diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/Kconfig.preempt | 12 | ||||
-rw-r--r-- | kernel/Makefile | 3 | ||||
-rw-r--r-- | kernel/cpu.c | 36 | ||||
-rw-r--r-- | kernel/dma/direct.c | 10 | ||||
-rw-r--r-- | kernel/dma/direct.h | 3 | ||||
-rw-r--r-- | kernel/dma/mapping.c | 2 | ||||
-rw-r--r-- | kernel/entry/common.c | 16 | ||||
-rw-r--r-- | kernel/events/core.c | 212 | ||||
-rw-r--r-- | kernel/irq/affinity.c | 5 | ||||
-rw-r--r-- | kernel/irq_work.c | 2 | ||||
-rw-r--r-- | kernel/sched/core.c | 16 | ||||
-rw-r--r-- | kernel/sched/idle.c | 1 | ||||
-rw-r--r-- | kernel/sched/sched.h | 6 | ||||
-rw-r--r-- | kernel/signal.c | 40 | ||||
-rw-r--r-- | kernel/smp.c | 2 | ||||
-rw-r--r-- | kernel/static_call.c | 541 | ||||
-rw-r--r-- | kernel/static_call_inline.c | 543 | ||||
-rw-r--r-- | kernel/time/tick-sched.c | 6 | ||||
-rw-r--r-- | kernel/time/timer.c | 11 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 1 | ||||
-rw-r--r-- | kernel/trace/fgraph.c | 17 | ||||
-rw-r--r-- | kernel/trace/trace_events_user.c | 86 | ||||
-rw-r--r-- | kernel/watch_queue.c | 1 |
23 files changed, 673 insertions, 899 deletions
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 8c6de5a9ecc4..c2f1fd95a821 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -133,14 +133,4 @@ config SCHED_CORE which is the likely usage by Linux distributions, there should be no measurable impact on performance. -config ARCH_WANTS_RT_DELAYED_SIGNALS - bool - help - This option is selected by architectures where raising signals - can happen in atomic contexts on PREEMPT_RT enabled kernels. This - option delays raising the signal until the return to user space - loop where it is also delivered. X86 requires this to deliver - signals from trap handlers which run on IST stacks. - -config RT_DELAYED_SIGNALS - def_bool PREEMPT_RT && ARCH_WANTS_RT_DELAYED_SIGNALS + diff --git a/kernel/Makefile b/kernel/Makefile index 471d71935e90..847a82bfe0e3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -114,7 +114,8 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_BPF) += bpf/ obj-$(CONFIG_KCSAN) += kcsan/ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o -obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/cpu.c b/kernel/cpu.c index 5797c2a7a93f..d0a9aa0b42e8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -71,7 +71,6 @@ struct cpuhp_cpu_state { bool rollback; bool single; bool bringup; - int cpu; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; @@ -475,7 +474,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state -cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; @@ -486,14 +485,15 @@ cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) st->target = target; st->single = false; st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); return prev_state; } static inline void -cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state prev_state) { bool bringup = !st->bringup; @@ -520,8 +520,8 @@ cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) } st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ @@ -541,15 +541,16 @@ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) wait_for_ap_thread(st, st->bringup); } -static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } @@ -581,7 +582,7 @@ static int bringup_wait_for_ap(unsigned int cpu) if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; - return cpuhp_kick_ap(st, st->target); + return cpuhp_kick_ap(cpu, st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -704,7 +705,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); @@ -721,7 +722,6 @@ static void cpuhp_create(unsigned int cpu) init_completion(&st->done_up); init_completion(&st->done_down); - st->cpu = cpu; } static int cpuhp_should_run(unsigned int cpu) @@ -875,7 +875,7 @@ static int cpuhp_kick_ap_work(unsigned int cpu) cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); - ret = cpuhp_kick_ap(st, st->target); + ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; @@ -1107,7 +1107,7 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, @@ -1134,7 +1134,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. @@ -1165,7 +1165,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); @@ -1352,7 +1352,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - cpuhp_set_state(st, target); + cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 35a1d29d6a2e..9743c6ccce1a 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -277,12 +277,16 @@ void *dma_direct_alloc(struct device *dev, size_t size, } if (remap) { + pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs); + + if (force_dma_unencrypted(dev)) + prot = pgprot_decrypted(prot); + /* remove any dirty cache lines on the kernel alias */ arch_dma_prep_coherent(page, size); /* create a coherent mapping */ - ret = dma_common_contiguous_remap(page, size, - dma_pgprot(dev, PAGE_KERNEL, attrs), + ret = dma_common_contiguous_remap(page, size, prot, __builtin_return_address(0)); if (!ret) goto out_free_pages; @@ -535,6 +539,8 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, int ret = -ENXIO; vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); + if (force_dma_unencrypted(dev)) + vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 4632b0f4f72e..8a6cd53dbe8c 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -114,6 +114,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, dma_direct_sync_single_for_cpu(dev, addr, size, dir); if (unlikely(is_swiotlb_buffer(dev, phys))) - swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); + swiotlb_tbl_unmap_single(dev, phys, size, dir, + attrs | DMA_ATTR_SKIP_CPU_SYNC); } #endif /* _KERNEL_DMA_DIRECT_H */ diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 559461a826ba..db7244291b74 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -407,8 +407,6 @@ EXPORT_SYMBOL(dma_get_sgtable_attrs); */ pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { - if (force_dma_unencrypted(dev)) - prot = pgprot_decrypted(prot); if (dev_is_dma_coherent(dev)) return prot; #ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE diff --git a/kernel/entry/common.c b/kernel/entry/common.c index ef8d94a98b7e..93c3b86e781c 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -142,18 +142,6 @@ void noinstr exit_to_user_mode(void) /* Workaround to allow gradual conversion of architecture code */ void __weak arch_do_signal_or_restart(struct pt_regs *regs) { } -#ifdef CONFIG_RT_DELAYED_SIGNALS -static inline void raise_delayed_signal(void) -{ - if (unlikely(current->forced_info.si_signo)) { - force_sig_info(¤t->forced_info); - current->forced_info.si_signo = 0; - } -} -#else -static inline void raise_delayed_signal(void) { } -#endif - static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, unsigned long ti_work) { @@ -168,8 +156,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, if (ti_work & _TIF_NEED_RESCHED) schedule(); - raise_delayed_signal(); - if (ti_work & _TIF_UPROBE) uprobe_notify_resume(regs); @@ -406,7 +392,7 @@ DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); void dynamic_irqentry_exit_cond_resched(void) { - if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) + if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) return; raw_irqentry_exit_cond_resched(); } diff --git a/kernel/events/core.c b/kernel/events/core.c index cfde994ce61c..23bb19716ad3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -574,8 +574,7 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, enum event_type_t event_type); static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void update_context_time(struct perf_event_context *ctx); static u64 perf_event_time(struct perf_event *event); @@ -781,7 +780,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, static inline void update_cgrp_time_from_event(struct perf_event *event) { struct perf_cgroup_info *info; - struct perf_cgroup *cgrp; /* * ensure we access cgroup data only when needed and @@ -790,21 +788,19 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current, event->ctx); + info = this_cpu_ptr(event->cgrp->info); /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { - info = this_cpu_ptr(event->cgrp->info); + if (info->active) __update_cgrp_time(info, perf_clock(), true); - } } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { - struct perf_cgroup *cgrp; + struct perf_event_context *ctx = &cpuctx->ctx; + struct perf_cgroup *cgrp = cpuctx->cgrp; struct perf_cgroup_info *info; struct cgroup_subsys_state *css; @@ -813,10 +809,10 @@ perf_cgroup_set_timestamp(struct task_struct *task, * ensure we do not access cgroup data * unless we have the cgroup pinned (css_get) */ - if (!task || !ctx->nr_cgroups) + if (!cgrp) return; - cgrp = perf_cgroup_from_task(task, ctx); + WARN_ON_ONCE(!ctx->nr_cgroups); for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); @@ -828,17 +824,12 @@ perf_cgroup_set_timestamp(struct task_struct *task, static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); -#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ -#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */ - /* * reschedule events based on the cgroup constraint of task. - * - * mode SWOUT : schedule out everything - * mode SWIN : schedule in based on cgroup for next */ -static void perf_cgroup_switch(struct task_struct *task, int mode) +static void perf_cgroup_switch(struct task_struct *task) { + struct perf_cgroup *cgrp; struct perf_cpu_context *cpuctx, *tmp; struct list_head *list; unsigned long flags; @@ -849,35 +840,31 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) */ local_irq_save(flags); + cgrp = perf_cgroup_from_task(task, NULL); + list = this_cpu_ptr(&cgrp_cpuctx_list); list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) { WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); + if (READ_ONCE(cpuctx->cgrp) == cgrp) + continue; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(cpuctx->ctx.pmu); - if (mode & PERF_CGROUP_SWOUT) { - cpu_ctx_sched_out(cpuctx, EVENT_ALL); - /* - * must not be done before ctxswout due - * to event_filter_match() in event_sched_out() - */ - cpuctx->cgrp = NULL; - } + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* + * must not be done before ctxswout due + * to update_cgrp_time_from_cpuctx() in + * ctx_sched_out() + */ + cpuctx->cgrp = cgrp; + /* + * set cgrp before ctxsw in to allow + * perf_cgroup_set_timestamp() in ctx_sched_in() + * to not have to pass task around + */ + cpu_ctx_sched_in(cpuctx, EVENT_ALL); - if (mode & PERF_CGROUP_SWIN) { - WARN_ON_ONCE(cpuctx->cgrp); - /* - * set cgrp before ctxsw in to allow - * event_filter_match() to not have to pass - * task around - * we pass the cpuctx->ctx to perf_cgroup_from_task() - * because cgorup events are only per-cpu - */ - cpuctx->cgrp = perf_cgroup_from_task(task, - &cpuctx->ctx); - cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); - } perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } @@ -885,58 +872,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_restore(flags); } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(next, NULL); - - /* - * only schedule out current cgroup events if we know - * that we are switching to a different cgroup. Otherwise, - * do no touch the cgroup events. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWOUT); - - rcu_read_unlock(); -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(prev, NULL); - - /* - * only need to schedule in cgroup events if we are changing - * cgroup during ctxsw. Cgroup events were not scheduled - * out of ctxsw out if that was not the case. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWIN); - - rcu_read_unlock(); -} - static int perf_cgroup_ensure_storage(struct perf_event *event, struct cgroup_subsys_state *css) { @@ -1032,22 +967,10 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct */ cpuctx = container_of(ctx, struct perf_cpu_context, ctx); - /* - * Since setting cpuctx->cgrp is conditional on the current @cgrp - * matching the event's cgroup, we must do this for every new event, - * because if the first would mismatch, the second would not try again - * and we would leave cpuctx->cgrp unset. - */ - if (ctx->is_active && !cpuctx->cgrp) { - struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx); - - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - cpuctx->cgrp = cgrp; - } - if (ctx->nr_cgroups++) return; + cpuctx->cgrp = perf_cgroup_from_task(current, ctx); list_add(&cpuctx->cgrp_cpuctx_entry, per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); } @@ -1069,9 +992,7 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c if (--ctx->nr_cgroups) return; - if (ctx->is_active && cpuctx->cgrp) - cpuctx->cgrp = NULL; - + cpuctx->cgrp = NULL; list_del(&cpuctx->cgrp_cpuctx_entry); } @@ -1100,16 +1021,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, { } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ -} - static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, struct perf_event_attr *attr, struct perf_event *group_leader) @@ -1118,13 +1029,7 @@ static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) -{ -} - -static inline void -perf_cgroup_switch(struct task_struct *task, struct task_struct *next) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { } @@ -1147,6 +1052,10 @@ static inline void perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) { } + +static void perf_cgroup_switch(struct task_struct *task) +{ +} #endif /* @@ -2713,8 +2622,7 @@ static void ctx_sched_out(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, @@ -2730,15 +2638,14 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, } static void perf_event_sched_in(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, - struct task_struct *task) + struct perf_event_context *ctx) { - cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task); + cpu_ctx_sched_in(cpuctx, EVENT_PINNED); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_PINNED); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE); } /* @@ -2788,7 +2695,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, else if (ctx_event_type & EVENT_PINNED) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); } @@ -3011,7 +2918,7 @@ static void __perf_event_enable(struct perf_event *event, return; if (!event_filter_match(event)) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3020,7 +2927,7 @@ static void __perf_event_enable(struct perf_event *event, * then don't put it on unless the group is on. */ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3668,7 +3575,7 @@ void __perf_event_task_sched_out(struct task_struct *task, * cgroup event are system-wide mode only */ if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_out(task, next); + perf_cgroup_switch(next); } /* @@ -3865,8 +3772,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { int is_active = ctx->is_active; @@ -3878,7 +3784,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (is_active ^ EVENT_TIME) { /* start ctx time */ __update_context_time(ctx, false); - perf_cgroup_set_timestamp(task, ctx); + perf_cgroup_set_timestamp(cpuctx); /* * CPU-release for the below ->is_active store, * see __load_acquire() in perf_event_time_now() @@ -3909,12 +3815,11 @@ ctx_sched_in(struct perf_event_context *ctx, } static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { struct perf_event_context *ctx = &cpuctx->ctx; - ctx_sched_in(ctx, cpuctx, event_type, task); + ctx_sched_in(ctx, cpuctx, event_type); } static void perf_event_context_sched_in(struct perf_event_context *ctx, @@ -3956,7 +3861,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, */ if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, ctx, task); + perf_event_sched_in(cpuctx, ctx); if (cpuctx->sched_cb_usage && pmu->sched_task) pmu->sched_task(cpuctx->task_ctx, true); @@ -3984,16 +3889,6 @@ void __perf_event_task_sched_in(struct task_struct *prev, struct perf_event_context *ctx; int ctxn; - /* - * If cgroup events exist on this CPU, then we need to check if we have - * to switch in PMU state; cgroup event are system-wide mode only. - * - * Since cgroup events are CPU events, we must schedule these in before - * we schedule in the task events. - */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_in(prev, task); - for_each_task_context_nr(ctxn) { ctx = task->perf_event_ctxp[ctxn]; if (likely(!ctx)) @@ -4267,7 +4162,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx) if (cpu_event) rotate_ctx(&cpuctx->ctx, cpu_event); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); @@ -4339,7 +4234,7 @@ static void perf_event_enable_on_exec(int ctxn) clone_ctx = unclone_ctx(ctx); ctx_resched(cpuctx, ctx, event_type); } else { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); } perf_ctx_unlock(cpuctx, ctx); @@ -11635,6 +11530,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->state = PERF_EVENT_STATE_INACTIVE; + if (parent_event) + event->event_caps = parent_event->event_caps; + if (event->attr.sigtrap) atomic_set(&event->event_limit, 1); @@ -13562,7 +13460,7 @@ static int __perf_cgroup_move(void *info) { struct task_struct *task = info; rcu_read_lock(); - perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + perf_cgroup_switch(task); rcu_read_unlock(); return 0; } diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f7ff8919dc9b..fdf170404650 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -269,8 +269,9 @@ static int __irq_build_affinity_masks(unsigned int startvec, */ if (numvecs <= nodes) { for_each_node_mask(n, nodemsk) { - cpumask_or(&masks[curvec].mask, &masks[curvec].mask, - node_to_cpumask[n]); + /* Ensure that only CPUs which are in both masks are set */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk); if (++curvec == last_affv) curvec = firstvec; } diff --git a/kernel/irq_work.c b/kernel/irq_work.c index f7df715ec28e..7afa40fe5cc4 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -137,7 +137,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) if (!irq_work_claim(work)) return false; - kasan_record_aux_stack(work); + kasan_record_aux_stack_noalloc(work); preempt_disable(); if (cpu != smp_processor_id()) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..51efaabac3e4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5752,6 +5752,8 @@ static inline struct task_struct *pick_task(struct rq *rq) extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi); +static void queue_core_balance(struct rq *rq); + static struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { @@ -5801,7 +5803,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } rq->core_pick = NULL; - return next; + goto out; } put_prev_task_balance(rq, prev, rf); @@ -5851,7 +5853,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) */ WARN_ON_ONCE(fi_before); task_vruntime_update(rq, next, false); - goto done; + goto out_set_next; } } @@ -5970,8 +5972,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) resched_curr(rq_i); } -done: +out_set_next: set_next_task(rq, next); +out: + if (rq->core->core_forceidle_count && next == rq->idle) + queue_core_balance(rq); + return next; } @@ -6000,7 +6006,7 @@ static bool try_steal_cookie(int this, int that) if (p == src->core_pick || p == src->curr) goto next; - if (!cpumask_test_cpu(this, &p->cpus_mask)) + if (!is_cpu_allowed(p, this)) goto next; if (p->core_occupation > dst->idle->core_occupation) @@ -6066,7 +6072,7 @@ static void sched_core_balance(struct rq *rq) static DEFINE_PER_CPU(struct callback_head, core_balance_head); -void queue_core_balance(struct rq *rq) +static void queue_core_balance(struct rq *rq) { if (!sched_core_enabled(rq)) return; diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f8b5020e76a..ecb0d7052877 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -434,7 +434,6 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir { update_idle_core(rq); schedstat_inc(rq->sched_goidle); - queue_core_balance(rq); } #ifdef CONFIG_SMP diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 58263f90c559..8dccb34eb190 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1232,8 +1232,6 @@ static inline bool sched_group_cookie_match(struct rq *rq, return false; } -extern void queue_core_balance(struct rq *rq); - static inline bool sched_core_enqueued(struct task_struct *p) { return !RB_EMPTY_NODE(&p->core_node); @@ -1267,10 +1265,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq) return &rq->__lock; } -static inline void queue_core_balance(struct rq *rq) -{ -} - static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p) { return true; diff --git a/kernel/signal.c b/kernel/signal.c index 368a34c25bbf..30cd1ca43bcd 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1308,43 +1308,6 @@ enum sig_handler { }; /* - * On some archictectures, PREEMPT_RT has to delay sending a signal from a - * trap since it cannot enable preemption, and the signal code's - * spin_locks turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME - * which will send the signal on exit of the trap. - */ -#ifdef CONFIG_RT_DELAYED_SIGNALS -static inline bool force_sig_delayed(struct kernel_siginfo *info, - struct task_struct *t) -{ - if (!in_atomic()) - return false; - - if (WARN_ON_ONCE(t->forced_info.si_signo)) - return true; - - if (is_si_special(info)) { - WARN_ON_ONCE(info != SEND_SIG_PRIV); - t->forced_info.si_signo = info->si_signo; - t->forced_info.si_errno = 0; - t->forced_info.si_code = SI_KERNEL; - t->forced_info.si_pid = 0; - t->forced_info.si_uid = 0; - } else { - t->forced_info = *info; - } - set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); - return true; -} -#else -static inline bool force_sig_delayed(struct kernel_siginfo *info, - struct task_struct *t) -{ - return false; -} -#endif - -/* * Force a signal that the process can't ignore: if necessary * we unblock the signal and change any SIG_IGN to SIG_DFL. * @@ -1364,9 +1327,6 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, struct k_sigaction *action; int sig = info->si_signo; - if (force_sig_delayed(info, t)) - return 0; - spin_lock_irqsave(&t->sighand->siglock, flags); action = &t->sighand->action[sig-1]; ignored = action->sa.sa_handler == SIG_IGN; diff --git a/kernel/smp.c b/kernel/smp.c index 01a7c1706a58..65a630f62363 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -579,7 +579,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline) /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && - !warned && !llist_empty(head))) { + !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); diff --git a/kernel/static_call.c b/kernel/static_call.c index f2b8baea35d2..e9c3e69f3837 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -1,549 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/init.h> #include <linux/static_call.h> -#include <linux/bug.h> -#include <linux/smp.h> -#include <linux/sort.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/cpu.h> -#include <linux/processor.h> -#include <asm/sections.h> - -extern struct static_call_site __start_static_call_sites[], - __stop_static_call_sites[]; -extern struct static_call_tramp_key __start_static_call_tramp_key[], - __stop_static_call_tramp_key[]; - -static bool static_call_initialized; - -/* mutex to protect key modules/sites */ -static DEFINE_MUTEX(static_call_mutex); - -static void static_call_lock(void) -{ - mutex_lock(&static_call_mutex); -} - -static void static_call_unlock(void) -{ - mutex_unlock(&static_call_mutex); -} - -static inline void *static_call_addr(struct static_call_site *site) -{ - return (void *)((long)site->addr + (long)&site->addr); -} - -static inline unsigned long __static_call_key(const struct static_call_site *site) -{ - return (long)site->key + (long)&site->key; -} - -static inline struct static_call_key *static_call_key(const struct static_call_site *site) -{ - return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); -} - -/* These assume the key is word-aligned. */ -static inline bool static_call_is_init(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_INIT; -} - -static inline bool static_call_is_tail(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_TAIL; -} - -static inline void static_call_set_init(struct static_call_site *site) -{ - site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - - (long)&site->key; -} - -static int static_call_site_cmp(const void *_a, const void *_b) -{ - const struct static_call_site *a = _a; - const struct static_call_site *b = _b; - const struct static_call_key *key_a = static_call_key(a); - const struct static_call_key *key_b = static_call_key(b); - - if (key_a < key_b) - return -1; - - if (key_a > key_b) - return 1; - - return 0; -} - -static void static_call_site_swap(void *_a, void *_b, int size) -{ - long delta = (unsigned long)_a - (unsigned long)_b; - struct static_call_site *a = _a; - struct static_call_site *b = _b; - struct static_call_site tmp = *a; - - a->addr = b->addr - delta; - a->key = b->key - delta; - - b->addr = tmp.addr + delta; - b->key = tmp.key + delta; -} - -static inline void static_call_sort_entries(struct static_call_site *start, - struct static_call_site *stop) -{ - sort(start, stop - start, sizeof(struct static_call_site), - static_call_site_cmp, static_call_site_swap); -} - -static inline bool static_call_key_has_mods(struct static_call_key *key) -{ - return !(key->type & 1); -} - -static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) -{ - if (!static_call_key_has_mods(key)) - return NULL; - - return key->mods; -} - -static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) -{ - if (static_call_key_has_mods(key)) - return NULL; - - return (struct static_call_site *)(key->type & ~1); -} - -void __static_call_update(struct static_call_key *key, void *tramp, void *func) -{ - struct static_call_site *site, *stop; - struct static_call_mod *site_mod, first; - - cpus_read_lock(); - static_call_lock(); - - if (key->func == func) - goto done; - - key->func = func; - - arch_static_call_transform(NULL, tramp, func, false); - - /* - * If uninitialized, we'll not update the callsites, but they still - * point to the trampoline and we just patched that. - */ - if (WARN_ON_ONCE(!static_call_initialized)) - goto done; - - first = (struct static_call_mod){ - .next = static_call_key_next(key), - .mod = NULL, - .sites = static_call_key_sites(key), - }; - - for (site_mod = &first; site_mod; site_mod = site_mod->next) { - bool init = system_state < SYSTEM_RUNNING; - struct module *mod = site_mod->mod; - - if (!site_mod->sites) { - /* - * This can happen if the static call key is defined in - * a module which doesn't use it. - * - * It also happens in the has_mods case, where the - * 'first' entry has no sites associated with it. - */ - continue; - } - - stop = __stop_static_call_sites; - - if (mod) { -#ifdef CONFIG_MODULES - stop = mod->static_call_sites + - mod->num_static_call_sites; - init = mod->state == MODULE_STATE_COMING; -#endif - } - - for (site = site_mod->sites; - site < stop && static_call_key(site) == key; site++) { - void *site_addr = static_call_addr(site); - - if (!init && static_call_is_init(site)) - continue; - - if (!kernel_text_address((unsigned long)site_addr)) { - /* - * This skips patching built-in __exit, which - * is part of init_section_contains() but is - * not part of kernel_text_address(). - * - * Skipping built-in __exit is fine since it - * will never be executed. - */ - WARN_ONCE(!static_call_is_init(site), - "can't patch static call site at %pS", - site_addr); - continue; - } - - arch_static_call_transform(site_addr, NULL, func, - static_call_is_tail(site)); - } - } - -done: - static_call_unlock(); - cpus_read_unlock(); -} -EXPORT_SYMBOL_GPL(__static_call_update); - -static int __static_call_init(struct module *mod, - struct static_call_site *start, - struct static_call_site *stop) -{ - struct static_call_site *site; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod; - - if (start == stop) - return 0; - - static_call_sort_entries(start, stop); - - for (site = start; site < stop; site++) { - void *site_addr = static_call_addr(site); - - if ((mod && within_module_init((unsigned long)site_addr, mod)) || - (!mod && init_section_contains(site_addr, 1))) - static_call_set_init(site); - - key = static_call_key(site); - if (key != prev_key) { - prev_key = key; - - /* - * For vmlinux (!mod) avoid the allocation by storing - * the sites pointer in the key itself. Also see - * __static_call_update()'s @first. - * - * This allows architectures (eg. x86) to call - * static_call_init() before memory allocation works. - */ - if (!mod) { - key->sites = site; - key->type |= 1; - goto do_transform; - } - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - - /* - * When the key has a direct sites pointer, extract - * that into an explicit struct static_call_mod, so we - * can have a list of modules. - */ - if (static_call_key_sites(key)) { - site_mod->mod = NULL; - site_mod->next = NULL; - site_mod->sites = static_call_key_sites(key); - - key->mods = site_mod; - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - } - - site_mod->mod = mod; - site_mod->sites = site; - site_mod->next = static_call_key_next(key); - key->mods = site_mod; - } - -do_transform: - arch_static_call_transform(site_addr, NULL, key->func, - static_call_is_tail(site)); - } - - return 0; -} - -static int addr_conflict(struct static_call_site *site, void *start, void *end) -{ - unsigned long addr = (unsigned long)static_call_addr(site); - - if (addr <= (unsigned long)end && - addr + CALL_INSN_SIZE > (unsigned long)start) - return 1; - - return 0; -} - -static int __static_call_text_reserved(struct static_call_site *iter_start, - struct static_call_site *iter_stop, - void *start, void *end, bool init) -{ - struct static_call_site *iter = iter_start; - - while (iter < iter_stop) { - if (init || !static_call_is_init(iter)) { - if (addr_conflict(iter, start, end)) - return 1; - } - iter++; - } - - return 0; -} - -#ifdef CONFIG_MODULES - -static int __static_call_mod_text_reserved(void *start, void *end) -{ - struct module *mod; - int ret; - - preempt_disable(); - mod = __module_text_address((unsigned long)start); - WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); - if (!try_module_get(mod)) - mod = NULL; - preempt_enable(); - - if (!mod) - return 0; - - ret = __static_call_text_reserved(mod->static_call_sites, - mod->static_call_sites + mod->num_static_call_sites, - start, end, mod->state == MODULE_STATE_COMING); - - module_put(mod); - - return ret; -} - -static unsigned long tramp_key_lookup(unsigned long addr) -{ - struct static_call_tramp_key *start = __start_static_call_tramp_key; - struct static_call_tramp_key *stop = __stop_static_call_tramp_key; - struct static_call_tramp_key *tramp_key; - - for (tramp_key = start; tramp_key != stop; tramp_key++) { - unsigned long tramp; - - tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; - if (tramp == addr) - return (long)tramp_key->key + (long)&tramp_key->key; - } - - return 0; -} - -static int static_call_add_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = start + mod->num_static_call_sites; - struct static_call_site *site; - - for (site = start; site != stop; site++) { - unsigned long s_key = __static_call_key(site); - unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; - unsigned long key; - - /* - * Is the key is exported, 'addr' points to the key, which - * means modules are allowed to call static_call_update() on - * it. - * - * Otherwise, the key isn't exported, and 'addr' points to the - * trampoline so we need to lookup the key. - * - * We go through this dance to prevent crazy modules from - * abusing sensitive static calls. - */ - if (!kernel_text_address(addr)) - continue; - - key = tramp_key_lookup(addr); - if (!key) { - pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", - static_call_addr(site)); - return -EINVAL; - } - - key |= s_key & STATIC_CALL_SITE_FLAGS; - site->key = key - (long)&site->key; - } - - return __static_call_init(mod, start, stop); -} - -static void static_call_del_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = mod->static_call_sites + - mod->num_static_call_sites; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod, **prev; - struct static_call_site *site; - - for (site = start; site < stop; site++) { - key = static_call_key(site); - if (key == prev_key) - continue; - - prev_key = key; - - for (prev = &key->mods, site_mod = key->mods; - site_mod && site_mod->mod != mod; - prev = &site_mod->next, site_mod = site_mod->next) - ; - - if (!site_mod) - continue; - - *prev = site_mod->next; - kfree(site_mod); - } -} - -static int static_call_module_notify(struct notifier_block *nb, - unsigned long val, void *data) -{ - struct module *mod = data; - int ret = 0; - - cpus_read_lock(); - static_call_lock(); - - switch (val) { - case MODULE_STATE_COMING: - ret = static_call_add_module(mod); - if (ret) { - WARN(1, "Failed to allocate memory for static calls"); - static_call_del_module(mod); - } - break; - case MODULE_STATE_GOING: - static_call_del_module(mod); - break; - } - - static_call_unlock(); - cpus_read_unlock(); - - return notifier_from_errno(ret); -} - -static struct notifier_block static_call_module_nb = { - .notifier_call = static_call_module_notify, -}; - -#else - -static inline int __static_call_mod_text_reserved(void *start, void *end) -{ - return 0; -} - -#endif /* CONFIG_MODULES */ - -int static_call_text_reserved(void *start, void *end) -{ - bool init = system_state < SYSTEM_RUNNING; - int ret = __static_call_text_reserved(__start_static_call_sites, - __stop_static_call_sites, start, end, init); - - if (ret) - return ret; - - return __static_call_mod_text_reserved(start, end); -} - -int __init static_call_init(void) -{ - int ret; - - if (static_call_initialized) - return 0; - - cpus_read_lock(); - static_call_lock(); - ret = __static_call_init(NULL, __start_static_call_sites, - __stop_static_call_sites); - static_call_unlock(); - cpus_read_unlock(); - - if (ret) { - pr_err("Failed to allocate memory for static_call!\n"); - BUG(); - } - - static_call_initialized = true; - -#ifdef CONFIG_MODULES - register_module_notifier(&static_call_module_nb); -#endif - return 0; -} -early_initcall(static_call_init); long __static_call_return0(void) { return 0; } EXPORT_SYMBOL_GPL(__static_call_return0); - -#ifdef CONFIG_STATIC_CALL_SELFTEST - -static int func_a(int x) -{ - return x+1; -} - -static int func_b(int x) -{ - return x+2; -} - -DEFINE_STATIC_CALL(sc_selftest, func_a); - -static struct static_call_data { - int (*func)(int); - int val; - int expect; -} static_call_data [] __initdata = { - { NULL, 2, 3 }, - { func_b, 2, 4 }, - { func_a, 2, 3 } -}; - -static int __init test_static_call_init(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { - struct static_call_data *scd = &static_call_data[i]; - - if (scd->func) - static_call_update(sc_selftest, scd->func); - - WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); - } - - return 0; -} -early_initcall(test_static_call_init); - -#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c new file mode 100644 index 000000000000..dc5665b62814 --- /dev/null +++ b/kernel/static_call_inline.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/static_call.h> +#include <linux/bug.h> +#include <linux/smp.h> +#include <linux/sort.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/processor.h> +#include <asm/sections.h> + +extern struct static_call_site __start_static_call_sites[], + __stop_static_call_sites[]; +extern struct static_call_tramp_key __start_static_call_tramp_key[], + __stop_static_call_tramp_key[]; + +static bool static_call_initialized; + +/* mutex to protect key modules/sites */ +static DEFINE_MUTEX(static_call_mutex); + +static void static_call_lock(void) +{ + mutex_lock(&static_call_mutex); +} + +static void static_call_unlock(void) +{ + mutex_unlock(&static_call_mutex); +} + +static inline void *static_call_addr(struct static_call_site *site) +{ + return (void *)((long)site->addr + (long)&site->addr); +} + +static inline unsigned long __static_call_key(const struct static_call_site *site) +{ + return (long)site->key + (long)&site->key; +} + +static inline struct static_call_key *static_call_key(const struct static_call_site *site) +{ + return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); +} + +/* These assume the key is word-aligned. */ +static inline bool static_call_is_init(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_INIT; +} + +static inline bool static_call_is_tail(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_TAIL; +} + +static inline void static_call_set_init(struct static_call_site *site) +{ + site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - + (long)&site->key; +} + +static int static_call_site_cmp(const void *_a, const void *_b) +{ + const struct static_call_site *a = _a; + const struct static_call_site *b = _b; + const struct static_call_key *key_a = static_call_key(a); + const struct static_call_key *key_b = static_call_key(b); + + if (key_a < key_b) + return -1; + + if (key_a > key_b) + return 1; + + return 0; +} + +static void static_call_site_swap(void *_a, void *_b, int size) +{ + long delta = (unsigned long)_a - (unsigned long)_b; + struct static_call_site *a = _a; + struct static_call_site *b = _b; + struct static_call_site tmp = *a; + + a->addr = b->addr - delta; + a->key = b->key - delta; + + b->addr = tmp.addr + delta; + b->key = tmp.key + delta; +} + +static inline void static_call_sort_entries(struct static_call_site *start, + struct static_call_site *stop) +{ + sort(start, stop - start, sizeof(struct static_call_site), + static_call_site_cmp, static_call_site_swap); +} + +static inline bool static_call_key_has_mods(struct static_call_key *key) +{ + return !(key->type & 1); +} + +static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) +{ + if (!static_call_key_has_mods(key)) + return NULL; + + return key->mods; +} + +static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) +{ + if (static_call_key_has_mods(key)) + return NULL; + + return (struct static_call_site *)(key->type & ~1); +} + +void __static_call_update(struct static_call_key *key, void *tramp, void *func) +{ + struct static_call_site *site, *stop; + struct static_call_mod *site_mod, first; + + cpus_read_lock(); + static_call_lock(); + + if (key->func == func) + goto done; + + key->func = func; + + arch_static_call_transform(NULL, tramp, func, false); + + /* + * If uninitialized, we'll not update the callsites, but they still + * point to the trampoline and we just patched that. + */ + if (WARN_ON_ONCE(!static_call_initialized)) + goto done; + + first = (struct static_call_mod){ + .next = static_call_key_next(key), + .mod = NULL, + .sites = static_call_key_sites(key), + }; + + for (site_mod = &first; site_mod; site_mod = site_mod->next) { + bool init = system_state < SYSTEM_RUNNING; + struct module *mod = site_mod->mod; + + if (!site_mod->sites) { + /* + * This can happen if the static call key is defined in + * a module which doesn't use it. + * + * It also happens in the has_mods case, where the + * 'first' entry has no sites associated with it. + */ + continue; + } + + stop = __stop_static_call_sites; + + if (mod) { +#ifdef CONFIG_MODULES + stop = mod->static_call_sites + + mod->num_static_call_sites; + init = mod->state == MODULE_STATE_COMING; +#endif + } + + for (site = site_mod->sites; + site < stop && static_call_key(site) == key; site++) { + void *site_addr = static_call_addr(site); + + if (!init && static_call_is_init(site)) + continue; + + if (!kernel_text_address((unsigned long)site_addr)) { + /* + * This skips patching built-in __exit, which + * is part of init_section_contains() but is + * not part of kernel_text_address(). + * + * Skipping built-in __exit is fine since it + * will never be executed. + */ + WARN_ONCE(!static_call_is_init(site), + "can't patch static call site at %pS", + site_addr); + continue; + } + + arch_static_call_transform(site_addr, NULL, func, + static_call_is_tail(site)); + } + } + +done: + static_call_unlock(); + cpus_read_unlock(); +} +EXPORT_SYMBOL_GPL(__static_call_update); + +static int __static_call_init(struct module *mod, + struct static_call_site *start, + struct static_call_site *stop) +{ + struct static_call_site *site; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod; + + if (start == stop) + return 0; + + static_call_sort_entries(start, stop); + + for (site = start; site < stop; site++) { + void *site_addr = static_call_addr(site); + + if ((mod && within_module_init((unsigned long)site_addr, mod)) || + (!mod && init_section_contains(site_addr, 1))) + static_call_set_init(site); + + key = static_call_key(site); + if (key != prev_key) { + prev_key = key; + + /* + * For vmlinux (!mod) avoid the allocation by storing + * the sites pointer in the key itself. Also see + * __static_call_update()'s @first. + * + * This allows architectures (eg. x86) to call + * static_call_init() before memory allocation works. + */ + if (!mod) { + key->sites = site; + key->type |= 1; + goto do_transform; + } + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + + /* + * When the key has a direct sites pointer, extract + * that into an explicit struct static_call_mod, so we + * can have a list of modules. + */ + if (static_call_key_sites(key)) { + site_mod->mod = NULL; + site_mod->next = NULL; + site_mod->sites = static_call_key_sites(key); + + key->mods = site_mod; + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + } + + site_mod->mod = mod; + site_mod->sites = site; + site_mod->next = static_call_key_next(key); + key->mods = site_mod; + } + +do_transform: + arch_static_call_transform(site_addr, NULL, key->func, + static_call_is_tail(site)); + } + + return 0; +} + +static int addr_conflict(struct static_call_site *site, void *start, void *end) +{ + unsigned long addr = (unsigned long)static_call_addr(site); + + if (addr <= (unsigned long)end && + addr + CALL_INSN_SIZE > (unsigned long)start) + return 1; + + return 0; +} + +static int __static_call_text_reserved(struct static_call_site *iter_start, + struct static_call_site *iter_stop, + void *start, void *end, bool init) +{ + struct static_call_site *iter = iter_start; + + while (iter < iter_stop) { + if (init || !static_call_is_init(iter)) { + if (addr_conflict(iter, start, end)) + return 1; + } + iter++; + } + + return 0; +} + +#ifdef CONFIG_MODULES + +static int __static_call_mod_text_reserved(void *start, void *end) +{ + struct module *mod; + int ret; + + preempt_disable(); + mod = __module_text_address((unsigned long)start); + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + if (!try_module_get(mod)) + mod = NULL; + preempt_enable(); + + if (!mod) + return 0; + + ret = __static_call_text_reserved(mod->static_call_sites, + mod->static_call_sites + mod->num_static_call_sites, + start, end, mod->state == MODULE_STATE_COMING); + + module_put(mod); + + return ret; +} + +static unsigned long tramp_key_lookup(unsigned long addr) +{ + struct static_call_tramp_key *start = __start_static_call_tramp_key; + struct static_call_tramp_key *stop = __stop_static_call_tramp_key; + struct static_call_tramp_key *tramp_key; + + for (tramp_key = start; tramp_key != stop; tramp_key++) { + unsigned long tramp; + + tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; + if (tramp == addr) + return (long)tramp_key->key + (long)&tramp_key->key; + } + + return 0; +} + +static int static_call_add_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = start + mod->num_static_call_sites; + struct static_call_site *site; + + for (site = start; site != stop; site++) { + unsigned long s_key = __static_call_key(site); + unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; + unsigned long key; + + /* + * Is the key is exported, 'addr' points to the key, which + * means modules are allowed to call static_call_update() on + * it. + * + * Otherwise, the key isn't exported, and 'addr' points to the + * trampoline so we need to lookup the key. + * + * We go through this dance to prevent crazy modules from + * abusing sensitive static calls. + */ + if (!kernel_text_address(addr)) + continue; + + key = tramp_key_lookup(addr); + if (!key) { + pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", + static_call_addr(site)); + return -EINVAL; + } + + key |= s_key & STATIC_CALL_SITE_FLAGS; + site->key = key - (long)&site->key; + } + + return __static_call_init(mod, start, stop); +} + +static void static_call_del_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = mod->static_call_sites + + mod->num_static_call_sites; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod, **prev; + struct static_call_site *site; + + for (site = start; site < stop; site++) { + key = static_call_key(site); + if (key == prev_key) + continue; + + prev_key = key; + + for (prev = &key->mods, site_mod = key->mods; + site_mod && site_mod->mod != mod; + prev = &site_mod->next, site_mod = site_mod->next) + ; + + if (!site_mod) + continue; + + *prev = site_mod->next; + kfree(site_mod); + } +} + +static int static_call_module_notify(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + int ret = 0; + + cpus_read_lock(); + static_call_lock(); + + switch (val) { + case MODULE_STATE_COMING: + ret = static_call_add_module(mod); + if (ret) { + WARN(1, "Failed to allocate memory for static calls"); + static_call_del_module(mod); + } + break; + case MODULE_STATE_GOING: + static_call_del_module(mod); + break; + } + + static_call_unlock(); + cpus_read_unlock(); + + return notifier_from_errno(ret); +} + +static struct notifier_block static_call_module_nb = { + .notifier_call = static_call_module_notify, +}; + +#else + +static inline int __static_call_mod_text_reserved(void *start, void *end) +{ + return 0; +} + +#endif /* CONFIG_MODULES */ + +int static_call_text_reserved(void *start, void *end) +{ + bool init = system_state < SYSTEM_RUNNING; + int ret = __static_call_text_reserved(__start_static_call_sites, + __stop_static_call_sites, start, end, init); + + if (ret) + return ret; + + return __static_call_mod_text_reserved(start, end); +} + +int __init static_call_init(void) +{ + int ret; + + if (static_call_initialized) + return 0; + + cpus_read_lock(); + static_call_lock(); + ret = __static_call_init(NULL, __start_static_call_sites, + __stop_static_call_sites); + static_call_unlock(); + cpus_read_unlock(); + + if (ret) { + pr_err("Failed to allocate memory for static_call!\n"); + BUG(); + } + + static_call_initialized = true; + +#ifdef CONFIG_MODULES + register_module_notifier(&static_call_module_nb); +#endif + return 0; +} +early_initcall(static_call_init); + +#ifdef CONFIG_STATIC_CALL_SELFTEST + +static int func_a(int x) +{ + return x+1; +} + +static int func_b(int x) +{ + return x+2; +} + +DEFINE_STATIC_CALL(sc_selftest, func_a); + +static struct static_call_data { + int (*func)(int); + int val; + int expect; +} static_call_data [] __initdata = { + { NULL, 2, 3 }, + { func_b, 2, 4 }, + { func_a, 2, 3 } +}; + +static int __init test_static_call_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { + struct static_call_data *scd = &static_call_data[i]; + + if (scd->func) + static_call_update(sc_selftest, scd->func); + + WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); + } + + return 0; +} +early_initcall(test_static_call_init); + +#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 2d76c91b85de..d257721c68b8 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -188,7 +188,7 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) */ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL - WARN_ON(tick_nohz_full_running); + WARN_ON_ONCE(tick_nohz_full_running); #endif tick_do_timer_cpu = cpu; } @@ -1538,7 +1538,7 @@ void tick_cancel_sched_timer(int cpu) } #endif -/** +/* * Async notification about clocksource changes */ void tick_clock_notify(void) @@ -1559,7 +1559,7 @@ void tick_oneshot_notify(void) set_bit(0, &ts->check_clocks); } -/** +/* * Check, if a change happened, which makes oneshot possible. * * Called cyclic from the hrtimer softirq (driven by the timer diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 85f1021ad459..9dd2a39cb3b0 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1722,11 +1722,14 @@ static inline void __run_timers(struct timer_base *base) time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* - * The only possible reason for not finding any expired - * timer at this clk is that all matching timers have been - * dequeued. + * The two possible reasons for not finding any expired + * timer at this clk are that all matching timers have been + * dequeued or no timer has been queued since + * base::next_expiry was set to base::clk + + * NEXT_TIMER_MAX_DELTA. */ - WARN_ON_ONCE(!levels && !base->next_expiry_recalc); + WARN_ON_ONCE(!levels && !base->next_expiry_recalc + && base->timers_pending); base->clk++; base->next_expiry = __next_timer_interrupt(base); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 9bb54c0b3b2d..2c43e327a619 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -767,6 +767,7 @@ config USER_EVENTS bool "User trace events" select TRACING select DYNAMIC_EVENTS + depends on BROKEN || COMPILE_TEST # API needs to be straighten out help User trace events are user-defined trace events that can be used like an existing kernel trace event. User trace diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 19028e072cdb..8f4fb328133a 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -7,6 +7,7 @@ * * Highly modified by Steven Rostedt (VMware). */ +#include <linux/jump_label.h> #include <linux/suspend.h> #include <linux/ftrace.h> #include <linux/slab.h> @@ -23,25 +24,13 @@ #define ASSIGN_OPS_HASH(opsname, val) #endif -static bool kill_ftrace_graph; +DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph); int ftrace_graph_active; /* Both enabled by default (can be cleared by function_graph tracer flags */ static bool fgraph_sleep_time = true; /** - * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called - * - * ftrace_graph_stop() is called when a severe error is detected in - * the function graph tracing. This function is called by the critical - * paths of function graph to keep those paths from doing any more harm. - */ -bool ftrace_graph_is_dead(void) -{ - return kill_ftrace_graph; -} - -/** * ftrace_graph_stop - set to permanently disable function graph tracing * * In case of an error int function graph tracing, this is called @@ -51,7 +40,7 @@ bool ftrace_graph_is_dead(void) */ void ftrace_graph_stop(void) { - kill_ftrace_graph = true; + static_branch_enable(&kill_ftrace_graph); } /* Add a function return address to the trace stack on thread info.*/ diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 8b3d241a31c2..706e1686b5eb 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -18,7 +18,12 @@ #include <linux/tracefs.h> #include <linux/types.h> #include <linux/uaccess.h> +/* Reminder to move to uapi when everything works */ +#ifdef CONFIG_COMPILE_TEST +#include <linux/user_events.h> +#else #include <uapi/linux/user_events.h> +#endif #include "trace.h" #include "trace_dynevent.h" @@ -42,9 +47,6 @@ #define MAX_FIELD_ARRAY_SIZE 1024 #define MAX_FIELD_ARG_NAME 256 -#define MAX_BPF_COPY_SIZE PAGE_SIZE -#define MAX_STACK_BPF_DATA 512 - static char *register_page_data; static DEFINE_MUTEX(reg_mutex); @@ -405,19 +407,6 @@ parse: type[0] != 'u', FILTER_OTHER); } -static void user_event_parse_flags(struct user_event *user, char *flags) -{ - char *flag; - - if (flags == NULL) - return; - - while ((flag = strsep(&flags, ",")) != NULL) { - if (strcmp(flag, "BPF_ITER") == 0) - user->flags |= FLAG_BPF_ITER; - } -} - static int user_event_parse_fields(struct user_event *user, char *args) { char *field; @@ -713,64 +702,14 @@ discard: } #ifdef CONFIG_PERF_EVENTS -static void user_event_bpf(struct user_event *user, struct iov_iter *i) -{ - struct user_bpf_context context; - struct user_bpf_iter bpf_i; - char fast_data[MAX_STACK_BPF_DATA]; - void *temp = NULL; - - if ((user->flags & FLAG_BPF_ITER) && iter_is_iovec(i)) { - /* Raw iterator */ - context.data_type = USER_BPF_DATA_ITER; - context.data_len = i->count; - context.iter = &bpf_i; - - bpf_i.iov_offset = i->iov_offset; - bpf_i.iov = i->iov; - bpf_i.nr_segs = i->nr_segs; - } else if (i->nr_segs == 1 && iter_is_iovec(i)) { - /* Single buffer from user */ - context.data_type = USER_BPF_DATA_USER; - context.data_len = i->count; - context.udata = i->iov->iov_base + i->iov_offset; - } else { - /* Multi buffer from user */ - struct iov_iter copy = *i; - size_t copy_size = min_t(size_t, i->count, MAX_BPF_COPY_SIZE); - - context.data_type = USER_BPF_DATA_KERNEL; - context.kdata = fast_data; - - if (unlikely(copy_size > sizeof(fast_data))) { - temp = kmalloc(copy_size, GFP_NOWAIT); - - if (temp) - context.kdata = temp; - else - copy_size = sizeof(fast_data); - } - - context.data_len = copy_nofault(context.kdata, - copy_size, ©); - } - - trace_call_bpf(&user->call, &context); - - kfree(temp); -} - /* - * Writes the user supplied payload out to perf ring buffer or eBPF program. + * Writes the user supplied payload out to perf ring buffer. */ static void user_event_perf(struct user_event *user, struct iov_iter *i, void *tpdata, bool *faulted) { struct hlist_head *perf_head; - if (bpf_prog_array_valid(&user->call)) - user_event_bpf(user, i); - perf_head = this_cpu_ptr(user->call.perf_events); if (perf_head && !hlist_empty(perf_head)) { @@ -1136,8 +1075,6 @@ static int user_event_parse(char *name, char *args, char *flags, user->tracepoint.name = name; - user_event_parse_flags(user, flags); - ret = user_event_parse_fields(user, args); if (ret) @@ -1165,11 +1102,11 @@ static int user_event_parse(char *name, char *args, char *flags, #endif mutex_lock(&event_mutex); + ret = user_event_trace_register(user); - mutex_unlock(&event_mutex); if (ret) - goto put_user; + goto put_user_lock; user->index = index; @@ -1181,8 +1118,12 @@ static int user_event_parse(char *name, char *args, char *flags, set_bit(user->index, page_bitmap); hash_add(register_table, &user->node, key); + mutex_unlock(&event_mutex); + *newuser = user; return 0; +put_user_lock: + mutex_unlock(&event_mutex); put_user: user_event_destroy_fields(user); user_event_destroy_validators(user); @@ -1575,9 +1516,6 @@ static int user_seq_show(struct seq_file *m, void *p) busy++; } - if (flags & FLAG_BPF_ITER) - seq_puts(m, " FLAG:BPF_ITER"); - seq_puts(m, "\n"); active++; } diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 3990e4df3d7b..230038d4f908 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -370,6 +370,7 @@ static void __put_watch_queue(struct kref *kref) for (i = 0; i < wqueue->nr_pages; i++) __free_page(wqueue->notes[i]); + kfree(wqueue->notes); bitmap_free(wqueue->notes_bitmap); wfilter = rcu_access_pointer(wqueue->filter); |