mm, madvise: fail with ENOMEM when splitting vma will hit max_map_count

If madvise(2) advice will result in the underlying vma being split and
the number of areas mapped by the process will exceed
/proc/sys/vm/max_map_count as a result, return ENOMEM instead of EAGAIN.

EAGAIN is returned by madvise(2) when a kernel resource, such as slab,
is temporarily unavailable.  It indicates that userspace should retry
the advice in the near future.  This is important for advice such as
MADV_DONTNEED which is often used by malloc implementations to free
memory back to the system: we really do want to free memory back when
madvise(2) returns EAGAIN because slab allocations (for vmas, anon_vmas,
or mempolicies) cannot be allocated.

Encountering /proc/sys/vm/max_map_count is not a temporary failure,
however, so return ENOMEM to indicate this is a more serious issue.  A
followup patch to the man page will specify this behavior.

Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1701241431120.42507@chino.kir.corp.google.com
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 46 insertions, 13 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index 0012071a6e50..11fc65f81ecd 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -92,14 +92,28 @@ static long madvise_behavior(struct vm_area_struct *vma,
         case MADV_MERGEABLE:
         case MADV_UNMERGEABLE:
                 error = ksm_madvise(vma, start, end, behavior, &new_flags);
-                if (error)
+                if (error) {
+                        /*
+                         * madvise() returns EAGAIN if kernel resources, such as
+                         * slab, are temporarily unavailable.
+                         */
+                        if (error == -ENOMEM)
+                                error = -EAGAIN;
                         goto out;
+                }
                 break;
         case MADV_HUGEPAGE:
         case MADV_NOHUGEPAGE:
                 error = hugepage_madvise(vma, &new_flags, behavior);
-                if (error)
+                if (error) {
+                        /*
+                         * madvise() returns EAGAIN if kernel resources, such as
+                         * slab, are temporarily unavailable.
+                         */
+                        if (error == -ENOMEM)
+                                error = -EAGAIN;
                         goto out;
+                }
                 break;
         }
 
@@ -120,15 +134,37 @@ static long madvise_behavior(struct vm_area_struct *vma,
         *prev = vma;
 
         if (start != vma->vm_start) {
-                error = split_vma(mm, vma, start, 1);
-                if (error)
+                if (unlikely(mm->map_count >= sysctl_max_map_count)) {
+                        error = -ENOMEM;
                         goto out;
+                }
+                error = __split_vma(mm, vma, start, 1);
+                if (error) {
+                        /*
+                         * madvise() returns EAGAIN if kernel resources, such as
+                         * slab, are temporarily unavailable.
+                         */
+                        if (error == -ENOMEM)
+                                error = -EAGAIN;
+                        goto out;
+                }
         }
 
         if (end != vma->vm_end) {
-                error = split_vma(mm, vma, end, 0);
-                if (error)
+                if (unlikely(mm->map_count >= sysctl_max_map_count)) {
+                        error = -ENOMEM;
+                        goto out;
+                }
+                error = __split_vma(mm, vma, end, 0);
+                if (error) {
+                        /*
+                         * madvise() returns EAGAIN if kernel resources, such as
+                         * slab, are temporarily unavailable.
+                         */
+                        if (error == -ENOMEM)
+                                error = -EAGAIN;
                         goto out;
+                }
         }
 
 success:
@@ -136,10 +172,7 @@ success:
          * vm_flags is protected by the mmap_sem held in write mode.
          */
         vma->vm_flags = new_flags;
-
 out:
-        if (error == -ENOMEM)
-                error = -EAGAIN;
         return error;
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 1cec28d20583..499b988b1639 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2499,11 +2499,11 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /*
- * __split_vma() bypasses sysctl_max_map_count checking.  We use this on the
- * munmap path where it doesn't make sense to fail.
+ * __split_vma() bypasses sysctl_max_map_count checking.  We use this where it
+ * has already been checked or doesn't make sense to fail.
  */
-static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
-              unsigned long addr, int new_below)
+int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+                unsigned long addr, int new_below)
 {
         struct vm_area_struct *new;
         int err;