[RFC PATCH 2/3] x86/mm/tlb: Avoid deferring PTI flushes on shootdown

[Nadav Amit <namit@vmware.com>]

When a shootdown is initiated, the initiating CPU has cycles to burn as
it waits for the responding CPUs to receive the IPI and acknowledge it.
In these cycles it is better to flush the user page-tables using
INVPCID, instead of deferring the TLB flush.

The best way to figure out whether there are cycles to burn is arguably
to expose from the SMP layer when an acknowledgment is received.
However, this would break some abstractions.

Instead, use a simpler solution: the initiating CPU of a TLB shootdown
would not defer PTI flushes. It is not always a win, relatively to
deferring user page-table flushes, but it prevents performance
regression.

Signed-off-by: Nadav Amit <namit@vmware.com>
---
 arch/x86/include/asm/tlbflush.h |  1 +
 arch/x86/mm/tlb.c               | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index da56aa3ccd07..066b3804f876 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -573,6 +573,7 @@ struct flush_tlb_info {
 	unsigned int		initiating_cpu;
 	u8			stride_shift;
 	u8			freed_tables;
+	u8			shootdown;
 };
 
 #define local_flush_tlb() __flush_tlb()
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 31260c55d597..ba50430275d4 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -592,8 +592,13 @@ static void flush_tlb_user_pt_range(u16 asid, const struct flush_tlb_info *f)
 
 	/*
 	 * We can defer flushes as long as page-tables were not freed.
+	 *
+	 * However, if there is a shootdown the initiating CPU has cycles to
+	 * spare, while it waits for the other cores to respond. In this case,
+	 * deferring the flushing can cause overheads, so avoid it.
 	 */
-	if (IS_ENABLED(CONFIG_X86_64) && !f->freed_tables) {
+	if (IS_ENABLED(CONFIG_X86_64) && !f->freed_tables &&
+	    (!f->shootdown || f->initiating_cpu != smp_processor_id())) {
 		flush_user_tlb_deferred(asid, start, end, stride_shift);
 		return;
 	}
@@ -861,6 +866,7 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
 	info->freed_tables	= freed_tables;
 	info->new_tlb_gen	= new_tlb_gen;
 	info->initiating_cpu	= smp_processor_id();
+	info->shootdown		= false;
 
 	return info;
 }
@@ -903,6 +909,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	 * flush_tlb_func_local() directly in this case.
 	 */
 	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+		info->shootdown = true;
 		flush_tlb_multi(mm_cpumask(mm), info);
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
@@ -970,6 +977,7 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	 * flush_tlb_func_local() directly in this case.
 	 */
 	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+		info->shootdown = true;
 		flush_tlb_multi(&batch->cpumask, info);
 	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
 		lockdep_assert_irqs_enabled();
-- 
2.17.1