iov_iter: Convert iterate*() to inline funcs

Convert the iov_iter iteration macros to inline functions to make the code
easier to follow.

The functions are marked __always_inline as we don't want to end up with
indirect calls in the code.  This, however, leaves dealing with ->copy_mc
in an awkard situation since the step function (memcpy_from_iter_mc())
needs to test the flag in the iterator, but isn't passed the iterator.
This will be dealt with in a follow-up patch.

The variable names in the per-type iterator functions have been harmonised
as much as possible and made clearer as to the variable purpose.

The iterator functions are also moved to a header file so that other
operations that need to scan over an iterator can be added.  For instance,
the rbd driver could use this to scan a buffer to see if it is all zeros
and libceph could use this to generate a crc.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/3710261.1691764329@warthog.procyon.org.uk/ # v1
Link: https://lore.kernel.org/r/855.1692047347@warthog.procyon.org.uk/ # v2
Link: https://lore.kernel.org/r/20230816120741.534415-1-dhowells@redhat.com/ # v3
Link: https://lore.kernel.org/r/20230925120309.1731676-8-dhowells@redhat.com
cc: Alexander Viro <viro@zeniv.linux.org.uk>
cc: Jens Axboe <axboe@kernel.dk>
cc: Christoph Hellwig <hch@lst.de>
cc: Christian Brauner <christian@brauner.io>
cc: Matthew Wilcox <willy@infradead.org>
cc: Linus Torvalds <torvalds@linux-foundation.org>
cc: David Laight <David.Laight@ACULAB.COM>
cc: linux-block@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 175 insertions, 241 deletions

diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 227c9f536b94..65374ee91ecd 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -13,189 +13,69 @@
 #include <net/checksum.h>
 #include <linux/scatterlist.h>
 #include <linux/instrumented.h>
+#include <linux/iov_iter.h>
 
-/* covers ubuf and kbuf alike */
-#define iterate_buf(i, n, base, len, off, __p, STEP) {		\
-	size_t __maybe_unused off = 0;				\
-	len = n;						\
-	base = __p + i->iov_offset;				\
-	len -= (STEP);						\
-	i->iov_offset += len;					\
-	n = len;						\
-}
-
-/* covers iovec and kvec alike */
-#define iterate_iovec(i, n, base, len, off, __p, STEP) {	\
-	size_t off = 0;						\
-	size_t skip = i->iov_offset;				\
-	do {							\
-		len = min(n, __p->iov_len - skip);		\
-		if (likely(len)) {				\
-			base = __p->iov_base + skip;		\
-			len -= (STEP);				\
-			off += len;				\
-			skip += len;				\
-			n -= len;				\
-			if (skip < __p->iov_len)		\
-				break;				\
-		}						\
-		__p++;						\
-		skip = 0;					\
-	} while (n);						\
-	i->iov_offset = skip;					\
-	n = off;						\
-}
-
-#define iterate_bvec(i, n, base, len, off, p, STEP) {		\
-	size_t off = 0;						\
-	unsigned skip = i->iov_offset;				\
-	while (n) {						\
-		unsigned offset = p->bv_offset + skip;		\
-		unsigned left;					\
-		void *kaddr = kmap_local_page(p->bv_page +	\
-					offset / PAGE_SIZE);	\
-		base = kaddr + offset % PAGE_SIZE;		\
-		len = min(min(n, (size_t)(p->bv_len - skip)),	\
-		     (size_t)(PAGE_SIZE - offset % PAGE_SIZE));	\
-		left = (STEP);					\
-		kunmap_local(kaddr);				\
-		len -= left;					\
-		off += len;					\
-		skip += len;					\
-		if (skip == p->bv_len) {			\
-			skip = 0;				\
-			p++;					\
-		}						\
-		n -= len;					\
-		if (left)					\
-			break;					\
-	}							\
-	i->iov_offset = skip;					\
-	n = off;						\
-}
-
-#define iterate_xarray(i, n, base, len, __off, STEP) {		\
-	__label__ __out;					\
-	size_t __off = 0;					\
-	struct folio *folio;					\
-	loff_t start = i->xarray_start + i->iov_offset;		\
-	pgoff_t index = start / PAGE_SIZE;			\
-	XA_STATE(xas, i->xarray, index);			\
-								\
-	len = PAGE_SIZE - offset_in_page(start);		\
-	rcu_read_lock();					\
-	xas_for_each(&xas, folio, ULONG_MAX) {			\
-		unsigned left;					\
-		size_t offset;					\
-		if (xas_retry(&xas, folio))			\
-			continue;				\
-		if (WARN_ON(xa_is_value(folio)))		\
-			break;					\
-		if (WARN_ON(folio_test_hugetlb(folio)))		\
-			break;					\
-		offset = offset_in_folio(folio, start + __off);	\
-		while (offset < folio_size(folio)) {		\
-			base = kmap_local_folio(folio, offset);	\
-			len = min(n, len);			\
-			left = (STEP);				\
-			kunmap_local(base);			\
-			len -= left;				\
-			__off += len;				\
-			n -= len;				\
-			if (left || n == 0)			\
-				goto __out;			\
-			offset += len;				\
-			len = PAGE_SIZE;			\
-		}						\
-	}							\
-__out:								\
-	rcu_read_unlock();					\
-	i->iov_offset += __off;					\
-	n = __off;						\
-}
-
-#define __iterate_and_advance(i, n, base, len, off, I, K) {	\
-	if (unlikely(i->count < n))				\
-		n = i->count;					\
-	if (likely(n)) {					\
-		if (likely(iter_is_ubuf(i))) {			\
-			void __user *base;			\
-			size_t len;				\
-			iterate_buf(i, n, base, len, off,	\
-						i->ubuf, (I)) 	\
-		} else if (likely(iter_is_iovec(i))) {		\
-			const struct iovec *iov = iter_iov(i);	\
-			void __user *base;			\
-			size_t len;				\
-			iterate_iovec(i, n, base, len, off,	\
-						iov, (I))	\
-			i->nr_segs -= iov - iter_iov(i);	\
-			i->__iov = iov;				\
-		} else if (iov_iter_is_bvec(i)) {		\
-			const struct bio_vec *bvec = i->bvec;	\
-			void *base;				\
-			size_t len;				\
-			iterate_bvec(i, n, base, len, off,	\
-						bvec, (K))	\
-			i->nr_segs -= bvec - i->bvec;		\
-			i->bvec = bvec;				\
-		} else if (iov_iter_is_kvec(i)) {		\
-			const struct kvec *kvec = i->kvec;	\
-			void *base;				\
-			size_t len;				\
-			iterate_iovec(i, n, base, len, off,	\
-						kvec, (K))	\
-			i->nr_segs -= kvec - i->kvec;		\
-			i->kvec = kvec;				\
-		} else if (iov_iter_is_xarray(i)) {		\
-			void *base;				\
-			size_t len;				\
-			iterate_xarray(i, n, base, len, off,	\
-							(K))	\
-		}						\
-		i->count -= n;					\
-	}							\
-}
-#define iterate_and_advance(i, n, base, len, off, I, K) \
-	__iterate_and_advance(i, n, base, len, off, I, ((void)(K),0))
-
-static int copyout(void __user *to, const void *from, size_t n)
+static __always_inline
+size_t copy_to_user_iter(void __user *iter_to, size_t progress,
+			 size_t len, void *from, void *priv2)
 {
 	if (should_fail_usercopy())
-		return n;
-	if (access_ok(to, n)) {
-		instrument_copy_to_user(to, from, n);
-		n = raw_copy_to_user(to, from, n);
+		return len;
+	if (access_ok(iter_to, len)) {
+		from += progress;
+		instrument_copy_to_user(iter_to, from, len);
+		len = raw_copy_to_user(iter_to, from, len);
 	}
-	return n;
+	return len;
 }
 
-static int copyout_nofault(void __user *to, const void *from, size_t n)
+static __always_inline
+size_t copy_to_user_iter_nofault(void __user *iter_to, size_t progress,
+				 size_t len, void *from, void *priv2)
 {
-	long res;
+	ssize_t res;
 
 	if (should_fail_usercopy())
-		return n;
-
-	res = copy_to_user_nofault(to, from, n);
+		return len;
 
-	return res < 0 ? n : res;
+	from += progress;
+	res = copy_to_user_nofault(iter_to, from, len);
+	return res < 0 ? len : res;
 }
 
-static int copyin(void *to, const void __user *from, size_t n)
+static __always_inline
+size_t copy_from_user_iter(void __user *iter_from, size_t progress,
+			   size_t len, void *to, void *priv2)
 {
-	size_t res = n;
+	size_t res = len;
 
 	if (should_fail_usercopy())
-		return n;
-	if (access_ok(from, n)) {
-		instrument_copy_from_user_before(to, from, n);
-		res = raw_copy_from_user(to, from, n);
-		instrument_copy_from_user_after(to, from, n, res);
+		return len;
+	if (access_ok(iter_from, len)) {
+		to += progress;
+		instrument_copy_from_user_before(to, iter_from, len);
+		res = raw_copy_from_user(to, iter_from, len);
+		instrument_copy_from_user_after(to, iter_from, len, res);
 	}
 	return res;
 }
 
+static __always_inline
+size_t memcpy_to_iter(void *iter_to, size_t progress,
+		      size_t len, void *from, void *priv2)
+{
+	memcpy(iter_to, from + progress, len);
+	return 0;
+}
+
+static __always_inline
+size_t memcpy_from_iter(void *iter_from, size_t progress,
+			size_t len, void *to, void *priv2)
+{
+	memcpy(to + progress, iter_from, len);
+	return 0;
+}
+
 /*
  * fault_in_iov_iter_readable - fault in iov iterator for reading
  * @i: iterator
@@ -312,23 +192,29 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 		return 0;
 	if (user_backed_iter(i))
 		might_fault();
-	iterate_and_advance(i, bytes, base, len, off,
-		copyout(base, addr + off, len),
-		memcpy(base, addr + off, len)
-	)
-
-	return bytes;
+	return iterate_and_advance(i, bytes, (void *)addr,
+				   copy_to_user_iter, memcpy_to_iter);
 }
 EXPORT_SYMBOL(_copy_to_iter);
 
 #ifdef CONFIG_ARCH_HAS_COPY_MC
-static int copyout_mc(void __user *to, const void *from, size_t n)
-{
-	if (access_ok(to, n)) {
-		instrument_copy_to_user(to, from, n);
-		n = copy_mc_to_user((__force void *) to, from, n);
+static __always_inline
+size_t copy_to_user_iter_mc(void __user *iter_to, size_t progress,
+			    size_t len, void *from, void *priv2)
+{
+	if (access_ok(iter_to, len)) {
+		from += progress;
+		instrument_copy_to_user(iter_to, from, len);
+		len = copy_mc_to_user(iter_to, from, len);
 	}
-	return n;
+	return len;
+}
+
+static __always_inline
+size_t memcpy_to_iter_mc(void *iter_to, size_t progress,
+			 size_t len, void *from, void *priv2)
+{
+	return copy_mc_to_kernel(iter_to, from + progress, len);
 }
 
 /**
@@ -361,22 +247,20 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 		return 0;
 	if (user_backed_iter(i))
 		might_fault();
-	__iterate_and_advance(i, bytes, base, len, off,
-		copyout_mc(base, addr + off, len),
-		copy_mc_to_kernel(base, addr + off, len)
-	)
-
-	return bytes;
+	return iterate_and_advance(i, bytes, (void *)addr,
+				   copy_to_user_iter_mc, memcpy_to_iter_mc);
 }
 EXPORT_SYMBOL_GPL(_copy_mc_to_iter);
 #endif /* CONFIG_ARCH_HAS_COPY_MC */
 
-static void *memcpy_from_iter(struct iov_iter *i, void *to, const void *from,
-				 size_t size)
+static size_t memcpy_from_iter_mc(void *iter_from, size_t progress,
+				  size_t len, void *to, void *priv2)
 {
-	if (iov_iter_is_copy_mc(i))
-		return (void *)copy_mc_to_kernel(to, from, size);
-	return memcpy(to, from, size);
+	struct iov_iter *iter = priv2;
+
+	if (iov_iter_is_copy_mc(iter))
+		return copy_mc_to_kernel(to + progress, iter_from, len);
+	return memcpy_from_iter(iter_from, progress, len, to, priv2);
 }
 
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
@@ -386,30 +270,46 @@ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 
 	if (user_backed_iter(i))
 		might_fault();
-	iterate_and_advance(i, bytes, base, len, off,
-		copyin(addr + off, base, len),
-		memcpy_from_iter(i, addr + off, base, len)
-	)
-
-	return bytes;
+	return iterate_and_advance2(i, bytes, addr, i,
+				    copy_from_user_iter,
+				    memcpy_from_iter_mc);
 }
 EXPORT_SYMBOL(_copy_from_iter);
 
+static __always_inline
+size_t copy_from_user_iter_nocache(void __user *iter_from, size_t progress,
+				   size_t len, void *to, void *priv2)
+{
+	return __copy_from_user_inatomic_nocache(to + progress, iter_from, len);
+}
+
 size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (WARN_ON_ONCE(!i->data_source))
 		return 0;
 
-	iterate_and_advance(i, bytes, base, len, off,
-		__copy_from_user_inatomic_nocache(addr + off, base, len),
-		memcpy(addr + off, base, len)
-	)
-
-	return bytes;
+	return iterate_and_advance(i, bytes, addr,
+				   copy_from_user_iter_nocache,
+				   memcpy_from_iter);
 }
 EXPORT_SYMBOL(_copy_from_iter_nocache);
 
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+static __always_inline
+size_t copy_from_user_iter_flushcache(void __user *iter_from, size_t progress,
+				      size_t len, void *to, void *priv2)
+{
+	return __copy_from_user_flushcache(to + progress, iter_from, len);
+}
+
+static __always_inline
+size_t memcpy_from_iter_flushcache(void *iter_from, size_t progress,
+				   size_t len, void *to, void *priv2)
+{
+	memcpy_flushcache(to + progress, iter_from, len);
+	return 0;
+}
+
 /**
  * _copy_from_iter_flushcache - write destination through cpu cache
  * @addr: destination kernel address
@@ -431,12 +331,9 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 	if (WARN_ON_ONCE(!i->data_source))
 		return 0;
 
-	iterate_and_advance(i, bytes, base, len, off,
-		__copy_from_user_flushcache(addr + off, base, len),
-		memcpy_flushcache(addr + off, base, len)
-	)
-
-	return bytes;
+	return iterate_and_advance(i, bytes, addr,
+				   copy_from_user_iter_flushcache,
+				   memcpy_from_iter_flushcache);
 }
 EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache);
 #endif
@@ -508,10 +405,9 @@ size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t byte
 		void *kaddr = kmap_local_page(page);
 		size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
 
-		iterate_and_advance(i, n, base, len, off,
-			copyout_nofault(base, kaddr + offset + off, len),
-			memcpy(base, kaddr + offset + off, len)
-		)
+		n = iterate_and_advance(i, bytes, kaddr,
+					copy_to_user_iter_nofault,
+					memcpy_to_iter);
 		kunmap_local(kaddr);
 		res += n;
 		bytes -= n;
@@ -554,14 +450,25 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 }
 EXPORT_SYMBOL(copy_page_from_iter);
 
-size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
+static __always_inline
+size_t zero_to_user_iter(void __user *iter_to, size_t progress,
+			 size_t len, void *priv, void *priv2)
 {
-	iterate_and_advance(i, bytes, base, len, count,
-		clear_user(base, len),
-		memset(base, 0, len)
-	)
+	return clear_user(iter_to, len);
+}
 
-	return bytes;
+static __always_inline
+size_t zero_to_iter(void *iter_to, size_t progress,
+		    size_t len, void *priv, void *priv2)
+{
+	memset(iter_to, 0, len);
+	return 0;
+}
+
+size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
+{
+	return iterate_and_advance(i, bytes, NULL,
+				   zero_to_user_iter, zero_to_iter);
 }
 EXPORT_SYMBOL(iov_iter_zero);
 
@@ -586,10 +493,9 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
 		}
 
 		p = kmap_atomic(page) + offset;
-		iterate_and_advance(i, n, base, len, off,
-			copyin(p + off, base, len),
-			memcpy_from_iter(i, p + off, base, len)
-		)
+		n = iterate_and_advance2(i, n, p, i,
+					 copy_from_user_iter,
+					 memcpy_from_iter_mc);
 		kunmap_atomic(p);
 		copied += n;
 		offset += n;
@@ -1180,32 +1086,64 @@ ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i,
 }
 EXPORT_SYMBOL(iov_iter_get_pages_alloc2);
 
+static __always_inline
+size_t copy_from_user_iter_csum(void __user *iter_from, size_t progress,
+				size_t len, void *to, void *priv2)
+{
+	__wsum next, *csum = priv2;
+
+	next = csum_and_copy_from_user(iter_from, to + progress, len);
+	*csum = csum_block_add(*csum, next, progress);
+	return next ? 0 : len;
+}
+
+static __always_inline
+size_t memcpy_from_iter_csum(void *iter_from, size_t progress,
+			     size_t len, void *to, void *priv2)
+{
+	__wsum *csum = priv2;
+
+	*csum = csum_and_memcpy(to + progress, iter_from, len, *csum, progress);
+	return 0;
+}
+
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum,
 			       struct iov_iter *i)
 {
-	__wsum sum, next;
-	sum = *csum;
 	if (WARN_ON_ONCE(!i->data_source))
 		return 0;
-
-	iterate_and_advance(i, bytes, base, len, off, ({
-		next = csum_and_copy_from_user(base, addr + off, len);
-		sum = csum_block_add(sum, next, off);
-		next ? 0 : len;
-	}), ({
-		sum = csum_and_memcpy(addr + off, base, len, sum, off);
-	})
-	)
-	*csum = sum;
-	return bytes;
+	return iterate_and_advance2(i, bytes, addr, csum,
+				    copy_from_user_iter_csum,
+				    memcpy_from_iter_csum);
 }
 EXPORT_SYMBOL(csum_and_copy_from_iter);
 
+static __always_inline
+size_t copy_to_user_iter_csum(void __user *iter_to, size_t progress,
+			      size_t len, void *from, void *priv2)
+{
+	__wsum next, *csum = priv2;
+
+	next = csum_and_copy_to_user(from + progress, iter_to, len);
+	*csum = csum_block_add(*csum, next, progress);
+	return next ? 0 : len;
+}
+
+static __always_inline
+size_t memcpy_to_iter_csum(void *iter_to, size_t progress,
+			   size_t len, void *from, void *priv2)
+{
+	__wsum *csum = priv2;
+
+	*csum = csum_and_memcpy(iter_to, from + progress, len, *csum, progress);
+	return 0;
+}
+
 size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate,
 			     struct iov_iter *i)
 {
 	struct csum_state *csstate = _csstate;
-	__wsum sum, next;
+	__wsum sum;
 
 	if (WARN_ON_ONCE(i->data_source))
 		return 0;
@@ -1219,14 +1157,10 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate,
 	}
 
 	sum = csum_shift(csstate->csum, csstate->off);
-	iterate_and_advance(i, bytes, base, len, off, ({
-		next = csum_and_copy_to_user(addr + off, base, len);
-		sum = csum_block_add(sum, next, off);
-		next ? 0 : len;
-	}), ({
-		sum = csum_and_memcpy(base, addr + off, len, sum, off);
-	})
-	)
+	
+	bytes = iterate_and_advance2(i, bytes, (void *)addr, &sum,
+				     copy_to_user_iter_csum,
+				     memcpy_to_iter_csum);
 	csstate->csum = csum_shift(sum, csstate->off);
 	csstate->off += bytes;
 	return bytes;