diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 1722 |
1 files changed, 1093 insertions, 629 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index 2bbf73eb53e7..7a1819c20643 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -12,6 +12,7 @@ #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> +#include <linux/compiler.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> @@ -31,6 +32,10 @@ #include <linux/kasan.h> #include <linux/memremap.h> #include <linux/slab.h> +#include <linux/cacheinfo.h> +#include <linux/rcuwait.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> struct mempolicy; struct anon_vma; @@ -39,22 +44,10 @@ struct user_struct; struct pt_regs; struct folio_batch; -extern int sysctl_page_lock_unfairness; - +void arch_mm_preinit(void); void mm_core_init(void); void init_mm_internals(void); -#ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ -extern unsigned long max_mapnr; - -static inline void set_max_mapnr(unsigned long limit) -{ - max_mapnr = limit; -} -#else -static inline void set_max_mapnr(unsigned long limit) { } -#endif - extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { @@ -77,8 +70,15 @@ static inline void totalram_pages_add(long count) } extern void * high_memory; -extern int page_cluster; -extern const int page_cluster_max; + +/* + * Convert between pages and MB + * 20 is the shift for 1MB (2^20 = 1MB) + * PAGE_SHIFT is the shift for page size (e.g., 12 for 4KB pages) + * So (20 - PAGE_SHIFT) converts between pages and MB + */ +#define PAGES_TO_MB(pages) ((pages) >> (20 - PAGE_SHIFT)) +#define MB_TO_PAGES(mb) ((mb) << (20 - PAGE_SHIFT)) #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; @@ -105,6 +105,8 @@ extern int mmap_rnd_compat_bits __read_mostly; # endif #endif +#define INVALID_PHYS_ADDR (~(phys_addr_t)0) + #include <asm/page.h> #include <asm/processor.h> @@ -208,23 +210,14 @@ extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; -extern int sysctl_overcommit_memory; -extern int sysctl_overcommit_ratio; -extern unsigned long sysctl_overcommit_kbytes; - -int overcommit_ratio_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); -int overcommit_kbytes_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); -int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); - #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) -#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) -#define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio)) +bool page_range_contiguous(const struct page *page, unsigned long nr_pages); #else -#define nth_page(page,n) ((page) + (n)) -#define folio_page_idx(folio, p) ((p) - &(folio)->page) +static inline bool page_range_contiguous(const struct page *page, + unsigned long nr_pages) +{ + return true; +} #endif /* to align the pointer to the (next) page boundary */ @@ -236,6 +229,20 @@ int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *, /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) +/** + * folio_page_idx - Return the number of a page in a folio. + * @folio: The folio. + * @page: The folio page. + * + * This function expects that the page is actually part of the folio. + * The returned number is relative to the start of the folio. + */ +static inline unsigned long folio_page_idx(const struct folio *folio, + const struct page *page) +{ + return page - &folio->page; +} + static inline struct folio *lru_to_folio(struct list_head *head) { return list_entry((head)->prev, struct folio, lru); @@ -256,8 +263,6 @@ void setup_initial_init_mm(void *start_code, void *end_code, struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); -/* Use only if VMA has no other users */ -void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; @@ -270,178 +275,235 @@ extern unsigned int kobjsize(const void *objp); * vm_flags in vm_area_struct, see mm_types.h. * When changing, update also include/trace/events/mmflags.h */ -#define VM_NONE 0x00000000 -#define VM_READ 0x00000001 /* currently active flags */ -#define VM_WRITE 0x00000002 -#define VM_EXEC 0x00000004 -#define VM_SHARED 0x00000008 +#define VM_NONE 0x00000000 -/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ -#define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */ -#define VM_MAYWRITE 0x00000020 -#define VM_MAYEXEC 0x00000040 -#define VM_MAYSHARE 0x00000080 +/** + * typedef vma_flag_t - specifies an individual VMA flag by bit number. + * + * This value is made type safe by sparse to avoid passing invalid flag values + * around. + */ +typedef int __bitwise vma_flag_t; -#define VM_GROWSDOWN 0x00000100 /* general info on the segment */ +#define DECLARE_VMA_BIT(name, bitnum) \ + VMA_ ## name ## _BIT = ((__force vma_flag_t)bitnum) +#define DECLARE_VMA_BIT_ALIAS(name, aliased) \ + VMA_ ## name ## _BIT = (VMA_ ## aliased ## _BIT) +enum { + DECLARE_VMA_BIT(READ, 0), + DECLARE_VMA_BIT(WRITE, 1), + DECLARE_VMA_BIT(EXEC, 2), + DECLARE_VMA_BIT(SHARED, 3), + /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ + DECLARE_VMA_BIT(MAYREAD, 4), /* limits for mprotect() etc. */ + DECLARE_VMA_BIT(MAYWRITE, 5), + DECLARE_VMA_BIT(MAYEXEC, 6), + DECLARE_VMA_BIT(MAYSHARE, 7), + DECLARE_VMA_BIT(GROWSDOWN, 8), /* general info on the segment */ #ifdef CONFIG_MMU -#define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ -#else /* CONFIG_MMU */ -#define VM_MAYOVERLAY 0x00000200 /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ -#define VM_UFFD_MISSING 0 + DECLARE_VMA_BIT(UFFD_MISSING, 9),/* missing pages tracking */ +#else + /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ + DECLARE_VMA_BIT(MAYOVERLAY, 9), #endif /* CONFIG_MMU */ -#define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ -#define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ - -#define VM_LOCKED 0x00002000 -#define VM_IO 0x00004000 /* Memory mapped I/O or similar */ - - /* Used by sys_madvise() */ -#define VM_SEQ_READ 0x00008000 /* App will access data sequentially */ -#define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */ - -#define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ -#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ -#define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */ -#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ -#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ -#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ -#define VM_SYNC 0x00800000 /* Synchronous page faults */ -#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ -#define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ -#define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ - + /* Page-ranges managed without "struct page", just pure PFN */ + DECLARE_VMA_BIT(PFNMAP, 10), + DECLARE_VMA_BIT(MAYBE_GUARD, 11), + DECLARE_VMA_BIT(UFFD_WP, 12), /* wrprotect pages tracking */ + DECLARE_VMA_BIT(LOCKED, 13), + DECLARE_VMA_BIT(IO, 14), /* Memory mapped I/O or similar */ + DECLARE_VMA_BIT(SEQ_READ, 15), /* App will access data sequentially */ + DECLARE_VMA_BIT(RAND_READ, 16), /* App will not benefit from clustered reads */ + DECLARE_VMA_BIT(DONTCOPY, 17), /* Do not copy this vma on fork */ + DECLARE_VMA_BIT(DONTEXPAND, 18),/* Cannot expand with mremap() */ + DECLARE_VMA_BIT(LOCKONFAULT, 19),/* Lock pages covered when faulted in */ + DECLARE_VMA_BIT(ACCOUNT, 20), /* Is a VM accounted object */ + DECLARE_VMA_BIT(NORESERVE, 21), /* should the VM suppress accounting */ + DECLARE_VMA_BIT(HUGETLB, 22), /* Huge TLB Page VM */ + DECLARE_VMA_BIT(SYNC, 23), /* Synchronous page faults */ + DECLARE_VMA_BIT(ARCH_1, 24), /* Architecture-specific flag */ + DECLARE_VMA_BIT(WIPEONFORK, 25),/* Wipe VMA contents in child. */ + DECLARE_VMA_BIT(DONTDUMP, 26), /* Do not include in the core dump */ + DECLARE_VMA_BIT(SOFTDIRTY, 27), /* NOT soft dirty clean area */ + DECLARE_VMA_BIT(MIXEDMAP, 28), /* Can contain struct page and pure PFN pages */ + DECLARE_VMA_BIT(HUGEPAGE, 29), /* MADV_HUGEPAGE marked this vma */ + DECLARE_VMA_BIT(NOHUGEPAGE, 30),/* MADV_NOHUGEPAGE marked this vma */ + DECLARE_VMA_BIT(MERGEABLE, 31), /* KSM may merge identical pages */ + /* These bits are reused, we define specific uses below. */ + DECLARE_VMA_BIT(HIGH_ARCH_0, 32), + DECLARE_VMA_BIT(HIGH_ARCH_1, 33), + DECLARE_VMA_BIT(HIGH_ARCH_2, 34), + DECLARE_VMA_BIT(HIGH_ARCH_3, 35), + DECLARE_VMA_BIT(HIGH_ARCH_4, 36), + DECLARE_VMA_BIT(HIGH_ARCH_5, 37), + DECLARE_VMA_BIT(HIGH_ARCH_6, 38), + /* + * This flag is used to connect VFIO to arch specific KVM code. It + * indicates that the memory under this VMA is safe for use with any + * non-cachable memory type inside KVM. Some VFIO devices, on some + * platforms, are thought to be unsafe and can cause machine crashes + * if KVM does not lock down the memory type. + */ + DECLARE_VMA_BIT(ALLOW_ANY_UNCACHED, 39), +#ifdef CONFIG_PPC32 + DECLARE_VMA_BIT_ALIAS(DROPPABLE, ARCH_1), +#else + DECLARE_VMA_BIT(DROPPABLE, 40), +#endif + DECLARE_VMA_BIT(UFFD_MINOR, 41), + DECLARE_VMA_BIT(SEALED, 42), + /* Flags that reuse flags above. */ + DECLARE_VMA_BIT_ALIAS(PKEY_BIT0, HIGH_ARCH_0), + DECLARE_VMA_BIT_ALIAS(PKEY_BIT1, HIGH_ARCH_1), + DECLARE_VMA_BIT_ALIAS(PKEY_BIT2, HIGH_ARCH_2), + DECLARE_VMA_BIT_ALIAS(PKEY_BIT3, HIGH_ARCH_3), + DECLARE_VMA_BIT_ALIAS(PKEY_BIT4, HIGH_ARCH_4), +#if defined(CONFIG_X86_USER_SHADOW_STACK) + /* + * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of + * support core mm. + * + * These VMAs will get a single end guard page. This helps userspace + * protect itself from attacks. A single page is enough for current + * shadow stack archs (x86). See the comments near alloc_shstk() in + * arch/x86/kernel/shstk.c for more details on the guard size. + */ + DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_5), +#elif defined(CONFIG_ARM64_GCS) + /* + * arm64's Guarded Control Stack implements similar functionality and + * has similar constraints to shadow stacks. + */ + DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_6), +#endif + DECLARE_VMA_BIT_ALIAS(SAO, ARCH_1), /* Strong Access Ordering (powerpc) */ + DECLARE_VMA_BIT_ALIAS(GROWSUP, ARCH_1), /* parisc */ + DECLARE_VMA_BIT_ALIAS(SPARC_ADI, ARCH_1), /* sparc64 */ + DECLARE_VMA_BIT_ALIAS(ARM64_BTI, ARCH_1), /* arm64 */ + DECLARE_VMA_BIT_ALIAS(ARCH_CLEAR, ARCH_1), /* sparc64, arm64 */ + DECLARE_VMA_BIT_ALIAS(MAPPED_COPY, ARCH_1), /* !CONFIG_MMU */ + DECLARE_VMA_BIT_ALIAS(MTE, HIGH_ARCH_4), /* arm64 */ + DECLARE_VMA_BIT_ALIAS(MTE_ALLOWED, HIGH_ARCH_5),/* arm64 */ +#ifdef CONFIG_STACK_GROWSUP + DECLARE_VMA_BIT_ALIAS(STACK, GROWSUP), + DECLARE_VMA_BIT_ALIAS(STACK_EARLY, GROWSDOWN), +#else + DECLARE_VMA_BIT_ALIAS(STACK, GROWSDOWN), +#endif +}; +#undef DECLARE_VMA_BIT +#undef DECLARE_VMA_BIT_ALIAS + +#define INIT_VM_FLAG(name) BIT((__force int) VMA_ ## name ## _BIT) +#define VM_READ INIT_VM_FLAG(READ) +#define VM_WRITE INIT_VM_FLAG(WRITE) +#define VM_EXEC INIT_VM_FLAG(EXEC) +#define VM_SHARED INIT_VM_FLAG(SHARED) +#define VM_MAYREAD INIT_VM_FLAG(MAYREAD) +#define VM_MAYWRITE INIT_VM_FLAG(MAYWRITE) +#define VM_MAYEXEC INIT_VM_FLAG(MAYEXEC) +#define VM_MAYSHARE INIT_VM_FLAG(MAYSHARE) +#define VM_GROWSDOWN INIT_VM_FLAG(GROWSDOWN) +#ifdef CONFIG_MMU +#define VM_UFFD_MISSING INIT_VM_FLAG(UFFD_MISSING) +#else +#define VM_UFFD_MISSING VM_NONE +#define VM_MAYOVERLAY INIT_VM_FLAG(MAYOVERLAY) +#endif +#define VM_PFNMAP INIT_VM_FLAG(PFNMAP) +#define VM_MAYBE_GUARD INIT_VM_FLAG(MAYBE_GUARD) +#define VM_UFFD_WP INIT_VM_FLAG(UFFD_WP) +#define VM_LOCKED INIT_VM_FLAG(LOCKED) +#define VM_IO INIT_VM_FLAG(IO) +#define VM_SEQ_READ INIT_VM_FLAG(SEQ_READ) +#define VM_RAND_READ INIT_VM_FLAG(RAND_READ) +#define VM_DONTCOPY INIT_VM_FLAG(DONTCOPY) +#define VM_DONTEXPAND INIT_VM_FLAG(DONTEXPAND) +#define VM_LOCKONFAULT INIT_VM_FLAG(LOCKONFAULT) +#define VM_ACCOUNT INIT_VM_FLAG(ACCOUNT) +#define VM_NORESERVE INIT_VM_FLAG(NORESERVE) +#define VM_HUGETLB INIT_VM_FLAG(HUGETLB) +#define VM_SYNC INIT_VM_FLAG(SYNC) +#define VM_ARCH_1 INIT_VM_FLAG(ARCH_1) +#define VM_WIPEONFORK INIT_VM_FLAG(WIPEONFORK) +#define VM_DONTDUMP INIT_VM_FLAG(DONTDUMP) #ifdef CONFIG_MEM_SOFT_DIRTY -# define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */ +#define VM_SOFTDIRTY INIT_VM_FLAG(SOFTDIRTY) #else -# define VM_SOFTDIRTY 0 +#define VM_SOFTDIRTY VM_NONE +#endif +#define VM_MIXEDMAP INIT_VM_FLAG(MIXEDMAP) +#define VM_HUGEPAGE INIT_VM_FLAG(HUGEPAGE) +#define VM_NOHUGEPAGE INIT_VM_FLAG(NOHUGEPAGE) +#define VM_MERGEABLE INIT_VM_FLAG(MERGEABLE) +#define VM_STACK INIT_VM_FLAG(STACK) +#ifdef CONFIG_STACK_GROWS_UP +#define VM_STACK_EARLY INIT_VM_FLAG(STACK_EARLY) +#else +#define VM_STACK_EARLY VM_NONE #endif - -#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ -#define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ -#define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ -#define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ - -#ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS -#define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ -#define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ -#define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ -#define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ -#define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ -#define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */ -#define VM_HIGH_ARCH_BIT_6 38 /* bit only usable on 64-bit architectures */ -#define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) -#define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) -#define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) -#define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) -#define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) -#define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5) -#define VM_HIGH_ARCH_6 BIT(VM_HIGH_ARCH_BIT_6) -#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ - #ifdef CONFIG_ARCH_HAS_PKEYS -# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 -# define VM_PKEY_BIT0 VM_HIGH_ARCH_0 -# define VM_PKEY_BIT1 VM_HIGH_ARCH_1 -# define VM_PKEY_BIT2 VM_HIGH_ARCH_2 +#define VM_PKEY_SHIFT ((__force int)VMA_HIGH_ARCH_0_BIT) +/* Despite the naming, these are FLAGS not bits. */ +#define VM_PKEY_BIT0 INIT_VM_FLAG(PKEY_BIT0) +#define VM_PKEY_BIT1 INIT_VM_FLAG(PKEY_BIT1) +#define VM_PKEY_BIT2 INIT_VM_FLAG(PKEY_BIT2) #if CONFIG_ARCH_PKEY_BITS > 3 -# define VM_PKEY_BIT3 VM_HIGH_ARCH_3 +#define VM_PKEY_BIT3 INIT_VM_FLAG(PKEY_BIT3) #else -# define VM_PKEY_BIT3 0 -#endif +#define VM_PKEY_BIT3 VM_NONE +#endif /* CONFIG_ARCH_PKEY_BITS > 3 */ #if CONFIG_ARCH_PKEY_BITS > 4 -# define VM_PKEY_BIT4 VM_HIGH_ARCH_4 +#define VM_PKEY_BIT4 INIT_VM_FLAG(PKEY_BIT4) #else -# define VM_PKEY_BIT4 0 -#endif +#define VM_PKEY_BIT4 VM_NONE +#endif /* CONFIG_ARCH_PKEY_BITS > 4 */ #endif /* CONFIG_ARCH_HAS_PKEYS */ - -#ifdef CONFIG_X86_USER_SHADOW_STACK -/* - * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of - * support core mm. - * - * These VMAs will get a single end guard page. This helps userspace protect - * itself from attacks. A single page is enough for current shadow stack archs - * (x86). See the comments near alloc_shstk() in arch/x86/kernel/shstk.c - * for more details on the guard size. - */ -# define VM_SHADOW_STACK VM_HIGH_ARCH_5 -#endif - -#if defined(CONFIG_ARM64_GCS) -/* - * arm64's Guarded Control Stack implements similar functionality and - * has similar constraints to shadow stacks. - */ -# define VM_SHADOW_STACK VM_HIGH_ARCH_6 -#endif - -#ifndef VM_SHADOW_STACK -# define VM_SHADOW_STACK VM_NONE +#if defined(CONFIG_X86_USER_SHADOW_STACK) || defined(CONFIG_ARM64_GCS) +#define VM_SHADOW_STACK INIT_VM_FLAG(SHADOW_STACK) +#else +#define VM_SHADOW_STACK VM_NONE #endif - -#if defined(CONFIG_X86) -# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ -#elif defined(CONFIG_PPC64) -# define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ +#if defined(CONFIG_PPC64) +#define VM_SAO INIT_VM_FLAG(SAO) #elif defined(CONFIG_PARISC) -# define VM_GROWSUP VM_ARCH_1 +#define VM_GROWSUP INIT_VM_FLAG(GROWSUP) #elif defined(CONFIG_SPARC64) -# define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ -# define VM_ARCH_CLEAR VM_SPARC_ADI +#define VM_SPARC_ADI INIT_VM_FLAG(SPARC_ADI) +#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR) #elif defined(CONFIG_ARM64) -# define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ -# define VM_ARCH_CLEAR VM_ARM64_BTI +#define VM_ARM64_BTI INIT_VM_FLAG(ARM64_BTI) +#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR) #elif !defined(CONFIG_MMU) -# define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ +#define VM_MAPPED_COPY INIT_VM_FLAG(MAPPED_COPY) #endif - -#if defined(CONFIG_ARM64_MTE) -# define VM_MTE VM_HIGH_ARCH_4 /* Use Tagged memory for access control */ -# define VM_MTE_ALLOWED VM_HIGH_ARCH_5 /* Tagged memory permitted */ -#else -# define VM_MTE VM_NONE -# define VM_MTE_ALLOWED VM_NONE -#endif - #ifndef VM_GROWSUP -# define VM_GROWSUP VM_NONE +#define VM_GROWSUP VM_NONE +#endif +#ifdef CONFIG_ARM64_MTE +#define VM_MTE INIT_VM_FLAG(MTE) +#define VM_MTE_ALLOWED INIT_VM_FLAG(MTE_ALLOWED) +#else +#define VM_MTE VM_NONE +#define VM_MTE_ALLOWED VM_NONE #endif - #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR -# define VM_UFFD_MINOR_BIT 38 -# define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ -#else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ -# define VM_UFFD_MINOR VM_NONE -#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ - -/* - * This flag is used to connect VFIO to arch specific KVM code. It - * indicates that the memory under this VMA is safe for use with any - * non-cachable memory type inside KVM. Some VFIO devices, on some - * platforms, are thought to be unsafe and can cause machine crashes - * if KVM does not lock down the memory type. - */ -#ifdef CONFIG_64BIT -#define VM_ALLOW_ANY_UNCACHED_BIT 39 -#define VM_ALLOW_ANY_UNCACHED BIT(VM_ALLOW_ANY_UNCACHED_BIT) +#define VM_UFFD_MINOR INIT_VM_FLAG(UFFD_MINOR) #else -#define VM_ALLOW_ANY_UNCACHED VM_NONE +#define VM_UFFD_MINOR VM_NONE #endif - #ifdef CONFIG_64BIT -#define VM_DROPPABLE_BIT 40 -#define VM_DROPPABLE BIT(VM_DROPPABLE_BIT) -#elif defined(CONFIG_PPC32) -#define VM_DROPPABLE VM_ARCH_1 +#define VM_ALLOW_ANY_UNCACHED INIT_VM_FLAG(ALLOW_ANY_UNCACHED) +#define VM_SEALED INIT_VM_FLAG(SEALED) #else -#define VM_DROPPABLE VM_NONE +#define VM_ALLOW_ANY_UNCACHED VM_NONE +#define VM_SEALED VM_NONE #endif - -#ifdef CONFIG_64BIT -/* VM is sealed, in vm_flags */ -#define VM_SEALED _BITUL(63) +#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32) +#define VM_DROPPABLE INIT_VM_FLAG(DROPPABLE) +#else +#define VM_DROPPABLE VM_NONE #endif /* Bits set in the VMA until the stack is in its final location */ @@ -467,12 +529,10 @@ extern unsigned int kobjsize(const void *objp); #define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) -#ifdef CONFIG_STACK_GROWSUP -#define VM_STACK VM_GROWSUP -#define VM_STACK_EARLY VM_GROWSDOWN +#ifdef CONFIG_MSEAL_SYSTEM_MAPPINGS +#define VM_SEALED_SYSMAP VM_SEALED #else -#define VM_STACK VM_GROWSDOWN -#define VM_STACK_EARLY 0 +#define VM_SEALED_SYSMAP VM_NONE #endif #define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) @@ -480,12 +540,26 @@ extern unsigned int kobjsize(const void *objp); /* VMA basic access permission flags */ #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) - /* * Special vmas that are non-mergable, non-mlock()able. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) +/* + * Physically remapped pages are special. Tell the + * rest of the world about it: + * VM_IO tells people not to look at these pages + * (accesses can have side effects). + * VM_PFNMAP tells the core MM that the base pages are just + * raw PFN mappings, and do not have a "struct page" associated + * with them. + * VM_DONTEXPAND + * Disable vma merging and expanding with mremap(). + * VM_DONTDUMP + * Omit vma from core dump, even when VM_IO turned off. + */ +#define VM_REMAP_FLAGS (VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP) + /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) @@ -495,13 +569,69 @@ extern unsigned int kobjsize(const void *objp); /* This mask represents all the VMA flag bits used by mlock */ #define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) +/* These flags can be updated atomically via VMA/mmap read lock. */ +#define VM_ATOMIC_SET_ALLOWED VM_MAYBE_GUARD + /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR -# define VM_ARCH_CLEAR VM_NONE +#define VM_ARCH_CLEAR VM_NONE #endif #define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR) /* + * Flags which should be 'sticky' on merge - that is, flags which, when one VMA + * possesses it but the other does not, the merged VMA should nonetheless have + * applied to it: + * + * VM_SOFTDIRTY - if a VMA is marked soft-dirty, that is has not had its + * references cleared via /proc/$pid/clear_refs, any merged VMA + * should be considered soft-dirty also as it operates at a VMA + * granularity. + * + * VM_MAYBE_GUARD - If a VMA may have guard regions in place it implies that + * mapped page tables may contain metadata not described by the + * VMA and thus any merged VMA may also contain this metadata, + * and thus we must make this flag sticky. + */ +#define VM_STICKY (VM_SOFTDIRTY | VM_MAYBE_GUARD) + +/* + * VMA flags we ignore for the purposes of merge, i.e. one VMA possessing one + * of these flags and the other not does not preclude a merge. + * + * VM_STICKY - When merging VMAs, VMA flags must match, unless they are + * 'sticky'. If any sticky flags exist in either VMA, we simply + * set all of them on the merged VMA. + */ +#define VM_IGNORE_MERGE VM_STICKY + +/* + * Flags which should result in page tables being copied on fork. These are + * flags which indicate that the VMA maps page tables which cannot be + * reconsistuted upon page fault, so necessitate page table copying upon + * + * VM_PFNMAP / VM_MIXEDMAP - These contain kernel-mapped data which cannot be + * reasonably reconstructed on page fault. + * + * VM_UFFD_WP - Encodes metadata about an installed uffd + * write protect handler, which cannot be + * reconstructed on page fault. + * + * We always copy pgtables when dst_vma has uffd-wp + * enabled even if it's file-backed + * (e.g. shmem). Because when uffd-wp is enabled, + * pgtable contains uffd-wp protection information, + * that's something we can't retrieve from page cache, + * and skip copying will lose those info. + * + * VM_MAYBE_GUARD - Could contain page guard region markers which + * by design are a property of the page tables + * only and thus cannot be reconstructed on page + * fault. + */ +#define VM_COPY_ON_FORK (VM_PFNMAP | VM_MIXEDMAP | VM_UFFD_WP | VM_MAYBE_GUARD) + +/* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ @@ -672,13 +802,21 @@ struct vm_operations_struct { struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); #endif +#ifdef CONFIG_FIND_NORMAL_PAGE /* - * Called by vm_normal_page() for special PTEs to find the - * page for @addr. This is useful if the default behavior - * (using pte_page()) would not find the correct page. + * Called by vm_normal_page() for special PTEs in @vma at @addr. This + * allows for returning a "normal" page from vm_normal_page() even + * though the PTE indicates that the "struct page" either does not exist + * or should not be touched: "special". + * + * Do not add new users: this really only works when a "normal" page + * was mapped, but then the PTE got changed to something weird (+ + * marked special) that would not make pte_pfn() identify the originally + * inserted page. */ - struct page *(*find_special_page)(struct vm_area_struct *vma, - unsigned long addr); + struct page *(*find_normal_page)(struct vm_area_struct *vma, + unsigned long addr); +#endif /* CONFIG_FIND_NORMAL_PAGE */ }; #ifdef CONFIG_NUMA_BALANCING @@ -695,109 +833,11 @@ static inline void vma_numab_state_init(struct vm_area_struct *vma) {} static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_PER_VMA_LOCK -/* - * Try to read-lock a vma. The function is allowed to occasionally yield false - * locked result to avoid performance overhead, in which case we fall back to - * using mmap_lock. The function should never yield false unlocked result. - */ -static inline bool vma_start_read(struct vm_area_struct *vma) -{ - /* - * Check before locking. A race might cause false locked result. - * We can use READ_ONCE() for the mm_lock_seq here, and don't need - * ACQUIRE semantics, because this is just a lockless check whose result - * we don't rely on for anything - the mm_lock_seq read against which we - * need ordering is below. - */ - if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq)) - return false; - - if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) - return false; - - /* - * Overflow might produce false locked result. - * False unlocked result is impossible because we modify and check - * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq - * modification invalidates all existing locks. - * - * We must use ACQUIRE semantics for the mm_lock_seq so that if we are - * racing with vma_end_write_all(), we only start reading from the VMA - * after it has been unlocked. - * This pairs with RELEASE semantics in vma_end_write_all(). - */ - if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) { - up_read(&vma->vm_lock->lock); - return false; - } - return true; -} - -static inline void vma_end_read(struct vm_area_struct *vma) -{ - rcu_read_lock(); /* keeps vma alive till the end of up_read */ - up_read(&vma->vm_lock->lock); - rcu_read_unlock(); -} - -/* WARNING! Can only be used if mmap_lock is expected to be write-locked */ -static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) -{ - mmap_assert_write_locked(vma->vm_mm); - - /* - * current task is holding mmap_write_lock, both vma->vm_lock_seq and - * mm->mm_lock_seq can't be concurrently modified. - */ - *mm_lock_seq = vma->vm_mm->mm_lock_seq; - return (vma->vm_lock_seq == *mm_lock_seq); -} - /* - * Begin writing to a VMA. - * Exclude concurrent readers under the per-VMA lock until the currently - * write-locked mmap_lock is dropped or downgraded. + * These must be here rather than mmap_lock.h as dependent on vm_fault type, + * declared in this header. */ -static inline void vma_start_write(struct vm_area_struct *vma) -{ - int mm_lock_seq; - - if (__is_vma_write_locked(vma, &mm_lock_seq)) - return; - - down_write(&vma->vm_lock->lock); - /* - * We should use WRITE_ONCE() here because we can have concurrent reads - * from the early lockless pessimistic check in vma_start_read(). - * We don't really care about the correctness of that early check, but - * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy. - */ - WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); - up_write(&vma->vm_lock->lock); -} - -static inline void vma_assert_write_locked(struct vm_area_struct *vma) -{ - int mm_lock_seq; - - VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); -} - -static inline void vma_assert_locked(struct vm_area_struct *vma) -{ - if (!rwsem_is_locked(&vma->vm_lock->lock)) - vma_assert_write_locked(vma); -} - -static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) -{ - /* When detaching vma should be write-locked */ - if (detached) - vma_assert_write_locked(vma); - vma->detached = detached; -} - +#ifdef CONFIG_PER_VMA_LOCK static inline void release_fault_lock(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) @@ -806,72 +846,73 @@ static inline void release_fault_lock(struct vm_fault *vmf) mmap_read_unlock(vmf->vma->vm_mm); } -static inline void assert_fault_locked(struct vm_fault *vmf) +static inline void assert_fault_locked(const struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_assert_locked(vmf->vma); else mmap_assert_locked(vmf->vma->vm_mm); } +#else +static inline void release_fault_lock(struct vm_fault *vmf) +{ + mmap_read_unlock(vmf->vma->vm_mm); +} -struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, - unsigned long address); - -#else /* CONFIG_PER_VMA_LOCK */ +static inline void assert_fault_locked(const struct vm_fault *vmf) +{ + mmap_assert_locked(vmf->vma->vm_mm); +} +#endif /* CONFIG_PER_VMA_LOCK */ -static inline bool vma_start_read(struct vm_area_struct *vma) - { return false; } -static inline void vma_end_read(struct vm_area_struct *vma) {} -static inline void vma_start_write(struct vm_area_struct *vma) {} -static inline void vma_assert_write_locked(struct vm_area_struct *vma) - { mmap_assert_write_locked(vma->vm_mm); } -static inline void vma_mark_detached(struct vm_area_struct *vma, - bool detached) {} +static inline bool mm_flags_test(int flag, const struct mm_struct *mm) +{ + return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); +} -static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, - unsigned long address) +static inline bool mm_flags_test_and_set(int flag, struct mm_struct *mm) { - return NULL; + return test_and_set_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); } -static inline void vma_assert_locked(struct vm_area_struct *vma) +static inline bool mm_flags_test_and_clear(int flag, struct mm_struct *mm) { - mmap_assert_locked(vma->vm_mm); + return test_and_clear_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); } -static inline void release_fault_lock(struct vm_fault *vmf) +static inline void mm_flags_set(int flag, struct mm_struct *mm) { - mmap_read_unlock(vmf->vma->vm_mm); + set_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); } -static inline void assert_fault_locked(struct vm_fault *vmf) +static inline void mm_flags_clear(int flag, struct mm_struct *mm) { - mmap_assert_locked(vmf->vma->vm_mm); + clear_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); } -#endif /* CONFIG_PER_VMA_LOCK */ +static inline void mm_flags_clear_all(struct mm_struct *mm) +{ + bitmap_zero(ACCESS_PRIVATE(&mm->flags, __mm_flags), NUM_MM_FLAG_BITS); +} extern const struct vm_operations_struct vma_dummy_vm_ops; -/* - * WARNING: vma_init does not initialize vma->vm_lock. - * Use vm_area_alloc()/vm_area_free() if vma needs locking. - */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); - vma_mark_detached(vma, false); - vma_numab_state_init(vma); + vma_lock_init(vma, false); } /* Use when VMA is not part of the VMA tree and needs no locking */ static inline void vm_flags_init(struct vm_area_struct *vma, vm_flags_t flags) { - ACCESS_PRIVATE(vma, __vm_flags) = flags; + VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY)); + vma_flags_clear_all(&vma->flags); + vma_flags_overwrite_word(&vma->flags, flags); } /* @@ -882,6 +923,7 @@ static inline void vm_flags_init(struct vm_area_struct *vma, static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { + VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY)); vma_assert_write_locked(vma); vm_flags_init(vma, flags); } @@ -890,21 +932,33 @@ static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { vma_assert_write_locked(vma); - WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); + /* + * If VMA flags exist beyond the first system word, also clear these. It + * is assumed the write once behaviour is required only for the first + * system word. + */ + if (NUM_VMA_FLAG_BITS > BITS_PER_LONG) { + unsigned long *bitmap = ACCESS_PRIVATE(&vma->flags, __vma_flags); + + bitmap_zero(&bitmap[1], NUM_VMA_FLAG_BITS - BITS_PER_LONG); + } + + vma_flags_overwrite_word_once(&vma->flags, flags); } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { vma_start_write(vma); - ACCESS_PRIVATE(vma, __vm_flags) |= flags; + vma_flags_set_word(&vma->flags, flags); } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { + VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY)); vma_start_write(vma); - ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; + vma_flags_clear_word(&vma->flags, flags); } /* @@ -928,6 +982,51 @@ static inline void vm_flags_mod(struct vm_area_struct *vma, __vm_flags_mod(vma, set, clear); } +static inline bool __vma_flag_atomic_valid(struct vm_area_struct *vma, + vma_flag_t bit) +{ + const vm_flags_t mask = BIT((__force int)bit); + + /* Only specific flags are permitted */ + if (WARN_ON_ONCE(!(mask & VM_ATOMIC_SET_ALLOWED))) + return false; + + return true; +} + +/* + * Set VMA flag atomically. Requires only VMA/mmap read lock. Only specific + * valid flags are allowed to do this. + */ +static inline void vma_flag_set_atomic(struct vm_area_struct *vma, + vma_flag_t bit) +{ + unsigned long *bitmap = ACCESS_PRIVATE(&vma->flags, __vma_flags); + + /* mmap read lock/VMA read lock must be held. */ + if (!rwsem_is_locked(&vma->vm_mm->mmap_lock)) + vma_assert_locked(vma); + + if (__vma_flag_atomic_valid(vma, bit)) + set_bit((__force int)bit, bitmap); +} + +/* + * Test for VMA flag atomically. Requires no locks. Only specific valid flags + * are allowed to do this. + * + * This is necessarily racey, so callers must ensure that serialisation is + * achieved through some other means, or that races are permissible. + */ +static inline bool vma_flag_test_atomic(struct vm_area_struct *vma, + vma_flag_t bit) +{ + if (__vma_flag_atomic_valid(vma, bit)) + return test_bit((__force int)bit, &vma->vm_flags); + + return false; +} + static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; @@ -963,7 +1062,7 @@ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) vma->vm_end >= vma->vm_mm->start_stack; } -static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) +static inline bool vma_is_temporary_stack(const struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -977,7 +1076,7 @@ static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) return false; } -static inline bool vma_is_foreign(struct vm_area_struct *vma) +static inline bool vma_is_foreign(const struct vm_area_struct *vma) { if (!current->mm) return true; @@ -988,7 +1087,7 @@ static inline bool vma_is_foreign(struct vm_area_struct *vma) return false; } -static inline bool vma_is_accessible(struct vm_area_struct *vma) +static inline bool vma_is_accessible(const struct vm_area_struct *vma) { return vma->vm_flags & VM_ACCESS_FLAGS; } @@ -999,7 +1098,7 @@ static inline bool is_shared_maywrite(vm_flags_t vm_flags) (VM_SHARED | VM_MAYWRITE); } -static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) +static inline bool vma_is_shared_maywrite(const struct vm_area_struct *vma) { return is_shared_maywrite(vma->vm_flags); } @@ -1057,6 +1156,7 @@ static inline int vma_iter_bulk_store(struct vma_iterator *vmi, if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; + vma_mark_attached(vma); return 0; } @@ -1082,14 +1182,14 @@ static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ -bool vma_is_shmem(struct vm_area_struct *vma); -bool vma_is_anon_shmem(struct vm_area_struct *vma); +bool vma_is_shmem(const struct vm_area_struct *vma); +bool vma_is_anon_shmem(const struct vm_area_struct *vma); #else -static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } -static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; } +static inline bool vma_is_shmem(const struct vm_area_struct *vma) { return false; } +static inline bool vma_is_anon_shmem(const struct vm_area_struct *vma) { return false; } #endif -int vma_is_stack_for_current(struct vm_area_struct *vma); +int vma_is_stack_for_current(const struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } @@ -1097,6 +1197,25 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; +extern void prep_compound_page(struct page *page, unsigned int order); + +static inline unsigned int folio_large_order(const struct folio *folio) +{ + return folio->_flags_1 & 0xff; +} + +#ifdef NR_PAGES_IN_LARGE_FOLIO +static inline unsigned long folio_large_nr_pages(const struct folio *folio) +{ + return folio->_nr_pages; +} +#else +static inline unsigned long folio_large_nr_pages(const struct folio *folio) +{ + return 1L << folio_large_order(folio); +} +#endif + /* * compound_order() can be called without holding a reference, which means * that niceties like page_folio() don't work. These callers should be @@ -1104,13 +1223,13 @@ struct inode; * set before the order is initialised, or this may be a tail page. * See compaction.c for some good examples. */ -static inline unsigned int compound_order(struct page *page) +static inline unsigned int compound_order(const struct page *page) { - struct folio *folio = (struct folio *)page; + const struct folio *folio = (struct folio *)page; - if (!test_bit(PG_head, &folio->flags)) + if (!test_bit(PG_head, &folio->flags.f)) return 0; - return folio->_flags_1 & 0xff; + return folio_large_order(folio); } /** @@ -1126,7 +1245,24 @@ static inline unsigned int folio_order(const struct folio *folio) { if (!folio_test_large(folio)) return 0; - return folio->_flags_1 & 0xff; + return folio_large_order(folio); +} + +/** + * folio_reset_order - Reset the folio order and derived _nr_pages + * @folio: The folio. + * + * Reset the order and derived _nr_pages to 0. Must only be used in the + * process of splitting large folios. + */ +static inline void folio_reset_order(struct folio *folio) +{ + if (WARN_ON_ONCE(!folio_test_large(folio))) + return; + folio->_flags_1 &= ~0xffUL; +#ifdef NR_PAGES_IN_LARGE_FOLIO + folio->_nr_pages = 0; +#endif } #include <linux/huge_mm.h> @@ -1219,6 +1355,8 @@ static inline int is_vmalloc_or_module_addr(const void *x) static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio_large_order(folio) == 1)) + return 0; return atomic_read(&folio->_entire_mapcount) + 1; } @@ -1305,7 +1443,7 @@ int folio_mc_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); /* Returns the number of bytes in this potentially compound page. */ -static inline unsigned long page_size(struct page *page) +static inline unsigned long page_size(const struct page *page) { return PAGE_SIZE << compound_order(page); } @@ -1351,7 +1489,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *page); void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr); @@ -1392,9 +1530,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf); * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * - * A page may belong to an inode's memory mapping. In this case, page->mapping - * is the pointer to the inode, and page->index is the file offset of the page, - * in units of PAGE_SIZE. + * A folio may belong to an inode's memory mapping. In this case, + * folio->mapping points to the inode, and folio->index is the file + * offset of the folio, in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that @@ -1418,25 +1556,6 @@ vm_fault_t finish_fault(struct vm_fault *vmf); * back into memory. */ -#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) -DECLARE_STATIC_KEY_FALSE(devmap_managed_key); - -bool __put_devmap_managed_folio_refs(struct folio *folio, int refs); -static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) -{ - if (!static_branch_unlikely(&devmap_managed_key)) - return false; - if (!folio_is_zone_device(folio)) - return false; - return __put_devmap_managed_folio_refs(folio, refs); -} -#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) -{ - return false; -} -#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ - /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) @@ -1457,7 +1576,12 @@ static inline void folio_get(struct folio *folio) static inline void get_page(struct page *page) { - folio_get(page_folio(page)); + struct folio *folio = page_folio(page); + if (WARN_ON_ONCE(folio_test_slab(folio))) + return; + if (WARN_ON_ONCE(folio_test_large_kmalloc(folio))) + return; + folio_get(folio); } static inline __must_check bool try_get_page(struct page *page) @@ -1551,12 +1675,9 @@ static inline void put_page(struct page *page) { struct folio *folio = page_folio(page); - /* - * For some devmap managed pages we need to catch refcount transition - * from 2 to 1: - */ - if (put_devmap_managed_folio_refs(folio, 1)) + if (folio_test_slab(folio) || folio_test_large_kmalloc(folio)) return; + folio_put(folio); } @@ -1636,21 +1757,26 @@ static inline bool is_nommu_shared_mapping(vm_flags_t flags) */ static inline int page_zone_id(struct page *page) { - return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; + return (page->flags.f >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS -int page_to_nid(const struct page *page); +int memdesc_nid(memdesc_flags_t mdf); #else -static inline int page_to_nid(const struct page *page) +static inline int memdesc_nid(memdesc_flags_t mdf) { - return (PF_POISONED_CHECK(page)->flags >> NODES_PGSHIFT) & NODES_MASK; + return (mdf.f >> NODES_PGSHIFT) & NODES_MASK; } #endif +static inline int page_to_nid(const struct page *page) +{ + return memdesc_nid(PF_POISONED_CHECK(page)->flags); +} + static inline int folio_nid(const struct folio *folio) { - return page_to_nid(&folio->page); + return memdesc_nid(folio->flags); } #ifdef CONFIG_NUMA_BALANCING @@ -1719,14 +1845,14 @@ static inline void page_cpupid_reset_last(struct page *page) #else static inline int folio_last_cpupid(struct folio *folio) { - return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; + return (folio->flags.f >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } int folio_xchg_last_cpupid(struct folio *folio, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { - page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; + page->flags.f |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ @@ -1822,7 +1948,7 @@ static inline u8 page_kasan_tag(const struct page *page) u8 tag = KASAN_TAG_KERNEL; if (kasan_enabled()) { - tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; + tag = (page->flags.f >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; } @@ -1837,12 +1963,12 @@ static inline void page_kasan_tag_set(struct page *page, u8 tag) return; tag ^= 0xff; - old_flags = READ_ONCE(page->flags); + old_flags = READ_ONCE(page->flags.f); do { flags = old_flags; flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; - } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); + } while (unlikely(!try_cmpxchg(&page->flags.f, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) @@ -1873,28 +1999,33 @@ static inline pg_data_t *page_pgdat(const struct page *page) return NODE_DATA(page_to_nid(page)); } -static inline struct zone *folio_zone(const struct folio *folio) +static inline pg_data_t *folio_pgdat(const struct folio *folio) { - return page_zone(&folio->page); + return NODE_DATA(folio_nid(folio)); } -static inline pg_data_t *folio_pgdat(const struct folio *folio) +static inline struct zone *folio_zone(const struct folio *folio) { - return page_pgdat(&folio->page); + return &folio_pgdat(folio)->node_zones[folio_zonenum(folio)]; } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { - page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); - page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; + page->flags.f &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); + page->flags.f |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } -static inline unsigned long page_to_section(const struct page *page) +static inline unsigned long memdesc_section(memdesc_flags_t mdf) { - return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; + return (mdf.f >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } -#endif +#else /* !SECTION_IN_PAGE_FLAGS */ +static inline unsigned long memdesc_section(memdesc_flags_t mdf) +{ + return 0; +} +#endif /* SECTION_IN_PAGE_FLAGS */ /** * folio_pfn - Return the Page Frame Number of a folio. @@ -1915,6 +2046,69 @@ static inline struct folio *pfn_folio(unsigned long pfn) return page_folio(pfn_to_page(pfn)); } +#ifdef CONFIG_MMU +static inline pte_t mk_pte(const struct page *page, pgprot_t pgprot) +{ + return pfn_pte(page_to_pfn(page), pgprot); +} + +/** + * folio_mk_pte - Create a PTE for this folio + * @folio: The folio to create a PTE for + * @pgprot: The page protection bits to use + * + * Create a page table entry for the first page of this folio. + * This is suitable for passing to set_ptes(). + * + * Return: A page table entry suitable for mapping this folio. + */ +static inline pte_t folio_mk_pte(const struct folio *folio, pgprot_t pgprot) +{ + return pfn_pte(folio_pfn(folio), pgprot); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/** + * folio_mk_pmd - Create a PMD for this folio + * @folio: The folio to create a PMD for + * @pgprot: The page protection bits to use + * + * Create a page table entry for the first page of this folio. + * This is suitable for passing to set_pmd_at(). + * + * Return: A page table entry suitable for mapping this folio. + */ +static inline pmd_t folio_mk_pmd(const struct folio *folio, pgprot_t pgprot) +{ + return pmd_mkhuge(pfn_pmd(folio_pfn(folio), pgprot)); +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +/** + * folio_mk_pud - Create a PUD for this folio + * @folio: The folio to create a PUD for + * @pgprot: The page protection bits to use + * + * Create a page table entry for the first page of this folio. + * This is suitable for passing to set_pud_at(). + * + * Return: A page table entry suitable for mapping this folio. + */ +static inline pud_t folio_mk_pud(const struct folio *folio, pgprot_t pgprot) +{ + return pud_mkhuge(pfn_pud(folio_pfn(folio), pgprot)); +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* CONFIG_MMU */ + +static inline bool folio_has_pincount(const struct folio *folio) +{ + if (IS_ENABLED(CONFIG_64BIT)) + return folio_test_large(folio); + return folio_order(folio) > 1; +} + /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. @@ -1931,7 +2125,7 @@ static inline struct folio *pfn_folio(unsigned long pfn) * get that many refcounts, and b) all the callers of this routine are * expected to be able to deal gracefully with a false positive. * - * For large folios, the result will be exactly correct. That's because + * For most large folios, the result will be exactly correct. That's because * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * @@ -1942,7 +2136,7 @@ static inline struct folio *pfn_folio(unsigned long pfn) */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { - if (folio_test_large(folio)) + if (folio_has_pincount(folio)) return atomic_read(&folio->_pincount) > 0; /* @@ -1968,7 +2162,7 @@ static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, { VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); - if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) + if (!mm_flags_test(MMF_HAS_PINNED, vma->vm_mm)) return false; return folio_maybe_dma_pinned(folio); @@ -2014,6 +2208,13 @@ static inline bool folio_is_longterm_pinnable(struct folio *folio) if (folio_is_device_coherent(folio)) return false; + /* + * Filesystems can only tolerate transient delays to truncate and + * hole-punch operations + */ + if (folio_is_fsdax(folio)) + return false; + /* Otherwise, non-movable zone folios can be pinned. */ return !folio_is_zone_movable(folio); @@ -2027,14 +2228,14 @@ static inline bool folio_is_longterm_pinnable(struct folio *folio) static inline void set_page_zone(struct page *page, enum zone_type zone) { - page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); - page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; + page->flags.f &= ~(ZONES_MASK << ZONES_PGSHIFT); + page->flags.f |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { - page->flags &= ~(NODES_MASK << NODES_PGSHIFT); - page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; + page->flags.f &= ~(NODES_MASK << NODES_PGSHIFT); + page->flags.f |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, @@ -2053,49 +2254,55 @@ static inline void set_page_links(struct page *page, enum zone_type zone, * * Return: A positive power of two. */ -static inline long folio_nr_pages(const struct folio *folio) +static inline unsigned long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; -#ifdef CONFIG_64BIT - return folio->_folio_nr_pages; -#else - return 1L << (folio->_flags_1 & 0xff); -#endif + return folio_large_nr_pages(folio); } -/* Only hugetlbfs can allocate folios larger than MAX_ORDER */ -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE -#define MAX_FOLIO_NR_PAGES (1UL << PUD_ORDER) +#if !defined(CONFIG_HAVE_GIGANTIC_FOLIOS) +/* + * We don't expect any folios that exceed buddy sizes (and consequently + * memory sections). + */ +#define MAX_FOLIO_ORDER MAX_PAGE_ORDER +#elif defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +/* + * Only pages within a single memory section are guaranteed to be + * contiguous. By limiting folios to a single memory section, all folio + * pages are guaranteed to be contiguous. + */ +#define MAX_FOLIO_ORDER PFN_SECTION_SHIFT +#elif defined(CONFIG_HUGETLB_PAGE) +/* + * There is no real limit on the folio size. We limit them to the maximum we + * currently expect (see CONFIG_HAVE_GIGANTIC_FOLIOS): with hugetlb, we expect + * no folios larger than 16 GiB on 64bit and 1 GiB on 32bit. + */ +#define MAX_FOLIO_ORDER get_order(IS_ENABLED(CONFIG_64BIT) ? SZ_16G : SZ_1G) #else -#define MAX_FOLIO_NR_PAGES MAX_ORDER_NR_PAGES +/* + * Without hugetlb, gigantic folios that are bigger than a single PUD are + * currently impossible. + */ +#define MAX_FOLIO_ORDER PUD_ORDER #endif +#define MAX_FOLIO_NR_PAGES (1UL << MAX_FOLIO_ORDER) + /* * compound_nr() returns the number of pages in this potentially compound * page. compound_nr() can be called on a tail page, and is defined to * return 1 in that case. */ -static inline unsigned long compound_nr(struct page *page) +static inline unsigned long compound_nr(const struct page *page) { - struct folio *folio = (struct folio *)page; + const struct folio *folio = (struct folio *)page; - if (!test_bit(PG_head, &folio->flags)) + if (!test_bit(PG_head, &folio->flags.f)) return 1; -#ifdef CONFIG_64BIT - return folio->_folio_nr_pages; -#else - return 1L << (folio->_flags_1 & 0xff); -#endif -} - -/** - * thp_nr_pages - The number of regular pages in this huge page. - * @page: The head page of a huge page. - */ -static inline int thp_nr_pages(struct page *page) -{ - return folio_nr_pages((struct folio *)page); + return folio_large_nr_pages(folio); } /** @@ -2148,23 +2355,18 @@ static inline size_t folio_size(const struct folio *folio) } /** - * folio_likely_mapped_shared - Estimate if the folio is mapped into the page - * tables of more than one MM + * folio_maybe_mapped_shared - Whether the folio is mapped into the page + * tables of more than one MM * @folio: The folio. * - * This function checks if the folio is currently mapped into more than one - * MM ("mapped shared"), or if the folio is only mapped into a single MM - * ("mapped exclusively"). + * This function checks if the folio maybe currently mapped into more than one + * MM ("maybe mapped shared"), or if the folio is certainly mapped into a single + * MM ("mapped exclusively"). * * For KSM folios, this function also returns "mapped shared" when a folio is * mapped multiple times into the same MM, because the individual page mappings * are independent. * - * As precise information is not easily available for all folios, this function - * estimates the number of MMs ("sharers") that are currently mapping a folio - * using the number of times the first page of the folio is currently mapped - * into page tables. - * * For small anonymous folios and anonymous hugetlb folios, the return * value will be exactly correct: non-KSM folios can only be mapped at most once * into an MM, and they cannot be partially mapped. KSM folios are @@ -2172,8 +2374,8 @@ static inline size_t folio_size(const struct folio *folio) * * For other folios, the result can be fuzzy: * #. For partially-mappable large folios (THP), the return value can wrongly - * indicate "mapped exclusively" (false negative) when the folio is - * only partially mapped into at least one MM. + * indicate "mapped shared" (false positive) if a folio was mapped by + * more than two MMs at one point in time. * #. For pagecache folios (including hugetlb), the return value can wrongly * indicate "mapped shared" (false positive) when two VMAs in the same MM * cover the same file range. @@ -2190,7 +2392,7 @@ static inline size_t folio_size(const struct folio *folio) * * Return: Whether the folio is estimated to be mapped into more than one MM. */ -static inline bool folio_likely_mapped_shared(struct folio *folio) +static inline bool folio_maybe_mapped_shared(struct folio *folio) { int mapcount = folio_mapcount(folio); @@ -2198,16 +2400,77 @@ static inline bool folio_likely_mapped_shared(struct folio *folio) if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) return mapcount > 1; - /* A single mapping implies "mapped exclusively". */ + /* + * vm_insert_page() without CONFIG_TRANSPARENT_HUGEPAGE ... + * simply assume "mapped shared", nobody should really care + * about this for arbitrary kernel allocations. + */ + if (!IS_ENABLED(CONFIG_MM_ID)) + return true; + + /* + * A single mapping implies "mapped exclusively", even if the + * folio flag says something different: it's easier to handle this + * case here instead of on the RMAP hot path. + */ if (mapcount <= 1) return false; + return test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids); +} - /* If any page is mapped more than once we treat it "mapped shared". */ - if (folio_entire_mapcount(folio) || mapcount > folio_nr_pages(folio)) - return true; +/** + * folio_expected_ref_count - calculate the expected folio refcount + * @folio: the folio + * + * Calculate the expected folio refcount, taking references from the pagecache, + * swapcache, PG_private and page table mappings into account. Useful in + * combination with folio_ref_count() to detect unexpected references (e.g., + * GUP or other temporary references). + * + * Does currently not consider references from the LRU cache. If the folio + * was isolated from the LRU (which is the case during migration or split), + * the LRU cache does not apply. + * + * Calling this function on an unmapped folio -- !folio_mapped() -- that is + * locked will return a stable result. + * + * Calling this function on a mapped folio will not result in a stable result, + * because nothing stops additional page table mappings from coming (e.g., + * fork()) or going (e.g., munmap()). + * + * Calling this function without the folio lock will also not result in a + * stable result: for example, the folio might get dropped from the swapcache + * concurrently. + * + * However, even when called without the folio lock or on a mapped folio, + * this function can be used to detect unexpected references early (for example, + * if it makes sense to even lock the folio and unmap it). + * + * The caller must add any reference (e.g., from folio_try_get()) it might be + * holding itself to the result. + * + * Returns the expected folio refcount. + */ +static inline int folio_expected_ref_count(const struct folio *folio) +{ + const int order = folio_order(folio); + int ref_count = 0; - /* Let's guess based on the first subpage. */ - return atomic_read(&folio->_mapcount) > 0; + if (WARN_ON_ONCE(page_has_type(&folio->page) && !folio_test_hugetlb(folio))) + return 0; + + if (folio_test_anon(folio)) { + /* One reference per page from the swapcache. */ + ref_count += folio_test_swapcache(folio) << order; + } else { + /* One reference per page from the pagecache. */ + ref_count += !!folio->mapping << order; + /* One reference from PG_private. */ + ref_count += folio_test_private(folio); + } + + /* One reference per page table mapping. */ + return ref_count + folio_mapcount(folio); } #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE @@ -2310,7 +2573,6 @@ static inline void clear_page_pfmemalloc(struct page *page) extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) -#define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* @@ -2319,6 +2581,7 @@ extern void pagefault_out_of_memory(void); struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ + bool reclaim_pt; /* Need reclaim page tables? */ zap_flags_t zap_flags; /* Extra flags for zapping */ }; @@ -2332,31 +2595,6 @@ struct zap_details { /* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ #define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) -#ifdef CONFIG_SCHED_MM_CID -void sched_mm_cid_before_execve(struct task_struct *t); -void sched_mm_cid_after_execve(struct task_struct *t); -void sched_mm_cid_fork(struct task_struct *t); -void sched_mm_cid_exit_signals(struct task_struct *t); -static inline int task_mm_cid(struct task_struct *t) -{ - return t->mm_cid; -} -#else -static inline void sched_mm_cid_before_execve(struct task_struct *t) { } -static inline void sched_mm_cid_after_execve(struct task_struct *t) { } -static inline void sched_mm_cid_fork(struct task_struct *t) { } -static inline void sched_mm_cid_exit_signals(struct task_struct *t) { } -static inline int task_mm_cid(struct task_struct *t) -{ - /* - * Use the processor id as a fall-back when the mm cid feature is - * disabled. This provides functional per-cpu data structure accesses - * in user-space, althrough it won't provide the memory usage benefits. - */ - return raw_smp_processor_id(); -} -#endif - #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else @@ -2373,6 +2611,8 @@ struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); +struct page *vm_normal_page_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t pud); void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); @@ -2385,7 +2625,7 @@ static inline void zap_vma_pages(struct vm_area_struct *vma) } void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long start, - unsigned long end, unsigned long tree_end, bool mm_wr_locked); + unsigned long end, unsigned long tree_end); struct mmu_notifier_range; @@ -2415,11 +2655,13 @@ struct follow_pfnmap_args { * Outputs: * * @pfn: the PFN of the address + * @addr_mask: address mask covering pfn * @pgprot: the pgprot_t of the mapping * @writable: whether the mapping is writable * @special: whether the mapping is a special mapping (real PFN maps) */ unsigned long pfn; + unsigned long addr_mask; pgprot_t pgprot; bool writable; bool special; @@ -2484,6 +2726,11 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); +#ifdef CONFIG_BPF_SYSCALL +extern int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr, + void *buf, int len, unsigned int gup_flags); +#endif + long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, @@ -2544,12 +2791,13 @@ void folio_add_pin(struct folio *folio); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, - struct task_struct *task, bool bypass_rlim); + const struct task_struct *task, bool bypass_rlim); struct kvec; -struct page *get_dump_page(unsigned long addr); +struct page *get_dump_page(unsigned long addr, int *locked); bool folio_mark_dirty(struct folio *folio); +bool folio_mark_dirty_lock(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); @@ -2582,7 +2830,7 @@ extern long change_protection(struct mmu_gather *tlb, unsigned long end, unsigned long cp_flags); extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, - unsigned long start, unsigned long end, unsigned long newflags); + unsigned long start, unsigned long end, vm_flags_t newflags); /* * doesn't attempt to fault and will return short. @@ -2603,6 +2851,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) return percpu_counter_read_positive(&mm->rss_stat[member]); } +static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member) +{ + return percpu_counter_sum_positive(&mm->rss_stat[member]); +} + void mm_trace_rss_stat(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) @@ -2662,8 +2915,8 @@ static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); - if ((mm)->hiwater_rss < _rss) - (mm)->hiwater_rss = _rss; + if (data_race(mm->hiwater_rss) < _rss) + data_race(mm->hiwater_rss = _rss); } static inline void update_hiwater_vm(struct mm_struct *mm) @@ -2722,13 +2975,6 @@ static inline pud_t pud_mkspecial(pud_t pud) } #endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ -#ifndef CONFIG_ARCH_HAS_PTE_DEVMAP -static inline int pte_devmap(pte_t pte) -{ - return 0; -} -#endif - extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, @@ -2862,16 +3108,23 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a } #endif /* CONFIG_MMU */ +enum pt_flags { + PT_kernel = PG_referenced, + PT_reserved = PG_reserved, + /* High bits are used for zone/node/section */ +}; + static inline struct ptdesc *virt_to_ptdesc(const void *x) { return page_ptdesc(virt_to_page(x)); } -static inline void *ptdesc_to_virt(const struct ptdesc *pt) -{ - return page_to_virt(ptdesc_page(pt)); -} - +/** + * ptdesc_address - Virtual address of page table. + * @pt: Page table descriptor. + * + * Return: The first byte of the page table described by @pt. + */ static inline void *ptdesc_address(const struct ptdesc *pt) { return folio_address(ptdesc_folio(pt)); @@ -2879,7 +3132,47 @@ static inline void *ptdesc_address(const struct ptdesc *pt) static inline bool pagetable_is_reserved(struct ptdesc *pt) { - return folio_test_reserved(ptdesc_folio(pt)); + return test_bit(PT_reserved, &pt->pt_flags.f); +} + +/** + * ptdesc_set_kernel - Mark a ptdesc used to map the kernel + * @ptdesc: The ptdesc to be marked + * + * Kernel page tables often need special handling. Set a flag so that + * the handling code knows this ptdesc will not be used for userspace. + */ +static inline void ptdesc_set_kernel(struct ptdesc *ptdesc) +{ + set_bit(PT_kernel, &ptdesc->pt_flags.f); +} + +/** + * ptdesc_clear_kernel - Mark a ptdesc as no longer used to map the kernel + * @ptdesc: The ptdesc to be unmarked + * + * Use when the ptdesc is no longer used to map the kernel and no longer + * needs special handling. + */ +static inline void ptdesc_clear_kernel(struct ptdesc *ptdesc) +{ + /* + * Note: the 'PG_referenced' bit does not strictly need to be + * cleared before freeing the page. But this is nice for + * symmetry. + */ + clear_bit(PT_kernel, &ptdesc->pt_flags.f); +} + +/** + * ptdesc_test_kernel - Check if a ptdesc is used to map the kernel + * @ptdesc: The ptdesc being tested + * + * Call to tell if the ptdesc used to map the kernel. + */ +static inline bool ptdesc_test_kernel(const struct ptdesc *ptdesc) +{ + return test_bit(PT_kernel, &ptdesc->pt_flags.f); } /** @@ -2900,6 +3193,21 @@ static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int orde } #define pagetable_alloc(...) alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__)) +static inline void __pagetable_free(struct ptdesc *pt) +{ + struct page *page = ptdesc_page(pt); + + __free_pages(page, compound_order(page)); +} + +#ifdef CONFIG_ASYNC_KERNEL_PGTABLE_FREE +void pagetable_free_kernel(struct ptdesc *pt); +#else +static inline void pagetable_free_kernel(struct ptdesc *pt) +{ + __pagetable_free(pt); +} +#endif /** * pagetable_free - Free pagetables * @pt: The page table descriptor @@ -2909,9 +3217,12 @@ static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int orde */ static inline void pagetable_free(struct ptdesc *pt) { - struct page *page = ptdesc_page(pt); - - __free_pages(page, compound_order(page)); + if (ptdesc_test_kernel(pt)) { + ptdesc_clear_kernel(pt); + pagetable_free_kernel(pt); + } else { + __pagetable_free(pt); + } } #if defined(CONFIG_SPLIT_PTE_PTLOCKS) @@ -2989,27 +3300,52 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ -static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) +static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); + return compound_nr(ptdesc_page(ptdesc)); +} - if (!ptlock_init(ptdesc)) - return false; - __folio_set_pgtable(folio); - lruvec_stat_add_folio(folio, NR_PAGETABLE); - return true; +static inline void __pagetable_ctor(struct ptdesc *ptdesc) +{ + pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); + + __SetPageTable(ptdesc_page(ptdesc)); + mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc)); } -static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) +static inline void pagetable_dtor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); + pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); ptlock_free(ptdesc); - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); + __ClearPageTable(ptdesc_page(ptdesc)); + mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc)); } -pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); +static inline void pagetable_dtor_free(struct ptdesc *ptdesc) +{ + pagetable_dtor(ptdesc); + pagetable_free(ptdesc); +} + +static inline bool pagetable_pte_ctor(struct mm_struct *mm, + struct ptdesc *ptdesc) +{ + if (mm != &init_mm && !ptlock_init(ptdesc)) + return false; + __pagetable_ctor(ptdesc); + return true; +} + +pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); +static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, + pmd_t *pmdvalp) +{ + pte_t *pte; + + __cond_lock(RCU, pte = ___pte_offset_map(pmd, addr, pmdvalp)); + return pte; +} static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr) { return __pte_offset_map(pmd, addr, NULL); @@ -3022,7 +3358,8 @@ static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, { pte_t *pte; - __cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)); + __cond_lock(RCU, __cond_lock(*ptlp, + pte = __pte_offset_map_lock(mm, pmd, addr, ptlp))); return pte; } @@ -3076,14 +3413,6 @@ static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) return ptlock_init(ptdesc); } -static inline void pmd_ptlock_free(struct ptdesc *ptdesc) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(ptdesc->pmd_huge_pte, ptdesc_page(ptdesc)); -#endif - ptlock_free(ptdesc); -} - #define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte) #else @@ -3094,7 +3423,6 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; } -static inline void pmd_ptlock_free(struct ptdesc *ptdesc) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) @@ -3107,26 +3435,16 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } -static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) +static inline bool pagetable_pmd_ctor(struct mm_struct *mm, + struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); - - if (!pmd_ptlock_init(ptdesc)) + if (mm != &init_mm && !pmd_ptlock_init(ptdesc)) return false; - __folio_set_pgtable(folio); - lruvec_stat_add_folio(folio, NR_PAGETABLE); + ptdesc_pmd_pts_init(ptdesc); + __pagetable_ctor(ptdesc); return true; } -static inline void pagetable_pmd_dtor(struct ptdesc *ptdesc) -{ - struct folio *folio = ptdesc_folio(ptdesc); - - pmd_ptlock_free(ptdesc); - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); -} - /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be @@ -3148,18 +3466,17 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); - - __folio_set_pgtable(folio); - lruvec_stat_add_folio(folio, NR_PAGETABLE); + __pagetable_ctor(ptdesc); } -static inline void pagetable_pud_dtor(struct ptdesc *ptdesc) +static inline void pagetable_p4d_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); + __pagetable_ctor(ptdesc); +} - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); +static inline void pagetable_pgd_ctor(struct ptdesc *ptdesc) +{ + __pagetable_ctor(ptdesc); } extern void __init pagecache_init(void); @@ -3181,7 +3498,6 @@ extern void reserve_bootmem_region(phys_addr_t start, /* Free the reserved page into the buddy system, so it gets managed. */ void free_reserved_page(struct page *page); -#define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) { @@ -3281,6 +3597,8 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); +struct vm_area_struct *vma_interval_tree_subtree_search(struct vm_area_struct *node, + unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, @@ -3308,10 +3626,11 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); avc; avc = anon_vma_interval_tree_iter_next(avc, start, last)) /* mmap.c */ -extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); +extern int __vm_enough_memory(const struct mm_struct *mm, long pages, int cap_sys_admin); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void exit_mmap(struct mm_struct *); -int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); +bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, bool write); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, @@ -3340,9 +3659,9 @@ extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); extern bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm); -extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, +struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, - unsigned long flags, + vm_flags_t vm_flags, const struct vm_special_mapping *spec); unsigned long randomize_stack_top(unsigned long stack_top); @@ -3359,9 +3678,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, return __get_unmapped_area(file, addr, len, pgoff, flags, 0); } -extern unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, - struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, @@ -3409,10 +3725,10 @@ struct vm_unmapped_area_info { extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ -extern void truncate_inode_pages(struct address_space *, loff_t); -extern void truncate_inode_pages_range(struct address_space *, - loff_t lstart, loff_t lend); -extern void truncate_inode_pages_final(struct address_space *); +void truncate_inode_pages(struct address_space *mapping, loff_t lstart); +void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, + uoff_t lend); +void truncate_inode_pages_final(struct address_space *mapping); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); @@ -3425,9 +3741,6 @@ extern unsigned long stack_guard_gap; int expand_stack_locked(struct vm_area_struct *vma, unsigned long address); struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr); -/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ -int expand_downwards(struct vm_area_struct *vma, unsigned long address); - /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, @@ -3453,7 +3766,7 @@ struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) return mtree_load(&mm->mm_mt, addr); } -static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) +static inline unsigned long stack_guard_start_gap(const struct vm_area_struct *vma) { if (vma->vm_flags & VM_GROWSDOWN) return stack_guard_gap; @@ -3465,7 +3778,7 @@ static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) return 0; } -static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +static inline unsigned long vm_start_gap(const struct vm_area_struct *vma) { unsigned long gap = stack_guard_start_gap(vma); unsigned long vm_start = vma->vm_start; @@ -3476,7 +3789,7 @@ static inline unsigned long vm_start_gap(struct vm_area_struct *vma) return vm_start; } -static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +static inline unsigned long vm_end_gap(const struct vm_area_struct *vma) { unsigned long vm_end = vma->vm_end; @@ -3488,11 +3801,95 @@ static inline unsigned long vm_end_gap(struct vm_area_struct *vma) return vm_end; } -static inline unsigned long vma_pages(struct vm_area_struct *vma) +static inline unsigned long vma_pages(const struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } +static inline unsigned long vma_desc_size(const struct vm_area_desc *desc) +{ + return desc->end - desc->start; +} + +static inline unsigned long vma_desc_pages(const struct vm_area_desc *desc) +{ + return vma_desc_size(desc) >> PAGE_SHIFT; +} + +/** + * mmap_action_remap - helper for mmap_prepare hook to specify that a pure PFN + * remap is required. + * @desc: The VMA descriptor for the VMA requiring remap. + * @start: The virtual address to start the remap from, must be within the VMA. + * @start_pfn: The first PFN in the range to remap. + * @size: The size of the range to remap, in bytes, at most spanning to the end + * of the VMA. + */ +static inline void mmap_action_remap(struct vm_area_desc *desc, + unsigned long start, + unsigned long start_pfn, + unsigned long size) +{ + struct mmap_action *action = &desc->action; + + /* [start, start + size) must be within the VMA. */ + WARN_ON_ONCE(start < desc->start || start >= desc->end); + WARN_ON_ONCE(start + size > desc->end); + + action->type = MMAP_REMAP_PFN; + action->remap.start = start; + action->remap.start_pfn = start_pfn; + action->remap.size = size; + action->remap.pgprot = desc->page_prot; +} + +/** + * mmap_action_remap_full - helper for mmap_prepare hook to specify that the + * entirety of a VMA should be PFN remapped. + * @desc: The VMA descriptor for the VMA requiring remap. + * @start_pfn: The first PFN in the range to remap. + */ +static inline void mmap_action_remap_full(struct vm_area_desc *desc, + unsigned long start_pfn) +{ + mmap_action_remap(desc, desc->start, start_pfn, vma_desc_size(desc)); +} + +/** + * mmap_action_ioremap - helper for mmap_prepare hook to specify that a pure PFN + * I/O remap is required. + * @desc: The VMA descriptor for the VMA requiring remap. + * @start: The virtual address to start the remap from, must be within the VMA. + * @start_pfn: The first PFN in the range to remap. + * @size: The size of the range to remap, in bytes, at most spanning to the end + * of the VMA. + */ +static inline void mmap_action_ioremap(struct vm_area_desc *desc, + unsigned long start, + unsigned long start_pfn, + unsigned long size) +{ + mmap_action_remap(desc, start, start_pfn, size); + desc->action.type = MMAP_IO_REMAP_PFN; +} + +/** + * mmap_action_ioremap_full - helper for mmap_prepare hook to specify that the + * entirety of a VMA should be PFN I/O remapped. + * @desc: The VMA descriptor for the VMA requiring remap. + * @start_pfn: The first PFN in the range to remap. + */ +static inline void mmap_action_ioremap_full(struct vm_area_desc *desc, + unsigned long start_pfn) +{ + mmap_action_ioremap(desc, desc->start, start_pfn, vma_desc_size(desc)); +} + +void mmap_action_prepare(struct mmap_action *action, + struct vm_area_desc *desc); +int mmap_action_complete(struct mmap_action *action, + struct vm_area_struct *vma); + /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) @@ -3505,17 +3902,17 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; } -static inline bool range_in_vma(struct vm_area_struct *vma, +static inline bool range_in_vma(const struct vm_area_struct *vma, unsigned long start, unsigned long end) { return (vma && vma->vm_start <= start && end <= vma->vm_end); } #ifdef CONFIG_MMU -pgprot_t vm_get_page_prot(unsigned long vm_flags); +pgprot_t vm_get_page_prot(vm_flags_t vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); #else -static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) +static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags) { return __pgprot(0); } @@ -3534,10 +3931,9 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, struct vm_area_struct *find_extend_vma_locked(struct mm_struct *, unsigned long addr); -int remap_pfn_range(struct vm_area_struct *, unsigned long addr, - unsigned long pfn, unsigned long size, pgprot_t); -int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, unsigned long size, pgprot_t prot); +int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t pgprot); + int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num); @@ -3545,14 +3941,16 @@ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); +vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page, + bool write); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn); + unsigned long pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, - unsigned long addr, pfn_t pfn); + unsigned long addr, unsigned long pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, @@ -3568,15 +3966,24 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -#ifndef io_remap_pfn_range -static inline int io_remap_pfn_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn, - unsigned long size, pgprot_t prot) +#ifndef io_remap_pfn_range_pfn +static inline unsigned long io_remap_pfn_range_pfn(unsigned long pfn, + unsigned long size) { - return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot)); + return pfn; } #endif +static inline int io_remap_pfn_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long orig_pfn, + unsigned long size, pgprot_t orig_prot) +{ + const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size); + const pgprot_t prot = pgprot_decrypted(orig_prot); + + return remap_pfn_range(vma, addr, pfn, size, prot); +} + static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) @@ -3619,7 +4026,7 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) * Indicates whether GUP can follow a PROT_NONE mapped page, or whether * a (NUMA hinting) fault is required. */ -static inline bool gup_can_follow_protnone(struct vm_area_struct *vma, +static inline bool gup_can_follow_protnone(const struct vm_area_struct *vma, unsigned int flags) { /* @@ -3749,7 +4156,7 @@ static inline bool debug_guardpage_enabled(void) return static_branch_unlikely(&_debug_guardpage_enabled); } -static inline bool page_is_guard(struct page *page) +static inline bool page_is_guard(const struct page *page) { if (!debug_guardpage_enabled()) return false; @@ -3780,7 +4187,7 @@ static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {} static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {} static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } -static inline bool page_is_guard(struct page *page) { return false; } +static inline bool page_is_guard(const struct page *page) { return false; } static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, @@ -3803,13 +4210,7 @@ static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) } #endif /* __HAVE_ARCH_GATE_AREA */ -extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); - -#ifdef CONFIG_SYSCTL -extern int sysctl_drop_caches; -int drop_caches_sysctl_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); -#endif +bool process_shares_mm(const struct task_struct *p, const struct mm_struct *mm); void drop_slab(void); @@ -3829,6 +4230,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) #endif void *sparse_buffer_alloc(unsigned long size); +unsigned long section_map_size(void); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); @@ -3837,7 +4239,8 @@ p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, - struct vmem_altmap *altmap, struct page *reuse); + struct vmem_altmap *altmap, unsigned long ptpfn, + unsigned long flags); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, @@ -3853,6 +4256,12 @@ int vmemmap_populate_hugepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); +int vmemmap_populate_hvo(unsigned long start, unsigned long end, int node, + unsigned long headsize); +int vmemmap_undo_hvo(unsigned long start, unsigned long end, int node, + unsigned long headsize); +void vmemmap_wrprotect_hvo(unsigned long start, unsigned long end, int node, + unsigned long headsize); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, @@ -3860,7 +4269,7 @@ void vmemmap_free(unsigned long start, unsigned long end, #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP -static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +static inline unsigned long vmem_altmap_offset(const struct vmem_altmap *altmap) { /* number of pfns from base where pfn_to_page() is valid */ if (altmap) @@ -3874,7 +4283,7 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap, altmap->alloc -= nr_pfns; } #else -static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +static inline unsigned long vmem_altmap_offset(const struct vmem_altmap *altmap) { return 0; } @@ -3919,9 +4328,6 @@ static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, } #endif -void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, - unsigned long nr_pages); - enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, @@ -3935,7 +4341,6 @@ enum mf_flags { int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); extern int memory_failure(unsigned long pfn, int flags); -extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); @@ -4027,6 +4432,7 @@ enum mf_action_page_type { MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_ALREADY_POISONED, + MF_MSG_PFN_MAP, MF_MSG_UNKNOWN, }; @@ -4082,56 +4488,15 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif -extern int sysctl_nr_trim_pages; - -#ifdef CONFIG_PRINTK -void mem_dump_obj(void *object); -#else -static inline void mem_dump_obj(void *object) {} -#endif - -/** - * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and - * handle them. - * @seals: the seals to check - * @vma: the vma to operate on - * - * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper - * check/handling on the vma flags. Return 0 if check pass, or <0 for errors. - */ -static inline int seal_check_write(int seals, struct vm_area_struct *vma) -{ - if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vm_flags_clear(vma, VM_MAYWRITE); - } - - return 0; -} - #ifdef CONFIG_ANON_VMA_NAME -int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, - unsigned long len_in, - struct anon_vma_name *anon_name); +int set_anon_vma_name(unsigned long addr, unsigned long size, + const char __user *uname); #else -static inline int -madvise_set_anon_name(struct mm_struct *mm, unsigned long start, - unsigned long len_in, struct anon_vma_name *anon_name) { - return 0; +static inline +int set_anon_vma_name(unsigned long addr, unsigned long size, + const char __user *uname) +{ + return -EINVAL; } #endif @@ -4163,6 +4528,7 @@ void vma_pgtable_walk_begin(struct vm_area_struct *vma); void vma_pgtable_walk_end(struct vm_area_struct *vma); int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); +int reserve_mem_release_by_name(const char *name); #ifdef CONFIG_64BIT int do_mseal(unsigned long start, size_t len_in, unsigned long flags); @@ -4174,8 +4540,106 @@ static inline int do_mseal(unsigned long start, size_t len_in, unsigned long fla } #endif +/* + * user_alloc_needs_zeroing checks if a user folio from page allocator needs to + * be zeroed or not. + */ +static inline bool user_alloc_needs_zeroing(void) +{ + /* + * for user folios, arch with cache aliasing requires cache flush and + * arc changes folio->flags to make icache coherent with dcache, so + * always return false to make caller use + * clear_user_page()/clear_user_highpage(). + */ + return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() || + !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, + &init_on_alloc); +} + int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); +/* + * DMA mapping IDs for page_pool + * + * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and + * stashes it in the upper bits of page->pp_magic. We always want to be able to + * unambiguously identify page pool pages (using page_pool_page_is_pp()). Non-PP + * pages can have arbitrary kernel pointers stored in the same field as pp_magic + * (since it overlaps with page->lru.next), so we must ensure that we cannot + * mistake a valid kernel pointer with any of the values we write into this + * field. + * + * On architectures that set POISON_POINTER_DELTA, this is already ensured, + * since this value becomes part of PP_SIGNATURE; meaning we can just use the + * space between the PP_SIGNATURE value (without POISON_POINTER_DELTA), and the + * lowest bits of POISON_POINTER_DELTA. On arches where POISON_POINTER_DELTA is + * 0, we use the lowest bit of PAGE_OFFSET as the boundary if that value is + * known at compile-time. + * + * If the value of PAGE_OFFSET is not known at compile time, or if it is too + * small to leave at least 8 bits available above PP_SIGNATURE, we define the + * number of bits to be 0, which turns off the DMA index tracking altogether + * (see page_pool_register_dma_index()). + */ +#define PP_DMA_INDEX_SHIFT (1 + __fls(PP_SIGNATURE - POISON_POINTER_DELTA)) +#if POISON_POINTER_DELTA > 0 +/* PP_SIGNATURE includes POISON_POINTER_DELTA, so limit the size of the DMA + * index to not overlap with that if set + */ +#define PP_DMA_INDEX_BITS MIN(32, __ffs(POISON_POINTER_DELTA) - PP_DMA_INDEX_SHIFT) +#else +/* Use the lowest bit of PAGE_OFFSET if there's at least 8 bits available; see above */ +#define PP_DMA_INDEX_MIN_OFFSET (1 << (PP_DMA_INDEX_SHIFT + 8)) +#define PP_DMA_INDEX_BITS ((__builtin_constant_p(PAGE_OFFSET) && \ + PAGE_OFFSET >= PP_DMA_INDEX_MIN_OFFSET && \ + !(PAGE_OFFSET & (PP_DMA_INDEX_MIN_OFFSET - 1))) ? \ + MIN(32, __ffs(PAGE_OFFSET) - PP_DMA_INDEX_SHIFT) : 0) + +#endif + +#define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \ + PP_DMA_INDEX_SHIFT) + +/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is + * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for + * the head page of compound page and bit 1 for pfmemalloc page, as well as the + * bits used for the DMA index. page_is_pfmemalloc() is checked in + * __page_pool_put_page() to avoid recycling the pfmemalloc page. + */ +#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL) + +#ifdef CONFIG_PAGE_POOL +static inline bool page_pool_page_is_pp(const struct page *page) +{ + return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE; +} +#else +static inline bool page_pool_page_is_pp(const struct page *page) +{ + return false; +} +#endif + +#define PAGE_SNAPSHOT_FAITHFUL (1 << 0) +#define PAGE_SNAPSHOT_PG_BUDDY (1 << 1) +#define PAGE_SNAPSHOT_PG_IDLE (1 << 2) + +struct page_snapshot { + struct folio folio_snapshot; + struct page page_snapshot; + unsigned long pfn; + unsigned long idx; + unsigned long flags; +}; + +static inline bool snapshot_page_is_faithful(const struct page_snapshot *ps) +{ + return ps->flags & PAGE_SNAPSHOT_FAITHFUL; +} + +void snapshot_page(struct page_snapshot *ps, const struct page *page); + #endif /* _LINUX_MM_H */ |