summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorRik van Riel <riel@redhat.com>2013-12-18 17:08:44 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-12-18 19:04:51 -0800
commit20841405940e7be0617612d521e206e4b6b325db (patch)
treeff60aa7674876d90e25db4046d9916f73680682b /include
parentde466bd628e8d663fdf3f791bc8db318ee85c714 (diff)
downloadlinux-20841405940e7be0617612d521e206e4b6b325db.tar.bz2
mm: fix TLB flush race between migration, and change_protection_range
There are a few subtle races, between change_protection_range (used by mprotect and change_prot_numa) on one side, and NUMA page migration and compaction on the other side. The basic race is that there is a time window between when the PTE gets made non-present (PROT_NONE or NUMA), and the TLB is flushed. During that time, a CPU may continue writing to the page. This is fine most of the time, however compaction or the NUMA migration code may come in, and migrate the page away. When that happens, the CPU may continue writing, through the cached translation, to what is no longer the current memory location of the process. This only affects x86, which has a somewhat optimistic pte_accessible. All other architectures appear to be safe, and will either always flush, or flush whenever there is a valid mapping, even with no permissions (SPARC). The basic race looks like this: CPU A CPU B CPU C load TLB entry make entry PTE/PMD_NUMA fault on entry read/write old page start migrating page change PTE/PMD to new page read/write old page [*] flush TLB reload TLB from new entry read/write new page lose data [*] the old page may belong to a new user at this point! The obvious fix is to flush remote TLB entries, by making sure that pte_accessible aware of the fact that PROT_NONE and PROT_NUMA memory may still be accessible if there is a TLB flush pending for the mm. This should fix both NUMA migration and compaction. [mgorman@suse.de: fix build] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Alex Thorlton <athorlton@sgi.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/pgtable.h2
-rw-r--r--include/linux/mm_types.h44
2 files changed, 45 insertions, 1 deletions
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f330d28e4d0e..b12079afbd5f 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -217,7 +217,7 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
#endif
#ifndef pte_accessible
-# define pte_accessible(pte) ((void)(pte),1)
+# define pte_accessible(mm, pte) ((void)(pte), 1)
#endif
#ifndef flush_tlb_fix_spurious_fault
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bd299418a934..e5c49c30460f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -443,6 +443,14 @@ struct mm_struct {
/* numa_scan_seq prevents two threads setting pte_numa */
int numa_scan_seq;
#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+ /*
+ * An operation with batched TLB flushing is going on. Anything that
+ * can move process memory needs to flush the TLB when moving a
+ * PROT_NONE or PROT_NUMA mapped page.
+ */
+ bool tlb_flush_pending;
+#endif
struct uprobes_state uprobes_state;
};
@@ -459,4 +467,40 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
return mm->cpu_vm_mask_var;
}
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+/*
+ * Memory barriers to keep this state in sync are graciously provided by
+ * the page table locks, outside of which no page table modifications happen.
+ * The barriers below prevent the compiler from re-ordering the instructions
+ * around the memory barriers that are already present in the code.
+ */
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+ barrier();
+ return mm->tlb_flush_pending;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+ mm->tlb_flush_pending = true;
+ barrier();
+}
+/* Clearing is done after a TLB flush, which also provides a barrier. */
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+ barrier();
+ mm->tlb_flush_pending = false;
+}
+#else
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+ return false;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+#endif
+
#endif /* _LINUX_MM_TYPES_H */