[PATCH v6 5/9] x86/mm/tlb: Privatize cpu_tlbstate

[Nadav Amit <nadav.amit@gmail.com>]

From: 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: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Nadav Amit <namit@vmware.com>

---
v5 -> v6:
* Fixed warning due to mismatch in
  {DEFINE|DECLARE}_PER_CPU_{SHARED_}ALIGNED
---
 arch/x86/include/asm/tlbflush.h | 39 ++++++++++++++++++---------------
 arch/x86/kernel/alternative.c   |  2 +-
 arch/x86/mm/init.c              |  2 +-
 arch/x86/mm/tlb.c               | 17 ++++++++------
 4 files changed, 33 insertions(+), 27 deletions(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 3c6681def912..fa952eadbc2e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/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
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8d778e46725d..94649f86d653 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -813,7 +813,7 @@ 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/mm/init.c b/arch/x86/mm/init.c
index dd694fb93916..ed2e36748758 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 8db87cd92e6b..345a0aff5de4 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -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);
 }
@@ -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;
@@ -469,7 +469,7 @@ 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
@@ -490,7 +490,7 @@ 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
-		 * 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 +598,7 @@ 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);
 }
 
 /*
@@ -690,7 +690,7 @@ static void flush_tlb_func(void *info)
 	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
@@ -790,11 +790,14 @@ static void flush_tlb_func(void *info)
 
 static 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_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
+EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared);
+
 STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 					 const struct flush_tlb_info *info)
 {
-- 
2.25.1