1 files changed, 88 insertions, 6 deletions

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 1c3b6e5c8bfd..9d8eeaa67d05 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -190,13 +190,81 @@ enum pageflags {
 
 #ifndef __GENERATING_BOUNDS_H
 
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
+			 hugetlb_free_vmemmap_enabled_key);
+
+static __always_inline bool hugetlb_free_vmemmap_enabled(void)
+{
+	return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
+				   &hugetlb_free_vmemmap_enabled_key);
+}
+
+/*
+ * If the feature of freeing some vmemmap pages associated with each HugeTLB
+ * page is enabled, the head vmemmap page frame is reused and all of the tail
+ * vmemmap addresses map to the head vmemmap page frame (furture details can
+ * refer to the figure at the head of the mm/hugetlb_vmemmap.c).  In other
+ * words, there are more than one page struct with PG_head associated with each
+ * HugeTLB page.  We __know__ that there is only one head page struct, the tail
+ * page structs with PG_head are fake head page structs.  We need an approach
+ * to distinguish between those two different types of page structs so that
+ * compound_head() can return the real head page struct when the parameter is
+ * the tail page struct but with PG_head.
+ *
+ * The page_fixed_fake_head() returns the real head page struct if the @page is
+ * fake page head, otherwise, returns @page which can either be a true page
+ * head or tail.
+ */
+static __always_inline const struct page *page_fixed_fake_head(const struct page *page)
+{
+	if (!hugetlb_free_vmemmap_enabled())
+		return page;
+
+	/*
+	 * Only addresses aligned with PAGE_SIZE of struct page may be fake head
+	 * struct page. The alignment check aims to avoid access the fields (
+	 * e.g. compound_head) of the @page[1]. It can avoid touch a (possibly)
+	 * cold cacheline in some cases.
+	 */
+	if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) &&
+	    test_bit(PG_head, &page->flags)) {
+		/*
+		 * We can safely access the field of the @page[1] with PG_head
+		 * because the @page is a compound page composed with at least
+		 * two contiguous pages.
+		 */
+		unsigned long head = READ_ONCE(page[1].compound_head);
+
+		if (likely(head & 1))
+			return (const struct page *)(head - 1);
+	}
+	return page;
+}
+#else
+static inline const struct page *page_fixed_fake_head(const struct page *page)
+{
+	return page;
+}
+
+static inline bool hugetlb_free_vmemmap_enabled(void)
+{
+	return false;
+}
+#endif
+
+static __always_inline int page_is_fake_head(struct page *page)
+{
+	return page_fixed_fake_head(page) != page;
+}
+
 static inline unsigned long _compound_head(const struct page *page)
 {
 	unsigned long head = READ_ONCE(page->compound_head);
 
 	if (unlikely(head & 1))
 		return head - 1;
-	return (unsigned long)page;
+	return (unsigned long)page_fixed_fake_head(page);
 }
 
 #define compound_head(page)	((typeof(page))_compound_head(page))
@@ -231,12 +299,13 @@ static inline unsigned long _compound_head(const struct page *page)
 
 static __always_inline int PageTail(struct page *page)
 {
-	return READ_ONCE(page->compound_head) & 1;
+	return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page);
 }
 
 static __always_inline int PageCompound(struct page *page)
 {
-	return test_bit(PG_head, &page->flags) || PageTail(page);
+	return test_bit(PG_head, &page->flags) ||
+	       READ_ONCE(page->compound_head) & 1;
 }
 
 #define	PAGE_POISON_PATTERN	-1l
@@ -412,7 +481,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
 	TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname)
 
 __PAGEFLAG(Locked, locked, PF_NO_TAIL)
-PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
+PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
 PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL)
 PAGEFLAG(Referenced, referenced, PF_HEAD)
 	TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
@@ -695,7 +764,20 @@ static inline bool test_set_page_writeback(struct page *page)
 	return set_page_writeback(page);
 }
 
-__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
+static __always_inline bool folio_test_head(struct folio *folio)
+{
+	return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY));
+}
+
+static __always_inline int PageHead(struct page *page)
+{
+	PF_POISONED_CHECK(page);
+	return test_bit(PG_head, &page->flags) && !page_is_fake_head(page);
+}
+
+__SETPAGEFLAG(Head, head, PF_ANY)
+__CLEARPAGEFLAG(Head, head, PF_ANY)
+CLEARPAGEFLAG(Head, head, PF_ANY)
 
 /**
  * folio_test_large() - Does this folio contain more than one page?
@@ -918,7 +1000,7 @@ PAGE_TYPE_OPS(Guard, guard)
 
 extern bool is_free_buddy_page(struct page *page);
 
-__PAGEFLAG(Isolated, isolated, PF_ANY);
+PAGEFLAG(Isolated, isolated, PF_ANY);
 
 #ifdef CONFIG_MMU
 #define __PG_MLOCKED		(1UL << PG_mlocked)