page_ref_inc(page);
}
+bool __must_check try_grab_page(struct page *page, unsigned int flags);
+
static inline __must_check bool try_get_page(struct page *page)
{
page = compound_head(page);
__put_page(page);
}
-/**
- * unpin_user_page() - release a gup-pinned page
- * @page: pointer to page to be released
+/*
+ * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload
+ * the page's refcount so that two separate items are tracked: the original page
+ * reference count, and also a new count of how many pin_user_pages() calls were
+ * made against the page. ("gup-pinned" is another term for the latter).
+ *
+ * With this scheme, pin_user_pages() becomes special: such pages are marked as
+ * distinct from normal pages. As such, the unpin_user_page() call (and its
+ * variants) must be used in order to release gup-pinned pages.
+ *
+ * Choice of value:
+ *
+ * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference
+ * counts with respect to pin_user_pages() and unpin_user_page() becomes
+ * simpler, due to the fact that adding an even power of two to the page
+ * refcount has the effect of using only the upper N bits, for the code that
+ * counts up using the bias value. This means that the lower bits are left for
+ * the exclusive use of the original code that increments and decrements by one
+ * (or at least, by much smaller values than the bias value).
*
- * Pages that were pinned via pin_user_pages*() must be released via either
- * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so
- * that eventually such pages can be separately tracked and uniquely handled. In
- * particular, interactions with RDMA and filesystems need special handling.
+ * Of course, once the lower bits overflow into the upper bits (and this is
+ * OK, because subtraction recovers the original values), then visual inspection
+ * no longer suffices to directly view the separate counts. However, for normal
+ * applications that don't have huge page reference counts, this won't be an
+ * issue.
*
- * unpin_user_page() and put_page() are not interchangeable, despite this early
- * implementation that makes them look the same. unpin_user_page() calls must
- * be perfectly matched up with pin*() calls.
+ * Locking: the lockless algorithm described in page_cache_get_speculative()
+ * and page_cache_gup_pin_speculative() provides safe operation for
+ * get_user_pages and page_mkclean and other calls that race to set up page
+ * table entries.
*/
-static inline void unpin_user_page(struct page *page)
-{
- put_page(page);
-}
+#define GUP_PIN_COUNTING_BIAS (1U << 10)
+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_pages(struct page **pages, unsigned long npages);
+/**
+ * page_maybe_dma_pinned() - report if a page is pinned for DMA.
+ *
+ * This function checks if a page has been pinned via a call to
+ * pin_user_pages*().
+ *
+ * For non-huge pages, the return value is partially fuzzy: false is not fuzzy,
+ * because it means "definitely not pinned for DMA", but true means "probably
+ * pinned for DMA, but possibly a false positive due to having at least
+ * GUP_PIN_COUNTING_BIAS worth of normal page references".
+ *
+ * False positives are OK, because: a) it's unlikely for a page to get that many
+ * refcounts, and b) all the callers of this routine are expected to be able to
+ * deal gracefully with a false positive.
+ *
+ * For more information, please see Documentation/vm/pin_user_pages.rst.
+ *
+ * @page: pointer to page to be queried.
+ * @Return: True, if it is likely that the page has been "dma-pinned".
+ * False, if the page is definitely not dma-pinned.
+ */
+static inline bool page_maybe_dma_pinned(struct page *page)
+{
+ /*
+ * page_ref_count() is signed. If that refcount overflows, then
+ * page_ref_count() returns a negative value, and callers will avoid
+ * further incrementing the refcount.
+ *
+ * Here, for that overflow case, use the signed bit to count a little
+ * bit higher via unsigned math, and thus still get an accurate result.
+ */
+ return ((unsigned int)page_ref_count(compound_head(page))) >=
+ GUP_PIN_COUNTING_BIAS;
+}
+
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTION_IN_PAGE_FLAGS
#endif
projects / linux-2.6-microblaze.git / blobdiff