Lines Matching full:pages

35 In other words, use pin_user_pages*() for DMA-pinned pages, and
40 multiple threads and call sites are free to pin the same struct pages, via both
55 pages* array, and the function then pins pages by incrementing each by a special
64 severely by huge pages, because each tail page adds a refcount to the
68 This also means that huge pages and large folios do not suffer
79 but the caller passed in a non-null struct pages* array, then the function
80 sets FOLL_GET for you, and proceeds to pin pages by incrementing the refcount
89 Tracking dma-pinned pages
93 pages:
115 * Because of that limitation, special handling is applied to the zero pages
121 * Callers must specifically request "dma-pinned tracking of pages". In other
133 There are GUP references to pages that are serving
145 There are GUP references to pages that are serving as DMA
152 NOTE: Some pages, such as DAX pages, cannot be pinned with longterm pins. That's
153 because DAX pages do not have a separate page cache, and so "pinning" implies
160 Device drivers can pin pages via get_user_pages*(), and register for mmu
163 the pages. There may be other possible schemes, such as for example explicitly
171 Either way, as long as the driver unpins the pages upon mmu notifier callback,
191     write to the data within the pages
196     write to the data within the pages
222 short term pins on pages whose data *will* get accessed. As such, FOLL_PIN is
224 restrictive case that has FOLL_PIN as a prerequisite: this is for pages that
238 You can monitor how many total dma-pinned pages have been acquired and released
248   acquired since the system was powered on. For huge pages, the head page is
251   pages: the head page is refcounted once for each tail or head page in the huge
255   the system was powered on. Note that pages are released (unpinned) on a