diff options
Diffstat (limited to 'kernel')
45 files changed, 2686 insertions, 590 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 8c201f414226..b2301bdc9773 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1851,7 +1851,6 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, } audit_get_stamp(ab->ctx, &t, &serial); - audit_clear_dummy(ab->ctx); audit_log_format(ab, "audit(%llu.%03lu:%u): ", (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial); diff --git a/kernel/audit.h b/kernel/audit.h index f0233dc40b17..ddc22878433d 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -290,13 +290,6 @@ extern int audit_signal_info_syscall(struct task_struct *t); extern void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx); extern struct list_head *audit_killed_trees(void); - -static inline void audit_clear_dummy(struct audit_context *ctx) -{ - if (ctx) - ctx->dummy = 0; -} - #else /* CONFIG_AUDITSYSCALL */ #define auditsc_get_stamp(c, t, s) 0 #define audit_put_watch(w) {} @@ -330,7 +323,6 @@ static inline int audit_signal_info_syscall(struct task_struct *t) } #define audit_filter_inodes(t, c) AUDIT_DISABLED -#define audit_clear_dummy(c) {} #endif /* CONFIG_AUDITSYSCALL */ extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 468a23390457..fd840c40abf7 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1417,6 +1417,9 @@ static void audit_log_proctitle(void) struct audit_context *context = audit_context(); struct audit_buffer *ab; + if (!context || context->dummy) + return; + ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE); if (!ab) return; /* audit_panic or being filtered */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9a1a98dd9e97..0443600146dc 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4058,6 +4058,11 @@ static int __btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, const char *tname, *sym; u32 btf_id, i; + if (!btf_vmlinux) { + bpf_log(log, "btf_vmlinux doesn't exist\n"); + return -EINVAL; + } + if (IS_ERR(btf_vmlinux)) { bpf_log(log, "btf_vmlinux is malformed\n"); return -EINVAL; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b4b288a3c3c9..b32cc8ce8ff6 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -779,15 +779,20 @@ static void htab_elem_free_rcu(struct rcu_head *head) htab_elem_free(htab, l); } -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) { struct bpf_map *map = &htab->map; + void *ptr; if (map->ops->map_fd_put_ptr) { - void *ptr = fd_htab_map_get_ptr(map, l); - + ptr = fd_htab_map_get_ptr(map, l); map->ops->map_fd_put_ptr(ptr); } +} + +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +{ + htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { __pcpu_freelist_push(&htab->freelist, &l->fnode); @@ -839,6 +844,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, */ pl_new = this_cpu_ptr(htab->extra_elems); l_new = *pl_new; + htab_put_fd_value(htab, old_elem); *pl_new = old_elem; } else { struct pcpu_freelist_node *l; diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index b6397a186ce9..d51175cedfca 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -64,7 +64,6 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) raw_spin_unlock_irqrestore(cpu_lock, flags); } -EXPORT_SYMBOL_GPL(cgroup_rstat_updated); /** * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 9f1557b98468..18175687133a 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -413,6 +413,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); VMCOREINFO_STRUCT_SIZE(mem_section); VMCOREINFO_OFFSET(mem_section, section_mem_map); + VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); #endif VMCOREINFO_STRUCT_SIZE(page); VMCOREINFO_STRUCT_SIZE(pglist_data); diff --git a/kernel/fork.c b/kernel/fork.c index efc5493203ae..0cc3d9cd6cc2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -359,7 +359,13 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (new) { - *new = *orig; + ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); + ASSERT_EXCLUSIVE_WRITER(orig->vm_file); + /* + * orig->shared.rb may be modified concurrently, but the clone + * will be reinitialized. + */ + *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; } @@ -1954,8 +1960,8 @@ static __latent_entropy struct task_struct *copy_process( rt_mutex_init_task(p); + lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING - DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = -EAGAIN; @@ -2035,19 +2041,11 @@ static __latent_entropy struct task_struct *copy_process( seqcount_init(&p->mems_allowed_seq); #endif #ifdef CONFIG_TRACE_IRQFLAGS - p->irq_events = 0; - p->hardirqs_enabled = 0; - p->hardirq_enable_ip = 0; - p->hardirq_enable_event = 0; - p->hardirq_disable_ip = _THIS_IP_; - p->hardirq_disable_event = 0; - p->softirqs_enabled = 1; - p->softirq_enable_ip = _THIS_IP_; - p->softirq_enable_event = 0; - p->softirq_disable_ip = 0; - p->softirq_disable_event = 0; - p->hardirq_context = 0; - p->softirq_context = 0; + memset(&p->irqtrace, 0, sizeof(p->irqtrace)); + p->irqtrace.hardirq_disable_ip = _THIS_IP_; + p->irqtrace.softirq_enable_ip = _THIS_IP_; + p->softirqs_enabled = 1; + p->softirq_context = 0; #endif p->pagefault_disabled = 0; diff --git a/kernel/futex.c b/kernel/futex.c index e646661f6282..4616d4ad609d 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -32,30 +32,13 @@ * "But they come in a choice of three flavours!" */ #include <linux/compat.h> -#include <linux/slab.h> -#include <linux/poll.h> -#include <linux/fs.h> -#include <linux/file.h> #include <linux/jhash.h> -#include <linux/init.h> -#include <linux/futex.h> -#include <linux/mount.h> #include <linux/pagemap.h> #include <linux/syscalls.h> -#include <linux/signal.h> -#include <linux/export.h> -#include <linux/magic.h> -#include <linux/pid.h> -#include <linux/nsproxy.h> -#include <linux/ptrace.h> -#include <linux/sched/rt.h> -#include <linux/sched/wake_q.h> -#include <linux/sched/mm.h> #include <linux/hugetlb.h> #include <linux/freezer.h> #include <linux/memblock.h> #include <linux/fault-inject.h> -#include <linux/refcount.h> #include <asm/futex.h> @@ -476,7 +459,7 @@ static u64 get_inode_sequence_number(struct inode *inode) /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex - * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED + * @fshared: false for a PROCESS_PRIVATE futex, true for PROCESS_SHARED * @key: address where result is stored. * @rw: mapping needs to be read/write (values: FUTEX_READ, * FUTEX_WRITE) @@ -500,8 +483,8 @@ static u64 get_inode_sequence_number(struct inode *inode) * * lock_page() might sleep, the caller should not hold a spinlock. */ -static int -get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_access rw) +static int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key, + enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; @@ -538,7 +521,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a again: /* Ignore any VERIFY_READ mapping (futex common case) */ - if (unlikely(should_fail_futex(fshared))) + if (unlikely(should_fail_futex(true))) return -EFAULT; err = get_user_pages_fast(address, 1, FOLL_WRITE, &page); @@ -626,7 +609,7 @@ again: * A RO anonymous page will never change and thus doesn't make * sense for futex operations. */ - if (unlikely(should_fail_futex(fshared)) || ro) { + if (unlikely(should_fail_futex(true)) || ro) { err = -EFAULT; goto out; } @@ -677,10 +660,6 @@ out: return err; } -static inline void put_futex_key(union futex_key *key) -{ -} - /** * fault_in_user_writeable() - Fault in user address and verify RW access * @uaddr: pointer to faulting user space address @@ -1611,13 +1590,13 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_READ); if (unlikely(ret != 0)) - goto out; + return ret; hb = hash_futex(&key); /* Make sure we really have tasks to wakeup */ if (!hb_waiters_pending(hb)) - goto out_put_key; + return ret; spin_lock(&hb->lock); @@ -1640,9 +1619,6 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) spin_unlock(&hb->lock); wake_up_q(&wake_q); -out_put_key: - put_futex_key(&key); -out: return ret; } @@ -1709,10 +1685,10 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, retry: ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ); if (unlikely(ret != 0)) - goto out; + return ret; ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) - goto out_put_key1; + return ret; hb1 = hash_futex(&key1); hb2 = hash_futex(&key2); @@ -1730,13 +1706,13 @@ retry_private: * an MMU, but we might get them from range checking */ ret = op_ret; - goto out_put_keys; + return ret; } if (op_ret == -EFAULT) { ret = fault_in_user_writeable(uaddr2); if (ret) - goto out_put_keys; + return ret; } if (!(flags & FLAGS_SHARED)) { @@ -1744,8 +1720,6 @@ retry_private: goto retry_private; } - put_futex_key(&key2); - put_futex_key(&key1); cond_resched(); goto retry; } @@ -1781,11 +1755,6 @@ retry_private: out_unlock: double_unlock_hb(hb1, hb2); wake_up_q(&wake_q); -out_put_keys: - put_futex_key(&key2); -out_put_key1: - put_futex_key(&key1); -out: return ret; } @@ -1992,20 +1961,18 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, retry: ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ); if (unlikely(ret != 0)) - goto out; + return ret; ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, requeue_pi ? FUTEX_WRITE : FUTEX_READ); if (unlikely(ret != 0)) - goto out_put_key1; + return ret; /* * The check above which compares uaddrs is not sufficient for * shared futexes. We need to compare the keys: */ - if (requeue_pi && match_futex(&key1, &key2)) { - ret = -EINVAL; - goto out_put_keys; - } + if (requeue_pi && match_futex(&key1, &key2)) + return -EINVAL; hb1 = hash_futex(&key1); hb2 = hash_futex(&key2); @@ -2025,13 +1992,11 @@ retry_private: ret = get_user(curval, uaddr1); if (ret) - goto out_put_keys; + return ret; if (!(flags & FLAGS_SHARED)) goto retry_private; - put_futex_key(&key2); - put_futex_key(&key1); goto retry; } if (curval != *cmpval) { @@ -2090,12 +2055,10 @@ retry_private: case -EFAULT: double_unlock_hb(hb1, hb2); hb_waiters_dec(hb2); - put_futex_key(&key2); - put_futex_key(&key1); ret = fault_in_user_writeable(uaddr2); if (!ret) goto retry; - goto out; + return ret; case -EBUSY: case -EAGAIN: /* @@ -2106,8 +2069,6 @@ retry_private: */ double_unlock_hb(hb1, hb2); hb_waiters_dec(hb2); - put_futex_key(&key2); - put_futex_key(&key1); /* * Handle the case where the owner is in the middle of * exiting. Wait for the exit to complete otherwise @@ -2216,12 +2177,6 @@ out_unlock: double_unlock_hb(hb1, hb2); wake_up_q(&wake_q); hb_waiters_dec(hb2); - -out_put_keys: - put_futex_key(&key2); -out_put_key1: - put_futex_key(&key1); -out: return ret ? ret : task_count; } @@ -2567,7 +2522,7 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) */ if (q->pi_state->owner != current) ret = fixup_pi_state_owner(uaddr, q, current); - goto out; + return ret ? ret : locked; } /* @@ -2580,7 +2535,7 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) */ if (q->pi_state->owner == current) { ret = fixup_pi_state_owner(uaddr, q, NULL); - goto out; + return ret; } /* @@ -2594,8 +2549,7 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) q->pi_state->owner); } -out: - return ret ? ret : locked; + return ret; } /** @@ -2692,12 +2646,11 @@ retry_private: ret = get_user(uval, uaddr); if (ret) - goto out; + return ret; if (!(flags & FLAGS_SHARED)) goto retry_private; - put_futex_key(&q->key); goto retry; } @@ -2706,9 +2659,6 @@ retry_private: ret = -EWOULDBLOCK; } -out: - if (ret) - put_futex_key(&q->key); return ret; } @@ -2853,7 +2803,6 @@ retry_private: * - EAGAIN: The user space value changed. */ queue_unlock(hb); - put_futex_key(&q.key); /* * Handle the case where the owner is in the middle of * exiting. Wait for the exit to complete otherwise @@ -2961,13 +2910,11 @@ no_block: put_pi_state(pi_state); } - goto out_put_key; + goto out; out_unlock_put_key: queue_unlock(hb); -out_put_key: - put_futex_key(&q.key); out: if (to) { hrtimer_cancel(&to->timer); @@ -2980,12 +2927,11 @@ uaddr_faulted: ret = fault_in_user_writeable(uaddr); if (ret) - goto out_put_key; + goto out; if (!(flags & FLAGS_SHARED)) goto retry_private; - put_futex_key(&q.key); goto retry; } @@ -3114,16 +3060,13 @@ retry: out_unlock: spin_unlock(&hb->lock); out_putkey: - put_futex_key(&key); return ret; pi_retry: - put_futex_key(&key); cond_resched(); goto retry; pi_faulted: - put_futex_key(&key); ret = fault_in_user_writeable(uaddr); if (!ret) @@ -3265,7 +3208,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, */ ret = futex_wait_setup(uaddr, val, flags, &q, &hb); if (ret) - goto out_key2; + goto out; /* * The check above which compares uaddrs is not sufficient for @@ -3274,7 +3217,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (match_futex(&q.key, &key2)) { queue_unlock(hb); ret = -EINVAL; - goto out_put_keys; + goto out; } /* Queue the futex_q, drop the hb lock, wait for wakeup. */ @@ -3284,7 +3227,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); spin_unlock(&hb->lock); if (ret) - goto out_put_keys; + goto out; /* * In order for us to be here, we know our q.key == key2, and since @@ -3374,11 +3317,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, ret = -EWOULDBLOCK; } -out_put_keys: - put_futex_key(&q.key); -out_key2: - put_futex_key(&key2); - out: if (to) { hrtimer_cancel(&to->timer); diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 4f9f844074db..b95ff5d5f4bd 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -112,6 +112,7 @@ static const struct irq_bit_descr irqdata_states[] = { BIT_MASK_DESCR(IRQD_AFFINITY_SET), BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING), BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED), + BIT_MASK_DESCR(IRQD_AFFINITY_ON_ACTIVATE), BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN), BIT_MASK_DESCR(IRQD_CAN_RESERVE), BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK), @@ -120,6 +121,10 @@ static const struct irq_bit_descr irqdata_states[] = { BIT_MASK_DESCR(IRQD_WAKEUP_STATE), BIT_MASK_DESCR(IRQD_WAKEUP_ARMED), + + BIT_MASK_DESCR(IRQD_DEFAULT_TRIGGER_SET), + + BIT_MASK_DESCR(IRQD_HANDLE_ENFORCE_IRQCTX), }; static const struct irq_bit_descr irqdesc_states[] = { diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 2a9fec53e159..48c38e09c673 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -320,12 +320,16 @@ static bool irq_set_affinity_deactivated(struct irq_data *data, struct irq_desc *desc = irq_data_to_desc(data); /* + * Handle irq chips which can handle affinity only in activated + * state correctly + * * If the interrupt is not yet activated, just store the affinity * mask and do not call the chip driver at all. On activation the * driver has to make sure anyway that the interrupt is in a * useable state so startup works. */ - if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || irqd_is_activated(data)) + if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || + irqd_is_activated(data) || !irqd_affinity_on_activate(data)) return false; cpumask_copy(desc->irq_common_data.affinity, mask); diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile index d4999b38d1be..65ca5539c470 100644 --- a/kernel/kcsan/Makefile +++ b/kernel/kcsan/Makefile @@ -7,8 +7,11 @@ CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_debugfs.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE) -CFLAGS_core.o := $(call cc-option,-fno-conserve-stack,) \ - $(call cc-option,-fno-stack-protector,) +CFLAGS_core.o := $(call cc-option,-fno-conserve-stack) \ + -fno-stack-protector -DDISABLE_BRANCH_PROFILING obj-y := core.o debugfs.o report.o -obj-$(CONFIG_KCSAN_SELFTEST) += test.o +obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o + +CFLAGS_kcsan-test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer +obj-$(CONFIG_KCSAN_TEST) += kcsan-test.o diff --git a/kernel/kcsan/atomic.h b/kernel/kcsan/atomic.h index be9e625227f3..75fe701f4127 100644 --- a/kernel/kcsan/atomic.h +++ b/kernel/kcsan/atomic.h @@ -3,8 +3,7 @@ #ifndef _KERNEL_KCSAN_ATOMIC_H #define _KERNEL_KCSAN_ATOMIC_H -#include <linux/jiffies.h> -#include <linux/sched.h> +#include <linux/types.h> /* * Special rules for certain memory where concurrent conflicting accesses are @@ -13,8 +12,7 @@ */ static bool kcsan_is_atomic_special(const volatile void *ptr) { - /* volatile globals that have been observed in data races. */ - return ptr == &jiffies || ptr == ¤t->state; + return false; } #endif /* _KERNEL_KCSAN_ATOMIC_H */ diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index 15f67949d11e..9147ff6a12e5 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -291,6 +291,20 @@ static inline unsigned int get_delay(void) 0); } +void kcsan_save_irqtrace(struct task_struct *task) +{ +#ifdef CONFIG_TRACE_IRQFLAGS + task->kcsan_save_irqtrace = task->irqtrace; +#endif +} + +void kcsan_restore_irqtrace(struct task_struct *task) +{ +#ifdef CONFIG_TRACE_IRQFLAGS + task->irqtrace = task->kcsan_save_irqtrace; +#endif +} + /* * Pull everything together: check_access() below contains the performance * critical operations; the fast-path (including check_access) functions should @@ -336,9 +350,11 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr, flags = user_access_save(); if (consumed) { + kcsan_save_irqtrace(current); kcsan_report(ptr, size, type, KCSAN_VALUE_CHANGE_MAYBE, KCSAN_REPORT_CONSUMED_WATCHPOINT, watchpoint - watchpoints); + kcsan_restore_irqtrace(current); } else { /* * The other thread may not print any diagnostics, as it has @@ -396,9 +412,14 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type) goto out; } + /* + * Save and restore the IRQ state trace touched by KCSAN, since KCSAN's + * runtime is entered for every memory access, and potentially useful + * information is lost if dirtied by KCSAN. + */ + kcsan_save_irqtrace(current); if (!kcsan_interrupt_watcher) - /* Use raw to avoid lockdep recursion via IRQ flags tracing. */ - raw_local_irq_save(irq_flags); + local_irq_save(irq_flags); watchpoint = insert_watchpoint((unsigned long)ptr, size, is_write); if (watchpoint == NULL) { @@ -539,7 +560,8 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type) kcsan_counter_dec(KCSAN_COUNTER_USED_WATCHPOINTS); out_unlock: if (!kcsan_interrupt_watcher) - raw_local_irq_restore(irq_flags); + local_irq_restore(irq_flags); + kcsan_restore_irqtrace(current); out: user_access_restore(ua_flags); } @@ -754,6 +776,7 @@ EXPORT_SYMBOL(__kcsan_check_access); */ #define DEFINE_TSAN_READ_WRITE(size) \ + void __tsan_read##size(void *ptr); \ void __tsan_read##size(void *ptr) \ { \ check_access(ptr, size, 0); \ @@ -762,6 +785,7 @@ EXPORT_SYMBOL(__kcsan_check_access); void __tsan_unaligned_read##size(void *ptr) \ __alias(__tsan_read##size); \ EXPORT_SYMBOL(__tsan_unaligned_read##size); \ + void __tsan_write##size(void *ptr); \ void __tsan_write##size(void *ptr) \ { \ check_access(ptr, size, KCSAN_ACCESS_WRITE); \ @@ -777,12 +801,14 @@ DEFINE_TSAN_READ_WRITE(4); DEFINE_TSAN_READ_WRITE(8); DEFINE_TSAN_READ_WRITE(16); +void __tsan_read_range(void *ptr, size_t size); void __tsan_read_range(void *ptr, size_t size) { check_access(ptr, size, 0); } EXPORT_SYMBOL(__tsan_read_range); +void __tsan_write_range(void *ptr, size_t size); void __tsan_write_range(void *ptr, size_t size) { check_access(ptr, size, KCSAN_ACCESS_WRITE); @@ -799,6 +825,7 @@ EXPORT_SYMBOL(__tsan_write_range); * the size-check of compiletime_assert_rwonce_type(). */ #define DEFINE_TSAN_VOLATILE_READ_WRITE(size) \ + void __tsan_volatile_read##size(void *ptr); \ void __tsan_volatile_read##size(void *ptr) \ { \ const bool is_atomic = size <= sizeof(long long) && \ @@ -811,6 +838,7 @@ EXPORT_SYMBOL(__tsan_write_range); void __tsan_unaligned_volatile_read##size(void *ptr) \ __alias(__tsan_volatile_read##size); \ EXPORT_SYMBOL(__tsan_unaligned_volatile_read##size); \ + void __tsan_volatile_write##size(void *ptr); \ void __tsan_volatile_write##size(void *ptr) \ { \ const bool is_atomic = size <= sizeof(long long) && \ @@ -836,14 +864,17 @@ DEFINE_TSAN_VOLATILE_READ_WRITE(16); * The below are not required by KCSAN, but can still be emitted by the * compiler. */ +void __tsan_func_entry(void *call_pc); void __tsan_func_entry(void *call_pc) { } EXPORT_SYMBOL(__tsan_func_entry); +void __tsan_func_exit(void); void __tsan_func_exit(void) { } EXPORT_SYMBOL(__tsan_func_exit); +void __tsan_init(void); void __tsan_init(void) { } diff --git a/kernel/kcsan/kcsan-test.c b/kernel/kcsan/kcsan-test.c new file mode 100644 index 000000000000..fed6fcb5768c --- /dev/null +++ b/kernel/kcsan/kcsan-test.c @@ -0,0 +1,1107 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KCSAN test with various race scenarious to test runtime behaviour. Since the + * interface with which KCSAN's reports are obtained is via the console, this is + * the output we should verify. For each test case checks the presence (or + * absence) of generated reports. Relies on 'console' tracepoint to capture + * reports as they appear in the kernel log. + * + * Makes use of KUnit for test organization, and the Torture framework for test + * thread control. + * + * Copyright (C) 2020, Google LLC. + * Author: Marco Elver <elver@google.com> + */ + +#include <kunit/test.h> +#include <linux/jiffies.h> +#include <linux/kcsan-checks.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/seqlock.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/timer.h> +#include <linux/torture.h> +#include <linux/tracepoint.h> +#include <linux/types.h> +#include <trace/events/printk.h> + +/* Points to current test-case memory access "kernels". */ +static void (*access_kernels[2])(void); + +static struct task_struct **threads; /* Lists of threads. */ +static unsigned long end_time; /* End time of test. */ + +/* Report as observed from console. */ +static struct { + spinlock_t lock; + int nlines; + char lines[3][512]; +} observed = { + .lock = __SPIN_LOCK_UNLOCKED(observed.lock), +}; + +/* Setup test checking loop. */ +static __no_kcsan inline void +begin_test_checks(void (*func1)(void), void (*func2)(void)) +{ + kcsan_disable_current(); + + /* + * Require at least as long as KCSAN_REPORT_ONCE_IN_MS, to ensure at + * least one race is reported. + */ + end_time = jiffies + msecs_to_jiffies(CONFIG_KCSAN_REPORT_ONCE_IN_MS + 500); + + /* Signal start; release potential initialization of shared data. */ + smp_store_release(&access_kernels[0], func1); + smp_store_release(&access_kernels[1], func2); +} + +/* End test checking loop. */ +static __no_kcsan inline bool +end_test_checks(bool stop) +{ + if (!stop && time_before(jiffies, end_time)) { + /* Continue checking */ + might_sleep(); + return false; + } + + kcsan_enable_current(); + return true; +} + +/* + * Probe for console output: checks if a race was reported, and obtains observed + * lines of interest. + */ +__no_kcsan +static void probe_console(void *ignore, const char *buf, size_t len) +{ + unsigned long flags; + int nlines; + + /* + * Note that KCSAN reports under a global lock, so we do not risk the + * possibility of having multiple reports interleaved. If that were the + * case, we'd expect tests to fail. + */ + + spin_lock_irqsave(&observed.lock, flags); + nlines = observed.nlines; + + if (strnstr(buf, "BUG: KCSAN: ", len) && strnstr(buf, "test_", len)) { + /* + * KCSAN report and related to the test. + * + * The provided @buf is not NUL-terminated; copy no more than + * @len bytes and let strscpy() add the missing NUL-terminator. + */ + strscpy(observed.lines[0], buf, min(len + 1, sizeof(observed.lines[0]))); + nlines = 1; + } else if ((nlines == 1 || nlines == 2) && strnstr(buf, "bytes by", len)) { + strscpy(observed.lines[nlines++], buf, min(len + 1, sizeof(observed.lines[0]))); + + if (strnstr(buf, "race at unknown origin", len)) { + if (WARN_ON(nlines != 2)) + goto out; + + /* No second line of interest. */ + strcpy(observed.lines[nlines++], "<none>"); + } + } + +out: + WRITE_ONCE(observed.nlines, nlines); /* Publish new nlines. */ + spin_unlock_irqrestore(&observed.lock, flags); +} + +/* Check if a report related to the test exists. */ +__no_kcsan +static bool report_available(void) +{ + return READ_ONCE(observed.nlines) == ARRAY_SIZE(observed.lines); +} + +/* Report information we expect in a report. */ +struct expect_report { + /* Access information of both accesses. */ + struct { + void *fn; /* Function pointer to expected function of top frame. */ + void *addr; /* Address of access; unchecked if NULL. */ + size_t size; /* Size of access; unchecked if @addr is NULL. */ + int type; /* Access type, see KCSAN_ACCESS definitions. */ + } access[2]; +}; + +/* Check observed report matches information in @r. */ +__no_kcsan +static bool report_matches(const struct expect_report *r) +{ + const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT; + bool ret = false; + unsigned long flags; + typeof(observed.lines) expect; + const char *end; + char *cur; + int i; + + /* Doubled-checked locking. */ + if (!report_available()) + return false; + + /* Generate expected report contents. */ + + /* Title */ + cur = expect[0]; + end = &expect[0][sizeof(expect[0]) - 1]; + cur += scnprintf(cur, end - cur, "BUG: KCSAN: %s in ", + is_assert ? "assert: race" : "data-race"); + if (r->access[1].fn) { + char tmp[2][64]; + int cmp; + + /* Expect lexographically sorted function names in title. */ + scnprintf(tmp[0], sizeof(tmp[0]), "%pS", r->access[0].fn); + scnprintf(tmp[1], sizeof(tmp[1]), "%pS", r->access[1].fn); + cmp = strcmp(tmp[0], tmp[1]); + cur += scnprintf(cur, end - cur, "%ps / %ps", + cmp < 0 ? r->access[0].fn : r->access[1].fn, + cmp < 0 ? r->access[1].fn : r->access[0].fn); + } else { + scnprintf(cur, end - cur, "%pS", r->access[0].fn); + /* The exact offset won't match, remove it. */ + cur = strchr(expect[0], '+'); + if (cur) + *cur = '\0'; + } + + /* Access 1 */ + cur = expect[1]; + end = &expect[1][sizeof(expect[1]) - 1]; + if (!r->access[1].fn) + cur += scnprintf(cur, end - cur, "race at unknown origin, with "); + + /* Access 1 & 2 */ + for (i = 0; i < 2; ++i) { + const char *const access_type = + (r->access[i].type & KCSAN_ACCESS_ASSERT) ? + ((r->access[i].type & KCSAN_ACCESS_WRITE) ? + "assert no accesses" : + "assert no writes") : + ((r->access[i].type & KCSAN_ACCESS_WRITE) ? + "write" : + "read"); + const char *const access_type_aux = + (r->access[i].type & KCSAN_ACCESS_ATOMIC) ? + " (marked)" : + ((r->access[i].type & KCSAN_ACCESS_SCOPED) ? + " (scoped)" : + ""); + + if (i == 1) { + /* Access 2 */ + cur = expect[2]; + end = &expect[2][sizeof(expect[2]) - 1]; + + if (!r->access[1].fn) { + /* Dummy string if no second access is available. */ + strcpy(cur, "<none>"); + break; + } + } + + cur += scnprintf(cur, end - cur, "%s%s to ", access_type, + access_type_aux); + + if (r->access[i].addr) /* Address is optional. */ + cur += scnprintf(cur, end - cur, "0x%px of %zu bytes", + r->access[i].addr, r->access[i].size); + } + + spin_lock_irqsave(&observed.lock, flags); + if (!report_available()) + goto out; /* A new report is being captured. */ + + /* Finally match expected output to what we actually observed. */ + ret = strstr(observed.lines[0], expect[0]) && + /* Access info may appear in any order. */ + ((strstr(observed.lines[1], expect[1]) && + strstr(observed.lines[2], expect[2])) || + (strstr(observed.lines[1], expect[2]) && + strstr(observed.lines[2], expect[1]))); +out: + spin_unlock_irqrestore(&observed.lock, flags); + return ret; +} + +/* ===== Test kernels ===== */ + +static long test_sink; +static long test_var; +/* @test_array should be large enough to fall into multiple watchpoint slots. */ +static long test_array[3 * PAGE_SIZE / sizeof(long)]; +static struct { + long val[8]; +} test_struct; +static DEFINE_SEQLOCK(test_seqlock); + +/* + * Helper to avoid compiler optimizing out reads, and to generate source values + * for writes. + */ +__no_kcsan +static noinline void sink_value(long v) { WRITE_ONCE(test_sink, v); } + +static noinline void test_kernel_read(void) { sink_value(test_var); } + +static noinline void test_kernel_write(void) +{ + test_var = READ_ONCE_NOCHECK(test_sink) + 1; +} + +static noinline void test_kernel_write_nochange(void) { test_var = 42; } + +/* Suffixed by value-change exception filter. */ +static noinline void test_kernel_write_nochange_rcu(void) { test_var = 42; } + +static noinline void test_kernel_read_atomic(void) +{ + sink_value(READ_ONCE(test_var)); +} + +static noinline void test_kernel_write_atomic(void) +{ + WRITE_ONCE(test_var, READ_ONCE_NOCHECK(test_sink) + 1); +} + +__no_kcsan +static noinline void test_kernel_write_uninstrumented(void) { test_var++; } + +static noinline void test_kernel_data_race(void) { data_race(test_var++); } + +static noinline void test_kernel_assert_writer(void) +{ + ASSERT_EXCLUSIVE_WRITER(test_var); +} + +static noinline void test_kernel_assert_access(void) +{ + ASSERT_EXCLUSIVE_ACCESS(test_var); +} + +#define TEST_CHANGE_BITS 0xff00ff00 + +static noinline void test_kernel_change_bits(void) +{ + if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { + /* + * Avoid race of unknown origin for this test, just pretend they + * are atomic. + */ + kcsan_nestable_atomic_begin(); + test_var ^= TEST_CHANGE_BITS; + kcsan_nestable_atomic_end(); + } else + WRITE_ONCE(test_var, READ_ONCE(test_var) ^ TEST_CHANGE_BITS); +} + +static noinline void test_kernel_assert_bits_change(void) +{ + ASSERT_EXCLUSIVE_BITS(test_var, TEST_CHANGE_BITS); +} + +static noinline void test_kernel_assert_bits_nochange(void) +{ + ASSERT_EXCLUSIVE_BITS(test_var, ~TEST_CHANGE_BITS); +} + +/* To check that scoped assertions do trigger anywhere in scope. */ +static noinline void test_enter_scope(void) +{ + int x = 0; + + /* Unrelated accesses to scoped assert. */ + READ_ONCE(test_sink); + kcsan_check_read(&x, sizeof(x)); +} + +static noinline void test_kernel_assert_writer_scoped(void) +{ + ASSERT_EXCLUSIVE_WRITER_SCOPED(test_var); + test_enter_scope(); +} + +static noinline void test_kernel_assert_access_scoped(void) +{ + ASSERT_EXCLUSIVE_ACCESS_SCOPED(test_var); + test_enter_scope(); +} + +static noinline void test_kernel_rmw_array(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(test_array); ++i) + test_array[i]++; +} + +static noinline void test_kernel_write_struct(void) +{ + kcsan_check_write(&test_struct, sizeof(test_struct)); + kcsan_disable_current(); + test_struct.val[3]++; /* induce value change */ + kcsan_enable_current(); +} + +static noinline void test_kernel_write_struct_part(void) +{ + test_struct.val[3] = 42; +} + +static noinline void test_kernel_read_struct_zero_size(void) +{ + kcsan_check_read(&test_struct.val[3], 0); +} + +static noinline void test_kernel_jiffies_reader(void) +{ + sink_value((long)jiffies); +} + +static noinline void test_kernel_seqlock_reader(void) +{ + unsigned int seq; + + do { + seq = read_seqbegin(&test_seqlock); + sink_value(test_var); + } while (read_seqretry(&test_seqlock, seq)); +} + +static noinline void test_kernel_seqlock_writer(void) +{ + unsigned long flags; + + write_seqlock_irqsave(&test_seqlock, flags); + test_var++; + write_sequnlock_irqrestore(&test_seqlock, flags); +} + +/* ===== Test cases ===== */ + +/* Simple test with normal data race. */ +__no_kcsan +static void test_basic(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + static const struct expect_report never = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + bool match_never = false; + + begin_test_checks(test_kernel_write, test_kernel_read); + do { + match_expect |= report_matches(&expect); + match_never = report_matches(&never); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_TRUE(test, match_expect); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* + * Stress KCSAN with lots of concurrent races on different addresses until + * timeout. + */ +__no_kcsan +static void test_concurrent_races(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + /* NULL will match any address. */ + { test_kernel_rmw_array, NULL, 0, KCSAN_ACCESS_WRITE }, + { test_kernel_rmw_array, NULL, 0, 0 }, + }, + }; + static const struct expect_report never = { + .access = { + { test_kernel_rmw_array, NULL, 0, 0 }, + { test_kernel_rmw_array, NULL, 0, 0 }, + }, + }; + bool match_expect = false; + bool match_never = false; + + begin_test_checks(test_kernel_rmw_array, test_kernel_rmw_array); + do { + match_expect |= report_matches(&expect); + match_never |= report_matches(&never); + } while (!end_test_checks(false)); + KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check matches exist. */ + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test the KCSAN_REPORT_VALUE_CHANGE_ONLY option. */ +__no_kcsan +static void test_novalue_change(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_nochange, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY)) + KUNIT_EXPECT_FALSE(test, match_expect); + else + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* + * Test that the rules where the KCSAN_REPORT_VALUE_CHANGE_ONLY option should + * never apply work. + */ +__no_kcsan +static void test_novalue_change_exception(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_nochange_rcu, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Test that data races of unknown origin are reported. */ +__no_kcsan +static void test_unknown_origin(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { NULL }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_uninstrumented, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN)) + KUNIT_EXPECT_TRUE(test, match_expect); + else + KUNIT_EXPECT_FALSE(test, match_expect); +} + +/* Test KCSAN_ASSUME_PLAIN_WRITES_ATOMIC if it is selected. */ +__no_kcsan +static void test_write_write_assume_atomic(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write, test_kernel_write); + do { + sink_value(READ_ONCE(test_var)); /* induce value-change */ + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) + KUNIT_EXPECT_FALSE(test, match_expect); + else + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* + * Test that data races with writes larger than word-size are always reported, + * even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected. + */ +__no_kcsan +static void test_write_write_struct(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_struct, test_kernel_write_struct); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* + * Test that data races where only one write is larger than word-size are always + * reported, even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected. + */ +__no_kcsan +static void test_write_write_struct_part(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_write_struct_part, &test_struct.val[3], sizeof(test_struct.val[3]), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_struct, test_kernel_write_struct_part); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Test that races with atomic accesses never result in reports. */ +__no_kcsan +static void test_read_atomic_write_atomic(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_read_atomic, test_kernel_write_atomic); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test that a race with an atomic and plain access result in reports. */ +__no_kcsan +static void test_read_plain_atomic_write(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { test_kernel_write_atomic, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC }, + }, + }; + bool match_expect = false; + + if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) + return; + + begin_test_checks(test_kernel_read, test_kernel_write_atomic); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Zero-sized accesses should never cause data race reports. */ +__no_kcsan +static void test_zero_size_access(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + }, + }; + const struct expect_report never = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_read_struct_zero_size, &test_struct.val[3], 0, 0 }, + }, + }; + bool match_expect = false; + bool match_never = false; + + begin_test_checks(test_kernel_write_struct, test_kernel_read_struct_zero_size); + do { + match_expect |= report_matches(&expect); + match_never = report_matches(&never); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check. */ + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test the data_race() macro. */ +__no_kcsan +static void test_data_race(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_data_race, test_kernel_data_race); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_assert_exclusive_writer(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_assert_writer, test_kernel_write_nochange); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +__no_kcsan +static void test_assert_exclusive_access(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_assert_access, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +__no_kcsan +static void test_assert_exclusive_access_writer(struct kunit *test) +{ + const struct expect_report expect_access_writer = { + .access = { + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + }, + }; + const struct expect_report expect_access_access = { + .access = { + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + }, + }; + const struct expect_report never = { + .access = { + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + }, + }; + bool match_expect_access_writer = false; + bool match_expect_access_access = false; + bool match_never = false; + + begin_test_checks(test_kernel_assert_access, test_kernel_assert_writer); + do { + match_expect_access_writer |= report_matches(&expect_access_writer); + match_expect_access_access |= report_matches(&expect_access_access); + match_never |= report_matches(&never); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_TRUE(test, match_expect_access_writer); + KUNIT_EXPECT_TRUE(test, match_expect_access_access); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_assert_exclusive_bits_change(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_assert_bits_change, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + { test_kernel_change_bits, &test_var, sizeof(test_var), + KCSAN_ACCESS_WRITE | (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) ? 0 : KCSAN_ACCESS_ATOMIC) }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_assert_bits_change, test_kernel_change_bits); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +__no_kcsan +static void test_assert_exclusive_bits_nochange(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_assert_bits_nochange, test_kernel_change_bits); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_assert_exclusive_writer_scoped(struct kunit *test) +{ + const struct expect_report expect_start = { + .access = { + { test_kernel_assert_writer_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + const struct expect_report expect_anywhere = { + .access = { + { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect_start = false; + bool match_expect_anywhere = false; + + begin_test_checks(test_kernel_assert_writer_scoped, test_kernel_write_nochange); + do { + match_expect_start |= report_matches(&expect_start); + match_expect_anywhere |= report_matches(&expect_anywhere); + } while (!end_test_checks(match_expect_start && match_expect_anywhere)); + KUNIT_EXPECT_TRUE(test, match_expect_start); + KUNIT_EXPECT_TRUE(test, match_expect_anywhere); +} + +__no_kcsan +static void test_assert_exclusive_access_scoped(struct kunit *test) +{ + const struct expect_report expect_start1 = { + .access = { + { test_kernel_assert_access_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + const struct expect_report expect_start2 = { + .access = { expect_start1.access[0], expect_start1.access[0] }, + }; + const struct expect_report expect_inscope = { + .access = { + { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect_start = false; + bool match_expect_inscope = false; + + begin_test_checks(test_kernel_assert_access_scoped, test_kernel_read); + end_time += msecs_to_jiffies(1000); /* This test requires a bit more time. */ + do { + match_expect_start |= report_matches(&expect_start1) || report_matches(&expect_start2); + match_expect_inscope |= report_matches(&expect_inscope); + } while (!end_test_checks(match_expect_start && match_expect_inscope)); + KUNIT_EXPECT_TRUE(test, match_expect_start); + KUNIT_EXPECT_TRUE(test, match_expect_inscope); +} + +/* + * jiffies is special (declared to be volatile) and its accesses are typically + * not marked; this test ensures that the compiler nor KCSAN gets confused about + * jiffies's declaration on different architectures. + */ +__no_kcsan +static void test_jiffies_noreport(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_jiffies_reader, test_kernel_jiffies_reader); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test that racing accesses in seqlock critical sections are not reported. */ +__no_kcsan +static void test_seqlock_noreport(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_seqlock_reader, test_kernel_seqlock_writer); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* + * Each test case is run with different numbers of threads. Until KUnit supports + * passing arguments for each test case, we encode #threads in the test case + * name (read by get_num_threads()). [The '-' was chosen as a stylistic + * preference to separate test name and #threads.] + * + * The thread counts are chosen to cover potentially interesting boundaries and + * corner cases (range 2-5), and then stress the system with larger counts. + */ +#define KCSAN_KUNIT_CASE(test_name) \ + { .run_case = test_name, .name = #test_name "-02" }, \ + { .run_case = test_name, .name = #test_name "-03" }, \ + { .run_case = test_name, .name = #test_name "-04" }, \ + { .run_case = test_name, .name = #test_name "-05" }, \ + { .run_case = test_name, .name = #test_name "-08" }, \ + { .run_case = test_name, .name = #test_name "-16" } + +static struct kunit_case kcsan_test_cases[] = { + KCSAN_KUNIT_CASE(test_basic), + KCSAN_KUNIT_CASE(test_concurrent_races), + KCSAN_KUNIT_CASE(test_novalue_change), + KCSAN_KUNIT_CASE(test_novalue_change_exception), + KCSAN_KUNIT_CASE(test_unknown_origin), + KCSAN_KUNIT_CASE(test_write_write_assume_atomic), + KCSAN_KUNIT_CASE(test_write_write_struct), + KCSAN_KUNIT_CASE(test_write_write_struct_part), + KCSAN_KUNIT_CASE(test_read_atomic_write_atomic), + KCSAN_KUNIT_CASE(test_read_plain_atomic_write), + KCSAN_KUNIT_CASE(test_zero_size_access), + KCSAN_KUNIT_CASE(test_data_race), + KCSAN_KUNIT_CASE(test_assert_exclusive_writer), + KCSAN_KUNIT_CASE(test_assert_exclusive_access), + KCSAN_KUNIT_CASE(test_assert_exclusive_access_writer), + KCSAN_KUNIT_CASE(test_assert_exclusive_bits_change), + KCSAN_KUNIT_CASE(test_assert_exclusive_bits_nochange), + KCSAN_KUNIT_CASE(test_assert_exclusive_writer_scoped), + KCSAN_KUNIT_CASE(test_assert_exclusive_access_scoped), + KCSAN_KUNIT_CASE(test_jiffies_noreport), + KCSAN_KUNIT_CASE(test_seqlock_noreport), + {}, +}; + +/* ===== End test cases ===== */ + +/* Get number of threads encoded in test name. */ +static bool __no_kcsan +get_num_threads(const char *test, int *nthreads) +{ + int len = strlen(test); + + if (WARN_ON(len < 3)) + return false; + + *nthreads = test[len - 1] - '0'; + *nthreads += (test[len - 2] - '0') * 10; + + if (WARN_ON(*nthreads < 0)) + return false; + + return true; +} + +/* Concurrent accesses from interrupts. */ +__no_kcsan +static void access_thread_timer(struct timer_list *timer) +{ + static atomic_t cnt = ATOMIC_INIT(0); + unsigned int idx; + void (*func)(void); + + idx = (unsigned int)atomic_inc_return(&cnt) % ARRAY_SIZE(access_kernels); + /* Acquire potential initialization. */ + func = smp_load_acquire(&access_kernels[idx]); + if (func) + func(); +} + +/* The main loop for each thread. */ +__no_kcsan +static int access_thread(void *arg) +{ + struct timer_list timer; + unsigned int cnt = 0; + unsigned int idx; + void (*func)(void); + + timer_setup_on_stack(&timer, access_thread_timer, 0); + do { + might_sleep(); + + if (!timer_pending(&timer)) + mod_timer(&timer, jiffies + 1); + else { + /* Iterate through all kernels. */ + idx = cnt++ % ARRAY_SIZE(access_kernels); + /* Acquire potential initialization. */ + func = smp_load_acquire(&access_kernels[idx]); + if (func) + func(); + } + } while (!torture_must_stop()); + del_timer_sync(&timer); + destroy_timer_on_stack(&timer); + + torture_kthread_stopping("access_thread"); + return 0; +} + +__no_kcsan +static int test_init(struct kunit *test) +{ + unsigned long flags; + int nthreads; + int i; + + spin_lock_irqsave(&observed.lock, flags); + for (i = 0; i < ARRAY_SIZE(observed.lines); ++i) + observed.lines[i][0] = '\0'; + observed.nlines = 0; + spin_unlock_irqrestore(&observed.lock, flags); + + if (!torture_init_begin((char *)test->name, 1)) + return -EBUSY; + + if (!get_num_threads(test->name, &nthreads)) + goto err; + + if (WARN_ON(threads)) + goto err; + + for (i = 0; i < ARRAY_SIZE(access_kernels); ++i) { + if (WARN_ON(access_kernels[i])) + goto err; + } + + if (!IS_ENABLED(CONFIG_PREEMPT) || !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) { + /* + * Without any preemption, keep 2 CPUs free for other tasks, one + * of which is the main test case function checking for + * completion or failure. + */ + const int min_unused_cpus = IS_ENABLED(CONFIG_PREEMPT_NONE) ? 2 : 0; + const int min_required_cpus = 2 + min_unused_cpus; + + if (num_online_cpus() < min_required_cpus) { + pr_err("%s: too few online CPUs (%u < %d) for test", + test->name, num_online_cpus(), min_required_cpus); + goto err; + } else if (nthreads > num_online_cpus() - min_unused_cpus) { + nthreads = num_online_cpus() - min_unused_cpus; + pr_warn("%s: limiting number of threads to %d\n", + test->name, nthreads); + } + } + + if (nthreads) { + threads = kcalloc(nthreads + 1, sizeof(struct task_struct *), + GFP_KERNEL); + if (WARN_ON(!threads)) + goto err; + + threads[nthreads] = NULL; + for (i = 0; i < nthreads; ++i) { + if (torture_create_kthread(access_thread, NULL, + threads[i])) + goto err; + } + } + + torture_init_end(); + + return 0; + +err: + kfree(threads); + threads = NULL; + torture_init_end(); + return -EINVAL; +} + +__no_kcsan +static void test_exit(struct kunit *test) +{ + struct task_struct **stop_thread; + int i; + + if (torture_cleanup_begin()) + return; + + for (i = 0; i < ARRAY_SIZE(access_kernels); ++i) + WRITE_ONCE(access_kernels[i], NULL); + + if (threads) { + for (stop_thread = threads; *stop_thread; stop_thread++) + torture_stop_kthread(reader_thread, *stop_thread); + + kfree(threads); + threads = NULL; + } + + torture_cleanup_end(); +} + +static struct kunit_suite kcsan_test_suite = { + .name = "kcsan-test", + .test_cases = kcsan_test_cases, + .init = test_init, + .exit = test_exit, +}; +static struct kunit_suite *kcsan_test_suites[] = { &kcsan_test_suite, NULL }; + +__no_kcsan +static void register_tracepoints(struct tracepoint *tp, void *ignore) +{ + check_trace_callback_type_console(probe_console); + if (!strcmp(tp->name, "console")) + WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); +} + +__no_kcsan +static void unregister_tracepoints(struct tracepoint *tp, void *ignore) +{ + if (!strcmp(tp->name, "console")) + tracepoint_probe_unregister(tp, probe_console, NULL); +} + +/* + * We only want to do tracepoints setup and teardown once, therefore we have to + * customize the init and exit functions and cannot rely on kunit_test_suite(). + */ +static int __init kcsan_test_init(void) +{ + /* + * Because we want to be able to build the test as a module, we need to + * iterate through all known tracepoints, since the static registration + * won't work here. + */ + for_each_kernel_tracepoint(register_tracepoints, NULL); + return __kunit_test_suites_init(kcsan_test_suites); +} + +static void kcsan_test_exit(void) +{ + __kunit_test_suites_exit(kcsan_test_suites); + for_each_kernel_tracepoint(unregister_tracepoints, NULL); + tracepoint_synchronize_unregister(); +} + +late_initcall(kcsan_test_init); +module_exit(kcsan_test_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Marco Elver <elver@google.com>"); diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h index 763d6d08d94b..29480010dc30 100644 --- a/kernel/kcsan/kcsan.h +++ b/kernel/kcsan/kcsan.h @@ -9,6 +9,7 @@ #define _KERNEL_KCSAN_KCSAN_H #include <linux/kcsan.h> +#include <linux/sched.h> /* The number of adjacent watchpoints to check. */ #define KCSAN_CHECK_ADJACENT 1 @@ -23,6 +24,12 @@ extern unsigned int kcsan_udelay_interrupt; extern bool kcsan_enabled; /* + * Save/restore IRQ flags state trace dirtied by KCSAN. + */ +void kcsan_save_irqtrace(struct task_struct *task); +void kcsan_restore_irqtrace(struct task_struct *task); + +/* * Initialize debugfs file. */ void kcsan_debugfs_init(void); diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c index ac5f8345bae9..9d07e175de0f 100644 --- a/kernel/kcsan/report.c +++ b/kernel/kcsan/report.c @@ -308,6 +308,9 @@ static void print_verbose_info(struct task_struct *task) if (!task) return; + /* Restore IRQ state trace for printing. */ + kcsan_restore_irqtrace(task); + pr_err("\n"); debug_show_held_locks(task); print_irqtrace_events(task); @@ -606,10 +609,11 @@ void kcsan_report(const volatile void *ptr, size_t size, int access_type, goto out; /* - * With TRACE_IRQFLAGS, lockdep's IRQ trace state becomes corrupted if - * we do not turn off lockdep here; this could happen due to recursion - * into lockdep via KCSAN if we detect a race in utilities used by - * lockdep. + * Because we may generate reports when we're in scheduler code, the use + * of printk() could deadlock. Until such time that all printing code + * called in print_report() is scheduler-safe, accept the risk, and just + * get our message out. As such, also disable lockdep to hide the + * warning, and avoid disabling lockdep for the rest of the kernel. */ lockdep_off(); diff --git a/kernel/kcsan/test.c b/kernel/kcsan/selftest.c index d26a052d3383..d26a052d3383 100644 --- a/kernel/kcsan/test.c +++ b/kernel/kcsan/selftest.c diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 29a8de4c50b9..f361d75a75ac 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -395,7 +395,7 @@ void lockdep_init_task(struct task_struct *task) static __always_inline void lockdep_recursion_finish(void) { - if (WARN_ON_ONCE(--current->lockdep_recursion)) + if (WARN_ON_ONCE((--current->lockdep_recursion) & LOCKDEP_RECURSION_MASK)) current->lockdep_recursion = 0; } @@ -2062,9 +2062,9 @@ print_bad_irq_dependency(struct task_struct *curr, pr_warn("-----------------------------------------------------\n"); pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", curr->comm, task_pid_nr(curr), - curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT, + lockdep_hardirq_context(), hardirq_count() >> HARDIRQ_SHIFT, curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT, - curr->hardirqs_enabled, + lockdep_hardirqs_enabled(), curr->softirqs_enabled); print_lock(next); @@ -3331,9 +3331,9 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n", curr->comm, task_pid_nr(curr), - lockdep_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT, + lockdep_hardirq_context(), hardirq_count() >> HARDIRQ_SHIFT, lockdep_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT, - lockdep_hardirqs_enabled(curr), + lockdep_hardirqs_enabled(), lockdep_softirqs_enabled(curr)); print_lock(this); @@ -3484,19 +3484,21 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this, void print_irqtrace_events(struct task_struct *curr) { - printk("irq event stamp: %u\n", curr->irq_events); + const struct irqtrace_events *trace = &curr->irqtrace; + + printk("irq event stamp: %u\n", trace->irq_events); printk("hardirqs last enabled at (%u): [<%px>] %pS\n", - curr->hardirq_enable_event, (void *)curr->hardirq_enable_ip, - (void *)curr->hardirq_enable_ip); + trace->hardirq_enable_event, (void *)trace->hardirq_enable_ip, + (void *)trace->hardirq_enable_ip); printk("hardirqs last disabled at (%u): [<%px>] %pS\n", - curr->hardirq_disable_event, (void *)curr->hardirq_disable_ip, - (void *)curr->hardirq_disable_ip); + trace->hardirq_disable_event, (void *)trace->hardirq_disable_ip, + (void *)trace->hardirq_disable_ip); printk("softirqs last enabled at (%u): [<%px>] %pS\n", - curr->softirq_enable_event, (void *)curr->softirq_enable_ip, - (void *)curr->softirq_enable_ip); + trace->softirq_enable_event, (void *)trace->softirq_enable_ip, + (void *)trace->softirq_enable_ip); printk("softirqs last disabled at (%u): [<%px>] %pS\n", - curr->softirq_disable_event, (void *)curr->softirq_disable_ip, - (void *)curr->softirq_disable_ip); + trace->softirq_disable_event, (void *)trace->softirq_disable_ip, + (void *)trace->softirq_disable_ip); } static int HARDIRQ_verbose(struct lock_class *class) @@ -3646,10 +3648,19 @@ static void __trace_hardirqs_on_caller(void) */ void lockdep_hardirqs_on_prepare(unsigned long ip) { - if (unlikely(!debug_locks || current->lockdep_recursion)) + if (unlikely(!debug_locks)) + return; + + /* + * NMIs do not (and cannot) track lock dependencies, nothing to do. + */ + if (unlikely(in_nmi())) + return; + + if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK)) return; - if (unlikely(current->hardirqs_enabled)) { + if (unlikely(lockdep_hardirqs_enabled())) { /* * Neither irq nor preemption are disabled here * so this is racy by nature but losing one hit @@ -3677,7 +3688,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip) * Can't allow enabling interrupts while in an interrupt handler, * that's general bad form and such. Recursion, limited stack etc.. */ - if (DEBUG_LOCKS_WARN_ON(current->hardirq_context)) + if (DEBUG_LOCKS_WARN_ON(lockdep_hardirq_context())) return; current->hardirq_chain_key = current->curr_chain_key; @@ -3690,12 +3701,35 @@ EXPORT_SYMBOL_GPL(lockdep_hardirqs_on_prepare); void noinstr lockdep_hardirqs_on(unsigned long ip) { - struct task_struct *curr = current; + struct irqtrace_events *trace = ¤t->irqtrace; + + if (unlikely(!debug_locks)) + return; + + /* + * NMIs can happen in the middle of local_irq_{en,dis}able() where the + * tracking state and hardware state are out of sync. + * + * NMIs must save lockdep_hardirqs_enabled() to restore IRQ state from, + * and not rely on hardware state like normal interrupts. + */ + if (unlikely(in_nmi())) { + if (!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_NMI)) + return; + + /* + * Skip: + * - recursion check, because NMI can hit lockdep; + * - hardware state check, because above; + * - chain_key check, see lockdep_hardirqs_on_prepare(). + */ + goto skip_checks; + } - if (unlikely(!debug_locks || curr->lockdep_recursion)) + if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK)) return; - if (curr->hardirqs_enabled) { + if (lockdep_hardirqs_enabled()) { /* * Neither irq nor preemption are disabled here * so this is racy by nature but losing one hit @@ -3720,10 +3754,11 @@ void noinstr lockdep_hardirqs_on(unsigned long ip) DEBUG_LOCKS_WARN_ON(current->hardirq_chain_key != current->curr_chain_key); +skip_checks: /* we'll do an OFF -> ON transition: */ - curr->hardirqs_enabled = 1; - curr->hardirq_enable_ip = ip; - curr->hardirq_enable_event = ++curr->irq_events; + this_cpu_write(hardirqs_enabled, 1); + trace->hardirq_enable_ip = ip; + trace->hardirq_enable_event = ++trace->irq_events; debug_atomic_inc(hardirqs_on_events); } EXPORT_SYMBOL_GPL(lockdep_hardirqs_on); @@ -3733,9 +3768,18 @@ EXPORT_SYMBOL_GPL(lockdep_hardirqs_on); */ void noinstr lockdep_hardirqs_off(unsigned long ip) { - struct task_struct *curr = current; + if (unlikely(!debug_locks)) + return; - if (unlikely(!debug_locks || curr->lockdep_recursion)) + /* + * Matching lockdep_hardirqs_on(), allow NMIs in the middle of lockdep; + * they will restore the software state. This ensures the software + * state is consistent inside NMIs as well. + */ + if (in_nmi()) { + if (!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_NMI)) + return; + } else if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK) return; /* @@ -3745,13 +3789,15 @@ void noinstr lockdep_hardirqs_off(unsigned long ip) if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return; - if (curr->hardirqs_enabled) { + if (lockdep_hardirqs_enabled()) { + struct irqtrace_events *trace = ¤t->irqtrace; + /* * We have done an ON -> OFF transition: */ - curr->hardirqs_enabled = 0; - curr->hardirq_disable_ip = ip; - curr->hardirq_disable_event = ++curr->irq_events; + this_cpu_write(hardirqs_enabled, 0); + trace->hardirq_disable_ip = ip; + trace->hardirq_disable_event = ++trace->irq_events; debug_atomic_inc(hardirqs_off_events); } else { debug_atomic_inc(redundant_hardirqs_off); @@ -3764,7 +3810,7 @@ EXPORT_SYMBOL_GPL(lockdep_hardirqs_off); */ void lockdep_softirqs_on(unsigned long ip) { - struct task_struct *curr = current; + struct irqtrace_events *trace = ¤t->irqtrace; if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -3776,7 +3822,7 @@ void lockdep_softirqs_on(unsigned long ip) if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return; - if (curr->softirqs_enabled) { + if (current->softirqs_enabled) { debug_atomic_inc(redundant_softirqs_on); return; } @@ -3785,17 +3831,17 @@ void lockdep_softirqs_on(unsigned long ip) /* * We'll do an OFF -> ON transition: */ - curr->softirqs_enabled = 1; - curr->softirq_enable_ip = ip; - curr->softirq_enable_event = ++curr->irq_events; + current->softirqs_enabled = 1; + trace->softirq_enable_ip = ip; + trace->softirq_enable_event = ++trace->irq_events; debug_atomic_inc(softirqs_on_events); /* * We are going to turn softirqs on, so set the * usage bit for all held locks, if hardirqs are * enabled too: */ - if (curr->hardirqs_enabled) - mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ); + if (lockdep_hardirqs_enabled()) + mark_held_locks(current, LOCK_ENABLED_SOFTIRQ); lockdep_recursion_finish(); } @@ -3804,8 +3850,6 @@ void lockdep_softirqs_on(unsigned long ip) */ void lockdep_softirqs_off(unsigned long ip) { - struct task_struct *curr = current; - if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -3815,13 +3859,15 @@ void lockdep_softirqs_off(unsigned long ip) if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return; - if (curr->softirqs_enabled) { + if (current->softirqs_enabled) { + struct irqtrace_events *trace = ¤t->irqtrace; + /* * We have done an ON -> OFF transition: */ - curr->softirqs_enabled = 0; - curr->softirq_disable_ip = ip; - curr->softirq_disable_event = ++curr->irq_events; + current->softirqs_enabled = 0; + trace->softirq_disable_ip = ip; + trace->softirq_disable_event = ++trace->irq_events; debug_atomic_inc(softirqs_off_events); /* * Whoops, we wanted softirqs off, so why aren't they? @@ -3843,7 +3889,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check) */ if (!hlock->trylock) { if (hlock->read) { - if (curr->hardirq_context) + if (lockdep_hardirq_context()) if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ_READ)) return 0; @@ -3852,7 +3898,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check) LOCK_USED_IN_SOFTIRQ_READ)) return 0; } else { - if (curr->hardirq_context) + if (lockdep_hardirq_context()) if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ)) return 0; if (curr->softirq_context) @@ -3890,7 +3936,7 @@ lock_used: static inline unsigned int task_irq_context(struct task_struct *task) { - return LOCK_CHAIN_HARDIRQ_CONTEXT * !!task->hardirq_context + + return LOCK_CHAIN_HARDIRQ_CONTEXT * !!lockdep_hardirq_context() + LOCK_CHAIN_SOFTIRQ_CONTEXT * !!task->softirq_context; } @@ -3983,7 +4029,7 @@ static inline short task_wait_context(struct task_struct *curr) * Set appropriate wait type for the context; for IRQs we have to take * into account force_irqthread as that is implied by PREEMPT_RT. */ - if (curr->hardirq_context) { + if (lockdep_hardirq_context()) { /* * Check if force_irqthreads will run us threaded. */ @@ -4826,11 +4872,11 @@ static void check_flags(unsigned long flags) return; if (irqs_disabled_flags(flags)) { - if (DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)) { + if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled())) { printk("possible reason: unannotated irqs-off.\n"); } } else { - if (DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled)) { + if (DEBUG_LOCKS_WARN_ON(!lockdep_hardirqs_enabled())) { printk("possible reason: unannotated irqs-on.\n"); } } @@ -5851,9 +5897,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) pr_warn("\n%srcu_scheduler_active = %d, debug_locks = %d\n", !rcu_lockdep_current_cpu_online() ? "RCU used illegally from offline CPU!\n" - : !rcu_is_watching() - ? "RCU used illegally from idle CPU!\n" - : "", + : "", rcu_scheduler_active, debug_locks); /* diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 5efbfc68ce99..8ff6f50e06a0 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -631,13 +631,13 @@ static int lock_torture_writer(void *arg) cxt.cur_ops->writelock(); if (WARN_ON_ONCE(lock_is_write_held)) lwsp->n_lock_fail++; - lock_is_write_held = 1; + lock_is_write_held = true; if (WARN_ON_ONCE(lock_is_read_held)) lwsp->n_lock_fail++; /* rare, but... */ lwsp->n_lock_acquired++; cxt.cur_ops->write_delay(&rand); - lock_is_write_held = 0; + lock_is_write_held = false; cxt.cur_ops->writeunlock(); stutter_wait("lock_torture_writer"); @@ -665,13 +665,13 @@ static int lock_torture_reader(void *arg) schedule_timeout_uninterruptible(1); cxt.cur_ops->readlock(); - lock_is_read_held = 1; + lock_is_read_held = true; if (WARN_ON_ONCE(lock_is_write_held)) lrsp->n_lock_fail++; /* rare, but... */ lrsp->n_lock_acquired++; cxt.cur_ops->read_delay(&rand); - lock_is_read_held = 0; + lock_is_read_held = false; cxt.cur_ops->readunlock(); stutter_wait("lock_torture_reader"); @@ -686,7 +686,7 @@ static int lock_torture_reader(void *arg) static void __torture_print_stats(char *page, struct lock_stress_stats *statp, bool write) { - bool fail = 0; + bool fail = false; int i, n_stress; long max = 0, min = statp ? statp[0].n_lock_acquired : 0; long long sum = 0; @@ -904,7 +904,7 @@ static int __init lock_torture_init(void) /* Initialize the statistics so that each run gets its own numbers. */ if (nwriters_stress) { - lock_is_write_held = 0; + lock_is_write_held = false; cxt.lwsa = kmalloc_array(cxt.nrealwriters_stress, sizeof(*cxt.lwsa), GFP_KERNEL); @@ -935,7 +935,7 @@ static int __init lock_torture_init(void) } if (nreaders_stress) { - lock_is_read_held = 0; + lock_is_read_held = false; cxt.lrsa = kmalloc_array(cxt.nrealreaders_stress, sizeof(*cxt.lrsa), GFP_KERNEL); diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index 1f7734949ac8..1de006ed3aa8 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -154,7 +154,11 @@ bool osq_lock(struct optimistic_spin_queue *lock) */ for (;;) { - if (prev->next == node && + /* + * cpu_relax() below implies a compiler barrier which would + * prevent this comparison being optimized away. + */ + if (data_race(prev->next) == node && cmpxchg(&prev->next, node, NULL) == node) break; diff --git a/kernel/padata.c b/kernel/padata.c index 4373f7adaa40..16cb894dc272 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -250,13 +250,11 @@ EXPORT_SYMBOL(padata_do_parallel); static struct padata_priv *padata_find_next(struct parallel_data *pd, bool remove_object) { - struct padata_parallel_queue *next_queue; struct padata_priv *padata; struct padata_list *reorder; int cpu = pd->cpu; - next_queue = per_cpu_ptr(pd->pqueue, cpu); - reorder = &next_queue->reorder; + reorder = per_cpu_ptr(pd->reorder_list, cpu); spin_lock(&reorder->lock); if (list_empty(&reorder->list)) { @@ -291,7 +289,7 @@ static void padata_reorder(struct parallel_data *pd) int cb_cpu; struct padata_priv *padata; struct padata_serial_queue *squeue; - struct padata_parallel_queue *next_queue; + struct padata_list *reorder; /* * We need to ensure that only one cpu can work on dequeueing of @@ -339,9 +337,8 @@ static void padata_reorder(struct parallel_data *pd) */ smp_mb(); - next_queue = per_cpu_ptr(pd->pqueue, pd->cpu); - if (!list_empty(&next_queue->reorder.list) && - padata_find_next(pd, false)) + reorder = per_cpu_ptr(pd->reorder_list, pd->cpu); + if (!list_empty(&reorder->list) && padata_find_next(pd, false)) queue_work(pinst->serial_wq, &pd->reorder_work); } @@ -401,17 +398,16 @@ void padata_do_serial(struct padata_priv *padata) { struct parallel_data *pd = padata->pd; int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr); - struct padata_parallel_queue *pqueue = per_cpu_ptr(pd->pqueue, - hashed_cpu); + struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu); struct padata_priv *cur; - spin_lock(&pqueue->reorder.lock); + spin_lock(&reorder->lock); /* Sort in ascending order of sequence number. */ - list_for_each_entry_reverse(cur, &pqueue->reorder.list, list) + list_for_each_entry_reverse(cur, &reorder->list, list) if (cur->seq_nr < padata->seq_nr) break; list_add(&padata->list, &cur->list); - spin_unlock(&pqueue->reorder.lock); + spin_unlock(&reorder->lock); /* * Ensure the addition to the reorder list is ordered correctly @@ -441,28 +437,6 @@ static int padata_setup_cpumasks(struct padata_instance *pinst) return err; } -static int pd_setup_cpumasks(struct parallel_data *pd, - const struct cpumask *pcpumask, - const struct cpumask *cbcpumask) -{ - int err = -ENOMEM; - - if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL)) - goto out; - if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) - goto free_pcpu_mask; - - cpumask_copy(pd->cpumask.pcpu, pcpumask); - cpumask_copy(pd->cpumask.cbcpu, cbcpumask); - - return 0; - -free_pcpu_mask: - free_cpumask_var(pd->cpumask.pcpu); -out: - return err; -} - static void __init padata_mt_helper(struct work_struct *w) { struct padata_work *pw = container_of(w, struct padata_work, pw_work); @@ -575,17 +549,15 @@ static void padata_init_squeues(struct parallel_data *pd) } } -/* Initialize all percpu queues used by parallel workers */ -static void padata_init_pqueues(struct parallel_data *pd) +/* Initialize per-CPU reorder lists */ +static void padata_init_reorder_list(struct parallel_data *pd) { int cpu; - struct padata_parallel_queue *pqueue; + struct padata_list *list; for_each_cpu(cpu, pd->cpumask.pcpu) { - pqueue = per_cpu_ptr(pd->pqueue, cpu); - - __padata_list_init(&pqueue->reorder); - atomic_set(&pqueue->num_obj, 0); + list = per_cpu_ptr(pd->reorder_list, cpu); + __padata_list_init(list); } } @@ -593,30 +565,31 @@ static void padata_init_pqueues(struct parallel_data *pd) static struct parallel_data *padata_alloc_pd(struct padata_shell *ps) { struct padata_instance *pinst = ps->pinst; - const struct cpumask *cbcpumask; - const struct cpumask *pcpumask; struct parallel_data *pd; - cbcpumask = pinst->rcpumask.cbcpu; - pcpumask = pinst->rcpumask.pcpu; - pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL); if (!pd) goto err; - pd->pqueue = alloc_percpu(struct padata_parallel_queue); - if (!pd->pqueue) + pd->reorder_list = alloc_percpu(struct padata_list); + if (!pd->reorder_list) goto err_free_pd; pd->squeue = alloc_percpu(struct padata_serial_queue); if (!pd->squeue) - goto err_free_pqueue; + goto err_free_reorder_list; pd->ps = ps; - if (pd_setup_cpumasks(pd, pcpumask, cbcpumask)) + + if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL)) goto err_free_squeue; + if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) + goto err_free_pcpu; + + cpumask_and(pd->cpumask.pcpu, pinst->cpumask.pcpu, cpu_online_mask); + cpumask_and(pd->cpumask.cbcpu, pinst->cpumask.cbcpu, cpu_online_mask); - padata_init_pqueues(pd); + padata_init_reorder_list(pd); padata_init_squeues(pd); pd->seq_nr = -1; atomic_set(&pd->refcnt, 1); @@ -626,10 +599,12 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps) return pd; +err_free_pcpu: + free_cpumask_var(pd->cpumask.pcpu); err_free_squeue: free_percpu(pd->squeue); -err_free_pqueue: - free_percpu(pd->pqueue); +err_free_reorder_list: + free_percpu(pd->reorder_list); err_free_pd: kfree(pd); err: @@ -640,7 +615,7 @@ static void padata_free_pd(struct parallel_data *pd) { free_cpumask_var(pd->cpumask.pcpu); free_cpumask_var(pd->cpumask.cbcpu); - free_percpu(pd->pqueue); + free_percpu(pd->reorder_list); free_percpu(pd->squeue); kfree(pd); } @@ -682,12 +657,6 @@ static int padata_replace(struct padata_instance *pinst) pinst->flags |= PADATA_RESET; - cpumask_and(pinst->rcpumask.pcpu, pinst->cpumask.pcpu, - cpu_online_mask); - - cpumask_and(pinst->rcpumask.cbcpu, pinst->cpumask.cbcpu, - cpu_online_mask); - list_for_each_entry(ps, &pinst->pslist, list) { err = padata_replace_one(ps); if (err) @@ -789,43 +758,6 @@ out: } EXPORT_SYMBOL(padata_set_cpumask); -/** - * padata_start - start the parallel processing - * - * @pinst: padata instance to start - * - * Return: 0 on success or negative error code - */ -int padata_start(struct padata_instance *pinst) -{ - int err = 0; - - mutex_lock(&pinst->lock); - - if (pinst->flags & PADATA_INVALID) - err = -EINVAL; - - __padata_start(pinst); - - mutex_unlock(&pinst->lock); - - return err; -} -EXPORT_SYMBOL(padata_start); - -/** - * padata_stop - stop the parallel processing - * - * @pinst: padata instance to stop - */ -void padata_stop(struct padata_instance *pinst) -{ - mutex_lock(&pinst->lock); - __padata_stop(pinst); - mutex_unlock(&pinst->lock); -} -EXPORT_SYMBOL(padata_stop); - #ifdef CONFIG_HOTPLUG_CPU static int __padata_add_cpu(struct padata_instance *pinst, int cpu) @@ -907,9 +839,6 @@ static void __padata_free(struct padata_instance *pinst) WARN_ON(!list_empty(&pinst->pslist)); - padata_stop(pinst); - free_cpumask_var(pinst->rcpumask.cbcpu); - free_cpumask_var(pinst->rcpumask.pcpu); free_cpumask_var(pinst->cpumask.pcpu); free_cpumask_var(pinst->cpumask.cbcpu); destroy_workqueue(pinst->serial_wq); @@ -1044,18 +973,12 @@ static struct kobj_type padata_attr_type = { }; /** - * padata_alloc - allocate and initialize a padata instance and specify - * cpumasks for serial and parallel workers. - * + * padata_alloc - allocate and initialize a padata instance * @name: used to identify the instance - * @pcpumask: cpumask that will be used for padata parallelization - * @cbcpumask: cpumask that will be used for padata serialization * * Return: new instance on success, NULL on error */ -static struct padata_instance *padata_alloc(const char *name, - const struct cpumask *pcpumask, - const struct cpumask *cbcpumask) +struct padata_instance *padata_alloc(const char *name) { struct padata_instance *pinst; @@ -1081,26 +1004,16 @@ static struct padata_instance *padata_alloc(const char *name, free_cpumask_var(pinst->cpumask.pcpu); goto err_free_serial_wq; } - if (!padata_validate_cpumask(pinst, pcpumask) || - !padata_validate_cpumask(pinst, cbcpumask)) - goto err_free_masks; - - if (!alloc_cpumask_var(&pinst->rcpumask.pcpu, GFP_KERNEL)) - goto err_free_masks; - if (!alloc_cpumask_var(&pinst->rcpumask.cbcpu, GFP_KERNEL)) - goto err_free_rcpumask_pcpu; INIT_LIST_HEAD(&pinst->pslist); - cpumask_copy(pinst->cpumask.pcpu, pcpumask); - cpumask_copy(pinst->cpumask.cbcpu, cbcpumask); - cpumask_and(pinst->rcpumask.pcpu, pcpumask, cpu_online_mask); - cpumask_and(pinst->rcpumask.cbcpu, cbcpumask, cpu_online_mask); + cpumask_copy(pinst->cpumask.pcpu, cpu_possible_mask); + cpumask_copy(pinst->cpumask.cbcpu, cpu_possible_mask); if (padata_setup_cpumasks(pinst)) - goto err_free_rcpumask_cbcpu; + goto err_free_masks; - pinst->flags = 0; + __padata_start(pinst); kobject_init(&pinst->kobj, &padata_attr_type); mutex_init(&pinst->lock); @@ -1116,10 +1029,6 @@ static struct padata_instance *padata_alloc(const char *name, return pinst; -err_free_rcpumask_cbcpu: - free_cpumask_var(pinst->rcpumask.cbcpu); -err_free_rcpumask_pcpu: - free_cpumask_var(pinst->rcpumask.pcpu); err_free_masks: free_cpumask_var(pinst->cpumask.pcpu); free_cpumask_var(pinst->cpumask.cbcpu); @@ -1133,21 +1042,7 @@ err_free_inst: err: return NULL; } - -/** - * padata_alloc_possible - Allocate and initialize padata instance. - * Use the cpu_possible_mask for serial and - * parallel workers. - * - * @name: used to identify the instance - * - * Return: new instance on success, NULL on error - */ -struct padata_instance *padata_alloc_possible(const char *name) -{ - return padata_alloc(name, cpu_possible_mask, cpu_possible_mask); -} -EXPORT_SYMBOL(padata_alloc_possible); +EXPORT_SYMBOL(padata_alloc); /** * padata_free - free a padata instance diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 452feae8de20..3cf6132a4bb9 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -61,6 +61,25 @@ config RCU_TORTURE_TEST Say M if you want the RCU torture tests to build as a module. Say N if you are unsure. +config RCU_REF_SCALE_TEST + tristate "Scalability tests for read-side synchronization (RCU and others)" + depends on DEBUG_KERNEL + select TORTURE_TEST + select SRCU + select TASKS_RCU + select TASKS_RUDE_RCU + select TASKS_TRACE_RCU + default n + help + This option provides a kernel module that runs performance tests + useful comparing RCU with various read-side synchronization mechanisms. + The kernel module may be built after the fact on the running kernel to be + tested, if desired. + + Say Y here if you want these performance tests built into the kernel. + Say M if you want to build it as a module instead. + Say N if you are unsure. + config RCU_CPU_STALL_TIMEOUT int "RCU CPU stall timeout in seconds" depends on RCU_STALL_COMMON diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index f91f2c2cf138..95f5117ef8da 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_TREE_SRCU) += srcutree.o obj-$(CONFIG_TINY_SRCU) += srcutiny.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o +obj-$(CONFIG_RCU_REF_SCALE_TEST) += refscale.o obj-$(CONFIG_TREE_RCU) += tree.o obj-$(CONFIG_TINY_RCU) += tiny.o obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index 9eb39c20082c..ec903d781778 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -69,6 +69,11 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>"); * value specified by nr_cpus for a read-only test. * * Various other use cases may of course be specified. + * + * Note that this test's readers are intended only as a test load for + * the writers. The reader performance statistics will be overly + * pessimistic due to the per-critical-section interrupt disabling, + * test-end checks, and the pair of calls through pointers. */ #ifdef MODULE @@ -309,8 +314,10 @@ static void rcu_perf_wait_shutdown(void) } /* - * RCU perf reader kthread. Repeatedly does empty RCU read-side - * critical section, minimizing update-side interference. + * RCU perf reader kthread. Repeatedly does empty RCU read-side critical + * section, minimizing update-side interference. However, the point of + * this test is not to evaluate reader performance, but instead to serve + * as a test load for update-side performance testing. */ static int rcu_perf_reader(void *arg) @@ -576,11 +583,8 @@ static int compute_real(int n) static int rcu_perf_shutdown(void *arg) { - do { - wait_event(shutdown_wq, - atomic_read(&n_rcu_perf_writer_finished) >= - nrealwriters); - } while (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters); + wait_event(shutdown_wq, + atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters); smp_mb(); /* Wake before output. */ rcu_perf_cleanup(); kernel_power_off(); @@ -693,11 +697,8 @@ kfree_perf_cleanup(void) static int kfree_perf_shutdown(void *arg) { - do { - wait_event(shutdown_wq, - atomic_read(&n_kfree_perf_thread_ended) >= - kfree_nrealthreads); - } while (atomic_read(&n_kfree_perf_thread_ended) < kfree_nrealthreads); + wait_event(shutdown_wq, + atomic_read(&n_kfree_perf_thread_ended) >= kfree_nrealthreads); smp_mb(); /* Wake before output. */ diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index efb792e13fca..d0d265304d14 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -7,7 +7,7 @@ * Authors: Paul E. McKenney <paulmck@linux.ibm.com> * Josh Triplett <josh@joshtriplett.org> * - * See also: Documentation/RCU/torture.txt + * See also: Documentation/RCU/torture.rst */ #define pr_fmt(fmt) fmt @@ -109,6 +109,10 @@ torture_param(int, object_debug, 0, torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (jiffies), 0=disable"); +torture_param(int, read_exit_delay, 13, + "Delay between read-then-exit episodes (s)"); +torture_param(int, read_exit_burst, 16, + "# of read-then-exit bursts per episode, zero to disable"); torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles"); torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); @@ -146,6 +150,7 @@ static struct task_struct *stall_task; static struct task_struct *fwd_prog_task; static struct task_struct **barrier_cbs_tasks; static struct task_struct *barrier_task; +static struct task_struct *read_exit_task; #define RCU_TORTURE_PIPE_LEN 10 @@ -177,6 +182,7 @@ static long n_rcu_torture_boosts; static atomic_long_t n_rcu_torture_timers; static long n_barrier_attempts; static long n_barrier_successes; /* did rcu_barrier test succeed? */ +static unsigned long n_read_exits; static struct list_head rcu_torture_removed; static unsigned long shutdown_jiffies; @@ -1166,6 +1172,7 @@ rcu_torture_writer(void *arg) WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count); } } while (!torture_must_stop()); + rcu_torture_current = NULL; // Let stats task know that we are done. /* Reset expediting back to unexpedited. */ if (expediting > 0) expediting = -expediting; @@ -1370,6 +1377,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp) struct rt_read_seg *rtrsp1; unsigned long long ts; + WARN_ON_ONCE(!rcu_is_watching()); newstate = rcutorture_extend_mask(readstate, trsp); rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++); started = cur_ops->get_gp_seq(); @@ -1539,10 +1547,11 @@ rcu_torture_stats_print(void) n_rcu_torture_boosts, atomic_long_read(&n_rcu_torture_timers)); torture_onoff_stats(); - pr_cont("barrier: %ld/%ld:%ld\n", + pr_cont("barrier: %ld/%ld:%ld ", data_race(n_barrier_successes), data_race(n_barrier_attempts), data_race(n_rcu_torture_barrier_error)); + pr_cont("read-exits: %ld\n", data_race(n_read_exits)); pr_alert("%s%s ", torture_type, TORTURE_FLAG); if (atomic_read(&n_rcu_torture_mberror) || @@ -1634,7 +1643,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) "stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d " "stall_cpu_block=%d " "n_barrier_cbs=%d " - "onoff_interval=%d onoff_holdoff=%d\n", + "onoff_interval=%d onoff_holdoff=%d " + "read_exit_delay=%d read_exit_burst=%d\n", torture_type, tag, nrealreaders, nfakewriters, stat_interval, verbose, test_no_idle_hz, shuffle_interval, stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, @@ -1643,7 +1653,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff, stall_cpu_block, n_barrier_cbs, - onoff_interval, onoff_holdoff); + onoff_interval, onoff_holdoff, + read_exit_delay, read_exit_burst); } static int rcutorture_booster_cleanup(unsigned int cpu) @@ -2175,7 +2186,7 @@ static void rcu_torture_barrier1cb(void *rcu_void) static int rcu_torture_barrier_cbs(void *arg) { long myid = (long)arg; - bool lastphase = 0; + bool lastphase = false; bool newphase; struct rcu_head rcu; @@ -2338,6 +2349,99 @@ static bool rcu_torture_can_boost(void) return true; } +static bool read_exit_child_stop; +static bool read_exit_child_stopped; +static wait_queue_head_t read_exit_wq; + +// Child kthread which just does an rcutorture reader and exits. +static int rcu_torture_read_exit_child(void *trsp_in) +{ + struct torture_random_state *trsp = trsp_in; + + set_user_nice(current, MAX_NICE); + // Minimize time between reading and exiting. + while (!kthread_should_stop()) + schedule_timeout_uninterruptible(1); + (void)rcu_torture_one_read(trsp); + return 0; +} + +// Parent kthread which creates and destroys read-exit child kthreads. +static int rcu_torture_read_exit(void *unused) +{ + int count = 0; + bool errexit = false; + int i; + struct task_struct *tsp; + DEFINE_TORTURE_RANDOM(trs); + + // Allocate and initialize. + set_user_nice(current, MAX_NICE); + VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of test"); + + // Each pass through this loop does one read-exit episode. + do { + if (++count > read_exit_burst) { + VERBOSE_TOROUT_STRING("rcu_torture_read_exit: End of episode"); + rcu_barrier(); // Wait for task_struct free, avoid OOM. + for (i = 0; i < read_exit_delay; i++) { + schedule_timeout_uninterruptible(HZ); + if (READ_ONCE(read_exit_child_stop)) + break; + } + if (!READ_ONCE(read_exit_child_stop)) + VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of episode"); + count = 0; + } + if (READ_ONCE(read_exit_child_stop)) + break; + // Spawn child. + tsp = kthread_run(rcu_torture_read_exit_child, + &trs, "%s", + "rcu_torture_read_exit_child"); + if (IS_ERR(tsp)) { + VERBOSE_TOROUT_ERRSTRING("out of memory"); + errexit = true; + tsp = NULL; + break; + } + cond_resched(); + kthread_stop(tsp); + n_read_exits ++; + stutter_wait("rcu_torture_read_exit"); + } while (!errexit && !READ_ONCE(read_exit_child_stop)); + + // Clean up and exit. + smp_store_release(&read_exit_child_stopped, true); // After reaping. + smp_mb(); // Store before wakeup. + wake_up(&read_exit_wq); + while (!torture_must_stop()) + schedule_timeout_uninterruptible(1); + torture_kthread_stopping("rcu_torture_read_exit"); + return 0; +} + +static int rcu_torture_read_exit_init(void) +{ + if (read_exit_burst <= 0) + return -EINVAL; + init_waitqueue_head(&read_exit_wq); + read_exit_child_stop = false; + read_exit_child_stopped = false; + return torture_create_kthread(rcu_torture_read_exit, NULL, + read_exit_task); +} + +static void rcu_torture_read_exit_cleanup(void) +{ + if (!read_exit_task) + return; + WRITE_ONCE(read_exit_child_stop, true); + smp_mb(); // Above write before wait. + wait_event(read_exit_wq, smp_load_acquire(&read_exit_child_stopped)); + torture_stop_kthread(rcutorture_read_exit, read_exit_task); +} + static enum cpuhp_state rcutor_hp; static void @@ -2359,6 +2463,7 @@ rcu_torture_cleanup(void) } show_rcu_gp_kthreads(); + rcu_torture_read_exit_cleanup(); rcu_torture_barrier_cleanup(); torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task); torture_stop_kthread(rcu_torture_stall, stall_task); @@ -2370,7 +2475,6 @@ rcu_torture_cleanup(void) reader_tasks[i]); kfree(reader_tasks); } - rcu_torture_current = NULL; if (fakewriter_tasks) { for (i = 0; i < nfakewriters; i++) { @@ -2682,6 +2786,9 @@ rcu_torture_init(void) firsterr = rcu_torture_barrier_init(); if (firsterr) goto unwind; + firsterr = rcu_torture_read_exit_init(); + if (firsterr) + goto unwind; if (object_debug) rcu_test_debug_objects(); torture_init_end(); diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c new file mode 100644 index 000000000000..d9291f883b54 --- /dev/null +++ b/kernel/rcu/refscale.c @@ -0,0 +1,717 @@ +// SPDX-License-Identifier: GPL-2.0+ +// +// Scalability test comparing RCU vs other mechanisms +// for acquiring references on objects. +// +// Copyright (C) Google, 2020. +// +// Author: Joel Fernandes <joel@joelfernandes.org> + +#define pr_fmt(fmt) fmt + +#include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/completion.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kthread.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/notifier.h> +#include <linux/percpu.h> +#include <linux/rcupdate.h> +#include <linux/rcupdate_trace.h> +#include <linux/reboot.h> +#include <linux/sched.h> +#include <linux/spinlock.h> +#include <linux/smp.h> +#include <linux/stat.h> +#include <linux/srcu.h> +#include <linux/slab.h> +#include <linux/torture.h> +#include <linux/types.h> + +#include "rcu.h" + +#define SCALE_FLAG "-ref-scale: " + +#define SCALEOUT(s, x...) \ + pr_alert("%s" SCALE_FLAG s, scale_type, ## x) + +#define VERBOSE_SCALEOUT(s, x...) \ + do { if (verbose) pr_alert("%s" SCALE_FLAG s, scale_type, ## x); } while (0) + +#define VERBOSE_SCALEOUT_ERRSTRING(s, x...) \ + do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! " s, scale_type, ## x); } while (0) + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Joel Fernandes (Google) <joel@joelfernandes.org>"); + +static char *scale_type = "rcu"; +module_param(scale_type, charp, 0444); +MODULE_PARM_DESC(scale_type, "Type of test (rcu, srcu, refcnt, rwsem, rwlock."); + +torture_param(int, verbose, 0, "Enable verbose debugging printk()s"); + +// Wait until there are multiple CPUs before starting test. +torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0, + "Holdoff time before test start (s)"); +// Number of loops per experiment, all readers execute operations concurrently. +torture_param(long, loops, 10000, "Number of loops per experiment."); +// Number of readers, with -1 defaulting to about 75% of the CPUs. +torture_param(int, nreaders, -1, "Number of readers, -1 for 75% of CPUs."); +// Number of runs. +torture_param(int, nruns, 30, "Number of experiments to run."); +// Reader delay in nanoseconds, 0 for no delay. +torture_param(int, readdelay, 0, "Read-side delay in nanoseconds."); + +#ifdef MODULE +# define REFSCALE_SHUTDOWN 0 +#else +# define REFSCALE_SHUTDOWN 1 +#endif + +torture_param(bool, shutdown, REFSCALE_SHUTDOWN, + "Shutdown at end of scalability tests."); + +struct reader_task { + struct task_struct *task; + int start_reader; + wait_queue_head_t wq; + u64 last_duration_ns; +}; + +static struct task_struct *shutdown_task; +static wait_queue_head_t shutdown_wq; + +static struct task_struct *main_task; +static wait_queue_head_t main_wq; +static int shutdown_start; + +static struct reader_task *reader_tasks; + +// Number of readers that are part of the current experiment. +static atomic_t nreaders_exp; + +// Use to wait for all threads to start. +static atomic_t n_init; +static atomic_t n_started; +static atomic_t n_warmedup; +static atomic_t n_cooleddown; + +// Track which experiment is currently running. +static int exp_idx; + +// Operations vector for selecting different types of tests. +struct ref_scale_ops { + void (*init)(void); + void (*cleanup)(void); + void (*readsection)(const int nloops); + void (*delaysection)(const int nloops, const int udl, const int ndl); + const char *name; +}; + +static struct ref_scale_ops *cur_ops; + +static void un_delay(const int udl, const int ndl) +{ + if (udl) + udelay(udl); + if (ndl) + ndelay(ndl); +} + +static void ref_rcu_read_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + rcu_read_lock(); + rcu_read_unlock(); + } +} + +static void ref_rcu_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + rcu_read_lock(); + un_delay(udl, ndl); + rcu_read_unlock(); + } +} + +static void rcu_sync_scale_init(void) +{ +} + +static struct ref_scale_ops rcu_ops = { + .init = rcu_sync_scale_init, + .readsection = ref_rcu_read_section, + .delaysection = ref_rcu_delay_section, + .name = "rcu" +}; + +// Definitions for SRCU ref scale testing. +DEFINE_STATIC_SRCU(srcu_refctl_scale); +static struct srcu_struct *srcu_ctlp = &srcu_refctl_scale; + +static void srcu_ref_scale_read_section(const int nloops) +{ + int i; + int idx; + + for (i = nloops; i >= 0; i--) { + idx = srcu_read_lock(srcu_ctlp); + srcu_read_unlock(srcu_ctlp, idx); + } +} + +static void srcu_ref_scale_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + int idx; + + for (i = nloops; i >= 0; i--) { + idx = srcu_read_lock(srcu_ctlp); + un_delay(udl, ndl); + srcu_read_unlock(srcu_ctlp, idx); + } +} + +static struct ref_scale_ops srcu_ops = { + .init = rcu_sync_scale_init, + .readsection = srcu_ref_scale_read_section, + .delaysection = srcu_ref_scale_delay_section, + .name = "srcu" +}; + +// Definitions for RCU Tasks ref scale testing: Empty read markers. +// These definitions also work for RCU Rude readers. +static void rcu_tasks_ref_scale_read_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) + continue; +} + +static void rcu_tasks_ref_scale_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) + un_delay(udl, ndl); +} + +static struct ref_scale_ops rcu_tasks_ops = { + .init = rcu_sync_scale_init, + .readsection = rcu_tasks_ref_scale_read_section, + .delaysection = rcu_tasks_ref_scale_delay_section, + .name = "rcu-tasks" +}; + +// Definitions for RCU Tasks Trace ref scale testing. +static void rcu_trace_ref_scale_read_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + rcu_read_lock_trace(); + rcu_read_unlock_trace(); + } +} + +static void rcu_trace_ref_scale_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + rcu_read_lock_trace(); + un_delay(udl, ndl); + rcu_read_unlock_trace(); + } +} + +static struct ref_scale_ops rcu_trace_ops = { + .init = rcu_sync_scale_init, + .readsection = rcu_trace_ref_scale_read_section, + .delaysection = rcu_trace_ref_scale_delay_section, + .name = "rcu-trace" +}; + +// Definitions for reference count +static atomic_t refcnt; + +static void ref_refcnt_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + atomic_inc(&refcnt); + atomic_dec(&refcnt); + } +} + +static void ref_refcnt_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + atomic_inc(&refcnt); + un_delay(udl, ndl); + atomic_dec(&refcnt); + } +} + +static struct ref_scale_ops refcnt_ops = { + .init = rcu_sync_scale_init, + .readsection = ref_refcnt_section, + .delaysection = ref_refcnt_delay_section, + .name = "refcnt" +}; + +// Definitions for rwlock +static rwlock_t test_rwlock; + +static void ref_rwlock_init(void) +{ + rwlock_init(&test_rwlock); +} + +static void ref_rwlock_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + read_lock(&test_rwlock); + read_unlock(&test_rwlock); + } +} + +static void ref_rwlock_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + read_lock(&test_rwlock); + un_delay(udl, ndl); + read_unlock(&test_rwlock); + } +} + +static struct ref_scale_ops rwlock_ops = { + .init = ref_rwlock_init, + .readsection = ref_rwlock_section, + .delaysection = ref_rwlock_delay_section, + .name = "rwlock" +}; + +// Definitions for rwsem +static struct rw_semaphore test_rwsem; + +static void ref_rwsem_init(void) +{ + init_rwsem(&test_rwsem); +} + +static void ref_rwsem_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + down_read(&test_rwsem); + up_read(&test_rwsem); + } +} + +static void ref_rwsem_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + down_read(&test_rwsem); + un_delay(udl, ndl); + up_read(&test_rwsem); + } +} + +static struct ref_scale_ops rwsem_ops = { + .init = ref_rwsem_init, + .readsection = ref_rwsem_section, + .delaysection = ref_rwsem_delay_section, + .name = "rwsem" +}; + +static void rcu_scale_one_reader(void) +{ + if (readdelay <= 0) + cur_ops->readsection(loops); + else + cur_ops->delaysection(loops, readdelay / 1000, readdelay % 1000); +} + +// Reader kthread. Repeatedly does empty RCU read-side +// critical section, minimizing update-side interference. +static int +ref_scale_reader(void *arg) +{ + unsigned long flags; + long me = (long)arg; + struct reader_task *rt = &(reader_tasks[me]); + u64 start; + s64 duration; + + VERBOSE_SCALEOUT("ref_scale_reader %ld: task started", me); + set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); + set_user_nice(current, MAX_NICE); + atomic_inc(&n_init); + if (holdoff) + schedule_timeout_interruptible(holdoff * HZ); +repeat: + VERBOSE_SCALEOUT("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id()); + + // Wait for signal that this reader can start. + wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) || + torture_must_stop()); + + if (torture_must_stop()) + goto end; + + // Make sure that the CPU is affinitized appropriately during testing. + WARN_ON_ONCE(smp_processor_id() != me); + + WRITE_ONCE(rt->start_reader, 0); + if (!atomic_dec_return(&n_started)) + while (atomic_read_acquire(&n_started)) + cpu_relax(); + + VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d started", me, exp_idx); + + + // To reduce noise, do an initial cache-warming invocation, check + // in, and then keep warming until everyone has checked in. + rcu_scale_one_reader(); + if (!atomic_dec_return(&n_warmedup)) + while (atomic_read_acquire(&n_warmedup)) + rcu_scale_one_reader(); + // Also keep interrupts disabled. This also has the effect + // of preventing entries into slow path for rcu_read_unlock(). + local_irq_save(flags); + start = ktime_get_mono_fast_ns(); + + rcu_scale_one_reader(); + + duration = ktime_get_mono_fast_ns() - start; + local_irq_restore(flags); + + rt->last_duration_ns = WARN_ON_ONCE(duration < 0) ? 0 : duration; + // To reduce runtime-skew noise, do maintain-load invocations until + // everyone is done. + if (!atomic_dec_return(&n_cooleddown)) + while (atomic_read_acquire(&n_cooleddown)) + rcu_scale_one_reader(); + + if (atomic_dec_and_test(&nreaders_exp)) + wake_up(&main_wq); + + VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d ended, (readers remaining=%d)", + me, exp_idx, atomic_read(&nreaders_exp)); + + if (!torture_must_stop()) + goto repeat; +end: + torture_kthread_stopping("ref_scale_reader"); + return 0; +} + +static void reset_readers(void) +{ + int i; + struct reader_task *rt; + + for (i = 0; i < nreaders; i++) { + rt = &(reader_tasks[i]); + + rt->last_duration_ns = 0; + } +} + +// Print the results of each reader and return the sum of all their durations. +static u64 process_durations(int n) +{ + int i; + struct reader_task *rt; + char buf1[64]; + char *buf; + u64 sum = 0; + + buf = kmalloc(128 + nreaders * 32, GFP_KERNEL); + if (!buf) + return 0; + buf[0] = 0; + sprintf(buf, "Experiment #%d (Format: <THREAD-NUM>:<Total loop time in ns>)", + exp_idx); + + for (i = 0; i < n && !torture_must_stop(); i++) { + rt = &(reader_tasks[i]); + sprintf(buf1, "%d: %llu\t", i, rt->last_duration_ns); + + if (i % 5 == 0) + strcat(buf, "\n"); + strcat(buf, buf1); + + sum += rt->last_duration_ns; + } + strcat(buf, "\n"); + + SCALEOUT("%s\n", buf); + + kfree(buf); + return sum; +} + +// The main_func is the main orchestrator, it performs a bunch of +// experiments. For every experiment, it orders all the readers +// involved to start and waits for them to finish the experiment. It +// then reads their timestamps and starts the next experiment. Each +// experiment progresses from 1 concurrent reader to N of them at which +// point all the timestamps are printed. +static int main_func(void *arg) +{ + bool errexit = false; + int exp, r; + char buf1[64]; + char *buf; + u64 *result_avg; + + set_cpus_allowed_ptr(current, cpumask_of(nreaders % nr_cpu_ids)); + set_user_nice(current, MAX_NICE); + + VERBOSE_SCALEOUT("main_func task started"); + result_avg = kzalloc(nruns * sizeof(*result_avg), GFP_KERNEL); + buf = kzalloc(64 + nruns * 32, GFP_KERNEL); + if (!result_avg || !buf) { + VERBOSE_SCALEOUT_ERRSTRING("out of memory"); + errexit = true; + } + if (holdoff) + schedule_timeout_interruptible(holdoff * HZ); + + // Wait for all threads to start. + atomic_inc(&n_init); + while (atomic_read(&n_init) < nreaders + 1) + schedule_timeout_uninterruptible(1); + + // Start exp readers up per experiment + for (exp = 0; exp < nruns && !torture_must_stop(); exp++) { + if (errexit) + break; + if (torture_must_stop()) + goto end; + + reset_readers(); + atomic_set(&nreaders_exp, nreaders); + atomic_set(&n_started, nreaders); + atomic_set(&n_warmedup, nreaders); + atomic_set(&n_cooleddown, nreaders); + + exp_idx = exp; + + for (r = 0; r < nreaders; r++) { + smp_store_release(&reader_tasks[r].start_reader, 1); + wake_up(&reader_tasks[r].wq); + } + + VERBOSE_SCALEOUT("main_func: experiment started, waiting for %d readers", + nreaders); + + wait_event(main_wq, + !atomic_read(&nreaders_exp) || torture_must_stop()); + + VERBOSE_SCALEOUT("main_func: experiment ended"); + + if (torture_must_stop()) + goto end; + + result_avg[exp] = div_u64(1000 * process_durations(nreaders), nreaders * loops); + } + + // Print the average of all experiments + SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n"); + + buf[0] = 0; + strcat(buf, "\n"); + strcat(buf, "Runs\tTime(ns)\n"); + + for (exp = 0; exp < nruns; exp++) { + u64 avg; + u32 rem; + + if (errexit) + break; + avg = div_u64_rem(result_avg[exp], 1000, &rem); + sprintf(buf1, "%d\t%llu.%03u\n", exp + 1, avg, rem); + strcat(buf, buf1); + } + + if (!errexit) + SCALEOUT("%s", buf); + + // This will shutdown everything including us. + if (shutdown) { + shutdown_start = 1; + wake_up(&shutdown_wq); + } + + // Wait for torture to stop us + while (!torture_must_stop()) + schedule_timeout_uninterruptible(1); + +end: + torture_kthread_stopping("main_func"); + kfree(result_avg); + kfree(buf); + return 0; +} + +static void +ref_scale_print_module_parms(struct ref_scale_ops *cur_ops, const char *tag) +{ + pr_alert("%s" SCALE_FLAG + "--- %s: verbose=%d shutdown=%d holdoff=%d loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag, + verbose, shutdown, holdoff, loops, nreaders, nruns, readdelay); +} + +static void +ref_scale_cleanup(void) +{ + int i; + + if (torture_cleanup_begin()) + return; + + if (!cur_ops) { + torture_cleanup_end(); + return; + } + + if (reader_tasks) { + for (i = 0; i < nreaders; i++) + torture_stop_kthread("ref_scale_reader", + reader_tasks[i].task); + } + kfree(reader_tasks); + + torture_stop_kthread("main_task", main_task); + kfree(main_task); + + // Do scale-type-specific cleanup operations. + if (cur_ops->cleanup != NULL) + cur_ops->cleanup(); + + torture_cleanup_end(); +} + +// Shutdown kthread. Just waits to be awakened, then shuts down system. +static int +ref_scale_shutdown(void *arg) +{ + wait_event(shutdown_wq, shutdown_start); + + smp_mb(); // Wake before output. + ref_scale_cleanup(); + kernel_power_off(); + + return -EINVAL; +} + +static int __init +ref_scale_init(void) +{ + long i; + int firsterr = 0; + static struct ref_scale_ops *scale_ops[] = { + &rcu_ops, &srcu_ops, &rcu_trace_ops, &rcu_tasks_ops, + &refcnt_ops, &rwlock_ops, &rwsem_ops, + }; + + if (!torture_init_begin(scale_type, verbose)) + return -EBUSY; + + for (i = 0; i < ARRAY_SIZE(scale_ops); i++) { + cur_ops = scale_ops[i]; + if (strcmp(scale_type, cur_ops->name) == 0) + break; + } + if (i == ARRAY_SIZE(scale_ops)) { + pr_alert("rcu-scale: invalid scale type: \"%s\"\n", scale_type); + pr_alert("rcu-scale types:"); + for (i = 0; i < ARRAY_SIZE(scale_ops); i++) + pr_cont(" %s", scale_ops[i]->name); + pr_cont("\n"); + WARN_ON(!IS_MODULE(CONFIG_RCU_REF_SCALE_TEST)); + firsterr = -EINVAL; + cur_ops = NULL; + goto unwind; + } + if (cur_ops->init) + cur_ops->init(); + + ref_scale_print_module_parms(cur_ops, "Start of test"); + + // Shutdown task + if (shutdown) { + init_waitqueue_head(&shutdown_wq); + firsterr = torture_create_kthread(ref_scale_shutdown, NULL, + shutdown_task); + if (firsterr) + goto unwind; + schedule_timeout_uninterruptible(1); + } + + // Reader tasks (default to ~75% of online CPUs). + if (nreaders < 0) + nreaders = (num_online_cpus() >> 1) + (num_online_cpus() >> 2); + reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]), + GFP_KERNEL); + if (!reader_tasks) { + VERBOSE_SCALEOUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + + VERBOSE_SCALEOUT("Starting %d reader threads\n", nreaders); + + for (i = 0; i < nreaders; i++) { + firsterr = torture_create_kthread(ref_scale_reader, (void *)i, + reader_tasks[i].task); + if (firsterr) + goto unwind; + + init_waitqueue_head(&(reader_tasks[i].wq)); + } + + // Main Task + init_waitqueue_head(&main_wq); + firsterr = torture_create_kthread(main_func, NULL, main_task); + if (firsterr) + goto unwind; + + torture_init_end(); + return 0; + +unwind: + torture_init_end(); + ref_scale_cleanup(); + return firsterr; +} + +module_init(ref_scale_init); +module_exit(ref_scale_cleanup); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 6d3ef700fb0e..c100acf332ed 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -766,7 +766,7 @@ static void srcu_flip(struct srcu_struct *ssp) * it, if this function was preempted for enough time for the counters * to wrap, it really doesn't matter whether or not we expedite the grace * period. The extra overhead of a needlessly expedited grace period is - * negligible when amoritized over that time period, and the extra latency + * negligible when amortized over that time period, and the extra latency * of a needlessly non-expedited grace period is similarly negligible. */ static bool srcu_might_be_idle(struct srcu_struct *ssp) @@ -777,14 +777,15 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp) unsigned long t; unsigned long tlast; + check_init_srcu_struct(ssp); /* If the local srcu_data structure has callbacks, not idle. */ - local_irq_save(flags); - sdp = this_cpu_ptr(ssp->sda); + sdp = raw_cpu_ptr(ssp->sda); + spin_lock_irqsave_rcu_node(sdp, flags); if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) { - local_irq_restore(flags); + spin_unlock_irqrestore_rcu_node(sdp, flags); return false; /* Callbacks already present, so not idle. */ } - local_irq_restore(flags); + spin_unlock_irqrestore_rcu_node(sdp, flags); /* * No local callbacks, so probabalistically probe global state. @@ -864,9 +865,8 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp, } rhp->func = func; idx = srcu_read_lock(ssp); - local_irq_save(flags); - sdp = this_cpu_ptr(ssp->sda); - spin_lock_rcu_node(sdp); + sdp = raw_cpu_ptr(ssp->sda); + spin_lock_irqsave_rcu_node(sdp, flags); rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_gp_seq)); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index ce23f6cc5043..835e2df8590a 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -103,6 +103,7 @@ module_param(rcu_task_stall_timeout, int, 0644); #define RTGS_WAIT_READERS 9 #define RTGS_INVOKE_CBS 10 #define RTGS_WAIT_CBS 11 +#ifndef CONFIG_TINY_RCU static const char * const rcu_tasks_gp_state_names[] = { "RTGS_INIT", "RTGS_WAIT_WAIT_CBS", @@ -117,6 +118,7 @@ static const char * const rcu_tasks_gp_state_names[] = { "RTGS_INVOKE_CBS", "RTGS_WAIT_CBS", }; +#endif /* #ifndef CONFIG_TINY_RCU */ //////////////////////////////////////////////////////////////////////// // @@ -129,6 +131,7 @@ static void set_tasks_gp_state(struct rcu_tasks *rtp, int newstate) rtp->gp_jiffies = jiffies; } +#ifndef CONFIG_TINY_RCU /* Return state name. */ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp) { @@ -139,6 +142,7 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp) return "???"; return rcu_tasks_gp_state_names[j]; } +#endif /* #ifndef CONFIG_TINY_RCU */ // Enqueue a callback for the specified flavor of Tasks RCU. static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, @@ -205,7 +209,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) if (!rtp->cbs_head) { WARN_ON(signal_pending(current)); set_tasks_gp_state(rtp, RTGS_WAIT_WAIT_CBS); - schedule_timeout_interruptible(HZ/10); + schedule_timeout_idle(HZ/10); } continue; } @@ -227,7 +231,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) cond_resched(); } /* Paranoid sleep to keep this from entering a tight loop */ - schedule_timeout_uninterruptible(HZ/10); + schedule_timeout_idle(HZ/10); set_tasks_gp_state(rtp, RTGS_WAIT_CBS); } @@ -268,6 +272,7 @@ static void __init rcu_tasks_bootup_oddness(void) #endif /* #ifndef CONFIG_TINY_RCU */ +#ifndef CONFIG_TINY_RCU /* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) { @@ -281,6 +286,7 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) ".C"[!!data_race(rtp->cbs_head)], s); } +#endif /* #ifndef CONFIG_TINY_RCU */ static void exit_tasks_rcu_finish_trace(struct task_struct *t); @@ -336,7 +342,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) /* Slowly back off waiting for holdouts */ set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS); - schedule_timeout_interruptible(HZ/fract); + schedule_timeout_idle(HZ/fract); if (fract > 1) fract--; @@ -402,7 +408,7 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop) } /* Processing between scanning taskslist and draining the holdout list. */ -void rcu_tasks_postscan(struct list_head *hop) +static void rcu_tasks_postscan(struct list_head *hop) { /* * Wait for tasks that are in the process of exiting. This @@ -557,10 +563,12 @@ static int __init rcu_spawn_tasks_kthread(void) } core_initcall(rcu_spawn_tasks_kthread); +#ifndef CONFIG_TINY_RCU static void show_rcu_tasks_classic_gp_kthread(void) { show_rcu_tasks_generic_gp_kthread(&rcu_tasks, ""); } +#endif /* #ifndef CONFIG_TINY_RCU */ /* Do the srcu_read_lock() for the above synchronize_srcu(). */ void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu) @@ -682,10 +690,12 @@ static int __init rcu_spawn_tasks_rude_kthread(void) } core_initcall(rcu_spawn_tasks_rude_kthread); +#ifndef CONFIG_TINY_RCU static void show_rcu_tasks_rude_gp_kthread(void) { show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, ""); } +#endif /* #ifndef CONFIG_TINY_RCU */ #else /* #ifdef CONFIG_TASKS_RUDE_RCU */ static void show_rcu_tasks_rude_gp_kthread(void) {} @@ -727,8 +737,8 @@ EXPORT_SYMBOL_GPL(rcu_trace_lock_map); #ifdef CONFIG_TASKS_TRACE_RCU -atomic_t trc_n_readers_need_end; // Number of waited-for readers. -DECLARE_WAIT_QUEUE_HEAD(trc_wait); // List of holdout tasks. +static atomic_t trc_n_readers_need_end; // Number of waited-for readers. +static DECLARE_WAIT_QUEUE_HEAD(trc_wait); // List of holdout tasks. // Record outstanding IPIs to each CPU. No point in sending two... static DEFINE_PER_CPU(bool, trc_ipi_to_cpu); @@ -835,7 +845,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) bool ofl = cpu_is_offline(cpu); if (task_curr(t)) { - WARN_ON_ONCE(ofl & !is_idle_task(t)); + WARN_ON_ONCE(ofl && !is_idle_task(t)); // If no chance of heavyweight readers, do it the hard way. if (!ofl && !IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) @@ -1118,11 +1128,10 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks_trace); * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period * * Control will return to the caller some time after a trace rcu-tasks - * grace period has elapsed, in other words after all currently - * executing rcu-tasks read-side critical sections have elapsed. These - * read-side critical sections are delimited by calls to schedule(), - * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory, - * anyway) cond_resched(). + * grace period has elapsed, in other words after all currently executing + * rcu-tasks read-side critical sections have elapsed. These read-side + * critical sections are delimited by calls to rcu_read_lock_trace() + * and rcu_read_unlock_trace(). * * This is a very specialized primitive, intended only for a few uses in * tracing and other situations requiring manipulation of function preambles @@ -1164,6 +1173,7 @@ static int __init rcu_spawn_tasks_trace_kthread(void) } core_initcall(rcu_spawn_tasks_trace_kthread); +#ifndef CONFIG_TINY_RCU static void show_rcu_tasks_trace_gp_kthread(void) { char buf[64]; @@ -1174,18 +1184,21 @@ static void show_rcu_tasks_trace_gp_kthread(void) data_race(n_heavy_reader_attempts)); show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf); } +#endif /* #ifndef CONFIG_TINY_RCU */ #else /* #ifdef CONFIG_TASKS_TRACE_RCU */ static void exit_tasks_rcu_finish_trace(struct task_struct *t) { } static inline void show_rcu_tasks_trace_gp_kthread(void) {} #endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */ +#ifndef CONFIG_TINY_RCU void show_rcu_tasks_gp_kthreads(void) { show_rcu_tasks_classic_gp_kthread(); show_rcu_tasks_rude_gp_kthread(); show_rcu_tasks_trace_gp_kthread(); } +#endif /* #ifndef CONFIG_TINY_RCU */ #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ static inline void rcu_tasks_bootup_oddness(void) {} diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index dd572ce7c747..aa897c3f2e92 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -23,6 +23,7 @@ #include <linux/cpu.h> #include <linux/prefetch.h> #include <linux/slab.h> +#include <linux/mm.h> #include "rcu.h" @@ -84,9 +85,9 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head) unsigned long offset = (unsigned long)head->func; rcu_lock_acquire(&rcu_callback_map); - if (__is_kfree_rcu_offset(offset)) { - trace_rcu_invoke_kfree_callback("", head, offset); - kfree((void *)head - offset); + if (__is_kvfree_rcu_offset(offset)) { + trace_rcu_invoke_kvfree_callback("", head, offset); + kvfree((void *)head - offset); rcu_lock_release(&rcu_callback_map); return true; } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 6c6569e0586c..ac7198ed3197 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -57,6 +57,8 @@ #include <linux/slab.h> #include <linux/sched/isolation.h> #include <linux/sched/clock.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> #include "../time/tick-internal.h" #include "tree.h" @@ -175,6 +177,15 @@ module_param(gp_init_delay, int, 0444); static int gp_cleanup_delay; module_param(gp_cleanup_delay, int, 0444); +/* + * This rcu parameter is runtime-read-only. It reflects + * a minimum allowed number of objects which can be cached + * per-CPU. Object size is equal to one page. This value + * can be changed at boot time. + */ +static int rcu_min_cached_objs = 2; +module_param(rcu_min_cached_objs, int, 0444); + /* Retrieve RCU kthreads priority for rcutorture */ int rcu_get_gp_kthreads_prio(void) { @@ -954,7 +965,6 @@ void __rcu_irq_enter_check_tick(void) /** * rcu_nmi_enter - inform RCU of entry to NMI context - * @irq: Is this call from rcu_irq_enter? * * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and * rdp->dynticks_nmi_nesting to let the RCU grace-period handling know @@ -990,8 +1000,11 @@ noinstr void rcu_nmi_enter(void) rcu_dynticks_eqs_exit(); // ... but is watching here. - if (!in_nmi()) + if (!in_nmi()) { + instrumentation_begin(); rcu_cleanup_after_idle(); + instrumentation_end(); + } instrumentation_begin(); // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs() @@ -1638,7 +1651,7 @@ static void rcu_gp_slow(int delay) if (delay > 0 && !(rcu_seq_ctr(rcu_state.gp_seq) % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) - schedule_timeout_uninterruptible(delay); + schedule_timeout_idle(delay); } static unsigned long sleep_duration; @@ -1661,7 +1674,7 @@ static void rcu_gp_torture_wait(void) duration = xchg(&sleep_duration, 0UL); if (duration > 0) { pr_alert("%s: Waiting %lu jiffies\n", __func__, duration); - schedule_timeout_uninterruptible(duration); + schedule_timeout_idle(duration); pr_alert("%s: Wait complete\n", __func__); } } @@ -2443,6 +2456,7 @@ static void rcu_do_batch(struct rcu_data *rdp) local_irq_save(flags); rcu_nocb_lock(rdp); count = -rcl.len; + rdp->n_cbs_invoked += count; trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(), is_idle_task(current), rcu_is_callbacks_kthread()); @@ -2726,7 +2740,7 @@ static void rcu_cpu_kthread(unsigned int cpu) } *statusp = RCU_KTHREAD_YIELDING; trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); - schedule_timeout_interruptible(2); + schedule_timeout_idle(2); trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); *statusp = RCU_KTHREAD_WAITING; } @@ -2894,8 +2908,8 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func) return; // Enqueued onto ->nocb_bypass, so just leave. // If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock. rcu_segcblist_enqueue(&rdp->cblist, head); - if (__is_kfree_rcu_offset((unsigned long)func)) - trace_rcu_kfree_callback(rcu_state.name, head, + if (__is_kvfree_rcu_offset((unsigned long)func)) + trace_rcu_kvfree_callback(rcu_state.name, head, (unsigned long)func, rcu_segcblist_n_cbs(&rdp->cblist)); else @@ -2957,53 +2971,53 @@ EXPORT_SYMBOL_GPL(call_rcu); /* Maximum number of jiffies to wait before draining a batch. */ #define KFREE_DRAIN_JIFFIES (HZ / 50) #define KFREE_N_BATCHES 2 - -/* - * This macro defines how many entries the "records" array - * will contain. It is based on the fact that the size of - * kfree_rcu_bulk_data structure becomes exactly one page. - */ -#define KFREE_BULK_MAX_ENTR ((PAGE_SIZE / sizeof(void *)) - 3) +#define FREE_N_CHANNELS 2 /** - * struct kfree_rcu_bulk_data - single block to store kfree_rcu() pointers + * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers * @nr_records: Number of active pointers in the array - * @records: Array of the kfree_rcu() pointers * @next: Next bulk object in the block chain - * @head_free_debug: For debug, when CONFIG_DEBUG_OBJECTS_RCU_HEAD is set + * @records: Array of the kvfree_rcu() pointers */ -struct kfree_rcu_bulk_data { +struct kvfree_rcu_bulk_data { unsigned long nr_records; - void *records[KFREE_BULK_MAX_ENTR]; - struct kfree_rcu_bulk_data *next; - struct rcu_head *head_free_debug; + struct kvfree_rcu_bulk_data *next; + void *records[]; }; +/* + * This macro defines how many entries the "records" array + * will contain. It is based on the fact that the size of + * kvfree_rcu_bulk_data structure becomes exactly one page. + */ +#define KVFREE_BULK_MAX_ENTR \ + ((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *)) + /** * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period * @head_free: List of kfree_rcu() objects waiting for a grace period - * @bhead_free: Bulk-List of kfree_rcu() objects waiting for a grace period + * @bkvhead_free: Bulk-List of kvfree_rcu() objects waiting for a grace period * @krcp: Pointer to @kfree_rcu_cpu structure */ struct kfree_rcu_cpu_work { struct rcu_work rcu_work; struct rcu_head *head_free; - struct kfree_rcu_bulk_data *bhead_free; + struct kvfree_rcu_bulk_data *bkvhead_free[FREE_N_CHANNELS]; struct kfree_rcu_cpu *krcp; }; /** * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period * @head: List of kfree_rcu() objects not yet waiting for a grace period - * @bhead: Bulk-List of kfree_rcu() objects not yet waiting for a grace period - * @bcached: Keeps at most one object for later reuse when build chain blocks + * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period * @lock: Synchronize access to this structure * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES * @monitor_todo: Tracks whether a @monitor_work delayed work is pending - * @initialized: The @lock and @rcu_work fields have been initialized + * @initialized: The @rcu_work fields have been initialized + * @count: Number of objects for which GP not started * * This is a per-CPU structure. The reason that it is not included in * the rcu_data structure is to permit this code to be extracted from @@ -3012,28 +3026,84 @@ struct kfree_rcu_cpu_work { */ struct kfree_rcu_cpu { struct rcu_head *head; - struct kfree_rcu_bulk_data *bhead; - struct kfree_rcu_bulk_data *bcached; + struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS]; struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; - spinlock_t lock; + raw_spinlock_t lock; struct delayed_work monitor_work; bool monitor_todo; bool initialized; - // Number of objects for which GP not started int count; + + /* + * A simple cache list that contains objects for + * reuse purpose. In order to save some per-cpu + * space the list is singular. Even though it is + * lockless an access has to be protected by the + * per-cpu lock. + */ + struct llist_head bkvcache; + int nr_bkv_objs; }; -static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc); +static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = { + .lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock), +}; static __always_inline void -debug_rcu_head_unqueue_bulk(struct rcu_head *head) +debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead) { #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD - for (; head; head = head->next) - debug_rcu_head_unqueue(head); + int i; + + for (i = 0; i < bhead->nr_records; i++) + debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i])); #endif } +static inline struct kfree_rcu_cpu * +krc_this_cpu_lock(unsigned long *flags) +{ + struct kfree_rcu_cpu *krcp; + + local_irq_save(*flags); // For safely calling this_cpu_ptr(). + krcp = this_cpu_ptr(&krc); + raw_spin_lock(&krcp->lock); + + return krcp; +} + +static inline void +krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags) +{ + raw_spin_unlock(&krcp->lock); + local_irq_restore(flags); +} + +static inline struct kvfree_rcu_bulk_data * +get_cached_bnode(struct kfree_rcu_cpu *krcp) +{ + if (!krcp->nr_bkv_objs) + return NULL; + + krcp->nr_bkv_objs--; + return (struct kvfree_rcu_bulk_data *) + llist_del_first(&krcp->bkvcache); +} + +static inline bool +put_cached_bnode(struct kfree_rcu_cpu *krcp, + struct kvfree_rcu_bulk_data *bnode) +{ + // Check the limit. + if (krcp->nr_bkv_objs >= rcu_min_cached_objs) + return false; + + llist_add((struct llist_node *) bnode, &krcp->bkvcache); + krcp->nr_bkv_objs++; + return true; + +} + /* * This function is invoked in workqueue context after a grace period. * It frees all the objects queued on ->bhead_free or ->head_free. @@ -3041,38 +3111,63 @@ debug_rcu_head_unqueue_bulk(struct rcu_head *head) static void kfree_rcu_work(struct work_struct *work) { unsigned long flags; + struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS], *bnext; struct rcu_head *head, *next; - struct kfree_rcu_bulk_data *bhead, *bnext; struct kfree_rcu_cpu *krcp; struct kfree_rcu_cpu_work *krwp; + int i, j; krwp = container_of(to_rcu_work(work), struct kfree_rcu_cpu_work, rcu_work); krcp = krwp->krcp; - spin_lock_irqsave(&krcp->lock, flags); - head = krwp->head_free; - krwp->head_free = NULL; - bhead = krwp->bhead_free; - krwp->bhead_free = NULL; - spin_unlock_irqrestore(&krcp->lock, flags); - - /* "bhead" is now private, so traverse locklessly. */ - for (; bhead; bhead = bnext) { - bnext = bhead->next; - debug_rcu_head_unqueue_bulk(bhead->head_free_debug); + raw_spin_lock_irqsave(&krcp->lock, flags); + // Channels 1 and 2. + for (i = 0; i < FREE_N_CHANNELS; i++) { + bkvhead[i] = krwp->bkvhead_free[i]; + krwp->bkvhead_free[i] = NULL; + } - rcu_lock_acquire(&rcu_callback_map); - trace_rcu_invoke_kfree_bulk_callback(rcu_state.name, - bhead->nr_records, bhead->records); + // Channel 3. + head = krwp->head_free; + krwp->head_free = NULL; + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + // Handle two first channels. + for (i = 0; i < FREE_N_CHANNELS; i++) { + for (; bkvhead[i]; bkvhead[i] = bnext) { + bnext = bkvhead[i]->next; + debug_rcu_bhead_unqueue(bkvhead[i]); + + rcu_lock_acquire(&rcu_callback_map); + if (i == 0) { // kmalloc() / kfree(). + trace_rcu_invoke_kfree_bulk_callback( + rcu_state.name, bkvhead[i]->nr_records, + bkvhead[i]->records); + + kfree_bulk(bkvhead[i]->nr_records, + bkvhead[i]->records); + } else { // vmalloc() / vfree(). + for (j = 0; j < bkvhead[i]->nr_records; j++) { + trace_rcu_invoke_kvfree_callback( + rcu_state.name, + bkvhead[i]->records[j], 0); + + vfree(bkvhead[i]->records[j]); + } + } + rcu_lock_release(&rcu_callback_map); - kfree_bulk(bhead->nr_records, bhead->records); - rcu_lock_release(&rcu_callback_map); + krcp = krc_this_cpu_lock(&flags); + if (put_cached_bnode(krcp, bkvhead[i])) + bkvhead[i] = NULL; + krc_this_cpu_unlock(krcp, flags); - if (cmpxchg(&krcp->bcached, NULL, bhead)) - free_page((unsigned long) bhead); + if (bkvhead[i]) + free_page((unsigned long) bkvhead[i]); - cond_resched_tasks_rcu_qs(); + cond_resched_tasks_rcu_qs(); + } } /* @@ -3082,14 +3177,15 @@ static void kfree_rcu_work(struct work_struct *work) */ for (; head; head = next) { unsigned long offset = (unsigned long)head->func; + void *ptr = (void *)head - offset; next = head->next; - debug_rcu_head_unqueue(head); + debug_rcu_head_unqueue((struct rcu_head *)ptr); rcu_lock_acquire(&rcu_callback_map); - trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset); + trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset); - if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset))) - kfree((void *)head - offset); + if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset))) + kvfree(ptr); rcu_lock_release(&rcu_callback_map); cond_resched_tasks_rcu_qs(); @@ -3105,8 +3201,8 @@ static void kfree_rcu_work(struct work_struct *work) static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) { struct kfree_rcu_cpu_work *krwp; - bool queued = false; - int i; + bool repeat = false; + int i, j; lockdep_assert_held(&krcp->lock); @@ -3114,21 +3210,25 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) krwp = &(krcp->krw_arr[i]); /* - * Try to detach bhead or head and attach it over any + * Try to detach bkvhead or head and attach it over any * available corresponding free channel. It can be that * a previous RCU batch is in progress, it means that * immediately to queue another one is not possible so * return false to tell caller to retry. */ - if ((krcp->bhead && !krwp->bhead_free) || + if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) || + (krcp->bkvhead[1] && !krwp->bkvhead_free[1]) || (krcp->head && !krwp->head_free)) { - /* Channel 1. */ - if (!krwp->bhead_free) { - krwp->bhead_free = krcp->bhead; - krcp->bhead = NULL; + // Channel 1 corresponds to SLAB ptrs. + // Channel 2 corresponds to vmalloc ptrs. + for (j = 0; j < FREE_N_CHANNELS; j++) { + if (!krwp->bkvhead_free[j]) { + krwp->bkvhead_free[j] = krcp->bkvhead[j]; + krcp->bkvhead[j] = NULL; + } } - /* Channel 2. */ + // Channel 3 corresponds to emergency path. if (!krwp->head_free) { krwp->head_free = krcp->head; krcp->head = NULL; @@ -3137,17 +3237,21 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) WRITE_ONCE(krcp->count, 0); /* - * One work is per one batch, so there are two "free channels", - * "bhead_free" and "head_free" the batch can handle. It can be - * that the work is in the pending state when two channels have - * been detached following each other, one by one. + * One work is per one batch, so there are three + * "free channels", the batch can handle. It can + * be that the work is in the pending state when + * channels have been detached following by each + * other. */ queue_rcu_work(system_wq, &krwp->rcu_work); - queued = true; } + + // Repeat if any "free" corresponding channel is still busy. + if (krcp->bkvhead[0] || krcp->bkvhead[1] || krcp->head) + repeat = true; } - return queued; + return !repeat; } static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp, @@ -3157,14 +3261,14 @@ static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp, krcp->monitor_todo = false; if (queue_kfree_rcu_work(krcp)) { // Success! Our job is done here. - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); return; } // Previous RCU batch still in progress, try again later. krcp->monitor_todo = true; schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES); - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } /* @@ -3177,32 +3281,50 @@ static void kfree_rcu_monitor(struct work_struct *work) struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu, monitor_work.work); - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); if (krcp->monitor_todo) kfree_rcu_drain_unlock(krcp, flags); else - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } static inline bool -kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, - struct rcu_head *head, rcu_callback_t func) +kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr) { - struct kfree_rcu_bulk_data *bnode; + struct kvfree_rcu_bulk_data *bnode; + int idx; if (unlikely(!krcp->initialized)) return false; lockdep_assert_held(&krcp->lock); + idx = !!is_vmalloc_addr(ptr); /* Check if a new block is required. */ - if (!krcp->bhead || - krcp->bhead->nr_records == KFREE_BULK_MAX_ENTR) { - bnode = xchg(&krcp->bcached, NULL); + if (!krcp->bkvhead[idx] || + krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) { + bnode = get_cached_bnode(krcp); if (!bnode) { - WARN_ON_ONCE(sizeof(struct kfree_rcu_bulk_data) > PAGE_SIZE); + /* + * To keep this path working on raw non-preemptible + * sections, prevent the optional entry into the + * allocator as it uses sleeping locks. In fact, even + * if the caller of kfree_rcu() is preemptible, this + * path still is not, as krcp->lock is a raw spinlock. + * With additional page pre-allocation in the works, + * hitting this return is going to be much less likely. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + return false; - bnode = (struct kfree_rcu_bulk_data *) + /* + * NOTE: For one argument of kvfree_rcu() we can + * drop the lock and get the page in sleepable + * context. That would allow to maintain an array + * for the CONFIG_PREEMPT_RT as well if no cached + * pages are available. + */ + bnode = (struct kvfree_rcu_bulk_data *) __get_free_page(GFP_NOWAIT | __GFP_NOWARN); } @@ -3212,53 +3334,62 @@ kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, /* Initialize the new block. */ bnode->nr_records = 0; - bnode->next = krcp->bhead; - bnode->head_free_debug = NULL; + bnode->next = krcp->bkvhead[idx]; /* Attach it to the head. */ - krcp->bhead = bnode; + krcp->bkvhead[idx] = bnode; } -#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD - head->func = func; - head->next = krcp->bhead->head_free_debug; - krcp->bhead->head_free_debug = head; -#endif - /* Finally insert. */ - krcp->bhead->records[krcp->bhead->nr_records++] = - (void *) head - (unsigned long) func; + krcp->bkvhead[idx]->records + [krcp->bkvhead[idx]->nr_records++] = ptr; return true; } /* - * Queue a request for lazy invocation of kfree_bulk()/kfree() after a grace - * period. Please note there are two paths are maintained, one is the main one - * that uses kfree_bulk() interface and second one is emergency one, that is - * used only when the main path can not be maintained temporary, due to memory - * pressure. + * Queue a request for lazy invocation of appropriate free routine after a + * grace period. Please note there are three paths are maintained, two are the + * main ones that use array of pointers interface and third one is emergency + * one, that is used only when the main path can not be maintained temporary, + * due to memory pressure. * - * Each kfree_call_rcu() request is added to a batch. The batch will be drained + * Each kvfree_call_rcu() request is added to a batch. The batch will be drained * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will * be free'd in workqueue context. This allows us to: batch requests together to - * reduce the number of grace periods during heavy kfree_rcu() load. + * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load. */ -void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) +void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { unsigned long flags; struct kfree_rcu_cpu *krcp; + bool success; + void *ptr; - local_irq_save(flags); // For safely calling this_cpu_ptr(). - krcp = this_cpu_ptr(&krc); - if (krcp->initialized) - spin_lock(&krcp->lock); + if (head) { + ptr = (void *) head - (unsigned long) func; + } else { + /* + * Please note there is a limitation for the head-less + * variant, that is why there is a clear rule for such + * objects: it can be used from might_sleep() context + * only. For other places please embed an rcu_head to + * your data. + */ + might_sleep(); + ptr = (unsigned long *) func; + } + + krcp = krc_this_cpu_lock(&flags); // Queue the object but don't yet schedule the batch. - if (debug_rcu_head_queue(head)) { + if (debug_rcu_head_queue(ptr)) { // Probable double kfree_rcu(), just leak. WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n", __func__, head); + + // Mark as success and leave. + success = true; goto unlock_return; } @@ -3266,10 +3397,16 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) * Under high memory pressure GFP_NOWAIT can fail, * in that case the emergency path is maintained. */ - if (unlikely(!kfree_call_rcu_add_ptr_to_bulk(krcp, head, func))) { + success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr); + if (!success) { + if (head == NULL) + // Inline if kvfree_rcu(one_arg) call. + goto unlock_return; + head->func = func; head->next = krcp->head; krcp->head = head; + success = true; } WRITE_ONCE(krcp->count, krcp->count + 1); @@ -3282,11 +3419,20 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) } unlock_return: - if (krcp->initialized) - spin_unlock(&krcp->lock); - local_irq_restore(flags); + krc_this_cpu_unlock(krcp, flags); + + /* + * Inline kvfree() after synchronize_rcu(). We can do + * it from might_sleep() context only, so the current + * CPU can pass the QS state. + */ + if (!success) { + debug_rcu_head_unqueue((struct rcu_head *) ptr); + synchronize_rcu(); + kvfree(ptr); + } } -EXPORT_SYMBOL_GPL(kfree_call_rcu); +EXPORT_SYMBOL_GPL(kvfree_call_rcu); static unsigned long kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) @@ -3315,11 +3461,11 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); count = krcp->count; - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); if (krcp->monitor_todo) kfree_rcu_drain_unlock(krcp, flags); else - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); sc->nr_to_scan -= count; freed += count; @@ -3328,7 +3474,7 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) break; } - return freed; + return freed == 0 ? SHRINK_STOP : freed; } static struct shrinker kfree_rcu_shrinker = { @@ -3346,15 +3492,15 @@ void __init kfree_rcu_scheduler_running(void) for_each_online_cpu(cpu) { struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); if (!krcp->head || krcp->monitor_todo) { - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); continue; } krcp->monitor_todo = true; schedule_delayed_work_on(cpu, &krcp->monitor_work, KFREE_DRAIN_JIFFIES); - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } } @@ -3842,10 +3988,9 @@ void rcu_cpu_starting(unsigned int cpu) { unsigned long flags; unsigned long mask; - int nbits; - unsigned long oldmask; struct rcu_data *rdp; struct rcu_node *rnp; + bool newcpu; if (per_cpu(rcu_cpu_started, cpu)) return; @@ -3857,12 +4002,10 @@ void rcu_cpu_starting(unsigned int cpu) mask = rdp->grpmask; raw_spin_lock_irqsave_rcu_node(rnp, flags); WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask); - oldmask = rnp->expmaskinitnext; + newcpu = !(rnp->expmaskinitnext & mask); rnp->expmaskinitnext |= mask; - oldmask ^= rnp->expmaskinitnext; - nbits = bitmap_weight(&oldmask, BITS_PER_LONG); /* Allow lockless access for expedited grace periods. */ - smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + nbits); /* ^^^ */ + smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + newcpu); /* ^^^ */ ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus); rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq); @@ -4249,13 +4392,23 @@ static void __init kfree_rcu_batch_init(void) for_each_possible_cpu(cpu) { struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + struct kvfree_rcu_bulk_data *bnode; - spin_lock_init(&krcp->lock); for (i = 0; i < KFREE_N_BATCHES; i++) { INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work); krcp->krw_arr[i].krcp = krcp; } + for (i = 0; i < rcu_min_cached_objs; i++) { + bnode = (struct kvfree_rcu_bulk_data *) + __get_free_page(GFP_NOWAIT | __GFP_NOWARN); + + if (bnode) + put_cached_bnode(krcp, bnode); + else + pr_err("Failed to preallocate for %d CPU!\n", cpu); + } + INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor); krcp->initialized = true; } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 43991a40b084..c96ae351688b 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -41,7 +41,7 @@ struct rcu_node { raw_spinlock_t __private lock; /* Root rcu_node's lock protects */ /* some rcu_state fields as well as */ /* following. */ - unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */ + unsigned long gp_seq; /* Track rsp->gp_seq. */ unsigned long gp_seq_needed; /* Track furthest future GP request. */ unsigned long completedqs; /* All QSes done for this node. */ unsigned long qsmask; /* CPUs or groups that need to switch in */ @@ -73,9 +73,9 @@ struct rcu_node { unsigned long ffmask; /* Fully functional CPUs. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ /* Only one bit will be set in this mask. */ - int grplo; /* lowest-numbered CPU or group here. */ - int grphi; /* highest-numbered CPU or group here. */ - u8 grpnum; /* CPU/group number for next level up. */ + int grplo; /* lowest-numbered CPU here. */ + int grphi; /* highest-numbered CPU here. */ + u8 grpnum; /* group number for next level up. */ u8 level; /* root is at level 0. */ bool wait_blkd_tasks;/* Necessary to wait for blocked tasks to */ /* exit RCU read-side critical sections */ @@ -149,7 +149,7 @@ union rcu_noqs { /* Per-CPU data for read-copy update. */ struct rcu_data { /* 1) quiescent-state and grace-period handling : */ - unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */ + unsigned long gp_seq; /* Track rsp->gp_seq counter. */ unsigned long gp_seq_needed; /* Track furthest future GP request. */ union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ bool core_needs_qs; /* Core waits for quiesc state. */ @@ -171,6 +171,7 @@ struct rcu_data { /* different grace periods. */ long qlen_last_fqs_check; /* qlen at last check for QS forcing */ + unsigned long n_cbs_invoked; /* # callbacks invoked since boot. */ unsigned long n_force_qs_snap; /* did other CPU force QS recently? */ long blimit; /* Upper limit on a processed batch */ @@ -301,6 +302,8 @@ struct rcu_state { u8 boost ____cacheline_internodealigned_in_smp; /* Subject to priority boost. */ unsigned long gp_seq; /* Grace-period sequence #. */ + unsigned long gp_max; /* Maximum GP duration in */ + /* jiffies. */ struct task_struct *gp_kthread; /* Task for grace periods. */ struct swait_queue_head gp_wq; /* Where GP task waits. */ short gp_flags; /* Commands for GP task. */ @@ -346,8 +349,6 @@ struct rcu_state { /* a reluctant CPU. */ unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */ /* GP start. */ - unsigned long gp_max; /* Maximum GP duration in */ - /* jiffies. */ const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 72952edad1e4..1888c0eb1216 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -403,7 +403,7 @@ retry_ipi: /* Online, so delay for a bit and try again. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("selectofl")); - schedule_timeout_uninterruptible(1); + schedule_timeout_idle(1); goto retry_ipi; } /* CPU really is offline, so we must report its QS. */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 352223664ebd..982fc5be5269 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1033,7 +1033,7 @@ static int rcu_boost_kthread(void *arg) if (spincnt > 10) { WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_YIELDING); trace_rcu_utilization(TPS("End boost kthread@rcu_yield")); - schedule_timeout_interruptible(2); + schedule_timeout_idle(2); trace_rcu_utilization(TPS("Start boost kthread@rcu_yield")); spincnt = 0; } @@ -2005,7 +2005,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) /* Polling, so trace if first poll in the series. */ if (gotcbs) trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll")); - schedule_timeout_interruptible(1); + schedule_timeout_idle(1); } else if (!needwait_gp) { /* Wait for callbacks to appear. */ trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep")); diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 54a6dba0280d..b5d3b4794db4 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -237,14 +237,12 @@ struct rcu_stall_chk_rdr { */ static bool check_slow_task(struct task_struct *t, void *arg) { - struct rcu_node *rnp; struct rcu_stall_chk_rdr *rscrp = arg; if (task_curr(t)) return false; // It is running, so decline to inspect it. rscrp->nesting = t->rcu_read_lock_nesting; rscrp->rs = t->rcu_read_unlock_special; - rnp = t->rcu_blocked_node; rscrp->on_blkd_list = !list_empty(&t->rcu_node_entry); return true; } @@ -468,7 +466,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) /* * OK, time to rat on our buddy... - * See Documentation/RCU/stallwarn.txt for info on how to debug + * See Documentation/RCU/stallwarn.rst for info on how to debug * RCU CPU stall warnings. */ pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name); @@ -535,7 +533,7 @@ static void print_cpu_stall(unsigned long gps) /* * OK, time to rat on ourselves... - * See Documentation/RCU/stallwarn.txt for info on how to debug + * See Documentation/RCU/stallwarn.rst for info on how to debug * RCU CPU stall warnings. */ pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name); @@ -649,6 +647,7 @@ static void check_cpu_stall(struct rcu_data *rdp) */ void show_rcu_gp_kthreads(void) { + unsigned long cbs = 0; int cpu; unsigned long j; unsigned long ja; @@ -690,9 +689,11 @@ void show_rcu_gp_kthreads(void) } for_each_possible_cpu(cpu) { rdp = per_cpu_ptr(&rcu_data, cpu); + cbs += data_race(rdp->n_cbs_invoked); if (rcu_segcblist_is_offloaded(&rdp->cblist)) show_rcu_nocb_state(rdp); } + pr_info("RCU callbacks invoked since boot: %lu\n", cbs); show_rcu_tasks_gp_kthreads(); } EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 84843adfd939..2de49b5d8dd2 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -42,6 +42,7 @@ #include <linux/kprobes.h> #include <linux/slab.h> #include <linux/irq_work.h> +#include <linux/rcupdate_trace.h> #define CREATE_TRACE_POINTS @@ -207,7 +208,7 @@ void rcu_end_inkernel_boot(void) rcu_unexpedite_gp(); if (rcu_normal_after_boot) WRITE_ONCE(rcu_normal, 1); - rcu_boot_ended = 1; + rcu_boot_ended = true; } /* @@ -279,6 +280,7 @@ struct lockdep_map rcu_sched_lock_map = { }; EXPORT_SYMBOL_GPL(rcu_sched_lock_map); +// Tell lockdep when RCU callbacks are being invoked. static struct lock_class_key rcu_callback_key; struct lockdep_map rcu_callback_map = STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key); @@ -390,13 +392,14 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, might_sleep(); continue; } - init_rcu_head_on_stack(&rs_array[i].head); - init_completion(&rs_array[i].completion); for (j = 0; j < i; j++) if (crcu_array[j] == crcu_array[i]) break; - if (j == i) + if (j == i) { + init_rcu_head_on_stack(&rs_array[i].head); + init_completion(&rs_array[i].completion); (crcu_array[i])(&rs_array[i].head, wakeme_after_rcu); + } } /* Wait for all callbacks to be invoked. */ @@ -407,9 +410,10 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, for (j = 0; j < i; j++) if (crcu_array[j] == crcu_array[i]) break; - if (j == i) + if (j == i) { wait_for_completion(&rs_array[i].completion); - destroy_rcu_head_on_stack(&rs_array[i].head); + destroy_rcu_head_on_stack(&rs_array[i].head); + } } } EXPORT_SYMBOL_GPL(__wait_rcu_gp); diff --git a/kernel/reboot.c b/kernel/reboot.c index 491f1347bf43..e7b78d5ae1ab 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -26,7 +26,7 @@ int C_A_D = 1; struct pid *cad_pid; EXPORT_SYMBOL(cad_pid); -#if defined(CONFIG_ARM) || defined(CONFIG_UNICORE32) +#if defined(CONFIG_ARM) #define DEFAULT_REBOOT_MODE = REBOOT_HARD #else #define DEFAULT_REBOOT_MODE diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index ba059fbfc53a..01f5d3020589 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -389,7 +389,7 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i int ret = default_wake_function(wq_entry, mode, sync, key); if (ret) - list_del_init(&wq_entry->entry); + list_del_init_careful(&wq_entry->entry); return ret; } diff --git a/kernel/signal.c b/kernel/signal.c index ee22ec78fd6d..6f16f7c5d375 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -719,7 +719,7 @@ static int dequeue_synchronous_signal(kernel_siginfo_t *info) * Return the first synchronous signal in the queue. */ list_for_each_entry(q, &pending->list, list) { - /* Synchronous signals have a postive si_code */ + /* Synchronous signals have a positive si_code */ if ((q->info.si_code > SI_USER) && (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) { sync = q; diff --git a/kernel/softirq.c b/kernel/softirq.c index c4201b7f42b1..5e9aaa648a74 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -107,6 +107,12 @@ static bool ksoftirqd_running(unsigned long pending) * where hardirqs are disabled legitimately: */ #ifdef CONFIG_TRACE_IRQFLAGS + +DEFINE_PER_CPU(int, hardirqs_enabled); +DEFINE_PER_CPU(int, hardirq_context); +EXPORT_PER_CPU_SYMBOL_GPL(hardirqs_enabled); +EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context); + void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) { unsigned long flags; @@ -224,7 +230,7 @@ static inline bool lockdep_softirq_start(void) { bool in_hardirq = false; - if (lockdep_hardirq_context(current)) { + if (lockdep_hardirq_context()) { in_hardirq = true; lockdep_hardirq_exit(); } diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index fa3f800d7d76..0deaf4b79fb4 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -20,31 +20,6 @@ #include "timekeeping.h" /** - * struct clock_read_data - data required to read from sched_clock() - * - * @epoch_ns: sched_clock() value at last update - * @epoch_cyc: Clock cycle value at last update. - * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit - * clocks. - * @read_sched_clock: Current clock source (or dummy source when suspended). - * @mult: Multipler for scaled math conversion. - * @shift: Shift value for scaled math conversion. - * - * Care must be taken when updating this structure; it is read by - * some very hot code paths. It occupies <=40 bytes and, when combined - * with the seqcount used to synchronize access, comfortably fits into - * a 64 byte cache line. - */ -struct clock_read_data { - u64 epoch_ns; - u64 epoch_cyc; - u64 sched_clock_mask; - u64 (*read_sched_clock)(void); - u32 mult; - u32 shift; -}; - -/** * struct clock_data - all data needed for sched_clock() (including * registration of a new clock source) * @@ -93,6 +68,17 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) return (cyc * mult) >> shift; } +struct clock_read_data *sched_clock_read_begin(unsigned int *seq) +{ + *seq = raw_read_seqcount_latch(&cd.seq); + return cd.read_data + (*seq & 1); +} + +int sched_clock_read_retry(unsigned int seq) +{ + return read_seqcount_retry(&cd.seq, seq); +} + unsigned long long notrace sched_clock(void) { u64 cyc, res; @@ -100,13 +86,12 @@ unsigned long long notrace sched_clock(void) struct clock_read_data *rd; do { - seq = raw_read_seqcount(&cd.seq); - rd = cd.read_data + (seq & 1); + rd = sched_clock_read_begin(&seq); cyc = (rd->read_sched_clock() - rd->epoch_cyc) & rd->sched_clock_mask; res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift); - } while (read_seqcount_retry(&cd.seq, seq)); + } while (sched_clock_read_retry(seq)); return res; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 3e2dc9b8858c..f0199a4ba1ad 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -351,16 +351,24 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu); /* - * Set a per-task tick dependency. Posix CPU timers need this in order to elapse - * per task timers. + * Set a per-task tick dependency. RCU need this. Also posix CPU timers + * in order to elapse per task timers. */ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { - /* - * We could optimize this with just kicking the target running the task - * if that noise matters for nohz full users. - */ - tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit); + if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) { + if (tsk == current) { + preempt_disable(); + tick_nohz_full_kick(); + preempt_enable(); + } else { + /* + * Some future tick_nohz_full_kick_task() + * should optimize this. + */ + tick_nohz_full_kick_all(); + } + } } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index df1ff803acc4..026ac01af9da 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -43,6 +43,7 @@ #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> +#include <linux/random.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -1742,6 +1743,13 @@ void update_process_times(int user_tick) scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); + + /* The current CPU might make use of net randoms without receiving IRQs + * to renew them often enough. Let's update the net_rand_state from a + * non-constant value that's not affine to the number of calls to make + * sure it's updated when there's some activity (we don't care in idle). + */ + this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick); } /** diff --git a/kernel/torture.c b/kernel/torture.c index a1a41484ff6d..1061492f14bd 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -45,6 +45,9 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>"); static bool disable_onoff_at_boot; module_param(disable_onoff_at_boot, bool, 0444); +static bool ftrace_dump_at_shutdown; +module_param(ftrace_dump_at_shutdown, bool, 0444); + static char *torture_type; static int verbose; @@ -527,7 +530,8 @@ static int torture_shutdown(void *arg) torture_shutdown_hook(); else VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping."); - rcu_ftrace_dump(DUMP_ALL); + if (ftrace_dump_at_shutdown) + rcu_ftrace_dump(DUMP_ALL); kernel_power_off(); /* Shut down the system. */ return 0; } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 5ef0484513ec..7ba62d68885a 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -348,7 +348,7 @@ static int __blk_trace_remove(struct request_queue *q) struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (!bt) return -EINVAL; @@ -362,9 +362,9 @@ int blk_trace_remove(struct request_queue *q) { int ret; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); ret = __blk_trace_remove(q); - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); return ret; } @@ -483,12 +483,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct dentry *dir = NULL; int ret; + lockdep_assert_held(&q->debugfs_mutex); + if (!buts->buf_size || !buts->buf_nr) return -EINVAL; - if (!blk_debugfs_root) - return -ENOENT; - strncpy(buts->name, name, BLKTRACE_BDEV_SIZE); buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0'; @@ -503,7 +502,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, * we can be. */ if (rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex))) { + lockdep_is_held(&q->debugfs_mutex))) { pr_warn("Concurrent blktraces are not allowed on %s\n", buts->name); return -EBUSY; @@ -522,12 +521,29 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!bt->msg_data) goto err; - ret = -ENOENT; - - dir = debugfs_lookup(buts->name, blk_debugfs_root); - if (!dir) + /* + * When tracing the whole disk reuse the existing debugfs directory + * created by the block layer on init. For partitions block devices, + * and scsi-generic block devices we create a temporary new debugfs + * directory that will be removed once the trace ends. + */ + if (bdev && bdev == bdev->bd_contains) + dir = q->debugfs_dir; + else bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); + /* + * As blktrace relies on debugfs for its interface the debugfs directory + * is required, contrary to the usual mantra of not checking for debugfs + * files or directories. + */ + if (IS_ERR_OR_NULL(dir)) { + pr_warn("debugfs_dir not present for %s so skipping\n", + buts->name); + ret = -ENOENT; + goto err; + } + bt->dev = dev; atomic_set(&bt->dropped, 0); INIT_LIST_HEAD(&bt->running_list); @@ -563,8 +579,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = 0; err: - if (dir && !bt->dir) - dput(dir); if (ret) blk_trace_free(bt); return ret; @@ -597,9 +611,9 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, { int ret; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); ret = __blk_trace_setup(q, name, dev, bdev, arg); - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); return ret; } @@ -645,7 +659,7 @@ static int __blk_trace_startstop(struct request_queue *q, int start) struct blk_trace *bt; bt = rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; @@ -685,9 +699,9 @@ int blk_trace_startstop(struct request_queue *q, int start) { int ret; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); ret = __blk_trace_startstop(q, start); - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); return ret; } @@ -716,7 +730,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); switch (cmd) { case BLKTRACESETUP: @@ -743,7 +757,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) break; } - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); return ret; } @@ -754,14 +768,14 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) **/ void blk_trace_shutdown(struct request_queue *q) { - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); if (rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex))) { + lockdep_is_held(&q->debugfs_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); } #ifdef CONFIG_BLK_CGROUP @@ -846,6 +860,13 @@ static void blk_add_trace_rq_issue(void *ignore, blk_trace_request_get_cgid(q, rq)); } +static void blk_add_trace_rq_merge(void *ignore, + struct request_queue *q, struct request *rq) +{ + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE, + blk_trace_request_get_cgid(q, rq)); +} + static void blk_add_trace_rq_requeue(void *ignore, struct request_queue *q, struct request *rq) @@ -1130,6 +1151,8 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); WARN_ON(ret); + ret = register_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); + WARN_ON(ret); ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); WARN_ON(ret); ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); @@ -1176,6 +1199,7 @@ static void blk_unregister_tracepoints(void) unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); + unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); @@ -1642,7 +1666,7 @@ static int blk_trace_remove_queue(struct request_queue *q) struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; @@ -1817,10 +1841,10 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; @@ -1838,7 +1862,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); out_bdput: bdput(bdev); out: @@ -1881,10 +1905,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&q->blk_trace_mutex); + mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { if (!!value == !!bt) { ret = 0; @@ -1901,7 +1925,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (bt == NULL) { ret = blk_trace_setup_queue(q, bdev); bt = rcu_dereference_protected(q->blk_trace, - lockdep_is_held(&q->blk_trace_mutex)); + lockdep_is_held(&q->debugfs_mutex)); } if (ret == 0) { @@ -1916,7 +1940,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } out_unlock_bdev: - mutex_unlock(&q->blk_trace_mutex); + mutex_unlock(&q->debugfs_mutex); out_bdput: bdput(bdev); out: |