Merge tag 'x86-mm-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 tlb updates from Ingo Molnar:
 "The x86 MM changes in this cycle were:

   - Implement concurrent TLB flushes, which overlaps the local TLB
     flush with the remote TLB flush.

     In testing this improved sysbench performance measurably by a
     couple of percentage points, especially if TLB-heavy security
     mitigations are active.

   - Further micro-optimizations to improve the performance of TLB
     flushes"

* tag 'x86-mm-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  smp: Micro-optimize smp_call_function_many_cond()
  smp: Inline on_each_cpu_cond() and on_each_cpu()
  x86/mm/tlb: Remove unnecessary uses of the inline keyword
  cpumask: Mark functions as pure
  x86/mm/tlb: Do not make is_lazy dirty for no reason
  x86/mm/tlb: Privatize cpu_tlbstate
  x86/mm/tlb: Flush remote and local TLBs concurrently
  x86/mm/tlb: Open-code on_each_cpu_cond_mask() for tlb_is_not_lazy()
  x86/mm/tlb: Unify flush_tlb_func_local() and flush_tlb_func_remote()
  smp: Run functions concurrently in smp_call_function_many_cond()

2 files changed, 89 insertions, 161 deletions

diff --git a/kernel/smp.c b/kernel/smp.c
index f472ef623956..e21074900006 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -850,12 +850,28 @@ call:
 }
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 
+/*
+ * Flags to be used as scf_flags argument of smp_call_function_many_cond().
+ *
+ * %SCF_WAIT:		Wait until function execution is completed
+ * %SCF_RUN_LOCAL:	Run also locally if local cpu is set in cpumask
+ */
+#define SCF_WAIT	(1U << 0)
+#define SCF_RUN_LOCAL	(1U << 1)
+
 static void smp_call_function_many_cond(const struct cpumask *mask,
 					smp_call_func_t func, void *info,
-					bool wait, smp_cond_func_t cond_func)
+					unsigned int scf_flags,
+					smp_cond_func_t cond_func)
 {
+	int cpu, last_cpu, this_cpu = smp_processor_id();
 	struct call_function_data *cfd;
-	int cpu, next_cpu, this_cpu = smp_processor_id();
+	bool wait = scf_flags & SCF_WAIT;
+	bool run_remote = false;
+	bool run_local = false;
+	int nr_cpus = 0;
+
+	lockdep_assert_preemption_disabled();
 
 	/*
 	 * Can deadlock when called with interrupts disabled.
@@ -863,8 +879,9 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 	 * send smp call function interrupt to this cpu and as such deadlocks
 	 * can't happen.
 	 */
-	WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
-		     && !oops_in_progress && !early_boot_irqs_disabled);
+	if (cpu_online(this_cpu) && !oops_in_progress &&
+	    !early_boot_irqs_disabled)
+		lockdep_assert_irqs_enabled();
 
 	/*
 	 * When @wait we can deadlock when we interrupt between llist_add() and
@@ -874,70 +891,75 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 	 */
 	WARN_ON_ONCE(!in_task());
 
-	/* Try to fastpath.  So, what's a CPU they want? Ignoring this one. */
+	/* Check if we need local execution. */
+	if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask))
+		run_local = true;
+
+	/* Check if we need remote execution, i.e., any CPU excluding this one. */
 	cpu = cpumask_first_and(mask, cpu_online_mask);
 	if (cpu == this_cpu)
 		cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
+	if (cpu < nr_cpu_ids)
+		run_remote = true;
 
-	/* No online cpus?  We're done. */
-	if (cpu >= nr_cpu_ids)
-		return;
+	if (run_remote) {
+		cfd = this_cpu_ptr(&cfd_data);
+		cpumask_and(cfd->cpumask, mask, cpu_online_mask);
+		__cpumask_clear_cpu(this_cpu, cfd->cpumask);
 
-	/* Do we have another CPU which isn't us? */
-	next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
-	if (next_cpu == this_cpu)
-		next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);
-
-	/* Fastpath: do that cpu by itself. */
-	if (next_cpu >= nr_cpu_ids) {
-		if (!cond_func || cond_func(cpu, info))
-			smp_call_function_single(cpu, func, info, wait);
-		return;
-	}
+		cpumask_clear(cfd->cpumask_ipi);
+		for_each_cpu(cpu, cfd->cpumask) {
+			struct cfd_percpu *pcpu = per_cpu_ptr(cfd->pcpu, cpu);
+			call_single_data_t *csd = &pcpu->csd;
 
-	cfd = this_cpu_ptr(&cfd_data);
+			if (cond_func && !cond_func(cpu, info))
+				continue;
 
-	cpumask_and(cfd->cpumask, mask, cpu_online_mask);
-	__cpumask_clear_cpu(this_cpu, cfd->cpumask);
+			csd_lock(csd);
+			if (wait)
+				csd->node.u_flags |= CSD_TYPE_SYNC;
+			csd->func = func;
+			csd->info = info;
+#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
+			csd->node.src = smp_processor_id();
+			csd->node.dst = cpu;
+#endif
+			cfd_seq_store(pcpu->seq_queue, this_cpu, cpu, CFD_SEQ_QUEUE);
+			if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) {
+				__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
+				nr_cpus++;
+				last_cpu = cpu;
 
-	/* Some callers race with other cpus changing the passed mask */
-	if (unlikely(!cpumask_weight(cfd->cpumask)))
-		return;
+				cfd_seq_store(pcpu->seq_ipi, this_cpu, cpu, CFD_SEQ_IPI);
+			} else {
+				cfd_seq_store(pcpu->seq_noipi, this_cpu, cpu, CFD_SEQ_NOIPI);
+			}
+		}
 
-	cpumask_clear(cfd->cpumask_ipi);
-	for_each_cpu(cpu, cfd->cpumask) {
-		struct cfd_percpu *pcpu = per_cpu_ptr(cfd->pcpu, cpu);
-		call_single_data_t *csd = &pcpu->csd;
+		cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->ping, this_cpu, CFD_SEQ_NOCPU, CFD_SEQ_PING);
 
-		if (cond_func && !cond_func(cpu, info))
-			continue;
+		/*
+		 * Choose the most efficient way to send an IPI. Note that the
+		 * number of CPUs might be zero due to concurrent changes to the
+		 * provided mask.
+		 */
+		if (nr_cpus == 1)
+			send_call_function_single_ipi(last_cpu);
+		else if (likely(nr_cpus > 1))
+			arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
 
-		csd_lock(csd);
-		if (wait)
-			csd->node.u_flags |= CSD_TYPE_SYNC;
-		csd->func = func;
-		csd->info = info;
-#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
-		csd->node.src = smp_processor_id();
-		csd->node.dst = cpu;
-#endif
-		cfd_seq_store(pcpu->seq_queue, this_cpu, cpu, CFD_SEQ_QUEUE);
-		if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) {
-			__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
-			cfd_seq_store(pcpu->seq_ipi, this_cpu, cpu, CFD_SEQ_IPI);
-		} else {
-			cfd_seq_store(pcpu->seq_noipi, this_cpu, cpu, CFD_SEQ_NOIPI);
-		}
+		cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->pinged, this_cpu, CFD_SEQ_NOCPU, CFD_SEQ_PINGED);
 	}
 
-	/* Send a message to all CPUs in the map */
-	cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->ping, this_cpu,
-		      CFD_SEQ_NOCPU, CFD_SEQ_PING);
-	arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
-	cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->pinged, this_cpu,
-		      CFD_SEQ_NOCPU, CFD_SEQ_PINGED);
+	if (run_local && (!cond_func || cond_func(this_cpu, info))) {
+		unsigned long flags;
 
-	if (wait) {
+		local_irq_save(flags);
+		func(info);
+		local_irq_restore(flags);
+	}
+
+	if (run_remote && wait) {
 		for_each_cpu(cpu, cfd->cpumask) {
 			call_single_data_t *csd;
 
@@ -948,12 +970,14 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 }
 
 /**
- * smp_call_function_many(): Run a function on a set of other CPUs.
+ * smp_call_function_many(): Run a function on a set of CPUs.
  * @mask: The set of cpus to run on (only runs on online subset).
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed
- *        on other CPUs.
+ * @flags: Bitmask that controls the operation. If %SCF_WAIT is set, wait
+ *        (atomically) until function has completed on other CPUs. If
+ *        %SCF_RUN_LOCAL is set, the function will also be run locally
+ *        if the local CPU is set in the @cpumask.
  *
  * If @wait is true, then returns once @func has returned.
  *
@@ -964,7 +988,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 void smp_call_function_many(const struct cpumask *mask,
 			    smp_call_func_t func, void *info, bool wait)
 {
-	smp_call_function_many_cond(mask, func, info, wait, NULL);
+	smp_call_function_many_cond(mask, func, info, wait * SCF_WAIT, NULL);
 }
 EXPORT_SYMBOL(smp_call_function_many);
 
@@ -1076,56 +1100,6 @@ void __init smp_init(void)
 }
 
 /*
- * Call a function on all processors.  May be used during early boot while
- * early_boot_irqs_disabled is set.  Use local_irq_save/restore() instead
- * of local_irq_disable/enable().
- */
-void on_each_cpu(smp_call_func_t func, void *info, int wait)
-{
-	unsigned long flags;
-
-	preempt_disable();
-	smp_call_function(func, info, wait);
-	local_irq_save(flags);
-	func(info);
-	local_irq_restore(flags);
-	preempt_enable();
-}
-EXPORT_SYMBOL(on_each_cpu);
-
-/**
- * on_each_cpu_mask(): Run a function on processors specified by
- * cpumask, which may include the local processor.
- * @mask: The set of cpus to run on (only runs on online subset).
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed
- *        on other CPUs.
- *
- * If @wait is true, then returns once @func has returned.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.  The
- * exception is that it may be used during early boot while
- * early_boot_irqs_disabled is set.
- */
-void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
-			void *info, bool wait)
-{
-	int cpu = get_cpu();
-
-	smp_call_function_many(mask, func, info, wait);
-	if (cpumask_test_cpu(cpu, mask)) {
-		unsigned long flags;
-		local_irq_save(flags);
-		func(info);
-		local_irq_restore(flags);
-	}
-	put_cpu();
-}
-EXPORT_SYMBOL(on_each_cpu_mask);
-
-/*
  * on_each_cpu_cond(): Call a function on each processor for which
  * the supplied function cond_func returns true, optionally waiting
  * for all the required CPUs to finish. This may include the local
@@ -1150,27 +1124,17 @@ EXPORT_SYMBOL(on_each_cpu_mask);
 void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 			   void *info, bool wait, const struct cpumask *mask)
 {
-	int cpu = get_cpu();
+	unsigned int scf_flags = SCF_RUN_LOCAL;
 
-	smp_call_function_many_cond(mask, func, info, wait, cond_func);
-	if (cpumask_test_cpu(cpu, mask) && cond_func(cpu, info)) {
-		unsigned long flags;
+	if (wait)
+		scf_flags |= SCF_WAIT;
 
-		local_irq_save(flags);
-		func(info);
-		local_irq_restore(flags);
-	}
-	put_cpu();
+	preempt_disable();
+	smp_call_function_many_cond(mask, func, info, scf_flags, cond_func);
+	preempt_enable();
 }
 EXPORT_SYMBOL(on_each_cpu_cond_mask);
 
-void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
-		      void *info, bool wait)
-{
-	on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask);
-}
-EXPORT_SYMBOL(on_each_cpu_cond);
-
 static void do_nothing(void *unused)
 {
 }
diff --git a/kernel/up.c b/kernel/up.c
index c6f323dcd45b..bf20b4a9af60 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -36,35 +36,6 @@ int smp_call_function_single_async(int cpu, call_single_data_t *csd)
 }
 EXPORT_SYMBOL(smp_call_function_single_async);
 
-void on_each_cpu(smp_call_func_t func, void *info, int wait)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	func(info);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(on_each_cpu);
-
-/*
- * Note we still need to test the mask even for UP
- * because we actually can get an empty mask from
- * code that on SMP might call us without the local
- * CPU in the mask.
- */
-void on_each_cpu_mask(const struct cpumask *mask,
-		      smp_call_func_t func, void *info, bool wait)
-{
-	unsigned long flags;
-
-	if (cpumask_test_cpu(0, mask)) {
-		local_irq_save(flags);
-		func(info);
-		local_irq_restore(flags);
-	}
-}
-EXPORT_SYMBOL(on_each_cpu_mask);
-
 /*
  * Preemption is disabled here to make sure the cond_func is called under the
  * same condtions in UP and SMP.
@@ -75,7 +46,7 @@ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 	unsigned long flags;
 
 	preempt_disable();
-	if (cond_func(0, info)) {
+	if ((!cond_func || cond_func(0, info)) && cpumask_test_cpu(0, mask)) {
 		local_irq_save(flags);
 		func(info);
 		local_irq_restore(flags);
@@ -84,13 +55,6 @@ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 }
 EXPORT_SYMBOL(on_each_cpu_cond_mask);
 
-void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
-		      void *info, bool wait)
-{
-	on_each_cpu_cond_mask(cond_func, func, info, wait, NULL);
-}
-EXPORT_SYMBOL(on_each_cpu_cond);
-
 int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys)
 {
 	int ret;