mm: brk: downgrade mmap_sem to read when shrinking

brk might be used to shrink memory mapping too other than munmap().  So,
it may hold write mmap_sem for long time when shrinking large mapping, as
what commit ("mm: mmap: zap pages with read mmap_sem in munmap")
described.

The brk() will not manipulate vmas anymore after __do_munmap() call for
the mapping shrink use case.  But, it may set mm->brk after __do_munmap(),
which needs hold write mmap_sem.

However, a simple trick can workaround this by setting mm->brk before
__do_munmap().  Then restore the original value if __do_munmap() fails.
With this trick, it is safe to downgrade to read mmap_sem.

So, the same optimization, which downgrades mmap_sem to read for zapping
pages, is also feasible and reasonable to this case.

The period of holding exclusive mmap_sem for shrinking large mapping would
be reduced significantly with this optimization.

[akpm@linux-foundation.org: tweak comment]
[yang.shi@linux.alibaba.com: fix unsigned compare against 0 issue]
Link: http://lkml.kernel.org/r/1538687672-17795-1-git-send-email-yang.shi@linux.alibaba.com
Link: http://lkml.kernel.org/r/1538067582-60038-2-git-send-email-yang.shi@linux.alibaba.com
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Cc: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/mmap.c b/mm/mmap.c
index 1bfd120..6c04292 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -191,16 +191,19 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
        unsigned long retval;
-       unsigned long newbrk, oldbrk;
+       unsigned long newbrk, oldbrk, origbrk;
        struct mm_struct *mm = current->mm;
        struct vm_area_struct *next;
        unsigned long min_brk;
        bool populate;
+       bool downgraded = false;
        LIST_HEAD(uf);
 
        if (down_write_killable(&mm->mmap_sem))
                return -EINTR;
 
+       origbrk = mm->brk;
+
 #ifdef CONFIG_COMPAT_BRK
        /*
         * CONFIG_COMPAT_BRK can still be overridden by setting
@@ -229,14 +232,32 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 
        newbrk = PAGE_ALIGN(brk);
        oldbrk = PAGE_ALIGN(mm->brk);
-       if (oldbrk == newbrk)
-               goto set_brk;
+       if (oldbrk == newbrk) {
+               mm->brk = brk;
+               goto success;
+       }
 
-       /* Always allow shrinking brk. */
+       /*
+        * Always allow shrinking brk.
+        * __do_munmap() may downgrade mmap_sem to read.
+        */
        if (brk <= mm->brk) {
-               if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf))
-                       goto set_brk;
-               goto out;
+               int ret;
+
+               /*
+                * mm->brk must to be protected by write mmap_sem so update it
+                * before downgrading mmap_sem. When __do_munmap() fails,
+                * mm->brk will be restored from origbrk.
+                */
+               mm->brk = brk;
+               ret = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true);
+               if (ret < 0) {
+                       mm->brk = origbrk;
+                       goto out;
+               } else if (ret == 1) {
+                       downgraded = true;
+               }
+               goto success;
        }
 
        /* Check against existing mmap mappings. */
@@ -247,18 +268,21 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
        /* Ok, looks good - let it rip. */
        if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
                goto out;
-
-set_brk:
        mm->brk = brk;
+
+success:
        populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
-       up_write(&mm->mmap_sem);
+       if (downgraded)
+               up_read(&mm->mmap_sem);
+       else
+               up_write(&mm->mmap_sem);
        userfaultfd_unmap_complete(mm, &uf);
        if (populate)
                mm_populate(oldbrk, newbrk - oldbrk);
        return brk;
 
 out:
-       retval = mm->brk;
+       retval = origbrk;
        up_write(&mm->mmap_sem);
        return retval;
 }