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()

Author: torvalds

arch/x86/hyperv/mmu.c

@@ -52,16 +52,16 @@ 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;
 	struct hv_tlb_flush *flush;
 	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 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	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;
 }

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)

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);
 

arch/x86/include/asm/tlbflush.h

@@ -89,23 +89,6 @@ struct tlb_state {
 	u16 loaded_mm_asid;
 	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).
@@ -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

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),

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);

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");
 	}

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,
 

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 */