From 625110b5e9dae9074d8a7e67dd07f821a053eed7 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Sat, 30 Nov 2019 17:51:32 -0800 Subject: 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 Acked-by: Kirill A. Shutemov Cc: Arnd Bergmann Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'mm/memory.c') diff --git a/mm/memory.c b/mm/memory.c index 62b5cce653f6..c3902201989f 100644 --- 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)) -- cgit v1.2.3-59-g8ed1b