From 22098763a10d9c1340827fcf6edab66f153b27f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 12:27:00 -0700 Subject: Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Don't destroy user event fields when removal fails User event fields are destroyed before the event is removed from visibility. But that can fail leaving the still visible event with no fields. Move the destroying of the fields to after the event is successfully removed from visibility. - Initialize function graph state is fork before calling copy_exec_state() For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, ftrace_graph_exit_task() will free the tasks ret_stack pointer. Since that pointer is still using the parent's ret_stack, it mistakenly frees the parent's pointer too. Call ftrace_graph_init() on the task first which will NULL out the new tasks's ret_stack and if the copy fails, it will not free anything. - Remove FGRAPH_MAX_INDEX The macro FGRAPH_MAX_INDEX was added but never used. Remove it. - Save ent_size in function graph printing of nested functions The function graph tracer needs to look at the next event to see if the next event is the return of the current function entry. If it is, it prints a single line: ktime_get(); Otherwise it prints it like a nested function: tick_nohz_irq_exit() { ktime_get(); kcpustat_irq_exit(); } In order to look at the next event, it must save the current event so that it has the information to print from it. It saves the event in the iterator descriptor called "ent". What it doesn't save is the ent_size of the event which is now used to know if the function graph arguments are to be printed. The peek doesn't save the size so the size used happens to be that of the size of the last event that was seen. Save the entry event size in the iterator descriptor so that the correct size is used. - Fix several errors with freeing data in the histogram code The histogram code had a lot of leaked or or incorrect accounting when failures happen. Correct them. - Fix histogram regression of .percent and .graph modifiers Up until 6.3 histogram values could have "percent" or "graph" modifiers that changed how they were printed. But a change that added restricting histograms values from being strings, stack traces and other modifiers inadvertently prevented them from using the percent and graph modifiers, which were legal use cases for values. Put back the percent and graph modifiers. - Fix various typos in the comments - Set the trace_clock before initializing a histogram with clock argument The histogram API allows the user to specific which trace clock to use via a "clock=" string. The histogram is set up first before the clock is checked. If the passed in clock is not valid, it exits without fully fixing up the histogram leaving it on the list and a use-after-free can trigger. Update the clock argument first and if it fails then exit gracefully before the histogram trigger is placed on any lists. - Restore :mod: trailer after parsing in ftrace_set_clr_event The function ftrace_set_clr_event() modifies the parse string and needs to put it back to what was passed in. It searches for ":mod:" via a strsep() but fails to put back the first ':' in the string. Add back the ':' in the passed in string. - Take trace_array reference when opening a tracer options file The options files are dynamically created and some tracers add their own options. When a tracer adds their own list of options, the trace_array holding them has an array to hold the list of options for each tracer. This array increases in size via a krealloc(), and the new entry gets a newly allocated array to hold the options of the new tracer being added. The element in each entry of the tracer's option array holds a pointer back to the trace_array, a pointer to the tracer it is associated to, a pointer to the flags of the option. The issue is that these arrays are freed when the trace_array is freed when its instance it represents is removed from the instances directory. There's a race that an open of one of these options files can happen when the instance is being removed. Add a new helper function to be called by the open function of the options file to iterate all existing trace_arrays under a lock and find the one that has the given option element in one of it's tracer arrays. If found, then update the associated trace_array's reference counter to keep it from being freed. If not found, have the open call return -ENODEV. - Disable interrupts when acquiring the lock in rb_wake_up_waiters() The function rb_wake_up_waiters() assumes it will be called in interrupt context and does not disable irqs when taking cpu_buffer->reader_lock, which can be called in hard interrupt context. The issue is in PREEMPT_RT, this function is called in thread context leaving this lock open to a deadlock. Take the lock with interrupts disabled. - Use rcu_assign_pointer() for tmp_ops filter hash The tmp_ops used in update_ftrace_direct_mod() assigns its filter_hash field directly, but that field is annotated as __rcu and sparse complains. Assign it with rcu_assign_pointer() - Fix use-after-free in enable_trigger_private_data_free() The trace_event_call is accessed through the event_trigger_data's trace_event_file pointer to put the trace_event_call on freeing. The issue is that the trace_event_file data may have been freed already causing a use-after-free. Add a field to the event_trigger_data that points directly to the trace_event_call so that it can decrement its reference directly without needing to go through the trace_event_file. - Fix accounting of buffer data remote headers trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the number of pages is needed for the asked for size as it doesn't take into account the meta data on each page. Add a helper function to do the calculation properly and use that in these functions. - Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. - Do not resize the subbuf order if any per_cpu buffer is disabled The mmapping of ring buffers disables resizing the subbuffers, but it is done per-cpu whereas the subbuf size change is done for all the per_cpu buffers under the buffer->mutex. It could change the size of some while the mapping is happening on others. Have the resize of the subbuf order check all the per_cpu buffers under the lock to see if any of them is disabled before starting and causing an inconsistency between buffers that are being mapped. * tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits) ring-buffer: Check resize_disabled before publishing the new subbuf order tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing tracing/remotes: Account for ring buffer page header in size calculation tracing: Don't dereference trace_event_file in deferred trigger free ftrace: Use rcu_assign_pointer() for tmp_ops filter hash ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() tracing: Take trace_array reference when opening a tracer options file tracing: Fix ring_buffer_read_page_size() kernel-doc tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() tracing: Fix memory corruption from a "STACKTRACE" histogram key tracing: Fix memory corruption from the histogram stacktrace modifier tracing: Undo the registration when enabling the histogram trigger fails tracing: Take the reference before publishing the named histogram trigger tracing: Set the trace clock before registering the histogram trigger tracing: Fix typo "preceeded" in comment tracing: Fix typo "availabe" in comment tracing: Let histogram values keep the percent and graph modifiers tracing: Keep the entry count when the histogram stats allocation fails tracing: Free histogram the field rejected for a bad modifier tracing: Free histogram the var ref when its initialization fails ... --- fs/ext2/ialloc.c | 673 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 673 insertions(+) create mode 100644 fs/ext2/ialloc.c (limited to 'fs/ext2/ialloc.c') diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c new file mode 100644 index 000000000..bf21b57cf --- /dev/null +++ b/fs/ext2/ialloc.c @@ -0,0 +1,673 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/ext2/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@dcs.ed.ac.uk), 1993 + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + */ + +#include +#include +#include +#include +#include +#include "ext2.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 ext2_group_desc *desc; + struct buffer_head *bh = NULL; + + desc = ext2_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) + ext2_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; +} + +static void ext2_release_inode(struct super_block *sb, int group, int dir) +{ + struct ext2_group_desc * desc; + struct buffer_head *bh; + + desc = ext2_get_group_desc(sb, group, &bh); + if (!desc) { + ext2_error(sb, "ext2_release_inode", + "can't get descriptor for group %d", group); + return; + } + + spin_lock(sb_bgl_lock(EXT2_SB(sb), group)); + le16_add_cpu(&desc->bg_free_inodes_count, 1); + if (dir) + le16_add_cpu(&desc->bg_used_dirs_count, -1); + spin_unlock(sb_bgl_lock(EXT2_SB(sb), group)); + percpu_counter_inc(&EXT2_SB(sb)->s_freeinodes_counter); + if (dir) + percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter); + mark_buffer_dirty(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 ext2_free_inode (struct inode * inode) +{ + struct super_block * sb = inode->i_sb; + int is_directory; + unsigned long ino; + struct buffer_head *bitmap_bh; + unsigned long block_group; + unsigned long bit; + struct ext2_super_block * es; + + ino = inode->i_ino; + ext2_debug ("freeing inode %lu\n", ino); + + /* + * Note: we must free any quota before locking the superblock, + * as writing the quota to disk may need the lock as well. + */ + /* Quota is already initialized in iput() */ + dquot_free_inode(inode); + dquot_drop(inode); + + es = EXT2_SB(sb)->s_es; + is_directory = S_ISDIR(inode->i_mode); + + if (ino < EXT2_FIRST_INO(sb) || + ino > le32_to_cpu(es->s_inodes_count)) { + ext2_error (sb, "ext2_free_inode", + "reserved or nonexistent inode %lu", ino); + return; + } + block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb); + bit = (ino - 1) % EXT2_INODES_PER_GROUP(sb); + bitmap_bh = read_inode_bitmap(sb, block_group); + if (!bitmap_bh) + return; + + /* Ok, now we can actually update the inode bitmaps.. */ + if (!ext2_clear_bit_atomic(sb_bgl_lock(EXT2_SB(sb), block_group), + bit, (void *) bitmap_bh->b_data)) + ext2_error (sb, "ext2_free_inode", + "bit already cleared for inode %lu", ino); + else + ext2_release_inode(sb, block_group, is_directory); + mark_buffer_dirty(bitmap_bh); + if (sb->s_flags & SB_SYNCHRONOUS) + sync_dirty_buffer(bitmap_bh); + + brelse(bitmap_bh); +} + +/* + * We perform asynchronous prereading of the new inode's inode block when + * we create the inode, in the expectation that the inode will be written + * back soon. There are two reasons: + * + * - When creating a large number of files, the async prereads will be + * nicely merged into large reads + * - When writing out a large number of inodes, we don't need to keep on + * stalling the writes while we read the inode block. + * + * FIXME: ext2_get_group_desc() needs to be simplified. + */ +static void ext2_preread_inode(struct inode *inode) +{ + unsigned long block_group; + unsigned long offset; + unsigned long block; + unsigned int ino = inode->i_ino; + struct ext2_group_desc * gdp; + + block_group = (ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb); + gdp = ext2_get_group_desc(inode->i_sb, block_group, NULL); + if (gdp == NULL) + return; + + /* + * Figure out the offset within the block group inode table + */ + offset = ((ino - 1) % EXT2_INODES_PER_GROUP(inode->i_sb)) * + EXT2_INODE_SIZE(inode->i_sb); + block = le32_to_cpu(gdp->bg_inode_table) + + (offset >> EXT2_BLOCK_SIZE_BITS(inode->i_sb)); + sb_breadahead(inode->i_sb, block); +} + +/* + * 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. + */ +static int find_group_dir(struct super_block *sb, struct inode *parent) +{ + int ngroups = EXT2_SB(sb)->s_groups_count; + int avefreei = ext2_count_free_inodes(sb) / ngroups; + struct ext2_group_desc *desc, *best_desc = NULL; + int group, best_group = -1; + + for (group = 0; group < ngroups; group++) { + desc = ext2_get_group_desc (sb, group, NULL); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) + continue; + if (!best_desc || + (le16_to_cpu(desc->bg_free_blocks_count) > + le16_to_cpu(best_desc->bg_free_blocks_count))) { + best_group = group; + best_desc = desc; + } + } + + return best_group; +} + +/* + * 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 = EXT2_I(parent)->i_block_group; + struct ext2_sb_info *sbi = EXT2_SB(sb); + struct ext2_super_block *es = sbi->s_es; + int ngroups = sbi->s_groups_count; + int inodes_per_group = EXT2_INODES_PER_GROUP(sb); + int freei; + int avefreei; + int free_blocks; + int avefreeb; + int blocks_per_dir; + int ndirs; + int max_debt, max_dirs, min_blocks, min_inodes; + int group = -1, i; + struct ext2_group_desc *desc; + + freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); + avefreei = freei / ngroups; + free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); + avefreeb = free_blocks / ngroups; + ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); + + if ((parent == d_inode(sb->s_root)) || + (EXT2_I(parent)->i_flags & EXT2_TOPDIR_FL)) { + int best_ndir = inodes_per_group; + int best_group = -1; + + parent_group = get_random_u32_below(ngroups); + for (i = 0; i < ngroups; i++) { + group = (parent_group + i) % ngroups; + desc = ext2_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) { + group = best_group; + goto found; + } + goto fallback; + } + + if (ndirs == 0) + ndirs = 1; /* percpu_counters are approximate... */ + + blocks_per_dir = (le32_to_cpu(es->s_blocks_count)-free_blocks) / ndirs; + + max_dirs = ndirs / ngroups + inodes_per_group / 16; + min_inodes = avefreei - inodes_per_group / 4; + min_blocks = avefreeb - EXT2_BLOCKS_PER_GROUP(sb) / 4; + + max_debt = EXT2_BLOCKS_PER_GROUP(sb) / max(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; + + for (i = 0; i < ngroups; i++) { + group = (parent_group + i) % ngroups; + desc = ext2_get_group_desc (sb, group, NULL); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (sbi->s_debts[group] >= max_debt) + 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; + goto found; + } + +fallback: + for (i = 0; i < ngroups; i++) { + group = (parent_group + i) % ngroups; + desc = ext2_get_group_desc (sb, group, NULL); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei) + goto found; + } + + 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; + +found: + return group; +} + +static int find_group_other(struct super_block *sb, struct inode *parent) +{ + int parent_group = EXT2_I(parent)->i_block_group; + int ngroups = EXT2_SB(sb)->s_groups_count; + struct ext2_group_desc *desc; + int group, i; + + /* + * Try to place the inode in its parent directory + */ + group = parent_group; + desc = ext2_get_group_desc (sb, group, NULL); + if (desc && le16_to_cpu(desc->bg_free_inodes_count) && + le16_to_cpu(desc->bg_free_blocks_count)) + goto found; + + /* + * 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 + (unsigned int)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 = ext2_get_group_desc (sb, group, NULL); + if (desc && le16_to_cpu(desc->bg_free_inodes_count) && + le16_to_cpu(desc->bg_free_blocks_count)) + goto found; + } + + /* + * 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 = ext2_get_group_desc (sb, group, NULL); + if (desc && le16_to_cpu(desc->bg_free_inodes_count)) + goto found; + } + + return -1; + +found: + return group; +} + +struct inode *ext2_new_inode(struct inode *dir, umode_t mode, + const struct qstr *qstr) +{ + struct super_block *sb; + struct buffer_head *bitmap_bh = NULL; + struct buffer_head *bh2; + int group, i; + ino_t ino = 0; + struct inode * inode; + struct ext2_group_desc *gdp; + struct ext2_super_block *es; + struct ext2_inode_info *ei; + struct ext2_sb_info *sbi; + int err; + + sb = dir->i_sb; + inode = new_inode(sb); + if (!inode) + return ERR_PTR(-ENOMEM); + + ei = EXT2_I(inode); + sbi = EXT2_SB(sb); + es = sbi->s_es; + if (S_ISDIR(mode)) { + if (test_opt(sb, OLDALLOC)) + group = find_group_dir(sb, dir); + else + group = find_group_orlov(sb, dir); + } else + group = find_group_other(sb, dir); + + if (group == -1) { + err = -ENOSPC; + goto fail; + } + + for (i = 0; i < sbi->s_groups_count; i++) { + gdp = ext2_get_group_desc(sb, group, &bh2); + if (!gdp) { + if (++group == sbi->s_groups_count) + group = 0; + continue; + } + brelse(bitmap_bh); + bitmap_bh = read_inode_bitmap(sb, group); + if (!bitmap_bh) { + err = -EIO; + goto fail; + } + ino = 0; + +repeat_in_this_group: + ino = ext2_find_next_zero_bit((unsigned long *)bitmap_bh->b_data, + EXT2_INODES_PER_GROUP(sb), ino); + if (ino >= EXT2_INODES_PER_GROUP(sb)) { + /* + * Rare race: find_group_xx() decided that there were + * free inodes in this group, but by the time we tried + * to allocate one, they're all gone. This can also + * occur because the counters which find_group_orlov() + * uses are approximate. So just go and search the + * next block group. + */ + if (++group == sbi->s_groups_count) + group = 0; + continue; + } + if (ext2_set_bit_atomic(sb_bgl_lock(sbi, group), + ino, bitmap_bh->b_data)) { + /* we lost this inode */ + if (++ino >= EXT2_INODES_PER_GROUP(sb)) { + /* this group is exhausted, try next group */ + if (++group == sbi->s_groups_count) + group = 0; + continue; + } + /* try to find free inode in the same group */ + goto repeat_in_this_group; + } + goto got; + } + + /* + * Scanned all blockgroups. + */ + brelse(bitmap_bh); + err = -ENOSPC; + goto fail; +got: + mark_buffer_dirty(bitmap_bh); + if (sb->s_flags & SB_SYNCHRONOUS) + sync_dirty_buffer(bitmap_bh); + brelse(bitmap_bh); + + ino += group * EXT2_INODES_PER_GROUP(sb) + 1; + if (ino < EXT2_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { + ext2_error (sb, "ext2_new_inode", + "reserved inode or inode > inodes count - " + "block_group = %d,inode=%lu", group, + (unsigned long) ino); + err = -EIO; + goto fail; + } + + percpu_counter_dec(&sbi->s_freeinodes_counter); + if (S_ISDIR(mode)) + percpu_counter_inc(&sbi->s_dirs_counter); + + spin_lock(sb_bgl_lock(sbi, group)); + le16_add_cpu(&gdp->bg_free_inodes_count, -1); + if (S_ISDIR(mode)) { + if (sbi->s_debts[group] < 255) + sbi->s_debts[group]++; + le16_add_cpu(&gdp->bg_used_dirs_count, 1); + } else { + if (sbi->s_debts[group]) + sbi->s_debts[group]--; + } + spin_unlock(sb_bgl_lock(sbi, group)); + + mark_buffer_dirty(bh2); + if (test_opt(sb, GRPID)) { + inode->i_mode = mode; + inode->i_uid = current_fsuid(); + inode->i_gid = dir->i_gid; + } else + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); + + inode->i_ino = ino; + inode->i_blocks = 0; + simple_inode_init_ts(inode); + memset(ei->i_data, 0, sizeof(ei->i_data)); + ei->i_flags = + ext2_mask_flags(mode, EXT2_I(dir)->i_flags & EXT2_FL_INHERITED); + ei->i_faddr = 0; + ei->i_frag_no = 0; + ei->i_frag_size = 0; + ei->i_file_acl = 0; + ei->i_dir_acl = 0; + ei->i_dtime = 0; + ei->i_block_alloc_info = NULL; + ei->i_block_group = group; + ei->i_dir_start_lookup = 0; + ei->i_state = EXT2_STATE_NEW; + ext2_set_inode_flags(inode); + spin_lock(&sbi->s_next_gen_lock); + inode->i_generation = sbi->s_next_generation++; + spin_unlock(&sbi->s_next_gen_lock); + if (insert_inode_locked(inode) < 0) { + ext2_error(sb, "ext2_new_inode", + "inode number already in use - inode=%lu", + (unsigned long) ino); + err = -EIO; + goto fail; + } + + err = dquot_initialize(inode); + if (err) + goto fail_drop; + + err = dquot_alloc_inode(inode); + if (err) + goto fail_drop; + + err = ext2_init_acl(inode, dir); + if (err) + goto fail_free_drop; + + err = ext2_init_security(inode, dir, qstr); + if (err) + goto fail_free_drop; + + mark_inode_dirty(inode); + ext2_debug("allocating inode %llu\n", inode->i_ino); + ext2_preread_inode(inode); + return inode; + +fail_free_drop: + dquot_free_inode(inode); + +fail_drop: + dquot_drop(inode); + inode->i_flags |= S_NOQUOTA; + clear_nlink(inode); + discard_new_inode(inode); + return ERR_PTR(err); + +fail: + make_bad_inode(inode); + iput(inode); + return ERR_PTR(err); +} + +unsigned long ext2_count_free_inodes (struct super_block * sb) +{ + struct ext2_group_desc *desc; + unsigned long desc_count = 0; + int i; + +#ifdef EXT2FS_DEBUG + struct ext2_super_block *es; + unsigned long bitmap_count = 0; + struct buffer_head *bitmap_bh = NULL; + + es = EXT2_SB(sb)->s_es; + for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { + unsigned x; + + desc = ext2_get_group_desc (sb, i, NULL); + if (!desc) + continue; + desc_count += le16_to_cpu(desc->bg_free_inodes_count); + brelse(bitmap_bh); + bitmap_bh = read_inode_bitmap(sb, i); + if (!bitmap_bh) + continue; + + x = ext2_count_free(bitmap_bh, EXT2_INODES_PER_GROUP(sb) / 8); + printk("group %d: stored = %d, counted = %u\n", + i, le16_to_cpu(desc->bg_free_inodes_count), x); + bitmap_count += x; + } + brelse(bitmap_bh); + printk("ext2_count_free_inodes: stored = %lu, computed = %lu, %lu\n", + (unsigned long) + percpu_counter_read(&EXT2_SB(sb)->s_freeinodes_counter), + desc_count, bitmap_count); + return desc_count; +#else + for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { + desc = ext2_get_group_desc (sb, i, NULL); + if (!desc) + continue; + desc_count += le16_to_cpu(desc->bg_free_inodes_count); + } + return desc_count; +#endif +} + +/* Called at mount-time, super-block is locked */ +unsigned long ext2_count_dirs (struct super_block * sb) +{ + unsigned long count = 0; + int i; + + for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { + struct ext2_group_desc *gdp = ext2_get_group_desc (sb, i, NULL); + if (!gdp) + continue; + count += le16_to_cpu(gdp->bg_used_dirs_count); + } + return count; +} + -- cgit v1.3.1