struct ext4_group_desc *gdp;
ext4_group_t i;
ext4_group_t ngroups = ext4_get_groups_count(sb);
+ struct ext4_group_info *grp;
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
ext4_fsblk_t bitmap_count;
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += ext4_free_group_clusters(sb, gdp);
+ grp = NULL;
+ if (EXT4_SB(sb)->s_group_info)
+ grp = ext4_get_group_info(sb, i);
+ if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ desc_count += ext4_free_group_clusters(sb, gdp);
brelse(bitmap_bh);
bitmap_bh = ext4_read_block_bitmap(sb, i);
if (bitmap_bh == NULL)
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += ext4_free_group_clusters(sb, gdp);
+ grp = NULL;
+ if (EXT4_SB(sb)->s_group_info)
+ grp = ext4_get_group_info(sb, i);
+ if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+ desc_count += ext4_free_group_clusters(sb, gdp);
}
return desc_count;
#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
+#include <linux/ratelimit.h>
#include <crypto/hash.h>
#ifdef __KERNEL__
#include <linux/compat.h>
unsigned long s_es_last_sorted;
struct percpu_counter s_extent_cache_cnt;
spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
+
+ /* Ratelimit ext4 messages. */
+ struct ratelimit_state s_err_ratelimit_state;
+ struct ratelimit_state s_warning_ratelimit_state;
+ struct ratelimit_state s_msg_ratelimit_state;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
clear_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
}
+/* Add these declarations here only so that these functions can be
+ * found by name. Otherwise, they are very hard to locate. */
+static inline int ext4_test_inode_flag(struct inode *inode, int bit);
+static inline void ext4_set_inode_flag(struct inode *inode, int bit);
+static inline void ext4_clear_inode_flag(struct inode *inode, int bit);
EXT4_INODE_BIT_FNS(flag, flags, 0)
+
+/* Add these declarations here only so that these functions can be
+ * found by name. Otherwise, they are very hard to locate. */
+static inline int ext4_test_inode_state(struct inode *inode, int bit);
+static inline void ext4_set_inode_state(struct inode *inode, int bit);
+static inline void ext4_clear_inode_state(struct inode *inode, int bit);
#if (BITS_PER_LONG < 64)
EXT4_INODE_BIT_FNS(state, state_flags, 0)
ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
struct ext4_extent *ex2)
{
- unsigned short ext1_ee_len, ext2_ee_len, max_len;
+ unsigned short ext1_ee_len, ext2_ee_len;
/*
* Make sure that both extents are initialized. We don't merge
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);
* as an RO_COMPAT feature, refuse to merge to extents if
* this can result in the top bit of ee_len being set.
*/
- if (ext1_ee_len + ext2_ee_len > max_len)
+ if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
return 0;
#ifdef AGGRESSIVE_TEST
if (ext1_ee_len >= 4)
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);
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)
struct ext4_ext_path *npath = NULL;
int depth, len, err;
ext4_lblk_t next;
- unsigned uninitialized = 0;
int mb_flags = 0;
if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
if (err)
return err;
- /*
- * 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;
if (err)
return err;
- /*
- * 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_block = newext->ee_block;
ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
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;
ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
grp = hinfo.hash;
} else
- get_random_bytes(&grp, sizeof(grp));
+ grp = prandom_u32();
parent_group = (unsigned)grp % ngroups;
for (i = 0; i < ngroups; i++) {
g = (parent_group + i) % ngroups;
struct inode *dir = dentry->d_parent->d_inode;
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
- unsigned short reclen;
int err;
struct ext4_dir_entry_2 *de;
- reclen = EXT4_DIR_REC_LEN(namelen);
err = ext4_find_dest_de(dir, inode, iloc->bh,
inline_start, inline_size,
name, namelen, &de);
if (ret < 0)
goto out;
+ ret = 0;
sb = inode->i_sb;
parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
offset = ctx->pos;
*
* @handle - handle for journal operations
* @mpd - extent to map
+ * @give_up_on_write - we set this to true iff there is a fatal error and there
+ * is no hope of writing the data. The caller should discard
+ * dirty pages to avoid infinite loops.
*
* The function maps extent starting at mpd->lblk of length mpd->len. If it is
* delayed, blocks are allocated, if it is unwritten, we may need to convert
struct address_space *mapping = mpd->inode->i_mapping;
struct pagevec pvec;
unsigned int nr_pages;
+ long left = mpd->wbc->nr_to_write;
pgoff_t index = mpd->first_page;
pgoff_t end = mpd->last_page;
int tag;
if (page->index > end)
goto out;
+ /*
+ * Accumulated enough dirty pages? This doesn't apply
+ * to WB_SYNC_ALL mode. For integrity sync we have to
+ * keep going because someone may be concurrently
+ * dirtying pages, and we might have synced a lot of
+ * newly appeared dirty pages, but have not synced all
+ * of the old dirty pages.
+ */
+ if (mpd->wbc->sync_mode == WB_SYNC_NONE && left <= 0)
+ goto out;
+
/* If we can't merge this page, we are done. */
if (mpd->map.m_len > 0 && mpd->next_page != page->index)
goto out;
if (err <= 0)
goto out;
err = 0;
-
- /*
- * Accumulated enough dirty pages? This doesn't apply
- * to WB_SYNC_ALL mode. For integrity sync we have to
- * keep going because someone may be concurrently
- * dirtying pages, and we might have synced a lot of
- * newly appeared dirty pages, but have not synced all
- * of the old dirty pages.
- */
- if (mpd->wbc->sync_mode == WB_SYNC_NONE &&
- mpd->next_page - mpd->first_page >=
- mpd->wbc->nr_to_write)
- goto out;
+ left--;
}
pagevec_release(&pvec);
cond_resched();
* because that could violate lock ordering on umount
*/
if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
- return 0;
+ goto out_writepages;
if (ext4_should_journal_data(inode)) {
struct blk_plug plug;
- int ret;
blk_start_plug(&plug);
ret = write_cache_pages(mapping, wbc, __writepage, mapping);
blk_finish_plug(&plug);
- return ret;
+ goto out_writepages;
}
/*
* *never* be called, so if that ever happens, we would want
* the stack trace.
*/
- if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED))
- return -EROFS;
+ if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+ ret = -EROFS;
+ goto out_writepages;
+ }
if (ext4_should_dioread_nolock(inode)) {
/*
inode = dentry->d_inode;
generic_fillattr(inode, stat);
+ /*
+ * If there is inline data in the inode, the inode will normally not
+ * have data blocks allocated (it may have an external xattr block).
+ * Report at least one sector for such files, so tools like tar, rsync,
+ * others doen't incorrectly think the file is completely sparse.
+ */
+ if (unlikely(ext4_has_inline_data(inode)))
+ stat->blocks += (stat->size + 511) >> 9;
+
/*
* We can't update i_blocks if the block allocation is delayed
* otherwise in the case of system crash before the real block
* blocks for this file.
*/
delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb),
- EXT4_I(inode)->i_reserved_data_blocks);
-
- stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits-9);
+ EXT4_I(inode)->i_reserved_data_blocks);
+ stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits - 9);
return 0;
}
" group:%d block:%d count:%lu failed"
" with %d", block_group, bit, count,
err);
- }
-
+ } else
+ EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
ext4_lock_group(sb, block_group);
mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
u32 new_seq;
do {
- get_random_bytes(&new_seq, sizeof(u32));
+ new_seq = prandom_u32();
} while (new_seq > EXT4_MMP_SEQ_MAX);
return new_seq;
static void ext4_add_complete_io(ext4_io_end_t *io_end)
{
struct ext4_inode_info *ei = EXT4_I(io_end->inode);
+ struct ext4_sb_info *sbi = EXT4_SB(io_end->inode->i_sb);
struct workqueue_struct *wq;
unsigned long flags;
/* Only reserved conversions from writeback should enter here */
WARN_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
- WARN_ON(!io_end->handle);
+ WARN_ON(!io_end->handle && sbi->s_journal);
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
- wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq;
+ wq = sbi->rsv_conversion_wq;
if (list_empty(&ei->i_rsv_conversion_list))
queue_work(wq, &ei->i_rsv_conversion_work);
list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);
sb->s_id);
}
+#define ext4_error_ratelimit(sb) \
+ ___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state), \
+ "EXT4-fs error")
+
void __ext4_error(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
- sb->s_id, function, line, current->comm, &vaf);
- va_end(args);
+ if (ext4_error_ratelimit(sb)) {
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
+ sb->s_id, function, line, current->comm, &vaf);
+ va_end(args);
+ }
save_error_info(sb, function, line);
-
ext4_handle_error(sb);
}
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
es->s_last_error_block = cpu_to_le64(block);
+ if (ext4_error_ratelimit(inode->i_sb)) {
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ if (block)
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+ "inode #%lu: block %llu: comm %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ block, current->comm, &vaf);
+ else
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+ "inode #%lu: comm %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ current->comm, &vaf);
+ va_end(args);
+ }
save_error_info(inode->i_sb, function, line);
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- if (block)
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
- "inode #%lu: block %llu: comm %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- block, current->comm, &vaf);
- else
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
- "inode #%lu: comm %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- current->comm, &vaf);
- va_end(args);
-
ext4_handle_error(inode->i_sb);
}
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
+ if (ext4_error_ratelimit(inode->i_sb)) {
+ path = d_path(&(file->f_path), pathname, sizeof(pathname));
+ if (IS_ERR(path))
+ path = "(unknown)";
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ if (block)
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+ "block %llu: comm %s: path %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ block, current->comm, path, &vaf);
+ else
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+ "comm %s: path %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ current->comm, path, &vaf);
+ va_end(args);
+ }
save_error_info(inode->i_sb, function, line);
- path = d_path(&(file->f_path), pathname, sizeof(pathname));
- if (IS_ERR(path))
- path = "(unknown)";
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- if (block)
- printk(KERN_CRIT
- "EXT4-fs error (device %s): %s:%d: inode #%lu: "
- "block %llu: comm %s: path %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- block, current->comm, path, &vaf);
- else
- printk(KERN_CRIT
- "EXT4-fs error (device %s): %s:%d: inode #%lu: "
- "comm %s: path %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- current->comm, path, &vaf);
- va_end(args);
-
ext4_handle_error(inode->i_sb);
}
(sb->s_flags & MS_RDONLY))
return;
- errstr = ext4_decode_error(sb, errno, nbuf);
- printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
- sb->s_id, function, line, errstr);
- save_error_info(sb, function, line);
+ if (ext4_error_ratelimit(sb)) {
+ errstr = ext4_decode_error(sb, errno, nbuf);
+ printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
+ sb->s_id, function, line, errstr);
+ }
+ save_error_info(sb, function, line);
ext4_handle_error(sb);
}
struct va_format vaf;
va_list args;
+ if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs"))
+ return;
+
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
struct va_format vaf;
va_list args;
+ if (!___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),
+ "EXT4-fs warning"))
+ return;
+
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
es->s_last_error_block = cpu_to_le64(block);
__save_error_info(sb, function, line);
- va_start(args, fmt);
-
- vaf.fmt = fmt;
- vaf.va = &args;
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
- sb->s_id, function, line, grp);
- if (ino)
- printk(KERN_CONT "inode %lu: ", ino);
- if (block)
- printk(KERN_CONT "block %llu:", (unsigned long long) block);
- printk(KERN_CONT "%pV\n", &vaf);
- va_end(args);
+ if (ext4_error_ratelimit(sb)) {
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
+ sb->s_id, function, line, grp);
+ if (ino)
+ printk(KERN_CONT "inode %lu: ", ino);
+ if (block)
+ printk(KERN_CONT "block %llu:",
+ (unsigned long long) block);
+ printk(KERN_CONT "%pV\n", &vaf);
+ va_end(args);
+ }
if (test_opt(sb, ERRORS_CONT)) {
ext4_commit_super(sb, 0);
EXT4_DEPRECATED_ATTR(max_writeback_mb_bump, 128);
EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
+EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_UI(err_ratelimit_burst, s_err_ratelimit_state.burst);
+EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
+EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
static struct attribute *ext4_attrs[] = {
ATTR_LIST(delayed_allocation_blocks),
ATTR_LIST(max_writeback_mb_bump),
ATTR_LIST(extent_max_zeroout_kb),
ATTR_LIST(trigger_fs_error),
+ ATTR_LIST(err_ratelimit_interval_ms),
+ ATTR_LIST(err_ratelimit_burst),
+ ATTR_LIST(warning_ratelimit_interval_ms),
+ ATTR_LIST(warning_ratelimit_burst),
+ ATTR_LIST(msg_ratelimit_interval_ms),
+ ATTR_LIST(msg_ratelimit_burst),
NULL,
};
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_li_request *elr;
- unsigned long rnd;
elr = kzalloc(sizeof(*elr), GFP_KERNEL);
if (!elr)
* spread the inode table initialization requests
* better.
*/
- get_random_bytes(&rnd, sizeof(rnd));
- elr->lr_next_sched = jiffies + (unsigned long)rnd %
- (EXT4_DEF_LI_MAX_START_DELAY * HZ);
-
+ elr->lr_next_sched = jiffies + (prandom_u32() %
+ (EXT4_DEF_LI_MAX_START_DELAY * HZ));
return elr;
}
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
+ /* Enable message ratelimiting. Default is 10 messages per 5 secs. */
+ ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10);
+ ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10);
+ ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
+
kfree(orig_data);
return 0;
new_extra_isize = s_min_extra_isize;
kfree(is); is = NULL;
kfree(bs); bs = NULL;
+ brelse(bh);
goto retry;
}
error = -1;
projects / cascardo / linux.git / commitdiff