diff options
Diffstat (limited to 'mm/mmap.c')
| -rw-r--r-- | mm/mmap.c | 2394 |
1 files changed, 1720 insertions, 674 deletions
diff --git a/mm/mmap.c b/mm/mmap.c index a32d28ce31c..129b847d30c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3,12 +3,16 @@ * * Written by obz. * - * Address space accounting code <alan@redhat.com> + * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> @@ -22,16 +26,28 @@ #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/profile.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> +#include <linux/mmu_notifier.h> +#include <linux/perf_event.h> +#include <linux/audit.h> +#include <linux/khugepaged.h> +#include <linux/uprobes.h> +#include <linux/rbtree_augmented.h> +#include <linux/sched/sysctl.h> +#include <linux/notifier.h> +#include <linux/memory.h> +#include <linux/printk.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlb.h> #include <asm/mmu_context.h> +#include "internal.h" + #ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif @@ -44,12 +60,6 @@ static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end); -/* - * WARNING: the debugging will use recursive algorithms so never enable this - * unless you know what you are doing. - */ -#undef DEBUG_MM_RB - /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: @@ -72,15 +82,37 @@ pgprot_t protection_map[16] = { pgprot_t vm_get_page_prot(unsigned long vm_flags) { - return protection_map[vm_flags & - (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]; + return __pgprot(pgprot_val(protection_map[vm_flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) | + pgprot_val(arch_vm_get_page_prot(vm_flags))); } EXPORT_SYMBOL(vm_get_page_prot); -int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ -int sysctl_overcommit_ratio = 50; /* default is 50% */ +int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; /* heuristic overcommit */ +int sysctl_overcommit_ratio __read_mostly = 50; /* default is 50% */ +unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; -atomic_t vm_committed_space = ATOMIC_INIT(0); +unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ +unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ +/* + * Make sure vm_committed_as in one cacheline and not cacheline shared with + * other variables. It can be updated by several CPUs frequently. + */ +struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; + +/* + * The global memory commitment made in the system can be a metric + * that can be used to drive ballooning decisions when Linux is hosted + * as a guest. On Hyper-V, the host implements a policy engine for dynamically + * balancing memory across competing virtual machines that are hosted. + * Several metrics drive this policy engine including the guest reported + * memory commitment. + */ +unsigned long vm_memory_committed(void) +{ + return percpu_counter_read_positive(&vm_committed_as); +} +EXPORT_SYMBOL_GPL(vm_memory_committed); /* * Check that a process has enough memory to allocate a new virtual @@ -100,7 +132,7 @@ atomic_t vm_committed_space = ATOMIC_INIT(0); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed; + unsigned long free, allowed, reserve; vm_acct_memory(pages); @@ -111,10 +143,18 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { - unsigned long n; + free = global_page_state(NR_FREE_PAGES); + free += global_page_state(NR_FILE_PAGES); - free = global_page_state(NR_FILE_PAGES); - free += nr_swap_pages; + /* + * shmem pages shouldn't be counted as free in this + * case, they can't be purged, only swapped out, and + * that won't affect the overall amount of available + * memory in the system. + */ + free -= global_page_state(NR_SHMEM); + + free += get_nr_swap_pages(); /* * Any slabs which are created with the @@ -125,34 +165,18 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) free += global_page_state(NR_SLAB_RECLAIMABLE); /* - * Leave the last 3% for root - */ - if (!cap_sys_admin) - free -= free / 32; - - if (free > pages) - return 0; - - /* - * nr_free_pages() is very expensive on large systems, - * only call if we're about to fail. - */ - n = nr_free_pages(); - - /* * Leave reserved pages. The pages are not for anonymous pages. */ - if (n <= totalreserve_pages) + if (free <= totalreserve_pages) goto error; else - n -= totalreserve_pages; + free -= totalreserve_pages; /* - * Leave the last 3% for root + * Reserve some for root */ if (!cap_sys_admin) - n -= n / 32; - free += n; + free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); if (free > pages) return 0; @@ -160,24 +184,22 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) goto error; } - allowed = (totalram_pages - hugetlb_total_pages()) - * sysctl_overcommit_ratio / 100; + allowed = vm_commit_limit(); /* - * Leave the last 3% for root + * Reserve some for root */ if (!cap_sys_admin) - allowed -= allowed / 32; - allowed += total_swap_pages; - - /* Don't let a single process grow too big: - leave 3% of the size of this process for other processes */ - allowed -= mm->total_vm / 32; + allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); /* - * cast `allowed' as a signed long because vm_committed_space - * sometimes has a negative value + * Don't let a single process grow so big a user can't recover */ - if (atomic_read(&vm_committed_space) < (long)allowed) + if (mm) { + reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); + allowed -= min(mm->total_vm / 32, reserve); + } + + if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; error: vm_unacct_memory(pages); @@ -186,26 +208,26 @@ error: } /* - * Requires inode->i_mapping->i_mmap_lock + * Requires inode->i_mapping->i_mmap_mutex */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) { if (vma->vm_flags & VM_DENYWRITE) - atomic_inc(&file->f_path.dentry->d_inode->i_writecount); + atomic_inc(&file_inode(file)->i_writecount); if (vma->vm_flags & VM_SHARED) mapping->i_mmap_writable--; flush_dcache_mmap_lock(mapping); if (unlikely(vma->vm_flags & VM_NONLINEAR)) - list_del_init(&vma->shared.vm_set.list); + list_del_init(&vma->shared.nonlinear); else - vma_prio_tree_remove(vma, &mapping->i_mmap); + vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* - * Unlink a file-based vm structure from its prio_tree, to hide + * Unlink a file-based vm structure from its interval tree, to hide * vma from rmap and vmtruncate before freeing its page tables. */ void unlink_file_vma(struct vm_area_struct *vma) @@ -214,9 +236,9 @@ void unlink_file_vma(struct vm_area_struct *vma) if (file) { struct address_space *mapping = file->f_mapping; - spin_lock(&mapping->i_mmap_lock); + mutex_lock(&mapping->i_mmap_mutex); __remove_shared_vm_struct(vma, file, mapping); - spin_unlock(&mapping->i_mmap_lock); + mutex_unlock(&mapping->i_mmap_mutex); } } @@ -232,20 +254,37 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) vma->vm_ops->close(vma); if (vma->vm_file) fput(vma->vm_file); - mpol_free(vma_policy(vma)); + mpol_put(vma_policy(vma)); kmem_cache_free(vm_area_cachep, vma); return next; } -asmlinkage unsigned long sys_brk(unsigned long brk) +static unsigned long do_brk(unsigned long addr, unsigned long len); + +SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long rlim, retval; unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; + unsigned long min_brk; + bool populate; down_write(&mm->mmap_sem); - if (brk < mm->start_brk) +#ifdef CONFIG_COMPAT_BRK + /* + * CONFIG_COMPAT_BRK can still be overridden by setting + * randomize_va_space to 2, which will still cause mm->start_brk + * to be arbitrarily shifted + */ + if (current->brk_randomized) + min_brk = mm->start_brk; + else + min_brk = mm->end_data; +#else + min_brk = mm->start_brk; +#endif + if (brk < min_brk) goto out; /* @@ -254,7 +293,7 @@ asmlinkage unsigned long sys_brk(unsigned long brk) * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ - rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur; + rlim = rlimit(RLIMIT_DATA); if (rlim < RLIM_INFINITY && (brk - mm->start_brk) + (mm->end_data - mm->start_data) > rlim) goto out; @@ -278,75 +317,217 @@ asmlinkage unsigned long sys_brk(unsigned long brk) /* Ok, looks good - let it rip. */ if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk) goto out; + set_brk: mm->brk = brk; + populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; + up_write(&mm->mmap_sem); + if (populate) + mm_populate(oldbrk, newbrk - oldbrk); + return brk; + out: retval = mm->brk; up_write(&mm->mmap_sem); return retval; } -#ifdef DEBUG_MM_RB +static long vma_compute_subtree_gap(struct vm_area_struct *vma) +{ + unsigned long max, subtree_gap; + max = vma->vm_start; + if (vma->vm_prev) + max -= vma->vm_prev->vm_end; + if (vma->vm_rb.rb_left) { + subtree_gap = rb_entry(vma->vm_rb.rb_left, + struct vm_area_struct, vm_rb)->rb_subtree_gap; + if (subtree_gap > max) + max = subtree_gap; + } + if (vma->vm_rb.rb_right) { + subtree_gap = rb_entry(vma->vm_rb.rb_right, + struct vm_area_struct, vm_rb)->rb_subtree_gap; + if (subtree_gap > max) + max = subtree_gap; + } + return max; +} + +#ifdef CONFIG_DEBUG_VM_RB static int browse_rb(struct rb_root *root) { - int i = 0, j; + int i = 0, j, bug = 0; struct rb_node *nd, *pn = NULL; unsigned long prev = 0, pend = 0; for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); - if (vma->vm_start < prev) - printk("vm_start %lx prev %lx\n", vma->vm_start, prev), i = -1; - if (vma->vm_start < pend) - printk("vm_start %lx pend %lx\n", vma->vm_start, pend); - if (vma->vm_start > vma->vm_end) - printk("vm_end %lx < vm_start %lx\n", vma->vm_end, vma->vm_start); + if (vma->vm_start < prev) { + pr_info("vm_start %lx prev %lx\n", vma->vm_start, prev); + bug = 1; + } + if (vma->vm_start < pend) { + pr_info("vm_start %lx pend %lx\n", vma->vm_start, pend); + bug = 1; + } + if (vma->vm_start > vma->vm_end) { + pr_info("vm_end %lx < vm_start %lx\n", + vma->vm_end, vma->vm_start); + bug = 1; + } + if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) { + pr_info("free gap %lx, correct %lx\n", + vma->rb_subtree_gap, + vma_compute_subtree_gap(vma)); + bug = 1; + } i++; pn = nd; prev = vma->vm_start; pend = vma->vm_end; } j = 0; - for (nd = pn; nd; nd = rb_prev(nd)) { + for (nd = pn; nd; nd = rb_prev(nd)) j++; + if (i != j) { + pr_info("backwards %d, forwards %d\n", j, i); + bug = 1; } - if (i != j) - printk("backwards %d, forwards %d\n", j, i), i = 0; - return i; + return bug ? -1 : i; } -void validate_mm(struct mm_struct *mm) +static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore) +{ + struct rb_node *nd; + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + struct vm_area_struct *vma; + vma = rb_entry(nd, struct vm_area_struct, vm_rb); + BUG_ON(vma != ignore && + vma->rb_subtree_gap != vma_compute_subtree_gap(vma)); + } +} + +static void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; - struct vm_area_struct *tmp = mm->mmap; - while (tmp) { - tmp = tmp->vm_next; + unsigned long highest_address = 0; + struct vm_area_struct *vma = mm->mmap; + while (vma) { + struct anon_vma_chain *avc; + vma_lock_anon_vma(vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_verify(avc); + vma_unlock_anon_vma(vma); + highest_address = vma->vm_end; + vma = vma->vm_next; i++; } - if (i != mm->map_count) - printk("map_count %d vm_next %d\n", mm->map_count, i), bug = 1; + if (i != mm->map_count) { + pr_info("map_count %d vm_next %d\n", mm->map_count, i); + bug = 1; + } + if (highest_address != mm->highest_vm_end) { + pr_info("mm->highest_vm_end %lx, found %lx\n", + mm->highest_vm_end, highest_address); + bug = 1; + } i = browse_rb(&mm->mm_rb); - if (i != mm->map_count) - printk("map_count %d rb %d\n", mm->map_count, i), bug = 1; + if (i != mm->map_count) { + pr_info("map_count %d rb %d\n", mm->map_count, i); + bug = 1; + } BUG_ON(bug); } #else +#define validate_mm_rb(root, ignore) do { } while (0) #define validate_mm(mm) do { } while (0) #endif -static struct vm_area_struct * -find_vma_prepare(struct mm_struct *mm, unsigned long addr, - struct vm_area_struct **pprev, struct rb_node ***rb_link, - struct rb_node ** rb_parent) +RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb, + unsigned long, rb_subtree_gap, vma_compute_subtree_gap) + +/* + * Update augmented rbtree rb_subtree_gap values after vma->vm_start or + * vma->vm_prev->vm_end values changed, without modifying the vma's position + * in the rbtree. + */ +static void vma_gap_update(struct vm_area_struct *vma) { - struct vm_area_struct * vma; - struct rb_node ** __rb_link, * __rb_parent, * rb_prev; + /* + * As it turns out, RB_DECLARE_CALLBACKS() already created a callback + * function that does exacltly what we want. + */ + vma_gap_callbacks_propagate(&vma->vm_rb, NULL); +} + +static inline void vma_rb_insert(struct vm_area_struct *vma, + struct rb_root *root) +{ + /* All rb_subtree_gap values must be consistent prior to insertion */ + validate_mm_rb(root, NULL); + + rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks); +} + +static void vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) +{ + /* + * All rb_subtree_gap values must be consistent prior to erase, + * with the possible exception of the vma being erased. + */ + validate_mm_rb(root, vma); + + /* + * Note rb_erase_augmented is a fairly large inline function, + * so make sure we instantiate it only once with our desired + * augmented rbtree callbacks. + */ + rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks); +} + +/* + * vma has some anon_vma assigned, and is already inserted on that + * anon_vma's interval trees. + * + * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the + * vma must be removed from the anon_vma's interval trees using + * anon_vma_interval_tree_pre_update_vma(). + * + * After the update, the vma will be reinserted using + * anon_vma_interval_tree_post_update_vma(). + * + * The entire update must be protected by exclusive mmap_sem and by + * the root anon_vma's mutex. + */ +static inline void +anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc; + + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); +} + +static inline void +anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc; + + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); +} + +static int find_vma_links(struct mm_struct *mm, unsigned long addr, + unsigned long end, struct vm_area_struct **pprev, + struct rb_node ***rb_link, struct rb_node **rb_parent) +{ + struct rb_node **__rb_link, *__rb_parent, *rb_prev; __rb_link = &mm->mm_rb.rb_node; rb_prev = __rb_parent = NULL; - vma = NULL; while (*__rb_link) { struct vm_area_struct *vma_tmp; @@ -355,9 +536,9 @@ find_vma_prepare(struct mm_struct *mm, unsigned long addr, vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb); if (vma_tmp->vm_end > addr) { - vma = vma_tmp; - if (vma_tmp->vm_start <= addr) - return vma; + /* Fail if an existing vma overlaps the area */ + if (vma_tmp->vm_start < end) + return -ENOMEM; __rb_link = &__rb_parent->rb_left; } else { rb_prev = __rb_parent; @@ -370,43 +551,71 @@ find_vma_prepare(struct mm_struct *mm, unsigned long addr, *pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb); *rb_link = __rb_link; *rb_parent = __rb_parent; - return vma; + return 0; } -static inline void -__vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, - struct vm_area_struct *prev, struct rb_node *rb_parent) +static unsigned long count_vma_pages_range(struct mm_struct *mm, + unsigned long addr, unsigned long end) { - if (prev) { - vma->vm_next = prev->vm_next; - prev->vm_next = vma; - } else { - mm->mmap = vma; - if (rb_parent) - vma->vm_next = rb_entry(rb_parent, - struct vm_area_struct, vm_rb); - else - vma->vm_next = NULL; + unsigned long nr_pages = 0; + struct vm_area_struct *vma; + + /* Find first overlaping mapping */ + vma = find_vma_intersection(mm, addr, end); + if (!vma) + return 0; + + nr_pages = (min(end, vma->vm_end) - + max(addr, vma->vm_start)) >> PAGE_SHIFT; + + /* Iterate over the rest of the overlaps */ + for (vma = vma->vm_next; vma; vma = vma->vm_next) { + unsigned long overlap_len; + + if (vma->vm_start > end) + break; + + overlap_len = min(end, vma->vm_end) - vma->vm_start; + nr_pages += overlap_len >> PAGE_SHIFT; } + + return nr_pages; } void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, struct rb_node **rb_link, struct rb_node *rb_parent) { + /* Update tracking information for the gap following the new vma. */ + if (vma->vm_next) + vma_gap_update(vma->vm_next); + else + mm->highest_vm_end = vma->vm_end; + + /* + * vma->vm_prev wasn't known when we followed the rbtree to find the + * correct insertion point for that vma. As a result, we could not + * update the vma vm_rb parents rb_subtree_gap values on the way down. + * So, we first insert the vma with a zero rb_subtree_gap value + * (to be consistent with what we did on the way down), and then + * immediately update the gap to the correct value. Finally we + * rebalance the rbtree after all augmented values have been set. + */ rb_link_node(&vma->vm_rb, rb_parent, rb_link); - rb_insert_color(&vma->vm_rb, &mm->mm_rb); + vma->rb_subtree_gap = 0; + vma_gap_update(vma); + vma_rb_insert(vma, &mm->mm_rb); } -static inline void __vma_link_file(struct vm_area_struct *vma) +static void __vma_link_file(struct vm_area_struct *vma) { - struct file * file; + struct file *file; file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; if (vma->vm_flags & VM_DENYWRITE) - atomic_dec(&file->f_path.dentry->d_inode->i_writecount); + atomic_dec(&file_inode(file)->i_writecount); if (vma->vm_flags & VM_SHARED) mapping->i_mmap_writable++; @@ -414,7 +623,7 @@ static inline void __vma_link_file(struct vm_area_struct *vma) if (unlikely(vma->vm_flags & VM_NONLINEAR)) vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); else - vma_prio_tree_insert(vma, &mapping->i_mmap); + vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } @@ -426,7 +635,6 @@ __vma_link(struct mm_struct *mm, struct vm_area_struct *vma, { __vma_link_list(mm, vma, prev, rb_parent); __vma_link_rb(mm, vma, rb_link, rb_parent); - __anon_vma_link(vma); } static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, @@ -435,39 +643,33 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, { struct address_space *mapping = NULL; - if (vma->vm_file) + if (vma->vm_file) { mapping = vma->vm_file->f_mapping; - - if (mapping) { - spin_lock(&mapping->i_mmap_lock); - vma->vm_truncate_count = mapping->truncate_count; + mutex_lock(&mapping->i_mmap_mutex); } - anon_vma_lock(vma); __vma_link(mm, vma, prev, rb_link, rb_parent); __vma_link_file(vma); - anon_vma_unlock(vma); if (mapping) - spin_unlock(&mapping->i_mmap_lock); + mutex_unlock(&mapping->i_mmap_mutex); mm->map_count++; validate_mm(mm); } /* - * Helper for vma_adjust in the split_vma insert case: - * insert vm structure into list and rbtree and anon_vma, - * but it has already been inserted into prio_tree earlier. + * Helper for vma_adjust() in the split_vma insert case: insert a vma into the + * mm's list and rbtree. It has already been inserted into the interval tree. */ -static void -__insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma) +static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { - struct vm_area_struct * __vma, * prev; - struct rb_node ** rb_link, * rb_parent; + struct vm_area_struct *prev; + struct rb_node **rb_link, *rb_parent; - __vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent); - BUG_ON(__vma && __vma->vm_start < vma->vm_end); + if (find_vma_links(mm, vma->vm_start, vma->vm_end, + &prev, &rb_link, &rb_parent)) + BUG(); __vma_link(mm, vma, prev, rb_link, rb_parent); mm->map_count++; } @@ -476,10 +678,15 @@ static inline void __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev) { - prev->vm_next = vma->vm_next; - rb_erase(&vma->vm_rb, &mm->mm_rb); - if (mm->mmap_cache == vma) - mm->mmap_cache = prev; + struct vm_area_struct *next; + + vma_rb_erase(vma, &mm->mm_rb); + prev->vm_next = next = vma->vm_next; + if (next) + next->vm_prev = prev; + + /* Kill the cache */ + vmacache_invalidate(mm); } /* @@ -489,20 +696,23 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ -void vma_adjust(struct vm_area_struct *vma, unsigned long start, +int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next = vma->vm_next; struct vm_area_struct *importer = NULL; struct address_space *mapping = NULL; - struct prio_tree_root *root = NULL; - struct file *file = vma->vm_file; + struct rb_root *root = NULL; struct anon_vma *anon_vma = NULL; + struct file *file = vma->vm_file; + bool start_changed = false, end_changed = false; long adjust_next = 0; int remove_next = 0; if (next && !insert) { + struct vm_area_struct *exporter = NULL; + if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and @@ -510,7 +720,7 @@ void vma_adjust(struct vm_area_struct *vma, unsigned long start, */ again: remove_next = 1 + (end > next->vm_end); end = next->vm_end; - anon_vma = next->anon_vma; + exporter = next; importer = vma; } else if (end > next->vm_start) { /* @@ -518,7 +728,7 @@ again: remove_next = 1 + (end > next->vm_end); * mprotect case 5 shifting the boundary up. */ adjust_next = (end - next->vm_start) >> PAGE_SHIFT; - anon_vma = next->anon_vma; + exporter = next; importer = vma; } else if (end < vma->vm_end) { /* @@ -527,28 +737,37 @@ again: remove_next = 1 + (end > next->vm_end); * mprotect case 4 shifting the boundary down. */ adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT); - anon_vma = next->anon_vma; + exporter = vma; importer = next; } + + /* + * Easily overlooked: when mprotect shifts the boundary, + * make sure the expanding vma has anon_vma set if the + * shrinking vma had, to cover any anon pages imported. + */ + if (exporter && exporter->anon_vma && !importer->anon_vma) { + if (anon_vma_clone(importer, exporter)) + return -ENOMEM; + importer->anon_vma = exporter->anon_vma; + } } if (file) { mapping = file->f_mapping; - if (!(vma->vm_flags & VM_NONLINEAR)) + if (!(vma->vm_flags & VM_NONLINEAR)) { root = &mapping->i_mmap; - spin_lock(&mapping->i_mmap_lock); - if (importer && - vma->vm_truncate_count != next->vm_truncate_count) { - /* - * unmap_mapping_range might be in progress: - * ensure that the expanding vma is rescanned. - */ - importer->vm_truncate_count = 0; + uprobe_munmap(vma, vma->vm_start, vma->vm_end); + + if (adjust_next) + uprobe_munmap(next, next->vm_start, + next->vm_end); } + + mutex_lock(&mapping->i_mmap_mutex); if (insert) { - insert->vm_truncate_count = vma->vm_truncate_count; /* - * Put into prio_tree now, so instantiated pages + * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. @@ -557,34 +776,35 @@ again: remove_next = 1 + (end > next->vm_end); } } - /* - * When changing only vma->vm_end, we don't really need - * anon_vma lock: but is that case worth optimizing out? - */ - if (vma->anon_vma) - anon_vma = vma->anon_vma; + vma_adjust_trans_huge(vma, start, end, adjust_next); + + anon_vma = vma->anon_vma; + if (!anon_vma && adjust_next) + anon_vma = next->anon_vma; if (anon_vma) { - spin_lock(&anon_vma->lock); - /* - * Easily overlooked: when mprotect shifts the boundary, - * make sure the expanding vma has anon_vma set if the - * shrinking vma had, to cover any anon pages imported. - */ - if (importer && !importer->anon_vma) { - importer->anon_vma = anon_vma; - __anon_vma_link(importer); - } + VM_BUG_ON(adjust_next && next->anon_vma && + anon_vma != next->anon_vma); + anon_vma_lock_write(anon_vma); + anon_vma_interval_tree_pre_update_vma(vma); + if (adjust_next) + anon_vma_interval_tree_pre_update_vma(next); } if (root) { flush_dcache_mmap_lock(mapping); - vma_prio_tree_remove(vma, root); + vma_interval_tree_remove(vma, root); if (adjust_next) - vma_prio_tree_remove(next, root); + vma_interval_tree_remove(next, root); } - vma->vm_start = start; - vma->vm_end = end; + if (start != vma->vm_start) { + vma->vm_start = start; + start_changed = true; + } + if (end != vma->vm_end) { + vma->vm_end = end; + end_changed = true; + } vma->vm_pgoff = pgoff; if (adjust_next) { next->vm_start += adjust_next << PAGE_SHIFT; @@ -593,8 +813,8 @@ again: remove_next = 1 + (end > next->vm_end); if (root) { if (adjust_next) - vma_prio_tree_insert(next, root); - vma_prio_tree_insert(vma, root); + vma_interval_tree_insert(next, root); + vma_interval_tree_insert(vma, root); flush_dcache_mmap_unlock(mapping); } @@ -606,8 +826,6 @@ again: remove_next = 1 + (end > next->vm_end); __vma_unlink(mm, next, vma); if (file) __remove_shared_vm_struct(next, file, mapping); - if (next->anon_vma) - __anon_vma_merge(vma, next); } else if (insert) { /* * split_vma has split insert from vma, and needs @@ -615,43 +833,80 @@ again: remove_next = 1 + (end > next->vm_end); * (it may either follow vma or precede it). */ __insert_vm_struct(mm, insert); + } else { + if (start_changed) + vma_gap_update(vma); + if (end_changed) { + if (!next) + mm->highest_vm_end = end; + else if (!adjust_next) + vma_gap_update(next); + } } - if (anon_vma) - spin_unlock(&anon_vma->lock); + if (anon_vma) { + anon_vma_interval_tree_post_update_vma(vma); + if (adjust_next) + anon_vma_interval_tree_post_update_vma(next); + anon_vma_unlock_write(anon_vma); + } if (mapping) - spin_unlock(&mapping->i_mmap_lock); + mutex_unlock(&mapping->i_mmap_mutex); + + if (root) { + uprobe_mmap(vma); + + if (adjust_next) + uprobe_mmap(next); + } if (remove_next) { - if (file) + if (file) { + uprobe_munmap(next, next->vm_start, next->vm_end); fput(file); + } + if (next->anon_vma) + anon_vma_merge(vma, next); mm->map_count--; - mpol_free(vma_policy(next)); + mpol_put(vma_policy(next)); kmem_cache_free(vm_area_cachep, next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter * up the code too much to do both in one go. */ - if (remove_next == 2) { - next = vma->vm_next; + next = vma->vm_next; + if (remove_next == 2) goto again; - } + else if (next) + vma_gap_update(next); + else + mm->highest_vm_end = end; } + if (insert && file) + uprobe_mmap(insert); validate_mm(mm); + + return 0; } /* * If the vma has a ->close operation then the driver probably needs to release * per-vma resources, so we don't attempt to merge those. */ -#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP) - static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags) { - if (vma->vm_flags != vm_flags) + /* + * VM_SOFTDIRTY should not prevent from VMA merging, if we + * match the flags but dirty bit -- the caller should mark + * merged VMA as dirty. If dirty bit won't be excluded from + * comparison, we increase pressue on the memory system forcing + * the kernel to generate new VMAs when old one could be + * extended instead. + */ + if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) return 0; if (vma->vm_file != file) return 0; @@ -661,9 +916,17 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, } static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, - struct anon_vma *anon_vma2) + struct anon_vma *anon_vma2, + struct vm_area_struct *vma) { - return !anon_vma1 || !anon_vma2 || (anon_vma1 == anon_vma2); + /* + * The list_is_singular() test is to avoid merging VMA cloned from + * parents. This can improve scalability caused by anon_vma lock. + */ + if ((!anon_vma1 || !anon_vma2) && (!vma || + list_is_singular(&vma->anon_vma_chain))) + return 1; + return anon_vma1 == anon_vma2; } /* @@ -682,7 +945,7 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff) { if (is_mergeable_vma(vma, file, vm_flags) && - is_mergeable_anon_vma(anon_vma, vma->anon_vma)) { + is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; } @@ -701,9 +964,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff) { if (is_mergeable_vma(vma, file, vm_flags) && - is_mergeable_anon_vma(anon_vma, vma->anon_vma)) { + is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; - vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + vm_pglen = vma_pages(vma); if (vma->vm_pgoff + vm_pglen == vm_pgoff) return 1; } @@ -747,6 +1010,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; + int err; /* * We later require that vma->vm_flags == vm_flags, @@ -778,13 +1042,16 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen) && is_mergeable_anon_vma(prev->anon_vma, - next->anon_vma)) { + next->anon_vma, NULL)) { /* cases 1, 6 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL); } else /* cases 2, 5, 7 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, end, prev->vm_pgoff, NULL); + if (err) + return NULL; + khugepaged_enter_vma_merge(prev); return prev; } @@ -796,11 +1063,14 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen)) { if (prev && addr < prev->vm_end) /* case 4 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL); else /* cases 3, 8 */ - vma_adjust(area, addr, next->vm_end, + err = vma_adjust(area, addr, next->vm_end, next->vm_pgoff - pglen, NULL); + if (err) + return NULL; + khugepaged_enter_vma_merge(area); return area; } @@ -808,6 +1078,61 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, } /* + * Rough compatbility check to quickly see if it's even worth looking + * at sharing an anon_vma. + * + * They need to have the same vm_file, and the flags can only differ + * in things that mprotect may change. + * + * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that + * we can merge the two vma's. For example, we refuse to merge a vma if + * there is a vm_ops->close() function, because that indicates that the + * driver is doing some kind of reference counting. But that doesn't + * really matter for the anon_vma sharing case. + */ +static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) +{ + return a->vm_end == b->vm_start && + mpol_equal(vma_policy(a), vma_policy(b)) && + a->vm_file == b->vm_file && + !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC|VM_SOFTDIRTY)) && + b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); +} + +/* + * Do some basic sanity checking to see if we can re-use the anon_vma + * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be + * the same as 'old', the other will be the new one that is trying + * to share the anon_vma. + * + * NOTE! This runs with mm_sem held for reading, so it is possible that + * the anon_vma of 'old' is concurrently in the process of being set up + * by another page fault trying to merge _that_. But that's ok: if it + * is being set up, that automatically means that it will be a singleton + * acceptable for merging, so we can do all of this optimistically. But + * we do that ACCESS_ONCE() to make sure that we never re-load the pointer. + * + * IOW: that the "list_is_singular()" test on the anon_vma_chain only + * matters for the 'stable anon_vma' case (ie the thing we want to avoid + * is to return an anon_vma that is "complex" due to having gone through + * a fork). + * + * We also make sure that the two vma's are compatible (adjacent, + * and with the same memory policies). That's all stable, even with just + * a read lock on the mm_sem. + */ +static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) +{ + if (anon_vma_compatible(a, b)) { + struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma); + + if (anon_vma && list_is_singular(&old->anon_vma_chain)) + return anon_vma; + } + return NULL; +} + +/* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive @@ -817,48 +1142,24 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { + struct anon_vma *anon_vma; struct vm_area_struct *near; - unsigned long vm_flags; near = vma->vm_next; if (!near) goto try_prev; - /* - * Since only mprotect tries to remerge vmas, match flags - * which might be mprotected into each other later on. - * Neither mlock nor madvise tries to remerge at present, - * so leave their flags as obstructing a merge. - */ - vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC); - vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC); - - if (near->anon_vma && vma->vm_end == near->vm_start && - mpol_equal(vma_policy(vma), vma_policy(near)) && - can_vma_merge_before(near, vm_flags, - NULL, vma->vm_file, vma->vm_pgoff + - ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT))) - return near->anon_vma; + anon_vma = reusable_anon_vma(near, vma, near); + if (anon_vma) + return anon_vma; try_prev: - /* - * It is potentially slow to have to call find_vma_prev here. - * But it's only on the first write fault on the vma, not - * every time, and we could devise a way to avoid it later - * (e.g. stash info in next's anon_vma_node when assigning - * an anon_vma, or when trying vma_merge). Another time. - */ - BUG_ON(find_vma_prev(vma->vm_mm, vma->vm_start, &near) != vma); + near = vma->vm_prev; if (!near) goto none; - vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC); - vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC); - - if (near->anon_vma && near->vm_end == vma->vm_start && - mpol_equal(vma_policy(near), vma_policy(vma)) && - can_vma_merge_after(near, vm_flags, - NULL, vma->vm_file, vma->vm_pgoff)) - return near->anon_vma; + anon_vma = reusable_anon_vma(near, near, vma); + if (anon_vma) + return anon_vma; none: /* * There's no absolute need to look only at touching neighbours: @@ -878,31 +1179,61 @@ void vm_stat_account(struct mm_struct *mm, unsigned long flags, const unsigned long stack_flags = VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN); + mm->total_vm += pages; + if (file) { mm->shared_vm += pages; if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC) mm->exec_vm += pages; } else if (flags & stack_flags) mm->stack_vm += pages; - if (flags & (VM_RESERVED|VM_IO)) - mm->reserved_vm += pages; } #endif /* CONFIG_PROC_FS */ /* - * The caller must hold down_write(current->mm->mmap_sem). + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} + +static inline int mlock_future_check(struct mm_struct *mm, + unsigned long flags, + unsigned long len) +{ + unsigned long locked, lock_limit; -unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, + /* mlock MCL_FUTURE? */ + if (flags & VM_LOCKED) { + locked = len >> PAGE_SHIFT; + locked += mm->locked_vm; + lock_limit = rlimit(RLIMIT_MEMLOCK); + lock_limit >>= PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) + return -EAGAIN; + } + return 0; +} + +/* + * The caller must hold down_write(¤t->mm->mmap_sem). + */ + +unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, - unsigned long flags, unsigned long pgoff) + unsigned long flags, unsigned long pgoff, + unsigned long *populate) { struct mm_struct * mm = current->mm; - struct inode *inode; - unsigned int vm_flags; - int error; - int accountable = 1; - unsigned long reqprot = prot; + vm_flags_t vm_flags; + + *populate = 0; /* * Does the application expect PROT_READ to imply PROT_EXEC? @@ -920,13 +1251,9 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); - error = arch_mmap_check(addr, len, flags); - if (error) - return error; - /* Careful about overflows.. */ len = PAGE_ALIGN(len); - if (!len || len > TASK_SIZE) + if (!len) return -ENOMEM; /* offset overflow? */ @@ -951,25 +1278,16 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; - if (flags & MAP_LOCKED) { + if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; - vm_flags |= VM_LOCKED; - } - /* mlock MCL_FUTURE? */ - if (vm_flags & VM_LOCKED) { - unsigned long locked, lock_limit; - locked = len >> PAGE_SHIFT; - locked += mm->locked_vm; - lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; - lock_limit >>= PAGE_SHIFT; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - return -EAGAIN; - } - inode = file ? file->f_path.dentry->d_inode : NULL; + if (mlock_future_check(mm, vm_flags, len)) + return -EAGAIN; if (file) { + struct inode *inode = file_inode(file); + switch (flags & MAP_TYPE) { case MAP_SHARED: if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE)) @@ -985,7 +1303,7 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, /* * Make sure there are no mandatory locks on the file. */ - if (locks_verify_locked(inode)) + if (locks_verify_locked(file)) return -EAGAIN; vm_flags |= VM_SHARED | VM_MAYSHARE; @@ -1001,11 +1319,11 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, return -EPERM; vm_flags &= ~VM_MAYEXEC; } - if (is_file_hugepages(file)) - accountable = 0; - if (!file->f_op || !file->f_op->mmap) + if (!file->f_op->mmap) return -ENODEV; + if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) + return -EINVAL; break; default: @@ -1014,6 +1332,12 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, } else { switch (flags & MAP_TYPE) { case MAP_SHARED: + if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) + return -EINVAL; + /* + * Ignore pgoff. + */ + pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; case MAP_PRIVATE: @@ -1027,14 +1351,101 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, } } - error = security_file_mmap(file, reqprot, prot, flags, addr, 0); - if (error) - return error; + /* + * Set 'VM_NORESERVE' if we should not account for the + * memory use of this mapping. + */ + if (flags & MAP_NORESERVE) { + /* We honor MAP_NORESERVE if allowed to overcommit */ + if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) + vm_flags |= VM_NORESERVE; + + /* hugetlb applies strict overcommit unless MAP_NORESERVE */ + if (file && is_file_hugepages(file)) + vm_flags |= VM_NORESERVE; + } + + addr = mmap_region(file, addr, len, vm_flags, pgoff); + if (!IS_ERR_VALUE(addr) && + ((vm_flags & VM_LOCKED) || + (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) + *populate = len; + return addr; +} + +SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, pgoff) +{ + struct file *file = NULL; + unsigned long retval = -EBADF; + + if (!(flags & MAP_ANONYMOUS)) { + audit_mmap_fd(fd, flags); + file = fget(fd); + if (!file) + goto out; + if (is_file_hugepages(file)) + len = ALIGN(len, huge_page_size(hstate_file(file))); + retval = -EINVAL; + if (unlikely(flags & MAP_HUGETLB && !is_file_hugepages(file))) + goto out_fput; + } else if (flags & MAP_HUGETLB) { + struct user_struct *user = NULL; + struct hstate *hs; + + hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & SHM_HUGE_MASK); + if (!hs) + return -EINVAL; + + len = ALIGN(len, huge_page_size(hs)); + /* + * VM_NORESERVE is used because the reservations will be + * taken when vm_ops->mmap() is called + * A dummy user value is used because we are not locking + * memory so no accounting is necessary + */ + file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, + VM_NORESERVE, + &user, HUGETLB_ANONHUGE_INODE, + (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); + if (IS_ERR(file)) + return PTR_ERR(file); + } + + flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + + retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); +out_fput: + if (file) + fput(file); +out: + return retval; +} + +#ifdef __ARCH_WANT_SYS_OLD_MMAP +struct mmap_arg_struct { + unsigned long addr; + unsigned long len; + unsigned long prot; + unsigned long flags; + unsigned long fd; + unsigned long offset; +}; + +SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) +{ + struct mmap_arg_struct a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + if (a.offset & ~PAGE_MASK) + return -EINVAL; - return mmap_region(file, addr, len, flags, vm_flags, pgoff, - accountable); + return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + a.offset >> PAGE_SHIFT); } -EXPORT_SYMBOL(do_mmap_pgoff); +#endif /* __ARCH_WANT_SYS_OLD_MMAP */ /* * Some shared mappigns will want the pages marked read-only @@ -1044,7 +1455,7 @@ EXPORT_SYMBOL(do_mmap_pgoff); */ int vma_wants_writenotify(struct vm_area_struct *vma) { - unsigned int vm_flags = vma->vm_flags; + vm_flags_t vm_flags = vma->vm_flags; /* If it was private or non-writable, the write bit is already clear */ if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED))) @@ -1060,7 +1471,7 @@ int vma_wants_writenotify(struct vm_area_struct *vma) return 0; /* Specialty mapping? */ - if (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) + if (vm_flags & VM_PFNMAP) return 0; /* Can the mapping track the dirty pages? */ @@ -1068,58 +1479,72 @@ int vma_wants_writenotify(struct vm_area_struct *vma) mapping_cap_account_dirty(vma->vm_file->f_mapping); } +/* + * We account for memory if it's a private writeable mapping, + * not hugepages and VM_NORESERVE wasn't set. + */ +static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) +{ + /* + * hugetlb has its own accounting separate from the core VM + * VM_HUGETLB may not be set yet so we cannot check for that flag. + */ + if (file && is_file_hugepages(file)) + return 0; + + return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; +} unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, unsigned long flags, - unsigned int vm_flags, unsigned long pgoff, - int accountable) + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - int correct_wcount = 0; int error; struct rb_node **rb_link, *rb_parent; unsigned long charged = 0; - struct inode *inode = file ? file->f_path.dentry->d_inode : NULL; + + /* Check against address space limit. */ + if (!may_expand_vm(mm, len >> PAGE_SHIFT)) { + unsigned long nr_pages; + + /* + * MAP_FIXED may remove pages of mappings that intersects with + * requested mapping. Account for the pages it would unmap. + */ + if (!(vm_flags & MAP_FIXED)) + return -ENOMEM; + + nr_pages = count_vma_pages_range(mm, addr, addr + len); + + if (!may_expand_vm(mm, (len >> PAGE_SHIFT) - nr_pages)) + return -ENOMEM; + } /* Clear old maps */ error = -ENOMEM; munmap_back: - vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent); - if (vma && vma->vm_start < addr + len) { + if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { if (do_munmap(mm, addr, len)) return -ENOMEM; goto munmap_back; } - /* Check against address space limit. */ - if (!may_expand_vm(mm, len >> PAGE_SHIFT)) - return -ENOMEM; - - if (accountable && (!(flags & MAP_NORESERVE) || - sysctl_overcommit_memory == OVERCOMMIT_NEVER)) { - if (vm_flags & VM_SHARED) { - /* Check memory availability in shmem_file_setup? */ - vm_flags |= VM_ACCOUNT; - } else if (vm_flags & VM_WRITE) { - /* - * Private writable mapping: check memory availability - */ - charged = len >> PAGE_SHIFT; - if (security_vm_enough_memory(charged)) - return -ENOMEM; - vm_flags |= VM_ACCOUNT; - } + /* + * Private writable mapping: check memory availability + */ + if (accountable_mapping(file, vm_flags)) { + charged = len >> PAGE_SHIFT; + if (security_vm_enough_memory_mm(mm, charged)) + return -ENOMEM; + vm_flags |= VM_ACCOUNT; } /* - * Can we just expand an old private anonymous mapping? - * The VM_SHARED test is necessary because shmem_zero_setup - * will create the file object for a shared anonymous map below. + * Can we just expand an old mapping? */ - if (!file && !(vm_flags & VM_SHARED) && - vma_merge(mm, prev, addr, addr + len, vm_flags, - NULL, NULL, pgoff, NULL)) + vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL); + if (vma) goto out; /* @@ -1139,77 +1564,85 @@ munmap_back: vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; + INIT_LIST_HEAD(&vma->anon_vma_chain); if (file) { - error = -EINVAL; - if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) - goto free_vma; if (vm_flags & VM_DENYWRITE) { error = deny_write_access(file); if (error) goto free_vma; - correct_wcount = 1; } - vma->vm_file = file; - get_file(file); + vma->vm_file = get_file(file); error = file->f_op->mmap(file, vma); if (error) goto unmap_and_free_vma; + + /* Can addr have changed?? + * + * Answer: Yes, several device drivers can do it in their + * f_op->mmap method. -DaveM + * Bug: If addr is changed, prev, rb_link, rb_parent should + * be updated for vma_link() + */ + WARN_ON_ONCE(addr != vma->vm_start); + + addr = vma->vm_start; + vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) goto free_vma; } - /* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform - * shmem_zero_setup (perhaps called through /dev/zero's ->mmap) - * that memory reservation must be checked; but that reservation - * belongs to shared memory object, not to vma: so now clear it. - */ - if ((vm_flags & (VM_SHARED|VM_ACCOUNT)) == (VM_SHARED|VM_ACCOUNT)) - vma->vm_flags &= ~VM_ACCOUNT; - - /* Can addr have changed?? - * - * Answer: Yes, several device drivers can do it in their - * f_op->mmap method. -DaveM - */ - addr = vma->vm_start; - pgoff = vma->vm_pgoff; - vm_flags = vma->vm_flags; + if (vma_wants_writenotify(vma)) { + pgprot_t pprot = vma->vm_page_prot; - if (vma_wants_writenotify(vma)) + /* Can vma->vm_page_prot have changed?? + * + * Answer: Yes, drivers may have changed it in their + * f_op->mmap method. + * + * Ensures that vmas marked as uncached stay that way. + */ vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED); - - if (!file || !vma_merge(mm, prev, addr, vma->vm_end, - vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) { - file = vma->vm_file; - vma_link(mm, vma, prev, rb_link, rb_parent); - if (correct_wcount) - atomic_inc(&inode->i_writecount); - } else { - if (file) { - if (correct_wcount) - atomic_inc(&inode->i_writecount); - fput(file); - } - mpol_free(vma_policy(vma)); - kmem_cache_free(vm_area_cachep, vma); + if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot))) + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); } -out: - mm->total_vm += len >> PAGE_SHIFT; + + vma_link(mm, vma, prev, rb_link, rb_parent); + /* Once vma denies write, undo our temporary denial count */ + if (vm_flags & VM_DENYWRITE) + allow_write_access(file); + file = vma->vm_file; +out: + perf_event_mmap(vma); + vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { - mm->locked_vm += len >> PAGE_SHIFT; - make_pages_present(addr, addr + len); + if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || + vma == get_gate_vma(current->mm))) + mm->locked_vm += (len >> PAGE_SHIFT); + else + vma->vm_flags &= ~VM_LOCKED; } - if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) - make_pages_present(addr, addr + len); + + if (file) + uprobe_mmap(vma); + + /* + * New (or expanded) vma always get soft dirty status. + * Otherwise user-space soft-dirty page tracker won't + * be able to distinguish situation when vma area unmapped, + * then new mapped in-place (which must be aimed as + * a completely new data area). + */ + vma->vm_flags |= VM_SOFTDIRTY; + return addr; unmap_and_free_vma: - if (correct_wcount) - atomic_inc(&inode->i_writecount); + if (vm_flags & VM_DENYWRITE) + allow_write_access(file); vma->vm_file = NULL; fput(file); @@ -1224,6 +1657,206 @@ unacct_error: return error; } +unsigned long unmapped_area(struct vm_unmapped_area_info *info) +{ + /* + * We implement the search by looking for an rbtree node that + * immediately follows a suitable gap. That is, + * - gap_start = vma->vm_prev->vm_end <= info->high_limit - length; + * - gap_end = vma->vm_start >= info->low_limit + length; + * - gap_end - gap_start >= length + */ + + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long length, low_limit, high_limit, gap_start, gap_end; + + /* Adjust search length to account for worst case alignment overhead */ + length = info->length + info->align_mask; + if (length < info->length) + return -ENOMEM; + + /* Adjust search limits by the desired length */ + if (info->high_limit < length) + return -ENOMEM; + high_limit = info->high_limit - length; + + if (info->low_limit > high_limit) + return -ENOMEM; + low_limit = info->low_limit + length; + + /* Check if rbtree root looks promising */ + if (RB_EMPTY_ROOT(&mm->mm_rb)) + goto check_highest; + vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); + if (vma->rb_subtree_gap < length) + goto check_highest; + + while (true) { + /* Visit left subtree if it looks promising */ + gap_end = vma->vm_start; + if (gap_end >= low_limit && vma->vm_rb.rb_left) { + struct vm_area_struct *left = + rb_entry(vma->vm_rb.rb_left, + struct vm_area_struct, vm_rb); + if (left->rb_subtree_gap >= length) { + vma = left; + continue; + } + } + + gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0; +check_current: + /* Check if current node has a suitable gap */ + if (gap_start > high_limit) + return -ENOMEM; + if (gap_end >= low_limit && gap_end - gap_start >= length) + goto found; + + /* Visit right subtree if it looks promising */ + if (vma->vm_rb.rb_right) { + struct vm_area_struct *right = + rb_entry(vma->vm_rb.rb_right, + struct vm_area_struct, vm_rb); + if (right->rb_subtree_gap >= length) { + vma = right; + continue; + } + } + + /* Go back up the rbtree to find next candidate node */ + while (true) { + struct rb_node *prev = &vma->vm_rb; + if (!rb_parent(prev)) + goto check_highest; + vma = rb_entry(rb_parent(prev), + struct vm_area_struct, vm_rb); + if (prev == vma->vm_rb.rb_left) { + gap_start = vma->vm_prev->vm_end; + gap_end = vma->vm_start; + goto check_current; + } + } + } + +check_highest: + /* Check highest gap, which does not precede any rbtree node */ + gap_start = mm->highest_vm_end; + gap_end = ULONG_MAX; /* Only for VM_BUG_ON below */ + if (gap_start > high_limit) + return -ENOMEM; + +found: + /* We found a suitable gap. Clip it with the original low_limit. */ + if (gap_start < info->low_limit) + gap_start = info->low_limit; + + /* Adjust gap address to the desired alignment */ + gap_start += (info->align_offset - gap_start) & info->align_mask; + + VM_BUG_ON(gap_start + info->length > info->high_limit); + VM_BUG_ON(gap_start + info->length > gap_end); + return gap_start; +} + +unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long length, low_limit, high_limit, gap_start, gap_end; + + /* Adjust search length to account for worst case alignment overhead */ + length = info->length + info->align_mask; + if (length < info->length) + return -ENOMEM; + + /* + * Adjust search limits by the desired length. + * See implementation comment at top of unmapped_area(). + */ + gap_end = info->high_limit; + if (gap_end < length) + return -ENOMEM; + high_limit = gap_end - length; + + if (info->low_limit > high_limit) + return -ENOMEM; + low_limit = info->low_limit + length; + + /* Check highest gap, which does not precede any rbtree node */ + gap_start = mm->highest_vm_end; + if (gap_start <= high_limit) + goto found_highest; + + /* Check if rbtree root looks promising */ + if (RB_EMPTY_ROOT(&mm->mm_rb)) + return -ENOMEM; + vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); + if (vma->rb_subtree_gap < length) + return -ENOMEM; + + while (true) { + /* Visit right subtree if it looks promising */ + gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0; + if (gap_start <= high_limit && vma->vm_rb.rb_right) { + struct vm_area_struct *right = + rb_entry(vma->vm_rb.rb_right, + struct vm_area_struct, vm_rb); + if (right->rb_subtree_gap >= length) { + vma = right; + continue; + } + } + +check_current: + /* Check if current node has a suitable gap */ + gap_end = vma->vm_start; + if (gap_end < low_limit) + return -ENOMEM; + if (gap_start <= high_limit && gap_end - gap_start >= length) + goto found; + + /* Visit left subtree if it looks promising */ + if (vma->vm_rb.rb_left) { + struct vm_area_struct *left = + rb_entry(vma->vm_rb.rb_left, + struct vm_area_struct, vm_rb); + if (left->rb_subtree_gap >= length) { + vma = left; + continue; + } + } + + /* Go back up the rbtree to find next candidate node */ + while (true) { + struct rb_node *prev = &vma->vm_rb; + if (!rb_parent(prev)) + return -ENOMEM; + vma = rb_entry(rb_parent(prev), + struct vm_area_struct, vm_rb); + if (prev == vma->vm_rb.rb_right) { + gap_start = vma->vm_prev ? + vma->vm_prev->vm_end : 0; + goto check_current; + } + } + } + +found: + /* We found a suitable gap. Clip it with the original high_limit. */ + if (gap_end > info->high_limit) + gap_end = info->high_limit; + +found_highest: + /* Compute highest gap address at the desired alignment */ + gap_end -= info->length; + gap_end -= (gap_end - info->align_offset) & info->align_mask; + + VM_BUG_ON(gap_end < info->low_limit); + VM_BUG_ON(gap_end < gap_start); + return gap_end; +} + /* Get an address range which is currently unmapped. * For shmat() with addr=0. * @@ -1242,9 +1875,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - unsigned long start_addr; + struct vm_unmapped_area_info info; - if (len > TASK_SIZE) + if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) @@ -1253,58 +1886,20 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vma->vm_start)) return addr; } - if (len > mm->cached_hole_size) { - start_addr = addr = mm->free_area_cache; - } else { - start_addr = addr = TASK_UNMAPPED_BASE; - mm->cached_hole_size = 0; - } -full_search: - for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { - /* At this point: (!vma || addr < vma->vm_end). */ - if (TASK_SIZE - len < addr) { - /* - * Start a new search - just in case we missed - * some holes. - */ - if (start_addr != TASK_UNMAPPED_BASE) { - addr = TASK_UNMAPPED_BASE; - start_addr = addr; - mm->cached_hole_size = 0; - goto full_search; - } - return -ENOMEM; - } - if (!vma || addr + len <= vma->vm_start) { - /* - * Remember the place where we stopped the search: - */ - mm->free_area_cache = addr + len; - return addr; - } - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - addr = vma->vm_end; - } + info.flags = 0; + info.length = len; + info.low_limit = mm->mmap_base; + info.high_limit = TASK_SIZE; + info.align_mask = 0; + return vm_unmapped_area(&info); } #endif -void arch_unmap_area(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the lowest possible address? - */ - if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) { - mm->free_area_cache = addr; - mm->cached_hole_size = ~0UL; - } -} - /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): @@ -1318,9 +1913,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, struct vm_area_struct *vma; struct mm_struct *mm = current->mm; unsigned long addr = addr0; + struct vm_unmapped_area_info info; /* requested length too big for entire address space */ - if (len > TASK_SIZE) + if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) @@ -1330,85 +1926,36 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vma->vm_start)) return addr; } - /* check if free_area_cache is useful for us */ - if (len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = mm->mmap_base; - } - - /* either no address requested or can't fit in requested address hole */ - addr = mm->free_area_cache; - - /* make sure it can fit in the remaining address space */ - if (addr > len) { - vma = find_vma(mm, addr-len); - if (!vma || addr <= vma->vm_start) - /* remember the address as a hint for next time */ - return (mm->free_area_cache = addr-len); - } - - if (mm->mmap_base < len) - goto bottomup; - - addr = mm->mmap_base-len; + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = max(PAGE_SIZE, mmap_min_addr); + info.high_limit = mm->mmap_base; + info.align_mask = 0; + addr = vm_unmapped_area(&info); - do { - /* - * Lookup failure means no vma is above this address, - * else if new region fits below vma->vm_start, - * return with success: - */ - vma = find_vma(mm, addr); - if (!vma || addr+len <= vma->vm_start) - /* remember the address as a hint for next time */ - return (mm->free_area_cache = addr); - - /* remember the largest hole we saw so far */ - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - - /* try just below the current vma->vm_start */ - addr = vma->vm_start-len; - } while (len < vma->vm_start); - -bottomup: /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ - mm->cached_hole_size = ~0UL; - mm->free_area_cache = TASK_UNMAPPED_BASE; - addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags); - /* - * Restore the topdown base: - */ - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = ~0UL; + if (addr & ~PAGE_MASK) { + VM_BUG_ON(addr != -ENOMEM); + info.flags = 0; + info.low_limit = TASK_UNMAPPED_BASE; + info.high_limit = TASK_SIZE; + addr = vm_unmapped_area(&info); + } return addr; } #endif -void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the highest possible address? - */ - if (addr > mm->free_area_cache) - mm->free_area_cache = addr; - - /* dont allow allocations above current base */ - if (mm->free_area_cache > mm->mmap_base) - mm->free_area_cache = mm->mmap_base; -} - unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -1416,8 +1963,16 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); + unsigned long error = arch_mmap_check(addr, len, flags); + if (error) + return error; + + /* Careful about overflows.. */ + if (len > TASK_SIZE) + return -ENOMEM; + get_area = current->mm->get_unmapped_area; - if (file && file->f_op && file->f_op->get_unmapped_area) + if (file && file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) @@ -1428,82 +1983,69 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (addr & ~PAGE_MASK) return -EINVAL; - return arch_rebalance_pgtables(addr, len); + addr = arch_rebalance_pgtables(addr, len); + error = security_mmap_addr(addr); + return error ? error : addr; } EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ -struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr) +struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = NULL; + struct rb_node *rb_node; + struct vm_area_struct *vma; - if (mm) { - /* Check the cache first. */ - /* (Cache hit rate is typically around 35%.) */ - vma = mm->mmap_cache; - if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) { - struct rb_node * rb_node; - - rb_node = mm->mm_rb.rb_node; - vma = NULL; - - while (rb_node) { - struct vm_area_struct * vma_tmp; - - vma_tmp = rb_entry(rb_node, - struct vm_area_struct, vm_rb); - - if (vma_tmp->vm_end > addr) { - vma = vma_tmp; - if (vma_tmp->vm_start <= addr) - break; - rb_node = rb_node->rb_left; - } else - rb_node = rb_node->rb_right; - } - if (vma) - mm->mmap_cache = vma; - } + /* Check the cache first. */ + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; + + rb_node = mm->mm_rb.rb_node; + vma = NULL; + + while (rb_node) { + struct vm_area_struct *tmp; + + tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); + + if (tmp->vm_end > addr) { + vma = tmp; + if (tmp->vm_start <= addr) + break; + rb_node = rb_node->rb_left; + } else + rb_node = rb_node->rb_right; } + + if (vma) + vmacache_update(addr, vma); return vma; } EXPORT_SYMBOL(find_vma); -/* Same as find_vma, but also return a pointer to the previous VMA in *pprev. */ +/* + * Same as find_vma, but also return a pointer to the previous VMA in *pprev. + */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { - struct vm_area_struct *vma = NULL, *prev = NULL; - struct rb_node * rb_node; - if (!mm) - goto out; - - /* Guard against addr being lower than the first VMA */ - vma = mm->mmap; - - /* Go through the RB tree quickly. */ - rb_node = mm->mm_rb.rb_node; - - while (rb_node) { - struct vm_area_struct *vma_tmp; - vma_tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); + struct vm_area_struct *vma; - if (addr < vma_tmp->vm_end) { - rb_node = rb_node->rb_left; - } else { - prev = vma_tmp; - if (!prev->vm_next || (addr < prev->vm_next->vm_end)) - break; + vma = find_vma(mm, addr); + if (vma) { + *pprev = vma->vm_prev; + } else { + struct rb_node *rb_node = mm->mm_rb.rb_node; + *pprev = NULL; + while (rb_node) { + *pprev = rb_entry(rb_node, struct vm_area_struct, vm_rb); rb_node = rb_node->rb_right; } } - -out: - *pprev = prev; - return prev ? prev->vm_next : vma; + return vma; } /* @@ -1511,7 +2053,7 @@ out: * update accounting. This is shared with both the * grow-up and grow-down cases. */ -static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, unsigned long grow) +static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; @@ -1522,7 +2064,7 @@ static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, un return -ENOMEM; /* Stack limit test */ - if (size > rlim[RLIMIT_STACK].rlim_cur) + if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -1530,7 +2072,8 @@ static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, un unsigned long locked; unsigned long limit; locked = mm->locked_vm + grow; - limit = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT; + limit = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur); + limit >>= PAGE_SHIFT; if (locked > limit && !capable(CAP_IPC_LOCK)) return -ENOMEM; } @@ -1545,11 +2088,10 @@ static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, un * Overcommit.. This must be the final test, as it will * update security statistics. */ - if (security_vm_enough_memory(grow)) + if (security_vm_enough_memory_mm(mm, grow)) return -ENOMEM; /* Ok, everything looks good - let it rip */ - mm->total_vm += grow; if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow); @@ -1561,9 +2103,6 @@ static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, un * PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. */ -#ifndef CONFIG_IA64 -static inline -#endif int expand_upwards(struct vm_area_struct *vma, unsigned long address) { int error; @@ -1577,7 +2116,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; - anon_vma_lock(vma); + vma_lock_anon_vma(vma); /* * vma->vm_start/vm_end cannot change under us because the caller @@ -1588,7 +2127,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) if (address < PAGE_ALIGN(address+4)) address = PAGE_ALIGN(address+4); else { - anon_vma_unlock(vma); + vma_unlock_anon_vma(vma); return -ENOMEM; } error = 0; @@ -1600,11 +2139,38 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; - error = acct_stack_growth(vma, size, grow); - if (!error) - vma->vm_end = address; + error = -ENOMEM; + if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { + error = acct_stack_growth(vma, size, grow); + if (!error) { + /* + * vma_gap_update() doesn't support concurrent + * updates, but we only hold a shared mmap_sem + * lock here, so we need to protect against + * concurrent vma expansions. + * vma_lock_anon_vma() doesn't help here, as + * we don't guarantee that all growable vmas + * in a mm share the same root anon vma. + * So, we reuse mm->page_table_lock to guard + * against concurrent vma expansions. + */ + spin_lock(&vma->vm_mm->page_table_lock); + anon_vma_interval_tree_pre_update_vma(vma); + vma->vm_end = address; + anon_vma_interval_tree_post_update_vma(vma); + if (vma->vm_next) + vma_gap_update(vma->vm_next); + else + vma->vm_mm->highest_vm_end = address; + spin_unlock(&vma->vm_mm->page_table_lock); + + perf_event_mmap(vma); + } + } } - anon_vma_unlock(vma); + vma_unlock_anon_vma(vma); + khugepaged_enter_vma_merge(vma); + validate_mm(vma->vm_mm); return error; } #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ @@ -1612,7 +2178,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) /* * vma is the first one with address < vma->vm_start. Have to extend vma. */ -static inline int expand_downwards(struct vm_area_struct *vma, +int expand_downwards(struct vm_area_struct *vma, unsigned long address) { int error; @@ -1625,11 +2191,11 @@ static inline int expand_downwards(struct vm_area_struct *vma, return -ENOMEM; address &= PAGE_MASK; - error = security_file_mmap(NULL, 0, 0, 0, address, 1); + error = security_mmap_addr(address); if (error) return error; - anon_vma_lock(vma); + vma_lock_anon_vma(vma); /* * vma->vm_start/vm_end cannot change under us because the caller @@ -1644,24 +2210,61 @@ static inline int expand_downwards(struct vm_area_struct *vma, size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; - error = acct_stack_growth(vma, size, grow); - if (!error) { - vma->vm_start = address; - vma->vm_pgoff -= grow; + error = -ENOMEM; + if (grow <= vma->vm_pgoff) { + error = acct_stack_growth(vma, size, grow); + if (!error) { + /* + * vma_gap_update() doesn't support concurrent + * updates, but we only hold a shared mmap_sem + * lock here, so we need to protect against + * concurrent vma expansions. + * vma_lock_anon_vma() doesn't help here, as + * we don't guarantee that all growable vmas + * in a mm share the same root anon vma. + * So, we reuse mm->page_table_lock to guard + * against concurrent vma expansions. + */ + spin_lock(&vma->vm_mm->page_table_lock); + anon_vma_interval_tree_pre_update_vma(vma); + vma->vm_start = address; + vma->vm_pgoff -= grow; + anon_vma_interval_tree_post_update_vma(vma); + vma_gap_update(vma); + spin_unlock(&vma->vm_mm->page_table_lock); + + perf_event_mmap(vma); + } } } - anon_vma_unlock(vma); + vma_unlock_anon_vma(vma); + khugepaged_enter_vma_merge(vma); + validate_mm(vma->vm_mm); return error; } -int expand_stack_downwards(struct vm_area_struct *vma, unsigned long address) -{ - return expand_downwards(vma, address); -} - +/* + * Note how expand_stack() refuses to expand the stack all the way to + * abut the next virtual mapping, *unless* that mapping itself is also + * a stack mapping. We want to leave room for a guard page, after all + * (the guard page itself is not added here, that is done by the + * actual page faulting logic) + * + * This matches the behavior of the guard page logic (see mm/memory.c: + * check_stack_guard_page()), which only allows the guard page to be + * removed under these circumstances. + */ #ifdef CONFIG_STACK_GROWSUP int expand_stack(struct vm_area_struct *vma, unsigned long address) { + struct vm_area_struct *next; + + address &= PAGE_MASK; + next = vma->vm_next; + if (next && next->vm_start == address + PAGE_SIZE) { + if (!(next->vm_flags & VM_GROWSUP)) + return -ENOMEM; + } return expand_upwards(vma, address); } @@ -1677,12 +2280,20 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) if (!prev || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) - make_pages_present(addr, prev->vm_end); + __mlock_vma_pages_range(prev, addr, prev->vm_end, NULL); return prev; } #else int expand_stack(struct vm_area_struct *vma, unsigned long address) { + struct vm_area_struct *prev; + + address &= PAGE_MASK; + prev = vma->vm_prev; + if (prev && prev->vm_end == address) { + if (!(prev->vm_flags & VM_GROWSDOWN)) + return -ENOMEM; + } return expand_downwards(vma, address); } @@ -1704,7 +2315,7 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr) if (expand_stack(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) - make_pages_present(addr, start); + __mlock_vma_pages_range(vma, addr, start, NULL); return vma; } #endif @@ -1717,17 +2328,19 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr) */ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) { + unsigned long nr_accounted = 0; + /* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); do { long nrpages = vma_pages(vma); - mm->total_vm -= nrpages; - if (vma->vm_flags & VM_LOCKED) - mm->locked_vm -= nrpages; + if (vma->vm_flags & VM_ACCOUNT) + nr_accounted += nrpages; vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages); vma = remove_vma(vma); } while (vma); + vm_unacct_memory(nr_accounted); validate_mm(mm); } @@ -1741,17 +2354,15 @@ static void unmap_region(struct mm_struct *mm, unsigned long start, unsigned long end) { struct vm_area_struct *next = prev? prev->vm_next: mm->mmap; - struct mmu_gather *tlb; - unsigned long nr_accounted = 0; + struct mmu_gather tlb; lru_add_drain(); - tlb = tlb_gather_mmu(mm, 0); + tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); - unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL); - vm_unacct_memory(nr_accounted); - free_pgtables(&tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS, - next? next->vm_start: 0); - tlb_finish_mmu(tlb, start, end); + unmap_vmas(&tlb, vma, start, end); + free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, + next ? next->vm_start : USER_PGTABLES_CEILING); + tlb_finish_mmu(&tlb, start, end); } /* @@ -1764,48 +2375,50 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, { struct vm_area_struct **insertion_point; struct vm_area_struct *tail_vma = NULL; - unsigned long addr; insertion_point = (prev ? &prev->vm_next : &mm->mmap); + vma->vm_prev = NULL; do { - rb_erase(&vma->vm_rb, &mm->mm_rb); + vma_rb_erase(vma, &mm->mm_rb); mm->map_count--; tail_vma = vma; vma = vma->vm_next; } while (vma && vma->vm_start < end); *insertion_point = vma; + if (vma) { + vma->vm_prev = prev; + vma_gap_update(vma); + } else + mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - if (mm->unmap_area == arch_unmap_area) - addr = prev ? prev->vm_end : mm->mmap_base; - else - addr = vma ? vma->vm_start : mm->mmap_base; - mm->unmap_area(mm, addr); - mm->mmap_cache = NULL; /* Kill the cache. */ + + /* Kill the cache */ + vmacache_invalidate(mm); } /* - * Split a vma into two pieces at address 'addr', a new vma is allocated - * either for the first part or the tail. + * __split_vma() bypasses sysctl_max_map_count checking. We use this on the + * munmap path where it doesn't make sense to fail. */ -int split_vma(struct mm_struct * mm, struct vm_area_struct * vma, +static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, unsigned long addr, int new_below) { - struct mempolicy *pol; struct vm_area_struct *new; + int err = -ENOMEM; - if (is_vm_hugetlb_page(vma) && (addr & ~HPAGE_MASK)) + if (is_vm_hugetlb_page(vma) && (addr & + ~(huge_page_mask(hstate_vma(vma))))) return -EINVAL; - if (mm->map_count >= sysctl_max_map_count) - return -ENOMEM; - new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) - return -ENOMEM; + goto out_err; /* most fields are the same, copy all, and then fixup */ *new = *vma; + INIT_LIST_HEAD(&new->anon_vma_chain); + if (new_below) new->vm_end = addr; else { @@ -1813,12 +2426,12 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } - pol = mpol_copy(vma_policy(vma)); - if (IS_ERR(pol)) { - kmem_cache_free(vm_area_cachep, new); - return PTR_ERR(pol); - } - vma_set_policy(new, pol); + err = vma_dup_policy(vma, new); + if (err) + goto out_free_vma; + + if (anon_vma_clone(new, vma)) + goto out_free_mpol; if (new->vm_file) get_file(new->vm_file); @@ -1827,12 +2440,40 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new->vm_ops->open(new); if (new_below) - vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + + err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), new); else - vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); + err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); - return 0; + /* Success. */ + if (!err) + return 0; + + /* Clean everything up if vma_adjust failed. */ + if (new->vm_ops && new->vm_ops->close) + new->vm_ops->close(new); + if (new->vm_file) + fput(new->vm_file); + unlink_anon_vmas(new); + out_free_mpol: + mpol_put(vma_policy(new)); + out_free_vma: + kmem_cache_free(vm_area_cachep, new); + out_err: + return err; +} + +/* + * Split a vma into two pieces at address 'addr', a new vma is allocated + * either for the first part or the tail. + */ +int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, int new_below) +{ + if (mm->map_count >= sysctl_max_map_count) + return -ENOMEM; + + return __split_vma(mm, vma, addr, new_below); } /* Munmap is split into 2 main parts -- this part which finds @@ -1852,9 +2493,10 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) return -EINVAL; /* Find the first overlapping VMA */ - vma = find_vma_prev(mm, start, &prev); + vma = find_vma(mm, start); if (!vma) return 0; + prev = vma->vm_prev; /* we have start < vma->vm_end */ /* if it doesn't overlap, we have nothing.. */ @@ -1870,7 +2512,17 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) * places tmp vma above, and higher split_vma places tmp vma below. */ if (start > vma->vm_start) { - int error = split_vma(mm, vma, start, 0); + int error; + + /* + * Make sure that map_count on return from munmap() will + * not exceed its limit; but let map_count go just above + * its limit temporarily, to help free resources as expected. + */ + if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count) + return -ENOMEM; + + error = __split_vma(mm, vma, start, 0); if (error) return error; prev = vma; @@ -1879,13 +2531,27 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) /* Does it split the last one? */ last = find_vma(mm, end); if (last && end > last->vm_start) { - int error = split_vma(mm, last, end, 1); + int error = __split_vma(mm, last, end, 1); if (error) return error; } vma = prev? prev->vm_next: mm->mmap; /* + * unlock any mlock()ed ranges before detaching vmas + */ + if (mm->locked_vm) { + struct vm_area_struct *tmp = vma; + while (tmp && tmp->vm_start < end) { + if (tmp->vm_flags & VM_LOCKED) { + mm->locked_vm -= vma_pages(tmp); + munlock_vma_pages_all(tmp); + } + tmp = tmp->vm_next; + } + } + + /* * Remove the vma's, and unmap the actual pages */ detach_vmas_to_be_unmapped(mm, vma, prev, end); @@ -1897,20 +2563,23 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) return 0; } -EXPORT_SYMBOL(do_munmap); - -asmlinkage long sys_munmap(unsigned long addr, size_t len) +int vm_munmap(unsigned long start, size_t len) { int ret; struct mm_struct *mm = current->mm; - profile_munmap(addr); - down_write(&mm->mmap_sem); - ret = do_munmap(mm, addr, len); + ret = do_munmap(mm, start, len); up_write(&mm->mmap_sem); return ret; } +EXPORT_SYMBOL(vm_munmap); + +SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) +{ + profile_munmap(addr); + return vm_munmap(addr, len); +} static inline void verify_mm_writelocked(struct mm_struct *mm) { @@ -1927,7 +2596,7 @@ static inline void verify_mm_writelocked(struct mm_struct *mm) * anonymous maps. eventually we may be able to do some * brk-specific accounting here. */ -unsigned long do_brk(unsigned long addr, unsigned long len) +static unsigned long do_brk(unsigned long addr, unsigned long len) { struct mm_struct * mm = current->mm; struct vm_area_struct * vma, * prev; @@ -1940,36 +2609,17 @@ unsigned long do_brk(unsigned long addr, unsigned long len) if (!len) return addr; - if ((addr + len) > TASK_SIZE || (addr + len) < addr) - return -EINVAL; - - if (is_hugepage_only_range(mm, addr, len)) - return -EINVAL; + flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; - error = security_file_mmap(NULL, 0, 0, 0, addr, 1); - if (error) + error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); + if (error & ~PAGE_MASK) return error; - flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; - - error = arch_mmap_check(addr, len, flags); + error = mlock_future_check(mm, mm->def_flags, len); if (error) return error; /* - * mlock MCL_FUTURE? - */ - if (mm->def_flags & VM_LOCKED) { - unsigned long locked, lock_limit; - locked = len >> PAGE_SHIFT; - locked += mm->locked_vm; - lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; - lock_limit >>= PAGE_SHIFT; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - return -EAGAIN; - } - - /* * mm->mmap_sem is required to protect against another thread * changing the mappings in case we sleep. */ @@ -1979,8 +2629,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len) * Clear old maps. this also does some error checking for us */ munmap_back: - vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent); - if (vma && vma->vm_start < addr + len) { + if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { if (do_munmap(mm, addr, len)) return -ENOMEM; goto munmap_back; @@ -1993,12 +2642,13 @@ unsigned long do_brk(unsigned long addr, unsigned long len) if (mm->map_count > sysctl_max_map_count) return -ENOMEM; - if (security_vm_enough_memory(len >> PAGE_SHIFT)) + if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; /* Can we just expand an old private anonymous mapping? */ - if (vma_merge(mm, prev, addr, addr + len, flags, - NULL, NULL, pgoff, NULL)) + vma = vma_merge(mm, prev, addr, addr + len, flags, + NULL, NULL, pgoff, NULL); + if (vma) goto out; /* @@ -2010,6 +2660,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len) return -ENOMEM; } + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -2018,55 +2669,88 @@ unsigned long do_brk(unsigned long addr, unsigned long len) vma->vm_page_prot = vm_get_page_prot(flags); vma_link(mm, vma, prev, rb_link, rb_parent); out: + perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; - if (flags & VM_LOCKED) { - mm->locked_vm += len >> PAGE_SHIFT; - make_pages_present(addr, addr + len); - } + if (flags & VM_LOCKED) + mm->locked_vm += (len >> PAGE_SHIFT); + vma->vm_flags |= VM_SOFTDIRTY; return addr; } -EXPORT_SYMBOL(do_brk); +unsigned long vm_brk(unsigned long addr, unsigned long len) +{ + struct mm_struct *mm = current->mm; + unsigned long ret; + bool populate; + + down_write(&mm->mmap_sem); + ret = do_brk(addr, len); + populate = ((mm->def_flags & VM_LOCKED) != 0); + up_write(&mm->mmap_sem); + if (populate) + mm_populate(addr, len); + return ret; +} +EXPORT_SYMBOL(vm_brk); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { - struct mmu_gather *tlb; - struct vm_area_struct *vma = mm->mmap; + struct mmu_gather tlb; + struct vm_area_struct *vma; unsigned long nr_accounted = 0; - unsigned long end; /* mm's last user has gone, and its about to be pulled down */ + mmu_notifier_release(mm); + + if (mm->locked_vm) { + vma = mm->mmap; + while (vma) { + if (vma->vm_flags & VM_LOCKED) + munlock_vma_pages_all(vma); + vma = vma->vm_next; + } + } + arch_exit_mmap(mm); + vma = mm->mmap; + if (!vma) /* Can happen if dup_mmap() received an OOM */ + return; + lru_add_drain(); flush_cache_mm(mm); - tlb = tlb_gather_mmu(mm, 1); - /* Don't update_hiwater_rss(mm) here, do_exit already did */ + tlb_gather_mmu(&tlb, mm, 0, -1); + /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ - end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL); - vm_unacct_memory(nr_accounted); - free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); - tlb_finish_mmu(tlb, 0, end); + unmap_vmas(&tlb, vma, 0, -1); + + free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); + tlb_finish_mmu(&tlb, 0, -1); /* * Walk the list again, actually closing and freeing it, * with preemption enabled, without holding any MM locks. */ - while (vma) + while (vma) { + if (vma->vm_flags & VM_ACCOUNT) + nr_accounted += vma_pages(vma); vma = remove_vma(vma); + } + vm_unacct_memory(nr_accounted); - BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); + WARN_ON(atomic_long_read(&mm->nr_ptes) > + (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); } /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL - * then i_mmap_lock is taken here. + * then i_mmap_mutex is taken here. */ -int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma) +int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { - struct vm_area_struct * __vma, * prev; - struct rb_node ** rb_link, * rb_parent; + struct vm_area_struct *prev; + struct rb_node **rb_link, *rb_parent; /* * The vm_pgoff of a purely anonymous vma should be irrelevant @@ -2084,12 +2768,13 @@ int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma) BUG_ON(vma->anon_vma); vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; } - __vma = find_vma_prepare(mm,vma->vm_start,&prev,&rb_link,&rb_parent); - if (__vma && __vma->vm_start < vma->vm_end) + if (find_vma_links(mm, vma->vm_start, vma->vm_end, + &prev, &rb_link, &rb_parent)) return -ENOMEM; if ((vma->vm_flags & VM_ACCOUNT) && security_vm_enough_memory_mm(mm, vma_pages(vma))) return -ENOMEM; + vma_link(mm, vma, prev, rb_link, rb_parent); return 0; } @@ -2099,53 +2784,78 @@ int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma) * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, - unsigned long addr, unsigned long len, pgoff_t pgoff) + unsigned long addr, unsigned long len, pgoff_t pgoff, + bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma, *prev; struct rb_node **rb_link, *rb_parent; - struct mempolicy *pol; + bool faulted_in_anon_vma = true; /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ - if (!vma->vm_file && !vma->anon_vma) + if (unlikely(!vma->vm_file && !vma->anon_vma)) { pgoff = addr >> PAGE_SHIFT; + faulted_in_anon_vma = false; + } - find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent); + if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) + return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma */ - if (vma_start >= new_vma->vm_start && - vma_start < new_vma->vm_end) - *vmap = new_vma; + if (unlikely(vma_start >= new_vma->vm_start && + vma_start < new_vma->vm_end)) { + /* + * The only way we can get a vma_merge with + * self during an mremap is if the vma hasn't + * been faulted in yet and we were allowed to + * reset the dst vma->vm_pgoff to the + * destination address of the mremap to allow + * the merge to happen. mremap must change the + * vm_pgoff linearity between src and dst vmas + * (in turn preventing a vma_merge) to be + * safe. It is only safe to keep the vm_pgoff + * linear if there are no pages mapped yet. + */ + VM_BUG_ON(faulted_in_anon_vma); + *vmap = vma = new_vma; + } + *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (new_vma) { *new_vma = *vma; - pol = mpol_copy(vma_policy(vma)); - if (IS_ERR(pol)) { - kmem_cache_free(vm_area_cachep, new_vma); - return NULL; - } - vma_set_policy(new_vma, pol); new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; + if (vma_dup_policy(vma, new_vma)) + goto out_free_vma; + INIT_LIST_HEAD(&new_vma->anon_vma_chain); + if (anon_vma_clone(new_vma, vma)) + goto out_free_mempol; if (new_vma->vm_file) get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); + *need_rmap_locks = false; } } return new_vma; + + out_free_mempol: + mpol_put(vma_policy(new_vma)); + out_free_vma: + kmem_cache_free(vm_area_cachep, new_vma); + return NULL; } /* @@ -2157,13 +2867,38 @@ int may_expand_vm(struct mm_struct *mm, unsigned long npages) unsigned long cur = mm->total_vm; /* pages */ unsigned long lim; - lim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT; + lim = rlimit(RLIMIT_AS) >> PAGE_SHIFT; if (cur + npages > lim) return 0; return 1; } +static int special_mapping_fault(struct vm_area_struct *vma, + struct vm_fault *vmf); + +/* + * Having a close hook prevents vma merging regardless of flags. + */ +static void special_mapping_close(struct vm_area_struct *vma) +{ +} + +static const char *special_mapping_name(struct vm_area_struct *vma) +{ + return ((struct vm_special_mapping *)vma->vm_private_data)->name; +} + +static const struct vm_operations_struct special_mapping_vmops = { + .close = special_mapping_close, + .fault = special_mapping_fault, + .name = special_mapping_name, +}; + +static const struct vm_operations_struct legacy_special_mapping_vmops = { + .close = special_mapping_close, + .fault = special_mapping_fault, +}; static int special_mapping_fault(struct vm_area_struct *vma, struct vm_fault *vmf) @@ -2179,7 +2914,13 @@ static int special_mapping_fault(struct vm_area_struct *vma, */ pgoff = vmf->pgoff - vma->vm_pgoff; - for (pages = vma->vm_private_data; pgoff && *pages; ++pages) + if (vma->vm_ops == &legacy_special_mapping_vmops) + pages = vma->vm_private_data; + else + pages = ((struct vm_special_mapping *)vma->vm_private_data)-> + pages; + + for (; pgoff && *pages; ++pages) pgoff--; if (*pages) { @@ -2192,17 +2933,44 @@ static int special_mapping_fault(struct vm_area_struct *vma, return VM_FAULT_SIGBUS; } -/* - * Having a close hook prevents vma merging regardless of flags. - */ -static void special_mapping_close(struct vm_area_struct *vma) +static struct vm_area_struct *__install_special_mapping( + struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, const struct vm_operations_struct *ops, + void *priv) { -} + int ret; + struct vm_area_struct *vma; -static struct vm_operations_struct special_mapping_vmops = { - .close = special_mapping_close, - .fault = special_mapping_fault, -}; + vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + if (unlikely(vma == NULL)) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&vma->anon_vma_chain); + vma->vm_mm = mm; + vma->vm_start = addr; + vma->vm_end = addr + len; + + vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY; + vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); + + vma->vm_ops = ops; + vma->vm_private_data = priv; + + ret = insert_vm_struct(mm, vma); + if (ret) + goto out; + + mm->total_vm += len >> PAGE_SHIFT; + + perf_event_mmap(vma); + + return vma; + +out: + kmem_cache_free(vm_area_cachep, vma); + return ERR_PTR(ret); +} /* * Called with mm->mmap_sem held for writing. @@ -2213,32 +2981,310 @@ static struct vm_operations_struct special_mapping_vmops = { * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ +struct vm_area_struct *_install_special_mapping( + struct mm_struct *mm, + unsigned long addr, unsigned long len, + unsigned long vm_flags, const struct vm_special_mapping *spec) +{ + return __install_special_mapping(mm, addr, len, vm_flags, + &special_mapping_vmops, (void *)spec); +} + int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { + struct vm_area_struct *vma = __install_special_mapping( + mm, addr, len, vm_flags, &legacy_special_mapping_vmops, + (void *)pages); + + return PTR_ERR_OR_ZERO(vma); +} + +static DEFINE_MUTEX(mm_all_locks_mutex); + +static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) +{ + if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_node)) { + /* + * The LSB of head.next can't change from under us + * because we hold the mm_all_locks_mutex. + */ + down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_sem); + /* + * We can safely modify head.next after taking the + * anon_vma->root->rwsem. If some other vma in this mm shares + * the same anon_vma we won't take it again. + * + * No need of atomic instructions here, head.next + * can't change from under us thanks to the + * anon_vma->root->rwsem. + */ + if (__test_and_set_bit(0, (unsigned long *) + &anon_vma->root->rb_root.rb_node)) + BUG(); + } +} + +static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) +{ + if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { + /* + * AS_MM_ALL_LOCKS can't change from under us because + * we hold the mm_all_locks_mutex. + * + * Operations on ->flags have to be atomic because + * even if AS_MM_ALL_LOCKS is stable thanks to the + * mm_all_locks_mutex, there may be other cpus + * changing other bitflags in parallel to us. + */ + if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) + BUG(); + mutex_lock_nest_lock(&mapping->i_mmap_mutex, &mm->mmap_sem); + } +} + +/* + * This operation locks against the VM for all pte/vma/mm related + * operations that could ever happen on a certain mm. This includes + * vmtruncate, try_to_unmap, and all page faults. + * + * The caller must take the mmap_sem in write mode before calling + * mm_take_all_locks(). The caller isn't allowed to release the + * mmap_sem until mm_drop_all_locks() returns. + * + * mmap_sem in write mode is required in order to block all operations + * that could modify pagetables and free pages without need of + * altering the vma layout (for example populate_range() with + * nonlinear vmas). It's also needed in write mode to avoid new + * anon_vmas to be associated with existing vmas. + * + * A single task can't take more than one mm_take_all_locks() in a row + * or it would deadlock. + * + * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in + * mapping->flags avoid to take the same lock twice, if more than one + * vma in this mm is backed by the same anon_vma or address_space. + * + * We can take all the locks in random order because the VM code + * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never + * takes more than one of them in a row. Secondly we're protected + * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex. + * + * mm_take_all_locks() and mm_drop_all_locks are expensive operations + * that may have to take thousand of locks. + * + * mm_take_all_locks() can fail if it's interrupted by signals. + */ +int mm_take_all_locks(struct mm_struct *mm) +{ struct vm_area_struct *vma; + struct anon_vma_chain *avc; - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); - if (unlikely(vma == NULL)) - return -ENOMEM; + BUG_ON(down_read_trylock(&mm->mmap_sem)); - vma->vm_mm = mm; - vma->vm_start = addr; - vma->vm_end = addr + len; + mutex_lock(&mm_all_locks_mutex); - vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND; - vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (signal_pending(current)) + goto out_unlock; + if (vma->vm_file && vma->vm_file->f_mapping) + vm_lock_mapping(mm, vma->vm_file->f_mapping); + } + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (signal_pending(current)) + goto out_unlock; + if (vma->anon_vma) + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_lock_anon_vma(mm, avc->anon_vma); + } - vma->vm_ops = &special_mapping_vmops; - vma->vm_private_data = pages; + return 0; - if (unlikely(insert_vm_struct(mm, vma))) { - kmem_cache_free(vm_area_cachep, vma); - return -ENOMEM; +out_unlock: + mm_drop_all_locks(mm); + return -EINTR; +} + +static void vm_unlock_anon_vma(struct anon_vma *anon_vma) +{ + if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_node)) { + /* + * The LSB of head.next can't change to 0 from under + * us because we hold the mm_all_locks_mutex. + * + * We must however clear the bitflag before unlocking + * the vma so the users using the anon_vma->rb_root will + * never see our bitflag. + * + * No need of atomic instructions here, head.next + * can't change from under us until we release the + * anon_vma->root->rwsem. + */ + if (!__test_and_clear_bit(0, (unsigned long *) + &anon_vma->root->rb_root.rb_node)) + BUG(); + anon_vma_unlock_write(anon_vma); } +} - mm->total_vm += len >> PAGE_SHIFT; +static void vm_unlock_mapping(struct address_space *mapping) +{ + if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { + /* + * AS_MM_ALL_LOCKS can't change to 0 from under us + * because we hold the mm_all_locks_mutex. + */ + mutex_unlock(&mapping->i_mmap_mutex); + if (!test_and_clear_bit(AS_MM_ALL_LOCKS, + &mapping->flags)) + BUG(); + } +} + +/* + * The mmap_sem cannot be released by the caller until + * mm_drop_all_locks() returns. + */ +void mm_drop_all_locks(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + struct anon_vma_chain *avc; + + BUG_ON(down_read_trylock(&mm->mmap_sem)); + BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (vma->anon_vma) + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_unlock_anon_vma(avc->anon_vma); + if (vma->vm_file && vma->vm_file->f_mapping) + vm_unlock_mapping(vma->vm_file->f_mapping); + } + + mutex_unlock(&mm_all_locks_mutex); +} + +/* + * initialise the VMA slab + */ +void __init mmap_init(void) +{ + int ret; + + ret = percpu_counter_init(&vm_committed_as, 0); + VM_BUG_ON(ret); +} + +/* + * Initialise sysctl_user_reserve_kbytes. + * + * This is intended to prevent a user from starting a single memory hogging + * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER + * mode. + * + * The default value is min(3% of free memory, 128MB) + * 128MB is enough to recover with sshd/login, bash, and top/kill. + */ +static int init_user_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); + return 0; +} +subsys_initcall(init_user_reserve); + +/* + * Initialise sysctl_admin_reserve_kbytes. + * + * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin + * to log in and kill a memory hogging process. + * + * Systems with more than 256MB will reserve 8MB, enough to recover + * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will + * only reserve 3% of free pages by default. + */ +static int init_admin_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); + return 0; +} +subsys_initcall(init_admin_reserve); + +/* + * Reinititalise user and admin reserves if memory is added or removed. + * + * The default user reserve max is 128MB, and the default max for the + * admin reserve is 8MB. These are usually, but not always, enough to + * enable recovery from a memory hogging process using login/sshd, a shell, + * and tools like top. It may make sense to increase or even disable the + * reserve depending on the existence of swap or variations in the recovery + * tools. So, the admin may have changed them. + * + * If memory is added and the reserves have been eliminated or increased above + * the default max, then we'll trust the admin. + * + * If memory is removed and there isn't enough free memory, then we + * need to reset the reserves. + * + * Otherwise keep the reserve set by the admin. + */ +static int reserve_mem_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + unsigned long tmp, free_kbytes; + + switch (action) { + case MEM_ONLINE: + /* Default max is 128MB. Leave alone if modified by operator. */ + tmp = sysctl_user_reserve_kbytes; + if (0 < tmp && tmp < (1UL << 17)) + init_user_reserve(); + + /* Default max is 8MB. Leave alone if modified by operator. */ + tmp = sysctl_admin_reserve_kbytes; + if (0 < tmp && tmp < (1UL << 13)) + init_admin_reserve(); + + break; + case MEM_OFFLINE: + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + if (sysctl_user_reserve_kbytes > free_kbytes) { + init_user_reserve(); + pr_info("vm.user_reserve_kbytes reset to %lu\n", + sysctl_user_reserve_kbytes); + } + + if (sysctl_admin_reserve_kbytes > free_kbytes) { + init_admin_reserve(); + pr_info("vm.admin_reserve_kbytes reset to %lu\n", + sysctl_admin_reserve_kbytes); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block reserve_mem_nb = { + .notifier_call = reserve_mem_notifier, +}; + +static int __meminit init_reserve_notifier(void) +{ + if (register_hotmemory_notifier(&reserve_mem_nb)) + pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } +subsys_initcall(init_reserve_notifier); |