mm/memory.c: fix a huge pud insertion race during faulting

A huge pud page can theoretically be faulted in racing with pmd_alloc()
in __handle_mm_fault().  That will lead to pmd_alloc() returning an
invalid pmd pointer.

Fix this by adding a pud_trans_unstable() function similar to
pmd_trans_unstable() and check whether the pud is really stable before
using the pmd pointer.

Race:
  Thread 1:             Thread 2:                 Comment
  create_huge_pud()                               Fallback - not taken.
                        create_huge_pud()         Taken.
  pmd_alloc()                                     Returns an invalid pointer.

This will result in user-visible huge page data corruption.

Note that this was caught during a code audit rather than a real
experienced problem.  It looks to me like the only implementation that
currently creates huge pud pagetable entries is dev_dax_huge_fault()
which doesn't appear to care much about private (COW) mappings or
write-tracking which is, I believe, a prerequisite for create_huge_pud()
falling back on thread 1, but not in thread 2.

Link: http://lkml.kernel.org/r/20191115115808.21181-2-thomas_os@shipmail.org
Fixes: a00cc7d9dd93 ("mm, x86: add support for PUD-sized transparent hugepages")
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 3127f90..798ea36 100644 (file)
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -938,6 +938,31 @@ static inline int pud_trans_huge(pud_t pud)
 }
 #endif
 
+/* See pmd_none_or_trans_huge_or_clear_bad for discussion. */
+static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud)
+{
+       pud_t pudval = READ_ONCE(*pud);
+
+       if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval))
+               return 1;
+       if (unlikely(pud_bad(pudval))) {
+               pud_clear_bad(pud);
+               return 1;
+       }
+       return 0;
+}
+
+/* See pmd_trans_unstable for discussion. */
+static inline int pud_trans_unstable(pud_t *pud)
+{
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&                    \
+       defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+       return pud_none_or_trans_huge_or_dev_or_clear_bad(pud);
+#else
+       return 0;
+#endif
+}
+
 #ifndef pmd_read_atomic
 static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
 {

diff --git a/mm/memory.c b/mm/memory.c
index 62b5cce..c390220 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4010,6 +4010,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
        vmf.pud = pud_alloc(mm, p4d, address);
        if (!vmf.pud)
                return VM_FAULT_OOM;
+retry_pud:
        if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) {
                ret = create_huge_pud(&vmf);
                if (!(ret & VM_FAULT_FALLBACK))
@@ -4036,6 +4037,11 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
        vmf.pmd = pmd_alloc(mm, vmf.pud, address);
        if (!vmf.pmd)
                return VM_FAULT_OOM;
+
+       /* Huge pud page fault raced with pmd_alloc? */
+       if (pud_trans_unstable(vmf.pud))
+               goto retry_pud;
+
        if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) {
                ret = create_huge_pmd(&vmf);
                if (!(ret & VM_FAULT_FALLBACK))