mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries

commit 3ea27719 upstream.

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.deReported-by: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

include/linux/mm_types.h

@@ -507,6 +507,10 @@ 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_X86_INTEL_MPX

mm/internal.h

@@ -472,6 +472,7 @@ struct tlbflush_unmap_batch;
 #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)
 {
@@ -479,7 +480,9 @@ 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[];

mm/madvise.c

@@ -21,6 +21,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/mmu_notifier.h>
+#include "internal.h"
 
 #include <asm/tlb.h>
 
@@ -282,6 +283,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 		return 0;
 
 	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;

mm/memory.c

@@ -1124,6 +1124,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	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;

mm/mprotect.c

@@ -74,6 +74,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	if (!pte)
 		return 0;
 
+	flush_tlb_batched_pending(vma->vm_mm);
 	arch_enter_lazy_mmu_mode();
 	do {
 		oldpte = *pte;

mm/mremap.c

@@ -142,6 +142,7 @@ 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,

mm/rmap.c

@@ -616,6 +616,13 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
 	cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(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()
@@ -643,6 +650,35 @@ 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,
 		struct page *page, bool writable)