diff options
Diffstat (limited to '')
| -rw-r--r-- | mm/util.c | 514 |
1 files changed, 397 insertions, 117 deletions
diff --git a/mm/util.c b/mm/util.c index 988d11e6c17c..12984e76767e 100644 --- a/mm/util.c +++ b/mm/util.c @@ -27,6 +27,7 @@ #include <linux/uaccess.h> #include "internal.h" +#include "swap.h" /** * kfree_const - conditionally free memory @@ -69,7 +70,8 @@ EXPORT_SYMBOL(kstrdup); * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * - * Note: Strings allocated by kstrdup_const should be freed by kfree_const. + * Note: Strings allocated by kstrdup_const should be freed by kfree_const and + * must not be passed to krealloc(). * * Return: source string if it is in .rodata section otherwise * fallback to kstrdup. @@ -270,38 +272,6 @@ 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) { @@ -310,6 +280,18 @@ int vma_is_stack_for_current(struct vm_area_struct *vma) return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } +/* + * Change backing file, only valid to use during initial VMA setup. + */ +void vma_set_file(struct vm_area_struct *vma, struct file *file) +{ + /* Changing an anonymous vma with this is illegal */ + get_file(file); + swap(vma->vm_file, file); + fput(file); +} +EXPORT_SYMBOL(vma_set_file); + #ifndef STACK_RND_MASK #define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ #endif @@ -330,8 +312,40 @@ 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()) @@ -425,7 +439,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped * * Assumes @task and @mm are valid (i.e. at least one reference on each), and - * that mmap_sem is held as writer. + * that mmap_lock is held as writer. * * Return: * * 0 on success @@ -437,7 +451,7 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, unsigned long locked_vm, limit; int ret = 0; - lockdep_assert_held_write(&mm->mmap_sem); + mmap_assert_write_locked(mm); locked_vm = mm->locked_vm; if (inc) { @@ -481,10 +495,10 @@ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc) if (pages == 0 || !mm) return 0; - down_write(&mm->mmap_sem); + mmap_write_lock(mm); ret = __account_locked_vm(mm, pages, inc, current, capable(CAP_IPC_LOCK)); - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); return ret; } @@ -501,11 +515,11 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, ret = security_mmap_file(file, prot, flag); if (!ret) { - if (down_write_killable(&mm->mmap_sem)) + if (mmap_write_lock_killable(mm)) return -EINTR; - ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff, - &populate, &uf); - up_write(&mm->mmap_sem); + ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate, + &uf); + mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(ret, populate); @@ -536,13 +550,10 @@ EXPORT_SYMBOL(vm_mmap); * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * - * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. + * 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. * - * Please note that any use of gfp flags outside of GFP_KERNEL is careful to not - * fall back to vmalloc. - * * Return: pointer to the allocated memory of %NULL in case of failure */ void *kvmalloc_node(size_t size, gfp_t flags, int node) @@ -551,13 +562,6 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) void *ret; /* - * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables) - * so the given set of flags has to be compatible. - */ - if ((flags & GFP_KERNEL) != GFP_KERNEL) - return kmalloc_node(size, flags, node); - - /* * 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. @@ -569,6 +573,9 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) 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); @@ -580,8 +587,25 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) if (ret || size <= PAGE_SIZE) return ret; - return __vmalloc_node_flags_caller(size, node, flags, - __builtin_return_address(0)); + /* non-sleeping allocations are not supported by vmalloc */ + if (!gfpflags_allow_blocking(flags)) + return NULL; + + /* Don't even allow crazy sizes */ + if (unlikely(size > INT_MAX)) { + WARN_ON_ONCE(!(flags & __GFP_NOWARN)); + return NULL; + } + + /* + * kvmalloc() can always use VM_ALLOW_HUGE_VMAP, + * since the callers already cannot assume anything + * about the resulting pointer, and cannot play + * protection games. + */ + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + flags, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, + node, __builtin_return_address(0)); } EXPORT_SYMBOL(kvmalloc_node); @@ -604,91 +628,160 @@ void kvfree(const void *addr) } EXPORT_SYMBOL(kvfree); -static inline void *__page_rmapping(struct page *page) +/** + * 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. + */ +void kvfree_sensitive(const void *addr, size_t len) +{ + 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); + +/** + * __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 *__vmalloc_array(size_t n, size_t size, gfp_t flags) { - unsigned long mapping; + size_t bytes; - mapping = (unsigned long)page->mapping; - mapping &= ~PAGE_MAPPING_FLAGS; + if (unlikely(check_mul_overflow(n, size, &bytes))) + return NULL; + return __vmalloc(bytes, flags); +} +EXPORT_SYMBOL(__vmalloc_array); - return (void *)mapping; +/** + * vmalloc_array - allocate memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + */ +void *vmalloc_array(size_t n, size_t size) +{ + return __vmalloc_array(n, size, GFP_KERNEL); } +EXPORT_SYMBOL(vmalloc_array); + +/** + * __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 *__vcalloc(size_t n, size_t size, gfp_t flags) +{ + return __vmalloc_array(n, size, flags | __GFP_ZERO); +} +EXPORT_SYMBOL(__vcalloc); + +/** + * vcalloc - allocate and zero memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + */ +void *vcalloc(size_t n, size_t size) +{ + return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO); +} +EXPORT_SYMBOL(vcalloc); /* Neutral page->mapping pointer to address_space or anon_vma or other */ void *page_rmapping(struct page *page) { - page = compound_head(page); - return __page_rmapping(page); + return folio_raw_mapping(page_folio(page)); } -/* - * Return true if this page is mapped into pagetables. - * For compound page it returns true if any subpage of compound page is mapped. +/** + * 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. */ -bool page_mapped(struct page *page) +bool folio_mapped(struct folio *folio) { - int i; + long i, nr; - if (likely(!PageCompound(page))) - return atomic_read(&page->_mapcount) >= 0; - page = compound_head(page); - if (atomic_read(compound_mapcount_ptr(page)) >= 0) + if (!folio_test_large(folio)) + return atomic_read(&folio->_mapcount) >= 0; + if (atomic_read(folio_mapcount_ptr(folio)) >= 0) return true; - if (PageHuge(page)) + if (folio_test_hugetlb(folio)) return false; - for (i = 0; i < compound_nr(page); i++) { - if (atomic_read(&page[i]._mapcount) >= 0) + + nr = folio_nr_pages(folio); + for (i = 0; i < nr; i++) { + if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0) return true; } return false; } -EXPORT_SYMBOL(page_mapped); +EXPORT_SYMBOL(folio_mapped); -struct anon_vma *page_anon_vma(struct page *page) +struct anon_vma *folio_anon_vma(struct folio *folio) { - unsigned long mapping; + unsigned long mapping = (unsigned long)folio->mapping; - page = compound_head(page); - mapping = (unsigned long)page->mapping; if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) return NULL; - return __page_rmapping(page); + return (void *)(mapping - PAGE_MAPPING_ANON); } -struct address_space *page_mapping(struct page *page) +/** + * folio_mapping - Find the mapping where this folio is stored. + * @folio: The folio. + * + * For folios which are in the page cache, return the mapping that this + * page belongs to. Folios in the swap cache return the swap mapping + * this page is stored in (which is different from the mapping for the + * swap file or swap device where the data is stored). + * + * 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 *mapping; - page = compound_head(page); - /* This happens if someone calls flush_dcache_page on slab page */ - if (unlikely(PageSlab(page))) + if (unlikely(folio_test_slab(folio))) return NULL; - if (unlikely(PageSwapCache(page))) { - swp_entry_t entry; - - entry.val = page_private(page); - return swap_address_space(entry); - } + if (unlikely(folio_test_swapcache(folio))) + return swap_address_space(folio_swap_entry(folio)); - mapping = page->mapping; - if ((unsigned long)mapping & PAGE_MAPPING_ANON) + mapping = folio->mapping; + if ((unsigned long)mapping & PAGE_MAPPING_FLAGS) return NULL; - return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); -} -EXPORT_SYMBOL(page_mapping); - -/* - * For file cache pages, return the address_space, otherwise return NULL - */ -struct address_space *page_mapping_file(struct page *page) -{ - if (unlikely(PageSwapCache(page))) - return NULL; - return page_mapping(page); + return mapping; } +EXPORT_SYMBOL(folio_mapping); /* Slow path of page_mapcount() for compound pages */ int __page_mapcount(struct page *page) @@ -710,6 +803,62 @@ int __page_mapcount(struct page *page) } EXPORT_SYMBOL_GPL(__page_mapcount); +/** + * folio_mapcount() - Calculate the number of mappings of this folio. + * @folio: The folio. + * + * A large folio tracks both how many times the entire folio is mapped, + * and how many times each individual page in the folio is mapped. + * This function calculates the total number of times the folio is + * mapped. + * + * Return: The number of times this folio is mapped. + */ +int folio_mapcount(struct folio *folio) +{ + int i, compound, nr, ret; + + if (likely(!folio_test_large(folio))) + return atomic_read(&folio->_mapcount) + 1; + + compound = folio_entire_mapcount(folio); + if (folio_test_hugetlb(folio)) + return compound; + ret = compound; + nr = folio_nr_pages(folio); + for (i = 0; i < nr; i++) + ret += atomic_read(&folio_page(folio, i)->_mapcount) + 1; + /* File pages has compound_mapcount included in _mapcount */ + if (!folio_test_anon(folio)) + return ret - compound * nr; + if (folio_test_double_map(folio)) + ret -= nr; + return ret; +} + +/** + * folio_copy - Copy the contents of one folio to another. + * @dst: Folio to copy to. + * @src: Folio to copy from. + * + * The bytes in the folio represented by @src are copied to @dst. + * Assumes the caller has validated that @dst is at least as large as @src. + * Can be called in atomic context for order-0 folios, but if the folio is + * larger, it may sleep. + */ +void folio_copy(struct folio *dst, struct folio *src) +{ + long i = 0; + long nr = folio_nr_pages(src); + + for (;;) { + copy_highpage(folio_page(dst, i), folio_page(src, i)); + if (++i == nr) + break; + cond_resched(); + } +} + int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; int sysctl_overcommit_ratio __read_mostly = 50; unsigned long sysctl_overcommit_kbytes __read_mostly; @@ -717,9 +866,8 @@ 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 __user *buffer, size_t *lenp, - loff_t *ppos) +int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { int ret; @@ -729,9 +877,49 @@ int overcommit_ratio_handler(struct ctl_table *table, int write, return ret; } -int overcommit_kbytes_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) +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) +{ + struct ctl_table t; + int new_policy = -1; + int ret; + + /* + * The deviation of sync_overcommit_as could be big with loose policy + * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to + * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply + * with the strict "NEVER", and to avoid possible race condition (even + * though user usually won't too frequently do the switching to policy + * OVERCOMMIT_NEVER), the switch is done in the following order: + * 1. changing the batch + * 2. sync percpu count on each CPU + * 3. switch the policy + */ + if (write) { + t = *table; + t.data = &new_policy; + ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (ret || new_policy == -1) + return ret; + + mm_compute_batch(new_policy); + if (new_policy == OVERCOMMIT_NEVER) + schedule_on_each_cpu(sync_overcommit_as); + sysctl_overcommit_memory = new_policy; + } else { + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + } + + return ret; +} + +int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { int ret; @@ -771,10 +959,15 @@ struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; * balancing memory across competing virtual machines that are hosted. * Several metrics drive this policy engine including the guest reported * memory commitment. + * + * The time cost of this is very low for small platforms, and for big + * platform like a 2S/36C/72T Skylake server, in worst case where + * vm_committed_as's spinlock is under severe contention, the time cost + * could be about 30~40 microseconds. */ unsigned long vm_memory_committed(void) { - return percpu_counter_read_positive(&vm_committed_as); + return percpu_counter_sum_positive(&vm_committed_as); } EXPORT_SYMBOL_GPL(vm_memory_committed); @@ -784,7 +977,7 @@ 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. @@ -798,10 +991,6 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { long allowed; - VM_WARN_ONCE(percpu_counter_read(&vm_committed_as) < - -(s64)vm_committed_as_batch * num_online_cpus(), - "memory commitment underflow"); - vm_acct_memory(pages); /* @@ -835,6 +1024,8 @@ 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: + pr_warn_ratelimited("%s: pid: %d, comm: %s, no enough memory for the allocation\n", + __func__, current->pid, current->comm); vm_unacct_memory(pages); return -ENOMEM; @@ -899,7 +1090,7 @@ out: return res; } -int memcmp_pages(struct page *page1, struct page *page2) +int __weak memcmp_pages(struct page *page1, struct page *page2) { char *addr1, *addr2; int ret; @@ -911,3 +1102,92 @@ int memcmp_pages(struct page *page1, struct page *page2) kunmap_atomic(addr1); return ret; } + +#ifdef CONFIG_PRINTK +/** + * mem_dump_obj - Print available provenance information + * @object: object for which to find provenance information. + * + * This function uses pr_cont(), so that the caller is expected to have + * printed out whatever preamble is appropriate. The provenance information + * depends on the type of object and on how much debugging is enabled. + * For example, for a slab-cache object, the slab name is printed, and, + * if available, the return address and stack trace from the allocation + * and last free path of that object. + */ +void mem_dump_obj(void *object) +{ + const char *type; + + if (kmem_valid_obj(object)) { + kmem_dump_obj(object); + return; + } + + if (vmalloc_dump_obj(object)) + return; + + if (virt_addr_valid(object)) + type = "non-slab/vmalloc memory"; + else if (object == NULL) + type = "NULL pointer"; + else if (object == ZERO_SIZE_PTR) + type = "zero-size pointer"; + else + type = "non-paged memory"; + + pr_cont(" %s\n", type); +} +EXPORT_SYMBOL_GPL(mem_dump_obj); +#endif + +/* + * A driver might set a page logically offline -- PageOffline() -- and + * turn the page inaccessible in the hypervisor; after that, access to page + * content can be fatal. + * + * Some special PFN walkers -- i.e., /proc/kcore -- read content of random + * pages after checking PageOffline(); however, these PFN walkers can race + * with drivers that set PageOffline(). + * + * page_offline_freeze()/page_offline_thaw() allows for a subsystem to + * synchronize with such drivers, achieving that a page cannot be set + * PageOffline() while frozen. + * + * page_offline_begin()/page_offline_end() is used by drivers that care about + * such races when setting a page PageOffline(). + */ +static DECLARE_RWSEM(page_offline_rwsem); + +void page_offline_freeze(void) +{ + down_read(&page_offline_rwsem); +} + +void page_offline_thaw(void) +{ + up_read(&page_offline_rwsem); +} + +void page_offline_begin(void) +{ + down_write(&page_offline_rwsem); +} +EXPORT_SYMBOL(page_offline_begin); + +void page_offline_end(void) +{ + up_write(&page_offline_rwsem); +} +EXPORT_SYMBOL(page_offline_end); + +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO +void flush_dcache_folio(struct folio *folio) +{ + long i, nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) + flush_dcache_page(folio_page(folio, i)); +} +EXPORT_SYMBOL(flush_dcache_folio); +#endif |