From bd8e0ff956456ad9071dbb6c2ed7d33bd22fc216 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 17 Mar 2015 14:04:02 -0700 Subject: new helper: iov_iter_rw() Get either READ or WRITE out of iter->type. Signed-off-by: Omar Sandoval Signed-off-by: Al Viro --- include/linux/uio.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/uio.h b/include/linux/uio.h index 15f11fb..8b01e1c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -112,6 +112,14 @@ static inline bool iter_is_iovec(struct iov_iter *i) } /* + * Get one of READ or WRITE out of iter->type without any other flags OR'd in + * with it. + * + * The ?: is just for type safety. + */ +#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & RW_MASK) + +/* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value * greater than the amount of data in iov_iter is fine - it'll just do -- cgit v1.1 From 17f8c842d24ac054e4212c82b5bd6ae455a334f3 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Mon, 16 Mar 2015 04:33:50 -0700 Subject: Remove rw from {,__,do_}blockdev_direct_IO() Most filesystems call through to these at some point, so we'll start here. Signed-off-by: Omar Sandoval Signed-off-by: Al Viro --- include/linux/fs.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index f1e3f65..c67b6de 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2634,16 +2634,18 @@ enum { void dio_end_io(struct bio *bio, int error); -ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, loff_t offset, - get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags); - -static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, - struct inode *inode, struct iov_iter *iter, loff_t offset, - get_block_t get_block) -{ - return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter, +ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, struct iov_iter *iter, + loff_t offset, get_block_t get_block, + dio_iodone_t end_io, dio_submit_t submit_io, + int flags); + +static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, + struct inode *inode, + struct iov_iter *iter, loff_t offset, + get_block_t get_block) +{ + return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, offset, get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } -- cgit v1.1 From a95cd6311512bd954e88684eb39373f7f4b0a984 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Mon, 16 Mar 2015 04:33:51 -0700 Subject: Remove rw from dax_{do_,}io() And use iov_iter_rw() instead. Signed-off-by: Omar Sandoval Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index c67b6de..295bc58 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2609,8 +2609,8 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset, extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); -ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *, - loff_t, get_block_t, dio_iodone_t, int flags); +ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, + get_block_t, dio_iodone_t, int flags); int dax_clear_blocks(struct inode *, sector_t block, long size); int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); int dax_truncate_page(struct inode *, loff_t from, get_block_t); -- cgit v1.1 From 22c6186ecea0be9eff1c399298ad36e94a59995f Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Mon, 16 Mar 2015 04:33:53 -0700 Subject: direct_IO: remove rw from a_ops->direct_IO() Now that no one is using rw, remove it completely. Signed-off-by: Omar Sandoval Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- include/linux/nfs_fs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 295bc58..72e3759 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -383,7 +383,7 @@ struct address_space_operations { void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); - ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset); + ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset); /* * migrate the contents of a page to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b01ccf3..3d1b0d2 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -447,7 +447,7 @@ static inline struct rpc_cred *nfs_file_cred(struct file *file) /* * linux/fs/nfs/direct.c */ -extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t); +extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *, loff_t); extern ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, loff_t pos); -- cgit v1.1 From 0fa6b005afdb3152ce85df963302e59b61115f9b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 4 Apr 2015 04:05:48 -0400 Subject: generic_write_checks(): drop isblk argument all remaining callers are passing 0; some just obscure that fact. Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 72e3759..492948e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2566,7 +2566,7 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); -int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); +int generic_write_checks(struct file *file, loff_t *pos, size_t *count); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); -- cgit v1.1 From 3309dd04cbcd2cdad168485af5cf3576b5051e49 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 9 Apr 2015 12:55:47 -0400 Subject: switch generic_write_checks() to iocb and iter ... returning -E... upon error and amount of data left in iter after (possible) truncation upon success. Note, that normal case gives a non-zero (positive) return value, so any tests for != 0 _must_ be updated. Signed-off-by: Al Viro Conflicts: fs/ext4/file.c --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index c7b21db..b4aa400 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2566,7 +2566,7 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); -int generic_write_checks(struct file *file, loff_t *pos, size_t *count); +extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); -- cgit v1.1 From 2ba48ce513c4e545318d22b138861d5876edf906 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 9 Apr 2015 13:52:01 -0400 Subject: mirror O_APPEND and O_DIRECT into iocb->ki_flags ... avoiding write_iter/fcntl races. Signed-off-by: Al Viro --- include/linux/fs.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b4aa400..b1d7db2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -315,6 +315,8 @@ struct address_space; struct writeback_control; #define IOCB_EVENTFD (1 << 0) +#define IOCB_APPEND (1 << 1) +#define IOCB_DIRECT (1 << 2) struct kiocb { struct file *ki_filp; @@ -329,10 +331,13 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) return kiocb->ki_complete == NULL; } +static inline int iocb_flags(struct file *file); + static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, + .ki_flags = iocb_flags(filp), }; } @@ -2779,6 +2784,16 @@ static inline bool io_is_direct(struct file *filp) return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp)); } +static inline int iocb_flags(struct file *file) +{ + int res = 0; + if (file->f_flags & O_APPEND) + res |= IOCB_APPEND; + if (io_is_direct(file)) + res |= IOCB_DIRECT; + return res; +} + static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; -- cgit v1.1 From 65a4a1cad7c56e7056fb4b35ac2d93695612612c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 9 Apr 2015 14:11:08 -0400 Subject: nfs: generic_write_checks() shouldn't be done on swapout... Signed-off-by: Al Viro --- include/linux/nfs_fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 3d1b0d2..410abd1 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -452,8 +452,7 @@ extern ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, loff_t pos); extern ssize_t nfs_file_direct_write(struct kiocb *iocb, - struct iov_iter *iter, - loff_t pos); + struct iov_iter *iter); /* * linux/fs/nfs/dir.c -- cgit v1.1 From 525d27b23555419e0e7b73fb6e78d4d678cb4f32 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 11 Feb 2015 13:40:17 +0000 Subject: VFS: Add owner-filesystem positive/negative dentry checks Supply two functions to test whether a filesystem's own dentries are positive or negative (d_really_is_positive() and d_really_is_negative()). The problem is that the DCACHE_ENTRY_TYPE field of dentry->d_flags may be overridden by the union part of a layered filesystem and isn't thus necessarily indicative of the type of dentry. Normally, this would involve a negative dentry (ie. ->d_inode == NULL) having ->d_layer.lower pointed to a lower layer dentry, DCACHE_PINNING_LOWER set and the DCACHE_ENTRY_TYPE field set to something other than DCACHE_MISS_TYPE - but it could also involve, say, a DCACHE_SPECIAL_TYPE being overridden to DCACHE_WHITEOUT_TYPE if a 0,0 chardev is detected in the top layer. However, inside a filesystem, when that fs is looking at its own dentries, it probably wants to know if they are really negative or not - and doesn't care about the fallthrough bits used by the union. To this end, a filesystem should normally use d_really_is_positive/negative() when looking at its own dentries rather than d_is_positive/negative() and should use d_inode() to get at the inode. Anyone looking at someone else's dentries (this includes pathwalk) should use d_is_xxx() and d_backing_inode(). Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/dcache.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d835879..e83768e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -482,6 +482,44 @@ static inline bool d_is_positive(const struct dentry *dentry) return !d_is_negative(dentry); } +/** + * d_really_is_negative - Determine if a dentry is really negative (ignoring fallthroughs) + * @dentry: The dentry in question + * + * Returns true if the dentry represents either an absent name or a name that + * doesn't map to an inode (ie. ->d_inode is NULL). The dentry could represent + * a true miss, a whiteout that isn't represented by a 0,0 chardev or a + * fallthrough marker in an opaque directory. + * + * Note! (1) This should be used *only* by a filesystem to examine its own + * dentries. It should not be used to look at some other filesystem's + * dentries. (2) It should also be used in combination with d_inode() to get + * the inode. (3) The dentry may have something attached to ->d_lower and the + * type field of the flags may be set to something other than miss or whiteout. + */ +static inline bool d_really_is_negative(const struct dentry *dentry) +{ + return dentry->d_inode == NULL; +} + +/** + * d_really_is_positive - Determine if a dentry is really positive (ignoring fallthroughs) + * @dentry: The dentry in question + * + * Returns true if the dentry represents a name that maps to an inode + * (ie. ->d_inode is not NULL). The dentry might still represent a whiteout if + * that is represented on medium as a 0,0 chardev. + * + * Note! (1) This should be used *only* by a filesystem to examine its own + * dentries. It should not be used to look at some other filesystem's + * dentries. (2) It should also be used in combination with d_inode() to get + * the inode. + */ +static inline bool d_really_is_positive(const struct dentry *dentry) +{ + return dentry->d_inode != NULL; +} + extern void d_set_fallthru(struct dentry *dentry); static inline bool d_is_fallthru(const struct dentry *dentry) -- cgit v1.1 From 4bf46a272647d89e780126b52eda04737defd9f4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 5 Mar 2015 14:09:22 +0000 Subject: VFS: Impose ordering on accesses of d_inode and d_flags Impose ordering on accesses of d_inode and d_flags to avoid the need to do this: if (!dentry->d_inode || d_is_negative(dentry)) { when this: if (d_is_negative(dentry)) { should suffice. This check is especially problematic if a dentry can have its type field set to something other than DENTRY_MISS_TYPE when d_inode is NULL (as in unionmount). What we really need to do is stick a write barrier between setting d_inode and setting d_flags and a read barrier between reading d_flags and reading d_inode. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/dcache.h | 21 +++------------------ 1 file changed, 3 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index e83768e..df334cb 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -404,26 +404,11 @@ static inline bool d_mountpoint(const struct dentry *dentry) /* * Directory cache entry type accessor functions. */ -static inline void __d_set_type(struct dentry *dentry, unsigned type) -{ - dentry->d_flags = (dentry->d_flags & ~DCACHE_ENTRY_TYPE) | type; -} - -static inline void __d_clear_type(struct dentry *dentry) -{ - __d_set_type(dentry, DCACHE_MISS_TYPE); -} - -static inline void d_set_type(struct dentry *dentry, unsigned type) -{ - spin_lock(&dentry->d_lock); - __d_set_type(dentry, type); - spin_unlock(&dentry->d_lock); -} - static inline unsigned __d_entry_type(const struct dentry *dentry) { - return dentry->d_flags & DCACHE_ENTRY_TYPE; + unsigned type = READ_ONCE(dentry->d_flags); + smp_rmb(); + return type & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) -- cgit v1.1