userfaultfd: propagate the full address in THP faults

The THP faults were not propagating the original fault address.  The
latest version of the API with uffd.arg.pagefault.address is supposed to
propagate the full address through THP faults.

This was not a kernel crashing bug and it wouldn't risk to corrupt user
memory, but it would cause a SIGBUS failure because the wrong page was
being copied.

For various reasons this wasn't easily reproducible in the qemu workload,
but the strestest exposed the problem immediately.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d38aaf9dcba60a3131b1a540033191087730e572..279a818a39b13d76e574bf8f330c7c925b8e3a67 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -717,13 +717,14 @@ static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
 
 static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
                                        struct vm_area_struct *vma,
-                                       unsigned long haddr, pmd_t *pmd,
+                                       unsigned long address, pmd_t *pmd,
                                        struct page *page, gfp_t gfp,
                                        unsigned int flags)
 {
        struct mem_cgroup *memcg;
        pgtable_t pgtable;
        spinlock_t *ptl;
+       unsigned long haddr = address & HPAGE_PMD_MASK;
 
        VM_BUG_ON_PAGE(!PageCompound(page), page);
 
@@ -765,7 +766,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
                        mem_cgroup_cancel_charge(page, memcg);
                        put_page(page);
                        pte_free(mm, pgtable);
-                       ret = handle_userfault(vma, haddr, flags,
+                       ret = handle_userfault(vma, address, flags,
                                               VM_UFFD_MISSING);
                        VM_BUG_ON(ret & VM_FAULT_FALLBACK);
                        return ret;
@@ -841,7 +842,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
                if (pmd_none(*pmd)) {
                        if (userfaultfd_missing(vma)) {
                                spin_unlock(ptl);
-                               ret = handle_userfault(vma, haddr, flags,
+                               ret = handle_userfault(vma, address, flags,
                                                       VM_UFFD_MISSING);
                                VM_BUG_ON(ret & VM_FAULT_FALLBACK);
                        } else {
@@ -865,7 +866,8 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
                count_vm_event(THP_FAULT_FALLBACK);
                return VM_FAULT_FALLBACK;
        }
-       return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page, gfp, flags);
+       return __do_huge_pmd_anonymous_page(mm, vma, address, pmd, page, gfp,
+                                           flags);
 }
 
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,