diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/configs/nopm.config | 15 | ||||
-rw-r--r-- | kernel/events/core.c | 47 | ||||
-rw-r--r-- | kernel/futex.c | 6 | ||||
-rw-r--r-- | kernel/irq/Kconfig | 10 | ||||
-rw-r--r-- | kernel/irq/affinity.c | 30 | ||||
-rw-r--r-- | kernel/irq/irqdomain.c | 118 | ||||
-rw-r--r-- | kernel/irq_work.c | 2 | ||||
-rw-r--r-- | kernel/jump_label.c | 12 | ||||
-rw-r--r-- | kernel/locking/lockdep.c | 2 | ||||
-rw-r--r-- | kernel/pid.c | 14 | ||||
-rw-r--r-- | kernel/power/main.c | 29 | ||||
-rw-r--r-- | kernel/power/snapshot.c | 6 | ||||
-rw-r--r-- | kernel/power/swap.c | 6 | ||||
-rw-r--r-- | kernel/sched/fair.c | 4 |
14 files changed, 136 insertions, 165 deletions
diff --git a/kernel/configs/nopm.config b/kernel/configs/nopm.config new file mode 100644 index 000000000000..81ff07863576 --- /dev/null +++ b/kernel/configs/nopm.config @@ -0,0 +1,15 @@ +CONFIG_PM=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n + +# Triggers PM on OMAP +CONFIG_CPU_IDLE=n + +# Triggers enablement via hibernate callbacks +CONFIG_XEN=n + +# ARM/ARM64 architectures that select PM unconditionally +CONFIG_ARCH_OMAP2PLUS_TYPICAL=n +CONFIG_ARCH_RENESAS=n +CONFIG_ARCH_TEGRA=n +CONFIG_ARCH_VEXPRESS=n diff --git a/kernel/events/core.c b/kernel/events/core.c index 4df5b695bf0d..5d8f4031f8d5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1231,6 +1231,10 @@ static void put_ctx(struct perf_event_context *ctx) * perf_event_context::lock * perf_event::mmap_mutex * mmap_sem + * + * cpu_hotplug_lock + * pmus_lock + * cpuctx->mutex / perf_event_context::mutex */ static struct perf_event_context * perf_event_ctx_lock_nested(struct perf_event *event, int nesting) @@ -4196,6 +4200,7 @@ int perf_event_release_kernel(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; struct perf_event *child, *tmp; + LIST_HEAD(free_list); /* * If we got here through err_file: fput(event_file); we will not have @@ -4268,8 +4273,7 @@ again: struct perf_event, child_list); if (tmp == child) { perf_remove_from_context(child, DETACH_GROUP); - list_del(&child->child_list); - free_event(child); + list_move(&child->child_list, &free_list); /* * This matches the refcount bump in inherit_event(); * this can't be the last reference. @@ -4284,6 +4288,11 @@ again: } mutex_unlock(&event->child_mutex); + list_for_each_entry_safe(child, tmp, &free_list, child_list) { + list_del(&child->child_list); + free_event(child); + } + no_ctx: put_event(event); /* Must be the 'last' reference */ return 0; @@ -8516,6 +8525,29 @@ fail_clear_files: return ret; } +static int +perf_tracepoint_set_filter(struct perf_event *event, char *filter_str) +{ + struct perf_event_context *ctx = event->ctx; + int ret; + + /* + * Beware, here be dragons!! + * + * the tracepoint muck will deadlock against ctx->mutex, but the tracepoint + * stuff does not actually need it. So temporarily drop ctx->mutex. As per + * perf_event_ctx_lock() we already have a reference on ctx. + * + * This can result in event getting moved to a different ctx, but that + * does not affect the tracepoint state. + */ + mutex_unlock(&ctx->mutex); + ret = ftrace_profile_set_filter(event, event->attr.config, filter_str); + mutex_lock(&ctx->mutex); + + return ret; +} + static int perf_event_set_filter(struct perf_event *event, void __user *arg) { char *filter_str; @@ -8532,8 +8564,7 @@ static int perf_event_set_filter(struct perf_event *event, void __user *arg) if (IS_ENABLED(CONFIG_EVENT_TRACING) && event->attr.type == PERF_TYPE_TRACEPOINT) - ret = ftrace_profile_set_filter(event, event->attr.config, - filter_str); + ret = perf_tracepoint_set_filter(event, filter_str); else if (has_addr_filter(event)) ret = perf_event_set_addr_filter(event, filter_str); @@ -9168,7 +9199,13 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) if (!try_module_get(pmu->module)) return -ENODEV; - if (event->group_leader != event) { + /* + * A number of pmu->event_init() methods iterate the sibling_list to, + * for example, validate if the group fits on the PMU. Therefore, + * if this is a sibling event, acquire the ctx->mutex to protect + * the sibling_list. + */ + if (event->group_leader != event && pmu->task_ctx_nr != perf_sw_context) { /* * This ctx->mutex can nest when we're called through * inheritance. See the perf_event_ctx_lock_nested() comment. diff --git a/kernel/futex.c b/kernel/futex.c index 8c5424dd5924..7f719d110908 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2311,9 +2311,6 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); oldowner = pi_state->owner; - /* Owner died? */ - if (!pi_state->owner) - newtid |= FUTEX_OWNER_DIED; /* * We are here because either: @@ -2374,6 +2371,9 @@ retry: } newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; + /* Owner died? */ + if (!pi_state->owner) + newtid |= FUTEX_OWNER_DIED; if (get_futex_value_locked(&uval, uaddr)) goto handle_fault; diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 89e355866450..6fc87ccda1d7 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -103,16 +103,6 @@ config GENERIC_IRQ_MATRIX_ALLOCATOR config GENERIC_IRQ_RESERVATION_MODE bool -config IRQ_DOMAIN_DEBUG - bool "Expose hardware/virtual IRQ mapping via debugfs" - depends on IRQ_DOMAIN && DEBUG_FS - help - This option will show the mapping relationship between hardware irq - numbers and Linux irq numbers. The mapping is exposed via debugfs - in the file "irq_domain_mapping". - - If you don't know what this means you don't need it. - # Support forced irq threading config IRQ_FORCED_THREADING bool diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index e12d35108225..a37a3b4b6342 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -39,7 +39,7 @@ static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk, } } -static cpumask_var_t *alloc_node_to_present_cpumask(void) +static cpumask_var_t *alloc_node_to_possible_cpumask(void) { cpumask_var_t *masks; int node; @@ -62,7 +62,7 @@ out_unwind: return NULL; } -static void free_node_to_present_cpumask(cpumask_var_t *masks) +static void free_node_to_possible_cpumask(cpumask_var_t *masks) { int node; @@ -71,22 +71,22 @@ static void free_node_to_present_cpumask(cpumask_var_t *masks) kfree(masks); } -static void build_node_to_present_cpumask(cpumask_var_t *masks) +static void build_node_to_possible_cpumask(cpumask_var_t *masks) { int cpu; - for_each_present_cpu(cpu) + for_each_possible_cpu(cpu) cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]); } -static int get_nodes_in_cpumask(cpumask_var_t *node_to_present_cpumask, +static int get_nodes_in_cpumask(cpumask_var_t *node_to_possible_cpumask, const struct cpumask *mask, nodemask_t *nodemsk) { int n, nodes = 0; /* Calculate the number of nodes in the supplied affinity mask */ for_each_node(n) { - if (cpumask_intersects(mask, node_to_present_cpumask[n])) { + if (cpumask_intersects(mask, node_to_possible_cpumask[n])) { node_set(n, *nodemsk); nodes++; } @@ -109,7 +109,7 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) int last_affv = affv + affd->pre_vectors; nodemask_t nodemsk = NODE_MASK_NONE; struct cpumask *masks; - cpumask_var_t nmsk, *node_to_present_cpumask; + cpumask_var_t nmsk, *node_to_possible_cpumask; /* * If there aren't any vectors left after applying the pre/post @@ -125,8 +125,8 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) if (!masks) goto out; - node_to_present_cpumask = alloc_node_to_present_cpumask(); - if (!node_to_present_cpumask) + node_to_possible_cpumask = alloc_node_to_possible_cpumask(); + if (!node_to_possible_cpumask) goto out; /* Fill out vectors at the beginning that don't need affinity */ @@ -135,8 +135,8 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) /* Stabilize the cpumasks */ get_online_cpus(); - build_node_to_present_cpumask(node_to_present_cpumask); - nodes = get_nodes_in_cpumask(node_to_present_cpumask, cpu_present_mask, + build_node_to_possible_cpumask(node_to_possible_cpumask); + nodes = get_nodes_in_cpumask(node_to_possible_cpumask, cpu_possible_mask, &nodemsk); /* @@ -146,7 +146,7 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) if (affv <= nodes) { for_each_node_mask(n, nodemsk) { cpumask_copy(masks + curvec, - node_to_present_cpumask[n]); + node_to_possible_cpumask[n]); if (++curvec == last_affv) break; } @@ -160,7 +160,7 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes; /* Get the cpus on this node which are in the mask */ - cpumask_and(nmsk, cpu_present_mask, node_to_present_cpumask[n]); + cpumask_and(nmsk, cpu_possible_mask, node_to_possible_cpumask[n]); /* Calculate the number of cpus per vector */ ncpus = cpumask_weight(nmsk); @@ -192,7 +192,7 @@ done: /* Fill out vectors at the end that don't need affinity */ for (; curvec < nvecs; curvec++) cpumask_copy(masks + curvec, irq_default_affinity); - free_node_to_present_cpumask(node_to_present_cpumask); + free_node_to_possible_cpumask(node_to_possible_cpumask); out: free_cpumask_var(nmsk); return masks; @@ -214,7 +214,7 @@ int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity return 0; get_online_cpus(); - ret = min_t(int, cpumask_weight(cpu_present_mask), vecs) + resv; + ret = min_t(int, cpumask_weight(cpu_possible_mask), vecs) + resv; put_online_cpus(); return ret; } diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 62068ad46930..e6a9c36470ee 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -897,124 +897,6 @@ unsigned int irq_find_mapping(struct irq_domain *domain, } EXPORT_SYMBOL_GPL(irq_find_mapping); -#ifdef CONFIG_IRQ_DOMAIN_DEBUG -static void virq_debug_show_one(struct seq_file *m, struct irq_desc *desc) -{ - struct irq_domain *domain; - struct irq_data *data; - - domain = desc->irq_data.domain; - data = &desc->irq_data; - - while (domain) { - unsigned int irq = data->irq; - unsigned long hwirq = data->hwirq; - struct irq_chip *chip; - bool direct; - - if (data == &desc->irq_data) - seq_printf(m, "%5d ", irq); - else - seq_printf(m, "%5d+ ", irq); - seq_printf(m, "0x%05lx ", hwirq); - - chip = irq_data_get_irq_chip(data); - seq_printf(m, "%-15s ", (chip && chip->name) ? chip->name : "none"); - - seq_printf(m, "0x%p ", irq_data_get_irq_chip_data(data)); - - seq_printf(m, " %c ", (desc->action && desc->action->handler) ? '*' : ' '); - direct = (irq == hwirq) && (irq < domain->revmap_direct_max_irq); - seq_printf(m, "%6s%-8s ", - (hwirq < domain->revmap_size) ? "LINEAR" : "RADIX", - direct ? "(DIRECT)" : ""); - seq_printf(m, "%s\n", domain->name); -#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY - domain = domain->parent; - data = data->parent_data; -#else - domain = NULL; -#endif - } -} - -static int virq_debug_show(struct seq_file *m, void *private) -{ - unsigned long flags; - struct irq_desc *desc; - struct irq_domain *domain; - struct radix_tree_iter iter; - void __rcu **slot; - int i; - - seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", - "name", "mapped", "linear-max", "direct-max", "devtree-node"); - mutex_lock(&irq_domain_mutex); - list_for_each_entry(domain, &irq_domain_list, link) { - struct device_node *of_node; - const char *name; - - int count = 0; - - of_node = irq_domain_get_of_node(domain); - if (of_node) - name = of_node_full_name(of_node); - else if (is_fwnode_irqchip(domain->fwnode)) - name = container_of(domain->fwnode, struct irqchip_fwid, - fwnode)->name; - else - name = ""; - - radix_tree_for_each_slot(slot, &domain->revmap_tree, &iter, 0) - count++; - seq_printf(m, "%c%-16s %6u %10u %10u %s\n", - domain == irq_default_domain ? '*' : ' ', domain->name, - domain->revmap_size + count, domain->revmap_size, - domain->revmap_direct_max_irq, - name); - } - mutex_unlock(&irq_domain_mutex); - - seq_printf(m, "%-5s %-7s %-15s %-*s %6s %-14s %s\n", "irq", "hwirq", - "chip name", (int)(2 * sizeof(void *) + 2), "chip data", - "active", "type", "domain"); - - for (i = 1; i < nr_irqs; i++) { - desc = irq_to_desc(i); - if (!desc) - continue; - - raw_spin_lock_irqsave(&desc->lock, flags); - virq_debug_show_one(m, desc); - raw_spin_unlock_irqrestore(&desc->lock, flags); - } - - return 0; -} - -static int virq_debug_open(struct inode *inode, struct file *file) -{ - return single_open(file, virq_debug_show, inode->i_private); -} - -static const struct file_operations virq_debug_fops = { - .open = virq_debug_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int __init irq_debugfs_init(void) -{ - if (debugfs_create_file("irq_domain_mapping", S_IRUGO, NULL, - NULL, &virq_debug_fops) == NULL) - return -ENOMEM; - - return 0; -} -__initcall(irq_debugfs_init); -#endif /* CONFIG_IRQ_DOMAIN_DEBUG */ - /** * irq_domain_xlate_onecell() - Generic xlate for direct one cell bindings * diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 40e9d739c169..6b7cdf17ccf8 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -36,7 +36,7 @@ static bool irq_work_claim(struct irq_work *work) */ flags = work->flags & ~IRQ_WORK_PENDING; for (;;) { - nflags = flags | IRQ_WORK_FLAGS; + nflags = flags | IRQ_WORK_CLAIMED; oflags = cmpxchg(&work->flags, flags, nflags); if (oflags == flags) break; diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 8594d24e4adc..b4517095db6a 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -79,7 +79,7 @@ int static_key_count(struct static_key *key) } EXPORT_SYMBOL_GPL(static_key_count); -static void static_key_slow_inc_cpuslocked(struct static_key *key) +void static_key_slow_inc_cpuslocked(struct static_key *key) { int v, v1; @@ -180,7 +180,7 @@ void static_key_disable(struct static_key *key) } EXPORT_SYMBOL_GPL(static_key_disable); -static void static_key_slow_dec_cpuslocked(struct static_key *key, +static void __static_key_slow_dec_cpuslocked(struct static_key *key, unsigned long rate_limit, struct delayed_work *work) { @@ -211,7 +211,7 @@ static void __static_key_slow_dec(struct static_key *key, struct delayed_work *work) { cpus_read_lock(); - static_key_slow_dec_cpuslocked(key, rate_limit, work); + __static_key_slow_dec_cpuslocked(key, rate_limit, work); cpus_read_unlock(); } @@ -229,6 +229,12 @@ void static_key_slow_dec(struct static_key *key) } EXPORT_SYMBOL_GPL(static_key_slow_dec); +void static_key_slow_dec_cpuslocked(struct static_key *key) +{ + STATIC_KEY_CHECK_USE(key); + __static_key_slow_dec_cpuslocked(key, 0, NULL); +} + void static_key_slow_dec_deferred(struct static_key_deferred *key) { STATIC_KEY_CHECK_USE(key); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 5fa1324a4f29..521659044719 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -49,6 +49,7 @@ #include <linux/gfp.h> #include <linux/random.h> #include <linux/jhash.h> +#include <linux/nmi.h> #include <asm/sections.h> @@ -4490,6 +4491,7 @@ retry: if (!unlock) if (read_trylock(&tasklist_lock)) unlock = 1; + touch_nmi_watchdog(); } while_each_thread(g, p); pr_warn("\n"); diff --git a/kernel/pid.c b/kernel/pid.c index 1e8bb6550ec4..5d30c87e3c42 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -41,7 +41,19 @@ #include <linux/sched/task.h> #include <linux/idr.h> -struct pid init_struct_pid = INIT_STRUCT_PID; +struct pid init_struct_pid = { + .count = ATOMIC_INIT(1), + .tasks = { + { .first = NULL }, + { .first = NULL }, + { .first = NULL }, + }, + .level = 0, + .numbers = { { + .nr = 0, + .ns = &init_pid_ns, + }, } +}; int pid_max = PID_MAX_DEFAULT; diff --git a/kernel/power/main.c b/kernel/power/main.c index 3a2ca9066583..705c2366dafe 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -22,6 +22,35 @@ DEFINE_MUTEX(pm_mutex); #ifdef CONFIG_PM_SLEEP +void lock_system_sleep(void) +{ + current->flags |= PF_FREEZER_SKIP; + mutex_lock(&pm_mutex); +} +EXPORT_SYMBOL_GPL(lock_system_sleep); + +void unlock_system_sleep(void) +{ + /* + * Don't use freezer_count() because we don't want the call to + * try_to_freeze() here. + * + * Reason: + * Fundamentally, we just don't need it, because freezing condition + * doesn't come into effect until we release the pm_mutex lock, + * since the freezer always works with pm_mutex held. + * + * More importantly, in the case of hibernation, + * unlock_system_sleep() gets called in snapshot_read() and + * snapshot_write() when the freezing condition is still in effect. + * Which means, if we use try_to_freeze() here, it would make them + * enter the refrigerator, thus causing hibernation to lockup. + */ + current->flags &= ~PF_FREEZER_SKIP; + mutex_unlock(&pm_mutex); +} +EXPORT_SYMBOL_GPL(unlock_system_sleep); + /* Routines for PM-transition notifications */ static BLOCKING_NOTIFIER_HEAD(pm_chain_head); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index bce0464524d8..3d37c279c090 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1645,8 +1645,7 @@ static unsigned long free_unnecessary_pages(void) * [number of saveable pages] - [number of pages that can be freed in theory] * * where the second term is the sum of (1) reclaimable slab pages, (2) active - * and (3) inactive anonymous pages, (4) active and (5) inactive file pages, - * minus mapped file pages. + * and (3) inactive anonymous pages, (4) active and (5) inactive file pages. */ static unsigned long minimum_image_size(unsigned long saveable) { @@ -1656,8 +1655,7 @@ static unsigned long minimum_image_size(unsigned long saveable) + global_node_page_state(NR_ACTIVE_ANON) + global_node_page_state(NR_INACTIVE_ANON) + global_node_page_state(NR_ACTIVE_FILE) - + global_node_page_state(NR_INACTIVE_FILE) - - global_node_page_state(NR_FILE_MAPPED); + + global_node_page_state(NR_INACTIVE_FILE); return saveable <= size ? 0 : saveable - size; } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 293ead59eccc..11b4282c2d20 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -240,7 +240,7 @@ static void hib_init_batch(struct hib_bio_batch *hb) static void hib_end_io(struct bio *bio) { struct hib_bio_batch *hb = bio->bi_private; - struct page *page = bio->bi_io_vec[0].bv_page; + struct page *page = bio_first_page_all(bio); if (bio->bi_status) { pr_alert("Read-error on swap-device (%u:%u:%Lu)\n", @@ -879,7 +879,7 @@ out_clean: * space avaiable from the resume partition. */ -static int enough_swap(unsigned int nr_pages, unsigned int flags) +static int enough_swap(unsigned int nr_pages) { unsigned int free_swap = count_swap_pages(root_swap, 1); unsigned int required; @@ -915,7 +915,7 @@ int swsusp_write(unsigned int flags) return error; } if (flags & SF_NOCOMPRESS_MODE) { - if (!enough_swap(pages, flags)) { + if (!enough_swap(pages)) { pr_err("Not enough free swap\n"); error = -ENOSPC; goto out_finish; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2fe3aa853e4d..26a71ebcd3c2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4365,12 +4365,12 @@ static inline bool cfs_bandwidth_used(void) void cfs_bandwidth_usage_inc(void) { - static_key_slow_inc(&__cfs_bandwidth_used); + static_key_slow_inc_cpuslocked(&__cfs_bandwidth_used); } void cfs_bandwidth_usage_dec(void) { - static_key_slow_dec(&__cfs_bandwidth_used); + static_key_slow_dec_cpuslocked(&__cfs_bandwidth_used); } #else /* HAVE_JUMP_LABEL */ static bool cfs_bandwidth_used(void) |