diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-12-28 16:55:46 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-12-28 16:55:46 -0800 |
commit | f346b0becb1bc62e45495f9cdbae3eef35d0b635 (patch) | |
tree | ae79f3dfb8e031da51d38f0f095f89d7d23f3643 /include | |
parent | 00d59fde8532b2d42e80909d2e58678755e04da9 (diff) | |
parent | 0f4991e8fd48987ae476a92cdee6bfec4aff31b8 (diff) |
Merge branch 'akpm' (patches from Andrew)
Merge misc updates from Andrew Morton:
- large KASAN update to use arm's "software tag-based mode"
- a few misc things
- sh updates
- ocfs2 updates
- just about all of MM
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (167 commits)
kernel/fork.c: mark 'stack_vm_area' with __maybe_unused
memcg, oom: notify on oom killer invocation from the charge path
mm, swap: fix swapoff with KSM pages
include/linux/gfp.h: fix typo
mm/hmm: fix memremap.h, move dev_page_fault_t callback to hmm
hugetlbfs: Use i_mmap_rwsem to fix page fault/truncate race
hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization
memory_hotplug: add missing newlines to debugging output
mm: remove __hugepage_set_anon_rmap()
include/linux/vmstat.h: remove unused page state adjustment macro
mm/page_alloc.c: allow error injection
mm: migrate: drop unused argument of migrate_page_move_mapping()
blkdev: avoid migration stalls for blkdev pages
mm: migrate: provide buffer_migrate_page_norefs()
mm: migrate: move migrate_page_lock_buffers()
mm: migrate: lock buffers before migrate_page_move_mapping()
mm: migration: factor out code to compute expected number of page references
mm, page_alloc: enable pcpu_drain with zone capability
kmemleak: add config to select auto scan
mm/page_alloc.c: don't call kasan_free_pages() at deferred mem init
...
Diffstat (limited to 'include')
31 files changed, 437 insertions, 188 deletions
diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h index 296c65442f00..95a159a4137f 100644 --- a/include/asm-generic/error-injection.h +++ b/include/asm-generic/error-injection.h @@ -8,6 +8,7 @@ enum { EI_ETYPE_NULL, /* Return NULL if failure */ EI_ETYPE_ERRNO, /* Return -ERRNO if failure */ EI_ETYPE_ERRNO_NULL, /* Return -ERRNO or NULL if failure */ + EI_ETYPE_TRUE, /* Return true if failure */ }; struct error_injection_entry { diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index a9cac82e9a7a..05e61e6c843f 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1057,6 +1057,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); +int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ @@ -1084,6 +1085,10 @@ static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } +static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) +{ + return 0; +} static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return 0; diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 9a6bc0951cfa..c31157135598 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -258,6 +258,14 @@ static inline void wb_get(struct bdi_writeback *wb) */ static inline void wb_put(struct bdi_writeback *wb) { + if (WARN_ON_ONCE(!wb->bdi)) { + /* + * A driver bug might cause a file to be removed before bdi was + * initialized. + */ + return; + } + if (wb != &wb->bdi->wb) percpu_ref_put(&wb->refcnt); } diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 3e7dafb3ea80..39f668d5066b 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -16,9 +16,13 @@ /* all clang versions usable with the kernel support KASAN ABI version 5 */ #define KASAN_ABI_VERSION 5 +#if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) /* emulate gcc's __SANITIZE_ADDRESS__ flag */ -#if __has_feature(address_sanitizer) #define __SANITIZE_ADDRESS__ +#define __no_sanitize_address \ + __attribute__((no_sanitize("address", "hwaddress"))) +#else +#define __no_sanitize_address #endif /* diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 2010493e1040..5776da43da97 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -143,6 +143,12 @@ #define KASAN_ABI_VERSION 3 #endif +#if __has_attribute(__no_sanitize_address__) +#define __no_sanitize_address __attribute__((no_sanitize_address)) +#else +#define __no_sanitize_address +#endif + #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index fe07b680dd4a..19f32b0c29af 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -200,19 +200,6 @@ #define __noreturn __attribute__((__noreturn__)) /* - * Optional: only supported since gcc >= 4.8 - * Optional: not supported by icc - * - * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fsanitize_005faddress-function-attribute - * clang: https://clang.llvm.org/docs/AttributeReference.html#no-sanitize-address-no-address-safety-analysis - */ -#if __has_attribute(__no_sanitize_address__) -# define __no_sanitize_address __attribute__((__no_sanitize_address__)) -#else -# define __no_sanitize_address -#endif - -/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-packed-type-attribute * clang: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-packed-variable-attribute */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 6d52ce6af4ff..811c77743dad 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3269,8 +3269,12 @@ extern int generic_check_addressable(unsigned, u64); extern int buffer_migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); +extern int buffer_migrate_page_norefs(struct address_space *, + struct page *, struct page *, + enum migrate_mode); #else #define buffer_migrate_page NULL +#define buffer_migrate_page_norefs NULL #endif extern int setattr_prepare(struct dentry *, struct iattr *); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0705164f928c..5f5e25fd6149 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -81,7 +81,7 @@ struct vm_area_struct; * * %__GFP_HARDWALL enforces the cpuset memory allocation policy. * - * %__GFP_THISNODE forces the allocation to be satisified from the requested + * %__GFP_THISNODE forces the allocation to be satisfied from the requested * node with no fallbacks or placement policy enforcements. * * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 0690679832d4..ea5cdbd8c2c3 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -36,7 +36,31 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); -extern unsigned long totalhigh_pages; +extern atomic_long_t _totalhigh_pages; +static inline unsigned long totalhigh_pages(void) +{ + return (unsigned long)atomic_long_read(&_totalhigh_pages); +} + +static inline void totalhigh_pages_inc(void) +{ + atomic_long_inc(&_totalhigh_pages); +} + +static inline void totalhigh_pages_dec(void) +{ + atomic_long_dec(&_totalhigh_pages); +} + +static inline void totalhigh_pages_add(long count) +{ + atomic_long_add(count, &_totalhigh_pages); +} + +static inline void totalhigh_pages_set(long val) +{ + atomic_long_set(&_totalhigh_pages, val); +} void kmap_flush_unused(void); @@ -51,7 +75,7 @@ static inline struct page *kmap_to_page(void *addr) return virt_to_page(addr); } -#define totalhigh_pages 0UL +static inline unsigned long totalhigh_pages(void) { return 0UL; } #ifndef ARCH_HAS_KMAP static inline void *kmap(struct page *page) diff --git a/include/linux/hmm.h b/include/linux/hmm.h index c6fb869a81c0..66f9ebbb1df3 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -69,6 +69,7 @@ #define LINUX_HMM_H #include <linux/kconfig.h> +#include <asm/pgtable.h> #if IS_ENABLED(CONFIG_HMM) @@ -486,6 +487,7 @@ struct hmm_devmem_ops { * @device: device to bind resource to * @ops: memory operations callback * @ref: per CPU refcount + * @page_fault: callback when CPU fault on an unaddressable device page * * This an helper structure for device drivers that do not wish to implement * the gory details related to hotplugging new memoy and allocating struct @@ -493,7 +495,28 @@ struct hmm_devmem_ops { * * Device drivers can directly use ZONE_DEVICE memory on their own if they * wish to do so. + * + * The page_fault() callback must migrate page back, from device memory to + * system memory, so that the CPU can access it. This might fail for various + * reasons (device issues, device have been unplugged, ...). When such error + * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and + * set the CPU page table entry to "poisoned". + * + * Note that because memory cgroup charges are transferred to the device memory, + * this should never fail due to memory restrictions. However, allocation + * of a regular system page might still fail because we are out of memory. If + * that happens, the page_fault() callback must return VM_FAULT_OOM. + * + * The page_fault() callback can also try to migrate back multiple pages in one + * chunk, as an optimization. It must, however, prioritize the faulting address + * over all the others. */ +typedef int (*dev_page_fault_t)(struct vm_area_struct *vma, + unsigned long addr, + const struct page *page, + unsigned int flags, + pmd_t *pmdp); + struct hmm_devmem { struct completion completion; unsigned long pfn_first; @@ -503,6 +526,7 @@ struct hmm_devmem { struct dev_pagemap pagemap; const struct hmm_devmem_ops *ops; struct percpu_ref ref; + dev_page_fault_t page_fault; }; /* @@ -512,8 +536,7 @@ struct hmm_devmem { * enough and allocate struct page for it. * * The device driver can wrap the hmm_devmem struct inside a private device - * driver struct. The device driver must call hmm_devmem_remove() before the - * device goes away and before freeing the hmm_devmem struct memory. + * driver struct. */ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, struct device *device, @@ -521,7 +544,6 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, struct device *device, struct resource *res); -void hmm_devmem_remove(struct hmm_devmem *devmem); /* * hmm_devmem_page_set_drvdata - set per-page driver data field diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 4663ee96cf59..381e872bfde0 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -93,7 +93,11 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); extern unsigned long transparent_hugepage_flags; -static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +/* + * to be used on vmas which are known to support THP. + * Use transparent_hugepage_enabled otherwise + */ +static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { if (vma->vm_flags & VM_NOHUGEPAGE) return false; @@ -117,6 +121,8 @@ static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } +bool transparent_hugepage_enabled(struct vm_area_struct *vma); + #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) @@ -257,6 +263,11 @@ static inline bool thp_migration_supported(void) #define hpage_nr_pages(x) 1 +static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) +{ + return false; +} + static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) { return false; diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 46aae129917c..b40ea104dd36 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -14,13 +14,13 @@ struct task_struct; #include <asm/kasan.h> #include <asm/pgtable.h> -extern unsigned char kasan_zero_page[PAGE_SIZE]; -extern pte_t kasan_zero_pte[PTRS_PER_PTE]; -extern pmd_t kasan_zero_pmd[PTRS_PER_PMD]; -extern pud_t kasan_zero_pud[PTRS_PER_PUD]; -extern p4d_t kasan_zero_p4d[MAX_PTRS_PER_P4D]; +extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; +extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE]; +extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD]; +extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD]; +extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; -int kasan_populate_zero_shadow(const void *shadow_start, +int kasan_populate_early_shadow(const void *shadow_start, const void *shadow_end); static inline void *kasan_mem_to_shadow(const void *addr) @@ -45,22 +45,24 @@ void kasan_free_pages(struct page *page, unsigned int order); void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags); -void kasan_cache_shrink(struct kmem_cache *cache); -void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_poison_slab(struct page *page); void kasan_unpoison_object_data(struct kmem_cache *cache, void *object); void kasan_poison_object_data(struct kmem_cache *cache, void *object); -void kasan_init_slab_obj(struct kmem_cache *cache, const void *object); +void * __must_check kasan_init_slab_obj(struct kmem_cache *cache, + const void *object); -void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); +void * __must_check kasan_kmalloc_large(const void *ptr, size_t size, + gfp_t flags); void kasan_kfree_large(void *ptr, unsigned long ip); void kasan_poison_kfree(void *ptr, unsigned long ip); -void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, - gfp_t flags); -void kasan_krealloc(const void *object, size_t new_size, gfp_t flags); +void * __must_check kasan_kmalloc(struct kmem_cache *s, const void *object, + size_t size, gfp_t flags); +void * __must_check kasan_krealloc(const void *object, size_t new_size, + gfp_t flags); -void kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags); +void * __must_check kasan_slab_alloc(struct kmem_cache *s, void *object, + gfp_t flags); bool kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip); struct kasan_cache { @@ -97,27 +99,40 @@ static inline void kasan_free_pages(struct page *page, unsigned int order) {} static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} -static inline void kasan_cache_shrink(struct kmem_cache *cache) {} -static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_poison_slab(struct page *page) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} static inline void kasan_poison_object_data(struct kmem_cache *cache, void *object) {} -static inline void kasan_init_slab_obj(struct kmem_cache *cache, - const void *object) {} +static inline void *kasan_init_slab_obj(struct kmem_cache *cache, + const void *object) +{ + return (void *)object; +} -static inline void kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags) {} +static inline void *kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags) +{ + return ptr; +} static inline void kasan_kfree_large(void *ptr, unsigned long ip) {} static inline void kasan_poison_kfree(void *ptr, unsigned long ip) {} -static inline void kasan_kmalloc(struct kmem_cache *s, const void *object, - size_t size, gfp_t flags) {} -static inline void kasan_krealloc(const void *object, size_t new_size, - gfp_t flags) {} +static inline void *kasan_kmalloc(struct kmem_cache *s, const void *object, + size_t size, gfp_t flags) +{ + return (void *)object; +} +static inline void *kasan_krealloc(const void *object, size_t new_size, + gfp_t flags) +{ + return (void *)object; +} -static inline void kasan_slab_alloc(struct kmem_cache *s, void *object, - gfp_t flags) {} +static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object, + gfp_t flags) +{ + return object; +} static inline bool kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip) { @@ -140,4 +155,40 @@ static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } #endif /* CONFIG_KASAN */ +#ifdef CONFIG_KASAN_GENERIC + +#define KASAN_SHADOW_INIT 0 + +void kasan_cache_shrink(struct kmem_cache *cache); +void kasan_cache_shutdown(struct kmem_cache *cache); + +#else /* CONFIG_KASAN_GENERIC */ + +static inline void kasan_cache_shrink(struct kmem_cache *cache) {} +static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} + +#endif /* CONFIG_KASAN_GENERIC */ + +#ifdef CONFIG_KASAN_SW_TAGS + +#define KASAN_SHADOW_INIT 0xFF + +void kasan_init_tags(void); + +void *kasan_reset_tag(const void *addr); + +void kasan_report(unsigned long addr, size_t size, + bool is_write, unsigned long ip); + +#else /* CONFIG_KASAN_SW_TAGS */ + +static inline void kasan_init_tags(void) { } + +static inline void *kasan_reset_tag(const void *addr) +{ + return (void *)addr; +} + +#endif /* CONFIG_KASAN_SW_TAGS */ + #endif /* LINUX_KASAN_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index aee299a6aa76..64c41cf45590 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -154,7 +154,6 @@ void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, phys_addr_t *out_end); -void __memblock_free_early(phys_addr_t base, phys_addr_t size); void __memblock_free_late(phys_addr_t base, phys_addr_t size); /** @@ -320,6 +319,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r) /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) #define MEMBLOCK_ALLOC_ACCESSIBLE 0 +#define MEMBLOCK_ALLOC_KASAN 1 /* We are using top down, so it is safe to use 0 here */ #define MEMBLOCK_LOW_LIMIT 0 @@ -414,13 +414,13 @@ static inline void * __init memblock_alloc_node_nopanic(phys_addr_t size, static inline void __init memblock_free_early(phys_addr_t base, phys_addr_t size) { - __memblock_free_early(base, size); + memblock_free(base, size); } static inline void __init memblock_free_early_nid(phys_addr_t base, phys_addr_t size, int nid) { - __memblock_free_early(base, size); + memblock_free(base, size); } static inline void __init memblock_free_late(phys_addr_t base, phys_addr_t size) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7ab2120155a4..83ae11cbd12c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -526,9 +526,11 @@ void mem_cgroup_handle_over_high(void); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); -void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, +void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); +void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); + static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); @@ -970,7 +972,12 @@ static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) } static inline void -mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) +mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) +{ +} + +static inline void +mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ffd9cd10fcf3..07da5c6c5ba0 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -107,8 +107,8 @@ static inline bool movable_node_is_enabled(void) } #ifdef CONFIG_MEMORY_HOTREMOVE -extern int arch_remove_memory(u64 start, u64 size, - struct vmem_altmap *altmap); +extern int arch_remove_memory(int nid, u64 start, u64 size, + struct vmem_altmap *altmap); extern int __remove_pages(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); #endif /* CONFIG_MEMORY_HOTREMOVE */ @@ -326,15 +326,14 @@ extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); -extern int add_memory_resource(int nid, struct resource *resource, bool online); +extern int add_memory_resource(int nid, struct resource *resource); extern int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap, bool want_memblock); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); -extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); -extern int sparse_add_one_section(struct pglist_data *pgdat, - unsigned long start_pfn, struct vmem_altmap *altmap); +extern int sparse_add_one_section(int nid, unsigned long start_pfn, + struct vmem_altmap *altmap); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, unsigned long map_offset, struct vmem_altmap *altmap); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 0ac69ddf5fc4..f0628660d541 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -4,8 +4,6 @@ #include <linux/ioport.h> #include <linux/percpu-refcount.h> -#include <asm/pgtable.h> - struct resource; struct device; @@ -66,62 +64,34 @@ enum memory_type { }; /* - * For MEMORY_DEVICE_PRIVATE we use ZONE_DEVICE and extend it with two - * callbacks: - * page_fault() - * page_free() - * * Additional notes about MEMORY_DEVICE_PRIVATE may be found in * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief * explanation in include/linux/memory_hotplug.h. * - * The page_fault() callback must migrate page back, from device memory to - * system memory, so that the CPU can access it. This might fail for various - * reasons (device issues, device have been unplugged, ...). When such error - * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and - * set the CPU page table entry to "poisoned". - * - * Note that because memory cgroup charges are transferred to the device memory, - * this should never fail due to memory restrictions. However, allocation - * of a regular system page might still fail because we are out of memory. If - * that happens, the page_fault() callback must return VM_FAULT_OOM. - * - * The page_fault() callback can also try to migrate back multiple pages in one - * chunk, as an optimization. It must, however, prioritize the faulting address - * over all the others. - * - * * The page_free() callback is called once the page refcount reaches 1 * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug. * This allows the device driver to implement its own memory management.) - * - * For MEMORY_DEVICE_PUBLIC only the page_free() callback matter. */ -typedef int (*dev_page_fault_t)(struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp); typedef void (*dev_page_free_t)(struct page *page, void *data); /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings - * @page_fault: callback when CPU fault on an unaddressable device page * @page_free: free page callback when page refcount reaches 1 * @altmap: pre-allocated/reserved memory for vmemmap allocations * @res: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping + * @kill: callback to transition @ref to the dead state * @dev: host device of the mapping for debug * @data: private data pointer for page_free() * @type: memory type: see MEMORY_* in memory_hotplug.h */ struct dev_pagemap { - dev_page_fault_t page_fault; dev_page_free_t page_free; struct vmem_altmap altmap; bool altmap_valid; struct resource res; struct percpu_ref *ref; + void (*kill)(struct percpu_ref *ref); struct device *dev; void *data; enum memory_type type; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index f2b4abbca55e..e13d9bf2f9a5 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -29,7 +29,7 @@ enum migrate_reason { }; /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ -extern char *migrate_reason_names[MR_TYPES]; +extern const char *migrate_reason_names[MR_TYPES]; static inline struct page *new_page_nodemask(struct page *page, int preferred_nid, nodemask_t *nodemask) @@ -77,8 +77,7 @@ extern void migrate_page_copy(struct page *newpage, struct page *page); extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page, - struct buffer_head *head, enum migrate_mode mode, + struct page *newpage, struct page *page, enum migrate_mode mode, int extra_count); #else diff --git a/include/linux/mm.h b/include/linux/mm.h index 5411de93a363..ea1f12d15365 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -48,7 +48,32 @@ static inline void set_max_mapnr(unsigned long limit) static inline void set_max_mapnr(unsigned long limit) { } #endif -extern unsigned long totalram_pages; +extern atomic_long_t _totalram_pages; +static inline unsigned long totalram_pages(void) +{ + return (unsigned long)atomic_long_read(&_totalram_pages); +} + +static inline void totalram_pages_inc(void) +{ + atomic_long_inc(&_totalram_pages); +} + +static inline void totalram_pages_dec(void) +{ + atomic_long_dec(&_totalram_pages); +} + +static inline void totalram_pages_add(long count) +{ + atomic_long_add(count, &_totalram_pages); +} + +static inline void totalram_pages_set(long val) +{ + atomic_long_set(&_totalram_pages, val); +} + extern void * high_memory; extern int page_cluster; @@ -804,6 +829,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) +#define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) /* * Define the bit shifts to access each section. For non-existent @@ -814,6 +840,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) +#define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS @@ -836,6 +863,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) +#define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) @@ -1101,6 +1129,32 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) } #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_KASAN_SW_TAGS +static inline u8 page_kasan_tag(const struct page *page) +{ + return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; +} + +static inline void |