mm/gup: add a range variant of unpin_user_pages_dirty_lock()

Add an unpin_user_page_range_dirty_lock() API which takes a starting page
and how many consecutive pages we want to unpin and optionally dirty.

To that end, define another iterator for_each_compound_range() that
operates in page ranges as opposed to page array.

For users (like RDMA mr_dereg) where each sg represents a contiguous set
of pages, we're able to more efficiently unpin pages without having to
supply an array of pages much of what happens today with
unpin_user_pages().

Link: https://lkml.kernel.org/r/20210212130843.13865-4-joao.m.martins@oracle.com
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2e5c207..702c2a7 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1265,6 +1265,8 @@ static inline void put_page(struct page *page)
 void unpin_user_page(struct page *page);
 void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
                                 bool make_dirty);
+void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
+                                     bool make_dirty);
 void unpin_user_pages(struct page **pages, unsigned long npages);
 
 /**

diff --git a/mm/gup.c b/mm/gup.c
index de1b75e..66522ae 100644 (file)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -213,6 +213,32 @@ void unpin_user_page(struct page *page)
 }
 EXPORT_SYMBOL(unpin_user_page);
 
+static inline void compound_range_next(unsigned long i, unsigned long npages,
+                                      struct page **list, struct page **head,
+                                      unsigned int *ntails)
+{
+       struct page *next, *page;
+       unsigned int nr = 1;
+
+       if (i >= npages)
+               return;
+
+       next = *list + i;
+       page = compound_head(next);
+       if (PageCompound(page) && compound_order(page) >= 1)
+               nr = min_t(unsigned int,
+                          page + compound_nr(page) - next, npages - i);
+
+       *head = page;
+       *ntails = nr;
+}
+
+#define for_each_compound_range(__i, __list, __npages, __head, __ntails) \
+       for (__i = 0, \
+            compound_range_next(__i, __npages, __list, &(__head), &(__ntails)); \
+            __i < __npages; __i += __ntails, \
+            compound_range_next(__i, __npages, __list, &(__head), &(__ntails)))
+
 static inline void compound_next(unsigned long i, unsigned long npages,
                                 struct page **list, struct page **head,
                                 unsigned int *ntails)
@@ -301,6 +327,42 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 }
 EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
 
+/**
+ * unpin_user_page_range_dirty_lock() - release and optionally dirty
+ * gup-pinned page range
+ *
+ * @page:  the starting page of a range maybe marked dirty, and definitely released.
+ * @npages: number of consecutive pages to release.
+ * @make_dirty: whether to mark the pages dirty
+ *
+ * "gup-pinned page range" refers to a range of pages that has had one of the
+ * pin_user_pages() variants called on that page.
+ *
+ * For the page ranges defined by [page .. page+npages], make that range (or
+ * its head pages, if a compound page) dirty, if @make_dirty is true, and if the
+ * page range was previously listed as clean.
+ *
+ * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
+ * required, then the caller should a) verify that this is really correct,
+ * because _lock() is usually required, and b) hand code it:
+ * set_page_dirty_lock(), unpin_user_page().
+ *
+ */
+void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
+                                     bool make_dirty)
+{
+       unsigned long index;
+       struct page *head;
+       unsigned int ntails;
+
+       for_each_compound_range(index, &page, npages, head, ntails) {
+               if (make_dirty && !PageDirty(head))
+                       set_page_dirty_lock(head);
+               put_compound_head(head, ntails, FOLL_PIN);
+       }
+}
+EXPORT_SYMBOL(unpin_user_page_range_dirty_lock);
+
 /**
  * unpin_user_pages() - release an array of gup-pinned pages.
  * @pages:  array of pages to be marked dirty and released.