1 files changed, 80 insertions, 35 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b94c2e8ee918..7748489fde1b 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -37,8 +37,14 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
 		    unsigned long cp_flags);
 
-vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
-vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn,
+			      bool write);
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn,
+			      bool write);
+vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio,
+				bool write);
+vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
+				bool write);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_UNSUPPORTED,
@@ -121,6 +127,8 @@ enum mthp_stat_item {
 	MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE,
 	MTHP_STAT_ZSWPOUT,
 	MTHP_STAT_SWPIN,
+	MTHP_STAT_SWPIN_FALLBACK,
+	MTHP_STAT_SWPIN_FALLBACK_CHARGE,
 	MTHP_STAT_SWPOUT,
 	MTHP_STAT_SWPOUT_FALLBACK,
 	MTHP_STAT_SHMEM_ALLOC,
@@ -255,7 +263,7 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
 }
 
 unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
-					 unsigned long vm_flags,
+					 vm_flags_t vm_flags,
 					 unsigned long tva_flags,
 					 unsigned long orders);
 
@@ -276,7 +284,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
  */
 static inline
 unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
-				       unsigned long vm_flags,
+				       vm_flags_t vm_flags,
 				       unsigned long tva_flags,
 				       unsigned long orders)
 {
@@ -311,7 +319,7 @@ struct thpsize {
 	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
 
 static inline bool vma_thp_disabled(struct vm_area_struct *vma,
-		unsigned long vm_flags)
+		vm_flags_t vm_flags)
 {
 	/*
 	 * Explicitly disabled through madvise or prctl, or some
@@ -339,6 +347,36 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		unsigned int new_order);
 int min_order_for_split(struct folio *folio);
 int split_folio_to_list(struct folio *folio, struct list_head *list);
+bool uniform_split_supported(struct folio *folio, unsigned int new_order,
+		bool warns);
+bool non_uniform_split_supported(struct folio *folio, unsigned int new_order,
+		bool warns);
+int folio_split(struct folio *folio, unsigned int new_order, struct page *page,
+		struct list_head *list);
+/*
+ * try_folio_split - try to split a @folio at @page using non uniform split.
+ * @folio: folio to be split
+ * @page: split to order-0 at the given page
+ * @list: store the after-split folios
+ *
+ * Try to split a @folio at @page using non uniform split to order-0, if
+ * non uniform split is not supported, fall back to uniform split.
+ *
+ * Return: 0: split is successful, otherwise split failed.
+ */
+static inline int try_folio_split(struct folio *folio, struct page *page,
+		struct list_head *list)
+{
+	int ret = min_order_for_split(folio);
+
+	if (ret < 0)
+		return ret;
+
+	if (!non_uniform_split_supported(folio, 0, false))
+		return split_huge_page_to_list_to_order(&folio->page, list,
+				ret);
+	return folio_split(folio, ret, page, list);
+}
 static inline int split_huge_page(struct page *page)
 {
 	struct folio *folio = page_folio(page);
@@ -359,20 +397,18 @@ static inline int split_huge_page(struct page *page)
 void deferred_split_folio(struct folio *folio, bool partially_mapped);
 
 void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long address, bool freeze, struct folio *folio);
+		unsigned long address, bool freeze);
 
 #define split_huge_pmd(__vma, __pmd, __address)				\
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
-		if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd)	\
-					|| pmd_devmap(*____pmd))	\
+		if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd))	\
 			__split_huge_pmd(__vma, __pmd, __address,	\
-						false, NULL);		\
+					 false);			\
 	}  while (0)
 
-
 void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
-		bool freeze, struct folio *folio);
+		bool freeze);
 
 void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
 		unsigned long address);
@@ -391,18 +427,16 @@ change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
 #define split_huge_pud(__vma, __pud, __address)				\
 	do {								\
 		pud_t *____pud = (__pud);				\
-		if (pud_trans_huge(*____pud)				\
-					|| pud_devmap(*____pud))	\
+		if (pud_trans_huge(*____pud))				\
 			__split_huge_pud(__vma, __pud, __address);	\
 	}  while (0)
 
-int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags,
+int hugepage_madvise(struct vm_area_struct *vma, vm_flags_t *vm_flags,
 		     int advice);
-int madvise_collapse(struct vm_area_struct *vma,
-		     struct vm_area_struct **prev,
-		     unsigned long start, unsigned long end);
+int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end, bool *lock_dropped);
 void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start,
-			   unsigned long end, long adjust_next);
+			   unsigned long end, struct vm_area_struct *next);
 spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma);
 spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma);
 
@@ -415,7 +449,7 @@ static inline int is_swap_pmd(pmd_t pmd)
 static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 		struct vm_area_struct *vma)
 {
-	if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
+	if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd))
 		return __pmd_trans_huge_lock(pmd, vma);
 	else
 		return NULL;
@@ -423,7 +457,7 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
 		struct vm_area_struct *vma)
 {
-	if (pud_trans_huge(*pud) || pud_devmap(*pud))
+	if (pud_trans_huge(*pud))
 		return __pud_trans_huge_lock(pud, vma);
 	else
 		return NULL;
@@ -438,9 +472,6 @@ static inline bool folio_test_pmd_mappable(struct folio *folio)
 	return folio_order(folio) >= HPAGE_PMD_ORDER;
 }
 
-struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, int flags, struct dev_pagemap **pgmap);
-
 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf);
 
 extern struct folio *huge_zero_folio;
@@ -451,23 +482,26 @@ static inline bool is_huge_zero_folio(const struct folio *folio)
 	return READ_ONCE(huge_zero_folio) == folio;
 }
 
+static inline bool is_huge_zero_pfn(unsigned long pfn)
+{
+	return READ_ONCE(huge_zero_pfn) == (pfn & ~(HPAGE_PMD_NR - 1));
+}
+
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
-	return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd);
+	return pmd_present(pmd) && is_huge_zero_pfn(pmd_pfn(pmd));
 }
 
 struct folio *mm_get_huge_zero_folio(struct mm_struct *mm);
 void mm_put_huge_zero_folio(struct mm_struct *mm);
 
-#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot))
-
 static inline bool thp_migration_supported(void)
 {
 	return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
 }
 
 void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
-			   pmd_t *pmd, bool freeze, struct folio *folio);
+			   pmd_t *pmd, bool freeze);
 bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr,
 			   pmd_t *pmdp, struct folio *folio);
 
@@ -491,7 +525,7 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
 }
 
 static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
-					unsigned long vm_flags,
+					vm_flags_t vm_flags,
 					unsigned long tva_flags,
 					unsigned long orders)
 {
@@ -531,17 +565,23 @@ static inline int split_folio_to_list(struct folio *folio, struct list_head *lis
 	return 0;
 }
 
+static inline int try_folio_split(struct folio *folio, struct page *page,
+		struct list_head *list)
+{
+	return 0;
+}
+
 static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {}
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)
 
 static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long address, bool freeze, struct folio *folio) {}
+		unsigned long address, bool freeze) {}
 static inline void split_huge_pmd_address(struct vm_area_struct *vma,
-		unsigned long address, bool freeze, struct folio *folio) {}
+		unsigned long address, bool freeze) {}
 static inline void split_huge_pmd_locked(struct vm_area_struct *vma,
 					 unsigned long address, pmd_t *pmd,
-					 bool freeze, struct folio *folio) {}
+					 bool freeze) {}
 
 static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma,
 					 unsigned long addr, pmd_t *pmdp,
@@ -554,14 +594,14 @@ static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma,
 	do { } while (0)
 
 static inline int hugepage_madvise(struct vm_area_struct *vma,
-				   unsigned long *vm_flags, int advice)
+				   vm_flags_t *vm_flags, int advice)
 {
 	return -EINVAL;
 }
 
 static inline int madvise_collapse(struct vm_area_struct *vma,
-				   struct vm_area_struct **prev,
-				   unsigned long start, unsigned long end)
+				   unsigned long start,
+				   unsigned long end, bool *lock_dropped)
 {
 	return -EINVAL;
 }
@@ -569,7 +609,7 @@ static inline int madvise_collapse(struct vm_area_struct *vma,
 static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 unsigned long start,
 					 unsigned long end,
-					 long adjust_next)
+					 struct vm_area_struct *next)
 {
 }
 static inline int is_swap_pmd(pmd_t pmd)
@@ -597,6 +637,11 @@ static inline bool is_huge_zero_folio(const struct folio *folio)
 	return false;
 }
 
+static inline bool is_huge_zero_pfn(unsigned long pfn)
+{
+	return false;
+}
+
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
 	return false;