[Deepin-Kernel-SIG] [linux 6.12-y] [Upstream] Merge x86,tlb: context switch optimizations

arch/x86/kernel/alternative.c

@@ -2053,11 +2053,18 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
 	return temp_state;
 }
 
+__ro_after_init struct mm_struct *poking_mm;
+__ro_after_init unsigned long poking_addr;
+
 static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
 {
 	lockdep_assert_irqs_disabled();
+
 	switch_mm_irqs_off(NULL, prev_state.mm, current);
 
+	/* Clear the cpumask, to indicate no TLB flushing is needed anywhere */
+	cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(poking_mm));
+
 	/*
 	 * Restore the breakpoints if they were disabled before the temporary mm
 	 * was loaded.
@@ -2066,9 +2073,6 @@ static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
 		hw_breakpoint_restore();
 }
 
-__ro_after_init struct mm_struct *poking_mm;
-__ro_after_init unsigned long poking_addr;
-
 static void text_poke_memcpy(void *dst, const void *src, size_t len)
 {
 	memcpy(dst, src, len);

arch/x86/mm/tlb.c

@@ -606,19 +606,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		 */
 		cond_mitigation(tsk);
 
-		/*
-		 * Stop remote flushes for the previous mm.
-		 * Skip kernel threads; we never send init_mm TLB flushing IPIs,
-		 * but the bitmap manipulation can cause cache line contention.
-		 */
-		if (prev != &init_mm) {
-			VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
-						mm_cpumask(prev)));
-			cpumask_clear_cpu(cpu, mm_cpumask(prev));
-		}
-
 		/* Start receiving IPIs and then read tlb_gen (and LAM below) */
-		if (next != &init_mm)
+		if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
@@ -766,8 +755,11 @@ static void flush_tlb_func(void *info)
 		count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 
 		/* Can only happen on remote CPUs */
-		if (f->mm && f->mm != loaded_mm)
+		if (f->mm && f->mm != loaded_mm) {
+			cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(f->mm));
+			trace_tlb_flush(TLB_REMOTE_WRONG_CPU, 0);
 			return;
+		}
 	}
 
 	if (unlikely(loaded_mm == &init_mm))

include/linux/mm_types.h

@@ -1365,6 +1365,7 @@ enum tlb_flush_reason {
 	TLB_LOCAL_SHOOTDOWN,
 	TLB_LOCAL_MM_SHOOTDOWN,
 	TLB_REMOTE_SEND_IPI,
+	TLB_REMOTE_WRONG_CPU,
 	NR_TLB_FLUSH_REASONS,
 };