[RFC PATCH v2 08/12] x86/tlb: Privatize cpu_tlbstate

[Nadav Amit <namit@vmware.com>]

cpu_tlbstate is mostly private and only the variable is_lazy is shared.
This causes some false-sharing when TLB flushes are performed.

Break cpu_tlbstate intro cpu_tlbstate and cpu_tlbstate_shared, and mark
each one accordingly.

Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Nadav Amit <namit@vmware.com>
---
 arch/x86/include/asm/tlbflush.h | 40 ++++++++++++++++++---------------
 arch/x86/mm/init.c              |  2 +-
 arch/x86/mm/tlb.c               | 15 ++++++++-----
 3 files changed, 32 insertions(+), 25 deletions(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 79272938cf79..a1fea36d5292 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -178,23 +178,6 @@ 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).
@@ -240,7 +223,27 @@ 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);
 
 /*
  * Blindly accessing user memory from NMI context can be dangerous
@@ -439,6 +442,7 @@ static inline void __native_flush_tlb_one_user(unsigned long addr)
 {
 	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
 
+	//invpcid_flush_one(kern_pcid(loaded_mm_asid), addr);
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fd10d91a6115..34027f36a944 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -951,7 +951,7 @@ void __init zone_sizes_init(void)
 	free_area_init_nodes(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 b0c3065aad5d..755b2bb3e5b6 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -144,7 +144,7 @@ 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);
 }
@@ -276,7 +276,7 @@ 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;
@@ -321,7 +321,7 @@ 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);
+	this_cpu_write(cpu_tlbstate_shared.is_lazy, false);
 
 	/*
 	 * The membarrier system call requires a full memory barrier and
@@ -462,7 +462,7 @@ 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);
 }
 
 /*
@@ -543,7 +543,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 	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
@@ -659,11 +659,14 @@ static void flush_tlb_func_remote(void *info)
 
 static inline bool tlb_is_not_lazy(int cpu)
 {
-	return !per_cpu(cpu_tlbstate.is_lazy, cpu);
+	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
 }
 
 static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
 
+DEFINE_PER_CPU_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
+EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared);
+
 void native_flush_tlb_multi(const struct cpumask *cpumask,
 			    const struct flush_tlb_info *info)
 {
-- 
2.20.1