[PATCH 5/7] x86,tlb: only send page table free TLB flush to lazy TLB CPUs

[Rik van Riel]

CPUs in !is_lazy have either received TLB flush IPIs earlier on during
the munmap (when the user memory was unmapped), or have context switched
and reloaded during that stage of the munmap.

Page table free TLB flushes only need to be sent to CPUs in lazy TLB
mode, which TLB contents might not yet be up to date yet.

Signed-off-by: Rik van Riel <riel@xxxxxxxxxxx>
Tested-by: Song Liu <songliubraving@xxxxxx>
---
 arch/x86/mm/tlb.c | 39 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 36 insertions(+), 3 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e59214ec52b1..c4073367219d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -718,14 +718,47 @@ void tlb_flush_remove_tables_local(void *arg)
 	}
 }
 
+static void mm_fill_lazy_tlb_cpu_mask(struct mm_struct *mm,
+				      struct cpumask* lazy_cpus)
+{
+	int cpu;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		if (!per_cpu(cpu_tlbstate.is_lazy, cpu))
+			cpumask_set_cpu(cpu, lazy_cpus);
+	}
+}
+
 void tlb_flush_remove_tables(struct mm_struct *mm)
 {
 	int cpu = get_cpu();
+	cpumask_var_t lazy_cpus;
+
+	if (cpumask_any_but(mm_cpumask(mm), cpu) >= nr_cpu_ids)
+		return;
+
+	if (!zalloc_cpumask_var(&lazy_cpus, GFP_ATOMIC)) {
+		/*
+		 * If the cpumask allocation fails, do a brute force flush
+		 * on all the CPUs that have this mm loaded.
+		 */
+		smp_call_function_many(mm_cpumask(mm),
+				tlb_flush_remove_tables_local, (void *)mm, 1);
+		return;
+	}
+
 	/*
-	 * XXX: this really only needs to be called for CPUs in lazy TLB mode.
+	 * CPUs with !is_lazy either received a TLB flush IPI while the user
+	 * pages in this address range were unmapped, or have context switched
+	 * and reloaded %CR3 since then.
+	 *
+	 * Shootdown IPIs at page table freeing time only need to be sent to
+	 * CPUs that may have out of date TLB contents.
 	 */
-	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
-		smp_call_function_many(mm_cpumask(mm), tlb_flush_remove_tables_local, (void *)mm, 1);
+	mm_fill_lazy_tlb_cpu_mask(mm, lazy_cpus);
+	smp_call_function_many(lazy_cpus,
+				tlb_flush_remove_tables_local, (void *)mm, 1);
+	free_cpumask_var(lazy_cpus);
 
 	put_cpu();
 }
-- 
2.14.4