*/
#include <linux/slab.h>
+#include <linux/mm.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
+#include <linux/capability.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/profile.h>
#include <linux/module.h>
#include <linux/mount.h>
+#include <linux/mempolicy.h>
+#include <linux/rmap.h>
+#include <linux/random.h>
#include <asm/uaccess.h>
-#include <asm/pgalloc.h>
+#include <asm/cacheflush.h>
#include <asm/tlb.h>
+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.
__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
};
-int sysctl_overcommit_memory = 0; /* default is heuristic overcommit */
+int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
-int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
+int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
atomic_t vm_committed_space = ATOMIC_INIT(0);
-EXPORT_SYMBOL(sysctl_overcommit_memory);
-EXPORT_SYMBOL(sysctl_overcommit_ratio);
-EXPORT_SYMBOL(sysctl_max_map_count);
-EXPORT_SYMBOL(vm_committed_space);
-
/*
- * Requires inode->i_mapping->i_shared_sem
+ * Check that a process has enough memory to allocate a new virtual
+ * mapping. 0 means there is enough memory for the allocation to
+ * succeed and -ENOMEM implies there is not.
+ *
+ * We currently support three overcommit policies, which are set via the
+ * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting
+ *
+ * Strict overcommit modes added 2002 Feb 26 by Alan Cox.
+ * Additional code 2002 Jul 20 by Robert Love.
+ *
+ * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
+ *
+ * Note this is a helper function intended to be used by LSMs which
+ * wish to use this logic.
*/
-static inline void
-__remove_shared_vm_struct(struct vm_area_struct *vma, struct inode *inode)
+int __vm_enough_memory(long pages, int cap_sys_admin)
{
- if (inode) {
- if (vma->vm_flags & VM_DENYWRITE)
- atomic_inc(&inode->i_writecount);
- list_del_init(&vma->shared);
+ unsigned long free, allowed;
+
+ vm_acct_memory(pages);
+
+ /*
+ * Sometimes we want to use more memory than we have
+ */
+ if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
+ return 0;
+
+ if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
+ unsigned long n;
+
+ free = get_page_cache_size();
+ free += nr_swap_pages;
+
+ /*
+ * Any slabs which are created with the
+ * SLAB_RECLAIM_ACCOUNT flag claim to have contents
+ * which are reclaimable, under pressure. The dentry
+ * cache and most inode caches should fall into this
+ */
+ free += atomic_read(&slab_reclaim_pages);
+
+ /*
+ * 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)
+ goto error;
+ else
+ n -= totalreserve_pages;
+
+ /*
+ * Leave the last 3% for root
+ */
+ if (!cap_sys_admin)
+ n -= n / 32;
+ free += n;
+
+ if (free > pages)
+ return 0;
+
+ goto error;
}
+
+ allowed = (totalram_pages - hugetlb_total_pages())
+ * sysctl_overcommit_ratio / 100;
+ /*
+ * Leave the last 3% 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 -= current->mm->total_vm / 32;
+
+ /*
+ * cast `allowed' as a signed long because vm_committed_space
+ * sometimes has a negative value
+ */
+ if (atomic_read(&vm_committed_space) < (long)allowed)
+ return 0;
+error:
+ vm_unacct_memory(pages);
+
+ return -ENOMEM;
+}
+
+EXPORT_SYMBOL(__vm_enough_memory);
+
+/*
+ * Requires inode->i_mapping->i_mmap_lock
+ */
+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_dentry->d_inode->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);
+ else
+ vma_prio_tree_remove(vma, &mapping->i_mmap);
+ flush_dcache_mmap_unlock(mapping);
}
/*
- * Remove one vm structure from the inode's i_mapping address space.
+ * Unlink a file-based vm structure from its prio_tree, to hide
+ * vma from rmap and vmtruncate before freeing its page tables.
*/
-static void remove_shared_vm_struct(struct vm_area_struct *vma)
+void unlink_file_vma(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
if (file) {
struct address_space *mapping = file->f_mapping;
- down(&mapping->i_shared_sem);
- __remove_shared_vm_struct(vma, file->f_dentry->d_inode);
- up(&mapping->i_shared_sem);
+ spin_lock(&mapping->i_mmap_lock);
+ __remove_shared_vm_struct(vma, file, mapping);
+ spin_unlock(&mapping->i_mmap_lock);
}
}
/*
- * sys_brk() for the most part doesn't need the global kernel
- * lock, except when an application is doing something nasty
- * like trying to un-brk an area that has already been mapped
- * to a regular file. in this case, the unmapping will need
- * to invoke file system routines that need the global lock.
+ * Close a vm structure and free it, returning the next.
*/
+static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
+{
+ struct vm_area_struct *next = vma->vm_next;
+
+ might_sleep();
+ if (vma->vm_ops && vma->vm_ops->close)
+ vma->vm_ops->close(vma);
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ mpol_free(vma_policy(vma));
+ kmem_cache_free(vm_area_cachep, vma);
+ return next;
+}
+
asmlinkage unsigned long sys_brk(unsigned long brk)
{
unsigned long rlim, retval;
if (brk < mm->end_code)
goto out;
+
+ /*
+ * Check against rlimit here. If this check is done later after the test
+ * of oldbrk with newbrk then it can escape the test and let the data
+ * 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;
+ if (rlim < RLIM_INFINITY && brk - mm->start_data > rlim)
+ goto out;
+
newbrk = PAGE_ALIGN(brk);
oldbrk = PAGE_ALIGN(mm->brk);
if (oldbrk == newbrk)
goto out;
}
- /* Check against rlimit.. */
- rlim = current->rlim[RLIMIT_DATA].rlim_cur;
- if (rlim < RLIM_INFINITY && brk - mm->start_data > rlim)
- goto out;
-
/* Check against existing mmap mappings. */
if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
goto out;
}
#ifdef DEBUG_MM_RB
-static int browse_rb(struct rb_root *root) {
- int i, j;
+static int browse_rb(struct rb_root *root)
+{
+ int i = 0, j;
struct rb_node *nd, *pn = NULL;
- i = 0;
unsigned long prev = 0, pend = 0;
for (nd = rb_first(root); nd; nd = rb_next(nd)) {
return i;
}
-void validate_mm(struct mm_struct * mm) {
+void validate_mm(struct mm_struct *mm)
+{
int bug = 0;
int i = 0;
- struct vm_area_struct * tmp = mm->mmap;
+ struct vm_area_struct *tmp = mm->mmap;
while (tmp) {
tmp = tmp->vm_next;
i++;
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 (bug)
- BUG();
+ BUG_ON(bug);
}
#else
#define validate_mm(mm) do { } while (0)
__vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node *rb_parent)
{
+ if (vma->vm_flags & VM_EXEC)
+ arch_add_exec_range(mm, vma->vm_end);
if (prev) {
vma->vm_next = prev->vm_next;
prev->vm_next = vma;
if (vma->vm_flags & VM_DENYWRITE)
atomic_dec(&file->f_dentry->d_inode->i_writecount);
-
if (vma->vm_flags & VM_SHARED)
- list_add_tail(&vma->shared, &mapping->i_mmap_shared);
+ mapping->i_mmap_writable++;
+
+ flush_dcache_mmap_lock(mapping);
+ if (unlikely(vma->vm_flags & VM_NONLINEAR))
+ vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
else
- list_add_tail(&vma->shared, &mapping->i_mmap);
+ vma_prio_tree_insert(vma, &mapping->i_mmap);
+ flush_dcache_mmap_unlock(mapping);
}
}
{
__vma_link_list(mm, vma, prev, rb_parent);
__vma_link_rb(mm, vma, rb_link, rb_parent);
- __vma_link_file(vma);
+ __anon_vma_link(vma);
}
static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
if (vma->vm_file)
mapping = vma->vm_file->f_mapping;
- if (mapping)
- down(&mapping->i_shared_sem);
- spin_lock(&mm->page_table_lock);
+ if (mapping) {
+ spin_lock(&mapping->i_mmap_lock);
+ vma->vm_truncate_count = mapping->truncate_count;
+ }
+ anon_vma_lock(vma);
+
__vma_link(mm, vma, prev, rb_link, rb_parent);
- spin_unlock(&mm->page_table_lock);
+ __vma_link_file(vma);
+
+ anon_vma_unlock(vma);
if (mapping)
- up(&mapping->i_shared_sem);
+ spin_unlock(&mapping->i_mmap_lock);
- mark_mm_hugetlb(mm, vma);
mm->map_count++;
validate_mm(mm);
}
/*
- * Insert vm structure into process list sorted by address and into the inode's
- * i_mmap ring. The caller should hold mm->page_table_lock and
- * ->f_mappping->i_shared_sem if vm_file is non-NULL.
+ * 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.
*/
static void
__insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
struct rb_node ** rb_link, * rb_parent;
__vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent);
- if (__vma && __vma->vm_start < vma->vm_end)
- BUG();
+ BUG_ON(__vma && __vma->vm_start < vma->vm_end);
__vma_link(mm, vma, prev, rb_link, rb_parent);
- mark_mm_hugetlb(mm, vma);
mm->map_count++;
+}
+
+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;
+ if (vma->vm_flags & VM_EXEC)
+ arch_remove_exec_range(mm, vma->vm_end);
+}
+
+/*
+ * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that
+ * is already present in an i_mmap tree without adjusting the tree.
+ * The following helper function should be used when such adjustments
+ * 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,
+ 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 anon_vma *anon_vma = NULL;
+ long adjust_next = 0;
+ int remove_next = 0;
+
+ if (next && !insert) {
+ if (end >= next->vm_end) {
+ /*
+ * vma expands, overlapping all the next, and
+ * perhaps the one after too (mprotect case 6).
+ */
+again: remove_next = 1 + (end > next->vm_end);
+ end = next->vm_end;
+ anon_vma = next->anon_vma;
+ importer = vma;
+ } else if (end > next->vm_start) {
+ /*
+ * vma expands, overlapping part of the next:
+ * mprotect case 5 shifting the boundary up.
+ */
+ adjust_next = (end - next->vm_start) >> PAGE_SHIFT;
+ anon_vma = next->anon_vma;
+ importer = vma;
+ } else if (end < vma->vm_end) {
+ /*
+ * vma shrinks, and !insert tells it's not
+ * split_vma inserting another: so it must be
+ * mprotect case 4 shifting the boundary down.
+ */
+ adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT);
+ anon_vma = next->anon_vma;
+ importer = next;
+ }
+ }
+
+ if (file) {
+ mapping = file->f_mapping;
+ 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;
+ }
+ if (insert) {
+ insert->vm_truncate_count = vma->vm_truncate_count;
+ /*
+ * Put into prio_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.
+ */
+ __vma_link_file(insert);
+ }
+ }
+
+ /*
+ * 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;
+ 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);
+ }
+ }
+
+ if (root) {
+ flush_dcache_mmap_lock(mapping);
+ vma_prio_tree_remove(vma, root);
+ if (adjust_next)
+ vma_prio_tree_remove(next, root);
+ }
+
+ vma->vm_start = start;
+ vma->vm_end = end;
+ vma->vm_pgoff = pgoff;
+ if (adjust_next) {
+ next->vm_start += adjust_next << PAGE_SHIFT;
+ next->vm_pgoff += adjust_next;
+ }
+
+ if (root) {
+ if (adjust_next)
+ vma_prio_tree_insert(next, root);
+ vma_prio_tree_insert(vma, root);
+ flush_dcache_mmap_unlock(mapping);
+ }
+
+ if (remove_next) {
+ /*
+ * vma_merge has merged next into vma, and needs
+ * us to remove next before dropping the locks.
+ */
+ __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
+ * us to insert it before dropping the locks
+ * (it may either follow vma or precede it).
+ */
+ __insert_vm_struct(mm, insert);
+ }
+
+ if (anon_vma)
+ spin_unlock(&anon_vma->lock);
+ if (mapping)
+ spin_unlock(&mapping->i_mmap_lock);
+
+ if (remove_next) {
+ if (file)
+ fput(file);
+ mm->map_count--;
+ mpol_free(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;
+ goto again;
+ }
+ }
+
validate_mm(mm);
}
* 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_DONTCOPY | VM_DONTEXPAND | VM_RESERVED)
+#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_ops && vma->vm_ops->close)
+ if (vma->vm_flags != vm_flags)
return 0;
if (vma->vm_file != file)
return 0;
- if (vma->vm_flags != vm_flags)
- return 0;
- if (vma->vm_private_data)
+ if (vma->vm_ops && vma->vm_ops->close)
return 0;
return 1;
}
+static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
+ struct anon_vma *anon_vma2)
+{
+ return !anon_vma1 || !anon_vma2 || (anon_vma1 == anon_vma2);
+}
+
/*
- * Return true if we can merge this (vm_flags,file,vm_pgoff,size)
+ * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
* in front of (at a lower virtual address and file offset than) the vma.
*
+ * We cannot merge two vmas if they have differently assigned (non-NULL)
+ * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
+ *
* We don't check here for the merged mmap wrapping around the end of pagecache
* indices (16TB on ia32) because do_mmap_pgoff() does not permit mmap's which
* wrap, nor mmaps which cover the final page at index -1UL.
*/
static int
can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
- struct file *file, unsigned long vm_pgoff, unsigned long size)
+ struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
{
- if (is_mergeable_vma(vma, file, vm_flags)) {
- if (!file)
- return 1; /* anon mapping */
- if (vma->vm_pgoff == vm_pgoff + size)
+ if (is_mergeable_vma(vma, file, vm_flags) &&
+ is_mergeable_anon_vma(anon_vma, vma->anon_vma)) {
+ if (vma->vm_pgoff == vm_pgoff)
return 1;
}
return 0;
}
/*
- * Return true if we can merge this (vm_flags,file,vm_pgoff)
+ * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
* beyond (at a higher virtual address and file offset than) the vma.
+ *
+ * We cannot merge two vmas if they have differently assigned (non-NULL)
+ * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
*/
static int
can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
- struct file *file, unsigned long vm_pgoff)
+ struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
{
- if (is_mergeable_vma(vma, file, vm_flags)) {
- unsigned long vma_size;
-
- if (!file)
- return 1; /* anon mapping */
-
- vma_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
- if (vma->vm_pgoff + vma_size == vm_pgoff)
+ if (is_mergeable_vma(vma, file, vm_flags) &&
+ is_mergeable_anon_vma(anon_vma, vma->anon_vma)) {
+ pgoff_t vm_pglen;
+ vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+ if (vma->vm_pgoff + vm_pglen == vm_pgoff)
return 1;
}
return 0;
}
/*
- * Given a new mapping request (addr,end,vm_flags,file,pgoff), figure out
- * whether that can be merged with its predecessor or its successor. Or
- * both (it neatly fills a hole).
+ * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out
+ * whether that can be merged with its predecessor or its successor.
+ * Or both (it neatly fills a hole).
+ *
+ * In most cases - when called for mmap, brk or mremap - [addr,end) is
+ * certain not to be mapped by the time vma_merge is called; but when
+ * called for mprotect, it is certain to be already mapped (either at
+ * an offset within prev, or at the start of next), and the flags of
+ * this area are about to be changed to vm_flags - and the no-change
+ * case has already been eliminated.
+ *
+ * The following mprotect cases have to be considered, where AAAA is
+ * the area passed down from mprotect_fixup, never extending beyond one
+ * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after:
+ *
+ * AAAA AAAA AAAA AAAA
+ * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPNNNNNN PPPPNNNNXXXX
+ * cannot merge might become might become might become
+ * PPNNNNNNNNNN PPPPPPPPPPNN PPPPPPPPPPPP 6 or
+ * mmap, brk or case 4 below case 5 below PPPPPPPPXXXX 7 or
+ * mremap move: PPPPNNNNNNNN 8
+ * AAAA
+ * PPPP NNNN PPPPPPPPPPPP PPPPPPPPNNNN PPPPNNNNNNNN
+ * might become case 1 below case 2 below case 3 below
+ *
+ * Odd one out? Case 8, because it extends NNNN but needs flags of XXXX:
+ * mprotect_fixup updates vm_flags & vm_page_prot on successful return.
*/
-static struct vm_area_struct *vma_merge(struct mm_struct *mm,
- struct vm_area_struct *prev,
- struct rb_node *rb_parent, unsigned long addr,
+struct vm_area_struct *vma_merge(struct mm_struct *mm,
+ struct vm_area_struct *prev, unsigned long addr,
unsigned long end, unsigned long vm_flags,
- struct file *file, unsigned long pgoff)
+ struct anon_vma *anon_vma, struct file *file,
+ pgoff_t pgoff, struct mempolicy *policy)
{
- spinlock_t *lock = &mm->page_table_lock;
- struct inode *inode = file ? file->f_dentry->d_inode : NULL;
- struct semaphore *i_shared_sem;
+ pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
+ struct vm_area_struct *area, *next;
/*
- * We later require that vma->vm_flags == vm_flags, so this tests
- * vma->vm_flags & VM_SPECIAL, too.
+ * We later require that vma->vm_flags == vm_flags,
+ * so this tests vma->vm_flags & VM_SPECIAL, too.
*/
if (vm_flags & VM_SPECIAL)
return NULL;
- i_shared_sem = file ? &file->f_mapping->i_shared_sem : NULL;
-
- if (!prev) {
- prev = rb_entry(rb_parent, struct vm_area_struct, vm_rb);
- goto merge_next;
- }
+ if (prev)
+ next = prev->vm_next;
+ else
+ next = mm->mmap;
+ area = next;
+ if (next && next->vm_end == end) /* cases 6, 7, 8 */
+ next = next->vm_next;
/*
* Can it merge with the predecessor?
*/
- if (prev->vm_end == addr &&
- can_vma_merge_after(prev, vm_flags, file, pgoff)) {
- struct vm_area_struct *next;
- int need_up = 0;
-
- if (unlikely(file && prev->vm_next &&
- prev->vm_next->vm_file == file)) {
- down(i_shared_sem);
- need_up = 1;
- }
- spin_lock(lock);
- prev->vm_end = end;
-
+ if (prev && prev->vm_end == addr &&
+ mpol_equal(vma_policy(prev), policy) &&
+ can_vma_merge_after(prev, vm_flags,
+ anon_vma, file, pgoff)) {
/*
- * OK, it did. Can we now merge in the successor as well?
+ * OK, it can. Can we now merge in the successor as well?
*/
- next = prev->vm_next;
- if (next && prev->vm_end == next->vm_start &&
- can_vma_merge_before(next, vm_flags, file,
- pgoff, (end - addr) >> PAGE_SHIFT)) {
- prev->vm_end = next->vm_end;
- __vma_unlink(mm, next, prev);
- __remove_shared_vm_struct(next, inode);
- spin_unlock(lock);
- if (need_up)
- up(i_shared_sem);
- if (file)
- fput(file);
-
- mm->map_count--;
- kmem_cache_free(vm_area_cachep, next);
- return prev;
- }
- spin_unlock(lock);
- if (need_up)
- up(i_shared_sem);
+ if (next && end == next->vm_start &&
+ mpol_equal(policy, vma_policy(next)) &&
+ can_vma_merge_before(next, vm_flags,
+ anon_vma, file, pgoff+pglen) &&
+ is_mergeable_anon_vma(prev->anon_vma,
+ next->anon_vma)) {
+ /* cases 1, 6 */
+ vma_adjust(prev, prev->vm_start,
+ next->vm_end, prev->vm_pgoff, NULL);
+ } else /* cases 2, 5, 7 */
+ vma_adjust(prev, prev->vm_start,
+ end, prev->vm_pgoff, NULL);
+ if (prev->vm_flags & VM_EXEC)
+ arch_add_exec_range(mm, prev->vm_end);
return prev;
}
/*
- * Can this new request be merged in front of prev->vm_next?
+ * Can this new request be merged in front of next?
*/
- prev = prev->vm_next;
- if (prev) {
- merge_next:
- if (!can_vma_merge_before(prev, vm_flags, file,
- pgoff, (end - addr) >> PAGE_SHIFT))
- return NULL;
- if (end == prev->vm_start) {
- if (file)
- down(i_shared_sem);
- spin_lock(lock);
- prev->vm_start = addr;
- prev->vm_pgoff -= (end - addr) >> PAGE_SHIFT;
- spin_unlock(lock);
- if (file)
- up(i_shared_sem);
- return prev;
- }
+ if (next && end == next->vm_start &&
+ mpol_equal(policy, vma_policy(next)) &&
+ 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,
+ addr, prev->vm_pgoff, NULL);
+ else /* cases 3, 8 */
+ vma_adjust(area, addr, next->vm_end,
+ next->vm_pgoff - pglen, NULL);
+ return area;
}
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
+ * sequence of mprotects and faults may otherwise lead to distinct
+ * anon_vmas being allocated, preventing vma merge in subsequent
+ * mprotect.
+ */
+struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *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;
+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);
+ 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;
+none:
+ /*
+ * There's no absolute need to look only at touching neighbours:
+ * we could search further afield for "compatible" anon_vmas.
+ * But it would probably just be a waste of time searching,
+ * or lead to too many vmas hanging off the same anon_vma.
+ * We're trying to allow mprotect remerging later on,
+ * not trying to minimize memory used for anon_vmas.
+ */
+ return NULL;
+}
+
+#ifdef CONFIG_PROC_FS
+void vm_stat_account(struct mm_struct *mm, unsigned long flags,
+ struct file *file, long pages)
+{
+ const unsigned long stack_flags
+ = VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN);
+
+ 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).
*/
int error;
struct rb_node ** rb_link, * rb_parent;
int accountable = 1;
- unsigned long charged = 0;
+ unsigned long charged = 0, reqprot = prot;
if (file) {
if (is_file_hugepages(file))
if (!file->f_op || !file->f_op->mmap)
return -ENODEV;
- if ((prot & PROT_EXEC) && (file->f_vfsmnt->mnt_flags & MNT_NOEXEC))
+ if ((prot & PROT_EXEC) &&
+ (file->f_vfsmnt->mnt_flags & MNT_NOEXEC))
return -EPERM;
}
+ /*
+ * Does the application expect PROT_READ to imply PROT_EXEC?
+ *
+ * (the exception is when the underlying filesystem is noexec
+ * mounted, in which case we dont add PROT_EXEC.)
+ */
+ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
+ if (!(file && (file->f_vfsmnt->mnt_flags & MNT_NOEXEC)))
+ prot |= PROT_EXEC;
if (!len)
- return addr;
+ return -EINVAL;
/* Careful about overflows.. */
len = PAGE_ALIGN(len);
if (!len || len > TASK_SIZE)
- return -EINVAL;
+ return -ENOMEM;
/* offset overflow? */
if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
- return -EINVAL;
+ return -EOVERFLOW;
/* Too many mappings? */
if (mm->map_count > sysctl_max_map_count)
/* Obtain the address to map to. we verify (or select) it and ensure
* that it represents a valid section of the address space.
*/
- addr = get_unmapped_area(file, addr, len, pgoff, flags);
+ addr = get_unmapped_area_prot(file, addr, len, pgoff, flags, prot & PROT_EXEC);
if (addr & ~PAGE_MASK)
return addr;
mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
if (flags & MAP_LOCKED) {
- if (!capable(CAP_IPC_LOCK))
+ if (!can_do_mlock())
return -EPERM;
vm_flags |= VM_LOCKED;
}
/* mlock MCL_FUTURE? */
if (vm_flags & VM_LOCKED) {
- unsigned long locked = mm->locked_vm << PAGE_SHIFT;
- locked += len;
- if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
+ 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;
}
return -EINVAL;
}
} else {
- vm_flags |= VM_SHARED | VM_MAYSHARE;
switch (flags & MAP_TYPE) {
- default:
- return -EINVAL;
- case MAP_PRIVATE:
- vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
- /* fall through */
case MAP_SHARED:
+ vm_flags |= VM_SHARED | VM_MAYSHARE;
+ break;
+ case MAP_PRIVATE:
+ /*
+ * Set pgoff according to addr for anon_vma.
+ */
+ pgoff = addr >> PAGE_SHIFT;
break;
+ default:
+ return -EINVAL;
}
}
- error = security_file_mmap(file, prot, flags);
+ error = security_file_mmap(file, reqprot, prot, flags);
if (error)
return error;
}
/* Check against address space limit. */
- if ((mm->total_vm << PAGE_SHIFT) + len
- > current->rlim[RLIMIT_AS].rlim_cur)
+ if (!may_expand_vm(mm, len >> PAGE_SHIFT))
return -ENOMEM;
if (accountable && (!(flags & MAP_NORESERVE) ||
- sysctl_overcommit_memory > 1)) {
+ sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
if (vm_flags & VM_SHARED) {
/* Check memory availability in shmem_file_setup? */
vm_flags |= VM_ACCOUNT;
}
}
- /* Can we just expand an old anonymous mapping? */
- if (!file && !(vm_flags & VM_SHARED) && rb_parent)
- if (vma_merge(mm, prev, rb_parent, addr, addr + len,
- vm_flags, NULL, 0))
- goto out;
+ /*
+ * 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.
+ */
+ if (!file && !(vm_flags & VM_SHARED) &&
+ vma_merge(mm, prev, addr, addr + len, vm_flags,
+ NULL, NULL, pgoff, NULL))
+ goto out;
/*
* Determine the object being mapped and call the appropriate
* specific mapper. the address has already been validated, but
* not unmapped, but the maps are removed from the list.
*/
- vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
- error = -ENOMEM;
- if (!vma)
+ vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ if (!vma) {
+ error = -ENOMEM;
goto unacct_error;
+ }
vma->vm_mm = mm;
vma->vm_start = addr;
vma->vm_end = addr + len;
vma->vm_flags = vm_flags;
vma->vm_page_prot = protection_map[vm_flags & 0x0f];
- vma->vm_ops = NULL;
vma->vm_pgoff = pgoff;
- vma->vm_file = NULL;
- vma->vm_private_data = NULL;
- vma->vm_next = NULL;
- INIT_LIST_HEAD(&vma->shared);
if (file) {
error = -EINVAL;
* f_op->mmap method. -DaveM
*/
addr = vma->vm_start;
+ pgoff = vma->vm_pgoff;
+ vm_flags = vma->vm_flags;
- if (!file || !rb_parent || !vma_merge(mm, prev, rb_parent, addr,
- addr + len, vma->vm_flags, file, pgoff)) {
+ 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);
atomic_inc(&inode->i_writecount);
fput(file);
}
+ mpol_free(vma_policy(vma));
kmem_cache_free(vm_area_cachep, vma);
}
out:
- mm->total_vm += len >> PAGE_SHIFT;
+ vx_vmpages_add(mm, len >> PAGE_SHIFT);
+ vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
if (vm_flags & VM_LOCKED) {
- mm->locked_vm += len >> PAGE_SHIFT;
+ vx_vmlocked_add(mm, len >> PAGE_SHIFT);
make_pages_present(addr, addr + len);
}
if (flags & MAP_POPULATE) {
up_write(&mm->mmap_sem);
- sys_remap_file_pages(addr, len, prot,
+ sys_remap_file_pages(addr, len, 0,
pgoff, flags & MAP_NONBLOCK);
down_write(&mm->mmap_sem);
}
fput(file);
/* Undo any partial mapping done by a device driver. */
- zap_page_range(vma, vma->vm_start, vma->vm_end - vma->vm_start, NULL);
+ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
+ charged = 0;
free_vma:
kmem_cache_free(vm_area_cachep, vma);
unacct_error:
* This function "knows" that -ENOMEM has the bits set.
*/
#ifndef HAVE_ARCH_UNMAPPED_AREA
-static inline unsigned long
+unsigned long
arch_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
(!vma || addr + len <= vma->vm_start))
return addr;
}
- start_addr = addr = mm->free_area_cache;
+ 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) {
* some holes.
*/
if (start_addr != TASK_UNMAPPED_BASE) {
- start_addr = addr = TASK_UNMAPPED_BASE;
+ addr = TASK_UNMAPPED_BASE;
+ start_addr = addr;
+ mm->cached_hole_size = 0;
goto full_search;
}
return -ENOMEM;
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;
}
}
-#else
-extern unsigned long
-arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
- unsigned long, unsigned long);
#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):
+ */
+#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
unsigned long
-get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
- unsigned long pgoff, unsigned long flags)
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
+ const unsigned long len, const unsigned long pgoff,
+ const unsigned long flags)
{
- if (flags & MAP_FIXED) {
- unsigned long ret;
+ struct vm_area_struct *vma;
+ struct mm_struct *mm = current->mm;
+ unsigned long addr = addr0;
- if (addr > TASK_SIZE - len)
- return -ENOMEM;
- if (addr & ~PAGE_MASK)
- return -EINVAL;
- if (file && is_file_hugepages(file)) {
- /*
- * Check if the given range is hugepage aligned, and
- * can be made suitable for hugepages.
- */
- ret = prepare_hugepage_range(addr, len);
- } else {
- /*
- * Ensure that a normal request is not falling in a
- * reserved hugepage range. For some archs like IA-64,
- * there is a separate region for hugepages.
- */
- ret = is_hugepage_only_range(addr, len);
- }
- if (ret)
- return -EINVAL;
- return addr;
+ /* requested length too big for entire address space */
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
+ /* requesting a specific address */
+ if (addr) {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(mm, addr);
+ if (TASK_SIZE - len >= addr &&
+ (!vma || addr + len <= vma->vm_start))
+ return addr;
}
- if (file && file->f_op && file->f_op->get_unmapped_area)
- return file->f_op->get_unmapped_area(file, addr, len,
- pgoff, flags);
+ /* 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);
+ }
- return arch_get_unmapped_area(file, addr, len, pgoff, flags);
-}
+ if (mm->mmap_base < len)
+ goto bottomup;
-EXPORT_SYMBOL(get_unmapped_area);
+ addr = mm->mmap_base-len;
-/* 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 *vma = NULL;
+ 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;
+
+ 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_prot(struct file *file, unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags, int exec)
+{
+ unsigned long ret;
+
+ if (!(flags & MAP_FIXED)) {
+ unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+
+ if (exec && current->mm->get_unmapped_exec_area)
+ get_area = current->mm->get_unmapped_exec_area;
+ else
+ get_area = current->mm->get_unmapped_area;
+
+ if (file && file->f_op && 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))
+ return addr;
+ }
+
+ if (addr > TASK_SIZE - len)
+ return -ENOMEM;
+ if (addr & ~PAGE_MASK)
+ return -EINVAL;
+ if (file && is_file_hugepages(file)) {
+ /*
+ * Check if the given range is hugepage aligned, and
+ * can be made suitable for hugepages.
+ */
+ ret = prepare_hugepage_range(addr, len);
+ } else {
+ /*
+ * Ensure that a normal request is not falling in a
+ * reserved hugepage range. For some archs like IA-64,
+ * there is a separate region for hugepages.
+ */
+ ret = is_hugepage_only_range(current->mm, addr, len);
+ }
+ if (ret)
+ return -EINVAL;
+ return addr;
+}
+
+EXPORT_SYMBOL(get_unmapped_area_prot);
+
+#define SHLIB_BASE 0x00111000
+
+unsigned long arch_get_unmapped_exec_area(struct file *filp, unsigned long addr0,
+ unsigned long len0, unsigned long pgoff, unsigned long flags)
+{
+ unsigned long addr = addr0, len = len0;
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ unsigned long tmp;
+
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
+ if (!addr && !(flags & MAP_FIXED))
+ addr = randomize_range(SHLIB_BASE, 0x01000000, len);
+
+ if (addr) {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(mm, addr);
+ if (TASK_SIZE - len >= addr &&
+ (!vma || addr + len <= vma->vm_start)) {
+ return addr;
+ }
+ }
+
+ addr = SHLIB_BASE;
+ for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
+ /* At this point: (!vma || addr < vma->vm_end). */
+ if (TASK_SIZE - len < addr)
+ return -ENOMEM;
+
+ if (!vma || addr + len <= vma->vm_start) {
+ /*
+ * Must not let a PROT_EXEC mapping get into the
+ * brk area:
+ */
+ if (addr + len > mm->brk)
+ goto failed;
+
+ /*
+ * Up until the brk area we randomize addresses
+ * as much as possible:
+ */
+ if (addr >= 0x01000000) {
+ tmp = randomize_range(0x01000000, PAGE_ALIGN(max(mm->start_brk, (unsigned long)0x08000000)), len);
+ vma = find_vma(mm, tmp);
+ if (TASK_SIZE - len >= tmp &&
+ (!vma || tmp + len <= vma->vm_start))
+ return tmp;
+ }
+ /*
+ * Ok, randomization didnt work out - return
+ * the result of the linear search:
+ */
+ return addr;
+ }
+ addr = vma->vm_end;
+ }
+
+failed:
+ return current->mm->get_unmapped_area(filp, addr0, len0, pgoff, flags);
+}
+
+
+/* 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 *vma = NULL;
if (mm) {
/* Check the cache first. */
return prev ? prev->vm_next : vma;
}
-#ifdef CONFIG_STACK_GROWSUP
+static int over_stack_limit(unsigned long sz)
+{
+ if (sz < EXEC_STACK_BIAS)
+ return 0;
+ return (sz - EXEC_STACK_BIAS) >
+ current->signal->rlim[RLIMIT_STACK].rlim_cur;
+}
+
/*
- * vma is the first one with address > vma->vm_end. Have to extend vma.
+ * Verify that the stack growth is acceptable and
+ * update accounting. This is shared with both the
+ * grow-up and grow-down cases.
*/
-int expand_stack(struct vm_area_struct * vma, unsigned long address)
+static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, unsigned long grow)
{
- unsigned long grow;
+ struct mm_struct *mm = vma->vm_mm;
+ struct rlimit *rlim = current->signal->rlim;
+
+ /* address space limit tests */
+ if (!may_expand_vm(mm, grow))
+ return -ENOMEM;
+
+ /* Stack limit test */
+ if (over_stack_limit(size))
+ return -ENOMEM;
+
+ /* mlock limit tests */
+ if (vma->vm_flags & VM_LOCKED) {
+ unsigned long locked;
+ unsigned long limit;
+ locked = mm->locked_vm + grow;
+ limit = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+ if (locked > limit && !capable(CAP_IPC_LOCK))
+ return -ENOMEM;
+ }
+
+ /*
+ * Overcommit.. This must be the final test, as it will
+ * update security statistics.
+ */
+ if (security_vm_enough_memory(grow))
+ return -ENOMEM;
+
+ /* Ok, everything looks good - let it rip */
+ vx_vmpages_add(mm, grow);
+ if (vma->vm_flags & VM_LOCKED)
+ vx_vmlocked_add(mm, grow);
+ vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow);
+ return 0;
+}
+
+#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64)
+/*
+ * 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;
if (!(vma->vm_flags & VM_GROWSUP))
return -EFAULT;
+ /*
+ * We must make sure the anon_vma is allocated
+ * so that the anon_vma locking is not a noop.
+ */
+ if (unlikely(anon_vma_prepare(vma)))
+ return -ENOMEM;
+ anon_vma_lock(vma);
+
/*
* vma->vm_start/vm_end cannot change under us because the caller
- * is required to hold the mmap_sem in read mode. We need to get
- * the spinlock only before relocating the vma range ourself.
+ * is required to hold the mmap_sem in read mode. We need the
+ * anon_vma lock to serialize against concurrent expand_stacks.
*/
address += 4 + PAGE_SIZE - 1;
address &= PAGE_MASK;
- spin_lock(&vma->vm_mm->page_table_lock);
- grow = (address - vma->vm_end) >> PAGE_SHIFT;
+ error = 0;
- /* Overcommit.. */
- if (security_vm_enough_memory(grow)) {
- spin_unlock(&vma->vm_mm->page_table_lock);
- return -ENOMEM;
- }
-
- if (address - vma->vm_start > current->rlim[RLIMIT_STACK].rlim_cur ||
- ((vma->vm_mm->total_vm + grow) << PAGE_SHIFT) >
- current->rlim[RLIMIT_AS].rlim_cur) {
- spin_unlock(&vma->vm_mm->page_table_lock);
- vm_unacct_memory(grow);
- return -ENOMEM;
+ /* Somebody else might have raced and expanded it already */
+ if (address > vma->vm_end) {
+ unsigned long size, grow;
+
+ 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;
}
- vma->vm_end = address;
- vma->vm_mm->total_vm += grow;
- if (vma->vm_flags & VM_LOCKED)
- vma->vm_mm->locked_vm += grow;
- spin_unlock(&vma->vm_mm->page_table_lock);
- return 0;
+ anon_vma_unlock(vma);
+ return error;
+}
+#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */
+
+#ifdef CONFIG_STACK_GROWSUP
+int expand_stack(struct vm_area_struct *vma, unsigned long address)
+{
+ return expand_upwards(vma, address);
}
struct vm_area_struct *
*/
int expand_stack(struct vm_area_struct *vma, unsigned long address)
{
- unsigned long grow;
+ int error;
+
+ /*
+ * We must make sure the anon_vma is allocated
+ * so that the anon_vma locking is not a noop.
+ */
+ if (unlikely(anon_vma_prepare(vma)))
+ return -ENOMEM;
+ anon_vma_lock(vma);
/*
* vma->vm_start/vm_end cannot change under us because the caller
- * is required to hold the mmap_sem in read mode. We need to get
- * the spinlock only before relocating the vma range ourself.
+ * is required to hold the mmap_sem in read mode. We need the
+ * anon_vma lock to serialize against concurrent expand_stacks.
*/
address &= PAGE_MASK;
- spin_lock(&vma->vm_mm->page_table_lock);
- grow = (vma->vm_start - address) >> PAGE_SHIFT;
+ error = 0;
- /* Overcommit.. */
- if (security_vm_enough_memory(grow)) {
- spin_unlock(&vma->vm_mm->page_table_lock);
- return -ENOMEM;
- }
-
- if (vma->vm_end - address > current->rlim[RLIMIT_STACK].rlim_cur ||
- ((vma->vm_mm->total_vm + grow) << PAGE_SHIFT) >
- current->rlim[RLIMIT_AS].rlim_cur) {
- spin_unlock(&vma->vm_mm->page_table_lock);
- vm_unacct_memory(grow);
- return -ENOMEM;
+ /* Somebody else might have raced and expanded it already */
+ if (address < vma->vm_start) {
+ unsigned long size, grow;
+
+ 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;
+ }
}
- vma->vm_start = address;
- vma->vm_pgoff -= grow;
- vma->vm_mm->total_vm += grow;
- if (vma->vm_flags & VM_LOCKED)
- vma->vm_mm->locked_vm += grow;
- spin_unlock(&vma->vm_mm->page_table_lock);
- return 0;
+ anon_vma_unlock(vma);
+ return error;
}
struct vm_area_struct *
#endif
/*
- * Try to free as many page directory entries as we can,
- * without having to work very hard at actually scanning
- * the page tables themselves.
- *
- * Right now we try to free page tables if we have a nice
- * PGDIR-aligned area that got free'd up. We could be more
- * granular if we want to, but this is fast and simple,
- * and covers the bad cases.
- *
- * "prev", if it exists, points to a vma before the one
- * we just free'd - but there's no telling how much before.
- */
-static void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *prev,
- unsigned long start, unsigned long end)
-{
- unsigned long first = start & PGDIR_MASK;
- unsigned long last = end + PGDIR_SIZE - 1;
- unsigned long start_index, end_index;
- struct mm_struct *mm = tlb->mm;
-
- if (!prev) {
- prev = mm->mmap;
- if (!prev)
- goto no_mmaps;
- if (prev->vm_end > start) {
- if (last > prev->vm_start)
- last = prev->vm_start;
- goto no_mmaps;
- }
- }
- for (;;) {
- struct vm_area_struct *next = prev->vm_next;
-
- if (next) {
- if (next->vm_start < start) {
- prev = next;
- continue;
- }
- if (last > next->vm_start)
- last = next->vm_start;
- }
- if (prev->vm_end > first)
- first = prev->vm_end + PGDIR_SIZE - 1;
- break;
- }
-no_mmaps:
- if (last < first) /* for arches with discontiguous pgd indices */
- return;
- /*
- * If the PGD bits are not consecutive in the virtual address, the
- * old method of shifting the VA >> by PGDIR_SHIFT doesn't work.
- */
- start_index = pgd_index(first);
- if (start_index < FIRST_USER_PGD_NR)
- start_index = FIRST_USER_PGD_NR;
- end_index = pgd_index(last);
- if (end_index > start_index) {
- clear_page_tables(tlb, start_index, end_index - start_index);
- flush_tlb_pgtables(mm, first & PGDIR_MASK, last & PGDIR_MASK);
- }
-}
-
-/* Normal function to fix up a mapping
- * This function is the default for when an area has no specific
- * function. This may be used as part of a more specific routine.
- *
- * By the time this function is called, the area struct has been
- * removed from the process mapping list.
- */
-static void unmap_vma(struct mm_struct *mm, struct vm_area_struct *area)
-{
- size_t len = area->vm_end - area->vm_start;
-
- area->vm_mm->total_vm -= len >> PAGE_SHIFT;
- if (area->vm_flags & VM_LOCKED)
- area->vm_mm->locked_vm -= len >> PAGE_SHIFT;
- /*
- * Is this a new hole at the lowest possible address?
- */
- if (area->vm_start >= TASK_UNMAPPED_BASE &&
- area->vm_start < area->vm_mm->free_area_cache)
- area->vm_mm->free_area_cache = area->vm_start;
-
- remove_shared_vm_struct(area);
-
- if (area->vm_ops && area->vm_ops->close)
- area->vm_ops->close(area);
- if (area->vm_file)
- fput(area->vm_file);
- kmem_cache_free(vm_area_cachep, area);
-}
-
-/*
- * Update the VMA and inode share lists.
- *
- * Ok - we have the memory areas we should free on the 'free' list,
+ * Ok - we have the memory areas we should free on the vma list,
* so release them, and do the vma updates.
+ *
+ * Called with the mm semaphore held.
*/
-static void unmap_vma_list(struct mm_struct *mm,
- struct vm_area_struct *mpnt)
+static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
{
+ /* Update high watermark before we lower total_vm */
+ update_hiwater_vm(mm);
do {
- struct vm_area_struct *next = mpnt->vm_next;
- unmap_vma(mm, mpnt);
- mpnt = next;
- } while (mpnt != NULL);
+ long nrpages = vma_pages(vma);
+
+ vx_vmpages_sub(mm, nrpages);
+ if (vma->vm_flags & VM_LOCKED)
+ vx_vmlocked_sub(mm, nrpages);
+ vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages);
+ vma = remove_vma(vma);
+ } while (vma);
validate_mm(mm);
}
/*
* Get rid of page table information in the indicated region.
*
- * Called with the page table lock held.
+ * Called with the mm semaphore held.
*/
static void unmap_region(struct mm_struct *mm,
- struct vm_area_struct *vma,
- struct vm_area_struct *prev,
- unsigned long start,
- unsigned long end)
+ struct vm_area_struct *vma, struct vm_area_struct *prev,
+ 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;
lru_add_drain();
tlb = tlb_gather_mmu(mm, 0);
- unmap_vmas(&tlb, mm, vma, start, end, &nr_accounted, NULL);
+ update_hiwater_rss(mm);
+ unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL);
vm_unacct_memory(nr_accounted);
-
- if (is_hugepage_only_range(start, end - start))
- hugetlb_free_pgtables(tlb, prev, start, end);
- else
- free_pgtables(tlb, prev, start, end);
+ free_pgtables(&tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
+ next? next->vm_start: 0);
tlb_finish_mmu(tlb, start, end);
}
/*
* Create a list of vma's touched by the unmap, removing them from the mm's
* vma list as we go..
- *
- * Called with the page_table_lock held.
*/
static void
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);
do {
} while (vma && vma->vm_start < end);
*insertion_point = vma;
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. */
}
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;
- struct address_space *mapping = NULL;
+
+ if (is_vm_hugetlb_page(vma) && (addr & ~HPAGE_MASK))
+ return -EINVAL;
if (mm->map_count >= sysctl_max_map_count)
return -ENOMEM;
/* most fields are the same, copy all, and then fixup */
*new = *vma;
- INIT_LIST_HEAD(&new->shared);
-
if (new_below)
new->vm_end = addr;
else {
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);
+
if (new->vm_file)
get_file(new->vm_file);
if (new->vm_ops && new->vm_ops->open)
new->vm_ops->open(new);
- if (vma->vm_file)
- mapping = vma->vm_file->f_mapping;
-
- if (mapping)
- down(&mapping->i_shared_sem);
- spin_lock(&mm->page_table_lock);
-
if (new_below) {
- vma->vm_start = addr;
- vma->vm_pgoff += ((addr - new->vm_start) >> PAGE_SHIFT);
- } else
- vma->vm_end = addr;
+ unsigned long old_end = vma->vm_end;
- __insert_vm_struct(mm, new);
-
- spin_unlock(&mm->page_table_lock);
- if (mapping)
- up(&mapping->i_shared_sem);
+ vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff +
+ ((addr - new->vm_start) >> PAGE_SHIFT), new);
+ if (vma->vm_flags & VM_EXEC)
+ arch_remove_exec_range(mm, old_end);
+ } else
+ vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new);
return 0;
}
int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
{
unsigned long end;
- struct vm_area_struct *mpnt, *prev, *last;
+ struct vm_area_struct *vma, *prev, *last;
if ((start & ~PAGE_MASK) || start > TASK_SIZE || len > TASK_SIZE-start)
return -EINVAL;
return -EINVAL;
/* Find the first overlapping VMA */
- mpnt = find_vma_prev(mm, start, &prev);
- if (!mpnt)
+ vma = find_vma_prev(mm, start, &prev);
+ if (!vma)
return 0;
- /* we have start < mpnt->vm_end */
-
- if (is_vm_hugetlb_page(mpnt)) {
- int ret = is_aligned_hugepage_range(start, len);
-
- if (ret)
- return ret;
- }
+ /* we have start < vma->vm_end */
/* if it doesn't overlap, we have nothing.. */
end = start + len;
- if (mpnt->vm_start >= end)
+ if (vma->vm_start >= end)
return 0;
- /* Something will probably happen, so notify. */
- if (mpnt->vm_file && (mpnt->vm_flags & VM_EXEC))
- profile_exec_unmap(mm);
-
/*
* If we need to split any vma, do it now to save pain later.
*
* unmapped vm_area_struct will remain in use: so lower split_vma
* places tmp vma above, and higher split_vma places tmp vma below.
*/
- if (start > mpnt->vm_start) {
- if (split_vma(mm, mpnt, start, 0))
- return -ENOMEM;
- prev = mpnt;
+ if (start > vma->vm_start) {
+ int error = split_vma(mm, vma, start, 0);
+ if (error)
+ return error;
+ prev = vma;
}
/* Does it split the last one? */
last = find_vma(mm, end);
if (last && end > last->vm_start) {
- if (split_vma(mm, last, end, 1))
- return -ENOMEM;
+ int error = split_vma(mm, last, end, 1);
+ if (error)
+ return error;
}
- mpnt = prev? prev->vm_next: mm->mmap;
+ vma = prev? prev->vm_next: mm->mmap;
/*
* Remove the vma's, and unmap the actual pages
*/
- spin_lock(&mm->page_table_lock);
- detach_vmas_to_be_unmapped(mm, mpnt, prev, end);
- unmap_region(mm, mpnt, prev, start, end);
- spin_unlock(&mm->page_table_lock);
+ detach_vmas_to_be_unmapped(mm, vma, prev, end);
+ unmap_region(mm, vma, prev, start, end);
/* Fix up all other VM information */
- unmap_vma_list(mm, mpnt);
+ remove_vma_list(mm, vma);
return 0;
}
int ret;
struct mm_struct *mm = current->mm;
+ profile_munmap(addr);
+
down_write(&mm->mmap_sem);
ret = do_munmap(mm, addr, len);
up_write(&mm->mmap_sem);
return ret;
}
+static inline void verify_mm_writelocked(struct mm_struct *mm)
+{
+#ifdef CONFIG_DEBUG_VM
+ if (unlikely(down_read_trylock(&mm->mmap_sem))) {
+ WARN_ON(1);
+ up_read(&mm->mmap_sem);
+ }
+#endif
+}
+
/*
* this is really a simplified "do_mmap". it only handles
* anonymous maps. eventually we may be able to do some
struct vm_area_struct * vma, * prev;
unsigned long flags;
struct rb_node ** rb_link, * rb_parent;
+ pgoff_t pgoff = addr >> PAGE_SHIFT;
len = PAGE_ALIGN(len);
if (!len)
* mlock MCL_FUTURE?
*/
if (mm->def_flags & VM_LOCKED) {
- unsigned long locked = mm->locked_vm << PAGE_SHIFT;
- locked += len;
- if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
+ 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;
+ if (!vx_vmlocked_avail(mm, len >> PAGE_SHIFT))
+ return -ENOMEM;
}
+ /*
+ * mm->mmap_sem is required to protect against another thread
+ * changing the mappings in case we sleep.
+ */
+ verify_mm_writelocked(mm);
+
/*
* Clear old maps. this also does some error checking for us
*/
}
/* Check against address space limits *after* clearing old maps... */
- if ((mm->total_vm << PAGE_SHIFT) + len
- > current->rlim[RLIMIT_AS].rlim_cur)
+ if (!may_expand_vm(mm, len >> PAGE_SHIFT))
return -ENOMEM;
if (mm->map_count > sysctl_max_map_count)
return -ENOMEM;
- if (security_vm_enough_memory(len >> PAGE_SHIFT))
+ if (security_vm_enough_memory(len >> PAGE_SHIFT) ||
+ !vx_vmpages_avail(mm, len >> PAGE_SHIFT))
return -ENOMEM;
flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
- /* Can we just expand an old anonymous mapping? */
- if (rb_parent && vma_merge(mm, prev, rb_parent, addr, addr + len,
- flags, NULL, 0))
+ /* Can we just expand an old private anonymous mapping? */
+ if (vma_merge(mm, prev, addr, addr + len, flags,
+ NULL, NULL, pgoff, NULL))
goto out;
/*
* create a vma struct for an anonymous mapping
*/
- vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
if (!vma) {
vm_unacct_memory(len >> PAGE_SHIFT);
return -ENOMEM;
vma->vm_mm = mm;
vma->vm_start = addr;
vma->vm_end = addr + len;
+ vma->vm_pgoff = pgoff;
vma->vm_flags = flags;
vma->vm_page_prot = protection_map[flags & 0x0f];
- vma->vm_ops = NULL;
- vma->vm_pgoff = 0;
- vma->vm_file = NULL;
- vma->vm_private_data = NULL;
- INIT_LIST_HEAD(&vma->shared);
-
vma_link(mm, vma, prev, rb_link, rb_parent);
-
out:
- mm->total_vm += len >> PAGE_SHIFT;
+ vx_vmpages_add(mm, len >> PAGE_SHIFT);
if (flags & VM_LOCKED) {
- mm->locked_vm += len >> PAGE_SHIFT;
+ vx_vmlocked_add(mm, len >> PAGE_SHIFT);
make_pages_present(addr, addr + len);
}
return addr;
void exit_mmap(struct mm_struct *mm)
{
struct mmu_gather *tlb;
- struct vm_area_struct *vma;
+ struct vm_area_struct *vma = mm->mmap;
unsigned long nr_accounted = 0;
+ unsigned long end;
- profile_exit_mmap(mm);
-
lru_add_drain();
-
- spin_lock(&mm->page_table_lock);
-
- tlb = tlb_gather_mmu(mm, 1);
flush_cache_mm(mm);
- /* Use ~0UL here to ensure all VMAs in the mm are unmapped */
- mm->map_count -= unmap_vmas(&tlb, mm, mm->mmap, 0,
- ~0UL, &nr_accounted, NULL);
+ tlb = tlb_gather_mmu(mm, 1);
+ /* Don't update_hiwater_rss(mm) here, do_exit already did */
+ /* 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);
- BUG_ON(mm->map_count); /* This is just debugging */
- clear_page_tables(tlb, FIRST_USER_PGD_NR, USER_PTRS_PER_PGD);
- tlb_finish_mmu(tlb, 0, MM_VM_SIZE(mm));
-
- vma = mm->mmap;
- mm->mmap = mm->mmap_cache = NULL;
- mm->mm_rb = RB_ROOT;
- mm->rss = 0;
- mm->total_vm = 0;
- mm->locked_vm = 0;
+ free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
+ tlb_finish_mmu(tlb, 0, end);
+ arch_flush_exec_range(mm);
- spin_unlock(&mm->page_table_lock);
+ set_mm_counter(mm, file_rss, 0);
+ set_mm_counter(mm, anon_rss, 0);
+ vx_vmpages_sub(mm, mm->total_vm);
+ vx_vmlocked_sub(mm, mm->locked_vm);
/*
- * Walk the list again, actually closing and freeing it
- * without holding any MM locks.
+ * Walk the list again, actually closing and freeing it,
+ * with preemption enabled, without holding any MM locks.
*/
- while (vma) {
- struct vm_area_struct *next = vma->vm_next;
- remove_shared_vm_struct(vma);
- if (vma->vm_ops) {
- if (vma->vm_ops->close)
- vma->vm_ops->close(vma);
- }
- if (vma->vm_file)
- fput(vma->vm_file);
- kmem_cache_free(vm_area_cachep, vma);
- vma = next;
- }
+ while (vma)
+ vma = remove_vma(vma);
+
+ BUG_ON(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 ring. If vm_file is non-NULL
- * then i_shared_sem is taken here.
+ * and into the inode's i_mmap tree. If vm_file is non-NULL
+ * then i_mmap_lock is taken here.
*/
-void 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;
+ /*
+ * The vm_pgoff of a purely anonymous vma should be irrelevant
+ * until its first write fault, when page's anon_vma and index
+ * are set. But now set the vm_pgoff it will almost certainly
+ * end up with (unless mremap moves it elsewhere before that
+ * first wfault), so /proc/pid/maps tells a consistent story.
+ *
+ * By setting it to reflect the virtual start address of the
+ * vma, merges and splits can happen in a seamless way, just
+ * using the existing file pgoff checks and manipulations.
+ * Similarly in do_mmap_pgoff and in do_brk.
+ */
+ if (!vma->vm_file) {
+ 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)
- BUG();
+ return -ENOMEM;
+ if ((vma->vm_flags & VM_ACCOUNT) &&
+ (security_vm_enough_memory(vma_pages(vma)) ||
+ !vx_vmpages_avail(mm, vma_pages(vma))))
+ return -ENOMEM;
vma_link(mm, vma, prev, rb_link, rb_parent);
+ return 0;
}
/*
* 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, unsigned long pgoff)
+ unsigned long addr, unsigned long len, pgoff_t pgoff)
{
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;
+
+ /*
+ * 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)
+ pgoff = addr >> PAGE_SHIFT;
find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
- new_vma = vma_merge(mm, prev, rb_parent, addr, addr + len,
- vma->vm_flags, vma->vm_file, pgoff);
+ 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
new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
if (new_vma) {
*new_vma = *vma;
- INIT_LIST_HEAD(&new_vma->shared);
+ 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;
}
return new_vma;
}
+
+/*
+ * Return true if the calling process may expand its vm space by the passed
+ * number of pages
+ */
+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;
+
+ if (cur + npages > lim)
+ return 0;
+ if (!vx_vmpages_avail(mm, npages))
+ return 0;
+ return 1;
+}
+
+
+static struct page *
+special_mapping_nopage(struct vm_area_struct *vma,
+ unsigned long address, int *type)
+{
+ struct page **pages;
+
+ BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+
+ address -= vma->vm_start;
+ for (pages = vma->vm_private_data; address > 0 && *pages; ++pages)
+ address -= PAGE_SIZE;
+
+ if (*pages) {
+ get_page(*pages);
+ return *pages;
+ }
+
+ return NOPAGE_SIGBUS;
+}
+
+static struct vm_operations_struct special_mapping_vmops = {
+ .nopage = special_mapping_nopage,
+};
+
+unsigned int vdso_populate = 1;
+
+/*
+ * Insert a new vma covering the given region, with the given flags and
+ * protections. Its pages are supplied by the given null-terminated array.
+ * The region past the last page supplied will always produce SIGBUS.
+ * The array pointer and the pages it points to are assumed to stay alive
+ * for as long as this mapping might exist.
+ */
+int install_special_mapping(struct mm_struct *mm,
+ unsigned long addr, unsigned long len,
+ unsigned long vm_flags, pgprot_t pgprot,
+ struct page **pages)
+{
+ struct vm_area_struct *vma;
+ int err;
+
+ vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+ if (unlikely(vma == NULL))
+ return -ENOMEM;
+ memset(vma, 0, sizeof(*vma));
+
+ vma->vm_mm = mm;
+ vma->vm_start = addr;
+ vma->vm_end = addr + len;
+
+ vma->vm_flags = vm_flags;
+ vma->vm_page_prot = pgprot;
+
+ vma->vm_ops = &special_mapping_vmops;
+ vma->vm_private_data = pages;
+
+ insert_vm_struct(mm, vma);
+ mm->total_vm += len >> PAGE_SHIFT;
+
+ if (!vdso_populate)
+ return 0;
+
+ err = 0;
+ while (*pages) {
+ struct page *page = *pages++;
+ get_page(page);
+ err = install_page(mm, vma, addr, page, vma->vm_page_prot);
+ if (err) {
+ put_page(page);
+ break;
+ }
+ addr += PAGE_SIZE;
+ }
+
+ return err;
+}