x86/mm/tlb: Open-code on_each_cpu_cond_mask() for tlb_is_not_lazy()

Open-code on_each_cpu_cond_mask() in native_flush_tlb_others() to
optimize the code. Open-coding eliminates the need for the indirect branch
that is used to call is_lazy(), and in CPUs that are vulnerable to
Spectre v2, it eliminates the retpoline. In addition, it allows to use a
preallocated cpumask to compute the CPUs that should be.

This would later allow us not to adapt on_each_cpu_cond_mask() to
support local and remote functions.

Note that calling tlb_is_not_lazy() for every CPU that needs to be
flushed, as done in native_flush_tlb_multi() might look ugly, but it is
equivalent to what is currently done in on_each_cpu_cond_mask().
Actually, native_flush_tlb_multi() does it more efficiently since it
avoids using an indirect branch for the matter.

Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20210220231712.2475218-4-namit@vmware.com

arch/x86/mm/tlb.c

@@ -788,11 +788,13 @@ done:
 			nr_invalidate);
 }
 
-static bool tlb_is_not_lazy(int cpu, void *data)
+static bool tlb_is_not_lazy(int cpu)
 {
 	return !per_cpu(cpu_tlbstate.is_lazy, cpu);
 }
 
+static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
+
 STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,
 					 const struct flush_tlb_info *info)
 {
@@ -813,12 +815,37 @@ STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,
 	 * up on the new contents of what used to be page tables, while
 	 * doing a speculative memory access.
 	 */
-	if (info->freed_tables)
+	if (info->freed_tables) {
 		smp_call_function_many(cpumask, flush_tlb_func,
 			       (void *)info, 1);
-	else
-		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func,
-				(void *)info, 1, cpumask);
+	} else {
+		/*
+		 * Although we could have used on_each_cpu_cond_mask(),
+		 * open-coding it has performance advantages, as it eliminates
+		 * the need for indirect calls or retpolines. In addition, it
+		 * allows to use a designated cpumask for evaluating the
+		 * condition, instead of allocating one.
+		 *
+		 * This code works under the assumption that there are no nested
+		 * TLB flushes, an assumption that is already made in
+		 * flush_tlb_mm_range().
+		 *
+		 * cond_cpumask is logically a stack-local variable, but it is
+		 * more efficient to have it off the stack and not to allocate
+		 * it on demand. Preemption is disabled and this code is
+		 * non-reentrant.
+		 */
+		struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask);
+		int cpu;
+
+		cpumask_clear(cond_cpumask);
+
+		for_each_cpu(cpu, 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);
+	}
 }
 
 void flush_tlb_others(const struct cpumask *cpumask,