thp: set compound tail page _count to zero

70b50f94f1644 ("mm: thp: tail page refcounting fix") keeps all
page_tail->_count zero at all times.  But the current kernel does not set
page_tail->_count to zero if a 1GB page is utilized.  So when an IOMMU 1GB
page is used at KVM, it wil result in a kernel oops because a tail page's
_count does not equal zero.

kernel BUG at include/linux/mm.h:386!
invalid opcode: 0000 [#1] SMP
Call Trace:
 [<ffffffff81072f7f>] gup_pud_range+0xb8/0x19d
 [<ffffffff8107312f>] get_user_pages_fast+0xcb/0x192
 [<ffffffff810bc450>] ? trace_hardirqs_off+0xd/0xf
 [<ffffffff81006a24>] hva_to_pfn+0x119/0x2f2
 [<ffffffff81006c29>] gfn_to_pfn_memslot+0x2c/0x2e
 [<ffffffff8100b909>] kvm_iommu_map_pages+0xfd/0x1c1
 [<ffffffff8100ba49>] kvm_iommu_map_memslots+0x7c/0xbd
 [<ffffffff8100b9cd>] ? kvm_iommu_map_pages+0x1c1/0x1c1
 [<ffffffff8100bb34>] kvm_iommu_map_guest+0xaa/0xbf
 [<ffffffff8100aeb0>] kvm_vm_ioctl_assigned_device+0x2ef/0xa47
 [<ffffffff8100ac6d>] ? kvm_vm_ioctl_assigned_device+0xac/0xa47
 [<ffffffff8104f2a6>] ? native_sched_clock+0x32/0x6b
 [<ffffffff810b0c02>] ? sched_clock_cpu+0x45/0xd4
 [<ffffffff810bc450>] ? trace_hardirqs_off+0xd/0xf
 [<ffffffff810b0cd2>] ? local_clock+0x41/0x5a
 [<ffffffff810bc8a1>] ? lock_release_holdtime+0x2c/0x129
 [<ffffffff8115762d>] ? cmpxchg_double_slab+0xd0/0x12b
 [<ffffffff81248f47>] ? avc_has_perm_noaudit+0x388/0x399
 [<ffffffff8104f2a6>] ? native_sched_clock+0x32/0x6b
 [<ffffffff8104f2e8>] ? sched_clock+0x9/0xd
 [<ffffffff81007dcb>] kvm_vm_ioctl+0x36c/0x3a2
 [<ffffffff8104f2a6>] ? native_sched_clock+0x32/0x6b
 [<ffffffff8104f2e8>] ? sched_clock+0x9/0xd
 [<ffffffff81174b10>] do_vfs_ioctl+0x49e/0x4e4
 [<ffffffff81174bb0>] sys_ioctl+0x5a/0x7c
 [<ffffffff81500e02>] system_call_fastpath+0x16/0x1b
RIP  [<ffffffff81072d13>] gup_huge_pud+0xf2/0x159

Signed-off-by: Youquan Song <youquan.song@intel.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bb28a5f9db8ddbf2f65391fe9206ca99b46a256b..73f17c0293c0a0e57a62f65f11c969b9319532f5 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -576,6 +576,7 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
        __SetPageHead(page);
        for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
                __SetPageTail(p);
+               set_page_count(p, 0);
                p->first_page = page;
        }
 }

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e51802d7c8ffad1c562ffa8b27a5d49d18f1d92e..500cde18f8414ad848341f0eb0c467b0e0cf5120 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -356,8 +356,8 @@ void prep_compound_page(struct page *page, unsigned long order)
        __SetPageHead(page);
        for (i = 1; i < nr_pages; i++) {
                struct page *p = page + i;
-
                __SetPageTail(p);
+               set_page_count(p, 0);
                p->first_page = page;
        }
 }