From d7e29933969e5ca7c112ce1368a07911f4485dc2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 27 Oct 2014 09:15:54 -0700 Subject: rcu: Make rcu_barrier() understand about missing rcuo kthreads Commit 35ce7f29a44a (rcu: Create rcuo kthreads only for onlined CPUs) avoids creating rcuo kthreads for CPUs that never come online. This fixes a bug in many instances of firmware: Instead of lying about their age, these systems instead lie about the number of CPUs that they have. Before commit 35ce7f29a44a, this could result in huge numbers of useless rcuo kthreads being created. It appears that experience indicates that I should have told the people suffering from this problem to fix their broken firmware, but I instead produced what turned out to be a partial fix. The missing piece supplied by this commit makes sure that rcu_barrier() knows not to post callbacks for no-CBs CPUs that have not yet come online, because otherwise rcu_barrier() will hang on systems having firmware that lies about the number of CPUs. It is tempting to simply have rcu_barrier() refuse to post a callback on any no-CBs CPU that does not have an rcuo kthread. This unfortunately does not work because rcu_barrier() is required to wait for all pending callbacks. It is therefore required to wait even for those callbacks that cannot possibly be invoked. Even if doing so hangs the system. Given that posting a callback to a no-CBs CPU that does not yet have an rcuo kthread can hang rcu_barrier(), It is tempting to report an error in this case. Unfortunately, this will result in false positives at boot time, when it is perfectly legal to post callbacks to the boot CPU before the scheduler has started, in other words, before it is legal to invoke rcu_barrier(). So this commit instead has rcu_barrier() avoid posting callbacks to CPUs having neither rcuo kthread nor pending callbacks, and has it complain bitterly if it finds CPUs having no rcuo kthread but some pending callbacks. And when rcu_barrier() does find CPUs having no rcuo kthread but pending callbacks, as noted earlier, it has no choice but to hang indefinitely. Reported-by: Yanko Kaneti Reported-by: Jay Vosburgh Reported-by: Meelis Roos Reported-by: Eric B Munson Signed-off-by: Paul E. McKenney Tested-by: Eric B Munson Tested-by: Jay Vosburgh Tested-by: Yanko Kaneti Tested-by: Kevin Fenzi Tested-by: Meelis Roos --- kernel/rcu/tree.c | 15 ++++++++++----- kernel/rcu/tree.h | 1 + kernel/rcu/tree_plugin.h | 33 +++++++++++++++++++++++++++++++++ 3 files changed, 44 insertions(+), 5 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 133e47223095..9815447d22e0 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3299,11 +3299,16 @@ static void _rcu_barrier(struct rcu_state *rsp) continue; rdp = per_cpu_ptr(rsp->rda, cpu); if (rcu_is_nocb_cpu(cpu)) { - _rcu_barrier_trace(rsp, "OnlineNoCB", cpu, - rsp->n_barrier_done); - atomic_inc(&rsp->barrier_cpu_count); - __call_rcu(&rdp->barrier_head, rcu_barrier_callback, - rsp, cpu, 0); + if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) { + _rcu_barrier_trace(rsp, "OfflineNoCB", cpu, + rsp->n_barrier_done); + } else { + _rcu_barrier_trace(rsp, "OnlineNoCB", cpu, + rsp->n_barrier_done); + atomic_inc(&rsp->barrier_cpu_count); + __call_rcu(&rdp->barrier_head, + rcu_barrier_callback, rsp, cpu, 0); + } } else if (ACCESS_ONCE(rdp->qlen)) { _rcu_barrier_trace(rsp, "OnlineQ", cpu, rsp->n_barrier_done); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index d03764652d91..bbdc45d8d74f 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -587,6 +587,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu); static void print_cpu_stall_info_end(void); static void zero_cpu_stall_ticks(struct rcu_data *rdp); static void increment_cpu_stall_ticks(void); +static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); static void rcu_init_one_nocb(struct rcu_node *rnp); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 387dd4599344..c1d7f27bd38f 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2049,6 +2049,33 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) } } +/* + * Does the specified CPU need an RCU callback for the specified flavor + * of rcu_barrier()? + */ +static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_head *rhp; + + /* No-CBs CPUs might have callbacks on any of three lists. */ + rhp = ACCESS_ONCE(rdp->nocb_head); + if (!rhp) + rhp = ACCESS_ONCE(rdp->nocb_gp_head); + if (!rhp) + rhp = ACCESS_ONCE(rdp->nocb_follower_head); + + /* Having no rcuo kthread but CBs after scheduler starts is bad! */ + if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp) { + /* RCU callback enqueued before CPU first came online??? */ + pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n", + cpu, rhp->func); + WARN_ON_ONCE(1); + } + + return !!rhp; +} + /* * Enqueue the specified string of rcu_head structures onto the specified * CPU's no-CBs lists. The CPU is specified by rdp, the head of the @@ -2642,6 +2669,12 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) #else /* #ifdef CONFIG_RCU_NOCB_CPU */ +static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) +{ + WARN_ON_ONCE(1); /* Should be dead code. */ + return false; +} + static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { } -- cgit v1.2.3