Merge pull request #744 from angolini/lf-6.12.20-2.0.0_up_6.12.49toradex_6.12-2.0.x-imx

Lf 6.12.20 2.0.0 up 6.12.49

1 files changed, 118 insertions, 0 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8617adc6becd..41f5c88bdf3b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2200,6 +2200,61 @@ static inline bool folio_likely_mapped_shared(struct folio *folio)
 	return atomic_read(&folio->_mapcount) > 0;
 }
 
+/**
+ * folio_expected_ref_count - calculate the expected folio refcount
+ * @folio: the folio
+ *
+ * Calculate the expected folio refcount, taking references from the pagecache,
+ * swapcache, PG_private and page table mappings into account. Useful in
+ * combination with folio_ref_count() to detect unexpected references (e.g.,
+ * GUP or other temporary references).
+ *
+ * Does currently not consider references from the LRU cache. If the folio
+ * was isolated from the LRU (which is the case during migration or split),
+ * the LRU cache does not apply.
+ *
+ * Calling this function on an unmapped folio -- !folio_mapped() -- that is
+ * locked will return a stable result.
+ *
+ * Calling this function on a mapped folio will not result in a stable result,
+ * because nothing stops additional page table mappings from coming (e.g.,
+ * fork()) or going (e.g., munmap()).
+ *
+ * Calling this function without the folio lock will also not result in a
+ * stable result: for example, the folio might get dropped from the swapcache
+ * concurrently.
+ *
+ * However, even when called without the folio lock or on a mapped folio,
+ * this function can be used to detect unexpected references early (for example,
+ * if it makes sense to even lock the folio and unmap it).
+ *
+ * The caller must add any reference (e.g., from folio_try_get()) it might be
+ * holding itself to the result.
+ *
+ * Returns the expected folio refcount.
+ */
+static inline int folio_expected_ref_count(const struct folio *folio)
+{
+	const int order = folio_order(folio);
+	int ref_count = 0;
+
+	if (WARN_ON_ONCE(folio_test_slab(folio)))
+		return 0;
+
+	if (folio_test_anon(folio)) {
+		/* One reference per page from the swapcache. */
+		ref_count += folio_test_swapcache(folio) << order;
+	} else if (!((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS)) {
+		/* One reference per page from the pagecache. */
+		ref_count += !!folio->mapping << order;
+		/* One reference from PG_private. */
+		ref_count += folio_test_private(folio);
+	}
+
+	/* One reference per page table mapping. */
+	return ref_count + folio_mapcount(folio);
+}
+
 #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE
 static inline int arch_make_folio_accessible(struct folio *folio)
 {
@@ -2592,6 +2647,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 	return percpu_counter_read_positive(&mm->rss_stat[member]);
 }
 
+static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member)
+{
+	return percpu_counter_sum_positive(&mm->rss_stat[member]);
+}
+
 void mm_trace_rss_stat(struct mm_struct *mm, int member);
 
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
@@ -4243,4 +4303,62 @@ static inline void pgalloc_tag_copy(struct folio *new, struct folio *old)
 }
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 
+/*
+ * DMA mapping IDs for page_pool
+ *
+ * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and
+ * stashes it in the upper bits of page->pp_magic. We always want to be able to
+ * unambiguously identify page pool pages (using page_pool_page_is_pp()). Non-PP
+ * pages can have arbitrary kernel pointers stored in the same field as pp_magic
+ * (since it overlaps with page->lru.next), so we must ensure that we cannot
+ * mistake a valid kernel pointer with any of the values we write into this
+ * field.
+ *
+ * On architectures that set POISON_POINTER_DELTA, this is already ensured,
+ * since this value becomes part of PP_SIGNATURE; meaning we can just use the
+ * space between the PP_SIGNATURE value (without POISON_POINTER_DELTA), and the
+ * lowest bits of POISON_POINTER_DELTA. On arches where POISON_POINTER_DELTA is
+ * 0, we make sure that we leave the two topmost bits empty, as that guarantees
+ * we won't mistake a valid kernel pointer for a value we set, regardless of the
+ * VMSPLIT setting.
+ *
+ * Altogether, this means that the number of bits available is constrained by
+ * the size of an unsigned long (at the upper end, subtracting two bits per the
+ * above), and the definition of PP_SIGNATURE (with or without
+ * POISON_POINTER_DELTA).
+ */
+#define PP_DMA_INDEX_SHIFT (1 + __fls(PP_SIGNATURE - POISON_POINTER_DELTA))
+#if POISON_POINTER_DELTA > 0
+/* PP_SIGNATURE includes POISON_POINTER_DELTA, so limit the size of the DMA
+ * index to not overlap with that if set
+ */
+#define PP_DMA_INDEX_BITS MIN(32, __ffs(POISON_POINTER_DELTA) - PP_DMA_INDEX_SHIFT)
+#else
+/* Always leave out the topmost two; see above. */
+#define PP_DMA_INDEX_BITS MIN(32, BITS_PER_LONG - PP_DMA_INDEX_SHIFT - 2)
+#endif
+
+#define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \
+				  PP_DMA_INDEX_SHIFT)
+
+/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
+ * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
+ * the head page of compound page and bit 1 for pfmemalloc page, as well as the
+ * bits used for the DMA index. page_is_pfmemalloc() is checked in
+ * __page_pool_put_page() to avoid recycling the pfmemalloc page.
+ */
+#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
+
+#ifdef CONFIG_PAGE_POOL
+static inline bool page_pool_page_is_pp(struct page *page)
+{
+	return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
+}
+#else
+static inline bool page_pool_page_is_pp(struct page *page)
+{
+	return false;
+}
+#endif
+
 #endif /* _LINUX_MM_H */