__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;
atomic_t vm_committed_space = ATOMIC_INIT(0);
{
struct file *file = vma->vm_file;
+ might_sleep();
if (file) {
struct address_space *mapping = file->f_mapping;
spin_lock(&mapping->i_mmap_lock);
flush_dcache_mmap_lock(mapping);
if (unlikely(vma->vm_flags & VM_NONLINEAR))
- list_add_tail(&vma->shared.vm_set.list,
- &mapping->i_mmap_nonlinear);
+ vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
else
vma_prio_tree_insert(vma, &mapping->i_mmap);
flush_dcache_mmap_unlock(mapping);
}
if (root) {
- if (adjust_next) {
- vma_prio_tree_init(next);
+ if (adjust_next)
vma_prio_tree_insert(next, root);
- }
- vma_prio_tree_init(vma);
vma_prio_tree_insert(vma, root);
flush_dcache_mmap_unlock(mapping);
}
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);
+
+#ifdef CONFIG_HUGETLB
+ if (flags & VM_HUGETLB) {
+ if (!(flags & VM_DONTCOPY))
+ mm->shared_vm += pages;
+ return;
+ }
+#endif /* CONFIG_HUGETLB */
+
+ if (file)
+ mm->shared_vm += pages;
+ else if (flags & stack_flags)
+ mm->stack_vm += pages;
+ if (flags & VM_EXEC)
+ mm->exec_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 accountable = 1;
unsigned long charged = 0;
- /*
- * Does the application expect PROT_READ to imply PROT_EXEC:
- */
- if (unlikely((prot & PROT_READ) &&
- (current->personality & READ_IMPLIES_EXEC)))
- prot |= PROT_EXEC;
-
if (file) {
if (is_file_hugepages(file))
accountable = 0;
(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;
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;
+ unsigned long locked, lock_limit;
+ locked = mm->locked_vm << PAGE_SHIFT;
+ lock_limit = current->rlim[RLIMIT_MEMLOCK].rlim_cur;
locked += len;
- if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
+ if (locked > lock_limit && !capable(CAP_IPC_LOCK))
return -EAGAIN;
}
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;
pgoff, flags & MAP_NONBLOCK);
down_write(&mm->mmap_sem);
}
+ __vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
return addr;
unmap_and_free_vma:
* 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)
{
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 vm_area_struct *area)
+{
+ /*
+ * 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;
+}
+
+/*
+ * 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
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
+ const unsigned long len, const unsigned long pgoff,
+ const unsigned long flags)
+{
+ struct vm_area_struct *vma, *prev_vma;
+ struct mm_struct *mm = current->mm;
+ unsigned long base = mm->mmap_base, addr = addr0;
+ int first_time = 1;
+
+ /* requested length too big for entire address space */
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
+ /* dont allow allocations above current base */
+ if (mm->free_area_cache > base)
+ mm->free_area_cache = base;
+
+ /* 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;
+ }
+
+try_again:
+ /* make sure it can fit in the remaining address space */
+ if (mm->free_area_cache < len)
+ goto fail;
+
+ /* either no address requested or cant fit in requested address hole */
+ addr = (mm->free_area_cache - len) & PAGE_MASK;
+ do {
+ /*
+ * Lookup failure means no vma is above this address,
+ * i.e. return with success:
+ */
+ if (!(vma = find_vma_prev(mm, addr, &prev_vma)))
+ return addr;
+
+ /*
+ * new region fits between prev_vma->vm_end and
+ * vma->vm_start, use it:
+ */
+ if (addr+len <= vma->vm_start &&
+ (!prev_vma || (addr >= prev_vma->vm_end)))
+ /* remember the address as a hint for next time */
+ return (mm->free_area_cache = addr);
+ else
+ /* pull free_area_cache down to the first hole */
+ if (mm->free_area_cache == vma->vm_end)
+ mm->free_area_cache = vma->vm_start;
+
+ /* try just below the current vma->vm_start */
+ addr = vma->vm_start-len;
+ } while (len <= vma->vm_start);
+
+fail:
+ /*
+ * if hint left us with no space for the requested
+ * mapping then try again:
+ */
+ if (first_time) {
+ mm->free_area_cache = base;
+ first_time = 0;
+ goto try_again;
+ }
+ /*
+ * 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->free_area_cache = TASK_UNMAPPED_BASE;
+ addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
+ /*
+ * Restore the topdown base:
+ */
+ mm->free_area_cache = base;
+
+ return addr;
+}
+#endif
+
+void arch_unmap_area_topdown(struct vm_area_struct *area)
+{
+ /*
+ * Is this a new hole at the highest possible address?
+ */
+ if (area->vm_end > area->vm_mm->free_area_cache)
+ area->vm_mm->free_area_cache = area->vm_end;
+}
+
unsigned long
get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
return file->f_op->get_unmapped_area(file, addr, len,
pgoff, flags);
- return arch_get_unmapped_area(file, addr, len, pgoff, flags);
+ return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
}
EXPORT_SYMBOL(get_unmapped_area);
if (vma->vm_flags & VM_LOCKED)
// vma->vm_mm->locked_vm += grow;
vx_vmlocked_add(vma->vm_mm, grow);
+ __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, grow);
anon_vma_unlock(vma);
return 0;
}
if (vma->vm_flags & VM_LOCKED)
// vma->vm_mm->locked_vm += grow;
vx_vmlocked_add(vma->vm_mm, grow);
+ __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, grow);
anon_vma_unlock(vma);
return 0;
}
// area->vm_mm->total_vm -= len >> PAGE_SHIFT;
vx_vmpages_sub(area->vm_mm, len >> PAGE_SHIFT);
-
+
if (area->vm_flags & VM_LOCKED)
// area->vm_mm->locked_vm -= len >> PAGE_SHIFT;
vx_vmlocked_sub(area->vm_mm, 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;
-
+ vm_stat_unaccount(area);
+ area->vm_mm->unmap_area(area);
remove_vm_struct(area);
}
/* most fields are the same, copy all, and then fixup */
*new = *vma;
- vma_prio_tree_init(new);
if (new_below)
new->vm_end = addr;
if (mpnt->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.
*
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);
* mlock MCL_FUTURE?
*/
if (mm->def_flags & VM_LOCKED) {
- unsigned long locked = mm->locked_vm << PAGE_SHIFT;
+ unsigned long locked, lock_limit;
+ locked = mm->locked_vm << PAGE_SHIFT;
+ lock_limit = current->rlim[RLIMIT_MEMLOCK].rlim_cur;
locked += len;
- if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
+ if (locked > lock_limit && !capable(CAP_IPC_LOCK))
return -EAGAIN;
if (!vx_vmlocked_avail(mm, len >> PAGE_SHIFT))
return -ENOMEM;
struct vm_area_struct *vma;
unsigned long nr_accounted = 0;
- profile_exit_mmap(mm);
-
lru_add_drain();
spin_lock(&mm->page_table_lock);
new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
if (new_vma) {
*new_vma = *vma;
- vma_prio_tree_init(new_vma);
pol = mpol_copy(vma_policy(vma));
if (IS_ERR(pol)) {
kmem_cache_free(vm_area_cachep, new_vma);