x86/mm: Give each mm TLB flush generation a unique ID

This adds two new variables to mmu_context_t: ctx_id and tlb_gen.
ctx_id uniquely identifies the mm_struct and will never be reused.
For a given mm_struct (and hence ctx_id), tlb_gen is a monotonic
count of the number of times that a TLB flush has been requested.
The pair (ctx_id, tlb_gen) can be used as an identifier for TLB
flush actions and will be used in subsequent patches to reliably
determine whether all needed TLB flushes have occurred on a given
CPU.

This patch is split out for ease of review.  By itself, it has no
real effect other than creating and updating the new variables.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Nadav Amit <nadav.amit@gmail.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/413a91c24dab3ed0caa5f4e4d017d87b0857f920.1498751203.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/mmu.h

@@ -3,12 +3,28 @@
 
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/atomic.h>
 
 /*
- * The x86 doesn't have a mmu context, but
- * we put the segment information here.
+ * x86 has arch-specific MMU state beyond what lives in mm_struct.
  */
 typedef struct {
+	/*
+	 * ctx_id uniquely identifies this mm_struct.  A ctx_id will never
+	 * be reused, and zero is not a valid ctx_id.
+	 */
+	u64 ctx_id;
+
+	/*
+	 * Any code that needs to do any sort of TLB flushing for this
+	 * mm will first make its changes to the page tables, then
+	 * increment tlb_gen, then flush.  This lets the low-level
+	 * flushing code keep track of what needs flushing.
+	 *
+	 * This is not used on Xen PV.
+	 */
+	atomic64_t tlb_gen;
+
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct ldt_struct *ldt;
 #endif
@@ -37,6 +53,11 @@ typedef struct {
 #endif
 } mm_context_t;
 
+#define INIT_MM_CONTEXT(mm)						\
+	.context = {							\
+		.ctx_id = 1,						\
+	}
+
 void leave_mm(int cpu);
 
 #endif /* _ASM_X86_MMU_H */

arch/x86/include/asm/mmu_context.h

@@ -12,6 +12,9 @@
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/mpx.h>
+
+extern atomic64_t last_mm_ctx_id;
+
 #ifndef CONFIG_PARAVIRT
 static inline void paravirt_activate_mm(struct mm_struct *prev,
 					struct mm_struct *next)
@@ -132,6 +135,9 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
+	atomic64_set(&mm->context.tlb_gen, 0);
+
 	#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
 		/* pkey 0 is the default and always allocated */

arch/x86/include/asm/tlbflush.h

@@ -57,6 +57,23 @@ static inline void invpcid_flush_all_nonglobals(void)
 	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
 }
 
+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+{
+	u64 new_tlb_gen;
+
+	/*
+	 * Bump the generation count.  This also serves as a full barrier
+	 * that synchronizes with switch_mm(): callers are required to order
+	 * their read of mm_cpumask after their writes to the paging
+	 * structures.
+	 */
+	smp_mb__before_atomic();
+	new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen);
+	smp_mb__after_atomic();
+
+	return new_tlb_gen;
+}
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
@@ -262,6 +279,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
 					struct mm_struct *mm)
 {
+	inc_mm_tlb_gen(mm);
 	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
 }
 

arch/x86/mm/tlb.c

@@ -28,6 +28,8 @@
  *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
+atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
+
 void leave_mm(int cpu)
 {
 	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
@@ -250,8 +252,8 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 
 	cpu = get_cpu();
 
-	/* Synchronize with switch_mm. */
-	smp_mb();
+	/* This is also a barrier that synchronizes with switch_mm(). */
+	inc_mm_tlb_gen(mm);
 
 	/* Should we flush just the requested range? */
 	if ((end != TLB_FLUSH_ALL) &&