From b0e165c035b13e1074fa0b555318bd9cb7102558 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 13 Sep 2009 09:15:09 -0700 Subject: rcu: Add debug checks to TREE_PREEMPT_RCU for premature grace periods Check to make sure that there are no blocked tasks for the previous grace period while initializing for the next grace period, verify that rcu_preempt_qs() is given the correct CPU number and is never called for an offline CPU. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu LKML-Reference: <12528585111986-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree_plugin.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 47789369ea59..b8e4b0384f00 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -86,6 +86,7 @@ static void rcu_preempt_qs(int cpu) if (t->rcu_read_lock_nesting && (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { + WARN_ON_ONCE(cpu != smp_processor_id()); /* Possibly blocking in an RCU read-side critical section. */ rdp = rcu_preempt_state.rda[cpu]; @@ -103,7 +104,11 @@ static void rcu_preempt_qs(int cpu) * state for the current grace period), then as long * as that task remains queued, the current grace period * cannot end. + * + * But first, note that the current CPU must still be + * on line! */ + WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0); phase = !(rnp->qsmask & rdp->grpmask) ^ (rnp->gpnum & 0x1); list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]); smp_mb(); /* Ensure later ctxt swtch seen after above. */ @@ -258,6 +263,18 @@ static void rcu_print_task_stall(struct rcu_node *rnp) #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ +/* + * Check that the list of blocked tasks for the newly completed grace + * period is in fact empty. It is a serious bug to complete a grace + * period that still has RCU readers blocked! This function must be + * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock + * must be held by the caller. + */ +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +{ + WARN_ON_ONCE(!list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])); +} + /* * Check for preempted RCU readers for the specified rcu_node structure. * If the caller needs a reliable answer, it must hold the rcu_node's @@ -450,6 +467,14 @@ static void rcu_print_task_stall(struct rcu_node *rnp) #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ +/* + * Because there is no preemptable RCU, there can be no readers blocked, + * so there is no need to check for blocked tasks. + */ +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +{ +} + /* * Because preemptable RCU does not exist, there are never any preempted * RCU readers. -- cgit v1.2.2 From c3422bea5f09b0e85704f51f2b01271630b8940b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 13 Sep 2009 09:15:10 -0700 Subject: rcu: Simplify rcu_read_unlock_special() quiescent-state accounting The earlier approach required two scheduling-clock ticks to note an preemptable-RCU quiescent state in the situation in which the scheduling-clock interrupt is unlucky enough to always interrupt an RCU read-side critical section. With this change, the quiescent state is instead noted by the outermost rcu_read_unlock() immediately following the first scheduling-clock tick, or, alternatively, by the first subsequent context switch. Therefore, this change also speeds up grace periods. Suggested-by: Josh Triplett Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu LKML-Reference: <12528585111945-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree_plugin.h | 54 ++++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 28 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index b8e4b0384f00..c9616e48379b 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -64,34 +64,42 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed); * not in a quiescent state. There might be any number of tasks blocked * while in an RCU read-side critical section. */ -static void rcu_preempt_qs_record(int cpu) +static void rcu_preempt_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); - rdp->passed_quiesc = 1; rdp->passed_quiesc_completed = rdp->completed; + barrier(); + rdp->passed_quiesc = 1; } /* - * We have entered the scheduler or are between softirqs in ksoftirqd. - * If we are in an RCU read-side critical section, we need to reflect - * that in the state of the rcu_node structure corresponding to this CPU. - * Caller must disable hardirqs. + * We have entered the scheduler, and the current task might soon be + * context-switched away from. If this task is in an RCU read-side + * critical section, we will no longer be able to rely on the CPU to + * record that fact, so we enqueue the task on the appropriate entry + * of the blocked_tasks[] array. The task will dequeue itself when + * it exits the outermost enclosing RCU read-side critical section. + * Therefore, the current grace period cannot be permitted to complete + * until the blocked_tasks[] entry indexed by the low-order bit of + * rnp->gpnum empties. + * + * Caller must disable preemption. */ -static void rcu_preempt_qs(int cpu) +static void rcu_preempt_note_context_switch(int cpu) { struct task_struct *t = current; + unsigned long flags; int phase; struct rcu_data *rdp; struct rcu_node *rnp; if (t->rcu_read_lock_nesting && (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { - WARN_ON_ONCE(cpu != smp_processor_id()); /* Possibly blocking in an RCU read-side critical section. */ rdp = rcu_preempt_state.rda[cpu]; rnp = rdp->mynode; - spin_lock(&rnp->lock); + spin_lock_irqsave(&rnp->lock, flags); t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED; t->rcu_blocked_node = rnp; @@ -112,7 +120,7 @@ static void rcu_preempt_qs(int cpu) phase = !(rnp->qsmask & rdp->grpmask) ^ (rnp->gpnum & 0x1); list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]); smp_mb(); /* Ensure later ctxt swtch seen after above. */ - spin_unlock(&rnp->lock); + spin_unlock_irqrestore(&rnp->lock, flags); } /* @@ -124,9 +132,8 @@ static void rcu_preempt_qs(int cpu) * grace period, then the fact that the task has been enqueued * means that we continue to block the current grace period. */ - rcu_preempt_qs_record(cpu); - t->rcu_read_unlock_special &= ~(RCU_READ_UNLOCK_NEED_QS | - RCU_READ_UNLOCK_GOT_QS); + rcu_preempt_qs(cpu); + t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; } /* @@ -162,7 +169,7 @@ static void rcu_read_unlock_special(struct task_struct *t) special = t->rcu_read_unlock_special; if (special & RCU_READ_UNLOCK_NEED_QS) { t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; - t->rcu_read_unlock_special |= RCU_READ_UNLOCK_GOT_QS; + rcu_preempt_qs(smp_processor_id()); } /* Hardware IRQ handlers cannot block. */ @@ -199,9 +206,7 @@ static void rcu_read_unlock_special(struct task_struct *t) */ if (!empty && rnp->qsmask == 0 && list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])) { - t->rcu_read_unlock_special &= - ~(RCU_READ_UNLOCK_NEED_QS | - RCU_READ_UNLOCK_GOT_QS); + t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; if (rnp->parent == NULL) { /* Only one rcu_node in the tree. */ cpu_quiet_msk_finish(&rcu_preempt_state, flags); @@ -352,19 +357,12 @@ static void rcu_preempt_check_callbacks(int cpu) struct task_struct *t = current; if (t->rcu_read_lock_nesting == 0) { - t->rcu_read_unlock_special &= - ~(RCU_READ_UNLOCK_NEED_QS | RCU_READ_UNLOCK_GOT_QS); - rcu_preempt_qs_record(cpu); + t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; + rcu_preempt_qs(cpu); return; } if (per_cpu(rcu_preempt_data, cpu).qs_pending) { - if (t->rcu_read_unlock_special & RCU_READ_UNLOCK_GOT_QS) { - rcu_preempt_qs_record(cpu); - t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_GOT_QS; - } else if (!(t->rcu_read_unlock_special & - RCU_READ_UNLOCK_NEED_QS)) { - t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; - } + t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } } @@ -451,7 +449,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed); * Because preemptable RCU does not exist, we never have to check for * CPUs being in quiescent states. */ -static void rcu_preempt_qs(int cpu) +static void rcu_preempt_note_context_switch(int cpu) { } -- cgit v1.2.2 From 28ecd58020409be8eb176c716f957fc3386fa2fa Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 18 Sep 2009 09:50:17 -0700 Subject: rcu: Add WARN_ON_ONCE() consistency checks covering state transitions o Verify that qsmask bits stay clear through GP initialization. o Verify that cpu_quiet_msk_finish() is never invoked unless there actually is an RCU grace period in progress. o Verify that all internal-node rcu_node structures have empty blocked_tasks[] lists. o Verify that child rcu_node structure's bits remain clear after acquiring parent's lock. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu LKML-Reference: <12532926191947-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree_plugin.h | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index c9616e48379b..5f94619450af 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -206,7 +206,8 @@ static void rcu_read_unlock_special(struct task_struct *t) */ if (!empty && rnp->qsmask == 0 && list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])) { - t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; + struct rcu_node *rnp_p; + if (rnp->parent == NULL) { /* Only one rcu_node in the tree. */ cpu_quiet_msk_finish(&rcu_preempt_state, flags); @@ -215,9 +216,10 @@ static void rcu_read_unlock_special(struct task_struct *t) /* Report up the rest of the hierarchy. */ mask = rnp->grpmask; spin_unlock_irqrestore(&rnp->lock, flags); - rnp = rnp->parent; - spin_lock_irqsave(&rnp->lock, flags); - cpu_quiet_msk(mask, &rcu_preempt_state, rnp, flags); + rnp_p = rnp->parent; + spin_lock_irqsave(&rnp_p->lock, flags); + WARN_ON_ONCE(rnp->qsmask); + cpu_quiet_msk(mask, &rcu_preempt_state, rnp_p, flags); return; } spin_unlock(&rnp->lock); @@ -278,6 +280,7 @@ static void rcu_print_task_stall(struct rcu_node *rnp) static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { WARN_ON_ONCE(!list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])); + WARN_ON_ONCE(rnp->qsmask); } /* @@ -302,7 +305,8 @@ static int rcu_preempted_readers(struct rcu_node *rnp) * The caller must hold rnp->lock with irqs disabled. */ static void rcu_preempt_offline_tasks(struct rcu_state *rsp, - struct rcu_node *rnp) + struct rcu_node *rnp, + struct rcu_data *rdp) { int i; struct list_head *lp; @@ -314,6 +318,9 @@ static void rcu_preempt_offline_tasks(struct rcu_state *rsp, WARN_ONCE(1, "Last CPU thought to be offlined?"); return; /* Shouldn't happen: at least one CPU online. */ } + WARN_ON_ONCE(rnp != rdp->mynode && + (!list_empty(&rnp->blocked_tasks[0]) || + !list_empty(&rnp->blocked_tasks[1]))); /* * Move tasks up to root rcu_node. Rely on the fact that the @@ -489,7 +496,8 @@ static int rcu_preempted_readers(struct rcu_node *rnp) * tasks that were blocked within RCU read-side critical sections. */ static void rcu_preempt_offline_tasks(struct rcu_state *rsp, - struct rcu_node *rnp) + struct rcu_node *rnp, + struct rcu_data *rdp) { } -- cgit v1.2.2 From e7d8842ed34a7fe19d1ed90f84c211fb056ac523 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 18 Sep 2009 09:50:18 -0700 Subject: rcu: Apply results of code inspection of kernel/rcutree_plugin.h o Drop the calls to cpu_quiet() from the online/offline code. These are unnecessary, since force_quiescent_state() will clean up, and removing them simplifies the code a bit. o Add a warning to check that we don't enqueue the same blocked task twice onto the ->blocked_tasks[] lists. o Rework the phase computation in rcu_preempt_note_context_switch() to be more readable, as suggested by Josh Triplett. o Disable irqs to close a race between the scheduling clock interrupt and rcu_preempt_note_context_switch() WRT the ->rcu_read_unlock_special field. o Add comments to rnp->lock acquisition and release within rcu_read_unlock_special() noting that irqs are already disabled. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu LKML-Reference: <12532926201851-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree_plugin.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 5f94619450af..cd6047cc7fc2 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -117,9 +117,9 @@ static void rcu_preempt_note_context_switch(int cpu) * on line! */ WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0); - phase = !(rnp->qsmask & rdp->grpmask) ^ (rnp->gpnum & 0x1); + WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); + phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1; list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]); - smp_mb(); /* Ensure later ctxt swtch seen after above. */ spin_unlock_irqrestore(&rnp->lock, flags); } @@ -133,7 +133,9 @@ static void rcu_preempt_note_context_switch(int cpu) * means that we continue to block the current grace period. */ rcu_preempt_qs(cpu); + local_irq_save(flags); t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; + local_irq_restore(flags); } /* @@ -189,10 +191,10 @@ static void rcu_read_unlock_special(struct task_struct *t) */ for (;;) { rnp = t->rcu_blocked_node; - spin_lock(&rnp->lock); + spin_lock(&rnp->lock); /* irqs already disabled. */ if (rnp == t->rcu_blocked_node) break; - spin_unlock(&rnp->lock); + spin_unlock(&rnp->lock); /* irqs remain disabled. */ } empty = list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]); list_del_init(&t->rcu_node_entry); -- cgit v1.2.2 From 49e291266d0920264471d9d64268fb030e33a99a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 18 Sep 2009 09:50:19 -0700 Subject: rcu: Fix thinko, actually initialize full tree Commit de078d8 ("rcu: Need to update rnp->gpnum if preemptable RCU is to be reliable") repeatedly and incorrectly initializes the root rcu_node structure's ->gpnum field rather than initializing the ->gpnum field of each node in the tree. Fix this. Also add an additional consistency check to catch this in the future. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu LKML-Reference: <125329262011-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree_plugin.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index cd6047cc7fc2..09b7325baad1 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -476,10 +476,12 @@ static void rcu_print_task_stall(struct rcu_node *rnp) /* * Because there is no preemptable RCU, there can be no readers blocked, - * so there is no need to check for blocked tasks. + * so there is no need to check for blocked tasks. So check only for + * bogus qsmask values. */ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { + WARN_ON_ONCE(rnp->qsmask); } /* -- cgit v1.2.2 From a71fca58b7f4abca551ae2256ac08dd9123a03f9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 18 Sep 2009 10:28:19 -0700 Subject: rcu: Fix whitespace inconsistencies Fix a number of whitespace ^Ierrors in the include/linux/rcu* and the kernel/rcu* files. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu LKML-Reference: <20090918172819.GA24405@linux.vnet.ibm.com> [ did more checkpatch fixlets ] Signed-off-by: Ingo Molnar --- kernel/rcutree_plugin.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 09b7325baad1..1cee04f627eb 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -370,9 +370,8 @@ static void rcu_preempt_check_callbacks(int cpu) rcu_preempt_qs(cpu); return; } - if (per_cpu(rcu_preempt_data, cpu).qs_pending) { + if (per_cpu(rcu_preempt_data, cpu).qs_pending) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; - } } /* -- cgit v1.2.2