Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (57 commits)
jbd2: Fix oops in jbd2_journal_init_inode() on corrupted fs
ext4: Remove "extents" mount option
block: Add Kconfig help which notes that ext4 needs CONFIG_LBD
ext4: Make printk's consistently prefixed with "EXT4-fs: "
ext4: Add sanity checks for the superblock before mounting the filesystem
ext4: Add mount option to set kjournald's I/O priority
jbd2: Submit writes to the journal using WRITE_SYNC
jbd2: Add pid and journal device name to the "kjournald2 starting" message
ext4: Add markers for better debuggability
ext4: Remove code to create the journal inode
ext4: provide function to release metadata pages under memory pressure
ext3: provide function to release metadata pages under memory pressure
add releasepage hooks to block devices which can be used by file systems
ext4: Fix s_dirty_blocks_counter if block allocation failed with nodelalloc
ext4: Init the complete page while building buddy cache
ext4: Don't allow new groups to be added during block allocation
ext4: mark the blocks/inode bitmap beyond end of group as used
ext4: Use new buffer_head flag to check uninit group bitmaps initialization
ext4: Fix the race between read_inode_bitmap() and ext4_new_inode()
ext4: code cleanup
...
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 174eaff..cec829b 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -58,13 +58,22 @@
# mount -t ext4 /dev/hda1 /wherever
- - When comparing performance with other filesystems, remember that
- ext3/4 by default offers higher data integrity guarantees than most.
- So when comparing with a metadata-only journalling filesystem, such
- as ext3, use `mount -o data=writeback'. And you might as well use
- `mount -o nobh' too along with it. Making the journal larger than
- the mke2fs default often helps performance with metadata-intensive
- workloads.
+ - When comparing performance with other filesystems, it's always
+ important to try multiple workloads; very often a subtle change in a
+ workload parameter can completely change the ranking of which
+ filesystems do well compared to others. When comparing versus ext3,
+ note that ext4 enables write barriers by default, while ext3 does
+ not enable write barriers by default. So it is useful to use
+ explicitly specify whether barriers are enabled or not when via the
+ '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems
+ for a fair comparison. When tuning ext3 for best benchmark numbers,
+ it is often worthwhile to try changing the data journaling mode; '-o
+ data=writeback,nobh' can be faster for some workloads. (Note
+ however that running mounted with data=writeback can potentially
+ leave stale data exposed in recently written files in case of an
+ unclean shutdown, which could be a security exposure in some
+ situations.) Configuring the filesystem with a large journal can
+ also be helpful for metadata-intensive workloads.
2. Features
===========
@@ -74,7 +83,7 @@
* ability to use filesystems > 16TB (e2fsprogs support not available yet)
* extent format reduces metadata overhead (RAM, IO for access, transactions)
* extent format more robust in face of on-disk corruption due to magics,
-* internal redunancy in tree
+* internal redundancy in tree
* improved file allocation (multi-block alloc)
* fix 32000 subdirectory limit
* nsec timestamps for mtime, atime, ctime, create time
@@ -116,10 +125,11 @@
When mounting an ext4 filesystem, the following option are accepted:
(*) == default
-extents (*) ext4 will use extents to address file data. The
- file system will no longer be mountable by ext3.
-
-noextents ext4 will not use extents for newly created files
+ro Mount filesystem read only. Note that ext4 will
+ replay the journal (and thus write to the
+ partition) even when mounted "read only". The
+ mount options "ro,noload" can be used to prevent
+ writes to the filesystem.
journal_checksum Enable checksumming of the journal transactions.
This will allow the recovery code in e2fsck and the
@@ -134,17 +144,17 @@
journal=update Update the ext4 file system's journal to the current
format.
-journal=inum When a journal already exists, this option is ignored.
- Otherwise, it specifies the number of the inode which
- will represent the ext4 file system's journal file.
-
journal_dev=devnum When the external journal device's major/minor numbers
have changed, this option allows the user to specify
the new journal location. The journal device is
identified through its new major/minor numbers encoded
in devnum.
-noload Don't load the journal on mounting.
+noload Don't load the journal on mounting. Note that
+ if the filesystem was not unmounted cleanly,
+ skipping the journal replay will lead to the
+ filesystem containing inconsistencies that can
+ lead to any number of problems.
data=journal All data are committed into the journal prior to being
written into the main file system.
@@ -219,9 +229,12 @@
debug Extra debugging information is sent to syslog.
-errors=remount-ro(*) Remount the filesystem read-only on an error.
+errors=remount-ro Remount the filesystem read-only on an error.
errors=continue Keep going on a filesystem error.
errors=panic Panic and halt the machine if an error occurs.
+ (These mount options override the errors behavior
+ specified in the superblock, which can be configured
+ using tune2fs)
data_err=ignore(*) Just print an error message if an error occurs
in a file data buffer in ordered mode.
@@ -261,6 +274,42 @@
nodelalloc Disable delayed allocation. Blocks are allocation
when data is copied from user to page cache.
+max_batch_time=usec Maximum amount of time ext4 should wait for
+ additional filesystem operations to be batch
+ together with a synchronous write operation.
+ Since a synchronous write operation is going to
+ force a commit and then a wait for the I/O
+ complete, it doesn't cost much, and can be a
+ huge throughput win, we wait for a small amount
+ of time to see if any other transactions can
+ piggyback on the synchronous write. The
+ algorithm used is designed to automatically tune
+ for the speed of the disk, by measuring the
+ amount of time (on average) that it takes to
+ finish committing a transaction. Call this time
+ the "commit time". If the time that the
+ transactoin has been running is less than the
+ commit time, ext4 will try sleeping for the
+ commit time to see if other operations will join
+ the transaction. The commit time is capped by
+ the max_batch_time, which defaults to 15000us
+ (15ms). This optimization can be turned off
+ entirely by setting max_batch_time to 0.
+
+min_batch_time=usec This parameter sets the commit time (as
+ described above) to be at least min_batch_time.
+ It defaults to zero microseconds. Increasing
+ this parameter may improve the throughput of
+ multi-threaded, synchronous workloads on very
+ fast disks, at the cost of increasing latency.
+
+journal_ioprio=prio The I/O priority (from 0 to 7, where 0 is the
+ highest priorty) which should be used for I/O
+ operations submitted by kjournald2 during a
+ commit operation. This defaults to 3, which is
+ a slightly higher priority than the default I/O
+ priority.
+
Data Mode
=========
There are 3 different data modes:
diff --git a/block/Kconfig b/block/Kconfig
index ac0956f..0cbb3b8 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -36,6 +36,12 @@
This option also enables support for single files larger than
2TB.
+ The ext4 filesystem requires that this feature be enabled in
+ order to support filesystems that have the huge_file feature
+ enabled. Otherwise, it will refuse to mount any filesystems
+ that use the huge_file feature, which is enabled by default
+ by mke2fs.ext4. The GFS2 filesystem also requires this feature.
+
If unsure, say N.
config BLK_DEV_IO_TRACE
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8ebbfdf..ac7031f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1234,6 +1234,20 @@
return blkdev_ioctl(bdev, mode, cmd, arg);
}
+/*
+ * Try to release a page associated with block device when the system
+ * is under memory pressure.
+ */
+static int blkdev_releasepage(struct page *page, gfp_t wait)
+{
+ struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;
+
+ if (super && super->s_op->bdev_try_to_free_page)
+ return super->s_op->bdev_try_to_free_page(super, page, wait);
+
+ return try_to_free_buffers(page);
+}
+
static const struct address_space_operations def_blk_aops = {
.readpage = blkdev_readpage,
.writepage = blkdev_writepage,
@@ -1241,6 +1255,7 @@
.write_begin = blkdev_write_begin,
.write_end = blkdev_write_end,
.writepages = generic_writepages,
+ .releasepage = blkdev_releasepage,
.direct_IO = blkdev_direct_IO,
};
diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c
index c30e149..7d215b4 100644
--- a/fs/ext3/hash.c
+++ b/fs/ext3/hash.c
@@ -35,23 +35,71 @@
/* The old legacy hash */
-static __u32 dx_hack_hash (const char *name, int len)
+static __u32 dx_hack_hash_unsigned(const char *name, int len)
{
- __u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
- while (len--) {
- __u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
+ __u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+ const unsigned char *ucp = (const unsigned char *) name;
- if (hash & 0x80000000) hash -= 0x7fffffff;
+ while (len--) {
+ hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373));
+
+ if (hash & 0x80000000)
+ hash -= 0x7fffffff;
hash1 = hash0;
hash0 = hash;
}
- return (hash0 << 1);
+ return hash0 << 1;
}
-static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+static __u32 dx_hack_hash_signed(const char *name, int len)
+{
+ __u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+ const signed char *scp = (const signed char *) name;
+
+ while (len--) {
+ hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));
+
+ if (hash & 0x80000000)
+ hash -= 0x7fffffff;
+ hash1 = hash0;
+ hash0 = hash;
+ }
+ return hash0 << 1;
+}
+
+static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
{
__u32 pad, val;
int i;
+ const signed char *scp = (const signed char *) msg;
+
+ pad = (__u32)len | ((__u32)len << 8);
+ pad |= pad << 16;
+
+ val = pad;
+ if (len > num*4)
+ len = num * 4;
+ for (i = 0; i < len; i++) {
+ if ((i % 4) == 0)
+ val = pad;
+ val = ((int) scp[i]) + (val << 8);
+ if ((i % 4) == 3) {
+ *buf++ = val;
+ val = pad;
+ num--;
+ }
+ }
+ if (--num >= 0)
+ *buf++ = val;
+ while (--num >= 0)
+ *buf++ = pad;
+}
+
+static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
+{
+ __u32 pad, val;
+ int i;
+ const unsigned char *ucp = (const unsigned char *) msg;
pad = (__u32)len | ((__u32)len << 8);
pad |= pad << 16;
@@ -62,7 +110,7 @@
for (i=0; i < len; i++) {
if ((i % 4) == 0)
val = pad;
- val = msg[i] + (val << 8);
+ val = ((int) ucp[i]) + (val << 8);
if ((i % 4) == 3) {
*buf++ = val;
val = pad;
@@ -95,6 +143,8 @@
const char *p;
int i;
__u32 in[8], buf[4];
+ void (*str2hashbuf)(const char *, int, __u32 *, int) =
+ str2hashbuf_signed;
/* Initialize the default seed for the hash checksum functions */
buf[0] = 0x67452301;
@@ -113,13 +163,18 @@
}
switch (hinfo->hash_version) {
- case DX_HASH_LEGACY:
- hash = dx_hack_hash(name, len);
+ case DX_HASH_LEGACY_UNSIGNED:
+ hash = dx_hack_hash_unsigned(name, len);
break;
+ case DX_HASH_LEGACY:
+ hash = dx_hack_hash_signed(name, len);
+ break;
+ case DX_HASH_HALF_MD4_UNSIGNED:
+ str2hashbuf = str2hashbuf_unsigned;
case DX_HASH_HALF_MD4:
p = name;
while (len > 0) {
- str2hashbuf(p, len, in, 8);
+ (*str2hashbuf)(p, len, in, 8);
half_md4_transform(buf, in);
len -= 32;
p += 32;
@@ -127,10 +182,12 @@
minor_hash = buf[2];
hash = buf[1];
break;
+ case DX_HASH_TEA_UNSIGNED:
+ str2hashbuf = str2hashbuf_unsigned;
case DX_HASH_TEA:
p = name;
while (len > 0) {
- str2hashbuf(p, len, in, 4);
+ (*str2hashbuf)(p, len, in, 4);
TEA_transform(buf, in);
len -= 16;
p += 16;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 8d6f965..69a3d19 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -364,6 +364,8 @@
goto fail;
}
hinfo->hash_version = root->info.hash_version;
+ if (hinfo->hash_version <= DX_HASH_TEA)
+ hinfo->hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
hinfo->seed = EXT3_SB(dir->i_sb)->s_hash_seed;
if (entry)
ext3fs_dirhash(entry->name, entry->len, hinfo);
@@ -632,6 +634,9 @@
dir = dir_file->f_path.dentry->d_inode;
if (!(EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) {
hinfo.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version;
+ if (hinfo.hash_version <= DX_HASH_TEA)
+ hinfo.hash_version +=
+ EXT3_SB(dir->i_sb)->s_hash_unsigned;
hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
start_hash, start_minor_hash);
@@ -1152,9 +1157,9 @@
u32 hash2;
struct dx_map_entry *map;
char *data1 = (*bh)->b_data, *data2;
- unsigned split, move, size, i;
+ unsigned split, move, size;
struct ext3_dir_entry_2 *de = NULL, *de2;
- int err = 0;
+ int err = 0, i;
bh2 = ext3_append (handle, dir, &newblock, &err);
if (!(bh2)) {
@@ -1394,6 +1399,8 @@
/* Initialize as for dx_probe */
hinfo.hash_version = root->info.hash_version;
+ if (hinfo.hash_version <= DX_HASH_TEA)
+ hinfo.hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
ext3fs_dirhash(name, namelen, &hinfo);
frame = frames;
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 01c235b..5d047a0 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -683,6 +683,26 @@
ext3_nfs_get_inode);
}
+/*
+ * Try to release metadata pages (indirect blocks, directories) which are
+ * mapped via the block device. Since these pages could have journal heads
+ * which would prevent try_to_free_buffers() from freeing them, we must use
+ * jbd layer's try_to_free_buffers() function to release them.
+ */
+static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
+ gfp_t wait)
+{
+ journal_t *journal = EXT3_SB(sb)->s_journal;
+
+ WARN_ON(PageChecked(page));
+ if (!page_has_buffers(page))
+ return 0;
+ if (journal)
+ return journal_try_to_free_buffers(journal, page,
+ wait & ~__GFP_WAIT);
+ return try_to_free_buffers(page);
+}
+
#ifdef CONFIG_QUOTA
#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
@@ -749,6 +769,7 @@
.quota_read = ext3_quota_read,
.quota_write = ext3_quota_write,
#endif
+ .bdev_try_to_free_page = bdev_try_to_free_page,
};
static const struct export_operations ext3_export_ops = {
@@ -1750,6 +1771,18 @@
for (i=0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
+ i = le32_to_cpu(es->s_flags);
+ if (i & EXT2_FLAGS_UNSIGNED_HASH)
+ sbi->s_hash_unsigned = 3;
+ else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+#ifdef __CHAR_UNSIGNED__
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+ sbi->s_hash_unsigned = 3;
+#else
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+#endif
+ sb->s_dirt = 1;
+ }
if (sbi->s_blocks_per_group > blocksize * 8) {
printk (KERN_ERR
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 38b3acf..6bba06b 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -20,6 +20,7 @@
#include "ext4.h"
#include "ext4_jbd2.h"
#include "group.h"
+#include "mballoc.h"
/*
* balloc.c contains the blocks allocation and deallocation routines
@@ -100,10 +101,10 @@
* 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 %lu\n", block_group);
- gdp->bg_free_blocks_count = 0;
- gdp->bg_free_inodes_count = 0;
- gdp->bg_itable_unused = 0;
+ "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);
memset(bh->b_data, 0xff, sb->s_blocksize);
return 0;
}
@@ -205,15 +206,15 @@
ext4_group_t block_group,
struct buffer_head **bh)
{
- unsigned long group_desc;
- unsigned long offset;
+ unsigned int group_desc;
+ unsigned int offset;
struct ext4_group_desc *desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (block_group >= sbi->s_groups_count) {
ext4_error(sb, "ext4_get_group_desc",
"block_group >= groups_count - "
- "block_group = %lu, groups_count = %lu",
+ "block_group = %u, groups_count = %u",
block_group, sbi->s_groups_count);
return NULL;
@@ -225,7 +226,7 @@
if (!sbi->s_group_desc[group_desc]) {
ext4_error(sb, "ext4_get_group_desc",
"Group descriptor not loaded - "
- "block_group = %lu, group_desc = %lu, desc = %lu",
+ "block_group = %u, group_desc = %u, desc = %u",
block_group, group_desc, offset);
return NULL;
}
@@ -315,29 +316,50 @@
if (unlikely(!bh)) {
ext4_error(sb, __func__,
"Cannot read block bitmap - "
- "block_group = %lu, block_bitmap = %llu",
+ "block_group = %u, block_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
}
- if (buffer_uptodate(bh) &&
- !(desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))
+
+ if (bitmap_uptodate(bh))
return bh;
lock_buffer(bh);
+ if (bitmap_uptodate(bh)) {
+ unlock_buffer(bh);
+ return bh;
+ }
spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
ext4_init_block_bitmap(sb, bh, block_group, desc);
+ set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
- unlock_buffer(bh);
spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ unlock_buffer(bh);
return bh;
}
spin_unlock(sb_bgl_lock(EXT4_SB(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;
+ }
+ /*
+ * 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 block bitmap - "
- "block_group = %lu, block_bitmap = %llu",
+ "block_group = %u, block_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
}
@@ -350,62 +372,44 @@
}
/**
- * ext4_free_blocks_sb() -- Free given blocks and update quota
+ * ext4_add_groupblocks() -- Add given blocks to an existing group
* @handle: handle to this transaction
* @sb: super block
- * @block: start physcial block to free
+ * @block: start physcial block to add to the block group
* @count: number of blocks to free
- * @pdquot_freed_blocks: pointer to quota
*
- * XXX This function is only used by the on-line resizing code, which
- * should probably be fixed up to call the mballoc variant. There
- * this needs to be cleaned up later; in fact, I'm not convinced this
- * is 100% correct in the face of the mballoc code. The online resizing
- * code needs to be fixed up to more tightly (and correctly) interlock
- * with the mballoc code.
+ * This marks the blocks as free in the bitmap. We ask the
+ * mballoc to reload the buddy after this by setting group
+ * EXT4_GROUP_INFO_NEED_INIT_BIT flag
*/
-void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
- ext4_fsblk_t block, unsigned long count,
- unsigned long *pdquot_freed_blocks)
+void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+ ext4_fsblk_t block, unsigned long count)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gd_bh;
ext4_group_t block_group;
ext4_grpblk_t bit;
- unsigned long i;
- unsigned long overflow;
+ unsigned int i;
struct ext4_group_desc *desc;
struct ext4_super_block *es;
struct ext4_sb_info *sbi;
- int err = 0, ret;
- ext4_grpblk_t group_freed;
+ int err = 0, ret, blk_free_count;
+ ext4_grpblk_t blocks_freed;
+ struct ext4_group_info *grp;
- *pdquot_freed_blocks = 0;
sbi = EXT4_SB(sb);
es = sbi->s_es;
- if (block < le32_to_cpu(es->s_first_data_block) ||
- block + count < block ||
- block + count > ext4_blocks_count(es)) {
- ext4_error(sb, "ext4_free_blocks",
- "Freeing blocks not in datazone - "
- "block = %llu, count = %lu", block, count);
- goto error_return;
- }
+ ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
- ext4_debug("freeing block(s) %llu-%llu\n", block, block + count - 1);
-
-do_more:
- overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+ grp = ext4_get_group_info(sb, block_group);
/*
* Check to see if we are freeing blocks across a group
* boundary.
*/
if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
- overflow = bit + count - EXT4_BLOCKS_PER_GROUP(sb);
- count -= overflow;
+ goto error_return;
}
- brelse(bitmap_bh);
bitmap_bh = ext4_read_block_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
@@ -418,18 +422,17 @@
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
sbi->s_itb_per_group)) {
- ext4_error(sb, "ext4_free_blocks",
- "Freeing blocks in system zones - "
+ ext4_error(sb, __func__,
+ "Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
goto error_return;
}
/*
- * We are about to start releasing blocks in the bitmap,
+ * We are about to add blocks to the bitmap,
* so we need undo access.
*/
- /* @@@ check errors */
BUFFER_TRACE(bitmap_bh, "getting undo access");
err = ext4_journal_get_undo_access(handle, bitmap_bh);
if (err)
@@ -444,107 +447,55 @@
err = ext4_journal_get_write_access(handle, gd_bh);
if (err)
goto error_return;
-
- jbd_lock_bh_state(bitmap_bh);
-
- for (i = 0, group_freed = 0; i < count; i++) {
- /*
- * An HJ special. This is expensive...
- */
-#ifdef CONFIG_JBD2_DEBUG
- jbd_unlock_bh_state(bitmap_bh);
- {
- struct buffer_head *debug_bh;
- debug_bh = sb_find_get_block(sb, block + i);
- if (debug_bh) {
- BUFFER_TRACE(debug_bh, "Deleted!");
- if (!bh2jh(bitmap_bh)->b_committed_data)
- BUFFER_TRACE(debug_bh,
- "No commited data in bitmap");
- BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap");
- __brelse(debug_bh);
- }
- }
- jbd_lock_bh_state(bitmap_bh);
-#endif
- if (need_resched()) {
- jbd_unlock_bh_state(bitmap_bh);
- cond_resched();
- jbd_lock_bh_state(bitmap_bh);
- }
- /* @@@ This prevents newly-allocated data from being
- * freed and then reallocated within the same
- * transaction.
- *
- * Ideally we would want to allow that to happen, but to
- * do so requires making jbd2_journal_forget() capable of
- * revoking the queued write of a data block, which
- * implies blocking on the journal lock. *forget()
- * cannot block due to truncate races.
- *
- * Eventually we can fix this by making jbd2_journal_forget()
- * return a status indicating whether or not it was able
- * to revoke the buffer. On successful revoke, it is
- * safe not to set the allocation bit in the committed
- * bitmap, because we know that there is no outstanding
- * activity on the buffer any more and so it is safe to
- * reallocate it.
- */
- BUFFER_TRACE(bitmap_bh, "set in b_committed_data");
- J_ASSERT_BH(bitmap_bh,
- bh2jh(bitmap_bh)->b_committed_data != NULL);
- ext4_set_bit_atomic(sb_bgl_lock(sbi, block_group), bit + i,
- bh2jh(bitmap_bh)->b_committed_data);
-
- /*
- * We clear the bit in the bitmap after setting the committed
- * data bit, because this is the reverse order to that which
- * the allocator uses.
- */
+ /*
+ * make sure we don't allow a parallel init on other groups in the
+ * same buddy cache
+ */
+ down_write(&grp->alloc_sem);
+ for (i = 0, blocks_freed = 0; i < count; i++) {
BUFFER_TRACE(bitmap_bh, "clear bit");
if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit + i, bitmap_bh->b_data)) {
- jbd_unlock_bh_state(bitmap_bh);
ext4_error(sb, __func__,
"bit already cleared for block %llu",
(ext4_fsblk_t)(block + i));
- jbd_lock_bh_state(bitmap_bh);
BUFFER_TRACE(bitmap_bh, "bit already cleared");
} else {
- group_freed++;
+ blocks_freed++;
}
}
- jbd_unlock_bh_state(bitmap_bh);
-
spin_lock(sb_bgl_lock(sbi, block_group));
- le16_add_cpu(&desc->bg_free_blocks_count, group_freed);
+ blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
+ ext4_free_blks_set(sb, desc, blk_free_count);
desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
spin_unlock(sb_bgl_lock(sbi, block_group));
- percpu_counter_add(&sbi->s_freeblocks_counter, count);
+ percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
spin_lock(sb_bgl_lock(sbi, flex_group));
- sbi->s_flex_groups[flex_group].free_blocks += count;
+ sbi->s_flex_groups[flex_group].free_blocks += blocks_freed;
spin_unlock(sb_bgl_lock(sbi, flex_group));
}
+ /*
+ * request to reload the buddy with the
+ * new bitmap information
+ */
+ set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
+ ext4_mb_update_group_info(grp, blocks_freed);
+ up_write(&grp->alloc_sem);
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
/* And the group descriptor block */
BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
- ret = ext4_journal_dirty_metadata(handle, gd_bh);
- if (!err) err = ret;
- *pdquot_freed_blocks += group_freed;
-
- if (overflow && !err) {
- block += count;
- count = overflow;
- goto do_more;
- }
+ ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
+ if (!err)
+ err = ret;
sb->s_dirt = 1;
+
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, err);
@@ -614,7 +565,7 @@
if (dirty_blocks < 0) {
printk(KERN_CRIT "Dirty block accounting "
"went wrong %lld\n",
- dirty_blocks);
+ (long long)dirty_blocks);
}
}
/* Check whether we have space after
@@ -666,101 +617,45 @@
return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
}
-#define EXT4_META_BLOCK 0x1
-
-static ext4_fsblk_t do_blk_alloc(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, ext4_fsblk_t goal,
- unsigned long *count, int *errp, int flags)
-{
- struct ext4_allocation_request ar;
- ext4_fsblk_t ret;
-
- memset(&ar, 0, sizeof(ar));
- /* Fill with neighbour allocated blocks */
-
- ar.inode = inode;
- ar.goal = goal;
- ar.len = *count;
- ar.logical = iblock;
-
- if (S_ISREG(inode->i_mode) && !(flags & EXT4_META_BLOCK))
- /* enable in-core preallocation for data block allocation */
- ar.flags = EXT4_MB_HINT_DATA;
- else
- /* disable in-core preallocation for non-regular files */
- ar.flags = 0;
-
- ret = ext4_mb_new_blocks(handle, &ar, errp);
- *count = ar.len;
- return ret;
-}
-
/*
* ext4_new_meta_blocks() -- allocate block for meta data (indexing) blocks
*
* @handle: handle to this transaction
* @inode: file inode
* @goal: given target block(filesystem wide)
- * @count: total number of blocks need
+ * @count: pointer to total number of blocks needed
* @errp: error code
*
- * Return 1st allocated block numberon success, *count stores total account
+ * Return 1st allocated block number on success, *count stores total account
* error stores in errp pointer
*/
ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp)
{
+ struct ext4_allocation_request ar;
ext4_fsblk_t ret;
- ret = do_blk_alloc(handle, inode, 0, goal,
- count, errp, EXT4_META_BLOCK);
+
+ memset(&ar, 0, sizeof(ar));
+ /* Fill with neighbour allocated blocks */
+ ar.inode = inode;
+ ar.goal = goal;
+ ar.len = count ? *count : 1;
+
+ ret = ext4_mb_new_blocks(handle, &ar, errp);
+ if (count)
+ *count = ar.len;
+
/*
* Account for the allocated meta blocks
*/
if (!(*errp) && EXT4_I(inode)->i_delalloc_reserved_flag) {
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- EXT4_I(inode)->i_allocated_meta_blocks += *count;
+ EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
}
return ret;
}
-/*
- * ext4_new_meta_block() -- allocate block for meta data (indexing) blocks
- *
- * @handle: handle to this transaction
- * @inode: file inode
- * @goal: given target block(filesystem wide)
- * @errp: error code
- *
- * Return allocated block number on success
- */
-ext4_fsblk_t ext4_new_meta_block(handle_t *handle, struct inode *inode,
- ext4_fsblk_t goal, int *errp)
-{
- unsigned long count = 1;
- return ext4_new_meta_blocks(handle, inode, goal, &count, errp);
-}
-
-/*
- * ext4_new_blocks() -- allocate data blocks
- *
- * @handle: handle to this transaction
- * @inode: file inode
- * @goal: given target block(filesystem wide)
- * @count: total number of blocks need
- * @errp: error code
- *
- * Return 1st allocated block numberon success, *count stores total account
- * error stores in errp pointer
- */
-
-ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, ext4_fsblk_t goal,
- unsigned long *count, int *errp)
-{
- return do_blk_alloc(handle, inode, iblock, goal, count, errp, 0);
-}
-
/**
* ext4_count_free_blocks() -- count filesystem free blocks
* @sb: superblock
@@ -776,7 +671,7 @@
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
ext4_fsblk_t bitmap_count;
- unsigned long x;
+ unsigned int x;
struct buffer_head *bitmap_bh = NULL;
es = EXT4_SB(sb)->s_es;
@@ -796,7 +691,7 @@
continue;
x = ext4_count_free(bitmap_bh, sb->s_blocksize);
- printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
+ printk(KERN_DEBUG "group %lu: stored = %d, counted = %u\n",
i, le16_to_cpu(gdp->bg_free_blocks_count), x);
bitmap_count += x;
}
@@ -812,7 +707,7 @@
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
+ desc_count += ext4_free_blks_count(sb, gdp);
}
return desc_count;
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index 0a7a666..fa3af81 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -15,10 +15,9 @@
static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
-unsigned long ext4_count_free(struct buffer_head *map, unsigned int numchars)
+unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars)
{
- unsigned int i;
- unsigned long sum = 0;
+ unsigned int i, sum = 0;
if (!map)
return 0;
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index fed5b61..2df2e40 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -64,7 +64,7 @@
int ext4_check_dir_entry(const char *function, struct inode *dir,
struct ext4_dir_entry_2 *de,
struct buffer_head *bh,
- unsigned long offset)
+ unsigned int offset)
{
const char *error_msg = NULL;
const int rlen = ext4_rec_len_from_disk(de->rec_len);
@@ -84,9 +84,9 @@
if (error_msg != NULL)
ext4_error(dir->i_sb, function,
"bad entry in directory #%lu: %s - "
- "offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
+ "offset=%u, inode=%u, rec_len=%d, name_len=%d",
dir->i_ino, error_msg, offset,
- (unsigned long) le32_to_cpu(de->inode),
+ le32_to_cpu(de->inode),
rlen, de->name_len);
return error_msg == NULL ? 1 : 0;
}
@@ -95,7 +95,7 @@
void *dirent, filldir_t filldir)
{
int error = 0;
- unsigned long offset;
+ unsigned int offset;
int i, stored;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
@@ -405,7 +405,7 @@
sb = inode->i_sb;
if (!fname) {
- printk(KERN_ERR "ext4: call_filldir: called with "
+ printk(KERN_ERR "EXT4-fs: call_filldir: called with "
"null fname?!?\n");
return 0;
}
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 6c46c64..c668e43 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -19,6 +19,7 @@
#include <linux/types.h>
#include <linux/blkdev.h>
#include <linux/magic.h>
+#include <linux/jbd2.h>
#include "ext4_i.h"
/*
@@ -94,9 +95,9 @@
/* phys. block for ^^^ */
ext4_fsblk_t pright;
/* how many blocks we want to allocate */
- unsigned long len;
+ unsigned int len;
/* flags. see above EXT4_MB_HINT_* */
- unsigned long flags;
+ unsigned int flags;
};
/*
@@ -156,12 +157,12 @@
__le32 bg_block_bitmap_lo; /* Blocks bitmap block */
__le32 bg_inode_bitmap_lo; /* Inodes bitmap block */
__le32 bg_inode_table_lo; /* Inodes table block */
- __le16 bg_free_blocks_count; /* Free blocks count */
- __le16 bg_free_inodes_count; /* Free inodes count */
- __le16 bg_used_dirs_count; /* Directories count */
+ __le16 bg_free_blocks_count_lo;/* Free blocks count */
+ __le16 bg_free_inodes_count_lo;/* Free inodes count */
+ __le16 bg_used_dirs_count_lo; /* Directories count */
__le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */
__u32 bg_reserved[2]; /* Likely block/inode bitmap checksum */
- __le16 bg_itable_unused; /* Unused inodes count */
+ __le16 bg_itable_unused_lo; /* Unused inodes count */
__le16 bg_checksum; /* crc16(sb_uuid+group+desc) */
__le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */
__le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */
@@ -169,7 +170,7 @@
__le16 bg_free_blocks_count_hi;/* Free blocks count MSB */
__le16 bg_free_inodes_count_hi;/* Free inodes count MSB */
__le16 bg_used_dirs_count_hi; /* Directories count MSB */
- __le16 bg_itable_unused_hi; /* Unused inodes count MSB */
+ __le16 bg_itable_unused_hi; /* Unused inodes count MSB */
__u32 bg_reserved2[3];
};
@@ -328,6 +329,7 @@
uid_t s_resuid;
gid_t s_resgid;
unsigned long s_commit_interval;
+ u32 s_min_batch_time, s_max_batch_time;
#ifdef CONFIG_QUOTA
int s_jquota_fmt;
char *s_qf_names[MAXQUOTAS];
@@ -534,7 +536,6 @@
#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
-#define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
#define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */
@@ -726,11 +727,11 @@
*/
#define EXT4_HAS_COMPAT_FEATURE(sb,mask) \
- (EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask))
+ ((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0)
#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \
- (EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask))
+ ((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0)
#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask) \
- (EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask))
+ ((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0)
#define EXT4_SET_COMPAT_FEATURE(sb,mask) \
EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask) \
@@ -806,6 +807,12 @@
#define EXT4_DEFM_JMODE_WBACK 0x0060
/*
+ * Default journal batch times
+ */
+#define EXT4_DEF_MIN_BATCH_TIME 0
+#define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */
+
+/*
* Structure of a directory entry
*/
#define EXT4_NAME_LEN 255
@@ -891,6 +898,9 @@
#define DX_HASH_LEGACY 0
#define DX_HASH_HALF_MD4 1
#define DX_HASH_TEA 2
+#define DX_HASH_LEGACY_UNSIGNED 3
+#define DX_HASH_HALF_MD4_UNSIGNED 4
+#define DX_HASH_TEA_UNSIGNED 5
#ifdef __KERNEL__
@@ -955,7 +965,7 @@
#define ERR_BAD_DX_DIR -75000
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
- unsigned long *blockgrpp, ext4_grpblk_t *offsetp);
+ ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
extern struct proc_dir_entry *ext4_proc_root;
@@ -987,6 +997,9 @@
# define ATTRIB_NORET __attribute__((noreturn))
# define NORET_AND noreturn,
+/* bitmap.c */
+extern unsigned int ext4_count_free(struct buffer_head *, unsigned);
+
/* balloc.c */
extern unsigned int ext4_block_group(struct super_block *sb,
ext4_fsblk_t blocknr);
@@ -995,20 +1008,14 @@
extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
ext4_group_t group);
-extern ext4_fsblk_t ext4_new_meta_block(handle_t *handle, struct inode *inode,
- ext4_fsblk_t goal, int *errp);
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp);
-extern ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, ext4_fsblk_t goal,
- unsigned long *count, int *errp);
extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
extern int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t block, unsigned long count, int metadata);
-extern void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
- ext4_fsblk_t block, unsigned long count,
- unsigned long *pdquot_freed_blocks);
+extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+ ext4_fsblk_t block, unsigned long count);
extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
extern void ext4_check_blocks_bitmap(struct super_block *);
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
@@ -1019,7 +1026,7 @@
/* dir.c */
extern int ext4_check_dir_entry(const char *, struct inode *,
struct ext4_dir_entry_2 *,
- struct buffer_head *, unsigned long);
+ struct buffer_head *, unsigned int);
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext4_dir_entry_2 *dirent);
@@ -1039,7 +1046,6 @@
extern unsigned long ext4_count_free_inodes(struct super_block *);
extern unsigned long ext4_count_dirs(struct super_block *);
extern void ext4_check_inodes_bitmap(struct super_block *);
-extern unsigned long ext4_count_free(struct buffer_head *, unsigned);
/* mballoc.c */
extern long ext4_mb_stats;
@@ -1054,12 +1060,13 @@
extern void exit_ext4_mballoc(void);
extern void ext4_mb_free_blocks(handle_t *, struct inode *,
unsigned long, unsigned long, int, unsigned long *);
-extern int ext4_mb_add_more_groupinfo(struct super_block *sb,
+extern int ext4_mb_add_groupinfo(struct super_block *sb,
ext4_group_t i, struct ext4_group_desc *desc);
extern void ext4_mb_update_group_info(struct ext4_group_info *grp,
ext4_grpblk_t add);
-
-
+extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
+extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
+ ext4_group_t, int);
/* inode.c */
int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr);
@@ -1069,10 +1076,6 @@
ext4_lblk_t, int, int *);
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
-int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, unsigned long maxblocks,
- struct buffer_head *bh_result,
- int create, int extend_disksize);
extern struct inode *ext4_iget(struct super_block *, unsigned long);
extern int ext4_write_inode(struct inode *, int);
@@ -1123,6 +1126,9 @@
__attribute__ ((format (printf, 3, 4)));
extern void ext4_warning(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
+extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
+ const char *, const char *, ...)
+ __attribute__ ((format (printf, 4, 5)));
extern void ext4_update_dynamic_rev(struct super_block *sb);
extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
__u32 compat);
@@ -1136,12 +1142,28 @@
struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg);
+extern __u32 ext4_free_blks_count(struct super_block *sb,
+ struct ext4_group_desc *bg);
+extern __u32 ext4_free_inodes_count(struct super_block *sb,
+ struct ext4_group_desc *bg);
+extern __u32 ext4_used_dirs_count(struct super_block *sb,
+ struct ext4_group_desc *bg);
+extern __u32 ext4_itable_unused_count(struct super_block *sb,
+ struct ext4_group_desc *bg);
extern void ext4_block_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
+extern void ext4_free_blks_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count);
+extern void ext4_free_inodes_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count);
+extern void ext4_used_dirs_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count);
+extern void ext4_itable_unused_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count);
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
@@ -1246,6 +1268,50 @@
return ;
}
+struct ext4_group_info {
+ unsigned long bb_state;
+ struct rb_root bb_free_root;
+ unsigned short bb_first_free;
+ unsigned short bb_free;
+ unsigned short bb_fragments;
+ struct list_head bb_prealloc_list;
+#ifdef DOUBLE_CHECK
+ void *bb_bitmap;
+#endif
+ struct rw_semaphore alloc_sem;
+ unsigned short bb_counters[];
+};
+
+#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
+#define EXT4_GROUP_INFO_LOCKED_BIT 1
+
+#define EXT4_MB_GRP_NEED_INIT(grp) \
+ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+
+static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
+{
+ struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+ bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+}
+
+static inline void ext4_unlock_group(struct super_block *sb,
+ ext4_group_t group)
+{
+ struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+ bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+}
+
+static inline int ext4_is_group_locked(struct super_block *sb,
+ ext4_group_t group)
+{
+ struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+ return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
+ &(grinfo->bb_state));
+}
+
/*
* Inodes and files operations
*/
@@ -1271,18 +1337,38 @@
extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
int chunk);
extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock,
- unsigned long max_blocks, struct buffer_head *bh_result,
- int create, int extend_disksize);
+ ext4_lblk_t iblock, unsigned int max_blocks,
+ struct buffer_head *bh_result,
+ int create, int extend_disksize);
extern void ext4_ext_truncate(struct inode *);
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
loff_t len);
extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode,
- sector_t block, unsigned long max_blocks,
+ sector_t block, unsigned int max_blocks,
struct buffer_head *bh, int create,
int extend_disksize, int flag);
+extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ __u64 start, __u64 len);
+
+/*
+ * Add new method to test wether block and inode bitmaps are properly
+ * initialized. With uninit_bg reading the block from disk is not enough
+ * to mark the bitmap uptodate. We need to also zero-out the bitmap
+ */
+#define BH_BITMAP_UPTODATE BH_JBDPrivateStart
+
+static inline int bitmap_uptodate(struct buffer_head *bh)
+{
+ return (buffer_uptodate(bh) &&
+ test_bit(BH_BITMAP_UPTODATE, &(bh)->b_state));
+}
+static inline void set_bitmap_uptodate(struct buffer_head *bh)
+{
+ set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
+}
+
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index bec7ce5..18cb67b 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -194,11 +194,6 @@
return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
}
-static inline void ext4_ext_tree_changed(struct inode *inode)
-{
- EXT4_I(inode)->i_ext_generation++;
-}
-
static inline void
ext4_ext_invalidate_cache(struct inode *inode)
{
diff --git a/fs/ext4/ext4_i.h b/fs/ext4/ext4_i.h
index 5c124c0..e69acc1 100644
--- a/fs/ext4/ext4_i.h
+++ b/fs/ext4/ext4_i.h
@@ -31,7 +31,7 @@
typedef __u32 ext4_lblk_t;
/* data type for block group number */
-typedef unsigned long ext4_group_t;
+typedef unsigned int ext4_group_t;
#define rsv_start rsv_window._rsv_start
#define rsv_end rsv_window._rsv_end
@@ -100,9 +100,6 @@
*/
loff_t i_disksize;
- /* on-disk additional length */
- __u16 i_extra_isize;
-
/*
* i_data_sem is for serialising ext4_truncate() against
* ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's
@@ -117,7 +114,6 @@
struct inode vfs_inode;
struct jbd2_inode jinode;
- unsigned long i_ext_generation;
struct ext4_ext_cache i_cached_extent;
/*
* File creation time. Its function is same as that of
@@ -130,10 +126,14 @@
spinlock_t i_prealloc_lock;
/* allocation reservation info for delalloc */
- unsigned long i_reserved_data_blocks;
- unsigned long i_reserved_meta_blocks;
- unsigned long i_allocated_meta_blocks;
+ unsigned int i_reserved_data_blocks;
+ unsigned int i_reserved_meta_blocks;
+ unsigned int i_allocated_meta_blocks;
unsigned short i_delalloc_reserved_flag;
+
+ /* on-disk additional length */
+ __u16 i_extra_isize;
+
spinlock_t i_block_reservation_lock;
};
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index c75384b..ad13a84 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -7,53 +7,96 @@
int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
struct buffer_head *bh)
{
- int err = jbd2_journal_get_undo_access(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_get_undo_access(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
int __ext4_journal_get_write_access(const char *where, handle_t *handle,
struct buffer_head *bh)
{
- int err = jbd2_journal_get_write_access(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_get_write_access(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
int __ext4_journal_forget(const char *where, handle_t *handle,
struct buffer_head *bh)
{
- int err = jbd2_journal_forget(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_forget(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
int __ext4_journal_revoke(const char *where, handle_t *handle,
ext4_fsblk_t blocknr, struct buffer_head *bh)
{
- int err = jbd2_journal_revoke(handle, blocknr, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_revoke(handle, blocknr, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
int __ext4_journal_get_create_access(const char *where,
handle_t *handle, struct buffer_head *bh)
{
- int err = jbd2_journal_get_create_access(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_get_create_access(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
-int __ext4_journal_dirty_metadata(const char *where,
- handle_t *handle, struct buffer_head *bh)
+int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
+ struct inode *inode, struct buffer_head *bh)
{
- int err = jbd2_journal_dirty_metadata(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_dirty_metadata(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ } else {
+ mark_buffer_dirty(bh);
+ if (inode && inode_needs_sync(inode)) {
+ sync_dirty_buffer(bh);
+ if (buffer_req(bh) && !buffer_uptodate(bh)) {
+ ext4_error(inode->i_sb, __func__,
+ "IO error syncing inode, "
+ "inode=%lu, block=%llu",
+ inode->i_ino,
+ (unsigned long long) bh->b_blocknr);
+ err = -EIO;
+ }
+ }
+ }
return err;
}
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index b455c68..be2f426 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -32,8 +32,8 @@
* 5 levels of tree + root which are stored in the inode. */
#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \
- (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \
- || test_opt(sb, EXTENTS) ? 27U : 8U)
+ (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \
+ ? 27U : 8U)
/* Extended attribute operations touch at most two data buffers,
* two bitmap buffers, and two group summaries, in addition to the inode
@@ -122,12 +122,6 @@
* been done yet.
*/
-static inline void ext4_journal_release_buffer(handle_t *handle,
- struct buffer_head *bh)
-{
- jbd2_journal_release_buffer(handle, bh);
-}
-
void ext4_journal_abort_handle(const char *caller, const char *err_fn,
struct buffer_head *bh, handle_t *handle, int err);
@@ -146,8 +140,8 @@
int __ext4_journal_get_create_access(const char *where,
handle_t *handle, struct buffer_head *bh);
-int __ext4_journal_dirty_metadata(const char *where,
- handle_t *handle, struct buffer_head *bh);
+int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
+ struct inode *inode, struct buffer_head *bh);
#define ext4_journal_get_undo_access(handle, bh) \
__ext4_journal_get_undo_access(__func__, (handle), (bh))
@@ -157,14 +151,57 @@
__ext4_journal_revoke(__func__, (handle), (blocknr), (bh))
#define ext4_journal_get_create_access(handle, bh) \
__ext4_journal_get_create_access(__func__, (handle), (bh))
-#define ext4_journal_dirty_metadata(handle, bh) \
- __ext4_journal_dirty_metadata(__func__, (handle), (bh))
#define ext4_journal_forget(handle, bh) \
__ext4_journal_forget(__func__, (handle), (bh))
+#define ext4_handle_dirty_metadata(handle, inode, bh) \
+ __ext4_handle_dirty_metadata(__func__, (handle), (inode), (bh))
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
int __ext4_journal_stop(const char *where, handle_t *handle);
+#define EXT4_NOJOURNAL_HANDLE ((handle_t *) 0x1)
+
+static inline int ext4_handle_valid(handle_t *handle)
+{
+ if (handle == EXT4_NOJOURNAL_HANDLE)
+ return 0;
+ return 1;
+}
+
+static inline void ext4_handle_sync(handle_t *handle)
+{
+ if (ext4_handle_valid(handle))
+ handle->h_sync = 1;
+}
+
+static inline void ext4_handle_release_buffer(handle_t *handle,
+ struct buffer_head *bh)
+{
+ if (ext4_handle_valid(handle))
+ jbd2_journal_release_buffer(handle, bh);
+}
+
+static inline int ext4_handle_is_aborted(handle_t *handle)
+{
+ if (ext4_handle_valid(handle))
+ return is_handle_aborted(handle);
+ return 0;
+}
+
+static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
+{
+ if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed)
+ return 0;
+ return 1;
+}
+
+static inline void ext4_journal_release_buffer(handle_t *handle,
+ struct buffer_head *bh)
+{
+ if (ext4_handle_valid(handle))
+ jbd2_journal_release_buffer(handle, bh);
+}
+
static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
{
return ext4_journal_start_sb(inode->i_sb, nblocks);
@@ -180,27 +217,37 @@
static inline int ext4_journal_extend(handle_t *handle, int nblocks)
{
- return jbd2_journal_extend(handle, nblocks);
+ if (ext4_handle_valid(handle))
+ return jbd2_journal_extend(handle, nblocks);
+ return 0;
}
static inline int ext4_journal_restart(handle_t *handle, int nblocks)
{
- return jbd2_journal_restart(handle, nblocks);
+ if (ext4_handle_valid(handle))
+ return jbd2_journal_restart(handle, nblocks);
+ return 0;
}
static inline int ext4_journal_blocks_per_page(struct inode *inode)
{
- return jbd2_journal_blocks_per_page(inode);
+ if (EXT4_JOURNAL(inode) != NULL)
+ return jbd2_journal_blocks_per_page(inode);
+ return 0;
}
static inline int ext4_journal_force_commit(journal_t *journal)
{
- return jbd2_journal_force_commit(journal);
+ if (journal)
+ return jbd2_journal_force_commit(journal);
+ return 0;
}
static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
{
- return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+ if (ext4_handle_valid(handle))
+ return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+ return 0;
}
/* super.c */
@@ -208,6 +255,8 @@
static inline int ext4_should_journal_data(struct inode *inode)
{
+ if (EXT4_JOURNAL(inode) == NULL)
+ return 0;
if (!S_ISREG(inode->i_mode))
return 1;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
@@ -219,6 +268,8 @@
static inline int ext4_should_order_data(struct inode *inode)
{
+ if (EXT4_JOURNAL(inode) == NULL)
+ return 0;
if (!S_ISREG(inode->i_mode))
return 0;
if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
@@ -230,6 +281,8 @@
static inline int ext4_should_writeback_data(struct inode *inode)
{
+ if (EXT4_JOURNAL(inode) == NULL)
+ return 0;
if (!S_ISREG(inode->i_mode))
return 0;
if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h
index b21f167..039b6ea 100644
--- a/fs/ext4/ext4_sb.h
+++ b/fs/ext4/ext4_sb.h
@@ -57,6 +57,7 @@
u32 s_next_generation;
u32 s_hash_seed[4];
int s_def_hash_version;
+ int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
struct percpu_counter s_freeblocks_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
@@ -73,6 +74,8 @@
struct journal_s *s_journal;
struct list_head s_orphan;
unsigned long s_commit_interval;
+ u32 s_max_batch_time;
+ u32 s_min_batch_time;
struct block_device *journal_bdev;
#ifdef CONFIG_JBD2_DEBUG
struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */
@@ -101,7 +104,8 @@
spinlock_t s_reserve_lock;
spinlock_t s_md_lock;
tid_t s_last_transaction;
- unsigned short *s_mb_offsets, *s_mb_maxs;
+ unsigned short *s_mb_offsets;
+ unsigned int *s_mb_maxs;
/* tunables */
unsigned long s_stripe;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3f54db3..54bf062 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -97,6 +97,8 @@
{
int err;
+ if (!ext4_handle_valid(handle))
+ return 0;
if (handle->h_buffer_credits > needed)
return 0;
err = ext4_journal_extend(handle, needed);
@@ -134,7 +136,7 @@
int err;
if (path->p_bh) {
/* path points to block */
- err = ext4_journal_dirty_metadata(handle, path->p_bh);
+ err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
} else {
/* path points to leaf/index in inode body */
err = ext4_mark_inode_dirty(handle, inode);
@@ -191,7 +193,7 @@
ext4_fsblk_t goal, newblock;
goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
- newblock = ext4_new_meta_block(handle, inode, goal, err);
+ newblock = ext4_new_meta_blocks(handle, inode, goal, NULL, err);
return newblock;
}
@@ -780,7 +782,7 @@
set_buffer_uptodate(bh);
unlock_buffer(bh);
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto cleanup;
brelse(bh);
@@ -859,7 +861,7 @@
set_buffer_uptodate(bh);
unlock_buffer(bh);
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto cleanup;
brelse(bh);
@@ -955,7 +957,7 @@
set_buffer_uptodate(bh);
unlock_buffer(bh);
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto out;
@@ -1160,15 +1162,13 @@
while (--depth >= 0) {
ix = path[depth].p_idx;
if (ix != EXT_LAST_INDEX(path[depth].p_hdr))
- break;
+ goto got_index;
}
- if (depth < 0) {
- /* we've gone up to the root and
- * found no index to the right */
- return 0;
- }
+ /* we've gone up to the root and found no index to the right */
+ return 0;
+got_index:
/* we've found index to the right, let's
* follow it and find the closest allocated
* block to the right */
@@ -1201,7 +1201,6 @@
*phys = ext_pblock(ex);
put_bh(bh);
return 0;
-
}
/*
@@ -1622,7 +1621,6 @@
ext4_ext_drop_refs(npath);
kfree(npath);
}
- ext4_ext_tree_changed(inode);
ext4_ext_invalidate_cache(inode);
return err;
}
@@ -2233,7 +2231,6 @@
}
}
out:
- ext4_ext_tree_changed(inode);
ext4_ext_drop_refs(path);
kfree(path);
ext4_journal_stop(handle);
@@ -2250,7 +2247,7 @@
* possible initialization would be here
*/
- if (test_opt(sb, EXTENTS)) {
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
printk(KERN_INFO "EXT4-fs: file extents enabled");
#ifdef AGGRESSIVE_TEST
printk(", aggressive tests");
@@ -2275,7 +2272,7 @@
*/
void ext4_ext_release(struct super_block *sb)
{
- if (!test_opt(sb, EXTENTS))
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
return;
#ifdef EXTENTS_STATS
@@ -2380,7 +2377,7 @@
struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t iblock,
- unsigned long max_blocks)
+ unsigned int max_blocks)
{
struct ext4_extent *ex, newex, orig_ex;
struct ext4_extent *ex1 = NULL;
@@ -2678,26 +2675,26 @@
*/
int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock,
- unsigned long max_blocks, struct buffer_head *bh_result,
+ unsigned int max_blocks, struct buffer_head *bh_result,
int create, int extend_disksize)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent_header *eh;
struct ext4_extent newex, *ex;
- ext4_fsblk_t goal, newblock;
- int err = 0, depth, ret;
- unsigned long allocated = 0;
+ ext4_fsblk_t newblock;
+ int err = 0, depth, ret, cache_type;
+ unsigned int allocated = 0;
struct ext4_allocation_request ar;
loff_t disksize;
__clear_bit(BH_New, &bh_result->b_state);
- ext_debug("blocks %u/%lu requested for inode %u\n",
+ ext_debug("blocks %u/%u requested for inode %u\n",
iblock, max_blocks, inode->i_ino);
/* check in cache */
- goal = ext4_ext_in_cache(inode, iblock, &newex);
- if (goal) {
- if (goal == EXT4_EXT_CACHE_GAP) {
+ cache_type = ext4_ext_in_cache(inode, iblock, &newex);
+ if (cache_type) {
+ if (cache_type == EXT4_EXT_CACHE_GAP) {
if (!create) {
/*
* block isn't allocated yet and
@@ -2706,7 +2703,7 @@
goto out2;
}
/* we should allocate requested block */
- } else if (goal == EXT4_EXT_CACHE_EXTENT) {
+ } else if (cache_type == EXT4_EXT_CACHE_EXTENT) {
/* block is already allocated */
newblock = iblock
- le32_to_cpu(newex.ee_block)
@@ -2854,7 +2851,7 @@
if (!newblock)
goto out2;
ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
- goal, newblock, allocated);
+ ar.goal, newblock, allocated);
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock);
@@ -2950,7 +2947,7 @@
* transaction synchronous.
*/
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
out_stop:
up_write(&EXT4_I(inode)->i_data_sem);
@@ -3004,7 +3001,7 @@
handle_t *handle;
ext4_lblk_t block;
loff_t new_size;
- unsigned long max_blocks;
+ unsigned int max_blocks;
int ret = 0;
int ret2 = 0;
int retries = 0;
@@ -3083,7 +3080,7 @@
/*
* Callback function called for each extent to gather FIEMAP information.
*/
-int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
+static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
struct ext4_ext_cache *newex, struct ext4_extent *ex,
void *data)
{
@@ -3152,7 +3149,8 @@
/* fiemap flags we can handle specified here */
#define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
-int ext4_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo)
+static int ext4_xattr_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo)
{
__u64 physical = 0;
__u64 length;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6bd11fb..f731cb5 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -140,9 +140,6 @@
return 0;
}
-extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
- __u64 start, __u64 len);
-
const struct file_operations ext4_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 556ca8e..ac8f168 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -35,23 +35,43 @@
/* The old legacy hash */
-static __u32 dx_hack_hash(const char *name, int len)
+static __u32 dx_hack_hash_unsigned(const char *name, int len)
{
- __u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
- while (len--) {
- __u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
+ __u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+ const unsigned char *ucp = (const unsigned char *) name;
- if (hash & 0x80000000) hash -= 0x7fffffff;
+ while (len--) {
+ hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373));
+
+ if (hash & 0x80000000)
+ hash -= 0x7fffffff;
hash1 = hash0;
hash0 = hash;
}
- return (hash0 << 1);
+ return hash0 << 1;
}
-static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+static __u32 dx_hack_hash_signed(const char *name, int len)
+{
+ __u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+ const signed char *scp = (const signed char *) name;
+
+ while (len--) {
+ hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));
+
+ if (hash & 0x80000000)
+ hash -= 0x7fffffff;
+ hash1 = hash0;
+ hash0 = hash;
+ }
+ return hash0 << 1;
+}
+
+static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
{
__u32 pad, val;
int i;
+ const signed char *scp = (const signed char *) msg;
pad = (__u32)len | ((__u32)len << 8);
pad |= pad << 16;
@@ -62,7 +82,35 @@
for (i = 0; i < len; i++) {
if ((i % 4) == 0)
val = pad;
- val = msg[i] + (val << 8);
+ val = ((int) scp[i]) + (val << 8);
+ if ((i % 4) == 3) {
+ *buf++ = val;
+ val = pad;
+ num--;
+ }
+ }
+ if (--num >= 0)
+ *buf++ = val;
+ while (--num >= 0)
+ *buf++ = pad;
+}
+
+static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
+{
+ __u32 pad, val;
+ int i;
+ const unsigned char *ucp = (const unsigned char *) msg;
+
+ pad = (__u32)len | ((__u32)len << 8);
+ pad |= pad << 16;
+
+ val = pad;
+ if (len > num*4)
+ len = num * 4;
+ for (i = 0; i < len; i++) {
+ if ((i % 4) == 0)
+ val = pad;
+ val = ((int) ucp[i]) + (val << 8);
if ((i % 4) == 3) {
*buf++ = val;
val = pad;
@@ -95,6 +143,8 @@
const char *p;
int i;
__u32 in[8], buf[4];
+ void (*str2hashbuf)(const char *, int, __u32 *, int) =
+ str2hashbuf_signed;
/* Initialize the default seed for the hash checksum functions */
buf[0] = 0x67452301;
@@ -113,13 +163,18 @@
}
switch (hinfo->hash_version) {
- case DX_HASH_LEGACY:
- hash = dx_hack_hash(name, len);
+ case DX_HASH_LEGACY_UNSIGNED:
+ hash = dx_hack_hash_unsigned(name, len);
break;
+ case DX_HASH_LEGACY:
+ hash = dx_hack_hash_signed(name, len);
+ break;
+ case DX_HASH_HALF_MD4_UNSIGNED:
+ str2hashbuf = str2hashbuf_unsigned;
case DX_HASH_HALF_MD4:
p = name;
while (len > 0) {
- str2hashbuf(p, len, in, 8);
+ (*str2hashbuf)(p, len, in, 8);
half_md4_transform(buf, in);
len -= 32;
p += 32;
@@ -127,10 +182,12 @@
minor_hash = buf[2];
hash = buf[1];
break;
+ case DX_HASH_TEA_UNSIGNED:
+ str2hashbuf = str2hashbuf_unsigned;
case DX_HASH_TEA:
p = name;
while (len > 0) {
- str2hashbuf(p, len, in, 4);
+ (*str2hashbuf)(p, len, in, 4);
TEA_transform(buf, in);
len -= 16;
p += 16;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 6e60528..4fb86a0 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -74,17 +74,17 @@
/* 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 %lu\n",
+ ext4_error(sb, __func__, "Checksum bad for group %u",
block_group);
- gdp->bg_free_blocks_count = 0;
- gdp->bg_free_inodes_count = 0;
- gdp->bg_itable_unused = 0;
+ ext4_free_blks_set(sb, gdp, 0);
+ ext4_free_inodes_set(sb, gdp, 0);
+ ext4_itable_unused_set(sb, gdp, 0);
memset(bh->b_data, 0xff, sb->s_blocksize);
return 0;
}
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);
@@ -111,29 +111,49 @@
if (unlikely(!bh)) {
ext4_error(sb, __func__,
"Cannot read inode bitmap - "
- "block_group = %lu, inode_bitmap = %llu",
+ "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);
+ if (bitmap_uptodate(bh)) {
+ unlock_buffer(bh);
+ return bh;
+ }
spin_lock(sb_bgl_lock(EXT4_SB(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);
- unlock_buffer(bh);
spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+ unlock_buffer(bh);
return bh;
}
spin_unlock(sb_bgl_lock(EXT4_SB(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;
+ }
+ /*
+ * 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 - "
- "block_group = %lu, inode_bitmap = %llu",
+ "block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
}
@@ -168,7 +188,7 @@
struct ext4_group_desc *gdp;
struct ext4_super_block *es;
struct ext4_sb_info *sbi;
- int fatal = 0, err;
+ int fatal = 0, err, count;
ext4_group_t flex_group;
if (atomic_read(&inode->i_count) > 1) {
@@ -190,6 +210,11 @@
ino = inode->i_ino;
ext4_debug("freeing inode %lu\n", ino);
+ trace_mark(ext4_free_inode,
+ "dev %s ino %lu mode %d uid %lu gid %lu bocks %llu",
+ sb->s_id, inode->i_ino, inode->i_mode,
+ (unsigned long) inode->i_uid, (unsigned long) inode->i_gid,
+ (unsigned long long) inode->i_blocks);
/*
* Note: we must free any quota before locking the superblock,
@@ -236,9 +261,12 @@
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);
+ 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);
+ }
gdp->bg_checksum = ext4_group_desc_csum(sbi,
block_group, gdp);
spin_unlock(sb_bgl_lock(sbi, block_group));
@@ -253,12 +281,12 @@
spin_unlock(sb_bgl_lock(sbi, flex_group));
}
}
- BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh2);
+ BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, bh2);
if (!fatal) fatal = err;
}
- BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!fatal)
fatal = err;
sb->s_dirt = 1;
@@ -291,13 +319,13 @@
for (group = 0; group < ngroups; group++) {
desc = ext4_get_group_desc(sb, group, NULL);
- if (!desc || !desc->bg_free_inodes_count)
+ if (!desc || !ext4_free_inodes_count(sb, desc))
continue;
- if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+ if (ext4_free_inodes_count(sb, desc) < avefreei)
continue;
if (!best_desc ||
- (le16_to_cpu(desc->bg_free_blocks_count) >
- le16_to_cpu(best_desc->bg_free_blocks_count))) {
+ (ext4_free_blks_count(sb, desc) >
+ ext4_free_blks_count(sb, best_desc))) {
*best_group = group;
best_desc = desc;
ret = 0;
@@ -369,7 +397,7 @@
for (i = best_flex * flex_size; i < ngroups &&
i < (best_flex + 1) * flex_size; i++) {
desc = ext4_get_group_desc(sb, i, &bh);
- if (le16_to_cpu(desc->bg_free_inodes_count)) {
+ if (ext4_free_inodes_count(sb, desc)) {
*best_group = i;
goto out;
}
@@ -443,17 +471,17 @@
for (i = 0; i < ngroups; i++) {
grp = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, grp, NULL);
- if (!desc || !desc->bg_free_inodes_count)
+ if (!desc || !ext4_free_inodes_count(sb, desc))
continue;
- if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
+ if (ext4_used_dirs_count(sb, desc) >= best_ndir)
continue;
- if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+ if (ext4_free_inodes_count(sb, desc) < avefreei)
continue;
- if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
+ if (ext4_free_blks_count(sb, desc) < avefreeb)
continue;
*group = grp;
ret = 0;
- best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
+ best_ndir = ext4_used_dirs_count(sb, desc);
}
if (ret == 0)
return ret;
@@ -479,13 +507,13 @@
for (i = 0; i < ngroups; i++) {
*group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (!desc || !desc->bg_free_inodes_count)
+ if (!desc || !ext4_free_inodes_count(sb, desc))
continue;
- if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
+ if (ext4_used_dirs_count(sb, desc) >= max_dirs)
continue;
- if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
+ if (ext4_free_inodes_count(sb, desc) < min_inodes)
continue;
- if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
+ if (ext4_free_blks_count(sb, desc) < min_blocks)
continue;
return 0;
}
@@ -494,8 +522,8 @@
for (i = 0; i < ngroups; i++) {
*group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (desc && desc->bg_free_inodes_count &&
- le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
+ if (desc && ext4_free_inodes_count(sb, desc) &&
+ ext4_free_inodes_count(sb, desc) >= avefreei)
return 0;
}
@@ -524,8 +552,8 @@
*/
*group = parent_group;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
- le16_to_cpu(desc->bg_free_blocks_count))
+ if (desc && ext4_free_inodes_count(sb, desc) &&
+ ext4_free_blks_count(sb, desc))
return 0;
/*
@@ -548,8 +576,8 @@
if (*group >= ngroups)
*group -= ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
- le16_to_cpu(desc->bg_free_blocks_count))
+ if (desc && ext4_free_inodes_count(sb, desc) &&
+ ext4_free_blks_count(sb, desc))
return 0;
}
@@ -562,7 +590,7 @@
if (++*group >= ngroups)
*group = 0;
desc = ext4_get_group_desc(sb, *group, NULL);
- if (desc && le16_to_cpu(desc->bg_free_inodes_count))
+ if (desc && ext4_free_inodes_count(sb, desc))
return 0;
}
@@ -570,6 +598,79 @@
}
/*
+ * claim the inode from the inode bitmap. If the group
+ * is uninit we need to take the groups's sb_bgl_lock
+ * and clear the uninit flag. The inode bitmap update
+ * and group desc uninit flag clear should be done
+ * after holding sb_bgl_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);
+
+ spin_lock(sb_bgl_lock(sbi, 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)) {
+ spin_unlock(sb_bgl_lock(sbi, group));
+ ext4_error(sb, __func__,
+ "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);
+ }
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+err_ret:
+ spin_unlock(sb_bgl_lock(sbi, 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
@@ -582,8 +683,8 @@
struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
{
struct super_block *sb;
- struct buffer_head *bitmap_bh = NULL;
- struct buffer_head *bh2;
+ struct buffer_head *inode_bitmap_bh = NULL;
+ struct buffer_head *group_desc_bh;
ext4_group_t group = 0;
unsigned long ino = 0;
struct inode *inode;
@@ -602,6 +703,8 @@
return ERR_PTR(-EPERM);
sb = dir->i_sb;
+ trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id,
+ dir->i_ino, mode);
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
@@ -631,40 +734,52 @@
for (i = 0; i < sbi->s_groups_count; i++) {
err = -EIO;
- gdp = ext4_get_group_desc(sb, group, &bh2);
+ gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
if (!gdp)
goto fail;
- brelse(bitmap_bh);
- bitmap_bh = ext4_read_inode_bitmap(sb, group);
- if (!bitmap_bh)
+ brelse(inode_bitmap_bh);
+ inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
+ if (!inode_bitmap_bh)
goto fail;
ino = 0;
repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
- bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino);
+ inode_bitmap_bh->b_data,
+ EXT4_INODES_PER_GROUP(sb), ino);
+
if (ino < EXT4_INODES_PER_GROUP(sb)) {
- BUFFER_TRACE(bitmap_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, bitmap_bh);
+ BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle,
+ inode_bitmap_bh);
if (err)
goto fail;
- if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
- ino, 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(bitmap_bh,
- "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle,
- bitmap_bh);
+ BUFFER_TRACE(inode_bitmap_bh,
+ "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle,
+ inode,
+ inode_bitmap_bh);
if (err)
goto fail;
+ /* zero bit is inode number 1*/
+ ino++;
goto got;
}
/* we lost it */
- jbd2_journal_release_buffer(handle, bitmap_bh);
+ 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;
@@ -684,30 +799,16 @@
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 = %lu, inode=%lu", group,
- ino + group * EXT4_INODES_PER_GROUP(sb));
- err = -EIO;
- goto fail;
- }
-
- BUFFER_TRACE(bh2, "get_write_access");
- err = ext4_journal_get_write_access(handle, bh2);
- 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)) {
- struct buffer_head *block_bh = ext4_read_block_bitmap(sb, group);
+ struct buffer_head *block_bitmap_bh;
- BUFFER_TRACE(block_bh, "get block bitmap access");
- err = ext4_journal_get_write_access(handle, block_bh);
+ block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+ BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
+ err = ext4_journal_get_write_access(handle, block_bitmap_bh);
if (err) {
- brelse(block_bh);
+ brelse(block_bitmap_bh);
goto fail;
}
@@ -715,9 +816,9 @@
spin_lock(sb_bgl_lock(sbi, group));
/* recheck and clear flag under lock if we still need to */
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
- gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
free = ext4_free_blocks_after_init(sb, group, gdp);
- gdp->bg_free_blocks_count = cpu_to_le16(free);
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+ ext4_free_blks_set(sb, gdp, free);
gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
gdp);
}
@@ -725,55 +826,19 @@
/* Don't need to dirty bitmap block if we didn't change it */
if (free) {
- BUFFER_TRACE(block_bh, "dirty block bitmap");
- err = ext4_journal_dirty_metadata(handle, block_bh);
+ BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
+ err = ext4_handle_dirty_metadata(handle,
+ NULL, block_bitmap_bh);
}
- brelse(block_bh);
+ brelse(block_bitmap_bh);
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) -
- le16_to_cpu(gdp->bg_itable_unused);
- }
-
- /*
- * 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)
- gdp->bg_itable_unused =
- cpu_to_le16(EXT4_INODES_PER_GROUP(sb) - ino);
- }
-
- le16_add_cpu(&gdp->bg_free_inodes_count, -1);
- if (S_ISDIR(mode)) {
- le16_add_cpu(&gdp->bg_used_dirs_count, 1);
- }
- gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
- spin_unlock(sb_bgl_lock(sbi, group));
- BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh2);
- if (err) goto fail;
+ BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
+ if (err)
+ goto fail;
percpu_counter_dec(&sbi->s_freeinodes_counter);
if (S_ISDIR(mode))
@@ -825,7 +890,7 @@
ext4_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
if (insert_inode_locked(inode) < 0) {
err = -EINVAL;
goto fail_drop;
@@ -852,7 +917,7 @@
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;
@@ -867,6 +932,8 @@
}
ext4_debug("allocating inode %lu\n", inode->i_ino);
+ trace_mark(ext4_allocate_inode, "dev %s ino %lu dir %lu mode %d",
+ sb->s_id, inode->i_ino, dir->i_ino, mode);
goto really_out;
fail:
ext4_std_error(sb, err);
@@ -874,7 +941,7 @@
iput(inode);
ret = ERR_PTR(err);
really_out:
- brelse(bitmap_bh);
+ brelse(inode_bitmap_bh);
return ret;
fail_free_drop:
@@ -886,7 +953,7 @@
inode->i_nlink = 0;
unlock_new_inode(inode);
iput(inode);
- brelse(bitmap_bh);
+ brelse(inode_bitmap_bh);
return ERR_PTR(err);
}
@@ -985,7 +1052,7 @@
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+ desc_count += ext4_free_inodes_count(sb, gdp);
brelse(bitmap_bh);
bitmap_bh = ext4_read_inode_bitmap(sb, i);
if (!bitmap_bh)
@@ -993,7 +1060,7 @@
x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
- i, le16_to_cpu(gdp->bg_free_inodes_count), x);
+ i, ext4_free_inodes_count(sb, gdp), x);
bitmap_count += x;
}
brelse(bitmap_bh);
@@ -1007,7 +1074,7 @@
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+ desc_count += ext4_free_inodes_count(sb, gdp);
cond_resched();
}
return desc_count;
@@ -1024,8 +1091,7 @@
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- count += le16_to_cpu(gdp->bg_used_dirs_count);
+ count += ext4_used_dirs_count(sb, gdp);
}
return count;
}
-
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 98d3fe7..a6444ce 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -72,12 +72,17 @@
* "bh" may be NULL: a metadata block may have been freed from memory
* but there may still be a record of it in the journal, and that record
* still needs to be revoked.
+ *
+ * If the handle isn't valid we're not journaling so there's nothing to do.
*/
int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr)
{
int err;
+ if (!ext4_handle_valid(handle))
+ return 0;
+
might_sleep();
BUFFER_TRACE(bh, "enter");
@@ -170,7 +175,9 @@
*/
static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
{
- if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS)
+ if (!ext4_handle_valid(handle))
+ return 0;
+ if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
return 0;
if (!ext4_journal_extend(handle, blocks_for_truncate(inode)))
return 0;
@@ -184,6 +191,7 @@
*/
static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
{
+ BUG_ON(EXT4_JOURNAL(inode) == NULL);
jbd_debug(2, "restarting handle %p\n", handle);
return ext4_journal_restart(handle, blocks_for_truncate(inode));
}
@@ -216,7 +224,7 @@
}
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
@@ -233,7 +241,7 @@
* enough credits left in the handle to remove the inode from
* the orphan list and set the dtime field.
*/
- if (handle->h_buffer_credits < 3) {
+ if (!ext4_handle_has_enough_credits(handle, 3)) {
err = ext4_journal_extend(handle, 3);
if (err > 0)
err = ext4_journal_restart(handle, 3);
@@ -506,10 +514,10 @@
* return the total number of blocks to be allocate, including the
* direct and indirect blocks.
*/
-static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned long blks,
+static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
int blocks_to_boundary)
{
- unsigned long count = 0;
+ unsigned int count = 0;
/*
* Simple case, [t,d]Indirect block(s) has not allocated yet
@@ -547,6 +555,7 @@
int indirect_blks, int blks,
ext4_fsblk_t new_blocks[4], int *err)
{
+ struct ext4_allocation_request ar;
int target, i;
unsigned long count = 0, blk_allocated = 0;
int index = 0;
@@ -595,10 +604,17 @@
if (!target)
goto allocated;
/* Now allocate data blocks */
- count = target;
- /* allocating blocks for data blocks */
- current_block = ext4_new_blocks(handle, inode, iblock,
- goal, &count, err);
+ memset(&ar, 0, sizeof(ar));
+ ar.inode = inode;
+ ar.goal = goal;
+ ar.len = target;
+ ar.logical = iblock;
+ if (S_ISREG(inode->i_mode))
+ /* enable in-core preallocation only for regular files */
+ ar.flags = EXT4_MB_HINT_DATA;
+
+ current_block = ext4_mb_new_blocks(handle, &ar, err);
+
if (*err && (target == blks)) {
/*
* if the allocation failed and we didn't allocate
@@ -614,7 +630,7 @@
*/
new_blocks[index] = current_block;
}
- blk_allocated += count;
+ blk_allocated += ar.len;
}
allocated:
/* total number of blocks allocated for direct blocks */
@@ -709,8 +725,8 @@
set_buffer_uptodate(bh);
unlock_buffer(bh);
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto failed;
}
@@ -792,8 +808,8 @@
* generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
*/
jbd_debug(5, "splicing indirect only\n");
- BUFFER_TRACE(where->bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, where->bh);
+ BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, where->bh);
if (err)
goto err_out;
} else {
@@ -840,10 +856,10 @@
* down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
* (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
*/
-int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, unsigned long maxblocks,
- struct buffer_head *bh_result,
- int create, int extend_disksize)
+static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
+ ext4_lblk_t iblock, unsigned int maxblocks,
+ struct buffer_head *bh_result,
+ int create, int extend_disksize)
{
int err = -EIO;
ext4_lblk_t offsets[4];
@@ -1045,7 +1061,7 @@
* It returns the error in case of allocation failure.
*/
int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
- unsigned long max_blocks, struct buffer_head *bh,
+ unsigned int max_blocks, struct buffer_head *bh,
int create, int extend_disksize, int flag)
{
int retval;
@@ -1221,8 +1237,8 @@
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (!fatal)
fatal = err;
} else {
@@ -1335,6 +1351,10 @@
pgoff_t index;
unsigned from, to;
+ trace_mark(ext4_write_begin,
+ "dev %s ino %lu pos %llu len %u flags %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, flags);
index = pos >> PAGE_CACHE_SHIFT;
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
@@ -1387,7 +1407,7 @@
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
set_buffer_uptodate(bh);
- return ext4_journal_dirty_metadata(handle, bh);
+ return ext4_handle_dirty_metadata(handle, NULL, bh);
}
/*
@@ -1406,6 +1426,10 @@
struct inode *inode = mapping->host;
int ret = 0, ret2;
+ trace_mark(ext4_ordered_write_end,
+ "dev %s ino %lu pos %llu len %u copied %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, copied);
ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
@@ -1444,6 +1468,10 @@
int ret = 0, ret2;
loff_t new_i_size;
+ trace_mark(ext4_writeback_write_end,
+ "dev %s ino %lu pos %llu len %u copied %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, copied);
new_i_size = pos + copied;
if (new_i_size > EXT4_I(inode)->i_disksize) {
ext4_update_i_disksize(inode, new_i_size);
@@ -1479,6 +1507,10 @@
unsigned from, to;
loff_t new_i_size;
+ trace_mark(ext4_journalled_write_end,
+ "dev %s ino %lu pos %llu len %u copied %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, copied);
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
@@ -1625,7 +1657,7 @@
get_block_t *get_block;
struct writeback_control *wbc;
int io_done;
- long pages_written;
+ int pages_written;
int retval;
};
@@ -1645,35 +1677,39 @@
*/
static int mpage_da_submit_io(struct mpage_da_data *mpd)
{
- struct address_space *mapping = mpd->inode->i_mapping;
- int ret = 0, err, nr_pages, i;
- unsigned long index, end;
- struct pagevec pvec;
long pages_skipped;
+ struct pagevec pvec;
+ unsigned long index, end;
+ int ret = 0, err, nr_pages, i;
+ struct inode *inode = mpd->inode;
+ struct address_space *mapping = inode->i_mapping;
BUG_ON(mpd->next_page <= mpd->first_page);
- pagevec_init(&pvec, 0);
+ /*
+ * We need to start from the first_page to the next_page - 1
+ * to make sure we also write the mapped dirty buffer_heads.
+ * If we look at mpd->lbh.b_blocknr we would only be looking
+ * at the currently mapped buffer_heads.
+ */
index = mpd->first_page;
end = mpd->next_page - 1;
+ pagevec_init(&pvec, 0);
while (index <= end) {
- /*
- * We can use PAGECACHE_TAG_DIRTY lookup here because
- * even though we have cleared the dirty flag on the page
- * We still keep the page in the radix tree with tag
- * PAGECACHE_TAG_DIRTY. See clear_page_dirty_for_io.
- * The PAGECACHE_TAG_DIRTY is cleared in set_page_writeback
- * which is called via the below writepage callback.
- */
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
- min(end - index,
- (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ index = page->index;
+ if (index > end)
+ break;
+ index++;
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(PageWriteback(page));
+
pages_skipped = mpd->wbc->pages_skipped;
err = mapping->a_ops->writepage(page, mpd->wbc);
if (!err && (pages_skipped == mpd->wbc->pages_skipped))
@@ -1831,13 +1867,13 @@
ext4_count_free_blocks(inode->i_sb));
printk(KERN_EMERG "Free/Dirty block details\n");
printk(KERN_EMERG "free_blocks=%lld\n",
- percpu_counter_sum(&sbi->s_freeblocks_counter));
+ (long long)percpu_counter_sum(&sbi->s_freeblocks_counter));
printk(KERN_EMERG "dirty_blocks=%lld\n",
- percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ (long long)percpu_counter_sum(&sbi->s_dirtyblocks_counter));
printk(KERN_EMERG "Block reservation details\n");
- printk(KERN_EMERG "i_reserved_data_blocks=%lu\n",
+ printk(KERN_EMERG "i_reserved_data_blocks=%u\n",
EXT4_I(inode)->i_reserved_data_blocks);
- printk(KERN_EMERG "i_reserved_meta_blocks=%lu\n",
+ printk(KERN_EMERG "i_reserved_meta_blocks=%u\n",
EXT4_I(inode)->i_reserved_meta_blocks);
return;
}
@@ -2087,11 +2123,29 @@
bh = head;
do {
BUG_ON(buffer_locked(bh));
+ /*
+ * We need to try to allocate
+ * unmapped blocks in the same page.
+ * Otherwise we won't make progress
+ * with the page in ext4_da_writepage
+ */
if (buffer_dirty(bh) &&
(!buffer_mapped(bh) || buffer_delay(bh))) {
mpage_add_bh_to_extent(mpd, logical, bh);
if (mpd->io_done)
return MPAGE_DA_EXTENT_TAIL;
+ } else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
+ /*
+ * mapped dirty buffer. We need to update
+ * the b_state because we look at
+ * b_state in mpage_da_map_blocks. We don't
+ * update b_size because if we find an
+ * unmapped buffer_head later we need to
+ * use the b_state flag of that buffer_head.
+ */
+ if (mpd->lbh.b_size == 0)
+ mpd->lbh.b_state =
+ bh->b_state & BH_FLAGS;
}
logical++;
} while ((bh = bh->b_this_page) != head);
@@ -2269,10 +2323,13 @@
{
int ret = 0;
loff_t size;
- unsigned long len;
+ unsigned int len;
struct buffer_head *page_bufs;
struct inode *inode = page->mapping->host;
+ trace_mark(ext4_da_writepage,
+ "dev %s ino %lu page_index %lu",
+ inode->i_sb->s_id, inode->i_ino, page->index);
size = i_size_read(inode);
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
@@ -2378,10 +2435,25 @@
struct mpage_da_data mpd;
struct inode *inode = mapping->host;
int no_nrwrite_index_update;
- long pages_written = 0, pages_skipped;
+ int pages_written = 0;
+ long pages_skipped;
int needed_blocks, ret = 0, nr_to_writebump = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+ trace_mark(ext4_da_writepages,
+ "dev %s ino %lu nr_t_write %ld "
+ "pages_skipped %ld range_start %llu "
+ "range_end %llu nonblocking %d "
+ "for_kupdate %d for_reclaim %d "
+ "for_writepages %d range_cyclic %d",
+ inode->i_sb->s_id, inode->i_ino,
+ wbc->nr_to_write, wbc->pages_skipped,
+ (unsigned long long) wbc->range_start,
+ (unsigned long long) wbc->range_end,
+ wbc->nonblocking, wbc->for_kupdate,
+ wbc->for_reclaim, wbc->for_writepages,
+ wbc->range_cyclic);
+
/*
* No pages to write? This is mainly a kludge to avoid starting
* a transaction for special inodes like journal inode on last iput()
@@ -2389,6 +2461,20 @@
*/
if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
return 0;
+
+ /*
+ * If the filesystem has aborted, it is read-only, so return
+ * right away instead of dumping stack traces later on that
+ * will obscure the real source of the problem. We test
+ * EXT4_MOUNT_ABORT instead of sb->s_flag's MS_RDONLY because
+ * the latter could be true if the filesystem is mounted
+ * read-only, and in that case, ext4_da_writepages should
+ * *never* be called, so if that ever happens, we would want
+ * the stack trace.
+ */
+ if (unlikely(sbi->s_mount_opt & EXT4_MOUNT_ABORT))
+ return -EROFS;
+
/*
* Make sure nr_to_write is >= sbi->s_mb_stream_request
* This make sure small files blocks are allocated in
@@ -2433,7 +2519,7 @@
handle = ext4_journal_start(inode, needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
- printk(KERN_EMERG "%s: jbd2_start: "
+ printk(KERN_CRIT "%s: jbd2_start: "
"%ld pages, ino %lu; err %d\n", __func__,
wbc->nr_to_write, inode->i_ino, ret);
dump_stack();
@@ -2486,6 +2572,14 @@
if (!no_nrwrite_index_update)
wbc->no_nrwrite_index_update = 0;
wbc->nr_to_write -= nr_to_writebump;
+ trace_mark(ext4_da_writepage_result,
+ "dev %s ino %lu ret %d pages_written %d "
+ "pages_skipped %ld congestion %d "
+ "more_io %d no_nrwrite_index_update %d",
+ inode->i_sb->s_id, inode->i_ino, ret,
+ pages_written, wbc->pages_skipped,
+ wbc->encountered_congestion, wbc->more_io,
+ wbc->no_nrwrite_index_update);
return ret;
}
@@ -2537,6 +2631,11 @@
len, flags, pagep, fsdata);
}
*fsdata = (void *)0;
+
+ trace_mark(ext4_da_write_begin,
+ "dev %s ino %lu pos %llu len %u flags %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, flags);
retry:
/*
* With delayed allocation, we don't log the i_disksize update
@@ -2626,6 +2725,10 @@
}
}
+ trace_mark(ext4_da_write_end,
+ "dev %s ino %lu pos %llu len %u copied %u",
+ inode->i_sb->s_id, inode->i_ino,
+ (unsigned long long) pos, len, copied);
start = pos & (PAGE_CACHE_SIZE - 1);
end = start + copied - 1;
@@ -2718,7 +2821,10 @@
filemap_write_and_wait(mapping);
}
- if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
+ BUG_ON(!EXT4_JOURNAL(inode) &&
+ EXT4_I(inode)->i_state & EXT4_STATE_JDATA);
+
+ if (EXT4_JOURNAL(inode) && EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
/*
* This is a REALLY heavyweight approach, but the use of
* bmap on dirty files is expected to be extremely rare:
@@ -2836,6 +2942,9 @@
loff_t size = i_size_read(inode);
loff_t len;
+ trace_mark(ext4_normal_writepage,
+ "dev %s ino %lu page_index %lu",
+ inode->i_sb->s_id, inode->i_ino, page->index);
J_ASSERT(PageLocked(page));
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
@@ -2921,6 +3030,9 @@
loff_t size = i_size_read(inode);
loff_t len;
+ trace_mark(ext4_journalled_writepage,
+ "dev %s ino %lu page_index %lu",
+ inode->i_sb->s_id, inode->i_ino, page->index);
J_ASSERT(PageLocked(page));
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
@@ -2989,7 +3101,10 @@
if (offset == 0)
ClearPageChecked(page);
- jbd2_journal_invalidatepage(journal, page, offset);
+ if (journal)
+ jbd2_journal_invalidatepage(journal, page, offset);
+ else
+ block_invalidatepage(page, offset);
}
static int ext4_releasepage(struct page *page, gfp_t wait)
@@ -2999,7 +3114,10 @@
WARN_ON(PageChecked(page));
if (!page_has_buffers(page))
return 0;
- return jbd2_journal_try_to_free_buffers(journal, page, wait);
+ if (journal)
+ return jbd2_journal_try_to_free_buffers(journal, page, wait);
+ else
+ return try_to_free_buffers(page);
}
/*
@@ -3271,7 +3389,7 @@
err = 0;
if (ext4_should_journal_data(inode)) {
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
} else {
if (ext4_should_order_data(inode))
err = ext4_jbd2_file_inode(handle, inode);
@@ -3395,8 +3513,8 @@
__le32 *p;
if (try_to_extend_transaction(handle, inode)) {
if (bh) {
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, inode, bh);
}
ext4_mark_inode_dirty(handle, inode);
ext4_journal_test_restart(handle, inode);
@@ -3496,7 +3614,7 @@
count, block_to_free_p, p);
if (this_bh) {
- BUFFER_TRACE(this_bh, "call ext4_journal_dirty_metadata");
+ BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");
/*
* The buffer head should have an attached journal head at this
@@ -3505,7 +3623,7 @@
* the block was cleared. Check for this instead of OOPSing.
*/
if (bh2jh(this_bh))
- ext4_journal_dirty_metadata(handle, this_bh);
+ ext4_handle_dirty_metadata(handle, inode, this_bh);
else
ext4_error(inode->i_sb, __func__,
"circular indirect block detected, "
@@ -3535,7 +3653,7 @@
ext4_fsblk_t nr;
__le32 *p;
- if (is_handle_aborted(handle))
+ if (ext4_handle_is_aborted(handle))
return;
if (depth--) {
@@ -3605,7 +3723,7 @@
* will merely complain about releasing a free block,
* rather than leaking blocks.
*/
- if (is_handle_aborted(handle))
+ if (ext4_handle_is_aborted(handle))
return;
if (try_to_extend_transaction(handle, inode)) {
ext4_mark_inode_dirty(handle, inode);
@@ -3624,9 +3742,10 @@
parent_bh)){
*p = 0;
BUFFER_TRACE(parent_bh,
- "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle,
- parent_bh);
+ "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle,
+ inode,
+ parent_bh);
}
}
}
@@ -3814,7 +3933,7 @@
* synchronous
*/
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
out_stop:
/*
* If this was a simple ftruncate(), and the file will remain alive
@@ -3844,7 +3963,7 @@
ext4_fsblk_t block;
int inodes_per_block, inode_offset;
- iloc->bh = 0;
+ iloc->bh = NULL;
if (!ext4_valid_inum(sb, inode->i_ino))
return -EIO;
@@ -3951,7 +4070,7 @@
num = EXT4_INODES_PER_GROUP(sb);
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
- num -= le16_to_cpu(gdp->bg_itable_unused);
+ num -= ext4_itable_unused_count(sb, gdp);
table += num / inodes_per_block;
if (end > table)
end = table;
@@ -4313,8 +4432,8 @@
EXT4_SET_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
sb->s_dirt = 1;
- handle->h_sync = 1;
- err = ext4_journal_dirty_metadata(handle,
+ ext4_handle_sync(handle);
+ err = ext4_handle_dirty_metadata(handle, inode,
EXT4_SB(sb)->s_sbh);
}
}
@@ -4341,9 +4460,8 @@
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
}
-
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- rc = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ rc = ext4_handle_dirty_metadata(handle, inode, bh);
if (!err)
err = rc;
ei->i_state &= ~EXT4_STATE_NEW;
@@ -4406,6 +4524,25 @@
return ext4_force_commit(inode->i_sb);
}
+int __ext4_write_dirty_metadata(struct inode *inode, struct buffer_head *bh)
+{
+ int err = 0;
+
+ mark_buffer_dirty(bh);
+ if (inode && inode_needs_sync(inode)) {
+ sync_dirty_buffer(bh);
+ if (buffer_req(bh) && !buffer_uptodate(bh)) {
+ ext4_error(inode->i_sb, __func__,
+ "IO error syncing inode, "
+ "inode=%lu, block=%llu",
+ inode->i_ino,
+ (unsigned long long)bh->b_blocknr);
+ err = -EIO;
+ }
+ }
+ return err;
+}
+
/*
* ext4_setattr()
*
@@ -4710,16 +4847,15 @@
ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc)
{
- int err = 0;
- if (handle) {
- err = ext4_get_inode_loc(inode, iloc);
- if (!err) {
- BUFFER_TRACE(iloc->bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, iloc->bh);
- if (err) {
- brelse(iloc->bh);
- iloc->bh = NULL;
- }
+ int err;
+
+ err = ext4_get_inode_loc(inode, iloc);
+ if (!err) {
+ BUFFER_TRACE(iloc->bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, iloc->bh);
+ if (err) {
+ brelse(iloc->bh);
+ iloc->bh = NULL;
}
}
ext4_std_error(inode->i_sb, err);
@@ -4791,7 +4927,8 @@
might_sleep();
err = ext4_reserve_inode_write(handle, inode, &iloc);
- if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
+ if (ext4_handle_valid(handle) &&
+ EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
!(EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND)) {
/*
* We need extra buffer credits since we may write into EA block
@@ -4843,6 +4980,11 @@
handle_t *current_handle = ext4_journal_current_handle();
handle_t *handle;
+ if (!ext4_handle_valid(current_handle)) {
+ ext4_mark_inode_dirty(current_handle, inode);
+ return;
+ }
+
handle = ext4_journal_start(inode, 2);
if (IS_ERR(handle))
goto out;
@@ -4880,8 +5022,9 @@
BUFFER_TRACE(iloc.bh, "get_write_access");
err = jbd2_journal_get_write_access(handle, iloc.bh);
if (!err)
- err = ext4_journal_dirty_metadata(handle,
- iloc.bh);
+ err = ext4_handle_dirty_metadata(handle,
+ inode,
+ iloc.bh);
brelse(iloc.bh);
}
}
@@ -4907,6 +5050,8 @@
*/
journal = EXT4_JOURNAL(inode);
+ if (!journal)
+ return 0;
if (is_journal_aborted(journal))
return -EROFS;
@@ -4936,7 +5081,7 @@
return PTR_ERR(handle);
err = ext4_mark_inode_dirty(handle, inode);
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
ext4_journal_stop(handle);
ext4_std_error(inode->i_sb, err);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index dc99b47..42dc83f 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -99,7 +99,7 @@
goto flags_out;
}
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto flags_err;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 444ad99..918aec0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -100,7 +100,7 @@
* inode as:
*
* { page }
- * [ group 0 buddy][ group 0 bitmap] [group 1][ group 1]...
+ * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]...
*
*
* one block each for bitmap and buddy information. So for each group we
@@ -330,6 +330,18 @@
* object
*
*/
+static struct kmem_cache *ext4_pspace_cachep;
+static struct kmem_cache *ext4_ac_cachep;
+static struct kmem_cache *ext4_free_ext_cachep;
+static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+ ext4_group_t group);
+static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
+ ext4_group_t group);
+static int ext4_mb_init_per_dev_proc(struct super_block *sb);
+static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
+static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
+
+
static inline void *mb_correct_addr_and_bit(int *bit, void *addr)
{
@@ -445,9 +457,9 @@
blocknr += first + i;
blocknr +=
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
-
- ext4_error(sb, __func__, "double-free of inode"
- " %lu's block %llu(bit %u in group %lu)\n",
+ ext4_grp_locked_error(sb, e4b->bd_group,
+ __func__, "double-free of inode"
+ " %lu's block %llu(bit %u in group %u)",
inode ? inode->i_ino : 0, blocknr,
first + i, e4b->bd_group);
}
@@ -477,7 +489,7 @@
b2 = (unsigned char *) bitmap;
for (i = 0; i < e4b->bd_sb->s_blocksize; i++) {
if (b1[i] != b2[i]) {
- printk(KERN_ERR "corruption in group %lu "
+ printk(KERN_ERR "corruption in group %u "
"at byte %u(%u): %x in copy != %x "
"on disk/prealloc\n",
e4b->bd_group, i, i * 8, b1[i], b2[i]);
@@ -690,8 +702,8 @@
grp->bb_fragments = fragments;
if (free != grp->bb_free) {
- ext4_error(sb, __func__,
- "EXT4-fs: group %lu: %u blocks in bitmap, %u in gd\n",
+ ext4_grp_locked_error(sb, group, __func__,
+ "EXT4-fs: group %u: %u blocks in bitmap, %u in gd",
group, free, grp->bb_free);
/*
* If we intent to continue, we consider group descritor
@@ -716,7 +728,7 @@
* stored in the inode as
*
* { page }
- * [ group 0 buddy][ group 0 bitmap] [group 1][ group 1]...
+ * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]...
*
*
* one block each for bitmap and buddy information.
@@ -782,25 +794,45 @@
if (bh[i] == NULL)
goto out;
- if (buffer_uptodate(bh[i]) &&
- !(desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))
+ if (bitmap_uptodate(bh[i]))
continue;
lock_buffer(bh[i]);
+ if (bitmap_uptodate(bh[i])) {
+ unlock_buffer(bh[i]);
+ continue;
+ }
spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
ext4_init_block_bitmap(sb, bh[i],
first_group + i, desc);
+ set_bitmap_uptodate(bh[i]);
set_buffer_uptodate(bh[i]);
- unlock_buffer(bh[i]);
spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+ unlock_buffer(bh[i]);
continue;
}
spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+ if (buffer_uptodate(bh[i])) {
+ /*
+ * if not uninit if bh is uptodate,
+ * bitmap is also uptodate
+ */
+ set_bitmap_uptodate(bh[i]);
+ unlock_buffer(bh[i]);
+ continue;
+ }
get_bh(bh[i]);
+ /*
+ * 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[i]);
bh[i]->b_end_io = end_buffer_read_sync;
submit_bh(READ, bh[i]);
- mb_debug("read bitmap for group %lu\n", first_group + i);
+ mb_debug("read bitmap for group %u\n", first_group + i);
}
/* wait for I/O completion */
@@ -814,6 +846,8 @@
err = 0;
first_block = page->index * blocks_per_page;
+ /* init the page */
+ memset(page_address(page), 0xff, PAGE_CACHE_SIZE);
for (i = 0; i < blocks_per_page; i++) {
int group;
struct ext4_group_info *grinfo;
@@ -840,7 +874,6 @@
BUG_ON(incore == NULL);
mb_debug("put buddy for group %u in page %lu/%x\n",
group, page->index, i * blocksize);
- memset(data, 0xff, blocksize);
grinfo = ext4_get_group_info(sb, group);
grinfo->bb_fragments = 0;
memset(grinfo->bb_counters, 0,
@@ -848,7 +881,9 @@
/*
* incore got set to the group block bitmap below
*/
+ ext4_lock_group(sb, group);
ext4_mb_generate_buddy(sb, data, incore, group);
+ ext4_unlock_group(sb, group);
incore = NULL;
} else {
/* this is block of bitmap */
@@ -862,6 +897,7 @@
/* mark all preallocated blks used in in-core bitmap */
ext4_mb_generate_from_pa(sb, data, group);
+ ext4_mb_generate_from_freelist(sb, data, group);
ext4_unlock_group(sb, group);
/* set incore so that the buddy information can be
@@ -886,18 +922,20 @@
ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
struct ext4_buddy *e4b)
{
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct inode *inode = sbi->s_buddy_cache;
int blocks_per_page;
int block;
int pnum;
int poff;
struct page *page;
int ret;
+ struct ext4_group_info *grp;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct inode *inode = sbi->s_buddy_cache;
- mb_debug("load group %lu\n", group);
+ mb_debug("load group %u\n", group);
blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+ grp = ext4_get_group_info(sb, group);
e4b->bd_blkbits = sb->s_blocksize_bits;
e4b->bd_info = ext4_get_group_info(sb, group);
@@ -905,6 +943,15 @@
e4b->bd_group = group;
e4b->bd_buddy_page = NULL;
e4b->bd_bitmap_page = NULL;
+ e4b->alloc_semp = &grp->alloc_sem;
+
+ /* Take the read lock on the group alloc
+ * sem. This would make sure a parallel
+ * ext4_mb_init_group happening on other
+ * groups mapped by the page is blocked
+ * till we are done with allocation
+ */
+ down_read(e4b->alloc_semp);
/*
* the buddy cache inode stores the block bitmap
@@ -920,6 +967,14 @@
page = find_get_page(inode->i_mapping, pnum);
if (page == NULL || !PageUptodate(page)) {
if (page)
+ /*
+ * drop the page reference and try
+ * to get the page with lock. If we
+ * are not uptodate that implies
+ * somebody just created the page but
+ * is yet to initialize the same. So
+ * wait for it to initialize.
+ */
page_cache_release(page);
page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
if (page) {
@@ -985,6 +1040,9 @@
page_cache_release(e4b->bd_buddy_page);
e4b->bd_buddy = NULL;
e4b->bd_bitmap = NULL;
+
+ /* Done with the buddy cache */
+ up_read(e4b->alloc_semp);
return ret;
}
@@ -994,6 +1052,9 @@
page_cache_release(e4b->bd_bitmap_page);
if (e4b->bd_buddy_page)
page_cache_release(e4b->bd_buddy_page);
+ /* Done with the buddy cache */
+ if (e4b->alloc_semp)
+ up_read(e4b->alloc_semp);
}
@@ -1031,7 +1092,10 @@
cur += 32;
continue;
}
- mb_clear_bit_atomic(lock, cur, bm);
+ if (lock)
+ mb_clear_bit_atomic(lock, cur, bm);
+ else
+ mb_clear_bit(cur, bm);
cur++;
}
}
@@ -1049,7 +1113,10 @@
cur += 32;
continue;
}
- mb_set_bit_atomic(lock, cur, bm);
+ if (lock)
+ mb_set_bit_atomic(lock, cur, bm);
+ else
+ mb_set_bit(cur, bm);
cur++;
}
}
@@ -1094,12 +1161,11 @@
blocknr += block;
blocknr +=
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
- ext4_unlock_group(sb, e4b->bd_group);
- ext4_error(sb, __func__, "double-free of inode"
- " %lu's block %llu(bit %u in group %lu)\n",
+ ext4_grp_locked_error(sb, e4b->bd_group,
+ __func__, "double-free of inode"
+ " %lu's block %llu(bit %u in group %u)",
inode ? inode->i_ino : 0, blocknr, block,
e4b->bd_group);
- ext4_lock_group(sb, e4b->bd_group);
}
mb_clear_bit(block, EXT4_MB_BITMAP(e4b));
e4b->bd_info->bb_counters[order]++;
@@ -1296,13 +1362,20 @@
ac->ac_tail = ret & 0xffff;
ac->ac_buddy = ret >> 16;
- /* XXXXXXX: SUCH A HORRIBLE **CK */
- /*FIXME!! Why ? */
+ /*
+ * take the page reference. We want the page to be pinned
+ * so that we don't get a ext4_mb_init_cache_call for this
+ * group until we update the bitmap. That would mean we
+ * double allocate blocks. The reference is dropped
+ * in ext4_mb_release_context
+ */
ac->ac_bitmap_page = e4b->bd_bitmap_page;
get_page(ac->ac_bitmap_page);
ac->ac_buddy_page = e4b->bd_buddy_page;
get_page(ac->ac_buddy_page);
-
+ /* on allocation we use ac to track the held semaphore */
+ ac->alloc_semp = e4b->alloc_semp;
+ e4b->alloc_semp = NULL;
/* store last allocated for subsequent stream allocation */
if ((ac->ac_flags & EXT4_MB_HINT_DATA)) {
spin_lock(&sbi->s_md_lock);
@@ -1326,6 +1399,8 @@
struct ext4_free_extent ex;
int max;
+ if (ac->ac_status == AC_STATUS_FOUND)
+ return;
/*
* We don't want to scan for a whole year
*/
@@ -1575,8 +1650,9 @@
* free blocks even though group info says we
* we have free blocks
*/
- ext4_error(sb, __func__, "%d free blocks as per "
- "group info. But bitmap says 0\n",
+ ext4_grp_locked_error(sb, e4b->bd_group,
+ __func__, "%d free blocks as per "
+ "group info. But bitmap says 0",
free);
break;
}
@@ -1584,8 +1660,9 @@
mb_find_extent(e4b, 0, i, ac->ac_g_ex.fe_len, &ex);
BUG_ON(ex.fe_len <= 0);
if (free < ex.fe_len) {
- ext4_error(sb, __func__, "%d free blocks as per "
- "group info. But got %d blocks\n",
+ ext4_grp_locked_error(sb, e4b->bd_group,
+ __func__, "%d free blocks as per "
+ "group info. But got %d blocks",
free, ex.fe_len);
/*
* The number of free blocks differs. This mostly
@@ -1692,6 +1769,173 @@
return 0;
}
+/*
+ * lock the group_info alloc_sem of all the groups
+ * belonging to the same buddy cache page. This
+ * make sure other parallel operation on the buddy
+ * cache doesn't happen whild holding the buddy cache
+ * lock
+ */
+int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group)
+{
+ int i;
+ int block, pnum;
+ int blocks_per_page;
+ int groups_per_page;
+ ext4_group_t first_group;
+ struct ext4_group_info *grp;
+
+ blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+ /*
+ * the buddy cache inode stores the block bitmap
+ * and buddy information in consecutive blocks.
+ * So for each group we need two blocks.
+ */
+ block = group * 2;
+ pnum = block / blocks_per_page;
+ first_group = pnum * blocks_per_page / 2;
+
+ groups_per_page = blocks_per_page >> 1;
+ if (groups_per_page == 0)
+ groups_per_page = 1;
+ /* read all groups the page covers into the cache */
+ for (i = 0; i < groups_per_page; i++) {
+
+ if ((first_group + i) >= EXT4_SB(sb)->s_groups_count)
+ break;
+ grp = ext4_get_group_info(sb, first_group + i);
+ /* take all groups write allocation
+ * semaphore. This make sure there is
+ * no block allocation going on in any
+ * of that groups
+ */
+ down_write_nested(&grp->alloc_sem, i);
+ }
+ return i;
+}
+
+void ext4_mb_put_buddy_cache_lock(struct super_block *sb,
+ ext4_group_t group, int locked_group)
+{
+ int i;
+ int block, pnum;
+ int blocks_per_page;
+ ext4_group_t first_group;
+ struct ext4_group_info *grp;
+
+ blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+ /*
+ * the buddy cache inode stores the block bitmap
+ * and buddy information in consecutive blocks.
+ * So for each group we need two blocks.
+ */
+ block = group * 2;
+ pnum = block / blocks_per_page;
+ first_group = pnum * blocks_per_page / 2;
+ /* release locks on all the groups */
+ for (i = 0; i < locked_group; i++) {
+
+ grp = ext4_get_group_info(sb, first_group + i);
+ /* take all groups write allocation
+ * semaphore. This make sure there is
+ * no block allocation going on in any
+ * of that groups
+ */
+ up_write(&grp->alloc_sem);
+ }
+
+}
+
+static int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
+{
+
+ int ret;
+ void *bitmap;
+ int blocks_per_page;
+ int block, pnum, poff;
+ int num_grp_locked = 0;
+ struct ext4_group_info *this_grp;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct inode *inode = sbi->s_buddy_cache;
+ struct page *page = NULL, *bitmap_page = NULL;
+
+ mb_debug("init group %lu\n", group);
+ blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+ this_grp = ext4_get_group_info(sb, group);
+ /*
+ * This ensures we don't add group
+ * to this buddy cache via resize
+ */
+ num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, group);
+ if (!EXT4_MB_GRP_NEED_INIT(this_grp)) {
+ /*
+ * somebody initialized the group
+ * return without doing anything
+ */
+ ret = 0;
+ goto err;
+ }
+ /*
+ * the buddy cache inode stores the block bitmap
+ * and buddy information in consecutive blocks.
+ * So for each group we need two blocks.
+ */
+ block = group * 2;
+ pnum = block / blocks_per_page;
+ poff = block % blocks_per_page;
+ page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+ if (page) {
+ BUG_ON(page->mapping != inode->i_mapping);
+ ret = ext4_mb_init_cache(page, NULL);
+ if (ret) {
+ unlock_page(page);
+ goto err;
+ }
+ unlock_page(page);
+ }
+ if (page == NULL || !PageUptodate(page)) {
+ ret = -EIO;
+ goto err;
+ }
+ mark_page_accessed(page);
+ bitmap_page = page;
+ bitmap = page_address(page) + (poff * sb->s_blocksize);
+
+ /* init buddy cache */
+ block++;
+ pnum = block / blocks_per_page;
+ poff = block % blocks_per_page;
+ page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+ if (page == bitmap_page) {
+ /*
+ * If both the bitmap and buddy are in
+ * the same page we don't need to force
+ * init the buddy
+ */
+ unlock_page(page);
+ } else if (page) {
+ BUG_ON(page->mapping != inode->i_mapping);
+ ret = ext4_mb_init_cache(page, bitmap);
+ if (ret) {
+ unlock_page(page);
+ goto err;
+ }
+ unlock_page(page);
+ }
+ if (page == NULL || !PageUptodate(page)) {
+ ret = -EIO;
+ goto err;
+ }
+ mark_page_accessed(page);
+err:
+ ext4_mb_put_buddy_cache_lock(sb, group, num_grp_locked);
+ if (bitmap_page)
+ page_cache_release(bitmap_page);
+ if (page)
+ page_cache_release(page);
+ return ret;
+}
+
static noinline_for_stack int
ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
{
@@ -1775,7 +2019,7 @@
group = 0;
/* quick check to skip empty groups */
- grp = ext4_get_group_info(ac->ac_sb, group);
+ grp = ext4_get_group_info(sb, group);
if (grp->bb_free == 0)
continue;
@@ -1788,10 +2032,9 @@
* we need full data about the group
* to make a good selection
*/
- err = ext4_mb_load_buddy(sb, group, &e4b);
+ err = ext4_mb_init_group(sb, group);
if (err)
goto out;
- ext4_mb_release_desc(&e4b);
}
/*
@@ -1932,13 +2175,13 @@
if (hs->op == EXT4_MB_HISTORY_ALLOC) {
fmt = "%-5u %-8u %-23s %-23s %-23s %-5u %-5u %-2u "
"%-5u %-5s %-5u %-6u\n";
- sprintf(buf2, "%lu/%d/%u@%u", hs->result.fe_group,
+ sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group,
hs->result.fe_start, hs->result.fe_len,
hs->result.fe_logical);
- sprintf(buf, "%lu/%d/%u@%u", hs->orig.fe_group,
+ sprintf(buf, "%u/%d/%u@%u", hs->orig.fe_group,
hs->orig.fe_start, hs->orig.fe_len,
hs->orig.fe_logical);
- sprintf(buf3, "%lu/%d/%u@%u", hs->goal.fe_group,
+ sprintf(buf3, "%u/%d/%u@%u", hs->goal.fe_group,
hs->goal.fe_start, hs->goal.fe_len,
hs->goal.fe_logical);
seq_printf(seq, fmt, hs->pid, hs->ino, buf, buf3, buf2,
@@ -1947,20 +2190,20 @@
hs->buddy ? 1 << hs->buddy : 0);
} else if (hs->op == EXT4_MB_HISTORY_PREALLOC) {
fmt = "%-5u %-8u %-23s %-23s %-23s\n";
- sprintf(buf2, "%lu/%d/%u@%u", hs->result.fe_group,
+ sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group,
hs->result.fe_start, hs->result.fe_len,
hs->result.fe_logical);
- sprintf(buf, "%lu/%d/%u@%u", hs->orig.fe_group,
+ sprintf(buf, "%u/%d/%u@%u", hs->orig.fe_group,
hs->orig.fe_start, hs->orig.fe_len,
hs->orig.fe_logical);
seq_printf(seq, fmt, hs->pid, hs->ino, buf, "", buf2);
} else if (hs->op == EXT4_MB_HISTORY_DISCARD) {
- sprintf(buf2, "%lu/%d/%u", hs->result.fe_group,
+ sprintf(buf2, "%u/%d/%u", hs->result.fe_group,
hs->result.fe_start, hs->result.fe_len);
seq_printf(seq, "%-5u %-8u %-23s discard\n",
hs->pid, hs->ino, buf2);
} else if (hs->op == EXT4_MB_HISTORY_FREE) {
- sprintf(buf2, "%lu/%d/%u", hs->result.fe_group,
+ sprintf(buf2, "%u/%d/%u", hs->result.fe_group,
hs->result.fe_start, hs->result.fe_len);
seq_printf(seq, "%-5u %-8u %-23s free\n",
hs->pid, hs->ino, buf2);
@@ -2073,7 +2316,7 @@
return NULL;
group = *pos + 1;
- return (void *) group;
+ return (void *) ((unsigned long) group);
}
static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
@@ -2086,13 +2329,13 @@
if (*pos < 0 || *pos >= sbi->s_groups_count)
return NULL;
group = *pos + 1;
- return (void *) group;;
+ return (void *) ((unsigned long) group);
}
static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
{
struct super_block *sb = seq->private;
- long group = (long) v;
+ ext4_group_t group = (ext4_group_t) ((unsigned long) v);
int i;
int err;
struct ext4_buddy e4b;
@@ -2114,7 +2357,7 @@
sizeof(struct ext4_group_info);
err = ext4_mb_load_buddy(sb, group, &e4b);
if (err) {
- seq_printf(seq, "#%-5lu: I/O error\n", group);
+ seq_printf(seq, "#%-5u: I/O error\n", group);
return 0;
}
ext4_lock_group(sb, group);
@@ -2122,7 +2365,7 @@
ext4_unlock_group(sb, group);
ext4_mb_release_desc(&e4b);
- seq_printf(seq, "#%-5lu: %-5u %-5u %-5u [", group, sg.info.bb_free,
+ seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
sg.info.bb_fragments, sg.info.bb_first_free);
for (i = 0; i <= 13; i++)
seq_printf(seq, " %-5u", i <= sb->s_blocksize_bits + 1 ?
@@ -2296,10 +2539,11 @@
ext4_free_blocks_after_init(sb, group, desc);
} else {
meta_group_info[i]->bb_free =
- le16_to_cpu(desc->bg_free_blocks_count);
+ ext4_free_blks_count(sb, desc);
}
INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
+ init_rwsem(&meta_group_info[i]->alloc_sem);
meta_group_info[i]->bb_free_root.rb_node = NULL;;
#ifdef DOUBLE_CHECK
@@ -2327,54 +2571,6 @@
} /* ext4_mb_add_groupinfo */
/*
- * Add a group to the existing groups.
- * This function is used for online resize
- */
-int ext4_mb_add_more_groupinfo(struct super_block *sb, ext4_group_t group,
- struct ext4_group_desc *desc)
-{
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct inode *inode = sbi->s_buddy_cache;
- int blocks_per_page;
- int block;
- int pnum;
- struct page *page;
- int err;
-
- /* Add group based on group descriptor*/
- err = ext4_mb_add_groupinfo(sb, group, desc);
- if (err)
- return err;
-
- /*
- * Cache pages containing dynamic mb_alloc datas (buddy and bitmap
- * datas) are set not up to date so that they will be re-initilaized
- * during the next call to ext4_mb_load_buddy
- */
-
- /* Set buddy page as not up to date */
- blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
- block = group * 2;
- pnum = block / blocks_per_page;
- page = find_get_page(inode->i_mapping, pnum);
- if (page != NULL) {
- ClearPageUptodate(page);
- page_cache_release(page);
- }
-
- /* Set bitmap page as not up to date */
- block++;
- pnum = block / blocks_per_page;
- page = find_get_page(inode->i_mapping, pnum);
- if (page != NULL) {
- ClearPageUptodate(page);
- page_cache_release(page);
- }
-
- return 0;
-}
-
-/*
* Update an existing group.
* This function is used for online resize
*/
@@ -2457,7 +2653,7 @@
desc = ext4_get_group_desc(sb, i, NULL);
if (desc == NULL) {
printk(KERN_ERR
- "EXT4-fs: can't read descriptor %lu\n", i);
+ "EXT4-fs: can't read descriptor %u\n", i);
goto err_freebuddy;
}
if (ext4_mb_add_groupinfo(sb, i, desc) != 0)
@@ -2493,6 +2689,8 @@
if (sbi->s_mb_offsets == NULL) {
return -ENOMEM;
}
+
+ i = (sb->s_blocksize_bits + 2) * sizeof(unsigned int);
sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL);
if (sbi->s_mb_maxs == NULL) {
kfree(sbi->s_mb_maxs);
@@ -2551,7 +2749,8 @@
ext4_mb_init_per_dev_proc(sb);
ext4_mb_history_init(sb);
- sbi->s_journal->j_commit_callback = release_blocks_on_commit;
+ if (sbi->s_journal)
+ sbi->s_journal->j_commit_callback = release_blocks_on_commit;
printk(KERN_INFO "EXT4-fs: mballoc enabled\n");
return 0;
@@ -2652,7 +2851,7 @@
list_for_each_safe(l, ltmp, &txn->t_private_list) {
entry = list_entry(l, struct ext4_free_data, list);
- mb_debug("gonna free %u blocks in group %lu (0x%p):",
+ mb_debug("gonna free %u blocks in group %u (0x%p):",
entry->count, entry->group, entry);
err = ext4_mb_load_buddy(sb, entry->group, &e4b);
@@ -2679,8 +2878,9 @@
discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb)
+ entry->start_blk
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
- trace_mark(ext4_discard_blocks, "dev %s blk %llu count %u", sb->s_id,
- (unsigned long long) discard_block, entry->count);
+ trace_mark(ext4_discard_blocks, "dev %s blk %llu count %u",
+ sb->s_id, (unsigned long long) discard_block,
+ entry->count);
sb_issue_discard(sb, discard_block, entry->count);
kmem_cache_free(ext4_free_ext_cachep, entry);
@@ -2791,7 +2991,7 @@
*/
static noinline_for_stack int
ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
- handle_t *handle, unsigned long reserv_blks)
+ handle_t *handle, unsigned int reserv_blks)
{
struct buffer_head *bitmap_bh = NULL;
struct ext4_super_block *es;
@@ -2824,7 +3024,7 @@
if (!gdp)
goto out_err;
- ext4_debug("using block group %lu(%d)\n", ac->ac_b_ex.fe_group,
+ ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
gdp->bg_free_blocks_count);
err = ext4_journal_get_write_access(handle, gdp_bh);
@@ -2843,8 +3043,8 @@
in_range(block + len - 1, ext4_inode_table(sb, gdp),
EXT4_SB(sb)->s_itb_per_group)) {
ext4_error(sb, __func__,
- "Allocating block in system zone - block = %llu",
- block);
+ "Allocating block %llu in system zone of %d group\n",
+ block, ac->ac_b_ex.fe_group);
/* File system mounted not to panic on error
* Fix the bitmap and repeat the block allocation
* We leak some of the blocks here.
@@ -2852,7 +3052,7 @@
mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group),
bitmap_bh->b_data, ac->ac_b_ex.fe_start,
ac->ac_b_ex.fe_len);
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!err)
err = -EAGAIN;
goto out_err;
@@ -2866,18 +3066,17 @@
}
}
#endif
- mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group), bitmap_bh->b_data,
- ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len);
-
spin_lock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
+ mb_set_bits(NULL, bitmap_bh->b_data,
+ ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len);
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
- gdp->bg_free_blocks_count =
- cpu_to_le16(ext4_free_blocks_after_init(sb,
- ac->ac_b_ex.fe_group,
- gdp));
+ ext4_free_blks_set(sb, gdp,
+ ext4_free_blocks_after_init(sb,
+ ac->ac_b_ex.fe_group, gdp));
}
- le16_add_cpu(&gdp->bg_free_blocks_count, -ac->ac_b_ex.fe_len);
+ len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len;
+ ext4_free_blks_set(sb, gdp, len);
gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
@@ -2899,10 +3098,10 @@
spin_unlock(sb_bgl_lock(sbi, flex_group));
}
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (err)
goto out_err;
- err = ext4_journal_dirty_metadata(handle, gdp_bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh);
out_err:
sb->s_dirt = 1;
@@ -3031,7 +3230,7 @@
/* check we don't cross already preallocated blocks */
rcu_read_lock();
list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
- unsigned long pa_end;
+ ext4_lblk_t pa_end;
if (pa->pa_deleted)
continue;
@@ -3075,7 +3274,7 @@
/* XXX: extra loop to check we really don't overlap preallocations */
rcu_read_lock();
list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
- unsigned long pa_end;
+ ext4_lblk_t pa_end;
spin_lock(&pa->pa_lock);
if (pa->pa_deleted == 0) {
pa_end = pa->pa_lstart + pa->pa_len;
@@ -3307,6 +3506,32 @@
}
/*
+ * the function goes through all block freed in the group
+ * but not yet committed and marks them used in in-core bitmap.
+ * buddy must be generated from this bitmap
+ * Need to be called with ext4 group lock (ext4_lock_group)
+ */
+static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
+ ext4_group_t group)
+{
+ struct rb_node *n;
+ struct ext4_group_info *grp;
+ struct ext4_free_data *entry;
+
+ grp = ext4_get_group_info(sb, group);
+ n = rb_first(&(grp->bb_free_root));
+
+ while (n) {
+ entry = rb_entry(n, struct ext4_free_data, node);
+ mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group),
+ bitmap, entry->start_blk,
+ entry->count);
+ n = rb_next(n);
+ }
+ return;
+}
+
+/*
* the function goes through all preallocation in this group and marks them
* used in in-core bitmap. buddy must be generated from this bitmap
* Need to be called with ext4 group lock (ext4_lock_group)
@@ -3346,7 +3571,7 @@
preallocated += len;
count++;
}
- mb_debug("prellocated %u for group %lu\n", preallocated, group);
+ mb_debug("prellocated %u for group %u\n", preallocated, group);
}
static void ext4_mb_pa_callback(struct rcu_head *head)
@@ -3363,7 +3588,7 @@
static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
struct super_block *sb, struct ext4_prealloc_space *pa)
{
- unsigned long grp;
+ ext4_group_t grp;
if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
return;
@@ -3473,6 +3698,10 @@
mb_debug("new inode pa %p: %llu/%u for %u\n", pa,
pa->pa_pstart, pa->pa_len, pa->pa_lstart);
+ trace_mark(ext4_mb_new_inode_pa,
+ "dev %s ino %lu pstart %llu len %u lstart %u",
+ sb->s_id, ac->ac_inode->i_ino,
+ pa->pa_pstart, pa->pa_len, pa->pa_lstart);
ext4_mb_use_inode_pa(ac, pa);
atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
@@ -3530,7 +3759,9 @@
pa->pa_linear = 1;
mb_debug("new group pa %p: %llu/%u for %u\n", pa,
- pa->pa_pstart, pa->pa_len, pa->pa_lstart);
+ pa->pa_pstart, pa->pa_len, pa->pa_lstart);
+ trace_mark(ext4_mb_new_group_pa, "dev %s pstart %llu len %u lstart %u",
+ sb->s_id, pa->pa_pstart, pa->pa_len, pa->pa_lstart);
ext4_mb_use_group_pa(ac, pa);
atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
@@ -3579,16 +3810,18 @@
{
struct super_block *sb = e4b->bd_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- unsigned long end;
- unsigned long next;
+ unsigned int end;
+ unsigned int next;
ext4_group_t group;
ext4_grpblk_t bit;
+ unsigned long long grp_blk_start;
sector_t start;
int err = 0;
int free = 0;
BUG_ON(pa->pa_deleted == 0);
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
+ grp_blk_start = pa->pa_pstart - bit;
BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
end = bit + pa->pa_len;
@@ -3618,6 +3851,10 @@
ext4_mb_store_history(ac);
}
+ trace_mark(ext4_mb_release_inode_pa,
+ "dev %s ino %lu block %llu count %u",
+ sb->s_id, pa->pa_inode->i_ino, grp_blk_start + bit,
+ next - bit);
mb_free_blocks(pa->pa_inode, e4b, bit, next - bit);
bit = next + 1;
}
@@ -3626,8 +3863,9 @@
pa, (unsigned long) pa->pa_lstart,
(unsigned long) pa->pa_pstart,
(unsigned long) pa->pa_len);
- ext4_error(sb, __func__, "free %u, pa_free %u\n",
- free, pa->pa_free);
+ ext4_grp_locked_error(sb, group,
+ __func__, "free %u, pa_free %u",
+ free, pa->pa_free);
/*
* pa is already deleted so we use the value obtained
* from the bitmap and continue.
@@ -3650,6 +3888,8 @@
if (ac)
ac->ac_op = EXT4_MB_HISTORY_DISCARD;
+ trace_mark(ext4_mb_release_group_pa, "dev %s pstart %llu len %d",
+ sb->s_id, pa->pa_pstart, pa->pa_len);
BUG_ON(pa->pa_deleted == 0);
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
@@ -3692,7 +3932,7 @@
int busy = 0;
int free = 0;
- mb_debug("discard preallocation for group %lu\n", group);
+ mb_debug("discard preallocation for group %u\n", group);
if (list_empty(&grp->bb_prealloc_list))
return 0;
@@ -3700,14 +3940,14 @@
bitmap_bh = ext4_read_block_bitmap(sb, group);
if (bitmap_bh == NULL) {
ext4_error(sb, __func__, "Error in reading block "
- "bitmap for %lu\n", group);
+ "bitmap for %u", group);
return 0;
}
err = ext4_mb_load_buddy(sb, group, &e4b);
if (err) {
ext4_error(sb, __func__, "Error in loading buddy "
- "information for %lu\n", group);
+ "information for %u", group);
put_bh(bitmap_bh);
return 0;
}
@@ -3815,6 +4055,8 @@
}
mb_debug("discard preallocation for inode %lu\n", inode->i_ino);
+ trace_mark(ext4_discard_preallocations, "dev %s ino %lu", sb->s_id,
+ inode->i_ino);
INIT_LIST_HEAD(&list);
@@ -3874,14 +4116,14 @@
err = ext4_mb_load_buddy(sb, group, &e4b);
if (err) {
ext4_error(sb, __func__, "Error in loading buddy "
- "information for %lu\n", group);
+ "information for %u", group);
continue;
}
bitmap_bh = ext4_read_block_bitmap(sb, group);
if (bitmap_bh == NULL) {
ext4_error(sb, __func__, "Error in reading block "
- "bitmap for %lu\n", group);
+ "bitmap for %u", group);
ext4_mb_release_desc(&e4b);
continue;
}
@@ -4024,8 +4266,8 @@
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
ext4_group_t group;
- unsigned long len;
- unsigned long goal;
+ unsigned int len;
+ ext4_fsblk_t goal;
ext4_grpblk_t block;
/* we can't allocate > group size */
@@ -4068,6 +4310,7 @@
ac->ac_pa = NULL;
ac->ac_bitmap_page = NULL;
ac->ac_buddy_page = NULL;
+ ac->alloc_semp = NULL;
ac->ac_lg = NULL;
/* we have to define context: we'll we work with a file or
@@ -4146,7 +4389,7 @@
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL);
if (ext4_mb_load_buddy(sb, group, &e4b)) {
ext4_error(sb, __func__, "Error in loading buddy "
- "information for %lu\n", group);
+ "information for %u", group);
continue;
}
ext4_lock_group(sb, group);
@@ -4248,6 +4491,8 @@
}
ext4_mb_put_pa(ac, ac->ac_sb, pa);
}
+ if (ac->alloc_semp)
+ up_read(ac->alloc_semp);
if (ac->ac_bitmap_page)
page_cache_release(ac->ac_bitmap_page);
if (ac->ac_buddy_page)
@@ -4264,6 +4509,8 @@
int ret;
int freed = 0;
+ trace_mark(ext4_mb_discard_preallocations, "dev %s needed %d",
+ sb->s_id, needed);
for (i = 0; i < EXT4_SB(sb)->s_groups_count && needed > 0; i++) {
ret = ext4_mb_discard_group_preallocations(sb, i, needed);
freed += ret;
@@ -4286,12 +4533,24 @@
struct ext4_sb_info *sbi;
struct super_block *sb;
ext4_fsblk_t block = 0;
- unsigned long inquota;
- unsigned long reserv_blks = 0;
+ unsigned int inquota;
+ unsigned int reserv_blks = 0;
sb = ar->inode->i_sb;
sbi = EXT4_SB(sb);
+ trace_mark(ext4_request_blocks, "dev %s flags %u len %u ino %lu "
+ "lblk %llu goal %llu lleft %llu lright %llu "
+ "pleft %llu pright %llu ",
+ sb->s_id, ar->flags, ar->len,
+ ar->inode ? ar->inode->i_ino : 0,
+ (unsigned long long) ar->logical,
+ (unsigned long long) ar->goal,
+ (unsigned long long) ar->lleft,
+ (unsigned long long) ar->lright,
+ (unsigned long long) ar->pleft,
+ (unsigned long long) ar->pright);
+
if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag) {
/*
* With delalloc we already reserved the blocks
@@ -4313,7 +4572,7 @@
}
if (ar->len == 0) {
*errp = -EDQUOT;
- return 0;
+ goto out3;
}
inquota = ar->len;
@@ -4348,10 +4607,14 @@
ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len)
ext4_mb_new_preallocation(ac);
}
-
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
if (*errp == -EAGAIN) {
+ /*
+ * drop the reference that we took
+ * in ext4_mb_use_best_found
+ */
+ ext4_mb_release_context(ac);
ac->ac_b_ex.fe_group = 0;
ac->ac_b_ex.fe_start = 0;
ac->ac_b_ex.fe_len = 0;
@@ -4382,6 +4645,26 @@
out1:
if (ar->len < inquota)
DQUOT_FREE_BLOCK(ar->inode, inquota - ar->len);
+out3:
+ if (!ar->len) {
+ if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag)
+ /* release all the reserved blocks if non delalloc */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ reserv_blks);
+ }
+
+ trace_mark(ext4_allocate_blocks,
+ "dev %s block %llu flags %u len %u ino %lu "
+ "logical %llu goal %llu lleft %llu lright %llu "
+ "pleft %llu pright %llu ",
+ sb->s_id, (unsigned long long) block,
+ ar->flags, ar->len, ar->inode ? ar->inode->i_ino : 0,
+ (unsigned long long) ar->logical,
+ (unsigned long long) ar->goal,
+ (unsigned long long) ar->lleft,
+ (unsigned long long) ar->lright,
+ (unsigned long long) ar->pleft,
+ (unsigned long long) ar->pright);
return block;
}
@@ -4403,27 +4686,23 @@
static noinline_for_stack int
ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
- ext4_group_t group, ext4_grpblk_t block, int count)
+ struct ext4_free_data *new_entry)
{
+ ext4_grpblk_t block;
+ struct ext4_free_data *entry;
struct ext4_group_info *db = e4b->bd_info;
struct super_block *sb = e4b->bd_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_free_data *entry, *new_entry;
struct rb_node **n = &db->bb_free_root.rb_node, *node;
struct rb_node *parent = NULL, *new_node;
-
+ BUG_ON(!ext4_handle_valid(handle));
BUG_ON(e4b->bd_bitmap_page == NULL);
BUG_ON(e4b->bd_buddy_page == NULL);
- new_entry = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
- new_entry->start_blk = block;
- new_entry->group = group;
- new_entry->count = count;
- new_entry->t_tid = handle->h_transaction->t_tid;
new_node = &new_entry->node;
+ block = new_entry->start_blk;
- ext4_lock_group(sb, group);
if (!*n) {
/* first free block exent. We need to
protect buddy cache from being freed,
@@ -4441,10 +4720,9 @@
else if (block >= (entry->start_blk + entry->count))
n = &(*n)->rb_right;
else {
- ext4_unlock_group(sb, group);
- ext4_error(sb, __func__,
- "Double free of blocks %d (%d %d)\n",
- block, entry->start_blk, entry->count);
+ ext4_grp_locked_error(sb, e4b->bd_group, __func__,
+ "Double free of blocks %d (%d %d)",
+ block, entry->start_blk, entry->count);
return 0;
}
}
@@ -4483,7 +4761,6 @@
spin_lock(&sbi->s_md_lock);
list_add(&new_entry->list, &handle->h_transaction->t_private_list);
spin_unlock(&sbi->s_md_lock);
- ext4_unlock_group(sb, group);
return 0;
}
@@ -4499,7 +4776,7 @@
struct ext4_allocation_context *ac = NULL;
struct ext4_group_desc *gdp;
struct ext4_super_block *es;
- unsigned long overflow;
+ unsigned int overflow;
ext4_grpblk_t bit;
struct buffer_head *gd_bh;
ext4_group_t block_group;
@@ -4522,6 +4799,10 @@
}
ext4_debug("freeing block %lu\n", block);
+ trace_mark(ext4_free_blocks,
+ "dev %s block %llu count %lu metadata %d ino %lu",
+ sb->s_id, (unsigned long long) block, count, metadata,
+ inode ? inode->i_ino : 0);
ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
if (ac) {
@@ -4581,11 +4862,6 @@
err = ext4_journal_get_write_access(handle, gd_bh);
if (err)
goto error_return;
-
- err = ext4_mb_load_buddy(sb, block_group, &e4b);
- if (err)
- goto error_return;
-
#ifdef AGGRESSIVE_CHECK
{
int i;
@@ -4593,13 +4869,6 @@
BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data));
}
#endif
- mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
- bit, count);
-
- /* We dirtied the bitmap block */
- BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
-
if (ac) {
ac->ac_b_ex.fe_group = block_group;
ac->ac_b_ex.fe_start = bit;
@@ -4607,19 +4876,41 @@
ext4_mb_store_history(ac);
}
- if (metadata) {
- /* blocks being freed are metadata. these blocks shouldn't
- * be used until this transaction is committed */
- ext4_mb_free_metadata(handle, &e4b, block_group, bit, count);
+ err = ext4_mb_load_buddy(sb, block_group, &e4b);
+ if (err)
+ goto error_return;
+ if (metadata && ext4_handle_valid(handle)) {
+ struct ext4_free_data *new_entry;
+ /*
+ * blocks being freed are metadata. these blocks shouldn't
+ * be used until this transaction is committed
+ */
+ new_entry = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+ new_entry->start_blk = bit;
+ new_entry->group = block_group;
+ new_entry->count = count;
+ new_entry->t_tid = handle->h_transaction->t_tid;
+ ext4_lock_group(sb, block_group);
+ mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
+ bit, count);
+ ext4_mb_free_metadata(handle, &e4b, new_entry);
+ ext4_unlock_group(sb, block_group);
} else {
ext4_lock_group(sb, block_group);
+ /* need to update group_info->bb_free and bitmap
+ * with group lock held. generate_buddy look at
+ * them with group lock_held
+ */
+ mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
+ bit, count);
mb_free_blocks(inode, &e4b, bit, count);
ext4_mb_return_to_preallocation(inode, &e4b, block, count);
ext4_unlock_group(sb, block_group);
}
spin_lock(sb_bgl_lock(sbi, block_group));
- le16_add_cpu(&gdp->bg_free_blocks_count, count);
+ ret = ext4_free_blks_count(sb, gdp) + count;
+ ext4_free_blks_set(sb, gdp, ret);
gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
spin_unlock(sb_bgl_lock(sbi, block_group));
percpu_counter_add(&sbi->s_freeblocks_counter, count);
@@ -4635,9 +4926,13 @@
*freed += count;
+ /* We dirtied the bitmap block */
+ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+
/* And the group descriptor block */
BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
- ret = ext4_journal_dirty_metadata(handle, gd_bh);
+ ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
if (!err)
err = ret;
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index b5dff1f..10a2921 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -20,6 +20,7 @@
#include <linux/version.h>
#include <linux/blkdev.h>
#include <linux/marker.h>
+#include <linux/mutex.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include "group.h"
@@ -98,9 +99,6 @@
*/
#define MB_DEFAULT_GROUP_PREALLOC 512
-static struct kmem_cache *ext4_pspace_cachep;
-static struct kmem_cache *ext4_ac_cachep;
-static struct kmem_cache *ext4_free_ext_cachep;
struct ext4_free_data {
/* this links the free block information from group_info */
@@ -120,26 +118,6 @@
tid_t t_tid;
};
-struct ext4_group_info {
- unsigned long bb_state;
- struct rb_root bb_free_root;
- unsigned short bb_first_free;
- unsigned short bb_free;
- unsigned short bb_fragments;
- struct list_head bb_prealloc_list;
-#ifdef DOUBLE_CHECK
- void *bb_bitmap;
-#endif
- unsigned short bb_counters[];
-};
-
-#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
-#define EXT4_GROUP_INFO_LOCKED_BIT 1
-
-#define EXT4_MB_GRP_NEED_INIT(grp) \
- (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
-
-
struct ext4_prealloc_space {
struct list_head pa_inode_list;
struct list_head pa_group_list;
@@ -217,6 +195,11 @@
__u8 ac_op; /* operation, for history only */
struct page *ac_bitmap_page;
struct page *ac_buddy_page;
+ /*
+ * pointer to the held semaphore upon successful
+ * block allocation
+ */
+ struct rw_semaphore *alloc_semp;
struct ext4_prealloc_space *ac_pa;
struct ext4_locality_group *ac_lg;
};
@@ -250,6 +233,7 @@
struct super_block *bd_sb;
__u16 bd_blkbits;
ext4_group_t bd_group;
+ struct rw_semaphore *alloc_semp;
};
#define EXT4_MB_BITMAP(e4b) ((e4b)->bd_bitmap)
#define EXT4_MB_BUDDY(e4b) ((e4b)->bd_buddy)
@@ -259,51 +243,12 @@
{
return;
}
-#else
-static void ext4_mb_store_history(struct ext4_allocation_context *ac);
#endif
#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
struct buffer_head *read_block_bitmap(struct super_block *, ext4_group_t);
-
-static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
- ext4_group_t group);
-static void ext4_mb_return_to_preallocation(struct inode *inode,
- struct ext4_buddy *e4b, sector_t block,
- int count);
-static void ext4_mb_put_pa(struct ext4_allocation_context *,
- struct super_block *, struct ext4_prealloc_space *pa);
-static int ext4_mb_init_per_dev_proc(struct super_block *sb);
-static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
-static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
-
-
-static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
-{
- struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
- bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
-}
-
-static inline void ext4_unlock_group(struct super_block *sb,
- ext4_group_t group)
-{
- struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
- bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
-}
-
-static inline int ext4_is_group_locked(struct super_block *sb,
- ext4_group_t group)
-{
- struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
- return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
- &(grinfo->bb_state));
-}
-
-static ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
+static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
struct ext4_free_extent *fex)
{
ext4_fsblk_t block;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index f2a9cf4..734abca 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -59,7 +59,8 @@
/*
* Make sure the credit we accumalated is not really high
*/
- if (needed && handle->h_buffer_credits >= EXT4_RESERVE_TRANS_BLOCKS) {
+ if (needed && ext4_handle_has_enough_credits(handle,
+ EXT4_RESERVE_TRANS_BLOCKS)) {
retval = ext4_journal_restart(handle, needed);
if (retval)
goto err_out;
@@ -229,7 +230,7 @@
{
int retval = 0, needed;
- if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS)
+ if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
return 0;
/*
* We are freeing a blocks. During this we touch
@@ -458,13 +459,13 @@
struct list_blocks_struct lb;
unsigned long max_entries;
- if (!test_opt(inode->i_sb, EXTENTS))
- /*
- * if mounted with noextents we don't allow the migrate
- */
- return -EINVAL;
-
- if ((EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ /*
+ * If the filesystem does not support extents, or the inode
+ * already is extent-based, error out.
+ */
+ if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_INCOMPAT_EXTENTS) ||
+ (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
return -EINVAL;
if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 4b8d431..fec0b4c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -368,6 +368,8 @@
goto fail;
}
hinfo->hash_version = root->info.hash_version;
+ if (hinfo->hash_version <= DX_HASH_TEA)
+ hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
if (d_name)
ext4fs_dirhash(d_name->name, d_name->len, hinfo);
@@ -637,6 +639,9 @@
dir = dir_file->f_path.dentry->d_inode;
if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+ if (hinfo.hash_version <= DX_HASH_TEA)
+ hinfo.hash_version +=
+ EXT4_SB(dir->i_sb)->s_hash_unsigned;
hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
start_hash, start_minor_hash);
@@ -802,7 +807,7 @@
static inline int search_dirblock(struct buffer_head *bh,
struct inode *dir,
const struct qstr *d_name,
- unsigned long offset,
+ unsigned int offset,
struct ext4_dir_entry_2 ** res_dir)
{
struct ext4_dir_entry_2 * de;
@@ -1039,11 +1044,11 @@
bh = ext4_find_entry(dir, &dentry->d_name, &de);
inode = NULL;
if (bh) {
- unsigned long ino = le32_to_cpu(de->inode);
+ __u32 ino = le32_to_cpu(de->inode);
brelse(bh);
if (!ext4_valid_inum(dir->i_sb, ino)) {
ext4_error(dir->i_sb, "ext4_lookup",
- "bad inode number: %lu", ino);
+ "bad inode number: %u", ino);
return ERR_PTR(-EIO);
}
inode = ext4_iget(dir->i_sb, ino);
@@ -1056,7 +1061,7 @@
struct dentry *ext4_get_parent(struct dentry *child)
{
- unsigned long ino;
+ __u32 ino;
struct inode *inode;
static const struct qstr dotdot = {
.name = "..",
@@ -1074,7 +1079,7 @@
if (!ext4_valid_inum(child->d_inode->i_sb, ino)) {
ext4_error(child->d_inode->i_sb, "ext4_get_parent",
- "bad inode number: %lu", ino);
+ "bad inode number: %u", ino);
return ERR_PTR(-EIO);
}
@@ -1162,9 +1167,9 @@
u32 hash2;
struct dx_map_entry *map;
char *data1 = (*bh)->b_data, *data2;
- unsigned split, move, size, i;
+ unsigned split, move, size;
struct ext4_dir_entry_2 *de = NULL, *de2;
- int err = 0;
+ int err = 0, i;
bh2 = ext4_append (handle, dir, &newblock, &err);
if (!(bh2)) {
@@ -1224,10 +1229,10 @@
de = de2;
}
dx_insert_block(frame, hash2 + continued, newblock);
- err = ext4_journal_dirty_metadata(handle, bh2);
+ err = ext4_handle_dirty_metadata(handle, dir, bh2);
if (err)
goto journal_error;
- err = ext4_journal_dirty_metadata(handle, frame->bh);
+ err = ext4_handle_dirty_metadata(handle, dir, frame->bh);
if (err)
goto journal_error;
brelse(bh2);
@@ -1262,7 +1267,7 @@
struct inode *dir = dentry->d_parent->d_inode;
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
- unsigned long offset = 0;
+ unsigned int offset = 0;
unsigned short reclen;
int nlen, rlen, err;
char *top;
@@ -1331,8 +1336,8 @@
ext4_update_dx_flag(dir);
dir->i_version++;
ext4_mark_inode_dirty(handle, dir);
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, dir, bh);
if (err)
ext4_std_error(dir->i_sb, err);
brelse(bh);
@@ -1404,6 +1409,8 @@
/* Initialize as for dx_probe */
hinfo.hash_version = root->info.hash_version;
+ if (hinfo.hash_version <= DX_HASH_TEA)
+ hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
ext4fs_dirhash(name, namelen, &hinfo);
frame = frames;
@@ -1433,7 +1440,6 @@
struct inode *inode)
{
struct inode *dir = dentry->d_parent->d_inode;
- unsigned long offset;
struct buffer_head *bh;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
@@ -1455,7 +1461,7 @@
ext4_mark_inode_dirty(handle, dir);
}
blocks = dir->i_size >> sb->s_blocksize_bits;
- for (block = 0, offset = 0; block < blocks; block++) {
+ for (block = 0; block < blocks; block++) {
bh = ext4_bread(handle, dir, block, 0, &retval);
if(!bh)
return retval;
@@ -1570,7 +1576,7 @@
dxtrace(dx_show_index("node", frames[1].entries));
dxtrace(dx_show_index("node",
((struct dx_node *) bh2->b_data)->entries));
- err = ext4_journal_dirty_metadata(handle, bh2);
+ err = ext4_handle_dirty_metadata(handle, inode, bh2);
if (err)
goto journal_error;
brelse (bh2);
@@ -1596,7 +1602,7 @@
if (err)
goto journal_error;
}
- ext4_journal_dirty_metadata(handle, frames[0].bh);
+ ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
}
de = do_split(handle, dir, &bh, frame, &hinfo, &err);
if (!de)
@@ -1642,8 +1648,8 @@
else
de->inode = 0;
dir->i_version++;
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, dir, bh);
return 0;
}
i += ext4_rec_len_from_disk(de->rec_len);
@@ -1721,7 +1727,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode (handle, dir, mode);
err = PTR_ERR(inode);
@@ -1755,7 +1761,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, mode);
err = PTR_ERR(inode);
@@ -1791,7 +1797,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFDIR | mode);
err = PTR_ERR(inode);
@@ -1820,8 +1826,8 @@
strcpy(de->name, "..");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
inode->i_nlink = 2;
- BUFFER_TRACE(dir_block, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, dir_block);
+ BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, dir, dir_block);
brelse(dir_block);
ext4_mark_inode_dirty(handle, inode);
err = ext4_add_entry(handle, dentry, inode);
@@ -1850,7 +1856,7 @@
*/
static int empty_dir(struct inode *inode)
{
- unsigned long offset;
+ unsigned int offset;
struct buffer_head *bh;
struct ext4_dir_entry_2 *de, *de1;
struct super_block *sb;
@@ -1895,7 +1901,7 @@
if (err)
ext4_error(sb, __func__,
"error %d reading directory"
- " #%lu offset %lu",
+ " #%lu offset %u",
err, inode->i_ino, offset);
offset += sb->s_blocksize;
continue;
@@ -1933,6 +1939,9 @@
struct ext4_iloc iloc;
int err = 0, rc;
+ if (!ext4_handle_valid(handle))
+ return 0;
+
lock_super(sb);
if (!list_empty(&EXT4_I(inode)->i_orphan))
goto out_unlock;
@@ -1961,7 +1970,7 @@
/* Insert this inode at the head of the on-disk orphan list... */
NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
- err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, inode, EXT4_SB(sb)->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
@@ -1995,10 +2004,13 @@
struct list_head *prev;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi;
- unsigned long ino_next;
+ __u32 ino_next;
struct ext4_iloc iloc;
int err = 0;
+ if (!ext4_handle_valid(handle))
+ return 0;
+
lock_super(inode->i_sb);
if (list_empty(&ei->i_orphan)) {
unlock_super(inode->i_sb);
@@ -2017,7 +2029,7 @@
* transaction handle with which to update the orphan list on
* disk, but we still need to remove the inode from the linked
* list in memory. */
- if (!handle)
+ if (sbi->s_journal && !handle)
goto out;
err = ext4_reserve_inode_write(handle, inode, &iloc);
@@ -2025,19 +2037,19 @@
goto out_err;
if (prev == &sbi->s_orphan) {
- jbd_debug(4, "superblock will point to %lu\n", ino_next);
+ jbd_debug(4, "superblock will point to %u\n", ino_next);
BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto out_brelse;
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
- err = ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, inode, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
&list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode;
- jbd_debug(4, "orphan inode %lu will point to %lu\n",
+ jbd_debug(4, "orphan inode %lu will point to %u\n",
i_prev->i_ino, ino_next);
err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
if (err)
@@ -2082,7 +2094,7 @@
goto end_rmdir;
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = dentry->d_inode;
@@ -2136,7 +2148,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
retval = -ENOENT;
bh = ext4_find_entry(dir, &dentry->d_name, &de);
@@ -2193,7 +2205,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO);
err = PTR_ERR(inode);
@@ -2256,7 +2268,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode->i_ctime = ext4_current_time(inode);
ext4_inc_count(handle, inode);
@@ -2305,7 +2317,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de);
/*
@@ -2359,8 +2371,8 @@
new_dir->i_ctime = new_dir->i_mtime =
ext4_current_time(new_dir);
ext4_mark_inode_dirty(handle, new_dir);
- BUFFER_TRACE(new_bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, new_bh);
+ BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, new_dir, new_bh);
brelse(new_bh);
new_bh = NULL;
}
@@ -2410,8 +2422,8 @@
BUFFER_TRACE(dir_bh, "get_write_access");
ext4_journal_get_write_access(handle, dir_bh);
PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino);
- BUFFER_TRACE(dir_bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, dir_bh);
+ BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
ext4_dec_count(handle, old_dir);
if (new_inode) {
/* checked empty_dir above, can't have another parent,
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index b6ec184..c328be5 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -50,7 +50,7 @@
ext4_get_group_no_and_offset(sb, start, NULL, &offset);
if (group != sbi->s_groups_count)
ext4_warning(sb, __func__,
- "Cannot add at group %u (only %lu groups)",
+ "Cannot add at group %u (only %u groups)",
input->group, sbi->s_groups_count);
else if (offset != 0)
ext4_warning(sb, __func__, "Last group not full");
@@ -149,7 +149,7 @@
{
int err;
- if (handle->h_buffer_credits >= thresh)
+ if (ext4_handle_has_enough_credits(handle, thresh))
return 0;
err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
@@ -232,7 +232,7 @@
memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
set_buffer_uptodate(gdb);
unlock_buffer(gdb);
- ext4_journal_dirty_metadata(handle, gdb);
+ ext4_handle_dirty_metadata(handle, NULL, gdb);
ext4_set_bit(bit, bh->b_data);
brelse(gdb);
}
@@ -251,7 +251,7 @@
err = PTR_ERR(bh);
goto exit_bh;
}
- ext4_journal_dirty_metadata(handle, gdb);
+ ext4_handle_dirty_metadata(handle, NULL, gdb);
ext4_set_bit(bit, bh->b_data);
brelse(gdb);
}
@@ -276,7 +276,7 @@
err = PTR_ERR(it);
goto exit_bh;
}
- ext4_journal_dirty_metadata(handle, it);
+ ext4_handle_dirty_metadata(handle, NULL, it);
brelse(it);
ext4_set_bit(bit, bh->b_data);
}
@@ -284,11 +284,9 @@
if ((err = extend_or_restart_transaction(handle, 2, bh)))
goto exit_bh;
- mark_bitmap_end(input->blocks_count, EXT4_BLOCKS_PER_GROUP(sb),
- bh->b_data);
- ext4_journal_dirty_metadata(handle, bh);
+ mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8, bh->b_data);
+ ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
-
/* Mark unused entries in inode bitmap used */
ext4_debug("clear inode bitmap %#04llx (+%llu)\n",
input->inode_bitmap, input->inode_bitmap - start);
@@ -297,9 +295,9 @@
goto exit_journal;
}
- 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);
- ext4_journal_dirty_metadata(handle, bh);
+ ext4_handle_dirty_metadata(handle, NULL, bh);
exit_bh:
brelse(bh);
@@ -486,12 +484,12 @@
* reserved inode, and will become GDT blocks (primary and backup).
*/
data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
- ext4_journal_dirty_metadata(handle, dind);
+ ext4_handle_dirty_metadata(handle, NULL, dind);
brelse(dind);
inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
ext4_mark_iloc_dirty(handle, inode, &iloc);
memset((*primary)->b_data, 0, sb->s_blocksize);
- ext4_journal_dirty_metadata(handle, *primary);
+ ext4_handle_dirty_metadata(handle, NULL, *primary);
o_group_desc = EXT4_SB(sb)->s_group_desc;
memcpy(n_group_desc, o_group_desc,
@@ -502,7 +500,7 @@
kfree(o_group_desc);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
- ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
return 0;
@@ -618,7 +616,7 @@
primary[i]->b_blocknr, gdbackups,
blk + primary[i]->b_blocknr); */
data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
- err2 = ext4_journal_dirty_metadata(handle, primary[i]);
+ err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]);
if (!err)
err = err2;
}
@@ -676,7 +674,8 @@
struct buffer_head *bh;
/* Out of journal space, and can't get more - abort - so sad */
- if (handle->h_buffer_credits == 0 &&
+ if (ext4_handle_valid(handle) &&
+ handle->h_buffer_credits == 0 &&
ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
(err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
break;
@@ -696,7 +695,7 @@
memset(bh->b_data + size, 0, rest);
set_buffer_uptodate(bh);
unlock_buffer(bh);
- ext4_journal_dirty_metadata(handle, bh);
+ ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
}
if ((err2 = ext4_journal_stop(handle)) && !err)
@@ -715,7 +714,7 @@
exit_err:
if (err) {
ext4_warning(sb, __func__,
- "can't update backup for group %lu (err %d), "
+ "can't update backup for group %u (err %d), "
"forcing fsck on next reboot", group, err);
sbi->s_mount_state &= ~EXT4_VALID_FS;
sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
@@ -747,6 +746,7 @@
struct inode *inode = NULL;
handle_t *handle;
int gdb_off, gdb_num;
+ int num_grp_locked = 0;
int err, err2;
gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
@@ -761,13 +761,13 @@
if (ext4_blocks_count(es) + input->blocks_count <
ext4_blocks_count(es)) {
- ext4_warning(sb, __func__, "blocks_count overflow\n");
+ ext4_warning(sb, __func__, "blocks_count overflow");
return -EINVAL;
}
if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) <
le32_to_cpu(es->s_inodes_count)) {
- ext4_warning(sb, __func__, "inodes_count overflow\n");
+ ext4_warning(sb, __func__, "inodes_count overflow");
return -EINVAL;
}
@@ -787,6 +787,7 @@
}
}
+
if ((err = verify_group_input(sb, input)))
goto exit_put;
@@ -855,6 +856,7 @@
* using the new disk blocks.
*/
+ num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, input->group);
/* Update group descriptor block for new group */
gdp = (struct ext4_group_desc *)((char *)primary->b_data +
gdb_off * EXT4_DESC_SIZE(sb));
@@ -862,17 +864,20 @@
ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
- gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count);
- gdp->bg_free_inodes_count = cpu_to_le16(EXT4_INODES_PER_GROUP(sb));
+ ext4_free_blks_set(sb, gdp, input->free_blocks_count);
+ ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
+ gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
/*
* We can allocate memory for mb_alloc based on the new group
* descriptor
*/
- err = ext4_mb_add_more_groupinfo(sb, input->group, gdp);
- if (err)
+ err = ext4_mb_add_groupinfo(sb, input->group, gdp);
+ if (err) {
+ ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked);
goto exit_journal;
+ }
/*
* Make the new blocks and inodes valid next. We do this before
@@ -914,8 +919,9 @@
/* Update the global fs size fields */
sbi->s_groups_count++;
+ ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked);
- ext4_journal_dirty_metadata(handle, primary);
+ ext4_handle_dirty_metadata(handle, NULL, primary);
/* Update the reserved block counts only once the new group is
* active. */
@@ -937,7 +943,7 @@
EXT4_INODES_PER_GROUP(sb);
}
- ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
sb->s_dirt = 1;
exit_journal:
@@ -975,9 +981,7 @@
struct buffer_head *bh;
handle_t *handle;
int err;
- unsigned long freed_blocks;
ext4_group_t group;
- struct ext4_group_info *grp;
/* We don't need to worry about locking wrt other resizers just
* yet: we're going to revalidate es->s_blocks_count after
@@ -997,8 +1001,7 @@
" too large to resize to %llu blocks safely\n",
sb->s_id, n_blocks_count);
if (sizeof(sector_t) < 8)
- ext4_warning(sb, __func__,
- "CONFIG_LBD not enabled\n");
+ ext4_warning(sb, __func__, "CONFIG_LBD not enabled");
return -EINVAL;
}
@@ -1071,62 +1074,18 @@
goto exit_put;
}
ext4_blocks_count_set(es, o_blocks_count + add);
- ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
sb->s_dirt = 1;
unlock_super(sb);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
- ext4_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);
+ /* We add the blocks to the bitmap and set the group need init bit */
+ ext4_add_groupblocks(handle, sb, o_blocks_count, add);
ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
if ((err = ext4_journal_stop(handle)))
goto exit_put;
- /*
- * Mark mballoc pages as not up to date so that they will be updated
- * next time they are loaded by ext4_mb_load_buddy.
- *
- * XXX Bad, Bad, BAD!!! We should not be overloading the
- * Uptodate flag, particularly on thte bitmap bh, as way of
- * hinting to ext4_mb_load_buddy() that it needs to be
- * overloaded. A user could take a LVM snapshot, then do an
- * on-line fsck, and clear the uptodate flag, and this would
- * not be a bug in userspace, but a bug in the kernel. FIXME!!!
- */
- {
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct inode *inode = sbi->s_buddy_cache;
- int blocks_per_page;
- int block;
- int pnum;
- struct page *page;
-
- /* Set buddy page as not up to date */
- blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
- block = group * 2;
- pnum = block / blocks_per_page;
- page = find_get_page(inode->i_mapping, pnum);
- if (page != NULL) {
- ClearPageUptodate(page);
- page_cache_release(page);
- }
-
- /* Set bitmap page as not up to date */
- block++;
- pnum = block / blocks_per_page;
- page = find_get_page(inode->i_mapping, pnum);
- if (page != NULL) {
- ClearPageUptodate(page);
- page_cache_release(page);
- }
-
- /* Get the info on the last group */
- grp = ext4_get_group_info(sb, group);
-
- /* Update free blocks in group info */
- ext4_mb_update_group_info(grp, add);
- }
-
if (test_opt(sb, DEBUG))
printk(KERN_DEBUG "EXT4-fs: extended group to %llu blocks\n",
ext4_blocks_count(es));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9494bb2..8f7e0be 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -51,8 +51,6 @@
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
-static int ext4_create_journal(struct super_block *, struct ext4_super_block *,
- unsigned int);
static void ext4_commit_super(struct super_block *sb,
struct ext4_super_block *es, int sync);
static void ext4_mark_recovery_complete(struct super_block *sb,
@@ -93,6 +91,38 @@
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}
+__u32 ext4_free_blks_count(struct super_block *sb,
+ struct ext4_group_desc *bg)
+{
+ return le16_to_cpu(bg->bg_free_blocks_count_lo) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
+}
+
+__u32 ext4_free_inodes_count(struct super_block *sb,
+ struct ext4_group_desc *bg)
+{
+ return le16_to_cpu(bg->bg_free_inodes_count_lo) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
+}
+
+__u32 ext4_used_dirs_count(struct super_block *sb,
+ struct ext4_group_desc *bg)
+{
+ return le16_to_cpu(bg->bg_used_dirs_count_lo) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
+}
+
+__u32 ext4_itable_unused_count(struct super_block *sb,
+ struct ext4_group_desc *bg)
+{
+ return le16_to_cpu(bg->bg_itable_unused_lo) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
+}
+
void ext4_block_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
@@ -117,6 +147,38 @@
bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
}
+void ext4_free_blks_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
+{
+ bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16);
+}
+
+void ext4_free_inodes_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
+{
+ bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
+}
+
+void ext4_used_dirs_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
+{
+ bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16);
+}
+
+void ext4_itable_unused_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
+{
+ bg->bg_itable_unused_lo = cpu_to_le16((__u16)count);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
+}
+
/*
* Wrappers for jbd2_journal_start/end.
*
@@ -136,13 +198,19 @@
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly. */
journal = EXT4_SB(sb)->s_journal;
- if (is_journal_aborted(journal)) {
- ext4_abort(sb, __func__,
- "Detected aborted journal");
- return ERR_PTR(-EROFS);
+ if (journal) {
+ if (is_journal_aborted(journal)) {
+ ext4_abort(sb, __func__,
+ "Detected aborted journal");
+ return ERR_PTR(-EROFS);
+ }
+ return jbd2_journal_start(journal, nblocks);
}
-
- return jbd2_journal_start(journal, nblocks);
+ /*
+ * We're not journaling, return the appropriate indication.
+ */
+ current->journal_info = EXT4_NOJOURNAL_HANDLE;
+ return current->journal_info;
}
/*
@@ -157,6 +225,14 @@
int err;
int rc;
+ if (!ext4_handle_valid(handle)) {
+ /*
+ * Do this here since we don't call jbd2_journal_stop() in
+ * no-journal mode.
+ */
+ current->journal_info = NULL;
+ return 0;
+ }
sb = handle->h_transaction->t_journal->j_private;
err = handle->h_err;
rc = jbd2_journal_stop(handle);
@@ -174,6 +250,8 @@
char nbuf[16];
const char *errstr = ext4_decode_error(NULL, err, nbuf);
+ BUG_ON(!ext4_handle_valid(handle));
+
if (bh)
BUFFER_TRACE(bh, "abort");
@@ -350,6 +428,44 @@
va_end(args);
}
+void ext4_grp_locked_error(struct super_block *sb, ext4_group_t grp,
+ const char *function, const char *fmt, ...)
+__releases(bitlock)
+__acquires(bitlock)
+{
+ va_list args;
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+ va_start(args, fmt);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ if (test_opt(sb, ERRORS_CONT)) {
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+ ext4_commit_super(sb, es, 0);
+ return;
+ }
+ ext4_unlock_group(sb, grp);
+ ext4_handle_error(sb);
+ /*
+ * We only get here in the ERRORS_RO case; relocking the group
+ * may be dangerous, but nothing bad will happen since the
+ * filesystem will have already been marked read/only and the
+ * journal has been aborted. We return 1 as a hint to callers
+ * who might what to use the return value from
+ * ext4_grp_locked_error() to distinguish beween the
+ * ERRORS_CONT and ERRORS_RO case, and perhaps return more
+ * aggressively from the ext4 function in question, with a
+ * more appropriate error code.
+ */
+ ext4_lock_group(sb, grp);
+ return;
+}
+
+
void ext4_update_dynamic_rev(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
@@ -389,7 +505,7 @@
return bdev;
fail:
- printk(KERN_ERR "EXT4: failed to open journal device %s: %ld\n",
+ printk(KERN_ERR "EXT4-fs: failed to open journal device %s: %ld\n",
__bdevname(dev, b), PTR_ERR(bdev));
return NULL;
}
@@ -448,11 +564,13 @@
ext4_mb_release(sb);
ext4_ext_release(sb);
ext4_xattr_put_super(sb);
- err = jbd2_journal_destroy(sbi->s_journal);
- sbi->s_journal = NULL;
- if (err < 0)
- ext4_abort(sb, __func__, "Couldn't clean up the journal");
-
+ if (sbi->s_journal) {
+ err = jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
+ if (err < 0)
+ ext4_abort(sb, __func__,
+ "Couldn't clean up the journal");
+ }
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
@@ -522,6 +640,11 @@
memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
+ /*
+ * Note: We can be called before EXT4_SB(sb)->s_journal is set,
+ * therefore it can be null here. Don't check it, just initialize
+ * jinode.
+ */
jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode);
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
@@ -588,7 +711,8 @@
}
#endif
ext4_discard_preallocations(inode);
- jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
+ if (EXT4_JOURNAL(inode))
+ jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
&EXT4_I(inode)->jinode);
}
@@ -681,10 +805,19 @@
#endif
if (!test_opt(sb, RESERVATION))
seq_puts(seq, ",noreservation");
- if (sbi->s_commit_interval) {
+ if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
seq_printf(seq, ",commit=%u",
(unsigned) (sbi->s_commit_interval / HZ));
}
+ if (sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) {
+ seq_printf(seq, ",min_batch_time=%u",
+ (unsigned) sbi->s_min_batch_time);
+ }
+ if (sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) {
+ seq_printf(seq, ",max_batch_time=%u",
+ (unsigned) sbi->s_min_batch_time);
+ }
+
/*
* We're changing the default of barrier mount option, so
* let's always display its mount state so it's clear what its
@@ -696,8 +829,6 @@
seq_puts(seq, ",journal_async_commit");
if (test_opt(sb, NOBH))
seq_puts(seq, ",nobh");
- if (!test_opt(sb, EXTENTS))
- seq_puts(seq, ",noextents");
if (test_opt(sb, I_VERSION))
seq_puts(seq, ",i_version");
if (!test_opt(sb, DELALLOC))
@@ -772,6 +903,25 @@
ext4_nfs_get_inode);
}
+/*
+ * Try to release metadata pages (indirect blocks, directories) which are
+ * mapped via the block device. Since these pages could have journal heads
+ * which would prevent try_to_free_buffers() from freeing them, we must use
+ * jbd2 layer's try_to_free_buffers() function to release them.
+ */
+static int bdev_try_to_free_page(struct super_block *sb, struct page *page, gfp_t wait)
+{
+ journal_t *journal = EXT4_SB(sb)->s_journal;
+
+ WARN_ON(PageChecked(page));
+ if (!page_has_buffers(page))
+ return 0;
+ if (journal)
+ return jbd2_journal_try_to_free_buffers(journal, page,
+ wait & ~__GFP_WAIT);
+ return try_to_free_buffers(page);
+}
+
#ifdef CONFIG_QUOTA
#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group")
#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
@@ -838,6 +988,7 @@
.quota_read = ext4_quota_read,
.quota_write = ext4_quota_write,
#endif
+ .bdev_try_to_free_page = bdev_try_to_free_page,
};
static const struct export_operations ext4_export_ops = {
@@ -852,16 +1003,17 @@
Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
- Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
+ Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
+ Opt_journal_update, Opt_journal_dev,
Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
- Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
+ Opt_grpquota, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
- Opt_inode_readahead_blks
+ Opt_inode_readahead_blks, Opt_journal_ioprio
};
static const match_table_t tokens = {
@@ -891,8 +1043,9 @@
{Opt_nobh, "nobh"},
{Opt_bh, "bh"},
{Opt_commit, "commit=%u"},
+ {Opt_min_batch_time, "min_batch_time=%u"},
+ {Opt_max_batch_time, "max_batch_time=%u"},
{Opt_journal_update, "journal=update"},
- {Opt_journal_inum, "journal=%u"},
{Opt_journal_dev, "journal_dev=%u"},
{Opt_journal_checksum, "journal_checksum"},
{Opt_journal_async_commit, "journal_async_commit"},
@@ -913,14 +1066,13 @@
{Opt_quota, "quota"},
{Opt_usrquota, "usrquota"},
{Opt_barrier, "barrier=%u"},
- {Opt_extents, "extents"},
- {Opt_noextents, "noextents"},
{Opt_i_version, "i_version"},
{Opt_stripe, "stripe=%u"},
{Opt_resize, "resize"},
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
+ {Opt_journal_ioprio, "journal_ioprio=%u"},
{Opt_err, NULL},
};
@@ -945,8 +1097,11 @@
return sb_block;
}
+#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+
static int parse_options(char *options, struct super_block *sb,
- unsigned int *inum, unsigned long *journal_devnum,
+ unsigned long *journal_devnum,
+ unsigned int *journal_ioprio,
ext4_fsblk_t *n_blocks_count, int is_remount)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -958,7 +1113,6 @@
int qtype, qfmt;
char *qname;
#endif
- ext4_fsblk_t last_block;
if (!options)
return 1;
@@ -1070,16 +1224,6 @@
}
set_opt(sbi->s_mount_opt, UPDATE_JOURNAL);
break;
- case Opt_journal_inum:
- if (is_remount) {
- printk(KERN_ERR "EXT4-fs: cannot specify "
- "journal on remount\n");
- return 0;
- }
- if (match_int(&args[0], &option))
- return 0;
- *inum = option;
- break;
case Opt_journal_dev:
if (is_remount) {
printk(KERN_ERR "EXT4-fs: cannot specify "
@@ -1109,6 +1253,22 @@
option = JBD2_DEFAULT_MAX_COMMIT_AGE;
sbi->s_commit_interval = HZ * option;
break;
+ case Opt_max_batch_time:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0)
+ return 0;
+ if (option == 0)
+ option = EXT4_DEF_MAX_BATCH_TIME;
+ sbi->s_max_batch_time = option;
+ break;
+ case Opt_min_batch_time:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0)
+ return 0;
+ sbi->s_min_batch_time = option;
+ break;
case Opt_data_journal:
data_opt = EXT4_MOUNT_JOURNAL_DATA;
goto datacheck;
@@ -1279,33 +1439,6 @@
case Opt_bh:
clear_opt(sbi->s_mount_opt, NOBH);
break;
- case Opt_extents:
- if (!EXT4_HAS_INCOMPAT_FEATURE(sb,
- EXT4_FEATURE_INCOMPAT_EXTENTS)) {
- ext4_warning(sb, __func__,
- "extents feature not enabled "
- "on this filesystem, use tune2fs\n");
- return 0;
- }
- set_opt(sbi->s_mount_opt, EXTENTS);
- break;
- case Opt_noextents:
- /*
- * When e2fsprogs support resizing an already existing
- * ext3 file system to greater than 2**32 we need to
- * add support to block allocator to handle growing
- * already existing block mapped inode so that blocks
- * allocated for them fall within 2**32
- */
- last_block = ext4_blocks_count(sbi->s_es) - 1;
- if (last_block > 0xffffffffULL) {
- printk(KERN_ERR "EXT4-fs: Filesystem too "
- "large to mount with "
- "-o noextents options\n");
- return 0;
- }
- clear_opt(sbi->s_mount_opt, EXTENTS);
- break;
case Opt_i_version:
set_opt(sbi->s_mount_opt, I_VERSION);
sb->s_flags |= MS_I_VERSION;
@@ -1330,6 +1463,14 @@
return 0;
sbi->s_inode_readahead_blks = option;
break;
+ case Opt_journal_ioprio:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0 || option > 7)
+ break;
+ *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE,
+ option);
+ break;
default:
printk(KERN_ERR
"EXT4-fs: Unrecognized mount option \"%s\" "
@@ -1405,24 +1546,19 @@
printk(KERN_WARNING
"EXT4-fs warning: checktime reached, "
"running e2fsck is recommended\n");
-#if 0
- /* @@@ We _will_ want to clear the valid bit if we find
- * inconsistencies, to force a fsck at reboot. But for
- * a plain journaled filesystem we can keep it set as
- * valid forever! :)
- */
- es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
-#endif
+ if (!sbi->s_journal)
+ es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
le16_add_cpu(&es->s_mnt_count, 1);
es->s_mtime = cpu_to_le32(get_seconds());
ext4_update_dynamic_rev(sb);
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ if (sbi->s_journal)
+ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, es, 1);
if (test_opt(sb, DEBUG))
- printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%lu, "
+ printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
"bpg=%lu, ipg=%lu, mo=%04lx]\n",
sb->s_blocksize,
sbi->s_groups_count,
@@ -1430,9 +1566,13 @@
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt);
- printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
- sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
- "external", EXT4_SB(sb)->s_journal->j_devname);
+ if (EXT4_SB(sb)->s_journal) {
+ printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
+ sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
+ "external", EXT4_SB(sb)->s_journal->j_devname);
+ } else {
+ printk(KERN_INFO "EXT4 FS on %s, no journal\n", sb->s_id);
+ }
return res;
}
@@ -1444,7 +1584,6 @@
ext4_group_t flex_group_count;
ext4_group_t flex_group;
int groups_per_flex = 0;
- __u64 block_bitmap = 0;
int i;
if (!sbi->s_es->s_log_groups_per_flex) {
@@ -1463,21 +1602,18 @@
sizeof(struct flex_groups), GFP_KERNEL);
if (sbi->s_flex_groups == NULL) {
printk(KERN_ERR "EXT4-fs: not enough memory for "
- "%lu flex groups\n", flex_group_count);
+ "%u flex groups\n", flex_group_count);
goto failed;
}
- gdp = ext4_get_group_desc(sb, 1, &bh);
- block_bitmap = ext4_block_bitmap(sb, gdp) - 1;
-
for (i = 0; i < sbi->s_groups_count; i++) {
gdp = ext4_get_group_desc(sb, i, &bh);
flex_group = ext4_flex_group(sbi, i);
sbi->s_flex_groups[flex_group].free_inodes +=
- le16_to_cpu(gdp->bg_free_inodes_count);
+ ext4_free_inodes_count(sb, gdp);
sbi->s_flex_groups[flex_group].free_blocks +=
- le16_to_cpu(gdp->bg_free_blocks_count);
+ ext4_free_blks_count(sb, gdp);
}
return 1;
@@ -1551,14 +1687,14 @@
block_bitmap = ext4_block_bitmap(sb, gdp);
if (block_bitmap < first_block || block_bitmap > last_block) {
printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
- "Block bitmap for group %lu not in group "
+ "Block bitmap for group %u not in group "
"(block %llu)!\n", i, block_bitmap);
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
if (inode_bitmap < first_block || inode_bitmap > last_block) {
printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
- "Inode bitmap for group %lu not in group "
+ "Inode bitmap for group %u not in group "
"(block %llu)!\n", i, inode_bitmap);
return 0;
}
@@ -1566,14 +1702,14 @@
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
- "Inode table for group %lu not in group "
+ "Inode table for group %u not in group "
"(block %llu)!\n", i, inode_table);
return 0;
}
spin_lock(sb_bgl_lock(sbi, i));
if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
- "Checksum for group %lu failed (%u!=%u)\n",
+ "Checksum for group %u failed (%u!=%u)\n",
i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
gdp)), le16_to_cpu(gdp->bg_checksum));
if (!(sb->s_flags & MS_RDONLY)) {
@@ -1865,19 +2001,20 @@
ext4_fsblk_t sb_block = get_sb_block(&data);
ext4_fsblk_t logical_sb_block;
unsigned long offset = 0;
- unsigned int journal_inum = 0;
unsigned long journal_devnum = 0;
unsigned long def_mount_opts;
struct inode *root;
char *cp;
+ const char *descr;
int ret = -EINVAL;
int blocksize;
- int db_count;
- int i;
+ unsigned int db_count;
+ unsigned int i;
int needs_recovery, has_huge_files;
- __le32 features;
+ int features;
__u64 blocks_count;
int err;
+ unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
@@ -1958,31 +2095,22 @@
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
+ sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
+ sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
+ sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
set_opt(sbi->s_mount_opt, RESERVATION);
set_opt(sbi->s_mount_opt, BARRIER);
/*
- * turn on extents feature by default in ext4 filesystem
- * only if feature flag already set by mkfs or tune2fs.
- * Use -o noextents to turn it off
- */
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
- set_opt(sbi->s_mount_opt, EXTENTS);
- else
- ext4_warning(sb, __func__,
- "extents feature not enabled on this filesystem, "
- "use tune2fs.\n");
-
- /*
* enable delayed allocation by default
* Use -o nodelalloc to turn it off
*/
set_opt(sbi->s_mount_opt, DELALLOC);
- if (!parse_options((char *) data, sb, &journal_inum, &journal_devnum,
- NULL, 0))
+ if (!parse_options((char *) data, sb, &journal_devnum,
+ &journal_ioprio, NULL, 0))
goto failed_mount;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
@@ -2004,15 +2132,17 @@
features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP);
if (features) {
printk(KERN_ERR "EXT4-fs: %s: couldn't mount because of "
- "unsupported optional features (%x).\n",
- sb->s_id, le32_to_cpu(features));
+ "unsupported optional features (%x).\n", sb->s_id,
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
+ ~EXT4_FEATURE_INCOMPAT_SUPP));
goto failed_mount;
}
features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP);
if (!(sb->s_flags & MS_RDONLY) && features) {
printk(KERN_ERR "EXT4-fs: %s: couldn't mount RDWR because of "
- "unsupported optional features (%x).\n",
- sb->s_id, le32_to_cpu(features));
+ "unsupported optional features (%x).\n", sb->s_id,
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
+ ~EXT4_FEATURE_RO_COMPAT_SUPP));
goto failed_mount;
}
has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
@@ -2117,6 +2247,18 @@
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
+ i = le32_to_cpu(es->s_flags);
+ if (i & EXT2_FLAGS_UNSIGNED_HASH)
+ sbi->s_hash_unsigned = 3;
+ else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+#ifdef __CHAR_UNSIGNED__
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+ sbi->s_hash_unsigned = 3;
+#else
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+#endif
+ sb->s_dirt = 1;
+ }
if (sbi->s_blocks_per_group > blocksize * 8) {
printk(KERN_ERR
@@ -2144,20 +2286,30 @@
if (EXT4_BLOCKS_PER_GROUP(sb) == 0)
goto cantfind_ext4;
- /* ensure blocks_count calculation below doesn't sign-extend */
- if (ext4_blocks_count(es) + EXT4_BLOCKS_PER_GROUP(sb) <
- le32_to_cpu(es->s_first_data_block) + 1) {
- printk(KERN_WARNING "EXT4-fs: bad geometry: block count %llu, "
- "first data block %u, blocks per group %lu\n",
- ext4_blocks_count(es),
- le32_to_cpu(es->s_first_data_block),
- EXT4_BLOCKS_PER_GROUP(sb));
+ /*
+ * It makes no sense for the first data block to be beyond the end
+ * of the filesystem.
+ */
+ if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
+ printk(KERN_WARNING "EXT4-fs: bad geometry: first data"
+ "block %u is beyond end of filesystem (%llu)\n",
+ le32_to_cpu(es->s_first_data_block),
+ ext4_blocks_count(es));
goto failed_mount;
}
blocks_count = (ext4_blocks_count(es) -
le32_to_cpu(es->s_first_data_block) +
EXT4_BLOCKS_PER_GROUP(sb) - 1);
do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
+ if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) {
+ printk(KERN_WARNING "EXT4-fs: groups count too large: %u "
+ "(block count %llu, first data block %u, "
+ "blocks per group %lu)\n", sbi->s_groups_count,
+ ext4_blocks_count(es),
+ le32_to_cpu(es->s_first_data_block),
+ EXT4_BLOCKS_PER_GROUP(sb));
+ goto failed_mount;
+ }
sbi->s_groups_count = blocks_count;
db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
EXT4_DESC_PER_BLOCK(sb);
@@ -2269,27 +2421,26 @@
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
ext4_commit_super(sb, es, 1);
- printk(KERN_CRIT
- "EXT4-fs (device %s): mount failed\n",
- sb->s_id);
goto failed_mount4;
}
}
- } else if (journal_inum) {
- if (ext4_create_journal(sb, es, journal_inum))
- goto failed_mount3;
+ } else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
+ EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
+ printk(KERN_ERR "EXT4-fs: required journal recovery "
+ "suppressed and not mounted read-only\n");
+ goto failed_mount4;
} else {
- if (!silent)
- printk(KERN_ERR
- "ext4: No journal on filesystem on %s\n",
- sb->s_id);
- goto failed_mount3;
+ clear_opt(sbi->s_mount_opt, DATA_FLAGS);
+ set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
+ sbi->s_journal = NULL;
+ needs_recovery = 0;
+ goto no_journal;
}
if (ext4_blocks_count(es) > 0xffffffffULL &&
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
- printk(KERN_ERR "ext4: Failed to set 64-bit journal feature\n");
+ printk(KERN_ERR "EXT4-fs: Failed to set 64-bit journal feature\n");
goto failed_mount4;
}
@@ -2334,6 +2485,9 @@
default:
break;
}
+ set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+
+no_journal:
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
@@ -2419,13 +2573,22 @@
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
- if (needs_recovery)
+ if (needs_recovery) {
printk(KERN_INFO "EXT4-fs: recovery complete.\n");
- ext4_mark_recovery_complete(sb, es);
- printk(KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n",
- test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal":
- test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
- "writeback");
+ ext4_mark_recovery_complete(sb, es);
+ }
+ if (EXT4_SB(sb)->s_journal) {
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ descr = " journalled data mode";
+ else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ descr = " ordered data mode";
+ else
+ descr = " writeback data mode";
+ } else
+ descr = "out journal";
+
+ printk(KERN_INFO "EXT4-fs: mounted filesystem %s with%s\n",
+ sb->s_id, descr);
lock_kernel();
return 0;
@@ -2437,8 +2600,11 @@
goto failed_mount;
failed_mount4:
- jbd2_journal_destroy(sbi->s_journal);
- sbi->s_journal = NULL;
+ printk(KERN_ERR "EXT4-fs (device %s): mount failed\n", sb->s_id);
+ if (sbi->s_journal) {
+ jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
+ }
failed_mount3:
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
@@ -2475,11 +2641,9 @@
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (sbi->s_commit_interval)
- journal->j_commit_interval = sbi->s_commit_interval;
- /* We could also set up an ext4-specific default for the commit
- * interval here, but for now we'll just fall back to the jbd
- * default. */
+ journal->j_commit_interval = sbi->s_commit_interval;
+ journal->j_min_batch_time = sbi->s_min_batch_time;
+ journal->j_max_batch_time = sbi->s_max_batch_time;
spin_lock(&journal->j_state_lock);
if (test_opt(sb, BARRIER))
@@ -2499,6 +2663,8 @@
struct inode *journal_inode;
journal_t *journal;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
/* First, test for the existence of a valid inode on disk. Bad
* things happen if we iget() an unused inode, as the subsequent
* iput() will try to delete it. */
@@ -2547,13 +2713,15 @@
struct ext4_super_block *es;
struct block_device *bdev;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
bdev = ext4_blkdev_get(j_dev);
if (bdev == NULL)
return NULL;
if (bd_claim(bdev, sb)) {
printk(KERN_ERR
- "EXT4: failed to claim external journal device.\n");
+ "EXT4-fs: failed to claim external journal device.\n");
blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
return NULL;
}
@@ -2634,6 +2802,8 @@
int err = 0;
int really_read_only;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
if (journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
printk(KERN_INFO "EXT4-fs: external journal device major/minor "
@@ -2718,48 +2888,6 @@
return 0;
}
-static int ext4_create_journal(struct super_block *sb,
- struct ext4_super_block *es,
- unsigned int journal_inum)
-{
- journal_t *journal;
- int err;
-
- if (sb->s_flags & MS_RDONLY) {
- printk(KERN_ERR "EXT4-fs: readonly filesystem when trying to "
- "create journal.\n");
- return -EROFS;
- }
-
- journal = ext4_get_journal(sb, journal_inum);
- if (!journal)
- return -EINVAL;
-
- printk(KERN_INFO "EXT4-fs: creating new journal on inode %u\n",
- journal_inum);
-
- err = jbd2_journal_create(journal);
- if (err) {
- printk(KERN_ERR "EXT4-fs: error creating journal.\n");
- jbd2_journal_destroy(journal);
- return -EIO;
- }
-
- EXT4_SB(sb)->s_journal = journal;
-
- ext4_update_dynamic_rev(sb);
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
- EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL);
-
- es->s_journal_inum = cpu_to_le32(journal_inum);
- sb->s_dirt = 1;
-
- /* Make sure we flush the recovery flag to disk. */
- ext4_commit_super(sb, es, 1);
-
- return 0;
-}
-
static void ext4_commit_super(struct super_block *sb,
struct ext4_super_block *es, int sync)
{
@@ -2776,20 +2904,23 @@
* be remapped. Nothing we can do but to retry the
* write and hope for the best.
*/
- printk(KERN_ERR "ext4: previous I/O error to "
+ printk(KERN_ERR "EXT4-fs: previous I/O error to "
"superblock detected for %s.\n", sb->s_id);
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
es->s_wtime = cpu_to_le32(get_seconds());
- ext4_free_blocks_count_set(es, ext4_count_free_blocks(sb));
- es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb));
+ ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
+ &EXT4_SB(sb)->s_freeblocks_counter));
+ es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive(
+ &EXT4_SB(sb)->s_freeinodes_counter));
+
BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
if (sync) {
sync_dirty_buffer(sbh);
if (buffer_write_io_error(sbh)) {
- printk(KERN_ERR "ext4: I/O error while writing "
+ printk(KERN_ERR "EXT4-fs: I/O error while writing "
"superblock for %s.\n", sb->s_id);
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
@@ -2808,6 +2939,10 @@
{
journal_t *journal = EXT4_SB(sb)->s_journal;
+ if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
+ BUG_ON(journal != NULL);
+ return;
+ }
jbd2_journal_lock_updates(journal);
if (jbd2_journal_flush(journal) < 0)
goto out;
@@ -2837,6 +2972,8 @@
int j_errno;
const char *errstr;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
journal = EXT4_SB(sb)->s_journal;
/*
@@ -2869,14 +3006,17 @@
int ext4_force_commit(struct super_block *sb)
{
journal_t *journal;
- int ret;
+ int ret = 0;
if (sb->s_flags & MS_RDONLY)
return 0;
journal = EXT4_SB(sb)->s_journal;
- sb->s_dirt = 0;
- ret = ext4_journal_force_commit(journal);
+ if (journal) {
+ sb->s_dirt = 0;
+ ret = ext4_journal_force_commit(journal);
+ }
+
return ret;
}
@@ -2888,9 +3028,13 @@
*/
static void ext4_write_super(struct super_block *sb)
{
- if (mutex_trylock(&sb->s_lock) != 0)
- BUG();
- sb->s_dirt = 0;
+ if (EXT4_SB(sb)->s_journal) {
+ if (mutex_trylock(&sb->s_lock) != 0)
+ BUG();
+ sb->s_dirt = 0;
+ } else {
+ ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
+ }
}
static int ext4_sync_fs(struct super_block *sb, int wait)
@@ -2899,10 +3043,14 @@
trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
sb->s_dirt = 0;
- if (wait)
- ret = ext4_force_commit(sb);
- else
- jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+ if (EXT4_SB(sb)->s_journal) {
+ if (wait)
+ ret = ext4_force_commit(sb);
+ else
+ jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+ } else {
+ ext4_commit_super(sb, EXT4_SB(sb)->s_es, wait);
+ }
return ret;
}
@@ -2917,15 +3065,17 @@
if (!(sb->s_flags & MS_RDONLY)) {
journal_t *journal = EXT4_SB(sb)->s_journal;
- /* Now we set up the journal barrier. */
- jbd2_journal_lock_updates(journal);
+ if (journal) {
+ /* Now we set up the journal barrier. */
+ jbd2_journal_lock_updates(journal);
- /*
- * We don't want to clear needs_recovery flag when we failed
- * to flush the journal.
- */
- if (jbd2_journal_flush(journal) < 0)
- return;
+ /*
+ * We don't want to clear needs_recovery flag when we
+ * failed to flush the journal.
+ */
+ if (jbd2_journal_flush(journal) < 0)
+ return;
+ }
/* Journal blocked and flushed, clear needs_recovery flag. */
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
@@ -2939,7 +3089,7 @@
*/
static void ext4_unlockfs(struct super_block *sb)
{
- if (!(sb->s_flags & MS_RDONLY)) {
+ if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) {
lock_super(sb);
/* Reser the needs_recovery flag before the fs is unlocked. */
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
@@ -2957,6 +3107,7 @@
unsigned long old_sb_flags;
struct ext4_mount_options old_opts;
ext4_group_t g;
+ unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
int err;
#ifdef CONFIG_QUOTA
int i;
@@ -2968,16 +3119,21 @@
old_opts.s_resuid = sbi->s_resuid;
old_opts.s_resgid = sbi->s_resgid;
old_opts.s_commit_interval = sbi->s_commit_interval;
+ old_opts.s_min_batch_time = sbi->s_min_batch_time;
+ old_opts.s_max_batch_time = sbi->s_max_batch_time;
#ifdef CONFIG_QUOTA
old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++)
old_opts.s_qf_names[i] = sbi->s_qf_names[i];
#endif
+ if (sbi->s_journal && sbi->s_journal->j_task->io_context)
+ journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
/*
* Allow the "check" option to be passed as a remount option.
*/
- if (!parse_options(data, sb, NULL, NULL, &n_blocks_count, 1)) {
+ if (!parse_options(data, sb, NULL, &journal_ioprio,
+ &n_blocks_count, 1)) {
err = -EINVAL;
goto restore_opts;
}
@@ -2990,7 +3146,10 @@
es = sbi->s_es;
- ext4_init_journal_params(sb, sbi->s_journal);
+ if (sbi->s_journal) {
+ ext4_init_journal_params(sb, sbi->s_journal);
+ set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+ }
if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
n_blocks_count > ext4_blocks_count(es)) {
@@ -3019,17 +3178,20 @@
* We have to unlock super so that we can wait for
* transactions.
*/
- unlock_super(sb);
- ext4_mark_recovery_complete(sb, es);
- lock_super(sb);
+ if (sbi->s_journal) {
+ unlock_super(sb);
+ ext4_mark_recovery_complete(sb, es);
+ lock_super(sb);
+ }
} else {
- __le32 ret;
+ int ret;
if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb,
~EXT4_FEATURE_RO_COMPAT_SUPP))) {
printk(KERN_WARNING "EXT4-fs: %s: couldn't "
"remount RDWR because of unsupported "
- "optional features (%x).\n",
- sb->s_id, le32_to_cpu(ret));
+ "optional features (%x).\n", sb->s_id,
+ (le32_to_cpu(sbi->s_es->s_feature_ro_compat) &
+ ~EXT4_FEATURE_RO_COMPAT_SUPP));
err = -EROFS;
goto restore_opts;
}
@@ -3046,7 +3208,7 @@
if (!ext4_group_desc_csum_verify(sbi, g, gdp)) {
printk(KERN_ERR
"EXT4-fs: ext4_remount: "
- "Checksum for group %lu failed (%u!=%u)\n",
+ "Checksum for group %u failed (%u!=%u)\n",
g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)),
le16_to_cpu(gdp->bg_checksum));
err = -EINVAL;
@@ -3075,7 +3237,8 @@
* been changed by e2fsck since we originally mounted
* the partition.)
*/
- ext4_clear_journal_err(sb, es);
+ if (sbi->s_journal)
+ ext4_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
if ((err = ext4_group_extend(sb, es, n_blocks_count)))
goto restore_opts;
@@ -3083,6 +3246,9 @@
sb->s_flags &= ~MS_RDONLY;
}
}
+ if (sbi->s_journal == NULL)
+ ext4_commit_super(sb, es, 1);
+
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
@@ -3097,6 +3263,8 @@
sbi->s_resuid = old_opts.s_resuid;
sbi->s_resgid = old_opts.s_resgid;
sbi->s_commit_interval = old_opts.s_commit_interval;
+ sbi->s_min_batch_time = old_opts.s_min_batch_time;
+ sbi->s_max_batch_time = old_opts.s_max_batch_time;
#ifdef CONFIG_QUOTA
sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++) {
@@ -3359,7 +3527,8 @@
* When we journal data on quota file, we have to flush journal to see
* all updates to the file when we bypass pagecache...
*/
- if (ext4_should_journal_data(path.dentry->d_inode)) {
+ if (EXT4_SB(sb)->s_journal &&
+ ext4_should_journal_data(path.dentry->d_inode)) {
/*
* We don't need to lock updates but journal_flush() could
* otherwise be livelocked...
@@ -3433,7 +3602,7 @@
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
- if (!handle) {
+ if (EXT4_SB(sb)->s_journal && !handle) {
printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)"
" cancelled because transaction is not started.\n",
(unsigned long long)off, (unsigned long long)len);
@@ -3458,7 +3627,7 @@
flush_dcache_page(bh->b_page);
unlock_buffer(bh);
if (journal_quota)
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
else {
/* Always do at least ordered writes for quotas */
err = ext4_jbd2_file_inode(handle, inode);
@@ -3512,18 +3681,15 @@
static ssize_t ext4_ui_proc_write(struct file *file, const char __user *buf,
size_t cnt, loff_t *ppos)
{
- unsigned int *p = PDE(file->f_path.dentry->d_inode)->data;
+ unsigned long *p = PDE(file->f_path.dentry->d_inode)->data;
char str[32];
- unsigned long value;
if (cnt >= sizeof(str))
return -EINVAL;
if (copy_from_user(str, buf, cnt))
return -EFAULT;
- value = simple_strtol(str, NULL, 0);
- if (value < 0)
- return -ERANGE;
- *p = value;
+
+ *p = simple_strtoul(str, NULL, 0);
return cnt;
}
@@ -3614,7 +3780,7 @@
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
-MODULE_DESCRIPTION("Fourth Extended Filesystem with extents");
+MODULE_DESCRIPTION("Fourth Extended Filesystem");
MODULE_LICENSE("GPL");
module_init(init_ext4_fs)
module_exit(exit_ext4_fs)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 80626d5..157ce65 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -457,7 +457,7 @@
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
sb->s_dirt = 1;
- ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
}
}
@@ -487,9 +487,9 @@
ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
} else {
le32_add_cpu(&BHDR(bh)->h_refcount, -1);
- error = ext4_journal_dirty_metadata(handle, bh);
+ error = ext4_handle_dirty_metadata(handle, inode, bh);
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
DQUOT_FREE_BLOCK(inode, 1);
ea_bdebug(bh, "refcount now=%d; releasing",
le32_to_cpu(BHDR(bh)->h_refcount));
@@ -724,8 +724,9 @@
if (error == -EIO)
goto bad_block;
if (!error)
- error = ext4_journal_dirty_metadata(handle,
- bs->bh);
+ error = ext4_handle_dirty_metadata(handle,
+ inode,
+ bs->bh);
if (error)
goto cleanup;
goto inserted;
@@ -794,8 +795,9 @@
ea_bdebug(new_bh, "reusing; refcount now=%d",
le32_to_cpu(BHDR(new_bh)->h_refcount));
unlock_buffer(new_bh);
- error = ext4_journal_dirty_metadata(handle,
- new_bh);
+ error = ext4_handle_dirty_metadata(handle,
+ inode,
+ new_bh);
if (error)
goto cleanup_dquot;
}
@@ -810,8 +812,8 @@
/* We need to allocate a new block */
ext4_fsblk_t goal = ext4_group_first_block_no(sb,
EXT4_I(inode)->i_block_group);
- ext4_fsblk_t block = ext4_new_meta_block(handle, inode,
- goal, &error);
+ ext4_fsblk_t block = ext4_new_meta_blocks(handle, inode,
+ goal, NULL, &error);
if (error)
goto cleanup;
ea_idebug(inode, "creating block %d", block);
@@ -833,7 +835,8 @@
set_buffer_uptodate(new_bh);
unlock_buffer(new_bh);
ext4_xattr_cache_insert(new_bh);
- error = ext4_journal_dirty_metadata(handle, new_bh);
+ error = ext4_handle_dirty_metadata(handle,
+ inode, new_bh);
if (error)
goto cleanup;
}
@@ -1040,7 +1043,7 @@
*/
is.iloc.bh = NULL;
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
}
cleanup:
diff --git a/fs/ioprio.c b/fs/ioprio.c
index 3569e0a..1a39ac3 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -27,7 +27,7 @@
#include <linux/security.h>
#include <linux/pid_namespace.h>
-static int set_task_ioprio(struct task_struct *task, int ioprio)
+int set_task_ioprio(struct task_struct *task, int ioprio)
{
int err;
struct io_context *ioc;
@@ -70,6 +70,7 @@
task_unlock(task);
return err;
}
+EXPORT_SYMBOL_GPL(set_task_ioprio);
asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
{
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 9497718..17159ca 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -249,16 +249,14 @@
return ret;
}
-#define NR_BATCH 64
-
static void
-__flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
+__flush_batch(journal_t *journal, int *batch_count)
{
int i;
- ll_rw_block(SWRITE, *batch_count, bhs);
+ ll_rw_block(SWRITE, *batch_count, journal->j_chkpt_bhs);
for (i = 0; i < *batch_count; i++) {
- struct buffer_head *bh = bhs[i];
+ struct buffer_head *bh = journal->j_chkpt_bhs[i];
clear_buffer_jwrite(bh);
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
@@ -277,8 +275,7 @@
* Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
*/
static int __process_buffer(journal_t *journal, struct journal_head *jh,
- struct buffer_head **bhs, int *batch_count,
- transaction_t *transaction)
+ int *batch_count, transaction_t *transaction)
{
struct buffer_head *bh = jh2bh(jh);
int ret = 0;
@@ -325,14 +322,14 @@
get_bh(bh);
J_ASSERT_BH(bh, !buffer_jwrite(bh));
set_buffer_jwrite(bh);
- bhs[*batch_count] = bh;
+ journal->j_chkpt_bhs[*batch_count] = bh;
__buffer_relink_io(jh);
jbd_unlock_bh_state(bh);
transaction->t_chp_stats.cs_written++;
(*batch_count)++;
- if (*batch_count == NR_BATCH) {
+ if (*batch_count == JBD2_NR_BATCH) {
spin_unlock(&journal->j_list_lock);
- __flush_batch(journal, bhs, batch_count);
+ __flush_batch(journal, batch_count);
ret = 1;
}
}
@@ -388,7 +385,6 @@
if (journal->j_checkpoint_transactions == transaction &&
transaction->t_tid == this_tid) {
int batch_count = 0;
- struct buffer_head *bhs[NR_BATCH];
struct journal_head *jh;
int retry = 0, err;
@@ -402,7 +398,7 @@
retry = 1;
break;
}
- retry = __process_buffer(journal, jh, bhs, &batch_count,
+ retry = __process_buffer(journal, jh, &batch_count,
transaction);
if (retry < 0 && !result)
result = retry;
@@ -419,7 +415,7 @@
spin_unlock(&journal->j_list_lock);
retry = 1;
}
- __flush_batch(journal, bhs, &batch_count);
+ __flush_batch(journal, &batch_count);
}
if (retry) {
@@ -686,6 +682,7 @@
safely remove this transaction from the log */
__jbd2_journal_drop_transaction(journal, transaction);
+ kfree(transaction);
/* Just in case anybody was waiting for more transactions to be
checkpointed... */
@@ -760,5 +757,4 @@
J_ASSERT(journal->j_running_transaction != transaction);
jbd_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid);
- kfree(transaction);
}
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index c8a1bac..62804e5 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -25,6 +25,7 @@
#include <linux/crc32.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
+#include <linux/bio.h>
/*
* Default IO end handler for temporary BJ_IO buffer_heads.
@@ -137,7 +138,7 @@
set_buffer_ordered(bh);
barrier_done = 1;
}
- ret = submit_bh(WRITE, bh);
+ ret = submit_bh(WRITE_SYNC, bh);
if (barrier_done)
clear_buffer_ordered(bh);
@@ -158,7 +159,7 @@
lock_buffer(bh);
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
- ret = submit_bh(WRITE, bh);
+ ret = submit_bh(WRITE_SYNC, bh);
}
*cbh = bh;
return ret;
@@ -168,12 +169,34 @@
* This function along with journal_submit_commit_record
* allows to write the commit record asynchronously.
*/
-static int journal_wait_on_commit_record(struct buffer_head *bh)
+static int journal_wait_on_commit_record(journal_t *journal,
+ struct buffer_head *bh)
{
int ret = 0;
+retry:
clear_buffer_dirty(bh);
wait_on_buffer(bh);
+ if (buffer_eopnotsupp(bh) && (journal->j_flags & JBD2_BARRIER)) {
+ printk(KERN_WARNING
+ "JBD2: wait_on_commit_record: sync failed on %s - "
+ "disabling barriers\n", journal->j_devname);
+ spin_lock(&journal->j_state_lock);
+ journal->j_flags &= ~JBD2_BARRIER;
+ spin_unlock(&journal->j_state_lock);
+
+ lock_buffer(bh);
+ clear_buffer_dirty(bh);
+ set_buffer_uptodate(bh);
+ bh->b_end_io = journal_end_buffer_io_sync;
+
+ ret = submit_bh(WRITE_SYNC, bh);
+ if (ret) {
+ unlock_buffer(bh);
+ return ret;
+ }
+ goto retry;
+ }
if (unlikely(!buffer_uptodate(bh)))
ret = -EIO;
@@ -332,13 +355,15 @@
int flags;
int err;
unsigned long long blocknr;
+ ktime_t start_time;
+ u64 commit_time;
char *tagp = NULL;
journal_header_t *header;
journal_block_tag_t *tag = NULL;
int space_left = 0;
int first_tag = 0;
int tag_flag;
- int i;
+ int i, to_free = 0;
int tag_bytes = journal_tag_bytes(journal);
struct buffer_head *cbh = NULL; /* For transactional checksums */
__u32 crc32_sum = ~0;
@@ -458,6 +483,7 @@
commit_transaction->t_state = T_FLUSH;
journal->j_committing_transaction = commit_transaction;
journal->j_running_transaction = NULL;
+ start_time = ktime_get();
commit_transaction->t_log_start = journal->j_head;
wake_up(&journal->j_wait_transaction_locked);
spin_unlock(&journal->j_state_lock);
@@ -803,7 +829,7 @@
__jbd2_journal_abort_hard(journal);
}
if (!err && !is_journal_aborted(journal))
- err = journal_wait_on_commit_record(cbh);
+ err = journal_wait_on_commit_record(journal, cbh);
if (err)
jbd2_journal_abort(journal, err);
@@ -981,14 +1007,23 @@
J_ASSERT(commit_transaction == journal->j_committing_transaction);
journal->j_commit_sequence = commit_transaction->t_tid;
journal->j_committing_transaction = NULL;
- spin_unlock(&journal->j_state_lock);
+ commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
- if (journal->j_commit_callback)
- journal->j_commit_callback(journal, commit_transaction);
+ /*
+ * weight the commit time higher than the average time so we don't
+ * react too strongly to vast changes in the commit time
+ */
+ if (likely(journal->j_average_commit_time))
+ journal->j_average_commit_time = (commit_time +
+ journal->j_average_commit_time*3) / 4;
+ else
+ journal->j_average_commit_time = commit_time;
+ spin_unlock(&journal->j_state_lock);
if (commit_transaction->t_checkpoint_list == NULL &&
commit_transaction->t_checkpoint_io_list == NULL) {
__jbd2_journal_drop_transaction(journal, commit_transaction);
+ to_free = 1;
} else {
if (journal->j_checkpoint_transactions == NULL) {
journal->j_checkpoint_transactions = commit_transaction;
@@ -1007,11 +1042,16 @@
}
spin_unlock(&journal->j_list_lock);
+ if (journal->j_commit_callback)
+ journal->j_commit_callback(journal, commit_transaction);
+
trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
- journal->j_devname, journal->j_commit_sequence,
+ journal->j_devname, commit_transaction->t_tid,
journal->j_tail_sequence);
jbd_debug(1, "JBD: commit %d complete, head %d\n",
journal->j_commit_sequence, journal->j_tail_sequence);
+ if (to_free)
+ kfree(commit_transaction);
wake_up(&journal->j_wait_done_commit);
}
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index f6bff9d..5667530 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -40,6 +40,7 @@
#include <asm/uaccess.h>
#include <asm/page.h>
+#include <asm/div64.h>
EXPORT_SYMBOL(jbd2_journal_start);
EXPORT_SYMBOL(jbd2_journal_restart);
@@ -66,7 +67,6 @@
EXPORT_SYMBOL(jbd2_journal_check_used_features);
EXPORT_SYMBOL(jbd2_journal_check_available_features);
EXPORT_SYMBOL(jbd2_journal_set_features);
-EXPORT_SYMBOL(jbd2_journal_create);
EXPORT_SYMBOL(jbd2_journal_load);
EXPORT_SYMBOL(jbd2_journal_destroy);
EXPORT_SYMBOL(jbd2_journal_abort);
@@ -132,8 +132,9 @@
journal->j_task = current;
wake_up(&journal->j_wait_done_commit);
- printk(KERN_INFO "kjournald2 starting. Commit interval %ld seconds\n",
- journal->j_commit_interval / HZ);
+ printk(KERN_INFO "kjournald2 starting: pid %d, dev %s, "
+ "commit interval %ld seconds\n", current->pid,
+ journal->j_devname, journal->j_commit_interval / HZ);
/*
* And now, wait forever for commit wakeup events.
@@ -650,6 +651,8 @@
return NULL;
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ if (!bh)
+ return NULL;
lock_buffer(bh);
memset(bh->b_data, 0, journal->j_blocksize);
set_buffer_uptodate(bh);
@@ -843,6 +846,8 @@
jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid));
seq_printf(seq, " %ums logging transaction\n",
jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid));
+ seq_printf(seq, " %luus average transaction commit time\n",
+ do_div(s->journal->j_average_commit_time, 1000));
seq_printf(seq, " %lu handles per transaction\n",
s->stats->u.run.rs_handle_count / s->stats->ts_tid);
seq_printf(seq, " %lu blocks per transaction\n",
@@ -980,6 +985,8 @@
spin_lock_init(&journal->j_state_lock);
journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
+ journal->j_min_batch_time = 0;
+ journal->j_max_batch_time = 15000; /* 15ms */
/* The journal is marked for error until we succeed with recovery! */
journal->j_flags = JBD2_ABORT;
@@ -1035,15 +1042,14 @@
/* journal descriptor can store up to n blocks -bzzz */
journal->j_blocksize = blocksize;
+ jbd2_stats_proc_init(journal);
n = journal->j_blocksize / sizeof(journal_block_tag_t);
journal->j_wbufsize = n;
journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
if (!journal->j_wbuf) {
printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
__func__);
- kfree(journal);
- journal = NULL;
- goto out;
+ goto out_err;
}
journal->j_dev = bdev;
journal->j_fs_dev = fs_dev;
@@ -1053,14 +1059,22 @@
p = journal->j_devname;
while ((p = strchr(p, '/')))
*p = '!';
- jbd2_stats_proc_init(journal);
bh = __getblk(journal->j_dev, start, journal->j_blocksize);
- J_ASSERT(bh != NULL);
+ if (!bh) {
+ printk(KERN_ERR
+ "%s: Cannot get buffer for journal superblock\n",
+ __func__);
+ goto out_err;
+ }
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
-out:
+
return journal;
+out_err:
+ jbd2_stats_proc_exit(journal);
+ kfree(journal);
+ return NULL;
}
/**
@@ -1108,9 +1122,7 @@
if (!journal->j_wbuf) {
printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
__func__);
- jbd2_stats_proc_exit(journal);
- kfree(journal);
- return NULL;
+ goto out_err;
}
err = jbd2_journal_bmap(journal, 0, &blocknr);
@@ -1118,17 +1130,24 @@
if (err) {
printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
__func__);
- jbd2_stats_proc_exit(journal);
- kfree(journal);
- return NULL;
+ goto out_err;
}
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
- J_ASSERT(bh != NULL);
+ if (!bh) {
+ printk(KERN_ERR
+ "%s: Cannot get buffer for journal superblock\n",
+ __func__);
+ goto out_err;
+ }
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
return journal;
+out_err:
+ jbd2_stats_proc_exit(journal);
+ kfree(journal);
+ return NULL;
}
/*
@@ -1177,77 +1196,6 @@
}
/**
- * int jbd2_journal_create() - Initialise the new journal file
- * @journal: Journal to create. This structure must have been initialised
- *
- * Given a journal_t structure which tells us which disk blocks we can
- * use, create a new journal superblock and initialise all of the
- * journal fields from scratch.
- **/
-int jbd2_journal_create(journal_t *journal)
-{
- unsigned long long blocknr;
- struct buffer_head *bh;
- journal_superblock_t *sb;
- int i, err;
-
- if (journal->j_maxlen < JBD2_MIN_JOURNAL_BLOCKS) {
- printk (KERN_ERR "Journal length (%d blocks) too short.\n",
- journal->j_maxlen);
- journal_fail_superblock(journal);
- return -EINVAL;
- }
-
- if (journal->j_inode == NULL) {
- /*
- * We don't know what block to start at!
- */
- printk(KERN_EMERG
- "%s: creation of journal on external device!\n",
- __func__);
- BUG();
- }
-
- /* Zero out the entire journal on disk. We cannot afford to
- have any blocks on disk beginning with JBD2_MAGIC_NUMBER. */
- jbd_debug(1, "JBD: Zeroing out journal blocks...\n");
- for (i = 0; i < journal->j_maxlen; i++) {
- err = jbd2_journal_bmap(journal, i, &blocknr);
- if (err)
- return err;
- bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
- lock_buffer(bh);
- memset (bh->b_data, 0, journal->j_blocksize);
- BUFFER_TRACE(bh, "marking dirty");
- mark_buffer_dirty(bh);
- BUFFER_TRACE(bh, "marking uptodate");
- set_buffer_uptodate(bh);
- unlock_buffer(bh);
- __brelse(bh);
- }
-
- sync_blockdev(journal->j_dev);
- jbd_debug(1, "JBD: journal cleared.\n");
-
- /* OK, fill in the initial static fields in the new superblock */
- sb = journal->j_superblock;
-
- sb->s_header.h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
- sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
-
- sb->s_blocksize = cpu_to_be32(journal->j_blocksize);
- sb->s_maxlen = cpu_to_be32(journal->j_maxlen);
- sb->s_first = cpu_to_be32(1);
-
- journal->j_transaction_sequence = 1;
-
- journal->j_flags &= ~JBD2_ABORT;
- journal->j_format_version = 2;
-
- return journal_reset(journal);
-}
-
-/**
* void jbd2_journal_update_superblock() - Update journal sb on disk.
* @journal: The journal to update.
* @wait: Set to '0' if you don't want to wait for IO completion.
@@ -1491,7 +1439,9 @@
spin_lock(&journal->j_list_lock);
while (journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
+ mutex_lock(&journal->j_checkpoint_mutex);
jbd2_log_do_checkpoint(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_list_lock);
}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 4f925a4..46b4e34 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -25,6 +25,7 @@
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/highmem.h>
+#include <linux/hrtimer.h>
static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
@@ -48,6 +49,7 @@
{
transaction->t_journal = journal;
transaction->t_state = T_RUNNING;
+ transaction->t_start_time = ktime_get();
transaction->t_tid = journal->j_transaction_sequence++;
transaction->t_expires = jiffies + journal->j_commit_interval;
spin_lock_init(&transaction->t_handle_lock);
@@ -1240,7 +1242,7 @@
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
- int old_handle_count, err;
+ int err;
pid_t pid;
J_ASSERT(journal_current_handle() == handle);
@@ -1263,24 +1265,54 @@
/*
* Implement synchronous transaction batching. If the handle
* was synchronous, don't force a commit immediately. Let's
- * yield and let another thread piggyback onto this transaction.
- * Keep doing that while new threads continue to arrive.
- * It doesn't cost much - we're about to run a commit and sleep
- * on IO anyway. Speeds up many-threaded, many-dir operations
- * by 30x or more...
+ * yield and let another thread piggyback onto this
+ * transaction. Keep doing that while new threads continue to
+ * arrive. It doesn't cost much - we're about to run a commit
+ * and sleep on IO anyway. Speeds up many-threaded, many-dir
+ * operations by 30x or more...
*
- * But don't do this if this process was the most recent one to
- * perform a synchronous write. We do this to detect the case where a
- * single process is doing a stream of sync writes. No point in waiting
- * for joiners in that case.
+ * We try and optimize the sleep time against what the
+ * underlying disk can do, instead of having a static sleep
+ * time. This is useful for the case where our storage is so
+ * fast that it is more optimal to go ahead and force a flush
+ * and wait for the transaction to be committed than it is to
+ * wait for an arbitrary amount of time for new writers to
+ * join the transaction. We achieve this by measuring how
+ * long it takes to commit a transaction, and compare it with
+ * how long this transaction has been running, and if run time
+ * < commit time then we sleep for the delta and commit. This
+ * greatly helps super fast disks that would see slowdowns as
+ * more threads started doing fsyncs.
+ *
+ * But don't do this if this process was the most recent one
+ * to perform a synchronous write. We do this to detect the
+ * case where a single process is doing a stream of sync
+ * writes. No point in waiting for joiners in that case.
*/
pid = current->pid;
if (handle->h_sync && journal->j_last_sync_writer != pid) {
+ u64 commit_time, trans_time;
+
journal->j_last_sync_writer = pid;
- do {
- old_handle_count = transaction->t_handle_count;
- schedule_timeout_uninterruptible(1);
- } while (old_handle_count != transaction->t_handle_count);
+
+ spin_lock(&journal->j_state_lock);
+ commit_time = journal->j_average_commit_time;
+ spin_unlock(&journal->j_state_lock);
+
+ trans_time = ktime_to_ns(ktime_sub(ktime_get(),
+ transaction->t_start_time));
+
+ commit_time = max_t(u64, commit_time,
+ 1000*journal->j_min_batch_time);
+ commit_time = min_t(u64, commit_time,
+ 1000*journal->j_max_batch_time);
+
+ if (trans_time < commit_time) {
+ ktime_t expires = ktime_add_ns(ktime_get(),
+ commit_time);
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_hrtimeout(&expires, HRTIMER_MODE_ABS);
+ }
}
current->journal_info = NULL;
diff --git a/fs/super.c b/fs/super.c
index 7d67387..ed080c4 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -810,6 +810,7 @@
}
s->s_flags |= MS_ACTIVE;
+ bdev->bd_super = s;
}
return simple_set_mnt(mnt, s);
@@ -829,6 +830,7 @@
struct block_device *bdev = sb->s_bdev;
fmode_t mode = sb->s_mode;
+ bdev->bd_super = 0;
generic_shutdown_super(sb);
sync_blockdev(bdev);
close_bdev_exclusive(bdev, mode);
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index d76800f..dd495b8 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -378,6 +378,13 @@
#define EXT3_ORPHAN_FS 0x0004 /* Orphans being recovered */
/*
+ * Misc. filesystem flags
+ */
+#define EXT2_FLAGS_SIGNED_HASH 0x0001 /* Signed dirhash in use */
+#define EXT2_FLAGS_UNSIGNED_HASH 0x0002 /* Unsigned dirhash in use */
+#define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */
+
+/*
* Mount flags
*/
#define EXT3_MOUNT_CHECK 0x00001 /* Do mount-time checks */
@@ -513,7 +520,23 @@
__u16 s_reserved_word_pad;
__le32 s_default_mount_opts;
__le32 s_first_meta_bg; /* First metablock block group */
- __u32 s_reserved[190]; /* Padding to the end of the block */
+ __le32 s_mkfs_time; /* When the filesystem was created */
+ __le32 s_jnl_blocks[17]; /* Backup of the journal inode */
+ /* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
+/*150*/ __le32 s_blocks_count_hi; /* Blocks count */
+ __le32 s_r_blocks_count_hi; /* Reserved blocks count */
+ __le32 s_free_blocks_count_hi; /* Free blocks count */
+ __le16 s_min_extra_isize; /* All inodes have at least # bytes */
+ __le16 s_want_extra_isize; /* New inodes should reserve # bytes */
+ __le32 s_flags; /* Miscellaneous flags */
+ __le16 s_raid_stride; /* RAID stride */
+ __le16 s_mmp_interval; /* # seconds to wait in MMP checking */
+ __le64 s_mmp_block; /* Block for multi-mount protection */
+ __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/
+ __u8 s_log_groups_per_flex; /* FLEX_BG group size */
+ __u8 s_reserved_char_pad2;
+ __le16 s_reserved_pad;
+ __u32 s_reserved[162]; /* Padding to the end of the block */
};
#ifdef __KERNEL__
@@ -718,6 +741,9 @@
#define DX_HASH_LEGACY 0
#define DX_HASH_HALF_MD4 1
#define DX_HASH_TEA 2
+#define DX_HASH_LEGACY_UNSIGNED 3
+#define DX_HASH_HALF_MD4_UNSIGNED 4
+#define DX_HASH_TEA_UNSIGNED 5
#ifdef __KERNEL__
diff --git a/include/linux/ext3_fs_sb.h b/include/linux/ext3_fs_sb.h
index 76fdc0f..f07f34d 100644
--- a/include/linux/ext3_fs_sb.h
+++ b/include/linux/ext3_fs_sb.h
@@ -57,6 +57,7 @@
u32 s_next_generation;
u32 s_hash_seed[4];
int s_def_hash_version;
+ int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
struct percpu_counter s_freeblocks_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e38a64d..0b87b29 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -565,6 +565,7 @@
struct block_device {
dev_t bd_dev; /* not a kdev_t - it's a search key */
struct inode * bd_inode; /* will die */
+ struct super_block * bd_super;
int bd_openers;
struct mutex bd_mutex; /* open/close mutex */
struct semaphore bd_mount_sem;
@@ -1389,6 +1390,7 @@
ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
#endif
+ int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
};
/*
diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index f98a656..76dad48 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -86,4 +86,6 @@
*/
extern int ioprio_best(unsigned short aprio, unsigned short bprio);
+extern int set_task_ioprio(struct task_struct *task, int ioprio);
+
#endif
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 3445647..b45109c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -638,6 +638,11 @@
unsigned long t_expires;
/*
+ * When this transaction started, in nanoseconds [no locking]
+ */
+ ktime_t t_start_time;
+
+ /*
* How many handles used this transaction? [t_handle_lock]
*/
int t_handle_count;
@@ -682,6 +687,8 @@
return end + (MAX_JIFFY_OFFSET - start);
}
+#define JBD2_NR_BATCH 64
+
/**
* struct journal_s - The journal_s type is the concrete type associated with
* journal_t.
@@ -826,6 +833,14 @@
struct mutex j_checkpoint_mutex;
/*
+ * List of buffer heads used by the checkpoint routine. This
+ * was moved from jbd2_log_do_checkpoint() to reduce stack
+ * usage. Access to this array is controlled by the
+ * j_checkpoint_mutex. [j_checkpoint_mutex]
+ */
+ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH];
+
+ /*
* Journal head: identifies the first unused block in the journal.
* [j_state_lock]
*/
@@ -939,8 +954,26 @@
struct buffer_head **j_wbuf;
int j_wbufsize;
+ /*
+ * this is the pid of hte last person to run a synchronous operation
+ * through the journal
+ */
pid_t j_last_sync_writer;
+ /*
+ * the average amount of time in nanoseconds it takes to commit a
+ * transaction to disk. [j_state_lock]
+ */
+ u64 j_average_commit_time;
+
+ /*
+ * minimum and maximum times that we should wait for
+ * additional filesystem operations to get batched into a
+ * synchronous handle in microseconds
+ */
+ u32 j_min_batch_time;
+ u32 j_max_batch_time;
+
/* This function is called when a transaction is closed */
void (*j_commit_callback)(journal_t *,
transaction_t *);
@@ -1102,7 +1135,6 @@
(journal_t *, unsigned long, unsigned long, unsigned long);
extern void jbd2_journal_clear_features
(journal_t *, unsigned long, unsigned long, unsigned long);
-extern int jbd2_journal_create (journal_t *);
extern int jbd2_journal_load (journal_t *journal);
extern int jbd2_journal_destroy (journal_t *);
extern int jbd2_journal_recover (journal_t *journal);
@@ -1177,8 +1209,8 @@
int jbd2_log_do_checkpoint(journal_t *journal);
void __jbd2_log_wait_for_space(journal_t *journal);
-extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
-extern int jbd2_cleanup_journal_tail(journal_t *);
+extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
+extern int jbd2_cleanup_journal_tail(journal_t *);
/* Debugging code only: */