summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c31
-rw-r--r--kernel/audit.h2
-rw-r--r--kernel/auditfilter.c10
-rw-r--r--kernel/cpuset.c10
-rw-r--r--kernel/irq/irqdomain.c1
-rw-r--r--kernel/irq/manage.c3
-rw-r--r--kernel/profile.c4
-rw-r--r--kernel/sched/clock.c4
-rw-r--r--kernel/sched/core.c9
-rw-r--r--kernel/sched/cpudeadline.c4
-rw-r--r--kernel/sched/deadline.c10
-rw-r--r--kernel/sched/fair.c8
-rw-r--r--kernel/sched/rt.c8
-rw-r--r--kernel/stop_machine.c2
-rw-r--r--kernel/trace/trace_events.c10
-rw-r--r--kernel/tracepoint.c7
16 files changed, 79 insertions, 44 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 34c5a23..3392d3e 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -182,7 +182,7 @@ struct audit_buffer {
struct audit_reply {
__u32 portid;
- pid_t pid;
+ struct net *net;
struct sk_buff *skb;
};
@@ -500,7 +500,7 @@ int audit_send_list(void *_dest)
{
struct audit_netlink_list *dest = _dest;
struct sk_buff *skb;
- struct net *net = get_net_ns_by_pid(dest->pid);
+ struct net *net = dest->net;
struct audit_net *aunet = net_generic(net, audit_net_id);
/* wait for parent to finish and send an ACK */
@@ -510,6 +510,7 @@ int audit_send_list(void *_dest)
while ((skb = __skb_dequeue(&dest->q)) != NULL)
netlink_unicast(aunet->nlsk, skb, dest->portid, 0);
+ put_net(net);
kfree(dest);
return 0;
@@ -543,7 +544,7 @@ out_kfree_skb:
static int audit_send_reply_thread(void *arg)
{
struct audit_reply *reply = (struct audit_reply *)arg;
- struct net *net = get_net_ns_by_pid(reply->pid);
+ struct net *net = reply->net;
struct audit_net *aunet = net_generic(net, audit_net_id);
mutex_lock(&audit_cmd_mutex);
@@ -552,12 +553,13 @@ static int audit_send_reply_thread(void *arg)
/* Ignore failure. It'll only happen if the sender goes away,
because our timeout is set to infinite. */
netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0);
+ put_net(net);
kfree(reply);
return 0;
}
/**
* audit_send_reply - send an audit reply message via netlink
- * @portid: netlink port to which to send reply
+ * @request_skb: skb of request we are replying to (used to target the reply)
* @seq: sequence number
* @type: audit message type
* @done: done (last) flag
@@ -568,9 +570,11 @@ static int audit_send_reply_thread(void *arg)
* Allocates an skb, builds the netlink message, and sends it to the port id.
* No failure notifications.
*/
-static void audit_send_reply(__u32 portid, int seq, int type, int done,
+static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
int multi, const void *payload, int size)
{
+ u32 portid = NETLINK_CB(request_skb).portid;
+ struct net *net = sock_net(NETLINK_CB(request_skb).sk);
struct sk_buff *skb;
struct task_struct *tsk;
struct audit_reply *reply = kmalloc(sizeof(struct audit_reply),
@@ -583,8 +587,8 @@ static void audit_send_reply(__u32 portid, int seq, int type, int done,
if (!skb)
goto out;
+ reply->net = get_net(net);
reply->portid = portid;
- reply->pid = task_pid_vnr(current);
reply->skb = skb;
tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
@@ -673,8 +677,7 @@ static int audit_get_feature(struct sk_buff *skb)
seq = nlmsg_hdr(skb)->nlmsg_seq;
- audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
- &af, sizeof(af));
+ audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af));
return 0;
}
@@ -794,8 +797,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
s.backlog = skb_queue_len(&audit_skb_queue);
s.version = AUDIT_VERSION_LATEST;
s.backlog_wait_time = audit_backlog_wait_time;
- audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
- &s, sizeof(s));
+ audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_SET: {
@@ -905,7 +907,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
seq, data, nlmsg_len(nlh));
break;
case AUDIT_LIST_RULES:
- err = audit_list_rules_send(NETLINK_CB(skb).portid, seq);
+ err = audit_list_rules_send(skb, seq);
break;
case AUDIT_TRIM:
audit_trim_trees();
@@ -970,8 +972,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
memcpy(sig_data->ctx, ctx, len);
security_release_secctx(ctx, len);
}
- audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO,
- 0, 0, sig_data, sizeof(*sig_data) + len);
+ audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0,
+ sig_data, sizeof(*sig_data) + len);
kfree(sig_data);
break;
case AUDIT_TTY_GET: {
@@ -983,8 +985,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
s.log_passwd = tsk->signal->audit_tty_log_passwd;
spin_unlock(&tsk->sighand->siglock);
- audit_send_reply(NETLINK_CB(skb).portid, seq,
- AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
+ audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_TTY_SET: {
diff --git a/kernel/audit.h b/kernel/audit.h
index 57cc64d..8df13221 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -247,7 +247,7 @@ extern void audit_panic(const char *message);
struct audit_netlink_list {
__u32 portid;
- pid_t pid;
+ struct net *net;
struct sk_buff_head q;
};
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 14a78cc..92062fd 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -29,6 +29,8 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/security.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
#include "audit.h"
/*
@@ -1065,11 +1067,13 @@ int audit_rule_change(int type, __u32 portid, int seq, void *data,
/**
* audit_list_rules_send - list the audit rules
- * @portid: target portid for netlink audit messages
+ * @request_skb: skb of request we are replying to (used to target the reply)
* @seq: netlink audit message sequence (serial) number
*/
-int audit_list_rules_send(__u32 portid, int seq)
+int audit_list_rules_send(struct sk_buff *request_skb, int seq)
{
+ u32 portid = NETLINK_CB(request_skb).portid;
+ struct net *net = sock_net(NETLINK_CB(request_skb).sk);
struct task_struct *tsk;
struct audit_netlink_list *dest;
int err = 0;
@@ -1083,8 +1087,8 @@ int audit_list_rules_send(__u32 portid, int seq)
dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
if (!dest)
return -ENOMEM;
+ dest->net = get_net(net);
dest->portid = portid;
- dest->pid = task_pid_vnr(current);
skb_queue_head_init(&dest->q);
mutex_lock(&audit_filter_mutex);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4410ac6..e6b1b66 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -974,12 +974,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
* Temporarilly set tasks mems_allowed to target nodes of migration,
* so that the migration code can allocate pages on these nodes.
*
- * Call holding cpuset_mutex, so current's cpuset won't change
- * during this call, as manage_mutex holds off any cpuset_attach()
- * calls. Therefore we don't need to take task_lock around the
- * call to guarantee_online_mems(), as we know no one is changing
- * our task's cpuset.
- *
* While the mm_struct we are migrating is typically from some
* other task, the task_struct mems_allowed that we are hacking
* is for our current task, which must allocate new pages for that
@@ -996,8 +990,10 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+ rcu_read_lock();
mems_cs = effective_nodemask_cpuset(task_cs(tsk));
guarantee_online_mems(mems_cs, &tsk->mems_allowed);
+ rcu_read_unlock();
}
/*
@@ -2486,9 +2482,9 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
task_lock(current);
cs = nearest_hardwall_ancestor(task_cs(current));
+ allowed = node_isset(node, cs->mems_allowed);
task_unlock(current);
- allowed = node_isset(node, cs->mems_allowed);
mutex_unlock(&callback_mutex);
return allowed;
}
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index cf68bb3..f140337 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -10,6 +10,7 @@
#include <linux/mutex.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/of_irq.h>
#include <linux/topology.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 481a13c..d3bf660 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -802,8 +802,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
static void wake_threads_waitq(struct irq_desc *desc)
{
- if (atomic_dec_and_test(&desc->threads_active) &&
- waitqueue_active(&desc->wait_for_threads))
+ if (atomic_dec_and_test(&desc->threads_active))
wake_up(&desc->wait_for_threads);
}
diff --git a/kernel/profile.c b/kernel/profile.c
index 6631e1e..ebdd9c1 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -549,14 +549,14 @@ static int create_hash_tables(void)
struct page *page;
page = alloc_pages_exact_node(node,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
per_cpu(cpu_profile_hits, cpu)[1]
= (struct profile_hit *)page_address(page);
page = alloc_pages_exact_node(node,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 43c2bcc..b30a292 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -301,14 +301,14 @@ u64 sched_clock_cpu(int cpu)
if (unlikely(!sched_clock_running))
return 0ull;
- preempt_disable();
+ preempt_disable_notrace();
scd = cpu_sdc(cpu);
if (cpu != smp_processor_id())
clock = sched_clock_remote(scd);
else
clock = sched_clock_local(scd);
- preempt_enable();
+ preempt_enable_notrace();
return clock;
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6edbef2..f5c6635 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3338,6 +3338,15 @@ recheck:
return -EPERM;
}
+ /*
+ * Can't set/change SCHED_DEADLINE policy at all for now
+ * (safest behavior); in the future we would like to allow
+ * unprivileged DL tasks to increase their relative deadline
+ * or reduce their runtime (both ways reducing utilization)
+ */
+ if (dl_policy(policy))
+ return -EPERM;
+
/*
* Treat SCHED_IDLE as nice 20. Only allow a switch to
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5b8838b..5b9bb42 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx)
static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
{
- WARN_ON(!cpu_present(idx) || idx == IDX_INVALID);
+ WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
if (dl_time_before(new_dl, cp->elements[idx].dl)) {
cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
}
out:
- WARN_ON(!cpu_present(best_cpu) && best_cpu != -1);
+ WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
return best_cpu;
}
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 15cbc17..6e79b3f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -135,7 +135,6 @@ static void update_dl_migration(struct dl_rq *dl_rq)
static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
struct task_struct *p = dl_task_of(dl_se);
- dl_rq = &rq_of_dl_rq(dl_rq)->dl;
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory++;
@@ -146,7 +145,6 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
struct task_struct *p = dl_task_of(dl_se);
- dl_rq = &rq_of_dl_rq(dl_rq)->dl;
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory--;
@@ -564,6 +562,8 @@ int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
return 1;
}
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
/*
* Update the current task's runtime statistics (provided it is still
* a -deadline task and has not been removed from the dl_rq).
@@ -627,11 +627,13 @@ static void update_curr_dl(struct rq *rq)
struct rt_rq *rt_rq = &rq->rt;
raw_spin_lock(&rt_rq->rt_runtime_lock);
- rt_rq->rt_time += delta_exec;
/*
* We'll let actual RT tasks worry about the overflow here, we
- * have our own CBS to keep us inline -- see above.
+ * have our own CBS to keep us inline; only account when RT
+ * bandwidth is relevant.
*/
+ if (sched_rt_bandwidth_account(rt_rq))
+ rt_rq->rt_time += delta_exec;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7815709..9b4c4f3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7001,15 +7001,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
struct cfs_rq *cfs_rq = cfs_rq_of(se);
/*
- * Ensure the task's vruntime is normalized, so that when its
+ * Ensure the task's vruntime is normalized, so that when it's
* switched back to the fair class the enqueue_entity(.flags=0) will
* do the right thing.
*
- * If it was on_rq, then the dequeue_entity(.flags=0) will already
- * have normalized the vruntime, if it was !on_rq, then only when
+ * If it's on_rq, then the dequeue_entity(.flags=0) will already
+ * have normalized the vruntime, if it's !on_rq, then only when
* the task is sleeping will it still have non-normalized vruntime.
*/
- if (!se->on_rq && p->state != TASK_RUNNING) {
+ if (!p->on_rq && p->state != TASK_RUNNING) {
/*
* Fix up our vruntime so that the current sleep doesn't
* cause 'unlimited' sleep bonus.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a2740b7..1999021 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -538,6 +538,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
#endif /* CONFIG_RT_GROUP_SCHED */
+bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
+{
+ struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+ return (hrtimer_active(&rt_b->rt_period_timer) ||
+ rt_rq->rt_time < rt_b->rt_runtime);
+}
+
#ifdef CONFIG_SMP
/*
* We ran out of runtime, see if we can borrow some from our neighbours.
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 84571e0..01fbae5 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -293,7 +293,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
*/
smp_call_function_single(min(cpu1, cpu2),
&irq_cpu_stop_queue_work,
- &call_args, 0);
+ &call_args, 1);
lg_local_unlock(&stop_cpus_lock);
preempt_enable();
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e71ffd4..f3989ce 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1777,6 +1777,16 @@ static void trace_module_add_events(struct module *mod)
{
struct ftrace_event_call **call, **start, **end;
+ if (!mod->num_trace_events)
+ return;
+
+ /* Don't add infrastructure for mods without tracepoints */
+ if (trace_module_has_bad_taint(mod)) {
+ pr_err("%s: module has bad taint, not creating trace events\n",
+ mod->name);
+ return;
+ }
+
start = mod->trace_events;
end = mod->trace_events + mod->num_trace_events;
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 29f2654..031cc56 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -631,6 +631,11 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter)
EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
#ifdef CONFIG_MODULES
+bool trace_module_has_bad_taint(struct module *mod)
+{
+ return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+}
+
static int tracepoint_module_coming(struct module *mod)
{
struct tp_module *tp_mod, *iter;
@@ -641,7 +646,7 @@ static int tracepoint_module_coming(struct module *mod)
* module headers (for forced load), to make sure we don't cause a crash.
* Staging and out-of-tree GPL modules are fine.
*/
- if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
+ if (trace_module_has_bad_taint(mod))
return 0;
mutex_lock(&tracepoints_mutex);
tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
generated by cgit v0.10.2 at 2024-07-21 15:54:24 (GMT)