From: Nicholas Piggin <npiggin@gmail.com>
To: linux-kernel@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-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
linux-mm@kvack.org, Anton Blanchard <anton@ozlabs.org>
Subject: [PATCH 5/8] lazy tlb: allow lazy tlb mm switching to be configurable
Date: Sun, 29 Nov 2020 02:01:38 +1000 [thread overview]
Message-ID: <20201128160141.1003903-6-npiggin@gmail.com> (raw)
In-Reply-To: <20201128160141.1003903-1-npiggin@gmail.com>
NOMMU systems could easily go without this and save a bit of code
and the refcount atomics, because their mm switch is a no-op. I
haven't flipped them over because haven't audited all arch code to
convert over to using the _lazy_tlb refcounting.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/Kconfig | 11 +++++++
include/linux/sched/mm.h | 13 ++++++--
kernel/sched/core.c | 68 +++++++++++++++++++++++++++++-----------
kernel/sched/sched.h | 4 ++-
4 files changed, 75 insertions(+), 21 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 56b6ccc0e32d..596bf589d74b 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -430,6 +430,17 @@ config ARCH_WANT_IRQS_OFF_ACTIVATE_MM
irqs disabled over activate_mm. Architectures that do IPI based TLB
shootdowns should enable this.
+# Should make this depend on MMU, because there is little use for lazy mm switching
+# with NOMMU. Must audit NOMMU architecture code for lazy mm refcounting first.
+config MMU_LAZY_TLB
+ def_bool y
+ help
+ Enable "lazy TLB" mmu context switching for kernel threads.
+
+config MMU_LAZY_TLB_REFCOUNT
+ def_bool y
+ depends on MMU_LAZY_TLB
+
config ARCH_HAVE_NMI_SAFE_CMPXCHG
bool
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 7157c0f6fef8..bd0f27402d4b 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -51,12 +51,21 @@ static inline void mmdrop(struct mm_struct *mm)
/* Helpers for lazy TLB mm refcounting */
static inline void mmgrab_lazy_tlb(struct mm_struct *mm)
{
- mmgrab(mm);
+ if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
+ mmgrab(mm);
}
static inline void mmdrop_lazy_tlb(struct mm_struct *mm)
{
- mmdrop(mm);
+ if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) {
+ mmdrop(mm);
+ } else {
+ /*
+ * mmdrop_lazy_tlb must provide a full memory barrier, see the
+ * membarrier comment finish_task_switch.
+ */
+ smp_mb();
+ }
}
/**
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e372b613d514..3b79c6cc3a37 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3579,7 +3579,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
__releases(rq->lock)
{
struct rq *rq = this_rq();
- struct mm_struct *mm = rq->prev_mm;
+ struct mm_struct *mm = NULL;
long prev_state;
/*
@@ -3598,7 +3598,10 @@ static struct rq *finish_task_switch(struct task_struct *prev)
current->comm, current->pid, preempt_count()))
preempt_count_set(FORK_PREEMPT_COUNT);
- rq->prev_mm = NULL;
+#ifdef CONFIG_MMU_LAZY_TLB_REFCOUNT
+ mm = rq->prev_lazy_mm;
+ rq->prev_lazy_mm = NULL;
+#endif
/*
* A task struct has one reference for the use as "current".
@@ -3630,6 +3633,8 @@ static struct rq *finish_task_switch(struct task_struct *prev)
* rq->curr, before returning to userspace, for
* {PRIVATE,GLOBAL}_EXPEDITED. This is implicitly provided by
* mmdrop_lazy_tlb().
+ *
+ * This same issue applies to other places that mmdrop_lazy_tlb().
*/
if (mm)
mmdrop_lazy_tlb(mm);
@@ -3719,22 +3724,10 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
calculate_sigpending();
}
-/*
- * context_switch - switch to the new MM and the new thread's register state.
- */
-static __always_inline struct rq *
-context_switch(struct rq *rq, struct task_struct *prev,
- struct task_struct *next, struct rq_flags *rf)
+static __always_inline void
+context_switch_mm(struct rq *rq, struct task_struct *prev,
+ struct task_struct *next)
{
- prepare_task_switch(rq, prev, next);
-
- /*
- * For paravirt, this is coupled with an exit in switch_to to
- * combine the page table reload and the switch backend into
- * one hypercall.
- */
- arch_start_context_switch(prev);
-
/*
* kernel -> kernel lazy + transfer active
* user -> kernel lazy + mmgrab_lazy_tlb() active
@@ -3765,11 +3758,50 @@ context_switch(struct rq *rq, struct task_struct *prev,
if (!prev->mm) { // from kernel
exit_lazy_tlb(prev->active_mm, next);
+#ifdef CONFIG_MMU_LAZY_TLB_REFCOUNT
/* will mmdrop_lazy_tlb() in finish_task_switch(). */
- rq->prev_mm = prev->active_mm;
+ rq->prev_lazy_mm = prev->active_mm;
prev->active_mm = NULL;
+#else
+ /* See membarrier comment in finish_task_switch(). */
+ smp_mb();
+#endif
}
}
+}
+
+static __always_inline void
+context_switch_mm_nolazy(struct rq *rq, struct task_struct *prev,
+ struct task_struct *next)
+{
+ if (!next->mm)
+ next->active_mm = &init_mm;
+ membarrier_switch_mm(rq, prev->active_mm, next->active_mm);
+ switch_mm_irqs_off(prev->active_mm, next->active_mm, next);
+ if (!prev->mm)
+ prev->active_mm = NULL;
+}
+
+/*
+ * context_switch - switch to the new MM and the new thread's register state.
+ */
+static __always_inline struct rq *
+context_switch(struct rq *rq, struct task_struct *prev,
+ struct task_struct *next, struct rq_flags *rf)
+{
+ prepare_task_switch(rq, prev, next);
+
+ /*
+ * For paravirt, this is coupled with an exit in switch_to to
+ * combine the page table reload and the switch backend into
+ * one hypercall.
+ */
+ arch_start_context_switch(prev);
+
+ if (IS_ENABLED(CONFIG_MMU_LAZY_TLB))
+ context_switch_mm(rq, prev, next);
+ else
+ context_switch_mm_nolazy(rq, prev, next);
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index df80bfcea92e..3b72aec5a2f2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -950,7 +950,9 @@ struct rq {
struct task_struct *idle;
struct task_struct *stop;
unsigned long next_balance;
- struct mm_struct *prev_mm;
+#ifdef CONFIG_MMU_LAZY_TLB_REFCOUNT
+ struct mm_struct *prev_lazy_mm;
+#endif
unsigned int clock_update_flags;
u64 clock;
--
2.23.0
next prev parent reply other threads:[~2020-11-28 22:02 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-28 16:01 [PATCH 0/8] shoot lazy tlbs Nicholas Piggin
2020-11-28 16:01 ` [PATCH 1/8] lazy tlb: introduce exit_lazy_tlb Nicholas Piggin
2020-11-29 0:38 ` Andy Lutomirski
2020-12-02 2:49 ` Nicholas Piggin
2020-11-28 16:01 ` [PATCH 2/8] x86: use exit_lazy_tlb rather than membarrier_mm_sync_core_before_usermode Nicholas Piggin
2020-11-28 17:55 ` Andy Lutomirski
2020-12-02 2:49 ` Nicholas Piggin
2020-12-03 5:09 ` Andy Lutomirski
2020-12-05 8:00 ` Nicholas Piggin
2020-12-05 16:11 ` Andy Lutomirski
2020-12-05 23:14 ` Nicholas Piggin
2020-12-06 0:36 ` Andy Lutomirski
2020-12-06 3:59 ` Nicholas Piggin
2020-12-11 0:11 ` Andy Lutomirski
2020-12-14 4:07 ` Nicholas Piggin
2020-12-14 5:53 ` Nicholas Piggin
2020-11-30 14:57 ` Mathieu Desnoyers
2020-11-28 16:01 ` [PATCH 3/8] x86: remove ARCH_HAS_SYNC_CORE_BEFORE_USERMODE Nicholas Piggin
2020-11-28 16:01 ` [PATCH 4/8] lazy tlb: introduce lazy mm refcount helper functions Nicholas Piggin
2020-11-28 16:01 ` Nicholas Piggin [this message]
2020-11-29 0:36 ` [PATCH 5/8] lazy tlb: allow lazy tlb mm switching to be configurable Andy Lutomirski
2020-12-02 2:49 ` Nicholas Piggin
2020-11-28 16:01 ` [PATCH 6/8] lazy tlb: shoot lazies, a non-refcounting lazy tlb option Nicholas Piggin
2020-11-29 3:54 ` Andy Lutomirski
2020-11-29 20:16 ` Andy Lutomirski
2020-11-30 9:25 ` Peter Zijlstra
2020-11-30 18:31 ` Andy Lutomirski
2020-12-01 21:27 ` Will Deacon
2020-12-01 21:50 ` Andy Lutomirski
2020-12-01 23:04 ` Will Deacon
2020-12-02 3:47 ` Nicholas Piggin
2020-12-03 5:05 ` Andy Lutomirski
2020-12-03 17:03 ` Alexander Gordeev
2020-12-03 17:14 ` Andy Lutomirski
2020-12-03 18:33 ` Alexander Gordeev
2020-11-30 9:26 ` Peter Zijlstra
2020-11-30 9:30 ` Peter Zijlstra
2020-11-30 9:34 ` Peter Zijlstra
2020-12-02 3:09 ` Nicholas Piggin
2020-12-02 11:17 ` Peter Zijlstra
2020-12-02 12:45 ` Peter Zijlstra
2020-12-02 14:19 ` Peter Zijlstra
2020-12-02 14:38 ` Andy Lutomirski
2020-12-02 16:29 ` Peter Zijlstra
2020-11-28 16:01 ` [PATCH 7/8] powerpc: use lazy mm refcount helper functions Nicholas Piggin
2020-11-28 16:01 ` [PATCH 8/8] powerpc/64s: enable MMU_LAZY_TLB_SHOOTDOWN 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=20201128160141.1003903-6-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).