From 757597f803f5770ebd7c70d4bf0068aa525c033a Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Mon, 5 Apr 2021 22:36:00 +0200 Subject: [PATCH 4.4] mm: check VMA flags to avoid invalid PROT_NONE NUMA balancing commit 38e088546522e1e86d2b8f401a1354ad3a9b3303 upstream. The NUMA balancing logic uses an arch-specific PROT_NONE page table flag defined by pte_protnone() or pmd_protnone() to mark PTEs or huge page PMDs respectively as requiring balancing upon a subsequent page fault. User-defined PROT_NONE memory regions which also have this flag set will not normally invoke the NUMA balancing code as do_page_fault() will send a segfault to the process before handle_mm_fault() is even called. However if access_remote_vm() is invoked to access a PROT_NONE region of memory, handle_mm_fault() is called via faultin_page() and __get_user_pages() without any access checks being performed, meaning the NUMA balancing logic is incorrectly invoked on a non-NUMA memory region. A simple means of triggering this problem is to access PROT_NONE mmap'd memory using /proc/self/mem which reliably results in the NUMA handling functions being invoked when CONFIG_NUMA_BALANCING is set. This issue was reported in bugzilla (issue 99101) which includes some simple repro code. There are BUG_ON() checks in do_numa_page() and do_huge_pmd_numa_page() added at commit c0e7cad to avoid accidentally provoking strange behaviour by attempting to apply NUMA balancing to pages that are in fact PROT_NONE. The BUG_ON()'s are consistently triggered by the repro. This patch moves the PROT_NONE check into mm/memory.c rather than invoking BUG_ON() as faulting in these pages via faultin_page() is a valid reason for reaching the NUMA check with the PROT_NONE page table flag set and is therefore not always a bug. Link: https://bugzilla.kernel.org/show_bug.cgi?id=99101 Reported-by: Trevor Saunders Signed-off-by: Lorenzo Stoakes Acked-by: Rik van Riel Cc: Andrew Morton Cc: Mel Gorman Signed-off-by: Linus Torvalds Signed-off-by: Tim Gardner Signed-off-by: Marcelo Henrique Cerri [cascardo: context adjustments were necessary] Signed-off-by: Thadeu Lima de Souza Cascardo --- mm/huge_memory.c | 3 --- mm/memory.c | 12 +++++++----- 2 files changed, 7 insertions(+), 8 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index fae45c56e2ee..2f53786098c5 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1340,9 +1340,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, bool was_writable; int flags = 0; - /* A PROT_NONE fault should not end up here */ - BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))); - ptl = pmd_lock(mm, pmdp); if (unlikely(!pmd_same(pmd, *pmdp))) goto out_unlock; diff --git a/mm/memory.c b/mm/memory.c index 360d28224a8e..6bfc6a021c4f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3209,9 +3209,6 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, bool was_writable = pte_write(pte); int flags = 0; - /* A PROT_NONE fault should not end up here */ - BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))); - /* * The "pte" at this point cannot be used safely without * validation through pte_unmap_same(). It's of NUMA type but @@ -3304,6 +3301,11 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_FALLBACK; } +static inline bool vma_is_accessible(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE); +} + /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most @@ -3350,7 +3352,7 @@ static int handle_pte_fault(struct mm_struct *mm, pte, pmd, flags, entry); } - if (pte_protnone(entry)) + if (pte_protnone(entry) && vma_is_accessible(vma)) return do_numa_page(mm, vma, address, entry, pte, pmd); ptl = pte_lockptr(mm, pmd); @@ -3425,7 +3427,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (pmd_trans_splitting(orig_pmd)) return 0; - if (pmd_protnone(orig_pmd)) + if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(mm, vma, address, orig_pmd, pmd); -- 2.30.2