drivers/scsi/sg.c: mark VMA as VM_IO to prevent migration
authorKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Wed, 3 Feb 2016 00:57:35 +0000 (16:57 -0800)
committerLinus Torvalds <torvalds@linux-foundation.org>
Wed, 3 Feb 2016 16:28:43 +0000 (08:28 -0800)
Reduced testcase:

    #include <fcntl.h>
    #include <unistd.h>
    #include <sys/mman.h>
    #include <numaif.h>

    #define SIZE 0x2000

    int main()
    {
        int fd;
        void *p;

        fd = open("/dev/sg0", O_RDWR);
        p = mmap(NULL, SIZE, PROT_EXEC, MAP_PRIVATE | MAP_LOCKED, fd, 0);
        mbind(p, SIZE, 0, NULL, 0, MPOL_MF_MOVE);
        return 0;
    }

We shouldn't try to migrate pages in sg VMA as we don't have a way to
update Sg_scatter_hold::pages accordingly from mm core.

Let's mark the VMA as VM_IO to indicate to mm core that the VMA is not
migratable.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Doug Gilbert <dgilbert@interlog.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Shiraz Hashim <shashim@codeaurora.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: syzkaller <syzkaller@googlegroups.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
drivers/scsi/sg.c

index 503ab8b..5e82067 100644 (file)
@@ -1261,7 +1261,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
        }
 
        sfp->mmap_called = 1;
-       vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+       vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
        vma->vm_private_data = sfp;
        vma->vm_ops = &sg_mmap_vm_ops;
        return 0;