1 files changed, 247 insertions, 68 deletions

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 306a3d1a0fa6..8b611e13153e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -125,36 +125,11 @@ struct page {
 			struct page_pool *pp;
 			unsigned long _pp_mapping_pad;
 			unsigned long dma_addr;
-			union {
-				/**
-				 * dma_addr_upper: might require a 64-bit
-				 * value on 32-bit architectures.
-				 */
-				unsigned long dma_addr_upper;
-				/**
-				 * For frag page support, not supported in
-				 * 32-bit architectures with 64-bit DMA.
-				 */
-				atomic_long_t pp_frag_count;
-			};
+			atomic_long_t pp_ref_count;
 		};
 		struct {	/* Tail pages of compound page */
 			unsigned long compound_head;	/* Bit zero is set */
 		};
-		struct {	/* Page table pages */
-			unsigned long _pt_pad_1;	/* compound_head */
-			pgtable_t pmd_huge_pte; /* protected by page->ptl */
-			unsigned long _pt_pad_2;	/* mapping */
-			union {
-				struct mm_struct *pt_mm; /* x86 pgds only */
-				atomic_t pt_frag_refcount; /* powerpc */
-			};
-#if ALLOC_SPLIT_PTLOCKS
-			spinlock_t *ptl;
-#else
-			spinlock_t ptl;
-#endif
-		};
 		struct {	/* ZONE_DEVICE pages */
 			/** @pgmap: Points to the hosting device page map. */
 			struct dev_pagemap *pgmap;
@@ -213,6 +188,10 @@ struct page {
 					   not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
 
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+	int _last_cpupid;
+#endif
+
 #ifdef CONFIG_KMSAN
 	/*
 	 * KMSAN metadata for this page:
@@ -224,10 +203,6 @@ struct page {
 	struct page *kmsan_shadow;
 	struct page *kmsan_origin;
 #endif
-
-#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
-	int _last_cpupid;
-#endif
 } _struct_page_alignment;
 
 /*
@@ -262,6 +237,14 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page)
 	return (struct page *)(~ENCODE_PAGE_BITS & (unsigned long)page);
 }
 
+/*
+ * A swap entry has to fit into a "unsigned long", as the entry is hidden
+ * in the "index" field of the swapper address space.
+ */
+typedef struct {
+	unsigned long val;
+} swp_entry_t;
+
 /**
  * struct folio - Represents a contiguous set of bytes.
  * @flags: Identical to the page flags.
@@ -272,14 +255,14 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page)
  * @index: Offset within the file, in units of pages.  For anonymous memory,
  *    this is the index from the beginning of the mmap.
  * @private: Filesystem per-folio data (see folio_attach_private()).
- *    Used for swp_entry_t if folio_test_swapcache().
+ * @swap: Used for swp_entry_t if folio_test_swapcache().
  * @_mapcount: Do not access this member directly.  Use folio_mapcount() to
  *    find out how many times this folio is mapped by userspace.
  * @_refcount: Do not access this member directly.  Use folio_ref_count()
  *    to find how many references there are to this folio.
  * @memcg_data: Memory Control Group data.
- * @_folio_dtor: Which destructor to use for this folio.
- * @_folio_order: Do not use directly, call folio_order().
+ * @virtual: Virtual address in the kernel direct map.
+ * @_last_cpupid: IDs of last CPU and last process that accessed the folio.
  * @_entire_mapcount: Do not use directly, call folio_entire_mapcount().
  * @_nr_pages_mapped: Do not use directly, call folio_mapcount().
  * @_pincount: Do not use directly, call folio_maybe_dma_pinned().
@@ -317,12 +300,21 @@ struct folio {
 			};
 			struct address_space *mapping;
 			pgoff_t index;
-			void *private;
+			union {
+				void *private;
+				swp_entry_t swap;
+			};
 			atomic_t _mapcount;
 			atomic_t _refcount;
 #ifdef CONFIG_MEMCG
 			unsigned long memcg_data;
 #endif
+#if defined(WANT_PAGE_VIRTUAL)
+			void *virtual;
+#endif
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+			int _last_cpupid;
+#endif
 	/* private: the union with struct page is transitional */
 		};
 		struct page page;
@@ -331,9 +323,8 @@ struct folio {
 		struct {
 			unsigned long _flags_1;
 			unsigned long _head_1;
+			unsigned long _folio_avail;
 	/* public: */
-			unsigned char _folio_dtor;
-			unsigned char _folio_order;
 			atomic_t _entire_mapcount;
 			atomic_t _nr_pages_mapped;
 			atomic_t _pincount;
@@ -379,6 +370,12 @@ FOLIO_MATCH(_refcount, _refcount);
 #ifdef CONFIG_MEMCG
 FOLIO_MATCH(memcg_data, memcg_data);
 #endif
+#if defined(WANT_PAGE_VIRTUAL)
+FOLIO_MATCH(virtual, virtual);
+#endif
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+FOLIO_MATCH(_last_cpupid, _last_cpupid);
+#endif
 #undef FOLIO_MATCH
 #define FOLIO_MATCH(pg, fl)						\
 	static_assert(offsetof(struct folio, fl) ==			\
@@ -391,8 +388,89 @@ FOLIO_MATCH(compound_head, _head_1);
 			offsetof(struct page, pg) + 2 * sizeof(struct page))
 FOLIO_MATCH(flags, _flags_2);
 FOLIO_MATCH(compound_head, _head_2);
+FOLIO_MATCH(flags, _flags_2a);
+FOLIO_MATCH(compound_head, _head_2a);
 #undef FOLIO_MATCH
 
+/**
+ * struct ptdesc -    Memory descriptor for page tables.
+ * @__page_flags:     Same as page flags. Unused for page tables.
+ * @pt_rcu_head:      For freeing page table pages.
+ * @pt_list:          List of used page tables. Used for s390 and x86.
+ * @_pt_pad_1:        Padding that aliases with page's compound head.
+ * @pmd_huge_pte:     Protected by ptdesc->ptl, used for THPs.
+ * @__page_mapping:   Aliases with page->mapping. Unused for page tables.
+ * @pt_mm:            Used for x86 pgds.
+ * @pt_frag_refcount: For fragmented page table tracking. Powerpc only.
+ * @_pt_pad_2:        Padding to ensure proper alignment.
+ * @ptl:              Lock for the page table.
+ * @__page_type:      Same as page->page_type. Unused for page tables.
+ * @__page_refcount:  Same as page refcount.
+ * @pt_memcg_data:    Memcg data. Tracked for page tables here.
+ *
+ * This struct overlays struct page for now. Do not modify without a good
+ * understanding of the issues.
+ */
+struct ptdesc {
+	unsigned long __page_flags;
+
+	union {
+		struct rcu_head pt_rcu_head;
+		struct list_head pt_list;
+		struct {
+			unsigned long _pt_pad_1;
+			pgtable_t pmd_huge_pte;
+		};
+	};
+	unsigned long __page_mapping;
+
+	union {
+		struct mm_struct *pt_mm;
+		atomic_t pt_frag_refcount;
+	};
+
+	union {
+		unsigned long _pt_pad_2;
+#if ALLOC_SPLIT_PTLOCKS
+		spinlock_t *ptl;
+#else
+		spinlock_t ptl;
+#endif
+	};
+	unsigned int __page_type;
+	atomic_t __page_refcount;
+#ifdef CONFIG_MEMCG
+	unsigned long pt_memcg_data;
+#endif
+};
+
+#define TABLE_MATCH(pg, pt)						\
+	static_assert(offsetof(struct page, pg) == offsetof(struct ptdesc, pt))
+TABLE_MATCH(flags, __page_flags);
+TABLE_MATCH(compound_head, pt_list);
+TABLE_MATCH(compound_head, _pt_pad_1);
+TABLE_MATCH(mapping, __page_mapping);
+TABLE_MATCH(rcu_head, pt_rcu_head);
+TABLE_MATCH(page_type, __page_type);
+TABLE_MATCH(_refcount, __page_refcount);
+#ifdef CONFIG_MEMCG
+TABLE_MATCH(memcg_data, pt_memcg_data);
+#endif
+#undef TABLE_MATCH
+static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
+
+#define ptdesc_page(pt)			(_Generic((pt),			\
+	const struct ptdesc *:		(const struct page *)(pt),	\
+	struct ptdesc *:		(struct page *)(pt)))
+
+#define ptdesc_folio(pt)		(_Generic((pt),			\
+	const struct ptdesc *:		(const struct folio *)(pt),	\
+	struct ptdesc *:		(struct folio *)(pt)))
+
+#define page_ptdesc(p)			(_Generic((p),			\
+	const struct page *:		(const struct ptdesc *)(p),	\
+	struct page *:			(struct ptdesc *)(p)))
+
 /*
  * Used for sizing the vmemmap region on some architectures
  */
@@ -471,14 +549,65 @@ struct anon_vma_name {
 	char name[];
 };
 
+#ifdef CONFIG_ANON_VMA_NAME
+/*
+ * mmap_lock should be read-locked when calling anon_vma_name(). Caller should
+ * either keep holding the lock while using the returned pointer or it should
+ * raise anon_vma_name refcount before releasing the lock.
+ */
+struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma);
+struct anon_vma_name *anon_vma_name_alloc(const char *name);
+void anon_vma_name_free(struct kref *kref);
+#else /* CONFIG_ANON_VMA_NAME */
+static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+
+static inline struct anon_vma_name *anon_vma_name_alloc(const char *name)
+{
+	return NULL;
+}
+#endif
+
 struct vma_lock {
 	struct rw_semaphore lock;
 };
 
 struct vma_numab_state {
+	/*
+	 * Initialised as time in 'jiffies' after which VMA
+	 * should be scanned.  Delays first scan of new VMA by at
+	 * least sysctl_numa_balancing_scan_delay:
+	 */
 	unsigned long next_scan;
-	unsigned long next_pid_reset;
-	unsigned long access_pids[2];
+
+	/*
+	 * Time in jiffies when pids_active[] is reset to
+	 * detect phase change behaviour:
+	 */
+	unsigned long pids_active_reset;
+
+	/*
+	 * Approximate tracking of PIDs that trapped a NUMA hinting
+	 * fault. May produce false positives due to hash collisions.
+	 *
+	 *   [0] Previous PID tracking
+	 *   [1] Current PID tracking
+	 *
+	 * Window moves after next_pid_reset has expired approximately
+	 * every VMA_PID_RESET_PERIOD jiffies:
+	 */
+	unsigned long pids_active[2];
+
+	/* MM scan sequence ID when scan first started after VMA creation */
+	int start_scan_seq;
+
+	/*
+	 * MM scan sequence ID when the VMA was last completely scanned.
+	 * A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq
+	 */
+	int prev_scan_seq;
 };
 
 /*
@@ -514,6 +643,20 @@ struct vm_area_struct {
 	};
 
 #ifdef CONFIG_PER_VMA_LOCK
+	/*
+	 * Can only be written (using WRITE_ONCE()) while holding both:
+	 *  - mmap_lock (in write mode)
+	 *  - vm_lock->lock (in write mode)
+	 * Can be read reliably while holding one of:
+	 *  - mmap_lock (in read or write mode)
+	 *  - vm_lock->lock (in read or write mode)
+	 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout
+	 * while holding nothing (except RCU to keep the VMA struct allocated).
+	 *
+	 * This sequence counter is explicitly allowed to overflow; sequence
+	 * counter reuse can only lead to occasional unnecessary use of the
+	 * slowpath.
+	 */
 	int vm_lock_seq;
 	struct vma_lock *vm_lock;
 
@@ -573,6 +716,12 @@ struct vm_area_struct {
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 } __randomize_layout;
 
+#ifdef CONFIG_NUMA
+#define vma_policy(vma) ((vma)->vm_policy)
+#else
+#define vma_policy(vma) NULL
+#endif
+
 #ifdef CONFIG_SCHED_MM_CID
 struct mm_cid {
 	u64 time;
@@ -581,8 +730,24 @@ struct mm_cid {
 #endif
 
 struct kioctx_table;
+struct iommu_mm_data;
 struct mm_struct {
 	struct {
+		/*
+		 * Fields which are often written to are placed in a separate
+		 * cache line.
+		 */
+		struct {
+			/**
+			 * @mm_count: The number of references to &struct
+			 * mm_struct (@mm_users count as 1).
+			 *
+			 * Use mmgrab()/mmdrop() to modify. When this drops to
+			 * 0, the &struct mm_struct is freed.
+			 */
+			atomic_t mm_count;
+		} ____cacheline_aligned_in_smp;
+
 		struct maple_tree mm_mt;
 #ifdef CONFIG_MMU
 		unsigned long (*get_unmapped_area) (struct file *filp,
@@ -620,14 +785,6 @@ struct mm_struct {
 		 */
 		atomic_t mm_users;
 
-		/**
-		 * @mm_count: The number of references to &struct mm_struct
-		 * (@mm_users count as 1).
-		 *
-		 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
-		 * &struct mm_struct is freed.
-		 */
-		atomic_t mm_count;
 #ifdef CONFIG_SCHED_MM_CID
 		/**
 		 * @pcpu_cid: Per-cpu current cid.
@@ -672,6 +829,20 @@ struct mm_struct {
 					  * by mmlist_lock
 					  */
 #ifdef CONFIG_PER_VMA_LOCK
+		/*
+		 * This field has lock-like semantics, meaning it is sometimes
+		 * accessed with ACQUIRE/RELEASE semantics.
+		 * Roughly speaking, incrementing the sequence number is
+		 * equivalent to releasing locks on VMAs; reading the sequence
+		 * number can be part of taking a read lock on a VMA.
+		 *
+		 * Can be modified under write mmap_lock using RELEASE
+		 * semantics.
+		 * Can be read with no other protection when holding write
+		 * mmap_lock.
+		 * Can be read with ACQUIRE semantics if not holding write
+		 * mmap_lock.
+		 */
 		int mm_lock_seq;
 #endif
 
@@ -771,13 +942,13 @@ struct mm_struct {
 #endif
 		struct work_struct async_put_work;
 
-#ifdef CONFIG_IOMMU_SVA
-		u32 pasid;
+#ifdef CONFIG_IOMMU_MM_DATA
+		struct iommu_mm_data *iommu_mm;
 #endif
 #ifdef CONFIG_KSM
 		/*
 		 * Represent how many pages of this process are involved in KSM
-		 * merging.
+		 * merging (not including ksm_zero_pages).
 		 */
 		unsigned long ksm_merging_pages;
 		/*
@@ -785,8 +956,13 @@ struct mm_struct {
 		 * including merged and not merged.
 		 */
 		unsigned long ksm_rmap_items;
-#endif
-#ifdef CONFIG_LRU_GEN
+		/*
+		 * Represent how many empty pages are merged with kernel zero
+		 * pages when enabling KSM use_zero_pages.
+		 */
+		unsigned long ksm_zero_pages;
+#endif /* CONFIG_KSM */
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 		struct {
 			/* this mm_struct is on lru_gen_mm_list */
 			struct list_head list;
@@ -801,7 +977,7 @@ struct mm_struct {
 			struct mem_cgroup *memcg;
 #endif
 		} lru_gen;
-#endif /* CONFIG_LRU_GEN */
+#endif /* CONFIG_LRU_GEN_WALKS_MMU */
 	} __randomize_layout;
 
 	/*
@@ -839,11 +1015,13 @@ struct lru_gen_mm_list {
 	spinlock_t lock;
 };
 
+#endif /* CONFIG_LRU_GEN */
+
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
+
 void lru_gen_add_mm(struct mm_struct *mm);
 void lru_gen_del_mm(struct mm_struct *mm);
-#ifdef CONFIG_MEMCG
 void lru_gen_migrate_mm(struct mm_struct *mm);
-#endif
 
 static inline void lru_gen_init_mm(struct mm_struct *mm)
 {
@@ -864,7 +1042,7 @@ static inline void lru_gen_use_mm(struct mm_struct *mm)
 	WRITE_ONCE(mm->lru_gen.bitmap, -1);
 }
 
-#else /* !CONFIG_LRU_GEN */
+#else /* !CONFIG_LRU_GEN_WALKS_MMU */
 
 static inline void lru_gen_add_mm(struct mm_struct *mm)
 {
@@ -874,11 +1052,9 @@ static inline void lru_gen_del_mm(struct mm_struct *mm)
 {
 }
 
-#ifdef CONFIG_MEMCG
 static inline void lru_gen_migrate_mm(struct mm_struct *mm)
 {
 }
-#endif
 
 static inline void lru_gen_init_mm(struct mm_struct *mm)
 {
@@ -888,7 +1064,7 @@ static inline void lru_gen_use_mm(struct mm_struct *mm)
 {
 }
 
-#endif /* CONFIG_LRU_GEN */
+#endif /* CONFIG_LRU_GEN_WALKS_MMU */
 
 struct vma_iterator {
 	struct ma_state mas;
@@ -899,7 +1075,8 @@ struct vma_iterator {
 		.mas = {						\
 			.tree = &(__mm)->mm_mt,				\
 			.index = __addr,				\
-			.node = MAS_START,				\
+			.node = NULL,					\
+			.status = ma_start,				\
 		},							\
 	}
 
@@ -1070,7 +1247,8 @@ enum vm_fault_reason {
 	{ VM_FAULT_RETRY,               "RETRY" },	\
 	{ VM_FAULT_FALLBACK,            "FALLBACK" },	\
 	{ VM_FAULT_DONE_COW,            "DONE_COW" },	\
-	{ VM_FAULT_NEEDDSYNC,           "NEEDDSYNC" }
+	{ VM_FAULT_NEEDDSYNC,           "NEEDDSYNC" },	\
+	{ VM_FAULT_COMPLETED,           "COMPLETED" }
 
 struct vm_special_mapping {
 	const char *name;	/* The name, e.g. "[vdso]". */
@@ -1104,14 +1282,6 @@ enum tlb_flush_reason {
 	NR_TLB_FLUSH_REASONS,
 };
 
- /*
-  * A swap entry has to fit into a "unsigned long", as the entry is hidden
-  * in the "index" field of the swapper address space.
-  */
-typedef struct {
-	unsigned long val;
-} swp_entry_t;
-
 /**
  * enum fault_flag - Fault flag definitions.
  * @FAULT_FLAG_WRITE: Fault was a write fault.
@@ -1251,6 +1421,15 @@ enum {
 	FOLL_PCI_P2PDMA = 1 << 10,
 	/* allow interrupts from generic signals */
 	FOLL_INTERRUPTIBLE = 1 << 11,
+	/*
+	 * Always honor (trigger) NUMA hinting faults.
+	 *
+	 * FOLL_WRITE implicitly honors NUMA hinting faults because a
+	 * PROT_NONE-mapped page is not writable (exceptions with FOLL_FORCE
+	 * apply). get_user_pages_fast_only() always implicitly honors NUMA
+	 * hinting faults.
+	 */
+	FOLL_HONOR_NUMA_FAULT = 1 << 12,
 
 	/* See also internal only FOLL flags in mm/internal.h */
 };