diff options
Diffstat (limited to 'fs/ext4')
| -rw-r--r-- | fs/ext4/ext4.h | 24 | ||||
| -rw-r--r-- | fs/ext4/file.c | 50 | ||||
| -rw-r--r-- | fs/ext4/indirect.c | 123 | ||||
| -rw-r--r-- | fs/ext4/inode.c | 166 | ||||
| -rw-r--r-- | fs/ext4/namei.c | 10 | ||||
| -rw-r--r-- | fs/ext4/super.c | 124 |
6 files changed, 359 insertions, 138 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index a75fba67bb1f..f63c3d5805c4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -364,7 +364,8 @@ struct flex_groups { #define EXT4_DIRTY_FL 0x00000100 #define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ #define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */ -#define EXT4_ECOMPR_FL 0x00000800 /* Compression error */ + /* nb: was previously EXT2_ECOMPR_FL */ +#define EXT4_ENCRYPT_FL 0x00000800 /* encrypted file */ /* End compression flags --- maybe not all used */ #define EXT4_INDEX_FL 0x00001000 /* hash-indexed directory */ #define EXT4_IMAGIC_FL 0x00002000 /* AFS directory */ @@ -421,7 +422,7 @@ enum { EXT4_INODE_DIRTY = 8, EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */ EXT4_INODE_NOCOMPR = 10, /* Don't compress */ - EXT4_INODE_ECOMPR = 11, /* Compression error */ + EXT4_INODE_ENCRYPT = 11, /* Compression error */ /* End compression flags --- maybe not all used */ EXT4_INODE_INDEX = 12, /* hash-indexed directory */ EXT4_INODE_IMAGIC = 13, /* AFS directory */ @@ -466,7 +467,7 @@ static inline void ext4_check_flag_values(void) CHECK_FLAG_VALUE(DIRTY); CHECK_FLAG_VALUE(COMPRBLK); CHECK_FLAG_VALUE(NOCOMPR); - CHECK_FLAG_VALUE(ECOMPR); + CHECK_FLAG_VALUE(ENCRYPT); CHECK_FLAG_VALUE(INDEX); CHECK_FLAG_VALUE(IMAGIC); CHECK_FLAG_VALUE(JOURNAL_DATA); @@ -965,6 +966,11 @@ struct ext4_inode_info { #define EXT4_MOUNT_ERRORS_MASK 0x00070 #define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ #define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ +#ifdef CONFIG_FS_DAX +#define EXT4_MOUNT_DAX 0x00200 /* Direct Access */ +#else +#define EXT4_MOUNT_DAX 0 +#endif #define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ #define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ #define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ @@ -1043,6 +1049,12 @@ extern void ext4_set_bits(void *bm, int cur, int len); /* Metadata checksum algorithm codes */ #define EXT4_CRC32C_CHKSUM 1 +/* Encryption algorithms */ +#define EXT4_ENCRYPTION_MODE_INVALID 0 +#define EXT4_ENCRYPTION_MODE_AES_256_XTS 1 +#define EXT4_ENCRYPTION_MODE_AES_256_GCM 2 +#define EXT4_ENCRYPTION_MODE_AES_256_CBC 3 + /* * Structure of the super block */ @@ -1156,7 +1168,8 @@ struct ext4_super_block { __le32 s_grp_quota_inum; /* inode for tracking group quota */ __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */ __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */ - __le32 s_reserved[106]; /* Padding to the end of the block */ + __u8 s_encrypt_algos[4]; /* Encryption algorithms in use */ + __le32 s_reserved[105]; /* Padding to the end of the block */ __le32 s_checksum; /* crc32c(superblock) */ }; @@ -1522,6 +1535,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) * GDT_CSUM bits are mutually exclusive. */ #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400 +#define EXT4_FEATURE_RO_COMPAT_READONLY 0x1000 #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 @@ -1537,6 +1551,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM 0x2000 /* use crc32c for bg */ #define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */ #define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */ +#define EXT4_FEATURE_INCOMPAT_ENCRYPT 0x10000 #define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR #define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ @@ -2578,6 +2593,7 @@ extern const struct file_operations ext4_dir_operations; /* file.c */ extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; +extern const struct file_operations ext4_dax_file_operations; extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); /* inline.c */ diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8131be8c0af3..33a09da16c9c 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -95,7 +95,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(iocb->ki_filp); struct mutex *aio_mutex = NULL; struct blk_plug plug; - int o_direct = file->f_flags & O_DIRECT; + int o_direct = io_is_direct(file); int overwrite = 0; size_t length = iov_iter_count(from); ssize_t ret; @@ -191,17 +191,41 @@ errout: return ret; } +#ifdef CONFIG_FS_DAX +static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + return dax_fault(vma, vmf, ext4_get_block); + /* Is this the right get_block? */ +} + +static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + return dax_mkwrite(vma, vmf, ext4_get_block); +} + +static const struct vm_operations_struct ext4_dax_vm_ops = { + .fault = ext4_dax_fault, + .page_mkwrite = ext4_dax_mkwrite, +}; +#else +#define ext4_dax_vm_ops ext4_file_vm_ops +#endif + static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); - vma->vm_ops = &ext4_file_vm_ops; + if (IS_DAX(file_inode(file))) { + vma->vm_ops = &ext4_dax_vm_ops; + vma->vm_flags |= VM_MIXEDMAP; + } else { + vma->vm_ops = &ext4_file_vm_ops; + } return 0; } @@ -600,6 +624,26 @@ const struct file_operations ext4_file_operations = { .fallocate = ext4_fallocate, }; +#ifdef CONFIG_FS_DAX +const struct file_operations ext4_dax_file_operations = { + .llseek = ext4_llseek, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = ext4_file_write_iter, + .unlocked_ioctl = ext4_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ext4_compat_ioctl, +#endif + .mmap = ext4_file_mmap, + .open = ext4_file_open, + .release = ext4_release_file, + .fsync = ext4_sync_file, + /* Splice not yet supported with DAX */ + .fallocate = ext4_fallocate, +}; +#endif + const struct inode_operations ext4_file_inode_operations = { .setattr = ext4_setattr, .getattr = ext4_getattr, diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 36b369697a13..45fe924f82bc 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -689,14 +689,22 @@ retry: inode_dio_done(inode); goto locked; } - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iter, offset, - ext4_get_block, NULL, NULL, 0); + if (IS_DAX(inode)) + ret = dax_do_io(rw, iocb, inode, iter, offset, + ext4_get_block, NULL, 0); + else + ret = __blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iter, offset, + ext4_get_block, NULL, NULL, 0); inode_dio_done(inode); } else { locked: - ret = blockdev_direct_IO(rw, iocb, inode, iter, - offset, ext4_get_block); + if (IS_DAX(inode)) + ret = dax_do_io(rw, iocb, inode, iter, offset, + ext4_get_block, NULL, DIO_LOCKING); + else + ret = blockdev_direct_IO(rw, iocb, inode, iter, + offset, ext4_get_block); if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); @@ -1393,10 +1401,7 @@ end_range: * to free. Everything was covered by the start * of the range. */ - return 0; - } else { - /* Shared branch grows from an indirect block */ - partial2--; + goto do_indirects; } } else { /* @@ -1427,56 +1432,96 @@ end_range: /* Punch happened within the same level (n == n2) */ partial = ext4_find_shared(inode, n, offsets, chain, &nr); partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); - /* - * ext4_find_shared returns Indirect structure which - * points to the last element which should not be - * removed by truncate. But this is end of the range - * in punch_hole so we need to point to the next element - */ - partial2->p++; - while ((partial > chain) || (partial2 > chain2)) { - /* We're at the same block, so we're almost finished */ - if ((partial->bh && partial2->bh) && - (partial->bh->b_blocknr == partial2->bh->b_blocknr)) { - if ((partial > chain) && (partial2 > chain2)) { + + /* Free top, but only if partial2 isn't its subtree. */ + if (nr) { + int level = min(partial - chain, partial2 - chain2); + int i; + int subtree = 1; + + for (i = 0; i <= level; i++) { + if (offsets[i] != offsets2[i]) { + subtree = 0; + break; + } + } + + if (!subtree) { + if (partial == chain) { + /* Shared branch grows from the inode */ + ext4_free_branches(handle, inode, NULL, + &nr, &nr+1, + (chain+n-1) - partial); + *partial->p = 0; + } else { + /* Shared branch grows from an indirect block */ + BUFFER_TRACE(partial->bh, "get_write_access"); ext4_free_branches(handle, inode, partial->bh, - partial->p + 1, - partial2->p, + partial->p, + partial->p+1, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); } - return 0; } + } + + if (!nr2) { /* - * Clear the ends of indirect blocks on the shared branch - * at the start of the range + * ext4_find_shared returns Indirect structure which + * points to the last element which should not be + * removed by truncate. But this is end of the range + * in punch_hole so we need to point to the next element */ - if (partial > chain) { + partial2->p++; + } + + while (partial > chain || partial2 > chain2) { + int depth = (chain+n-1) - partial; + int depth2 = (chain2+n2-1) - partial2; + + if (partial > chain && partial2 > chain2 && + partial->bh->b_blocknr == partial2->bh->b_blocknr) { + /* + * We've converged on the same block. Clear the range, + * then we're done. + */ ext4_free_branches(handle, inode, partial->bh, - partial->p + 1, - (__le32 *)partial->bh->b_data+addr_per_block, - (chain+n-1) - partial); + partial->p + 1, + partial2->p, + (chain+n-1) - partial); BUFFER_TRACE(partial->bh, "call brelse"); brelse(partial->bh); - partial--; + BUFFER_TRACE(partial2->bh, "call brelse"); + brelse(partial2->bh); + return 0; } + /* - * Clear the ends of indirect blocks on the shared branch - * at the end of the range + * The start and end partial branches may not be at the same + * level even though the punch happened within one level. So, we + * give them a chance to arrive at the same level, then walk + * them in step with each other until we converge on the same + * block. */ - if (partial2 > chain2) { + if (partial > chain && depth <= depth2) { + ext4_free_branches(handle, inode, partial->bh, + partial->p + 1, + (__le32 *)partial->bh->b_data+addr_per_block, + (chain+n-1) - partial); + BUFFER_TRACE(partial->bh, "call brelse"); + brelse(partial->bh); + partial--; + } + if (partial2 > chain2 && depth2 <= depth) { ext4_free_branches(handle, inode, partial2->bh, (__le32 *)partial2->bh->b_data, partial2->p, - (chain2+n-1) - partial2); + (chain2+n2-1) - partial2); BUFFER_TRACE(partial2->bh, "call brelse"); brelse(partial2->bh); partial2--; } } + return 0; do_indirects: /* Kill the remaining (whole) subtrees */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5653fa42930b..5cb9a212b86f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -657,6 +657,18 @@ has_zeroout: return retval; } +static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate) +{ + struct inode *inode = bh->b_assoc_map->host; + /* XXX: breaks on 32-bit > 16GB. Is that even supported? */ + loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits; + int err; + if (!uptodate) + return; + WARN_ON(!buffer_unwritten(bh)); + err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size); +} + /* Maximum number of blocks we map for direct IO at once. */ #define DIO_MAX_BLOCKS 4096 @@ -694,6 +706,11 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) { + bh->b_assoc_map = inode->i_mapping; + bh->b_private = (void *)(unsigned long)iblock; + bh->b_end_io = ext4_end_io_unwritten; + } if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN) set_buffer_defer_completion(bh); bh->b_size = inode->i_sb->s_blocksize * map.m_len; @@ -1007,6 +1024,7 @@ static int ext4_write_end(struct file *file, { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; @@ -1037,6 +1055,8 @@ static int ext4_write_end(struct file *file, unlock_page(page); page_cache_release(page); + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock @@ -1078,6 +1098,7 @@ static int ext4_journalled_write_end(struct file *file, { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; int ret = 0, ret2; int partial = 0; unsigned from, to; @@ -1110,6 +1131,9 @@ static int ext4_journalled_write_end(struct file *file, unlock_page(page); page_cache_release(page); + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); + if (size_changed) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) @@ -3010,13 +3034,14 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; } - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iter, - offset, - get_block_func, - ext4_end_io_dio, - NULL, - dio_flags); + if (IS_DAX(inode)) + ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func, + ext4_end_io_dio, dio_flags); + else + ret = __blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iter, offset, + get_block_func, + ext4_end_io_dio, NULL, dio_flags); /* * Put our reference to io_end. This can free the io_end structure e.g. @@ -3180,19 +3205,12 @@ void ext4_set_aops(struct inode *inode) inode->i_mapping->a_ops = &ext4_aops; } -/* - * ext4_block_zero_page_range() zeros out a mapping of length 'length' - * starting from file offset 'from'. The range to be zero'd must - * be contained with in one block. If the specified range exceeds - * the end of the block it will be shortened to end of the block - * that cooresponds to 'from' - */ -static int ext4_block_zero_page_range(handle_t *handle, +static int __ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT; unsigned offset = from & (PAGE_CACHE_SIZE-1); - unsigned blocksize, max, pos; + unsigned blocksize, pos; ext4_lblk_t iblock; struct inode *inode = mapping->host; struct buffer_head *bh; @@ -3205,14 +3223,6 @@ static int ext4_block_zero_page_range(handle_t *handle, return -ENOMEM; blocksize = inode->i_sb->s_blocksize; - max = blocksize - (offset & (blocksize - 1)); - - /* - * correct length if it does not fall between - * 'from' and the end of the block - */ - if (length > max || length < 0) - length = max; iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); @@ -3278,6 +3288,33 @@ unlock: } /* + * ext4_block_zero_page_range() zeros out a mapping of length 'length' + * starting from file offset 'from'. The range to be zero'd must + * be contained with in one block. If the specified range exceeds + * the end of the block it will be shortened to end of the block + * that cooresponds to 'from' + */ +static int ext4_block_zero_page_range(handle_t *handle, + struct address_space *mapping, loff_t from, loff_t length) +{ + struct inode *inode = mapping->host; + unsigned offset = from & (PAGE_CACHE_SIZE-1); + unsigned blocksize = inode->i_sb->s_blocksize; + unsigned max = blocksize - (offset & (blocksize - 1)); + + /* + * correct length if it does not fall between + * 'from' and the end of the block + */ + if (length > max || length < 0) + length = max; + + if (IS_DAX(inode)) + return dax_zero_page_range(inode, from, length, ext4_get_block); + return __ext4_block_zero_page_range(handle, mapping, from, length); +} + +/* * ext4_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. * This required during truncate. We need to physically zero the tail end @@ -3798,8 +3835,10 @@ void ext4_set_inode_flags(struct inode *inode) new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) new_fl |= S_DIRSYNC; + if (test_opt(inode->i_sb, DAX)) + new_fl |= S_DAX; inode_set_flags(inode, new_fl, - S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); + S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX); } /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */ @@ -4052,7 +4091,10 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (S_ISREG(inode->i_mode)) { inode->i_op = &ext4_file_inode_operations; - inode->i_fop = &ext4_file_operations; + if (test_opt(inode->i_sb, DAX)) + inode->i_fop = &ext4_dax_file_operations; + else + inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); } else if (S_ISDIR(inode->i_mode)) { inode->i_op = &ext4_dir_inode_operations; @@ -4139,6 +4181,65 @@ static int ext4_inode_blocks_set(handle_t *handle, return 0; } +struct other_inode { + unsigned long orig_ino; + struct ext4_inode *raw_inode; +}; + +static int other_inode_match(struct inode * inode, unsigned long ino, + void *data) +{ + struct other_inode *oi = (struct other_inode *) data; + + if ((inode->i_ino != ino) || + (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW | + I_DIRTY_SYNC | I_DIRTY_DATASYNC)) || + ((inode->i_state & I_DIRTY_TIME) == 0)) + return 0; + spin_lock(&inode->i_lock); + if (((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW | + I_DIRTY_SYNC | I_DIRTY_DATASYNC)) == 0) && + (inode->i_state & I_DIRTY_TIME)) { + struct ext4_inode_info *ei = EXT4_I(inode); + + inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED); + spin_unlock(&inode->i_lock); + + spin_lock(&ei->i_raw_lock); + EXT4_INODE_SET_XTIME(i_ctime, inode, oi->raw_inode); + EXT4_INODE_SET_XTIME(i_mtime, inode, oi->raw_inode); + EXT4_INODE_SET_XTIME(i_atime, inode, oi->raw_inode); + ext4_inode_csum_set(inode, oi->raw_inode, ei); + spin_unlock(&ei->i_raw_lock); + trace_ext4_other_inode_update_time(inode, oi->orig_ino); + return -1; + } + spin_unlock(&inode->i_lock); + return -1; +} + +/* + * Opportunistically update the other time fields for other inodes in + * the same inode table block. + */ +static void ext4_update_other_inodes_time(struct super_block *sb, + unsigned long orig_ino, char *buf) +{ + struct other_inode oi; + unsigned long ino; + int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; + int inode_size = EXT4_INODE_SIZE(sb); + + oi.orig_ino = orig_ino; + ino = orig_ino & ~(inodes_per_block - 1); + for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) { + if (ino == orig_ino) + continue; + oi.raw_inode = (struct ext4_inode *) buf; + (void) find_inode_nowait(sb, ino, other_inode_match, &oi); + } +} + /* * Post the struct inode info into an on-disk inode location in the * buffer-cache. This gobbles the caller's reference to the @@ -4248,10 +4349,11 @@ static int ext4_do_update_inode(handle_t *handle, cpu_to_le16(ei->i_extra_isize); } } - ext4_inode_csum_set(inode, raw_inode, ei); - spin_unlock(&ei->i_raw_lock); + if (inode->i_sb->s_flags & MS_LAZYTIME) + ext4_update_other_inodes_time(inode->i_sb, inode->i_ino, + bh->b_data); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); rc = ext4_handle_dirty_metadata(handle, NULL, bh); @@ -4534,7 +4636,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) * Truncate pagecache after we've waited for commit * in data=journal mode to make pages freeable. */ - truncate_pagecache(inode, inode->i_size); + truncate_pagecache(inode, inode->i_size); } /* * We want to call ext4_truncate() even if attr->ia_size == @@ -4840,11 +4942,17 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) * If the inode is marked synchronous, we don't honour that here - doing * so would cause a commit on atime updates, which we don't bother doing. * We handle synchronous inodes at the highest possible level. + * + * If only the I_DIRTY_TIME flag is set, we can skip everything. If + * I_DIRTY_TIME and I_DIRTY_SYNC is set, the only inode fields we need + * to copy into the on-disk inode structure are the timestamp files. */ void ext4_dirty_inode(struct inode *inode, int flags) { handle_t *handle; + if (flags == I_DIRTY_TIME) + return; handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) goto out; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 2291923dae4e..28fe71a2904c 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2235,7 +2235,10 @@ retry: err = PTR_ERR(inode); if (!IS_ERR(inode)) { inode->i_op = &ext4_file_inode_operations; - inode->i_fop = &ext4_file_operations; + if (test_opt(inode->i_sb, DAX)) + inode->i_fop = &ext4_dax_file_operations; + else + inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); err = ext4_add_nondir(handle, dentry, inode); if (!err && IS_DIRSYNC(dir)) @@ -2299,7 +2302,10 @@ retry: err = PTR_ERR(inode); if (!IS_ERR(inode)) { inode->i_op = &ext4_file_inode_operations; - inode->i_fop = &ext4_file_operations; + if (test_opt(inode->i_sb, DAX)) + inode->i_fop = &ext4_dax_file_operations; + else + inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); d_tmpfile(dentry, inode); err = ext4_orphan_add(handle, inode); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 74c5f53595fb..e061e66c8280 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -334,7 +334,7 @@ static void save_error_info(struct super_block *sb, const char *func, static int block_device_ejected(struct super_block *sb) { struct inode *bd_inode = sb->s_bdev->bd_inode; - struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(bd_inode); return bdi->dev == NULL; } @@ -1046,10 +1046,7 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, struct path *path); -static int ext4_quota_on_sysfile(struct super_block *sb, int type, - int format_id); static int ext4_quota_off(struct super_block *sb, int type); -static int ext4_quota_off_sysfile(struct super_block *sb, int type); static int ext4_quota_on_mount(struct super_block *sb, int type); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); @@ -1084,16 +1081,6 @@ static const struct quotactl_ops ext4_qctl_operations = { .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk }; - -static const struct quotactl_ops ext4_qctl_sysfile_operations = { - .quota_on_meta = ext4_quota_on_sysfile, - .quota_off = ext4_quota_off_sysfile, - .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, - .set_info = dquot_set_dqinfo, - .get_dqblk = dquot_get_dqblk, - .set_dqblk = dquot_set_dqblk -}; #endif static const struct super_operations ext4_sops = { @@ -1137,8 +1124,9 @@ enum { Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, - Opt_usrquota, Opt_grpquota, Opt_i_version, + Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_dax, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit, + Opt_lazytime, Opt_nolazytime, Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, @@ -1200,8 +1188,11 @@ static const match_table_t tokens = { {Opt_barrier, "barrier"}, {Opt_nobarrier, "nobarrier"}, {Opt_i_version, "i_version"}, + {Opt_dax, "dax"}, {Opt_stripe, "stripe=%u"}, {Opt_delalloc, "delalloc"}, + {Opt_lazytime, "lazytime"}, + {Opt_nolazytime, "nolazytime"}, {Opt_nodelalloc, "nodelalloc"}, {Opt_removed, "mblk_io_submit"}, {Opt_removed, "nomblk_io_submit"}, @@ -1384,6 +1375,7 @@ static const struct mount_opts { {Opt_min_batch_time, 0, MOPT_GTE0}, {Opt_inode_readahead_blks, 0, MOPT_GTE0}, {Opt_init_itable, 0, MOPT_GTE0}, + {Opt_dax, EXT4_MOUNT_DAX, MOPT_SET}, {Opt_stripe, 0, MOPT_GTE0}, {Opt_resuid, 0, MOPT_GTE0}, {Opt_resgid, 0, MOPT_GTE0}, @@ -1459,6 +1451,12 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, case Opt_i_version: sb->s_flags |= MS_I_VERSION; return 1; + case Opt_lazytime: + sb->s_flags |= MS_LAZYTIME; + return 1; + case Opt_nolazytime: + sb->s_flags &= ~MS_LAZYTIME; + return 1; } for (m = ext4_mount_opts; m->token != Opt_err; m++) @@ -1620,6 +1618,11 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } sbi->s_jquota_fmt = m->mount_opt; #endif +#ifndef CONFIG_FS_DAX + } else if (token == Opt_dax) { + ext4_msg(sb, KERN_INFO, "dax option not supported"); + return -1; +#endif } else { if (!args->from) arg = 1; @@ -2776,6 +2779,12 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) if (readonly) return 1; + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_READONLY)) { + ext4_msg(sb, KERN_INFO, "filesystem is read-only"); + sb->s_flags |= MS_RDONLY; + return 1; + } + /* Check that feature set is OK for a read-write mount */ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) { ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of " @@ -3602,6 +3611,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "both data=journal and dioread_nolock"); goto failed_mount; } + if (test_opt(sb, DAX)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and dax"); + goto failed_mount; + } if (test_opt(sb, DELALLOC)) clear_opt(sb, DELALLOC); } @@ -3665,6 +3679,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } + if (sbi->s_mount_opt & EXT4_MOUNT_DAX) { + if (blocksize != PAGE_SIZE) { + ext4_msg(sb, KERN_ERR, + "error: unsupported blocksize for dax"); + goto failed_mount; + } + if (!sb->s_bdev->bd_disk->fops->direct_access) { + ext4_msg(sb, KERN_ERR, + "error: device does not support dax"); + goto failed_mount; + } + } + if (sb->s_blocksize != blocksize) { /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { @@ -3915,9 +3942,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); - init_timer(&sbi->s_err_report); - sbi->s_err_report.function = print_daily_error_info; - sbi->s_err_report.data = (unsigned long) sb; + setup_timer(&sbi->s_err_report, print_daily_error_info, + (unsigned long) sb); /* Register extent status tree shrinker */ if (ext4_es_register_shrinker(sbi)) @@ -3935,7 +3961,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - sb->s_qcop = &ext4_qctl_sysfile_operations; + sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; @@ -4845,9 +4871,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal && sbi->s_journal->j_task->io_context) journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; - /* - * Allow the "check" option to be passed as a remount option. - */ if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; goto restore_opts; @@ -4856,17 +4879,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " - "during remount not supported"); - err = -EINVAL; - goto restore_opts; - } - - if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ - test_opt(sb, JOURNAL_CHECKSUM)) { - ext4_msg(sb, KERN_ERR, "changing journal_checksum " - "during remount not supported"); - err = -EINVAL; - goto restore_opts; + "during remount not supported; ignoring"); + sbi->s_mount_opt ^= EXT4_MOUNT_JOURNAL_CHECKSUM; } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { @@ -4882,6 +4896,18 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) err = -EINVAL; goto restore_opts; } + if (test_opt(sb, DAX)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and dax"); + err = -EINVAL; + goto restore_opts; + } + } + + if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) { + ext4_msg(sb, KERN_WARNING, "warning: refusing change of " + "dax flag with busy inodes while remounting"); + sbi->s_mount_opt ^= EXT4_MOUNT_DAX; } if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) @@ -4930,7 +4956,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_mark_recovery_complete(sb, es); } else { /* Make sure we can mount this feature set readwrite */ - if (!ext4_feature_set_ok(sb, 0)) { + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_READONLY) || + !ext4_feature_set_ok(sb, 0)) { err = -EROFS; goto restore_opts; } @@ -5020,6 +5048,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } #endif + *flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME); ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); kfree(orig_data); return 0; @@ -5288,21 +5317,6 @@ static int ext4_enable_quotas(struct super_block *sb) return 0; } -/* - * quota_on function that is used when QUOTA feature is set. - */ -static int ext4_quota_on_sysfile(struct super_block *sb, int type, - int format_id) -{ - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - return -EINVAL; - - /* - * USAGE was enabled at mount time. Only need to enable LIMITS now. - */ - return ext4_quota_enable(sb, type, format_id, DQUOT_LIMITS_ENABLED); -} - static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; @@ -5329,18 +5343,6 @@ out: return dquot_quota_off(sb, type); } -/* - * quota_off function that is used when QUOTA feature is set. - */ -static int ext4_quota_off_sysfile(struct super_block *sb, int type) -{ - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - return -EINVAL; - - /* Disable only the limits. */ - return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); -} - /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) |