1 files changed, 33 insertions, 1 deletions

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 379cd3658799..bfd9b2a35a0b 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -116,8 +116,36 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 #endif
 		cpumask_set_cpu(cpu, mm_cpumask(next));
 
-		/* Re-load page tables */
+		/*
+		 * Re-load page tables.
+		 *
+		 * This logic has an ordering constraint:
+		 *
+		 *  CPU 0: Write to a PTE for 'next'
+		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
+		 *  CPU 1: set bit 1 in next's mm_cpumask
+		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
+		 *
+		 * We need to prevent an outcome in which CPU 1 observes
+		 * the new PTE value and CPU 0 observes bit 1 clear in
+		 * mm_cpumask.  (If that occurs, then the IPI will never
+		 * be sent, and CPU 0's TLB will contain a stale entry.)
+		 *
+		 * The bad outcome can occur if either CPU's load is
+		 * reordered before that CPU's store, so both CPUs must
+		 * execute full barriers to prevent this from happening.
+		 *
+		 * Thus, switch_mm needs a full barrier between the
+		 * store to mm_cpumask and any operation that could load
+		 * from next->pgd.  TLB fills are special and can happen
+		 * due to instruction fetches or for no reason at all,
+		 * and neither LOCK nor MFENCE orders them.
+		 * Fortunately, load_cr3() is serializing and gives the
+		 * ordering guarantee we need.
+		 *
+		 */
 		load_cr3(next->pgd);
+
 		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 
 		/* Stop flush ipis for the previous mm */
@@ -156,10 +184,14 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			 * schedule, protecting us from simultaneous changes.
 			 */
 			cpumask_set_cpu(cpu, mm_cpumask(next));
+
 			/*
 			 * We were in lazy tlb mode and leave_mm disabled
 			 * tlb flush IPI delivery. We must reload CR3
 			 * to make sure to use no freed page tables.
+			 *
+			 * As above, load_cr3() is serializing and orders TLB
+			 * fills with respect to the mm_cpumask write.
 			 */
 			load_cr3(next->pgd);
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);