// SPDX-License-Identifier: GPL-2.0-only
-#include <crypto/hash.h>
#include <linux/export.h>
#include <linux/bvec.h>
#include <linux/fault-inject-usercopy.h>
#include <linux/vmalloc.h>
#include <linux/splice.h>
#include <linux/compat.h>
-#include <net/checksum.h>
#include <linux/scatterlist.h>
#include <linux/instrumented.h>
+#include <linux/iov_iter.h>
-#define PIPE_PARANOIA /* for now */
-
-/* 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 = i->iov; \
- void __user *base; \
- size_t len; \
- iterate_iovec(i, n, base, len, off, \
- iov, (I)) \
- i->nr_segs -= iov - i->iov; \
- 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 copyin(void *to, const void __user *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)
{
+ ssize_t res;
+
if (should_fail_usercopy())
- return n;
- if (access_ok(from, n)) {
- instrument_copy_from_user(to, from, n);
- n = raw_copy_from_user(to, from, n);
- }
- return n;
-}
+ return len;
-static inline struct pipe_buffer *pipe_buf(const struct pipe_inode_info *pipe,
- unsigned int slot)
-{
- return &pipe->bufs[slot & (pipe->ring_size - 1)];
+ from += progress;
+ res = copy_to_user_nofault(iter_to, from, len);
+ return res < 0 ? len : res;
}
-#ifdef PIPE_PARANOIA
-static bool sanity(const struct iov_iter *i)
+static __always_inline
+size_t copy_from_user_iter(void __user *iter_from, size_t progress,
+ size_t len, void *to, void *priv2)
{
- struct pipe_inode_info *pipe = i->pipe;
- unsigned int p_head = pipe->head;
- unsigned int p_tail = pipe->tail;
- unsigned int p_occupancy = pipe_occupancy(p_head, p_tail);
- unsigned int i_head = i->head;
- unsigned int idx;
-
- if (i->last_offset) {
- struct pipe_buffer *p;
- if (unlikely(p_occupancy == 0))
- goto Bad; // pipe must be non-empty
- if (unlikely(i_head != p_head - 1))
- goto Bad; // must be at the last buffer...
+ size_t res = len;
- p = pipe_buf(pipe, i_head);
- if (unlikely(p->offset + p->len != abs(i->last_offset)))
- goto Bad; // ... at the end of segment
- } else {
- if (i_head != p_head)
- goto Bad; // must be right after the last buffer
- }
- return true;
-Bad:
- 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++)
- printk(KERN_ERR "[%p %p %d %d]\n",
- pipe->bufs[idx].ops,
- pipe->bufs[idx].page,
- pipe->bufs[idx].offset,
- pipe->bufs[idx].len);
- WARN_ON(1);
- return false;
-}
-#else
-#define sanity(i) true
-#endif
-
-static struct page *push_anon(struct pipe_inode_info *pipe, unsigned size)
-{
- struct page *page = alloc_page(GFP_USER);
- if (page) {
- struct pipe_buffer *buf = pipe_buf(pipe, pipe->head++);
- *buf = (struct pipe_buffer) {
- .ops = &default_pipe_buf_ops,
- .page = page,
- .offset = 0,
- .len = size
- };
+ if (should_fail_usercopy())
+ 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 page;
-}
-
-static void push_page(struct pipe_inode_info *pipe, struct page *page,
- unsigned int offset, unsigned int size)
-{
- struct pipe_buffer *buf = pipe_buf(pipe, pipe->head++);
- *buf = (struct pipe_buffer) {
- .ops = &page_cache_pipe_buf_ops,
- .page = page,
- .offset = offset,
- .len = size
- };
- get_page(page);
-}
-
-static inline int last_offset(const struct pipe_buffer *buf)
-{
- if (buf->ops == &default_pipe_buf_ops)
- return buf->len; // buf->offset is 0 for those
- else
- return -(buf->offset + buf->len);
+ return res;
}
-static struct page *append_pipe(struct iov_iter *i, size_t size,
- unsigned int *off)
+static __always_inline
+size_t memcpy_to_iter(void *iter_to, size_t progress,
+ size_t len, void *from, void *priv2)
{
- struct pipe_inode_info *pipe = i->pipe;
- int offset = i->last_offset;
- struct pipe_buffer *buf;
- struct page *page;
-
- if (offset > 0 && offset < PAGE_SIZE) {
- // some space in the last buffer; add to it
- buf = pipe_buf(pipe, pipe->head - 1);
- 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;
- size = min_t(size_t, size, PAGE_SIZE);
- if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
- return NULL;
- page = push_anon(pipe, size);
- if (!page)
- return NULL;
- i->head = pipe->head - 1;
- i->last_offset = size;
- i->count -= size;
- return page;
+ memcpy(iter_to, from + progress, len);
+ return 0;
}
-static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes,
- struct iov_iter *i)
+static __always_inline
+size_t memcpy_from_iter(void *iter_from, size_t progress,
+ size_t len, void *to, void *priv2)
{
- struct pipe_inode_info *pipe = i->pipe;
- unsigned int head = pipe->head;
-
- if (unlikely(bytes > i->count))
- bytes = i->count;
-
- if (unlikely(!bytes))
- return 0;
-
- if (!sanity(i))
- return 0;
-
- 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->last_offset -= bytes;
- i->count -= bytes;
- return bytes;
- }
- }
- if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
- return 0;
-
- push_page(pipe, page, offset, bytes);
- i->last_offset = -(offset + bytes);
- i->head = head;
- i->count -= bytes;
- return bytes;
+ memcpy(to + progress, iter_from, len);
+ return 0;
}
/*
size_t skip;
size -= count;
- for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) {
+ for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) {
size_t len = min(count, p->iov_len - skip);
size_t ret;
size_t skip;
size -= count;
- for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) {
+ for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) {
size_t len = min(count, p->iov_len - skip);
size_t ret;
*i = (struct iov_iter) {
.iter_type = ITER_IOVEC,
.nofault = false,
- .user_backed = true,
.data_source = direction,
- .iov = iov,
+ .__iov = iov,
.nr_segs = nr_segs,
.iov_offset = 0,
.count = count
}
EXPORT_SYMBOL(iov_iter_init);
-// 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
- (*npages)++;
- return off;
- }
- return 0;
-}
-
-static size_t copy_pipe_to_iter(const void *addr, size_t bytes,
- struct iov_iter *i)
-{
- unsigned int off, chunk;
-
- if (unlikely(bytes > i->count))
- bytes = i->count;
- if (unlikely(!bytes))
- return 0;
-
- if (!sanity(i))
- return 0;
-
- for (size_t n = bytes; n; n -= chunk) {
- struct page *page = append_pipe(i, n, &off);
- chunk = min_t(size_t, n, PAGE_SIZE - off);
- if (!page)
- return bytes - n;
- memcpy_to_page(page, off, addr, chunk);
- addr += chunk;
- }
- return bytes;
-}
-
-static __wsum csum_and_memcpy(void *to, const void *from, size_t len,
- __wsum sum, size_t off)
-{
- __wsum next = csum_partial_copy_nocheck(from, to, len);
- return csum_block_add(sum, next, off);
-}
-
-static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes,
- struct iov_iter *i, __wsum *sump)
-{
- __wsum sum = *sump;
- size_t off = 0;
- unsigned int chunk, r;
-
- if (unlikely(bytes > i->count))
- bytes = i->count;
- if (unlikely(!bytes))
- return 0;
-
- if (!sanity(i))
- return 0;
-
- while (bytes) {
- struct page *page = append_pipe(i, bytes, &r);
- char *p;
-
- if (!page)
- break;
- chunk = min_t(size_t, bytes, PAGE_SIZE - r);
- p = kmap_local_page(page);
- sum = csum_and_memcpy(p + r, addr + off, chunk, sum, off);
- kunmap_local(p);
- off += chunk;
- bytes -= chunk;
- }
- *sump = sum;
- return off;
-}
-
size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
{
- if (unlikely(iov_iter_is_pipe(i)))
- return copy_pipe_to_iter(addr, bytes, i);
+ if (WARN_ON_ONCE(i->data_source))
+ 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 size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes,
- struct iov_iter *i)
+static __always_inline
+size_t memcpy_to_iter_mc(void *iter_to, size_t progress,
+ size_t len, void *from, void *priv2)
{
- size_t xfer = 0;
- unsigned int off, chunk;
-
- if (unlikely(bytes > i->count))
- bytes = i->count;
- if (unlikely(!bytes))
- return 0;
-
- if (!sanity(i))
- return 0;
-
- while (bytes) {
- struct page *page = append_pipe(i, bytes, &off);
- unsigned long rem;
- char *p;
-
- if (!page)
- break;
- chunk = min_t(size_t, bytes, PAGE_SIZE - off);
- p = kmap_local_page(page);
- rem = copy_mc_to_kernel(p + off, addr + xfer, chunk);
- chunk -= rem;
- kunmap_local(p);
- xfer += chunk;
- bytes -= chunk;
- if (rem) {
- iov_iter_revert(i, rem);
- break;
- }
- }
- return xfer;
+ return copy_mc_to_kernel(iter_to, from + progress, len);
}
/**
* alignment and poison alignment assumptions to avoid re-triggering
* hardware exceptions.
*
- * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
- * Compare to copy_to_iter() where only ITER_IOVEC attempts might return
- * a short copy.
+ * * ITER_KVEC and ITER_BVEC can return short copies. Compare to
+ * copy_to_iter() where only ITER_IOVEC attempts might return a short copy.
*
* Return: number of bytes copied (may be %0)
*/
size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
{
- if (unlikely(iov_iter_is_pipe(i)))
- return copy_mc_pipe_to_iter(addr, bytes, i);
+ if (WARN_ON_ONCE(i->data_source))
+ 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 __always_inline
+size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
+{
+ return iterate_and_advance(i, bytes, addr,
+ copy_from_user_iter, memcpy_from_iter);
+}
+
size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
{
- if (unlikely(iov_iter_is_pipe(i))) {
- WARN_ON(1);
+ if (WARN_ON_ONCE(!i->data_source))
return 0;
- }
+
if (user_backed_iter(i))
might_fault();
- iterate_and_advance(i, bytes, base, len, off,
- copyin(addr + off, base, len),
- memcpy(addr + off, base, len)
- )
-
- return bytes;
+ return __copy_from_iter(addr, bytes, i);
}
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 (unlikely(iov_iter_is_pipe(i))) {
- WARN_ON(1);
+ 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
*/
size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
{
- if (unlikely(iov_iter_is_pipe(i))) {
- WARN_ON(1);
+ 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
head = compound_head(page);
v += (page - head) << PAGE_SHIFT;
- if (likely(n <= v && v <= (page_size(head))))
- return true;
- WARN_ON(1);
- return false;
+ if (WARN_ON(n > v || v > page_size(head)))
+ return false;
+ return true;
}
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i)
{
size_t res = 0;
- if (unlikely(!page_copy_sane(page, offset, bytes)))
+ if (!page_copy_sane(page, offset, bytes))
+ return 0;
+ if (WARN_ON_ONCE(i->data_source))
return 0;
- if (unlikely(iov_iter_is_pipe(i)))
- return copy_page_to_iter_pipe(page, offset, bytes, i);
page += offset / PAGE_SIZE; // first subpage
offset %= PAGE_SIZE;
while (1) {
}
EXPORT_SYMBOL(copy_page_to_iter);
+size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes,
+ struct iov_iter *i)
+{
+ size_t res = 0;
+
+ if (!page_copy_sane(page, offset, bytes))
+ return 0;
+ if (WARN_ON_ONCE(i->data_source))
+ return 0;
+ page += offset / PAGE_SIZE; // first subpage
+ offset %= PAGE_SIZE;
+ while (1) {
+ void *kaddr = kmap_local_page(page);
+ size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
+
+ n = iterate_and_advance(i, n, kaddr + offset,
+ copy_to_user_iter_nofault,
+ memcpy_to_iter);
+ kunmap_local(kaddr);
+ res += n;
+ bytes -= n;
+ if (!bytes || !n)
+ break;
+ offset += n;
+ if (offset == PAGE_SIZE) {
+ page++;
+ offset = 0;
+ }
+ }
+ return res;
+}
+EXPORT_SYMBOL(copy_page_to_iter_nofault);
+
size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i)
{
}
EXPORT_SYMBOL(copy_page_from_iter);
-static size_t pipe_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)
{
- unsigned int chunk, off;
-
- if (unlikely(bytes > i->count))
- bytes = i->count;
- if (unlikely(!bytes))
- return 0;
-
- if (!sanity(i))
- return 0;
-
- for (size_t n = bytes; n; n -= chunk) {
- struct page *page = append_pipe(i, n, &off);
- char *p;
+ return clear_user(iter_to, len);
+}
- if (!page)
- return bytes - n;
- chunk = min_t(size_t, n, PAGE_SIZE - off);
- p = kmap_local_page(page);
- memset(p + off, 0, chunk);
- kunmap_local(p);
- }
- 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)
{
- if (unlikely(iov_iter_is_pipe(i)))
- return pipe_zero(bytes, i);
- iterate_and_advance(i, bytes, base, len, count,
- clear_user(base, len),
- memset(base, 0, len)
- )
-
- return bytes;
+ return iterate_and_advance(i, bytes, NULL,
+ zero_to_user_iter, zero_to_iter);
}
EXPORT_SYMBOL(iov_iter_zero);
-size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes,
- struct iov_iter *i)
+size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
+ size_t bytes, struct iov_iter *i)
{
- char *kaddr = kmap_atomic(page), *p = kaddr + offset;
- if (unlikely(!page_copy_sane(page, offset, bytes))) {
- kunmap_atomic(kaddr);
+ size_t n, copied = 0;
+
+ if (!page_copy_sane(page, offset, bytes))
return 0;
- }
- if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
- kunmap_atomic(kaddr);
- WARN_ON(1);
+ if (WARN_ON_ONCE(!i->data_source))
return 0;
- }
- iterate_and_advance(i, bytes, base, len, off,
- copyin(p + off, base, len),
- memcpy(p + off, base, len)
- )
- kunmap_atomic(kaddr);
- return bytes;
-}
-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;
- int off = i->last_offset;
+ do {
+ char *p;
- if (!off && !size) {
- pipe_discard_from(pipe, i->start_head); // discard everything
- return;
- }
- i->count -= size;
- while (1) {
- struct pipe_buffer *buf = pipe_buf(pipe, i->head);
- if (off) /* make it relative to the beginning of buffer */
- size += abs(off) - buf->offset;
- if (size <= buf->len) {
- buf->len = size;
- i->last_offset = last_offset(buf);
- break;
+ n = bytes - copied;
+ if (PageHighMem(page)) {
+ page += offset / PAGE_SIZE;
+ offset %= PAGE_SIZE;
+ n = min_t(size_t, n, PAGE_SIZE - offset);
}
- size -= buf->len;
- i->head++;
- off = 0;
- }
- pipe_discard_from(pipe, i->head + 1); // discard everything past this one
+
+ p = kmap_atomic(page) + offset;
+ n = __copy_from_iter(p, n, i);
+ kunmap_atomic(p);
+ copied += n;
+ offset += n;
+ } while (PageHighMem(page) && copied != bytes && n > 0);
+
+ return copied;
}
+EXPORT_SYMBOL(copy_page_from_iter_atomic);
static void iov_iter_bvec_advance(struct iov_iter *i, size_t size)
{
i->count -= size;
size += i->iov_offset; // from beginning of current segment
- for (iov = i->iov, end = iov + i->nr_segs; iov < end; iov++) {
+ for (iov = iter_iov(i), end = iov + i->nr_segs; iov < end; iov++) {
if (likely(size < iov->iov_len))
break;
size -= iov->iov_len;
}
i->iov_offset = size;
- i->nr_segs -= iov - i->iov;
- i->iov = iov;
+ i->nr_segs -= iov - iter_iov(i);
+ i->__iov = iov;
}
void iov_iter_advance(struct iov_iter *i, size_t size)
iov_iter_iovec_advance(i, size);
} else if (iov_iter_is_bvec(i)) {
iov_iter_bvec_advance(i, size);
- } else if (iov_iter_is_pipe(i)) {
- pipe_advance(i, size);
} else if (iov_iter_is_discard(i)) {
i->count -= size;
}
if (WARN_ON(unroll > MAX_RW_COUNT))
return;
i->count += unroll;
- if (unlikely(iov_iter_is_pipe(i))) {
- struct pipe_inode_info *pipe = i->pipe;
- unsigned int head = pipe->head;
-
- while (head > i->start_head) {
- struct pipe_buffer *b = pipe_buf(pipe, --head);
- if (unroll < b->len) {
- b->len -= unroll;
- i->last_offset = last_offset(b);
- i->head = head;
- return;
- }
- unroll -= b->len;
- pipe_buf_release(pipe, b);
- pipe->head--;
- }
- i->last_offset = 0;
- i->head = head;
- return;
- }
if (unlikely(iov_iter_is_discard(i)))
return;
if (unroll <= i->iov_offset) {
unroll -= n;
}
} else { /* same logics for iovec and kvec */
- const struct iovec *iov = i->iov;
+ const struct iovec *iov = iter_iov(i);
while (1) {
size_t n = (--iov)->iov_len;
i->nr_segs++;
if (unroll <= n) {
- i->iov = iov;
+ i->__iov = iov;
i->iov_offset = n - unroll;
return;
}
{
if (i->nr_segs > 1) {
if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i)))
- return min(i->count, i->iov->iov_len - i->iov_offset);
+ return min(i->count, iter_iov(i)->iov_len - i->iov_offset);
if (iov_iter_is_bvec(i))
return min(i->count, i->bvec->bv_len - i->iov_offset);
}
}
EXPORT_SYMBOL(iov_iter_bvec);
-void iov_iter_pipe(struct iov_iter *i, unsigned int direction,
- struct pipe_inode_info *pipe,
- size_t count)
-{
- BUG_ON(direction != READ);
- WARN_ON(pipe_full(pipe->head, pipe->tail, pipe->ring_size));
- *i = (struct iov_iter){
- .iter_type = ITER_PIPE,
- .data_source = false,
- .pipe = pipe,
- .head = pipe->head,
- .start_head = pipe->head,
- .last_offset = 0,
- .count = count
- };
-}
-EXPORT_SYMBOL(iov_iter_pipe);
-
/**
* iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray
* @i: The iterator to initialise.
static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask,
unsigned len_mask)
{
+ const struct iovec *iov = iter_iov(i);
size_t size = i->count;
size_t skip = i->iov_offset;
- unsigned k;
- for (k = 0; k < i->nr_segs; k++, skip = 0) {
- size_t len = i->iov[k].iov_len - skip;
+ do {
+ size_t len = iov->iov_len - skip;
if (len > size)
len = size;
if (len & len_mask)
return false;
- if ((unsigned long)(i->iov[k].iov_base + skip) & addr_mask)
+ if ((unsigned long)(iov->iov_base + skip) & addr_mask)
return false;
+ iov++;
size -= len;
- if (!size)
- break;
- }
+ skip = 0;
+ } while (size);
+
return true;
}
static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask,
unsigned len_mask)
{
- size_t size = i->count;
+ const struct bio_vec *bvec = i->bvec;
unsigned skip = i->iov_offset;
- unsigned k;
+ size_t size = i->count;
- for (k = 0; k < i->nr_segs; k++, skip = 0) {
- size_t len = i->bvec[k].bv_len - skip;
+ do {
+ size_t len = bvec->bv_len;
if (len > size)
len = size;
if (len & len_mask)
return false;
- if ((unsigned long)(i->bvec[k].bv_offset + skip) & addr_mask)
+ if ((unsigned long)(bvec->bv_offset + skip) & addr_mask)
return false;
+ bvec++;
size -= len;
- if (!size)
- break;
- }
+ skip = 0;
+ } while (size);
+
return true;
}
if (iov_iter_is_bvec(i))
return iov_iter_aligned_bvec(i, addr_mask, len_mask);
- if (iov_iter_is_pipe(i)) {
- size_t size = i->count;
-
- if (size & len_mask)
- return false;
- if (size && i->last_offset > 0) {
- if (i->last_offset & addr_mask)
- return false;
- }
-
- return true;
- }
-
if (iov_iter_is_xarray(i)) {
if (i->count & len_mask)
return false;
static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i)
{
+ const struct iovec *iov = iter_iov(i);
unsigned long res = 0;
size_t size = i->count;
size_t skip = i->iov_offset;
- unsigned k;
- for (k = 0; k < i->nr_segs; k++, skip = 0) {
- size_t len = i->iov[k].iov_len - skip;
+ do {
+ size_t len = iov->iov_len - skip;
if (len) {
- res |= (unsigned long)i->iov[k].iov_base + skip;
+ res |= (unsigned long)iov->iov_base + skip;
if (len > size)
len = size;
res |= len;
size -= len;
- if (!size)
- break;
}
- }
+ iov++;
+ skip = 0;
+ } while (size);
return res;
}
static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i)
{
+ const struct bio_vec *bvec = i->bvec;
unsigned res = 0;
size_t size = i->count;
unsigned skip = i->iov_offset;
- unsigned k;
- for (k = 0; k < i->nr_segs; k++, skip = 0) {
- size_t len = i->bvec[k].bv_len - skip;
- res |= (unsigned long)i->bvec[k].bv_offset + skip;
+ do {
+ size_t len = bvec->bv_len - skip;
+ res |= (unsigned long)bvec->bv_offset + skip;
if (len > size)
len = size;
res |= len;
+ bvec++;
size -= len;
- if (!size)
- break;
- }
+ skip = 0;
+ } while (size);
+
return res;
}
if (iov_iter_is_bvec(i))
return iov_iter_alignment_bvec(i);
- if (iov_iter_is_pipe(i)) {
- size_t size = i->count;
-
- if (size && i->last_offset > 0)
- return size | i->last_offset;
- return size;
- }
-
if (iov_iter_is_xarray(i))
return (i->xarray_start + i->iov_offset) | i->count;
return ~0U;
for (k = 0; k < i->nr_segs; k++) {
- if (i->iov[k].iov_len) {
- unsigned long base = (unsigned long)i->iov[k].iov_base;
+ const struct iovec *iov = iter_iov(i) + k;
+ if (iov->iov_len) {
+ unsigned long base = (unsigned long)iov->iov_base;
if (v) // if not the first one
res |= base | v; // this start | previous end
- v = base + i->iov[k].iov_len;
- if (size <= i->iov[k].iov_len)
+ v = base + iov->iov_len;
+ if (size <= iov->iov_len)
break;
- size -= i->iov[k].iov_len;
+ size -= iov->iov_len;
}
}
return res;
return count;
}
-static ssize_t pipe_get_pages(struct iov_iter *i,
- struct page ***pages, size_t maxsize, unsigned maxpages,
- size_t *start)
-{
- unsigned int npages, count, off, chunk;
- struct page **p;
- size_t left;
-
- if (!sanity(i))
- return -EFAULT;
-
- *start = off = pipe_npages(i, &npages);
- if (!npages)
- return -EFAULT;
- count = want_pages_array(pages, maxsize, off, min(npages, maxpages));
- if (!count)
- return -ENOMEM;
- p = *pages;
- for (npages = 0, left = maxsize ; npages < count; npages++, left -= chunk) {
- struct page *page = append_pipe(i, left, &off);
- if (!page)
- break;
- chunk = min_t(size_t, left, PAGE_SIZE - off);
- get_page(*p++ = page);
- }
- if (!npages)
- return -EFAULT;
- return maxsize - left;
-}
-
static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa,
pgoff_t index, unsigned int nr_pages)
{
return (unsigned long)i->ubuf + i->iov_offset;
for (k = 0, skip = i->iov_offset; k < i->nr_segs; k++, skip = 0) {
- size_t len = i->iov[k].iov_len - skip;
+ const struct iovec *iov = iter_iov(i) + k;
+ size_t len = iov->iov_len - skip;
if (unlikely(!len))
continue;
if (*size > len)
*size = len;
- return (unsigned long)i->iov[k].iov_base + skip;
+ return (unsigned long)iov->iov_base + skip;
}
BUG(); // if it had been empty, we wouldn't get called
}
struct page ***pages, size_t maxsize,
unsigned int maxpages, size_t *start)
{
- unsigned int n;
+ unsigned int n, gup_flags = 0;
if (maxsize > i->count)
maxsize = i->count;
maxsize = MAX_RW_COUNT;
if (likely(user_backed_iter(i))) {
- unsigned int gup_flags = 0;
unsigned long addr;
int res;
}
return maxsize;
}
- if (iov_iter_is_pipe(i))
- return pipe_get_pages(i, pages, maxsize, maxpages, start);
if (iov_iter_is_xarray(i))
return iter_xarray_get_pages(i, pages, maxsize, maxpages, start);
return -EFAULT;
}
-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_pages2(struct iov_iter *i, struct page **pages,
+ size_t maxsize, unsigned maxpages, size_t *start)
{
if (!maxpages)
return 0;
EXPORT_SYMBOL(iov_iter_get_pages2);
ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i,
- struct page ***pages, size_t maxsize,
- size_t *start)
+ struct page ***pages, size_t maxsize, size_t *start)
{
ssize_t len;
}
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)
-{
- __wsum sum, next;
- sum = *csum;
- if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
- WARN_ON(1);
- 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;
-}
-EXPORT_SYMBOL(csum_and_copy_from_iter);
-
-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;
-
- if (unlikely(iov_iter_is_discard(i))) {
- WARN_ON(1); /* for now */
- return 0;
- }
-
- sum = csum_shift(csstate->csum, csstate->off);
- if (unlikely(iov_iter_is_pipe(i)))
- bytes = csum_and_copy_to_pipe_iter(addr, bytes, i, &sum);
- else 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);
- })
- )
- csstate->csum = csum_shift(sum, csstate->off);
- csstate->off += bytes;
- return bytes;
-}
-EXPORT_SYMBOL(csum_and_copy_to_iter);
-
-size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
- struct iov_iter *i)
-{
-#ifdef CONFIG_CRYPTO_HASH
- struct ahash_request *hash = hashp;
- struct scatterlist sg;
- size_t copied;
-
- copied = copy_to_iter(addr, bytes, i);
- sg_init_one(&sg, addr, copied);
- ahash_request_set_crypt(hash, &sg, NULL, copied);
- crypto_ahash_update(hash);
- return copied;
-#else
- return 0;
-#endif
-}
-EXPORT_SYMBOL(hash_and_copy_to_iter);
-
static int iov_npages(const struct iov_iter *i, int maxpages)
{
size_t skip = i->iov_offset, size = i->count;
const struct iovec *p;
int npages = 0;
- for (p = i->iov; size; skip = 0, p++) {
+ for (p = iter_iov(i); size; skip = 0, p++) {
unsigned offs = offset_in_page(p->iov_base + skip);
size_t len = min(p->iov_len - skip, size);
return iov_npages(i, maxpages);
if (iov_iter_is_bvec(i))
return bvec_npages(i, maxpages);
- if (iov_iter_is_pipe(i)) {
- int npages;
-
- if (!sanity(i))
- return 0;
-
- pipe_npages(i, &npages);
- return min(npages, maxpages);
- }
if (iov_iter_is_xarray(i)) {
unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE;
int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE);
const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
{
*new = *old;
- if (unlikely(iov_iter_is_pipe(new))) {
- WARN_ON(1);
- return NULL;
- }
if (iov_iter_is_bvec(new))
return new->bvec = kmemdup(new->bvec,
new->nr_segs * sizeof(struct bio_vec),
flags);
else if (iov_iter_is_kvec(new) || iter_is_iovec(new))
/* iovec and kvec have identical layout */
- return new->iov = kmemdup(new->iov,
+ return new->__iov = kmemdup(new->__iov,
new->nr_segs * sizeof(struct iovec),
flags);
return NULL;
}
EXPORT_SYMBOL(dup_iter);
-static int copy_compat_iovec_from_user(struct iovec *iov,
- const struct iovec __user *uvec, unsigned long nr_segs)
+static __noclone int copy_compat_iovec_from_user(struct iovec *iov,
+ const struct iovec __user *uvec, u32 nr_segs)
{
const struct compat_iovec __user *uiov =
(const struct compat_iovec __user *)uvec;
- int ret = -EFAULT, i;
+ int ret = -EFAULT;
+ u32 i;
if (!user_access_begin(uiov, nr_segs * sizeof(*uiov)))
return -EFAULT;
return ret;
}
-static int copy_iovec_from_user(struct iovec *iov,
- const struct iovec __user *uvec, unsigned long nr_segs)
+static __noclone int copy_iovec_from_user(struct iovec *iov,
+ const struct iovec __user *uiov, unsigned long nr_segs)
{
- unsigned long seg;
+ int ret = -EFAULT;
- if (copy_from_user(iov, uvec, nr_segs * sizeof(*uvec)))
+ if (!user_access_begin(uiov, nr_segs * sizeof(*uiov)))
return -EFAULT;
- for (seg = 0; seg < nr_segs; seg++) {
- if ((ssize_t)iov[seg].iov_len < 0)
- return -EINVAL;
- }
- return 0;
+ do {
+ void __user *buf;
+ ssize_t len;
+
+ unsafe_get_user(len, &uiov->iov_len, uaccess_end);
+ unsafe_get_user(buf, &uiov->iov_base, uaccess_end);
+
+ /* check for size_t not fitting in ssize_t .. */
+ if (unlikely(len < 0)) {
+ ret = -EINVAL;
+ goto uaccess_end;
+ }
+ iov->iov_base = buf;
+ iov->iov_len = len;
+
+ uiov++; iov++;
+ } while (--nr_segs);
+
+ ret = 0;
+uaccess_end:
+ user_access_end();
+ return ret;
}
struct iovec *iovec_from_user(const struct iovec __user *uvec,
return ERR_PTR(-ENOMEM);
}
- if (compat)
+ if (unlikely(compat))
ret = copy_compat_iovec_from_user(iov, uvec, nr_segs);
else
ret = copy_iovec_from_user(iov, uvec, nr_segs);
return iov;
}
+/*
+ * Single segment iovec supplied by the user, import it as ITER_UBUF.
+ */
+static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec,
+ struct iovec **iovp, struct iov_iter *i,
+ bool compat)
+{
+ struct iovec *iov = *iovp;
+ ssize_t ret;
+
+ if (compat)
+ ret = copy_compat_iovec_from_user(iov, uvec, 1);
+ else
+ ret = copy_iovec_from_user(iov, uvec, 1);
+ if (unlikely(ret))
+ return ret;
+
+ ret = import_ubuf(type, iov->iov_base, iov->iov_len, i);
+ if (unlikely(ret))
+ return ret;
+ *iovp = NULL;
+ return i->count;
+}
+
ssize_t __import_iovec(int type, const struct iovec __user *uvec,
unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
struct iov_iter *i, bool compat)
unsigned long seg;
struct iovec *iov;
+ if (nr_segs == 1)
+ return __import_iovec_ubuf(type, uvec, iovp, i, compat);
+
iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat);
if (IS_ERR(iov)) {
*iovp = NULL;
}
EXPORT_SYMBOL(import_iovec);
-int import_single_range(int rw, void __user *buf, size_t len,
- struct iovec *iov, struct iov_iter *i)
+int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i)
{
if (len > MAX_RW_COUNT)
len = MAX_RW_COUNT;
if (unlikely(!access_ok(buf, len)))
return -EFAULT;
- iov->iov_base = buf;
- iov->iov_len = len;
- iov_iter_init(i, rw, iov, 1, len);
+ iov_iter_ubuf(i, rw, buf, len);
return 0;
}
-EXPORT_SYMBOL(import_single_range);
+EXPORT_SYMBOL_GPL(import_ubuf);
/**
* iov_iter_restore() - Restore a &struct iov_iter to the same state as when
*/
void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state)
{
- if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) &&
- !iov_iter_is_kvec(i) && !iter_is_ubuf(i))
+ if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i) &&
+ !iter_is_ubuf(i)) && !iov_iter_is_kvec(i))
return;
i->iov_offset = state->iov_offset;
i->count = state->count;
if (iov_iter_is_bvec(i))
i->bvec -= state->nr_segs - i->nr_segs;
else
- i->iov -= state->nr_segs - i->nr_segs;
+ i->__iov -= state->nr_segs - i->nr_segs;
i->nr_segs = state->nr_segs;
}
+
+/*
+ * Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not
+ * get references on the pages, nor does it get a pin on them.
+ */
+static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i,
+ struct page ***pages, size_t maxsize,
+ unsigned int maxpages,
+ iov_iter_extraction_t extraction_flags,
+ size_t *offset0)
+{
+ struct page *page, **p;
+ unsigned int nr = 0, offset;
+ loff_t pos = i->xarray_start + i->iov_offset;
+ pgoff_t index = pos >> PAGE_SHIFT;
+ XA_STATE(xas, i->xarray, index);
+
+ offset = pos & ~PAGE_MASK;
+ *offset0 = offset;
+
+ maxpages = want_pages_array(pages, maxsize, offset, maxpages);
+ if (!maxpages)
+ return -ENOMEM;
+ p = *pages;
+
+ rcu_read_lock();
+ for (page = xas_load(&xas); page; page = xas_next(&xas)) {
+ if (xas_retry(&xas, page))
+ continue;
+
+ /* Has the page moved or been split? */
+ if (unlikely(page != xas_reload(&xas))) {
+ xas_reset(&xas);
+ continue;
+ }
+
+ p[nr++] = find_subpage(page, xas.xa_index);
+ if (nr == maxpages)
+ break;
+ }
+ rcu_read_unlock();
+
+ maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize);
+ iov_iter_advance(i, maxsize);
+ return maxsize;
+}
+
+/*
+ * Extract a list of contiguous pages from an ITER_BVEC iterator. This does
+ * not get references on the pages, nor does it get a pin on them.
+ */
+static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i,
+ struct page ***pages, size_t maxsize,
+ unsigned int maxpages,
+ iov_iter_extraction_t extraction_flags,
+ size_t *offset0)
+{
+ struct page **p, *page;
+ size_t skip = i->iov_offset, offset, size;
+ int k;
+
+ for (;;) {
+ if (i->nr_segs == 0)
+ return 0;
+ size = min(maxsize, i->bvec->bv_len - skip);
+ if (size)
+ break;
+ i->iov_offset = 0;
+ i->nr_segs--;
+ i->bvec++;
+ skip = 0;
+ }
+
+ skip += i->bvec->bv_offset;
+ page = i->bvec->bv_page + skip / PAGE_SIZE;
+ offset = skip % PAGE_SIZE;
+ *offset0 = offset;
+
+ maxpages = want_pages_array(pages, size, offset, maxpages);
+ if (!maxpages)
+ return -ENOMEM;
+ p = *pages;
+ for (k = 0; k < maxpages; k++)
+ p[k] = page + k;
+
+ size = min_t(size_t, size, maxpages * PAGE_SIZE - offset);
+ iov_iter_advance(i, size);
+ return size;
+}
+
+/*
+ * Extract a list of virtually contiguous pages from an ITER_KVEC iterator.
+ * This does not get references on the pages, nor does it get a pin on them.
+ */
+static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i,
+ struct page ***pages, size_t maxsize,
+ unsigned int maxpages,
+ iov_iter_extraction_t extraction_flags,
+ size_t *offset0)
+{
+ struct page **p, *page;
+ const void *kaddr;
+ size_t skip = i->iov_offset, offset, len, size;
+ int k;
+
+ for (;;) {
+ if (i->nr_segs == 0)
+ return 0;
+ size = min(maxsize, i->kvec->iov_len - skip);
+ if (size)
+ break;
+ i->iov_offset = 0;
+ i->nr_segs--;
+ i->kvec++;
+ skip = 0;
+ }
+
+ kaddr = i->kvec->iov_base + skip;
+ offset = (unsigned long)kaddr & ~PAGE_MASK;
+ *offset0 = offset;
+
+ maxpages = want_pages_array(pages, size, offset, maxpages);
+ if (!maxpages)
+ return -ENOMEM;
+ p = *pages;
+
+ kaddr -= offset;
+ len = offset + size;
+ for (k = 0; k < maxpages; k++) {
+ size_t seg = min_t(size_t, len, PAGE_SIZE);
+
+ if (is_vmalloc_or_module_addr(kaddr))
+ page = vmalloc_to_page(kaddr);
+ else
+ page = virt_to_page(kaddr);
+
+ p[k] = page;
+ len -= seg;
+ kaddr += PAGE_SIZE;
+ }
+
+ size = min_t(size_t, size, maxpages * PAGE_SIZE - offset);
+ iov_iter_advance(i, size);
+ return size;
+}
+
+/*
+ * Extract a list of contiguous pages from a user iterator and get a pin on
+ * each of them. This should only be used if the iterator is user-backed
+ * (IOBUF/UBUF).
+ *
+ * It does not get refs on the pages, but the pages must be unpinned by the
+ * caller once the transfer is complete.
+ *
+ * This is safe to be used where background IO/DMA *is* going to be modifying
+ * the buffer; using a pin rather than a ref makes forces fork() to give the
+ * child a copy of the page.
+ */
+static ssize_t iov_iter_extract_user_pages(struct iov_iter *i,
+ struct page ***pages,
+ size_t maxsize,
+ unsigned int maxpages,
+ iov_iter_extraction_t extraction_flags,
+ size_t *offset0)
+{
+ unsigned long addr;
+ unsigned int gup_flags = 0;
+ size_t offset;
+ int res;
+
+ if (i->data_source == ITER_DEST)
+ gup_flags |= FOLL_WRITE;
+ if (extraction_flags & ITER_ALLOW_P2PDMA)
+ gup_flags |= FOLL_PCI_P2PDMA;
+ if (i->nofault)
+ gup_flags |= FOLL_NOFAULT;
+
+ addr = first_iovec_segment(i, &maxsize);
+ *offset0 = offset = addr % PAGE_SIZE;
+ addr &= PAGE_MASK;
+ maxpages = want_pages_array(pages, maxsize, offset, maxpages);
+ if (!maxpages)
+ return -ENOMEM;
+ res = pin_user_pages_fast(addr, maxpages, gup_flags, *pages);
+ if (unlikely(res <= 0))
+ return res;
+ maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - offset);
+ iov_iter_advance(i, maxsize);
+ return maxsize;
+}
+
+/**
+ * iov_iter_extract_pages - Extract a list of contiguous pages from an iterator
+ * @i: The iterator to extract from
+ * @pages: Where to return the list of pages
+ * @maxsize: The maximum amount of iterator to extract
+ * @maxpages: The maximum size of the list of pages
+ * @extraction_flags: Flags to qualify request
+ * @offset0: Where to return the starting offset into (*@pages)[0]
+ *
+ * Extract a list of contiguous pages from the current point of the iterator,
+ * advancing the iterator. The maximum number of pages and the maximum amount
+ * of page contents can be set.
+ *
+ * If *@pages is NULL, a page list will be allocated to the required size and
+ * *@pages will be set to its base. If *@pages is not NULL, it will be assumed
+ * that the caller allocated a page list at least @maxpages in size and this
+ * will be filled in.
+ *
+ * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA
+ * be allowed on the pages extracted.
+ *
+ * The iov_iter_extract_will_pin() function can be used to query how cleanup
+ * should be performed.
+ *
+ * Extra refs or pins on the pages may be obtained as follows:
+ *
+ * (*) If the iterator is user-backed (ITER_IOVEC/ITER_UBUF), pins will be
+ * added to the pages, but refs will not be taken.
+ * iov_iter_extract_will_pin() will return true.
+ *
+ * (*) If the iterator is ITER_KVEC, ITER_BVEC or ITER_XARRAY, the pages are
+ * merely listed; no extra refs or pins are obtained.
+ * iov_iter_extract_will_pin() will return 0.
+ *
+ * Note also:
+ *
+ * (*) Use with ITER_DISCARD is not supported as that has no content.
+ *
+ * On success, the function sets *@pages to the new pagelist, if allocated, and
+ * sets *offset0 to the offset into the first page.
+ *
+ * It may also return -ENOMEM and -EFAULT.
+ */
+ssize_t iov_iter_extract_pages(struct iov_iter *i,
+ struct page ***pages,
+ size_t maxsize,
+ unsigned int maxpages,
+ iov_iter_extraction_t extraction_flags,
+ size_t *offset0)
+{
+ maxsize = min_t(size_t, min_t(size_t, maxsize, i->count), MAX_RW_COUNT);
+ if (!maxsize)
+ return 0;
+
+ if (likely(user_backed_iter(i)))
+ return iov_iter_extract_user_pages(i, pages, maxsize,
+ maxpages, extraction_flags,
+ offset0);
+ if (iov_iter_is_kvec(i))
+ return iov_iter_extract_kvec_pages(i, pages, maxsize,
+ maxpages, extraction_flags,
+ offset0);
+ if (iov_iter_is_bvec(i))
+ return iov_iter_extract_bvec_pages(i, pages, maxsize,
+ maxpages, extraction_flags,
+ offset0);
+ if (iov_iter_is_xarray(i))
+ return iov_iter_extract_xarray_pages(i, pages, maxsize,
+ maxpages, extraction_flags,
+ offset0);
+ return -EFAULT;
+}
+EXPORT_SYMBOL_GPL(iov_iter_extract_pages);