A large part of this code is from the generic VFS code in fs/ioctl.c in the upstream kernel. Index: linux-2.6.18-128.1.6/fs/ext4/ioctl.c =================================================================== --- linux-2.6.18-128.1.6.orig/fs/ext4/ioctl.c +++ linux-2.6.18-128.1.6/fs/ext4/ioctl.c @@ -17,6 +17,162 @@ #include "ext4_jbd2.h" #include "ext4.h" +#include "fiemap.h" + +/* So that the fiemap access checks can't overflow on 32 bit machines. */ +#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) + +/** + * 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 + * @lun: LUN on which this extent resides + * + * 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_DIRECT_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED \ + |FIEMAP_EXTENT_NET) +#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, dev_t dev) +{ + struct fiemap_extent extent = { 0 }; + 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_DIRECT_FLAGS) + flags |= FIEMAP_EXTENT_NO_DIRECT; + if (flags & SET_NOT_ALIGNED_FLAGS) + flags |= FIEMAP_EXTENT_NOT_ALIGNED; + if (flags & SET_NO_UNMOUNTED_IO_FLAGS) + flags |= FIEMAP_EXTENT_ENCODED; + + extent.fe_logical = logical; + extent.fe_physical = phys; + extent.fe_length = len; + extent.fe_flags = flags; + extent.fe_device = new_encode_dev(dev); + + 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; +} + +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; +} + +/* + * 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; +} + +int ioctl_fiemap(struct inode *inode, struct file *filp, unsigned long arg) +{ + struct fiemap fiemap; + u64 len; + struct fiemap_extent_info fieinfo = {0, }; + struct super_block *sb = inode->i_sb; + int error = 0; + + 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, (void *)arg, + offsetof(typeof(fiemap), fm_extents[fiemap.fm_extent_count]))) + return -EFAULT; + + if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC) + filemap_write_and_wait(inode->i_mapping); + + error = ext4_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; +} + long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = filp->f_dentry->d_inode; @@ -257,6 +413,10 @@ flags_err: case EXT4_IOC_MIGRATE: return ext4_ext_migrate(inode, filp, cmd, arg); + case EXT4_IOC_FIEMAP: { + return ioctl_fiemap(inode, filp, arg); + } + default: return -ENOTTY; } Index: linux-2.6.18-128.1.6/fs/ext4/ext4.h =================================================================== --- linux-2.6.18-128.1.6.orig/fs/ext4/ext4.h +++ linux-2.6.18-128.1.6/fs/ext4/ext4.h @@ -300,6 +300,7 @@ struct ext4_new_group_data { #define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) #define EXT4_IOC_GROUP_ADD _IOW('f', 8, struct ext4_new_group_input) #define EXT4_IOC_MIGRATE _IO('f', 9) +#define EXT4_IOC_FIEMAP _IOWR('f', 11, struct fiemap) /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */ /* @@ -317,6 +318,8 @@ struct ext4_new_group_data { #define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION #define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION +/* FIEMAP flags supported by ext4 */ +#define EXT4_FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC) /* * Mount options @@ -1117,6 +1120,9 @@ extern int ext4_page_mkwrite(struct vm_a /* ioctl.c */ extern long ext4_ioctl(struct file *, unsigned int, unsigned long); extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); +struct fiemap_extent_info; +extern int ext4_fiemap(struct inode *, struct fiemap_extent_info *, __u64, + __u64); /* migrate.c */ extern int ext4_ext_migrate(struct inode *, struct file *, unsigned int, Index: linux-2.6.18-128.1.6/fs/ext4/fiemap.h =================================================================== --- /dev/null +++ linux-2.6.18-128.1.6/fs/ext4/fiemap.h @@ -0,0 +1,85 @@ +/* + * FIEMAP ioctl infrastructure. + * + * Copyright 2008 Sun Microsystems, Inc + * + * Author: Kalpak Shah + * Andreas Dilger + */ + +#ifndef _LINUX_EXT4_FIEMAP_H +#define _LINUX_EXT4_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_device; /* device number for this extent */ + __u32 fe_reserved[2]; +}; + +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) */ +}; + +/* + * FIEMAP helper definition. + */ +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_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); +int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, + u64 phys, u64 len, u32 flags, u32 lun); + +#define FIEMAP_MAX_OFFSET (~0ULL) + +#define FIEMAP_FLAG_SYNC 0x00000001 /* sync file data before map */ +#define FIEMAP_FLAG_XATTR 0x00000002 /* map extended attribute tree */ + +/* ldiskfs only supports FLAG_SYNC flag currently */ +#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_DIRECT. */ +#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. */ + +/* Lustre specific flags - use a high bit, don't conflict with upstream flag */ +#define FIEMAP_EXTENT_NO_DIRECT 0x40000000 /* Data mapping undefined */ +#define FIEMAP_EXTENT_NET 0x80000000 /* Data stored remotely. + * Sets NO_DIRECT flag */ + +#endif /* _LINUX_EXT4_FIEMAP_H */ +