[PATCH v9 10/12] x86/mm: do targeted broadcast flushing from tlbbatch code

[Rik van Riel <riel@surriel.com>]

Instead of doing a system-wide TLB flush from arch_tlbbatch_flush,
queue up asynchronous, targeted flushes from arch_tlbbatch_add_pending.

This also allows us to avoid adding the CPUs of processes using broadcast
flushing to the batch->cpumask, and will hopefully further reduce TLB
flushing from the reclaim and compaction paths.

Signed-off-by: Rik van Riel <riel@surriel.com>
Tested-by: Manali Shukla <Manali.Shukla@amd.com>
---
 arch/x86/include/asm/invlpgb.h  | 21 +++++----
 arch/x86/include/asm/tlbflush.h | 17 ++++---
 arch/x86/mm/tlb.c               | 80 +++++++++++++++++++++++++++++++--
 3 files changed, 95 insertions(+), 23 deletions(-)

diff --git a/arch/x86/include/asm/invlpgb.h b/arch/x86/include/asm/invlpgb.h
index a1d5dedd5217..357e3cc417e4 100644
--- a/arch/x86/include/asm/invlpgb.h
+++ b/arch/x86/include/asm/invlpgb.h
@@ -31,9 +31,8 @@ static inline void __invlpgb(unsigned long asid, unsigned long pcid,
 }
 
 /* Wait for INVLPGB originated by this CPU to complete. */
-static inline void tlbsync(void)
+static inline void __tlbsync(void)
 {
-	cant_migrate();
 	/* TLBSYNC: supported in binutils >= 0.36. */
 	asm volatile(".byte 0x0f, 0x01, 0xff" ::: "memory");
 }
@@ -61,19 +60,19 @@ static inline void invlpgb_flush_user(unsigned long pcid,
 				      unsigned long addr)
 {
 	__invlpgb(0, pcid, addr, 0, 0, INVLPGB_PCID | INVLPGB_VA);
-	tlbsync();
+	__tlbsync();
 }
 
-static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
-						unsigned long addr,
-						u16 nr,
-						bool pmd_stride)
+static inline void __invlpgb_flush_user_nr_nosync(unsigned long pcid,
+						  unsigned long addr,
+						  u16 nr,
+						  bool pmd_stride)
 {
 	__invlpgb(0, pcid, addr, nr - 1, pmd_stride, INVLPGB_PCID | INVLPGB_VA);
 }
 
 /* Flush all mappings for a given PCID, not including globals. */
-static inline void invlpgb_flush_single_pcid_nosync(unsigned long pcid)
+static inline void __invlpgb_flush_single_pcid_nosync(unsigned long pcid)
 {
 	__invlpgb(0, pcid, 0, 0, 0, INVLPGB_PCID);
 }
@@ -82,11 +81,11 @@ static inline void invlpgb_flush_single_pcid_nosync(unsigned long pcid)
 static inline void invlpgb_flush_all(void)
 {
 	__invlpgb(0, 0, 0, 0, 0, INVLPGB_INCLUDE_GLOBAL);
-	tlbsync();
+	__tlbsync();
 }
 
 /* Flush addr, including globals, for all PCIDs. */
-static inline void invlpgb_flush_addr_nosync(unsigned long addr, u16 nr)
+static inline void __invlpgb_flush_addr_nosync(unsigned long addr, u16 nr)
 {
 	__invlpgb(0, 0, addr, nr - 1, 0, INVLPGB_INCLUDE_GLOBAL);
 }
@@ -95,7 +94,7 @@ static inline void invlpgb_flush_addr_nosync(unsigned long addr, u16 nr)
 static inline void invlpgb_flush_all_nonglobals(void)
 {
 	__invlpgb(0, 0, 0, 0, 0, 0);
-	tlbsync();
+	__tlbsync();
 }
 
 #endif /* _ASM_X86_INVLPGB */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 234277a5ef89..bf167e215e8e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -106,6 +106,7 @@ struct tlb_state {
 	 * need to be invalidated.
 	 */
 	bool invalidate_other;
+	bool need_tlbsync;
 
 #ifdef CONFIG_ADDRESS_MASKING
 	/*
@@ -310,6 +311,10 @@ static inline void broadcast_tlb_flush(struct flush_tlb_info *info)
 static inline void consider_global_asid(struct mm_struct *mm)
 {
 }
+
+static inline void tlbsync(void)
+{
+}
 #endif
 
 #ifdef CONFIG_PARAVIRT
@@ -359,21 +364,15 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 	return atomic64_inc_return(&mm->context.tlb_gen);
 }
 
-static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
-					     struct mm_struct *mm,
-					     unsigned long uaddr)
-{
-	inc_mm_tlb_gen(mm);
-	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
-	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
-}
-
 static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
 {
 	flush_tlb_mm(mm);
 }
 
 extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
+extern void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+					     struct mm_struct *mm,
+					     unsigned long uaddr);
 
 static inline bool pte_flags_need_flush(unsigned long oldflags,
 					unsigned long newflags,
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 05390f0e6cb0..4253c3efd7e4 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -488,6 +488,37 @@ static void finish_asid_transition(struct flush_tlb_info *info)
 	WRITE_ONCE(mm->context.asid_transition, false);
 }
 
+static inline void tlbsync(void)
+{
+	if (!this_cpu_read(cpu_tlbstate.need_tlbsync))
+		return;
+	__tlbsync();
+	this_cpu_write(cpu_tlbstate.need_tlbsync, false);
+}
+
+static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
+						unsigned long addr,
+						u16 nr, bool pmd_stride)
+{
+	__invlpgb_flush_user_nr_nosync(pcid, addr, nr, pmd_stride);
+	if (!this_cpu_read(cpu_tlbstate.need_tlbsync))
+		this_cpu_write(cpu_tlbstate.need_tlbsync, true);
+}
+
+static inline void invlpgb_flush_single_pcid_nosync(unsigned long pcid)
+{
+	__invlpgb_flush_single_pcid_nosync(pcid);
+	if (!this_cpu_read(cpu_tlbstate.need_tlbsync))
+		this_cpu_write(cpu_tlbstate.need_tlbsync, true);
+}
+
+static inline void invlpgb_flush_addr_nosync(unsigned long addr, u16 nr)
+{
+	__invlpgb_flush_addr_nosync(addr, nr);
+	if (!this_cpu_read(cpu_tlbstate.need_tlbsync))
+		this_cpu_write(cpu_tlbstate.need_tlbsync, true);
+}
+
 static void broadcast_tlb_flush(struct flush_tlb_info *info)
 {
 	bool pmd = info->stride_shift == PMD_SHIFT;
@@ -794,6 +825,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
 		WARN_ON_ONCE(!irqs_disabled());
 
+	tlbsync();
+
 	/*
 	 * Verify that CR3 is what we think it is.  This will catch
 	 * hypothetical buggy code that directly switches to swapper_pg_dir
@@ -973,6 +1006,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
  */
 void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
+	tlbsync();
+
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
 		return;
 
@@ -1650,9 +1685,7 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
-		invlpgb_flush_all_nonglobals();
-	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+	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();
@@ -1661,12 +1694,53 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 		local_irq_enable();
 	}
 
+	/*
+	 * If we issued (asynchronous) INVLPGB flushes, wait for them here.
+	 * The cpumask above contains only CPUs that were running tasks
+	 * not using broadcast TLB flushing.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		tlbsync();
+
 	cpumask_clear(&batch->cpumask);
 
 	put_flush_tlb_info();
 	put_cpu();
 }
 
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+					     struct mm_struct *mm,
+					     unsigned long uaddr)
+{
+	u16 asid = mm_global_asid(mm);
+
+	if (asid) {
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), uaddr, 1, false);
+		/* Do any CPUs supporting INVLPGB need PTI? */
+		if (static_cpu_has(X86_FEATURE_PTI))
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), uaddr, 1, false);
+
+		/*
+		 * Some CPUs might still be using a local ASID for this
+		 * process, and require IPIs, while others are using the
+		 * global ASID.
+		 *
+		 * In this corner case we need to do both the broadcast
+		 * TLB invalidation, and send IPIs. The IPIs will help
+		 * stragglers transition to the broadcast ASID.
+		 */
+		if (in_asid_transition(mm))
+			asid = 0;
+	}
+
+	if (!asid) {
+		inc_mm_tlb_gen(mm);
+		cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+	}
+
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
+}
+
 /*
  * Blindly accessing user memory from NMI context can be dangerous
  * if we're in the middle of switching the current user task or
-- 
2.47.1