From 28b89b9e6f7b6c8fef7b3af39828722bca20cfee Mon Sep 17 00:00:00 2001 From: Joonwoo Park Date: Sun, 11 Sep 2016 21:14:58 -0700 Subject: cpuset: handle race between CPU hotplug and cpuset_hotplug_work A discrepancy between cpu_online_mask and cpuset's effective_cpus mask is inevitable during hotplug since cpuset defers updating of effective_cpus mask using a workqueue, during which time nothing prevents the system from more hotplug operations. For that reason guarantee_online_cpus() walks up the cpuset hierarchy until it finds an intersection under the assumption that top cpuset's effective_cpus mask intersects with cpu_online_mask even with such a race occurring. However a sequence of CPU hotplugs can open a time window, during which none of the effective CPUs in the top cpuset intersect with cpu_online_mask. For example when there are 4 possible CPUs 0-3 and only CPU0 is online: ======================== =========================== cpu_online_mask top_cpuset.effective_cpus ======================== =========================== echo 1 > cpu2/online. CPU hotplug notifier woke up hotplug work but not yet scheduled. [0,2] [0] echo 0 > cpu0/online. The workqueue is still runnable. [2] [0] ======================== =========================== Now there is no intersection between cpu_online_mask and top_cpuset.effective_cpus. Thus invoking sys_sched_setaffinity() at this moment can cause following: Unable to handle kernel NULL pointer dereference at virtual address 000000d0 ------------[ cut here ]------------ Kernel BUG at ffffffc0001389b0 [verbose debug info unavailable] Internal error: Oops - BUG: 96000005 [#1] PREEMPT SMP Modules linked in: CPU: 2 PID: 1420 Comm: taskset Tainted: G W 4.4.8+ #98 task: ffffffc06a5c4880 ti: ffffffc06e124000 task.ti: ffffffc06e124000 PC is at guarantee_online_cpus+0x2c/0x58 LR is at cpuset_cpus_allowed+0x4c/0x6c Process taskset (pid: 1420, stack limit = 0xffffffc06e124020) Call trace: [] guarantee_online_cpus+0x2c/0x58 [] cpuset_cpus_allowed+0x4c/0x6c [] sched_setaffinity+0xc0/0x1ac [] SyS_sched_setaffinity+0x98/0xac [] el0_svc_naked+0x24/0x28 The top cpuset's effective_cpus are guaranteed to be identical to cpu_online_mask eventually. Hence fall back to cpu_online_mask when there is no intersection between top cpuset's effective_cpus and cpu_online_mask. Signed-off-by: Joonwoo Park Acked-by: Li Zefan Cc: Tejun Heo Cc: cgroups@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: # 3.17+ Signed-off-by: Tejun Heo --- kernel/cpuset.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index c27e53326bef..c08585ad996b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -325,8 +325,7 @@ static struct file_system_type cpuset_fs_type = { /* * Return in pmask the portion of a cpusets's cpus_allowed that * are online. If none are online, walk up the cpuset hierarchy - * until we find one that does have some online cpus. The top - * cpuset always has some cpus online. + * until we find one that does have some online cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. @@ -335,8 +334,20 @@ static struct file_system_type cpuset_fs_type = { */ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) { - while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) + while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) { cs = parent_cs(cs); + if (unlikely(!cs)) { + /* + * The top cpuset doesn't have any online cpu as a + * consequence of a race between cpuset_hotplug_work + * and cpu hotplug notifier. But we know the top + * cpuset's effective_cpus is on its way to to be + * identical to cpu_online_mask. + */ + cpumask_copy(pmask, cpu_online_mask); + return; + } + } cpumask_and(pmask, cs->effective_cpus, cpu_online_mask); } -- cgit v1.2.3 From 8a15b81741879fa89601b03c0e50b0d780d65bc0 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Fri, 16 Sep 2016 13:02:37 +0000 Subject: cpuset: fix non static symbol warning Fixes the following sparse warning: kernel/cpuset.c:2088:6: warning: symbol 'cpuset_fork' was not declared. Should it be static? Signed-off-by: Wei Yongjun Signed-off-by: Tejun Heo --- kernel/cpuset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index c08585ad996b..2b4c20ab5bbe 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2085,7 +2085,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ -void cpuset_fork(struct task_struct *task) +static void cpuset_fork(struct task_struct *task) { if (task_css_is_root(task, cpuset_cgrp_id)) return; -- cgit v1.2.3 From 1984e075915cbae65336a99b1879865080d8e55e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 19 Sep 2016 09:49:27 +0100 Subject: genirq: Skip chained interrupt trigger setup if type is IRQ_TYPE_NONE There is no point in trying to configure the trigger of a chained interrupt if no trigger information has been configured. At best this is ignored, and at the worse this confuses the underlying irqchip (which is likely not to handle such a thing), and unnecessarily alarms the user. Only apply the configuration if type is not IRQ_TYPE_NONE. Fixes: 1e12c4a9393b ("genirq: Correctly configure the trigger on chained interrupts") Reported-and-tested-by: Geert Uytterhoeven Signed-off-by: Marc Zyngier Link: https://lkml.kernel.org/r/CAMuHMdVW1eTn20=EtYcJ8hkVwohaSuH_yQXrY2MGBEvZ8fpFOg@mail.gmail.com Link: http://lkml.kernel.org/r/1474274967-15984-1-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner --- kernel/irq/chip.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 637389088b3f..26ba5654d9d5 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -820,6 +820,8 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, desc->name = name; if (handle != handle_bad_irq && is_chained) { + unsigned int type = irqd_get_trigger_type(&desc->irq_data); + /* * We're about to start this interrupt immediately, * hence the need to set the trigger configuration. @@ -828,8 +830,10 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, * chained interrupt. Reset it immediately because we * do know better. */ - __irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data)); - desc->handle_irq = handle; + if (type != IRQ_TYPE_NONE) { + __irq_set_trigger(desc, type); + desc->handle_irq = handle; + } irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); -- cgit v1.2.3 From 3bf6215a1b30db7df6083c708caab3fe1a8e8abe Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Tue, 20 Sep 2016 18:48:11 +0300 Subject: perf/core: Limit matching exclusive events to one PMU An "exclusive" PMU is the one that can only have one event scheduled in at any given time. There may be more than one of such PMUs in a system, though, like Intel PT and BTS. It should be allowed to have one event for either of those inside the same context (there may be other constraints that may prevent this, but those would be hardware-specific). However, the exclusivity code is written so that only one event from any of the "exclusive" PMUs is allowed in a context. Fix this by making the exclusive event filter explicitly match two events' PMUs. Signed-off-by: Alexander Shishkin Acked-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160920154811.3255-3-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index a54f2c2cdb20..fc9bb2225291 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3929,7 +3929,7 @@ static void exclusive_event_destroy(struct perf_event *event) static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2) { - if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && + if ((e1->pmu == e2->pmu) && (e1->cpu == e2->cpu || e1->cpu == -1 || e2->cpu == -1)) -- cgit v1.2.3 From 9157056da8f8c4a6305f15619e269f164b63a6de Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 23 Sep 2016 16:55:49 -0400 Subject: cgroup: fix invalid controller enable rejections with cgroup namespace On the v2 hierarchy, "cgroup.subtree_control" rejects controller enables if the cgroup has processes in it. The enforcement of this logic assumes that the cgroup wouldn't have any css_sets associated with it if there are no tasks in the cgroup, which is no longer true since a79a908fd2b0 ("cgroup: introduce cgroup namespaces"). When a cgroup namespace is created, it pins the css_set of the creating task to use it as the root css_set of the namespace. This extra reference stays as long as the namespace is around and makes "cgroup.subtree_control" think that the namespace root cgroup is not empty even when it is and thus reject controller enables. Fix it by making cgroup_subtree_control() walk and test emptiness of each css_set instead of testing whether the list_head is empty. While at it, update the comment of cgroup_task_count() to indicate that the returned value may be higher than the number of tasks, which has always been true due to temporary references and doesn't break anything. Signed-off-by: Tejun Heo Reported-by: Evgeny Vereshchagin Cc: Serge E. Hallyn Cc: Aditya Kali Cc: Eric W. Biederman Cc: stable@vger.kernel.org # v4.6+ Fixes: a79a908fd2b0 ("cgroup: introduce cgroup namespaces") Link: https://github.com/systemd/systemd/pull/3589#issuecomment-249089541 --- kernel/cgroup.c | 29 +++++++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d1c51b7f5221..0d4ee1ea5c31 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3446,9 +3446,28 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, * Except for the root, subtree_control must be zero for a cgroup * with tasks so that child cgroups don't compete against tasks. */ - if (enable && cgroup_parent(cgrp) && !list_empty(&cgrp->cset_links)) { - ret = -EBUSY; - goto out_unlock; + if (enable && cgroup_parent(cgrp)) { + struct cgrp_cset_link *link; + + /* + * Because namespaces pin csets too, @cgrp->cset_links + * might not be empty even when @cgrp is empty. Walk and + * verify each cset. + */ + spin_lock_irq(&css_set_lock); + + ret = 0; + list_for_each_entry(link, &cgrp->cset_links, cset_link) { + if (css_set_populated(link->cset)) { + ret = -EBUSY; + break; + } + } + + spin_unlock_irq(&css_set_lock); + + if (ret) + goto out_unlock; } /* save and update control masks and prepare csses */ @@ -3899,7 +3918,9 @@ void cgroup_file_notify(struct cgroup_file *cfile) * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question * - * Return the number of tasks in the cgroup. + * Return the number of tasks in the cgroup. The returned number can be + * higher than the actual number of tasks due to css_set references from + * namespace roots and temporary usages. */ static int cgroup_task_count(const struct cgroup *cgrp) { -- cgit v1.2.3 From 1245800c0f96eb6ebb368593e251d66c01e61022 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 23 Sep 2016 22:57:13 -0400 Subject: tracing: Move mutex to protect against resetting of seq data The iter->seq can be reset outside the protection of the mutex. So can reading of user data. Move the mutex up to the beginning of the function. Fixes: d7350c3f45694 ("tracing/core: make the read callbacks reentrants") Cc: stable@vger.kernel.org # 2.6.30+ Reported-by: Al Viro Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8a4bd6b68a0b..8fb4847b0450 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4890,19 +4890,20 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, struct trace_iterator *iter = filp->private_data; ssize_t sret; - /* return any leftover data */ - sret = trace_seq_to_user(&iter->seq, ubuf, cnt); - if (sret != -EBUSY) - return sret; - - trace_seq_init(&iter->seq); - /* * Avoid more than one consumer on a single file descriptor * This is just a matter of traces coherency, the ring buffer itself * is protected. */ mutex_lock(&iter->mutex); + + /* return any leftover data */ + sret = trace_seq_to_user(&iter->seq, ubuf, cnt); + if (sret != -EBUSY) + goto out; + + trace_seq_init(&iter->seq); + if (iter->trace->read) { sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); if (sret) -- cgit v1.2.3 From 1ae2293dd6d2f5c823cf97e60b70d03631cd622f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 17 Sep 2016 18:31:46 -0400 Subject: fix memory leaks in tracing_buffers_splice_read() Cc: stable@vger.kernel.org Signed-off-by: Al Viro --- kernel/trace/trace.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8fb4847b0450..77eeab2776ef 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5930,9 +5930,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return -EBUSY; #endif - if (splice_grow_spd(pipe, &spd)) - return -ENOMEM; - if (*ppos & (PAGE_SIZE - 1)) return -EINVAL; @@ -5942,6 +5939,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, len &= PAGE_MASK; } + if (splice_grow_spd(pipe, &spd)) + return -ENOMEM; + again: trace_access_lock(iter->cpu_file); entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); @@ -5999,19 +5999,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { if (ret) - return ret; + goto out; + ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) - return -EAGAIN; + goto out; ret = wait_on_pipe(iter, true); if (ret) - return ret; + goto out; goto again; } ret = splice_to_pipe(pipe, &spd); +out: splice_shrink_spd(&spd); return ret; -- cgit v1.2.3