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 2/8] x86: use exit_lazy_tlb rather than membarrier_mm_sync_core_before_usermode
Date: Sun, 29 Nov 2020 02:01:35 +1000 [thread overview]
Message-ID: <20201128160141.1003903-3-npiggin@gmail.com> (raw)
In-Reply-To: <20201128160141.1003903-1-npiggin@gmail.com>
And get rid of the generic sync_core_before_usermode facility. This is
functionally a no-op in the core scheduler code, but it also catches
This helper is the wrong way around I think. The idea that membarrier
state requires a core sync before returning to user is the easy one
that does not need hiding behind membarrier calls. The gap in core
synchronization due to x86's sysret/sysexit and lazy tlb mode, is the
tricky detail that is better put in x86 lazy tlb code.
Consider if an arch did not synchronize core in switch_mm either, then
membarrier_mm_sync_core_before_usermode would be in the wrong place
but arch specific mmu context functions would still be the right place.
There is also a exit_lazy_tlb case that is not covered by this call, which
could be a bugs (kthread use mm the membarrier process's mm then context
switch back to the process without switching mm or lazy mm switch).
This makes lazy tlb code a bit more modular.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
.../membarrier-sync-core/arch-support.txt | 6 ++++-
arch/x86/include/asm/mmu_context.h | 27 +++++++++++++++++++
include/linux/sched/mm.h | 14 ----------
kernel/cpu.c | 4 ++-
kernel/sched/core.c | 16 +++++------
5 files changed, 42 insertions(+), 25 deletions(-)
diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
index 47e6903f47a5..0763a63a7097 100644
--- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt
+++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
@@ -5,6 +5,10 @@
#
# Architecture requirements
#
+# If your architecture returns to user-space through non-core-serializing
+# instructions, you need to ensure these are done in switch_mm and exit_lazy_tlb
+# (if lazy tlb switching is implemented).
+#
# * arm/arm64/powerpc
#
# Rely on implicit context synchronization as a result of exception return
@@ -24,7 +28,7 @@
# instead on write_cr3() performed by switch_mm() to provide core serialization
# after changing the current mm, and deal with the special case of kthread ->
# uthread (temporarily keeping current mm into active_mm) by issuing a
-# sync_core_before_usermode() in that specific case.
+# serializing instruction in exit_lazy_mm() in that specific case.
#
-----------------------
| arch |status|
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 36afcbea6a9f..8094893254f1 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -6,12 +6,14 @@
#include <linux/atomic.h>
#include <linux/mm_types.h>
#include <linux/pkeys.h>
+#include <linux/sched/mm.h>
#include <trace/events/tlb.h>
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
#include <asm/debugreg.h>
+#include <asm/sync_core.h>
extern atomic64_t last_mm_ctx_id;
@@ -94,6 +96,31 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
#define enter_lazy_tlb enter_lazy_tlb
extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
+#ifdef CONFIG_MEMBARRIER
+/*
+ * Ensure that a core serializing instruction is issued before returning
+ * to user-mode, if a SYNC_CORE was requested. x86 implements return to
+ * user-space through sysexit, sysrel, and sysretq, which are not core
+ * serializing.
+ *
+ * See the membarrier comment in finish_task_switch as to why this is done
+ * in exit_lazy_tlb.
+ */
+#define exit_lazy_tlb exit_lazy_tlb
+static inline void exit_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+ /* Switching mm is serializing with write_cr3 */
+ if (tsk->mm != mm)
+ return;
+
+ if (likely(!(atomic_read(&mm->membarrier_state) &
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE)))
+ return;
+
+ sync_core_before_usermode();
+}
+#endif
+
/*
* Init a new mm. Used on mm copies, like at fork()
* and on mm's that are brand-new, like at execve().
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index d5ece7a9a403..2c6bcdf76d99 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -7,7 +7,6 @@
#include <linux/sched.h>
#include <linux/mm_types.h>
#include <linux/gfp.h>
-#include <linux/sync_core.h>
/*
* Routines for handling mm_structs
@@ -335,16 +334,6 @@ enum {
#include <asm/membarrier.h>
#endif
-static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
-{
- if (current->mm != mm)
- return;
- if (likely(!(atomic_read(&mm->membarrier_state) &
- MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE)))
- return;
- sync_core_before_usermode();
-}
-
extern void membarrier_exec_mmap(struct mm_struct *mm);
#else
@@ -358,9 +347,6 @@ static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
static inline void membarrier_exec_mmap(struct mm_struct *mm)
{
}
-static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
-{
-}
#endif
#endif /* _LINUX_SCHED_MM_H */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6ff2578ecf17..134688d79589 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -572,7 +572,9 @@ static int finish_cpu(unsigned int cpu)
/*
* idle_task_exit() will have switched to &init_mm, now
- * clean up any remaining active_mm state.
+ * clean up any remaining active_mm state. exit_lazy_tlb
+ * is not done, if an arch did any accounting in these
+ * functions it would have to be added.
*/
if (mm != &init_mm)
idle->active_mm = &init_mm;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dcc46039ade5..e4e8cebd82e2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3620,22 +3620,19 @@ static struct rq *finish_task_switch(struct task_struct *prev)
kcov_finish_switch(current);
fire_sched_in_preempt_notifiers(current);
+
/*
* When switching through a kernel thread, the loop in
* membarrier_{private,global}_expedited() may have observed that
* kernel thread and not issued an IPI. It is therefore possible to
* schedule between user->kernel->user threads without passing though
- * switch_mm(). Membarrier requires a barrier after storing to
- * rq->curr, before returning to userspace, so provide them here:
- *
- * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
- * provided by mmdrop(),
- * - a sync_core for SYNC_CORE.
+ * switch_mm(). Membarrier requires a full barrier after storing to
+ * rq->curr, before returning to userspace, for
+ * {PRIVATE,GLOBAL}_EXPEDITED. This is implicitly provided by mmdrop().
*/
- if (mm) {
- membarrier_mm_sync_core_before_usermode(mm);
+ if (mm)
mmdrop(mm);
- }
+
if (unlikely(prev_state == TASK_DEAD)) {
if (prev->sched_class->task_dead)
prev->sched_class->task_dead(prev);
@@ -6689,6 +6686,7 @@ void idle_task_exit(void)
BUG_ON(current != this_rq()->idle);
if (mm != &init_mm) {
+ /* enter_lazy_tlb is not done because we're about to go down */
switch_mm(mm, &init_mm, current);
finish_arch_post_lock_switch();
}
--
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 ` Nicholas Piggin [this message]
2020-11-28 17:55 ` [PATCH 2/8] x86: use exit_lazy_tlb rather than membarrier_mm_sync_core_before_usermode 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 ` [PATCH 5/8] lazy tlb: allow lazy tlb mm switching to be configurable Nicholas Piggin
2020-11-29 0:36 ` 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=20201128160141.1003903-3-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).