Re: [PATCH 7.2 v10 2/2] x86/tlb: skip redundant sync IPIs for native TLB flush

[Lance Yang <lance.yang@linux.dev>]

On Fri, Apr 24, 2026 at 05:12:47PM +0200, Peter Zijlstra wrote:
>On Fri, Apr 24, 2026 at 02:25:28PM +0800, Lance Yang wrote:
>> diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
>> index cfcb60468b01..2cf1eeaffd6f 100644
>> --- a/arch/x86/hyperv/mmu.c
>> +++ b/arch/x86/hyperv/mmu.c
>> @@ -63,7 +63,7 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus,
>>  	struct hv_tlb_flush *flush;
>>  	u64 status;
>>  	unsigned long flags;
>> -	bool do_lazy = !info->freed_tables;
>> +	bool do_lazy = !info->wake_lazy_cpus;
>>  
>>  	trace_hyperv_mmu_flush_tlb_multi(cpus, info);
>>  
>> @@ -198,7 +198,7 @@ static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
>>  
>>  	flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
>>  	nr_bank = cpumask_to_vpset_skip(&flush->hv_vp_set, cpus,
>> -			info->freed_tables ? NULL : cpu_is_lazy);
>> +			info->wake_lazy_cpus ? NULL : cpu_is_lazy);
>>  	if (nr_bank < 0)
>>  		return HV_STATUS_INVALID_PARAMETER;
>>  
>> diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
>> index 866ea78ba156..fb256fd95f95 100644
>> --- a/arch/x86/include/asm/tlb.h
>> +++ b/arch/x86/include/asm/tlb.h
>
>>  static inline void tlb_flush(struct mmu_gather *tlb)
>>  {
>>  	unsigned long start = 0UL, end = TLB_FLUSH_ALL;
>>  	unsigned int stride_shift = tlb_get_unmap_shift(tlb);
>>  
>> +	/*
>> +	 * Both freed_tables and unshared_tables must wake lazy-TLB CPUs, so
>> +	 * they receive IPIs before reusing or freeing page tables, allowing
>> +	 * us to safely implement tlb_table_flush_implies_ipi_broadcast().
>> +	 */
>> +	bool wake_lazy_cpus = tlb->freed_tables || tlb->unshared_tables;
>> +
>>  	if (!tlb->fullmm && !tlb->need_flush_all) {
>>  		start = tlb->start;
>>  		end = tlb->end;
>>  	}
>>  
>> -	flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables);
>> +	flush_tlb_mm_range(tlb->mm, start, end, stride_shift, wake_lazy_cpus);
>>  }
>>  
>>  static inline void invlpg(unsigned long addr)
>> diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
>> index 5a3cdc439e38..39b9454781c3 100644
>> --- a/arch/x86/include/asm/tlbflush.h
>> +++ b/arch/x86/include/asm/tlbflush.h
>> @@ -225,7 +227,7 @@ struct flush_tlb_info {
>>  	u64			new_tlb_gen;
>>  	unsigned int		initiating_cpu;
>>  	u8			stride_shift;
>> -	u8			freed_tables;
>> +	u8			wake_lazy_cpus;
>>  	u8			trim_cpumask;
>>  };
>>  
>> @@ -315,7 +317,7 @@ static inline bool mm_in_asid_transition(struct mm_struct *mm) { return false; }
>>  extern void flush_tlb_all(void);
>>  extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
>>  				unsigned long end, unsigned int stride_shift,
>> -				bool freed_tables);
>> +				bool wake_lazy_cpus);
>>  extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
>>  
>>  static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
>
>> diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
>> index 621e09d049cb..3ce254a3982c 100644
>> --- a/arch/x86/mm/tlb.c
>> +++ b/arch/x86/mm/tlb.c
>> @@ -1360,16 +1362,16 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
>>  				(info->end - info->start) >> PAGE_SHIFT);
>>  
>>  	/*
>> -	 * If no page tables were freed, we can skip sending IPIs to
>> -	 * CPUs in lazy TLB mode. They will flush the CPU themselves
>> -	 * at the next context switch.
>> +	 * If lazy-TLB CPUs do not need to be woken, we can skip sending
>> +	 * IPIs to them. They will flush themselves at the next context
>> +	 * switch.
>>  	 *
>> -	 * However, if page tables are getting freed, we need to send the
>> -	 * IPI everywhere, to prevent CPUs in lazy TLB mode from tripping
>> -	 * up on the new contents of what used to be page tables, while
>> -	 * doing a speculative memory access.
>> +	 * However, if page tables are getting freed or unshared, we need
>> +	 * to send the IPI everywhere, to prevent CPUs in lazy TLB mode
>> +	 * from tripping up on the new contents of what used to be page
>> +	 * tables, while doing a speculative memory access.
>>  	 */
>> -	if (info->freed_tables || mm_in_asid_transition(info->mm))
>> +	if (info->wake_lazy_cpus || mm_in_asid_transition(info->mm))
>>  		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
>>  	else
>>  		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,
>> @@ -1402,7 +1404,7 @@ static DEFINE_PER_CPU(unsigned int, flush_tlb_info_idx);
>>  
>>  static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
>>  			unsigned long start, unsigned long end,
>> -			unsigned int stride_shift, bool freed_tables,
>> +			unsigned int stride_shift, bool wake_lazy_cpus,
>>  			u64 new_tlb_gen)
>>  {
>>  	struct flush_tlb_info *info = this_cpu_ptr(&flush_tlb_info);
>> @@ -1429,7 +1431,7 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
>>  	info->end		= end;
>>  	info->mm		= mm;
>>  	info->stride_shift	= stride_shift;
>> -	info->freed_tables	= freed_tables;
>> +	info->wake_lazy_cpus	= wake_lazy_cpus;
>>  	info->new_tlb_gen	= new_tlb_gen;
>>  	info->initiating_cpu	= smp_processor_id();
>>  	info->trim_cpumask	= 0;
>> @@ -1448,7 +1450,7 @@ static void put_flush_tlb_info(void)
>>  
>>  void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
>>  				unsigned long end, unsigned int stride_shift,
>> -				bool freed_tables)
>> +				bool wake_lazy_cpus)
>>  {
>>  	struct flush_tlb_info *info;
>>  	int cpu = get_cpu();
>> @@ -1457,7 +1459,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
>>  	/* This is also a barrier that synchronizes with switch_mm(). */
>>  	new_tlb_gen = inc_mm_tlb_gen(mm);
>>  
>> -	info = get_flush_tlb_info(mm, start, end, stride_shift, freed_tables,
>> +	info = get_flush_tlb_info(mm, start, end, stride_shift, wake_lazy_cpus,
>>  				  new_tlb_gen);
>>  
>>  	/*
>
>This whole s/freed_tables/wake_lazy_cpus/ rename should probably be its
>own patch, as should that include unshare_tables thing be.
>
>That seems like unrelated changes.

Thanks, makes sense! Will split the pure s/freed_tables/wake_lazy_cpus/
rename out.

For the tlb->unshared_tables part, I would keep it with this patch, 
since lazy-TLB CPUs still have to be woken before reusing unshared page
tables.

@Dave what do you think?

Thanks,
Lance