Re: [PATCH v2] mm: page_alloc: move mlocked flag clearance into free_pages_prepare()

[Roman Gushchin <roman.gushchin@linux.dev>]

On Tue, Oct 22, 2024 at 04:47:19AM +0100, Matthew Wilcox wrote:
> On Tue, Oct 22, 2024 at 02:14:39AM +0000, Roman Gushchin wrote:
> > On Mon, Oct 21, 2024 at 09:34:24PM +0100, Matthew Wilcox wrote:
> > > On Mon, Oct 21, 2024 at 05:34:55PM +0000, Roman Gushchin wrote:
> > > > Fix it by moving the mlocked flag clearance down to
> > > > free_page_prepare().
> > > 
> > > Urgh, I don't like this new reference to folio in free_pages_prepare().
> > > It feels like a layering violation.  I'll think about where else we
> > > could put this.
> > 
> > I agree, but it feels like it needs quite some work to do it in a nicer way,
> > no way it can be backported to older kernels. As for this fix, I don't
> > have better ideas...
> 
> Well, what is KVM doing that causes this page to get mapped to userspace?
> Don't tell me to look at the reproducer as it is 403 Forbidden.  All I
> can tell is that it's freed with vfree().
> 
> Is it from kvm_dirty_ring_get_page()?  That looks like the obvious thing,
> but I'd hate to spend a lot of time on it and then discover I was looking
> at the wrong thing.

One of the pages is vcpu->run, others belong to kvm->coalesced_mmio_ring.

Here is the reproducer:

#define _GNU_SOURCE

#include <endian.h>
#include <fcntl.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mount.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <unistd.h>

#ifndef __NR_mlock2
#define __NR_mlock2 325
#endif

uint64_t r[3] = {0xffffffffffffffff, 0xffffffffffffffff, 0xffffffffffffffff};

#ifndef KVM_CREATE_VM
#define KVM_CREATE_VM 0xae01
#endif

#ifndef KVM_CREATE_VCPU
#define KVM_CREATE_VCPU 0xae41
#endif

int main(void)
{
  syscall(__NR_mmap, /*addr=*/0x1ffff000ul, /*len=*/0x1000ul, /*prot=*/0ul,
          /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
          /*offset=*/0ul);
  syscall(__NR_mmap, /*addr=*/0x20000000ul, /*len=*/0x1000000ul,
          /*prot=PROT_WRITE|PROT_READ|PROT_EXEC*/ 7ul,
          /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
          /*offset=*/0ul);
  syscall(__NR_mmap, /*addr=*/0x21000000ul, /*len=*/0x1000ul, /*prot=*/0ul,
          /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
          /*offset=*/0ul);
  intptr_t res = syscall(__NR_openat, /*fd=*/0xffffff9c, /*file=*/"/dev/kvm",
                /*flags=*/0, /*mode=*/0);
  if (res != -1)
    r[0] = res;
  res = syscall(__NR_ioctl, /*fd=*/r[0], /*cmd=*/KVM_CREATE_VM, /*type=*/0ul);
  if (res != -1)
    r[1] = res;
  res = syscall(__NR_ioctl, /*fd=*/r[1], /*cmd=*/KVM_CREATE_VCPU, /*id=*/0ul);
  if (res != -1)
    r[2] = res;
  syscall(__NR_mmap, /*addr=*/0x20000000ul, /*len=*/0xb36000ul,
          /*prot=PROT_SEM|PROT_WRITE|PROT_READ|PROT_EXEC*/ 0xful,
          /*flags=MAP_FIXED|MAP_SHARED*/ 0x11ul, /*fd=*/r[2], /*offset=*/0ul);
  syscall(__NR_mlock2, /*addr=*/0x20000000ul, /*size=*/0x400000ul,
          /*flags=*/0ul);
  syscall(__NR_mremap, /*addr=*/0x200ab000ul, /*len=*/0x1000ul,
          /*newlen=*/0x1000ul,
          /*flags=MREMAP_DONTUNMAP|MREMAP_FIXED|MREMAP_MAYMOVE*/ 7ul,
          /*newaddr=*/0x20ffc000ul);
  return 0;
}