1 files changed, 132 insertions, 53 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 00351ccb49a3..8b4f93e84868 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -16,8 +16,9 @@
 struct ctl_table;
 struct user_struct;
 struct mmu_gather;
+struct node;
 
-#ifndef is_hugepd
+#ifndef CONFIG_ARCH_HAS_HUGEPD
 typedef struct { unsigned long pd; } hugepd_t;
 #define is_hugepd(hugepd) (0)
 #define __hugepd(x) ((hugepd_t) { (x) })
@@ -43,6 +44,9 @@ 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,
 };
 
@@ -111,6 +115,12 @@ struct file_region {
 #endif
 };
 
+struct hugetlb_vma_lock {
+	struct kref refs;
+	struct rw_semaphore rw_sema;
+	struct vm_area_struct *vma;
+};
+
 extern struct resv_map *resv_map_alloc(void);
 void resv_map_release(struct kref *ref);
 
@@ -123,7 +133,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
 						long min_hpages);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
-void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
+void hugetlb_dup_vma_private(struct vm_area_struct *vma);
 void clear_vma_resv_huge_pages(struct vm_area_struct *vma);
 int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *);
 int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *,
@@ -137,20 +147,22 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 			     struct vm_area_struct *new_vma,
 			     unsigned long old_addr, unsigned long new_addr,
 			     unsigned long len);
-int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
+int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
+			    struct vm_area_struct *, struct vm_area_struct *);
 long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			 struct page **, struct vm_area_struct **,
 			 unsigned long *, unsigned long *, long, unsigned int,
 			 int *);
 void unmap_hugepage_range(struct vm_area_struct *,
-			  unsigned long, unsigned long, struct page *);
+			  unsigned long, unsigned long, struct page *,
+			  zap_flags_t);
 void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 			  struct vm_area_struct *vma,
 			  unsigned long start, unsigned long end,
-			  struct page *ref_page);
+			  struct page *ref_page, zap_flags_t zap_flags);
 void hugetlb_report_meminfo(struct seq_file *);
 int hugetlb_report_node_meminfo(char *buf, int len, int nid);
-void hugetlb_show_meminfo(void);
+void hugetlb_show_meminfo_node(int nid);
 unsigned long hugetlb_total_pages(void);
 vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, unsigned int flags);
@@ -160,15 +172,17 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte,
 				unsigned long dst_addr,
 				unsigned long src_addr,
 				enum mcopy_atomic_mode mode,
-				struct page **pagep);
+				struct page **pagep,
+				bool wp_copy);
 #endif /* CONFIG_USERFAULTFD */
 bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						vm_flags_t vm_flags);
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
-bool isolate_huge_page(struct page *page, struct list_head *list);
+int isolate_hugetlb(struct page *page, struct list_head *list);
 int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags);
 void putback_active_hugepage(struct page *page);
 void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
 void free_huge_page(struct page *page);
@@ -190,8 +204,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
+unsigned long hugetlb_mask_last_page(struct hstate *h);
 int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
-				unsigned long *addr, pte_t *ptep);
+				unsigned long addr, pte_t *ptep);
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
@@ -199,24 +214,33 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 struct page *follow_huge_pd(struct vm_area_struct *vma,
 			    unsigned long address, hugepd_t hpd,
 			    int flags, int pdshift);
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-				pmd_t *pmd, int flags);
+struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address,
+				 int flags);
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int flags);
 struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
 			     pgd_t *pgd, int flags);
 
+void hugetlb_vma_lock_read(struct vm_area_struct *vma);
+void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
+void hugetlb_vma_lock_write(struct vm_area_struct *vma);
+void hugetlb_vma_unlock_write(struct vm_area_struct *vma);
+int hugetlb_vma_trylock_write(struct vm_area_struct *vma);
+void hugetlb_vma_assert_locked(struct vm_area_struct *vma);
+void hugetlb_vma_lock_release(struct kref *kref);
+
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pud);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
-		unsigned long address, unsigned long end, pgprot_t newprot);
+		unsigned long address, unsigned long end, pgprot_t newprot,
+		unsigned long cp_flags);
 
 bool is_hugetlb_entry_migration(pte_t pte);
 void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
-static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
+static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 {
 }
 
@@ -237,7 +261,7 @@ static inline struct address_space *hugetlb_page_mapping_lock_write(
 
 static inline int huge_pmd_unshare(struct mm_struct *mm,
 					struct vm_area_struct *vma,
-					unsigned long *addr, pte_t *ptep)
+					unsigned long addr, pte_t *ptep)
 {
 	return 0;
 }
@@ -265,7 +289,9 @@ static inline struct page *follow_huge_addr(struct mm_struct *mm,
 }
 
 static inline int copy_hugetlb_page_range(struct mm_struct *dst,
-			struct mm_struct *src, struct vm_area_struct *vma)
+					  struct mm_struct *src,
+					  struct vm_area_struct *dst_vma,
+					  struct vm_area_struct *src_vma)
 {
 	BUG();
 	return 0;
@@ -290,7 +316,7 @@ static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid)
 	return 0;
 }
 
-static inline void hugetlb_show_meminfo(void)
+static inline void hugetlb_show_meminfo_node(int nid)
 {
 }
 
@@ -301,8 +327,8 @@ static inline struct page *follow_huge_pd(struct vm_area_struct *vma,
 	return NULL;
 }
 
-static inline struct page *follow_huge_pmd(struct mm_struct *mm,
-				unsigned long address, pmd_t *pmd, int flags)
+static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma,
+				unsigned long address, int flags)
 {
 	return NULL;
 }
@@ -325,6 +351,31 @@ static inline int prepare_hugepage_range(struct file *file,
 	return -EINVAL;
 }
 
+static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma)
+{
+}
+
+static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma)
+{
+	return 1;
+}
+
+static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
+{
+}
+
 static inline int pmd_huge(pmd_t pmd)
 {
 	return 0;
@@ -355,7 +406,8 @@ static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 						unsigned long dst_addr,
 						unsigned long src_addr,
 						enum mcopy_atomic_mode mode,
-						struct page **pagep)
+						struct page **pagep,
+						bool wp_copy)
 {
 	BUG();
 	return 0;
@@ -368,9 +420,9 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 	return NULL;
 }
 
-static inline bool isolate_huge_page(struct page *page, struct list_head *list)
+static inline int isolate_hugetlb(struct page *page, struct list_head *list)
 {
-	return false;
+	return -EBUSY;
 }
 
 static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
@@ -378,6 +430,11 @@ static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
 	return 0;
 }
 
+static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+{
+	return 0;
+}
+
 static inline void putback_active_hugepage(struct page *page)
 {
 }
@@ -389,14 +446,16 @@ static inline void move_hugetlb_state(struct page *oldpage,
 
 static inline unsigned long hugetlb_change_protection(
 			struct vm_area_struct *vma, unsigned long address,
-			unsigned long end, pgprot_t newprot)
+			unsigned long end, pgprot_t newprot,
+			unsigned long cp_flags)
 {
 	return 0;
 }
 
 static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 			struct vm_area_struct *vma, unsigned long start,
-			unsigned long end, struct page *ref_page)
+			unsigned long end, struct page *ref_page,
+			zap_flags_t zap_flags)
 {
 	BUG();
 }
@@ -513,6 +572,11 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long flags);
 #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */
 
+unsigned long
+generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+				  unsigned long len, unsigned long pgoff,
+				  unsigned long flags);
+
 /*
  * huegtlb page specific state flags.  These flags are located in page.private
  * of the hugetlb head page.  Functions created via the below macros should be
@@ -530,7 +594,7 @@ unsigned long 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.
@@ -540,6 +604,8 @@ unsigned long 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,
@@ -547,6 +613,7 @@ enum hugetlb_page_flags {
 	HPG_temporary,
 	HPG_freed,
 	HPG_vmemmap_optimized,
+	HPG_raw_hwp_unreliable,
 	__NR_HPAGEFLAGS,
 };
 
@@ -593,6 +660,7 @@ HPAGEFLAG(Migratable, migratable)
 HPAGEFLAG(Temporary, temporary)
 HPAGEFLAG(Freed, freed)
 HPAGEFLAG(VmemmapOptimized, vmemmap_optimized)
+HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable)
 
 #ifdef CONFIG_HUGETLB_PAGE
 
@@ -617,13 +685,10 @@ 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_FREE_VMEMMAP
-	unsigned int nr_free_vmemmap_pages;
-#endif
 #ifdef CONFIG_CGROUP_HUGETLB
 	/* cgroup control files */
-	struct cftype cgroup_files_dfl[7];
-	struct cftype cgroup_files_legacy[9];
+	struct cftype cgroup_files_dfl[8];
+	struct cftype cgroup_files_legacy[10];
 #endif
 	char name[HSTATE_NAME_LEN];
 };
@@ -640,7 +705,7 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
 				nodemask_t *nmask, gfp_t gfp_mask);
 struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
-int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
+int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address, struct page *page);
@@ -695,7 +760,7 @@ 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;
 }
@@ -724,7 +789,7 @@ 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;
 }
@@ -754,7 +819,7 @@ static inline void arch_clear_hugepage_flags(struct page *page) { }
 static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift,
 				       vm_flags_t flags)
 {
-	return entry;
+	return pte_mkhuge(entry);
 }
 #endif
 
@@ -778,6 +843,14 @@ 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)
@@ -883,14 +956,6 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 	atomic_long_sub(l, &mm->hugetlb_usage);
 }
 
-#ifndef set_huge_swap_pte_at
-static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
-					pte_t *ptep, pte_t pte, unsigned long sz)
-{
-	set_huge_pte_at(mm, addr, ptep, pte);
-}
-#endif
-
 #ifndef huge_ptep_modify_prot_start
 #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
 static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
@@ -910,6 +975,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 }
 #endif
 
+#ifdef CONFIG_NUMA
+void hugetlb_register_node(struct node *node);
+void hugetlb_unregister_node(struct node *node);
+#endif
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
@@ -970,6 +1040,11 @@ static inline struct hstate *page_hstate(struct page *page)
 	return NULL;
 }
 
+static inline struct hstate *size_to_hstate(unsigned long size)
+{
+	return NULL;
+}
+
 static inline unsigned long huge_page_size(struct hstate *h)
 {
 	return PAGE_SIZE;
@@ -1069,17 +1144,25 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 {
 }
 
-static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
-					pte_t *ptep, pte_t pte, unsigned long sz)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
 {
+	return *ptep;
 }
-#endif	/* CONFIG_HUGETLB_PAGE */
 
-#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
-extern bool hugetlb_free_vmemmap_enabled;
-#else
-#define hugetlb_free_vmemmap_enabled	false
-#endif
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+}
+
+static inline void hugetlb_register_node(struct node *node)
+{
+}
+
+static inline void hugetlb_unregister_node(struct node *node)
+{
+}
+#endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
 					struct mm_struct *mm, pte_t *pte)
@@ -1093,14 +1176,10 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h,
 
 #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
 extern void __init hugetlb_cma_reserve(int order);
-extern void __init hugetlb_cma_check(void);
 #else
 static inline __init void hugetlb_cma_reserve(int order)
 {
 }
-static inline __init void hugetlb_cma_check(void)
-{
-}
 #endif
 
 bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);