iov_iter: Add a function to extract a page list from an iterator

Add a function, iov_iter_extract_pages(), to extract a list of pages from
an iterator.  The pages may be returned with a pin added or nothing,
depending on the type of iterator.

Add a second function, iov_iter_extract_will_pin(), to determine how the
cleanup should be done.

There are two cases:

 (1) ITER_IOVEC or ITER_UBUF iterator.

     Extracted pages will have pins (FOLL_PIN) obtained on them so that a
     concurrent fork() will forcibly copy the page so that DMA is done
     to/from the parent's buffer and is unavailable to/unaffected by the
     child process.

     iov_iter_extract_will_pin() will return true for this case.  The
     caller should use something like unpin_user_page() to dispose of the
     page.

 (2) Any other sort of iterator.

     No refs or pins are obtained on the page, the assumption is made that
     the caller will manage page retention.

     iov_iter_extract_will_pin() will return false.  The pages don't need
     additional disposal.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: John Hubbard <jhubbard@nvidia.com>
cc: David Hildenbrand <david@redhat.com>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
Signed-off-by: Steve French <stfrench@microsoft.com>

diff --git a/include/linux/uio.h b/include/linux/uio.h
index eec6ed8a627a305d1eb8ea3787f5815cc1ca01af..514e3b7b06b8082ae087b1c290e4fcc57af6d695 100644 (file)
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -361,9 +361,34 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
                .count = count
        };
 }
-
 /* Flags for iov_iter_get/extract_pages*() */
 /* Allow P2PDMA on the extracted pages */
 #define ITER_ALLOW_P2PDMA      ((__force iov_iter_extraction_t)0x01)
 
+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);
+
+/**
+ * iov_iter_extract_will_pin - Indicate how pages from the iterator will be retained
+ * @iter: The iterator
+ *
+ * Examine the iterator and indicate by returning true or false as to how, if
+ * at all, pages extracted from the iterator will be retained by the extraction
+ * function.
+ *
+ * %true indicates that the pages will have a pin placed in them that the
+ * caller must unpin.  This is must be done for DMA/async DIO to force fork()
+ * to forcibly copy a page for the child (the parent must retain the original
+ * page).
+ *
+ * %false indicates that no measures are taken and that it's up to the caller
+ * to retain the pages.
+ */
+static inline bool iov_iter_extract_will_pin(const struct iov_iter *iter)
+{
+       return user_backed_iter(iter);
+}
+
 #endif

diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 9d4949ea9b274f3570e6667d0a433e6224c8d93b..e53b162353851fcdef4ce042faff35a94f4993c7 100644 (file)
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1910,3 +1910,267 @@ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state)
                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;
+       int k;
+
+       for (;;) {
+               if (i->nr_segs == 0)
+                       return 0;
+               maxsize = min(maxsize, i->bvec->bv_len - skip);
+               if (maxsize)
+                       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, maxsize, offset, maxpages);
+       if (!maxpages)
+               return -ENOMEM;
+       p = *pages;
+       for (k = 0; k < maxpages; k++)
+               p[k] = page + k;
+
+       maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset);
+       iov_iter_advance(i, maxsize);
+       return maxsize;
+}
+
+/*
+ * 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;
+       int k;
+
+       for (;;) {
+               if (i->nr_segs == 0)
+                       return 0;
+               maxsize = min(maxsize, i->kvec->iov_len - skip);
+               if (maxsize)
+                       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, maxsize, offset, maxpages);
+       if (!maxpages)
+               return -ENOMEM;
+       p = *pages;
+
+       kaddr -= offset;
+       len = offset + maxsize;
+       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;
+       }
+
+       maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset);
+       iov_iter_advance(i, maxsize);
+       return maxsize;
+}
+
+/*
+ * 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);