x86/mm/tlb: Flush remote and local TLBs concurrently

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.

Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Michael Kelley <mikelley@microsoft.com> # Hyper-v parts
Reviewed-by: Juergen Gross <jgross@suse.com> # Xen and paravirt parts
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20210220231712.2475218-5-namit@vmware.com

4 files changed, 8 insertions, 8 deletions

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 4abf110e2243..45b55e3e0630 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -50,7 +50,7 @@ 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)
@@ -68,10 +68,10 @@ 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 de87087d3bde..b7b35d5d58e7 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -188,8 +188,8 @@ 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 a7a598af116d..3c6681def912 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -175,7 +175,7 @@ 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.
@@ -209,7 +209,7 @@ struct flush_tlb_info {
 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),