From 1383a7ed67490fb00d793e36c7a4d599ff88a64d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:40:31 +1100 Subject: vfs: check file ranges before cloning files Move the file range checks from vfs_clone_file_prep into a separate generic_remap_checks function so that all the checks are collected in a central location. This forms the basis for adding more checks from generic_write_checks that will make cloning's input checking more consistent with write input checking. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 897eae8faee1..ba93a6e7dac4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe); +extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, @@ -2967,6 +2967,9 @@ 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 *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +extern int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + uint64_t *count, bool is_dedupe); 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 v1.2.3 From a83ab01a62e61616ebb8b97f90f568c1214dc10d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:08 +1100 Subject: vfs: rename vfs_clone_file_prep to be more descriptive The vfs_clone_file_prep is a generic function to be called by filesystem implementations only. Rename the prefix to generic_ and make it more clear that it applies to remap operations, not just clones. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ba93a6e7dac4..55729e1c2e75 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 *count, bool is_dedupe); +extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3 From 2e5dfc99f2e61c42083ba742395e7a7b353513d1 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:21 +1100 Subject: vfs: combine the clone and dedupe into a single remap_file_range Combine the clone_file_range and dedupe_file_range operations into a single remap_file_range file operation dispatch since they're fundamentally the same operation. The differences between the two can be made in the prep functions. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 55729e1c2e75..888cef35c7d7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1721,6 +1721,24 @@ struct block_device_operations; #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) +/* + * These flags control the behavior of the remap_file_range function pointer. + * If it is called with len == 0 that means "remap to end of source file". + * See Documentation/filesystems/vfs.txt for more details about this call. + * + * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + */ +#define REMAP_FILE_DEDUP (1 << 0) + +/* + * These flags signal that the caller is ok with altering various aspects of + * the behavior of the remap operation. The changes must be made by the + * implementation; the vfs remap helper functions can take advantage of them. + * Flags in this category exist to preserve the quirky behavior of the hoisted + * btrfs clone/dedupe ioctls. + * There are no flags yet, but subsequent commits will add some. + */ +#define REMAP_FILE_ADVISORY (0) struct iov_iter; @@ -1759,10 +1777,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); - int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); + int (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; -- cgit v1.2.3 From a91ae49bbaf43910edb09e03fedf26b23875bd52 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:28 +1100 Subject: vfs: pass remap flags to generic_remap_file_range_prep Plumb the remap flags through the filesystem from the vfs function dispatcher all the way to the prep function to prepare for behavior changes in subsequent patches. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 888cef35c7d7..631c28ce1436 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1844,7 +1844,7 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *count, bool is_dedupe); + u64 *count, unsigned int remap_flags); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3 From 3d28193e1df043764deb7abdaba5e3a6660bc393 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:34 +1100 Subject: vfs: pass remap flags to generic_remap_checks Pass the same remap flags to generic_remap_checks for consistency. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 631c28ce1436..c5435ca81132 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2986,7 +2986,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, bool is_dedupe); + uint64_t *count, unsigned int remap_flags); 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 v1.2.3 From 42ec3d4c02187a18e27ff94b409ec27234bf2ffd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:49 +1100 Subject: vfs: make remap_file_range functions take and return bytes completed Change the remap_file_range functions to take a number of bytes to operate upon and return the number of bytes they operated on. This is a requirement for allowing fs implementations to return short clone/dedupe results to the user, which will enable us to obey resource limits in a graceful manner. A subsequent patch will enable copy_file_range to signal to the ->clone_file_range implementation that it can handle a short length, which will be returned in the function's return value. For now the short return is not implemented anywhere so the behavior won't change -- either copy_file_range manages to clone the entire range or it tries an alternative. Neither clone ioctl can take advantage of this, alas. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c5435ca81132..c72d8c3c065a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1777,9 +1777,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*remap_file_range)(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len, unsigned int remap_flags); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; @@ -1844,19 +1844,22 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *count, unsigned int remap_flags); -extern int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); -extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); + loff_t *count, + unsigned int remap_flags); +extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); +extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); -extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, - u64 len); +extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len); struct super_operations { @@ -2986,7 +2989,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, unsigned int remap_flags); + loff_t *count, unsigned int remap_flags); 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 v1.2.3 From 452ce65951a2f0719e4e119ecca134c06cfe22ee Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:56 +1100 Subject: vfs: plumb remap flags through the vfs clone functions Plumb a remap_flags argument through the {do,vfs}_clone_file_range functions so that clone can take advantage of it. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c72d8c3c065a..1c5e55d2a67d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1848,10 +1848,10 @@ extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - loff_t len); + loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - loff_t len); + loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); -- cgit v1.2.3 From df3658361951e17364f1e1c3fa92862a990ad8bd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:03 +1100 Subject: vfs: plumb remap flags through the vfs dedupe functions Plumb a remap_flags argument through the vfs_dedupe_file_range_one functions so that dedupe can take advantage of it. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1c5e55d2a67d..544ab5083b48 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1859,7 +1859,7 @@ extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, - loff_t len); + loff_t len, unsigned int remap_flags); struct super_operations { -- cgit v1.2.3 From eca3654e3cc7d93e9734d0fa96cfb15c7f356244 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:10 +1100 Subject: vfs: enable remap callers that can handle short operations Plumb in a remap flag that enables the filesystem remap handler to shorten remapping requests for callers that can handle it. Now copy_file_range can report partial success (in case we run up against alignment problems, resource limits, etc.). We also enable CAN_SHORTEN for fideduperange to maintain existing userspace-visible behavior where xfs/btrfs shorten the dedupe range to avoid stale post-eof data exposure. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 544ab5083b48..34c22d695011 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1727,8 +1727,10 @@ struct block_device_operations; * See Documentation/filesystems/vfs.txt for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) +#define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of @@ -1736,9 +1738,8 @@ struct block_device_operations; * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. - * There are no flags yet, but subsequent commits will add some. */ -#define REMAP_FILE_ADVISORY (0) +#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; -- cgit v1.2.3 From c32e5f39953fa6bbff35c655bdcb7b3128f1e79f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:17 +1100 Subject: vfs: hide file range comparison function There are no callers of vfs_dedupe_file_range_compare, so we might as well make it a static helper and remove the export. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 34c22d695011..346036a84f18 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1853,9 +1853,6 @@ extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); -extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, - loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, -- cgit v1.2.3