Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Rik van Riel <riel@surriel.com>
To:     linux-kernel@vger.kernel.org
Cc:     x86@kernel.org, luto@kernel.org, dave.hansen@linux.intel.com,
        mingo@kernel.org, kernel-team@fb.com, tglx@linutronix.de,
        efault@gmx.de, songliubraving@fb.com,
        Rik van Riel <riel@surriel.com>
Subject: [PATCH 3/6] x86,tlb: make lazy TLB mode lazier
Date:   Tue, 26 Jun 2018 13:31:23 -0400
Message-Id: <20180626173126.12296-4-riel@surriel.com>
In-Reply-To: <20180626173126.12296-1-riel@surriel.com>
References: <20180626173126.12296-1-riel@surriel.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Lazy TLB mode can result in an idle CPU being woken up by a TLB flush,
when all it really needs to do is reload %CR3 at the next context switch,
assuming no page table pages got freed.

Memory ordering is used to prevent race conditions between switch_mm_irqs_off,
which checks whether .tlb_gen changed, and the TLB invalidation code, which
increments .tlb_gen whenever page table entries get invalidated.

The atomic increment in inc_mm_tlb_gen is its own barrier; the context
switch code adds an explicit barrier between reading tlbstate.is_lazy and
next->context.tlb_gen.

Unlike the 2016 version of this patch, CPUs with cpu_tlbstate.is_lazy set
are not removed from the mm_cpumask(mm), since that would prevent the TLB
flush IPIs at page table free time from being sent to all the CPUs
that need them.

Signed-off-by: Rik van Riel <riel@surriel.com>
Tested-by: Song Liu <songliubraving@fb.com>
---
 arch/x86/include/asm/uv/uv.h  |   6 +-
 arch/x86/mm/tlb.c             | 131 ++++++++++++++++++++++++++++--------------
 arch/x86/platform/uv/tlb_uv.c |   2 +-
 3 files changed, 92 insertions(+), 47 deletions(-)

diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index a80c0673798f..d801afb5fe90 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -17,7 +17,7 @@ extern int is_uv_hubless(void);
 extern void uv_cpu_init(void);
 extern void uv_nmi_init(void);
 extern void uv_system_init(void);
-extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
+extern struct cpumask *uv_flush_tlb_others(struct cpumask *cpumask,
 						 const struct flush_tlb_info *info);
 
 #else	/* X86_UV */
@@ -27,8 +27,8 @@ static inline int is_uv_system(void)	{ return 0; }
 static inline int is_uv_hubless(void)	{ return 0; }
 static inline void uv_cpu_init(void)	{ }
 static inline void uv_system_init(void)	{ }
-static inline const struct cpumask *
-uv_flush_tlb_others(const struct cpumask *cpumask,
+static inline struct cpumask *
+uv_flush_tlb_others(struct cpumask *cpumask,
 		    const struct flush_tlb_info *info)
 { return cpumask; }
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 9a893673c56b..137a2c62c75b 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
+#include <linux/gfp.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -185,8 +186,11 @@ 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);
 	unsigned cpu = smp_processor_id();
 	u64 next_tlb_gen;
+	bool need_flush;
+	u16 new_asid;
 
 	/*
 	 * NB: The scheduler will call us with prev == next when switching
@@ -250,10 +254,20 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 
-		return;
+		/*
+		 * Switching straight from one thread in a process to another
+		 * thread in the same process requires no TLB flush at all.
+		 */
+		if (!was_lazy)
+			return;
+
+		/*
+		 * The code below checks whether there was a TLB flush while
+		 * this CPU was in lazy TLB mode. The barrier ensures ordering
+		 * with the TLB invalidation code advancing .tlb_gen.
+		 */
+		smp_rmb();
 	} else {
-		u16 new_asid;
-		bool need_flush;
 		u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
 
 		/*
@@ -290,48 +304,47 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 				real_prev != &init_mm);
 		cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
 
-		/*
-		 * Start remote flushes and then read tlb_gen.
-		 */
+		/* Start remote flushes. */
 		cpumask_set_cpu(cpu, mm_cpumask(next));
-		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
-
-		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+	}
 
-		if (need_flush) {
-			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
-			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-			load_new_mm_cr3(next->pgd, new_asid, true);
+	/* Read the tlb_gen to check whether a flush is needed. */
+	next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+	choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
 
-			/*
-			 * NB: This gets called via leave_mm() in the idle path
-			 * where RCU functions differently.  Tracing normally
-			 * uses RCU, so we need to use the _rcuidle variant.
-			 *
-			 * (There is no good reason for this.  The idle code should
-			 *  be rearranged to call this before rcu_idle_enter().)
-			 */
-			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-		} else {
-			/* The new ASID is already up to date. */
-			load_new_mm_cr3(next->pgd, new_asid, false);
-
-			/* See above wrt _rcuidle. */
-			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
-		}
+	if (need_flush) {
+		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
+		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
+		load_new_mm_cr3(next->pgd, new_asid, true);
 
 		/*
-		 * Record last user mm's context id, so we can avoid
-		 * flushing branch buffer with IBPB if we switch back
-		 * to the same user.
+		 * NB: This gets called via leave_mm() in the idle path
+		 * where RCU functions differently.  Tracing normally
+		 * uses RCU, so we need to use the _rcuidle variant.
+		 *
+		 * (There is no good reason for this.  The idle code should
+		 *  be rearranged to call this before rcu_idle_enter().)
 		 */
-		if (next != &init_mm)
-			this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+	} else {
+		/* The new ASID is already up to date. */
+		load_new_mm_cr3(next->pgd, new_asid, false);
 
-		this_cpu_write(cpu_tlbstate.loaded_mm, next);
-		this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+		/* See above wrt _rcuidle. */
+		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
 
+	/*
+	 * Record last user mm's context id, so we can avoid
+	 * flushing branch buffer with IBPB if we switch back
+	 * to the same user.
+	 */
+	if (next != &init_mm)
+		this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+
+	this_cpu_write(cpu_tlbstate.loaded_mm, next);
+	this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+
 	load_mm_cr4(next);
 	switch_ldt(real_prev, next);
 }
@@ -454,6 +467,9 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 		 * paging-structure cache to avoid speculatively reading
 		 * garbage into our TLB.  Since switching to init_mm is barely
 		 * slower than a minimal flush, just switch to init_mm.
+		 *
+		 * This should be rare, with native_flush_tlb_others skipping
+		 * IPIs to lazy TLB mode CPUs.
 		 */
 		switch_mm_irqs_off(NULL, &init_mm, NULL);
 		return;
@@ -560,6 +576,22 @@ static void flush_tlb_func_remote(void *info)
 void native_flush_tlb_others(const struct cpumask *cpumask,
 			     const struct flush_tlb_info *info)
 {
+	cpumask_t *mask = (struct cpumask *)cpumask;
+	cpumask_var_t varmask;
+	bool can_lazy_flush = false;
+	unsigned int cpu;
+
+	/*
+	 * A temporary cpumask allows the kernel to skip sending IPIs
+	 * to CPUs in lazy TLB state, without also removing them from
+	 * mm_cpumask(mm).
+	 */
+	if (alloc_cpumask_var(&varmask, GFP_ATOMIC)) {
+		cpumask_copy(varmask, cpumask);
+		mask = varmask;
+		can_lazy_flush = true;
+	}
+
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (info->end == TLB_FLUSH_ALL)
 		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
@@ -583,17 +615,30 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 		 * that UV should be updated so that smp_call_function_many(),
 		 * etc, are optimal on UV.
 		 */
-		unsigned int cpu;
-
 		cpu = smp_processor_id();
-		cpumask = uv_flush_tlb_others(cpumask, info);
-		if (cpumask)
-			smp_call_function_many(cpumask, flush_tlb_func_remote,
+		mask = uv_flush_tlb_others(mask, info);
+		if (mask)
+			smp_call_function_many(mask, flush_tlb_func_remote,
 					       (void *)info, 1);
-		return;
+		goto out;
+	}
+
+	/*
+	 * Instead of sending IPIs to CPUs in lazy TLB mode, move that
+	 * CPU's TLB state to TLBSTATE_FLUSH, causing the TLB to be flushed
+	 * at the next context switch, or at page table free time.
+	 */
+	if (can_lazy_flush) {
+		for_each_cpu(cpu, mask) {
+			if (per_cpu(cpu_tlbstate.is_lazy, cpu))
+				cpumask_clear_cpu(cpu, mask);
+		}
 	}
-	smp_call_function_many(cpumask, flush_tlb_func_remote,
+
+	smp_call_function_many(mask, flush_tlb_func_remote,
 			       (void *)info, 1);
+ out:
+	free_cpumask_var(varmask);
 }
 
 /*
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index ca446da48fd2..84a4c6679da6 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1102,7 +1102,7 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,
  * Returns pointer to cpumask if some remote flushing remains to be
  * done.  The returned pointer is valid till preemption is re-enabled.
  */
-const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
+struct cpumask *uv_flush_tlb_others(struct cpumask *cpumask,
 					  const struct flush_tlb_info *info)
 {
 	unsigned int cpu = smp_processor_id();
-- 
2.14.4