From fcb14cb1bdacec5b4374fe161e83fb8208164a85 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
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 <viro@zeniv.linux.org.uk>
---
 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 v1.2.3-59-g8ed1b


From 10f525a8cd7a525e9fc73288bb35428c9cad5e63 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
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 <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h |  5 +++-
 lib/iov_iter.c      | 77 ++++++++++++++++++++++++++---------------------------
 2 files changed, 42 insertions(+), 40 deletions(-)

(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;
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index c2e08004a1eb..8834f3f61220 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -199,7 +199,7 @@ static bool sanity(const struct iov_iter *i)
 	unsigned int i_head = i->head;
 	unsigned int idx;
 
-	if (i->iov_offset) {
+	if (i->last_offset) {
 		struct pipe_buffer *p;
 		if (unlikely(p_occupancy == 0))
 			goto Bad;	// pipe must be non-empty
@@ -207,7 +207,7 @@ static bool sanity(const struct iov_iter *i)
 			goto Bad;	// must be at the last buffer...
 
 		p = pipe_buf(pipe, i_head);
-		if (unlikely(p->offset + p->len != i->iov_offset))
+		if (unlikely(p->offset + p->len != abs(i->last_offset)))
 			goto Bad;	// ... at the end of segment
 	} else {
 		if (i_head != p_head)
@@ -215,7 +215,7 @@ static bool sanity(const struct iov_iter *i)
 	}
 	return true;
 Bad:
-	printk(KERN_ERR "idx = %d, offset = %zd\n", i_head, i->iov_offset);
+	printk(KERN_ERR "idx = %d, offset = %d\n", i_head, i->last_offset);
 	printk(KERN_ERR "head = %d, tail = %d, buffers = %d\n",
 			p_head, p_tail, pipe->ring_size);
 	for (idx = 0; idx < pipe->ring_size; idx++)
@@ -259,30 +259,31 @@ static void push_page(struct pipe_inode_info *pipe, struct page *page,
 	get_page(page);
 }
 
-static inline bool allocated(struct pipe_buffer *buf)
+static inline int last_offset(const struct pipe_buffer *buf)
 {
-	return buf->ops == &default_pipe_buf_ops;
+	if (buf->ops == &default_pipe_buf_ops)
+		return buf->len;	// buf->offset is 0 for those
+	else
+		return -(buf->offset + buf->len);
 }
 
 static struct page *append_pipe(struct iov_iter *i, size_t size,
 				unsigned int *off)
 {
 	struct pipe_inode_info *pipe = i->pipe;
-	size_t offset = i->iov_offset;
+	int offset = i->last_offset;
 	struct pipe_buffer *buf;
 	struct page *page;
 
-	if (offset && offset < PAGE_SIZE) {
-		// some space in the last buffer; can we add to it?
+	if (offset > 0 && offset < PAGE_SIZE) {
+		// some space in the last buffer; add to it
 		buf = pipe_buf(pipe, pipe->head - 1);
-		if (allocated(buf)) {
-			size = min_t(size_t, size, PAGE_SIZE - offset);
-			buf->len += size;
-			i->iov_offset += size;
-			i->count -= size;
-			*off = offset;
-			return buf->page;
-		}
+		size = min_t(size_t, size, PAGE_SIZE - offset);
+		buf->len += size;
+		i->last_offset += size;
+		i->count -= size;
+		*off = offset;
+		return buf->page;
 	}
 	// OK, we need a new buffer
 	*off = 0;
@@ -293,7 +294,7 @@ static struct page *append_pipe(struct iov_iter *i, size_t size,
 	if (!page)
 		return NULL;
 	i->head = pipe->head - 1;
-	i->iov_offset = size;
+	i->last_offset = size;
 	i->count -= size;
 	return page;
 }
@@ -313,11 +314,11 @@ static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t by
 	if (!sanity(i))
 		return 0;
 
-	if (offset && i->iov_offset == offset) { // could we merge it?
+	if (offset && i->last_offset == -offset) { // could we merge it?
 		struct pipe_buffer *buf = pipe_buf(pipe, head - 1);
 		if (buf->page == page) {
 			buf->len += bytes;
-			i->iov_offset += bytes;
+			i->last_offset -= bytes;
 			i->count -= bytes;
 			return bytes;
 		}
@@ -326,7 +327,7 @@ static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t by
 		return 0;
 
 	push_page(pipe, page, offset, bytes);
-	i->iov_offset = offset + bytes;
+	i->last_offset = -(offset + bytes);
 	i->head = head;
 	i->count -= bytes;
 	return bytes;
@@ -438,16 +439,15 @@ EXPORT_SYMBOL(iov_iter_init);
 static inline void data_start(const struct iov_iter *i,
 			      unsigned int *iter_headp, size_t *offp)
 {
-	unsigned int iter_head = i->head;
-	size_t off = i->iov_offset;
+	int off = i->last_offset;
 
-	if (off && (!allocated(pipe_buf(i->pipe, iter_head)) ||
-		    off == PAGE_SIZE)) {
-		iter_head++;
-		off = 0;
+	if (off > 0 && off < PAGE_SIZE) { // anon and not full
+		*iter_headp = i->pipe->head - 1;
+		*offp = off;
+	} else {
+		*iter_headp = i->pipe->head;
+		*offp = 0;
 	}
-	*iter_headp = iter_head;
-	*offp = off;
 }
 
 static size_t copy_pipe_to_iter(const void *addr, size_t bytes,
@@ -819,7 +819,7 @@ EXPORT_SYMBOL(copy_page_from_iter_atomic);
 static void pipe_advance(struct iov_iter *i, size_t size)
 {
 	struct pipe_inode_info *pipe = i->pipe;
-	unsigned int off = i->iov_offset;
+	int off = i->last_offset;
 
 	if (!off && !size) {
 		pipe_discard_from(pipe, i->start_head); // discard everything
@@ -829,10 +829,10 @@ static void pipe_advance(struct iov_iter *i, size_t size)
 	while (1) {
 		struct pipe_buffer *buf = pipe_buf(pipe, i->head);
 		if (off) /* make it relative to the beginning of buffer */
-			size += off - buf->offset;
+			size += abs(off) - buf->offset;
 		if (size <= buf->len) {
 			buf->len = size;
-			i->iov_offset = buf->offset + size;
+			i->last_offset = last_offset(buf);
 			break;
 		}
 		size -= buf->len;
@@ -916,7 +916,7 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll)
 			struct pipe_buffer *b = pipe_buf(pipe, --head);
 			if (unroll < b->len) {
 				b->len -= unroll;
-				i->iov_offset = b->offset + b->len;
+				i->last_offset = last_offset(b);
 				i->head = head;
 				return;
 			}
@@ -924,7 +924,7 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll)
 			pipe_buf_release(pipe, b);
 			pipe->head--;
 		}
-		i->iov_offset = 0;
+		i->last_offset = 0;
 		i->head = head;
 		return;
 	}
@@ -1027,7 +1027,7 @@ void iov_iter_pipe(struct iov_iter *i, unsigned int direction,
 		.pipe = pipe,
 		.head = pipe->head,
 		.start_head = pipe->head,
-		.iov_offset = 0,
+		.last_offset = 0,
 		.count = count
 	};
 }
@@ -1158,13 +1158,12 @@ bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask,
 		return iov_iter_aligned_bvec(i, addr_mask, len_mask);
 
 	if (iov_iter_is_pipe(i)) {
-		unsigned int p_mask = i->pipe->ring_size - 1;
 		size_t size = i->count;
 
 		if (size & len_mask)
 			return false;
-		if (size && allocated(&i->pipe->bufs[i->head & p_mask])) {
-			if (i->iov_offset & addr_mask)
+		if (size && i->last_offset > 0) {
+			if (i->last_offset & addr_mask)
 				return false;
 		}
 
@@ -1243,8 +1242,8 @@ unsigned long iov_iter_alignment(const struct iov_iter *i)
 	if (iov_iter_is_pipe(i)) {
 		size_t size = i->count;
 
-		if (size && i->iov_offset && allocated(pipe_buf(i->pipe, i->head)))
-			return size | i->iov_offset;
+		if (size && i->last_offset > 0)
+			return size | i->last_offset;
 		return size;
 	}
 
-- 
cgit v1.2.3-59-g8ed1b


From 12d426ab64a1c75f1b2ee5c33e933a4c16004049 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
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 <viro@zeniv.linux.org.uk>
---
 include/linux/pipe_fs_i.h | 20 --------------------
 lib/iov_iter.c            | 44 +++++++++++++++++++-------------------------
 2 files changed, 19 insertions(+), 45 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
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 8834f3f61220..12dda1013bea 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -436,18 +436,20 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
 }
 EXPORT_SYMBOL(iov_iter_init);
 
-static inline void data_start(const struct iov_iter *i,
-			      unsigned int *iter_headp, size_t *offp)
+// returns the offset in partial buffer (if any)
+static inline unsigned int pipe_npages(const struct iov_iter *i, int *npages)
 {
+	struct pipe_inode_info *pipe = i->pipe;
+	int used = pipe->head - pipe->tail;
 	int off = i->last_offset;
 
+	*npages = max((int)pipe->max_usage - used, 0);
+
 	if (off > 0 && off < PAGE_SIZE) { // anon and not full
-		*iter_headp = i->pipe->head - 1;
-		*offp = off;
-	} else {
-		*iter_headp = i->pipe->head;
-		*offp = 0;
+		(*npages)++;
+		return off;
 	}
+	return 0;
 }
 
 static size_t copy_pipe_to_iter(const void *addr, size_t bytes,
@@ -1318,18 +1320,16 @@ static ssize_t pipe_get_pages(struct iov_iter *i,
 		   struct page **pages, size_t maxsize, unsigned maxpages,
 		   size_t *start)
 {
-	unsigned int iter_head, npages;
+	unsigned int npages, off;
 	size_t capacity;
 
 	if (!sanity(i))
 		return -EFAULT;
 
-	data_start(i, &iter_head, start);
-	/* Amount of free space: some of this one + all after this one */
-	npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe);
-	capacity = min(npages, maxpages) * PAGE_SIZE - *start;
+	*start = off = pipe_npages(i, &npages);
+	capacity = min(npages, maxpages) * PAGE_SIZE - off;
 
-	return __pipe_get_pages(i, min(maxsize, capacity), pages, *start);
+	return __pipe_get_pages(i, min(maxsize, capacity), pages, off);
 }
 
 static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa,
@@ -1494,24 +1494,22 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
 		   size_t *start)
 {
 	struct page **p;
-	unsigned int iter_head, npages;
+	unsigned int npages, off;
 	ssize_t n;
 
 	if (!sanity(i))
 		return -EFAULT;
 
-	data_start(i, &iter_head, start);
-	/* Amount of free space: some of this one + all after this one */
-	npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe);
-	n = npages * PAGE_SIZE - *start;
+	*start = off = pipe_npages(i, &npages);
+	n = npages * PAGE_SIZE - off;
 	if (maxsize > n)
 		maxsize = n;
 	else
-		npages = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE);
+		npages = DIV_ROUND_UP(maxsize + off, PAGE_SIZE);
 	p = get_pages_array(npages);
 	if (!p)
 		return -ENOMEM;
-	n = __pipe_get_pages(i, maxsize, p, *start);
+	n = __pipe_get_pages(i, maxsize, p, off);
 	if (n > 0)
 		*pages = p;
 	else
@@ -1739,16 +1737,12 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages)
 	if (iov_iter_is_bvec(i))
 		return bvec_npages(i, maxpages);
 	if (iov_iter_is_pipe(i)) {
-		unsigned int iter_head;
 		int npages;
-		size_t off;
 
 		if (!sanity(i))
 			return 0;
 
-		data_start(i, &iter_head, &off);
-		/* some of this one + all after this one */
-		npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe);
+		pipe_npages(i, &npages);
 		return min(npages, maxpages);
 	}
 	if (iov_iter_is_xarray(i)) {
-- 
cgit v1.2.3-59-g8ed1b


From 1ef255e257173f4bc44317ef2076e7e0de688fdf Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
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 <jlayton@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/vhost/scsi.c |  4 +---
 fs/ceph/file.c       |  3 +--
 fs/cifs/file.c       |  6 ++----
 fs/cifs/misc.c       |  3 +--
 fs/direct-io.c       |  3 +--
 fs/fuse/dev.c        |  3 +--
 fs/fuse/file.c       |  3 +--
 fs/nfs/direct.c      |  6 ++----
 include/linux/uio.h  | 20 ++++++++++++++++++++
 net/core/datagram.c  |  3 +--
 net/core/skmsg.c     |  3 +--
 net/rds/message.c    |  3 +--
 net/tls/tls_sw.c     |  4 +---
 13 files changed, 34 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index ffd9e6c2ffc1..9b65509424dc 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -643,14 +643,12 @@ vhost_scsi_map_to_sgl(struct vhost_scsi_cmd *cmd,
 	size_t offset;
 	unsigned int npages = 0;
 
-	bytes = iov_iter_get_pages(iter, pages, LONG_MAX,
+	bytes = iov_iter_get_pages2(iter, pages, LONG_MAX,
 				VHOST_SCSI_PREALLOC_UPAGES, &offset);
 	/* No pages were pinned */
 	if (bytes <= 0)
 		return bytes < 0 ? bytes : -EFAULT;
 
-	iov_iter_advance(iter, bytes);
-
 	while (bytes) {
 		unsigned n = min_t(unsigned, PAGE_SIZE - offset, bytes);
 		sg_set_page(sg++, pages[npages++], n, offset);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index c535de5852bf..8fab5db16c73 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -95,12 +95,11 @@ static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize,
 		size_t start;
 		int idx = 0;
 
-		bytes = iov_iter_get_pages(iter, pages, maxsize - size,
+		bytes = iov_iter_get_pages2(iter, pages, maxsize - size,
 					   ITER_GET_BVECS_PAGES, &start);
 		if (bytes < 0)
 			return size ?: bytes;
 
-		iov_iter_advance(iter, bytes);
 		size += bytes;
 
 		for ( ; bytes; idx++, bvec_idx++) {
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index e1e05b253daa..3ba013e2987f 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3022,7 +3022,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		if (ctx->direct_io) {
 			ssize_t result;
 
-			result = iov_iter_get_pages_alloc(
+			result = iov_iter_get_pages_alloc2(
 				from, &pagevec, cur_len, &start);
 			if (result < 0) {
 				cifs_dbg(VFS,
@@ -3036,7 +3036,6 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 				break;
 			}
 			cur_len = (size_t)result;
-			iov_iter_advance(from, cur_len);
 
 			nr_pages =
 				(cur_len + start + PAGE_SIZE - 1) / PAGE_SIZE;
@@ -3758,7 +3757,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		if (ctx->direct_io) {
 			ssize_t result;
 
-			result = iov_iter_get_pages_alloc(
+			result = iov_iter_get_pages_alloc2(
 					&direct_iov, &pagevec,
 					cur_len, &start);
 			if (result < 0) {
@@ -3774,7 +3773,6 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 				break;
 			}
 			cur_len = (size_t)result;
-			iov_iter_advance(&direct_iov, cur_len);
 
 			rdata = cifs_readdata_direct_alloc(
 					pagevec, cifs_uncached_readv_complete);
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 0e84e6fcf8ab..f833953bab61 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -1029,7 +1029,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw)
 	saved_len = count;
 
 	while (count && npages < max_pages) {
-		rc = iov_iter_get_pages(iter, pages, count, max_pages, &start);
+		rc = iov_iter_get_pages2(iter, pages, count, max_pages, &start);
 		if (rc < 0) {
 			cifs_dbg(VFS, "Couldn't get user pages (rc=%zd)\n", rc);
 			break;
@@ -1041,7 +1041,6 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw)
 			break;
 		}
 
-		iov_iter_advance(iter, rc);
 		count -= rc;
 		rc += start;
 		cur_npages = DIV_ROUND_UP(rc, PAGE_SIZE);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index c7fc01c2d509..f669163d5860 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -169,7 +169,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
 	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
 	ssize_t ret;
 
-	ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
+	ret = iov_iter_get_pages2(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
 				&sdio->from);
 
 	if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) {
@@ -191,7 +191,6 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
 	}
 
 	if (ret >= 0) {
-		iov_iter_advance(sdio->iter, ret);
 		ret += sdio->from;
 		sdio->head = 0;
 		sdio->tail = (ret + PAGE_SIZE - 1) / PAGE_SIZE;
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 8d657c2cd6f7..51897427a534 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -730,14 +730,13 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 		}
 	} else {
 		size_t off;
-		err = iov_iter_get_pages(cs->iter, &page, PAGE_SIZE, 1, &off);
+		err = iov_iter_get_pages2(cs->iter, &page, PAGE_SIZE, 1, &off);
 		if (err < 0)
 			return err;
 		BUG_ON(!err);
 		cs->len = err;
 		cs->offset = off;
 		cs->pg = page;
-		iov_iter_advance(cs->iter, err);
 	}
 
 	return lock_request(cs->req);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index c982e3afe3b4..69e19fc0afc1 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1401,14 +1401,13 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
 	while (nbytes < *nbytesp && ap->num_pages < max_pages) {
 		unsigned npages;
 		size_t start;
-		ret = iov_iter_get_pages(ii, &ap->pages[ap->num_pages],
+		ret = iov_iter_get_pages2(ii, &ap->pages[ap->num_pages],
 					*nbytesp - nbytes,
 					max_pages - ap->num_pages,
 					&start);
 		if (ret < 0)
 			break;
 
-		iov_iter_advance(ii, ret);
 		nbytes += ret;
 
 		ret += start;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 022e1ce63e62..c275c83f0aef 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -364,13 +364,12 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 		size_t pgbase;
 		unsigned npages, i;
 
-		result = iov_iter_get_pages_alloc(iter, &pagevec, 
+		result = iov_iter_get_pages_alloc2(iter, &pagevec,
 						  rsize, &pgbase);
 		if (result < 0)
 			break;
 	
 		bytes = result;
-		iov_iter_advance(iter, bytes);
 		npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
 		for (i = 0; i < npages; i++) {
 			struct nfs_page *req;
@@ -812,13 +811,12 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 		size_t pgbase;
 		unsigned npages, i;
 
-		result = iov_iter_get_pages_alloc(iter, &pagevec, 
+		result = iov_iter_get_pages_alloc2(iter, &pagevec,
 						  wsize, &pgbase);
 		if (result < 0)
 			break;
 
 		bytes = result;
-		iov_iter_advance(iter, bytes);
 		npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
 		for (i = 0; i < npages; i++) {
 			struct nfs_page *req;
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
diff --git a/net/core/datagram.c b/net/core/datagram.c
index f3988ef8e9af..7255531f63ae 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -632,12 +632,11 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 		if (frag == MAX_SKB_FRAGS)
 			return -EMSGSIZE;
 
-		copied = iov_iter_get_pages(from, pages, length,
+		copied = iov_iter_get_pages2(from, pages, length,
 					    MAX_SKB_FRAGS - frag, &start);
 		if (copied < 0)
 			return -EFAULT;
 
-		iov_iter_advance(from, copied);
 		length -= copied;
 
 		truesize = PAGE_ALIGN(copied + start);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 81627892bdd4..cf3c24c8610d 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -324,14 +324,13 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 			goto out;
 		}
 
-		copied = iov_iter_get_pages(from, pages, bytes, maxpages,
+		copied = iov_iter_get_pages2(from, pages, bytes, maxpages,
 					    &offset);
 		if (copied <= 0) {
 			ret = -EFAULT;
 			goto out;
 		}
 
-		iov_iter_advance(from, copied);
 		bytes -= copied;
 		msg->sg.size += copied;
 
diff --git a/net/rds/message.c b/net/rds/message.c
index 799034e0f513..d74be4e3f3fa 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -391,7 +391,7 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter *
 		size_t start;
 		ssize_t copied;
 
-		copied = iov_iter_get_pages(from, &pages, PAGE_SIZE,
+		copied = iov_iter_get_pages2(from, &pages, PAGE_SIZE,
 					    1, &start);
 		if (copied < 0) {
 			struct mmpin *mmp;
@@ -405,7 +405,6 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter *
 			goto err;
 		}
 		total_copied += copied;
-		iov_iter_advance(from, copied);
 		length -= copied;
 		sg_set_page(sg, pages, copied, start);
 		rm->data.op_nents++;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 17db8c8811fa..f76119f62f1b 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1352,7 +1352,7 @@ static int tls_setup_from_iter(struct iov_iter *from,
 			rc = -EFAULT;
 			goto out;
 		}
-		copied = iov_iter_get_pages(from, pages,
+		copied = iov_iter_get_pages2(from, pages,
 					    length,
 					    maxpages, &offset);
 		if (copied <= 0) {
@@ -1360,8 +1360,6 @@ static int tls_setup_from_iter(struct iov_iter *from,
 			goto out;
 		}
 
-		iov_iter_advance(from, copied);
-
 		length -= copied;
 		size += copied;
 		while (copied) {
-- 
cgit v1.2.3-59-g8ed1b


From eba2d3d798295dc43cae8fade102f9d083a2a741 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
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 <jlayton@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h | 24 ++----------------------
 lib/iov_iter.c      | 27 ++++++++++++++++++---------
 2 files changed, 20 insertions(+), 31 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
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index f003a20d8683..c48c83602aae 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1328,6 +1328,7 @@ static ssize_t pipe_get_pages(struct iov_iter *i,
 		left -= PAGE_SIZE - off;
 		if (left <= 0) {
 			buf->len += maxsize;
+			iov_iter_advance(i, maxsize);
 			return maxsize;
 		}
 		buf->len = PAGE_SIZE;
@@ -1347,7 +1348,9 @@ static ssize_t pipe_get_pages(struct iov_iter *i,
 	}
 	if (!npages)
 		return -EFAULT;
-	return maxsize - left;
+	maxsize -= left;
+	iov_iter_advance(i, maxsize);
+	return maxsize;
 }
 
 static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa,
@@ -1397,7 +1400,9 @@ static ssize_t iter_xarray_get_pages(struct iov_iter *i,
 	if (nr == 0)
 		return 0;
 
-	return min_t(size_t, nr * PAGE_SIZE - offset, maxsize);
+	maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize);
+	iov_iter_advance(i, maxsize);
+	return maxsize;
 }
 
 /* must be done on non-empty ITER_UBUF or ITER_IOVEC one */
@@ -1469,7 +1474,9 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
 		res = get_user_pages_fast(addr, n, gup_flags, *pages);
 		if (unlikely(res <= 0))
 			return res;
-		return min_t(size_t, maxsize, res * PAGE_SIZE - *start);
+		maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - *start);
+		iov_iter_advance(i, maxsize);
+		return maxsize;
 	}
 	if (iov_iter_is_bvec(i)) {
 		struct page **p;
@@ -1481,8 +1488,10 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
 			return -ENOMEM;
 		p = *pages;
 		for (int k = 0; k < n; k++)
-			get_page(*p++ = page++);
-		return min_t(size_t, maxsize, n * PAGE_SIZE - *start);
+			get_page(p[k] = page + k);
+		maxsize = min_t(size_t, maxsize, n * PAGE_SIZE - *start);
+		iov_iter_advance(i, maxsize);
+		return maxsize;
 	}
 	if (iov_iter_is_pipe(i))
 		return pipe_get_pages(i, pages, maxsize, maxpages, start);
@@ -1491,7 +1500,7 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
 	return -EFAULT;
 }
 
-ssize_t iov_iter_get_pages(struct iov_iter *i,
+ssize_t iov_iter_get_pages2(struct iov_iter *i,
 		   struct page **pages, size_t maxsize, unsigned maxpages,
 		   size_t *start)
 {
@@ -1501,9 +1510,9 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
 
 	return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, start);
 }
-EXPORT_SYMBOL(iov_iter_get_pages);
+EXPORT_SYMBOL(iov_iter_get_pages2);
 
-ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
+ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i,
 		   struct page ***pages, size_t maxsize,
 		   size_t *start)
 {
@@ -1518,7 +1527,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 	}
 	return len;
 }
-EXPORT_SYMBOL(iov_iter_get_pages_alloc);
+EXPORT_SYMBOL(iov_iter_get_pages_alloc2);
 
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum,
 			       struct iov_iter *i)
-- 
cgit v1.2.3-59-g8ed1b