From 3ea277194daaeaa84ce75180ec7c7a2075027a68 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 2 Aug 2017 13:31:52 -0700 Subject: [PATCH] mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries Nadav Amit identified a theoritical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. For some operations like mprotect, it's not necessarily a data integrity issue but it is a correctness issue as there is a window where an mprotect that limits access still allows access. For munmap, it's potentially a data integrity issue although the race is massive as an munmap, mmap and return to userspace must all complete between the window when reclaim drops the PTL and flushes the TLB. However, it's theoritically possible so handle this issue by flushing the mm if reclaim is potentially currently batching TLB flushes. Other instances where a flush is required for a present pte should be ok as either the page lock is held preventing parallel reclaim or a page reference count is elevated preventing a parallel free leading to corruption. In the case of page_mkclean there isn't an obvious path that userspace could take advantage of without using the operations that are guarded by this patch. Other users such as gup as a race with reclaim looks just at PTEs. huge page variants should be ok as they don't race with reclaim. mincore only looks at PTEs. userfault also should be ok as if a parallel reclaim takes place, it will either fault the page back in or read some of the data before the flush occurs triggering a fault. Note that a variant of this patch was acked by Andy Lutomirski but this was for the x86 parts on top of his PCID work which didn't make the 4.13 merge window as expected. His ack is dropped from this version and there will be a follow-on patch on top of PCID that will include his ack. [akpm@linux-foundation.org: tweak comments] [akpm@linux-foundation.org: fix spello] Link: http://lkml.kernel.org/r/20170717155523.emckq2esjro6hf3z@suse.de Reported-by: Nadav Amit Signed-off-by: Mel Gorman Cc: Andy Lutomirski Cc: [v4.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 4 ++++ mm/internal.h | 5 ++++- mm/madvise.c | 1 + mm/memory.c | 1 + mm/mprotect.c | 1 + mm/mremap.c | 1 + mm/rmap.c | 36 ++++++++++++++++++++++++++++++++++++ 7 files changed, 48 insertions(+), 1 deletion(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ff151814a02d..7f384bb62d8e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -494,6 +494,10 @@ struct mm_struct { * PROT_NONE or PROT_NUMA mapped page. */ bool tlb_flush_pending; +#endif +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH + /* See flush_tlb_batched_pending() */ + bool tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/internal.h b/mm/internal.h index 24d88f084705..4ef49fc55e58 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -498,6 +498,7 @@ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); +void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { @@ -505,7 +506,9 @@ static inline void try_to_unmap_flush(void) static inline void try_to_unmap_flush_dirty(void) { } - +static inline void flush_tlb_batched_pending(struct mm_struct *mm) +{ +} #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; diff --git a/mm/madvise.c b/mm/madvise.c index 9976852f1e1c..47d8d8a25eae 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -320,6 +320,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, tlb_remove_check_page_size_change(tlb, PAGE_SIZE); orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = *pte; diff --git a/mm/memory.c b/mm/memory.c index 0e517be91a89..f65beaad319b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1197,6 +1197,7 @@ again: init_rss_vec(rss); start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte = start_pte; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; diff --git a/mm/mprotect.c b/mm/mprotect.c index 1a8c9ca83e48..4180ad8cc9c5 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -64,6 +64,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, atomic_read(&vma->vm_mm->mm_users) == 1) target_node = numa_node_id(); + flush_tlb_batched_pending(vma->vm_mm); arch_enter_lazy_mmu_mode(); do { oldpte = *pte; diff --git a/mm/mremap.c b/mm/mremap.c index cd8a1b199ef9..6e3d857458de 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -152,6 +152,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_ptl = pte_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + flush_tlb_batched_pending(vma->vm_mm); arch_enter_lazy_mmu_mode(); for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, diff --git a/mm/rmap.c b/mm/rmap.c index ced14f1af6dc..c8993c63eb25 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -604,6 +604,13 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; + /* + * Ensure compiler does not re-order the setting of tlb_flush_batched + * before the PTE is cleared. + */ + barrier(); + mm->tlb_flush_batched = true; + /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() @@ -631,6 +638,35 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) return should_defer; } + +/* + * Reclaim unmaps pages under the PTL but do not flush the TLB prior to + * releasing the PTL if TLB flushes are batched. It's possible for a parallel + * operation such as mprotect or munmap to race between reclaim unmapping + * the page and flushing the page. If this race occurs, it potentially allows + * access to data via a stale TLB entry. Tracking all mm's that have TLB + * batching in flight would be expensive during reclaim so instead track + * whether TLB batching occurred in the past and if so then do a flush here + * if required. This will cost one additional flush per reclaim cycle paid + * by the first operation at risk such as mprotect and mumap. + * + * This must be called under the PTL so that an access to tlb_flush_batched + * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise + * via the PTL. + */ +void flush_tlb_batched_pending(struct mm_struct *mm) +{ + if (mm->tlb_flush_batched) { + flush_tlb_mm(mm); + + /* + * Do not allow the compiler to re-order the clearing of + * tlb_flush_batched before the tlb is flushed. + */ + barrier(); + mm->tlb_flush_batched = false; + } +} #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) {