diff options
31 files changed, 1210 insertions, 412 deletions
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX index fa57139f50bf..f773a264ae02 100644 --- a/Documentation/RCU/00-INDEX +++ b/Documentation/RCU/00-INDEX @@ -12,6 +12,8 @@ lockdep-splat.txt - RCU Lockdep splats explained. NMI-RCU.txt - Using RCU to Protect Dynamic NMI Handlers +rcu_dereference.txt + - Proper care and feeding of return values from rcu_dereference() rcubarrier.txt - RCU and Unloadable Modules rculist_nulls.txt diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 9d10d1db16a5..877947130ebe 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -114,12 +114,16 @@ over a rather long period of time, but improvements are always welcome! http://www.openvms.compaq.com/wizard/wiz_2637.html The rcu_dereference() primitive is also an excellent - documentation aid, letting the person reading the code - know exactly which pointers are protected by RCU. + documentation aid, letting the person reading the + code know exactly which pointers are protected by RCU. Please note that compilers can also reorder code, and they are becoming increasingly aggressive about doing - just that. The rcu_dereference() primitive therefore - also prevents destructive compiler optimizations. + just that. The rcu_dereference() primitive therefore also + prevents destructive compiler optimizations. However, + with a bit of devious creativity, it is possible to + mishandle the return value from rcu_dereference(). + Please see rcu_dereference.txt in this directory for + more information. The rcu_dereference() primitive is used by the various "_rcu()" list-traversal primitives, such diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt new file mode 100644 index 000000000000..ceb05da5a5ac --- /dev/null +++ b/Documentation/RCU/rcu_dereference.txt @@ -0,0 +1,371 @@ +PROPER CARE AND FEEDING OF RETURN VALUES FROM rcu_dereference() + +Most of the time, you can use values from rcu_dereference() or one of +the similar primitives without worries. Dereferencing (prefix "*"), +field selection ("->"), assignment ("="), address-of ("&"), addition and +subtraction of constants, and casts all work quite naturally and safely. + +It is nevertheless possible to get into trouble with other operations. +Follow these rules to keep your RCU code working properly: + +o You must use one of the rcu_dereference() family of primitives + to load an RCU-protected pointer, otherwise CONFIG_PROVE_RCU + will complain. Worse yet, your code can see random memory-corruption + bugs due to games that compilers and DEC Alpha can play. + Without one of the rcu_dereference() primitives, compilers + can reload the value, and won't your code have fun with two + different values for a single pointer! Without rcu_dereference(), + DEC Alpha can load a pointer, dereference that pointer, and + return data preceding initialization that preceded the store of + the pointer. + + In addition, the volatile cast in rcu_dereference() prevents the + compiler from deducing the resulting pointer value. Please see + the section entitled "EXAMPLE WHERE THE COMPILER KNOWS TOO MUCH" + for an example where the compiler can in fact deduce the exact + value of the pointer, and thus cause misordering. + +o Do not use single-element RCU-protected arrays. The compiler + is within its right to assume that the value of an index into + such an array must necessarily evaluate to zero. The compiler + could then substitute the constant zero for the computation, so + that the array index no longer depended on the value returned + by rcu_dereference(). If the array index no longer depends + on rcu_dereference(), then both the compiler and the CPU + are within their rights to order the array access before the + rcu_dereference(), which can cause the array access to return + garbage. + +o Avoid cancellation when using the "+" and "-" infix arithmetic + operators. For example, for a given variable "x", avoid + "(x-x)". There are similar arithmetic pitfalls from other + arithmetic operatiors, such as "(x*0)", "(x/(x+1))" or "(x%1)". + The compiler is within its rights to substitute zero for all of + these expressions, so that subsequent accesses no longer depend + on the rcu_dereference(), again possibly resulting in bugs due + to misordering. + + Of course, if "p" is a pointer from rcu_dereference(), and "a" + and "b" are integers that happen to be equal, the expression + "p+a-b" is safe because its value still necessarily depends on + the rcu_dereference(), thus maintaining proper ordering. + +o Avoid all-zero operands to the bitwise "&" operator, and + similarly avoid all-ones operands to the bitwise "|" operator. + If the compiler is able to deduce the value of such operands, + it is within its rights to substitute the corresponding constant + for the bitwise operation. Once again, this causes subsequent + accesses to no longer depend on the rcu_dereference(), causing + bugs due to misordering. + + Please note that single-bit operands to bitwise "&" can also + be dangerous. At this point, the compiler knows that the + resulting value can only take on one of two possible values. + Therefore, a very small amount of additional information will + allow the compiler to deduce the exact value, which again can + result in misordering. + +o If you are using RCU to protect JITed functions, so that the + "()" function-invocation operator is applied to a value obtained + (directly or indirectly) from rcu_dereference(), you may need to + interact directly with the hardware to flush instruction caches. + This issue arises on some systems when a newly JITed function is + using the same memory that was used by an earlier JITed function. + +o Do not use the results from the boolean "&&" and "||" when + dereferencing. For example, the following (rather improbable) + code is buggy: + + int a[2]; + int index; + int force_zero_index = 1; + + ... + + r1 = rcu_dereference(i1) + r2 = a[r1 && force_zero_index]; /* BUGGY!!! */ + + The reason this is buggy is that "&&" and "||" are often compiled + using branches. While weak-memory machines such as ARM or PowerPC + do order stores after such branches, they can speculate loads, + which can result in misordering bugs. + +o Do not use the results from relational operators ("==", "!=", + ">", ">=", "<", or "<=") when dereferencing. For example, + the following (quite strange) code is buggy: + + int a[2]; + int index; + int flip_index = 0; + + ... + + r1 = rcu_dereference(i1) + r2 = a[r1 != flip_index]; /* BUGGY!!! */ + + As before, the reason this is buggy is that relational operators + are often compiled using branches. And as before, although + weak-memory machines such as ARM or PowerPC do order stores + after such branches, but can speculate loads, which can again + result in misordering bugs. + +o Be very careful about comparing pointers obtained from + rcu_dereference() against non-NULL values. As Linus Torvalds + explained, if the two pointers are equal, the compiler could + substitute the pointer you are comparing against for the pointer + obtained from rcu_dereference(). For example: + + p = rcu_dereference(gp); + if (p == &default_struct) + do_default(p->a); + + Because the compiler now knows that the value of "p" is exactly + the address of the variable "default_struct", it is free to + transform this code into the following: + + p = rcu_dereference(gp); + if (p == &default_struct) + do_default(default_struct.a); + + On ARM and Power hardware, the load from "default_struct.a" + can now be speculated, such that it might happen before the + rcu_dereference(). This could result in bugs due to misordering. + + However, comparisons are OK in the following cases: + + o The comparison was against the NULL pointer. If the + compiler knows that the pointer is NULL, you had better + not be dereferencing it anyway. If the comparison is + non-equal, the compiler is none the wiser. Therefore, + it is safe to compare pointers from rcu_dereference() + against NULL pointers. + + o The pointer is never dereferenced after being compared. + Since there are no subsequent dereferences, the compiler + cannot use anything it learned from the comparison + to reorder the non-existent subsequent dereferences. + This sort of comparison occurs frequently when scanning + RCU-protected circular linked lists. + + o The comparison is against a pointer that references memory + that was initialized "a long time ago." The reason + this is safe is that even if misordering occurs, the + misordering will not affect the accesses that follow + the comparison. So exactly how long ago is "a long + time ago"? Here are some possibilities: + + o Compile time. + + o Boot time. + + o Module-init time for module code. + + o Prior to kthread creation for kthread code. + + o During some prior acquisition of the lock that + we now hold. + + o Before mod_timer() time for a timer handler. + + There are many other possibilities involving the Linux + kernel's wide array of primitives that cause code to + be invoked at a later time. + + o The pointer being compared against also came from + rcu_dereference(). In this case, both pointers depend + on one rcu_dereference() or another, so you get proper + ordering either way. + + That said, this situation can make certain RCU usage + bugs more likely to happen. Which can be a good thing, + at least if they happen during testing. An example + of such an RCU usage bug is shown in the section titled + "EXAMPLE OF AMPLIFIED RCU-USAGE BUG". + + o All of the accesses following the comparison are stores, + so that a control dependency preserves the needed ordering. + That said, it is easy to get control dependencies wrong. + Please see the "CONTROL DEPENDENCIES" section of + Documentation/memory-barriers.txt for more details. + + o The pointers are not equal -and- the compiler does + not have enough information to deduce the value of the + pointer. Note that the volatile cast in rcu_dereference() + will normally prevent the compiler from knowing too much. + +o Disable any value-speculation optimizations that your compiler + might provide, especially if you are making use of feedback-based + optimizations that take data collected from prior runs. Such + value-speculation optimizations reorder operations by design. + + There is one exception to this rule: Value-speculation + optimizations that leverage the branch-prediction hardware are + safe on strongly ordered systems (such as x86), but not on weakly + ordered systems (such as ARM or Power). Choose your compiler + command-line options wisely! + + +EXAMPLE OF AMPLIFIED RCU-USAGE BUG + +Because updaters can run concurrently with RCU readers, RCU readers can +see stale and/or inconsistent values. If RCU readers need fresh or +consistent values, which they sometimes do, they need to take proper +precautions. To see this, consider the following code fragment: + + struct foo { + int a; + int b; + int c; + }; + struct foo *gp1; + struct foo *gp2; + + void updater(void) + { + struct foo *p; + + p = kmalloc(...); + if (p == NULL) + deal_with_it(); + p->a = 42; /* Each field in its own cache line. */ + p->b = 43; + p->c = 44; + rcu_assign_pointer(gp1, p); + p->b = 143; + p->c = 144; + rcu_assign_pointer(gp2, p); + } + + void reader(void) + { + struct foo *p; + struct foo *q; + int r1, r2; + + p = rcu_dereference(gp2); + if (p == NULL) + return; + r1 = p->b; /* Guaranteed to get 143. */ + q = rcu_dereference(gp1); /* Guaranteed non-NULL. */ + if (p == q) { + /* The compiler decides that q->c is same as p->c. */ + r2 = p->c; /* Could get 44 on weakly order system. */ + } + do_something_with(r1, r2); + } + +You might be surprised that the outcome (r1 == 143 && r2 == 44) is possible, +but you should not be. After all, the updater might have been invoked +a second time between the time reader() loaded into "r1" and the time +that it loaded into "r2". The fact that this same result can occur due +to some reordering from the compiler and CPUs is beside the point. + +But suppose that the reader needs a consistent view? + +Then one approach is to use locking, for example, as follows: + + struct foo { + int a; + int b; + int c; + spinlock_t lock; + }; + struct foo *gp1; + struct foo *gp2; + + void updater(void) + { + struct foo *p; + + p = kmalloc(...); + if (p == NULL) + deal_with_it(); + spin_lock(&p->lock); + p->a = 42; /* Each field in its own cache line. */ + p->b = 43; + p->c = 44; + spin_unlock(&p->lock); + rcu_assign_pointer(gp1, p); + spin_lock(&p->lock); + p->b = 143; + p->c = 144; + spin_unlock(&p->lock); + rcu_assign_pointer(gp2, p); + } + + void reader(void) + { + struct foo *p; + struct foo *q; + int r1, r2; + + p = rcu_dereference(gp2); + if (p == NULL) + return; + spin_lock(&p->lock); + r1 = p->b; /* Guaranteed to get 143. */ + q = rcu_dereference(gp1); /* Guaranteed non-NULL. */ + if (p == q) { + /* The compiler decides that q->c is same as p->c. */ + r2 = p->c; /* Locking guarantees r2 == 144. */ + } + spin_unlock(&p->lock); + do_something_with(r1, r2); + } + +As always, use the right tool for the job! + + +EXAMPLE WHERE THE COMPILER KNOWS TOO MUCH + +If a pointer obtained from rcu_dereference() compares not-equal to some +other pointer, the compiler normally has no clue what the value of the +first pointer might be. This lack of knowledge prevents the compiler +from carrying out optimizations that otherwise might destroy the ordering +guarantees that RCU depends on. And the volatile cast in rcu_dereference() +should prevent the compiler from guessing the value. + +But without rcu_dereference(), the compiler knows more than you might +expect. Consider the following code fragment: + + struct foo { + int a; + int b; + }; + static struct foo variable1; + static struct foo variable2; + static struct foo *gp = &variable1; + + void updater(void) + { + initialize_foo(&variable2); + rcu_assign_pointer(gp, &variable2); + /* + * The above is the only store to gp in this translation unit, + * and the address of gp is not exported in any way. + */ + } + + int reader(void) + { + struct foo *p; + + p = gp; + barrier(); + if (p == &variable1) + return p->a; /* Must be variable1.a. */ + else + return p->b; /* Must be variable2.b. */ + } + +Because the compiler can see all stores to "gp", it knows that the only +possible values of "gp" are "variable1" on the one hand and "variable2" +on the other. The comparison in reader() therefore tells the compiler +the exact value of "p" even in the not-equals case. This allows the +compiler to make the return values independent of the load from "gp", +in turn destroying the ordering between this load and the loads of the +return values. This can result in "p->b" returning pre-initialization +garbage values. + +In short, rcu_dereference() is -not- optional when you are going to +dereference the resulting pointer. diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 6f3a0057548e..68fe3ad27015 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -24,7 +24,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT timing of the next warning for the current stall. Stall-warning messages may be enabled and disabled completely via - /sys/module/rcutree/parameters/rcu_cpu_stall_suppress. + /sys/module/rcupdate/parameters/rcu_cpu_stall_suppress. CONFIG_RCU_CPU_STALL_VERBOSE diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 0f0fb7c432c2..49b8551a3b68 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -326,11 +326,11 @@ used as follows: a. synchronize_rcu() rcu_read_lock() / rcu_read_unlock() call_rcu() rcu_dereference() -b. call_rcu_bh() rcu_read_lock_bh() / rcu_read_unlock_bh() - rcu_dereference_bh() +b. synchronize_rcu_bh() rcu_read_lock_bh() / rcu_read_unlock_bh() + call_rcu_bh() rcu_dereference_bh() c. synchronize_sched() rcu_read_lock_sched() / rcu_read_unlock_sched() - preempt_disable() / preempt_enable() + call_rcu_sched() preempt_disable() / preempt_enable() local_irq_save() / local_irq_restore() hardirq enter / hardirq exit NMI enter / NMI exit @@ -794,10 +794,22 @@ in docbook. Here is the list, by category. RCU list traversal: + list_entry_rcu + list_first_entry_rcu + list_next_rcu list_for_each_entry_rcu + list_for_each_entry_continue_rcu + hlist_first_rcu + hlist_next_rcu + hlist_pprev_rcu hlist_for_each_entry_rcu + hlist_for_each_entry_rcu_bh + hlist_for_each_entry_continue_rcu + hlist_for_each_entry_continue_rcu_bh + hlist_nulls_first_rcu hlist_nulls_for_each_entry_rcu - list_for_each_entry_continue_rcu + hlist_bl_first_rcu + hlist_bl_for_each_entry_rcu RCU pointer/list update: @@ -806,28 +818,38 @@ RCU pointer/list update: list_add_tail_rcu list_del_rcu list_replace_rcu - hlist_del_rcu hlist_add_after_rcu hlist_add_before_rcu hlist_add_head_rcu + hlist_del_rcu + hlist_del_init_rcu hlist_replace_rcu list_splice_init_rcu() + hlist_nulls_del_init_rcu + hlist_nulls_del_rcu + hlist_nulls_add_head_rcu + hlist_bl_add_head_rcu + hlist_bl_del_init_rcu + hlist_bl_del_rcu + hlist_bl_set_first_rcu RCU: Critical sections Grace period Barrier rcu_read_lock synchronize_net rcu_barrier rcu_read_unlock synchronize_rcu rcu_dereference synchronize_rcu_expedited - call_rcu - kfree_rcu - + rcu_read_lock_held call_rcu + rcu_dereference_check kfree_rcu + rcu_dereference_protected bh: Critical sections Grace period Barrier rcu_read_lock_bh call_rcu_bh rcu_barrier_bh rcu_read_unlock_bh synchronize_rcu_bh rcu_dereference_bh synchronize_rcu_bh_expedited - + rcu_dereference_bh_check + rcu_dereference_bh_protected + rcu_read_lock_bh_held sched: Critical sections Grace period Barrier @@ -835,7 +857,12 @@ sched: Critical sections Grace period Barrier rcu_read_unlock_sched call_rcu_sched [preempt_disable] synchronize_sched_expedited [and friends] + rcu_read_lock_sched_notrace + rcu_read_unlock_sched_notrace rcu_dereference_sched + rcu_dereference_sched_check + rcu_dereference_sched_protected + rcu_read_lock_sched_held SRCU: Critical sections Grace period Barrier @@ -843,6 +870,8 @@ SRCU: Critical sections Grace period Barrier srcu_read_lock synchronize_srcu srcu_barrier srcu_read_unlock call_srcu srcu_dereference synchronize_srcu_expedited + srcu_dereference_check + srcu_read_lock_held SRCU: Initialization/cleanup init_srcu_struct @@ -850,9 +879,13 @@ SRCU: Initialization/cleanup All: lockdep-checked RCU-protected pointer access - rcu_dereference_check - rcu_dereference_protected + rcu_access_index rcu_access_pointer + rcu_dereference_index_check + rcu_dereference_raw + rcu_lockdep_assert + rcu_sleep_check + RCU_NONIDLE See the comment headers in the source code (or the docbook generated from them) for more information. diff --git a/include/linux/percpu.h b/include/linux/percpu.h index e7a0b95ed527..495c6543a8f2 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -639,7 +639,7 @@ do { \ # define raw_cpu_add_return_8(pcp, val) raw_cpu_generic_add_return(pcp, val) # endif # define raw_cpu_add_return(pcp, val) \ - __pcpu_size_call_return2(raw_add_return_, pcp, val) + __pcpu_size_call_return2(raw_cpu_add_return_, pcp, val) #endif #define raw_cpu_sub_return(pcp, val) raw_cpu_add_return(pcp, -(typeof(pcp))(val)) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 00a7fd61b3c6..5a75d19aa661 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -44,6 +44,7 @@ #include <linux/debugobjects.h> #include <linux/bug.h> #include <linux/compiler.h> +#include <linux/percpu.h> #include <asm/barrier.h> extern int rcu_expedited; /* for sysctl */ @@ -51,7 +52,17 @@ extern int rcu_expedited; /* for sysctl */ extern int rcutorture_runnable; /* for sysctl */ #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ +enum rcutorture_type { + RCU_FLAVOR, + RCU_BH_FLAVOR, + RCU_SCHED_FLAVOR, + SRCU_FLAVOR, + INVALID_RCU_FLAVOR +}; + #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) +void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, + unsigned long *gpnum, unsigned long *completed); void rcutorture_record_test_transition(void); void rcutorture_record_progress(unsigned long vernum); void do_trace_rcu_torture_read(const char *rcutorturename, @@ -60,6 +71,15 @@ void do_trace_rcu_torture_read(const char *rcutorturename, unsigned long c_old, unsigned long c); #else +static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, + int *flags, + unsigned long *gpnum, + unsigned long *completed) +{ + *flags = 0; + *gpnum = 0; + *completed = 0; +} static inline void rcutorture_record_test_transition(void) { } @@ -228,6 +248,18 @@ void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); +#ifdef CONFIG_RCU_STALL_COMMON +void rcu_sysrq_start(void); +void rcu_sysrq_end(void); +#else /* #ifdef CONFIG_RCU_STALL_COMMON */ +static inline void rcu_sysrq_start(void) +{ +} +static inline void rcu_sysrq_end(void) +{ +} +#endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ + #ifdef CONFIG_RCU_USER_QS void rcu_user_enter(void); void rcu_user_exit(void); @@ -268,6 +300,41 @@ bool __rcu_is_watching(void); #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */ /* + * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings. + */ + +#define RCU_COND_RESCHED_LIM 256 /* ms vs. 100s of ms. */ +DECLARE_PER_CPU(int, rcu_cond_resched_count); +void rcu_resched(void); + +/* + * Is it time to report RCU quiescent states? + * + * Note unsynchronized access to rcu_cond_resched_count. Yes, we might + * increment some random CPU's count, and possibly also load the result from + * yet another CPU's count. We might even clobber some other CPU's attempt + * to zero its counter. This is all OK because the goal is not precision, + * but rather reasonable amortization of rcu_note_context_switch() overhead + * and extremely high probability of avoiding RCU CPU stall warnings. + * Note that this function has to be preempted in just the wrong place, + * many thousands of times in a row, for anything bad to happen. + */ +static inline bool rcu_should_resched(void) +{ + return raw_cpu_inc_return(rcu_cond_resched_count) >= + RCU_COND_RESCHED_LIM; +} + +/* + * Report quiscent states to RCU if it is time to do so. + */ +static inline void rcu_cond_resched(void) +{ + if (unlikely(rcu_should_resched())) + rcu_resched(); +} + +/* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ @@ -328,7 +395,7 @@ extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; -extern int debug_lockdep_rcu_enabled(void); +int debug_lockdep_rcu_enabled(void); /** * rcu_read_lock_held() - might we be in RCU read-side critical section? @@ -949,6 +1016,9 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer -after- you have completely initialized * the reader-accessible portions of the linked structure. + * + * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no + * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 425c659d54e5..d40a6a451330 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -119,6 +119,10 @@ static inline void rcu_sched_force_quiescent_state(void) { } +static inline void show_rcu_gp_kthreads(void) +{ +} + static inline void rcu_cpu_stall_reset(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index a59ca05fd4e3..3e2f5d432743 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -84,6 +84,7 @@ extern unsigned long rcutorture_vernum; long rcu_batches_completed(void); long rcu_batches_completed_bh(void); long rcu_batches_completed_sched(void); +void show_rcu_gp_kthreads(void); void rcu_force_quiescent_state(void); void rcu_bh_force_quiescent_state(void); diff --git a/include/linux/torture.h b/include/linux/torture.h index b2e2b468e511..5ca58fcbaf1b 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -49,12 +49,6 @@ #define VERBOSE_TOROUT_ERRSTRING(s) \ do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0) -/* Definitions for a non-string torture-test module parameter. */ -#define torture_parm(type, name, init, msg) \ - static type name = init; \ - module_param(name, type, 0444); \ - MODULE_PARM_DESC(name, msg); - /* Definitions for online/offline exerciser. */ int torture_onoff_init(long ooholdoff, long oointerval); char *torture_onoff_stats(char *page); @@ -81,7 +75,7 @@ void stutter_wait(const char *title); int torture_stutter_init(int s); /* Initialization and cleanup. */ -void torture_init_begin(char *ttype, bool v, int *runnable); +bool torture_init_begin(char *ttype, bool v, int *runnable); void torture_init_end(void); bool torture_cleanup(void); bool torture_must_stop(void); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index f26b1a18e34e..dbafeac18e4d 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -82,14 +82,14 @@ struct lock_writer_stress_stats { }; static struct lock_writer_stress_stats *lwsa; -#if defined(MODULE) || defined(CONFIG_LOCK_TORTURE_TEST_RUNNABLE) +#if defined(MODULE) #define LOCKTORTURE_RUNNABLE_INIT 1 #else #define LOCKTORTURE_RUNNABLE_INIT 0 #endif int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT; module_param(locktorture_runnable, int, 0444); -MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at boot"); +MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at module init"); /* Forward reference. */ static void lock_torture_cleanup(void); @@ -219,7 +219,8 @@ static int lock_torture_writer(void *arg) set_user_nice(current, 19); do { - schedule_timeout_uninterruptible(1); + if ((torture_random(&rand) & 0xfffff) == 0) + schedule_timeout_uninterruptible(1); cur_ops->writelock(); if (WARN_ON_ONCE(lock_is_write_held)) lwsp->n_write_lock_fail++; @@ -354,7 +355,8 @@ static int __init lock_torture_init(void) &lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops, }; - torture_init_begin(torture_type, verbose, &locktorture_runnable); + if (!torture_init_begin(torture_type, verbose, &locktorture_runnable)) + return -EBUSY; /* Process args and tell the world that the torturer is on the job. */ for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index bd30bc61bc05..7fa34f86e5ba 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -58,9 +58,11 @@ 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)"); torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)"); +torture_param(bool, gp_cond, false, "Use conditional/async GP wait primitives"); torture_param(bool, gp_exp, false, "Use expedited GP wait primitives"); torture_param(bool, gp_normal, false, "Use normal (non-expedited) GP wait primitives"); +torture_param(bool, gp_sync, false, "Use synchronous GP wait primitives"); torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers"); torture_param(int, n_barrier_cbs, 0, "# of callbacks/kthreads for barrier testing"); @@ -138,6 +140,18 @@ static long n_barrier_attempts; static long n_barrier_successes; static struct list_head rcu_torture_removed; +static int rcu_torture_writer_state; +#define RTWS_FIXED_DELAY 0 +#define RTWS_DELAY 1 +#define RTWS_REPLACE 2 +#define RTWS_DEF_FREE 3 +#define RTWS_EXP_SYNC 4 +#define RTWS_COND_GET 5 +#define RTWS_COND_SYNC 6 +#define RTWS_SYNC 7 +#define RTWS_STUTTER 8 +#define RTWS_STOPPING 9 + #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE) #define RCUTORTURE_RUNNABLE_INIT 1 #else @@ -214,6 +228,7 @@ rcu_torture_free(struct rcu_torture *p) */ struct rcu_torture_ops { + int ttype; void (*init)(void); int (*readlock)(void); void (*read_delay)(struct torture_random_state *rrsp); @@ -222,6 +237,8 @@ struct rcu_torture_ops { void (*deferred_free)(struct rcu_torture *p); void (*sync)(void); void (*exp_sync)(void); + unsigned long (*get_state)(void); + void (*cond_sync)(unsigned long oldstate); void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); void (*cb_barrier)(void); void (*fqs)(void); @@ -273,10 +290,48 @@ static int rcu_torture_completed(void) return rcu_batches_completed(); } +/* + * Update callback in the pipe. This should be invoked after a grace period. + */ +static bool +rcu_torture_pipe_update_one(struct rcu_torture *rp) +{ + int i; + + i = rp->rtort_pipe_count; + if (i > RCU_TORTURE_PIPE_LEN) + i = RCU_TORTURE_PIPE_LEN; + atomic_inc(&rcu_torture_wcount[i]); + if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) { + rp->rtort_mbtest = 0; + return true; + } + return false; +} + +/* + * Update all callbacks in the pipe. Suitable for synchronous grace-period + * primitives. + */ +static void +rcu_torture_pipe_update(struct rcu_torture *old_rp) +{ + struct rcu_torture *rp; + struct rcu_torture *rp1; + + if (old_rp) + list_add(&old_rp->rtort_free, &rcu_torture_removed); + list_for_each_entry_safe(rp, rp1, &rcu_torture_removed, rtort_free) { + if (rcu_torture_pipe_update_one(rp)) { + list_del(&rp->rtort_free); + rcu_torture_free(rp); + } + } +} + static void rcu_torture_cb(struct rcu_head *p) { - int i; struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu); if (torture_must_stop_irq()) { @@ -284,16 +339,10 @@ rcu_torture_cb(struct rcu_head *p) /* The next initialization will pick up the pieces. */ return; } - i = rp->rtort_pipe_count; - if (i > RCU_TORTURE_PIPE_LEN) - i = RCU_TORTURE_PIPE_LEN; - atomic_inc(&rcu_torture_wcount[i]); - if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) { - rp->rtort_mbtest = 0; + if (rcu_torture_pipe_update_one(rp)) rcu_torture_free(rp); - } else { + else cur_ops->deferred_free(rp); - } } static int rcu_no_completed(void) @@ -312,6 +361,7 @@ static void rcu_sync_torture_init(void) } static struct rcu_torture_ops rcu_ops = { + .ttype = RCU_FLAVOR, .init = rcu_sync_torture_init, .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, @@ -320,6 +370,8 @@ static struct rcu_torture_ops rcu_ops = { .deferred_free = rcu_torture_deferred_free, .sync = synchronize_rcu, .exp_sync = synchronize_rcu_expedited, + .get_state = get_state_synchronize_rcu, + .cond_sync = cond_synchronize_rcu, .call = call_rcu, .cb_barrier = rcu_barrier, .fqs = rcu_force_quiescent_state, @@ -355,6 +407,7 @@ static void rcu_bh_torture_deferred_free(struct rcu_torture *p) } static struct rcu_torture_ops rcu_bh_ops = { + .ttype = RCU_BH_FLAVOR, .init = rcu_sync_torture_init, .readlock = rcu_bh_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ @@ -397,6 +450,7 @@ call_rcu_busted(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } static struct rcu_torture_ops rcu_busted_ops = { + .ttype = INVALID_RCU_FLAVOR, .init = rcu_sync_torture_init, .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ @@ -479,9 +533,11 @@ static void srcu_torture_stats(char *page) page += sprintf(page, "%s%s per-CPU(idx=%d):", torture_type, TORTURE_FLAG, idx); for_each_possible_cpu(cpu) { - page += sprintf(page, " %d(%lu,%lu)", cpu, - per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx], - per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]); + 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); } sprintf(page, "\n"); } @@ -492,6 +548,7 @@ static void srcu_torture_synchronize_expedited(void) } static struct rcu_torture_ops srcu_ops = { + .ttype = SRCU_FLAVOR, .init = rcu_sync_torture_init, .readlock = srcu_torture_read_lock, .read_delay = srcu_read_delay, @@ -527,6 +584,7 @@ static void rcu_sched_torture_deferred_free(struct rcu_torture *p) } static struct rcu_torture_ops sched_ops = { + .ttype = RCU_SCHED_FLAVOR, .init = rcu_sync_torture_init, .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ @@ -688,23 +746,59 @@ rcu_torture_fqs(void *arg) static int rcu_torture_writer(void *arg) { - bool exp; + unsigned long gp_snap; + bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal; + bool gp_sync1 = gp_sync; int i; struct rcu_torture *rp; - struct rcu_torture *rp1; struct rcu_torture *old_rp; static DEFINE_TORTURE_RANDOM(rand); + int synctype[] = { RTWS_DEF_FREE, RTWS_EXP_SYNC, + RTWS_COND_GET, RTWS_SYNC }; + int nsynctypes = 0; VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); - set_user_nice(current, MAX_NICE); + + /* Initialize synctype[] array. If none set, take default. */ + if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync) + gp_cond1 = gp_exp1 = gp_normal1 = gp_sync1 = true; + if (gp_cond1 && cur_ops->get_state && cur_ops->cond_sync) + synctype[nsynctypes++] = RTWS_COND_GET; + else if (gp_cond && (!cur_ops->get_state || !cur_ops->cond_sync)) + pr_alert("rcu_torture_writer: gp_cond without primitives.\n"); + if (gp_exp1 && cur_ops->exp_sync) + synctype[nsynctypes++] = RTWS_EXP_SYNC; + else if (gp_exp && !cur_ops->exp_sync) + pr_alert("rcu_torture_writer: gp_exp without primitives.\n"); + if (gp_normal1 && cur_ops->deferred_free) + synctype[nsynctypes++] = RTWS_DEF_FREE; + else if (gp_normal && !cur_ops->deferred_free) + pr_alert("rcu_torture_writer: gp_normal without primitives.\n"); + if (gp_sync1 && cur_ops->sync) + synctype[nsynctypes++] = RTWS_SYNC; + else if (gp_sync && !cur_ops->sync) + pr_alert("rcu_torture_writer: gp_sync without primitives.\n"); + if (WARN_ONCE(nsynctypes == 0, + "rcu_torture_writer: No update-side primitives.\n")) { + /* + * No updates primitives, so don't try updating. + * The resulting test won't be testing much, hence the + * above WARN_ONCE(). + */ + rcu_torture_writer_state = RTWS_STOPPING; + torture_kthread_stopping("rcu_torture_writer"); + } do { + rcu_torture_writer_state = RTWS_FIXED_DELAY; schedule_timeout_uninterruptible(1); rp = rcu_torture_alloc(); if (rp == NULL) continue; rp->rtort_pipe_count = 0; + rcu_torture_writer_state = RTWS_DELAY; udelay(torture_random(&rand) & 0x3ff); + rcu_torture_writer_state = RTWS_REPLACE; old_rp = rcu_dereference_check(rcu_torture_current, current == writer_task); rp->rtort_mbtest = 1; @@ -716,35 +810,42 @@ rcu_torture_writer(void *arg) i = RCU_TORTURE_PIPE_LEN; atomic_inc(&rcu_torture_wcount[i]); old_rp->rtort_pipe_count++; - if (gp_normal == gp_exp) - exp = !!(torture_random(&rand) & 0x80); - else - exp = gp_exp; - if (!exp) { + switch (synctype[torture_random(&rand) % nsynctypes]) { + case RTWS_DEF_FREE: + rcu_torture_writer_state = RTWS_DEF_FREE; cur_ops->deferred_free(old_rp); - } else { + break; + case RTWS_EXP_SYNC: + rcu_torture_writer_state = RTWS_EXP_SYNC; cur_ops->exp_sync(); - list_add(&old_rp->rtort_free, - &rcu_torture_removed); - list_for_each_entry_safe(rp, rp1, - &rcu_torture_removed, - rtort_free) { - i = rp->rtort_pipe_count; - if (i > RCU_TORTURE_PIPE_LEN) - i = RCU_TORTURE_PIPE_LEN; - atomic_inc(&rcu_torture_wcount[i]); - if (++rp->rtort_pipe_count >= - RCU_TORTURE_PIPE_LEN) { - rp->rtort_mbtest = 0; - list_del(&rp->rtort_free); - rcu_torture_free(rp); - } - } + rcu_torture_pipe_update(old_rp); + break; + case RTWS_COND_GET: + rcu_torture_writer_state = RTWS_COND_GET; + gp_snap = cur_ops->get_state(); + i = torture_random(&rand) % 16; + if (i != 0) + schedule_timeout_interruptible(i); + udelay(torture_random(&rand) % 1000); + rcu_torture_writer_state = RTWS_COND_SYNC; + cur_ops->cond_sync(gp_snap); + rcu_torture_pipe_update(old_rp); + break; + case RTWS_SYNC: + rcu_torture_writer_state = RTWS_SYNC; + cur_ops->sync(); + rcu_torture_pipe_update(old_rp); + break; + default: + WARN_ON_ONCE(1); + break; } } rcutorture_record_progress(++rcu_torture_current_version); + rcu_torture_writer_state = RTWS_STUTTER; stutter_wait("rcu_torture_writer"); } while (!torture_must_stop()); + rcu_torture_writer_state = RTWS_STOPPING; torture_kthread_stopping("rcu_torture_writer"); return 0; } @@ -784,7 +885,7 @@ rcu_torture_fakewriter(void *arg) return 0; } -void rcutorture_trace_dump(void) +static void rcutorture_trace_dump(void) { static atomic_t beenhere = ATOMIC_INIT(0); @@ -918,11 +1019,13 @@ rcu_torture_reader(void *arg) __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); cur_ops->readunlock(idx); - schedule(); + cond_resched(); stutter_wait("rcu_torture_reader"); } while (!torture_must_stop()); - if (irqreader && cur_ops->irq_capable) + if (irqreader && cur_ops->irq_capable) { del_timer_sync(&t); + destroy_timer_on_stack(&t); + } torture_kthread_stopping("rcu_torture_reader"); return 0; } @@ -937,6 +1040,7 @@ rcu_torture_printk(char *page) int i; long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 }; long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 }; + static unsigned long rtcv_snap = ULONG_MAX; for_each_possible_cpu(cpu) { for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) { @@ -997,6 +1101,22 @@ rcu_torture_printk(char *page) page += sprintf(page, "\n"); if (cur_ops->stats) cur_ops->stats(page); + if (rtcv_snap == rcu_torture_current_version && + rcu_torture_current != NULL) { + int __maybe_unused flags; + unsigned long __maybe_unused gpnum; + unsigned long __maybe_unused completed; + + 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); + show_rcu_gp_kthreads(); + rcutorture_trace_dump(); + } + rtcv_snap = rcu_torture_current_version; } /* @@ -1146,7 +1266,7 @@ static int __init rcu_torture_stall_init(void) } /* Callback function for RCU barrier testing. */ -void rcu_torture_barrier_cbf(struct rcu_head *rcu) +static void rcu_torture_barrier_cbf(struct rcu_head *rcu) { atomic_inc(&barrier_cbs_invoked); } @@ -1416,7 +1536,8 @@ rcu_torture_init(void) &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops, }; - torture_init_begin(torture_type, verbose, &rcutorture_runnable); + if (!torture_init_begin(torture_type, verbose, &rcutorture_runnable)) + return -EBUSY; /* Process args and tell the world that the torturer is on the job. */ for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { @@ -1441,10 +1562,13 @@ rcu_torture_init(void) if (cur_ops->init) cur_ops->init(); /* no "goto unwind" prior to this point!!! */ - if (nreaders >= 0) + if (nreaders >= 0) { nrealreaders = nreaders; - else - nrealreaders = 2 * num_online_cpus(); + } else { + nrealreaders = num_online_cpus() - 1; + if (nrealreaders <= 0) + nrealreaders = 1; + } rcu_torture_print_module_parms(cur_ops, "Start of test"); /* Set up the freelist. */ @@ -1533,7 +1657,8 @@ rcu_torture_init(void) fqs_duration = 0; if (fqs_duration) { /* Create the fqs thread */ - torture_create_kthread(rcu_torture_fqs, NULL, fqs_task); + firsterr = torture_create_kthread(rcu_torture_fqs, NULL, + fqs_task); if (firsterr) goto unwind; } diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h index 431528520562..858c56569127 100644 --- a/kernel/rcu/tiny_plugin.h +++ b/kernel/rcu/tiny_plugin.h @@ -144,7 +144,7 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp) return; rcp->ticks_this_gp++; j = jiffies; - js = rcp->jiffies_stall; + js = ACCESS_ONCE(rcp->jiffies_stall); if (*rcp->curtail && ULONG_CMP_GE(j, js)) { pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n", rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting, @@ -152,17 +152,17 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp) dump_stack(); } if (*rcp->curtail && ULONG_CMP_GE(j, js)) - rcp->jiffies_stall = jiffies + + ACCESS_ONCE(rcp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; else if (ULONG_CMP_GE(j, js)) - rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check(); + ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check(); } static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp) { rcp->ticks_this_gp = 0; rcp->gp_start = jiffies; - rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check(); + ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check(); } static void check_cpu_stalls(void) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 0c47e300210a..3e3f13e8b429 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -101,7 +101,7 @@ DEFINE_PER_CPU(struct rcu_data, sname##_data) RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh); -static struct rcu_state *rcu_state; +static struct rcu_state *rcu_state_p; LIST_HEAD(rcu_struct_flavors); /* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */ @@ -243,7 +243,7 @@ static ulong jiffies_till_next_fqs = ULONG_MAX; module_param(jiffies_till_first_fqs, ulong, 0644); module_param(jiffies_till_next_fqs, ulong, 0644); -static void rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, +static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp, bool *isidle, @@ -271,6 +271,15 @@ long rcu_batches_completed_bh(void) EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); /* + * Force a quiescent state. + */ +void rcu_force_quiescent_state(void) +{ + force_quiescent_state(rcu_state_p); +} +EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); + +/* * Force a quiescent state for RCU BH. */ void rcu_bh_force_quiescent_state(void) @@ -280,6 +289,21 @@ void rcu_bh_force_quiescent_state(void) EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); /* + * Show the state of the grace-period kthreads. + */ +void show_rcu_gp_kthreads(void) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + pr_info("%s: wait state: %d ->state: %#lx\n", + rsp->name, rsp->gp_state, rsp->gp_kthread->state); + /* sched_show_task(rsp->gp_kthread); */ + } +} +EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); + +/* * Record the number of times rcutorture tests have been initiated and * terminated. This information allows the debugfs tracing stats to be * correlated to the rcutorture messages, even when the rcutorture module @@ -294,6 +318,39 @@ void rcutorture_record_test_transition(void) EXPORT_SYMBOL_GPL(rcutorture_record_test_transition); /* + * Send along grace-period-related data for rcutorture diagnostics. + */ +void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, + unsigned long *gpnum, unsigned long *completed) +{ + struct rcu_state *rsp = NULL; + + switch (test_type) { + case RCU_FLAVOR: + rsp = rcu_state_p; + break; + case RCU_BH_FLAVOR: + rsp = &rcu_bh_state; + break; + case RCU_SCHED_FLAVOR: + rsp = &rcu_sched_state; + break; + default: + break; + } + if (rsp != NULL) { + *flags = ACCESS_ONCE(rsp->gp_flags); + *gpnum = ACCESS_ONCE(rsp->gpnum); + *completed = ACCESS_ONCE(rsp->completed); + return; + } + *flags = 0; + *gpnum = 0; + *completed = 0; +} +EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); + +/* * Record the number of writer passes through the current rcutorture test. * This is also used to correlate debugfs tracing stats with the rcutorture * messages. @@ -324,6 +381,28 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp) } /* + * Return the root node of the specified rcu_state structure. + */ +static struct rcu_node *rcu_get_root(struct rcu_state *rsp) +{ + return &rsp->node[0]; +} + +/* + * Is there any need for future grace periods? + * Interrupts must be disabled. If the caller does not hold the root + * rnp_node structure's ->lock, the results are advisory only. + */ +static int rcu_future_needs_gp(struct rcu_state *rsp) +{ + struct rcu_node *rnp = rcu_get_root(rsp); + int idx = (ACCESS_ONCE(rnp->completed) + 1) & 0x1; + int *fp = &rnp->need_future_gp[idx]; + + return ACCESS_ONCE(*fp); +} + +/* * Does the current CPU require a not-yet-started grace period? * The caller must have disabled interrupts to prevent races with * normal callback registry. @@ -335,7 +414,7 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) if (rcu_gp_in_progress(rsp)) return 0; /* No, a grace period is already in progress. */ - if (rcu_nocb_needs_gp(rsp)) + if (rcu_future_needs_gp(rsp)) return 1; /* Yes, a no-CBs CPU needs one. */ if (!rdp->nxttail[RCU_NEXT_TAIL]) return 0; /* No, this is a no-CBs (or offline) CPU. */ @@ -350,14 +429,6 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) } /* - * Return the root node of the specified rcu_state structure. - */ -static struct rcu_node *rcu_get_root(struct rcu_state *rsp) -{ - return &rsp->node[0]; -} - -/* * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state * * If the new value of the ->dynticks_nesting counter now is zero, @@ -758,7 +829,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, { rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks); rcu_sysidle_check_cpu(rdp, isidle, maxj); - return (rdp->dynticks_snap & 0x1) == 0; + if ((rdp->dynticks_snap & 0x1) == 0) { + trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + return 1; + } else { + return 0; + } } /* @@ -834,7 +910,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, * we will beat on the first one until it gets unstuck, then move * to the next. Only do this for the primary flavor of RCU. */ - if (rdp->rsp == rcu_state && + if (rdp->rsp == rcu_state_p && ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { rdp->rsp->jiffies_resched += 5; resched_cpu(rdp->cpu); @@ -851,7 +927,7 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) rsp->gp_start = j; smp_wmb(); /* Record start time before stall time. */ j1 = rcu_jiffies_till_stall_check(); - rsp->jiffies_stall = j + j1; + ACCESS_ONCE(rsp->jiffies_stall) = j + j1; rsp->jiffies_resched = j + j1 / 2; } @@ -890,12 +966,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp) /* Only let one CPU complain about others per time interval. */ raw_spin_lock_irqsave(&rnp->lock, flags); - delta = jiffies - rsp->jiffies_stall; + delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall); if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } - rsp->jiffies_stall = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; + ACCESS_ONCE(rsp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; raw_spin_unlock_irqrestore(&rnp->lock, flags); /* @@ -932,9 +1008,9 @@ static void print_other_cpu_stall(struct rcu_state *rsp) print_cpu_stall_info_end(); for_each_possible_cpu(cpu) totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen; - pr_cont("(detected by %d, t=%ld jiffies, g=%lu, c=%lu, q=%lu)\n", + pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n", smp_processor_id(), (long)(jiffies - rsp->gp_start), - rsp->gpnum, rsp->completed, totqlen); + (long)rsp->gpnum, (long)rsp->completed, totqlen); if (ndetected == 0) pr_err("INFO: Stall ended before state dump start\n"); else if (!trigger_all_cpu_backtrace()) @@ -947,12 +1023,6 @@ static void print_other_cpu_stall(struct rcu_state *rsp) force_quiescent_state(rsp); /* Kick them all. */ } -/* - * This function really isn't for public consumption, but RCU is special in - * that context switches can allow the state machine to make progress. - */ -extern void resched_cpu(int cpu); - static void print_cpu_stall(struct rcu_state *rsp) { int cpu; @@ -971,14 +1041,15 @@ static void print_cpu_stall(struct rcu_state *rsp) print_cpu_stall_info_end(); for_each_possible_cpu(cpu) totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen; - pr_cont(" (t=%lu jiffies g=%lu c=%lu q=%lu)\n", - jiffies - rsp->gp_start, rsp->gpnum, rsp->completed, totqlen); + pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n", + jiffies - rsp->gp_start, + (long)rsp->gpnum, (long)rsp->completed, totqlen); if (!trigger_all_cpu_backtrace()) dump_stack(); raw_spin_lock_irqsave(&rnp->lock, flags); - if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall)) - rsp->jiffies_stall = jiffies + + if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall))) + ACCESS_ONCE(rsp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -1062,7 +1133,7 @@ void rcu_cpu_stall_reset(void) struct rcu_state *rsp; for_each_rcu_flavor(rsp) - rsp->jiffies_stall = jiffies + ULONG_MAX / 2; + ACCESS_ONCE(rsp->jiffies_stall) = jiffies + ULONG_MAX / 2; } /* @@ -1123,15 +1194,18 @@ static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, /* * Start some future grace period, as needed to handle newly arrived * callbacks. The required future grace periods are recorded in each - * rcu_node structure's ->need_future_gp field. + * rcu_node structure's ->need_future_gp field. Returns true if there + * is reason to awaken the grace-period kthread. * * The caller must hold the specified rcu_node structure's ->lock. */ -static unsigned long __maybe_unused -rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp) +static bool __maybe_unused +rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, + unsigned long *c_out) { unsigned long c; int i; + bool ret = false; struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); /* @@ -1142,7 +1216,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp) trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf")); if (rnp->need_future_gp[c & 0x1]) { trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf")); - return c; + goto out; } /* @@ -1156,7 +1230,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp) ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) { rnp->need_future_gp[c & 0x1]++; trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf")); - return c; + goto out; } /* @@ -1197,12 +1271,15 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp) trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot")); } else { trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot")); - rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp); + ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp); } unlock_out: if (rnp != rnp_root) raw_spin_unlock(&rnp_root->lock); - return c; +out: + if (c_out != NULL) + *c_out = c; + return ret; } /* @@ -1226,25 +1303,43 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) } /* + * Awaken the grace-period kthread for the specified flavor of RCU. + * Don't do a self-awaken, and don't bother awakening when there is + * nothing for the grace-period kthread to do (as in several CPUs + * raced to awaken, and we lost), and finally don't try to awaken + * a kthread that has not yet been created. + */ +static void rcu_gp_kthread_wake(struct rcu_state *rsp) +{ + if (current == rsp->gp_kthread || + !ACCESS_ONCE(rsp->gp_flags) || + !rsp->gp_kthread) + return; + wake_up(&rsp->gp_wq); +} + +/* * If there is room, assign a ->completed number to any callbacks on * this CPU that have not already been assigned. Also accelerate any * callbacks that were previously assigned a ->completed number that has * since proven to be too conservative, which can happen if callbacks get * assigned a ->completed number while RCU is idle, but with reference to * a non-root rcu_node structure. This function is idempotent, so it does - * not hurt to call it repeatedly. + * not hurt to call it repeatedly. Returns an flag saying that we should + * awaken the RCU grace-period kthread. * * The caller must hold rnp->lock with interrupts disabled. */ -static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, +static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { unsigned long c; int i; + bool ret; /* If the CPU has no callbacks, nothing to do. */ if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL]) - return; + return false; /* * Starting from the sublist containing the callbacks most @@ -1273,7 +1368,7 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * be grouped into. */ if (++i >= RCU_NEXT_TAIL) - return; + return false; /* * Assign all subsequent callbacks' ->completed number to the next @@ -1285,13 +1380,14 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, rdp->nxtcompleted[i] = c; } /* Record any needed additional grace periods. */ - rcu_start_future_gp(rnp, rdp); + ret = rcu_start_future_gp(rnp, rdp, NULL); /* Trace depending on how much we were able to accelerate. */ if (!*rdp->nxttail[RCU_WAIT_TAIL]) trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB")); else trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB")); + return ret; } /* @@ -1300,17 +1396,18 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL * sublist. This function is idempotent, so it does not hurt to * invoke it repeatedly. As long as it is not invoked -too- often... + * Returns true if the RCU grace-period kthread needs to be awakened. * * The caller must hold rnp->lock with interrupts disabled. */ -static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, +static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { int i, j; /* If the CPU has no callbacks, nothing to do. */ if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL]) - return; + return false; /* * Find all callbacks whose ->completed numbers indicate that they @@ -1334,26 +1431,30 @@ static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, } /* Classify any remaining callbacks. */ - rcu_accelerate_cbs(rsp, rnp, rdp); + return rcu_accelerate_cbs(rsp, rnp, rdp); } /* * Update CPU-local rcu_data state to record the beginnings and ends of * grace periods. The caller must hold the ->lock of the leaf rcu_node * structure corresponding to the current CPU, and must have irqs disabled. + * Returns true if the grace-period kthread needs to be awakened. */ -static void __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) +static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) { + bool ret; + /* Handle the ends of any preceding grace periods first. */ if (rdp->completed == rnp->completed) { /* No grace period end, so just accelerate recent callbacks. */ - rcu_accelerate_cbs(rsp, rnp, rdp); + ret = rcu_accelerate_cbs(rsp, rnp, rdp); } else { /* Advance callbacks. */ - rcu_advance_cbs(rsp, rnp, rdp); + ret = rcu_advance_cbs(rsp, rnp, rdp); /* Remember that we saw this grace-period completion. */ rdp->completed = rnp->completed; @@ -1372,11 +1473,13 @@ static void __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, struc rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); } + return ret; } static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; + bool needwake; struct rcu_node *rnp; local_irq_save(flags); @@ -1388,8 +1491,10 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) return; } smp_mb__after_unlock_lock(); - __note_gp_changes(rsp, rnp, rdp); + needwake = __note_gp_changes(rsp, rnp, rdp); raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (needwake) + rcu_gp_kthread_wake(rsp); } /* @@ -1403,12 +1508,12 @@ static int rcu_gp_init(struct rcu_state *rsp) rcu_bind_gp_kthread(); raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); - if (rsp->gp_flags == 0) { + if (!ACCESS_ONCE(rsp->gp_flags)) { /* Spurious wakeup, tell caller to go back to sleep. */ raw_spin_unlock_irq(&rnp->lock); return 0; } - rsp->gp_flags = 0; /* Clear all flags: New grace period. */ + ACCESS_ONCE(rsp->gp_flags) = 0; /* Clear all flags: New grace period. */ if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) { /* @@ -1453,7 +1558,7 @@ static int rcu_gp_init(struct rcu_state *rsp) WARN_ON_ONCE(rnp->completed != rsp->completed); ACCESS_ONCE(rnp->completed) = rsp->completed; if (rnp == rdp->mynode) - __note_gp_changes(rsp, rnp, rdp); + (void)__note_gp_changes(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); trace_rcu_grace_period_init(rsp->name, rnp->gpnum, rnp->level, rnp->grplo, @@ -1501,7 +1606,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); - rsp->gp_flags &= ~RCU_GP_FLAG_FQS; + ACCESS_ONCE(rsp->gp_flags) &= ~RCU_GP_FLAG_FQS; raw_spin_unlock_irq(&rnp->lock); } return fqs_state; @@ -1513,6 +1618,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) static void rcu_gp_cleanup(struct rcu_state *rsp) { unsigned long gp_duration; + bool needgp = false; int nocb = 0; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); @@ -1548,7 +1654,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) ACCESS_ONCE(rnp->completed) = rsp->gpnum; rdp = this_cpu_ptr(rsp->rda); if (rnp == rdp->mynode) - __note_gp_changes(rsp, rnp, rdp); + needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ nocb += rcu_future_gp_cleanup(rsp, rnp); raw_spin_unlock_irq(&rnp->lock); @@ -1564,9 +1670,10 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); rsp->fqs_state = RCU_GP_IDLE; rdp = this_cpu_ptr(rsp->rda); - rcu_advance_cbs(rsp, rnp, rdp); /* Reduce false positives below. */ - if (cpu_needs_another_gp(rsp, rdp)) { - rsp->gp_flags = RCU_GP_FLAG_INIT; + /* Advance CBs to reduce false positives below. */ + needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp; + if (needgp || cpu_needs_another_gp(rsp, rdp)) { + ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT; trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("newreq")); @@ -1593,6 +1700,7 @@ static int __noreturn rcu_gp_kthread(void *arg) trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("reqwait")); + rsp->gp_state = RCU_GP_WAIT_GPS; wait_event_interruptible(rsp->gp_wq, ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); @@ -1620,6 +1728,7 @@ static int __noreturn rcu_gp_kthread(void *arg) trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("fqswait")); + rsp->gp_state = RCU_GP_WAIT_FQS; ret = wait_event_interruptible_timeout(rsp->gp_wq, ((gf = ACCESS_ONCE(rsp->gp_flags)) & RCU_GP_FLAG_FQS) || @@ -1665,14 +1774,6 @@ static int __noreturn rcu_gp_kthread(void *arg) } } -static void rsp_wakeup(struct irq_work *work) -{ - struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work); - - /* Wake up rcu_gp_kthread() to start the grace period. */ - wake_up(&rsp->gp_wq); -} - /* * Start a new RCU grace period if warranted, re-initializing the hierarchy * in preparation for detecting the next grace period. The caller must hold @@ -1681,8 +1782,10 @@ static void rsp_wakeup(struct irq_work *work) * Note that it is legal for a dying CPU (which is marked as offline) to * invoke this function. This can happen when the dying CPU reports its * quiescent state. + * + * Returns true if the grace-period kthread must be awakened. */ -static void +static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { @@ -1693,20 +1796,18 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, * or a grace period is already in progress. * Either way, don't start a new grace period. */ - return; + return false; } - rsp->gp_flags = RCU_GP_FLAG_INIT; + ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT; trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("newreq")); /* * We can't do wakeups while holding the rnp->lock, as that * could cause possible deadlocks with the rq->lock. Defer - * the wakeup to interrupt context. And don't bother waking - * up the running kthread. + * the wakeup to our caller. */ - if (current != rsp->gp_kthread) - irq_work_queue(&rsp->wakeup_work); + return true; } /* @@ -1715,12 +1816,14 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, * is invoked indirectly from rcu_advance_cbs(), which would result in * endless recursion -- or would do so if it wasn't for the self-deadlock * that is encountered beforehand. + * + * Returns true if the grace-period kthread needs to be awakened. */ -static void -rcu_start_gp(struct rcu_state *rsp) +static bool rcu_start_gp(struct rcu_state *rsp) { struct rcu_data *rdp = this_cpu_ptr(rsp->rda); struct rcu_node *rnp = rcu_get_root(rsp); + bool ret = false; /* * If there is no grace period in progress right now, any @@ -1730,8 +1833,9 @@ rcu_start_gp(struct rcu_state *rsp) * resulting in pointless grace periods. So, advance callbacks * then start the grace period! */ - rcu_advance_cbs(rsp, rnp, rdp); - rcu_start_gp_advanced(rsp, rnp, rdp); + ret = rcu_advance_cbs(rsp, rnp, rdp) || ret; + ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret; + return ret; } /* @@ -1820,6 +1924,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; unsigned long mask; + bool needwake; struct rcu_node *rnp; rnp = rdp->mynode; @@ -1848,9 +1953,11 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * This GP can't end until cpu checks in, so all of our * callbacks can be processed during the next GP. */ - rcu_accelerate_cbs(rsp, rnp, rdp); + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */ + if (needwake) + rcu_gp_kthread_wake(rsp); } } @@ -1951,7 +2058,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags) { int i; - struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); + struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); /* No-CBs CPUs are handled specially. */ if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags)) @@ -2320,7 +2427,7 @@ static void force_quiescent_state(struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp_old->lock, flags); return; /* Someone beat us to it. */ } - rsp->gp_flags |= RCU_GP_FLAG_FQS; + ACCESS_ONCE(rsp->gp_flags) |= RCU_GP_FLAG_FQS; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ } @@ -2334,7 +2441,8 @@ static void __rcu_process_callbacks(struct rcu_state *rsp) { unsigned long flags; - struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); + bool needwake; + struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); WARN_ON_ONCE(rdp->beenonline == 0); @@ -2345,8 +2453,10 @@ __rcu_process_callbacks(struct rcu_state *rsp) local_irq_save(flags); if (cpu_needs_another_gp(rsp, rdp)) { raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */ - rcu_start_gp(rsp); + needwake = rcu_start_gp(rsp); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); + if (needwake) + rcu_gp_kthread_wake(rsp); } else { local_irq_restore(flags); } @@ -2404,6 +2514,8 @@ static void invoke_rcu_core(void) static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, struct rcu_head *head, unsigned long flags) { + bool needwake; + /* * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. @@ -2433,8 +2545,10 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, raw_spin_lock(&rnp_root->lock); smp_mb__after_unlock_lock(); - rcu_start_gp(rsp); + needwake = rcu_start_gp(rsp); raw_spin_unlock(&rnp_root->lock); + if (needwake) + rcu_gp_kthread_wake(rsp); } else { /* Give the grace period a kick. */ rdp->blimit = LONG_MAX; @@ -2537,6 +2651,20 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) EXPORT_SYMBOL_GPL(call_rcu_bh); /* + * Queue an RCU callback for lazy invocation after a grace period. + * This will likely be later named something like "call_rcu_lazy()", + * but this change will require some way of tagging the lazy RCU + * callbacks in the list of pending callbacks. Until then, this + * function may only be called from __kfree_rcu(). + */ +void kfree_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, rcu_state_p, -1, 1); +} +EXPORT_SYMBOL_GPL(kfree_call_rcu); + +/* * Because a context switch is a grace period for RCU-sched and RCU-bh, * any blocking grace-period wait automatically implies a grace period * if there is only one CPU online at any point time during execution @@ -2659,7 +2787,7 @@ unsigned long get_state_synchronize_rcu(void) * time-consuming work between get_state_synchronize_rcu() * and cond_synchronize_rcu(). */ - return smp_load_acquire(&rcu_state->gpnum); + return smp_load_acquire(&rcu_state_p->gpnum); } EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); @@ -2685,7 +2813,7 @@ void cond_synchronize_rcu(unsigned long oldstate) * Ensure that this load happens before any RCU-destructive * actions the caller might carry out after we return. */ - newstate = smp_load_acquire(&rcu_state->completed); + newstate = smp_load_acquire(&rcu_state_p->completed); if (ULONG_CMP_GE(oldstate, newstate)) synchronize_rcu(); } @@ -2988,7 +3116,7 @@ static void rcu_barrier_callback(struct rcu_head *rhp) static void rcu_barrier_func(void *type) { struct rcu_state *rsp = type; - struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); + struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); _rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done); atomic_inc(&rsp->barrier_cpu_count); @@ -3160,7 +3288,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) * that this CPU cannot possibly have any RCU callbacks in flight yet. */ static void -rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) +rcu_init_percpu_data(int cpu, struct rcu_state *rsp) { unsigned long flags; unsigned long mask; @@ -3173,7 +3301,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->beenonline = 1; /* We have now been online. */ - rdp->preemptible = preemptible; rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; @@ -3217,8 +3344,7 @@ static void rcu_prepare_cpu(int cpu) struct rcu_state *rsp; for_each_rcu_flavor(rsp) - rcu_init_percpu_data(cpu, rsp, - strcmp(rsp->name, "rcu_preempt") == 0); + rcu_init_percpu_data(cpu, rsp); } /* @@ -3228,7 +3354,7 @@ static int rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { long cpu = (long)hcpu; - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); struct rcu_node *rnp = rdp->mynode; struct rcu_state *rsp; @@ -3402,8 +3528,8 @@ static void __init rcu_init_one(struct rcu_state *rsp, rnp->qsmaskinit = 0; rnp->grplo = j * cpustride; rnp->grphi = (j + 1) * cpustride - 1; - if (rnp->grphi >= NR_CPUS) - rnp->grphi = NR_CPUS - 1; + if (rnp->grphi >= nr_cpu_ids) + rnp->grphi = nr_cpu_ids - 1; if (i == 0) { rnp->grpnum = 0; rnp->grpmask = 0; @@ -3422,7 +3548,6 @@ static void __init rcu_init_one(struct rcu_state *rsp, rsp->rda = rda; init_waitqueue_head(&rsp->gp_wq); - init_irq_work(&rsp->wakeup_work, rsp_wakeup); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 75dc3c39a02a..bf2c1e669691 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -252,7 +252,6 @@ struct rcu_data { bool passed_quiesce; /* User-mode/idle loop etc. */ bool qs_pending; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ - bool preemptible; /* Preemptible RCU? */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ #ifdef CONFIG_RCU_CPU_STALL_INFO @@ -406,7 +405,8 @@ struct rcu_state { unsigned long completed; /* # of last completed gp. */ struct task_struct *gp_kthread; /* Task for grace periods. */ wait_queue_head_t gp_wq; /* Where GP task waits. */ - int gp_flags; /* Commands for GP task. */ + short gp_flags; /* Commands for GP task. */ + short gp_state; /* GP kthread sleep state. */ /* End of fields guarded by root rcu_node's lock. */ @@ -462,13 +462,17 @@ struct rcu_state { const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ struct list_head flavors; /* List of RCU flavors. */ - struct irq_work wakeup_work; /* Postponed wakeups */ }; /* Values for rcu_state structure's gp_flags field. */ #define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */ #define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */ +/* Values for rcu_state structure's gp_flags field. */ +#define RCU_GP_WAIT_INIT 0 /* Initial state. */ +#define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ +#define RCU_GP_WAIT_FQS 2 /* Wait for force-quiescent-state time. */ + extern struct list_head rcu_struct_flavors; /* Sequence through rcu_state structures for each RCU flavor. */ @@ -547,7 +551,6 @@ 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 int rcu_nocb_needs_gp(struct rcu_state *rsp); 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 962d1d589929..29977ae84e7e 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -116,7 +116,7 @@ static void __init rcu_bootup_announce_oddness(void) #ifdef CONFIG_TREE_PREEMPT_RCU RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu); -static struct rcu_state *rcu_state = &rcu_preempt_state; +static struct rcu_state *rcu_state_p = &rcu_preempt_state; static int rcu_preempted_readers_exp(struct rcu_node *rnp); @@ -149,15 +149,6 @@ long rcu_batches_completed(void) EXPORT_SYMBOL_GPL(rcu_batches_completed); /* - * Force a quiescent state for preemptible RCU. - */ -void rcu_force_quiescent_state(void) -{ - force_quiescent_state(&rcu_preempt_state); -} -EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); - -/* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is * not in a quiescent state. There might be any number of tasks blocked @@ -688,20 +679,6 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu); -/* - * Queue an RCU callback for lazy invocation after a grace period. - * This will likely be later named something like "call_rcu_lazy()", - * but this change will require some way of tagging the lazy RCU - * callbacks in the list of pending callbacks. Until then, this - * function may only be called from __kfree_rcu(). - */ -void kfree_call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *rcu)) -{ - __call_rcu(head, func, &rcu_preempt_state, -1, 1); -} -EXPORT_SYMBOL_GPL(kfree_call_rcu); - /** * synchronize_rcu - wait until a grace period has elapsed. * @@ -970,7 +947,7 @@ void exit_rcu(void) #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ -static struct rcu_state *rcu_state = &rcu_sched_state; +static struct rcu_state *rcu_state_p = &rcu_sched_state; /* * Tell them what RCU they are running. @@ -991,16 +968,6 @@ long rcu_batches_completed(void) EXPORT_SYMBOL_GPL(rcu_batches_completed); /* - * Force a quiescent state for RCU, which, because there is no preemptible - * RCU, becomes the same as rcu-sched. - */ -void rcu_force_quiescent_state(void) -{ - rcu_sched_force_quiescent_state(); -} -EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); - -/* * Because preemptible RCU does not exist, we never have to check for * CPUs being in quiescent states. */ @@ -1080,22 +1047,6 @@ static void rcu_preempt_check_callbacks(int cpu) } /* - * Queue an RCU callback for lazy invocation after a grace period. - * This will likely be later named something like "call_rcu_lazy()", - * but this change will require some way of tagging the lazy RCU - * callbacks in the list of pending callbacks. Until then, this - * function may only be called from __kfree_rcu(). - * - * Because there is no preemptible RCU, we use RCU-sched instead. - */ -void kfree_call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *rcu)) -{ - __call_rcu(head, func, &rcu_sched_state, -1, 1); -} -EXPORT_SYMBOL_GPL(kfree_call_rcu); - -/* * Wait for an rcu-preempt grace period, but make it happen quickly. * But because preemptible RCU does not exist, map to rcu-sched. */ @@ -1517,11 +1468,11 @@ static int __init rcu_spawn_kthreads(void) for_each_possible_cpu(cpu) per_cpu(rcu_cpu_has_work, cpu) = 0; BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); - rnp = rcu_get_root(rcu_state); - (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); + rnp = rcu_get_root(rcu_state_p); + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); if (NUM_RCU_NODES > 1) { - rcu_for_each_leaf_node(rcu_state, rnp) - (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); + rcu_for_each_leaf_node(rcu_state_p, rnp) + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); } return 0; } @@ -1529,12 +1480,12 @@ early_initcall(rcu_spawn_kthreads); static void rcu_prepare_kthreads(int cpu) { - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); struct rcu_node *rnp = rdp->mynode; /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ if (rcu_scheduler_fully_active) - (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); } #else /* #ifdef CONFIG_RCU_BOOST */ @@ -1744,6 +1695,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj) static void rcu_prepare_for_idle(int cpu) { #ifndef CONFIG_RCU_NOCB_CPU_ALL + bool needwake; struct rcu_data *rdp; struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); struct rcu_node *rnp; @@ -1792,8 +1744,10 @@ static void rcu_prepare_for_idle(int cpu) rnp = rdp->mynode; raw_spin_lock(&rnp->lock); /* irqs already disabled. */ smp_mb__after_unlock_lock(); - rcu_accelerate_cbs(rsp, rnp, rdp); + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + if (needwake) + rcu_gp_kthread_wake(rsp); } #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ } @@ -1855,7 +1809,7 @@ static void rcu_oom_notify_cpu(void *unused) struct rcu_data *rdp; for_each_rcu_flavor(rsp) { - rdp = __this_cpu_ptr(rsp->rda); + rdp = raw_cpu_ptr(rsp->rda); if (rdp->qlen_lazy != 0) { atomic_inc(&oom_callback_count); rsp->call(&rdp->oom_head, rcu_oom_callback); @@ -1997,7 +1951,7 @@ static void increment_cpu_stall_ticks(void) struct rcu_state *rsp; for_each_rcu_flavor(rsp) - __this_cpu_ptr(rsp->rda)->ticks_this_gp++; + raw_cpu_inc(rsp->rda->ticks_this_gp); } #else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ @@ -2068,19 +2022,6 @@ static int __init parse_rcu_nocb_poll(char *arg) early_param("rcu_nocb_poll", parse_rcu_nocb_poll); /* - * Do any no-CBs CPUs need another grace period? - * - * Interrupts must be disabled. If the caller does not hold the root - * rnp_node structure's ->lock, the results are advisory only. - */ -static int rcu_nocb_needs_gp(struct rcu_state *rsp) -{ - struct rcu_node *rnp = rcu_get_root(rsp); - - return rnp->need_future_gp[(ACCESS_ONCE(rnp->completed) + 1) & 0x1]; -} - -/* * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended * grace period. */ @@ -2109,7 +2050,7 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) } #ifndef CONFIG_RCU_NOCB_CPU_ALL -/* Is the specified CPU a no-CPUs CPU? */ +/* Is the specified CPU a no-CBs CPU? */ bool rcu_is_nocb_cpu(int cpu) { if (have_rcu_nocb_mask) @@ -2243,12 +2184,15 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) unsigned long c; bool d; unsigned long flags; + bool needwake; struct rcu_node *rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - c = rcu_start_future_gp(rnp, rdp); + needwake = rcu_start_future_gp(rnp, rdp, &c); raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (needwake) + rcu_gp_kthread_wake(rdp->rsp); /* * Wait for the grace period. Do so interruptibly to avoid messing @@ -2402,11 +2346,6 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) #else /* #ifdef CONFIG_RCU_NOCB_CPU */ -static int rcu_nocb_needs_gp(struct rcu_state *rsp) -{ - return 0; -} - static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { } @@ -2657,20 +2596,6 @@ static bool is_sysidle_rcu_state(struct rcu_state *rsp) } /* - * Bind the grace-period kthread for the sysidle flavor of RCU to the - * timekeeping CPU. - */ -static void rcu_bind_gp_kthread(void) -{ - int cpu = ACCESS_ONCE(tick_do_timer_cpu); - - if (cpu < 0 || cpu >= nr_cpu_ids) - return; - if (raw_smp_processor_id() != cpu) - set_cpus_allowed_ptr(current, cpumask_of(cpu)); -} - -/* * Return a delay in jiffies based on the number of CPUs, rcu_node * leaf fanout, and jiffies tick rate. The idea is to allow larger * systems more time to transition to full-idle state in order to @@ -2734,7 +2659,8 @@ static void rcu_sysidle(unsigned long j) static void rcu_sysidle_cancel(void) { smp_mb(); - ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT; + if (full_sysidle_state > RCU_SYSIDLE_SHORT) + ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT; } /* @@ -2880,10 +2806,6 @@ static bool is_sysidle_rcu_state(struct rcu_state *rsp) return false; } -static void rcu_bind_gp_kthread(void) -{ -} - static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, unsigned long maxj) { @@ -2914,3 +2836,19 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp) #endif /* #ifdef CONFIG_NO_HZ_FULL */ return 0; } + +/* + * Bind the grace-period kthread for the sysidle flavor of RCU to the + * timekeeping CPU. + */ +static void rcu_bind_gp_kthread(void) +{ +#ifdef CONFIG_NO_HZ_FULL + int cpu = ACCESS_ONCE(tick_do_timer_cpu); + + if (cpu < 0 || cpu >= nr_cpu_ids) + return; + if (raw_smp_processor_id() != cpu) + set_cpus_allowed_ptr(current, cpumask_of(cpu)); +#endif /* #ifdef CONFIG_NO_HZ_FULL */ +} diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 4c0a9b0af469..a2aeb4df0f60 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -320,6 +320,18 @@ int rcu_jiffies_till_stall_check(void) return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; } +void rcu_sysrq_start(void) +{ + if (!rcu_cpu_stall_suppress) + rcu_cpu_stall_suppress = 2; +} + +void rcu_sysrq_end(void) +{ + if (rcu_cpu_stall_suppress == 2) + rcu_cpu_stall_suppress = 0; +} + static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) { rcu_cpu_stall_suppress = 1; @@ -338,3 +350,21 @@ static int __init check_cpu_stall_init(void) early_initcall(check_cpu_stall_init); #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ + +/* + * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings. + */ + +DEFINE_PER_CPU(int, rcu_cond_resched_count); + +/* + * Report a set of RCU quiescent states, for use by cond_resched() + * and friends. Out of line due to being called infrequently. + */ +void rcu_resched(void) +{ + preempt_disable(); + __this_cpu_write(rcu_cond_resched_count, 0); + rcu_note_context_switch(smp_processor_id()); + preempt_enable(); +} diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0a7251678982..71d9a9c93954 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4084,6 +4084,7 @@ static void __cond_resched(void) int __sched _cond_resched(void) { + rcu_cond_resched(); if (should_resched()) { __cond_resched(); return 1; @@ -4102,15 +4103,18 @@ EXPORT_SYMBOL(_cond_resched); */ int __cond_resched_lock(spinlock_t *lock) { + bool need_rcu_resched = rcu_should_resched(); int resched = should_resched(); int ret = 0; lockdep_assert_held(lock); - if (spin_needbreak(lock) || resched) { + if (spin_needbreak(lock) || resched || need_rcu_resched) { spin_unlock(lock); if (resched) __cond_resched(); + else if (unlikely(need_rcu_resched)) + rcu_resched(); else cpu_relax(); ret = 1; @@ -4124,6 +4128,7 @@ int __sched __cond_resched_softirq(void) { BUG_ON(!in_softirq()); + rcu_cond_resched(); /* BH disabled OK, just recording QSes. */ if (should_resched()) { local_bh_enable(); __cond_resched(); diff --git a/kernel/softirq.c b/kernel/softirq.c index 92f24f5e8d52..5918d227730f 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -232,7 +232,6 @@ asmlinkage __visible void __do_softirq(void) bool in_hardirq; __u32 pending; int softirq_bit; - int cpu; /* * Mask out PF_MEMALLOC s current task context is borrowed for the @@ -247,7 +246,6 @@ asmlinkage __visible void __do_softirq(void) __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET); in_hardirq = lockdep_softirq_start(); - cpu = smp_processor_id(); restart: /* Reset the pending bitmask before enabling irqs */ set_softirq_pending(0); @@ -276,11 +274,11 @@ restart: prev_count, preempt_count()); preempt_count_set(prev_count); } - rcu_bh_qs(cpu); h++; pending >>= softirq_bit; } + rcu_bh_qs(smp_processor_id()); local_irq_disable(); pending = local_softirq_pending(); diff --git a/kernel/torture.c b/kernel/torture.c index acc9afc2f26e..40bb511cca48 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -335,13 +335,8 @@ static void torture_shuffle_tasks(void) shuffle_idle_cpu = cpumask_next(shuffle_idle_cpu, shuffle_tmp_mask); if (shuffle_idle_cpu >= nr_cpu_ids) shuffle_idle_cpu = -1; - if (shuffle_idle_cpu != -1) { + else cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask); - if (cpumask_empty(shuffle_tmp_mask)) { - put_online_cpus(); - return; - } - } mutex_lock(&shuffle_task_mutex); list_for_each_entry(stp, &shuffle_task_list, st_l) @@ -533,7 +528,11 @@ void stutter_wait(const char *title) while (ACCESS_ONCE(stutter_pause_test) || (torture_runnable && !ACCESS_ONCE(*torture_runnable))) { if (stutter_pause_test) - schedule_timeout_interruptible(1); + if (ACCESS_ONCE(stutter_pause_test) == 1) + schedule_timeout_interruptible(1); + else + while (ACCESS_ONCE(stutter_pause_test)) + cond_resched(); else schedule_timeout_interruptible(round_jiffies_relative(HZ)); torture_shutdown_absorb(title); @@ -550,7 +549,11 @@ static int torture_stutter(void *arg) VERBOSE_TOROUT_STRING("torture_stutter task started"); do { if (!torture_must_stop()) { - schedule_timeout_interruptible(stutter); + if (stutter > 1) { + schedule_timeout_interruptible(stutter - 1); + ACCESS_ONCE(stutter_pause_test) = 2; + } + schedule_timeout_interruptible(1); ACCESS_ONCE(stutter_pause_test) = 1; } if (!torture_must_stop()) @@ -596,21 +599,27 @@ static void torture_stutter_cleanup(void) * The runnable parameter points to a flag that controls whether or not * the test is currently runnable. If there is no such flag, pass in NULL. */ -void __init torture_init_begin(char *ttype, bool v, int *runnable) +bool torture_init_begin(char *ttype, bool v, int *runnable) { mutex_lock(&fullstop_mutex); + if (torture_type != NULL) { + pr_alert("torture_init_begin: refusing %s init: %s running", + ttype, torture_type); + mutex_unlock(&fullstop_mutex); + return false; + } torture_type = ttype; verbose = v; torture_runnable = runnable; fullstop = FULLSTOP_DONTSTOP; - + return true; } EXPORT_SYMBOL_GPL(torture_init_begin); /* * Tell the torture module that initialization is complete. */ -void __init torture_init_end(void) +void torture_init_end(void) { mutex_unlock(&fullstop_mutex); register_reboot_notifier(&torture_shutdown_nb); @@ -642,6 +651,9 @@ bool torture_cleanup(void) torture_shuffle_cleanup(); torture_stutter_cleanup(); torture_onoff_cleanup(); + mutex_lock(&fullstop_mutex); + torture_type = NULL; + mutex_unlock(&fullstop_mutex); return false; } EXPORT_SYMBOL_GPL(torture_cleanup); @@ -674,8 +686,10 @@ EXPORT_SYMBOL_GPL(torture_must_stop_irq); */ void torture_kthread_stopping(char *title) { - if (verbose) - VERBOSE_TOROUT_STRING(title); + char buf[128]; + + snprintf(buf, sizeof(buf), "Stopping %s", title); + VERBOSE_TOROUT_STRING(buf); while (!kthread_should_stop()) { torture_shutdown_absorb(title); schedule_timeout_uninterruptible(1); diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index a1be6e62add1..9c3f3d39b934 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -62,7 +62,7 @@ grep '^grep' < $T/u.sh > $T/upd.sh echo "cat - $c" >> $T/upd.sh make mrproper make $buildloc distclean > $builddir/Make.distclean 2>&1 -make $buildloc defconfig > $builddir/Make.defconfig.out 2>&1 +make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1 mv $builddir/.config $builddir/.config.sav sh $T/upd.sh < $builddir/.config.sav > $builddir/.config cp $builddir/.config $builddir/.config.new diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 9b17e810ddc3..d01b865bb100 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -76,15 +76,39 @@ configfrag_hotplug_cpu () { grep -q '^CONFIG_HOTPLUG_CPU=y$' "$1" } +# identify_boot_image qemu-cmd +# +# Returns the relative path to the kernel build image. This will be +# arch/<arch>/boot/bzImage unless overridden with the TORTURE_BOOT_IMAGE +# environment variable. +identify_boot_image () { + if test -n "$TORTURE_BOOT_IMAGE" + then + echo $TORTURE_BOOT_IMAGE + else + case "$1" in + qemu-system-x86_64|qemu-system-i386) + echo arch/x86/boot/bzImage + ;; + qemu-system-ppc64) + echo arch/powerpc/boot/bzImage + ;; + *) + echo "" + ;; + esac + fi +} + # identify_qemu builddir # # Returns our best guess as to which qemu command is appropriate for -# the kernel at hand. Override with the RCU_QEMU_CMD environment variable. +# the kernel at hand. Override with the TORTURE_QEMU_CMD environment variable. identify_qemu () { local u="`file "$1"`" - if test -n "$RCU_QEMU_CMD" + if test -n "$TORTURE_QEMU_CMD" then - echo $RCU_QEMU_CMD + echo $TORTURE_QEMU_CMD elif echo $u | grep -q x86-64 then echo qemu-system-x86_64 @@ -98,7 +122,7 @@ identify_qemu () { echo Cannot figure out what qemu command to use! 1>&2 echo file $1 output: $u # Usually this will be one of /usr/bin/qemu-system-* - # Use RCU_QEMU_CMD environment variable or appropriate + # Use TORTURE_QEMU_CMD environment variable or appropriate # argument to top-level script. exit 1 fi @@ -107,14 +131,14 @@ identify_qemu () { # identify_qemu_append qemu-cmd # # Output arguments for the qemu "-append" string based on CPU type -# and the RCU_QEMU_INTERACTIVE environment variable. +# and the TORTURE_QEMU_INTERACTIVE environment variable. identify_qemu_append () { case "$1" in qemu-system-x86_64|qemu-system-i386) echo noapic selinux=0 initcall_debug debug ;; esac - if test -n "$RCU_QEMU_INTERACTIVE" + if test -n "$TORTURE_QEMU_INTERACTIVE" then echo root=/dev/sda else @@ -124,8 +148,8 @@ identify_qemu_append () { # identify_qemu_args qemu-cmd serial-file # -# Output arguments for qemu arguments based on the RCU_QEMU_MAC -# and RCU_QEMU_INTERACTIVE environment variables. +# Output arguments for qemu arguments based on the TORTURE_QEMU_MAC +# and TORTURE_QEMU_INTERACTIVE environment variables. identify_qemu_args () { case "$1" in qemu-system-x86_64|qemu-system-i386) @@ -133,17 +157,17 @@ identify_qemu_args () { qemu-system-ppc64) echo -enable-kvm -M pseries -cpu POWER7 -nodefaults echo -device spapr-vscsi - if test -n "$RCU_QEMU_INTERACTIVE" -a -n "$RCU_QEMU_MAC" + if test -n "$TORTURE_QEMU_INTERACTIVE" -a -n "$TORTURE_QEMU_MAC" then - echo -device spapr-vlan,netdev=net0,mac=$RCU_QEMU_MAC + echo -device spapr-vlan,netdev=net0,mac=$TORTURE_QEMU_MAC echo -netdev bridge,br=br0,id=net0 - elif test -n "$RCU_QEMU_INTERACTIVE" + elif test -n "$TORTURE_QEMU_INTERACTIVE" then echo -net nic -net user fi ;; esac - if test -n "$RCU_QEMU_INTERACTIVE" + if test -n "$TORTURE_QEMU_INTERACTIVE" then echo -monitor stdio -serial pty -S else diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 197901ec10bf..7c1e56b46de4 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -45,9 +45,9 @@ T=/tmp/test-linux.sh.$$ trap 'rm -rf $T' 0 mkdir $T -cat ${config_template} | grep -v CONFIG_RCU_TORTURE_TEST > $T/config +grep -v 'CONFIG_[A-Z]*_TORTURE_TEST' < ${config_template} > $T/config cat << ___EOF___ >> $T/config -CONFIG_INITRAMFS_SOURCE="$RCU_INITRD" +CONFIG_INITRAMFS_SOURCE="$TORTURE_INITRD" CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_CONSOLE=y ___EOF___ @@ -60,7 +60,7 @@ then exit 2 fi ncpus=`cpus2use.sh` -make O=$builddir -j$ncpus $RCU_KMAKE_ARG > $builddir/Make.out 2>&1 +make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $builddir/Make.out 2>&1 retval=$? if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh index 829186e19eb1..7f1ff1a8fc4b 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh @@ -35,7 +35,7 @@ configfile=`echo $i | sed -e 's/^.*\///'` ncs=`grep "Writes: Total:" $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* Total: //' -e 's/ .*$//'` if test -z "$ncs" then - echo $configfile + echo "$configfile -------" else title="$configfile ------- $ncs acquisitions/releases" dur=`sed -e 's/^.* locktorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null` diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index d75b1dc5ae53..307c4b95f325 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -35,7 +35,7 @@ configfile=`echo $i | sed -e 's/^.*\///'` ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'` if test -z "$ngps" then - echo $configfile + echo "$configfile -------" else title="$configfile ------- $ngps grace periods" dur=`sed -e 's/^.* rcutorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null` diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index a44daaa259a9..ee1f6cae3d70 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -25,6 +25,7 @@ # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH +. tools/testing/selftests/rcutorture/bin/functions.sh for rd in "$@" do firsttime=1 @@ -39,13 +40,24 @@ do fi TORTURE_SUITE="`cat $i/../TORTURE_SUITE`" kvm-recheck-${TORTURE_SUITE}.sh $i - configcheck.sh $i/.config $i/ConfigFragment - parse-build.sh $i/Make.out $configfile - parse-rcutorture.sh $i/console.log $configfile - parse-console.sh $i/console.log $configfile - if test -r $i/Warnings + if test -f "$i/console.log" then - cat $i/Warnings + configcheck.sh $i/.config $i/ConfigFragment + parse-build.sh $i/Make.out $configfile + parse-torture.sh $i/console.log $configfile + parse-console.sh $i/console.log $configfile + if test -r $i/Warnings + then + cat $i/Warnings + fi + else + if test -f "$i/qemu-cmd" + then + print_bug qemu failed + else + print_bug Build failed + fi + echo " $i" fi done done 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 94b28bb37d36..27e544e29510 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -94,9 +94,17 @@ fi # CONFIG_YENTA=n if kvm-build.sh $config_template $builddir $T then + QEMU="`identify_qemu $builddir/vmlinux`" + BOOT_IMAGE="`identify_boot_image $QEMU`" cp $builddir/Make*.out $resdir cp $builddir/.config $resdir - cp $builddir/arch/x86/boot/bzImage $resdir + if test -n "$BOOT_IMAGE" + then + cp $builddir/$BOOT_IMAGE $resdir + else + echo No identifiable boot image, not running KVM, see $resdir. + echo Do the torture scripts know about your architecture? + fi parse-build.sh $resdir/Make.out $title if test -f $builddir.wait then @@ -104,6 +112,7 @@ then fi else cp $builddir/Make*.out $resdir + cp $builddir/.config $resdir || : echo Build failed, not running KVM, see $resdir. if test -f $builddir.wait then @@ -124,9 +133,6 @@ cd $KVM kstarttime=`awk 'BEGIN { print systime() }' < /dev/null` echo ' ---' `date`: Starting kernel -# Determine the appropriate flavor of qemu command. -QEMU="`identify_qemu $builddir/vmlinux`" - # Generate -smp qemu argument. qemu_args="-nographic $qemu_args" cpu_count=`configNR_CPUS.sh $config_template` @@ -151,27 +157,38 @@ boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" # Generate kernel-version-specific boot parameters boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`" -echo $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd -if test -n "$RCU_BUILDONLY" +echo $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd +if test -n "$TORTURE_BUILDONLY" then echo Build-only run specified, boot/test omitted. exit 0 fi -$QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "$qemu_append $boot_args" & +( $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) & qemu_pid=$! commandcompleted=0 echo Monitoring qemu job at pid $qemu_pid -for ((i=0;i<$seconds;i++)) +while : do + kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if kill -0 $qemu_pid > /dev/null 2>&1 then + if test $kruntime -ge $seconds + then + break; + fi sleep 1 else commandcompleted=1 - kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if test $kruntime -lt $seconds then echo Completed in $kruntime vs. $seconds >> $resdir/Warnings 2>&1 + grep "^(qemu) qemu:" $resdir/kvm-test-1-run.sh.out >> $resdir/Warnings 2>&1 + killpid="`sed -n "s/^(qemu) qemu: terminating on signal [0-9]* from pid \([0-9]*\).*$/\1/p" $resdir/Warnings`" + if test -n "$killpid" + then + echo "ps -fp $killpid" >> $resdir/Warnings 2>&1 + ps -fp $killpid >> $resdir/Warnings 2>&1 + fi else echo ' ---' `date`: Kernel done fi @@ -181,23 +198,25 @@ done if test $commandcompleted -eq 0 then echo Grace period for qemu job at pid $qemu_pid - for ((i=0;i<=$grace;i++)) + while : do + kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if kill -0 $qemu_pid > /dev/null 2>&1 then - sleep 1 + : else break fi - if test $i -eq $grace + if test $kruntime -ge $((seconds + grace)) then - kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }'` echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1 kill -KILL $qemu_pid + break fi + sleep 1 done fi cp $builddir/console.log $resdir -parse-${TORTURE_SUITE}torture.sh $resdir/console.log $title +parse-torture.sh $resdir/console.log $title parse-console.sh $resdir/console.log $title diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 5a78cbf55f06..40285c58653e 100644 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -38,9 +38,10 @@ dur=30 dryrun="" KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM PATH=${KVM}/bin:$PATH; export PATH -builddir="${KVM}/b1" -RCU_INITRD="$KVM/initrd"; export RCU_INITRD -RCU_KMAKE_ARG=""; export RCU_KMAKE_ARG +TORTURE_DEFCONFIG=defconfig +TORTURE_BOOT_IMAGE="" +TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD +TORTURE_KMAKE_ARG="" TORTURE_SUITE=rcu resdir="" configs="" @@ -53,11 +54,12 @@ kversion="" usage () { echo "Usage: $scriptname optional arguments:" echo " --bootargs kernel-boot-arguments" - echo " --builddir absolute-pathname" + echo " --bootimage relative-path-to-kernel-boot-image" echo " --buildonly" echo " --configs \"config-file list\"" echo " --cpus N" echo " --datestamp string" + echo " --defconfig string" echo " --dryrun sched|script" echo " --duration minutes" echo " --interactive" @@ -67,7 +69,6 @@ usage () { echo " --no-initrd" echo " --qemu-args qemu-system-..." echo " --qemu-cmd qemu-system-..." - echo " --relbuilddir relative-pathname" echo " --results absolute-pathname" echo " --torture rcu" exit 1 @@ -78,17 +79,16 @@ do case "$1" in --bootargs) checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--' - RCU_BOOTARGS="$2" + TORTURE_BOOTARGS="$2" shift ;; - --builddir) - checkarg --builddir "(absolute pathname)" "$#" "$2" '^/' '^error' - builddir=$2 - gotbuilddir=1 + --bootimage) + checkarg --bootimage "(relative path to kernel boot image)" "$#" "$2" '[a-zA-Z0-9][a-zA-Z0-9_]*' '^--' + TORTURE_BOOT_IMAGE="$2" shift ;; --buildonly) - RCU_BUILDONLY=1; export RCU_BUILDONLY + TORTURE_BUILDONLY=1 ;; --configs) checkarg --configs "(list of config files)" "$#" "$2" '^[^/]*$' '^--' @@ -105,6 +105,11 @@ do ds=$2 shift ;; + --defconfig) + checkarg --defconfig "defconfigtype" "$#" "$2" '^[^/][^/]*$' '^--' + TORTURE_DEFCONFIG=$2 + shift + ;; --dryrun) checkarg --dryrun "sched|script" $# "$2" 'sched\|script' '^--' dryrun=$2 @@ -116,11 +121,11 @@ do shift ;; --interactive) - RCU_QEMU_INTERACTIVE=1; export RCU_QEMU_INTERACTIVE + TORTURE_QEMU_INTERACTIVE=1; export TORTURE_QEMU_INTERACTIVE ;; --kmake-arg) checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$' - RCU_KMAKE_ARG="$2"; export RCU_KMAKE_ARG + TORTURE_KMAKE_ARG="$2" shift ;; --kversion) @@ -130,27 +135,20 @@ do ;; --mac) checkarg --mac "(MAC address)" $# "$2" '^\([0-9a-fA-F]\{2\}:\)\{5\}[0-9a-fA-F]\{2\}$' error - RCU_QEMU_MAC=$2; export RCU_QEMU_MAC + TORTURE_QEMU_MAC=$2 shift ;; --no-initrd) - RCU_INITRD=""; export RCU_INITRD + TORTURE_INITRD=""; export TORTURE_INITRD ;; --qemu-args) checkarg --qemu-args "-qemu args" $# "$2" '^-' '^error' - RCU_QEMU_ARG="$2" + TORTURE_QEMU_ARG="$2" shift ;; --qemu-cmd) checkarg --qemu-cmd "(qemu-system-...)" $# "$2" 'qemu-system-' '^--' - RCU_QEMU_CMD="$2"; export RCU_QEMU_CMD - shift - ;; - --relbuilddir) - checkarg --relbuilddir "(relative pathname)" "$#" "$2" '^[^/]*$' '^--' - relbuilddir=$2 - gotrelbuilddir=1 - builddir=${KVM}/${relbuilddir} + TORTURE_QEMU_CMD="$2" shift ;; --results) @@ -184,30 +182,6 @@ then resdir=$KVM/res fi -if test "$dryrun" = "" -then - if ! test -e $resdir - then - mkdir -p "$resdir" || : - fi - mkdir $resdir/$ds - - # Be noisy only if running the script. - echo Results directory: $resdir/$ds - echo $scriptname $args - - touch $resdir/$ds/log - echo $scriptname $args >> $resdir/$ds/log - echo ${TORTURE_SUITE} > $resdir/$ds/TORTURE_SUITE - - pwd > $resdir/$ds/testid.txt - if test -d .git - then - git status >> $resdir/$ds/testid.txt - git rev-parse HEAD >> $resdir/$ds/testid.txt - fi -fi - # Create a file of test-name/#cpus pairs, sorted by decreasing #cpus. touch $T/cfgcpu for CF in $configs @@ -274,7 +248,39 @@ END { # Generate a script to execute the tests in appropriate batches. cat << ___EOF___ > $T/script +CONFIGFRAG="$CONFIGFRAG"; export CONFIGFRAG +KVM="$KVM"; export KVM +KVPATH="$KVPATH"; export KVPATH +PATH="$PATH"; export PATH +TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE +TORTURE_BUILDONLY="$TORTURE_BUILDONLY"; export TORTURE_BUILDONLY +TORTURE_DEFCONFIG="$TORTURE_DEFCONFIG"; export TORTURE_DEFCONFIG +TORTURE_INITRD="$TORTURE_INITRD"; export TORTURE_INITRD +TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG +TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD +TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE +TORTURE_QEMU_MAC="$TORTURE_QEMU_MAC"; export TORTURE_QEMU_MAC TORTURE_SUITE="$TORTURE_SUITE"; export TORTURE_SUITE +if ! test -e $resdir +then + mkdir -p "$resdir" || : +fi +mkdir $resdir/$ds +echo Results directory: $resdir/$ds +echo $scriptname $args +touch $resdir/$ds/log +echo $scriptname $args >> $resdir/$ds/log +echo ${TORTURE_SUITE} > $resdir/$ds/TORTURE_SUITE +pwd > $resdir/$ds/testid.txt +if test -d .git +then + git status >> $resdir/$ds/testid.txt + git rev-parse HEAD >> $resdir/$ds/testid.txt + if ! git diff HEAD > $T/git-diff 2>&1 + then + cp $T/git-diff $resdir/$ds + fi +fi ___EOF___ awk < $T/cfgcpu.pack \ -v CONFIGDIR="$CONFIGFRAG/$kversion/" \ @@ -282,8 +288,8 @@ awk < $T/cfgcpu.pack \ -v ncpus=$cpus \ -v rd=$resdir/$ds/ \ -v dur=$dur \ - -v RCU_QEMU_ARG=$RCU_QEMU_ARG \ - -v RCU_BOOTARGS=$RCU_BOOTARGS \ + -v TORTURE_QEMU_ARG="$TORTURE_QEMU_ARG" \ + -v TORTURE_BOOTARGS="$TORTURE_BOOTARGS" \ 'BEGIN { i = 0; } @@ -320,7 +326,7 @@ function dump(first, pastlast) print "touch " builddir ".wait"; print "mkdir " builddir " > /dev/null 2>&1 || :"; print "mkdir " rd cfr[jn] " || :"; - print "kvm-test-1-run.sh " CONFIGDIR cf[j], builddir, rd cfr[jn], dur " \"" RCU_QEMU_ARG "\" \"" RCU_BOOTARGS "\" > " rd cfr[jn] "/kvm-test-1-run.sh.out 2>&1 &" + print "kvm-test-1-run.sh " CONFIGDIR cf[j], builddir, rd cfr[jn], dur " \"" TORTURE_QEMU_ARG "\" \"" TORTURE_BOOTARGS "\" > " rd cfr[jn] "/kvm-test-1-run.sh.out 2>&1 &" print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date`"; print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date` >> " rd "/log"; print "while test -f " builddir ".wait" @@ -374,28 +380,26 @@ END { dump(first, i); }' >> $T/script +cat << ___EOF___ >> $T/script +echo +echo +echo " --- `date` Test summary:" +echo Results directory: $resdir/$ds +if test -z "$TORTURE_BUILDONLY" +then + kvm-recheck.sh $resdir/$ds +fi +___EOF___ + if test "$dryrun" = script then - # Dump out the script, but define the environment variables that - # it needs to run standalone. - echo CONFIGFRAG="$CONFIGFRAG; export CONFIGFRAG" - echo KVM="$KVM; export KVM" - echo KVPATH="$KVPATH; export KVPATH" - echo PATH="$PATH; export PATH" - echo RCU_BUILDONLY="$RCU_BUILDONLY; export RCU_BUILDONLY" - echo RCU_INITRD="$RCU_INITRD; export RCU_INITRD" - echo RCU_KMAKE_ARG="$RCU_KMAKE_ARG; export RCU_KMAKE_ARG" - echo RCU_QEMU_CMD="$RCU_QEMU_CMD; export RCU_QEMU_CMD" - echo RCU_QEMU_INTERACTIVE="$RCU_QEMU_INTERACTIVE; export RCU_QEMU_INTERACTIVE" - echo RCU_QEMU_MAC="$RCU_QEMU_MAC; export RCU_QEMU_MAC" - echo "mkdir -p "$resdir" || :" - echo "mkdir $resdir/$ds" cat $T/script exit 0 elif test "$dryrun" = sched then # Extract the test run schedule from the script. - egrep 'start batch|Starting build\.' $T/script | + egrep 'Start batch|Starting build\.' $T/script | + grep -v ">>" | sed -e 's/:.*$//' -e 's/^echo //' exit 0 else @@ -404,9 +408,3 @@ else fi # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier - -echo -echo -echo " --- `date` Test summary:" -echo Results directory: $resdir/$ds -kvm-recheck.sh $resdir/$ds diff --git a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh index dd0a275d9796..3455560ab4e4 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-torture.sh @@ -1,14 +1,14 @@ #!/bin/sh # -# Check the console output from an rcutorture run for goodness. +# Check the console output from a torture run for goodness. # The "file" is a pathname on the local system, and "title" is # a text string for error-message purposes. # -# The file must contain rcutorture output, but can be interspersed -# with other dmesg text. +# The file must contain torture output, but can be interspersed +# with other dmesg text, as in console-log output. # # Usage: -# sh parse-rcutorture.sh file title +# sh 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 @@ -28,7 +28,7 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> -T=/tmp/parse-rcutorture.sh.$$ +T=/tmp/parse-torture.sh.$$ file="$1" title="$2" @@ -36,13 +36,13 @@ trap 'rm -f $T.seq' 0 . functions.sh -# check for presence of rcutorture.txt file +# check for presence of torture output file. if test -f "$file" -a -r "$file" then : else - echo $title unreadable rcutorture.txt file: $file + echo $title unreadable torture output file: $file exit 1 fi @@ -76,9 +76,9 @@ BEGIN { END { if (badseq) { if (badseqno1 == badseqno2 && badseqno2 == ver) - print "RCU GP HANG at " ver " rcutorture stat " badseqnr; + print "GP HANG at " ver " torture stat " badseqnr; else - print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " RCU version " badseqnr; + print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr; } }' > $T.seq @@ -91,13 +91,13 @@ then exit 2 fi else - if grep -q RCU_HOTPLUG $file + if grep -q "_HOTPLUG:" $file then print_warning HOTPLUG FAILURES $title `cat $T.seq` echo " " $file exit 3 fi - echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful RCU version messages + echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages if test -s $T.seq then print_warning $title `cat $T.seq` diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T new file mode 100644 index 000000000000..61c8d9ce5bb2 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T @@ -0,0 +1,25 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=8 +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +#CHECK#CONFIG_TREE_PREEMPT_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_RCU_TRACE=y +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_FANOUT=3 +CONFIG_RCU_FANOUT_LEAF=3 +CONFIG_RCU_FANOUT_EXACT=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_LOCKING=n +CONFIG_PROVE_RCU_DELAY=n +CONFIG_RCU_CPU_STALL_INFO=n +CONFIG_RCU_CPU_STALL_VERBOSE=y +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot new file mode 100644 index 000000000000..3b42b8b033cd --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot @@ -0,0 +1 @@ +rcutorture.torture_type=sched |