From fcb14cb1bdacec5b4374fe161e83fb8208164a85 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 22 May 2022 14:59:25 -0400 Subject: new iov_iter flavour - ITER_UBUF Equivalent of single-segment iovec. Initialized by iov_iter_ubuf(), checked for by iter_is_ubuf(), otherwise behaves like ITER_IOVEC ones. We are going to expose the things like ->write_iter() et.al. to those in subsequent commits. New predicate (user_backed_iter()) that is true for ITER_IOVEC and ITER_UBUF; places like direct-IO handling should use that for checking that pages we modify after getting them from iov_iter_get_pages() would need to be dirtied. DO NOT assume that replacing iter_is_iovec() with user_backed_iter() will solve all problems - there's code that uses iter_is_iovec() to decide how to poke around in iov_iter guts and for that the predicate replacement obviously won't suffice. Signed-off-by: Al Viro --- include/linux/uio.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 9a2dc496d535..85bef84fd294 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -26,6 +26,7 @@ enum iter_type { ITER_PIPE, ITER_XARRAY, ITER_DISCARD, + ITER_UBUF, }; struct iov_iter_state { @@ -38,6 +39,7 @@ struct iov_iter { u8 iter_type; bool nofault; bool data_source; + bool user_backed; size_t iov_offset; size_t count; union { @@ -46,6 +48,7 @@ struct iov_iter { const struct bio_vec *bvec; struct xarray *xarray; struct pipe_inode_info *pipe; + void __user *ubuf; }; union { unsigned long nr_segs; @@ -70,6 +73,11 @@ static inline void iov_iter_save_state(struct iov_iter *iter, state->nr_segs = iter->nr_segs; } +static inline bool iter_is_ubuf(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_UBUF; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -105,6 +113,11 @@ static inline unsigned char iov_iter_rw(const struct iov_iter *i) return i->data_source ? WRITE : READ; } +static inline bool user_backed_iter(const struct iov_iter *i) +{ + return i->user_backed; +} + /* * Total number of bytes covered by an iovec. * @@ -322,4 +335,17 @@ ssize_t __import_iovec(int type, const struct iovec __user *uvec, int import_single_range(int type, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i); +static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, + void __user *buf, size_t count) +{ + WARN_ON(direction & ~(READ | WRITE)); + *i = (struct iov_iter) { + .iter_type = ITER_UBUF, + .user_backed = true, + .data_source = direction, + .ubuf = buf, + .count = count + }; +} + #endif -- cgit v1.2.3 From 10f525a8cd7a525e9fc73288bb35428c9cad5e63 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 15 Jun 2022 02:02:51 -0400 Subject: ITER_PIPE: cache the type of last buffer We often need to find whether the last buffer is anon or not, and currently it's rather clumsy: check if ->iov_offset is non-zero (i.e. that pipe is not empty) if so, get the corresponding pipe_buffer and check its ->ops if it's &default_pipe_buf_ops, we have an anon buffer. Let's replace the use of ->iov_offset (which is nowhere near similar to its role for other flavours) with signed field (->last_offset), with the following rules: empty, no buffers occupied: 0 anon, with bytes up to N-1 filled: N zero-copy, with bytes up to N-1 filled: -N That way abs(i->last_offset) is equal to what used to be in i->iov_offset and empty vs. anon vs. zero-copy can be distinguished by the sign of i->last_offset. Checks for "should we extend the last buffer or should we start a new one?" become easier to follow that way. Note that most of the operations can only be done in a sane state - i.e. when the pipe has nothing past the current position of iterator. About the only thing that could be done outside of that state is iov_iter_advance(), which transitions to the sane state by truncating the pipe. There are only two cases where we leave the sane state: 1) iov_iter_get_pages()/iov_iter_get_pages_alloc(). Will be dealt with later, when we make get_pages advancing - the callers are actually happier that way. 2) iov_iter copied, then something is put into the copy. Since they share the underlying pipe, the original gets behind. When we decide that we are done with the copy (original is not usable until then) we advance the original. direct_io used to be done that way; nowadays it operates on the original and we do iov_iter_revert() to discard the excessive data. At the moment there's nothing in the kernel that could do that to ITER_PIPE iterators, so this reason for insane state is theoretical right now. Signed-off-by: Al Viro --- include/linux/uio.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 85bef84fd294..e7fc29b5ad19 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -40,7 +40,10 @@ struct iov_iter { bool nofault; bool data_source; bool user_backed; - size_t iov_offset; + union { + size_t iov_offset; + int last_offset; + }; size_t count; union { const struct iovec *iov; -- cgit v1.2.3 From 12d426ab64a1c75f1b2ee5c33e933a4c16004049 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 15 Jun 2022 09:44:38 -0400 Subject: ITER_PIPE: fold data_start() and pipe_space_for_user() together All their callers are next to each other; all of them want the total amount of pages and, possibly, the offset in the partial final buffer. Combine into a new helper (pipe_npages()), fix the bogosity in pipe_space_for_user(), while we are at it. Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 4ea496924106..6cb65df3e3ba 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -156,26 +156,6 @@ static inline bool pipe_full(unsigned int head, unsigned int tail, return pipe_occupancy(head, tail) >= limit; } -/** - * pipe_space_for_user - Return number of slots available to userspace - * @head: The pipe ring head pointer - * @tail: The pipe ring tail pointer - * @pipe: The pipe info structure - */ -static inline unsigned int pipe_space_for_user(unsigned int head, unsigned int tail, - struct pipe_inode_info *pipe) -{ - unsigned int p_occupancy, p_space; - - p_occupancy = pipe_occupancy(head, tail); - if (p_occupancy >= pipe->max_usage) - return 0; - p_space = pipe->ring_size - p_occupancy; - if (p_space > pipe->max_usage) - p_space = pipe->max_usage; - return p_space; -} - /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to -- cgit v1.2.3 From 1ef255e257173f4bc44317ef2076e7e0de688fdf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 9 Jun 2022 10:28:36 -0400 Subject: iov_iter: advancing variants of iov_iter_get_pages{,_alloc}() Most of the users immediately follow successful iov_iter_get_pages() with advancing by the amount it had returned. Provide inline wrappers doing that, convert trivial open-coded uses of those. BTW, iov_iter_get_pages() never returns more than it had been asked to; such checks in cifs ought to be removed someday... Reviewed-by: Jeff Layton Signed-off-by: Al Viro --- include/linux/uio.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index e7fc29b5ad19..b70d28693400 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -351,4 +351,24 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, }; } +static inline ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, + size_t maxsize, unsigned maxpages, size_t *start) +{ + ssize_t res = iov_iter_get_pages(i, pages, maxsize, maxpages, start); + + if (res >= 0) + iov_iter_advance(i, res); + return res; +} + +static inline ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, + size_t maxsize, size_t *start) +{ + ssize_t res = iov_iter_get_pages_alloc(i, pages, maxsize, start); + + if (res >= 0) + iov_iter_advance(i, res); + return res; +} + #endif -- cgit v1.2.3 From eba2d3d798295dc43cae8fade102f9d083a2a741 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 10 Jun 2022 13:05:12 -0400 Subject: get rid of non-advancing variants mechanical change; will be further massaged in subsequent commits Reviewed-by: Jeff Layton Signed-off-by: Al Viro --- include/linux/uio.h | 24 ++---------------------- 1 file changed, 2 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index b70d28693400..5896af36199c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -247,9 +247,9 @@ void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); -ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, +ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); -ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, +ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); @@ -351,24 +351,4 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, }; } -static inline ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, - size_t maxsize, unsigned maxpages, size_t *start) -{ - ssize_t res = iov_iter_get_pages(i, pages, maxsize, maxpages, start); - - if (res >= 0) - iov_iter_advance(i, res); - return res; -} - -static inline ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, - size_t maxsize, size_t *start) -{ - ssize_t res = iov_iter_get_pages_alloc(i, pages, maxsize, start); - - if (res >= 0) - iov_iter_advance(i, res); - return res; -} - #endif -- cgit v1.2.3