* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (97 commits)
jbd2: Unify log messages in jbd2 code
jbd/jbd2: validate sb->s_first in journal_get_superblock()
ext4: let ext4_ext_rm_leaf work with EXT_DEBUG defined
ext4: fix a syntax error in ext4_ext_insert_extent when debugging enabled
ext4: fix a typo in struct ext4_allocation_context
ext4: Don't normalize an falloc request if it can fit in 1 extent.
ext4: remove comments about extent mount option in ext4_new_inode()
ext4: let ext4_discard_partial_buffers handle unaligned range correctly
ext4: return ENOMEM if find_or_create_pages fails
ext4: move vars to local scope in ext4_discard_partial_page_buffers_no_lock()
ext4: Create helper function for EXT4_IO_END_UNWRITTEN and i_aiodio_unwritten
ext4: optimize locking for end_io extent conversion
ext4: remove unnecessary call to waitqueue_active()
ext4: Use correct locking for ext4_end_io_nolock()
ext4: fix race in xattr block allocation path
ext4: trace punch_hole correctly in ext4_ext_map_blocks
ext4: clean up AGGRESSIVE_TEST code
ext4: move variables to their scope
ext4: fix quota accounting during migration
ext4: migrate cleanup
...
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
#define EXT4_MAP_UNINIT (1 << BH_Uninit)
+ /* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
+ * ext4_map_blocks wants to know whether or not the underlying cluster has
+ * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
+ * the requested mapping was from previously mapped (or delayed allocated)
+ * cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster
+ * should never appear on buffer_head's state flags.
+ */
+ #define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
- EXT4_MAP_UNINIT)
+ EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
#endif
#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof(__u32))
+ #define EXT4_CLUSTER_SIZE(s) (EXT4_BLOCK_SIZE(s) << \
+ EXT4_SB(s)->s_cluster_bits)
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits)
+ # define EXT4_CLUSTER_BITS(s) (EXT4_SB(s)->s_cluster_bits)
#else
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10)
#endif
#endif
#define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits)))
+ /* Translate a block number to a cluster number */
+ #define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits)
+ /* Translate a cluster number to a block number */
+ #define EXT4_C2B(sbi, cluster) ((cluster) << (sbi)->s_cluster_bits)
+ /* Translate # of blks to # of clusters */
+ #define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \
+ (sbi)->s_cluster_bits)
+
/*
* Structure of a blocks group descriptor
*/
struct flex_groups {
atomic_t free_inodes;
- atomic_t free_blocks;
+ atomic_t free_clusters;
atomic_t used_dirs;
};
#define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size)
#ifdef __KERNEL__
# define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group)
+ # define EXT4_CLUSTERS_PER_GROUP(s) (EXT4_SB(s)->s_clusters_per_group)
# define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block)
# define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group)
# define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits)
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
- EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\
- EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
+ EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 0x0020
/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040
+ /* Request will not result in inode size update (user for fallocate) */
+ #define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080
/*
* Flags used by ext4_free_blocks
#define EXT4_FREE_BLOCKS_FORGET 0x0002
#define EXT4_FREE_BLOCKS_VALIDATED 0x0004
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008
+ #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010
+ #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020
+
+ /*
+ * Flags used by ext4_discard_partial_page_buffers
+ */
+ #define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED 0x0001
/*
* ioctl commands
#define EXT4_IOC_SETVERSION _IOW('f', 4, long)
#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION
#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION
- #ifdef CONFIG_JBD2_DEBUG
- #define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long)
- #endif
#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long)
#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long)
#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long)
#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int)
#define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input)
- #ifdef CONFIG_JBD2_DEBUG
- #define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int)
- #endif
#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
#endif
ext4_group_t i_last_alloc_group;
/* allocation reservation info for delalloc */
+ /* In case of bigalloc, these refer to clusters rather than blocks */
unsigned int i_reserved_data_blocks;
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
/*
* Mount flags
*/
- #define EXT4_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */
#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */
#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */
#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
#define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */
#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */
+ #define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly
+ specified delalloc */
+
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
#define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \
/*10*/ __le32 s_free_inodes_count; /* Free inodes count */
__le32 s_first_data_block; /* First Data Block */
__le32 s_log_block_size; /* Block size */
- __le32 s_obso_log_frag_size; /* Obsoleted fragment size */
+ __le32 s_log_cluster_size; /* Allocation cluster size */
/*20*/ __le32 s_blocks_per_group; /* # Blocks per group */
- __le32 s_obso_frags_per_group; /* Obsoleted fragments per group */
+ __le32 s_clusters_per_group; /* # Clusters per group */
__le32 s_inodes_per_group; /* # Inodes per group */
__le32 s_mtime; /* Mount time */
/*30*/ __le32 s_wtime; /* Write time */
__u8 s_last_error_func[32]; /* function where the error happened */
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
__u8 s_mount_opts[64];
- __le32 s_reserved[112]; /* Padding to the end of the block */
+ __le32 s_usr_quota_inum; /* inode for tracking user quota */
+ __le32 s_grp_quota_inum; /* inode for tracking group quota */
+ __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
+ __le32 s_reserved[109]; /* Padding to the end of the block */
};
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
unsigned long s_desc_size; /* Size of a group descriptor in bytes */
unsigned long s_inodes_per_block;/* Number of inodes per block */
unsigned long s_blocks_per_group;/* Number of blocks in a group */
+ unsigned long s_clusters_per_group; /* Number of clusters in a group */
unsigned long s_inodes_per_group;/* Number of inodes in a group */
unsigned long s_itb_per_group; /* Number of inode table blocks per group */
unsigned long s_gdb_count; /* Number of group descriptor blocks */
ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
unsigned long s_overhead_last; /* Last calculated overhead */
unsigned long s_blocks_last; /* Last seen block count */
+ unsigned int s_cluster_ratio; /* Number of blocks per cluster */
+ unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
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_freeclusters_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
- struct percpu_counter s_dirtyblocks_counter;
+ struct percpu_counter s_dirtyclusters_counter;
struct blockgroup_lock *s_blockgroup_lock;
struct proc_dir_entry *s_proc;
struct kobject s_kobj;
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) */
- wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */
- #endif
#ifdef CONFIG_QUOTA
char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
int s_jquota_fmt; /* Format of quota to use */
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
+ static inline void ext4_set_io_unwritten_flag(struct inode *inode,
+ struct ext4_io_end *io_end)
+ {
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ }
+ }
+
/*
* Inode dynamic state flags
*/
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
#define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100
+ #define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200
#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001
#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002
EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
- EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
+ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC)
/*
* Default values for user and/or group using reserved blocks
unsigned int flags,
unsigned long *count,
int *errp);
- extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
- s64 nblocks, unsigned int flags);
- extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
+ extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
+ s64 nclusters, unsigned int flags);
+ extern ext4_fsblk_t ext4_count_free_clusters(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,
ext4_group_t block_group,
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
ext4_group_t block_group);
- extern unsigned ext4_init_block_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
- #define ext4_free_blocks_after_init(sb, group, desc) \
- ext4_init_block_bitmap(sb, NULL, group, desc)
+ extern void ext4_init_block_bitmap(struct super_block *sb,
+ struct buffer_head *bh,
+ ext4_group_t group,
+ struct ext4_group_desc *desc);
+ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp);
+ extern unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+ ext4_group_t block_group);
+ extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
/* dir.c */
/* ialloc.c */
extern struct inode *ext4_new_inode(handle_t *, struct inode *, int,
- const struct qstr *qstr, __u32 goal);
+ const struct qstr *qstr, __u32 goal,
+ uid_t *owner);
extern void ext4_free_inode(handle_t *, struct inode *);
extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
extern unsigned long ext4_count_free_inodes(struct super_block *);
struct address_space *mapping, loff_t from);
extern int ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length);
+ extern int ext4_discard_partial_page_buffers(handle_t *handle,
+ struct address_space *mapping, loff_t from,
+ loff_t length, int flags);
+ extern int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+ struct inode *inode, struct page *page, loff_t from,
+ loff_t length, int flags);
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 void ext4_da_update_reserve_space(struct inode *inode,
extern void *ext4_kvmalloc(size_t size, gfp_t flags);
extern void *ext4_kvzalloc(size_t size, gfp_t flags);
extern void ext4_kvfree(void *ptr);
-extern void __ext4_error(struct super_block *, const char *, unsigned int,
- const char *, ...)
- __attribute__ ((format (printf, 4, 5)));
+extern __printf(4, 5)
+void __ext4_error(struct super_block *, const char *, unsigned int,
+ const char *, ...);
#define ext4_error(sb, message...) __ext4_error(sb, __func__, \
__LINE__, ## message)
-extern void ext4_error_inode(struct inode *, const char *, unsigned int,
- ext4_fsblk_t, const char *, ...)
- __attribute__ ((format (printf, 5, 6)));
-extern void ext4_error_file(struct file *, const char *, unsigned int,
- ext4_fsblk_t, const char *, ...)
- __attribute__ ((format (printf, 5, 6)));
+extern __printf(5, 6)
+void ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
+ const char *, ...);
+extern __printf(5, 6)
+void ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
+ const char *, ...);
extern void __ext4_std_error(struct super_block *, const char *,
unsigned int, int);
-extern void __ext4_abort(struct super_block *, const char *, unsigned int,
- const char *, ...)
- __attribute__ ((format (printf, 4, 5)));
+extern __printf(4, 5)
+void __ext4_abort(struct super_block *, const char *, unsigned int,
+ const char *, ...);
#define ext4_abort(sb, message...) __ext4_abort(sb, __func__, \
__LINE__, ## message)
-extern void __ext4_warning(struct super_block *, const char *, unsigned int,
- const char *, ...)
- __attribute__ ((format (printf, 4, 5)));
+extern __printf(4, 5)
+void __ext4_warning(struct super_block *, const char *, unsigned int,
+ const char *, ...);
#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, \
__LINE__, ## message)
-extern void ext4_msg(struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
+extern __printf(3, 4)
+void ext4_msg(struct super_block *, const char *, const char *, ...);
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
const char *, unsigned int, const char *);
#define dump_mmp_msg(sb, mmp, msg) __dump_mmp_msg(sb, mmp, __func__, \
__LINE__, msg)
-extern void __ext4_grp_locked_error(const char *, unsigned int, \
- struct super_block *, ext4_group_t, \
- unsigned long, ext4_fsblk_t, \
- const char *, ...)
- __attribute__ ((format (printf, 7, 8)));
+extern __printf(7, 8)
+void __ext4_grp_locked_error(const char *, unsigned int,
+ struct super_block *, ext4_group_t,
+ unsigned long, ext4_fsblk_t,
+ const char *, ...);
#define ext4_grp_locked_error(sb, grp, message...) \
__ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
extern void ext4_update_dynamic_rev(struct super_block *sb);
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_group_clusters(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, 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_group_clusters_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,
} while (0)
#ifdef CONFIG_SMP
- /* Each CPU can accumulate percpu_counter_batch blocks in their local
- * counters. So we need to make sure we have free blocks more
+ /* Each CPU can accumulate percpu_counter_batch clusters in their local
+ * counters. So we need to make sure we have free clusters more
* than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times.
*/
- #define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
+ #define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
#else
- #define EXT4_FREEBLOCKS_WATERMARK 0
+ #define EXT4_FREECLUSTERS_WATERMARK 0
#endif
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
enum ext4_state_bits {
BH_Uninit /* blocks are allocated but uninitialized on disk */
= BH_JBDPrivateStart,
+ BH_AllocFromCluster, /* allocated blocks were part of already
+ * allocated cluster. Note that this flag will
+ * never, ever appear in a buffer_head's state
+ * flag. See EXT4_MAP_FROM_CLUSTER to see where
+ * this is used. */
+ BH_Da_Mapped, /* Delayed allocated block that now has a mapping. This
+ * flag is set when ext4_map_blocks is called on a
+ * delayed allocated block to get its real mapping. */
};
BUFFER_FNS(Uninit, uninit)
TAS_BUFFER_FNS(Uninit, uninit)
+ BUFFER_FNS(Da_Mapped, da_mapped)
/*
* Add new method to test wether block and inode bitmaps are properly
#endif /* __KERNEL__ */
+ #include "ext4_extents.h"
+
#endif /* _EXT4_H */
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
- memcpy(sbi->s_es->s_last_mounted, cp,
- sizeof(sbi->s_es->s_last_mounted));
+ strlcpy(sbi->s_es->s_last_mounted, cp,
+ sizeof(sbi->s_es->s_last_mounted));
ext4_mark_super_dirty(sb);
}
}
maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
else
maxbytes = inode->i_sb->s_maxbytes;
- mutex_lock(&inode->i_mutex);
- switch (origin) {
- case SEEK_END:
- offset += inode->i_size;
- break;
- case SEEK_CUR:
- if (offset == 0) {
- mutex_unlock(&inode->i_mutex);
- return file->f_pos;
- }
- offset += file->f_pos;
- break;
- case SEEK_DATA:
- /*
- * In the generic case the entire file is data, so as long as
- * offset isn't at the end of the file then the offset is data.
- */
- if (offset >= inode->i_size) {
- mutex_unlock(&inode->i_mutex);
- return -ENXIO;
- }
- break;
- case SEEK_HOLE:
- /*
- * There is a virtual hole at the end of the file, so as long as
- * offset isn't i_size or larger, return i_size.
- */
- if (offset >= inode->i_size) {
- mutex_unlock(&inode->i_mutex);
- return -ENXIO;
- }
- offset = inode->i_size;
- break;
- }
-
- if (offset < 0 || offset > maxbytes) {
- mutex_unlock(&inode->i_mutex);
- return -EINVAL;
- }
-
- if (offset != file->f_pos) {
- file->f_pos = offset;
- file->f_version = 0;
- }
- mutex_unlock(&inode->i_mutex);
- return offset;
+ return generic_file_llseek_size(file, offset, origin, maxbytes);
}
const struct file_operations ext4_file_operations = {
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
- #include "ext4_extents.h"
#include "truncate.h"
#include <trace/events/ext4.h>
struct ext4_inode_info *ei = EXT4_I(inode);
spin_lock(&ei->i_block_reservation_lock);
- trace_ext4_da_update_reserve_space(inode, used);
+ trace_ext4_da_update_reserve_space(inode, used, quota_claim);
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",
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
used + ei->i_allocated_meta_blocks);
ei->i_allocated_meta_blocks = 0;
* only when we have written all of the delayed
* allocation blocks.
*/
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
/* Update quota subsystem for data blocks */
if (quota_claim)
- dquot_claim_block(inode, used);
+ dquot_claim_block(inode, EXT4_C2B(sbi, used));
else {
/*
* We did fallocate with an offset that is already delayed
* allocated. So on delayed allocated writeback we should
* not re-claim the quota for fallocated blocks.
*/
- dquot_release_reservation_block(inode, used);
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
}
/*
return num;
}
+ /*
+ * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map.
+ */
+ static void set_buffers_da_mapped(struct inode *inode,
+ struct ext4_map_blocks *map)
+ {
+ struct address_space *mapping = inode->i_mapping;
+ struct pagevec pvec;
+ int i, nr_pages;
+ pgoff_t index, end;
+
+ index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (map->m_lblk + map->m_len - 1) >>
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ pagevec_init(&pvec, 0);
+ while (index <= end) {
+ nr_pages = pagevec_lookup(&pvec, mapping, index,
+ min(end - index + 1,
+ (pgoff_t)PAGEVEC_SIZE));
+ if (nr_pages == 0)
+ break;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ struct buffer_head *bh, *head;
+
+ if (unlikely(page->mapping != mapping) ||
+ !PageDirty(page))
+ break;
+
+ if (page_has_buffers(page)) {
+ bh = head = page_buffers(page);
+ do {
+ set_buffer_da_mapped(bh);
+ bh = bh->b_this_page;
+ } while (bh != head);
+ }
+ index++;
+ }
+ pagevec_release(&pvec);
+ }
+ }
+
/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
* the buffer head is mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
- * that casem, buffer head is unmapped
+ * that case, buffer head is unmapped
*
* It returns the error in case of allocation failure.
*/
*/
down_read((&EXT4_I(inode)->i_data_sem));
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
- retval = ext4_ext_map_blocks(handle, inode, map, 0);
+ retval = ext4_ext_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
} else {
- retval = ext4_ind_map_blocks(handle, inode, map, 0);
+ retval = ext4_ind_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
}
up_read((&EXT4_I(inode)->i_data_sem));
* Returns if the blocks have already allocated
*
* Note that if blocks have been preallocated
- * ext4_ext_get_block() returns th create = 0
+ * ext4_ext_get_block() returns the create = 0
* with buffer head unmapped.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
+ /* If we have successfully mapped the delayed allocated blocks,
+ * set the BH_Da_Mapped bit on them. Its important to do this
+ * under the protection of i_data_sem.
+ */
+ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
+ set_buffers_da_mapped(inode, map);
+ }
+
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int ret = check_block_validity(inode, map);
return bh;
if (buffer_uptodate(bh))
return bh;
- ll_rw_block(READ_META, 1, &bh);
+ ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
ext4_orphan_add(handle, inode);
if (ret2 < 0)
ret = ret2;
+ } else {
+ unlock_page(page);
+ page_cache_release(page);
}
+
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
}
/*
- * Reserve a single block located at lblock
+ * Reserve a single cluster located at lblock
*/
static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
{
int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
- unsigned long md_needed;
+ unsigned int md_needed;
int ret;
/*
*/
repeat:
spin_lock(&ei->i_block_reservation_lock);
- md_needed = ext4_calc_metadata_amount(inode, lblock);
+ md_needed = EXT4_NUM_B2C(sbi,
+ ext4_calc_metadata_amount(inode, lblock));
trace_ext4_da_reserve_space(inode, md_needed);
spin_unlock(&ei->i_block_reservation_lock);
* us from metadata over-estimation, though we may go over by
* a small amount in the end. Here we just reserve for data.
*/
- ret = dquot_reserve_block(inode, 1);
+ ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
if (ret)
return ret;
/*
* We do still charge estimated metadata to the sb though;
* we cannot afford to run out of free blocks.
*/
- if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) {
- dquot_release_reservation_block(inode, 1);
+ if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) {
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
* We can release all of the reserved metadata blocks
* only when we have written all of the delayed
* allocation blocks.
+ * Note that in case of bigalloc, i_reserved_meta_blocks,
+ * i_reserved_data_blocks, etc. refer to number of clusters.
*/
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
}
/* update fs dirty data blocks counter */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- dquot_release_reservation_block(inode, to_free);
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
}
static void ext4_da_page_release_reservation(struct page *page,
int to_release = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
+ struct inode *inode = page->mapping->host;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ int num_clusters;
head = page_buffers(page);
bh = head;
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
clear_buffer_delay(bh);
+ clear_buffer_da_mapped(bh);
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
- ext4_da_release_space(page->mapping->host, to_release);
+
+ /* If we have released all the blocks belonging to a cluster, then we
+ * need to release the reserved space for that cluster. */
+ num_clusters = EXT4_NUM_B2C(sbi, to_release);
+ while (num_clusters > 0) {
+ ext4_fsblk_t lblk;
+ lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) +
+ ((num_clusters - 1) << sbi->s_cluster_bits);
+ if (sbi->s_cluster_ratio == 1 ||
+ !ext4_find_delalloc_cluster(inode, lblk, 1))
+ ext4_da_release_space(inode, 1);
+
+ num_clusters--;
+ }
}
/*
clear_buffer_delay(bh);
bh->b_blocknr = pblock;
}
+ if (buffer_da_mapped(bh))
+ clear_buffer_da_mapped(bh);
if (buffer_unwritten(bh) ||
buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
printk(KERN_CRIT "Total free blocks count %lld\n",
- ext4_count_free_blocks(inode->i_sb));
+ EXT4_C2B(EXT4_SB(inode->i_sb),
+ ext4_count_free_clusters(inode->i_sb)));
printk(KERN_CRIT "Free/Dirty block details\n");
printk(KERN_CRIT "free_blocks=%lld\n",
- (long long) percpu_counter_sum(&sbi->s_freeblocks_counter));
+ (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ percpu_counter_sum(&sbi->s_freeclusters_counter)));
printk(KERN_CRIT "dirty_blocks=%lld\n",
- (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
printk(KERN_CRIT "Block reservation details\n");
printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
EXT4_I(inode)->i_reserved_data_blocks);
if (err == -EAGAIN)
goto submit_io;
- if (err == -ENOSPC &&
- ext4_count_free_blocks(sb)) {
+ if (err == -ENOSPC && ext4_count_free_clusters(sb)) {
mpd->retval = err;
goto submit_io;
}
for (i = 0; i < map.m_len; i++)
unmap_underlying_metadata(bdev, map.m_pblk + i);
- }
- if (ext4_should_order_data(mpd->inode)) {
- err = ext4_jbd2_file_inode(handle, mpd->inode);
- if (err)
- /* This only happens if the journal is aborted */
- return;
+ if (ext4_should_order_data(mpd->inode)) {
+ err = ext4_jbd2_file_inode(handle, mpd->inode);
+ if (err) {
+ /* Only if the journal is aborted */
+ mpd->retval = err;
+ goto submit_io;
+ }
+ }
}
/*
return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
}
+ /*
+ * This function is grabs code from the very beginning of
+ * ext4_map_blocks, but assumes that the caller is from delayed write
+ * time. This function looks up the requested blocks and sets the
+ * buffer delay bit under the protection of i_data_sem.
+ */
+ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
+ struct ext4_map_blocks *map,
+ struct buffer_head *bh)
+ {
+ int retval;
+ sector_t invalid_block = ~((sector_t) 0xffff);
+
+ if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
+ invalid_block = ~0;
+
+ map->m_flags = 0;
+ ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
+ "logical block %lu\n", inode->i_ino, map->m_len,
+ (unsigned long) map->m_lblk);
+ /*
+ * Try to see if we can get the block without requesting a new
+ * file system block.
+ */
+ down_read((&EXT4_I(inode)->i_data_sem));
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ retval = ext4_ext_map_blocks(NULL, inode, map, 0);
+ else
+ retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+
+ if (retval == 0) {
+ /*
+ * XXX: __block_prepare_write() unmaps passed block,
+ * is it OK?
+ */
+ /* If the block was allocated from previously allocated cluster,
+ * then we dont need to reserve it again. */
+ if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
+ retval = ext4_da_reserve_space(inode, iblock);
+ if (retval)
+ /* not enough space to reserve */
+ goto out_unlock;
+ }
+
+ /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
+ * and it should not appear on the bh->b_state.
+ */
+ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
+
+ map_bh(bh, inode->i_sb, invalid_block);
+ set_buffer_new(bh);
+ set_buffer_delay(bh);
+ }
+
+ out_unlock:
+ up_read((&EXT4_I(inode)->i_data_sem));
+
+ return retval;
+ }
+
/*
* This is a special get_blocks_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
{
struct ext4_map_blocks map;
int ret = 0;
- sector_t invalid_block = ~((sector_t) 0xffff);
-
- if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
- invalid_block = ~0;
BUG_ON(create == 0);
BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
+ ret = ext4_da_map_blocks(inode, iblock, &map, bh);
+ if (ret <= 0)
return ret;
- if (ret == 0) {
- if (buffer_delay(bh))
- return 0; /* Not sure this could or should happen */
- /*
- * XXX: __block_write_begin() unmaps passed block, is it OK?
- */
- ret = ext4_da_reserve_space(inode, iblock);
- if (ret)
- /* not enough space to reserve */
- return ret;
-
- map_bh(bh, inode->i_sb, invalid_block);
- set_buffer_new(bh);
- set_buffer_delay(bh);
- return 0;
- }
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
* We don't want to do block allocation, so redirty
* the page and return. We may reach here when we do
* a journal commit via journal_submit_inode_data_buffers.
- * We can also reach here via shrink_page_list
+ * We can also reach here via shrink_page_list but it
+ * should never be for direct reclaim so warn if that
+ * happens
*/
+ WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
+ PF_MEMALLOC);
goto redirty_page;
}
if (commit_write)
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
pgoff_t done_index = 0;
pgoff_t end;
+ struct blk_plug plug;
trace_ext4_da_writepages(inode, wbc);
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
+ blk_start_plug(&plug);
while (!ret && wbc->nr_to_write > 0) {
/*
ret = 0;
} else if (ret == MPAGE_DA_EXTENT_TAIL) {
/*
- * got one extent now try with
- * rest of the pages
+ * Got one extent now try with rest of the pages.
+ * If mpd.retval is set -EIO, journal is aborted.
+ * So we don't need to write any more.
*/
pages_written += mpd.pages_written;
- ret = 0;
+ ret = mpd.retval;
io_done = 1;
} else if (wbc->nr_to_write)
/*
*/
break;
}
+ blk_finish_plug(&plug);
if (!io_done && !cycled) {
cycled = 1;
index = 0;
* Delalloc need an accurate free block accounting. So switch
* to non delalloc when we are near to error range.
*/
- free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
- dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+ free_blocks = EXT4_C2B(sbi,
+ percpu_counter_read_positive(&sbi->s_freeclusters_counter));
+ dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
if (2 * free_blocks < 3 * dirty_blocks ||
- free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+ free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
/*
* free block count is less than 150% of dirty blocks
* or free blocks is less than watermark
pgoff_t index;
struct inode *inode = mapping->host;
handle_t *handle;
+ loff_t page_len;
index = pos >> PAGE_CACHE_SHIFT;
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
+ } else {
+ page_len = pos & (PAGE_CACHE_SIZE - 1);
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers_no_lock(handle,
+ inode, page, pos - page_len, page_len,
+ EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+ }
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
+ loff_t page_len;
if (write_mode == FALL_BACK_TO_NONDELALLOC) {
if (ext4_should_order_data(inode)) {
}
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
+
+ page_len = PAGE_CACHE_SIZE -
+ ((pos + copied - 1) & (PAGE_CACHE_SIZE - 1));
+
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers_no_lock(handle,
+ inode, page, pos + copied - 1, page_len,
+ EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+ }
+
copied = ret2;
if (ret2 < 0)
ret = ret2;
* but being more careful is always safe for the future change.
*/
inode = io_end->inode;
- if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
- io_end->flag |= EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
- }
+ ext4_set_io_unwritten_flag(inode, io_end);
/* Add the io_end to per-inode completed io list*/
spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
struct inode *inode = file->f_mapping->host;
ssize_t ret;
+ /*
+ * If we are doing data journalling we don't support O_DIRECT
+ */
+ if (ext4_should_journal_data(inode))
+ return 0;
+
trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
inode->i_mapping->a_ops = &ext4_journalled_aops;
}
+
+ /*
+ * ext4_discard_partial_page_buffers()
+ * Wrapper function for ext4_discard_partial_page_buffers_no_lock.
+ * This function finds and locks the page containing the offset
+ * "from" and passes it to ext4_discard_partial_page_buffers_no_lock.
+ * Calling functions that already have the page locked should call
+ * ext4_discard_partial_page_buffers_no_lock directly.
+ */
+ int ext4_discard_partial_page_buffers(handle_t *handle,
+ struct address_space *mapping, loff_t from,
+ loff_t length, int flags)
+ {
+ struct inode *inode = mapping->host;
+ struct page *page;
+ int err = 0;
+
+ page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
+ mapping_gfp_mask(mapping) & ~__GFP_FS);
+ if (!page)
+ return -ENOMEM;
+
+ err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page,
+ from, length, flags);
+
+ unlock_page(page);
+ page_cache_release(page);
+ return err;
+ }
+
+ /*
+ * ext4_discard_partial_page_buffers_no_lock()
+ * Zeros a page range of length 'length' starting from offset 'from'.
+ * Buffer heads that correspond to the block aligned regions of the
+ * zeroed range will be unmapped. Unblock aligned regions
+ * will have the corresponding buffer head mapped if needed so that
+ * that region of the page can be updated with the partial zero out.
+ *
+ * This function assumes that the page has already been locked. The
+ * The range to be discarded must be contained with in the given page.
+ * If the specified range exceeds the end of the page it will be shortened
+ * to the end of the page that corresponds to 'from'. This function is
+ * appropriate for updating a page and it buffer heads to be unmapped and
+ * zeroed for blocks that have been either released, or are going to be
+ * released.
+ *
+ * handle: The journal handle
+ * inode: The files inode
+ * page: A locked page that contains the offset "from"
+ * from: The starting byte offset (from the begining of the file)
+ * to begin discarding
+ * len: The length of bytes to discard
+ * flags: Optional flags that may be used:
+ *
+ * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED
+ * Only zero the regions of the page whose buffer heads
+ * have already been unmapped. This flag is appropriate
+ * for updateing the contents of a page whose blocks may
+ * have already been released, and we only want to zero
+ * out the regions that correspond to those released blocks.
+ *
+ * Returns zero on sucess or negative on failure.
+ */
+ int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+ struct inode *inode, struct page *page, loff_t from,
+ loff_t length, int flags)
+ {
+ ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
+ unsigned int offset = from & (PAGE_CACHE_SIZE-1);
+ unsigned int blocksize, max, pos;
+ ext4_lblk_t iblock;
+ struct buffer_head *bh;
+ int err = 0;
+
+ blocksize = inode->i_sb->s_blocksize;
+ max = PAGE_CACHE_SIZE - offset;
+
+ if (index != page->index)
+ return -EINVAL;
+
+ /*
+ * correct length if it does not fall between
+ * 'from' and the end of the page
+ */
+ if (length > max || length < 0)
+ length = max;
+
+ iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+
+ if (!page_has_buffers(page)) {
+ /*
+ * If the range to be discarded covers a partial block
+ * we need to get the page buffers. This is because
+ * partial blocks cannot be released and the page needs
+ * to be updated with the contents of the block before
+ * we write the zeros on top of it.
+ */
+ if ((from & (blocksize - 1)) ||
+ ((from + length) & (blocksize - 1))) {
+ create_empty_buffers(page, blocksize, 0);
+ } else {
+ /*
+ * If there are no partial blocks,
+ * there is nothing to update,
+ * so we can return now
+ */
+ return 0;
+ }
+ }
+
+ /* Find the buffer that contains "offset" */
+ bh = page_buffers(page);
+ pos = blocksize;
+ while (offset >= pos) {
+ bh = bh->b_this_page;
+ iblock++;
+ pos += blocksize;
+ }
+
+ pos = offset;
+ while (pos < offset + length) {
+ unsigned int end_of_block, range_to_discard;
+
+ err = 0;
+
+ /* The length of space left to zero and unmap */
+ range_to_discard = offset + length - pos;
+
+ /* The length of space until the end of the block */
+ end_of_block = blocksize - (pos & (blocksize-1));
+
+ /*
+ * Do not unmap or zero past end of block
+ * for this buffer head
+ */
+ if (range_to_discard > end_of_block)
+ range_to_discard = end_of_block;
+
+
+ /*
+ * Skip this buffer head if we are only zeroing unampped
+ * regions of the page
+ */
+ if (flags & EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED &&
+ buffer_mapped(bh))
+ goto next;
+
+ /* If the range is block aligned, unmap */
+ if (range_to_discard == blocksize) {
+ clear_buffer_dirty(bh);
+ bh->b_bdev = NULL;
+ clear_buffer_mapped(bh);
+ clear_buffer_req(bh);
+ clear_buffer_new(bh);
+ clear_buffer_delay(bh);
+ clear_buffer_unwritten(bh);
+ clear_buffer_uptodate(bh);
+ zero_user(page, pos, range_to_discard);
+ BUFFER_TRACE(bh, "Buffer discarded");
+ goto next;
+ }
+
+ /*
+ * If this block is not completely contained in the range
+ * to be discarded, then it is not going to be released. Because
+ * we need to keep this block, we need to make sure this part
+ * of the page is uptodate before we modify it by writeing
+ * partial zeros on it.
+ */
+ if (!buffer_mapped(bh)) {
+ /*
+ * Buffer head must be mapped before we can read
+ * from the block
+ */
+ BUFFER_TRACE(bh, "unmapped");
+ ext4_get_block(inode, iblock, bh, 0);
+ /* unmapped? It's a hole - nothing to do */
+ if (!buffer_mapped(bh)) {
+ BUFFER_TRACE(bh, "still unmapped");
+ goto next;
+ }
+ }
+
+ /* Ok, it's mapped. Make sure it's up-to-date */
+ if (PageUptodate(page))
+ set_buffer_uptodate(bh);
+
+ if (!buffer_uptodate(bh)) {
+ err = -EIO;
+ ll_rw_block(READ, 1, &bh);
+ wait_on_buffer(bh);
+ /* Uhhuh. Read error. Complain and punt.*/
+ if (!buffer_uptodate(bh))
+ goto next;
+ }
+
+ if (ext4_should_journal_data(inode)) {
+ BUFFER_TRACE(bh, "get write access");
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err)
+ goto next;
+ }
+
+ zero_user(page, pos, range_to_discard);
+
+ err = 0;
+ if (ext4_should_journal_data(inode)) {
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+ } else
+ mark_buffer_dirty(bh);
+
+ BUFFER_TRACE(bh, "Partial buffer zeroed");
+ next:
+ bh = bh->b_this_page;
+ iblock++;
+ pos += range_to_discard;
+ }
+
+ return err;
+ }
+
/*
* ext4_block_truncate_page() zeroes out a mapping from file offset `from'
* up to the end of the block which corresponds to `from'.
page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
mapping_gfp_mask(mapping) & ~__GFP_FS);
if (!page)
- return -EINVAL;
+ return -ENOMEM;
blocksize = inode->i_sb->s_blocksize;
max = blocksize - (offset & (blocksize - 1));
err = 0;
if (ext4_should_journal_data(inode)) {
err = ext4_handle_dirty_metadata(handle, inode, bh);
- } else {
- if (ext4_should_order_data(inode) && EXT4_I(inode)->jinode)
- err = ext4_jbd2_file_inode(handle, inode);
+ } else
mark_buffer_dirty(bh);
- }
unlock:
unlock_page(page);
return -ENOTSUPP;
}
+ if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
+ /* TODO: Add support for bigalloc file systems */
+ return -ENOTSUPP;
+ }
+
return ext4_ext_punch_hole(file, offset, length);
}
trace_ext4_load_inode(inode);
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(READ_META, bh);
+ submit_bh(READ | REQ_META | REQ_PRIO, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
EXT4_ERROR_INODE_BLOCK(inode, block,
PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
unlock_page(page);
ret = VM_FAULT_SIGBUS;
+ ext4_journal_stop(handle);
goto out;
}
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
bh = ext4_getblk(NULL, dir, b++, 0, &err);
bh_use[ra_max] = bh;
if (bh)
- ll_rw_block(READ_META, 1, &bh);
+ ll_rw_block(READ | REQ_META | REQ_PRIO,
+ 1, &bh);
}
}
if ((bh = bh_use[ra_ptr++]) == NULL)
dxtrace(dx_show_index("node", frames[1].entries));
dxtrace(dx_show_index("node",
((struct dx_node *) bh2->b_data)->entries));
- err = ext4_handle_dirty_metadata(handle, inode, bh2);
+ err = ext4_handle_dirty_metadata(handle, dir, bh2);
if (err)
goto journal_error;
brelse (bh2);
if (err)
goto journal_error;
}
- err = ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
+ err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh);
if (err) {
ext4_std_error(inode->i_sb, err);
goto cleanup;
*/
static void ext4_dec_count(handle_t *handle, struct inode *inode)
{
- drop_nlink(inode);
- if (S_ISDIR(inode->i_mode) && inode->i_nlink == 0)
- inc_nlink(inode);
+ if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
+ drop_nlink(inode);
}
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
- inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
+ inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
inode->i_op = &ext4_file_inode_operations;
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
- inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0);
+ inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFDIR | mode,
- &dentry->d_name, 0);
+ &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
inode->i_nlink = 2;
BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, dir, dir_block);
+ err = ext4_handle_dirty_metadata(handle, inode, dir_block);
if (err)
goto out_clear_inode;
err = ext4_mark_inode_dirty(handle, inode);
ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO,
- &dentry->d_name, 0);
+ &dentry->d_name, 0, NULL);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
cpu_to_le32(new_dir->i_ino);
BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
- retval = ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
+ retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh);
if (retval) {
ext4_std_error(old_dir->i_sb, retval);
goto end_rename;
/* Flags that should be inherited by new inodes from their parent. */
#define EXT3_FL_INHERITED (EXT3_SECRM_FL | EXT3_UNRM_FL | EXT3_COMPR_FL |\
- EXT3_SYNC_FL | EXT3_IMMUTABLE_FL | EXT3_APPEND_FL |\
- EXT3_NODUMP_FL | EXT3_NOATIME_FL | EXT3_COMPRBLK_FL|\
+ EXT3_SYNC_FL | EXT3_NODUMP_FL |\
+ EXT3_NOATIME_FL | EXT3_COMPRBLK_FL |\
EXT3_NOCOMPR_FL | EXT3_JOURNAL_DATA_FL |\
EXT3_NOTAIL_FL | EXT3_DIRSYNC_FL)
* Mount flags
*/
#define EXT3_MOUNT_CHECK 0x00001 /* Do mount-time checks */
-#define EXT3_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */
+/* EXT3_MOUNT_OLDALLOC was there */
#define EXT3_MOUNT_GRPID 0x00004 /* Create files with directory's group */
#define EXT3_MOUNT_DEBUG 0x00008 /* Some debugging messages */
#define EXT3_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
ext3_fsblk_t n_blocks_count);
/* super.c */
-extern void ext3_error (struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
+extern __printf(3, 4)
+void ext3_error(struct super_block *, const char *, const char *, ...);
extern void __ext3_std_error (struct super_block *, const char *, int);
-extern void ext3_abort (struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
-extern void ext3_warning (struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
-extern void ext3_msg(struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
+extern __printf(3, 4)
+void ext3_abort(struct super_block *, const char *, const char *, ...);
+extern __printf(3, 4)
+void ext3_warning(struct super_block *, const char *, const char *, ...);
+extern __printf(3, 4)
+void ext3_msg(struct super_block *, const char *, const char *, ...);
extern void ext3_update_dynamic_rev (struct super_block *sb);
#define ext3_std_error(sb, errno) \
#define NR_FILE 8192 /* this can well be larger on a larger system */
-#define MAY_EXEC 1
-#define MAY_WRITE 2
-#define MAY_READ 4
-#define MAY_APPEND 8
-#define MAY_ACCESS 16
-#define MAY_OPEN 32
-#define MAY_CHDIR 64
-#define MAY_NOT_BLOCK 128 /* called from RCU mode, don't block */
+#define MAY_EXEC 0x00000001
+#define MAY_WRITE 0x00000002
+#define MAY_READ 0x00000004
+#define MAY_APPEND 0x00000008
+#define MAY_ACCESS 0x00000010
+#define MAY_OPEN 0x00000020
+#define MAY_CHDIR 0x00000040
+/* called from RCU mode, don't block */
+#define MAY_NOT_BLOCK 0x00000080
/*
* flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond
#define READA RWA_MASK
#define READ_SYNC (READ | REQ_SYNC)
-#define READ_META (READ | REQ_META)
#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE)
#define WRITE_ODIRECT (WRITE | REQ_SYNC)
-#define WRITE_META (WRITE | REQ_META)
#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
unsigned long i_ino;
unsigned int i_nlink;
dev_t i_rdev;
- loff_t i_size;
struct timespec i_atime;
struct timespec i_mtime;
struct timespec i_ctime;
- unsigned int i_blkbits;
+ spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
+ unsigned short i_bytes;
blkcnt_t i_blocks;
+ loff_t i_size;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
/* Misc */
unsigned long i_state;
- spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
struct mutex i_mutex;
unsigned long dirtied_when; /* jiffies of first dirtying */
struct rcu_head i_rcu;
};
atomic_t i_count;
+ unsigned int i_blkbits;
u64 i_version;
- unsigned short i_bytes;
atomic_t i_dio_count;
+ atomic_t i_writecount;
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
struct file_lock *i_flock;
struct address_space i_data;
#ifdef CONFIG_IMA
atomic_t i_readcount; /* struct files open RO */
#endif
- atomic_t i_writecount;
void *i_private; /* fs or device private pointer */
};
#define f_dentry f_path.dentry
#define f_vfsmnt f_path.mnt
const struct file_operations *f_op;
- spinlock_t f_lock; /* f_ep_links, f_flags, no IRQ */
+
+ /*
+ * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
+ * Must not be taken from IRQ context.
+ */
+ spinlock_t f_lock;
#ifdef CONFIG_SMP
int f_sb_list_cpu;
#endif
#define FL_LEASE 32 /* lease held on this file */
#define FL_CLOSE 64 /* unlock on close */
#define FL_SLEEP 128 /* A blocking lock */
+#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */
+#define FL_UNLOCK_PENDING 512 /* Lease is being broken */
/*
* Special return value from posix_lock_file() and vfs_lock_file() for
struct list_head fl_link; /* doubly linked list of all locks */
struct list_head fl_block; /* circular list of blocked processes */
fl_owner_t fl_owner;
- unsigned char fl_flags;
+ unsigned int fl_flags;
unsigned char fl_type;
unsigned int fl_pid;
struct pid *fl_nspid;
loff_t fl_end;
struct fasync_struct * fl_fasync; /* for lease break notifications */
- unsigned long fl_break_time; /* for nonblocking lease breaks */
+ /* for lease breaks: */
+ unsigned long fl_break_time;
+ unsigned long fl_downgrade_time;
const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */
const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */
struct seq_file;
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
- unsigned long nr_segs, unsigned long fast_segs,
- struct iovec *fast_pointer,
- struct iovec **ret_pointer);
+ unsigned long nr_segs, unsigned long fast_segs,
+ struct iovec *fast_pointer,
+ struct iovec **ret_pointer,
+ int check_access);
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern struct inode * iget_locked(struct super_block *, unsigned long);
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
+#else
+static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
+#endif
extern void unlock_new_inode(struct inode *);
extern unsigned int get_next_ino(void);
extern loff_t noop_llseek(struct file *file, loff_t offset, int origin);
extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
-extern loff_t generic_file_llseek_unlocked(struct file *file, loff_t offset,
- int origin);
+extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
+ int origin, loff_t maxsize);
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);
.llseek = generic_file_llseek, \
};
-static inline void __attribute__((format(printf, 1, 2)))
-__simple_attr_check_format(const char *fmt, ...)
+static inline __printf(1, 2)
+void __simple_attr_check_format(const char *fmt, ...)
{
/* don't do anything, just let the compiler check the arguments; */
}