summaryrefslogtreecommitdiff
path: root/mm/mmap.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/mmap.c')
-rw-r--r--mm/mmap.c71
1 files changed, 56 insertions, 15 deletions
diff --git a/mm/mmap.c b/mm/mmap.c
index f19efcf75418..924839fac0e6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -44,6 +44,7 @@
#include <linux/userfaultfd_k.h>
#include <linux/moduleparam.h>
#include <linux/pkeys.h>
+#include <linux/oom.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
@@ -684,7 +685,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *next = vma->vm_next, *orig_vma = vma;
struct address_space *mapping = NULL;
- struct rb_root *root = NULL;
+ struct rb_root_cached *root = NULL;
struct anon_vma *anon_vma = NULL;
struct file *file = vma->vm_file;
bool start_changed = false, end_changed = false;
@@ -1386,9 +1387,24 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
if (file) {
struct inode *inode = file_inode(file);
+ unsigned long flags_mask;
+
+ flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
switch (flags & MAP_TYPE) {
case MAP_SHARED:
+ /*
+ * Force use of MAP_SHARED_VALIDATE with non-legacy
+ * flags. E.g. MAP_SYNC is dangerous to use with
+ * MAP_SHARED as you don't know which consistency model
+ * you will get. We silently ignore unsupported flags
+ * with MAP_SHARED to preserve backward compatibility.
+ */
+ flags &= LEGACY_MAP_MASK;
+ /* fall through */
+ case MAP_SHARED_VALIDATE:
+ if (flags & ~flags_mask)
+ return -EOPNOTSUPP;
if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
return -EACCES;
@@ -2639,13 +2655,6 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
if (vma->vm_start >= end)
return 0;
- if (uf) {
- int error = userfaultfd_unmap_prep(vma, start, end, uf);
-
- if (error)
- return error;
- }
-
/*
* If we need to split any vma, do it now to save pain later.
*
@@ -2679,6 +2688,21 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
}
vma = prev ? prev->vm_next : mm->mmap;
+ if (unlikely(uf)) {
+ /*
+ * If userfaultfd_unmap_prep returns an error the vmas
+ * will remain splitted, but userland will get a
+ * highly unexpected error anyway. This is no
+ * different than the case where the first of the two
+ * __split_vma fails, but we don't undo the first
+ * split, despite we could. This is unlikely enough
+ * failure that it's not worth optimizing it for.
+ */
+ int error = userfaultfd_unmap_prep(vma, start, end, uf);
+ if (error)
+ return error;
+ }
+
/*
* unlock any mlock()ed ranges before detaching vmas
*/
@@ -2993,6 +3017,23 @@ void exit_mmap(struct mm_struct *mm)
/* Use -1 here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, vma, 0, -1);
+ set_bit(MMF_OOM_SKIP, &mm->flags);
+ if (unlikely(tsk_is_oom_victim(current))) {
+ /*
+ * Wait for oom_reap_task() to stop working on this
+ * mm. Because MMF_OOM_SKIP is already set before
+ * calling down_read(), oom_reap_task() will not run
+ * on this "mm" post up_write().
+ *
+ * tsk_is_oom_victim() cannot be set from under us
+ * either because current->mm is already set to NULL
+ * under task_lock before calling mmput and oom_mm is
+ * set not NULL by the OOM killer only if current->mm
+ * is found not NULL while holding the task_lock.
+ */
+ down_write(&mm->mmap_sem);
+ up_write(&mm->mmap_sem);
+ }
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
tlb_finish_mmu(&tlb, 0, -1);
@@ -3314,7 +3355,7 @@ 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)) {
+ if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) {
/*
* The LSB of head.next can't change from under us
* because we hold the mm_all_locks_mutex.
@@ -3330,7 +3371,7 @@ static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
* anon_vma->root->rwsem.
*/
if (__test_and_set_bit(0, (unsigned long *)
- &anon_vma->root->rb_root.rb_node))
+ &anon_vma->root->rb_root.rb_root.rb_node))
BUG();
}
}
@@ -3432,7 +3473,7 @@ out_unlock:
static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
{
- if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_node)) {
+ if (test_bit(0, (unsigned long *) &anon_vma->root->rb_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.
@@ -3446,7 +3487,7 @@ static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
* anon_vma->root->rwsem.
*/
if (!__test_and_clear_bit(0, (unsigned long *)
- &anon_vma->root->rb_root.rb_node))
+ &anon_vma->root->rb_root.rb_root.rb_node))
BUG();
anon_vma_unlock_write(anon_vma);
}
@@ -3514,7 +3555,7 @@ static int init_user_reserve(void)
{
unsigned long free_kbytes;
- free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
+ free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17);
return 0;
@@ -3535,7 +3576,7 @@ static int init_admin_reserve(void)
{
unsigned long free_kbytes;
- free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
+ free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13);
return 0;
@@ -3579,7 +3620,7 @@ static int reserve_mem_notifier(struct notifier_block *nb,
break;
case MEM_OFFLINE:
- free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
+ free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
if (sysctl_user_reserve_kbytes > free_kbytes) {
init_user_reserve();
generated by cgit v1.2.3 (git 2.46.0) at 2025-09-07 22:49:03 +0000