From 01341fbd0d8d4e717fc1231cdffe00343088ce0b Mon Sep 17 00:00:00 2001 From: Yunfeng Ye Date: Thu, 19 Nov 2020 14:21:25 +0800 Subject: workqueue: Kick a worker based on the actual activation of delayed works In realtime scenario, We do not want to have interference on the isolated cpu cores. but when invoking alloc_workqueue() for percpu wq on the housekeeping cpu, it kick a kworker on the isolated cpu. alloc_workqueue pwq_adjust_max_active wake_up_worker The comment in pwq_adjust_max_active() said: "Need to kick a worker after thawed or an unbound wq's max_active is bumped" So it is unnecessary to kick a kworker for percpu's wq when invoking alloc_workqueue(). this patch only kick a worker based on the actual activation of delayed works. Signed-off-by: Yunfeng Ye Reviewed-by: Lai Jiangshan Signed-off-by: Tejun Heo --- kernel/workqueue.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 437935e7a199..0695c7895c89 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3728,17 +3728,24 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq) * is updated and visible. */ if (!freezable || !workqueue_freezing) { + bool kick = false; + pwq->max_active = wq->saved_max_active; while (!list_empty(&pwq->delayed_works) && - pwq->nr_active < pwq->max_active) + pwq->nr_active < pwq->max_active) { pwq_activate_first_delayed(pwq); + kick = true; + } /* * Need to kick a worker after thawed or an unbound wq's - * max_active is bumped. It's a slow path. Do it always. + * max_active is bumped. In realtime scenarios, always kicking a + * worker will cause interference on the isolated cpu cores, so + * let's kick iff work items were activated. */ - wake_up_worker(pwq->pool); + if (kick) + wake_up_worker(pwq->pool); } else { pwq->max_active = 0; } -- cgit v1.2.3 From 58315c96651152b9f438e5e56c910994234e2c7a Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Mon, 9 Nov 2020 16:01:11 +0530 Subject: kernel: cgroup: Mundane spelling fixes throughout the file Few spelling fixes throughout the file. Signed-off-by: Bhaskar Chowdhury Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e41c21819ba0..690f477d537c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -244,7 +244,7 @@ bool cgroup_ssid_enabled(int ssid) * * The default hierarchy is the v2 interface of cgroup and this function * can be used to test whether a cgroup is on the default hierarchy for - * cases where a subsystem should behave differnetly depending on the + * cases where a subsystem should behave differently depending on the * interface version. * * List of changed behaviors: @@ -262,7 +262,7 @@ bool cgroup_ssid_enabled(int ssid) * "cgroup.procs" instead. * * - "cgroup.procs" is not sorted. pids will be unique unless they got - * recycled inbetween reads. + * recycled in-between reads. * * - "release_agent" and "notify_on_release" are removed. Replacement * notification mechanism will be implemented. @@ -345,7 +345,7 @@ static bool cgroup_is_mixable(struct cgroup *cgrp) return !cgroup_parent(cgrp); } -/* can @cgrp become a thread root? should always be true for a thread root */ +/* can @cgrp become a thread root? Should always be true for a thread root */ static bool cgroup_can_be_thread_root(struct cgroup *cgrp) { /* mixables don't care */ @@ -530,7 +530,7 @@ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, * the root css is returned, so this function always returns a valid css. * * The returned css is not guaranteed to be online, and therefore it is the - * callers responsiblity to tryget a reference for it. + * callers responsibility to try get a reference for it. */ struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) @@ -702,7 +702,7 @@ EXPORT_SYMBOL_GPL(of_css); ; \ else -/* walk live descendants in preorder */ +/* walk live descendants in pre order */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ @@ -936,7 +936,7 @@ void put_css_set_locked(struct css_set *cset) WARN_ON_ONCE(!list_empty(&cset->threaded_csets)); - /* This css_set is dead. unlink it and release cgroup and css refs */ + /* This css_set is dead. Unlink it and release cgroup and css refs */ for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); css_put(cset->subsys[ssid]); @@ -1061,7 +1061,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset, /* * Build the set of subsystem state objects that we want to see in the - * new css_set. while subsystems can change globally, the entries here + * new css_set. While subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { @@ -1151,7 +1151,7 @@ static void link_css_set(struct list_head *tmp_links, struct css_set *cset, /* * Always add links to the tail of the lists so that the lists are - * in choronological order. + * in chronological order. */ list_move_tail(&link->cset_link, &cgrp->cset_links); list_add_tail(&link->cgrp_link, &cset->cgrp_links); @@ -4137,7 +4137,7 @@ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, * implies that if we observe !CSS_RELEASED on @pos in this RCU * critical section, the one pointed to by its next pointer is * guaranteed to not have finished its RCU grace period even if we - * have dropped rcu_read_lock() inbetween iterations. + * have dropped rcu_read_lock() in-between iterations. * * If @pos has CSS_RELEASED set, its next pointer can't be * dereferenced; however, as each css is given a monotonically @@ -4385,7 +4385,7 @@ static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) } /** - * css_task_iter_advance_css_set - advance a task itererator to the next css_set + * css_task_iter_advance_css_set - advance a task iterator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. @@ -6320,7 +6320,7 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on - * success, ERR_PTR(-ENOENT) if @path doens't exist and ERR_PTR(-ENOTDIR) + * success, ERR_PTR(-ENOENT) if @path doesn't exist and ERR_PTR(-ENOTDIR) * if @path points to a non-directory. */ struct cgroup *cgroup_get_from_path(const char *path) -- cgit v1.2.3 From 5a7b5f32c5aa628841502d19a813c633ff6ecbe4 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Fri, 6 Nov 2020 22:47:40 +0800 Subject: cgroup/cgroup.c: replace 'of->kn->priv' with of_cft() we have supplied the inline function: of_cft() in cgroup.h. So replace the direct use 'of->kn->priv' with inline func of_cft(), which is more readable. Signed-off-by: Hui Su Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 690f477d537c..385f80cf7d0c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3657,7 +3657,7 @@ static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, static int cgroup_file_open(struct kernfs_open_file *of) { - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of); if (cft->open) return cft->open(of); @@ -3666,7 +3666,7 @@ static int cgroup_file_open(struct kernfs_open_file *of) static void cgroup_file_release(struct kernfs_open_file *of) { - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of); if (cft->release) cft->release(of); @@ -3677,7 +3677,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, { struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup *cgrp = of->kn->parent->priv; - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; @@ -3727,7 +3727,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) { - struct cftype *cft = of->kn->priv; + struct cftype *cft = of_cft(of); if (cft->poll) return cft->poll(of, pt); -- cgit v1.2.3 From 1b04fa9900263b4e217ca2509fd778b32c2b4eb2 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Wed, 9 Dec 2020 21:27:31 +0100 Subject: rcu-tasks: Move RCU-tasks initialization to before early_initcall() PowerPC testing encountered boot failures due to RCU Tasks not being fully initialized until core_initcall() time. This commit therefore initializes RCU Tasks (along with Rude RCU and RCU Tasks Trace) just before early_initcall() time, thus allowing waiting on RCU Tasks grace periods from early_initcall() handlers. Link: https://lore.kernel.org/rcu/87eekfh80a.fsf@dja-thinkpad.axtens.net/ Fixes: 36dadef23fcc ("kprobes: Init kprobes in early_initcall") Tested-by: Daniel Axtens Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 6 ++++++ init/main.c | 1 + kernel/rcu/tasks.h | 25 +++++++++++++++++++++---- 3 files changed, 28 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 6cdd0152c253..5c119d6cecf1 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -86,6 +86,12 @@ void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); +#ifdef CONFIG_TASKS_RCU_GENERIC +void rcu_init_tasks_generic(void); +#else +static inline void rcu_init_tasks_generic(void) { } +#endif + #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); diff --git a/init/main.c b/init/main.c index 32b2a8affafd..9d964511fe0c 100644 --- a/init/main.c +++ b/init/main.c @@ -1512,6 +1512,7 @@ static noinline void __init kernel_init_freeable(void) init_mm_internals(); + rcu_init_tasks_generic(); do_pre_smp_initcalls(); lockup_detector_init(); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index d5d9f2d03e8a..73bbe792fe1e 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -241,7 +241,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) } } -/* Spawn RCU-tasks grace-period kthread, e.g., at core_initcall() time. */ +/* Spawn RCU-tasks grace-period kthread. */ static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp) { struct task_struct *t; @@ -569,7 +569,6 @@ static int __init rcu_spawn_tasks_kthread(void) rcu_spawn_tasks_kthread_generic(&rcu_tasks); return 0; } -core_initcall(rcu_spawn_tasks_kthread); #ifndef CONFIG_TINY_RCU static void show_rcu_tasks_classic_gp_kthread(void) @@ -697,7 +696,6 @@ static int __init rcu_spawn_tasks_rude_kthread(void) rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude); return 0; } -core_initcall(rcu_spawn_tasks_rude_kthread); #ifndef CONFIG_TINY_RCU static void show_rcu_tasks_rude_gp_kthread(void) @@ -975,6 +973,11 @@ static void rcu_tasks_trace_pregp_step(void) static void rcu_tasks_trace_pertask(struct task_struct *t, struct list_head *hop) { + // During early boot when there is only the one boot CPU, there + // is no idle task for the other CPUs. Just return. + if (unlikely(t == NULL)) + return; + WRITE_ONCE(t->trc_reader_special.b.need_qs, false); WRITE_ONCE(t->trc_reader_checked, false); t->trc_ipi_to_cpu = -1; @@ -1200,7 +1203,6 @@ static int __init rcu_spawn_tasks_trace_kthread(void) rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace); return 0; } -core_initcall(rcu_spawn_tasks_trace_kthread); #ifndef CONFIG_TINY_RCU static void show_rcu_tasks_trace_gp_kthread(void) @@ -1229,6 +1231,21 @@ void show_rcu_tasks_gp_kthreads(void) } #endif /* #ifndef CONFIG_TINY_RCU */ +void __init rcu_init_tasks_generic(void) +{ +#ifdef CONFIG_TASKS_RCU + rcu_spawn_tasks_kthread(); +#endif + +#ifdef CONFIG_TASKS_RUDE_RCU + rcu_spawn_tasks_rude_kthread(); +#endif + +#ifdef CONFIG_TASKS_TRACE_RCU + rcu_spawn_tasks_trace_kthread(); +#endif +} + #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ static inline void rcu_tasks_bootup_oddness(void) {} void show_rcu_tasks_gp_kthreads(void) {} -- cgit v1.2.3 From 2d18e54dd8662442ef5898c6bdadeaf90b3cebbc Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Thu, 10 Dec 2020 09:29:43 +0800 Subject: cgroup: Fix memory leak when parsing multiple source parameters A memory leak is found in cgroup1_parse_param() when multiple source parameters overwrite fc->source in the fs_context struct without free. unreferenced object 0xffff888100d930e0 (size 16): comm "mount", pid 520, jiffies 4303326831 (age 152.783s) hex dump (first 16 bytes): 74 65 73 74 6c 65 61 6b 00 00 00 00 00 00 00 00 testleak........ backtrace: [<000000003e5023ec>] kmemdup_nul+0x2d/0xa0 [<00000000377dbdaa>] vfs_parse_fs_string+0xc0/0x150 [<00000000cb2b4882>] generic_parse_monolithic+0x15a/0x1d0 [<000000000f750198>] path_mount+0xee1/0x1820 [<0000000004756de2>] do_mount+0xea/0x100 [<0000000094cafb0a>] __x64_sys_mount+0x14b/0x1f0 Fix this bug by permitting a single source parameter and rejecting with an error all subsequent ones. Fixes: 8d2451f4994f ("cgroup1: switch to option-by-option parsing") Reported-by: Hulk Robot Signed-off-by: Qinglang Miao Reviewed-by: Zefan Li Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup-v1.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 191c329e482a..32596fdbcd5b 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -908,6 +908,8 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { if (strcmp(param->key, "source") == 0) { + if (fc->source) + return invalf(fc, "Multiple sources not supported"); fc->source = param->string; param->string = NULL; return 0; -- cgit v1.2.3 From d467d80dc399ba77875d647f2f37b7d1a70d94c2 Mon Sep 17 00:00:00 2001 From: Tian Tao Date: Wed, 16 Dec 2020 10:47:15 +0800 Subject: bpf: Remove unused including Remove including that don't need it. Signed-off-by: Tian Tao Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/1608086835-54523-1-git-send-email-tiantao6@hisilicon.com --- kernel/bpf/syscall.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 287be337d5f6..bb2700ec5bf3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From e7e518053c267bb6be3799520d9f4a34c7264a2e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 21 Dec 2020 11:25:06 -0800 Subject: bpf: Add schedule point in htab_init_buckets() We noticed that with a LOCKDEP enabled kernel, allocating a hash table with 65536 buckets would use more than 60ms. htab_init_buckets() runs from process context, it is safe to schedule to avoid latency spikes. Fixes: c50eb518e262 ("bpf: Use separate lockdep class for each hashtab") Reported-by: John Sperbeck Signed-off-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201221192506.707584-1-eric.dumazet@gmail.com --- kernel/bpf/hashtab.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 7e848200cd26..c1ac7f964bc9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -152,6 +152,7 @@ static void htab_init_buckets(struct bpf_htab *htab) lockdep_set_class(&htab->buckets[i].lock, &htab->lockdep_key); } + cond_resched(); } } -- cgit v1.2.3 From 69ca310f34168eae0ada434796bfc22fb4a0fa26 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Fri, 18 Dec 2020 10:50:30 -0800 Subject: bpf: Save correct stopping point in file seq iteration On some systems, some variant of the following splat is repeatedly seen. The common factor in all traces seems to be the entry point to task_file_seq_next(). With the patch, all warnings go away. rcu: INFO: rcu_sched self-detected stall on CPU rcu: \x0926-....: (20992 ticks this GP) idle=d7e/1/0x4000000000000002 softirq=81556231/81556231 fqs=4876 \x09(t=21033 jiffies g=159148529 q=223125) NMI backtrace for cpu 26 CPU: 26 PID: 2015853 Comm: bpftool Kdump: loaded Not tainted 5.6.13-0_fbk4_3876_gd8d1f9bf80bb #1 Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A12 10/08/2018 Call Trace: dump_stack+0x50/0x70 nmi_cpu_backtrace.cold.6+0x13/0x50 ? lapic_can_unplug_cpu.cold.30+0x40/0x40 nmi_trigger_cpumask_backtrace+0xba/0xca rcu_dump_cpu_stacks+0x99/0xc7 rcu_sched_clock_irq.cold.90+0x1b4/0x3aa ? tick_sched_do_timer+0x60/0x60 update_process_times+0x24/0x50 tick_sched_timer+0x37/0x70 __hrtimer_run_queues+0xfe/0x270 hrtimer_interrupt+0xf4/0x210 smp_apic_timer_interrupt+0x5e/0x120 apic_timer_interrupt+0xf/0x20 RIP: 0010:get_pid_task+0x38/0x80 Code: 89 f6 48 8d 44 f7 08 48 8b 00 48 85 c0 74 2b 48 83 c6 55 48 c1 e6 04 48 29 f0 74 19 48 8d 78 20 ba 01 00 00 00 f0 0f c1 50 20 <85> d2 74 27 78 11 83 c2 01 78 0c 48 83 c4 08 c3 31 c0 48 83 c4 08 RSP: 0018:ffffc9000d293dc8 EFLAGS: 00000202 ORIG_RAX: ffffffffffffff13 RAX: ffff888637c05600 RBX: ffffc9000d293e0c RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000550 RDI: ffff888637c05620 RBP: ffffffff8284eb80 R08: ffff88831341d300 R09: ffff88822ffd8248 R10: ffff88822ffd82d0 R11: 00000000003a93c0 R12: 0000000000000001 R13: 00000000ffffffff R14: ffff88831341d300 R15: 0000000000000000 ? find_ge_pid+0x1b/0x20 task_seq_get_next+0x52/0xc0 task_file_seq_get_next+0x159/0x220 task_file_seq_next+0x4f/0xa0 bpf_seq_read+0x159/0x390 vfs_read+0x8a/0x140 ksys_read+0x59/0xd0 do_syscall_64+0x42/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f95ae73e76e Code: Bad RIP value. RSP: 002b:00007ffc02c1dbf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 000000000170faa0 RCX: 00007f95ae73e76e RDX: 0000000000001000 RSI: 00007ffc02c1dc30 RDI: 0000000000000007 RBP: 00007ffc02c1ec70 R08: 0000000000000005 R09: 0000000000000006 R10: fffffffffffff20b R11: 0000000000000246 R12: 00000000019112a0 R13: 0000000000000000 R14: 0000000000000007 R15: 00000000004283c0 If unable to obtain the file structure for the current task, proceed to the next task number after the one returned from task_seq_get_next(), instead of the next task number from the original iterator. Also, save the stopping task number from task_seq_get_next() on failure in case of restarts. Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets") Signed-off-by: Jonathan Lemon Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201218185032.2464558-2-jonathan.lemon@gmail.com --- kernel/bpf/task_iter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 0458a40edf10..8033ab19138a 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -158,13 +158,14 @@ again: if (!curr_task) { info->task = NULL; info->files = NULL; + info->tid = curr_tid; return NULL; } curr_files = get_files_struct(curr_task); if (!curr_files) { put_task_struct(curr_task); - curr_tid = ++(info->tid); + curr_tid = curr_tid + 1; info->fd = 0; goto again; } -- cgit v1.2.3 From a61daaf351da7c8493f2586437617d60c24350b0 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Fri, 18 Dec 2020 10:50:31 -0800 Subject: bpf: Use thread_group_leader() Instead of directly comparing task->tgid and task->pid, use the thread_group_leader() helper. This helps with readability, and there should be no functional change. Signed-off-by: Jonathan Lemon Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201218185032.2464558-3-jonathan.lemon@gmail.com --- kernel/bpf/task_iter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 8033ab19138a..dc4007f1843b 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -37,7 +37,7 @@ retry: if (!task) { ++*tid; goto retry; - } else if (skip_if_dup_files && task->tgid != task->pid && + } else if (skip_if_dup_files && !thread_group_leader(task) && task->files == task->group_leader->files) { put_task_struct(task); task = NULL; -- cgit v1.2.3 From b1b6b5a30dce872f500dc43f067cba8e7f86fc7d Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 30 Dec 2020 21:34:16 +0000 Subject: kernel/io_uring: cancel io_uring before task works For cancelling io_uring requests it needs either to be able to run currently enqueued task_works or having it shut down by that moment. Otherwise io_uring_cancel_files() may be waiting for requests that won't ever complete. Go with the first way and do cancellations before setting PF_EXITING and so before putting the task_work infrastructure into a transition state where task_work_run() would better not be called. Cc: stable@vger.kernel.org # 5.5+ Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/file.c | 2 -- kernel/exit.c | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/fs/file.c b/fs/file.c index c0b60961c672..dab120b71e44 100644 --- a/fs/file.c +++ b/fs/file.c @@ -21,7 +21,6 @@ #include #include #include -#include unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; @@ -428,7 +427,6 @@ void exit_files(struct task_struct *tsk) struct files_struct * files = tsk->files; if (files) { - io_uring_files_cancel(files); task_lock(tsk); tsk->files = NULL; task_unlock(tsk); diff --git a/kernel/exit.c b/kernel/exit.c index 3594291a8542..04029e35e69a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include @@ -776,6 +777,7 @@ void __noreturn do_exit(long code) schedule(); } + io_uring_files_cancel(tsk->files); exit_signals(tsk); /* sets PF_EXITING */ /* sync mm's RSS info before statistics gathering */ -- cgit v1.2.3 From 04901aab40ea3779f6fc6383ef74d8e130e817bf Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 30 Dec 2020 21:24:18 -0800 Subject: bpf: Fix a task_iter bug caused by a merge conflict resolution Latest bpf tree has a bug for bpf_iter selftest: $ ./test_progs -n 4/25 test_bpf_sk_storage_get:PASS:bpf_iter_bpf_sk_storage_helpers__open_and_load 0 nsec test_bpf_sk_storage_get:PASS:socket 0 nsec ... do_dummy_read:PASS:read 0 nsec test_bpf_sk_storage_get:FAIL:bpf_map_lookup_elem map value wasn't set correctly (expected 1792, got -1, err=0) #4/25 bpf_sk_storage_get:FAIL #4 bpf_iter:FAIL Summary: 0/0 PASSED, 0 SKIPPED, 2 FAILED When doing merge conflict resolution, Commit 4bfc4714849d missed to save curr_task to seq_file private data. The task pointer in seq_file private data is passed to bpf program. This caused NULL-pointer task passed to bpf program which will immediately return upon checking whether task pointer is NULL. This patch added back the assignment of curr_task to seq_file private data and fixed the issue. Fixes: 4bfc4714849d ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf") Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20201231052418.577024-1-yhs@fb.com --- kernel/bpf/task_iter.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 3efe38191d1c..175b7b42bfc4 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -159,6 +159,7 @@ again: } /* set info->task and info->tid */ + info->task = curr_task; if (curr_tid == info->tid) { curr_fd = info->fd; } else { -- cgit v1.2.3 From 00b8c557d096f0930d5c07df618223d3d06902d6 Mon Sep 17 00:00:00 2001 From: Matthias Maennich Date: Wed, 6 Jan 2021 15:52:01 +0000 Subject: staging: ION: remove some references to CONFIG_ION With commit e722a295cf49 ("staging: ion: remove from the tree"), ION and its corresponding config CONFIG_ION is gone. Remove stale references from drivers/staging/media/atomisp/pci and from the recommended Android kernel config. Fixes: e722a295cf49 ("staging: ion: remove from the tree") Cc: Hridya Valsaraju Cc: Rob Herring Cc: linux-media@vger.kernel.org Cc: devel@driverdev.osuosl.org Signed-off-by: Matthias Maennich Link: https://lore.kernel.org/r/20210106155201.2845319-1-maennich@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/media/atomisp/pci/atomisp_subdev.c | 20 -------------------- kernel/configs/android-recommended.config | 1 - 2 files changed, 21 deletions(-) (limited to 'kernel') diff --git a/drivers/staging/media/atomisp/pci/atomisp_subdev.c b/drivers/staging/media/atomisp/pci/atomisp_subdev.c index 52b9fb18c87f..b666cb23e5ca 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_subdev.c +++ b/drivers/staging/media/atomisp/pci/atomisp_subdev.c @@ -1062,26 +1062,6 @@ static const struct v4l2_ctrl_config ctrl_select_isp_version = { .def = 0, }; -#if 0 /* #ifdef CONFIG_ION */ -/* - * Control for ISP ion device fd - * - * userspace will open ion device and pass the fd to kernel. - * this fd will be used to map shared fd to buffer. - */ -/* V4L2_CID_ATOMISP_ION_DEVICE_FD is not defined */ -static const struct v4l2_ctrl_config ctrl_ion_dev_fd = { - .ops = &ctrl_ops, - .id = V4L2_CID_ATOMISP_ION_DEVICE_FD, - .type = V4L2_CTRL_TYPE_INTEGER, - .name = "Ion Device Fd", - .min = -1, - .max = 1024, - .step = 1, - .def = ION_FD_UNSET -}; -#endif - static void atomisp_init_subdev_pipe(struct atomisp_sub_device *asd, struct atomisp_video_pipe *pipe, enum v4l2_buf_type buf_type) { diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config index 53d688bdd894..eb0029c9a6a6 100644 --- a/kernel/configs/android-recommended.config +++ b/kernel/configs/android-recommended.config @@ -81,7 +81,6 @@ CONFIG_INPUT_JOYSTICK=y CONFIG_INPUT_MISC=y CONFIG_INPUT_TABLET=y CONFIG_INPUT_UINPUT=y -CONFIG_ION=y CONFIG_JOYSTICK_XPAD=y CONFIG_JOYSTICK_XPAD_FF=y CONFIG_JOYSTICK_XPAD_LEDS=y -- cgit v1.2.3 From 35d0b389f3b23439ad15b610d6e43fc72fc75779 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 5 Jan 2021 11:32:43 -0700 Subject: task_work: unconditionally run task_work from get_signal() Song reported a boot regression in a kvm image with 5.11-rc, and bisected it down to the below patch. Debugging this issue, turns out that the boot stalled when a task is waiting on a pipe being released. As we no longer run task_work from get_signal() unless it's queued with TWA_SIGNAL, the task goes idle without running the task_work. This prevents ->release() from being called on the pipe, which another boot task is waiting on. For now, re-instate the unconditional task_work run from get_signal(). For 5.12, we'll collapse TWA_RESUME and TWA_SIGNAL, as it no longer makes sense to have a distinction between the two. This will turn task_work notification into a simple boolean, whether to notify or not. Fixes: 98b89b649fce ("signal: kill JOBCTL_TASK_WORK") Reported-by: Song Liu Tested-by: John Stultz Tested-by: Douglas Anderson Tested-by: Sedat Dilek # LLVM/Clang version 11.0.1 Signed-off-by: Jens Axboe --- kernel/signal.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index 5736c55aaa1a..6b9c431da08f 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2550,6 +2550,9 @@ bool get_signal(struct ksignal *ksig) struct signal_struct *signal = current->signal; int signr; + if (unlikely(current->task_works)) + task_work_run(); + /* * For non-generic architectures, check for TIF_NOTIFY_SIGNAL so * that the arch handlers don't all have to do it. If we get here -- cgit v1.2.3 From 7bb83f6fc4ee84e95d0ac0d14452c2619fb3fe70 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 8 Jan 2021 13:19:38 +0900 Subject: tracing/kprobes: Do the notrace functions check without kprobes on ftrace Enable the notrace function check on the architecture which doesn't support kprobes on ftrace but support dynamic ftrace. This notrace function check is not only for the kprobes on ftrace but also sw-breakpoint based kprobes. Thus there is no reason to limit this check for the arch which supports kprobes on ftrace. This also changes the dependency of Kconfig. Because kprobe event uses the function tracer's address list for identifying notrace function, if the CONFIG_DYNAMIC_FTRACE=n, it can not check whether the target function is notrace or not. Link: https://lkml.kernel.org/r/20210105065730.2634785-1-naveen.n.rao@linux.vnet.ibm.com Link: https://lkml.kernel.org/r/161007957862.114704.4512260007555399463.stgit@devnote2 Cc: stable@vger.kernel.org Fixes: 45408c4f92506 ("tracing: kprobes: Prohibit probing on notrace function") Acked-by: Naveen N. Rao Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/Kconfig | 2 +- kernel/trace/trace_kprobe.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d5a19413d4f8..c1a62ae7e812 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -538,7 +538,7 @@ config KPROBE_EVENTS config KPROBE_EVENTS_ON_NOTRACE bool "Do NOT protect notrace function from kprobe events" depends on KPROBE_EVENTS - depends on KPROBES_ON_FTRACE + depends on DYNAMIC_FTRACE default n help This is only for the developers who want to debug ftrace itself diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 9c31f42245e9..e6fba1798771 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -434,7 +434,7 @@ static int disable_trace_kprobe(struct trace_event_call *call, return 0; } -#if defined(CONFIG_KPROBES_ON_FTRACE) && \ +#if defined(CONFIG_DYNAMIC_FTRACE) && \ !defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE) static bool __within_notrace_func(unsigned long addr) { -- cgit v1.2.3