[PATCH v8 10/12] x86/mm: do targeted broadcast flushing from tlbbatch code

[Rik van Riel <riel@surriel.com>]

Instead of doing a system-wide TLB flush from arch_tlbbatch_flush,
queue up asynchronous, targeted flushes from arch_tlbbatch_add_pending.

This also allows us to avoid adding the CPUs of processes using broadcast
flushing to the batch->cpumask, and will hopefully further reduce TLB
flushing from the reclaim and compaction paths.

Signed-off-by: Rik van Riel <riel@surriel.com>
Tested-by: Manali Shukla <Manali.Shukla@amd.com>
---
 arch/x86/include/asm/tlbbatch.h |  1 +
 arch/x86/include/asm/tlbflush.h | 12 ++-----
 arch/x86/mm/tlb.c               | 57 +++++++++++++++++++++++++++++++--
 3 files changed, 58 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h
index 1ad56eb3e8a8..f9a17edf63ad 100644
--- a/arch/x86/include/asm/tlbbatch.h
+++ b/arch/x86/include/asm/tlbbatch.h
@@ -10,6 +10,7 @@ struct arch_tlbflush_unmap_batch {
 	 * the PFNs being flushed..
 	 */
 	struct cpumask cpumask;
+	bool used_invlpgb;
 };
 
 #endif /* _ARCH_X86_TLBBATCH_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 7e2f3f7f6455..f8aaa4bcb4d8 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -359,21 +359,15 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 	return atomic64_inc_return(&mm->context.tlb_gen);
 }
 
-static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
-					     struct mm_struct *mm,
-					     unsigned long uaddr)
-{
-	inc_mm_tlb_gen(mm);
-	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
-	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
-}
-
 static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
 {
 	flush_tlb_mm(mm);
 }
 
 extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
+extern void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+					     struct mm_struct *mm,
+					     unsigned long uaddr);
 
 static inline bool pte_flags_need_flush(unsigned long oldflags,
 					unsigned long newflags,
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 7b363ae1569b..c064e27df1f3 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1646,9 +1646,7 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
-		invlpgb_flush_all_nonglobals();
-	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
 		flush_tlb_multi(&batch->cpumask, info);
 	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
 		lockdep_assert_irqs_enabled();
@@ -1657,12 +1655,65 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 		local_irq_enable();
 	}
 
+	/*
+	 * If we issued (asynchronous) INVLPGB flushes, wait for them here.
+	 * The cpumask above contains only CPUs that were running tasks
+	 * not using broadcast TLB flushing.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch->used_invlpgb) {
+		tlbsync();
+		migrate_enable();
+		batch->used_invlpgb = false;
+	}
+
 	cpumask_clear(&batch->cpumask);
 
 	put_flush_tlb_info();
 	put_cpu();
 }
 
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+					     struct mm_struct *mm,
+					     unsigned long uaddr)
+{
+	u16 asid = mm_global_asid(mm);
+
+	if (asid) {
+		/*
+		 * Queue up an asynchronous invalidation. The corresponding
+		 * TLBSYNC is done in arch_tlbbatch_flush(), and must be done
+		 * on the same CPU.
+		 */
+		if (!batch->used_invlpgb) {
+			batch->used_invlpgb = true;
+			migrate_disable();
+		}
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), uaddr, 1, false);
+		/* Do any CPUs supporting INVLPGB need PTI? */
+		if (static_cpu_has(X86_FEATURE_PTI))
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), uaddr, 1, false);
+
+		/*
+		 * Some CPUs might still be using a local ASID for this
+		 * process, and require IPIs, while others are using the
+		 * global ASID.
+		 *
+		 * In this corner case we need to do both the broadcast
+		 * TLB invalidation, and send IPIs. The IPIs will help
+		 * stragglers transition to the broadcast ASID.
+		 */
+		if (READ_ONCE(mm->context.asid_transition))
+			asid = 0;
+	}
+
+	if (!asid) {
+		inc_mm_tlb_gen(mm);
+		cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+	}
+
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
+}
+
 /*
  * Blindly accessing user memory from NMI context can be dangerous
  * if we're in the middle of switching the current user task or
-- 
2.47.1