[PATCH v3 3/9] x86/mm/tlb: Open-code on_each_cpu_cond_mask() for tlb_is_not_lazy()

[Nadav Amit <namit@vmware.com>]

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.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Nadav Amit <namit@vmware.com>
---
 arch/x86/mm/tlb.c | 40 ++++++++++++++++++++++++++++++++++------
 1 file changed, 34 insertions(+), 6 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 233f3d8308db..abbf55fa8b81 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -658,11 +658,13 @@ static void flush_tlb_func_remote(void *info)
 	flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN);
 }
 
-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);
+
 void native_flush_tlb_others(const struct cpumask *cpumask,
 			     const struct flush_tlb_info *info)
 {
@@ -706,12 +708,38 @@ 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_remote,
 			       (void *)info, 1);
-	else
-		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func_remote,
-				(void *)info, 1, GFP_ATOMIC, 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_remote,
+					 (void *)info, 1);
+	}
 }
 
 /*
@@ -865,7 +893,7 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	if (cpumask_test_cpu(cpu, &batch->cpumask)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();
-		flush_tlb_func_local(&full_flush_tlb_info);
+		flush_tlb_func_local((void *)&full_flush_tlb_info);
 		local_irq_enable();
 	}
 
-- 
2.20.1