diff options
| -rw-r--r-- | block/bdev.c | 23 | ||||
| -rw-r--r-- | fs/crypto/inline_crypt.c | 49 | ||||
| -rw-r--r-- | fs/ext4/ext4.h | 1 | ||||
| -rw-r--r-- | fs/ext4/file.c | 37 | ||||
| -rw-r--r-- | fs/ext4/inode.c | 37 | ||||
| -rw-r--r-- | fs/f2fs/f2fs.h | 40 | ||||
| -rw-r--r-- | fs/f2fs/file.c | 43 | ||||
| -rw-r--r-- | fs/stat.c | 14 | ||||
| -rw-r--r-- | fs/xfs/xfs_iops.c | 10 | ||||
| -rw-r--r-- | include/linux/blkdev.h | 4 | ||||
| -rw-r--r-- | include/linux/fscrypt.h | 7 | ||||
| -rw-r--r-- | include/linux/stat.h | 2 | ||||
| -rw-r--r-- | include/uapi/linux/stat.h | 4 |
13 files changed, 188 insertions, 83 deletions
diff --git a/block/bdev.c b/block/bdev.c index ce05175e71ce..d699ecdb3260 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -26,6 +26,7 @@ #include <linux/namei.h> #include <linux/part_stat.h> #include <linux/uaccess.h> +#include <linux/stat.h> #include "../fs/internal.h" #include "blk.h" @@ -1069,3 +1070,25 @@ void sync_bdevs(bool wait) spin_unlock(&blockdev_superblock->s_inode_list_lock); iput(old_inode); } + +/* + * Handle STATX_DIOALIGN for block devices. + * + * Note that the inode passed to this is the inode of a block device node file, + * not the block device's internal inode. Therefore it is *not* valid to use + * I_BDEV() here; the block device has to be looked up by i_rdev instead. + */ +void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +{ + struct block_device *bdev; + + bdev = blkdev_get_no_open(inode->i_rdev); + if (!bdev) + return; + + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + stat->result_mask |= STATX_DIOALIGN; + + blkdev_put_no_open(bdev); +} diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index c40bd55bc781..cea8b14007e6 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -396,46 +396,45 @@ bool fscrypt_mergeable_bio_bh(struct bio *bio, EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio_bh); /** - * fscrypt_dio_supported() - check whether a DIO (direct I/O) request is - * supported as far as encryption is concerned - * @iocb: the file and position the I/O is targeting - * @iter: the I/O data segment(s) + * fscrypt_dio_supported() - check whether DIO (direct I/O) is supported on an + * inode, as far as encryption is concerned + * @inode: the inode in question * * Return: %true if there are no encryption constraints that prevent DIO from * being supported; %false if DIO is unsupported. (Note that in the * %true case, the filesystem might have other, non-encryption-related - * constraints that prevent DIO from actually being supported.) + * constraints that prevent DIO from actually being supported. Also, on + * encrypted files the filesystem is still responsible for only allowing + * DIO when requests are filesystem-block-aligned.) */ -bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter) +bool fscrypt_dio_supported(struct inode *inode) { - const struct inode *inode = file_inode(iocb->ki_filp); - const unsigned int blocksize = i_blocksize(inode); + int err; /* If the file is unencrypted, no veto from us. */ if (!fscrypt_needs_contents_encryption(inode)) return true; - /* We only support DIO with inline crypto, not fs-layer crypto. */ - if (!fscrypt_inode_uses_inline_crypto(inode)) - return false; - /* - * Since the granularity of encryption is filesystem blocks, the file - * position and total I/O length must be aligned to the filesystem block - * size -- not just to the block device's logical block size as is - * traditionally the case for DIO on many filesystems. + * We only support DIO with inline crypto, not fs-layer crypto. * - * We require that the user-provided memory buffers be filesystem block - * aligned too. It is simpler to have a single alignment value required - * for all properties of the I/O, as is normally the case for DIO. - * Also, allowing less aligned buffers would imply that data units could - * cross bvecs, which would greatly complicate the I/O stack, which - * assumes that bios can be split at any bvec boundary. + * To determine whether the inode is using inline crypto, we have to set + * up the key if it wasn't already done. This is because in the current + * design of fscrypt, the decision of whether to use inline crypto or + * not isn't made until the inode's encryption key is being set up. In + * the DIO read/write case, the key will always be set up already, since + * the file will be open. But in the case of statx(), the key might not + * be set up yet, as the file might not have been opened yet. */ - if (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), blocksize)) + err = fscrypt_require_key(inode); + if (err) { + /* + * Key unavailable or couldn't be set up. This edge case isn't + * worth worrying about; just report that DIO is unsupported. + */ return false; - - return true; + } + return fscrypt_inode_uses_inline_crypto(inode); } EXPORT_SYMBOL_GPL(fscrypt_dio_supported); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3bf9a6926798..e5f2f5ca5120 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2977,6 +2977,7 @@ extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct user_namespace *, struct dentry *, struct iattr *); +extern u32 ext4_dio_alignment(struct inode *inode); extern int ext4_getattr(struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); extern void ext4_evict_inode(struct inode *); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 109d07629f81..8bb1c35fd6dd 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -36,19 +36,34 @@ #include "acl.h" #include "truncate.h" -static bool ext4_dio_supported(struct kiocb *iocb, struct iov_iter *iter) +/* + * Returns %true if the given DIO request should be attempted with DIO, or + * %false if it should fall back to buffered I/O. + * + * DIO isn't well specified; when it's unsupported (either due to the request + * being misaligned, or due to the file not supporting DIO at all), filesystems + * either fall back to buffered I/O or return EINVAL. For files that don't use + * any special features like encryption or verity, ext4 has traditionally + * returned EINVAL for misaligned DIO. iomap_dio_rw() uses this convention too. + * In this case, we should attempt the DIO, *not* fall back to buffered I/O. + * + * In contrast, in cases where DIO is unsupported due to ext4 features, ext4 + * traditionally falls back to buffered I/O. + * + * This function implements the traditional ext4 behavior in all these cases. + */ +static bool ext4_should_use_dio(struct kiocb *iocb, struct iov_iter *iter) { struct inode *inode = file_inode(iocb->ki_filp); + u32 dio_align = ext4_dio_alignment(inode); - if (!fscrypt_dio_supported(iocb, iter)) - return false; - if (fsverity_active(inode)) + if (dio_align == 0) return false; - if (ext4_should_journal_data(inode)) - return false; - if (ext4_has_inline_data(inode)) - return false; - return true; + + if (dio_align == 1) + return true; + + return IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), dio_align); } static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -63,7 +78,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) inode_lock_shared(inode); } - if (!ext4_dio_supported(iocb, to)) { + if (!ext4_should_use_dio(iocb, to)) { inode_unlock_shared(inode); /* * Fallback to buffered I/O if the operation being performed on @@ -511,7 +526,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) } /* Fallback to buffered I/O if the inode does not support direct I/O. */ - if (!ext4_dio_supported(iocb, from)) { + if (!ext4_should_use_dio(iocb, from)) { if (ilock_shared) inode_unlock_shared(inode); else diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 601214453c3a..364774230d87 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5550,6 +5550,22 @@ err_out: return error; } +u32 ext4_dio_alignment(struct inode *inode) +{ + if (fsverity_active(inode)) + return 0; + if (ext4_should_journal_data(inode)) + return 0; + if (ext4_has_inline_data(inode)) + return 0; + if (IS_ENCRYPTED(inode)) { + if (!fscrypt_dio_supported(inode)) + return 0; + return i_blocksize(inode); + } + return 1; /* use the iomap defaults */ +} + int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -5565,6 +5581,27 @@ int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->btime.tv_nsec = ei->i_crtime.tv_nsec; } + /* + * Return the DIO alignment restrictions if requested. We only return + * this information when requested, since on encrypted files it might + * take a fair bit of work to get if the file wasn't opened recently. + */ + if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) { + u32 dio_align = ext4_dio_alignment(inode); + + stat->result_mask |= STATX_DIOALIGN; + if (dio_align == 1) { + struct block_device *bdev = inode->i_sb->s_bdev; + + /* iomap defaults */ + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + } else { + stat->dio_mem_align = dio_align; + stat->dio_offset_align = dio_align; + } + } + flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (flags & EXT4_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 3c7cdb70fe2e..aea816a133a8 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -4471,17 +4471,6 @@ static inline void f2fs_i_compr_blocks_update(struct inode *inode, f2fs_mark_inode_dirty_sync(inode, true); } -static inline int block_unaligned_IO(struct inode *inode, - struct kiocb *iocb, struct iov_iter *iter) -{ - unsigned int i_blkbits = READ_ONCE(inode->i_blkbits); - unsigned int blocksize_mask = (1 << i_blkbits) - 1; - loff_t offset = iocb->ki_pos; - unsigned long align = offset | iov_iter_alignment(iter); - - return align & blocksize_mask; -} - static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi, int flag) { @@ -4492,35 +4481,6 @@ static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi, return sbi->aligned_blksize; } -static inline bool f2fs_force_buffered_io(struct inode *inode, - struct kiocb *iocb, struct iov_iter *iter) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - int rw = iov_iter_rw(iter); - - if (!fscrypt_dio_supported(iocb, iter)) - return true; - if (fsverity_active(inode)) - return true; - if (f2fs_compressed_file(inode)) - return true; - - /* disallow direct IO if any of devices has unaligned blksize */ - if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) - return true; - - if (f2fs_lfs_mode(sbi) && (rw == WRITE)) { - if (block_unaligned_IO(inode, iocb, iter)) - return true; - if (F2FS_IO_ALIGNED(sbi)) - return true; - } - if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED)) - return true; - - return false; -} - static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) { return fsverity_active(inode) && diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ce4905a073b3..791770507328 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -808,6 +808,29 @@ int f2fs_truncate(struct inode *inode) return 0; } +static bool f2fs_force_buffered_io(struct inode *inode, int rw) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (!fscrypt_dio_supported(inode)) + return true; + if (fsverity_active(inode)) + return true; + if (f2fs_compressed_file(inode)) + return true; + + /* disallow direct IO if any of devices has unaligned blksize */ + if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) + return true; + + if (f2fs_lfs_mode(sbi) && rw == WRITE && F2FS_IO_ALIGNED(sbi)) + return true; + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + return true; + + return false; +} + int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -824,6 +847,24 @@ int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->btime.tv_nsec = fi->i_crtime.tv_nsec; } + /* + * Return the DIO alignment restrictions if requested. We only return + * this information when requested, since on encrypted files it might + * take a fair bit of work to get if the file wasn't opened recently. + * + * f2fs sometimes supports DIO reads but not DIO writes. STATX_DIOALIGN + * cannot represent that, so in that case we report no DIO support. + */ + if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) { + unsigned int bsize = i_blocksize(inode); + + stat->result_mask |= STATX_DIOALIGN; + if (!f2fs_force_buffered_io(inode, WRITE)) { + stat->dio_mem_align = bsize; + stat->dio_offset_align = bsize; + } + } + flags = fi->i_flags; if (flags & F2FS_COMPR_FL) stat->attributes |= STATX_ATTR_COMPRESSED; @@ -4182,7 +4223,7 @@ static bool f2fs_should_use_dio(struct inode *inode, struct kiocb *iocb, if (!(iocb->ki_flags & IOCB_DIRECT)) return false; - if (f2fs_force_buffered_io(inode, iocb, iter)) + if (f2fs_force_buffered_io(inode, iov_iter_rw(iter))) return false; /* diff --git a/fs/stat.c b/fs/stat.c index 9ced8860e0f3..ef50573c72a2 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -5,6 +5,7 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ +#include <linux/blkdev.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/errno.h> @@ -230,11 +231,22 @@ retry: goto out; error = vfs_getattr(&path, stat, request_mask, flags); + stat->mnt_id = real_mount(path.mnt)->mnt_id; stat->result_mask |= STATX_MNT_ID; + if (path.mnt->mnt_root == path.dentry) stat->attributes |= STATX_ATTR_MOUNT_ROOT; stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; + + /* Handle STATX_DIOALIGN for block devices. */ + if (request_mask & STATX_DIOALIGN) { + struct inode *inode = d_backing_inode(path.dentry); + + if (S_ISBLK(inode->i_mode)) + bdev_statx_dioalign(inode, stat); + } + path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -611,6 +623,8 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_dev_major = MAJOR(stat->dev); tmp.stx_dev_minor = MINOR(stat->dev); tmp.stx_mnt_id = stat->mnt_id; + tmp.stx_dio_mem_align = stat->dio_mem_align; + tmp.stx_dio_offset_align = stat->dio_offset_align; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 45518b8c613c..f51c60d7e205 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -604,6 +604,16 @@ xfs_vn_getattr( stat->blksize = BLKDEV_IOSIZE; stat->rdev = inode->i_rdev; break; + case S_IFREG: + if (request_mask & STATX_DIOALIGN) { + struct xfs_buftarg *target = xfs_inode_buftarg(ip); + struct block_device *bdev = target->bt_bdev; + + stat->result_mask |= STATX_DIOALIGN; + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + } + fallthrough; default: stat->blksize = xfs_stat_blksize(ip); stat->rdev = 0; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 84b13fdd34a7..8038c5fbde40 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1498,6 +1498,7 @@ int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); +void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); void printk_all_partitions(void); #else static inline void invalidate_bdev(struct block_device *bdev) @@ -1514,6 +1515,9 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } +static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +{ +} static inline void printk_all_partitions(void) { } diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 1f12ebb4a69d..cad78b569c7e 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -764,7 +764,7 @@ bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, bool fscrypt_mergeable_bio_bh(struct bio *bio, const struct buffer_head *next_bh); -bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter); +bool fscrypt_dio_supported(struct inode *inode); u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks); @@ -797,11 +797,8 @@ static inline bool fscrypt_mergeable_bio_bh(struct bio *bio, return true; } -static inline bool fscrypt_dio_supported(struct kiocb *iocb, - struct iov_iter *iter) +static inline bool fscrypt_dio_supported(struct inode *inode) { - const struct inode *inode = file_inode(iocb->ki_filp); - return !fscrypt_needs_contents_encryption(inode); } diff --git a/include/linux/stat.h b/include/linux/stat.h index 7df06931f25d..ff277ced50e9 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -50,6 +50,8 @@ struct kstat { struct timespec64 btime; /* File creation time */ u64 blocks; u64 mnt_id; + u32 dio_mem_align; + u32 dio_offset_align; }; #endif diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 1500a0f58041..7cab2c65d3d7 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -124,7 +124,8 @@ struct statx { __u32 stx_dev_minor; /* 0x90 */ __u64 stx_mnt_id; - __u64 __spare2; + __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ + __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ /* 0xa0 */ __u64 __spare3[12]; /* Spare space for future expansion */ /* 0x100 */ @@ -152,6 +153,7 @@ struct statx { #define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ +#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ |