Merge tag 'mm-stable-2022-08-09' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull remaining MM updates from Andrew Morton:
 "Three patch series - two that perform cleanups and one feature:

   - hugetlb_vmemmap cleanups from Muchun Song

   - hardware poisoning support for 1GB hugepages, from Naoya Horiguchi

   - highmem documentation fixups from Fabio De Francesco"

* tag 'mm-stable-2022-08-09' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (23 commits)
  Documentation/mm: add details about kmap_local_page() and preemption
  highmem: delete a sentence from kmap_local_page() kdocs
  Documentation/mm: rrefer kmap_local_page() and avoid kmap()
  Documentation/mm: avoid invalid use of addresses from kmap_local_page()
  Documentation/mm: don't kmap*() pages which can't come from HIGHMEM
  highmem: specify that kmap_local_page() is callable from interrupts
  highmem: remove unneeded spaces in kmap_local_page() kdocs
  mm, hwpoison: enable memory error handling on 1GB hugepage
  mm, hwpoison: skip raw hwpoison page in freeing 1GB hugepage
  mm, hwpoison: make __page_handle_poison returns int
  mm, hwpoison: set PG_hwpoison for busy hugetlb pages
  mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage
  mm, hwpoison, hugetlb: support saving mechanism of raw error pages
  mm/hugetlb: make pud_huge() and follow_huge_pud() aware of non-present pud entry
  mm/hugetlb: check gigantic_page_runtime_supported() in return_unused_surplus_pages()
  mm: hugetlb_vmemmap: use PTRS_PER_PTE instead of PMD_SIZE / PAGE_SIZE
  mm: hugetlb_vmemmap: move code comments to vmemmap_dedup.rst
  mm: hugetlb_vmemmap: improve hugetlb_vmemmap code readability
  mm: hugetlb_vmemmap: replace early_param() with core_param()
  mm: hugetlb_vmemmap: move vmemmap code related to HugeTLB to hugetlb_vmemmap.c
  ...

7 files changed, 39 insertions, 47 deletions

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 177b07944640..25679035ca28 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -60,11 +60,11 @@ static inline void kmap_flush_unused(void);
 
 /**
  * kmap_local_page - Map a page for temporary usage
- * @page:	Pointer to the page to be mapped
+ * @page: Pointer to the page to be mapped
  *
  * Returns: The virtual address of the mapping
  *
- * Can be invoked from any context.
+ * Can be invoked from any context, including interrupts.
  *
  * Requires careful handling when nesting multiple mappings because the map
  * management is stack based. The unmap has to be in the reverse order of
@@ -86,8 +86,7 @@ static inline void kmap_flush_unused(void);
  * temporarily mapped.
  *
  * While it is significantly faster than kmap() for the higmem case it
- * comes with restrictions about the pointer validity. Only use when really
- * necessary.
+ * comes with restrictions about the pointer validity.
  *
  * On HIGHMEM enabled systems mapping a highmem page has the side effect of
  * disabling migration in order to keep the virtual address stable across
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 4cdfce976644..3ec981a0d8b3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -43,6 +43,9 @@ enum {
 	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
 	__MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD,
 #endif
+#ifdef CONFIG_MEMORY_FAILURE
+	SUBPAGE_INDEX_HWPOISON,
+#endif
 	__NR_USED_SUBPAGE,
 };
 
@@ -551,7 +554,7 @@ generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
  *	Synchronization:  Initially set after new page allocation with no
  *	locking.  When examined and modified during migration processing
  *	(isolate, migrate, putback) the hugetlb_lock is held.
- * HPG_temporary - - Set on a page that is temporarily allocated from the buddy
+ * HPG_temporary - Set on a page that is temporarily allocated from the buddy
  *	allocator.  Typically used for migration target pages when no pages
  *	are available in the pool.  The hugetlb free page path will
  *	immediately free pages with this flag set to the buddy allocator.
@@ -561,6 +564,8 @@ generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
  * HPG_freed - Set when page is on the free lists.
  *	Synchronization: hugetlb_lock held for examination and modification.
  * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed.
+ * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page
+ *     that is not tracked by raw_hwp_page list.
  */
 enum hugetlb_page_flags {
 	HPG_restore_reserve = 0,
@@ -568,6 +573,7 @@ enum hugetlb_page_flags {
 	HPG_temporary,
 	HPG_freed,
 	HPG_vmemmap_optimized,
+	HPG_raw_hwp_unreliable,
 	__NR_HPAGEFLAGS,
 };
 
@@ -614,6 +620,7 @@ HPAGEFLAG(Migratable, migratable)
 HPAGEFLAG(Temporary, temporary)
 HPAGEFLAG(Freed, freed)
 HPAGEFLAG(VmemmapOptimized, vmemmap_optimized)
+HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable)
 
 #ifdef CONFIG_HUGETLB_PAGE
 
@@ -638,9 +645,6 @@ struct hstate {
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
-#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
-	unsigned int optimize_vmemmap_pages;
-#endif
 #ifdef CONFIG_CGROUP_HUGETLB
 	/* cgroup control files */
 	struct cftype cgroup_files_dfl[8];
@@ -716,7 +720,7 @@ static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
 	return hstate_file(vma->vm_file);
 }
 
-static inline unsigned long huge_page_size(struct hstate *h)
+static inline unsigned long huge_page_size(const struct hstate *h)
 {
 	return (unsigned long)PAGE_SIZE << h->order;
 }
@@ -745,7 +749,7 @@ static inline bool hstate_is_gigantic(struct hstate *h)
 	return huge_page_order(h) >= MAX_ORDER;
 }
 
-static inline unsigned int pages_per_huge_page(struct hstate *h)
+static inline unsigned int pages_per_huge_page(const struct hstate *h)
 {
 	return 1 << h->order;
 }
@@ -799,6 +803,14 @@ extern int dissolve_free_huge_page(struct page *page);
 extern int dissolve_free_huge_pages(unsigned long start_pfn,
 				    unsigned long end_pfn);
 
+#ifdef CONFIG_MEMORY_FAILURE
+extern void hugetlb_clear_page_hwpoison(struct page *hpage);
+#else
+static inline void hugetlb_clear_page_hwpoison(struct page *hpage)
+{
+}
+#endif
+
 #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
 #ifndef arch_hugetlb_migration_supported
 static inline bool arch_hugetlb_migration_supported(struct hstate *h)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 18e01474cf6b..3bedc449c14d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3142,13 +3142,6 @@ static inline void print_vma_addr(char *prefix, unsigned long rip)
 }
 #endif
 
-#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
-int vmemmap_remap_free(unsigned long start, unsigned long end,
-		       unsigned long reuse);
-int vmemmap_remap_alloc(unsigned long start, unsigned long end,
-			unsigned long reuse, gfp_t gfp_mask);
-#endif
-
 void *sparse_buffer_alloc(unsigned long size);
 struct page * __populate_section_memmap(unsigned long pfn,
 		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
@@ -3183,6 +3176,7 @@ enum mf_flags {
 	MF_SOFT_OFFLINE = 1 << 3,
 	MF_UNPOISON = 1 << 4,
 	MF_SW_SIMULATED = 1 << 5,
+	MF_NO_RETRY = 1 << 6,
 };
 int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		      unsigned long count, int mf_flags);
@@ -3235,7 +3229,6 @@ enum mf_action_page_type {
 	MF_MSG_DIFFERENT_COMPOUND,
 	MF_MSG_HUGE,
 	MF_MSG_FREE_HUGE,
-	MF_MSG_NON_PMD_HUGE,
 	MF_MSG_UNMAP_FAILED,
 	MF_MSG_DIRTY_SWAPCACHE,
 	MF_MSG_CLEAN_SWAPCACHE,
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index ea19528564d1..465ff35a8c00 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -205,34 +205,15 @@ enum pageflags {
 #ifndef __GENERATING_BOUNDS_H
 
 #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
-DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON,
-			 hugetlb_optimize_vmemmap_key);
-
-static __always_inline bool hugetlb_optimize_vmemmap_enabled(void)
-{
-	return static_branch_maybe(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON,
-				   &hugetlb_optimize_vmemmap_key);
-}
+DECLARE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key);
 
 /*
- * If the feature of optimizing 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.
+ * Return the real head page struct iff the @page is a fake head page, otherwise
+ * return the @page itself. See Documentation/mm/vmemmap_dedup.rst.
  */
 static __always_inline const struct page *page_fixed_fake_head(const struct page *page)
 {
-	if (!hugetlb_optimize_vmemmap_enabled())
+	if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key))
 		return page;
 
 	/*
@@ -260,11 +241,6 @@ static inline const struct page *page_fixed_fake_head(const struct page *page)
 {
 	return page;
 }
-
-static inline bool hugetlb_optimize_vmemmap_enabled(void)
-{
-	return false;
-}
 #endif
 
 static __always_inline int page_is_fake_head(struct page *page)
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index bb7afd03a324..a3d435bf9f97 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -490,6 +490,11 @@ static inline void num_poisoned_pages_dec(void)
 	atomic_long_dec(&num_poisoned_pages);
 }
 
+static inline void num_poisoned_pages_sub(long i)
+{
+	atomic_long_sub(i, &num_poisoned_pages);
+}
+
 #else
 
 static inline swp_entry_t make_hwpoison_entry(struct page *page)
@@ -505,6 +510,10 @@ static inline int is_hwpoison_entry(swp_entry_t swp)
 static inline void num_poisoned_pages_inc(void)
 {
 }
+
+static inline void num_poisoned_pages_sub(long i)
+{
+}
 #endif
 
 static inline int non_swap_entry(swp_entry_t entry)
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 17b42ce89d3e..780690dc08cd 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -268,6 +268,10 @@ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table *
 	return NULL;
 }
 
+static inline void register_sysctl_init(const char *path, struct ctl_table *table)
+{
+}
+
 static inline struct ctl_table_header *register_sysctl_mount_point(const char *path)
 {
 	return NULL;
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index d0337a41141c..cbd3ddd7c33d 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -360,7 +360,6 @@ TRACE_EVENT(aer_event,
 	EM ( MF_MSG_DIFFERENT_COMPOUND, "different compound page after locking" ) \
 	EM ( MF_MSG_HUGE, "huge page" )					\
 	EM ( MF_MSG_FREE_HUGE, "free huge page" )			\
-	EM ( MF_MSG_NON_PMD_HUGE, "non-pmd-sized huge page" )		\
 	EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" )		\
 	EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" )		\
 	EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" )		\