linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Nicholas Piggin <npiggin@gmail.com>
To: linux-arch@vger.kernel.org
Cc: Nicholas Piggin <npiggin@gmail.com>,
	x86@kernel.org,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Peter Zijlstra <peterz@infradead.org>,
	linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	linux-mm@kvack.org, Anton Blanchard <anton@ozlabs.org>
Subject: [RFC PATCH 7/7] lazy tlb: shoot lazies, a non-refcounting lazy tlb option
Date: Fri, 10 Jul 2020 11:56:46 +1000	[thread overview]
Message-ID: <20200710015646.2020871-8-npiggin@gmail.com> (raw)
In-Reply-To: <20200710015646.2020871-1-npiggin@gmail.com>

On big systems, the mm refcount can become highly contented when doing
a lot of context switching with threaded applications (particularly
switching between the idle thread and an application thread).

Abandoning lazy tlb slows switching down quite a bit in the important
user->idle->user cases, so so instead implement a non-refcounted scheme
that causes __mmdrop() to IPI all CPUs in the mm_cpumask and shoot down
any remaining lazy ones.

On a 16-socket 192-core POWER8 system, a context switching benchmark
with as many software threads as CPUs (so each switch will go in and
out of idle), upstream can achieve a rate of about 1 million context
switches per second. After this patch it goes up to 118 million.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/Kconfig             | 16 ++++++++++++++++
 arch/powerpc/Kconfig     |  1 +
 include/linux/sched/mm.h |  6 +++---
 kernel/fork.c            | 39 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 59 insertions(+), 3 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 2daf8fe6146a..edf69437a971 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -418,6 +418,22 @@ config MMU_LAZY_TLB
 	help
 	  Enable "lazy TLB" mmu context switching for kernel threads.
 
+config MMU_LAZY_TLB_REFCOUNT
+	def_bool y
+	depends on MMU_LAZY_TLB
+	depends on !MMU_LAZY_TLB_SHOOTDOWN
+
+config MMU_LAZY_TLB_SHOOTDOWN
+	bool
+	depends on MMU_LAZY_TLB
+	help
+	  Instead of refcounting the "lazy tlb" mm struct, which can cause
+	  contention with multi-threaded apps on large multiprocessor systems,
+	  this option causes __mmdrop to IPI all CPUs in the mm_cpumask and
+	  switch to init_mm if they were using the to-be-freed mm as the lazy
+	  tlb. Architectures which do not track all possible lazy tlb CPUs in
+	  mm_cpumask can not use this (without modification).
+
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
 	bool
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 920c4e3ca4ef..24ac85c868db 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -225,6 +225,7 @@ config PPC
 	select HAVE_PERF_USER_STACK_DUMP
 	select MMU_GATHER_RCU_TABLE_FREE
 	select MMU_GATHER_PAGE_SIZE
+	select MMU_LAZY_TLB_SHOOTDOWN
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
 	select HAVE_SYSCALL_TRACEPOINTS
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 2c2b20e2ccc7..1067af8039bd 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -53,19 +53,19 @@ void mmdrop(struct mm_struct *mm);
 /* Helpers for lazy TLB mm refcounting */
 static inline void mmgrab_lazy_tlb(struct mm_struct *mm)
 {
-	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB))
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
 		mmgrab(mm);
 }
 
 static inline void mmdrop_lazy_tlb(struct mm_struct *mm)
 {
-	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB))
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
 		mmdrop(mm);
 }
 
 static inline void mmdrop_lazy_tlb_smp_mb(struct mm_struct *mm)
 {
-	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB))
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
 		mmdrop(mm); /* This depends on mmdrop providing a full smp_mb() */
 	else
 		smp_mb();
diff --git a/kernel/fork.c b/kernel/fork.c
index 142b23645d82..da0fba9e6079 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -685,6 +685,40 @@ static void check_mm(struct mm_struct *mm)
 #define allocate_mm()	(kmem_cache_alloc(mm_cachep, GFP_KERNEL))
 #define free_mm(mm)	(kmem_cache_free(mm_cachep, (mm)))
 
+static void do_shoot_lazy_tlb(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (current->active_mm == mm) {
+		BUG_ON(current->mm);
+		switch_mm(mm, &init_mm, current);
+		current->active_mm = &init_mm;
+	}
+}
+
+static void do_check_lazy_tlb(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	BUG_ON(current->active_mm == mm);
+}
+
+static void shoot_lazy_tlbs(struct mm_struct *mm)
+{
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) {
+		smp_call_function_many(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1);
+		do_shoot_lazy_tlb(mm);
+	}
+}
+
+static void check_lazy_tlbs(struct mm_struct *mm)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_VM)) {
+		smp_call_function(do_check_lazy_tlb, (void *)mm, 1);
+		do_check_lazy_tlb(mm);
+	}
+}
+
 /*
  * Called when the last reference to the mm
  * is dropped: either by a lazy thread or by
@@ -695,6 +729,11 @@ void __mmdrop(struct mm_struct *mm)
 	BUG_ON(mm == &init_mm);
 	WARN_ON_ONCE(mm == current->mm);
 	WARN_ON_ONCE(mm == current->active_mm);
+
+	/* Ensure no CPUs are using this as their lazy tlb mm */
+	shoot_lazy_tlbs(mm);
+	check_lazy_tlbs(mm);
+
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_subscriptions_destroy(mm);
-- 
2.23.0



  parent reply	other threads:[~2020-07-10  1:57 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-10  1:56 [RFC PATCH 0/7] mmu context cleanup, lazy tlb cleanup, Nicholas Piggin
2020-07-10  1:56 ` [RFC PATCH 1/7] asm-generic: add generic MMU versions of mmu context functions Nicholas Piggin
2020-07-10  1:56 ` [RFC PATCH 2/7] arch: use asm-generic mmu context for no-op implementations Nicholas Piggin
2020-07-10  1:56 ` [RFC PATCH 3/7] mm: introduce exit_lazy_tlb Nicholas Piggin
2020-07-10  1:56 ` [RFC PATCH 4/7] x86: use exit_lazy_tlb rather than membarrier_mm_sync_core_before_usermode Nicholas Piggin
2020-07-10  9:42   ` Peter Zijlstra
2020-07-10 14:02   ` Mathieu Desnoyers
2020-07-10 17:04   ` Andy Lutomirski
2020-07-13  4:45     ` Nicholas Piggin
2020-07-13 13:47       ` Nicholas Piggin
2020-07-13 14:13         ` Mathieu Desnoyers
2020-07-13 15:48           ` Andy Lutomirski
2020-07-13 16:37             ` Nicholas Piggin
2020-07-16  4:15           ` Nicholas Piggin
2020-07-16  4:42             ` Nicholas Piggin
2020-07-16 15:46               ` Mathieu Desnoyers
2020-07-16 16:03                 ` Mathieu Desnoyers
2020-07-16 18:58                   ` Mathieu Desnoyers
2020-07-16 21:24                     ` Alan Stern
2020-07-17 13:39                       ` Mathieu Desnoyers
2020-07-17 14:51                         ` Alan Stern
2020-07-17 15:39                           ` Mathieu Desnoyers
2020-07-17 16:11                             ` Alan Stern
2020-07-17 16:22                               ` Mathieu Desnoyers
2020-07-17 17:44                                 ` Alan Stern
2020-07-17 17:52                                   ` Mathieu Desnoyers
2020-07-17  0:00                     ` Nicholas Piggin
2020-07-16  5:18             ` Andy Lutomirski
2020-07-16  6:06               ` Nicholas Piggin
2020-07-16  8:50               ` Peter Zijlstra
2020-07-16 10:03                 ` Nicholas Piggin
2020-07-16 11:00                   ` peterz
2020-07-16 15:34                     ` Mathieu Desnoyers
2020-07-16 23:26                     ` Nicholas Piggin
2020-07-17 13:42                       ` Mathieu Desnoyers
2020-07-20  3:03                         ` Nicholas Piggin
2020-07-20 16:46                           ` Mathieu Desnoyers
2020-07-21 10:04                             ` Nicholas Piggin
2020-07-21 13:11                               ` Mathieu Desnoyers
2020-07-21 14:30                                 ` Nicholas Piggin
2020-07-21 15:06                               ` peterz
2020-07-21 15:15                                 ` Mathieu Desnoyers
2020-07-21 15:19                                   ` Peter Zijlstra
2020-07-21 15:22                                     ` Mathieu Desnoyers
2020-07-10  1:56 ` [RFC PATCH 5/7] lazy tlb: introduce lazy mm refcount helper functions Nicholas Piggin
2020-07-10  9:48   ` Peter Zijlstra
2020-07-10  1:56 ` [RFC PATCH 6/7] lazy tlb: allow lazy tlb mm switching to be configurable Nicholas Piggin
2020-07-10  1:56 ` Nicholas Piggin [this message]
2020-07-10  9:35   ` [RFC PATCH 7/7] lazy tlb: shoot lazies, a non-refcounting lazy tlb option Peter Zijlstra
2020-07-13  4:58     ` Nicholas Piggin
2020-07-13 15:59   ` Andy Lutomirski
2020-07-13 16:48     ` Nicholas Piggin
2020-07-13 18:18       ` Andy Lutomirski
2020-07-14  5:04         ` Nicholas Piggin
2020-07-14  6:31           ` Nicholas Piggin
2020-07-14 12:46             ` Andy Lutomirski
2020-07-14 13:23               ` Peter Zijlstra
2020-07-16  2:26               ` Nicholas Piggin
2020-07-16  2:35               ` Nicholas Piggin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200710015646.2020871-8-npiggin@gmail.com \
    --to=npiggin@gmail.com \
    --cc=anton@ozlabs.org \
    --cc=arnd@arndb.de \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=peterz@infradead.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).