From 6e16b0f7bae3817ea67f4bef4f84298e880fbf66 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 16 Sep 2021 14:10:47 +0200 Subject: rcu: Move rcu_data.cpu_no_qs.b.exp reset to rcu_export_exp_rdp() On non-preemptible RCU, move clearing of the rcu_data structure's ->cpu_no_qs.b.exp filed to the actual expedited quiescent state report function, matching hw preemptible RCU handles the ->exp_deferred_qs field. This prepares for removing ->exp_deferred_qs in favor of ->cpu_no_qs.b.exp for both preemptible and non-preemptible RCU. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_exp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/rcu/tree_exp.h') diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index f3947c49eee7..6c6eb3220385 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -256,6 +256,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, static void rcu_report_exp_rdp(struct rcu_data *rdp) { WRITE_ONCE(rdp->exp_deferred_qs, false); + WRITE_ONCE(rdp->cpu_no_qs.b.exp, false); rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true); } -- cgit v1.2.3-70-g09d2 From 6120b72e25e195b6fa15b0a674479a38166c392a Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 16 Sep 2021 14:10:48 +0200 Subject: rcu: Remove rcu_data.exp_deferred_qs and convert to rcu_data.cpu no_qs.b.exp Having two fields for the same purpose with subtle differences on different RCU flavours is confusing, especially when both fields always exist on both RCU flavours. Fortunately, it is now safe for preemptible RCU to rely on the rcu_data structure's ->cpu_no_qs.b.exp field, just like non-preemptible RCU. This commit therefore removes the ad-hoc ->exp_deferred_qs field. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.h | 1 - kernel/rcu/tree_exp.h | 5 ++--- kernel/rcu/tree_plugin.h | 12 ++++++------ 3 files changed, 8 insertions(+), 10 deletions(-) (limited to 'kernel/rcu/tree_exp.h') diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 305cf6aeb408..ea46ed40f6bc 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -157,7 +157,6 @@ struct rcu_data { bool core_needs_qs; /* Core waits for quiescent state. */ bool beenonline; /* CPU online at least once. */ bool gpwrap; /* Possible ->gp_seq wrap. */ - bool exp_deferred_qs; /* This CPU awaiting a deferred QS? */ bool cpu_started; /* RCU watching this onlining CPU. */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 6c6eb3220385..fc2ee326a6f7 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -255,7 +255,6 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, */ static void rcu_report_exp_rdp(struct rcu_data *rdp) { - WRITE_ONCE(rdp->exp_deferred_qs, false); WRITE_ONCE(rdp->cpu_no_qs.b.exp, false); rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true); } @@ -656,7 +655,7 @@ static void rcu_exp_handler(void *unused) rcu_dynticks_curr_cpu_in_eqs()) { rcu_report_exp_rdp(rdp); } else { - rdp->exp_deferred_qs = true; + WRITE_ONCE(rdp->cpu_no_qs.b.exp, true); set_tsk_need_resched(t); set_preempt_need_resched(); } @@ -678,7 +677,7 @@ static void rcu_exp_handler(void *unused) if (depth > 0) { raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->expmask & rdp->grpmask) { - rdp->exp_deferred_qs = true; + WRITE_ONCE(rdp->cpu_no_qs.b.exp, true); t->rcu_read_unlock_special.b.exp_hint = true; } raw_spin_unlock_irqrestore_rcu_node(rnp, flags); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 6d58b75d2782..e1a9fb96e0b9 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -260,10 +260,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * no need to check for a subsequent expedited GP. (Though we are * still in a quiescent state in any case.) */ - if (blkd_state & RCU_EXP_BLKD && rdp->exp_deferred_qs) + if (blkd_state & RCU_EXP_BLKD && rdp->cpu_no_qs.b.exp) rcu_report_exp_rdp(rdp); else - WARN_ON_ONCE(rdp->exp_deferred_qs); + WARN_ON_ONCE(rdp->cpu_no_qs.b.exp); } /* @@ -354,7 +354,7 @@ void rcu_note_context_switch(bool preempt) * means that we continue to block the current grace period. */ rcu_qs(); - if (rdp->exp_deferred_qs) + if (rdp->cpu_no_qs.b.exp) rcu_report_exp_rdp(rdp); rcu_tasks_qs(current, preempt); trace_rcu_utilization(TPS("End context switch")); @@ -481,7 +481,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) */ special = t->rcu_read_unlock_special; rdp = this_cpu_ptr(&rcu_data); - if (!special.s && !rdp->exp_deferred_qs) { + if (!special.s && !rdp->cpu_no_qs.b.exp) { local_irq_restore(flags); return; } @@ -501,7 +501,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) * tasks are handled when removing the task from the * blocked-tasks list below. */ - if (rdp->exp_deferred_qs) + if (rdp->cpu_no_qs.b.exp) rcu_report_exp_rdp(rdp); /* Clean up if blocked during RCU read-side critical section. */ @@ -584,7 +584,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) */ static bool rcu_preempt_need_deferred_qs(struct task_struct *t) { - return (__this_cpu_read(rcu_data.exp_deferred_qs) || + return (__this_cpu_read(rcu_data.cpu_no_qs.b.exp) || READ_ONCE(t->rcu_read_unlock_special.s)) && rcu_preempt_depth() == 0; } -- cgit v1.2.3-70-g09d2 From 5401cc5264fff75aea10cf44b380b265d18d17ba Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 28 Sep 2021 11:06:35 -0700 Subject: rcu: Mark sync_sched_exp_online_cleanup() ->cpu_no_qs.b.exp load The sync_sched_exp_online_cleanup() is called from rcutree_online_cpu(), which can be invoked with interrupts enabled. This means that the ->cpu_no_qs.b.exp field is subject to data races from the rcu_exp_handler() IPI handler, so this commit marks the load from that field. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_exp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/rcu/tree_exp.h') diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index fc2ee326a6f7..12f1a18d7b6d 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -759,7 +759,7 @@ static void sync_sched_exp_online_cleanup(int cpu) my_cpu = get_cpu(); /* Quiescent state either not needed or already requested, leave. */ if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) || - rdp->cpu_no_qs.b.exp) { + READ_ONCE(rdp->cpu_no_qs.b.exp)) { put_cpu(); return; } -- cgit v1.2.3-70-g09d2 From 147f04b14adde831eb4a0a1e378667429732f9e8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 29 Sep 2021 09:21:34 -0700 Subject: rcu: Prevent expedited GP from enabling tick on offline CPU If an RCU expedited grace period starts just when a CPU is in the process of going offline, so that the outgoing CPU has completed its pass through stop-machine but has not yet completed its final dive into the idle loop, RCU will attempt to enable that CPU's scheduling-clock tick via a call to tick_dep_set_cpu(). For this to happen, that CPU has to have been online when the expedited grace period completed its CPU-selection phase. This is pointless: The outgoing CPU has interrupts disabled, so it cannot take a scheduling-clock tick anyway. In addition, the tick_dep_set_cpu() function's eventual call to irq_work_queue_on() will splat as follows: smpboot: CPU 1 is now offline WARNING: CPU: 6 PID: 124 at kernel/irq_work.c:95 +irq_work_queue_on+0x57/0x60 Modules linked in: CPU: 6 PID: 124 Comm: kworker/6:2 Not tainted 5.15.0-rc1+ #3 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS +rel-1.14.0-0-g155821a-rebuilt.opensuse.org 04/01/2014 Workqueue: rcu_gp wait_rcu_exp_gp RIP: 0010:irq_work_queue_on+0x57/0x60 Code: 8b 05 1d c7 ea 62 a9 00 00 f0 00 75 21 4c 89 ce 44 89 c7 e8 +9b 37 fa ff ba 01 00 00 00 89 d0 c3 4c 89 cf e8 3b ff ff ff eb ee <0f> 0b eb b7 +0f 0b eb db 90 48 c7 c0 98 2a 02 00 65 48 03 05 91 6f RSP: 0000:ffffb12cc038fe48 EFLAGS: 00010282 RAX: 0000000000000001 RBX: 0000000000005208 RCX: 0000000000000020 RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff9ad01f45a680 RBP: 000000000004c990 R08: 0000000000000001 R09: ffff9ad01f45a680 R10: ffffb12cc0317db0 R11: 0000000000000001 R12: 00000000fffecee8 R13: 0000000000000001 R14: 0000000000026980 R15: ffffffff9e53ae00 FS: 0000000000000000(0000) GS:ffff9ad01f580000(0000) +knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000000de0c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tick_nohz_dep_set_cpu+0x59/0x70 rcu_exp_wait_wake+0x54e/0x870 ? sync_rcu_exp_select_cpus+0x1fc/0x390 process_one_work+0x1ef/0x3c0 ? process_one_work+0x3c0/0x3c0 worker_thread+0x28/0x3c0 ? process_one_work+0x3c0/0x3c0 kthread+0x115/0x140 ? set_kthread_struct+0x40/0x40 ret_from_fork+0x22/0x30 ---[ end trace c5bf75eb6aa80bc6 ]--- This commit therefore avoids invoking tick_dep_set_cpu() on offlined CPUs to limit both futility and false-positive splats. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_exp.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/rcu/tree_exp.h') diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 12f1a18d7b6d..a96d17206d87 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -506,7 +506,10 @@ static void synchronize_rcu_expedited_wait(void) if (rdp->rcu_forced_tick_exp) continue; rdp->rcu_forced_tick_exp = true; - tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP); + preempt_disable(); + if (cpu_online(cpu)) + tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP); + preempt_enable(); } } j = READ_ONCE(jiffies_till_first_fqs); -- cgit v1.2.3-70-g09d2 From 81f6d49cce2d2fe507e3fddcc4a6db021d9c2e7b Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 30 Nov 2021 17:21:08 +0100 Subject: rcu/exp: Mark current CPU as exp-QS in IPI loop second pass Expedited RCU grace periods invoke sync_rcu_exp_select_node_cpus(), which takes two passes over the leaf rcu_node structure's CPUs. The first pass gathers up the current CPU and CPUs that are in dynticks idle mode. The workqueue will report a quiescent state on their behalf later. The second pass sends IPIs to the rest of the CPUs, but excludes the current CPU, incorrectly assuming it has been included in the first pass's list of CPUs. Unfortunately the current CPU may have changed between the first and second pass, due to the fact that the various rcu_node structures' ->lock fields have been dropped, thus momentarily enabling preemption. This means that if the second pass's CPU was not on the first pass's list, it will be ignored completely. There will be no IPI sent to it, and there will be no reporting of quiescent states on its behalf. Unfortunately, the expedited grace period will nevertheless be waiting for that CPU to report a quiescent state, but with that CPU having no reason to believe that such a report is needed. The result will be an expedited grace period stall. Fix this by no longer excluding the current CPU from consideration during the second pass. Fixes: b9ad4d6ed18e ("rcu: Avoid self-IPI in sync_rcu_exp_select_node_cpus()") Reviewed-by: Neeraj Upadhyay Signed-off-by: Frederic Weisbecker Cc: Uladzislau Rezki Cc: Neeraj Upadhyay Cc: Boqun Feng Cc: Josh Triplett Cc: Joel Fernandes Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_exp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/rcu/tree_exp.h') diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index a96d17206d87..237a79989aba 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -387,6 +387,7 @@ retry_ipi: continue; } if (get_cpu() == cpu) { + mask_ofl_test |= mask; put_cpu(); continue; } -- cgit v1.2.3-70-g09d2