#include <linux/mempolicy.h>
#include <linux/rmap.h>
#include <linux/mmu_notifier.h>
+#include <linux/perf_event.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
-atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
+struct percpu_counter vm_committed_as;
/*
* Check that a process has enough memory to allocate a new virtual
if (mm)
allowed -= mm->total_vm / 32;
- /*
- * cast `allowed' as a signed long because vm_committed_space
- * sometimes has a negative value
- */
- if (atomic_long_read(&vm_committed_space) < (long)allowed)
+ if (percpu_counter_read_positive(&vm_committed_as) < allowed)
return 0;
error:
vm_unacct_memory(pages);
/*
* When changing only vma->vm_end, we don't really need
- * anon_vma lock: but is that case worth optimizing out?
+ * anon_vma lock.
*/
- if (vma->anon_vma)
+ if (vma->anon_vma && (insert || importer || start != vma->vm_start))
anon_vma = vma->anon_vma;
if (anon_vma) {
spin_lock(&anon_vma->lock);
validate_mm(mm);
}
-/* Flags that can be inherited from an existing mapping when merging */
-#define VM_MERGEABLE_FLAGS (VM_CAN_NONLINEAR)
-
/*
* 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.
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_MERGEABLE_FLAGS)
+ /* VM_CAN_NONLINEAR may get set later by f_op->mmap() */
+ if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR)
return 0;
if (vma->vm_file != file)
return 0;
#endif /* CONFIG_PROC_FS */
/*
- * The caller must hold down_write(current->mm->mmap_sem).
+ * The caller must hold down_write(¤t->mm->mmap_sem).
*/
unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
struct inode *inode;
unsigned int vm_flags;
int error;
- int accountable = 1;
unsigned long reqprot = prot;
/*
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? */
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) {
return -EPERM;
vm_flags &= ~VM_MAYEXEC;
}
- if (is_file_hugepages(file))
- accountable = 0;
if (!file->f_op || !file->f_op->mmap)
return -ENODEV;
if (error)
return error;
- return mmap_region(file, addr, len, flags, vm_flags, pgoff,
- accountable);
+ return mmap_region(file, addr, len, flags, vm_flags, pgoff);
}
EXPORT_SYMBOL(do_mmap_pgoff);
+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)) {
+ if (unlikely(flags & MAP_HUGETLB))
+ return -EINVAL;
+ file = fget(fd);
+ if (!file)
+ goto out;
+ } else if (flags & MAP_HUGETLB) {
+ struct user_struct *user = NULL;
+ /*
+ * 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
+ */
+ len = ALIGN(len, huge_page_size(&default_hstate));
+ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
+ &user, HUGETLB_ANONHUGE_INODE);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+ }
+
+ flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+ down_write(¤t->mm->mmap_sem);
+ retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ up_write(¤t->mm->mmap_sem);
+
+ if (file)
+ fput(file);
+out:
+ return retval;
+}
+
/*
* Some shared mappigns will want the pages marked read-only
* to track write events. If so, we'll downgrade vm_page_prot
/*
* We account for memory if it's a private writeable mapping,
- * and VM_NORESERVE wasn't set.
+ * not hugepages and VM_NORESERVE wasn't set.
*/
-static inline int accountable_mapping(unsigned int vm_flags)
+static inline int accountable_mapping(struct file *file, unsigned int 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 int vm_flags, unsigned long pgoff)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
/*
* Set 'VM_NORESERVE' if we should not account for the
- * memory use of this mapping. We only honor MAP_NORESERVE
- * if we're allowed to overcommit memory.
+ * memory use of this mapping.
*/
- if ((flags & MAP_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER)
- vm_flags |= VM_NORESERVE;
- if (!accountable)
- vm_flags |= VM_NORESERVE;
+ 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;
+ }
/*
* Private writable mapping: check memory availability
*/
- if (accountable_mapping(vm_flags)) {
+ if (accountable_mapping(file, vm_flags)) {
charged = len >> PAGE_SHIFT;
if (security_vm_enough_memory(charged))
return -ENOMEM;
goto unmap_and_free_vma;
if (vm_flags & VM_EXECUTABLE)
added_exe_file_vma(mm);
+
+ /* 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;
} else if (vm_flags & VM_SHARED) {
error = shmem_zero_setup(vma);
if (error)
goto free_vma;
}
- /* 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 (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ }
vma_link(mm, vma, prev, rb_link, rb_parent);
file = vma->vm_file;
if (correct_wcount)
atomic_inc(&inode->i_writecount);
out:
+ perf_event_mmap(vma);
+
mm->total_vm += len >> PAGE_SHIFT;
vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
if (vm_flags & VM_LOCKED) {
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)
get_area = file->f_op->get_unmapped_area;
* 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 */
}
/*
- * 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;
~(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;
return 0;
}
+/*
+ * 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
* what needs doing, and the areas themselves, which do the
* work. This now handles partial unmappings.
* 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;
/* 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;
}
if (!len)
return addr;
- if ((addr + len) > TASK_SIZE || (addr + len) < addr)
- return -EINVAL;
-
- if (is_hugepage_only_range(mm, addr, len))
- return -EINVAL;
-
error = security_file_mmap(NULL, 0, 0, 0, addr, 1);
if (error)
return error;
flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
- error = arch_mmap_check(addr, len, flags);
- if (error)
+ error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
+ if (error & ~PAGE_MASK)
return error;
/*
unsigned long end;
/* mm's last user has gone, and its about to be pulled down */
- arch_exit_mmap(mm);
mmu_notifier_release(mm);
- if (!mm->mmap) /* Can happen if dup_mmap() received an OOM */
- return;
-
if (mm->locked_vm) {
vma = mm->mmap;
while (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);
/* 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);
{
}
-static struct vm_operations_struct special_mapping_vmops = {
+static const struct vm_operations_struct special_mapping_vmops = {
.close = special_mapping_close,
.fault = special_mapping_fault,
};
mm->total_vm += len >> PAGE_SHIFT;
+ perf_event_mmap(vma);
+
return 0;
}
*/
void __init mmap_init(void)
{
- vm_area_cachep = kmem_cache_create("vm_area_struct",
- sizeof(struct vm_area_struct), 0,
- SLAB_PANIC, NULL);
+ int ret;
+
+ ret = percpu_counter_init(&vm_committed_as, 0);
+ VM_BUG_ON(ret);
}