x86/mm/tlb: Flush remote and local TLBs concurrently

To improve TLB shootdown performance, flush the remote and local TLBs
concurrently. Introduce flush_tlb_multi() that does so. Introduce
paravirtual versions of flush_tlb_multi() for KVM, Xen and hyper-v (Xen
and hyper-v are only compile-tested).

While the updated smp infrastructure is capable of running a function on
a single local core, it is not optimized for this case. The multiple
function calls and the indirect branch introduce some overhead, and
might make local TLB flushes slower than they were before the recent
changes.

Before calling the SMP infrastructure, check if only a local TLB flush
is needed to restore the lost performance in this common case. This
requires to check mm_cpumask() one more time, but unless this mask is
updated very frequently, this should impact performance negatively.

Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Michael Kelley <mikelley@microsoft.com> # Hyper-v parts
Reviewed-by: Juergen Gross <jgross@suse.com> # Xen and paravirt parts
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20210220231712.2475218-5-namit@vmware.com

1 files changed, 29 insertions, 17 deletions

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 07b6701a540a..8db87cd92e6b 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -24,7 +24,7 @@
 # define __flush_tlb_local		native_flush_tlb_local
 # define __flush_tlb_global		native_flush_tlb_global
 # define __flush_tlb_one_user(addr)	native_flush_tlb_one_user(addr)
-# define __flush_tlb_others(msk, info)	native_flush_tlb_others(msk, info)
+# define __flush_tlb_multi(msk, info)	native_flush_tlb_multi(msk, info)
 #endif
 
 /*
@@ -490,7 +490,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		/*
 		 * Even in lazy TLB mode, the CPU should stay set in the
 		 * mm_cpumask. The TLB shootdown code can figure out from
-		 * from cpu_tlbstate.is_lazy whether or not to send an IPI.
+		 * cpu_tlbstate.is_lazy whether or not to send an IPI.
 		 */
 		if (WARN_ON_ONCE(real_prev != &init_mm &&
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
@@ -697,7 +697,7 @@ static void flush_tlb_func(void *info)
 		 * garbage into our TLB.  Since switching to init_mm is barely
 		 * slower than a minimal flush, just switch to init_mm.
 		 *
-		 * This should be rare, with native_flush_tlb_others skipping
+		 * This should be rare, with native_flush_tlb_multi() skipping
 		 * IPIs to lazy TLB mode CPUs.
 		 */
 		switch_mm_irqs_off(NULL, &init_mm, NULL);
@@ -795,9 +795,14 @@ static bool tlb_is_not_lazy(int cpu)
 
 static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
 
-STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,
+STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 					 const struct flush_tlb_info *info)
 {
+	/*
+	 * Do accounting and tracing. Note that there are (and have always been)
+	 * cases in which a remote TLB flush will be traced, but eventually
+	 * would not happen.
+	 */
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (info->end == TLB_FLUSH_ALL)
 		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
@@ -816,8 +821,7 @@ STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,
 	 * doing a speculative memory access.
 	 */
 	if (info->freed_tables) {
-		smp_call_function_many(cpumask, flush_tlb_func,
-			       (void *)info, 1);
+		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
 	} else {
 		/*
 		 * Although we could have used on_each_cpu_cond_mask(),
@@ -844,14 +848,14 @@ STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,
 			if (tlb_is_not_lazy(cpu))
 				__cpumask_set_cpu(cpu, cond_cpumask);
 		}
-		smp_call_function_many(cond_cpumask, flush_tlb_func, (void *)info, 1);
+		on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true);
 	}
 }
 
-void flush_tlb_others(const struct cpumask *cpumask,
+void flush_tlb_multi(const struct cpumask *cpumask,
 		      const struct flush_tlb_info *info)
 {
-	__flush_tlb_others(cpumask, info);
+	__flush_tlb_multi(cpumask, info);
 }
 
 /*
@@ -931,16 +935,20 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	info = get_flush_tlb_info(mm, start, end, stride_shift, freed_tables,
 				  new_tlb_gen);
 
-	if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
+	/*
+	 * flush_tlb_multi() is not optimized for the common case in which only
+	 * a local TLB flush is needed. Optimize this use-case by calling
+	 * flush_tlb_func_local() directly in this case.
+	 */
+	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+		flush_tlb_multi(mm_cpumask(mm), info);
+	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();
 		flush_tlb_func(info);
 		local_irq_enable();
 	}
 
-	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), info);
-
 	put_flush_tlb_info();
 	put_cpu();
 }
@@ -1152,16 +1160,20 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	int cpu = get_cpu();
 
 	info = get_flush_tlb_info(NULL, 0, TLB_FLUSH_ALL, 0, false, 0);
-	if (cpumask_test_cpu(cpu, &batch->cpumask)) {
+	/*
+	 * flush_tlb_multi() is not optimized for the common case in which only
+	 * a local TLB flush is needed. Optimize this use-case by calling
+	 * flush_tlb_func_local() directly in this case.
+	 */
+	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();
 		local_irq_disable();
 		flush_tlb_func(info);
 		local_irq_enable();
 	}
 
-	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids)
-		flush_tlb_others(&batch->cpumask, info);
-
 	cpumask_clear(&batch->cpumask);
 
 	put_flush_tlb_info();