From 1f7c14c62ce63805f9574664a6c6de3633d4a354 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Thu, 9 Oct 2008 12:50:59 -0400 Subject: percpu counter: clean up percpu_counter_sum_and_set() percpu_counter_sum_and_set() and percpu_counter_sum() is the same except the former updates the global counter after accounting. Since we are taking the fbc->lock to calculate the precise value of the counter in percpu_counter_sum() anyway, it should simply set fbc->count too, as the percpu_counter_sum_and_set() does. This patch merges these two interfaces into one. Signed-off-by: Mingming Cao Acked-by: Peter Zijlstra Cc: Signed-off-by: Andrew Morton Signed-off-by: "Theodore Ts'o" --- include/linux/percpu_counter.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 20838883535..9007ccdfc11 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount); void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); -s64 __percpu_counter_sum(struct percpu_counter *fbc, int set); +s64 __percpu_counter_sum(struct percpu_counter *fbc); static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -44,19 +44,13 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { - s64 ret = __percpu_counter_sum(fbc, 0); + s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } -static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc) -{ - return __percpu_counter_sum(fbc, 1); -} - - static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { - return __percpu_counter_sum(fbc, 0); + return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) -- cgit v1.2.3-70-g09d2 From 05496769e5da83ce22ed97345afd9c7b71d6bd24 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 16 Sep 2008 14:36:17 -0400 Subject: jbd2: clean up how the journal device name is printed Calculate the journal device name once and stash it away in the journal_s structure. This avoids needing to call bdevname() everywhere and reduces stack usage by not needing to allocate an on-stack buffer. In addition, we eliminate the '/' that can appear in device names (e.g. "cciss/c0d0p9" --- see kernel bugzilla #11321) that can cause problems when creating proc directory names, and include the inode number to support ocfs2 which creates multiple journals with different inode numbers. Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 12 +++--------- fs/jbd2/commit.c | 11 +++-------- fs/jbd2/journal.c | 48 ++++++++++++++++-------------------------------- include/linux/jbd2.h | 3 ++- 4 files changed, 24 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f58cc0309dc..64e1c21eb5d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1476,15 +1476,9 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt); - if (EXT4_SB(sb)->s_journal->j_inode == NULL) { - char b[BDEVNAME_SIZE]; - - printk(KERN_INFO "EXT4 FS on %s, external journal on %s\n", - sb->s_id, bdevname(EXT4_SB(sb)->s_journal->j_dev, b)); - } else { - printk(KERN_INFO "EXT4 FS on %s, internal journal\n", - sb->s_id); - } + 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); return res; } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index f2ad061e95e..b091e5378fe 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -147,12 +147,9 @@ static int journal_submit_commit_record(journal_t *journal, * to remember if we sent a barrier request */ if (ret == -EOPNOTSUPP && barrier_done) { - char b[BDEVNAME_SIZE]; - printk(KERN_WARNING - "JBD: barrier-based sync failed on %s - " - "disabling barriers\n", - bdevname(journal->j_dev, b)); + "JBD: barrier-based 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); @@ -681,11 +678,9 @@ start_journal_io: */ err = journal_finish_inode_data_buffers(journal, commit_transaction); if (err) { - char b[BDEVNAME_SIZE]; - printk(KERN_WARNING "JBD2: Detected IO errors while flushing file data " - "on %s\n", bdevname(journal->j_fs_dev, b)); + "on %s\n", journal->j_devname); err = 0; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 8207a01c4ed..81186a29742 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -597,13 +597,9 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, if (ret) *retp = ret; else { - char b[BDEVNAME_SIZE]; - printk(KERN_ALERT "%s: journal block not found " "at offset %lu on %s\n", - __func__, - blocknr, - bdevname(journal->j_dev, b)); + __func__, blocknr, journal->j_devname); err = -EIO; __journal_abort_soft(journal, err); } @@ -901,10 +897,7 @@ static struct proc_dir_entry *proc_jbd2_stats; static void jbd2_stats_proc_init(journal_t *journal) { - char name[BDEVNAME_SIZE]; - - bdevname(journal->j_dev, name); - journal->j_proc_entry = proc_mkdir(name, proc_jbd2_stats); + journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); if (journal->j_proc_entry) { proc_create_data("history", S_IRUGO, journal->j_proc_entry, &jbd2_seq_history_fops, journal); @@ -915,12 +908,9 @@ static void jbd2_stats_proc_init(journal_t *journal) static void jbd2_stats_proc_exit(journal_t *journal) { - char name[BDEVNAME_SIZE]; - - bdevname(journal->j_dev, name); remove_proc_entry("info", journal->j_proc_entry); remove_proc_entry("history", journal->j_proc_entry); - remove_proc_entry(name, proc_jbd2_stats); + remove_proc_entry(journal->j_devname, proc_jbd2_stats); } static void journal_init_stats(journal_t *journal) @@ -1018,6 +1008,7 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, { journal_t *journal = journal_init_common(); struct buffer_head *bh; + char *p; int n; if (!journal) @@ -1039,6 +1030,10 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, journal->j_fs_dev = fs_dev; journal->j_blk_offset = start; journal->j_maxlen = len; + bdevname(journal->j_dev, journal->j_devname); + p = journal->j_devname; + while ((p = strchr(p, '/'))) + *p = '!'; jbd2_stats_proc_init(journal); bh = __getblk(journal->j_dev, start, journal->j_blocksize); @@ -1061,6 +1056,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode) { struct buffer_head *bh; journal_t *journal = journal_init_common(); + char *p; int err; int n; unsigned long long blocknr; @@ -1070,6 +1066,12 @@ journal_t * jbd2_journal_init_inode (struct inode *inode) journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev; journal->j_inode = inode; + bdevname(journal->j_dev, journal->j_devname); + p = journal->j_devname; + while ((p = strchr(p, '/'))) + *p = '!'; + p = journal->j_devname + strlen(journal->j_devname); + sprintf(p, ":%lu", journal->j_inode->i_ino); jbd_debug(1, "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n", journal, inode->i_sb->s_id, inode->i_ino, @@ -1760,23 +1762,6 @@ int jbd2_journal_wipe(journal_t *journal, int write) return err; } -/* - * journal_dev_name: format a character string to describe on what - * device this journal is present. - */ - -static const char *journal_dev_name(journal_t *journal, char *buffer) -{ - struct block_device *bdev; - - if (journal->j_inode) - bdev = journal->j_inode->i_sb->s_bdev; - else - bdev = journal->j_dev; - - return bdevname(bdev, buffer); -} - /* * Journal abort has very specific semantics, which we describe * for journal abort. @@ -1793,13 +1778,12 @@ static const char *journal_dev_name(journal_t *journal, char *buffer) void __jbd2_journal_abort_hard(journal_t *journal) { transaction_t *transaction; - char b[BDEVNAME_SIZE]; if (journal->j_flags & JBD2_ABORT) return; printk(KERN_ERR "Aborting journal on device %s.\n", - journal_dev_name(journal, b)); + journal->j_devname); spin_lock(&journal->j_state_lock); journal->j_flags |= JBD2_ABORT; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 3dd20900709..66c3499478b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -850,7 +850,8 @@ struct journal_s */ struct block_device *j_dev; int j_blocksize; - unsigned long long j_blk_offset; + unsigned long long j_blk_offset; + char j_devname[BDEVNAME_SIZE+24]; /* * Device which holds the client fs. For internal journal this will be -- cgit v1.2.3-70-g09d2 From c4b929b85bdb64afacbbf6453b1f2bf7e14c9e89 Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Wed, 8 Oct 2008 19:44:18 -0400 Subject: vfs: vfs-level fiemap interface Basic vfs-level fiemap infrastructure, which sets up a new ->fiemap inode operation. Userspace can get extent information on a file via fiemap ioctl. As input, the fiemap ioctl takes a struct fiemap which includes an array of struct fiemap_extent (fm_extents). Size of the extent array is passed as fm_extent_count and number of extents returned will be written into fm_mapped_extents. Offset and length fields on the fiemap structure (fm_start, fm_length) describe a logical range which will be searched for extents. All extents returned will at least partially contain this range. The actual extent offsets and ranges returned will be unmodified from their offset and range on-disk. The fiemap ioctl returns '0' on success. On error, -1 is returned and errno is set. If errno is equal to EBADR, then fm_flags will contain those flags which were passed in which the kernel did not understand. On all other errors, the contents of fm_extents is undefined. As fiemap evolved, there have been many authors of the vfs patch. As far as I can tell, the list includes: Kalpak Shah Andreas Dilger Eric Sandeen Mark Fasheh Signed-off-by: Mark Fasheh Signed-off-by: "Theodore Ts'o" Cc: Michael Kerrisk Cc: linux-api@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org --- Documentation/filesystems/fiemap.txt | 228 +++++++++++++++++++++++++++++++++++ fs/ioctl.c | 155 ++++++++++++++++++++++++ include/linux/fiemap.h | 64 ++++++++++ include/linux/fs.h | 18 +++ 4 files changed, 465 insertions(+) create mode 100644 Documentation/filesystems/fiemap.txt create mode 100644 include/linux/fiemap.h (limited to 'include') diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt new file mode 100644 index 00000000000..1e3defcfe50 --- /dev/null +++ b/Documentation/filesystems/fiemap.txt @@ -0,0 +1,228 @@ +============ +Fiemap Ioctl +============ + +The fiemap ioctl is an efficient method for userspace to get file +extent mappings. Instead of block-by-block mapping (such as bmap), fiemap +returns a list of extents. + + +Request Basics +-------------- + +A fiemap request is encoded within struct fiemap: + +struct fiemap { + __u64 fm_start; /* logical offset (inclusive) at + * which to start mapping (in) */ + __u64 fm_length; /* logical length of mapping which + * userspace cares about (in) */ + __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */ + __u32 fm_mapped_extents; /* number of extents that were + * mapped (out) */ + __u32 fm_extent_count; /* size of fm_extents array (in) */ + __u32 fm_reserved; + struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ +}; + + +fm_start, and fm_length specify the logical range within the file +which the process would like mappings for. Extents returned mirror +those on disk - that is, the logical offset of the 1st returned extent +may start before fm_start, and the range covered by the last returned +extent may end after fm_length. All offsets and lengths are in bytes. + +Certain flags to modify the way in which mappings are looked up can be +set in fm_flags. If the kernel doesn't understand some particular +flags, it will return EBADR and the contents of fm_flags will contain +the set of flags which caused the error. If the kernel is compatible +with all flags passed, the contents of fm_flags will be unmodified. +It is up to userspace to determine whether rejection of a particular +flag is fatal to it's operation. This scheme is intended to allow the +fiemap interface to grow in the future but without losing +compatibility with old software. + +fm_extent_count specifies the number of elements in the fm_extents[] array +that can be used to return extents. If fm_extent_count is zero, then the +fm_extents[] array is ignored (no extents will be returned), and the +fm_mapped_extents count will hold the number of extents needed in +fm_extents[] to hold the file's current mapping. Note that there is +nothing to prevent the file from changing between calls to FIEMAP. + +The following flags can be set in fm_flags: + +* FIEMAP_FLAG_SYNC +If this flag is set, the kernel will sync the file before mapping extents. + +* FIEMAP_FLAG_XATTR +If this flag is set, the extents returned will describe the inodes +extended attribute lookup tree, instead of it's data tree. + + +Extent Mapping +-------------- + +Extent information is returned within the embedded fm_extents array +which userspace must allocate along with the fiemap structure. The +number of elements in the fiemap_extents[] array should be passed via +fm_extent_count. The number of extents mapped by kernel will be +returned via fm_mapped_extents. If the number of fiemap_extents +allocated is less than would be required to map the requested range, +the maximum number of extents that can be mapped in the fm_extent[] +array will be returned and fm_mapped_extents will be equal to +fm_extent_count. In that case, the last extent in the array will not +complete the requested range and will not have the FIEMAP_EXTENT_LAST +flag set (see the next section on extent flags). + +Each extent is described by a single fiemap_extent structure as +returned in fm_extents. + +struct fiemap_extent { + __u64 fe_logical; /* logical offset in bytes for the start of + * the extent */ + __u64 fe_physical; /* physical offset in bytes for the start + * of the extent */ + __u64 fe_length; /* length in bytes for the extent */ + __u64 fe_reserved64[2]; + __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */ + __u32 fe_reserved[3]; +}; + +All offsets and lengths are in bytes and mirror those on disk. It is valid +for an extents logical offset to start before the request or it's logical +length to extend past the request. Unless FIEMAP_EXTENT_NOT_ALIGNED is +returned, fe_logical, fe_physical, and fe_length will be aligned to the +block size of the file system. With the exception of extents flagged as +FIEMAP_EXTENT_MERGED, adjacent extents will not be merged. + +The fe_flags field contains flags which describe the extent returned. +A special flag, FIEMAP_EXTENT_LAST is always set on the last extent in +the file so that the process making fiemap calls can determine when no +more extents are available, without having to call the ioctl again. + +Some flags are intentionally vague and will always be set in the +presence of other more specific flags. This way a program looking for +a general property does not have to know all existing and future flags +which imply that property. + +For example, if FIEMAP_EXTENT_DATA_INLINE or FIEMAP_EXTENT_DATA_TAIL +are set, FIEMAP_EXTENT_NOT_ALIGNED will also be set. A program looking +for inline or tail-packed data can key on the specific flag. Software +which simply cares not to try operating on non-aligned extents +however, can just key on FIEMAP_EXTENT_NOT_ALIGNED, and not have to +worry about all present and future flags which might imply unaligned +data. Note that the opposite is not true - it would be valid for +FIEMAP_EXTENT_NOT_ALIGNED to appear alone. + +* FIEMAP_EXTENT_LAST +This is the last extent in the file. A mapping attempt past this +extent will return nothing. + +* FIEMAP_EXTENT_UNKNOWN +The location of this extent is currently unknown. This may indicate +the data is stored on an inaccessible volume or that no storage has +been allocated for the file yet. + +* FIEMAP_EXTENT_DELALLOC + - This will also set FIEMAP_EXTENT_UNKNOWN. +Delayed allocation - while there is data for this extent, it's +physical location has not been allocated yet. + +* FIEMAP_EXTENT_ENCODED +This extent does not consist of plain filesystem blocks but is +encoded (e.g. encrypted or compressed). Reading the data in this +extent via I/O to the block device will have undefined results. + +Note that it is *always* undefined to try to update the data +in-place by writing to the indicated location without the +assistance of the filesystem, or to access the data using the +information returned by the FIEMAP interface while the filesystem +is mounted. In other words, user applications may only read the +extent data via I/O to the block device while the filesystem is +unmounted, and then only if the FIEMAP_EXTENT_ENCODED flag is +clear; user applications must not try reading or writing to the +filesystem via the block device under any other circumstances. + +* FIEMAP_EXTENT_DATA_ENCRYPTED + - This will also set FIEMAP_EXTENT_ENCODED +The data in this extent has been encrypted by the file system. + +* FIEMAP_EXTENT_NOT_ALIGNED +Extent offsets and length are not guaranteed to be block aligned. + +* FIEMAP_EXTENT_DATA_INLINE + This will also set FIEMAP_EXTENT_NOT_ALIGNED +Data is located within a meta data block. + +* FIEMAP_EXTENT_DATA_TAIL + This will also set FIEMAP_EXTENT_NOT_ALIGNED +Data is packed into a block with data from other files. + +* FIEMAP_EXTENT_UNWRITTEN +Unwritten extent - the extent is allocated but it's data has not been +initialized. This indicates the extent's data will be all zero if read +through the filesystem but the contents are undefined if read directly from +the device. + +* FIEMAP_EXTENT_MERGED +This will be set when a file does not support extents, i.e., it uses a block +based addressing scheme. Since returning an extent for each block back to +userspace would be highly inefficient, the kernel will try to merge most +adjacent blocks into 'extents'. + + +VFS -> File System Implementation +--------------------------------- + +File systems wishing to support fiemap must implement a ->fiemap callback on +their inode_operations structure. The fs ->fiemap call is responsible for +defining it's set of supported fiemap flags, and calling a helper function on +each discovered extent: + +struct inode_operations { + ... + + int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, + u64 len); + +->fiemap is passed struct fiemap_extent_info which describes the +fiemap request: + +struct fiemap_extent_info { + unsigned int fi_flags; /* Flags as passed from user */ + unsigned int fi_extents_mapped; /* Number of mapped extents */ + unsigned int fi_extents_max; /* Size of fiemap_extent array */ + struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */ +}; + +It is intended that the file system should not need to access any of this +structure directly. + + +Flag checking should be done at the beginning of the ->fiemap callback via the +fiemap_check_flags() helper: + +int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); + +The struct fieinfo should be passed in as recieved from ioctl_fiemap(). The +set of fiemap flags which the fs understands should be passed via fs_flags. If +fiemap_check_flags finds invalid user flags, it will place the bad values in +fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from +fiemap_check_flags(), it should immediately exit, returning that error back to +ioctl_fiemap(). + + +For each extent in the request range, the file system should call +the helper function, fiemap_fill_next_extent(): + +int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, + u64 phys, u64 len, u32 flags, u32 dev); + +fiemap_fill_next_extent() will use the passed values to populate the +next free extent in the fm_extents array. 'General' extent flags will +automatically be set from specific flags on behalf of the calling file +system so that the userspace API is not broken. + +fiemap_fill_next_extent() returns 0 on success, and 1 when the +user-supplied fm_extents array is full. If an error is encountered +while copying the extent to user memory, -EFAULT will be returned. diff --git a/fs/ioctl.c b/fs/ioctl.c index 7db32b3382d..045d9601fbb 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -16,6 +16,9 @@ #include +/* So that the fiemap access checks can't overflow on 32 bit machines. */ +#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) + /** * vfs_ioctl - call filesystem specific ioctl methods * @filp: open file to invoke ioctl method on @@ -71,6 +74,156 @@ static int ioctl_fibmap(struct file *filp, int __user *p) return put_user(res, p); } +/** + * fiemap_fill_next_extent - Fiemap helper function + * @fieinfo: Fiemap context passed into ->fiemap + * @logical: Extent logical start offset, in bytes + * @phys: Extent physical start offset, in bytes + * @len: Extent length, in bytes + * @flags: FIEMAP_EXTENT flags that describe this extent + * + * Called from file system ->fiemap callback. Will populate extent + * info as passed in via arguments and copy to user memory. On + * success, extent count on fieinfo is incremented. + * + * Returns 0 on success, -errno on error, 1 if this was the last + * extent that will fit in user array. + */ +#define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC) +#define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED) +#define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE) +int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, + u64 phys, u64 len, u32 flags) +{ + struct fiemap_extent extent; + struct fiemap_extent *dest = fieinfo->fi_extents_start; + + /* only count the extents */ + if (fieinfo->fi_extents_max == 0) { + fieinfo->fi_extents_mapped++; + return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; + } + + if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) + return 1; + + if (flags & SET_UNKNOWN_FLAGS) + flags |= FIEMAP_EXTENT_UNKNOWN; + if (flags & SET_NO_UNMOUNTED_IO_FLAGS) + flags |= FIEMAP_EXTENT_ENCODED; + if (flags & SET_NOT_ALIGNED_FLAGS) + flags |= FIEMAP_EXTENT_NOT_ALIGNED; + + memset(&extent, 0, sizeof(extent)); + extent.fe_logical = logical; + extent.fe_physical = phys; + extent.fe_length = len; + extent.fe_flags = flags; + + dest += fieinfo->fi_extents_mapped; + if (copy_to_user(dest, &extent, sizeof(extent))) + return -EFAULT; + + fieinfo->fi_extents_mapped++; + if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) + return 1; + return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; +} +EXPORT_SYMBOL(fiemap_fill_next_extent); + +/** + * fiemap_check_flags - check validity of requested flags for fiemap + * @fieinfo: Fiemap context passed into ->fiemap + * @fs_flags: Set of fiemap flags that the file system understands + * + * Called from file system ->fiemap callback. This will compute the + * intersection of valid fiemap flags and those that the fs supports. That + * value is then compared against the user supplied flags. In case of bad user + * flags, the invalid values will be written into the fieinfo structure, and + * -EBADR is returned, which tells ioctl_fiemap() to return those values to + * userspace. For this reason, a return code of -EBADR should be preserved. + * + * Returns 0 on success, -EBADR on bad flags. + */ +int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags) +{ + u32 incompat_flags; + + incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags); + if (incompat_flags) { + fieinfo->fi_flags = incompat_flags; + return -EBADR; + } + return 0; +} +EXPORT_SYMBOL(fiemap_check_flags); + +static int fiemap_check_ranges(struct super_block *sb, + u64 start, u64 len, u64 *new_len) +{ + *new_len = len; + + if (len == 0) + return -EINVAL; + + if (start > sb->s_maxbytes) + return -EFBIG; + + /* + * Shrink request scope to what the fs can actually handle. + */ + if ((len > sb->s_maxbytes) || + (sb->s_maxbytes - len) < start) + *new_len = sb->s_maxbytes - start; + + return 0; +} + +static int ioctl_fiemap(struct file *filp, unsigned long arg) +{ + struct fiemap fiemap; + struct fiemap_extent_info fieinfo = { 0, }; + struct inode *inode = filp->f_path.dentry->d_inode; + struct super_block *sb = inode->i_sb; + u64 len; + int error; + + if (!inode->i_op->fiemap) + return -EOPNOTSUPP; + + if (copy_from_user(&fiemap, (struct fiemap __user *)arg, + sizeof(struct fiemap))) + return -EFAULT; + + if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) + return -EINVAL; + + error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length, + &len); + if (error) + return error; + + fieinfo.fi_flags = fiemap.fm_flags; + fieinfo.fi_extents_max = fiemap.fm_extent_count; + fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap)); + + if (fiemap.fm_extent_count != 0 && + !access_ok(VERIFY_WRITE, fieinfo.fi_extents_start, + fieinfo.fi_extents_max * sizeof(struct fiemap_extent))) + return -EFAULT; + + if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC) + filemap_write_and_wait(inode->i_mapping); + + error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len); + fiemap.fm_flags = fieinfo.fi_flags; + fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; + if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap))) + error = -EFAULT; + + return error; +} + static int file_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { @@ -80,6 +233,8 @@ static int file_ioctl(struct file *filp, unsigned int cmd, switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); + case FS_IOC_FIEMAP: + return ioctl_fiemap(filp, arg); case FIGETBSZ: return put_user(inode->i_sb->s_blocksize, p); case FIONREAD: diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h new file mode 100644 index 00000000000..671decbd2ae --- /dev/null +++ b/include/linux/fiemap.h @@ -0,0 +1,64 @@ +/* + * FS_IOC_FIEMAP ioctl infrastructure. + * + * Some portions copyright (C) 2007 Cluster File Systems, Inc + * + * Authors: Mark Fasheh + * Kalpak Shah + * Andreas Dilger + */ + +#ifndef _LINUX_FIEMAP_H +#define _LINUX_FIEMAP_H + +struct fiemap_extent { + __u64 fe_logical; /* logical offset in bytes for the start of + * the extent from the beginning of the file */ + __u64 fe_physical; /* physical offset in bytes for the start + * of the extent from the beginning of the disk */ + __u64 fe_length; /* length in bytes for this extent */ + __u64 fe_reserved64[2]; + __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */ + __u32 fe_reserved[3]; +}; + +struct fiemap { + __u64 fm_start; /* logical offset (inclusive) at + * which to start mapping (in) */ + __u64 fm_length; /* logical length of mapping which + * userspace wants (in) */ + __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */ + __u32 fm_mapped_extents;/* number of extents that were mapped (out) */ + __u32 fm_extent_count; /* size of fm_extents array (in) */ + __u32 fm_reserved; + struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ +}; + +#define FIEMAP_MAX_OFFSET (~0ULL) + +#define FIEMAP_FLAG_SYNC 0x00000001 /* sync file data before map */ +#define FIEMAP_FLAG_XATTR 0x00000002 /* map extended attribute tree */ + +#define FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR) + +#define FIEMAP_EXTENT_LAST 0x00000001 /* Last extent in file. */ +#define FIEMAP_EXTENT_UNKNOWN 0x00000002 /* Data location unknown. */ +#define FIEMAP_EXTENT_DELALLOC 0x00000004 /* Location still pending. + * Sets EXTENT_UNKNOWN. */ +#define FIEMAP_EXTENT_ENCODED 0x00000008 /* Data can not be read + * while fs is unmounted */ +#define FIEMAP_EXTENT_DATA_ENCRYPTED 0x00000080 /* Data is encrypted by fs. + * Sets EXTENT_NO_BYPASS. */ +#define FIEMAP_EXTENT_NOT_ALIGNED 0x00000100 /* Extent offsets may not be + * block aligned. */ +#define FIEMAP_EXTENT_DATA_INLINE 0x00000200 /* Data mixed with metadata. + * Sets EXTENT_NOT_ALIGNED.*/ +#define FIEMAP_EXTENT_DATA_TAIL 0x00000400 /* Multiple files in block. + * Sets EXTENT_NOT_ALIGNED.*/ +#define FIEMAP_EXTENT_UNWRITTEN 0x00000800 /* Space allocated, but + * no data (i.e. zero). */ +#define FIEMAP_EXTENT_MERGED 0x00001000 /* File does not natively + * support extents. Result + * merged for efficiency. */ + +#endif /* _LINUX_FIEMAP_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 580b513668f..194fb237a30 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -231,6 +231,7 @@ extern int dir_notify_enable; #define FS_IOC_SETFLAGS _IOW('f', 2, long) #define FS_IOC_GETVERSION _IOR('v', 1, long) #define FS_IOC_SETVERSION _IOW('v', 2, long) +#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap) #define FS_IOC32_GETFLAGS _IOR('f', 1, int) #define FS_IOC32_SETFLAGS _IOW('f', 2, int) #define FS_IOC32_GETVERSION _IOR('v', 1, int) @@ -291,6 +292,7 @@ extern int dir_notify_enable; #include #include #include +#include #include #include @@ -1178,6 +1180,20 @@ extern void dentry_unhash(struct dentry *dentry); */ extern int file_permission(struct file *, int); +/* + * VFS FS_IOC_FIEMAP helper definitions. + */ +struct fiemap_extent_info { + unsigned int fi_flags; /* Flags as passed from user */ + unsigned int fi_extents_mapped; /* Number of mapped extents */ + unsigned int fi_extents_max; /* Size of fiemap_extent array */ + struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent + * array */ +}; +int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, + u64 phys, u64 len, u32 flags); +int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); + /* * File types * @@ -1287,6 +1303,8 @@ struct inode_operations { void (*truncate_range)(struct inode *, loff_t, loff_t); long (*fallocate)(struct inode *inode, int mode, loff_t offset, loff_t len); + int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, + u64 len); }; struct seq_file; -- cgit v1.2.3-70-g09d2 From 68c9d702bb72f367f3b148963ec6cf5e07ff7f65 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 3 Oct 2008 17:32:43 -0400 Subject: generic block based fiemap implementation Any block based fs (this patch includes ext3) just has to declare its own fiemap() function and then call this generic function with its own get_block_t. This works well for block based filesystems that will map multiple contiguous blocks at one time, but will work for filesystems that only map one block at a time, you will just end up with an "extent" for each block. One gotcha is this will not play nicely where there is hole+data after the EOF. This function will assume its hit the end of the data as soon as it hits a hole after the EOF, so if there is any data past that it will not pick that up. AFAIK no block based fs does this anyway, but its in the comments of the function anyway just in case. Signed-off-by: Josef Bacik Signed-off-by: Mark Fasheh Signed-off-by: "Theodore Ts'o" Cc: linux-fsdevel@vger.kernel.org --- fs/ext2/ext2.h | 2 + fs/ext2/file.c | 1 + fs/ext2/inode.c | 8 ++++ fs/ext3/file.c | 1 + fs/ext3/inode.c | 8 ++++ fs/ioctl.c | 118 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/ext3_fs.h | 2 + include/linux/fs.h | 3 ++ 8 files changed, 143 insertions(+) (limited to 'include') diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 47d88da2d33..bae998c1e44 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *); extern int ext2_setattr (struct dentry *, struct iattr *); extern void ext2_set_inode_flags(struct inode *inode); extern void ext2_get_inode_flags(struct ext2_inode_info *); +extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len); int __ext2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 5f2fa9c3629..45ed0712218 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = { #endif .setattr = ext2_setattr, .permission = ext2_permission, + .fiemap = ext2_fiemap, }; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 991d6dfeb51..7658b33e265 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "ext2.h" #include "acl.h" #include "xip.h" @@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_ } +int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + return generic_block_fiemap(inode, fieinfo, start, len, + ext2_get_block); +} + static int ext2_writepage(struct page *page, struct writeback_control *wbc) { return block_write_full_page(page, ext2_get_block, wbc); diff --git a/fs/ext3/file.c b/fs/ext3/file.c index acc4913d301..3be1e0689c9 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = { .removexattr = generic_removexattr, #endif .permission = ext3_permission, + .fiemap = ext3_fiemap, }; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 507d8689b11..ebfec4d0148 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "xattr.h" #include "acl.h" @@ -981,6 +982,13 @@ out: return ret; } +int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + return generic_block_fiemap(inode, fieinfo, start, len, + ext3_get_block); +} + /* * `handle' can be NULL if create is zero */ diff --git a/fs/ioctl.c b/fs/ioctl.c index 045d9601fbb..33a6b7ecb8b 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -13,6 +13,8 @@ #include #include #include +#include +#include #include @@ -224,6 +226,122 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg) return error; } +#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits) +#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits); + +/* + * @inode - the inode to map + * @arg - the pointer to userspace where we copy everything to + * @get_block - the fs's get_block function + * + * This does FIEMAP for block based inodes. Basically it will just loop + * through get_block until we hit the number of extents we want to map, or we + * go past the end of the file and hit a hole. + * + * If it is possible to have data blocks beyond a hole past @inode->i_size, then + * please do not use this function, it will stop at the first unmapped block + * beyond i_size + */ +int generic_block_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, u64 start, + u64 len, get_block_t *get_block) +{ + struct buffer_head tmp; + unsigned int start_blk; + long long length = 0, map_len = 0; + u64 logical = 0, phys = 0, size = 0; + u32 flags = FIEMAP_EXTENT_MERGED; + int ret = 0; + + if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC))) + return ret; + + start_blk = logical_to_blk(inode, start); + + /* guard against change */ + mutex_lock(&inode->i_mutex); + + length = (long long)min_t(u64, len, i_size_read(inode)); + map_len = length; + + do { + /* + * we set b_size to the total size we want so it will map as + * many contiguous blocks as possible at once + */ + memset(&tmp, 0, sizeof(struct buffer_head)); + tmp.b_size = map_len; + + ret = get_block(inode, start_blk, &tmp, 0); + if (ret) + break; + + /* HOLE */ + if (!buffer_mapped(&tmp)) { + /* + * first hole after going past the EOF, this is our + * last extent + */ + if (length <= 0) { + flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST; + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, + flags); + break; + } + + length -= blk_to_logical(inode, 1); + + /* if we have holes up to/past EOF then we're done */ + if (length <= 0) + break; + + start_blk++; + } else { + if (length <= 0 && size) { + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, + flags); + if (ret) + break; + } + + logical = blk_to_logical(inode, start_blk); + phys = blk_to_logical(inode, tmp.b_blocknr); + size = tmp.b_size; + flags = FIEMAP_EXTENT_MERGED; + + length -= tmp.b_size; + start_blk += logical_to_blk(inode, size); + + /* + * if we are past the EOF we need to loop again to see + * if there is a hole so we can mark this extent as the + * last one, and if not keep mapping things until we + * find a hole, or we run out of slots in the extent + * array + */ + if (length <= 0) + continue; + + ret = fiemap_fill_next_extent(fieinfo, logical, phys, + size, flags); + if (ret) + break; + } + cond_resched(); + } while (1); + + mutex_unlock(&inode->i_mutex); + + /* if ret is 1 then we just hit the end of the extent array */ + if (ret == 1) + ret = 0; + + return ret; +} +EXPORT_SYMBOL(generic_block_fiemap); + static int file_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 80171ee89a2..8120fa1bc23 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -837,6 +837,8 @@ extern void ext3_truncate (struct inode *); extern void ext3_set_inode_flags(struct inode *); extern void ext3_get_inode_flags(struct ext3_inode_info *); extern void ext3_set_aops(struct inode *inode); +extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len); /* ioctl.c */ extern int ext3_ioctl (struct inode *, struct file *, unsigned int, diff --git a/include/linux/fs.h b/include/linux/fs.h index 194fb237a30..385c9a197df 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1998,6 +1998,9 @@ extern int vfs_fstat(unsigned int, struct kstat *); extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg); +extern int generic_block_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, u64 start, + u64 len, get_block_t *get_block); extern void get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); -- cgit v1.2.3-70-g09d2