summaryrefslogtreecommitdiffstats
path: root/kernel/smp.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-10-18 23:34:50 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-18 23:34:50 +0200
commit41eea65e2aaadc0611fd56a1b177ce25dcc4c1df (patch)
tree75a923658e76b40792db00c79ff2f115b07b963a /kernel/smp.c
parentMerge tag 'mailbox-v5.10' of git://git.linaro.org/landing-teams/working/fujit... (diff)
parentMerge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/pau... (diff)
downloadlinux-41eea65e2aaadc0611fd56a1b177ce25dcc4c1df.tar.xz
linux-41eea65e2aaadc0611fd56a1b177ce25dcc4c1df.zip
Merge tag 'core-rcu-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull RCU changes from Ingo Molnar: - Debugging for smp_call_function() - RT raw/non-raw lock ordering fixes - Strict grace periods for KASAN - New smp_call_function() torture test - Torture-test updates - Documentation updates - Miscellaneous fixes [ This doesn't actually pull the tag - I've dropped the last merge from the RCU branch due to questions about the series. - Linus ] * tag 'core-rcu-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (77 commits) smp: Make symbol 'csd_bug_count' static kernel/smp: Provide CSD lock timeout diagnostics smp: Add source and destination CPUs to __call_single_data rcu: Shrink each possible cpu krcp rcu/segcblist: Prevent useless GP start if no CBs to accelerate torture: Add gdb support rcutorture: Allow pointer leaks to test diagnostic code rcutorture: Hoist OOM registry up one level refperf: Avoid null pointer dereference when buf fails to allocate rcutorture: Properly synchronize with OOM notifier rcutorture: Properly set rcu_fwds for OOM handling torture: Add kvm.sh --help and update help message rcutorture: Add CONFIG_PROVE_RCU_LIST to TREE05 torture: Update initrd documentation rcutorture: Replace HTTP links with HTTPS ones locktorture: Make function torture_percpu_rwsem_init() static torture: document --allcpus argument added to the kvm.sh script rcutorture: Output number of elapsed grace periods rcutorture: Remove KCSAN stubs rcu: Remove unused "cpu" parameter from rcu_report_qs_rdp() ...
Diffstat (limited to 'kernel/smp.c')
-rw-r--r--kernel/smp.c134
1 files changed, 134 insertions, 0 deletions
diff --git a/kernel/smp.c b/kernel/smp.c
index d9832a171046..4d17501433be 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -20,6 +20,9 @@
#include <linux/sched.h>
#include <linux/sched/idle.h>
#include <linux/hypervisor.h>
+#include <linux/sched/clock.h>
+#include <linux/nmi.h>
+#include <linux/sched/debug.h>
#include "smpboot.h"
#include "sched/smp.h"
@@ -96,6 +99,103 @@ void __init call_function_init(void)
smpcfd_prepare_cpu(smp_processor_id());
}
+#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
+
+static DEFINE_PER_CPU(call_single_data_t *, cur_csd);
+static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func);
+static DEFINE_PER_CPU(void *, cur_csd_info);
+
+#define CSD_LOCK_TIMEOUT (5ULL * NSEC_PER_SEC)
+static atomic_t csd_bug_count = ATOMIC_INIT(0);
+
+/* Record current CSD work for current CPU, NULL to erase. */
+static void csd_lock_record(call_single_data_t *csd)
+{
+ if (!csd) {
+ smp_mb(); /* NULL cur_csd after unlock. */
+ __this_cpu_write(cur_csd, NULL);
+ return;
+ }
+ __this_cpu_write(cur_csd_func, csd->func);
+ __this_cpu_write(cur_csd_info, csd->info);
+ smp_wmb(); /* func and info before csd. */
+ __this_cpu_write(cur_csd, csd);
+ smp_mb(); /* Update cur_csd before function call. */
+ /* Or before unlock, as the case may be. */
+}
+
+static __always_inline int csd_lock_wait_getcpu(call_single_data_t *csd)
+{
+ unsigned int csd_type;
+
+ csd_type = CSD_TYPE(csd);
+ if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC)
+ return csd->dst; /* Other CSD_TYPE_ values might not have ->dst. */
+ return -1;
+}
+
+/*
+ * Complain if too much time spent waiting. Note that only
+ * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU,
+ * so waiting on other types gets much less information.
+ */
+static __always_inline bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id)
+{
+ int cpu = -1;
+ int cpux;
+ bool firsttime;
+ u64 ts2, ts_delta;
+ call_single_data_t *cpu_cur_csd;
+ unsigned int flags = READ_ONCE(csd->flags);
+
+ if (!(flags & CSD_FLAG_LOCK)) {
+ if (!unlikely(*bug_id))
+ return true;
+ cpu = csd_lock_wait_getcpu(csd);
+ pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n",
+ *bug_id, raw_smp_processor_id(), cpu);
+ return true;
+ }
+
+ ts2 = sched_clock();
+ ts_delta = ts2 - *ts1;
+ if (likely(ts_delta <= CSD_LOCK_TIMEOUT))
+ return false;
+
+ firsttime = !*bug_id;
+ if (firsttime)
+ *bug_id = atomic_inc_return(&csd_bug_count);
+ cpu = csd_lock_wait_getcpu(csd);
+ if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu))
+ cpux = 0;
+ else
+ cpux = cpu;
+ cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */
+ pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n",
+ firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts2 - ts0,
+ cpu, csd->func, csd->info);
+ if (cpu_cur_csd && csd != cpu_cur_csd) {
+ pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n",
+ *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)),
+ READ_ONCE(per_cpu(cur_csd_info, cpux)));
+ } else {
+ pr_alert("\tcsd: CSD lock (#%d) %s.\n",
+ *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request");
+ }
+ if (cpu >= 0) {
+ if (!trigger_single_cpu_backtrace(cpu))
+ dump_cpu_task(cpu);
+ if (!cpu_cur_csd) {
+ pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu);
+ arch_send_call_function_single_ipi(cpu);
+ }
+ }
+ dump_stack();
+ *ts1 = ts2;
+
+ return false;
+}
+
/*
* csd_lock/csd_unlock used to serialize access to per-cpu csd resources
*
@@ -105,8 +205,28 @@ void __init call_function_init(void)
*/
static __always_inline void csd_lock_wait(call_single_data_t *csd)
{
+ int bug_id = 0;
+ u64 ts0, ts1;
+
+ ts1 = ts0 = sched_clock();
+ for (;;) {
+ if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id))
+ break;
+ cpu_relax();
+ }
+ smp_acquire__after_ctrl_dep();
+}
+
+#else
+static void csd_lock_record(call_single_data_t *csd)
+{
+}
+
+static __always_inline void csd_lock_wait(call_single_data_t *csd)
+{
smp_cond_load_acquire(&csd->flags, !(VAL & CSD_FLAG_LOCK));
}
+#endif
static __always_inline void csd_lock(call_single_data_t *csd)
{
@@ -166,9 +286,11 @@ static int generic_exec_single(int cpu, call_single_data_t *csd)
* We can unlock early even for the synchronous on-stack case,
* since we're doing this from the same CPU..
*/
+ csd_lock_record(csd);
csd_unlock(csd);
local_irq_save(flags);
func(info);
+ csd_lock_record(NULL);
local_irq_restore(flags);
return 0;
}
@@ -268,8 +390,10 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
entry = &csd_next->llist;
}
+ csd_lock_record(csd);
func(info);
csd_unlock(csd);
+ csd_lock_record(NULL);
} else {
prev = &csd->llist;
}
@@ -296,8 +420,10 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
smp_call_func_t func = csd->func;
void *info = csd->info;
+ csd_lock_record(csd);
csd_unlock(csd);
func(info);
+ csd_lock_record(NULL);
} else if (type == CSD_TYPE_IRQ_WORK) {
irq_work_single(csd);
}
@@ -375,6 +501,10 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
csd->func = func;
csd->info = info;
+#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
+ csd->src = smp_processor_id();
+ csd->dst = cpu;
+#endif
err = generic_exec_single(cpu, csd);
@@ -540,6 +670,10 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
csd->flags |= CSD_TYPE_SYNC;
csd->func = func;
csd->info = info;
+#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
+ csd->src = smp_processor_id();
+ csd->dst = cpu;
+#endif
if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
}