diff options
Diffstat (limited to 'include/linux/mm.h')
-rw-r--r-- | include/linux/mm.h | 194 |
1 files changed, 111 insertions, 83 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..dc7b87310c10 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -15,6 +15,7 @@ #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> +#include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> @@ -28,6 +29,7 @@ #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> +#include <linux/pgtable.h> struct mempolicy; struct anon_vma; @@ -92,7 +94,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #endif #include <asm/page.h> -#include <asm/pgtable.h> #include <asm/processor.h> /* @@ -201,10 +202,10 @@ extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; -extern int overcommit_ratio_handler(struct ctl_table *, int, void __user *, - size_t *, loff_t *); -extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, - size_t *, loff_t *); +int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) @@ -325,17 +326,13 @@ extern unsigned int kobjsize(const void *objp); #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI +#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 #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif -#if defined(CONFIG_X86_INTEL_MPX) -/* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_HIGH_ARCH_4 -#else -# define VM_MPX VM_NONE -#endif - #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif @@ -405,7 +402,7 @@ extern pgprot_t protection_map[16]; * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. - * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_sem and wait when retrying. + * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. @@ -455,10 +452,10 @@ extern pgprot_t protection_map[16]; * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * * This is mostly used for places where we want to try to avoid taking - * the mmap_sem for too long a time when waiting for another condition + * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the - * mmap_sem in the first round to avoid potential starvation of other - * processes that would also want the mmap_sem. + * mmap_lock in the first round to avoid potential starvation of other + * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. @@ -505,7 +502,6 @@ struct vm_fault { pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Page handler may use for COW fault */ - struct mem_cgroup *memcg; /* Cgroup cow_page belongs to */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by @@ -586,7 +582,7 @@ struct vm_operations_struct { * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not - * marked as MPOL_SHARED. vma policies are protected by the mmap_sem. + * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. @@ -781,7 +777,13 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) } extern void kvfree(const void *addr); +extern void kvfree_sensitive(const void *addr, size_t len); +/* + * Mapcount of compound page as a whole, does not include mapped sub-pages. + * + * Must be called only for compound pages or any their tail sub-pages. + */ static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); @@ -801,10 +803,16 @@ static inline void page_mapcount_reset(struct page *page) int __page_mapcount(struct page *page); +/* + * Mapcount of 0-order page; when compound sub-page, includes + * compound_mapcount(). + * + * Result is undefined for pages which cannot be mapped into userspace. + * For example SLAB or special types of pages. See function page_has_type(). + * They use this place in struct page differently. + */ static inline int page_mapcount(struct page *page) { - VM_BUG_ON_PAGE(PageSlab(page), page); - if (unlikely(PageCompound(page))) return __page_mapcount(page); return atomic_read(&page->_mapcount) + 1; @@ -860,7 +868,7 @@ enum compound_dtor_id { #endif NR_COMPOUND_DTORS, }; -extern compound_page_dtor * const compound_page_dtors[]; +extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) @@ -869,10 +877,10 @@ static inline void set_compound_page_dtor(struct page *page, page[1].compound_dtor = compound_dtor; } -static inline compound_page_dtor *get_compound_page_dtor(struct page *page) +static inline void destroy_compound_page(struct page *page) { VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); - return compound_page_dtors[page[1].compound_dtor]; + compound_page_dtors[page[1].compound_dtor](page); } static inline unsigned int compound_order(struct page *page) @@ -939,8 +947,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, - struct page *page); +vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif @@ -1219,7 +1226,7 @@ void unpin_user_pages(struct page **pages, unsigned long npages); * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS * scheme). * - * For more information, please see Documentation/vm/pin_user_pages.rst. + * For more information, please see Documentation/core-api/pin_user_pages.rst. * * @page: pointer to page to be queried. * @Return: True, if it is likely that the page has been "dma-pinned". @@ -1367,7 +1374,7 @@ static inline int cpu_pid_to_cpupid(int nid, int pid) static inline bool cpupid_pid_unset(int cpupid) { - return 1; + return true; } static inline void page_cpupid_reset_last(struct page *page) @@ -1700,8 +1707,12 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages, struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); +long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); +long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, + struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); @@ -1718,7 +1729,7 @@ struct frame_vector { unsigned int nr_frames; /* Number of frames stored in ptrs array */ bool got_ref; /* Did we pin pages by getting page ref? */ bool is_pfns; /* Does array contain pages or pfns? */ - void *ptrs[0]; /* Array of pinned pfns / pages. Use + void *ptrs[]; /* Array of pinned pfns / pages. Use * pfns_vector_pages() or pfns_vector_pfns() * for access */ }; @@ -1816,8 +1827,16 @@ extern int mprotect_fixup(struct vm_area_struct *vma, /* * doesn't attempt to fault and will return short. */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages); +int get_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); +int pin_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); + +static inline bool get_user_page_fast_only(unsigned long addr, + unsigned int gup_flags, struct page **pagep) +{ + return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1; +} /* * per-process(per-mm_struct) statistics. */ @@ -2060,11 +2079,6 @@ int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) -/* - * The following ifdef needed to get the 5level-fixup.h header to work. - * Remove it when 5level-fixup.h has been removed. - */ -#ifndef __ARCH_HAS_5LEVEL_HACK static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { @@ -2078,13 +2092,52 @@ static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } -#endif /* !__ARCH_HAS_5LEVEL_HACK */ + +static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, + unsigned long address, + pgtbl_mod_mask *mod_mask) + +{ + if (unlikely(pgd_none(*pgd))) { + if (__p4d_alloc(mm, pgd, address)) + return NULL; + *mod_mask |= PGTBL_PGD_MODIFIED; + } + + return p4d_offset(pgd, address); +} + +static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(p4d_none(*p4d))) { + if (__pud_alloc(mm, p4d, address)) + return NULL; + *mod_mask |= PGTBL_P4D_MODIFIED; + } + + return pud_offset(p4d, address); +} static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } + +static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(pud_none(*pud))) { + if (__pmd_alloc(mm, pud, address)) + return NULL; + *mod_mask |= PGTBL_PUD_MODIFIED; + } + + return pmd_offset(pud, address); +} #endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS @@ -2200,6 +2253,11 @@ static inline void pgtable_pte_page_dtor(struct page *page) ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) +#define pte_alloc_kernel_track(pmd, address, mask) \ + ((unlikely(pmd_none(*(pmd))) && \ + (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ + NULL: pte_offset_kernel(pmd, address)) + #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) @@ -2272,9 +2330,7 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void free_area_init(unsigned long * zones_size); -extern void __init free_area_init_node(int nid, unsigned long * zones_size, - unsigned long zone_start_pfn, unsigned long *zholes_size); +extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* @@ -2344,34 +2400,26 @@ static inline unsigned long get_num_physpages(void) return phys_pages; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its - * zones, allocate the backing mem_map and account for memory holes in a more - * architecture independent manner. This is a substitute for creating the - * zone_sizes[] and zholes_size[] arrays and passing them to - * free_area_init_node() + * Using memblock node mappings, an architecture may initialise its + * zones, allocate the backing mem_map and account for memory holes in an + * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling - * free_area_init_nodes() passing in the PFN each zone ends at. At a basic + * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid) - * free_area_init_nodes(max_zone_pfns); + * free_area_init(max_zone_pfns); * - * free_bootmem_with_active_regions() calls free_bootmem_node() for each - * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. - * - * See mm/page_alloc.c for more information on each function exposed by - * CONFIG_HAVE_MEMBLOCK_NODE_MAP. */ -extern void free_area_init_nodes(unsigned long *max_zone_pfn); +void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); @@ -2380,16 +2428,10 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -extern void free_bootmem_with_active_regions(int nid, - unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - -#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ - !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) -static inline int __early_pfn_to_nid(unsigned long pfn, - struct mminit_pfnnid_cache *state) +#ifndef CONFIG_NEED_MULTIPLE_NODES +static inline int early_pfn_to_nid(unsigned long pfn) { return 0; } @@ -2425,6 +2467,7 @@ extern void setup_per_cpu_pageset(void); extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; +extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; @@ -2601,25 +2644,6 @@ extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); int __must_check write_one_page(struct page *page); void task_dirty_inc(struct task_struct *tsk); -/* readahead.c */ -#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) - -int force_page_cache_readahead(struct address_space *mapping, struct file *filp, - pgoff_t offset, unsigned long nr_to_read); - -void page_cache_sync_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - pgoff_t offset, - unsigned long size); - -void page_cache_async_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - struct page *pg, - pgoff_t offset, - unsigned long size); - extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); @@ -2780,6 +2804,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ #define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ +#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each @@ -2834,7 +2859,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * - * Please see Documentation/vm/pin_user_pages.rst for more information. + * Please see Documentation/core-api/pin_user_pages.rst for more information. */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) @@ -2957,8 +2982,8 @@ 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(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); #endif void drop_slab(void); @@ -3012,6 +3037,7 @@ enum mf_flags { }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); +extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern int get_hwpoison_page(struct page *page); #define put_hwpoison_page(page) put_page(page) @@ -3140,5 +3166,7 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif +extern int sysctl_nr_trim_pages; + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ |