diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/core.c | 45 | ||||
-rw-r--r-- | kernel/bpf/sockmap.c | 3 | ||||
-rw-r--r-- | kernel/events/callchain.c | 25 | ||||
-rw-r--r-- | kernel/events/core.c | 8 | ||||
-rw-r--r-- | kernel/fork.c | 3 | ||||
-rw-r--r-- | kernel/kprobes.c | 2 | ||||
-rw-r--r-- | kernel/livepatch/shadow.c | 108 | ||||
-rw-r--r-- | kernel/time/posix-cpu-timers.c | 4 | ||||
-rw-r--r-- | kernel/time/tick-oneshot.c | 11 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 7 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 25 | ||||
-rw-r--r-- | kernel/trace/trace_entries.h | 2 | ||||
-rw-r--r-- | kernel/trace/trace_events_filter.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 2 |
14 files changed, 156 insertions, 103 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d315b393abdd..ba03ec39efb3 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1572,13 +1572,32 @@ int bpf_prog_array_length(struct bpf_prog_array __rcu *progs) return cnt; } +static bool bpf_prog_array_copy_core(struct bpf_prog **prog, + u32 *prog_ids, + u32 request_cnt) +{ + int i = 0; + + for (; *prog; prog++) { + if (*prog == &dummy_bpf_prog.prog) + continue; + prog_ids[i] = (*prog)->aux->id; + if (++i == request_cnt) { + prog++; + break; + } + } + + return !!(*prog); +} + int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, __u32 __user *prog_ids, u32 cnt) { struct bpf_prog **prog; unsigned long err = 0; - u32 i = 0, *ids; bool nospc; + u32 *ids; /* users of this function are doing: * cnt = bpf_prog_array_length(); @@ -1595,16 +1614,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, return -ENOMEM; rcu_read_lock(); prog = rcu_dereference(progs)->progs; - for (; *prog; prog++) { - if (*prog == &dummy_bpf_prog.prog) - continue; - ids[i] = (*prog)->aux->id; - if (++i == cnt) { - prog++; - break; - } - } - nospc = !!(*prog); + nospc = bpf_prog_array_copy_core(prog, ids, cnt); rcu_read_unlock(); err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); kfree(ids); @@ -1683,22 +1693,25 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, } int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, - __u32 __user *prog_ids, u32 request_cnt, - __u32 __user *prog_cnt) + u32 *prog_ids, u32 request_cnt, + u32 *prog_cnt) { + struct bpf_prog **prog; u32 cnt = 0; if (array) cnt = bpf_prog_array_length(array); - if (copy_to_user(prog_cnt, &cnt, sizeof(cnt))) - return -EFAULT; + *prog_cnt = cnt; /* return early if user requested only program count or nothing to copy */ if (!request_cnt || !cnt) return 0; - return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt); + /* this function is called under trace/bpf_trace.c: bpf_event_mutex */ + prog = rcu_dereference_check(array, 1)->progs; + return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC + : 0; } static void bpf_prog_free_deferred(struct work_struct *work) diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 8dd9210d7db7..a3b21385e947 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1442,9 +1442,6 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); - if (attr->value_size > KMALLOC_MAX_SIZE) - return ERR_PTR(-E2BIG); - err = bpf_tcp_ulp_register(); if (err && err != -EEXIST) return ERR_PTR(err); diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 772a43fea825..c187aa3df3c8 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -119,23 +119,20 @@ int get_callchain_buffers(int event_max_stack) goto exit; } - if (count > 1) { - /* If the allocation failed, give up */ - if (!callchain_cpus_entries) - err = -ENOMEM; - /* - * If requesting per event more than the global cap, - * return a different error to help userspace figure - * this out. - * - * And also do it here so that we have &callchain_mutex held. - */ - if (event_max_stack > sysctl_perf_event_max_stack) - err = -EOVERFLOW; + /* + * If requesting per event more than the global cap, + * return a different error to help userspace figure + * this out. + * + * And also do it here so that we have &callchain_mutex held. + */ + if (event_max_stack > sysctl_perf_event_max_stack) { + err = -EOVERFLOW; goto exit; } - err = alloc_callchain_buffers(); + if (count == 1) + err = alloc_callchain_buffers(); exit: if (err) atomic_dec(&nr_callchain_events); diff --git a/kernel/events/core.c b/kernel/events/core.c index 2d5fe26551f8..67612ce359ad 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7587,6 +7587,10 @@ static void perf_event_switch(struct task_struct *task, }, }; + if (!sched_in && task->state == TASK_RUNNING) + switch_event.event_id.header.misc |= + PERF_RECORD_MISC_SWITCH_OUT_PREEMPT; + perf_iterate_sb(perf_event_switch_output, &switch_event, NULL); @@ -10205,9 +10209,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, * __u16 sample size limit. */ if (attr->sample_stack_user >= USHRT_MAX) - ret = -EINVAL; + return -EINVAL; else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64))) - ret = -EINVAL; + return -EINVAL; } if (!attr->sample_max_stack) diff --git a/kernel/fork.c b/kernel/fork.c index 242c8c93d285..a5d21c42acfc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -216,10 +216,9 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) if (!s) continue; -#ifdef CONFIG_DEBUG_KMEMLEAK /* Clear stale pointers from reused stack. */ memset(s->addr, 0, THREAD_SIZE); -#endif + tsk->stack_vm_area = s; return s->addr; } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 102160ff5c66..ea619021d901 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2428,7 +2428,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) struct kprobe_blacklist_entry *ent = list_entry(v, struct kprobe_blacklist_entry, list); - seq_printf(m, "0x%p-0x%p\t%ps\n", (void *)ent->start_addr, + seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, (void *)ent->end_addr, (void *)ent->start_addr); return 0; } diff --git a/kernel/livepatch/shadow.c b/kernel/livepatch/shadow.c index fdac27588d60..83958c814439 100644 --- a/kernel/livepatch/shadow.c +++ b/kernel/livepatch/shadow.c @@ -113,8 +113,10 @@ void *klp_shadow_get(void *obj, unsigned long id) } EXPORT_SYMBOL_GPL(klp_shadow_get); -static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data, - size_t size, gfp_t gfp_flags, bool warn_on_exist) +static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, + size_t size, gfp_t gfp_flags, + klp_shadow_ctor_t ctor, void *ctor_data, + bool warn_on_exist) { struct klp_shadow *new_shadow; void *shadow_data; @@ -125,18 +127,15 @@ static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data, if (shadow_data) goto exists; - /* Allocate a new shadow variable for use inside the lock below */ + /* + * Allocate a new shadow variable. Fill it with zeroes by default. + * More complex setting can be done by @ctor function. But it is + * called only when the buffer is really used (under klp_shadow_lock). + */ new_shadow = kzalloc(size + sizeof(*new_shadow), gfp_flags); if (!new_shadow) return NULL; - new_shadow->obj = obj; - new_shadow->id = id; - - /* Initialize the shadow variable if data provided */ - if (data) - memcpy(new_shadow->data, data, size); - /* Look for <obj, id> again under the lock */ spin_lock_irqsave(&klp_shadow_lock, flags); shadow_data = klp_shadow_get(obj, id); @@ -150,6 +149,22 @@ static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data, goto exists; } + new_shadow->obj = obj; + new_shadow->id = id; + + if (ctor) { + int err; + + err = ctor(obj, new_shadow->data, ctor_data); + if (err) { + spin_unlock_irqrestore(&klp_shadow_lock, flags); + kfree(new_shadow); + pr_err("Failed to construct shadow variable <%p, %lx> (%d)\n", + obj, id, err); + return NULL; + } + } + /* No <obj, id> found, so attach the newly allocated one */ hash_add_rcu(klp_shadow_hash, &new_shadow->node, (unsigned long)new_shadow->obj); @@ -170,26 +185,32 @@ exists: * klp_shadow_alloc() - allocate and add a new shadow variable * @obj: pointer to parent object * @id: data identifier - * @data: pointer to data to attach to parent * @size: size of attached data * @gfp_flags: GFP mask for allocation + * @ctor: custom constructor to initialize the shadow data (optional) + * @ctor_data: pointer to any data needed by @ctor (optional) + * + * Allocates @size bytes for new shadow variable data using @gfp_flags. + * The data are zeroed by default. They are further initialized by @ctor + * function if it is not NULL. The new shadow variable is then added + * to the global hashtable. * - * Allocates @size bytes for new shadow variable data using @gfp_flags - * and copies @size bytes from @data into the new shadow variable's own - * data space. If @data is NULL, @size bytes are still allocated, but - * no copy is performed. The new shadow variable is then added to the - * global hashtable. + * If an existing <obj, id> shadow variable can be found, this routine will + * issue a WARN, exit early and return NULL. * - * If an existing <obj, id> shadow variable can be found, this routine - * will issue a WARN, exit early and return NULL. + * This function guarantees that the constructor function is called only when + * the variable did not exist before. The cost is that @ctor is called + * in atomic context under a spin lock. * * Return: the shadow variable data element, NULL on duplicate or * failure. */ -void *klp_shadow_alloc(void *obj, unsigned long id, void *data, - size_t size, gfp_t gfp_flags) +void *klp_shadow_alloc(void *obj, unsigned long id, + size_t size, gfp_t gfp_flags, + klp_shadow_ctor_t ctor, void *ctor_data) { - return __klp_shadow_get_or_alloc(obj, id, data, size, gfp_flags, true); + return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags, + ctor, ctor_data, true); } EXPORT_SYMBOL_GPL(klp_shadow_alloc); @@ -197,37 +218,51 @@ EXPORT_SYMBOL_GPL(klp_shadow_alloc); * klp_shadow_get_or_alloc() - get existing or allocate a new shadow variable * @obj: pointer to parent object * @id: data identifier - * @data: pointer to data to attach to parent * @size: size of attached data * @gfp_flags: GFP mask for allocation + * @ctor: custom constructor to initialize the shadow data (optional) + * @ctor_data: pointer to any data needed by @ctor (optional) * * Returns a pointer to existing shadow data if an <obj, id> shadow * variable is already present. Otherwise, it creates a new shadow * variable like klp_shadow_alloc(). * - * This function guarantees that only one shadow variable exists with - * the given @id for the given @obj. It also guarantees that the shadow - * variable will be initialized by the given @data only when it did not - * exist before. + * This function guarantees that only one shadow variable exists with the given + * @id for the given @obj. It also guarantees that the constructor function + * will be called only when the variable did not exist before. The cost is + * that @ctor is called in atomic context under a spin lock. * * Return: the shadow variable data element, NULL on failure. */ -void *klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data, - size_t size, gfp_t gfp_flags) +void *klp_shadow_get_or_alloc(void *obj, unsigned long id, + size_t size, gfp_t gfp_flags, + klp_shadow_ctor_t ctor, void *ctor_data) { - return __klp_shadow_get_or_alloc(obj, id, data, size, gfp_flags, false); + return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags, + ctor, ctor_data, false); } EXPORT_SYMBOL_GPL(klp_shadow_get_or_alloc); +static void klp_shadow_free_struct(struct klp_shadow *shadow, + klp_shadow_dtor_t dtor) +{ + hash_del_rcu(&shadow->node); + if (dtor) + dtor(shadow->obj, shadow->data); + kfree_rcu(shadow, rcu_head); +} + /** * klp_shadow_free() - detach and free a <obj, id> shadow variable * @obj: pointer to parent object * @id: data identifier + * @dtor: custom callback that can be used to unregister the variable + * and/or free data that the shadow variable points to (optional) * * This function releases the memory for this <obj, id> shadow variable * instance, callers should stop referencing it accordingly. */ -void klp_shadow_free(void *obj, unsigned long id) +void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor) { struct klp_shadow *shadow; unsigned long flags; @@ -239,8 +274,7 @@ void klp_shadow_free(void *obj, unsigned long id) (unsigned long)obj) { if (klp_shadow_match(shadow, obj, id)) { - hash_del_rcu(&shadow->node); - kfree_rcu(shadow, rcu_head); + klp_shadow_free_struct(shadow, dtor); break; } } @@ -252,11 +286,13 @@ EXPORT_SYMBOL_GPL(klp_shadow_free); /** * klp_shadow_free_all() - detach and free all <*, id> shadow variables * @id: data identifier + * @dtor: custom callback that can be used to unregister the variable + * and/or free data that the shadow variable points to (optional) * * This function releases the memory for all <*, id> shadow variable * instances, callers should stop referencing them accordingly. */ -void klp_shadow_free_all(unsigned long id) +void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor) { struct klp_shadow *shadow; unsigned long flags; @@ -266,10 +302,8 @@ void klp_shadow_free_all(unsigned long id) /* Delete all <*, id> from hash */ hash_for_each(klp_shadow_hash, i, shadow, node) { - if (klp_shadow_match(shadow, shadow->obj, id)) { - hash_del_rcu(&shadow->node); - kfree_rcu(shadow, rcu_head); - } + if (klp_shadow_match(shadow, shadow->obj, id)) + klp_shadow_free_struct(shadow, dtor); } spin_unlock_irqrestore(&klp_shadow_lock, flags); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 2541bd89f20e..5a6251ac6f7a 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1205,10 +1205,12 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, u64 *newval, u64 *oldval) { u64 now; + int ret; WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED); + ret = cpu_timer_sample_group(clock_idx, tsk, &now); - if (oldval && cpu_timer_sample_group(clock_idx, tsk, &now) != -EINVAL) { + if (oldval && ret != -EINVAL) { /* * We are setting itimer. The *oldval is absolute and we update * it to be relative, *newval argument is relative and we update diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index c1f518e7aa80..6fe615d57ebb 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -82,16 +82,15 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) || !tick_device_is_functional(dev)) { - printk(KERN_INFO "Clockevents: " - "could not switch to one-shot mode:"); + pr_info("Clockevents: could not switch to one-shot mode:"); if (!dev) { - printk(" no tick device\n"); + pr_cont(" no tick device\n"); } else { if (!tick_device_is_functional(dev)) - printk(" %s is not functional.\n", dev->name); + pr_cont(" %s is not functional.\n", dev->name); else - printk(" %s does not support one-shot mode.\n", - dev->name); + pr_cont(" %s does not support one-shot mode.\n", + dev->name); } return -EINVAL; } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index ca90219a1e73..dcf7f20fcd12 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2139,13 +2139,6 @@ unsigned long get_seconds(void) } EXPORT_SYMBOL(get_seconds); -struct timespec __current_kernel_time(void) -{ - struct timekeeper *tk = &tk_core.timekeeper; - - return timespec64_to_timespec(tk_xtime(tk)); -} - struct timespec64 current_kernel_time64(void) { struct timekeeper *tk = &tk_core.timekeeper; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d88e96d4e12c..56ba0f2a01db 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -977,6 +977,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) { struct perf_event_query_bpf __user *uquery = info; struct perf_event_query_bpf query = {}; + u32 *ids, prog_cnt, ids_len; int ret; if (!capable(CAP_SYS_ADMIN)) @@ -985,16 +986,32 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) return -EINVAL; if (copy_from_user(&query, uquery, sizeof(query))) return -EFAULT; - if (query.ids_len > BPF_TRACE_MAX_PROGS) + + ids_len = query.ids_len; + if (ids_len > BPF_TRACE_MAX_PROGS) return -E2BIG; + ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN); + if (!ids) + return -ENOMEM; + /* + * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which + * is required when user only wants to check for uquery->prog_cnt. + * There is no need to check for it since the case is handled + * gracefully in bpf_prog_array_copy_info. + */ mutex_lock(&bpf_event_mutex); ret = bpf_prog_array_copy_info(event->tp_event->prog_array, - uquery->ids, - query.ids_len, - &uquery->prog_cnt); + ids, + ids_len, + &prog_cnt); mutex_unlock(&bpf_event_mutex); + if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) || + copy_to_user(uquery->ids, ids, ids_len * sizeof(u32))) + ret = -EFAULT; + + kfree(ids); return ret; } diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e954ae3d82c0..e3a658bac10f 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -356,7 +356,7 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __field( unsigned int, seqnum ) ), - F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n", + F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n", __entry->seqnum, __entry->tv_sec, __entry->tv_nsec, diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 9b4716bb8bb0..1f951b3df60c 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1499,14 +1499,14 @@ static int process_preds(struct trace_event_call *call, return ret; } - if (!nr_preds) { - prog = NULL; - } else { - prog = predicate_parse(filter_string, nr_parens, nr_preds, + if (!nr_preds) + return -EINVAL; + + prog = predicate_parse(filter_string, nr_parens, nr_preds, parse_pred, call, pe); - if (IS_ERR(prog)) - return PTR_ERR(prog); - } + if (IS_ERR(prog)) + return PTR_ERR(prog); + rcu_assign_pointer(filter->prog, prog); return 0; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 1cd3fb4d70f8..02aed76e0978 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -512,8 +512,6 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) if (ret == 0) tk->tp.flags |= TP_FLAG_REGISTERED; else { - pr_warn("Could not insert probe at %s+%lu: %d\n", - trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret); if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) { pr_warn("This probe might be able to register after target module is loaded. Continue.\n"); ret = 0; |