x86/mm/tlb: Only trim the mm_cpumask once a second

Setting and clearing CPU bits in the mm_cpumask is only ever done
by the CPU itself, from the context switch code or the TLB flush
code.

Synchronization is handled by switch_mm_irqs_off() blocking interrupts.

Sending TLB flush IPIs to CPUs that are in the mm_cpumask, but no
longer running the program causes a regression in the will-it-scale
tlbflush2 test. This test is contrived, but a large regression here
might cause a small regression in some real world workload.

Instead of always sending IPIs to CPUs that are in the mm_cpumask,
but no longer running the program, send these IPIs only once a second.

The rest of the time we can skip over CPUs where the loaded_mm is
different from the target mm.

Reported-by: kernel test roboto <oliver.sang@intel.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20241204210316.612ee573@fangorn
Closes: https://lore.kernel.org/oe-lkp/202411282207.6bd28eae-lkp@intel.com/

arch/x86/include/asm/mmu.h

@@ -37,6 +37,8 @@ typedef struct {
 	 */
 	atomic64_t tlb_gen;
 
+	unsigned long next_trim_cpumask;
+
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct rw_semaphore	ldt_usr_sem;
 	struct ldt_struct	*ldt;

arch/x86/include/asm/mmu_context.h

@@ -151,6 +151,7 @@ static inline int init_new_context(struct task_struct *tsk,
 
 	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
 	atomic64_set(&mm->context.tlb_gen, 0);
+	mm->context.next_trim_cpumask = jiffies + HZ;
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {

arch/x86/include/asm/tlbflush.h

@@ -222,6 +222,7 @@ struct flush_tlb_info {
 	unsigned int		initiating_cpu;
 	u8			stride_shift;
 	u8			freed_tables;
+	u8			trim_cpumask;
 };
 
 void flush_tlb_local(void);

arch/x86/mm/tlb.c

@@ -892,9 +892,36 @@ done:
 			nr_invalidate);
 }
 
-static bool tlb_is_not_lazy(int cpu, void *data)
+static bool should_flush_tlb(int cpu, void *data)
 {
-	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
+	struct flush_tlb_info *info = data;
+
+	/* Lazy TLB will get flushed at the next context switch. */
+	if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
+		return false;
+
+	/* No mm means kernel memory flush. */
+	if (!info->mm)
+		return true;
+
+	/* The target mm is loaded, and the CPU is not lazy. */
+	if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm)
+		return true;
+
+	/* In cpumask, but not the loaded mm? Periodically remove by flushing. */
+	if (info->trim_cpumask)
+		return true;
+
+	return false;
+}
+
+static bool should_trim_cpumask(struct mm_struct *mm)
+{
+	if (time_after(jiffies, READ_ONCE(mm->context.next_trim_cpumask))) {
+		WRITE_ONCE(mm->context.next_trim_cpumask, jiffies + HZ);
+		return true;
+	}
+	return false;
 }
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
@@ -928,7 +955,7 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 	if (info->freed_tables)
 		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
 	else
-		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func,
+		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,
 				(void *)info, 1, cpumask);
 }
 
@@ -979,6 +1006,7 @@ 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->trim_cpumask	= 0;
 
 	return info;
 }
@@ -1021,6 +1049,7 @@ 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->trim_cpumask = should_trim_cpumask(mm);
 		flush_tlb_multi(mm_cpumask(mm), info);
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();