From mboxrd@z Thu Jan 1 00:00:00 1970 From: Nicholas Piggin Subject: [RFC PATCH 5/7] lazy tlb: introduce lazy mm refcount helper functions Date: Fri, 10 Jul 2020 11:56:44 +1000 Message-ID: <20200710015646.2020871-6-npiggin@gmail.com> References: <20200710015646.2020871-1-npiggin@gmail.com> Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Return-path: Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40934 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727123AbgGJB5d (ORCPT ); Thu, 9 Jul 2020 21:57:33 -0400 In-Reply-To: <20200710015646.2020871-1-npiggin@gmail.com> Sender: linux-arch-owner@vger.kernel.org List-ID: To: linux-arch@vger.kernel.org Cc: Nicholas Piggin , x86@kernel.org, Mathieu Desnoyers , Arnd Bergmann , Peter Zijlstra , linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-mm@kvack.org, Anton Blanchard Add explicit _lazy_tlb annotated functions for lazy mm refcounting. This makes things a bit more explicit, and allows explicit refcounting to be removed if it is not used. Signed-off-by: Nicholas Piggin --- arch/powerpc/kernel/smp.c | 2 +- arch/powerpc/mm/book3s64/radix_tlb.c | 4 ++-- fs/exec.c | 2 +- include/linux/sched/mm.h | 17 +++++++++++++++++ kernel/cpu.c | 2 +- kernel/exit.c | 2 +- kernel/kthread.c | 11 +++++++---- kernel/sched/core.c | 13 +++++++------ 8 files changed, 37 insertions(+), 16 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 73199470c265..ad95812d2a3f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1253,7 +1253,7 @@ void start_secondary(void *unused) unsigned int cpu = smp_processor_id(); struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask; - mmgrab(&init_mm); + mmgrab(&init_mm); /* XXX: where is the mmput for this? */ current->active_mm = &init_mm; smp_store_cpu_info(cpu); diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index b5cc9b23cf02..52730629b3eb 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -652,10 +652,10 @@ static void do_exit_flush_lazy_tlb(void *arg) * Must be a kernel thread because sender is single-threaded. */ BUG_ON(current->mm); - mmgrab(&init_mm); + mmgrab_lazy_tlb(&init_mm); switch_mm(mm, &init_mm, current); current->active_mm = &init_mm; - mmdrop(mm); + mmdrop_lazy_tlb(mm); } _tlbiel_pid(pid, RIC_FLUSH_ALL); } diff --git a/fs/exec.c b/fs/exec.c index e2ab71e88293..3a01b2751ea9 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1119,7 +1119,7 @@ static int exec_mmap(struct mm_struct *mm) mmput(old_mm); } else { exit_lazy_tlb(active_mm, tsk); - mmdrop(active_mm); + mmdrop_lazy_tlb(active_mm); } return 0; } diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 9b026264b445..110d4ad21de6 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -50,6 +50,23 @@ static inline void mmdrop(struct mm_struct *mm) void mmdrop(struct mm_struct *mm); +/* Helpers for lazy TLB mm refcounting */ +static inline void mmgrab_lazy_tlb(struct mm_struct *mm) +{ + mmgrab(mm); +} + +static inline void mmdrop_lazy_tlb(struct mm_struct *mm) +{ + mmdrop(mm); +} + +static inline void mmdrop_lazy_tlb_smp_mb(struct mm_struct *mm) +{ + /* This depends on mmdrop providing a full smp_mb() */ + mmdrop(mm); +} + /* * This has to be called after a get_task_mm()/mmget_not_zero() * followed by taking the mmap_lock for writing before modifying the diff --git a/kernel/cpu.c b/kernel/cpu.c index 134688d79589..ff9fcbc4e76b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -578,7 +578,7 @@ static int finish_cpu(unsigned int cpu) */ if (mm != &init_mm) idle->active_mm = &init_mm; - mmdrop(mm); + mmdrop_lazy_tlb(mm); return 0; } diff --git a/kernel/exit.c b/kernel/exit.c index 727150f28103..d535da9fd2f8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -470,7 +470,7 @@ static void exit_mm(void) __set_current_state(TASK_RUNNING); mmap_read_lock(mm); } - mmgrab(mm); + mmgrab_lazy_tlb(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); diff --git a/kernel/kthread.c b/kernel/kthread.c index 6f93c649aa97..a7133cc2ddaf 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1238,12 +1238,12 @@ void kthread_use_mm(struct mm_struct *mm) WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); + mmgrab(mm); + task_lock(tsk); active_mm = tsk->active_mm; - if (active_mm != mm) { - mmgrab(mm); + if (active_mm != mm) tsk->active_mm = mm; - } tsk->mm = mm; switch_mm(active_mm, mm, tsk); task_unlock(tsk); @@ -1253,7 +1253,7 @@ void kthread_use_mm(struct mm_struct *mm) exit_lazy_tlb(active_mm, tsk); if (active_mm != mm) - mmdrop(active_mm); + mmdrop_lazy_tlb(active_mm); to_kthread(tsk)->oldfs = get_fs(); set_fs(USER_DS); @@ -1276,9 +1276,12 @@ void kthread_unuse_mm(struct mm_struct *mm) task_lock(tsk); sync_mm_rss(mm); tsk->mm = NULL; + mmgrab_lazy_tlb(mm); /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); task_unlock(tsk); + + mmdrop(mm); } EXPORT_SYMBOL_GPL(kthread_unuse_mm); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 31e22c79826c..d19f2f517f6c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3302,10 +3302,11 @@ static struct rq *finish_task_switch(struct task_struct *prev) * schedule between user->kernel->user threads without passing though * 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(). + * {PRIVATE,GLOBAL}_EXPEDITED. This is implicitly provided by + * mmdrop_lazy_tlb_smp_mb(). */ if (mm) - mmdrop(mm); + mmdrop_lazy_tlb_smp_mb(mm); if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) @@ -3410,9 +3411,9 @@ context_switch(struct rq *rq, struct task_struct *prev, /* * kernel -> kernel lazy + transfer active - * user -> kernel lazy + mmgrab() active + * user -> kernel lazy + mmgrab_lazy_tlb() active * - * kernel -> user switch + mmdrop() active + * kernel -> user switch + mmdrop_lazy_tlb() active * user -> user switch */ if (!next->mm) { // to kernel @@ -3420,7 +3421,7 @@ context_switch(struct rq *rq, struct task_struct *prev, next->active_mm = prev->active_mm; if (prev->mm) // from user - mmgrab(prev->active_mm); + mmgrab_lazy_tlb(prev->active_mm); else prev->active_mm = NULL; } else { // to user @@ -3438,7 +3439,7 @@ context_switch(struct rq *rq, struct task_struct *prev, if (!prev->mm) { // from kernel exit_lazy_tlb(prev->active_mm, next); - /* will mmdrop() in finish_task_switch(). */ + /* will mmdrop_lazy_tlb() in finish_task_switch(). */ rq->prev_mm = prev->active_mm; prev->active_mm = NULL; } -- 2.23.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Nicholas Piggin Subject: [RFC PATCH 5/7] lazy tlb: introduce lazy mm refcount helper functions Date: Fri, 10 Jul 2020 11:56:44 +1000 Message-ID: <20200710015646.2020871-6-npiggin@gmail.com> In-Reply-To: <20200710015646.2020871-1-npiggin@gmail.com> References: <20200710015646.2020871-1-npiggin@gmail.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-linux-mm@kvack.org To: linux-arch@vger.kernel.org Cc: Nicholas Piggin , x86@kernel.org, Mathieu Desnoyers , Arnd Bergmann , Peter Zijlstra , linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-mm@kvack.org, Anton Blanchard List-ID: Message-ID: <20200710015644.tVij13Fpdyu_wRgJDfqqloHzET2V4x0hXqWgu_3DpwI@z> Add explicit _lazy_tlb annotated functions for lazy mm refcounting. This makes things a bit more explicit, and allows explicit refcounting to be removed if it is not used. Signed-off-by: Nicholas Piggin --- arch/powerpc/kernel/smp.c | 2 +- arch/powerpc/mm/book3s64/radix_tlb.c | 4 ++-- fs/exec.c | 2 +- include/linux/sched/mm.h | 17 +++++++++++++++++ kernel/cpu.c | 2 +- kernel/exit.c | 2 +- kernel/kthread.c | 11 +++++++---- kernel/sched/core.c | 13 +++++++------ 8 files changed, 37 insertions(+), 16 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 73199470c265..ad95812d2a3f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1253,7 +1253,7 @@ void start_secondary(void *unused) unsigned int cpu =3D smp_processor_id(); struct cpumask *(*sibling_mask)(int) =3D cpu_sibling_mask; =20 - mmgrab(&init_mm); + mmgrab(&init_mm); /* XXX: where is the mmput for this? */ current->active_mm =3D &init_mm; =20 smp_store_cpu_info(cpu); diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3= s64/radix_tlb.c index b5cc9b23cf02..52730629b3eb 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -652,10 +652,10 @@ static void do_exit_flush_lazy_tlb(void *arg) * Must be a kernel thread because sender is single-threaded. */ BUG_ON(current->mm); - mmgrab(&init_mm); + mmgrab_lazy_tlb(&init_mm); switch_mm(mm, &init_mm, current); current->active_mm =3D &init_mm; - mmdrop(mm); + mmdrop_lazy_tlb(mm); } _tlbiel_pid(pid, RIC_FLUSH_ALL); } diff --git a/fs/exec.c b/fs/exec.c index e2ab71e88293..3a01b2751ea9 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1119,7 +1119,7 @@ static int exec_mmap(struct mm_struct *mm) mmput(old_mm); } else { exit_lazy_tlb(active_mm, tsk); - mmdrop(active_mm); + mmdrop_lazy_tlb(active_mm); } return 0; } diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 9b026264b445..110d4ad21de6 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -50,6 +50,23 @@ static inline void mmdrop(struct mm_struct *mm) =20 void mmdrop(struct mm_struct *mm); =20 +/* Helpers for lazy TLB mm refcounting */ +static inline void mmgrab_lazy_tlb(struct mm_struct *mm) +{ + mmgrab(mm); +} + +static inline void mmdrop_lazy_tlb(struct mm_struct *mm) +{ + mmdrop(mm); +} + +static inline void mmdrop_lazy_tlb_smp_mb(struct mm_struct *mm) +{ + /* This depends on mmdrop providing a full smp_mb() */ + mmdrop(mm); +} + /* * This has to be called after a get_task_mm()/mmget_not_zero() * followed by taking the mmap_lock for writing before modifying the diff --git a/kernel/cpu.c b/kernel/cpu.c index 134688d79589..ff9fcbc4e76b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -578,7 +578,7 @@ static int finish_cpu(unsigned int cpu) */ if (mm !=3D &init_mm) idle->active_mm =3D &init_mm; - mmdrop(mm); + mmdrop_lazy_tlb(mm); return 0; } =20 diff --git a/kernel/exit.c b/kernel/exit.c index 727150f28103..d535da9fd2f8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -470,7 +470,7 @@ static void exit_mm(void) __set_current_state(TASK_RUNNING); mmap_read_lock(mm); } - mmgrab(mm); + mmgrab_lazy_tlb(mm); BUG_ON(mm !=3D current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); diff --git a/kernel/kthread.c b/kernel/kthread.c index 6f93c649aa97..a7133cc2ddaf 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1238,12 +1238,12 @@ void kthread_use_mm(struct mm_struct *mm) WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); =20 + mmgrab(mm); + task_lock(tsk); active_mm =3D tsk->active_mm; - if (active_mm !=3D mm) { - mmgrab(mm); + if (active_mm !=3D mm) tsk->active_mm =3D mm; - } tsk->mm =3D mm; switch_mm(active_mm, mm, tsk); task_unlock(tsk); @@ -1253,7 +1253,7 @@ void kthread_use_mm(struct mm_struct *mm) =20 exit_lazy_tlb(active_mm, tsk); if (active_mm !=3D mm) - mmdrop(active_mm); + mmdrop_lazy_tlb(active_mm); =20 to_kthread(tsk)->oldfs =3D get_fs(); set_fs(USER_DS); @@ -1276,9 +1276,12 @@ void kthread_unuse_mm(struct mm_struct *mm) task_lock(tsk); sync_mm_rss(mm); tsk->mm =3D NULL; + mmgrab_lazy_tlb(mm); /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); task_unlock(tsk); + + mmdrop(mm); } EXPORT_SYMBOL_GPL(kthread_unuse_mm); =20 diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 31e22c79826c..d19f2f517f6c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3302,10 +3302,11 @@ static struct rq *finish_task_switch(struct task_= struct *prev) * schedule between user->kernel->user threads without passing though * 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(). + * {PRIVATE,GLOBAL}_EXPEDITED. This is implicitly provided by + * mmdrop_lazy_tlb_smp_mb(). */ if (mm) - mmdrop(mm); + mmdrop_lazy_tlb_smp_mb(mm); =20 if (unlikely(prev_state =3D=3D TASK_DEAD)) { if (prev->sched_class->task_dead) @@ -3410,9 +3411,9 @@ context_switch(struct rq *rq, struct task_struct *p= rev, =20 /* * kernel -> kernel lazy + transfer active - * user -> kernel lazy + mmgrab() active + * user -> kernel lazy + mmgrab_lazy_tlb() active * - * kernel -> user switch + mmdrop() active + * kernel -> user switch + mmdrop_lazy_tlb() active * user -> user switch */ if (!next->mm) { // to kernel @@ -3420,7 +3421,7 @@ context_switch(struct rq *rq, struct task_struct *p= rev, =20 next->active_mm =3D prev->active_mm; if (prev->mm) // from user - mmgrab(prev->active_mm); + mmgrab_lazy_tlb(prev->active_mm); else prev->active_mm =3D NULL; } else { // to user @@ -3438,7 +3439,7 @@ context_switch(struct rq *rq, struct task_struct *p= rev, if (!prev->mm) { // from kernel exit_lazy_tlb(prev->active_mm, next); =20 - /* will mmdrop() in finish_task_switch(). */ + /* will mmdrop_lazy_tlb() in finish_task_switch(). */ rq->prev_mm =3D prev->active_mm; prev->active_mm =3D NULL; } --=20 2.23.0