Merge tag 'x86-mm-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 tlb updates from Ingo Molnar:
 "The x86 MM changes in this cycle were:

   - Implement concurrent TLB flushes, which overlaps the local TLB
     flush with the remote TLB flush.

     In testing this improved sysbench performance measurably by a
     couple of percentage points, especially if TLB-heavy security
     mitigations are active.

   - Further micro-optimizations to improve the performance of TLB
     flushes"

* tag 'x86-mm-2021-04-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  smp: Micro-optimize smp_call_function_many_cond()
  smp: Inline on_each_cpu_cond() and on_each_cpu()
  x86/mm/tlb: Remove unnecessary uses of the inline keyword
  cpumask: Mark functions as pure
  x86/mm/tlb: Do not make is_lazy dirty for no reason
  x86/mm/tlb: Privatize cpu_tlbstate
  x86/mm/tlb: Flush remote and local TLBs concurrently
  x86/mm/tlb: Open-code on_each_cpu_cond_mask() for tlb_is_not_lazy()
  x86/mm/tlb: Unify flush_tlb_func_local() and flush_tlb_func_remote()
  smp: Run functions concurrently in smp_call_function_many_cond()

11 files changed, 158 insertions, 116 deletions

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index c0ba8874d9cb..bd13736d0c05 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -52,8 +52,8 @@ 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;
@@ -61,7 +61,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	u64 status;
 	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;
@@ -164,7 +164,7 @@ check_status:
 	if (hv_result_success(status))
 		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,
@@ -239,6 +239,6 @@ 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 43992e5c52c2..da3a1ac82be5 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -63,7 +63,7 @@ static inline void slow_down_io(void)
 void native_flush_tlb_local(void);
 void native_flush_tlb_global(void);
 void native_flush_tlb_one_user(unsigned long addr);
-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 void __flush_tlb_local(void)
@@ -81,10 +81,10 @@ 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,
+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 ae692c3194e9..d9d6b0203ec4 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -161,8 +161,8 @@ 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 8c87a2e0b660..fa952eadbc2e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -90,23 +90,6 @@ struct tlb_state {
 	u16 next_asid;
 
 	/*
-	 * We can be in one of several states:
-	 *
-	 *  - Actively using an mm.  Our CPU's bit will be set in
-	 *    mm_cpumask(loaded_mm) and is_lazy == false;
-	 *
-	 *  - Not using a real mm.  loaded_mm == &init_mm.  Our CPU's bit
-	 *    will not be set in mm_cpumask(&init_mm) and is_lazy == false.
-	 *
-	 *  - Lazily using a real mm.  loaded_mm != &init_mm, our bit
-	 *    is set in mm_cpumask(loaded_mm), but is_lazy == true.
-	 *    We're heuristically guessing that the CR3 load we
-	 *    skipped more than makes up for the overhead added by
-	 *    lazy mode.
-	 */
-	bool is_lazy;
-
-	/*
 	 * If set we changed the page tables in such a way that we
 	 * needed an invalidation of all contexts (aka. PCIDs / ASIDs).
 	 * This tells us to go invalidate all the non-loaded ctxs[]
@@ -151,7 +134,27 @@ struct tlb_state {
 	 */
 	struct tlb_context ctxs[TLB_NR_DYN_ASIDS];
 };
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
+DECLARE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate);
+
+struct tlb_state_shared {
+	/*
+	 * We can be in one of several states:
+	 *
+	 *  - Actively using an mm.  Our CPU's bit will be set in
+	 *    mm_cpumask(loaded_mm) and is_lazy == false;
+	 *
+	 *  - Not using a real mm.  loaded_mm == &init_mm.  Our CPU's bit
+	 *    will not be set in mm_cpumask(&init_mm) and is_lazy == false.
+	 *
+	 *  - Lazily using a real mm.  loaded_mm != &init_mm, our bit
+	 *    is set in mm_cpumask(loaded_mm), but is_lazy == true.
+	 *    We're heuristically guessing that the CR3 load we
+	 *    skipped more than makes up for the overhead added by
+	 *    lazy mode.
+	 */
+	bool is_lazy;
+};
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
 
 bool nmi_uaccess_okay(void);
 #define nmi_uaccess_okay nmi_uaccess_okay
@@ -175,7 +178,7 @@ extern void initialize_tlbstate_and_flush(void);
  *  - 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.
@@ -201,14 +204,15 @@ struct flush_tlb_info {
 	unsigned long		start;
 	unsigned long		end;
 	u64			new_tlb_gen;
-	unsigned int		stride_shift;
-	bool			freed_tables;
+	unsigned int		initiating_cpu;
+	u8			stride_shift;
+	u8			freed_tables;
 };
 
 void flush_tlb_local(void);
 void flush_tlb_one_user(unsigned long addr);
 void flush_tlb_one_kernel(unsigned long addr);
-void flush_tlb_others(const struct cpumask *cpumask,
+void flush_tlb_multi(const struct cpumask *cpumask,
 		      const struct flush_tlb_info *info);
 
 #ifdef CONFIG_PARAVIRT
diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h
index 4d705cb4d63b..a8e5a7a2b460 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/alternative.c b/arch/x86/kernel/alternative.c
index 84ec0ba491e4..6974b5174495 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -706,7 +706,7 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
 	 * with a stale address space WITHOUT being in lazy mode after
 	 * restoring the previous mm.
 	 */
-	if (this_cpu_read(cpu_tlbstate.is_lazy))
+	if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
 		leave_mm(smp_processor_id());
 
 	temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 172c947240b9..5d32fa477a62 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -613,7 +613,7 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
 }
 #endif
 
-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;
@@ -627,6 +627,11 @@ 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)) {
@@ -636,7 +641,7 @@ 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)
@@ -654,7 +659,7 @@ static void __init kvm_guest_init(void)
 	}
 
 	if (pv_tlb_flush_supported()) {
-		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;
 		pr_info("KVM setup pv remote TLB flush\n");
 	}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index d0730264786b..04cafc057bed 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -291,7 +291,7 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.flush_tlb_user	= native_flush_tlb_local,
 	.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/init.c b/arch/x86/mm/init.c
index fbf41dd142ca..75ef19aa8903 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1017,7 +1017,7 @@ void __init zone_sizes_init(void)
 	free_area_init(max_zone_pfns);
 }
 
-__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
+__visible DEFINE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate) = {
 	.loaded_mm = &init_mm,
 	.next_asid = 1,
 	.cr4 = ~0UL,	/* fail hard if we screw up cr4 shadow initialization */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 98f269560d40..78804680e923 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -24,7 +24,7 @@
 # define __flush_tlb_local		native_flush_tlb_local
 # define __flush_tlb_global		native_flush_tlb_global
 # define __flush_tlb_one_user(addr)	native_flush_tlb_one_user(addr)
-# define __flush_tlb_others(msk, info)	native_flush_tlb_others(msk, info)
+# define __flush_tlb_multi(msk, info)	native_flush_tlb_multi(msk, info)
 #endif
 
 /*
@@ -300,7 +300,7 @@ void leave_mm(int cpu)
 		return;
 
 	/* Warn if we're not lazy. */
-	WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy));
+	WARN_ON(!this_cpu_read(cpu_tlbstate_shared.is_lazy));
 
 	switch_mm(NULL, &init_mm, NULL);
 }
@@ -316,7 +316,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	local_irq_restore(flags);
 }
 
-static inline unsigned long mm_mangle_tif_spec_ib(struct task_struct *next)
+static unsigned long mm_mangle_tif_spec_ib(struct task_struct *next)
 {
 	unsigned long next_tif = task_thread_info(next)->flags;
 	unsigned long ibpb = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_IBPB;
@@ -424,7 +424,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 {
 	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
-	bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy);
+	bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
 	unsigned cpu = smp_processor_id();
 	u64 next_tlb_gen;
 	bool need_flush;
@@ -439,7 +439,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	 * NB: leave_mm() calls us with prev == NULL and tsk == NULL.
 	 */
 
-	/* We don't want flush_tlb_func_* to run concurrently with us. */
+	/* We don't want flush_tlb_func() to run concurrently with us. */
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
 		WARN_ON_ONCE(!irqs_disabled());
 
@@ -469,7 +469,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		__flush_tlb_all();
 	}
 #endif
-	this_cpu_write(cpu_tlbstate.is_lazy, false);
+	if (was_lazy)
+		this_cpu_write(cpu_tlbstate_shared.is_lazy, false);
 
 	/*
 	 * The membarrier system call requires a full memory barrier and
@@ -490,7 +491,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		/*
 		 * Even in lazy TLB mode, the CPU should stay set in the
 		 * mm_cpumask. The TLB shootdown code can figure out from
-		 * from cpu_tlbstate.is_lazy whether or not to send an IPI.
+		 * cpu_tlbstate_shared.is_lazy whether or not to send an IPI.
 		 */
 		if (WARN_ON_ONCE(real_prev != &init_mm &&
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
@@ -598,7 +599,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
 		return;
 
-	this_cpu_write(cpu_tlbstate.is_lazy, true);
+	this_cpu_write(cpu_tlbstate_shared.is_lazy, true);
 }
 
 /*
@@ -647,14 +648,13 @@ void initialize_tlbstate_and_flush(void)
 }
 
 /*
- * flush_tlb_func_common()'s memory ordering requirement is that any
+ * flush_tlb_func()'s memory ordering requirement is that any
  * TLB fills that happen after we flush the TLB are ordered after we
  * read active_mm's tlb_gen.  We don't need any explicit barriers
  * because all x86 flush operations are serializing and the
  * atomic64_read operation won't be reordered by the compiler.
  */
-static void flush_tlb_func_common(const struct flush_tlb_info *f,
-				  bool local, enum tlb_flush_reason reason)
+static void flush_tlb_func(void *info)
 {
 	/*
 	 * We have three different tlb_gen values in here.  They are:
@@ -665,28 +665,40 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 	 * - f->new_tlb_gen: the generation that the requester of the flush
 	 *                   wants us to catch up to.
 	 */
+	const struct flush_tlb_info *f = info;
 	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
 	u64 mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen);
 	u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+	bool local = smp_processor_id() == f->initiating_cpu;
+	unsigned long nr_invalidate = 0;
 
 	/* This code cannot presently handle being reentered. */
 	VM_WARN_ON(!irqs_disabled());
 
+	if (!local) {
+		inc_irq_stat(irq_tlb_count);
+		count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+
+		/* Can only happen on remote CPUs */
+		if (f->mm && f->mm != loaded_mm)
+			return;
+	}
+
 	if (unlikely(loaded_mm == &init_mm))
 		return;
 
 	VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
 		   loaded_mm->context.ctx_id);
 
-	if (this_cpu_read(cpu_tlbstate.is_lazy)) {
+	if (this_cpu_read(cpu_tlbstate_shared.is_lazy)) {
 		/*
 		 * We're in lazy mode.  We need to at least flush our
 		 * paging-structure cache to avoid speculatively reading
 		 * 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);
@@ -700,8 +712,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 		 * be handled can catch us all the way up, leaving no work for
 		 * the second flush.
 		 */
-		trace_tlb_flush(reason, 0);
-		return;
+		goto done;
 	}
 
 	WARN_ON_ONCE(local_tlb_gen > mm_tlb_gen);
@@ -748,56 +759,54 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 	    f->new_tlb_gen == local_tlb_gen + 1 &&
 	    f->new_tlb_gen == mm_tlb_gen) {
 		/* Partial flush */
-		unsigned long nr_invalidate = (f->end - f->start) >> f->stride_shift;
 		unsigned long addr = f->start;
 
+		nr_invalidate = (f->end - f->start) >> f->stride_shift;
+
 		while (addr < f->end) {
 			flush_tlb_one_user(addr);
 			addr += 1UL << f->stride_shift;
 		}
 		if (local)
 			count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_invalidate);
-		trace_tlb_flush(reason, nr_invalidate);
 	} else {
 		/* Full flush. */
+		nr_invalidate = TLB_FLUSH_ALL;
+
 		flush_tlb_local();
 		if (local)
 			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-		trace_tlb_flush(reason, TLB_FLUSH_ALL);
 	}
 
 	/* Both paths above update our state to mm_tlb_gen. */
 	this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen);
-}
-
-static void flush_tlb_func_local(const void *info, enum tlb_flush_reason reason)
-{
-	const struct flush_tlb_info *f = info;
 
-	flush_tlb_func_common(f, true, reason);
+	/* Tracing is done in a unified manner to reduce the code size */
+done:
+	trace_tlb_flush(!local ? TLB_REMOTE_SHOOTDOWN :
+				(f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN :
+						  TLB_LOCAL_MM_SHOOTDOWN,
+			nr_invalidate);
 }
 
-static void flush_tlb_func_remote(void *info)
+static bool tlb_is_not_lazy(int cpu)
 {
-	const struct flush_tlb_info *f = info;
-
-	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, false, TLB_REMOTE_SHOOTDOWN);
+	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
 }
 
-static bool tlb_is_not_lazy(int cpu, void *data)
-{
-	return !per_cpu(cpu_tlbstate.is_lazy, cpu);
-}
+static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
+
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
+EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared);
 
-STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,
+STATIC_NOPV 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);
@@ -815,18 +824,42 @@ STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,
 	 * up on the new contents of what used to be page tables, while
 	 * doing a speculative memory access.
 	 */
-	if (info->freed_tables)
-		smp_call_function_many(cpumask, flush_tlb_func_remote,
-			       (void *)info, 1);
-	else
-		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func_remote,
-				(void *)info, 1, cpumask);
+	if (info->freed_tables) {
+		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
+	} else {
+		/*
+		 * Although we could have used on_each_cpu_cond_mask(),
+		 * open-coding it has performance advantages, as it eliminates
+		 * the need for indirect calls or retpolines. In addition, it
+		 * allows to use a designated cpumask for evaluating the
+		 * condition, instead of allocating one.
+		 *
+		 * This code works under the assumption that there are no nested
+		 * TLB flushes, an assumption that is already made in
+		 * flush_tlb_mm_range().
+		 *
+		 * cond_cpumask is logically a stack-local variable, but it is
+		 * more efficient to have it off the stack and not to allocate
+		 * it on demand. Preemption is disabled and this code is
+		 * non-reentrant.
+		 */
+		struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask);
+		int cpu;
+
+		cpumask_clear(cond_cpumask);
+
+		for_each_cpu(cpu, cpumask) {
+			if (tlb_is_not_lazy(cpu))
+				__cpumask_set_cpu(cpu, cond_cpumask);
+		}
+		on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true);
+	}
 }
 
-void flush_tlb_others(const struct cpumask *cpumask,
+void flush_tlb_multi(const struct cpumask *cpumask,
 		      const struct flush_tlb_info *info)
 {
-	__flush_tlb_others(cpumask, info);
+	__flush_tlb_multi(cpumask, info);
 }
 
 /*
@@ -847,7 +880,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct flush_tlb_info, flush_tlb_info);
 static DEFINE_PER_CPU(unsigned int, flush_tlb_info_idx);
 #endif
 
-static inline struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
+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,
 			u64 new_tlb_gen)
@@ -869,11 +902,12 @@ static inline struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
 	info->stride_shift	= stride_shift;
 	info->freed_tables	= freed_tables;
 	info->new_tlb_gen	= new_tlb_gen;
+	info->initiating_cpu	= smp_processor_id();
 
 	return info;
 }
 
-static inline void put_flush_tlb_info(void)
+static void put_flush_tlb_info(void)
 {
 #ifdef CONFIG_DEBUG_VM
 	/* Complete reentrancy prevention checks */
@@ -905,16 +939,20 @@ 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, TLB_LOCAL_MM_SHOOTDOWN);
+		flush_tlb_func(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();
 }
@@ -1119,34 +1157,30 @@ void __flush_tlb_all(void)
 }
 EXPORT_SYMBOL_GPL(__flush_tlb_all);
 
-/*
- * arch_tlbbatch_flush() performs a full TLB flush regardless of the active mm.
- * This means that the 'struct flush_tlb_info' that describes which mappings to
- * flush is actually fixed. We therefore set a single fixed struct and use it in
- * arch_tlbbatch_flush().
- */
-static const struct flush_tlb_info full_flush_tlb_info = {
-	.mm = NULL,
-	.start = 0,
-	.end = TLB_FLUSH_ALL,
-};
-
 void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
+	struct flush_tlb_info *info;
+
 	int cpu = get_cpu();
 
-	if (cpumask_test_cpu(cpu, &batch->cpumask)) {
+	info = get_flush_tlb_info(NULL, 0, TLB_FLUSH_ALL, 0, false, 0);
+	/*
+	 * 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, info);
+	} else 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);
+		flush_tlb_func(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_flush_tlb_info();
 	put_cpu();
 }
 
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 1e28c880f642..ade789e73ee4 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1247,8 +1247,8 @@ 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;
@@ -1258,7 +1258,7 @@ 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 */
@@ -1267,9 +1267,8 @@ 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 &&
@@ -2086,7 +2085,7 @@ 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,