigned int ndirs; int max_debt, max_dirs, min_inodes; ext3_grpblk_t min_blocks; int group = -1, i; struct ext3_group_desc *desc; freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); avefreei = freei / ngroups; freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter); avefreeb = freeb / ngroups; ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); if ((parent == sb->s_root->d_inode) || (EXT3_I(parent)->i_flags & EXT3_TOPDIR_FL)) { int best_ndir = inodes_per_group; int best_group = -1; get_random_bytes(&group, sizeof(group)); parent_group = (unsigned)group % ngroups; for (i = 0; i < ngroups; i++) { group = (parent_group + i) % ngroups; desc = ext3_get_group_desc (sb, group, NULL); if (!desc || !desc->bg_free_inodes_count) continue; if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir) continue; if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) continue; if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb) continue; best_group = group; best_ndir = le16_to_cpu(desc->bg_used_dirs_count); } if (best_group >= 0) return best_group; goto fallback; } blocks_per_dir = (le32_to_cpu(es->s_blocks_count) - freeb) / ndirs; max_dirs = ndirs / ngroups + inodes_per_group / 16; min_inodes = avefreei - inodes_per_group / 4; min_blocks = avefreeb - EXT3_BLOCKS_PER_GROUP(sb) / 4; max_debt = EXT3_BLOCKS_PER_GROUP(sb) / max(blocks_per_dir, (ext3_fsblk_t)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; for (i = 0; i < ngroups; i++) { group = (parent_group + i) % ngroups; desc = ext3_get_group_desc (sb, group, NULL); if (!desc || !desc->bg_free_inodes_count) continue; if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs) continue; if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes) continue; if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks) continue; return group; } fallback: for (i = 0; i < ngroups; i++) { group = (parent_group + i) % ngroups; desc = ext3_get_group_desc (sb, group, NULL); if (!desc || !desc->bg_free_inodes_count) continue; if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei) return group; } if (avefreei) { /* * The free-inodes counter is approximate, and for really small * filesystems the above test can fail to find any blockgroups */ avefreei = 0; goto fallback; } return -1;} static int find_group_other(struct super_block *sb, struct inode *parent){ int parent_group = EXT3_I(parent)->i_block_group; int ngroups = EXT3_SB(sb)->s_groups_count; struct ext3_group_desc *desc; int group, i; /* * Try to place the inode in its parent directory */ group = parent_group; desc = ext3_get_group_desc (sb, group, NULL); if (desc && le16_to_cpu(desc->bg_free_inodes_count) && le16_to_cpu(desc->bg_free_blocks_count)) return group; /* * We're going to place this inode in a different blockgroup from its * parent. We want to cause files in a common directory to all land in * the same blockgroup. But we want files which are in a different * directory which shares a blockgroup with our parent to land in a * different blockgroup. * * So add our directory's i_ino into the starting point for the hash. */ group = (group + parent->i_ino) % ngroups; /* * Use a quadratic hash to find a group with a free inode and some free * blocks. */ for (i = 1; i < ngroups; i <<= 1) { group += i; if (group >= ngroups) group -= ngroups; desc = ext3_get_group_desc (sb, group, NULL); if (desc && le16_to_cpu(desc->bg_free_inodes_count) && le16_to_cpu(desc->bg_free_blocks_count)) return group; } /* * That failed: try linear search for a free inode, even if that group * has no free blocks. */ group = parent_group; for (i = 0; i < ngroups; i++) { if (++group >= ngroups) group = 0; desc = ext3_get_group_desc (sb, group, NULL); if (desc && le16_to_cpu(desc->bg_free_inodes_count)) return group; } return -1;} /* * 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 * the groups with above-average free space, that group with the fewest * directories already is chosen. * * For other inodes, search forward from the parent directory's block * group to find a free inode. */struct inode *ext3_new_inode(handle_t *handle, struct inode * dir, const struct qstr *qstr, int mode){ struct super_block *sb; struct buffer_head *bitmap_bh = NULL; struct buffer_head *bh2; int group; unsigned long ino = 0; struct inode * inode; struct ext3_group_desc * gdp = NULL; struct ext3_super_block * es; struct ext3_inode_info *ei; struct ext3_sb_info *sbi; int err = 0; struct inode *ret; int i; /* Cannot create files in a deleted directory */ if (!dir || !dir->i_nlink) return ERR_PTR(-EPERM); sb = dir->i_sb; trace_ext3_request_inode(dir, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT3_I(inode); sbi = EXT3_SB(sb); es = sbi->s_es; if (S_ISDIR(mode)) group = find_group_orlov(sb, dir); else group = find_group_other(sb, dir); err = -ENOSPC; if (group == -1) goto out; for (i = 0; i < sbi->s_groups_count; i++) { err = -EIO; gdp = ext3_get_group_desc(sb, group, &bh2); if (!gdp) goto fail; brelse(bitmap_bh); bitmap_bh = read_inode_bitmap(sb, group); if (!bitmap_bh) goto fail; ino = 0; repeat_in_this_group: ino = ext3_find_next_zero_bit((unsigned long *) bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino); if (ino < EXT3_INODES_PER_GROUP(sb)) { BUFFER_TRACE(bitmap_bh, "get_write_access"); err = ext3_journal_get_write_access(handle, bitmap_bh); if (err) goto fail; if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group), ino, bitmap_bh->b_data)) { /* we won it */ BUFFER_TRACE(bitmap_bh, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, bitmap_bh); if (err) goto fail; goto got; } /* we lost it */ journal_release_buffer(handle, bitmap_bh); if (++ino < EXT3_INODES_PER_GROUP(sb)) goto repeat_in_this_group; } /* * This case is possible in concurrent environment. It is very * rare. We cannot repeat the find_group_xxx() call because * that will simply return the same blockgroup, because the * group descriptor metadata has not yet been updated. * So we just go onto the next blockgroup. */ if (++group == sbi->s_groups_count) group = 0; } err = -ENOSPC; goto out; got: ino += group * EXT3_INODES_PER_GROUP(sb) + 1; if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { ext3_error (sb, "ext3_new_inode", "reserved inode or inode > inodes count - " "block_group = %d, inode=%lu", group, ino); err = -EIO; goto fail; } BUFFER_TRACE(bh2, "get_write_access"); err = ext3_journal_get_write_access(handle, bh2); if (err) goto fail; spin_lock(sb_bgl_lock(sbi, group)); le16_add_cpu(&gdp->bg_free_inodes_count, -1); if (S_ISDIR(mode)) { le16_add_cpu(&gdp->bg_used_dirs_count, 1); } spin_unlock(sb_bgl_lock(sbi, group)); BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, bh2); if (err) goto fail; percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter); if (test_opt(sb, GRPID)) { inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = dir->i_gid; } else inode_init_owner(inode, dir, mode);Lines 1–500 of 729. Load more
/* * linux/fs/ext3/ialloc.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * BSD ufs-inspired inode and directory allocation by * Stephen Tweedie (sct@redhat.com), 1993 * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd.h> #include <linux/ext3_fs.h> #include <linux/ext3_jbd.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/quotaops.h> #include <linux/buffer_head.h> #include <linux/random.h> #include <linux/bitops.h> #include <trace/events/ext3.h> #include <asm/byteorder.h> #include "xattr.h" #include "acl.h" /* * ialloc.c contains the inodes allocation and deallocation routines */ /* * The free inodes are managed by bitmaps. A file system contains several * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap * block for inodes, N blocks for the inode table and data blocks. * * The file system contains group descriptors which are located after the * super block. Each descriptor contains the number of the bitmap block and * the free blocks count in the block. */ /* * Read the inode allocation bitmap for a given block_group, reading * into the specified slot in the superblock's bitmap cache. * * Return buffer_head of bitmap on success or NULL. */ static struct buffer_head * read_inode_bitmap(struct super_block * sb, unsigned long block_group) { struct ext3_group_desc *desc; struct buffer_head *bh = NULL; desc = ext3_get_group_desc(sb, block_group, NULL); if (!desc) goto error_out; bh = sb_bread(sb, le32_to_cpu(desc->bg_inode_bitmap)); if (!bh) ext3_error(sb, "read_inode_bitmap", "Cannot read inode bitmap - " "block_group = %lu, inode_bitmap = %u", block_group, le32_to_cpu(desc->bg_inode_bitmap)); error_out: return bh; } /* * NOTE! When we get the inode, we're the only people * that have access to it, and as such there are no * race conditions we have to worry about. The inode * is not on the hash-lists, and it cannot be reached * through the filesystem because the directory entry * has been deleted earlier. * * HOWEVER: we must make sure that we get no aliases, * which means that we have to call "clear_inode()" * _before_ we mark the inode not in use in the inode * bitmaps. Otherwise a newly created file might use * the same inode number (not actually the same pointer * though), and then we'd have two inodes sharing the * same inode number and space on the harddisk. */ void ext3_free_inode (handle_t *handle, struct inode * inode) { struct super_block * sb = inode->i_sb; int is_directory; unsigned long ino; struct buffer_head *bitmap_bh = NULL; struct buffer_head *bh2; unsigned long block_group; unsigned long bit; struct ext3_group_desc * gdp; struct ext3_super_block * es; struct ext3_sb_info *sbi; int fatal = 0, err; if (atomic_read(&inode->i_count) > 1) { printk ("ext3_free_inode: inode has count=%d\n", atomic_read(&inode->i_count)); return; } if (inode->i_nlink) { printk ("ext3_free_inode: inode has nlink=%d\n", inode->i_nlink); return; } if (!sb) { printk("ext3_free_inode: inode on nonexistent device\n"); return; } sbi = EXT3_SB(sb); ino = inode->i_ino; ext3_debug ("freeing inode %lu\n", ino); trace_ext3_free_inode(inode); is_directory = S_ISDIR(inode->i_mode); es = EXT3_SB(sb)->s_es; if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { ext3_error (sb, "ext3_free_inode", "reserved or nonexistent inode %lu", ino); goto error_return; } block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT3_INODES_PER_GROUP(sb); bitmap_bh = read_inode_bitmap(sb, block_group); if (!bitmap_bh) goto error_return; BUFFER_TRACE(bitmap_bh, "get_write_access"); fatal = ext3_journal_get_write_access(handle, bitmap_bh); if (fatal) goto error_return; /* Ok, now we can actually update the inode bitmaps.. */ if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group), bit, bitmap_bh->b_data)) ext3_error (sb, "ext3_free_inode", "bit already cleared for inode %lu", ino); else { gdp = ext3_get_group_desc (sb, block_group, &bh2); BUFFER_TRACE(bh2, "get_write_access"); fatal = ext3_journal_get_write_access(handle, bh2); if (fatal) goto error_return; if (gdp) { spin_lock(sb_bgl_lock(sbi, block_group)); le16_add_cpu(&gdp->bg_free_inodes_count, 1); if (is_directory) le16_add_cpu(&gdp->bg_used_dirs_count, -1); spin_unlock(sb_bgl_lock(sbi, block_group)); percpu_counter_inc(&sbi->s_freeinodes_counter); if (is_directory) percpu_counter_dec(&sbi->s_dirs_counter); } BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, bh2); if (!fatal) fatal = err; } BUFFER_TRACE(bitmap_bh, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, bitmap_bh); if (!fatal) fatal = err; error_return: brelse(bitmap_bh); ext3_std_error(sb, fatal); } /* * Orlov's allocator for directories. * * We always try to spread first-level directories. * * If there are blockgroups with both free inodes and free blocks counts * not worse than average we return one with smallest directory count. * Otherwise we simply return a random group. * * For the rest rules look so: * * It's OK to put directory into a group unless * 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) { int parent_group = EXT3_I(parent)->i_block_group; struct ext3_sb_info *sbi = EXT3_SB(sb); struct ext3_super_block *es = sbi->s_es; int ngroups = sbi->s_groups_count; int inodes_per_group = EXT3_INODES_PER_GROUP(sb); unsigned int freei, avefreei; ext3_fsblk_t freeb, avefreeb; ext3_fsblk_t blocks_per_dir; unsigned int ndirs; int max_debt, max_dirs, min_inodes; ext3_grpblk_t min_blocks; int group = -1, i; struct ext3_group_desc *desc; freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); avefreei = freei / ngroups; freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter); avefreeb = freeb / ngroups; ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); if ((parent == sb->s_root->d_inode) || (EXT3_I(parent)->i_flags & EXT3_TOPDIR_FL)) { int best_ndir = inodes_per_group; int best_group = -1; get_random_bytes(&group, sizeof(group)); parent_group = (unsigned)group % ngroups; for (i = 0; i < ngroups; i++) { group = (parent_group + i) % ngroups; desc = ext3_get_group_desc (sb, group, NULL); if (!desc || !desc->bg_free_inodes_count) continue; if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir) continue; if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) continue; if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb) continue; best_group = group; best_ndir = le16_to_cpu(desc->bg_used_dirs_count); } if (best_group >= 0) return best_group; goto fallback; } blocks_per_dir = (le32_to_cpu(es->s_blocks_count) - freeb) / ndirs; max_dirs = ndirs / ngroups + inodes_per_group / 16; min_inodes = avefreei - inodes_per_group / 4; min_blocks = avefreeb - EXT3_BLOCKS_PER_GROUP(sb) / 4; max_debt = EXT3_BLOCKS_PER_GROUP(sb) / max(blocks_per_dir, (ext3_fsblk_t)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; for (i = 0; i < ngroups; i++) { group = (parent_group + i) % ngroups; desc = ext3_get_group_desc (sb, group, NULL); if (!desc || !desc->bg_free_inodes_count) continue; if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs) continue; if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes) continue; if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks) continue; return group; } fallback: for (i = 0; i < ngroups; i++) { group = (parent_group + i) % ngroups; desc = ext3_get_group_desc (sb, group, NULL); if (!desc || !desc->bg_free_inodes_count) continue; if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei) return group; } if (avefreei) { /* * The free-inodes counter is approximate, and for really small * filesystems the above test can fail to find any blockgroups */ avefreei = 0; goto fallback; } return -1; } static int find_group_other(struct super_block *sb, struct inode *parent) { int parent_group = EXT3_I(parent)->i_block_group; int ngroups = EXT3_SB(sb)->s_groups_count; struct ext3_group_desc *desc; int group, i; /* * Try to place the inode in its parent directory */ group = parent_group; desc = ext3_get_group_desc (sb, group, NULL); if (desc && le16_to_cpu(desc->bg_free_inodes_count) && le16_to_cpu(desc->bg_free_blocks_count)) return group; /* * We're going to place this inode in a different blockgroup from its * parent. We want to cause files in a common directory to all land in * the same blockgroup. But we want files which are in a different * directory which shares a blockgroup with our parent to land in a * different blockgroup. * * So add our directory's i_ino into the starting point for the hash. */ group = (group + parent->i_ino) % ngroups; /* * Use a quadratic hash to find a group with a free inode and some free * blocks. */ for (i = 1; i < ngroups; i <<= 1) { group += i; if (group >= ngroups) group -= ngroups; desc = ext3_get_group_desc (sb, group, NULL); if (desc && le16_to_cpu(desc->bg_free_inodes_count) && le16_to_cpu(desc->bg_free_blocks_count)) return group; } /* * That failed: try linear search for a free inode, even if that group * has no free blocks. */ group = parent_group; for (i = 0; i < ngroups; i++) { if (++group >= ngroups) group = 0; desc = ext3_get_group_desc (sb, group, NULL); if (desc && le16_to_cpu(desc->bg_free_inodes_count)) return group; } return -1; } /* * 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 * the groups with above-average free space, that group with the fewest * directories already is chosen. * * For other inodes, search forward from the parent directory's block * group to find a free inode. */ struct inode *ext3_new_inode(handle_t *handle, struct inode * dir, const struct qstr *qstr, int mode) { struct super_block *sb; struct buffer_head *bitmap_bh = NULL; struct buffer_head *bh2; int group; unsigned long ino = 0; struct inode * inode; struct ext3_group_desc * gdp = NULL; struct ext3_super_block * es; struct ext3_inode_info *ei; struct ext3_sb_info *sbi; int err = 0; struct inode *ret; int i; /* Cannot create files in a deleted directory */ if (!dir || !dir->i_nlink) return ERR_PTR(-EPERM); sb = dir->i_sb; trace_ext3_request_inode(dir, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT3_I(inode); sbi = EXT3_SB(sb); es = sbi->s_es; if (S_ISDIR(mode)) group = find_group_orlov(sb, dir); else group = find_group_other(sb, dir); err = -ENOSPC; if (group == -1) goto out; for (i = 0; i < sbi->s_groups_count; i++) { err = -EIO; gdp = ext3_get_group_desc(sb, group, &bh2); if (!gdp) goto fail; brelse(bitmap_bh); bitmap_bh = read_inode_bitmap(sb, group); if (!bitmap_bh) goto fail; ino = 0; repeat_in_this_group: ino = ext3_find_next_zero_bit((unsigned long *) bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino); if (ino < EXT3_INODES_PER_GROUP(sb)) { BUFFER_TRACE(bitmap_bh, "get_write_access"); err = ext3_journal_get_write_access(handle, bitmap_bh); if (err) goto fail; if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group), ino, bitmap_bh->b_data)) { /* we won it */ BUFFER_TRACE(bitmap_bh, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, bitmap_bh); if (err) goto fail; goto got; } /* we lost it */ journal_release_buffer(handle, bitmap_bh); if (++ino < EXT3_INODES_PER_GROUP(sb)) goto repeat_in_this_group; } /* * This case is possible in concurrent environment. It is very * rare. We cannot repeat the find_group_xxx() call because * that will simply return the same blockgroup, because the * group descriptor metadata has not yet been updated. * So we just go onto the next blockgroup. */ if (++group == sbi->s_groups_count) group = 0; } err = -ENOSPC; goto out; got: ino += group * EXT3_INODES_PER_GROUP(sb) + 1; if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { ext3_error (sb, "ext3_new_inode", "reserved inode or inode > inodes count - " "block_group = %d, inode=%lu", group, ino); err = -EIO; goto fail; } BUFFER_TRACE(bh2, "get_write_access"); err = ext3_journal_get_write_access(handle, bh2); if (err) goto fail; spin_lock(sb_bgl_lock(sbi, group)); le16_add_cpu(&gdp->bg_free_inodes_count, -1); if (S_ISDIR(mode)) { le16_add_cpu(&gdp->bg_used_dirs_count, 1); } spin_unlock(sb_bgl_lock(sbi, group)); BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, bh2); if (err) goto fail; percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter); if (test_opt(sb, GRPID)) { inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = dir->i_gid; } else inode_init_owner(inode, dir, mode);