From bb4e2c08bbfa8eb032db7814f6100086aac102d3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 6 Jan 2017 22:04:22 -0800 Subject: rcu: Eliminate unused expedited_normal counter Expedited grace periods no longer fall back to normal grace periods in response to lock contention, given that expedited grace periods now use the rcu_node tree so as to avoid contention. This commit therfore removes the expedited_normal counter. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcu/tree.h | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/rcu/tree.h') diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index fe98dd24adf8..8f750dffb0dd 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -521,7 +521,6 @@ struct rcu_state { struct mutex exp_mutex; /* Serialize expedited GP. */ struct mutex exp_wake_mutex; /* Serialize wakeup. */ unsigned long expedited_sequence; /* Take a ticket. */ - atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ struct swait_queue_head expedited_wq; /* Wait for check-ins. */ int ncpus_snap; /* # CPUs seen last time. */ -- cgit v1.2.3 From 02a5c550b2738f2bfea8e1e00aa75944d71c9e18 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 2 Nov 2016 17:25:06 -0700 Subject: rcu: Abstract extended quiescent state determination This commit is the fourth step towards full abstraction of all accesses to the ->dynticks counter, implementing previously open-coded checks and comparisons in new rcu_dynticks_in_eqs() and rcu_dynticks_in_eqs_since() functions. This abstraction will ease changes to the ->dynticks counter operation. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcutiny.h | 6 ++++++ kernel/rcu/tree.c | 52 +++++++++++++++++++++++++++++++++++------------- kernel/rcu/tree.h | 2 ++ kernel/rcu/tree_exp.h | 6 +++--- kernel/rcu/tree_plugin.h | 2 +- kernel/rcu/tree_trace.c | 2 +- 6 files changed, 51 insertions(+), 19 deletions(-) (limited to 'kernel/rcu/tree.h') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index ac81e4063b40..4f9b2fa2173d 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,6 +27,12 @@ #include +struct rcu_dynticks; +static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) +{ + return 0; +} + static inline unsigned long get_state_synchronize_rcu(void) { return 0; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3169d5a21b55..8b970319c75b 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -336,17 +336,48 @@ static void rcu_dynticks_eqs_online(void) atomic_add(0x1, &rdtp->dynticks); } +/* + * Is the current CPU in an extended quiescent state? + * + * No ordering, as we are sampling CPU-local information. + */ +bool rcu_dynticks_curr_cpu_in_eqs(void) +{ + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + + return !(atomic_read(&rdtp->dynticks) & 0x1); +} + /* * Snapshot the ->dynticks counter with full ordering so as to allow * stable comparison of this counter with past and future snapshots. */ -static int rcu_dynticks_snap(struct rcu_dynticks *rdtp) +int rcu_dynticks_snap(struct rcu_dynticks *rdtp) { int snap = atomic_add_return(0, &rdtp->dynticks); return snap; } +/* + * Return true if the snapshot returned from rcu_dynticks_snap() + * indicates that RCU is in an extended quiescent state. + */ +static bool rcu_dynticks_in_eqs(int snap) +{ + return !(snap & 0x1); +} + +/* + * Return true if the CPU corresponding to the specified rcu_dynticks + * structure has spent some time in an extended quiescent state since + * rcu_dynticks_snap() returned the specified snapshot. + */ +static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap) +{ + return snap != rcu_dynticks_snap(rdtp); +} + /* * Do a double-increment of the ->dynticks counter to emulate a * momentary idle-CPU quiescent state. @@ -1045,7 +1076,7 @@ void rcu_nmi_enter(void) * to be in the outermost NMI handler that interrupted an RCU-idle * period (observation due to Andy Lutomirski). */ - if (!(atomic_read(&rdtp->dynticks) & 0x1)) { + if (rcu_dynticks_curr_cpu_in_eqs()) { rcu_dynticks_eqs_exit(); incby = 1; } @@ -1071,7 +1102,7 @@ void rcu_nmi_exit(void) * to us!) */ WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0); - WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs()); /* * If the nesting level is not 1, the CPU wasn't RCU-idle, so @@ -1097,9 +1128,7 @@ void rcu_nmi_exit(void) */ bool notrace __rcu_is_watching(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - return atomic_read(&rdtp->dynticks) & 0x1; + return !rcu_dynticks_curr_cpu_in_eqs(); } /** @@ -1184,7 +1213,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, { rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); rcu_sysidle_check_cpu(rdp, isidle, maxj); - if ((rdp->dynticks_snap & 0x1) == 0) { + if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rdp->mynode->gpnum)) @@ -1203,12 +1232,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, bool *isidle, unsigned long *maxj) { - unsigned int curr; int *rcrmp; - unsigned int snap; - - curr = (unsigned int)rcu_dynticks_snap(rdp->dynticks); - snap = (unsigned int)rdp->dynticks_snap; /* * If the CPU passed through or entered a dynticks idle phase with @@ -1218,7 +1242,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, * read-side critical section that started before the beginning * of the current RCU grace period. */ - if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) { + if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); rdp->dynticks_fqs++; return 1; @@ -3807,7 +3831,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu); rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); - WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); + WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks))); rdp->cpu = cpu; rdp->rsp = rsp; rcu_boot_init_nocb_percpu_data(rdp); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index fe98dd24adf8..3b953dcf6afc 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -595,6 +595,8 @@ extern struct rcu_state rcu_bh_state; extern struct rcu_state rcu_preempt_state; #endif /* #ifdef CONFIG_PREEMPT_RCU */ +int rcu_dynticks_snap(struct rcu_dynticks *rdtp); + #ifdef CONFIG_RCU_BOOST DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 011f626b2fd8..e155a465cf84 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -360,7 +360,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, rdp->exp_dynticks_snap = rcu_dynticks_snap(rdp->dynticks); if (raw_smp_processor_id() == cpu || - !(rdp->exp_dynticks_snap & 0x1) || + rcu_dynticks_in_eqs(rdp->exp_dynticks_snap) || !(rnp->qsmaskinitnext & rdp->grpmask)) mask_ofl_test |= rdp->grpmask; } @@ -383,8 +383,8 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, if (!(mask_ofl_ipi & mask)) continue; retry_ipi: - if (rcu_dynticks_snap(rdp->dynticks) != - rdp->exp_dynticks_snap) { + if (rcu_dynticks_in_eqs_since(rdp->dynticks, + rdp->exp_dynticks_snap)) { mask_ofl_test |= mask; continue; } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 56583e764ebf..652209589adf 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1643,7 +1643,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)], ticks_value, ticks_title, - atomic_read(&rdtp->dynticks) & 0xfff, + rcu_dynticks_snap(rdtp) & 0xfff, rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart, diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index b1f28972872c..b833cd0a29e8 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -124,7 +124,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu), rdp->core_needs_qs); seq_printf(m, " dt=%d/%llx/%d df=%lu", - atomic_read(&rdp->dynticks->dynticks), + rcu_dynticks_snap(rdp->dynticks), rdp->dynticks->dynticks_nesting, rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); -- cgit v1.2.3 From d85b62f18d543c663cbdd6061054efeb9e66cee7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 28 Nov 2016 12:08:49 -0800 Subject: srcu: Force full grace-period ordering If a process invokes synchronize_srcu(), is delayed just the right amount of time, and thus does not sleep when waiting for the grace period to complete, there is no ordering between the end of the grace period and the code following the synchronize_srcu(). Similarly, there can be a lack of ordering between the end of the SRCU grace period and callback invocation. This commit adds the necessary ordering. Reported-by: Lance Roy Signed-off-by: Paul E. McKenney [ paulmck: Further smp_mb() adjustment per email with Lance Roy. ] --- include/linux/rcupdate.h | 12 ++++++++++++ kernel/rcu/srcu.c | 10 ++++++++-- kernel/rcu/tree.h | 12 ------------ 3 files changed, 20 insertions(+), 14 deletions(-) (limited to 'kernel/rcu/tree.h') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 01f71e1d2e94..6ade6a52d9d4 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -1161,5 +1161,17 @@ do { \ ftrace_dump(oops_dump_mode); \ } while (0) +/* + * Place this after a lock-acquisition primitive to guarantee that + * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies + * if the UNLOCK and LOCK are executed by the same CPU or if the + * UNLOCK and LOCK operate on the same lock variable. + */ +#ifdef CONFIG_PPC +#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ +#else /* #ifdef CONFIG_PPC */ +#define smp_mb__after_unlock_lock() do { } while (0) +#endif /* #else #ifdef CONFIG_PPC */ + #endif /* __LINUX_RCUPDATE_H */ diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index c9a0015e1c2e..665bc9951523 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -358,6 +358,7 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head, head->next = NULL; head->func = func; spin_lock_irqsave(&sp->queue_lock, flags); + smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */ rcu_batch_queue(&sp->batch_queue, head); if (!sp->running) { sp->running = true; @@ -391,6 +392,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) head->next = NULL; head->func = wakeme_after_rcu; spin_lock_irq(&sp->queue_lock); + smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */ if (!sp->running) { /* steal the processing owner */ sp->running = true; @@ -410,8 +412,11 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) spin_unlock_irq(&sp->queue_lock); } - if (!done) + if (!done) { wait_for_completion(&rcu.completion); + smp_mb(); /* Caller's later accesses after GP. */ + } + } /** @@ -579,7 +584,8 @@ static void srcu_advance_batches(struct srcu_struct *sp, int trycount) /* * Invoke a limited number of SRCU callbacks that have passed through * their grace period. If there are more to do, SRCU will reschedule - * the workqueue. + * the workqueue. Note that needed memory barriers have been executed + * in this task's context by srcu_readers_active_idx_check(). */ static void srcu_invoke_callbacks(struct srcu_struct *sp) { diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index fe98dd24adf8..abcc25bdcb29 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -687,18 +687,6 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) } #endif /* #ifdef CONFIG_RCU_TRACE */ -/* - * Place this after a lock-acquisition primitive to guarantee that - * an UNLOCK+LOCK pair act as a full barrier. This guarantee applies - * if the UNLOCK and LOCK are executed by the same CPU or if the - * UNLOCK and LOCK operate on the same lock variable. - */ -#ifdef CONFIG_PPC -#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ -#else /* #ifdef CONFIG_PPC */ -#define smp_mb__after_unlock_lock() do { } while (0) -#endif /* #else #ifdef CONFIG_PPC */ - /* * Wrappers for the rcu_node::lock acquire and release. * -- cgit v1.2.3