@@ -229,6 +229,11 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages);
const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
+ssize_t iov_iter_pin_user_pages(struct iov_iter *i, struct page **pages,
+ size_t maxsize, unsigned int maxpages, size_t *start);
+ssize_t iov_iter_pin_user_pages_alloc(struct iov_iter *i, struct page ***pages,
+ size_t maxsize, size_t *start);
+
static inline size_t iov_iter_count(const struct iov_iter *i)
{
return i->count;
@@ -1309,6 +1309,44 @@ static ssize_t pipe_get_pages(struct iov_iter *i,
return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head, start);
}
+ssize_t iov_iter_pin_user_pages(struct iov_iter *i,
+ struct page **pages, size_t maxsize, unsigned int maxpages,
+ size_t *start)
+{
+ size_t skip = i->iov_offset;
+ const struct iovec *iov;
+ struct iovec v;
+
+ if (WARN_ON_ONCE(!iter_is_iovec(i)))
+ return -EFAULT;
+
+ if (unlikely(!maxsize))
+ return 0;
+ maxsize = min(maxsize, i->count);
+
+ iterate_iovec(i, maxsize, v, iov, skip, ({
+ unsigned long addr = (unsigned long)v.iov_base;
+ size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
+ int n;
+ int res;
+
+ if (len > maxpages * PAGE_SIZE)
+ len = maxpages * PAGE_SIZE;
+ addr &= ~(PAGE_SIZE - 1);
+ n = DIV_ROUND_UP(len, PAGE_SIZE);
+
+ res = pin_user_pages_fast(addr, n,
+ iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0,
+ pages);
+ if (unlikely(res < 0))
+ return res;
+ return (res == n ? len : res * PAGE_SIZE) - *start;
+ 0;
+ }))
+ return 0;
+}
+EXPORT_SYMBOL(iov_iter_pin_user_pages);
+
ssize_t iov_iter_get_pages(struct iov_iter *i,
struct page **pages, size_t maxsize, unsigned maxpages,
size_t *start)
@@ -1388,6 +1426,48 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
return n;
}
+ssize_t iov_iter_pin_user_pages_alloc(struct iov_iter *i,
+ struct page ***pages, size_t maxsize,
+ size_t *start)
+{
+ struct page **p;
+ size_t skip = i->iov_offset;
+ const struct iovec *iov;
+ struct iovec v;
+
+ if (WARN_ON_ONCE(!iter_is_iovec(i)))
+ return -EFAULT;
+
+ if (unlikely(!maxsize))
+ return 0;
+ maxsize = min(maxsize, i->count);
+
+ iterate_iovec(i, maxsize, v, iov, skip, ({
+ unsigned long addr = (unsigned long)v.iov_base;
+ size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
+ int n;
+ int res;
+
+ addr &= ~(PAGE_SIZE - 1);
+ n = DIV_ROUND_UP(len, PAGE_SIZE);
+ p = get_pages_array(n);
+ if (!p)
+ return -ENOMEM;
+
+ res = pin_user_pages_fast(addr, n,
+ iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0, p);
+ if (unlikely(res < 0)) {
+ kvfree(p);
+ return res;
+ }
+ *pages = p;
+ return (res == n ? len : res * PAGE_SIZE) - *start;
+ 0;
+ }))
+ return 0;
+}
+EXPORT_SYMBOL(iov_iter_pin_user_pages_alloc);
+
ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
struct page ***pages, size_t maxsize,
size_t *start)
The new routines are: iov_iter_pin_user_pages() iov_iter_pin_user_pages_alloc() and those correspond to these pre-existing routines: iov_iter_get_pages() iov_iter_get_pages_alloc() Unlike the iov_iter_get_pages*() routines, the iov_iter_pin_user_pages*() routines assert that only ITER_IOVEC items are passed in. They then call pin_user_pages_fast(), instead of get_user_pages_fast(). Why: In order to incrementally change Direct IO callers from calling get_user_pages_fast() and put_page(), over to calling pin_user_pages_fast() and unpin_user_page(), there need to be mid-level routines that specifically call one or the other systems, for both page acquisition and page release. Signed-off-by: John Hubbard <jhubbard@nvidia.com> --- include/linux/uio.h | 5 +++ lib/iov_iter.c | 80 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 85 insertions(+)