diff options
Diffstat (limited to 'mm/util.c')
| -rw-r--r-- | mm/util.c | 885 |
1 files changed, 630 insertions, 255 deletions
diff --git a/mm/util.c b/mm/util.c index 7e43369064c8..97cae40c0209 100644 --- a/mm/util.c +++ b/mm/util.c @@ -12,6 +12,7 @@ #include <linux/security.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/sysctl.h> #include <linux/mman.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> @@ -23,10 +24,15 @@ #include <linux/processor.h> #include <linux/sizes.h> #include <linux/compat.h> +#include <linux/fsnotify.h> +#include <linux/page_idle.h> #include <linux/uaccess.h> +#include <kunit/visibility.h> + #include "internal.h" +#include "swap.h" /** * kfree_const - conditionally free memory @@ -42,26 +48,41 @@ void kfree_const(const void *x) EXPORT_SYMBOL(kfree_const); /** - * kstrdup - allocate space for and copy an existing string - * @s: the string to duplicate + * __kmemdup_nul - Create a NUL-terminated string from @s, which might be unterminated. + * @s: The data to copy + * @len: The size of the data, not including the NUL terminator * @gfp: the GFP mask used in the kmalloc() call when allocating memory * - * Return: newly allocated copy of @s or %NULL in case of error + * Return: newly allocated copy of @s with NUL-termination or %NULL in + * case of error */ -char *kstrdup(const char *s, gfp_t gfp) +static __always_inline char *__kmemdup_nul(const char *s, size_t len, gfp_t gfp) { - size_t len; char *buf; - if (!s) + /* '+1' for the NUL terminator */ + buf = kmalloc_track_caller(len + 1, gfp); + if (!buf) return NULL; - len = strlen(s) + 1; - buf = kmalloc_track_caller(len, gfp); - if (buf) - memcpy(buf, s, len); + memcpy(buf, s, len); + /* Ensure the buf is always NUL-terminated, regardless of @s. */ + buf[len] = '\0'; return buf; } + +/** + * kstrdup - allocate space for and copy an existing string + * @s: the string to duplicate + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Return: newly allocated copy of @s or %NULL in case of error + */ +noinline +char *kstrdup(const char *s, gfp_t gfp) +{ + return s ? __kmemdup_nul(s, strlen(s), gfp) : NULL; +} EXPORT_SYMBOL(kstrdup); /** @@ -96,19 +117,7 @@ EXPORT_SYMBOL(kstrdup_const); */ char *kstrndup(const char *s, size_t max, gfp_t gfp) { - size_t len; - char *buf; - - if (!s) - return NULL; - - len = strnlen(s, max); - buf = kmalloc_track_caller(len+1, gfp); - if (buf) { - memcpy(buf, s, len); - buf[len] = '\0'; - } - return buf; + return s ? __kmemdup_nul(s, strnlen(s, max), gfp) : NULL; } EXPORT_SYMBOL(kstrndup); @@ -119,18 +128,57 @@ EXPORT_SYMBOL(kstrndup); * @len: memory region length * @gfp: GFP mask to use * - * Return: newly allocated copy of @src or %NULL in case of error + * Return: newly allocated copy of @src or %NULL in case of error, + * result is physically contiguous. Use kfree() to free. + */ +void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) +{ + void *p; + + p = kmalloc_node_track_caller_noprof(len, gfp, NUMA_NO_NODE, _RET_IP_); + if (p) + memcpy(p, src, len); + return p; +} +EXPORT_SYMBOL(kmemdup_noprof); + +/** + * kmemdup_array - duplicate a given array. + * + * @src: array to duplicate. + * @count: number of elements to duplicate from array. + * @element_size: size of each element of array. + * @gfp: GFP mask to use. + * + * Return: duplicated array of @src or %NULL in case of error, + * result is physically contiguous. Use kfree() to free. + */ +void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) +{ + return kmemdup(src, size_mul(element_size, count), gfp); +} +EXPORT_SYMBOL(kmemdup_array); + +/** + * kvmemdup - duplicate region of memory + * + * @src: memory region to duplicate + * @len: memory region length + * @gfp: GFP mask to use + * + * Return: newly allocated copy of @src or %NULL in case of error, + * result may be not physically contiguous. Use kvfree() to free. */ -void *kmemdup(const void *src, size_t len, gfp_t gfp) +void *kvmemdup(const void *src, size_t len, gfp_t gfp) { void *p; - p = kmalloc_track_caller(len, gfp); + p = kvmalloc(len, gfp); if (p) memcpy(p, src, len); return p; } -EXPORT_SYMBOL(kmemdup); +EXPORT_SYMBOL(kvmemdup); /** * kmemdup_nul - Create a NUL-terminated string from unterminated data @@ -143,19 +191,19 @@ EXPORT_SYMBOL(kmemdup); */ char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) { - char *buf; + return s ? __kmemdup_nul(s, len, gfp) : NULL; +} +EXPORT_SYMBOL(kmemdup_nul); - if (!s) - return NULL; +static kmem_buckets *user_buckets __ro_after_init; - buf = kmalloc_track_caller(len + 1, gfp); - if (buf) { - memcpy(buf, s, len); - buf[len] = '\0'; - } - return buf; +static int __init init_user_buckets(void) +{ + user_buckets = kmem_buckets_create("memdup_user", 0, 0, INT_MAX, NULL); + + return 0; } -EXPORT_SYMBOL(kmemdup_nul); +subsys_initcall(init_user_buckets); /** * memdup_user - duplicate memory region from user space @@ -170,7 +218,7 @@ void *memdup_user(const void __user *src, size_t len) { void *p; - p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); + p = kmem_buckets_alloc_track_caller(user_buckets, len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -196,7 +244,7 @@ void *vmemdup_user(const void __user *src, size_t len) { void *p; - p = kvmalloc(len, GFP_USER); + p = kmem_buckets_valloc(user_buckets, len, GFP_USER); if (!p) return ERR_PTR(-ENOMEM); @@ -252,12 +300,7 @@ void *memdup_user_nul(const void __user *src, size_t len) { char *p; - /* - * Always use GFP_KERNEL, since copy_from_user() can sleep and - * cause pagefault, which makes it pointless to use GFP_NOFS - * or GFP_ATOMIC. - */ - p = kmalloc_track_caller(len + 1, GFP_KERNEL); + p = kmem_buckets_alloc_track_caller(user_buckets, len + 1, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -271,40 +314,8 @@ void *memdup_user_nul(const void __user *src, size_t len) } EXPORT_SYMBOL(memdup_user_nul); -void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, - struct vm_area_struct *prev) -{ - struct vm_area_struct *next; - - vma->vm_prev = prev; - if (prev) { - next = prev->vm_next; - prev->vm_next = vma; - } else { - next = mm->mmap; - mm->mmap = vma; - } - vma->vm_next = next; - if (next) - next->vm_prev = vma; -} - -void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma) -{ - struct vm_area_struct *prev, *next; - - next = vma->vm_next; - prev = vma->vm_prev; - if (prev) - prev->vm_next = next; - else - mm->mmap = next; - if (next) - next->vm_prev = prev; -} - /* Check if the vma is being used as a stack by this task */ -int vma_is_stack_for_current(struct vm_area_struct *vma) +int vma_is_stack_for_current(const struct vm_area_struct *vma) { struct task_struct * __maybe_unused t = current; @@ -343,8 +354,40 @@ unsigned long randomize_stack_top(unsigned long stack_top) #endif } +/** + * randomize_page - Generate a random, page aligned address + * @start: The smallest acceptable address the caller will take. + * @range: The size of the area, starting at @start, within which the + * random address must fall. + * + * If @start + @range would overflow, @range is capped. + * + * NOTE: Historical use of randomize_range, which this replaces, presumed that + * @start was already page aligned. We now align it regardless. + * + * Return: A page aligned address within [start, start + range). On error, + * @start is returned. + */ +unsigned long randomize_page(unsigned long start, unsigned long range) +{ + if (!PAGE_ALIGNED(start)) { + range -= PAGE_ALIGN(start) - start; + start = PAGE_ALIGN(start); + } + + if (start > ULONG_MAX - range) + range = ULONG_MAX - start; + + range >>= PAGE_SHIFT; + + if (range == 0) + return start; + + return start + (get_random_long() % range << PAGE_SHIFT); +} + #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT -unsigned long arch_randomize_brk(struct mm_struct *mm) +unsigned long __weak arch_randomize_brk(struct mm_struct *mm) { /* Is the current task 32bit ? */ if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task()) @@ -367,12 +410,15 @@ unsigned long arch_mmap_rnd(void) return rnd << PAGE_SHIFT; } -static int mmap_is_legacy(struct rlimit *rlim_stack) +static int mmap_is_legacy(const struct rlimit *rlim_stack) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; - if (rlim_stack->rlim_cur == RLIM_INFINITY) + /* On parisc the stack always grows up - so a unlimited stack should + * not be an indicator to use the legacy memory layout. */ + if (rlim_stack->rlim_cur == RLIM_INFINITY && + !IS_ENABLED(CONFIG_STACK_GROWSUP)) return 1; return sysctl_legacy_va_layout; @@ -385,8 +431,17 @@ static int mmap_is_legacy(struct rlimit *rlim_stack) #define MIN_GAP (SZ_128M) #define MAX_GAP (STACK_TOP / 6 * 5) -static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) +static unsigned long mmap_base(const unsigned long rnd, const struct rlimit *rlim_stack) { +#ifdef CONFIG_STACK_GROWSUP + /* + * For an upwards growing stack the calculation is much simpler. + * Memory for the maximum stack size is reserved at the top of the + * task. mmap_base starts directly below the stack and grows + * downwards. + */ + return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd); +#else unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_guard_gap; @@ -398,15 +453,16 @@ static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) if (gap + pad > gap) gap += pad; - if (gap < MIN_GAP) + if (gap < MIN_GAP && MIN_GAP < MAX_GAP) gap = MIN_GAP; else if (gap > MAX_GAP) gap = MAX_GAP; return PAGE_ALIGN(STACK_TOP - gap - rnd); +#endif } -void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) +void arch_pick_mmap_layout(struct mm_struct *mm, const struct rlimit *rlim_stack) { unsigned long random_factor = 0UL; @@ -415,19 +471,22 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; - mm->get_unmapped_area = arch_get_unmapped_area; + mm_flags_clear(MMF_TOPDOWN, mm); } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; + mm_flags_set(MMF_TOPDOWN, mm); } } #elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) -void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) +void arch_pick_mmap_layout(struct mm_struct *mm, const struct rlimit *rlim_stack) { mm->mmap_base = TASK_UNMAPPED_BASE; - mm->get_unmapped_area = arch_get_unmapped_area; + mm_flags_clear(MMF_TOPDOWN, mm); } #endif +#ifdef CONFIG_MMU +EXPORT_SYMBOL_IF_KUNIT(arch_pick_mmap_layout); +#endif /** * __account_locked_vm - account locked pages to an mm's locked_vm @@ -445,7 +504,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ 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) { unsigned long locked_vm, limit; int ret = 0; @@ -507,16 +566,19 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff) { + loff_t off = (loff_t)pgoff << PAGE_SHIFT; unsigned long ret; struct mm_struct *mm = current->mm; unsigned long populate; LIST_HEAD(uf); ret = security_mmap_file(file, prot, flag); + if (!ret) + ret = fsnotify_mmap_perm(file, prot, off, len); if (!ret) { if (mmap_write_lock_killable(mm)) return -EINTR; - ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate, + ret = do_mmap(file, addr, len, prot, flag, 0, pgoff, &populate, &uf); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); @@ -526,6 +588,23 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, return ret; } +/* + * Perform a userland memory mapping into the current process address space. See + * the comment for do_mmap() for more details on this operation in general. + * + * This differs from do_mmap() in that: + * + * a. An offset parameter is provided rather than pgoff, which is both checked + * for overflow and page alignment. + * b. mmap locking is performed on the caller's behalf. + * c. Userfaultfd unmap events and memory population are handled. + * + * This means that this function performs essentially the same work as if + * userland were invoking mmap (2). + * + * Returns either an error, or the address at which the requested mapping has + * been performed. + */ unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long offset) @@ -540,153 +619,62 @@ unsigned long vm_mmap(struct file *file, unsigned long addr, EXPORT_SYMBOL(vm_mmap); /** - * kvmalloc_node - attempt to allocate physically contiguous memory, but upon - * failure, fall back to non-contiguous (vmalloc) allocation. - * @size: size of the request. - * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL. - * @node: numa node to allocate from - * - * Uses kmalloc to get the memory but if the allocation fails then falls back - * to the vmalloc allocator. Use kvfree for freeing the memory. - * - * GFP_NOWAIT and GFP_ATOMIC are not supported, neither is the __GFP_NORETRY modifier. - * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is - * preferable to the vmalloc fallback, due to visible performance drawbacks. - * - * Return: pointer to the allocated memory of %NULL in case of failure + * __vmalloc_array - allocate memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + * @flags: the type of memory to allocate (see kmalloc). */ -void *kvmalloc_node(size_t size, gfp_t flags, int node) +void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { - gfp_t kmalloc_flags = flags; - void *ret; - - /* - * We want to attempt a large physically contiguous block first because - * it is less likely to fragment multiple larger blocks and therefore - * contribute to a long term fragmentation less than vmalloc fallback. - * However make sure that larger requests are not too disruptive - no - * OOM killer and no allocation failure warnings as we have a fallback. - */ - if (size > PAGE_SIZE) { - kmalloc_flags |= __GFP_NOWARN; + size_t bytes; - if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) - kmalloc_flags |= __GFP_NORETRY; - - /* nofail semantic is implemented by the vmalloc fallback */ - kmalloc_flags &= ~__GFP_NOFAIL; - } - - ret = kmalloc_node(size, kmalloc_flags, node); - - /* - * It doesn't really make sense to fallback to vmalloc for sub page - * requests - */ - if (ret || size <= PAGE_SIZE) - return ret; - - /* Don't even allow crazy sizes */ - if (WARN_ON_ONCE(size > INT_MAX)) + if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - - return __vmalloc_node(size, 1, flags, node, - __builtin_return_address(0)); + return __vmalloc_noprof(bytes, flags); } -EXPORT_SYMBOL(kvmalloc_node); +EXPORT_SYMBOL(__vmalloc_array_noprof); /** - * kvfree() - Free memory. - * @addr: Pointer to allocated memory. - * - * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). - * It is slightly more efficient to use kfree() or vfree() if you are certain - * that you know which one to use. - * - * Context: Either preemptible task context or not-NMI interrupt. + * vmalloc_array - allocate memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. */ -void kvfree(const void *addr) +void *vmalloc_array_noprof(size_t n, size_t size) { - if (is_vmalloc_addr(addr)) - vfree(addr); - else - kfree(addr); + return __vmalloc_array_noprof(n, size, GFP_KERNEL); } -EXPORT_SYMBOL(kvfree); +EXPORT_SYMBOL(vmalloc_array_noprof); /** - * kvfree_sensitive - Free a data object containing sensitive information. - * @addr: address of the data object to be freed. - * @len: length of the data object. - * - * Use the special memzero_explicit() function to clear the content of a - * kvmalloc'ed object containing sensitive data to make sure that the - * compiler won't optimize out the data clearing. + * __vcalloc - allocate and zero memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + * @flags: the type of memory to allocate (see kmalloc). */ -void kvfree_sensitive(const void *addr, size_t len) +void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) { - if (likely(!ZERO_OR_NULL_PTR(addr))) { - memzero_explicit((void *)addr, len); - kvfree(addr); - } -} -EXPORT_SYMBOL(kvfree_sensitive); - -void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) -{ - void *newp; - - if (oldsize >= newsize) - return (void *)p; - newp = kvmalloc(newsize, flags); - if (!newp) - return NULL; - memcpy(newp, p, oldsize); - kvfree(p); - return newp; -} -EXPORT_SYMBOL(kvrealloc); - -/* Neutral page->mapping pointer to address_space or anon_vma or other */ -void *page_rmapping(struct page *page) -{ - return folio_raw_mapping(page_folio(page)); + return __vmalloc_array_noprof(n, size, flags | __GFP_ZERO); } +EXPORT_SYMBOL(__vcalloc_noprof); /** - * folio_mapped - Is this folio mapped into userspace? - * @folio: The folio. - * - * Return: True if any page in this folio is referenced by user page tables. + * vcalloc - allocate and zero memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. */ -bool folio_mapped(struct folio *folio) +void *vcalloc_noprof(size_t n, size_t size) { - long i, nr; - - if (!folio_test_large(folio)) - return atomic_read(&folio->_mapcount) >= 0; - if (atomic_read(folio_mapcount_ptr(folio)) >= 0) - return true; - if (folio_test_hugetlb(folio)) - return false; - - nr = folio_nr_pages(folio); - for (i = 0; i < nr; i++) { - if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0) - return true; - } - return false; + return __vmalloc_array_noprof(n, size, GFP_KERNEL | __GFP_ZERO); } -EXPORT_SYMBOL(folio_mapped); +EXPORT_SYMBOL(vcalloc_noprof); -struct anon_vma *page_anon_vma(struct page *page) +struct anon_vma *folio_anon_vma(const struct folio *folio) { - struct folio *folio = page_folio(page); unsigned long mapping = (unsigned long)folio->mapping; - if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) + if ((mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) return NULL; - return (void *)(mapping - PAGE_MAPPING_ANON); + return (void *)(mapping - FOLIO_MAPPING_ANON); } /** @@ -701,7 +689,7 @@ struct anon_vma *page_anon_vma(struct page *page) * You can call this for folios which aren't in the swap cache or page * cache and it will return NULL. */ -struct address_space *folio_mapping(struct folio *folio) +struct address_space *folio_mapping(const struct folio *folio) { struct address_space *mapping; @@ -710,36 +698,16 @@ struct address_space *folio_mapping(struct folio *folio) return NULL; if (unlikely(folio_test_swapcache(folio))) - return swap_address_space(folio_swap_entry(folio)); + return swap_address_space(folio->swap); mapping = folio->mapping; - if ((unsigned long)mapping & PAGE_MAPPING_ANON) + if ((unsigned long)mapping & FOLIO_MAPPING_FLAGS) return NULL; - return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); + return mapping; } EXPORT_SYMBOL(folio_mapping); -/* Slow path of page_mapcount() for compound pages */ -int __page_mapcount(struct page *page) -{ - int ret; - - ret = atomic_read(&page->_mapcount) + 1; - /* - * For file THP page->_mapcount contains total number of mapping - * of the page: no need to look into compound_mapcount. - */ - if (!PageAnon(page) && !PageHuge(page)) - return ret; - page = compound_head(page); - ret += atomic_read(compound_mapcount_ptr(page)) + 1; - if (PageDoubleMap(page)) - ret--; - return ret; -} -EXPORT_SYMBOL_GPL(__page_mapcount); - /** * folio_copy - Copy the contents of one folio to another. * @dst: Folio to copy to. @@ -762,16 +730,36 @@ void folio_copy(struct folio *dst, struct folio *src) cond_resched(); } } +EXPORT_SYMBOL(folio_copy); + +int folio_mc_copy(struct folio *dst, struct folio *src) +{ + long nr = folio_nr_pages(src); + long i = 0; + + for (;;) { + if (copy_mc_highpage(folio_page(dst, i), folio_page(src, i))) + return -EHWPOISON; + if (++i == nr) + break; + cond_resched(); + } + + return 0; +} +EXPORT_SYMBOL(folio_mc_copy); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; -int sysctl_overcommit_ratio __read_mostly = 50; -unsigned long sysctl_overcommit_kbytes __read_mostly; +static int sysctl_overcommit_ratio __read_mostly = 50; +static unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ -int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) +#ifdef CONFIG_SYSCTL + +static int overcommit_ratio_handler(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -786,8 +774,8 @@ static void sync_overcommit_as(struct work_struct *dummy) percpu_counter_sync(&vm_committed_as); } -int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) +static int overcommit_policy_handler(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int new_policy = -1; @@ -822,8 +810,8 @@ int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer, return ret; } -int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) +static int overcommit_kbytes_handler(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -833,6 +821,54 @@ int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer, return ret; } +static const struct ctl_table util_sysctl_table[] = { + { + .procname = "overcommit_memory", + .data = &sysctl_overcommit_memory, + .maxlen = sizeof(sysctl_overcommit_memory), + .mode = 0644, + .proc_handler = overcommit_policy_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { + .procname = "overcommit_ratio", + .data = &sysctl_overcommit_ratio, + .maxlen = sizeof(sysctl_overcommit_ratio), + .mode = 0644, + .proc_handler = overcommit_ratio_handler, + }, + { + .procname = "overcommit_kbytes", + .data = &sysctl_overcommit_kbytes, + .maxlen = sizeof(sysctl_overcommit_kbytes), + .mode = 0644, + .proc_handler = overcommit_kbytes_handler, + }, + { + .procname = "user_reserve_kbytes", + .data = &sysctl_user_reserve_kbytes, + .maxlen = sizeof(sysctl_user_reserve_kbytes), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "admin_reserve_kbytes", + .data = &sysctl_admin_reserve_kbytes, + .maxlen = sizeof(sysctl_admin_reserve_kbytes), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, +}; + +static int __init init_vm_util_sysctls(void) +{ + register_sysctl_init("vm", util_sysctl_table); + return 0; +} +subsys_initcall(init_vm_util_sysctls); +#endif /* CONFIG_SYSCTL */ + /* * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used */ @@ -881,7 +917,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the - * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst + * vm.overcommit_memory sysctl. See Documentation/mm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. @@ -891,9 +927,10 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); * Note this is a helper function intended to be used by LSMs which * wish to use this logic. */ -int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) +int __vm_enough_memory(const struct mm_struct *mm, long pages, int cap_sys_admin) { long allowed; + unsigned long bytes_failed; vm_acct_memory(pages); @@ -928,6 +965,9 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; error: + bytes_failed = pages << PAGE_SHIFT; + pr_warn_ratelimited("%s: pid: %d, comm: %s, bytes: %lu not enough memory for the allocation\n", + __func__, current->pid, current->comm, bytes_failed); vm_unacct_memory(pages); return -ENOMEM; @@ -997,11 +1037,11 @@ int __weak memcmp_pages(struct page *page1, struct page *page2) char *addr1, *addr2; int ret; - addr1 = kmap_atomic(page1); - addr2 = kmap_atomic(page2); + addr1 = kmap_local_page(page1); + addr2 = kmap_local_page(page2); ret = memcmp(addr1, addr2, PAGE_SIZE); - kunmap_atomic(addr2); - kunmap_atomic(addr1); + kunmap_local(addr2); + kunmap_local(addr1); return ret; } @@ -1021,15 +1061,15 @@ void mem_dump_obj(void *object) { const char *type; - if (kmem_valid_obj(object)) { - kmem_dump_obj(object); + if (kmem_dump_obj(object)) return; - } if (vmalloc_dump_obj(object)) return; - if (virt_addr_valid(object)) + if (is_vmalloc_addr(object)) + type = "vmalloc memory"; + else if (virt_addr_valid(object)) type = "non-slab/vmalloc memory"; else if (object == NULL) type = "NULL pointer"; @@ -1083,7 +1123,7 @@ void page_offline_end(void) } EXPORT_SYMBOL(page_offline_end); -#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO +#ifndef flush_dcache_folio void flush_dcache_folio(struct folio *folio) { long i, nr = folio_nr_pages(folio); @@ -1093,3 +1133,338 @@ void flush_dcache_folio(struct folio *folio) } EXPORT_SYMBOL(flush_dcache_folio); #endif + +/** + * __compat_vma_mmap() - See description for compat_vma_mmap() + * for details. This is the same operation, only with a specific file operations + * struct which may or may not be the same as vma->vm_file->f_op. + * @f_op: The file operations whose .mmap_prepare() hook is specified. + * @file: The file which backs or will back the mapping. + * @vma: The VMA to apply the .mmap_prepare() hook to. + * Returns: 0 on success or error. + */ +int __compat_vma_mmap(const struct file_operations *f_op, + struct file *file, struct vm_area_struct *vma) +{ + struct vm_area_desc desc = { + .mm = vma->vm_mm, + .file = file, + .start = vma->vm_start, + .end = vma->vm_end, + + .pgoff = vma->vm_pgoff, + .vm_file = vma->vm_file, + .vm_flags = vma->vm_flags, + .page_prot = vma->vm_page_prot, + + .action.type = MMAP_NOTHING, /* Default */ + }; + int err; + + err = f_op->mmap_prepare(&desc); + if (err) + return err; + + mmap_action_prepare(&desc.action, &desc); + set_vma_from_desc(vma, &desc); + return mmap_action_complete(&desc.action, vma); +} +EXPORT_SYMBOL(__compat_vma_mmap); + +/** + * compat_vma_mmap() - Apply the file's .mmap_prepare() hook to an + * existing VMA and execute any requested actions. + * @file: The file which possesss an f_op->mmap_prepare() hook. + * @vma: The VMA to apply the .mmap_prepare() hook to. + * + * Ordinarily, .mmap_prepare() is invoked directly upon mmap(). However, certain + * stacked filesystems invoke a nested mmap hook of an underlying file. + * + * Until all filesystems are converted to use .mmap_prepare(), we must be + * conservative and continue to invoke these stacked filesystems using the + * deprecated .mmap() hook. + * + * However we have a problem if the underlying file system possesses an + * .mmap_prepare() hook, as we are in a different context when we invoke the + * .mmap() hook, already having a VMA to deal with. + * + * compat_vma_mmap() is a compatibility function that takes VMA state, + * establishes a struct vm_area_desc descriptor, passes to the underlying + * .mmap_prepare() hook and applies any changes performed by it. + * + * Once the conversion of filesystems is complete this function will no longer + * be required and will be removed. + * + * Returns: 0 on success or error. + */ +int compat_vma_mmap(struct file *file, struct vm_area_struct *vma) +{ + return __compat_vma_mmap(file->f_op, file, vma); +} +EXPORT_SYMBOL(compat_vma_mmap); + +static void set_ps_flags(struct page_snapshot *ps, const struct folio *folio, + const struct page *page) +{ + /* + * Only the first page of a high-order buddy page has PageBuddy() set. + * So we have to check manually whether this page is part of a high- + * order buddy page. + */ + if (PageBuddy(page)) + ps->flags |= PAGE_SNAPSHOT_PG_BUDDY; + else if (page_count(page) == 0 && is_free_buddy_page(page)) + ps->flags |= PAGE_SNAPSHOT_PG_BUDDY; + + if (folio_test_idle(folio)) + ps->flags |= PAGE_SNAPSHOT_PG_IDLE; +} + +/** + * snapshot_page() - Create a snapshot of a struct page + * @ps: Pointer to a struct page_snapshot to store the page snapshot + * @page: The page to snapshot + * + * Create a snapshot of the page and store both its struct page and struct + * folio representations in @ps. + * + * A snapshot is marked as "faithful" if the compound state of @page was + * stable and allowed safe reconstruction of the folio representation. In + * rare cases where this is not possible (e.g. due to folio splitting), + * snapshot_page() falls back to treating @page as a single page and the + * snapshot is marked as "unfaithful". The snapshot_page_is_faithful() + * helper can be used to check for this condition. + */ +void snapshot_page(struct page_snapshot *ps, const struct page *page) +{ + unsigned long head, nr_pages = 1; + struct folio *foliop; + int loops = 5; + + ps->pfn = page_to_pfn(page); + ps->flags = PAGE_SNAPSHOT_FAITHFUL; + +again: + memset(&ps->folio_snapshot, 0, sizeof(struct folio)); + memcpy(&ps->page_snapshot, page, sizeof(*page)); + head = ps->page_snapshot.compound_head; + if ((head & 1) == 0) { + ps->idx = 0; + foliop = (struct folio *)&ps->page_snapshot; + if (!folio_test_large(foliop)) { + set_ps_flags(ps, page_folio(page), page); + memcpy(&ps->folio_snapshot, foliop, + sizeof(struct page)); + return; + } + foliop = (struct folio *)page; + } else { + foliop = (struct folio *)(head - 1); + ps->idx = folio_page_idx(foliop, page); + } + + if (ps->idx < MAX_FOLIO_NR_PAGES) { + memcpy(&ps->folio_snapshot, foliop, 2 * sizeof(struct page)); + nr_pages = folio_nr_pages(&ps->folio_snapshot); + if (nr_pages > 1) + memcpy(&ps->folio_snapshot.__page_2, &foliop->__page_2, + sizeof(struct page)); + set_ps_flags(ps, foliop, page); + } + + if (ps->idx > nr_pages) { + if (loops-- > 0) + goto again; + clear_compound_head(&ps->page_snapshot); + foliop = (struct folio *)&ps->page_snapshot; + memcpy(&ps->folio_snapshot, foliop, sizeof(struct page)); + ps->flags = 0; + ps->idx = 0; + } +} + +static int mmap_action_finish(struct mmap_action *action, + const struct vm_area_struct *vma, int err) +{ + /* + * If an error occurs, unmap the VMA altogether and return an error. We + * only clear the newly allocated VMA, since this function is only + * invoked if we do NOT merge, so we only clean up the VMA we created. + */ + if (err) { + const size_t len = vma_pages(vma) << PAGE_SHIFT; + + do_munmap(current->mm, vma->vm_start, len, NULL); + + if (action->error_hook) { + /* We may want to filter the error. */ + err = action->error_hook(err); + + /* The caller should not clear the error. */ + VM_WARN_ON_ONCE(!err); + } + return err; + } + + if (action->success_hook) + return action->success_hook(vma); + + return 0; +} + +#ifdef CONFIG_MMU +/** + * mmap_action_prepare - Perform preparatory setup for an VMA descriptor + * action which need to be performed. + * @desc: The VMA descriptor to prepare for @action. + * @action: The action to perform. + */ +void mmap_action_prepare(struct mmap_action *action, + struct vm_area_desc *desc) +{ + switch (action->type) { + case MMAP_NOTHING: + break; + case MMAP_REMAP_PFN: + remap_pfn_range_prepare(desc, action->remap.start_pfn); + break; + case MMAP_IO_REMAP_PFN: + io_remap_pfn_range_prepare(desc, action->remap.start_pfn, + action->remap.size); + break; + } +} +EXPORT_SYMBOL(mmap_action_prepare); + +/** + * mmap_action_complete - Execute VMA descriptor action. + * @action: The action to perform. + * @vma: The VMA to perform the action upon. + * + * Similar to mmap_action_prepare(). + * + * Return: 0 on success, or error, at which point the VMA will be unmapped. + */ +int mmap_action_complete(struct mmap_action *action, + struct vm_area_struct *vma) +{ + int err = 0; + + switch (action->type) { + case MMAP_NOTHING: + break; + case MMAP_REMAP_PFN: + err = remap_pfn_range_complete(vma, action->remap.start, + action->remap.start_pfn, action->remap.size, + action->remap.pgprot); + break; + case MMAP_IO_REMAP_PFN: + err = io_remap_pfn_range_complete(vma, action->remap.start, + action->remap.start_pfn, action->remap.size, + action->remap.pgprot); + break; + } + + return mmap_action_finish(action, vma, err); +} +EXPORT_SYMBOL(mmap_action_complete); +#else +void mmap_action_prepare(struct mmap_action *action, + struct vm_area_desc *desc) +{ + switch (action->type) { + case MMAP_NOTHING: + break; + case MMAP_REMAP_PFN: + case MMAP_IO_REMAP_PFN: + WARN_ON_ONCE(1); /* nommu cannot handle these. */ + break; + } +} +EXPORT_SYMBOL(mmap_action_prepare); + +int mmap_action_complete(struct mmap_action *action, + struct vm_area_struct *vma) +{ + int err = 0; + + switch (action->type) { + case MMAP_NOTHING: + break; + case MMAP_REMAP_PFN: + case MMAP_IO_REMAP_PFN: + WARN_ON_ONCE(1); /* nommu cannot handle this. */ + + err = -EINVAL; + break; + } + + return mmap_action_finish(action, vma, err); +} +EXPORT_SYMBOL(mmap_action_complete); +#endif + +#ifdef CONFIG_MMU +/** + * folio_pte_batch - detect a PTE batch for a large folio + * @folio: The large folio to detect a PTE batch for. + * @ptep: Page table pointer for the first entry. + * @pte: Page table entry for the first page. + * @max_nr: The maximum number of table entries to consider. + * + * This is a simplified variant of folio_pte_batch_flags(). + * + * Detect a PTE batch: consecutive (present) PTEs that map consecutive + * pages of the same large folio in a single VMA and a single page table. + * + * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, + * the accessed bit, writable bit, dirt-bit and soft-dirty bit. + * + * ptep must map any page of the folio. max_nr must be at least one and + * must be limited by the caller so scanning cannot exceed a single VMA and + * a single page table. + * + * Return: the number of table entries in the batch. + */ +unsigned int folio_pte_batch(struct folio *folio, pte_t *ptep, pte_t pte, + unsigned int max_nr) +{ + return folio_pte_batch_flags(folio, NULL, ptep, &pte, max_nr, 0); +} +#endif /* CONFIG_MMU */ + +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +/** + * page_range_contiguous - test whether the page range is contiguous + * @page: the start of the page range. + * @nr_pages: the number of pages in the range. + * + * Test whether the page range is contiguous, such that they can be iterated + * naively, corresponding to iterating a contiguous PFN range. + * + * This function should primarily only be used for debug checks, or when + * working with page ranges that are not naturally contiguous (e.g., pages + * within a folio are). + * + * Returns true if contiguous, otherwise false. + */ +bool page_range_contiguous(const struct page *page, unsigned long nr_pages) +{ + const unsigned long start_pfn = page_to_pfn(page); + const unsigned long end_pfn = start_pfn + nr_pages; + unsigned long pfn; + + /* + * The memmap is allocated per memory section, so no need to check + * within the first section. However, we need to check each other + * spanned memory section once, making sure the first page in a + * section could similarly be reached by just iterating pages. + */ + for (pfn = ALIGN(start_pfn, PAGES_PER_SECTION); + pfn < end_pfn; pfn += PAGES_PER_SECTION) + if (unlikely(page + (pfn - start_pfn) != pfn_to_page(pfn))) + return false; + return true; +} +EXPORT_SYMBOL(page_range_contiguous); +#endif |