diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/verifier.c | 10 | ||||
-rw-r--r-- | kernel/cgroup/cpuset.c | 2 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_io.c | 99 | ||||
-rw-r--r-- | kernel/dma/map_benchmark.c | 6 | ||||
-rw-r--r-- | kernel/irq/cpuhotplug.c | 16 | ||||
-rw-r--r-- | kernel/sched/core.c | 2 | ||||
-rw-r--r-- | kernel/sched/fair.c | 53 | ||||
-rw-r--r-- | kernel/sched/topology.c | 2 | ||||
-rw-r--r-- | kernel/softirq.c | 12 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 9 |
10 files changed, 128 insertions, 83 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 94d952967fbf..07ca1157f97c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5568,7 +5568,8 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); - if (func_id != BPF_FUNC_map_update_elem) + if (func_id != BPF_FUNC_map_update_elem && + func_id != BPF_FUNC_map_delete_elem) return false; /* It's not possible to get access to a locked struct sock in these @@ -5579,6 +5580,11 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) if (eatype == BPF_TRACE_ITER) return true; break; + case BPF_PROG_TYPE_SOCK_OPS: + /* map_update allowed only via dedicated helpers with event type checks */ + if (func_id == BPF_FUNC_map_delete_elem) + return true; + break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: @@ -5666,7 +5672,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && @@ -5676,7 +5681,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 6905079c15c2..82df5a07a869 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1938,7 +1938,7 @@ bool current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP - if (val < -1 || val >= sched_domain_level_max) + if (val < -1 || val > sched_domain_level_max + 1) return -EINVAL; #endif diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 6735ac36b718..a3b4b55d2e2e 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -172,6 +172,33 @@ char kdb_getchar(void) unreachable(); } +/** + * kdb_position_cursor() - Place cursor in the correct horizontal position + * @prompt: Nil-terminated string containing the prompt string + * @buffer: Nil-terminated string containing the entire command line + * @cp: Cursor position, pointer the character in buffer where the cursor + * should be positioned. + * + * The cursor is positioned by sending a carriage-return and then printing + * the content of the line until we reach the correct cursor position. + * + * There is some additional fine detail here. + * + * Firstly, even though kdb_printf() will correctly format zero-width fields + * we want the second call to kdb_printf() to be conditional. That keeps things + * a little cleaner when LOGGING=1. + * + * Secondly, we can't combine everything into one call to kdb_printf() since + * that renders into a fixed length buffer and the combined print could result + * in unwanted truncation. + */ +static void kdb_position_cursor(char *prompt, char *buffer, char *cp) +{ + kdb_printf("\r%s", kdb_prompt_str); + if (cp > buffer) + kdb_printf("%.*s", (int)(cp - buffer), buffer); +} + /* * kdb_read * @@ -200,7 +227,6 @@ static char *kdb_read(char *buffer, size_t bufsize) * and null byte */ char *lastchar; char *p_tmp; - char tmp; static char tmpbuffer[CMD_BUFLEN]; int len = strlen(buffer); int len_tmp; @@ -237,12 +263,8 @@ poll_again: } *(--lastchar) = '\0'; --cp; - kdb_printf("\b%s \r", cp); - tmp = *cp; - *cp = '\0'; - kdb_printf(kdb_prompt_str); - kdb_printf("%s", buffer); - *cp = tmp; + kdb_printf("\b%s ", cp); + kdb_position_cursor(kdb_prompt_str, buffer, cp); } break; case 13: /* enter */ @@ -259,19 +281,14 @@ poll_again: memcpy(tmpbuffer, cp+1, lastchar - cp - 1); memcpy(cp, tmpbuffer, lastchar - cp - 1); *(--lastchar) = '\0'; - kdb_printf("%s \r", cp); - tmp = *cp; - *cp = '\0'; - kdb_printf(kdb_prompt_str); - kdb_printf("%s", buffer); - *cp = tmp; + kdb_printf("%s ", cp); + kdb_position_cursor(kdb_prompt_str, buffer, cp); } break; case 1: /* Home */ if (cp > buffer) { - kdb_printf("\r"); - kdb_printf(kdb_prompt_str); cp = buffer; + kdb_position_cursor(kdb_prompt_str, buffer, cp); } break; case 5: /* End */ @@ -287,11 +304,10 @@ poll_again: } break; case 14: /* Down */ - memset(tmpbuffer, ' ', - strlen(kdb_prompt_str) + (lastchar-buffer)); - *(tmpbuffer+strlen(kdb_prompt_str) + - (lastchar-buffer)) = '\0'; - kdb_printf("\r%s\r", tmpbuffer); + case 16: /* Up */ + kdb_printf("\r%*c\r", + (int)(strlen(kdb_prompt_str) + (lastchar - buffer)), + ' '); *lastchar = (char)key; *(lastchar+1) = '\0'; return lastchar; @@ -301,15 +317,6 @@ poll_again: ++cp; } break; - case 16: /* Up */ - memset(tmpbuffer, ' ', - strlen(kdb_prompt_str) + (lastchar-buffer)); - *(tmpbuffer+strlen(kdb_prompt_str) + - (lastchar-buffer)) = '\0'; - kdb_printf("\r%s\r", tmpbuffer); - *lastchar = (char)key; - *(lastchar+1) = '\0'; - return lastchar; case 9: /* Tab */ if (tab < 2) ++tab; @@ -353,15 +360,25 @@ poll_again: kdb_printf("\n"); kdb_printf(kdb_prompt_str); kdb_printf("%s", buffer); + if (cp != lastchar) + kdb_position_cursor(kdb_prompt_str, buffer, cp); } else if (tab != 2 && count > 0) { - len_tmp = strlen(p_tmp); - strncpy(p_tmp+len_tmp, cp, lastchar-cp+1); - len_tmp = strlen(p_tmp); - strncpy(cp, p_tmp+len, len_tmp-len + 1); - len = len_tmp - len; - kdb_printf("%s", cp); - cp += len; - lastchar += len; + /* How many new characters do we want from tmpbuffer? */ + len_tmp = strlen(p_tmp) - len; + if (lastchar + len_tmp >= bufend) + len_tmp = bufend - lastchar; + + if (len_tmp) { + /* + 1 ensures the '\0' is memmove'd */ + memmove(cp+len_tmp, cp, (lastchar-cp) + 1); + memcpy(cp, p_tmp+len, len_tmp); + kdb_printf("%s", cp); + cp += len_tmp; + lastchar += len_tmp; + if (cp != lastchar) + kdb_position_cursor(kdb_prompt_str, + buffer, cp); + } } kdb_nextline = 1; /* reset output line number */ break; @@ -372,13 +389,9 @@ poll_again: memcpy(cp+1, tmpbuffer, lastchar - cp); *++lastchar = '\0'; *cp = key; - kdb_printf("%s\r", cp); + kdb_printf("%s", cp); ++cp; - tmp = *cp; - *cp = '\0'; - kdb_printf(kdb_prompt_str); - kdb_printf("%s", buffer); - *cp = tmp; + kdb_position_cursor(kdb_prompt_str, buffer, cp); } else { *++lastchar = '\0'; *cp++ = key; diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index 9b9af1bd6be3..b7f8bb7a1e5c 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -124,7 +124,6 @@ static int do_map_benchmark(struct map_benchmark_data *map) struct task_struct **tsk; int threads = map->bparam.threads; int node = map->bparam.node; - const cpumask_t *cpu_mask = cpumask_of_node(node); u64 loops; int ret = 0; int i; @@ -145,7 +144,7 @@ static int do_map_benchmark(struct map_benchmark_data *map) } if (node != NUMA_NO_NODE) - kthread_bind_mask(tsk[i], cpu_mask); + kthread_bind_mask(tsk[i], cpumask_of_node(node)); } /* clear the old value in the previous benchmark */ @@ -231,7 +230,8 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, } if (map->bparam.node != NUMA_NO_NODE && - !node_possible(map->bparam.node)) { + (map->bparam.node < 0 || map->bparam.node >= MAX_NUMNODES || + !node_possible(map->bparam.node))) { pr_err("invalid numa node\n"); return -EINVAL; } diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 39a41c56ad4f..24fd9db84cfb 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -70,6 +70,14 @@ static bool migrate_one_irq(struct irq_desc *desc) } /* + * Complete an eventually pending irq move cleanup. If this + * interrupt was moved in hard irq context, then the vectors need + * to be cleaned up. It can't wait until this interrupt actually + * happens and this CPU was involved. + */ + irq_force_complete_move(desc); + + /* * No move required, if: * - Interrupt is per cpu * - Interrupt is not started @@ -88,14 +96,6 @@ static bool migrate_one_irq(struct irq_desc *desc) } /* - * Complete an eventually pending irq move cleanup. If this - * interrupt was moved in hard irq context, then the vectors need - * to be cleaned up. It can't wait until this interrupt actually - * happens and this CPU was involved. - */ - irq_force_complete_move(desc); - - /* * If there is a setaffinity pending, then try to reuse the pending * mask, so the last change of the affinity does not get lost. If * there is no move pending or the pending mask does not contain diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 25b8ea91168e..b43da6201b9a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10828,7 +10828,7 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of, { struct task_group *tg = css_tg(of_css(of)); u64 period = tg_get_cfs_period(tg); - u64 burst = tg_get_cfs_burst(tg); + u64 burst = tg->cfs_bandwidth.burst; u64 quota; int ret; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4a1393405a6f..94fcd585eb7f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5746,21 +5746,41 @@ static inline unsigned long cpu_util(int cpu); static inline bool cpu_overutilized(int cpu) { - unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); - unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + unsigned long rq_util_min, rq_util_max; + + if (!sched_energy_enabled()) + return false; + + rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); + rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); return !util_fits_cpu(cpu_util(cpu), rq_util_min, rq_util_max, cpu); } -static inline void update_overutilized_status(struct rq *rq) +static inline void set_rd_overutilized_status(struct root_domain *rd, + unsigned int status) { - if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) { - WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED); - trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED); - } + if (!sched_energy_enabled()) + return; + + WRITE_ONCE(rd->overutilized, status); + trace_sched_overutilized_tp(rd, !!status); +} + +static inline void check_update_overutilized_status(struct rq *rq) +{ + /* + * overutilized field is used for load balancing decisions only + * if energy aware scheduler is being used + */ + if (!sched_energy_enabled()) + return; + + if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) + set_rd_overutilized_status(rq->rd, SG_OVERUTILIZED); } #else -static inline void update_overutilized_status(struct rq *rq) { } +static inline void check_update_overutilized_status(struct rq *rq) { } #endif /* Runqueue only has SCHED_IDLE tasks enqueued */ @@ -5868,7 +5888,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) * and the following generally works well enough in practice. */ if (!task_new) - update_overutilized_status(rq); + check_update_overutilized_status(rq); enqueue_throttle: if (cfs_bandwidth_used()) { @@ -9577,19 +9597,14 @@ next_group: env->fbq_type = fbq_classify_group(&sds->busiest_stat); if (!env->sd->parent) { - struct root_domain *rd = env->dst_rq->rd; - /* update overload indicator if we are at root domain */ - WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD); + WRITE_ONCE(env->dst_rq->rd->overload, sg_status & SG_OVERLOAD); /* Update over-utilization (tipping point, U >= 0) indicator */ - WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED); - trace_sched_overutilized_tp(rd, sg_status & SG_OVERUTILIZED); + set_rd_overutilized_status(env->dst_rq->rd, + sg_status & SG_OVERUTILIZED); } else if (sg_status & SG_OVERUTILIZED) { - struct root_domain *rd = env->dst_rq->rd; - - WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED); - trace_sched_overutilized_tp(rd, SG_OVERUTILIZED); + set_rd_overutilized_status(env->dst_rq->rd, SG_OVERUTILIZED); } update_idle_cpu_scan(env, sum_util); @@ -11460,7 +11475,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) task_tick_numa(rq, curr); update_misfit_status(curr, rq); - update_overutilized_status(task_rq(curr)); + check_update_overutilized_status(task_rq(curr)); task_tick_core(rq, curr); } diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 4e8698e62f07..8c82ca3aa652 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1405,7 +1405,7 @@ static void set_domain_attribute(struct sched_domain *sd, } else request = attr->relax_domain_level; - if (sd->level > request) { + if (sd->level >= request) { /* Turn off idle balance on this domain: */ sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 41f470929e99..dc60f0c66a25 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -512,7 +512,7 @@ static inline bool lockdep_softirq_start(void) { return false; } static inline void lockdep_softirq_end(bool in_hardirq) { } #endif -asmlinkage __visible void __softirq_entry __do_softirq(void) +static void handle_softirqs(bool ksirqd) { unsigned long end = jiffies + MAX_SOFTIRQ_TIME; unsigned long old_flags = current->flags; @@ -567,8 +567,7 @@ restart: pending >>= softirq_bit; } - if (!IS_ENABLED(CONFIG_PREEMPT_RT) && - __this_cpu_read(ksoftirqd) == current) + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && ksirqd) rcu_softirq_qs(); local_irq_disable(); @@ -588,6 +587,11 @@ restart: current_restore_flags(old_flags, PF_MEMALLOC); } +asmlinkage __visible void __softirq_entry __do_softirq(void) +{ + handle_softirqs(false); +} + /** * irq_enter_rcu - Enter an interrupt context with RCU watching */ @@ -918,7 +922,7 @@ static void run_ksoftirqd(unsigned int cpu) * We can safely run softirq on inline stack, as we are not deep * in the task stack here. */ - __do_softirq(); + handle_softirqs(true); ksoftirqd_run_end(); cond_resched(); return; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2ec1473146ca..f9f0c198cb43 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1568,6 +1568,11 @@ static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, * * As a safety measure we check to make sure the data pages have not * been corrupted. + * + * Callers of this function need to guarantee that the list of pages doesn't get + * modified during the check. In particular, if it's possible that the function + * is invoked with concurrent readers which can swap in a new reader page then + * the caller should take cpu_buffer->reader_lock. */ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) { @@ -2289,8 +2294,12 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, */ synchronize_rcu(); for_each_buffer_cpu(buffer, cpu) { + unsigned long flags; + cpu_buffer = buffer->buffers[cpu]; + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); rb_check_pages(cpu_buffer); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } atomic_dec(&buffer->record_disabled); } |