[RFC PATCH 4/6] x86/mm/tlb: Refactor common code into flush_tlb_on_cpus()

From: Nadav Amit
Date: Sat May 25 2019 - 04:25:33 EST


arch_tlbbatch_flush() and flush_tlb_mm_range() have very similar code,
which is effectively the same. Extract the mutual code into a new
function flush_tlb_on_cpus().

There is one functional change, which should not affect correctness:
flush_tlb_mm_range compared loaded_mm and the mm to figure out if local
flush is needed. Instead, the common code would look at the mm_cpumask()
which should give the same result. Performance should not be affected,
since this cpumask should not change in such a frequency that would
introduce cache contention.

Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
---
arch/x86/mm/tlb.c | 55 ++++++++++++++++++++++-------------------------
1 file changed, 26 insertions(+), 29 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 7f61431c75fb..afd2859a6966 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -733,7 +733,11 @@ static inline struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
unsigned int stride_shift, bool freed_tables,
u64 new_tlb_gen)
{
- struct flush_tlb_info *info = this_cpu_ptr(&flush_tlb_info);
+ struct flush_tlb_info *info;
+
+ preempt_disable();
+
+ info = this_cpu_ptr(&flush_tlb_info);

#ifdef CONFIG_DEBUG_VM
/*
@@ -761,6 +765,23 @@ static inline void put_flush_tlb_info(void)
barrier();
this_cpu_dec(flush_tlb_info_idx);
#endif
+ preempt_enable();
+}
+
+static void flush_tlb_on_cpus(const cpumask_t *cpumask,
+ const struct flush_tlb_info *info)
+{
+ int this_cpu = smp_processor_id();
+
+ if (cpumask_test_cpu(this_cpu, cpumask)) {
+ lockdep_assert_irqs_enabled();
+ local_irq_disable();
+ flush_tlb_func_local(info, TLB_LOCAL_MM_SHOOTDOWN);
+ local_irq_enable();
+ }
+
+ if (cpumask_any_but(cpumask, this_cpu) < nr_cpu_ids)
+ flush_tlb_others(cpumask, info);
}

void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
@@ -769,9 +790,6 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
{
struct flush_tlb_info *info;
u64 new_tlb_gen;
- int cpu;
-
- cpu = get_cpu();

/* Should we flush just the requested range? */
if ((end == TLB_FLUSH_ALL) ||
@@ -786,18 +804,9 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
info = get_flush_tlb_info(mm, start, end, stride_shift, freed_tables,
new_tlb_gen);

- if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
- lockdep_assert_irqs_enabled();
- local_irq_disable();
- flush_tlb_func_local(info, TLB_LOCAL_MM_SHOOTDOWN);
- local_irq_enable();
- }
-
- if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
- flush_tlb_others(mm_cpumask(mm), info);
+ flush_tlb_on_cpus(mm_cpumask(mm), info);

put_flush_tlb_info();
- put_cpu();
}


@@ -832,13 +841,11 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
} else {
struct flush_tlb_info *info;

- preempt_disable();
info = get_flush_tlb_info(NULL, start, end, 0, false, 0);

on_each_cpu(do_kernel_range_flush, info, 1);

put_flush_tlb_info();
- preempt_enable();
}
}

@@ -856,21 +863,11 @@ static const struct flush_tlb_info full_flush_tlb_info = {

void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
{
- int cpu = get_cpu();
-
- if (cpumask_test_cpu(cpu, &batch->cpumask)) {
- lockdep_assert_irqs_enabled();
- local_irq_disable();
- flush_tlb_func_local(&full_flush_tlb_info, TLB_LOCAL_SHOOTDOWN);
- local_irq_enable();
- }
-
- if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids)
- flush_tlb_others(&batch->cpumask, &full_flush_tlb_info);
+ preempt_disable();
+ flush_tlb_on_cpus(&batch->cpumask, &full_flush_tlb_info);
+ preempt_enable();

cpumask_clear(&batch->cpumask);
-
- put_cpu();
}

static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
--
2.20.1