[PATCH v7 14/14] x86/mm: Re-enable preemption before flush_tlb_multi()

[Chuyi Zhou]

flush_tlb_mm_range() and arch_tlbbatch_flush() pin the current CPU while
they decide whether the flush can be handled locally or must be sent to
remote CPUs. The CPU pinning is needed for the current CPU number and for
the local TLB flush path, which reads per-CPU TLB state.

It is not needed while waiting for a remote TLB flush to complete. After
the remote-flush path has been selected, flush_tlb_info is caller-private
stack storage, so the caller no longer has to stay on the same CPU to
protect a shared per-CPU flush_tlb_info object.

flush_tlb_multi() may also route through x86 PV backends. Those backends
must protect their own CPU-local scratch state instead of relying on the
caller to stay pinned. Hyper-V already does this by disabling interrupts
while using hyperv_pcpu_input_arg, and Xen's multicall path brackets its
per-CPU multicall buffer with xen_mc_batch()/xen_mc_issue(). The previous
patch makes the KVM backend do the same for __pv_cpu_mask.

Remote TLB flushes may synchronously wait for many CPUs, and the wait can
take tens of milliseconds when remote CPUs have interrupts disabled or
when many CPUs are involved. Keeping preemption disabled for that whole
wait unnecessarily increases scheduling latency on the initiating CPU.

Drop the CPU pinning before calling flush_tlb_multi() in the remote paths
of flush_tlb_mm_range() and arch_tlbbatch_flush(). Keep the local paths
inside the pinned section because they still access this CPU's TLB state.

Signed-off-by: Chuyi Zhou <zhouchuyi@xxxxxxxxxxxxx>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Tested-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
---
 arch/x86/mm/tlb.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 0c55ee84d50c..807a15b1af19 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1404,6 +1404,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 {
 	struct flush_tlb_info _info;
 	struct flush_tlb_info *info = &_info;
+	bool remote_flush = false;
 	int cpu = get_cpu();
 	u64 new_tlb_gen;
 
@@ -1421,9 +1422,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	if (mm_global_asid(mm)) {
 		broadcast_tlb_flush(info);
 	} else if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
-		info->trim_cpumask = should_trim_cpumask(mm);
-		flush_tlb_multi(mm_cpumask(mm), info);
-		consider_global_asid(mm);
+		remote_flush = true;
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();
@@ -1432,6 +1431,13 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	}
 
 	put_cpu();
+
+	if (remote_flush) {
+		info->trim_cpumask = should_trim_cpumask(mm);
+		flush_tlb_multi(mm_cpumask(mm), info);
+		consider_global_asid(mm);
+	}
+
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
@@ -1678,7 +1684,7 @@ EXPORT_SYMBOL_FOR_KVM(__flush_tlb_all);
 void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
 	struct flush_tlb_info info;
-
+	bool remote_flush = false;
 	int cpu = get_cpu();
 
 	init_flush_tlb_info(&info, NULL, 0, TLB_FLUSH_ALL, 0, false,
@@ -1692,7 +1698,7 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 		invlpgb_flush_all_nonglobals();
 		batch->unmapped_pages = false;
 	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
-		flush_tlb_multi(&batch->cpumask, &info);
+		remote_flush = true;
 	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();
@@ -1700,9 +1706,12 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 		local_irq_enable();
 	}
 
-	cpumask_clear(&batch->cpumask);
-
 	put_cpu();
+
+	if (remote_flush)
+		flush_tlb_multi(&batch->cpumask, &info);
+
+	cpumask_clear(&batch->cpumask);
 }
 
 /*
-- 
2.20.1