tree 6843f9ee4ec0d9e1a23292a664e704955ccca81d
parent 5701feb0a9f5b1c30222d77b12e15cc17c9cd4bf
author Longpeng <longpeng2@huawei.com> 1587431631 -0700
committer Linus Torvalds <torvalds@linux-foundation.org> 1587492715 -0700

mm/hugetlb: fix a addressing exception caused by huge_pte_offset

Our machine encountered a panic(addressing exception) after run for a
long time and the calltrace is:

    RIP: hugetlb_fault+0x307/0xbe0
    RSP: 0018:ffff9567fc27f808  EFLAGS: 00010286
    RAX: e800c03ff1258d48 RBX: ffffd3bb003b69c0 RCX: e800c03ff1258d48
    RDX: 17ff3fc00eda72b7 RSI: 00003ffffffff000 RDI: e800c03ff1258d48
    RBP: ffff9567fc27f8c8 R08: e800c03ff1258d48 R09: 0000000000000080
    R10: ffffaba0704c22a8 R11: 0000000000000001 R12: ffff95c87b4b60d8
    R13: 00005fff00000000 R14: 0000000000000000 R15: ffff9567face8074
    FS:  00007fe2d9ffb700(0000) GS:ffff956900e40000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: ffffd3bb003b69c0 CR3: 000000be67374000 CR4: 00000000003627e0
    DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
    DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
    Call Trace:
      follow_hugetlb_page+0x175/0x540
      __get_user_pages+0x2a0/0x7e0
      __get_user_pages_unlocked+0x15d/0x210
      __gfn_to_pfn_memslot+0x3c5/0x460 [kvm]
      try_async_pf+0x6e/0x2a0 [kvm]
      tdp_page_fault+0x151/0x2d0 [kvm]
     ...
      kvm_arch_vcpu_ioctl_run+0x330/0x490 [kvm]
      kvm_vcpu_ioctl+0x309/0x6d0 [kvm]
      do_vfs_ioctl+0x3f0/0x540
      SyS_ioctl+0xa1/0xc0
      system_call_fastpath+0x22/0x27

For 1G hugepages, huge_pte_offset() wants to return NULL or pudp, but it
may return a wrong 'pmdp' if there is a race.  Please look at the
following code snippet:

    ...
    pud = pud_offset(p4d, addr);
    if (sz != PUD_SIZE && pud_none(*pud))
        return NULL;
    /* hugepage or swap? */
    if (pud_huge(*pud) || !pud_present(*pud))
        return (pte_t *)pud;

    pmd = pmd_offset(pud, addr);
    if (sz != PMD_SIZE && pmd_none(*pmd))
        return NULL;
    /* hugepage or swap? */
    if (pmd_huge(*pmd) || !pmd_present(*pmd))
        return (pte_t *)pmd;
    ...

The following sequence would trigger this bug:

 - CPU0: sz = PUD_SIZE and *pud = 0 , continue
 - CPU0: "pud_huge(*pud)" is false
 - CPU1: calling hugetlb_no_page and set *pud to xxxx8e7(PRESENT)
 - CPU0: "!pud_present(*pud)" is false, continue
 - CPU0: pmd = pmd_offset(pud, addr) and maybe return a wrong pmdp

However, we want CPU0 to return NULL or pudp in this case.

We must make sure there is exactly one dereference of pud and pmd.

Signed-off-by: Longpeng <longpeng2@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200413010342.771-1-longpeng2@huawei.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>