summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/Kconfig1
-rw-r--r--fs/ext4/acl.c74
-rw-r--r--fs/ext4/block_validity.c1
-rw-r--r--fs/ext4/ext4.h8
-rw-r--r--fs/ext4/ext4_extents.h3
-rw-r--r--fs/ext4/extents.c77
-rw-r--r--fs/ext4/fsync.c16
-rw-r--r--fs/ext4/inode.c235
-rw-r--r--fs/ext4/mballoc.c8
-rw-r--r--fs/ext4/mballoc.h1
-rw-r--r--fs/ext4/super.c19
-rw-r--r--fs/ext4/xattr.c33
-rw-r--r--fs/ext4/xattr_security.c20
-rw-r--r--fs/ext4/xattr_trusted.c20
-rw-r--r--fs/ext4/xattr_user.c25
15 files changed, 303 insertions, 238 deletions
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 9acf7e80813..9ed1bb1f319 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -28,6 +28,7 @@ config EXT4_FS
config EXT4_USE_FOR_EXT23
bool "Use ext4 for ext2/ext3 file systems"
+ depends on EXT4_FS
depends on EXT3_FS=n || EXT2_FS=n
default y
help
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 0df88b2a69b..8a2a29d35a6 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -364,12 +364,12 @@ out:
* Extended attribute handlers
*/
static size_t
-ext4_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
- const char *name, size_t name_len)
+ext4_xattr_list_acl_access(struct dentry *dentry, char *list, size_t list_len,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_len)
memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
@@ -377,12 +377,12 @@ ext4_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
}
static size_t
-ext4_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
- const char *name, size_t name_len)
+ext4_xattr_list_acl_default(struct dentry *dentry, char *list, size_t list_len,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_len)
memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
@@ -390,15 +390,18 @@ ext4_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
}
static int
-ext4_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
+ext4_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
struct posix_acl *acl;
int error;
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return -EOPNOTSUPP;
- acl = ext4_get_acl(inode, type);
+ acl = ext4_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
@@ -410,31 +413,16 @@ ext4_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
}
static int
-ext4_xattr_get_acl_access(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int
-ext4_xattr_get_acl_default(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
-static int
-ext4_xattr_set_acl(struct inode *inode, int type, const void *value,
- size_t size)
+ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags, int type)
{
+ struct inode *inode = dentry->d_inode;
handle_t *handle;
struct posix_acl *acl;
int error, retries = 0;
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
if (!test_opt(inode->i_sb, POSIX_ACL))
return -EOPNOTSUPP;
if (!is_owner_or_cap(inode))
@@ -466,34 +454,18 @@ release_and_out:
return error;
}
-static int
-ext4_xattr_set_acl_access(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static int
-ext4_xattr_set_acl_default(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
struct xattr_handler ext4_xattr_acl_access_handler = {
.prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
.list = ext4_xattr_list_acl_access,
- .get = ext4_xattr_get_acl_access,
- .set = ext4_xattr_set_acl_access,
+ .get = ext4_xattr_get_acl,
+ .set = ext4_xattr_set_acl,
};
struct xattr_handler ext4_xattr_acl_default_handler = {
.prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
.list = ext4_xattr_list_acl_default,
- .get = ext4_xattr_get_acl_default,
- .set = ext4_xattr_set_acl_default,
+ .get = ext4_xattr_get_acl,
+ .set = ext4_xattr_set_acl,
};
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 4df8621ec31..a60ab9aad57 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -16,7 +16,6 @@
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
-#include <linux/version.h>
#include <linux/blkdev.h>
#include <linux/mutex.h>
#include "ext4.h"
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ab31e65d46d..af7b62699ea 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -699,11 +699,17 @@ struct ext4_inode_info {
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
unsigned short i_delalloc_reserved_flag;
+ sector_t i_da_metadata_calc_last_lblock;
+ int i_da_metadata_calc_len;
/* on-disk additional length */
__u16 i_extra_isize;
spinlock_t i_block_reservation_lock;
+#ifdef CONFIG_QUOTA
+ /* quota space reservation, managed internally by quota code */
+ qsize_t i_reserved_quota;
+#endif
/* completed async DIOs that might need unwritten extents handling */
struct list_head i_aio_dio_complete_list;
@@ -1435,7 +1441,7 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
extern int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
-extern qsize_t ext4_get_reserved_space(struct inode *inode);
+extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern int flush_aio_dio_completed_IO(struct inode *inode);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 2ca686454e8..bdb6ce7e2eb 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -225,7 +225,8 @@ static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
}
-extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
+extern int ext4_ext_calc_metadata_amount(struct inode *inode,
+ sector_t lblocks);
extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex);
extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3a7928f825e..7d7b74e9468 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -296,29 +296,44 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
* to allocate @blocks
* Worse case is one block per extent
*/
-int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks)
+int ext4_ext_calc_metadata_amount(struct inode *inode, sector_t lblock)
{
- int lcap, icap, rcap, leafs, idxs, num;
- int newextents = blocks;
-
- rcap = ext4_ext_space_root_idx(inode, 0);
- lcap = ext4_ext_space_block(inode, 0);
- icap = ext4_ext_space_block_idx(inode, 0);
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int idxs, num = 0;
- /* number of new leaf blocks needed */
- num = leafs = (newextents + lcap - 1) / lcap;
+ idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
+ / sizeof(struct ext4_extent_idx));
/*
- * Worse case, we need separate index block(s)
- * to link all new leaf blocks
+ * If the new delayed allocation block is contiguous with the
+ * previous da block, it can share index blocks with the
+ * previous block, so we only need to allocate a new index
+ * block every idxs leaf blocks. At ldxs**2 blocks, we need
+ * an additional index block, and at ldxs**3 blocks, yet
+ * another index blocks.
*/
- idxs = (leafs + icap - 1) / icap;
- do {
- num += idxs;
- idxs = (idxs + icap - 1) / icap;
- } while (idxs > rcap);
+ if (ei->i_da_metadata_calc_len &&
+ ei->i_da_metadata_calc_last_lblock+1 == lblock) {
+ if ((ei->i_da_metadata_calc_len % idxs) == 0)
+ num++;
+ if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
+ num++;
+ if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) {
+ num++;
+ ei->i_da_metadata_calc_len = 0;
+ } else
+ ei->i_da_metadata_calc_len++;
+ ei->i_da_metadata_calc_last_lblock++;
+ return num;
+ }
- return num;
+ /*
+ * In the worst case we need a new set of index blocks at
+ * every level of the inode's extent tree.
+ */
+ ei->i_da_metadata_calc_len = 1;
+ ei->i_da_metadata_calc_last_lblock = lblock;
+ return ext_depth(inode) + 1;
}
static int
@@ -3023,6 +3038,14 @@ out:
return err;
}
+static void unmap_underlying_metadata_blocks(struct block_device *bdev,
+ sector_t block, int count)
+{
+ int i;
+ for (i = 0; i < count; i++)
+ unmap_underlying_metadata(bdev, block + i);
+}
+
static int
ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, unsigned int max_blocks,
@@ -3098,6 +3121,18 @@ out:
} else
allocated = ret;
set_buffer_new(bh_result);
+ /*
+ * if we allocated more blocks than requested
+ * we need to make sure we unmap the extra block
+ * allocated. The actual needed block will get
+ * unmapped later when we find the buffer_head marked
+ * new.
+ */
+ if (allocated > max_blocks) {
+ unmap_underlying_metadata_blocks(inode->i_sb->s_bdev,
+ newblock + max_blocks,
+ allocated - max_blocks);
+ }
map_out:
set_buffer_mapped(bh_result);
out1:
@@ -3190,7 +3225,13 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
* this situation is possible, though, _during_ tree modification;
* this is why assert can't be put in ext4_ext_find_extent()
*/
- BUG_ON(path[depth].p_ext == NULL && depth != 0);
+ if (path[depth].p_ext == NULL && depth != 0) {
+ ext4_error(inode->i_sb, __func__, "bad extent address "
+ "inode: %lu, iblock: %d, depth: %d",
+ inode->i_ino, iblock, depth);
+ err = -EIO;
+ goto out2;
+ }
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 0b22497d92e..98bd140aad0 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -88,9 +88,21 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
return ext4_force_commit(inode->i_sb);
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
- if (jbd2_log_start_commit(journal, commit_tid))
+ if (jbd2_log_start_commit(journal, commit_tid)) {
+ /*
+ * When the journal is on a different device than the
+ * fs data disk, we need to issue the barrier in
+ * writeback mode. (In ordered mode, the jbd2 layer
+ * will take care of issuing the barrier. In
+ * data=journal, all of the data blocks are written to
+ * the journal device.)
+ */
+ if (ext4_should_writeback_data(inode) &&
+ (journal->j_fs_dev != journal->j_dev) &&
+ (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
jbd2_log_wait_commit(journal, commit_tid);
- else if (journal->j_flags & JBD2_BARRIER)
+ } else if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5352db1a308..c818972c830 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1003,83 +1003,94 @@ out:
return err;
}
-qsize_t ext4_get_reserved_space(struct inode *inode)
+#ifdef CONFIG_QUOTA
+qsize_t *ext4_get_reserved_space(struct inode *inode)
{
- unsigned long long total;
-
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- total = EXT4_I(inode)->i_reserved_data_blocks +
- EXT4_I(inode)->i_reserved_meta_blocks;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-
- return (total << inode->i_blkbits);
+ return &EXT4_I(inode)->i_reserved_quota;
}
+#endif
+
/*
* Calculate the number of metadata blocks need to reserve
- * to allocate @blocks for non extent file based file
+ * to allocate a new block at @lblocks for non extent file based file
*/
-static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
+static int ext4_indirect_calc_metadata_amount(struct inode *inode,
+ sector_t lblock)
{
- int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- int ind_blks, dind_blks, tind_blks;
-
- /* number of new indirect blocks needed */
- ind_blks = (blocks + icap - 1) / icap;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int dind_mask = EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1;
+ int blk_bits;
- dind_blks = (ind_blks + icap - 1) / icap;
+ if (lblock < EXT4_NDIR_BLOCKS)
+ return 0;
- tind_blks = 1;
+ lblock -= EXT4_NDIR_BLOCKS;
- return ind_blks + dind_blks + tind_blks;
+ if (ei->i_da_metadata_calc_len &&
+ (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
+ ei->i_da_metadata_calc_len++;
+ return 0;
+ }
+ ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
+ ei->i_da_metadata_calc_len = 1;
+ blk_bits = roundup_pow_of_two(lblock + 1);
+ return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
}
/*
* Calculate the number of metadata blocks need to reserve
- * to allocate given number of blocks
+ * to allocate a block located at @lblock
*/
-static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
+static int ext4_calc_metadata_amount(struct inode *inode, sector_t lblock)
{
- if (!blocks)
- return 0;
-
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
- return ext4_ext_calc_metadata_amount(inode, blocks);
+ return ext4_ext_calc_metadata_amount(inode, lblock);
- return ext4_indirect_calc_metadata_amount(inode, blocks);
+ return ext4_indirect_calc_metadata_amount(inode, lblock);
}
+/*
+ * Called with i_data_sem down, which is important since we can call
+ * ext4_discard_preallocations() from here.
+ */
static void ext4_da_update_reserve_space(struct inode *inode, int used)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- int total, mdb, mdb_free;
-
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- /* recalculate the number of metablocks still need to be reserved */
- total = EXT4_I(inode)->i_reserved_data_blocks - used;
- mdb = ext4_calc_metadata_amount(inode, total);
-
- /* figure out how many metablocks to release */
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
-
- if (mdb_free) {
- /* Account for allocated meta_blocks */
- mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
-
- /* update fs dirty blocks counter */
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int mdb_free = 0;
+
+ spin_lock(&ei->i_block_reservation_lock);
+ if (unlikely(used > ei->i_reserved_data_blocks)) {
+ ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
+ "with only %d reserved data blocks\n",
+ __func__, inode->i_ino, used,
+ ei->i_reserved_data_blocks);
+ WARN_ON(1);
+ used = ei->i_reserved_data_blocks;
+ }
+
+ /* Update per-inode reservations */
+ ei->i_reserved_data_blocks -= used;
+ used += ei->i_allocated_meta_blocks;
+ ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
+ ei->i_allocated_meta_blocks = 0;
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, used);
+
+ if (ei->i_reserved_data_blocks == 0) {
+ /*
+ * We can release all of the reserved metadata blocks
+ * only when we have written all of the delayed
+ * allocation blocks.
+ */
+ mdb_free = ei->i_reserved_meta_blocks;
+ ei->i_reserved_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
- EXT4_I(inode)->i_allocated_meta_blocks = 0;
- EXT4_I(inode)->i_reserved_meta_blocks = mdb;
}
-
- /* update per-inode reservations */
- BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks);
- EXT4_I(inode)->i_reserved_data_blocks -= used;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- /*
- * free those over-booking quota for metadata blocks
- */
+ /* Update quota subsystem */
+ vfs_dq_claim_block(inode, used);
if (mdb_free)
vfs_dq_release_reservation_block(inode, mdb_free);
@@ -1088,7 +1099,8 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
* there aren't any writers on the inode, we can discard the
* inode's preallocations.
*/
- if (!total && (atomic_read(&inode->i_writecount) == 0))
+ if ((ei->i_reserved_data_blocks == 0) &&
+ (atomic_read(&inode->i_writecount) == 0))
ext4_discard_preallocations(inode);
}
@@ -1797,11 +1809,15 @@ static int ext4_journalled_write_end(struct file *file,
return ret ? ret : copied;
}
-static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
+/*
+ * Reserve a single block located at lblock
+ */
+static int ext4_da_reserve_space(struct inode *inode, sector_t lblock)
{
int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned long md_needed, mdblocks, total = 0;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned long md_needed, md_reserved;
/*
* recalculate the amount of metadata blocks to reserve
@@ -1809,86 +1825,90 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
* worse case is one extent per block
*/
repeat:
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
- mdblocks = ext4_calc_metadata_amount(inode, total);
- BUG_ON(mdblocks < EXT4_I(inode)->i_reserved_meta_blocks);
-
- md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
- total = md_needed + nrblocks;
+ spin_lock(&ei->i_block_reservation_lock);
+ md_reserved = ei->i_reserved_meta_blocks;
+ md_needed = ext4_calc_metadata_amount(inode, lblock);
+ spin_unlock(&ei->i_block_reservation_lock);
/*
* Make quota reservation here to prevent quota overflow
* later. Real quota accounting is done at pages writeout
* time.
*/
- if (vfs_dq_reserve_block(inode, total)) {
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ if (vfs_dq_reserve_block(inode, md_needed + 1)) {
+ /*
+ * We tend to badly over-estimate the amount of
+ * metadata blocks which are needed, so if we have
+ * reserved any metadata blocks, try to force out the
+ * inode and see if we have any better luck.
+ */
+ if (md_reserved && retries++ <= 3)
+ goto retry;
return -EDQUOT;
}
- if (ext4_claim_free_blocks(sbi, total)) {
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- vfs_dq_release_reservation_block(inode, total);
+ if (ext4_claim_free_blocks(sbi, md_needed + 1)) {
+ vfs_dq_release_reservation_block(inode, md_needed + 1);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+ retry:
+ if (md_reserved)
+ write_inode_now(inode, (retries == 3));
yield();
goto repeat;
}
return -ENOSPC;
}
- EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
- EXT4_I(inode)->i_reserved_meta_blocks = mdblocks;
+ spin_lock(&ei->i_block_reservation_lock);
+ ei->i_reserved_data_blocks++;
+ ei->i_reserved_meta_blocks += md_needed;
+ spin_unlock(&ei->i_block_reservation_lock);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
return 0; /* success */
}
static void ext4_da_release_space(struct inode *inode, int to_free)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- int total, mdb, mdb_free, release;
+ struct ext4_inode_info *ei = EXT4_I(inode);
if (!to_free)
return; /* Nothing to release, exit */
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- if (!EXT4_I(inode)->i_reserved_data_blocks) {
+ if (unlikely(to_free > ei->i_reserved_data_blocks)) {
/*
- * if there is no reserved blocks, but we try to free some
- * then the counter is messed up somewhere.
- * but since this function is called from invalidate
- * page, it's harmless to return without any action
+ * if there aren't enough reserved blocks, then the
+ * counter is messed up somewhere. Since this
+ * function is called from invalidate page, it's
+ * harmless to return without any action.
*/
- printk(KERN_INFO "ext4 delalloc try to release %d reserved "
- "blocks for inode %lu, but there is no reserved "
- "data blocks\n", to_free, inode->i_ino);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- return;
+ ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
+ "ino %lu, to_free %d with only %d reserved "
+ "data blocks\n", inode->i_ino, to_free,
+ ei->i_reserved_data_blocks);
+ WARN_ON(1);
+ to_free = ei->i_reserved_data_blocks;
}
+ ei->i_reserved_data_blocks -= to_free;
- /* recalculate the number of metablocks still need to be reserved */
- total = EXT4_I(inode)->i_reserved_data_blocks - to_free;
- mdb = ext4_calc_metadata_amount(inode, total);
-
- /* figure out how many metablocks to release */
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
-
- release = to_free + mdb_free;
-
- /* update fs dirty blocks counter for truncate case */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, release);
+ if (ei->i_reserved_data_blocks == 0) {
+ /*
+ * We can release all of the reserved metadata blocks
+ * only when we have written all of the delayed
+ * allocation blocks.
+ */
+ to_free += ei->i_reserved_meta_blocks;
+ ei->i_reserved_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
+ }
- /* update per-inode reservations */
- BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
- EXT4_I(inode)->i_reserved_data_blocks -= to_free;
+ /* update fs dirty blocks counter */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- EXT4_I(inode)->i_reserved_meta_blocks = mdb;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- vfs_dq_release_reservation_block(inode, release);
+ vfs_dq_release_reservation_block(inode, to_free);
}
static void ext4_da_page_release_reservation(struct page *page,
@@ -2494,7 +2514,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
* XXX: __block_prepare_write() unmaps passed block,
* is it OK?
*/
- ret = ext4_da_reserve_space(inode, 1);
+ ret = ext4_da_reserve_space(inode, iblock);
if (ret)
/* not enough space to reserve */
return ret;
@@ -2968,8 +2988,7 @@ retry:
out_writepages:
if (!no_nrwrite_index_update)
wbc->no_nrwrite_index_update = 0;
- if (wbc->nr_to_write > nr_to_writebump)
- wbc->nr_to_write -= nr_to_writebump;
+ wbc->nr_to_write -= nr_to_writebump;
wbc->range_start = range_start;
trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
return ret;
@@ -2994,11 +3013,18 @@ static int ext4_nonda_switch(struct super_block *sb)
if (2 * free_blocks < 3 * dirty_blocks ||
free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
/*
- * free block count is less that 150% of dirty blocks
- * or free blocks is less that watermark
+ * free block count is less than 150% of dirty blocks
+ * or free blocks is less than watermark
*/
return 1;
}
+ /*
+ * Even if we don't switch but are nearing capacity,
+ * start pushing delalloc when 1/2 of free blocks are dirty.
+ */
+ if (free_blocks < 2 * dirty_blocks)
+ writeback_inodes_sb_if_idle(sb);
+
return 0;
}
@@ -4794,6 +4820,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
inode->i_size = ext4_isize(raw_inode);
ei->i_disksize = inode->i_size;
+#ifdef CONFIG_QUOTA
+ ei->i_reserved_quota = 0;
+#endif
inode->i_generation = le32_to_cpu(raw_inode->i_generation);
ei->i_block_group = iloc.block_group;
ei->i_last_alloc_group = ~0;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c1e19d5b598..d34afad3e13 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2755,12 +2755,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
/* release all the reserved blocks if non delalloc */
percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
- else {
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
- ac->ac_b_ex.fe_len);
- /* convert reserved quota blocks to real quota blocks */
- vfs_dq_claim_block(ac->ac_inode, ac->ac_b_ex.fe_len);
- }
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi,
@@ -3955,7 +3949,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
* per cpu locality group is to reduce the contention between block
* request from multiple CPUs.
*/
- ac->ac_lg = per_cpu_ptr(sbi->s_locality_groups, raw_smp_processor_id());
+ ac->ac_lg = __this_cpu_ptr(sbi->s_locality_groups);
/* we're going to use group allocation */
ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 0ca811061bc..436521cae45 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -17,7 +17,6 @@
#include <linux/proc_fs.h>
#include <linux/pagemap.h>
#include <linux/seq_file.h>
-#include <linux/version.h>
#include <linux/blkdev.h>
#include <linux/mutex.h>
#include "ext4_jbd2.h"
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 768c111a77e..735c20d5fd5 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -702,8 +702,12 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
ei->i_delalloc_reserved_flag = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
+#ifdef CONFIG_QUOTA
+ ei->i_reserved_quota = 0;
+#endif
INIT_LIST_HEAD(&ei->i_aio_dio_complete_list);
ei->cur_aio_dio = NULL;
ei->i_sync_tid = 0;
@@ -1014,7 +1018,9 @@ static const struct dquot_operations ext4_quota_operations = {
.reserve_space = dquot_reserve_space,
.claim_space = dquot_claim_space,
.release_rsv = dquot_release_reserved_space,
+#ifdef CONFIG_QUOTA
.get_reserved_space = ext4_get_reserved_space,
+#endif
.alloc_inode = dquot_alloc_inode,
.free_space = dquot_free_space,
.free_inode = dquot_free_inode,
@@ -2137,11 +2143,8 @@ static int parse_strtoul(const char *buf,
{
char *endp;
- while (*buf && isspace(*buf))
- buf++;
- *value = simple_strtoul(buf, &endp, 0);
- while (*endp && isspace(*endp))
- endp++;
+ *value = simple_strtoul(skip_spaces(buf), &endp, 0);
+ endp = skip_spaces(endp);
if (*endp || *value > max)
return -EINVAL;
@@ -2172,9 +2175,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a,
struct super_block *sb = sbi->s_buddy_cache->i_sb;
return snprintf(buf, PAGE_SIZE, "%llu\n",
- sbi->s_kbytes_written +
+ (unsigned long long)(sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
- EXT4_SB(sb)->s_sectors_written_start) >> 1));
+ EXT4_SB(sb)->s_sectors_written_start) >> 1)));
}
static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
@@ -4003,6 +4006,7 @@ static inline void unregister_as_ext2(void)
{
unregister_filesystem(&ext2_fs_type);
}
+MODULE_ALIAS("ext2");
#else
static inline void register_as_ext2(void) { }
static inline void unregister_as_ext2(void) { }
@@ -4029,6 +4033,7 @@ static inline void unregister_as_ext3(void)
{
unregister_filesystem(&ext3_fs_type);
}
+MODULE_ALIAS("ext3");
#else
static inline void register_as_ext3(void) { }
static inline void unregister_as_ext3(void) { }
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 910bf9a59cb..f3a2f7ed45a 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -92,7 +92,7 @@ static struct buffer_head *ext4_xattr_cache_find(struct inode *,
struct mb_cache_entry **);
static void ext4_xattr_rehash(struct ext4_xattr_header *,
struct ext4_xattr_entry *);
-static int ext4_xattr_list(struct inode *inode, char *buffer,
+static int ext4_xattr_list(struct dentry *dentry, char *buffer,
size_t buffer_size);
static struct mb_cache *ext4_xattr_cache;
@@ -140,7 +140,7 @@ ext4_xattr_handler(int name_index)
ssize_t
ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
- return ext4_xattr_list(dentry->d_inode, buffer, size);
+ return ext4_xattr_list(dentry, buffer, size);
}
static int
@@ -325,7 +325,7 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
}
static int
-ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
+ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry,
char *buffer, size_t buffer_size)
{
size_t rest = buffer_size;
@@ -335,9 +335,10 @@ ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
ext4_xattr_handler(entry->e_name_index);
if (handler) {
- size_t size = handler->list(inode, buffer, rest,
+ size_t size = handler->list(dentry, buffer, rest,
entry->e_name,
- entry->e_name_len);
+ entry->e_name_len,
+ handler->flags);
if (buffer) {
if (size > rest)
return -ERANGE;
@@ -350,8 +351,9 @@ ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
}
static int
-ext4_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
+ struct inode *inode = dentry->d_inode;
struct buffer_head *bh = NULL;
int error;
@@ -376,7 +378,7 @@ ext4_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
goto cleanup;
}
ext4_xattr_cache_insert(bh);
- error = ext4_xattr_list_entries(inode, BFIRST(bh), buffer, buffer_size);
+ error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
cleanup:
brelse(bh);
@@ -385,8 +387,9 @@ cleanup:
}
static int
-ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
+ struct inode *inode = dentry->d_inode;
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
@@ -404,7 +407,7 @@ ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
error = ext4_xattr_check_names(IFIRST(header), end);
if (error)
goto cleanup;
- error = ext4_xattr_list_entries(inode, IFIRST(header),
+ error = ext4_xattr_list_entries(dentry, IFIRST(header),
buffer, buffer_size);
cleanup:
@@ -423,12 +426,12 @@ cleanup:
* used / required on success.
*/
static int
-ext4_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext4_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
int i_error, b_error;
- down_read(&EXT4_I(inode)->xattr_sem);
- i_error = ext4_xattr_ibody_list(inode, buffer, buffer_size);
+ down_read(&EXT4_I(dentry->d_inode)->xattr_sem);
+ i_error = ext4_xattr_ibody_list(dentry, buffer, buffer_size);
if (i_error < 0) {
b_error = 0;
} else {
@@ -436,11 +439,11 @@ ext4_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
buffer += i_error;
buffer_size -= i_error;
}
- b_error = ext4_xattr_block_list(inode, buffer, buffer_size);
+ b_error = ext4_xattr_block_list(dentry, buffer, buffer_size);
if (b_error < 0)
i_error = 0;
}
- up_read(&EXT4_I(inode)->xattr_sem);
+ up_read(&EXT4_I(dentry->d_inode)->xattr_sem);
return i_error + b_error;
}
@@ -1329,6 +1332,8 @@ retry:
goto cleanup;
kfree(b_entry_name);
kfree(buffer);
+ b_entry_name = NULL;
+ buffer = NULL;
brelse(is->iloc.bh);
kfree(is);
kfree(bs);
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index ca5f89fc6ca..983c253999a 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -12,8 +12,8 @@
#include "xattr.h"
static size_t
-ext4_xattr_security_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext4_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
const size_t total_len = prefix_len + name_len + 1;
@@ -28,23 +28,23 @@ ext4_xattr_security_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext4_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext4_xattr_security_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_get(inode, EXT4_XATTR_INDEX_SECURITY, name,
- buffer, size);
+ return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_SECURITY,
+ name, buffer, size);
}
static int
-ext4_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext4_xattr_security_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_set(inode, EXT4_XATTR_INDEX_SECURITY, name,
- value, size, flags);
+ return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_SECURITY,
+ name, value, size, flags);
}
int
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
index ac1a52cf2a3..15b50edc658 100644
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@@ -14,8 +14,8 @@
#include "xattr.h"
static size_t
-ext4_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext4_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
@@ -32,23 +32,23 @@ ext4_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext4_xattr_trusted_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext4_xattr_trusted_get(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_get(inode, EXT4_XATTR_INDEX_TRUSTED, name,
- buffer, size);
+ return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_TRUSTED,
+ name, buffer, size);
}
static int
-ext4_xattr_trusted_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext4_xattr_trusted_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_set(inode, EXT4_XATTR_INDEX_TRUSTED, name,
- value, size, flags);
+ return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_TRUSTED,
+ name, value, size, flags);
}
struct xattr_handler ext4_xattr_trusted_handler = {
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
index d91aa61b42a..c4ce05746ce 100644
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@@ -13,13 +13,13 @@
#include "xattr.h"
static size_t
-ext4_xattr_user_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext4_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_USER_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return 0;
if (list && total_len <= list_size) {
@@ -31,26 +31,27 @@ ext4_xattr_user_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext4_xattr_user_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext4_xattr_user_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext4_xattr_get(inode, EXT4_XATTR_INDEX_USER, name, buffer, size);
+ return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_USER,
+ name, buffer, size);
}
static int
-ext4_xattr_user_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext4_xattr_user_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext4_xattr_set(inode, EXT4_XATTR_INDEX_USER, name,
- value, size, flags);
+ return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_USER,
+ name, value, size, flags);
}
struct xattr_handler ext4_xattr_user_handler = {
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-27 07:09:30 +0000