[v3,4/9] x86/mm/tlb: Flush remote and local TLBs concurrently
diff mbox series

Message ID 20190719005837.4150-5-namit@vmware.com
State New
Headers show
Series
  • x86: Concurrent TLB flushes
Related show

Commit Message

Nadav Amit July 19, 2019, 12:58 a.m. UTC
To improve TLB shootdown performance, flush the remote and local TLBs
concurrently. Introduce flush_tlb_multi() that does so. Introduce
paravirtual versions of flush_tlb_multi() for KVM, Xen and hyper-v (Xen
and hyper-v are only compile-tested).

While the updated smp infrastructure is capable of running a function on
a single local core, it is not optimized for this case. The multiple
function calls and the indirect branch introduce some overhead, and
might make local TLB flushes slower than they were before the recent
changes.

Before calling the SMP infrastructure, check if only a local TLB flush
is needed to restore the lost performance in this common case. This
requires to check mm_cpumask() one more time, but unless this mask is
updated very frequently, this should impact performance negatively.

Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Sasha Levin <sashal@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org
Cc: Juergen Gross <jgross@suse.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: linux-hyperv@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Cc: kvm@vger.kernel.org
Cc: xen-devel@lists.xenproject.org
Signed-off-by: Nadav Amit <namit@vmware.com>
---
 arch/x86/hyperv/mmu.c                 | 10 +++---
 arch/x86/include/asm/paravirt.h       |  6 ++--
 arch/x86/include/asm/paravirt_types.h |  4 +--
 arch/x86/include/asm/tlbflush.h       |  8 ++---
 arch/x86/include/asm/trace/hyperv.h   |  2 +-
 arch/x86/kernel/kvm.c                 | 11 +++++--
 arch/x86/kernel/paravirt.c            |  2 +-
 arch/x86/mm/tlb.c                     | 47 ++++++++++++++++++---------
 arch/x86/xen/mmu_pv.c                 | 11 +++----
 include/trace/events/xen.h            |  2 +-
 10 files changed, 62 insertions(+), 41 deletions(-)

Comments

Peter Zijlstra July 22, 2019, 7:14 p.m. UTC | #1
On Thu, Jul 18, 2019 at 05:58:32PM -0700, Nadav Amit wrote:
> @@ -709,8 +716,9 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
>  	 * doing a speculative memory access.
>  	 */
>  	if (info->freed_tables) {
> -		smp_call_function_many(cpumask, flush_tlb_func_remote,
> -			       (void *)info, 1);
> +		__smp_call_function_many(cpumask, flush_tlb_func_remote,
> +					 flush_tlb_func_local,
> +					 (void *)info, 1);
>  	} else {
>  		/*
>  		 * Although we could have used on_each_cpu_cond_mask(),
> @@ -737,7 +745,8 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
>  			if (tlb_is_not_lazy(cpu))
>  				__cpumask_set_cpu(cpu, cond_cpumask);
>  		}
> -		smp_call_function_many(cond_cpumask, flush_tlb_func_remote,
> +		__smp_call_function_many(cond_cpumask, flush_tlb_func_remote,
> +					 flush_tlb_func_local,
>  					 (void *)info, 1);
>  	}
>  }

Do we really need that _local/_remote distinction? ISTR you had a patch
that frobbed flush_tlb_info into the csd and that gave space
constraints, but I'm not seeing that here (probably a wise, get stuff
merged etc..).

struct __call_single_data {
        struct llist_node          llist;                /*     0     8 */
        smp_call_func_t            func;                 /*     8     8 */
        void *                     info;                 /*    16     8 */
        unsigned int               flags;                /*    24     4 */

        /* size: 32, cachelines: 1, members: 4 */
        /* padding: 4 */
        /* last cacheline: 32 bytes */
};

struct flush_tlb_info {
        struct mm_struct *         mm;                   /*     0     8 */
        long unsigned int          start;                /*     8     8 */
        long unsigned int          end;                  /*    16     8 */
        u64                        new_tlb_gen;          /*    24     8 */
        unsigned int               stride_shift;         /*    32     4 */
        bool                       freed_tables;         /*    36     1 */

        /* size: 40, cachelines: 1, members: 6 */
        /* padding: 3 */
        /* last cacheline: 40 bytes */
};

IIRC what you did was make void *__call_single_data::info the last
member and a union until the full cacheline size (64). Given the above
that would get us 24 bytes for csd, leaving us 40 for that
flush_tlb_info.

But then we can still do something like the below, which doesn't change
things and still gets rid of that dual function crud, simplifying
smp_call_function_many again.

Index: linux-2.6/arch/x86/include/asm/tlbflush.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/tlbflush.h
+++ linux-2.6/arch/x86/include/asm/tlbflush.h
@@ -546,8 +546,9 @@ struct flush_tlb_info {
 	unsigned long		start;
 	unsigned long		end;
 	u64			new_tlb_gen;
-	unsigned int		stride_shift;
-	bool			freed_tables;
+	unsigned int		cpu;
+	unsigned short		stride_shift;
+	unsigned char		freed_tables;
 };
 
 #define local_flush_tlb() __flush_tlb()
Index: linux-2.6/arch/x86/mm/tlb.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/tlb.c
+++ linux-2.6/arch/x86/mm/tlb.c
@@ -659,6 +659,27 @@ static void flush_tlb_func_remote(void *
 	flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN);
 }
 
+static void flush_tlb_func(void *info)
+{
+	const struct flush_tlb_info *f = info;
+	enum tlb_flush_reason reason = TLB_REMOTE_SHOOTDOWN;
+	bool local = false;
+
+	if (f->cpu == smp_processor_id()) {
+		local = true;
+		reason = (f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN : TLB_LOCAL_MM_SHOOTDOWN;
+	} else {
+		inc_irq_stat(irq_tlb_count);
+
+		if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm))
+			return;
+
+		count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	}
+
+	flush_tlb_func_common(f, local, reason);
+}
+
 static bool tlb_is_not_lazy(int cpu)
 {
 	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
Nadav Amit July 22, 2019, 7:27 p.m. UTC | #2
> On Jul 22, 2019, at 12:14 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> 
> On Thu, Jul 18, 2019 at 05:58:32PM -0700, Nadav Amit wrote:
>> @@ -709,8 +716,9 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
>> 	 * doing a speculative memory access.
>> 	 */
>> 	if (info->freed_tables) {
>> -		smp_call_function_many(cpumask, flush_tlb_func_remote,
>> -			       (void *)info, 1);
>> +		__smp_call_function_many(cpumask, flush_tlb_func_remote,
>> +					 flush_tlb_func_local,
>> +					 (void *)info, 1);
>> 	} else {
>> 		/*
>> 		 * Although we could have used on_each_cpu_cond_mask(),
>> @@ -737,7 +745,8 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
>> 			if (tlb_is_not_lazy(cpu))
>> 				__cpumask_set_cpu(cpu, cond_cpumask);
>> 		}
>> -		smp_call_function_many(cond_cpumask, flush_tlb_func_remote,
>> +		__smp_call_function_many(cond_cpumask, flush_tlb_func_remote,
>> +					 flush_tlb_func_local,
>> 					 (void *)info, 1);
>> 	}
>> }
> 
> Do we really need that _local/_remote distinction? ISTR you had a patch
> that frobbed flush_tlb_info into the csd and that gave space
> constraints, but I'm not seeing that here (probably a wise, get stuff
> merged etc..).
> 
> struct __call_single_data {
>        struct llist_node          llist;                /*     0     8 */
>        smp_call_func_t            func;                 /*     8     8 */
>        void *                     info;                 /*    16     8 */
>        unsigned int               flags;                /*    24     4 */
> 
>        /* size: 32, cachelines: 1, members: 4 */
>        /* padding: 4 */
>        /* last cacheline: 32 bytes */
> };
> 
> struct flush_tlb_info {
>        struct mm_struct *         mm;                   /*     0     8 */
>        long unsigned int          start;                /*     8     8 */
>        long unsigned int          end;                  /*    16     8 */
>        u64                        new_tlb_gen;          /*    24     8 */
>        unsigned int               stride_shift;         /*    32     4 */
>        bool                       freed_tables;         /*    36     1 */
> 
>        /* size: 40, cachelines: 1, members: 6 */
>        /* padding: 3 */
>        /* last cacheline: 40 bytes */
> };
> 
> IIRC what you did was make void *__call_single_data::info the last
> member and a union until the full cacheline size (64). Given the above
> that would get us 24 bytes for csd, leaving us 40 for that
> flush_tlb_info.
> 
> But then we can still do something like the below, which doesn't change
> things and still gets rid of that dual function crud, simplifying
> smp_call_function_many again.
> 
> Index: linux-2.6/arch/x86/include/asm/tlbflush.h
> ===================================================================
> --- linux-2.6.orig/arch/x86/include/asm/tlbflush.h
> +++ linux-2.6/arch/x86/include/asm/tlbflush.h
> @@ -546,8 +546,9 @@ struct flush_tlb_info {
> 	unsigned long		start;
> 	unsigned long		end;
> 	u64			new_tlb_gen;
> -	unsigned int		stride_shift;
> -	bool			freed_tables;
> +	unsigned int		cpu;
> +	unsigned short		stride_shift;
> +	unsigned char		freed_tables;
> };
> 
> #define local_flush_tlb() __flush_tlb()
> Index: linux-2.6/arch/x86/mm/tlb.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/mm/tlb.c
> +++ linux-2.6/arch/x86/mm/tlb.c
> @@ -659,6 +659,27 @@ static void flush_tlb_func_remote(void *
> 	flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN);
> }
> 
> +static void flush_tlb_func(void *info)
> +{
> +	const struct flush_tlb_info *f = info;
> +	enum tlb_flush_reason reason = TLB_REMOTE_SHOOTDOWN;
> +	bool local = false;
> +
> +	if (f->cpu == smp_processor_id()) {
> +		local = true;
> +		reason = (f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN : TLB_LOCAL_MM_SHOOTDOWN;
> +	} else {
> +		inc_irq_stat(irq_tlb_count);
> +
> +		if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm))
> +			return;
> +
> +		count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
> +	}
> +
> +	flush_tlb_func_common(f, local, reason);
> +}
> +
> static bool tlb_is_not_lazy(int cpu)
> {
> 	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);

Nice! I will add it on top, if you don’t mind (instead squashing it).

The original decision to have local/remote functions was mostly to provide
the generality.

I would change the last argument of __smp_call_function_many() from “wait”
to “flags” that would indicate whether to run the function locally, since I
don’t want to change the semantics of smp_call_function_many() and decide
whether to run the function locally purely based on the mask. Let me know if
you disagree.
Peter Zijlstra July 22, 2019, 7:32 p.m. UTC | #3
On Mon, Jul 22, 2019 at 07:27:09PM +0000, Nadav Amit wrote:
> > On Jul 22, 2019, at 12:14 PM, Peter Zijlstra <peterz@infradead.org> wrote:

> > But then we can still do something like the below, which doesn't change
> > things and still gets rid of that dual function crud, simplifying
> > smp_call_function_many again.

> Nice! I will add it on top, if you don’t mind (instead squashing it).

Not at all.

> The original decision to have local/remote functions was mostly to provide
> the generality.
> 
> I would change the last argument of __smp_call_function_many() from “wait”
> to “flags” that would indicate whether to run the function locally, since I
> don’t want to change the semantics of smp_call_function_many() and decide
> whether to run the function locally purely based on the mask. Let me know if
> you disagree.

Agreed.
Juergen Gross July 26, 2019, 7:28 a.m. UTC | #4
On 19.07.19 02:58, Nadav Amit wrote:
> To improve TLB shootdown performance, flush the remote and local TLBs
> concurrently. Introduce flush_tlb_multi() that does so. Introduce
> paravirtual versions of flush_tlb_multi() for KVM, Xen and hyper-v (Xen
> and hyper-v are only compile-tested).
> 
> While the updated smp infrastructure is capable of running a function on
> a single local core, it is not optimized for this case. The multiple
> function calls and the indirect branch introduce some overhead, and
> might make local TLB flushes slower than they were before the recent
> changes.
> 
> Before calling the SMP infrastructure, check if only a local TLB flush
> is needed to restore the lost performance in this common case. This
> requires to check mm_cpumask() one more time, but unless this mask is
> updated very frequently, this should impact performance negatively.
> 
> Cc: "K. Y. Srinivasan" <kys@microsoft.com>
> Cc: Haiyang Zhang <haiyangz@microsoft.com>
> Cc: Stephen Hemminger <sthemmin@microsoft.com>
> Cc: Sasha Levin <sashal@kernel.org>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Borislav Petkov <bp@alien8.de>
> Cc: x86@kernel.org
> Cc: Juergen Gross <jgross@suse.com>
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Dave Hansen <dave.hansen@linux.intel.com>
> Cc: Andy Lutomirski <luto@kernel.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
> Cc: linux-hyperv@vger.kernel.org
> Cc: linux-kernel@vger.kernel.org
> Cc: virtualization@lists.linux-foundation.org
> Cc: kvm@vger.kernel.org
> Cc: xen-devel@lists.xenproject.org
> Signed-off-by: Nadav Amit <namit@vmware.com>
> ---
>   arch/x86/hyperv/mmu.c                 | 10 +++---
>   arch/x86/include/asm/paravirt.h       |  6 ++--
>   arch/x86/include/asm/paravirt_types.h |  4 +--
>   arch/x86/include/asm/tlbflush.h       |  8 ++---
>   arch/x86/include/asm/trace/hyperv.h   |  2 +-
>   arch/x86/kernel/kvm.c                 | 11 +++++--
>   arch/x86/kernel/paravirt.c            |  2 +-
>   arch/x86/mm/tlb.c                     | 47 ++++++++++++++++++---------
>   arch/x86/xen/mmu_pv.c                 | 11 +++----
>   include/trace/events/xen.h            |  2 +-
>   10 files changed, 62 insertions(+), 41 deletions(-)

Xen and paravirt parts: Reviewed-by: Juergen Gross <jgross@suse.com>


Juergen
Michael Kelley July 31, 2019, 12:13 a.m. UTC | #5
From: Nadav Amit <namit@vmware.com> Sent: Thursday, July 18, 2019 5:59 PM
> 
> To improve TLB shootdown performance, flush the remote and local TLBs
> concurrently. Introduce flush_tlb_multi() that does so. Introduce
> paravirtual versions of flush_tlb_multi() for KVM, Xen and hyper-v (Xen
> and hyper-v are only compile-tested).
> 
> While the updated smp infrastructure is capable of running a function on
> a single local core, it is not optimized for this case. The multiple
> function calls and the indirect branch introduce some overhead, and
> might make local TLB flushes slower than they were before the recent
> changes.
> 
> Before calling the SMP infrastructure, check if only a local TLB flush
> is needed to restore the lost performance in this common case. This
> requires to check mm_cpumask() one more time, but unless this mask is
> updated very frequently, this should impact performance negatively.
> 
> Cc: "K. Y. Srinivasan" <kys@microsoft.com>
> Cc: Haiyang Zhang <haiyangz@microsoft.com>
> Cc: Stephen Hemminger <sthemmin@microsoft.com>
> Cc: Sasha Levin <sashal@kernel.org>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Borislav Petkov <bp@alien8.de>
> Cc: x86@kernel.org
> Cc: Juergen Gross <jgross@suse.com>
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Dave Hansen <dave.hansen@linux.intel.com>
> Cc: Andy Lutomirski <luto@kernel.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
> Cc: linux-hyperv@vger.kernel.org
> Cc: linux-kernel@vger.kernel.org
> Cc: virtualization@lists.linux-foundation.org
> Cc: kvm@vger.kernel.org
> Cc: xen-devel@lists.xenproject.org
> Signed-off-by: Nadav Amit <namit@vmware.com>
> ---
>  arch/x86/hyperv/mmu.c                 | 10 +++---
>  arch/x86/include/asm/paravirt.h       |  6 ++--
>  arch/x86/include/asm/paravirt_types.h |  4 +--
>  arch/x86/include/asm/tlbflush.h       |  8 ++---
>  arch/x86/include/asm/trace/hyperv.h   |  2 +-
>  arch/x86/kernel/kvm.c                 | 11 +++++--
>  arch/x86/kernel/paravirt.c            |  2 +-
>  arch/x86/mm/tlb.c                     | 47 ++++++++++++++++++---------
>  arch/x86/xen/mmu_pv.c                 | 11 +++----
>  include/trace/events/xen.h            |  2 +-
>  10 files changed, 62 insertions(+), 41 deletions(-)
> 

For the Hyper-V parts --
Reviewed-by: Michael Kelley <mikelley@microsoft.com>

Patch
diff mbox series

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index e65d7fe6489f..8740d8b21db3 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -50,8 +50,8 @@  static inline int fill_gva_list(u64 gva_list[], int offset,
 	return gva_n - offset;
 }
 
-static void hyperv_flush_tlb_others(const struct cpumask *cpus,
-				    const struct flush_tlb_info *info)
+static void hyperv_flush_tlb_multi(const struct cpumask *cpus,
+				   const struct flush_tlb_info *info)
 {
 	int cpu, vcpu, gva_n, max_gvas;
 	struct hv_tlb_flush **flush_pcpu;
@@ -59,7 +59,7 @@  static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	u64 status = U64_MAX;
 	unsigned long flags;
 
-	trace_hyperv_mmu_flush_tlb_others(cpus, info);
+	trace_hyperv_mmu_flush_tlb_multi(cpus, info);
 
 	if (!hv_hypercall_pg)
 		goto do_native;
@@ -156,7 +156,7 @@  static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	if (!(status & HV_HYPERCALL_RESULT_MASK))
 		return;
 do_native:
-	native_flush_tlb_others(cpus, info);
+	native_flush_tlb_multi(cpus, info);
 }
 
 static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
@@ -231,6 +231,6 @@  void hyperv_setup_mmu_ops(void)
 		return;
 
 	pr_info("Using hypercall for remote TLB flush\n");
-	pv_ops.mmu.flush_tlb_others = hyperv_flush_tlb_others;
+	pv_ops.mmu.flush_tlb_multi = hyperv_flush_tlb_multi;
 	pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 }
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index dce26f1d13e1..8c6c2394393b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -62,10 +62,10 @@  static inline void __flush_tlb_one_user(unsigned long addr)
 	PVOP_VCALL1(mmu.flush_tlb_one_user, addr);
 }
 
-static inline void flush_tlb_others(const struct cpumask *cpumask,
-				    const struct flush_tlb_info *info)
+static inline void flush_tlb_multi(const struct cpumask *cpumask,
+				   const struct flush_tlb_info *info)
 {
-	PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info);
+	PVOP_VCALL2(mmu.flush_tlb_multi, cpumask, info);
 }
 
 static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 639b2df445ee..c82969f38845 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -211,8 +211,8 @@  struct pv_mmu_ops {
 	void (*flush_tlb_user)(void);
 	void (*flush_tlb_kernel)(void);
 	void (*flush_tlb_one_user)(unsigned long addr);
-	void (*flush_tlb_others)(const struct cpumask *cpus,
-				 const struct flush_tlb_info *info);
+	void (*flush_tlb_multi)(const struct cpumask *cpus,
+				const struct flush_tlb_info *info);
 
 	void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
 
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index dee375831962..610e47dc66ef 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -517,7 +517,7 @@  static inline void __flush_tlb_one_kernel(unsigned long addr)
  *  - flush_tlb_page(vma, vmaddr) flushes one page
  *  - flush_tlb_range(vma, start, end) flushes a range of pages
  *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
- *  - flush_tlb_others(cpumask, info) flushes TLBs on other cpus
+ *  - flush_tlb_multi(cpumask, info) flushes TLBs on multiple cpus
  *
  * ..but the i386 has somewhat limited tlb flushing capabilities,
  * and page-granular flushes are available only on i486 and up.
@@ -569,7 +569,7 @@  static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
 	flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false);
 }
 
-void native_flush_tlb_others(const struct cpumask *cpumask,
+void native_flush_tlb_multi(const struct cpumask *cpumask,
 			     const struct flush_tlb_info *info);
 
 static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
@@ -593,8 +593,8 @@  static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
 extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 
 #ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, info)	\
-	native_flush_tlb_others(mask, info)
+#define flush_tlb_multi(mask, info)	\
+	native_flush_tlb_multi(mask, info)
 
 #define paravirt_tlb_remove_table(tlb, page) \
 	tlb_remove_page(tlb, (void *)(page))
diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h
index ace464f09681..85ca8560c7f9 100644
--- a/arch/x86/include/asm/trace/hyperv.h
+++ b/arch/x86/include/asm/trace/hyperv.h
@@ -8,7 +8,7 @@ 
 
 #if IS_ENABLED(CONFIG_HYPERV)
 
-TRACE_EVENT(hyperv_mmu_flush_tlb_others,
+TRACE_EVENT(hyperv_mmu_flush_tlb_multi,
 	    TP_PROTO(const struct cpumask *cpus,
 		     const struct flush_tlb_info *info),
 	    TP_ARGS(cpus, info),
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b7f34fe2171e..de40657d9025 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -595,7 +595,7 @@  static void __init kvm_apf_trap_init(void)
 
 static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
 
-static void kvm_flush_tlb_others(const struct cpumask *cpumask,
+static void kvm_flush_tlb_multi(const struct cpumask *cpumask,
 			const struct flush_tlb_info *info)
 {
 	u8 state;
@@ -609,6 +609,11 @@  static void kvm_flush_tlb_others(const struct cpumask *cpumask,
 	 * queue flush_on_enter for pre-empted vCPUs
 	 */
 	for_each_cpu(cpu, flushmask) {
+		/*
+		 * The local vCPU is never preempted, so we do not explicitly
+		 * skip check for local vCPU - it will never be cleared from
+		 * flushmask.
+		 */
 		src = &per_cpu(steal_time, cpu);
 		state = READ_ONCE(src->preempted);
 		if ((state & KVM_VCPU_PREEMPTED)) {
@@ -618,7 +623,7 @@  static void kvm_flush_tlb_others(const struct cpumask *cpumask,
 		}
 	}
 
-	native_flush_tlb_others(flushmask, info);
+	native_flush_tlb_multi(flushmask, info);
 }
 
 static void __init kvm_guest_init(void)
@@ -643,7 +648,7 @@  static void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
 	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
 	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
-		pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
+		pv_ops.mmu.flush_tlb_multi = kvm_flush_tlb_multi;
 		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 	}
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 0aa6256eedd8..6af40844a730 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -363,7 +363,7 @@  struct paravirt_patch_template pv_ops = {
 	.mmu.flush_tlb_user	= native_flush_tlb,
 	.mmu.flush_tlb_kernel	= native_flush_tlb_global,
 	.mmu.flush_tlb_one_user	= native_flush_tlb_one_user,
-	.mmu.flush_tlb_others	= native_flush_tlb_others,
+	.mmu.flush_tlb_multi	= native_flush_tlb_multi,
 	.mmu.tlb_remove_table	=
 			(void (*)(struct mmu_gather *, void *))tlb_remove_page,
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index abbf55fa8b81..63c00908bdd9 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -551,7 +551,7 @@  static void flush_tlb_func_common(const struct flush_tlb_info *f,
 		 * garbage into our TLB.  Since switching to init_mm is barely
 		 * slower than a minimal flush, just switch to init_mm.
 		 *
-		 * This should be rare, with native_flush_tlb_others skipping
+		 * This should be rare, with native_flush_tlb_multi() skipping
 		 * IPIs to lazy TLB mode CPUs.
 		 */
 		switch_mm_irqs_off(NULL, &init_mm, NULL);
@@ -665,9 +665,14 @@  static bool tlb_is_not_lazy(int cpu)
 
 static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
 
-void native_flush_tlb_others(const struct cpumask *cpumask,
-			     const struct flush_tlb_info *info)
+void native_flush_tlb_multi(const struct cpumask *cpumask,
+			    const struct flush_tlb_info *info)
 {
+	/*
+	 * Do accounting and tracing. Note that there are (and have always been)
+	 * cases in which a remote TLB flush will be traced, but eventually
+	 * would not happen.
+	 */
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (info->end == TLB_FLUSH_ALL)
 		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
@@ -687,10 +692,12 @@  void native_flush_tlb_others(const struct cpumask *cpumask,
 		 * means that the percpu tlb_gen variables won't be updated
 		 * and we'll do pointless flushes on future context switches.
 		 *
-		 * Rather than hooking native_flush_tlb_others() here, I think
+		 * Rather than hooking native_flush_tlb_multi() here, I think
 		 * that UV should be updated so that smp_call_function_many(),
 		 * etc, are optimal on UV.
 		 */
+		flush_tlb_func_local((void *)info);
+
 		cpumask = uv_flush_tlb_others(cpumask, info);
 		if (cpumask)
 			smp_call_function_many(cpumask, flush_tlb_func_remote,
@@ -709,8 +716,9 @@  void native_flush_tlb_others(const struct cpumask *cpumask,
 	 * doing a speculative memory access.
 	 */
 	if (info->freed_tables) {
-		smp_call_function_many(cpumask, flush_tlb_func_remote,
-			       (void *)info, 1);
+		__smp_call_function_many(cpumask, flush_tlb_func_remote,
+					 flush_tlb_func_local,
+					 (void *)info, 1);
 	} else {
 		/*
 		 * Although we could have used on_each_cpu_cond_mask(),
@@ -737,7 +745,8 @@  void native_flush_tlb_others(const struct cpumask *cpumask,
 			if (tlb_is_not_lazy(cpu))
 				__cpumask_set_cpu(cpu, cond_cpumask);
 		}
-		smp_call_function_many(cond_cpumask, flush_tlb_func_remote,
+		__smp_call_function_many(cond_cpumask, flush_tlb_func_remote,
+					 flush_tlb_func_local,
 					 (void *)info, 1);
 	}
 }
@@ -818,16 +827,20 @@  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)) {
+	/*
+	 * flush_tlb_multi() is not optimized for the common case in which only
+	 * a local TLB flush is needed. Optimize this use-case by calling
+	 * flush_tlb_func_local() directly in this case.
+	 */
+	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+		flush_tlb_multi(mm_cpumask(mm), info);
+	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();
 		flush_tlb_func_local(info);
 		local_irq_enable();
 	}
 
-	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), info);
-
 	put_flush_tlb_info();
 	put_cpu();
 }
@@ -890,16 +903,20 @@  void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
 	int cpu = get_cpu();
 
-	if (cpumask_test_cpu(cpu, &batch->cpumask)) {
+	/*
+	 * flush_tlb_multi() is not optimized for the common case in which only
+	 * a local TLB flush is needed. Optimize this use-case by calling
+	 * flush_tlb_func_local() directly in this case.
+	 */
+	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+		flush_tlb_multi(&batch->cpumask, &full_flush_tlb_info);
+	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();
 		flush_tlb_func_local((void *)&full_flush_tlb_info);
 		local_irq_enable();
 	}
 
-	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids)
-		flush_tlb_others(&batch->cpumask, &full_flush_tlb_info);
-
 	cpumask_clear(&batch->cpumask);
 
 	put_cpu();
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 26e8b326966d..48f7c7eb4dbc 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1345,8 +1345,8 @@  static void xen_flush_tlb_one_user(unsigned long addr)
 	preempt_enable();
 }
 
-static void xen_flush_tlb_others(const struct cpumask *cpus,
-				 const struct flush_tlb_info *info)
+static void xen_flush_tlb_multi(const struct cpumask *cpus,
+				const struct flush_tlb_info *info)
 {
 	struct {
 		struct mmuext_op op;
@@ -1356,7 +1356,7 @@  static void xen_flush_tlb_others(const struct cpumask *cpus,
 	const size_t mc_entry_size = sizeof(args->op) +
 		sizeof(args->mask[0]) * BITS_TO_LONGS(num_possible_cpus());
 
-	trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end);
+	trace_xen_mmu_flush_tlb_multi(cpus, info->mm, info->start, info->end);
 
 	if (cpumask_empty(cpus))
 		return;		/* nothing to do */
@@ -1365,9 +1365,8 @@  static void xen_flush_tlb_others(const struct cpumask *cpus,
 	args = mcs.args;
 	args->op.arg2.vcpumask = to_cpumask(args->mask);
 
-	/* Remove us, and any offline CPUS. */
+	/* Remove any offline CPUs */
 	cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
 
 	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
 	if (info->end != TLB_FLUSH_ALL &&
@@ -2396,7 +2395,7 @@  static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.flush_tlb_user = xen_flush_tlb,
 	.flush_tlb_kernel = xen_flush_tlb,
 	.flush_tlb_one_user = xen_flush_tlb_one_user,
-	.flush_tlb_others = xen_flush_tlb_others,
+	.flush_tlb_multi = xen_flush_tlb_multi,
 	.tlb_remove_table = tlb_remove_table,
 
 	.pgd_alloc = xen_pgd_alloc,
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index 9a0e8af21310..546022acf160 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -362,7 +362,7 @@  TRACE_EVENT(xen_mmu_flush_tlb_one_user,
 	    TP_printk("addr %lx", __entry->addr)
 	);
 
-TRACE_EVENT(xen_mmu_flush_tlb_others,
+TRACE_EVENT(xen_mmu_flush_tlb_multi,
 	    TP_PROTO(const struct cpumask *cpus, struct mm_struct *mm,
 		     unsigned long addr, unsigned long end),
 	    TP_ARGS(cpus, mm, addr, end),