diff options
29 files changed, 501 insertions, 256 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 5ae8608ca9f5..0a104be4ad86 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2881,6 +2881,24 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Lazy RCU callbacks are those which RCU can prove do nothing more than free memory. + rcutorture.cbflood_inter_holdoff= [KNL] + Set holdoff time (jiffies) between successive + callback-flood tests. + + rcutorture.cbflood_intra_holdoff= [KNL] + Set holdoff time (jiffies) between successive + bursts of callbacks within a given callback-flood + test. + + rcutorture.cbflood_n_burst= [KNL] + Set the number of bursts making up a given + callback-flood test. Set this to zero to + disable callback-flood testing. + + rcutorture.cbflood_n_per_burst= [KNL] + Set the number of callbacks to be registered + in a given burst of a callback-flood test. + rcutorture.fqs_duration= [KNL] Set duration of force_quiescent_state bursts. diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index a4de88fb55f0..22a969cdd476 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -574,30 +574,14 @@ However, stores are not speculated. This means that ordering -is- provided in the following example: q = ACCESS_ONCE(a); - if (ACCESS_ONCE(q)) { - ACCESS_ONCE(b) = p; - } - -Please note that ACCESS_ONCE() is not optional! Without the ACCESS_ONCE(), -the compiler is within its rights to transform this example: - - q = a; if (q) { - b = p; /* BUG: Compiler can reorder!!! */ - do_something(); - } else { - b = p; /* BUG: Compiler can reorder!!! */ - do_something_else(); + ACCESS_ONCE(b) = p; } -into this, which of course defeats the ordering: - - b = p; - q = a; - if (q) - do_something(); - else - do_something_else(); +Please note that ACCESS_ONCE() is not optional! Without the +ACCESS_ONCE(), might combine the load from 'a' with other loads from +'a', and the store to 'b' with other stores to 'b', with possible highly +counterintuitive effects on ordering. Worse yet, if the compiler is able to prove (say) that the value of variable 'a' is always non-zero, it would be well within its rights @@ -605,11 +589,12 @@ to optimize the original example by eliminating the "if" statement as follows: q = a; - b = p; /* BUG: Compiler can reorder!!! */ - do_something(); + b = p; /* BUG: Compiler and CPU can both reorder!!! */ + +So don't leave out the ACCESS_ONCE(). -The solution is again ACCESS_ONCE() and barrier(), which preserves the -ordering between the load from variable 'a' and the store to variable 'b': +It is tempting to try to enforce ordering on identical stores on both +branches of the "if" statement as follows: q = ACCESS_ONCE(a); if (q) { @@ -622,18 +607,11 @@ ordering between the load from variable 'a' and the store to variable 'b': do_something_else(); } -The initial ACCESS_ONCE() is required to prevent the compiler from -proving the value of 'a', and the pair of barrier() invocations are -required to prevent the compiler from pulling the two identical stores -to 'b' out from the legs of the "if" statement. - -It is important to note that control dependencies absolutely require a -a conditional. For example, the following "optimized" version of -the above example breaks ordering, which is why the barrier() invocations -are absolutely required if you have identical stores in both legs of -the "if" statement: +Unfortunately, current compilers will transform this as follows at high +optimization levels: q = ACCESS_ONCE(a); + barrier(); ACCESS_ONCE(b) = p; /* BUG: No ordering vs. load from a!!! */ if (q) { /* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */ @@ -643,21 +621,36 @@ the "if" statement: do_something_else(); } -It is of course legal for the prior load to be part of the conditional, -for example, as follows: +Now there is no conditional between the load from 'a' and the store to +'b', which means that the CPU is within its rights to reorder them: +The conditional is absolutely required, and must be present in the +assembly code even after all compiler optimizations have been applied. +Therefore, if you need ordering in this example, you need explicit +memory barriers, for example, smp_store_release(): - if (ACCESS_ONCE(a) > 0) { - barrier(); - ACCESS_ONCE(b) = q / 2; + q = ACCESS_ONCE(a); + if (q) { + smp_store_release(&b, p); do_something(); } else { - barrier(); - ACCESS_ONCE(b) = q / 3; + smp_store_release(&b, p); + do_something_else(); + } + +In contrast, without explicit memory barriers, two-legged-if control +ordering is guaranteed only when the stores differ, for example: + + q = ACCESS_ONCE(a); + if (q) { + ACCESS_ONCE(b) = p; + do_something(); + } else { + ACCESS_ONCE(b) = r; do_something_else(); } -This will again ensure that the load from variable 'a' is ordered before the -stores to variable 'b'. +The initial ACCESS_ONCE() is still required to prevent the compiler from +proving the value of 'a'. In addition, you need to be careful what you do with the local variable 'q', otherwise the compiler might be able to guess the value and again remove @@ -665,12 +658,10 @@ the needed conditional. For example: q = ACCESS_ONCE(a); if (q % MAX) { - barrier(); ACCESS_ONCE(b) = p; do_something(); } else { - barrier(); - ACCESS_ONCE(b) = p; + ACCESS_ONCE(b) = r; do_something_else(); } @@ -682,9 +673,12 @@ transform the above code into the following: ACCESS_ONCE(b) = p; do_something_else(); -This transformation loses the ordering between the load from variable 'a' -and the store to variable 'b'. If you are relying on this ordering, you -should do something like the following: +Given this transformation, the CPU is not required to respect the ordering +between the load from variable 'a' and the store to variable 'b'. It is +tempting to add a barrier(), but this does not help. The conditional +is gone, and the barrier won't bring it back. Therefore, if you are +relying on this ordering, you should make sure that MAX is greater than +one, perhaps as follows: q = ACCESS_ONCE(a); BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */ @@ -692,35 +686,45 @@ should do something like the following: ACCESS_ONCE(b) = p; do_something(); } else { - ACCESS_ONCE(b) = p; + ACCESS_ONCE(b) = r; do_something_else(); } +Please note once again that the stores to 'b' differ. If they were +identical, as noted earlier, the compiler could pull this store outside +of the 'if' statement. + Finally, control dependencies do -not- provide transitivity. This is -demonstrated by two related examples: +demonstrated by two related examples, with the initial values of +x and y both being zero: CPU 0 CPU 1 ===================== ===================== r1 = ACCESS_ONCE(x); r2 = ACCESS_ONCE(y); - if (r1 >= 0) if (r2 >= 0) + if (r1 > 0) if (r2 > 0) ACCESS_ONCE(y) = 1; ACCESS_ONCE(x) = 1; assert(!(r1 == 1 && r2 == 1)); The above two-CPU example will never trigger the assert(). However, if control dependencies guaranteed transitivity (which they do not), -then adding the following two CPUs would guarantee a related assertion: +then adding the following CPU would guarantee a related assertion: - CPU 2 CPU 3 - ===================== ===================== - ACCESS_ONCE(x) = 2; ACCESS_ONCE(y) = 2; + CPU 2 + ===================== + ACCESS_ONCE(x) = 2; + + assert(!(r1 == 2 && r2 == 1 && x == 2)); /* FAILS!!! */ - assert(!(r1 == 2 && r2 == 2 && x == 1 && y == 1)); /* FAILS!!! */ +But because control dependencies do -not- provide transitivity, the above +assertion can fail after the combined three-CPU example completes. If you +need the three-CPU example to provide ordering, you will need smp_mb() +between the loads and stores in the CPU 0 and CPU 1 code fragments, +that is, just before or just after the "if" statements. -But because control dependencies do -not- provide transitivity, the -above assertion can fail after the combined four-CPU example completes. -If you need the four-CPU example to provide ordering, you will need -smp_mb() between the loads and stores in the CPU 0 and CPU 1 code fragments. +These two examples are the LB and WWC litmus tests from this paper: +http://www.cl.cam.ac.uk/users/pes20/ppc-supplemental/test6.pdf and this +site: https://www.cl.cam.ac.uk/~pes20/ppcmem/index.html. In summary: diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 321ed0d4e675..334ff89aada0 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -269,6 +269,14 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* CONFIG_RCU_USER_QS */ +#ifdef CONFIG_RCU_NOCB_CPU +void rcu_init_nohz(void); +#else /* #ifdef CONFIG_RCU_NOCB_CPU */ +static inline void rcu_init_nohz(void) +{ +} +#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ + /** * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers * @a: Code that RCU needs to pay attention to. diff --git a/include/linux/torture.h b/include/linux/torture.h index 5ca58fcbaf1b..fec46f8c08eb 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -51,7 +51,7 @@ /* Definitions for online/offline exerciser. */ int torture_onoff_init(long ooholdoff, long oointerval); -char *torture_onoff_stats(char *page); +void torture_onoff_stats(void); bool torture_onoff_failures(void); /* Low-rider random number generator. */ diff --git a/init/Kconfig b/init/Kconfig index e84c6423a2e5..64ee4d967786 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -737,7 +737,7 @@ choice config RCU_NOCB_CPU_NONE bool "No build_forced no-CBs CPUs" - depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL + depends on RCU_NOCB_CPU help This option does not force any of the CPUs to be no-CBs CPUs. Only CPUs designated by the rcu_nocbs= boot parameter will be @@ -751,7 +751,7 @@ config RCU_NOCB_CPU_NONE config RCU_NOCB_CPU_ZERO bool "CPU 0 is a build_forced no-CBs CPU" - depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL + depends on RCU_NOCB_CPU help This option forces CPU 0 to be a no-CBs CPU, so that its RCU callbacks are invoked by a per-CPU kthread whose name begins diff --git a/init/main.c b/init/main.c index bb1aed928f21..e3c4cdd94d5b 100644 --- a/init/main.c +++ b/init/main.c @@ -578,6 +578,7 @@ asmlinkage __visible void __init start_kernel(void) idr_init_cache(); rcu_init(); tick_nohz_init(); + rcu_init_nohz(); context_tracking_init(); radix_tree_init(); /* init some links before init_ISA_irqs() */ diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 948a7693748e..0bcd53adac73 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -49,11 +49,19 @@ #include <linux/trace_clock.h> #include <asm/byteorder.h> #include <linux/torture.h> +#include <linux/vmalloc.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>"); +torture_param(int, cbflood_inter_holdoff, HZ, + "Holdoff between floods (jiffies)"); +torture_param(int, cbflood_intra_holdoff, 1, + "Holdoff between bursts (jiffies)"); +torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable"); +torture_param(int, cbflood_n_per_burst, 20000, + "# callbacks per burst in flood"); torture_param(int, fqs_duration, 0, "Duration of fqs bursts (us), 0 to disable"); torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)"); @@ -96,10 +104,12 @@ module_param(torture_type, charp, 0444); MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)"); static int nrealreaders; +static int ncbflooders; static struct task_struct *writer_task; static struct task_struct **fakewriter_tasks; static struct task_struct **reader_tasks; static struct task_struct *stats_task; +static struct task_struct **cbflood_task; static struct task_struct *fqs_task; static struct task_struct *boost_tasks[NR_CPUS]; static struct task_struct *stall_task; @@ -138,6 +148,7 @@ static long n_rcu_torture_boosts; static long n_rcu_torture_timers; static long n_barrier_attempts; static long n_barrier_successes; +static atomic_long_t n_cbfloods; static struct list_head rcu_torture_removed; static int rcu_torture_writer_state; @@ -182,7 +193,7 @@ static u64 notrace rcu_trace_clock_local(void) #endif /* #else #ifdef CONFIG_RCU_TRACE */ static unsigned long boost_starttime; /* jiffies of next boost test start. */ -DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ +static DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */ static bool barrier_phase; /* Test phase. */ @@ -242,7 +253,7 @@ struct rcu_torture_ops { void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); void (*cb_barrier)(void); void (*fqs)(void); - void (*stats)(char *page); + void (*stats)(void); int irq_capable; int can_boost; const char *name; @@ -525,21 +536,21 @@ static void srcu_torture_barrier(void) srcu_barrier(&srcu_ctl); } -static void srcu_torture_stats(char *page) +static void srcu_torture_stats(void) { int cpu; int idx = srcu_ctl.completed & 0x1; - page += sprintf(page, "%s%s per-CPU(idx=%d):", - torture_type, TORTURE_FLAG, idx); + pr_alert("%s%s per-CPU(idx=%d):", + torture_type, TORTURE_FLAG, idx); for_each_possible_cpu(cpu) { long c0, c1; c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx]; c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]; - page += sprintf(page, " %d(%ld,%ld)", cpu, c0, c1); + pr_cont(" %d(%ld,%ld)", cpu, c0, c1); } - sprintf(page, "\n"); + pr_cont("\n"); } static void srcu_torture_synchronize_expedited(void) @@ -707,6 +718,58 @@ checkwait: stutter_wait("rcu_torture_boost"); return 0; } +static void rcu_torture_cbflood_cb(struct rcu_head *rhp) +{ +} + +/* + * RCU torture callback-flood kthread. Repeatedly induces bursts of calls + * to call_rcu() or analogous, increasing the probability of occurrence + * of callback-overflow corner cases. + */ +static int +rcu_torture_cbflood(void *arg) +{ + int err = 1; + int i; + int j; + struct rcu_head *rhp; + + if (cbflood_n_per_burst > 0 && + cbflood_inter_holdoff > 0 && + cbflood_intra_holdoff > 0 && + cur_ops->call && + cur_ops->cb_barrier) { + rhp = vmalloc(sizeof(*rhp) * + cbflood_n_burst * cbflood_n_per_burst); + err = !rhp; + } + if (err) { + VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM"); + while (!torture_must_stop()) + schedule_timeout_interruptible(HZ); + return 0; + } + VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started"); + do { + schedule_timeout_interruptible(cbflood_inter_holdoff); + atomic_long_inc(&n_cbfloods); + WARN_ON(signal_pending(current)); + for (i = 0; i < cbflood_n_burst; i++) { + for (j = 0; j < cbflood_n_per_burst; j++) { + cur_ops->call(&rhp[i * cbflood_n_per_burst + j], + rcu_torture_cbflood_cb); + } + schedule_timeout_interruptible(cbflood_intra_holdoff); + WARN_ON(signal_pending(current)); + } + cur_ops->cb_barrier(); + stutter_wait("rcu_torture_cbflood"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_cbflood"); + return 0; +} + /* * RCU torture force-quiescent-state kthread. Repeatedly induces * bursts of calls to force_quiescent_state(), increasing the probability @@ -1031,10 +1094,15 @@ rcu_torture_reader(void *arg) } /* - * Create an RCU-torture statistics message in the specified buffer. + * Print torture statistics. Caller must ensure that there is only + * one call to this function at a given time!!! This is normally + * accomplished by relying on the module system to only have one copy + * of the module loaded, and then by giving the rcu_torture_stats + * kthread full control (or the init/cleanup functions when rcu_torture_stats + * thread is not running). */ static void -rcu_torture_printk(char *page) +rcu_torture_stats_print(void) { int cpu; int i; @@ -1052,55 +1120,61 @@ rcu_torture_printk(char *page) if (pipesummary[i] != 0) break; } - page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG); - page += sprintf(page, - "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", - rcu_torture_current, - rcu_torture_current_version, - list_empty(&rcu_torture_freelist), - atomic_read(&n_rcu_torture_alloc), - atomic_read(&n_rcu_torture_alloc_fail), - atomic_read(&n_rcu_torture_free)); - page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ", - atomic_read(&n_rcu_torture_mberror), - n_rcu_torture_boost_ktrerror, - n_rcu_torture_boost_rterror); - page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ", - n_rcu_torture_boost_failure, - n_rcu_torture_boosts, - n_rcu_torture_timers); - page = torture_onoff_stats(page); - page += sprintf(page, "barrier: %ld/%ld:%ld", - n_barrier_successes, - n_barrier_attempts, - n_rcu_torture_barrier_error); - page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", + rcu_torture_current, + rcu_torture_current_version, + list_empty(&rcu_torture_freelist), + atomic_read(&n_rcu_torture_alloc), + atomic_read(&n_rcu_torture_alloc_fail), + atomic_read(&n_rcu_torture_free)); + pr_cont("rtmbe: %d rtbke: %ld rtbre: %ld ", + atomic_read(&n_rcu_torture_mberror), + n_rcu_torture_boost_ktrerror, + n_rcu_torture_boost_rterror); + pr_cont("rtbf: %ld rtb: %ld nt: %ld ", + n_rcu_torture_boost_failure, + n_rcu_torture_boosts, + n_rcu_torture_timers); + torture_onoff_stats(); + pr_cont("barrier: %ld/%ld:%ld ", + n_barrier_successes, + n_barrier_attempts, + n_rcu_torture_barrier_error); + pr_cont("cbflood: %ld\n", atomic_long_read(&n_cbfloods)); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); if (atomic_read(&n_rcu_torture_mberror) != 0 || n_rcu_torture_barrier_error != 0 || n_rcu_torture_boost_ktrerror != 0 || n_rcu_torture_boost_rterror != 0 || n_rcu_torture_boost_failure != 0 || i > 1) { - page += sprintf(page, "!!! "); + pr_cont("%s", "!!! "); atomic_inc(&n_rcu_torture_error); WARN_ON_ONCE(1); } - page += sprintf(page, "Reader Pipe: "); + pr_cont("Reader Pipe: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) - page += sprintf(page, " %ld", pipesummary[i]); - page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG); - page += sprintf(page, "Reader Batch: "); + pr_cont(" %ld", pipesummary[i]); + pr_cont("\n"); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("Reader Batch: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) - page += sprintf(page, " %ld", batchsummary[i]); - page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG); - page += sprintf(page, "Free-Block Circulation: "); + pr_cont(" %ld", batchsummary[i]); + pr_cont("\n"); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("Free-Block Circulation: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) { - page += sprintf(page, " %d", - atomic_read(&rcu_torture_wcount[i])); + pr_cont(" %d", atomic_read(&rcu_torture_wcount[i])); } - page += sprintf(page, "\n"); + pr_cont("\n"); + if (cur_ops->stats) - cur_ops->stats(page); + cur_ops->stats(); if (rtcv_snap == rcu_torture_current_version && rcu_torture_current != NULL) { int __maybe_unused flags; @@ -1109,10 +1183,9 @@ rcu_torture_printk(char *page) rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed); - page += sprintf(page, - "??? Writer stall state %d g%lu c%lu f%#x\n", - rcu_torture_writer_state, - gpnum, completed, flags); + pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n", + rcu_torture_writer_state, + gpnum, completed, flags); show_rcu_gp_kthreads(); rcutorture_trace_dump(); } @@ -1120,30 +1193,6 @@ rcu_torture_printk(char *page) } /* - * Print torture statistics. Caller must ensure that there is only - * one call to this function at a given time!!! This is normally - * accomplished by relying on the module system to only have one copy - * of the module loaded, and then by giving the rcu_torture_stats - * kthread full control (or the init/cleanup functions when rcu_torture_stats - * thread is not running). - */ -static void -rcu_torture_stats_print(void) -{ - int size = nr_cpu_ids * 200 + 8192; - char *buf; - - buf = kmalloc(size, GFP_KERNEL); - if (!buf) { - pr_err("rcu-torture: Out of memory, need: %d", size); - return; - } - rcu_torture_printk(buf); - pr_alert("%s", buf); - kfree(buf); -} - -/* * Periodically prints torture statistics, if periodic statistics printing * was specified via the stat_interval module parameter. */ @@ -1447,6 +1496,8 @@ rcu_torture_cleanup(void) torture_stop_kthread(rcu_torture_stats, stats_task); torture_stop_kthread(rcu_torture_fqs, fqs_task); + for (i = 0; i < ncbflooders; i++) + torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]); if ((test_boost == 1 && cur_ops->can_boost) || test_boost == 2) { unregister_cpu_notifier(&rcutorture_cpu_nb); @@ -1693,6 +1744,24 @@ rcu_torture_init(void) goto unwind; if (object_debug) rcu_test_debug_objects(); + if (cbflood_n_burst > 0) { + /* Create the cbflood threads */ + ncbflooders = (num_online_cpus() + 3) / 4; + cbflood_task = kcalloc(ncbflooders, sizeof(*cbflood_task), + GFP_KERNEL); + if (!cbflood_task) { + VERBOSE_TOROUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < ncbflooders; i++) { + firsterr = torture_create_kthread(rcu_torture_cbflood, + NULL, + cbflood_task[i]); + if (firsterr) + goto unwind; + } + } rcutorture_record_test_transition(); torture_init_end(); return 0; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3e002c1cb441..be0d0a1b7129 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3451,6 +3451,7 @@ static int rcu_cpu_notify(struct notifier_block *self, case CPU_UP_PREPARE_FROZEN: rcu_prepare_cpu(cpu); rcu_prepare_kthreads(cpu); + rcu_spawn_all_nocb_kthreads(cpu); break; case CPU_ONLINE: case CPU_DOWN_FAILED: @@ -3498,7 +3499,7 @@ static int rcu_pm_notify(struct notifier_block *self, } /* - * Spawn the kthread that handles this RCU flavor's grace periods. + * Spawn the kthreads that handle each RCU flavor's grace periods. */ static int __init rcu_spawn_gp_kthread(void) { @@ -3507,6 +3508,7 @@ static int __init rcu_spawn_gp_kthread(void) struct rcu_state *rsp; struct task_struct *t; + rcu_scheduler_fully_active = 1; for_each_rcu_flavor(rsp) { t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name); BUG_ON(IS_ERR(t)); @@ -3514,8 +3516,9 @@ static int __init rcu_spawn_gp_kthread(void) raw_spin_lock_irqsave(&rnp->lock, flags); rsp->gp_kthread = t; raw_spin_unlock_irqrestore(&rnp->lock, flags); - rcu_spawn_nocb_kthreads(rsp); } + rcu_spawn_nocb_kthreads(); + rcu_spawn_boost_kthreads(); return 0; } early_initcall(rcu_spawn_gp_kthread); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index e33562f2a655..ffedcb9d42dc 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -577,6 +577,7 @@ static void rcu_preempt_do_callbacks(void); static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_BOOST */ +static void __init rcu_spawn_boost_kthreads(void); static void rcu_prepare_kthreads(int cpu); static void rcu_cleanup_after_idle(int cpu); static void rcu_prepare_for_idle(int cpu); @@ -597,7 +598,11 @@ static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp); static void do_nocb_deferred_wakeup(struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); -static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp); +static void rcu_spawn_all_nocb_kthreads(int cpu); +static void __init rcu_spawn_nocb_kthreads(void); +#ifdef CONFIG_RCU_NOCB_CPU +static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ static void __maybe_unused rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index bbb0a0cd091b..59318ea32bc8 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -85,33 +85,6 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); -#ifdef CONFIG_RCU_NOCB_CPU -#ifndef CONFIG_RCU_NOCB_CPU_NONE - if (!have_rcu_nocb_mask) { - zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL); - have_rcu_nocb_mask = true; - } -#ifdef CONFIG_RCU_NOCB_CPU_ZERO - pr_info("\tOffload RCU callbacks from CPU 0\n"); - cpumask_set_cpu(0, rcu_nocb_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ -#ifdef CONFIG_RCU_NOCB_CPU_ALL - pr_info("\tOffload RCU callbacks from all CPUs\n"); - cpumask_copy(rcu_nocb_mask, cpu_possible_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ - if (have_rcu_nocb_mask) { - if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { - pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); - cpumask_and(rcu_nocb_mask, cpu_possible_mask, - rcu_nocb_mask); - } - cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); - pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); - if (rcu_nocb_poll) - pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); - } -#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ } #ifdef CONFIG_TREE_PREEMPT_RCU @@ -1463,14 +1436,13 @@ static struct smp_hotplug_thread rcu_cpu_thread_spec = { }; /* - * Spawn all kthreads -- called as soon as the scheduler is running. + * Spawn boost kthreads -- called as soon as the scheduler is running. */ -static int __init rcu_spawn_kthreads(void) +static void __init rcu_spawn_boost_kthreads(void) { struct rcu_node *rnp; int cpu; - rcu_scheduler_fully_active = 1; for_each_possible_cpu(cpu) per_cpu(rcu_cpu_has_work, cpu) = 0; BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); @@ -1480,9 +1452,7 @@ static int __init rcu_spawn_kthreads(void) rcu_for_each_leaf_node(rcu_state_p, rnp) (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); } - return 0; } -early_initcall(rcu_spawn_kthreads); static void rcu_prepare_kthreads(int cpu) { @@ -1520,12 +1490,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { } -static int __init rcu_scheduler_really_started(void) +static void __init rcu_spawn_boost_kthreads(void) { - rcu_scheduler_fully_active = 1; - return 0; } -early_initcall(rcu_scheduler_really_started); static void rcu_prepare_kthreads(int cpu) { @@ -2076,7 +2043,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) if (!ACCESS_ONCE(rdp_leader->nocb_kthread)) return; if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) { - /* Prior xchg orders against prior callback enqueue. */ + /* Prior smp_mb__after_atomic() orders against prior enqueue. */ ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false; wake_up(&rdp_leader->nocb_wq); } @@ -2105,6 +2072,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, ACCESS_ONCE(*old_rhpp) = rhp; atomic_long_add(rhcount, &rdp->nocb_q_count); atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy); + smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */ /* If we are not being polled and there is a kthread, awaken it ... */ t = ACCESS_ONCE(rdp->nocb_kthread); @@ -2158,7 +2126,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, { if (!rcu_is_nocb_cpu(rdp->cpu)) - return 0; + return false; __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags); if (__is_kfree_rcu_offset((unsigned long)rhp->func)) trace_rcu_kfree_callback(rdp->rsp->name, rhp, @@ -2169,7 +2137,18 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, trace_rcu_callback(rdp->rsp->name, rhp, -atomic_long_read(&rdp->nocb_q_count_lazy), -atomic_long_read(&rdp->nocb_q_count)); - return 1; + + /* + * If called from an extended quiescent state with interrupts + * disabled, invoke the RCU core in order to allow the idle-entry + * deferred-wakeup check to function. + */ + if (irqs_disabled_flags(flags) && + !rcu_is_watching() && + cpu_online(smp_processor_id())) + invoke_rcu_core(); + + return true; } /* @@ -2185,7 +2164,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, /* If this is not a no-CBs CPU, tell the caller to do it the old way. */ if (!rcu_is_nocb_cpu(smp_processor_id())) - return 0; + return false; rsp->qlen = 0; rsp->qlen_lazy = 0; @@ -2204,7 +2183,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, rsp->orphan_nxtlist = NULL; rsp->orphan_nxttail = &rsp->orphan_nxtlist; } - return 1; + return true; } /* @@ -2335,6 +2314,7 @@ wait_again: atomic_long_add(rdp->nocb_gp_count, &rdp->nocb_follower_count); atomic_long_add(rdp->nocb_gp_count_lazy, &rdp->nocb_follower_count_lazy); + smp_mb__after_atomic(); /* Store *tail before wakeup. */ if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { /* * List was empty, wake up the follower. @@ -2463,6 +2443,71 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake")); } +void __init rcu_init_nohz(void) +{ + int cpu; + bool need_rcu_nocb_mask = true; + struct rcu_state *rsp; + +#ifdef CONFIG_RCU_NOCB_CPU_NONE + need_rcu_nocb_mask = false; +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ + +#if defined(CONFIG_NO_HZ_FULL) + if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) + need_rcu_nocb_mask = true; +#endif /* #if defined(CONFIG_NO_HZ_FULL) */ + + if (!have_rcu_nocb_mask && need_rcu_nocb_mask) { + if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) { + pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n"); + return; + } + have_rcu_nocb_mask = true; + } + if (!have_rcu_nocb_mask) + return; + +#ifdef CONFIG_RCU_NOCB_CPU_ZERO + pr_info("\tOffload RCU callbacks from CPU 0\n"); + cpumask_set_cpu(0, rcu_nocb_mask); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ +#ifdef CONFIG_RCU_NOCB_CPU_ALL + pr_info("\tOffload RCU callbacks from all CPUs\n"); + cpumask_copy(rcu_nocb_mask, cpu_possible_mask); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ +#if defined(CONFIG_NO_HZ_FULL) + if (tick_nohz_full_running) + cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); +#endif /* #if defined(CONFIG_NO_HZ_FULL) */ + + if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { + pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); + cpumask_and(rcu_nocb_mask, cpu_possible_mask, + rcu_nocb_mask); + } + cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); + pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); + if (rcu_nocb_poll) + pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); + + for_each_rcu_flavor(rsp) { + for_each_cpu(cpu, rcu_nocb_mask) { + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + + /* + * If there are early callbacks, they will need + * to be moved to the nocb lists. + */ + WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] != + &rdp->nxtlist && + rdp->nxttail[RCU_NEXT_TAIL] != NULL); + init_nocb_callback_list(rdp); + } + rcu_organize_nocb_kthreads(rsp); + } +} + /* Initialize per-rcu_data variables for no-CBs CPUs. */ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { @@ -2471,15 +2516,85 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) rdp->nocb_follower_tail = &rdp->nocb_follower_head; } +/* + * If the specified CPU is a no-CBs CPU that does not already have its + * rcuo kthread for the specified RCU flavor, spawn it. If the CPUs are + * brought online out of order, this can require re-organizing the + * leader-follower relationships. + */ +static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu) +{ + struct rcu_data *rdp; + struct rcu_data *rdp_last; + struct rcu_data *rdp_old_leader; + struct rcu_data *rdp_spawn = per_cpu_ptr(rsp->rda, cpu); + struct task_struct *t; + + /* + * If this isn't a no-CBs CPU or if it already has an rcuo kthread, + * then nothing to do. + */ + if (!rcu_is_nocb_cpu(cpu) || rdp_spawn->nocb_kthread) + return; + + /* If we didn't spawn the leader first, reorganize! */ + rdp_old_leader = rdp_spawn->nocb_leader; + if (rdp_old_leader != rdp_spawn && !rdp_old_leader->nocb_kthread) { + rdp_last = NULL; + rdp = rdp_old_leader; + do { + rdp->nocb_leader = rdp_spawn; + if (rdp_last && rdp != rdp_spawn) + rdp_last->nocb_next_follower = rdp; + rdp_last = rdp; + rdp = rdp->nocb_next_follower; + rdp_last->nocb_next_follower = NULL; + } while (rdp); + rdp_spawn->nocb_next_follower = rdp_old_leader; + } + + /* Spawn the kthread for this CPU and RCU flavor. */ + t = kthread_run(rcu_nocb_kthread, rdp_spawn, + "rcuo%c/%d", rsp->abbr, cpu); + BUG_ON(IS_ERR(t)); + ACCESS_ONCE(rdp_spawn->nocb_kthread) = t; +} + +/* + * If the specified CPU is a no-CBs CPU that does not already have its + * rcuo kthreads, spawn them. + */ +static void rcu_spawn_all_nocb_kthreads(int cpu) +{ + struct rcu_state *rsp; + + if (rcu_scheduler_fully_active) + for_each_rcu_flavor(rsp) + rcu_spawn_one_nocb_kthread(rsp, cpu); +} + +/* + * Once the scheduler is running, spawn rcuo kthreads for all online + * no-CBs CPUs. This assumes that the early_initcall()s happen before + * non-boot CPUs come online -- if this changes, we will need to add + * some mutual exclusion. + */ +static void __init rcu_spawn_nocb_kthreads(void) +{ + int cpu; + + for_each_online_cpu(cpu) + rcu_spawn_all_nocb_kthreads(cpu); +} + /* How many follower CPU IDs per leader? Default of -1 for sqrt(nr_cpu_ids). */ static int rcu_nocb_leader_stride = -1; module_param(rcu_nocb_leader_stride, int, 0444); /* - * Create a kthread for each RCU flavor for each no-CBs CPU. - * Also initialize leader-follower relationships. + * Initialize leader-follower relationships for all no-CBs CPU. */ -static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) +static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp) { int cpu; int ls = rcu_nocb_leader_stride; @@ -2487,14 +2602,9 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) struct rcu_data *rdp; struct rcu_data *rdp_leader = NULL; /* Suppress misguided gcc warn. */ struct rcu_data *rdp_prev = NULL; - struct task_struct *t; - if (rcu_nocb_mask == NULL) + if (!have_rcu_nocb_mask) return; -#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) - if (tick_nohz_full_running) - cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); -#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */ if (ls == -1) { ls = int_sqrt(nr_cpu_ids); rcu_nocb_leader_stride = ls; @@ -2517,21 +2627,15 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) rdp_prev->nocb_next_follower = rdp; } rdp_prev = rdp; - - /* Spawn the kthread for this CPU. */ - t = kthread_run(rcu_nocb_kthread, rdp, - "rcuo%c/%d", rsp->abbr, cpu); - BUG_ON(IS_ERR(t)); - ACCESS_ONCE(rdp->nocb_kthread) = t; } } /* Prevent __call_rcu() from enqueuing callbacks on no-CBs CPUs */ static bool init_nocb_callback_list(struct rcu_data *rdp) { - if (rcu_nocb_mask == NULL || - !cpumask_test_cpu(rdp->cpu, rcu_nocb_mask)) + if (!rcu_is_nocb_cpu(rdp->cpu)) return false; + rdp->nxttail[RCU_NEXT_TAIL] = NULL; return true; } @@ -2553,14 +2657,14 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy, unsigned long flags) { - return 0; + return false; } static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, struct rcu_data *rdp, unsigned long flags) { - return 0; + return false; } static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) @@ -2576,7 +2680,11 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) { } -static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) +static void rcu_spawn_all_nocb_kthreads(int cpu) +{ +} + +static void __init rcu_spawn_nocb_kthreads(void) { } @@ -2607,16 +2715,6 @@ static void __maybe_unused rcu_kick_nohz_cpu(int cpu) #ifdef CONFIG_NO_HZ_FULL_SYSIDLE -/* - * Define RCU flavor that holds sysidle state. This needs to be the - * most active flavor of RCU. - */ -#ifdef CONFIG_PREEMPT_RCU -static struct rcu_state *rcu_sysidle_state = &rcu_preempt_state; -#else /* #ifdef CONFIG_PREEMPT_RCU */ -static struct rcu_state *rcu_sysidle_state = &rcu_sched_state; -#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ - static int full_sysidle_state; /* Current system-idle state. */ #define RCU_SYSIDLE_NOT 0 /* Some CPU is not idle. */ #define RCU_SYSIDLE_SHORT 1 /* All CPUs idle for brief period. */ @@ -2634,6 +2732,10 @@ static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq) { unsigned long j; + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + /* Adjust nesting, check for fully idle. */ if (irq) { rdtp->dynticks_idle_nesting--; @@ -2699,6 +2801,10 @@ void rcu_sysidle_force_exit(void) */ static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq) { + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + /* Adjust nesting, check for already non-idle. */ if (irq) { rdtp->dynticks_idle_nesting++; @@ -2753,12 +2859,16 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, unsigned long j; struct rcu_dynticks *rdtp = rdp->dynticks; + /* If there are no nohz_full= CPUs, don't check system-wide idleness. */ + if (!tick_nohz_full_enabled()) + return; + /* * If some other CPU has already reported non-idle, if this is * not the flavor of RCU that tracks sysidle state, or if this * is an offline or the timekeeping CPU, nothing to do. */ - if (!*isidle || rdp->rsp != rcu_sysidle_state || + if (!*isidle || rdp->rsp != rcu_state_p || cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu) return; if (rcu_gp_in_progress(rdp->rsp)) @@ -2784,7 +2894,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, */ static bool is_sysidle_rcu_state(struct rcu_state *rsp) { - return rsp == rcu_sysidle_state; + return rsp == rcu_state_p; } /* @@ -2862,7 +2972,7 @@ static void rcu_sysidle_cancel(void) static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, unsigned long maxj, bool gpkt) { - if (rsp != rcu_sysidle_state) + if (rsp != rcu_state_p) return; /* Wrong flavor, ignore. */ if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) return; /* Running state machine from timekeeping CPU. */ @@ -2879,6 +2989,10 @@ static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, unsigned long maxj) { + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + rcu_sysidle_report(rsp, isidle, maxj, true); } @@ -2905,7 +3019,8 @@ static void rcu_sysidle_cb(struct rcu_head *rhp) /* * Check to see if the system is fully idle, other than the timekeeping CPU. - * The caller must have disabled interrupts. + * The caller must have disabled interrupts. This is not intended to be + * called unless tick_nohz_full_enabled(). */ bool rcu_sys_is_idle(void) { @@ -2931,13 +3046,12 @@ bool rcu_sys_is_idle(void) /* Scan all the CPUs looking for nonidle CPUs. */ for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rcu_sysidle_state->rda, cpu); + rdp = per_cpu_ptr(rcu_state_p->rda, cpu); rcu_sysidle_check_cpu(rdp, &isidle, &maxj); if (!isidle) break; } - rcu_sysidle_report(rcu_sysidle_state, - isidle, maxj, false); + rcu_sysidle_report(rcu_state_p, isidle, maxj, false); oldrss = rss; rss = ACCESS_ONCE(full_sysidle_state); } @@ -2964,7 +3078,7 @@ bool rcu_sys_is_idle(void) * provided by the memory allocator. */ if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL && - !rcu_gp_in_progress(rcu_sysidle_state) && + !rcu_gp_in_progress(rcu_state_p) && !rsh.inuse && xchg(&rsh.inuse, 1) == 0) call_rcu(&rsh.rh, rcu_sysidle_cb); return false; diff --git a/kernel/torture.c b/kernel/torture.c index d600af21f022..ede8b25ec1ae 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -211,18 +211,16 @@ EXPORT_SYMBOL_GPL(torture_onoff_cleanup); /* * Print online/offline testing statistics. */ -char *torture_onoff_stats(char *page) +void torture_onoff_stats(void) { #ifdef CONFIG_HOTPLUG_CPU - page += sprintf(page, - "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ", - n_online_successes, n_online_attempts, - n_offline_successes, n_offline_attempts, - min_online, max_online, - min_offline, max_offline, - sum_online, sum_offline, HZ); + pr_cont("onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ", + n_online_successes, n_online_attempts, + n_offline_successes, n_offline_attempts, + min_online, max_online, + min_offline, max_offline, + sum_online, sum_offline, HZ); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ - return page; } EXPORT_SYMBOL_GPL(torture_onoff_stats); diff --git a/tools/testing/selftests/rcutorture/bin/config2frag.sh b/tools/testing/selftests/rcutorture/bin/config2frag.sh index 9f9ffcd427d3..56f51ae13d73 100644..100755 --- a/tools/testing/selftests/rcutorture/bin/config2frag.sh +++ b/tools/testing/selftests/rcutorture/bin/config2frag.sh @@ -1,5 +1,5 @@ -#!/bin/sh -# Usage: sh config2frag.sh < .config > configfrag +#!/bin/bash +# Usage: config2frag.sh < .config > configfrag # # Converts the "# CONFIG_XXX is not set" to "CONFIG_XXX=n" so that the # resulting file becomes a legitimate Kconfig fragment. diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh index d686537dd55c..eee31e261bf7 100755 --- a/tools/testing/selftests/rcutorture/bin/configcheck.sh +++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh @@ -1,5 +1,5 @@ -#!/bin/sh -# Usage: sh configcheck.sh .config .config-template +#!/bin/bash +# Usage: configcheck.sh .config .config-template # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index 9c3f3d39b934..15f1a17ca96e 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -1,6 +1,6 @@ -#!/bin/sh +#!/bin/bash # -# sh configinit.sh config-spec-file [ build output dir ] +# Usage: configinit.sh config-spec-file [ build output dir ] # # Create a .config file from the spec file. Run from the kernel source tree. # Exits with 0 if all went well, with 1 if all went well but the config diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index d01b865bb100..b325470c01b3 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -64,6 +64,26 @@ configfrag_boot_params () { fi } +# configfrag_boot_cpus bootparam-string config-fragment-file config-cpus +# +# Decreases number of CPUs based on any maxcpus= boot parameters specified. +configfrag_boot_cpus () { + local bootargs="`configfrag_boot_params "$1" "$2"`" + local maxcpus + if echo "${bootargs}" | grep -q 'maxcpus=[0-9]' + then + maxcpus="`echo "${bootargs}" | sed -e 's/^.*maxcpus=\([0-9]*\).*$/\1/'`" + if test "$3" -gt "$maxcpus" + then + echo $maxcpus + else + echo $3 + fi + else + echo $3 + fi +} + # configfrag_hotplug_cpu config-fragment-file # # Returns 1 if the config fragment specifies hotplug CPU. diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 7c1e56b46de4..00cb0db2643d 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -2,7 +2,7 @@ # # Build a kvm-ready Linux kernel from the tree in the current directory. # -# Usage: sh kvm-build.sh config-template build-dir more-configs +# Usage: kvm-build.sh config-template build-dir more-configs # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh index 7f1ff1a8fc4b..43f764098e50 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh @@ -2,7 +2,7 @@ # # Analyze a given results directory for locktorture progress. # -# Usage: sh kvm-recheck-lock.sh resdir +# Usage: kvm-recheck-lock.sh resdir # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index 307c4b95f325..d6cc07fc137f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -2,7 +2,7 @@ # # Analyze a given results directory for rcutorture progress. # -# Usage: sh kvm-recheck-rcu.sh resdir +# Usage: kvm-recheck-rcu.sh resdir # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 3f6c9b78d177..4f5b20f367a9 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -4,7 +4,7 @@ # check the build and console output for errors. Given a directory # containing results directories, this recursively checks them all. # -# Usage: sh kvm-recheck.sh resdir ... +# Usage: kvm-recheck.sh resdir ... # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 0f69dcbf9def..f6b2b4771b78 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -6,7 +6,7 @@ # Execute this in the source tree. Do not run it as a background task # because qemu does not seem to like that much. # -# Usage: sh kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args +# Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args # # qemu-args defaults to "-nographic", along with arguments specifying the # number of CPUs and other options generated from @@ -140,6 +140,7 @@ fi # Generate -smp qemu argument. qemu_args="-nographic $qemu_args" cpu_count=`configNR_CPUS.sh $config_template` +cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"` vcpus=`identify_qemu_vcpus` if test $cpu_count -gt $vcpus then @@ -214,7 +215,7 @@ then fi if test $kruntime -ge $((seconds + grace)) then - echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1 + echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1 kill -KILL $qemu_pid break fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 589e9c38413b..e527dc952eb0 100644..100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -7,7 +7,7 @@ # Edit the definitions below to set the locations of the various directories, # as well as the test duration. # -# Usage: sh kvm.sh [ options ] +# Usage: kvm.sh [ options ] # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by @@ -188,7 +188,9 @@ for CF in $configs do if test -f "$CONFIGFRAG/$kversion/$CF" then - echo $CF `configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` >> $T/cfgcpu + cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` + cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$kversion/$CF" "$cpu_count"` + echo $CF $cpu_count >> $T/cfgcpu else echo "The --configs file $CF does not exist, terminating." exit 1 diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh index 543230951c38..499d1e598e42 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-build.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # # Check the build output from an rcutorture run for goodness. # The "file" is a pathname on the local system, and "title" is @@ -6,8 +6,7 @@ # # The file must contain kernel build output. # -# Usage: -# sh parse-build.sh file title +# Usage: parse-build.sh file title # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 4185d4cab32e..f962ba4cf68b 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -1,11 +1,10 @@ -#!/bin/sh +#!/bin/bash # # Check the console output from an rcutorture run for oopses. # The "file" is a pathname on the local system, and "title" is # a text string for error-message purposes. # -# Usage: -# sh parse-console.sh file title +# Usage: parse-console.sh file title # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by @@ -33,6 +32,10 @@ title="$2" . functions.sh +if grep -Pq '\x00' < $file +then + print_warning Console output contains nul bytes, old qemu still running? +fi egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T if test -s $T then diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh index 3455560ab4e4..e3c5f0705696 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-torture.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # # Check the console output from a torture run for goodness. # The "file" is a pathname on the local system, and "title" is @@ -7,8 +7,7 @@ # The file must contain torture output, but can be interspersed # with other dmesg text, as in console-log output. # -# Usage: -# sh parse-torture.sh file title +# Usage: parse-torture.sh file title # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 063b7079c621..38e3895759dd 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -1,5 +1,4 @@ CONFIG_SMP=y -CONFIG_NR_CPUS=8 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y @@ -10,8 +9,7 @@ CONFIG_NO_HZ_FULL=n CONFIG_RCU_FAST_NO_HZ=y CONFIG_RCU_TRACE=y CONFIG_HOTPLUG_CPU=y -CONFIG_RCU_FANOUT=8 -CONFIG_RCU_FANOUT_EXACT=n +CONFIG_MAXSMP=y CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ZERO=y CONFIG_DEBUG_LOCK_ALLOC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot index 0fc8a3428938..adc3abc82fb8 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot @@ -1 +1 @@ -rcutorture.torture_type=rcu_bh +rcutorture.torture_type=rcu_bh maxcpus=8 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index ab6225506909..8f1017666aa7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -1,5 +1,6 @@ CONFIG_SMP=y CONFIG_NR_CPUS=16 +CONFIG_CPUMASK_OFFSTACK=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n @@ -7,7 +8,7 @@ CONFIG_PREEMPT=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y -CONFIG_NO_HZ_FULL_ALL=y +CONFIG_NO_HZ_FULL_ALL=n CONFIG_NO_HZ_FULL_SYSIDLE=y CONFIG_RCU_FAST_NO_HZ=n CONFIG_RCU_TRACE=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot new file mode 100644 index 000000000000..d44609937503 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot @@ -0,0 +1 @@ +nohz_full=2-9 diff --git a/tools/testing/selftests/rcutorture/doc/initrd.txt b/tools/testing/selftests/rcutorture/doc/initrd.txt index 49d134c25c04..4170e714f044 100644 --- a/tools/testing/selftests/rcutorture/doc/initrd.txt +++ b/tools/testing/selftests/rcutorture/doc/initrd.txt @@ -6,6 +6,7 @@ this case. There are probably much better ways of doing this. That said, here are the commands: ------------------------------------------------------------------------ +cd tools/testing/selftests/rcutorture zcat /initrd.img > /tmp/initrd.img.zcat mkdir initrd cd initrd |