summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/cpumap.c35
-rw-r--r--kernel/bpf/inode.c6
-rw-r--r--kernel/bpf/verifier.c32
-rw-r--r--kernel/cpu.c144
-rw-r--r--kernel/entry/common.c3
-rw-r--r--kernel/events/core.c6
-rw-r--r--kernel/irq/chip.c11
-rw-r--r--kernel/irq/internals.h4
-rw-r--r--kernel/irq/manage.c26
-rw-r--r--kernel/irq/resend.c7
-rw-r--r--kernel/kallsyms.c27
-rw-r--r--kernel/kallsyms_selftest.c23
-rw-r--r--kernel/kprobes.c14
-rw-r--r--kernel/locking/locktorture.c12
-rw-r--r--kernel/locking/rtmutex.c170
-rw-r--r--kernel/locking/rtmutex_api.c2
-rw-r--r--kernel/locking/rtmutex_common.h47
-rw-r--r--kernel/locking/ww_mutex.h12
-rw-r--r--kernel/nsproxy.c4
-rw-r--r--kernel/power/hibernate.c2
-rw-r--r--kernel/rcu/rcu.h8
-rw-r--r--kernel/rcu/rcuscale.c83
-rw-r--r--kernel/rcu/rcutorture.c7
-rw-r--r--kernel/rcu/refscale.c37
-rw-r--r--kernel/rcu/tasks.h136
-rw-r--r--kernel/rcu/tree.c16
-rw-r--r--kernel/rcu/tree_nocb.h4
-rw-r--r--kernel/scftorture.c12
-rw-r--r--kernel/sched/completion.c26
-rw-r--r--kernel/sched/core.c5
-rw-r--r--kernel/sched/fair.c4
-rw-r--r--kernel/sched/sched.h13
-rw-r--r--kernel/sched/swait.c8
-rw-r--r--kernel/sched/wait.c5
-rw-r--r--kernel/seccomp.c84
-rw-r--r--kernel/signal.c4
-rw-r--r--kernel/smp.c13
-rw-r--r--kernel/sys.c10
-rw-r--r--kernel/time/clocksource.c8
-rw-r--r--kernel/torture.c39
-rw-r--r--kernel/trace/bpf_trace.c17
-rw-r--r--kernel/trace/ring_buffer.c39
-rw-r--r--kernel/trace/trace.c73
-rw-r--r--kernel/trace/trace.h10
-rw-r--r--kernel/trace/trace_events.c14
-rw-r--r--kernel/trace/trace_events_hist.c3
-rw-r--r--kernel/trace/trace_events_synth.c104
-rw-r--r--kernel/trace/trace_events_trigger.c2
-rw-r--r--kernel/trace/trace_irqsoff.c3
-rw-r--r--kernel/trace/trace_probe.c8
-rw-r--r--kernel/trace/trace_sched_wakeup.c2
-rw-r--r--kernel/trace/trace_seq.c1
-rw-r--r--kernel/trace/tracing_map.h4
-rw-r--r--kernel/workqueue.c43
54 files changed, 1012 insertions, 420 deletions
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 6ae02be7a48e..286ab3db0fde 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -28,6 +28,7 @@
#include <linux/sched.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
+#include <linux/completion.h>
#include <trace/events/xdp.h>
#include <linux/btf_ids.h>
@@ -73,6 +74,7 @@ struct bpf_cpu_map_entry {
struct rcu_head rcu;
struct work_struct kthread_stop_wq;
+ struct completion kthread_running;
};
struct bpf_cpu_map {
@@ -129,11 +131,17 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
* invoked cpu_map_kthread_stop(). Catch any broken behaviour
* gracefully and warn once.
*/
- struct xdp_frame *xdpf;
+ void *ptr;
- while ((xdpf = ptr_ring_consume(ring)))
- if (WARN_ON_ONCE(xdpf))
- xdp_return_frame(xdpf);
+ while ((ptr = ptr_ring_consume(ring))) {
+ WARN_ON_ONCE(1);
+ if (unlikely(__ptr_test_bit(0, &ptr))) {
+ __ptr_clear_bit(0, &ptr);
+ kfree_skb(ptr);
+ continue;
+ }
+ xdp_return_frame(ptr);
+ }
}
static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
@@ -153,7 +161,6 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
static void cpu_map_kthread_stop(struct work_struct *work)
{
struct bpf_cpu_map_entry *rcpu;
- int err;
rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
@@ -163,14 +170,7 @@ static void cpu_map_kthread_stop(struct work_struct *work)
rcu_barrier();
/* kthread_stop will wake_up_process and wait for it to complete */
- err = kthread_stop(rcpu->kthread);
- if (err) {
- /* kthread_stop may be called before cpu_map_kthread_run
- * is executed, so we need to release the memory related
- * to rcpu.
- */
- put_cpu_map_entry(rcpu);
- }
+ kthread_stop(rcpu->kthread);
}
static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
@@ -298,11 +298,11 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
return nframes;
}
-
static int cpu_map_kthread_run(void *data)
{
struct bpf_cpu_map_entry *rcpu = data;
+ complete(&rcpu->kthread_running);
set_current_state(TASK_INTERRUPTIBLE);
/* When kthread gives stop order, then rcpu have been disconnected
@@ -467,6 +467,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
goto free_ptr_ring;
/* Setup kthread */
+ init_completion(&rcpu->kthread_running);
rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
"cpumap/%d/map:%d", cpu,
map->id);
@@ -480,6 +481,12 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
kthread_bind(rcpu->kthread, cpu);
wake_up_process(rcpu->kthread);
+ /* Make sure kthread has been running, so kthread_stop() will not
+ * stop the kthread prematurely and all pending frames or skbs
+ * will be handled by the kthread before kthread_stop() returns.
+ */
+ wait_for_completion(&rcpu->kthread_running);
+
return rcpu;
free_prog:
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 4174f76133df..99d0625b6c82 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -118,9 +118,8 @@ static struct inode *bpf_get_inode(struct super_block *sb,
return ERR_PTR(-ENOSPC);
inode->i_ino = get_next_ino();
- inode->i_atime = current_time(inode);
+ inode->i_atime = inode_set_ctime_current(inode);
inode->i_mtime = inode->i_atime;
- inode->i_ctime = inode->i_atime;
inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
@@ -148,8 +147,7 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode,
d_instantiate(dentry, inode);
dget(dentry);
- dir->i_mtime = current_time(dir);
- dir->i_ctime = dir->i_mtime;
+ dir->i_mtime = inode_set_ctime_current(dir);
}
static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 930b5555cfd3..02a021c524ab 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5573,16 +5573,17 @@ static int update_stack_depth(struct bpf_verifier_env *env,
* Since recursion is prevented by check_cfg() this algorithm
* only needs a local stack of MAX_CALL_FRAMES to remember callsites
*/
-static int check_max_stack_depth(struct bpf_verifier_env *env)
+static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx)
{
- int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
+ int depth = 0, frame = 0, i, subprog_end;
bool tail_call_reachable = false;
int ret_insn[MAX_CALL_FRAMES];
int ret_prog[MAX_CALL_FRAMES];
int j;
+ i = subprog[idx].start;
process_func:
/* protect against potential stack overflow that might happen when
* bpf2bpf calls get combined with tailcalls. Limit the caller's stack
@@ -5621,7 +5622,7 @@ process_func:
continue_func:
subprog_end = subprog[idx + 1].start;
for (; i < subprog_end; i++) {
- int next_insn;
+ int next_insn, sidx;
if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
continue;
@@ -5631,14 +5632,14 @@ continue_func:
/* find the callee */
next_insn = i + insn[i].imm + 1;
- idx = find_subprog(env, next_insn);
- if (idx < 0) {
+ sidx = find_subprog(env, next_insn);
+ if (sidx < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
next_insn);
return -EFAULT;
}
- if (subprog[idx].is_async_cb) {
- if (subprog[idx].has_tail_call) {
+ if (subprog[sidx].is_async_cb) {
+ if (subprog[sidx].has_tail_call) {
verbose(env, "verifier bug. subprog has tail_call and async cb\n");
return -EFAULT;
}
@@ -5647,6 +5648,7 @@ continue_func:
continue;
}
i = next_insn;
+ idx = sidx;
if (subprog[idx].has_tail_call)
tail_call_reachable = true;
@@ -5682,6 +5684,22 @@ continue_func:
goto continue_func;
}
+static int check_max_stack_depth(struct bpf_verifier_env *env)
+{
+ struct bpf_subprog_info *si = env->subprog_info;
+ int ret;
+
+ for (int i = 0; i < env->subprog_cnt; i++) {
+ if (!i || si[i].is_async_cb) {
+ ret = check_max_stack_depth_subprog(env, i);
+ if (ret < 0)
+ return ret;
+ }
+ continue;
+ }
+ return 0;
+}
+
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
static int get_callee_stack_depth(struct bpf_verifier_env *env,
const struct bpf_insn *insn, int idx)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 88a7ede322bd..f6811c857102 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -592,7 +592,10 @@ static void lockdep_release_cpus_lock(void)
void __weak arch_smt_update(void) { }
#ifdef CONFIG_HOTPLUG_SMT
+
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+static unsigned int cpu_smt_max_threads __ro_after_init;
+unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX;
void __init cpu_smt_disable(bool force)
{
@@ -606,16 +609,33 @@ void __init cpu_smt_disable(bool force)
pr_info("SMT: disabled\n");
cpu_smt_control = CPU_SMT_DISABLED;
}
+ cpu_smt_num_threads = 1;
}
/*
* The decision whether SMT is supported can only be done after the full
* CPU identification. Called from architecture code.
*/
-void __init cpu_smt_check_topology(void)
+void __init cpu_smt_set_num_threads(unsigned int num_threads,
+ unsigned int max_threads)
{
- if (!topology_smt_supported())
+ WARN_ON(!num_threads || (num_threads > max_threads));
+
+ if (max_threads == 1)
cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+
+ cpu_smt_max_threads = max_threads;
+
+ /*
+ * If SMT has been disabled via the kernel command line or SMT is
+ * not supported, set cpu_smt_num_threads to 1 for consistency.
+ * If enabled, take the architecture requested number of threads
+ * to bring up into account.
+ */
+ if (cpu_smt_control != CPU_SMT_ENABLED)
+ cpu_smt_num_threads = 1;
+ else if (num_threads < cpu_smt_num_threads)
+ cpu_smt_num_threads = num_threads;
}
static int __init smt_cmdline_disable(char *str)
@@ -625,9 +645,23 @@ static int __init smt_cmdline_disable(char *str)
}
early_param("nosmt", smt_cmdline_disable);
+/*
+ * For Archicture supporting partial SMT states check if the thread is allowed.
+ * Otherwise this has already been checked through cpu_smt_max_threads when
+ * setting the SMT level.
+ */
+static inline bool cpu_smt_thread_allowed(unsigned int cpu)
+{
+#ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC
+ return topology_smt_thread_allowed(cpu);
+#else
+ return true;
+#endif
+}
+
static inline bool cpu_smt_allowed(unsigned int cpu)
{
- if (cpu_smt_control == CPU_SMT_ENABLED)
+ if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu))
return true;
if (topology_is_primary_thread(cpu))
@@ -642,7 +676,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu)
return !cpumask_test_cpu(cpu, &cpus_booted_once_mask);
}
-/* Returns true if SMT is not supported of forcefully (irreversibly) disabled */
+/* Returns true if SMT is supported and not forcefully (irreversibly) disabled */
bool cpu_smt_possible(void)
{
return cpu_smt_control != CPU_SMT_FORCE_DISABLED &&
@@ -650,22 +684,8 @@ bool cpu_smt_possible(void)
}
EXPORT_SYMBOL_GPL(cpu_smt_possible);
-static inline bool cpuhp_smt_aware(void)
-{
- return topology_smt_supported();
-}
-
-static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
-{
- return cpu_primary_thread_mask;
-}
#else
static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
-static inline bool cpuhp_smt_aware(void) { return false; }
-static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
-{
- return cpu_present_mask;
-}
#endif
static inline enum cpuhp_state
@@ -1793,6 +1813,16 @@ static int __init parallel_bringup_parse_param(char *arg)
}
early_param("cpuhp.parallel", parallel_bringup_parse_param);
+static inline bool cpuhp_smt_aware(void)
+{
+ return cpu_smt_max_threads > 1;
+}
+
+static inline const struct cpumask *cpuhp_get_primary_thread_mask(void)
+{
+ return cpu_primary_thread_mask;
+}
+
/*
* On architectures which have enabled parallel bringup this invokes all BP
* prepare states for each of the to be onlined APs first. The last state
@@ -2626,6 +2656,12 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
for_each_online_cpu(cpu) {
if (topology_is_primary_thread(cpu))
continue;
+ /*
+ * Disable can be called with CPU_SMT_ENABLED when changing
+ * from a higher to lower number of SMT threads per core.
+ */
+ if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu))
+ continue;
ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
if (ret)
break;
@@ -2660,6 +2696,8 @@ int cpuhp_smt_enable(void)
/* Skip online CPUs and CPUs on offline nodes */
if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
continue;
+ if (!cpu_smt_thread_allowed(cpu))
+ continue;
ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
if (ret)
break;
@@ -2838,20 +2876,19 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
#ifdef CONFIG_HOTPLUG_SMT
+static bool cpu_smt_num_threads_valid(unsigned int threads)
+{
+ if (IS_ENABLED(CONFIG_SMT_NUM_THREADS_DYNAMIC))
+ return threads >= 1 && threads <= cpu_smt_max_threads;
+ return threads == 1 || threads == cpu_smt_max_threads;
+}
+
static ssize_t
__store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
- int ctrlval, ret;
-
- if (sysfs_streq(buf, "on"))
- ctrlval = CPU_SMT_ENABLED;
- else if (sysfs_streq(buf, "off"))
- ctrlval = CPU_SMT_DISABLED;
- else if (sysfs_streq(buf, "forceoff"))
- ctrlval = CPU_SMT_FORCE_DISABLED;
- else
- return -EINVAL;
+ int ctrlval, ret, num_threads, orig_threads;
+ bool force_off;
if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
return -EPERM;
@@ -2859,21 +2896,39 @@ __store_smt_control(struct device *dev, struct device_attribute *attr,
if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
return -ENODEV;
+ if (sysfs_streq(buf, "on")) {
+ ctrlval = CPU_SMT_ENABLED;
+ num_threads = cpu_smt_max_threads;
+ } else if (sysfs_streq(buf, "off")) {
+ ctrlval = CPU_SMT_DISABLED;
+ num_threads = 1;
+ } else if (sysfs_streq(buf, "forceoff")) {
+ ctrlval = CPU_SMT_FORCE_DISABLED;
+ num_threads = 1;
+ } else if (kstrtoint(buf, 10, &num_threads) == 0) {
+ if (num_threads == 1)
+ ctrlval = CPU_SMT_DISABLED;
+ else if (cpu_smt_num_threads_valid(num_threads))
+ ctrlval = CPU_SMT_ENABLED;
+ else
+ return -EINVAL;
+ } else {
+ return -EINVAL;
+ }
+
ret = lock_device_hotplug_sysfs();
if (ret)
return ret;
- if (ctrlval != cpu_smt_control) {
- switch (ctrlval) {
- case CPU_SMT_ENABLED:
- ret = cpuhp_smt_enable();
- break;
- case CPU_SMT_DISABLED:
- case CPU_SMT_FORCE_DISABLED:
- ret = cpuhp_smt_disable(ctrlval);
- break;
- }
- }
+ orig_threads = cpu_smt_num_threads;
+ cpu_smt_num_threads = num_threads;
+
+ force_off = ctrlval != cpu_smt_control && ctrlval == CPU_SMT_FORCE_DISABLED;
+
+ if (num_threads > orig_threads)
+ ret = cpuhp_smt_enable();
+ else if (num_threads < orig_threads || force_off)
+ ret = cpuhp_smt_disable(ctrlval);
unlock_device_hotplug();
return ret ? ret : count;
@@ -2901,6 +2956,17 @@ static ssize_t control_show(struct device *dev,
{
const char *state = smt_states[cpu_smt_control];
+#ifdef CONFIG_HOTPLUG_SMT
+ /*
+ * If SMT is enabled but not all threads are enabled then show the
+ * number of threads. If all threads are enabled show "on". Otherwise
+ * show the state name.
+ */
+ if (cpu_smt_control == CPU_SMT_ENABLED &&
+ cpu_smt_num_threads != cpu_smt_max_threads)
+ return sysfs_emit(buf, "%d\n", cpu_smt_num_threads);
+#endif
+
return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
}
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index be61332c66b5..d7ee4bc3f2ba 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -205,8 +205,7 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
arch_exit_to_user_mode_prepare(regs, ti_work);
- /* Ensure that the address limit is intact and no locks are held */
- addr_limit_user_check();
+ /* Ensure that kernel state is sane for a return to userspace */
kmap_assert_nomap();
lockdep_assert_irqs_disabled();
lockdep_sys_exit();
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 78ae7b6f90fd..2554f5fc70dc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8249,7 +8249,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
unsigned int size;
memset(comm, 0, sizeof(comm));
- strlcpy(comm, comm_event->task->comm, sizeof(comm));
+ strscpy(comm, comm_event->task->comm, sizeof(comm));
size = ALIGN(strlen(comm)+1, sizeof(u64));
comm_event->comm = comm;
@@ -8704,7 +8704,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
}
cpy_name:
- strlcpy(tmp, name, sizeof(tmp));
+ strscpy(tmp, name, sizeof(tmp));
name = tmp;
got_name:
/*
@@ -9128,7 +9128,7 @@ void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister,
ksym_type == PERF_RECORD_KSYMBOL_TYPE_UNKNOWN)
goto err;
- strlcpy(name, sym, KSYM_NAME_LEN);
+ strscpy(name, sym, KSYM_NAME_LEN);
name_len = strlen(name) + 1;
while (!IS_ALIGNED(name_len, sizeof(u64)))
name[name_len++] = '\0';
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index ee8c0acf39df..dc94e0bf2c94 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -473,11 +473,12 @@ void handle_nested_irq(unsigned int irq)
action = desc->action;
if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
desc->istate |= IRQS_PENDING;
- goto out_unlock;
+ raw_spin_unlock_irq(&desc->lock);
+ return;
}
kstat_incr_irqs_this_cpu(desc);
- irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
+ atomic_inc(&desc->threads_active);
raw_spin_unlock_irq(&desc->lock);
action_ret = IRQ_NONE;
@@ -487,11 +488,7 @@ void handle_nested_irq(unsigned int irq)
if (!irq_settings_no_debug(desc))
note_interrupt(desc, action_ret);
- raw_spin_lock_irq(&desc->lock);
- irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
-
-out_unlock:
- raw_spin_unlock_irq(&desc->lock);
+ wake_threads_waitq(desc);
}
EXPORT_SYMBOL_GPL(handle_nested_irq);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index bdd35bb9c735..bcc7f21db9ee 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -108,8 +108,6 @@ extern int __irq_get_irqchip_state(struct irq_data *data,
enum irqchip_irq_state which,
bool *state);
-extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
-
irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc);
irqreturn_t handle_irq_event_percpu(struct irq_desc *desc);
irqreturn_t handle_irq_event(struct irq_desc *desc);
@@ -121,6 +119,8 @@ void irq_resend_init(struct irq_desc *desc);
bool irq_wait_for_poll(struct irq_desc *desc);
void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action);
+void wake_threads_waitq(struct irq_desc *desc);
+
#ifdef CONFIG_PROC_FS
extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d2742af0f0fd..d309ba84e08a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -108,6 +108,16 @@ bool synchronize_hardirq(unsigned int irq)
}
EXPORT_SYMBOL(synchronize_hardirq);
+static void __synchronize_irq(struct irq_desc *desc)
+{
+ __synchronize_hardirq(desc, true);
+ /*
+ * We made sure that no hardirq handler is running. Now verify that no
+ * threaded handlers are active.
+ */
+ wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
+}
+
/**
* synchronize_irq - wait for pending IRQ handlers (on other CPUs)
* @irq: interrupt number to wait for
@@ -127,16 +137,8 @@ void synchronize_irq(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
- if (desc) {
- __synchronize_hardirq(desc, true);
- /*
- * We made sure that no hardirq handler is
- * running. Now verify that no threaded handlers are
- * active.
- */
- wait_event(desc->wait_for_threads,
- !atomic_read(&desc->threads_active));
- }
+ if (desc)
+ __synchronize_irq(desc);
}
EXPORT_SYMBOL(synchronize_irq);
@@ -1216,7 +1218,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
return ret;
}
-static void wake_threads_waitq(struct irq_desc *desc)
+void wake_threads_waitq(struct irq_desc *desc)
{
if (atomic_dec_and_test(&desc->threads_active))
wake_up(&desc->wait_for_threads);
@@ -1944,7 +1946,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
* supports it also make sure that there is no (not yet serviced)
* interrupt in flight at the hardware level.
*/
- __synchronize_hardirq(desc, true);
+ __synchronize_irq(desc);
#ifdef CONFIG_DEBUG_SHIRQ
/*
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index edec335c0a7a..5f2c66860ac6 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -68,11 +68,16 @@ static int irq_sw_resend(struct irq_desc *desc)
*/
if (!desc->parent_irq)
return -EINVAL;
+
+ desc = irq_to_desc(desc->parent_irq);
+ if (!desc)
+ return -EINVAL;
}
/* Add to resend_list and activate the softirq: */
raw_spin_lock(&irq_resend_lock);
- hlist_add_head(&desc->resend_node, &irq_resend_list);
+ if (hlist_unhashed(&desc->resend_node))
+ hlist_add_head(&desc->resend_node, &irq_resend_list);
raw_spin_unlock(&irq_resend_lock);
tasklet_schedule(&resend_tasklet);
return 0;
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 016d997131d4..18edd57b5fe8 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -163,12 +163,12 @@ unsigned long kallsyms_sym_address(int idx)
return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
}
-static bool cleanup_symbol_name(char *s)
+static void cleanup_symbol_name(char *s)
{
char *res;
if (!IS_ENABLED(CONFIG_LTO_CLANG))
- return false;
+ return;
/*
* LLVM appends various suffixes for local functions and variables that
@@ -178,26 +178,21 @@ static bool cleanup_symbol_name(char *s)
* - foo.llvm.[0-9a-f]+
*/
res = strstr(s, ".llvm.");
- if (res) {
+ if (res)
*res = '\0';
- return true;
- }
- return false;
+ return;
}
static int compare_symbol_name(const char *name, char *namebuf)
{
- int ret;
-
- ret = strcmp(name, namebuf);
- if (!ret)
- return ret;
-
- if (cleanup_symbol_name(namebuf) && !strcmp(name, namebuf))
- return 0;
-
- return ret;
+ /* The kallsyms_seqs_of_names is sorted based on names after
+ * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled.
+ * To ensure correct bisection in kallsyms_lookup_names(), do
+ * cleanup_symbol_name(namebuf) before comparing name and namebuf.
+ */
+ cleanup_symbol_name(namebuf);
+ return strcmp(name, namebuf);
}
static unsigned int get_symbol_seq(int index)
diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c
index a2e3745d15c4..e05ddc33a752 100644
--- a/kernel/kallsyms_selftest.c
+++ b/kernel/kallsyms_selftest.c
@@ -196,7 +196,7 @@ static bool match_cleanup_name(const char *s, const char *name)
if (!IS_ENABLED(CONFIG_LTO_CLANG))
return false;
- p = strchr(s, '.');
+ p = strstr(s, ".llvm.");
if (!p)
return false;
@@ -344,27 +344,6 @@ static int test_kallsyms_basic_function(void)
goto failed;
}
- /*
- * The first '.' may be the initial letter, in which case the
- * entire symbol name will be truncated to an empty string in
- * cleanup_symbol_name(). Do not test these symbols.
- *
- * For example:
- * cat /proc/kallsyms | awk '{print $3}' | grep -E "^\." | head
- * .E_read_words
- * .E_leading_bytes
- * .E_trailing_bytes
- * .E_write_words
- * .E_copy
- * .str.292.llvm.12122243386960820698
- * .str.24.llvm.12122243386960820698
- * .str.29.llvm.12122243386960820698
- * .str.75.llvm.12122243386960820698
- * .str.99.llvm.12122243386960820698
- */
- if (IS_ENABLED(CONFIG_LTO_CLANG) && !namebuf[0])
- continue;
-
lookup_addr = kallsyms_lookup_name(namebuf);
memset(stat, 0, sizeof(*stat));
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1fc6095d502d..ca385b61d546 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1545,6 +1545,17 @@ static int check_ftrace_location(struct kprobe *p)
return 0;
}
+static bool is_cfi_preamble_symbol(unsigned long addr)
+{
+ char symbuf[KSYM_NAME_LEN];
+
+ if (lookup_symbol_name(addr, symbuf))
+ return false;
+
+ return str_has_prefix("__cfi_", symbuf) ||
+ str_has_prefix("__pfx_", symbuf);
+}
+
static int check_kprobe_address_safe(struct kprobe *p,
struct module **probed_mod)
{
@@ -1563,7 +1574,8 @@ static int check_kprobe_address_safe(struct kprobe *p,
within_kprobe_blacklist((unsigned long) p->addr) ||
jump_label_text_reserved(p->addr, p->addr) ||
static_call_text_reserved(p->addr, p->addr) ||
- find_bug((unsigned long)p->addr)) {
+ find_bug((unsigned long)p->addr) ||
+ is_cfi_preamble_symbol((unsigned long)p->addr)) {
ret = -EINVAL;
goto out;
}
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 949d3deae506..270c7f80ce84 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -45,6 +45,7 @@ torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
torture_param(int, rt_boost, 2,
"Do periodic rt-boost. 0=Disable, 1=Only for rt_mutex, 2=For all lock types.");
torture_param(int, rt_boost_factor, 50, "A factor determining how often rt-boost happens.");
+torture_param(int, writer_fifo, 0, "Run writers at sched_set_fifo() priority");
torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
torture_param(int, nested_locks, 0, "Number of nested locks (max = 8)");
/* Going much higher trips "BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!" errors */
@@ -809,7 +810,8 @@ static int lock_torture_writer(void *arg)
bool skip_main_lock;
VERBOSE_TOROUT_STRING("lock_torture_writer task started");
- set_user_nice(current, MAX_NICE);
+ if (!rt_task(current))
+ set_user_nice(current, MAX_NICE);
do {
if ((torture_random(&rand) & 0xfffff) == 0)
@@ -1015,8 +1017,7 @@ static void lock_torture_cleanup(void)
if (writer_tasks) {
for (i = 0; i < cxt.nrealwriters_stress; i++)
- torture_stop_kthread(lock_torture_writer,
- writer_tasks[i]);
+ torture_stop_kthread(lock_torture_writer, writer_tasks[i]);
kfree(writer_tasks);
writer_tasks = NULL;
}
@@ -1244,8 +1245,9 @@ static int __init lock_torture_init(void)
goto create_reader;
/* Create writer. */
- firsterr = torture_create_kthread(lock_torture_writer, &cxt.lwsa[i],
- writer_tasks[i]);
+ firsterr = torture_create_kthread_cb(lock_torture_writer, &cxt.lwsa[i],
+ writer_tasks[i],
+ writer_fifo ? sched_set_fifo : NULL);
if (torture_init_error(firsterr))
goto unwind;
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 728f434de2bb..21db0df0eb00 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -333,21 +333,43 @@ static __always_inline int __waiter_prio(struct task_struct *task)
return prio;
}
+/*
+ * Update the waiter->tree copy of the sort keys.
+ */
static __always_inline void
waiter_update_prio(struct rt_mutex_waiter *waiter, struct task_struct *task)
{
- waiter->prio = __waiter_prio(task);
- waiter->deadline = task->dl.deadline;
+ lockdep_assert_held(&waiter->lock->wait_lock);
+ lockdep_assert(RB_EMPTY_NODE(&waiter->tree.entry));
+
+ waiter->tree.prio = __waiter_prio(task);
+ waiter->tree.deadline = task->dl.deadline;
+}
+
+/*
+ * Update the waiter->pi_tree copy of the sort keys (from the tree copy).
+ */
+static __always_inline void
+waiter_clone_prio(struct rt_mutex_waiter *waiter, struct task_struct *task)
+{
+ lockdep_assert_held(&waiter->lock->wait_lock);
+ lockdep_assert_held(&task->pi_lock);
+ lockdep_assert(RB_EMPTY_NODE(&waiter->pi_tree.entry));
+
+ waiter->pi_tree.prio = waiter->tree.prio;
+ waiter->pi_tree.deadline = waiter->tree.deadline;
}
/*
- * Only use with rt_mutex_waiter_{less,equal}()
+ * Only use with rt_waiter_node_{less,equal}()
*/
+#define task_to_waiter_node(p) \
+ &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
#define task_to_waiter(p) \
- &(struct rt_mutex_waiter){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
+ &(struct rt_mutex_waiter){ .tree = *task_to_waiter_node(p) }
-static __always_inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left,
- struct rt_mutex_waiter *right)
+static __always_inline int rt_waiter_node_less(struct rt_waiter_node *left,
+ struct rt_waiter_node *right)
{
if (left->prio < right->prio)
return 1;
@@ -364,8 +386,8 @@ static __always_inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left,
return 0;
}
-static __always_inline int rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
- struct rt_mutex_waiter *right)
+static __always_inline int rt_waiter_node_equal(struct rt_waiter_node *left,
+ struct rt_waiter_node *right)
{
if (left->prio != right->prio)
return 0;
@@ -385,7 +407,7 @@ static __always_inline int rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
struct rt_mutex_waiter *top_waiter)
{
- if (rt_mutex_waiter_less(waiter, top_waiter))
+ if (rt_waiter_node_less(&waiter->tree, &top_waiter->tree))
return true;
#ifdef RT_MUTEX_BUILD_SPINLOCKS
@@ -393,30 +415,30 @@ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
* Note that RT tasks are excluded from same priority (lateral)
* steals to prevent the introduction of an unbounded latency.
*/
- if (rt_prio(waiter->prio) || dl_prio(waiter->prio))
+ if (rt_prio(waiter->tree.prio) || dl_prio(waiter->tree.prio))
return false;
- return rt_mutex_waiter_equal(waiter, top_waiter);
+ return rt_waiter_node_equal(&waiter->tree, &top_waiter->tree);
#else
return false;
#endif
}
#define __node_2_waiter(node) \
- rb_entry((node), struct rt_mutex_waiter, tree_entry)
+ rb_entry((node), struct rt_mutex_waiter, tree.entry)
static __always_inline bool __waiter_less(struct rb_node *a, const struct rb_node *b)
{
struct rt_mutex_waiter *aw = __node_2_waiter(a);
struct rt_mutex_waiter *bw = __node_2_waiter(b);
- if (rt_mutex_waiter_less(aw, bw))
+ if (rt_waiter_node_less(&aw->tree, &bw->tree))
return 1;
if (!build_ww_mutex())
return 0;
- if (rt_mutex_waiter_less(bw, aw))
+ if (rt_waiter_node_less(&bw->tree, &aw->tree))
return 0;
/* NOTE: relies on waiter->ww_ctx being set before insertion */
@@ -434,48 +456,58 @@ static __always_inline bool __waiter_less(struct rb_node *a, const struct rb_nod
static __always_inline void
rt_mutex_enqueue(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter)
{
- rb_add_cached(&waiter->tree_entry, &lock->waiters, __waiter_less);
+ lockdep_assert_held(&lock->wait_lock);
+
+ rb_add_cached(&waiter->tree.entry, &lock->waiters, __waiter_less);
}
static __always_inline void
rt_mutex_dequeue(struct rt_mutex_base *lock, struct rt_mutex_waiter *waiter)
{
- if (RB_EMPTY_NODE(&waiter->tree_entry))
+ lockdep_assert_held(&lock->wait_lock);
+
+ if (RB_EMPTY_NODE(&waiter->tree.entry))
return;
- rb_erase_cached(&waiter->tree_entry, &lock->waiters);
- RB_CLEAR_NODE(&waiter->tree_entry);
+ rb_erase_cached(&waiter->tree.entry, &lock->waiters);
+ RB_CLEAR_NODE(&waiter->tree.entry);
}
-#define __node_2_pi_waiter(node) \
- rb_entry((node), struct rt_mutex_waiter, pi_tree_entry)
+#define __node_2_rt_node(node) \
+ rb_entry((node), struct rt_waiter_node, entry)
-static __always_inline bool
-__pi_waiter_less(struct rb_node *a, const struct rb_node *b)
+static __always_inline bool __pi_waiter_less(struct rb_node *a, const struct rb_node *b)
{
- return rt_mutex_waiter_less(__node_2_pi_waiter(a), __node_2_pi_waiter(b));
+ return rt_waiter_node_less(__node_2_rt_node(a), __node_2_rt_node(b));
}
static __always_inline void
rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
{
- rb_add_cached(&waiter->pi_tree_entry, &task->pi_waiters, __pi_waiter_less);
+ lockdep_assert_held(&task->pi_lock);
+
+ rb_add_cached(&waiter->pi_tree.entry, &task->pi_waiters, __pi_waiter_less);
}
static __always_inline void
rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
{
- if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
+ lockdep_assert_held(&task->pi_lock);
+
+ if (RB_EMPTY_NODE(&waiter->pi_tree.entry))
return;
- rb_erase_cached(&waiter->pi_tree_entry, &task->pi_waiters);
- RB_CLEAR_NODE(&waiter->pi_tree_entry);
+ rb_erase_cached(&waiter->pi_tree.entry, &task->pi_waiters);
+ RB_CLEAR_NODE(&waiter->pi_tree.entry);
}
-static __always_inline void rt_mutex_adjust_prio(struct task_struct *p)
+static __always_inline void rt_mutex_adjust_prio(struct rt_mutex_base *lock,
+ struct task_struct *p)
{
struct task_struct *pi_task = NULL;
+ lockdep_assert_held(&lock->wait_lock);
+ lockdep_assert(rt_mutex_owner(lock) == p);
lockdep_assert_held(&p->pi_lock);
if (task_has_pi_waiters(p))
@@ -571,9 +603,14 @@ static __always_inline struct rt_mutex_base *task_blocked_on_lock(struct task_st
* Chain walk basics and protection scope
*
* [R] refcount on task
- * [P] task->pi_lock held
+ * [Pn] task->pi_lock held
* [L] rtmutex->wait_lock held
*
+ * Normal locking order:
+ *
+ * rtmutex->wait_lock
+ * task->pi_lock
+ *
* Step Description Protected by
* function arguments:
* @task [R]
@@ -588,27 +625,32 @@ static __always_inline struct rt_mutex_base *task_blocked_on_lock(struct task_st
* again:
* loop_sanity_check();
* retry:
- * [1] lock(task->pi_lock); [R] acquire [P]
- * [2] waiter = task->pi_blocked_on; [P]
- * [3] check_exit_conditions_1(); [P]
- * [4] lock = waiter->lock; [P]
- * [5] if (!try_lock(lock->wait_lock)) { [P] try to acquire [L]
- * unlock(task->pi_lock); release [P]
+ * [1] lock(task->pi_lock); [R] acquire [P1]
+ * [2] waiter = task->pi_blocked_on; [P1]
+ * [3] check_exit_conditions_1(); [P1]
+ * [4] lock = waiter->lock; [P1]
+ * [5] if (!try_lock(lock->wait_lock)) { [P1] try to acquire [L]
+ * unlock(task->pi_lock); release [P1]
* goto retry;
* }
- * [6] check_exit_conditions_2(); [P] + [L]
- * [7] requeue_lock_waiter(lock, waiter); [P] + [L]
- * [8] unlock(task->pi_lock); release [P]
+ * [6] check_exit_conditions_2(); [P1] + [L]
+ * [7] requeue_lock_waiter(lock, waiter); [P1] + [L]
+ * [8] unlock(task->pi_lock); release [P1]
* put_task_struct(task); release [R]
* [9] check_exit_conditions_3(); [L]
* [10] task = owner(lock); [L]
* get_task_struct(task); [L] acquire [R]
- * lock(task->pi_lock); [L] acquire [P]
- * [11] requeue_pi_waiter(tsk, waiters(lock));[P] + [L]
- * [12] check_exit_conditions_4(); [P] + [L]
- * [13] unlock(task->pi_lock); release [P]
+ * lock(task->pi_lock); [L] acquire [P2]
+ * [11] requeue_pi_waiter(tsk, waiters(lock));[P2] + [L]
+ * [12] check_exit_conditions_4(); [P2] + [L]
+ * [13] unlock(task->pi_lock); release [P2]
* unlock(lock->wait_lock); release [L]
* goto again;
+ *
+ * Where P1 is the blocking task and P2 is the lock owner; going up one step
+ * the owner becomes the next blocked task etc..
+ *
+*
*/
static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
enum rtmutex_chainwalk chwalk,
@@ -756,7 +798,7 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
* enabled we continue, but stop the requeueing in the chain
* walk.
*/
- if (rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
+ if (rt_waiter_node_equal(&waiter->tree, task_to_waiter_node(task))) {
if (!detect_deadlock)
goto out_unlock_pi;
else
@@ -764,13 +806,18 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
}
/*
- * [4] Get the next lock
+ * [4] Get the next lock; per holding task->pi_lock we can't unblock
+ * and guarantee @lock's existence.
*/
lock = waiter->lock;
/*
* [5] We need to trylock here as we are holding task->pi_lock,
* which is the reverse lock order versus the other rtmutex
* operations.
+ *
+ * Per the above, holding task->pi_lock guarantees lock exists, so
+ * inverting this lock order is infeasible from a life-time
+ * perspective.
*/
if (!raw_spin_trylock(&lock->wait_lock)) {
raw_spin_unlock_irq(&task->pi_lock);
@@ -874,17 +921,18 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
* or
*
* DL CBS enforcement advancing the effective deadline.
- *
- * Even though pi_waiters also uses these fields, and that tree is only
- * updated in [11], we can do this here, since we hold [L], which
- * serializes all pi_waiters access and rb_erase() does not care about
- * the values of the node being removed.
*/
waiter_update_prio(waiter, task);
rt_mutex_enqueue(lock, waiter);
- /* [8] Release the task */
+ /*
+ * [8] Release the (blocking) task in preparation for
+ * taking the owner task in [10].
+ *
+ * Since we hold lock->waiter_lock, task cannot unblock, even if we
+ * release task->pi_lock.
+ */
raw_spin_unlock(&task->pi_lock);
put_task_struct(task);
@@ -908,7 +956,12 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
return 0;
}
- /* [10] Grab the next task, i.e. the owner of @lock */
+ /*
+ * [10] Grab the next task, i.e. the owner of @lock
+ *
+ * Per holding lock->wait_lock and checking for !owner above, there
+ * must be an owner and it cannot go away.
+ */
task = get_task_struct(rt_mutex_owner(lock));
raw_spin_lock(&task->pi_lock);
@@ -921,8 +974,9 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
* and adjust the priority of the owner.
*/
rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
+ waiter_clone_prio(waiter, task);
rt_mutex_enqueue_pi(task, waiter);
- rt_mutex_adjust_prio(task);
+ rt_mutex_adjust_prio(lock, task);
} else if (prerequeue_top_waiter == waiter) {
/*
@@ -937,8 +991,9 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
*/
rt_mutex_dequeue_pi(task, waiter);
waiter = rt_mutex_top_waiter(lock);
+ waiter_clone_prio(waiter, task);
rt_mutex_enqueue_pi(task, waiter);
- rt_mutex_adjust_prio(task);
+ rt_mutex_adjust_prio(lock, task);
} else {
/*
* Nothing changed. No need to do any priority
@@ -1154,6 +1209,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
waiter->task = task;
waiter->lock = lock;
waiter_update_prio(waiter, task);
+ waiter_clone_prio(waiter, task);
/* Get the top priority waiter on the lock */
if (rt_mutex_has_waiters(lock))
@@ -1187,7 +1243,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
rt_mutex_dequeue_pi(owner, top_waiter);
rt_mutex_enqueue_pi(owner, waiter);
- rt_mutex_adjust_prio(owner);
+ rt_mutex_adjust_prio(lock, owner);
if (owner->pi_blocked_on)
chain_walk = 1;
} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
@@ -1234,6 +1290,8 @@ static void __sched mark_wakeup_next_waiter(struct rt_wake_q_head *wqh,
{
struct rt_mutex_waiter *waiter;
+ lockdep_assert_held(&lock->wait_lock);
+
raw_spin_lock(&current->pi_lock);
waiter = rt_mutex_top_waiter(lock);
@@ -1246,7 +1304,7 @@ static void __sched mark_wakeup_next_waiter(struct rt_wake_q_head *wqh,
* task unblocks.
*/
rt_mutex_dequeue_pi(current, waiter);
- rt_mutex_adjust_prio(current);
+ rt_mutex_adjust_prio(lock, current);
/*
* As we are waking up the top waiter, and the waiter stays
@@ -1482,7 +1540,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
if (rt_mutex_has_waiters(lock))
rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
- rt_mutex_adjust_prio(owner);
+ rt_mutex_adjust_prio(lock, owner);
/* Store the lock on which owner is blocked or NULL */
next_lock = task_blocked_on_lock(owner);
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index cb9fdff76a8a..a6974d044593 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -459,7 +459,7 @@ void __sched rt_mutex_adjust_pi(struct task_struct *task)
raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
- if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
+ if (!waiter || rt_waiter_node_equal(&waiter->tree, task_to_waiter_node(task))) {
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index c47e8361bfb5..1162e07cdaea 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -17,27 +17,44 @@
#include <linux/rtmutex.h>
#include <linux/sched/wake_q.h>
+
+/*
+ * This is a helper for the struct rt_mutex_waiter below. A waiter goes in two
+ * separate trees and they need their own copy of the sort keys because of
+ * different locking requirements.
+ *
+ * @entry: rbtree node to enqueue into the waiters tree
+ * @prio: Priority of the waiter
+ * @deadline: Deadline of the waiter if applicable
+ *
+ * See rt_waiter_node_less() and waiter_*_prio().
+ */
+struct rt_waiter_node {
+ struct rb_node entry;
+ int prio;
+ u64 deadline;
+};
+
/*
* This is the control structure for tasks blocked on a rt_mutex,
* which is allocated on the kernel stack on of the blocked task.
*
- * @tree_entry: pi node to enqueue into the mutex waiters tree
- * @pi_tree_entry: pi node to enqueue into the mutex owner waiters tree
+ * @tree: node to enqueue into the mutex waiters tree
+ * @pi_tree: node to enqueue into the mutex owner waiters tree
* @task: task reference to the blocked task
* @lock: Pointer to the rt_mutex on which the waiter blocks
* @wake_state: Wakeup state to use (TASK_NORMAL or TASK_RTLOCK_WAIT)
- * @prio: Priority of the waiter
- * @deadline: Deadline of the waiter if applicable
* @ww_ctx: WW context pointer
+ *
+ * @tree is ordered by @lock->wait_lock
+ * @pi_tree is ordered by rt_mutex_owner(@lock)->pi_lock
*/
struct rt_mutex_waiter {
- struct rb_node tree_entry;
- struct rb_node pi_tree_entry;
+ struct rt_waiter_node tree;
+ struct rt_waiter_node pi_tree;
struct task_struct *task;
struct rt_mutex_base *lock;
unsigned int wake_state;
- int prio;
- u64 deadline;
struct ww_acquire_ctx *ww_ctx;
};
@@ -105,7 +122,7 @@ static inline bool rt_mutex_waiter_is_top_waiter(struct rt_mutex_base *lock,
{
struct rb_node *leftmost = rb_first_cached(&lock->waiters);
- return rb_entry(leftmost, struct rt_mutex_waiter, tree_entry) == waiter;
+ return rb_entry(leftmost, struct rt_mutex_waiter, tree.entry) == waiter;
}
static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex_base *lock)
@@ -113,8 +130,10 @@ static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex_base *
struct rb_node *leftmost = rb_first_cached(&lock->waiters);
struct rt_mutex_waiter *w = NULL;
+ lockdep_assert_held(&lock->wait_lock);
+
if (leftmost) {
- w = rb_entry(leftmost, struct rt_mutex_waiter, tree_entry);
+ w = rb_entry(leftmost, struct rt_mutex_waiter, tree.entry);
BUG_ON(w->lock != lock);
}
return w;
@@ -127,8 +146,10 @@ static inline int task_has_pi_waiters(struct task_struct *p)
static inline struct rt_mutex_waiter *task_top_pi_waiter(struct task_struct *p)
{
+ lockdep_assert_held(&p->pi_lock);
+
return rb_entry(p->pi_waiters.rb_leftmost, struct rt_mutex_waiter,
- pi_tree_entry);
+ pi_tree.entry);
}
#define RT_MUTEX_HAS_WAITERS 1UL
@@ -190,8 +211,8 @@ static inline void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
static inline void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
{
debug_rt_mutex_init_waiter(waiter);
- RB_CLEAR_NODE(&waiter->pi_tree_entry);
- RB_CLEAR_NODE(&waiter->tree_entry);
+ RB_CLEAR_NODE(&waiter->pi_tree.entry);
+ RB_CLEAR_NODE(&waiter->tree.entry);
waiter->wake_state = TASK_NORMAL;
waiter->task = NULL;
}
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 56f139201f24..3ad2cc4823e5 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -96,25 +96,25 @@ __ww_waiter_first(struct rt_mutex *lock)
struct rb_node *n = rb_first(&lock->rtmutex.waiters.rb_root);
if (!n)
return NULL;
- return rb_entry(n, struct rt_mutex_waiter, tree_entry);
+ return rb_entry(n, struct rt_mutex_waiter, tree.entry);
}
static inline struct rt_mutex_waiter *
__ww_waiter_next(struct rt_mutex *lock, struct rt_mutex_waiter *w)
{
- struct rb_node *n = rb_next(&w->tree_entry);
+ struct rb_node *n = rb_next(&w->tree.entry);
if (!n)
return NULL;
- return rb_entry(n, struct rt_mutex_waiter, tree_entry);
+ return rb_entry(n, struct rt_mutex_waiter, tree.entry);
}
static inline struct rt_mutex_waiter *
__ww_waiter_prev(struct rt_mutex *lock, struct rt_mutex_waiter *w)
{
- struct rb_node *n = rb_prev(&w->tree_entry);
+ struct rb_node *n = rb_prev(&w->tree.entry);
if (!n)
return NULL;
- return rb_entry(n, struct rt_mutex_waiter, tree_entry);
+ return rb_entry(n, struct rt_mutex_waiter, tree.entry);
}
static inline struct rt_mutex_waiter *
@@ -123,7 +123,7 @@ __ww_waiter_last(struct rt_mutex *lock)
struct rb_node *n = rb_last(&lock->rtmutex.waiters.rb_root);
if (!n)
return NULL;
- return rb_entry(n, struct rt_mutex_waiter, tree_entry);
+ return rb_entry(n, struct rt_mutex_waiter, tree.entry);
}
static inline void
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 80d9c6d77a45..15781acaac1c 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -30,7 +30,7 @@
static struct kmem_cache *nsproxy_cachep;
struct nsproxy init_nsproxy = {
- .count = ATOMIC_INIT(1),
+ .count = REFCOUNT_INIT(1),
.uts_ns = &init_uts_ns,
#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
.ipc_ns = &init_ipc_ns,
@@ -55,7 +55,7 @@ static inline struct nsproxy *create_nsproxy(void)
nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
if (nsproxy)
- atomic_set(&nsproxy->count, 1);
+ refcount_set(&nsproxy->count, 1);
return nsproxy;
}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index e1b4bfa938dd..2b4a946a6ff5 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -1166,7 +1166,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
int error;
if (!hibernation_available())
- return 0;
+ return n;
if (len && buf[len-1] == '\n')
len--;
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 98c1544cf572..5befd8780dcd 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -511,6 +511,14 @@ static inline void show_rcu_tasks_gp_kthreads(void) {}
void rcu_request_urgent_qs_task(struct task_struct *t);
#endif /* #else #ifdef CONFIG_TINY_RCU */
+#ifdef CONFIG_TASKS_RCU
+struct task_struct *get_rcu_tasks_gp_kthread(void);
+#endif // # ifdef CONFIG_TASKS_RCU
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+struct task_struct *get_rcu_tasks_rude_gp_kthread(void);
+#endif // # ifdef CONFIG_TASKS_RUDE_RCU
+
#define RCU_SCHEDULER_INACTIVE 0
#define RCU_SCHEDULER_INIT 1
#define RCU_SCHEDULER_RUNNING 2
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index d1221731c7cf..ffdb30495e3c 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -84,15 +84,17 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
#endif
torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
-torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
+torture_param(int, gp_async_max, 1000, "Max # outstanding waits per writer");
torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
+torture_param(int, minruntime, 0, "Minimum run time (s)");
torture_param(int, nreaders, -1, "Number of RCU reader threads");
torture_param(int, nwriters, -1, "Number of RCU updater threads");
torture_param(bool, shutdown, RCUSCALE_SHUTDOWN,
"Shutdown at end of scalability tests.");
torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
+torture_param(int, writer_holdoff_jiffies, 0, "Holdoff (jiffies) between GPs, zero to disable");
torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() scale test?");
torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate.");
torture_param(int, kfree_by_call_rcu, 0, "Use call_rcu() to emulate kfree_rcu()?");
@@ -139,6 +141,7 @@ struct rcu_scale_ops {
void (*gp_barrier)(void);
void (*sync)(void);
void (*exp_sync)(void);
+ struct task_struct *(*rso_gp_kthread)(void);
const char *name;
};
@@ -295,6 +298,7 @@ static struct rcu_scale_ops tasks_ops = {
.gp_barrier = rcu_barrier_tasks,
.sync = synchronize_rcu_tasks,
.exp_sync = synchronize_rcu_tasks,
+ .rso_gp_kthread = get_rcu_tasks_gp_kthread,
.name = "tasks"
};
@@ -306,6 +310,44 @@ static struct rcu_scale_ops tasks_ops = {
#endif // #else // #ifdef CONFIG_TASKS_RCU
+#ifdef CONFIG_TASKS_RUDE_RCU
+
+/*
+ * Definitions for RCU-tasks-rude scalability testing.
+ */
+
+static int tasks_rude_scale_read_lock(void)
+{
+ return 0;
+}
+
+static void tasks_rude_scale_read_unlock(int idx)
+{
+}
+
+static struct rcu_scale_ops tasks_rude_ops = {
+ .ptype = RCU_TASKS_RUDE_FLAVOR,
+ .init = rcu_sync_scale_init,
+ .readlock = tasks_rude_scale_read_lock,
+ .readunlock = tasks_rude_scale_read_unlock,
+ .get_gp_seq = rcu_no_completed,
+ .gp_diff = rcu_seq_diff,
+ .async = call_rcu_tasks_rude,
+ .gp_barrier = rcu_barrier_tasks_rude,
+ .sync = synchronize_rcu_tasks_rude,
+ .exp_sync = synchronize_rcu_tasks_rude,
+ .rso_gp_kthread = get_rcu_tasks_rude_gp_kthread,
+ .name = "tasks-rude"
+};
+
+#define TASKS_RUDE_OPS &tasks_rude_ops,
+
+#else // #ifdef CONFIG_TASKS_RUDE_RCU
+
+#define TASKS_RUDE_OPS
+
+#endif // #else // #ifdef CONFIG_TASKS_RUDE_RCU
+
#ifdef CONFIG_TASKS_TRACE_RCU
/*
@@ -334,6 +376,7 @@ static struct rcu_scale_ops tasks_tracing_ops = {
.gp_barrier = rcu_barrier_tasks_trace,
.sync = synchronize_rcu_tasks_trace,
.exp_sync = synchronize_rcu_tasks_trace,
+ .rso_gp_kthread = get_rcu_tasks_trace_gp_kthread,
.name = "tasks-tracing"
};
@@ -410,10 +453,12 @@ rcu_scale_writer(void *arg)
{
int i = 0;
int i_max;
+ unsigned long jdone;
long me = (long)arg;
struct rcu_head *rhp = NULL;
bool started = false, done = false, alldone = false;
u64 t;
+ DEFINE_TORTURE_RANDOM(tr);
u64 *wdp;
u64 *wdpp = writer_durations[me];
@@ -424,7 +469,7 @@ rcu_scale_writer(void *arg)
sched_set_fifo_low(current);
if (holdoff)
- schedule_timeout_uninterruptible(holdoff * HZ);
+ schedule_timeout_idle(holdoff * HZ);
/*
* Wait until rcu_end_inkernel_boot() is called for normal GP tests
@@ -445,9 +490,12 @@ rcu_scale_writer(void *arg)
}
}
+ jdone = jiffies + minruntime * HZ;
do {
if (writer_holdoff)
udelay(writer_holdoff);
+ if (writer_holdoff_jiffies)
+ schedule_timeout_idle(torture_random(&tr) % writer_holdoff_jiffies + 1);
wdp = &wdpp[i];
*wdp = ktime_get_mono_fast_ns();
if (gp_async) {
@@ -475,7 +523,7 @@ retry:
if (!started &&
atomic_read(&n_rcu_scale_writer_started) >= nrealwriters)
started = true;
- if (!done && i >= MIN_MEAS) {
+ if (!done && i >= MIN_MEAS && time_after(jiffies, jdone)) {
done = true;
sched_set_normal(current, 0);
pr_alert("%s%s rcu_scale_writer %ld has %d measurements\n",
@@ -518,8 +566,8 @@ static void
rcu_scale_print_module_parms(struct rcu_scale_ops *cur_ops, const char *tag)
{
pr_alert("%s" SCALE_FLAG
- "--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n",
- scale_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
+ "--- %s: gp_async=%d gp_async_max=%d gp_exp=%d holdoff=%d minruntime=%d nreaders=%d nwriters=%d writer_holdoff=%d writer_holdoff_jiffies=%d verbose=%d shutdown=%d\n",
+ scale_type, tag, gp_async, gp_async_max, gp_exp, holdoff, minruntime, nrealreaders, nrealwriters, writer_holdoff, writer_holdoff_jiffies, verbose, shutdown);
}
/*
@@ -556,6 +604,8 @@ static struct task_struct **kfree_reader_tasks;
static int kfree_nrealthreads;
static atomic_t n_kfree_scale_thread_started;
static atomic_t n_kfree_scale_thread_ended;
+static struct task_struct *kthread_tp;
+static u64 kthread_stime;
struct kfree_obj {
char kfree_obj[8];
@@ -701,6 +751,10 @@ kfree_scale_init(void)
unsigned long jif_start;
unsigned long orig_jif;
+ pr_alert("%s" SCALE_FLAG
+ "--- kfree_rcu_test: kfree_mult=%d kfree_by_call_rcu=%d kfree_nthreads=%d kfree_alloc_num=%d kfree_loops=%d kfree_rcu_test_double=%d kfree_rcu_test_single=%d\n",
+ scale_type, kfree_mult, kfree_by_call_rcu, kfree_nthreads, kfree_alloc_num, kfree_loops, kfree_rcu_test_double, kfree_rcu_test_single);
+
// Also, do a quick self-test to ensure laziness is as much as
// expected.
if (kfree_by_call_rcu && !IS_ENABLED(CONFIG_RCU_LAZY)) {
@@ -797,6 +851,18 @@ rcu_scale_cleanup(void)
if (gp_exp && gp_async)
SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");
+ // If built-in, just report all of the GP kthread's CPU time.
+ if (IS_BUILTIN(CONFIG_RCU_SCALE_TEST) && !kthread_tp && cur_ops->rso_gp_kthread)
+ kthread_tp = cur_ops->rso_gp_kthread();
+ if (kthread_tp) {
+ u32 ns;
+ u64 us;
+
+ kthread_stime = kthread_tp->stime - kthread_stime;
+ us = div_u64_rem(kthread_stime, 1000, &ns);
+ pr_info("rcu_scale: Grace-period kthread CPU time: %llu.%03u us\n", us, ns);
+ show_rcu_gp_kthreads();
+ }
if (kfree_rcu_test) {
kfree_scale_cleanup();
return;
@@ -885,7 +951,7 @@ rcu_scale_init(void)
long i;
int firsterr = 0;
static struct rcu_scale_ops *scale_ops[] = {
- &rcu_ops, &srcu_ops, &srcud_ops, TASKS_OPS TASKS_TRACING_OPS
+ &rcu_ops, &srcu_ops, &srcud_ops, TASKS_OPS TASKS_RUDE_OPS TASKS_TRACING_OPS
};
if (!torture_init_begin(scale_type, verbose))
@@ -910,6 +976,11 @@ rcu_scale_init(void)
if (cur_ops->init)
cur_ops->init();
+ if (cur_ops->rso_gp_kthread) {
+ kthread_tp = cur_ops->rso_gp_kthread();
+ if (kthread_tp)
+ kthread_stime = kthread_tp->stime;
+ }
if (kfree_rcu_test)
return kfree_scale_init();
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 147551c23baf..ade42d6a9d9b 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1581,6 +1581,7 @@ rcu_torture_writer(void *arg)
rcu_access_pointer(rcu_torture_current) !=
&rcu_tortures[i]) {
tracing_off();
+ show_rcu_gp_kthreads();
WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count);
rcu_ftrace_dump(DUMP_ALL);
}
@@ -1876,7 +1877,7 @@ static int
rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
{
int mask = rcutorture_extend_mask_max();
- unsigned long randmask1 = torture_random(trsp) >> 8;
+ unsigned long randmask1 = torture_random(trsp);
unsigned long randmask2 = randmask1 >> 3;
unsigned long preempts = RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED;
unsigned long preempts_irq = preempts | RCUTORTURE_RDR_IRQ;
@@ -1935,7 +1936,7 @@ rcutorture_loop_extend(int *readstate, struct torture_random_state *trsp,
if (!((mask - 1) & mask))
return rtrsp; /* Current RCU reader not extendable. */
/* Bias towards larger numbers of loops. */
- i = (torture_random(trsp) >> 3);
+ i = torture_random(trsp);
i = ((i | (i >> 3)) & RCUTORTURE_RDR_MAX_LOOPS) + 1;
for (j = 0; j < i; j++) {
mask = rcutorture_extend_mask(*readstate, trsp);
@@ -2136,7 +2137,7 @@ static int rcu_nocb_toggle(void *arg)
toggle_fuzz = NSEC_PER_USEC;
do {
r = torture_random(&rand);
- cpu = (r >> 4) % (maxcpu + 1);
+ cpu = (r >> 1) % (maxcpu + 1);
if (r & 0x1) {
rcu_nocb_cpu_offload(cpu);
atomic_long_inc(&n_nocb_offload);
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index 1970ce5f22d4..91a0fd0d4d9a 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -528,6 +528,38 @@ static struct ref_scale_ops clock_ops = {
.name = "clock"
};
+static void ref_jiffies_section(const int nloops)
+{
+ u64 x = 0;
+ int i;
+
+ preempt_disable();
+ for (i = nloops; i >= 0; i--)
+ x += jiffies;
+ preempt_enable();
+ stopopts = x;
+}
+
+static void ref_jiffies_delay_section(const int nloops, const int udl, const int ndl)
+{
+ u64 x = 0;
+ int i;
+
+ preempt_disable();
+ for (i = nloops; i >= 0; i--) {
+ x += jiffies;
+ un_delay(udl, ndl);
+ }
+ preempt_enable();
+ stopopts = x;
+}
+
+static struct ref_scale_ops jiffies_ops = {
+ .readsection = ref_jiffies_section,
+ .delaysection = ref_jiffies_delay_section,
+ .name = "jiffies"
+};
+
////////////////////////////////////////////////////////////////////////
//
// Methods leveraging SLAB_TYPESAFE_BY_RCU.
@@ -1047,7 +1079,7 @@ ref_scale_init(void)
int firsterr = 0;
static struct ref_scale_ops *scale_ops[] = {
&rcu_ops, &srcu_ops, RCU_TRACE_OPS RCU_TASKS_OPS &refcnt_ops, &rwlock_ops,
- &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops,
+ &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops, &jiffies_ops,
&typesafe_ref_ops, &typesafe_lock_ops, &typesafe_seqlock_ops,
};
@@ -1107,12 +1139,11 @@ ref_scale_init(void)
VERBOSE_SCALEOUT("Starting %d reader threads", nreaders);
for (i = 0; i < nreaders; i++) {
+ init_waitqueue_head(&reader_tasks[i].wq);
firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
reader_tasks[i].task);
if (torture_init_error(firsterr))
goto unwind;
-
- init_waitqueue_head(&(reader_tasks[i].wq));
}
// Main Task
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index b770add3f843..8d65f7d576a3 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -25,6 +25,8 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
* @cblist: Callback list.
* @lock: Lock protecting per-CPU callback list.
* @rtp_jiffies: Jiffies counter value for statistics.
+ * @lazy_timer: Timer to unlazify callbacks.
+ * @urgent_gp: Number of additional non-lazy grace periods.
* @rtp_n_lock_retries: Rough lock-contention statistic.
* @rtp_work: Work queue for invoking callbacks.
* @rtp_irq_work: IRQ work queue for deferred wakeups.
@@ -38,6 +40,8 @@ struct rcu_tasks_percpu {
raw_spinlock_t __private lock;
unsigned long rtp_jiffies;
unsigned long rtp_n_lock_retries;
+ struct timer_list lazy_timer;
+ unsigned int urgent_gp;
struct work_struct rtp_work;
struct irq_work rtp_irq_work;
struct rcu_head barrier_q_head;
@@ -51,7 +55,6 @@ struct rcu_tasks_percpu {
* @cbs_wait: RCU wait allowing a new callback to get kthread's attention.
* @cbs_gbl_lock: Lock protecting callback list.
* @tasks_gp_mutex: Mutex protecting grace period, needed during mid-boot dead zone.
- * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
* @gp_func: This flavor's grace-period-wait function.
* @gp_state: Grace period's most recent state transition (debugging).
* @gp_sleep: Per-grace-period sleep to prevent CPU-bound looping.
@@ -61,6 +64,8 @@ struct rcu_tasks_percpu {
* @tasks_gp_seq: Number of grace periods completed since boot.
* @n_ipis: Number of IPIs sent to encourage grace periods to end.
* @n_ipis_fails: Number of IPI-send failures.
+ * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
+ * @lazy_jiffies: Number of jiffies to allow callbacks to be lazy.
* @pregp_func: This flavor's pre-grace-period function (optional).
* @pertask_func: This flavor's per-task scan function (optional).
* @postscan_func: This flavor's post-task scan function (optional).
@@ -92,6 +97,7 @@ struct rcu_tasks {
unsigned long n_ipis;
unsigned long n_ipis_fails;
struct task_struct *kthread_ptr;
+ unsigned long lazy_jiffies;
rcu_tasks_gp_func_t gp_func;
pregp_func_t pregp_func;
pertask_func_t pertask_func;
@@ -127,6 +133,7 @@ static struct rcu_tasks rt_name = \
.gp_func = gp, \
.call_func = call, \
.rtpcpu = &rt_name ## __percpu, \
+ .lazy_jiffies = DIV_ROUND_UP(HZ, 4), \
.name = n, \
.percpu_enqueue_shift = order_base_2(CONFIG_NR_CPUS), \
.percpu_enqueue_lim = 1, \
@@ -139,9 +146,7 @@ static struct rcu_tasks rt_name = \
#ifdef CONFIG_TASKS_RCU
/* Track exiting tasks in order to allow them to be waited for. */
DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
-#endif
-#ifdef CONFIG_TASKS_RCU
/* Report delay in synchronize_srcu() completion in rcu_tasks_postscan(). */
static void tasks_rcu_exit_srcu_stall(struct timer_list *unused);
static DEFINE_TIMER(tasks_rcu_exit_srcu_stall_timer, tasks_rcu_exit_srcu_stall);
@@ -171,6 +176,8 @@ static int rcu_task_contend_lim __read_mostly = 100;
module_param(rcu_task_contend_lim, int, 0444);
static int rcu_task_collapse_lim __read_mostly = 10;
module_param(rcu_task_collapse_lim, int, 0444);
+static int rcu_task_lazy_lim __read_mostly = 32;
+module_param(rcu_task_lazy_lim, int, 0444);
/* RCU tasks grace-period state for debugging. */
#define RTGS_INIT 0
@@ -229,7 +236,7 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
#endif /* #ifndef CONFIG_TINY_RCU */
// Initialize per-CPU callback lists for the specified flavor of
-// Tasks RCU.
+// Tasks RCU. Do not enqueue callbacks before this function is invoked.
static void cblist_init_generic(struct rcu_tasks *rtp)
{
int cpu;
@@ -237,7 +244,6 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
int lim;
int shift;
- raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
if (rcu_task_enqueue_lim < 0) {
rcu_task_enqueue_lim = 1;
rcu_task_cb_adjust = true;
@@ -260,22 +266,48 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
WARN_ON_ONCE(!rtpcp);
if (cpu)
raw_spin_lock_init(&ACCESS_PRIVATE(rtpcp, lock));
- raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
+ local_irq_save(flags); // serialize initialization
if (rcu_segcblist_empty(&rtpcp->cblist))
rcu_segcblist_init(&rtpcp->cblist);
+ local_irq_restore(flags);
INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq);
rtpcp->cpu = cpu;
rtpcp->rtpp = rtp;
if (!rtpcp->rtp_blkd_tasks.next)
INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
- raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
}
- raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name,
data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim), rcu_task_cb_adjust);
}
+// Compute wakeup time for lazy callback timer.
+static unsigned long rcu_tasks_lazy_time(struct rcu_tasks *rtp)
+{
+ return jiffies + rtp->lazy_jiffies;
+}
+
+// Timer handler that unlazifies lazy callbacks.
+static void call_rcu_tasks_generic_timer(struct timer_list *tlp)
+{
+ unsigned long flags;
+ bool needwake = false;
+ struct rcu_tasks *rtp;
+ struct rcu_tasks_percpu *rtpcp = from_timer(rtpcp, tlp, lazy_timer);
+
+ rtp = rtpcp->rtpp;
+ raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+ if (!rcu_segcblist_empty(&rtpcp->cblist) && rtp->lazy_jiffies) {
+ if (!rtpcp->urgent_gp)
+ rtpcp->urgent_gp = 1;
+ needwake = true;
+ mod_timer(&rtpcp->lazy_timer, rcu_tasks_lazy_time(rtp));
+ }
+ raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+ if (needwake)
+ rcuwait_wake_up(&rtp->cbs_wait);
+}
+
// IRQ-work handler that does deferred wakeup for call_rcu_tasks_generic().
static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp)
{
@@ -292,6 +324,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
{
int chosen_cpu;
unsigned long flags;
+ bool havekthread = smp_load_acquire(&rtp->kthread_ptr);
int ideal_cpu;
unsigned long j;
bool needadjust = false;
@@ -316,12 +349,19 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
READ_ONCE(rtp->percpu_enqueue_lim) != nr_cpu_ids)
needadjust = true; // Defer adjustment to avoid deadlock.
}
- if (!rcu_segcblist_is_enabled(&rtpcp->cblist)) {
- raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
- cblist_init_generic(rtp);
- raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
+ // Queuing callbacks before initialization not yet supported.
+ if (WARN_ON_ONCE(!rcu_segcblist_is_enabled(&rtpcp->cblist)))
+ rcu_segcblist_init(&rtpcp->cblist);
+ needwake = (func == wakeme_after_rcu) ||
+ (rcu_segcblist_n_cbs(&rtpcp->cblist) == rcu_task_lazy_lim);
+ if (havekthread && !needwake && !timer_pending(&rtpcp->lazy_timer)) {
+ if (rtp->lazy_jiffies)
+ mod_timer(&rtpcp->lazy_timer, rcu_tasks_lazy_time(rtp));
+ else
+ needwake = rcu_segcblist_empty(&rtpcp->cblist);
}
- needwake = rcu_segcblist_empty(&rtpcp->cblist);
+ if (needwake)
+ rtpcp->urgent_gp = 3;
rcu_segcblist_enqueue(&rtpcp->cblist, rhp);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
if (unlikely(needadjust)) {
@@ -415,9 +455,14 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
}
rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq));
(void)rcu_segcblist_accelerate(&rtpcp->cblist, rcu_seq_snap(&rtp->tasks_gp_seq));
- if (rcu_segcblist_pend_cbs(&rtpcp->cblist))
+ if (rtpcp->urgent_gp > 0 && rcu_segcblist_pend_cbs(&rtpcp->cblist)) {
+ if (rtp->lazy_jiffies)
+ rtpcp->urgent_gp--;
needgpcb |= 0x3;
- if (!rcu_segcblist_empty(&rtpcp->cblist))
+ } else if (rcu_segcblist_empty(&rtpcp->cblist)) {
+ rtpcp->urgent_gp = 0;
+ }
+ if (rcu_segcblist_ready_cbs(&rtpcp->cblist))
needgpcb |= 0x1;
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
}
@@ -525,10 +570,12 @@ static void rcu_tasks_one_gp(struct rcu_tasks *rtp, bool midboot)
if (unlikely(midboot)) {
needgpcb = 0x2;
} else {
+ mutex_unlock(&rtp->tasks_gp_mutex);
set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
rcuwait_wait_event(&rtp->cbs_wait,
(needgpcb = rcu_tasks_need_gpcb(rtp)),
TASK_IDLE);
+ mutex_lock(&rtp->tasks_gp_mutex);
}
if (needgpcb & 0x2) {
@@ -549,11 +596,19 @@ static void rcu_tasks_one_gp(struct rcu_tasks *rtp, bool midboot)
// RCU-tasks kthread that detects grace periods and invokes callbacks.
static int __noreturn rcu_tasks_kthread(void *arg)
{
+ int cpu;
struct rcu_tasks *rtp = arg;
+ for_each_possible_cpu(cpu) {
+ struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
+
+ timer_setup(&rtpcp->lazy_timer, call_rcu_tasks_generic_timer, 0);
+ rtpcp->urgent_gp = 1;
+ }
+
/* Run on housekeeping CPUs by default. Sysadm can move if desired. */
housekeeping_affine(current, HK_TYPE_RCU);
- WRITE_ONCE(rtp->kthread_ptr, current); // Let GPs start!
+ smp_store_release(&rtp->kthread_ptr, current); // Let GPs start!
/*
* Each pass through the following loop makes one check for
@@ -635,16 +690,22 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
{
int cpu;
bool havecbs = false;
+ bool haveurgent = false;
+ bool haveurgentcbs = false;
for_each_possible_cpu(cpu) {
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
- if (!data_race(rcu_segcblist_empty(&rtpcp->cblist))) {
+ if (!data_race(rcu_segcblist_empty(&rtpcp->cblist)))
havecbs = true;
+ if (data_race(rtpcp->urgent_gp))
+ haveurgent = true;
+ if (!data_race(rcu_segcblist_empty(&rtpcp->cblist)) && data_race(rtpcp->urgent_gp))
+ haveurgentcbs = true;
+ if (havecbs && haveurgent && haveurgentcbs)
break;
- }
}
- pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c %s\n",
+ pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c%c%c l:%lu %s\n",
rtp->kname,
tasks_gp_state_getname(rtp), data_race(rtp->gp_state),
jiffies - data_race(rtp->gp_jiffies),
@@ -652,6 +713,9 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
data_race(rtp->n_ipis_fails), data_race(rtp->n_ipis),
".k"[!!data_race(rtp->kthread_ptr)],
".C"[havecbs],
+ ".u"[haveurgent],
+ ".U"[haveurgentcbs],
+ rtp->lazy_jiffies,
s);
}
#endif // #ifndef CONFIG_TINY_RCU
@@ -1020,11 +1084,16 @@ void rcu_barrier_tasks(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
+int rcu_tasks_lazy_ms = -1;
+module_param(rcu_tasks_lazy_ms, int, 0444);
+
static int __init rcu_spawn_tasks_kthread(void)
{
cblist_init_generic(&rcu_tasks);
rcu_tasks.gp_sleep = HZ / 10;
rcu_tasks.init_fract = HZ / 10;
+ if (rcu_tasks_lazy_ms >= 0)
+ rcu_tasks.lazy_jiffies = msecs_to_jiffies(rcu_tasks_lazy_ms);
rcu_tasks.pregp_func = rcu_tasks_pregp_step;
rcu_tasks.pertask_func = rcu_tasks_pertask;
rcu_tasks.postscan_func = rcu_tasks_postscan;
@@ -1042,6 +1111,12 @@ void show_rcu_tasks_classic_gp_kthread(void)
EXPORT_SYMBOL_GPL(show_rcu_tasks_classic_gp_kthread);
#endif // !defined(CONFIG_TINY_RCU)
+struct task_struct *get_rcu_tasks_gp_kthread(void)
+{
+ return rcu_tasks.kthread_ptr;
+}
+EXPORT_SYMBOL_GPL(get_rcu_tasks_gp_kthread);
+
/*
* Contribute to protect against tasklist scan blind spot while the
* task is exiting and may be removed from the tasklist. See
@@ -1173,10 +1248,15 @@ void rcu_barrier_tasks_rude(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks_rude);
+int rcu_tasks_rude_lazy_ms = -1;
+module_param(rcu_tasks_rude_lazy_ms, int, 0444);
+
static int __init rcu_spawn_tasks_rude_kthread(void)
{
cblist_init_generic(&rcu_tasks_rude);
rcu_tasks_rude.gp_sleep = HZ / 10;
+ if (rcu_tasks_rude_lazy_ms >= 0)
+ rcu_tasks_rude.lazy_jiffies = msecs_to_jiffies(rcu_tasks_rude_lazy_ms);
rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
return 0;
}
@@ -1188,6 +1268,13 @@ void show_rcu_tasks_rude_gp_kthread(void)
}
EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
#endif // !defined(CONFIG_TINY_RCU)
+
+struct task_struct *get_rcu_tasks_rude_gp_kthread(void)
+{
+ return rcu_tasks_rude.kthread_ptr;
+}
+EXPORT_SYMBOL_GPL(get_rcu_tasks_rude_gp_kthread);
+
#endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
////////////////////////////////////////////////////////////////////////
@@ -1793,6 +1880,9 @@ void rcu_barrier_tasks_trace(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace);
+int rcu_tasks_trace_lazy_ms = -1;
+module_param(rcu_tasks_trace_lazy_ms, int, 0444);
+
static int __init rcu_spawn_tasks_trace_kthread(void)
{
cblist_init_generic(&rcu_tasks_trace);
@@ -1807,6 +1897,8 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
if (rcu_tasks_trace.init_fract <= 0)
rcu_tasks_trace.init_fract = 1;
}
+ if (rcu_tasks_trace_lazy_ms >= 0)
+ rcu_tasks_trace.lazy_jiffies = msecs_to_jiffies(rcu_tasks_trace_lazy_ms);
rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step;
rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan;
rcu_tasks_trace.holdouts_func = check_all_holdout_tasks_trace;
@@ -1830,6 +1922,12 @@ void show_rcu_tasks_trace_gp_kthread(void)
EXPORT_SYMBOL_GPL(show_rcu_tasks_trace_gp_kthread);
#endif // !defined(CONFIG_TINY_RCU)
+struct task_struct *get_rcu_tasks_trace_gp_kthread(void)
+{
+ return rcu_tasks_trace.kthread_ptr;
+}
+EXPORT_SYMBOL_GPL(get_rcu_tasks_trace_gp_kthread);
+
#else /* #ifdef CONFIG_TASKS_TRACE_RCU */
static void exit_tasks_rcu_finish_trace(struct task_struct *t) { }
#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1449cb69a0e0..cb1caefa8bd0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -632,7 +632,7 @@ void __rcu_irq_enter_check_tick(void)
// prevents self-deadlock. So we can safely recheck under the lock.
// Note that the nohz_full state currently cannot change.
raw_spin_lock_rcu_node(rdp->mynode);
- if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
+ if (READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) {
// A nohz_full CPU is in the kernel and RCU needs a
// quiescent state. Turn on the tick!
WRITE_ONCE(rdp->rcu_forced_tick, true);
@@ -677,12 +677,16 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
}
/**
- * rcu_is_watching - see if RCU thinks that the current CPU is not idle
+ * rcu_is_watching - RCU read-side critical sections permitted on current CPU?
*
- * Return true if RCU is watching the running CPU, which means that this
- * CPU can safely enter RCU read-side critical sections. In other words,
- * if the current CPU is not in its idle loop or is in an interrupt or
- * NMI handler, return true.
+ * Return @true if RCU is watching the running CPU and @false otherwise.
+ * An @true return means that this CPU can safely enter RCU read-side
+ * critical sections.
+ *
+ * Although calls to rcu_is_watching() from most parts of the kernel
+ * will return @true, there are important exceptions. For example, if the
+ * current CPU is deep within its idle loop, in kernel entry/exit code,
+ * or offline, rcu_is_watching() will return @false.
*
* Make notrace because it can be called by the internal functions of
* ftrace, and making this notrace removes unnecessary recursion calls.
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 43229d2b0c44..5598212d1f27 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -77,9 +77,9 @@ __setup("rcu_nocbs", rcu_nocb_setup);
static int __init parse_rcu_nocb_poll(char *arg)
{
rcu_nocb_poll = true;
- return 0;
+ return 1;
}
-early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
+__setup("rcu_nocb_poll", parse_rcu_nocb_poll);
/*
* Don't bother bypassing ->cblist if the call_rcu() rate is low.
diff --git a/kernel/scftorture.c b/kernel/scftorture.c
index 5d113aa59e77..59032aaccd18 100644
--- a/kernel/scftorture.c
+++ b/kernel/scftorture.c
@@ -171,7 +171,8 @@ static void scf_torture_stats_print(void)
scfs.n_all_wait += scf_stats_p[i].n_all_wait;
}
if (atomic_read(&n_errs) || atomic_read(&n_mb_in_errs) ||
- atomic_read(&n_mb_out_errs) || atomic_read(&n_alloc_errs))
+ atomic_read(&n_mb_out_errs) ||
+ (!IS_ENABLED(CONFIG_KASAN) && atomic_read(&n_alloc_errs)))
bangstr = "!!! ";
pr_alert("%s %sscf_invoked_count %s: %lld resched: %lld single: %lld/%lld single_ofl: %lld/%lld single_rpc: %lld single_rpc_ofl: %lld many: %lld/%lld all: %lld/%lld ",
SCFTORT_FLAG, bangstr, isdone ? "VER" : "ver", invoked_count, scfs.n_resched,
@@ -312,6 +313,7 @@ static void scf_handler_1(void *scfc_in)
// Randomly do an smp_call_function*() invocation.
static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_random_state *trsp)
{
+ bool allocfail = false;
uintptr_t cpu;
int ret = 0;
struct scf_check *scfcp = NULL;
@@ -323,8 +325,10 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
preempt_disable();
if (scfsp->scfs_prim == SCF_PRIM_SINGLE || scfsp->scfs_wait) {
scfcp = kmalloc(sizeof(*scfcp), GFP_ATOMIC);
- if (WARN_ON_ONCE(!scfcp)) {
+ if (!scfcp) {
+ WARN_ON_ONCE(!IS_ENABLED(CONFIG_KASAN));
atomic_inc(&n_alloc_errs);
+ allocfail = true;
} else {
scfcp->scfc_cpu = -1;
scfcp->scfc_wait = scfsp->scfs_wait;
@@ -431,7 +435,9 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
cpus_read_unlock();
else
preempt_enable();
- if (!(torture_random(trsp) & 0xfff))
+ if (allocfail)
+ schedule_timeout_idle((1 + longwait) * HZ); // Let no-wait handlers complete.
+ else if (!(torture_random(trsp) & 0xfff))
schedule_timeout_uninterruptible(1);
}
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index d57a5c1c1cd9..3561ab533dd4 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -13,6 +13,23 @@
* Waiting for completion is a typically sync point, but not an exclusion point.
*/
+static void complete_with_flags(struct completion *x, int wake_flags)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
+
+ if (x->done != UINT_MAX)
+ x->done++;
+ swake_up_locked(&x->wait, wake_flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+
+void complete_on_current_cpu(struct completion *x)
+{
+ return complete_with_flags(x, WF_CURRENT_CPU);
+}
+
/**
* complete: - signals a single thread waiting on this completion
* @x: holds the state of this particular completion
@@ -27,14 +44,7 @@
*/
void complete(struct completion *x)
{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&x->wait.lock, flags);
-
- if (x->done != UINT_MAX)
- x->done++;
- swake_up_locked(&x->wait);
- raw_spin_unlock_irqrestore(&x->wait.lock, flags);
+ complete_with_flags(x, 0);
}
EXPORT_SYMBOL(complete);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c52c2eba7c73..4d63e063608a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4193,8 +4193,7 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
* Return: %true if @p->state changes (an actual wakeup was done),
* %false otherwise.
*/
-static int
-try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
+int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
unsigned long flags;
int cpu, success = 0;
@@ -7030,7 +7029,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
void *key)
{
- WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
return try_to_wake_up(curr->private, mode, wake_flags);
}
EXPORT_SYMBOL(default_wake_function);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b3e25be58e2b..ceb5d4c4738e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7741,6 +7741,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
if (wake_flags & WF_TTWU) {
record_wakee(p);
+ if ((wake_flags & WF_CURRENT_CPU) &&
+ cpumask_test_cpu(cpu, p->cpus_ptr))
+ return cpu;
+
if (sched_energy_enabled()) {
new_cpu = find_energy_efficient_cpu(p, prev_cpu);
if (new_cpu >= 0)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e93e006a942b..48d0be005f08 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2131,12 +2131,13 @@ static inline int task_on_rq_migrating(struct task_struct *p)
}
/* Wake flags. The first three directly map to some SD flag value */
-#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
-#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
-#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
+#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
+#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
+#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
-#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
-#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
+#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_CURRENT_CPU 0x40 /* Prefer to move the wakee to the current CPU. */
#ifdef CONFIG_SMP
static_assert(WF_EXEC == SD_BALANCE_EXEC);
@@ -3229,6 +3230,8 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
extern void swake_up_all_locked(struct swait_queue_head *q);
extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
+extern int try_to_wake_up(struct task_struct *tsk, unsigned int state, int wake_flags);
+
#ifdef CONFIG_PREEMPT_DYNAMIC
extern int preempt_dynamic_mode;
extern int sched_dynamic_mode(const char *str);
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index 76b9b796e695..72505cd3b60a 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -18,7 +18,7 @@ EXPORT_SYMBOL(__init_swait_queue_head);
* If for some reason it would return 0, that means the previously waiting
* task is already running, so it will observe condition true (or has already).
*/
-void swake_up_locked(struct swait_queue_head *q)
+void swake_up_locked(struct swait_queue_head *q, int wake_flags)
{
struct swait_queue *curr;
@@ -26,7 +26,7 @@ void swake_up_locked(struct swait_queue_head *q)
return;
curr = list_first_entry(&q->task_list, typeof(*curr), task_list);
- wake_up_process(curr->task);
+ try_to_wake_up(curr->task, TASK_NORMAL, wake_flags);
list_del_init(&curr->task_list);
}
EXPORT_SYMBOL(swake_up_locked);
@@ -41,7 +41,7 @@ EXPORT_SYMBOL(swake_up_locked);
void swake_up_all_locked(struct swait_queue_head *q)
{
while (!list_empty(&q->task_list))
- swake_up_locked(q);
+ swake_up_locked(q, 0);
}
void swake_up_one(struct swait_queue_head *q)
@@ -49,7 +49,7 @@ void swake_up_one(struct swait_queue_head *q)
unsigned long flags;
raw_spin_lock_irqsave(&q->lock, flags);
- swake_up_locked(q);
+ swake_up_locked(q, 0);
raw_spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(swake_up_one);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 48c53e4739ea..802d98cf2de3 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -161,6 +161,11 @@ int __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
}
EXPORT_SYMBOL(__wake_up);
+void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key)
+{
+ __wake_up_common_lock(wq_head, mode, 1, WF_CURRENT_CPU, key);
+}
+
/*
* Same as __wake_up but called with the spinlock in wait_queue_head_t held.
*/
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d3e584065c7f..255999ba9190 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -110,11 +110,13 @@ struct seccomp_knotif {
* @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC
* is allowed.
* @ioctl_flags: The flags used for the seccomp_addfd ioctl.
+ * @setfd: whether or not SECCOMP_ADDFD_FLAG_SETFD was set during notify_addfd
* @ret: The return value of the installing process. It is set to the fd num
* upon success (>= 0).
* @completion: Indicates that the installing process has completed fd
* installation, or gone away (either due to successful
* reply, or signal)
+ * @list: list_head for chaining seccomp_kaddfd together.
*
*/
struct seccomp_kaddfd {
@@ -138,14 +140,17 @@ struct seccomp_kaddfd {
* structure is fairly large, we store the notification-specific stuff in a
* separate structure.
*
- * @request: A semaphore that users of this notification can wait on for
- * changes. Actual reads and writes are still controlled with
- * filter->notify_lock.
+ * @requests: A semaphore that users of this notification can wait on for
+ * changes. Actual reads and writes are still controlled with
+ * filter->notify_lock.
+ * @flags: A set of SECCOMP_USER_NOTIF_FD_* flags.
* @next_id: The id of the next request.
* @notifications: A list of struct seccomp_knotif elements.
*/
+
struct notification {
- struct semaphore request;
+ atomic_t requests;
+ u32 flags;
u64 next_id;
struct list_head notifications;
};
@@ -555,6 +560,8 @@ static void __seccomp_filter_release(struct seccomp_filter *orig)
* drop its reference count, and notify
* about unused filters
*
+ * @tsk: task the filter should be released from.
+ *
* This function should only be called when the task is exiting as
* it detaches it from its filter tree. As such, READ_ONCE() and
* barriers are not needed here, as would normally be needed.
@@ -574,6 +581,8 @@ void seccomp_filter_release(struct task_struct *tsk)
/**
* seccomp_sync_threads: sets all threads to use current's filter
*
+ * @flags: SECCOMP_FILTER_FLAG_* flags to set during sync.
+ *
* Expects sighand and cred_guard_mutex locks to be held, and for
* seccomp_can_sync_threads() to have returned success already
* without dropping the locks.
@@ -1116,8 +1125,11 @@ static int seccomp_do_user_notification(int this_syscall,
list_add_tail(&n.list, &match->notif->notifications);
INIT_LIST_HEAD(&n.addfd);
- up(&match->notif->request);
- wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
+ atomic_inc(&match->notif->requests);
+ if (match->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+ wake_up_poll_on_current_cpu(&match->wqh, EPOLLIN | EPOLLRDNORM);
+ else
+ wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
/*
* This is where we wait for a reply from userspace.
@@ -1450,6 +1462,37 @@ find_notification(struct seccomp_filter *filter, u64 id)
return NULL;
}
+static int recv_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync,
+ void *key)
+{
+ /* Avoid a wakeup if event not interesting for us. */
+ if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR)))
+ return 0;
+ return autoremove_wake_function(wait, mode, sync, key);
+}
+
+static int recv_wait_event(struct seccomp_filter *filter)
+{
+ DEFINE_WAIT_FUNC(wait, recv_wake_function);
+ int ret;
+
+ if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
+ return 0;
+
+ for (;;) {
+ ret = prepare_to_wait_event(&filter->wqh, &wait, TASK_INTERRUPTIBLE);
+
+ if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
+ break;
+
+ if (ret)
+ return ret;
+
+ schedule();
+ }
+ finish_wait(&filter->wqh, &wait);
+ return 0;
+}
static long seccomp_notify_recv(struct seccomp_filter *filter,
void __user *buf)
@@ -1467,7 +1510,7 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
memset(&unotif, 0, sizeof(unotif));
- ret = down_interruptible(&filter->notif->request);
+ ret = recv_wait_event(filter);
if (ret < 0)
return ret;
@@ -1515,7 +1558,8 @@ out:
if (should_sleep_killable(filter, knotif))
complete(&knotif->ready);
knotif->state = SECCOMP_NOTIFY_INIT;
- up(&filter->notif->request);
+ atomic_inc(&filter->notif->requests);
+ wake_up_poll(&filter->wqh, EPOLLIN | EPOLLRDNORM);
}
mutex_unlock(&filter->notify_lock);
}
@@ -1561,7 +1605,10 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
knotif->error = resp.error;
knotif->val = resp.val;
knotif->flags = resp.flags;
- complete(&knotif->ready);
+ if (filter->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+ complete_on_current_cpu(&knotif->ready);
+ else
+ complete(&knotif->ready);
out:
mutex_unlock(&filter->notify_lock);
return ret;
@@ -1591,6 +1638,22 @@ static long seccomp_notify_id_valid(struct seccomp_filter *filter,
return ret;
}
+static long seccomp_notify_set_flags(struct seccomp_filter *filter,
+ unsigned long flags)
+{
+ long ret;
+
+ if (flags & ~SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+ return -EINVAL;
+
+ ret = mutex_lock_interruptible(&filter->notify_lock);
+ if (ret < 0)
+ return ret;
+ filter->notif->flags = flags;
+ mutex_unlock(&filter->notify_lock);
+ return 0;
+}
+
static long seccomp_notify_addfd(struct seccomp_filter *filter,
struct seccomp_notif_addfd __user *uaddfd,
unsigned int size)
@@ -1720,6 +1783,8 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
case SECCOMP_IOCTL_NOTIF_ID_VALID:
return seccomp_notify_id_valid(filter, buf);
+ case SECCOMP_IOCTL_NOTIF_SET_FLAGS:
+ return seccomp_notify_set_flags(filter, arg);
}
/* Extensible Argument ioctls */
@@ -1777,7 +1842,6 @@ static struct file *init_listener(struct seccomp_filter *filter)
if (!filter->notif)
goto out;
- sema_init(&filter->notif->request, 0);
filter->notif->next_id = get_random_u64();
INIT_LIST_HEAD(&filter->notif->notifications);
diff --git a/kernel/signal.c b/kernel/signal.c
index b5370fe5c198..128e9bb3d1a2 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -562,6 +562,10 @@ bool unhandled_signal(struct task_struct *tsk, int sig)
if (handler != SIG_IGN && handler != SIG_DFL)
return false;
+ /* If dying, we handle all new signals by ignoring them */
+ if (fatal_signal_pending(tsk))
+ return false;
+
/* if ptraced, let the tracer determine */
return !tsk->ptrace;
}
diff --git a/kernel/smp.c b/kernel/smp.c
index 385179dae360..8455a53465af 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -46,6 +46,8 @@ static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data);
static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
+static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1);
+
static void __flush_smp_call_function_queue(bool warn_cpu_offline);
int smpcfd_prepare_cpu(unsigned int cpu)
@@ -253,13 +255,15 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
*bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request");
}
if (cpu >= 0) {
- dump_cpu_task(cpu);
+ if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0))
+ dump_cpu_task(cpu);
if (!cpu_cur_csd) {
pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu);
arch_send_call_function_single_ipi(cpu);
}
}
- dump_stack();
+ if (firsttime)
+ dump_stack();
*ts1 = ts2;
return false;
@@ -433,9 +437,14 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline)
struct llist_node *entry, *prev;
struct llist_head *head;
static bool warned;
+ atomic_t *tbt;
lockdep_assert_irqs_disabled();
+ /* Allow waiters to send backtrace NMI from here onwards */
+ tbt = this_cpu_ptr(&trigger_backtrace);
+ atomic_set_release(tbt, 1);
+
head = this_cpu_ptr(&call_single_queue);
entry = llist_del_all(head);
entry = llist_reverse_order(entry);
diff --git a/kernel/sys.c b/kernel/sys.c
index 05f838929e72..2410e3999ebe 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2535,11 +2535,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
else
return -EINVAL;
break;
- case PR_GET_AUXV:
- if (arg4 || arg5)
- return -EINVAL;
- error = prctl_get_auxv((void __user *)arg2, arg3);
- break;
default:
return -EINVAL;
}
@@ -2694,6 +2689,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_SET_VMA:
error = prctl_set_vma(arg2, arg3, arg4, arg5);
break;
+ case PR_GET_AUXV:
+ if (arg4 || arg5)
+ return -EINVAL;
+ error = prctl_get_auxv((void __user *)arg2, arg3);
+ break;
#ifdef CONFIG_KSM
case PR_SET_MEMORY_MERGE:
if (arg3 || arg4 || arg5)
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 88cbc1181b23..c108ed8a9804 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -473,8 +473,8 @@ static void clocksource_watchdog(struct timer_list *unused)
/* Check the deviation from the watchdog clocksource. */
md = cs->uncertainty_margin + watchdog->uncertainty_margin;
if (abs(cs_nsec - wd_nsec) > md) {
- u64 cs_wd_msec;
- u64 wd_msec;
+ s64 cs_wd_msec;
+ s64 wd_msec;
u32 wd_rem;
pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n",
@@ -483,8 +483,8 @@ static void clocksource_watchdog(struct timer_list *unused)
watchdog->name, wd_nsec, wdnow, wdlast, watchdog->mask);
pr_warn(" '%s' cs_nsec: %lld cs_now: %llx cs_last: %llx mask: %llx\n",
cs->name, cs_nsec, csnow, cslast, cs->mask);
- cs_wd_msec = div_u64_rem(cs_nsec - wd_nsec, 1000U * 1000U, &wd_rem);
- wd_msec = div_u64_rem(wd_nsec, 1000U * 1000U, &wd_rem);
+ cs_wd_msec = div_s64_rem(cs_nsec - wd_nsec, 1000 * 1000, &wd_rem);
+ wd_msec = div_s64_rem(wd_nsec, 1000 * 1000, &wd_rem);
pr_warn(" Clocksource '%s' skewed %lld ns (%lld ms) over watchdog '%s' interval of %lld ns (%lld ms)\n",
cs->name, cs_nsec - wd_nsec, cs_wd_msec, watchdog->name, wd_nsec, wd_msec);
if (curr_clocksource == cs)
diff --git a/kernel/torture.c b/kernel/torture.c
index 1a0519b836ac..b28b05bbef02 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -37,6 +37,7 @@
#include <linux/ktime.h>
#include <asm/byteorder.h>
#include <linux/torture.h>
+#include <linux/sched/rt.h>
#include "rcu/rcu.h"
MODULE_LICENSE("GPL");
@@ -54,6 +55,9 @@ module_param(verbose_sleep_frequency, int, 0444);
static int verbose_sleep_duration = 1;
module_param(verbose_sleep_duration, int, 0444);
+static int random_shuffle;
+module_param(random_shuffle, int, 0444);
+
static char *torture_type;
static int verbose;
@@ -88,8 +92,8 @@ int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, struct torture_random_s
ktime_t hto = baset_ns;
if (trsp)
- hto += (torture_random(trsp) >> 3) % fuzzt_ns;
- set_current_state(TASK_UNINTERRUPTIBLE);
+ hto += torture_random(trsp) % fuzzt_ns;
+ set_current_state(TASK_IDLE);
return schedule_hrtimeout(&hto, HRTIMER_MODE_REL);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_ns);
@@ -350,22 +354,22 @@ torture_onoff(void *arg)
if (onoff_holdoff > 0) {
VERBOSE_TOROUT_STRING("torture_onoff begin holdoff");
- schedule_timeout_interruptible(onoff_holdoff);
+ torture_hrtimeout_jiffies(onoff_holdoff, &rand);
VERBOSE_TOROUT_STRING("torture_onoff end holdoff");
}
while (!torture_must_stop()) {
if (disable_onoff_at_boot && !rcu_inkernel_boot_has_ended()) {
- schedule_timeout_interruptible(HZ / 10);
+ torture_hrtimeout_jiffies(HZ / 10, &rand);
continue;
}
- cpu = (torture_random(&rand) >> 4) % (maxcpu + 1);
+ cpu = torture_random(&rand) % (maxcpu + 1);
if (!torture_offline(cpu,
&n_offline_attempts, &n_offline_successes,
&sum_offline, &min_offline, &max_offline))
torture_online(cpu,
&n_online_attempts, &n_online_successes,
&sum_online, &min_online, &max_online);
- schedule_timeout_interruptible(onoff_interval);
+ torture_hrtimeout_jiffies(onoff_interval, &rand);
}
stop:
@@ -518,6 +522,7 @@ static void torture_shuffle_task_unregister_all(void)
*/
static void torture_shuffle_tasks(void)
{
+ DEFINE_TORTURE_RANDOM(rand);
struct shuffle_task *stp;
cpumask_setall(shuffle_tmp_mask);
@@ -537,8 +542,10 @@ static void torture_shuffle_tasks(void)
cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask);
mutex_lock(&shuffle_task_mutex);
- list_for_each_entry(stp, &shuffle_task_list, st_l)
- set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask);
+ list_for_each_entry(stp, &shuffle_task_list, st_l) {
+ if (!random_shuffle || torture_random(&rand) & 0x1)
+ set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask);
+ }
mutex_unlock(&shuffle_task_mutex);
cpus_read_unlock();
@@ -550,9 +557,11 @@ static void torture_shuffle_tasks(void)
*/
static int torture_shuffle(void *arg)
{
+ DEFINE_TORTURE_RANDOM(rand);
+
VERBOSE_TOROUT_STRING("torture_shuffle task started");
do {
- schedule_timeout_interruptible(shuffle_interval);
+ torture_hrtimeout_jiffies(shuffle_interval, &rand);
torture_shuffle_tasks();
torture_shutdown_absorb("torture_shuffle");
} while (!torture_must_stop());
@@ -728,12 +737,12 @@ bool stutter_wait(const char *title)
cond_resched_tasks_rcu_qs();
spt = READ_ONCE(stutter_pause_test);
for (; spt; spt = READ_ONCE(stutter_pause_test)) {
- if (!ret) {
+ if (!ret && !rt_task(current)) {
sched_set_normal(current, MAX_NICE);
ret = true;
}
if (spt == 1) {
- schedule_timeout_interruptible(1);
+ torture_hrtimeout_jiffies(1, NULL);
} else if (spt == 2) {
while (READ_ONCE(stutter_pause_test)) {
if (!(i++ & 0xffff))
@@ -741,7 +750,7 @@ bool stutter_wait(const char *title)
cond_resched();
}
} else {
- schedule_timeout_interruptible(round_jiffies_relative(HZ));
+ torture_hrtimeout_jiffies(round_jiffies_relative(HZ), NULL);
}
torture_shutdown_absorb(title);
}
@@ -926,7 +935,7 @@ EXPORT_SYMBOL_GPL(torture_kthread_stopping);
* it starts, you will need to open-code your own.
*/
int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
- char *f, struct task_struct **tp)
+ char *f, struct task_struct **tp, void (*cbf)(struct task_struct *tp))
{
int ret = 0;
@@ -938,6 +947,10 @@ int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
*tp = NULL;
return ret;
}
+
+ if (cbf)
+ cbf(*tp);
+
wake_up_process(*tp); // Process is sleeping, so ordering provided.
torture_shuffle_task_register(*tp);
return ret;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 5f2dcabad202..bd1a42b23f3f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -661,8 +661,7 @@ static DEFINE_PER_CPU(int, bpf_trace_nest_level);
BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
u64, flags, void *, data, u64, size)
{
- struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds);
- int nest_level = this_cpu_inc_return(bpf_trace_nest_level);
+ struct bpf_trace_sample_data *sds;
struct perf_raw_record raw = {
.frag = {
.size = size,
@@ -670,7 +669,11 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
},
};
struct perf_sample_data *sd;
- int err;
+ int nest_level, err;
+
+ preempt_disable();
+ sds = this_cpu_ptr(&bpf_trace_sds);
+ nest_level = this_cpu_inc_return(bpf_trace_nest_level);
if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) {
err = -EBUSY;
@@ -688,9 +691,9 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
perf_sample_save_raw_data(sd, &raw);
err = __bpf_perf_event_output(regs, map, flags, sd);
-
out:
this_cpu_dec(bpf_trace_nest_level);
+ preempt_enable();
return err;
}
@@ -715,7 +718,6 @@ static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds);
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
{
- int nest_level = this_cpu_inc_return(bpf_event_output_nest_level);
struct perf_raw_frag frag = {
.copy = ctx_copy,
.size = ctx_size,
@@ -732,8 +734,12 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
};
struct perf_sample_data *sd;
struct pt_regs *regs;
+ int nest_level;
u64 ret;
+ preempt_disable();
+ nest_level = this_cpu_inc_return(bpf_event_output_nest_level);
+
if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) {
ret = -EBUSY;
goto out;
@@ -748,6 +754,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
ret = __bpf_perf_event_output(regs, map, flags, sd);
out:
this_cpu_dec(bpf_event_output_nest_level);
+ preempt_enable();
return ret;
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 14d8001140c8..52dea5dd5362 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -523,6 +523,8 @@ struct ring_buffer_per_cpu {
rb_time_t before_stamp;
u64 event_stamp[MAX_NEST];
u64 read_stamp;
+ /* pages removed since last reset */
+ unsigned long pages_removed;
/* ring buffer pages to update, > 0 to add, < 0 to remove */
long nr_pages_to_update;
struct list_head new_pages; /* new pages to add */
@@ -536,6 +538,7 @@ struct trace_buffer {
unsigned flags;
int cpus;
atomic_t record_disabled;
+ atomic_t resizing;
cpumask_var_t cpumask;
struct lock_class_key *reader_lock_key;
@@ -558,6 +561,7 @@ struct ring_buffer_iter {
struct buffer_page *head_page;
struct buffer_page *cache_reader_page;
unsigned long cache_read;
+ unsigned long cache_pages_removed;
u64 read_stamp;
u64 page_stamp;
struct ring_buffer_event *event;
@@ -946,6 +950,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
/**
* ring_buffer_wake_waiters - wake up any waiters on this ring buffer
* @buffer: The ring buffer to wake waiters on
+ * @cpu: The CPU buffer to wake waiters on
*
* In the case of a file that represents a ring buffer is closing,
* it is prudent to wake up any waiters that are on this.
@@ -1956,6 +1961,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
to_remove = rb_list_head(to_remove)->next;
head_bit |= (unsigned long)to_remove & RB_PAGE_HEAD;
}
+ /* Read iterators need to reset themselves when some pages removed */
+ cpu_buffer->pages_removed += nr_removed;
next_page = rb_list_head(to_remove)->next;
@@ -1977,12 +1984,6 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
cpu_buffer->head_page = list_entry(next_page,
struct buffer_page, list);
- /*
- * change read pointer to make sure any read iterators reset
- * themselves
- */
- cpu_buffer->read = 0;
-
/* pages are removed, resume tracing and then free the pages */
atomic_dec(&cpu_buffer->record_disabled);
raw_spin_unlock_irq(&cpu_buffer->reader_lock);
@@ -2167,7 +2168,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
/* prevent another thread from changing buffer sizes */
mutex_lock(&buffer->mutex);
-
+ atomic_inc(&buffer->resizing);
if (cpu_id == RING_BUFFER_ALL_CPUS) {
/*
@@ -2322,6 +2323,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
atomic_dec(&buffer->record_disabled);
}
+ atomic_dec(&buffer->resizing);
mutex_unlock(&buffer->mutex);
return 0;
@@ -2342,6 +2344,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
}
}
out_err_unlock:
+ atomic_dec(&buffer->resizing);
mutex_unlock(&buffer->mutex);
return err;
}
@@ -3373,7 +3376,6 @@ void ring_buffer_nest_end(struct trace_buffer *buffer)
/**
* ring_buffer_unlock_commit - commit a reserved
* @buffer: The buffer to commit to
- * @event: The event pointer to commit.
*
* This commits the data to the ring buffer, and releases any locks held.
*
@@ -4392,6 +4394,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
iter->cache_reader_page = iter->head_page;
iter->cache_read = cpu_buffer->read;
+ iter->cache_pages_removed = cpu_buffer->pages_removed;
if (iter->head) {
iter->read_stamp = cpu_buffer->read_stamp;
@@ -4846,12 +4849,13 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
buffer = cpu_buffer->buffer;
/*
- * Check if someone performed a consuming read to
- * the buffer. A consuming read invalidates the iterator
- * and we need to reset the iterator in this case.
+ * Check if someone performed a consuming read to the buffer
+ * or removed some pages from the buffer. In these cases,
+ * iterator was invalidated and we need to reset it.
*/
if (unlikely(iter->cache_read != cpu_buffer->read ||
- iter->cache_reader_page != cpu_buffer->reader_page))
+ iter->cache_reader_page != cpu_buffer->reader_page ||
+ iter->cache_pages_removed != cpu_buffer->pages_removed))
rb_iter_reset(iter);
again:
@@ -5295,6 +5299,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->last_overrun = 0;
rb_head_page_activate(cpu_buffer);
+ cpu_buffer->pages_removed = 0;
}
/* Must have disabled the cpu buffer then done a synchronize_rcu */
@@ -5353,7 +5358,6 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
/**
* ring_buffer_reset_online_cpus - reset a ring buffer per CPU buffer
* @buffer: The ring buffer to reset a per cpu buffer of
- * @cpu: The CPU buffer to be reset
*/
void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
{
@@ -5541,6 +5545,15 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
if (local_read(&cpu_buffer_b->committing))
goto out_dec;
+ /*
+ * When resize is in progress, we cannot swap it because
+ * it will mess the state of the cpu buffer.
+ */
+ if (atomic_read(&buffer_a->resizing))
+ goto out_dec;
+ if (atomic_read(&buffer_b->resizing))
+ goto out_dec;
+
buffer_a->buffers[cpu] = cpu_buffer_b;
buffer_b->buffers[cpu] = cpu_buffer_a;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index be847d45d81c..8e64aaad5361 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1928,9 +1928,10 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
* place on this CPU. We fail to record, but we reset
* the max trace buffer (no one writes directly to it)
* and flag that it failed.
+ * Another reason is resize is in progress.
*/
trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_,
- "Failed to swap buffers due to commit in progress\n");
+ "Failed to swap buffers due to commit or resize in progress\n");
}
WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
@@ -4212,8 +4213,15 @@ static void *s_start(struct seq_file *m, loff_t *pos)
* will point to the same string as current_trace->name.
*/
mutex_lock(&trace_types_lock);
- if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name))
+ if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) {
+ /* Close iter->trace before switching to the new current tracer */
+ if (iter->trace->close)
+ iter->trace->close(iter);
*iter->trace = *tr->current_trace;
+ /* Reopen the new current tracer */
+ if (iter->trace->open)
+ iter->trace->open(iter);
+ }
mutex_unlock(&trace_types_lock);
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -5276,11 +5284,17 @@ int tracing_set_cpumask(struct trace_array *tr,
!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
atomic_inc(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled);
ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu);
+#ifdef CONFIG_TRACER_MAX_TRACE
+ ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu);
+#endif
}
if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) &&
cpumask_test_cpu(cpu, tracing_cpumask_new)) {
atomic_dec(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled);
ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu);
+#ifdef CONFIG_TRACER_MAX_TRACE
+ ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu);
+#endif
}
}
arch_spin_unlock(&tr->max_lock);
@@ -6704,10 +6718,36 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
#endif
+static int open_pipe_on_cpu(struct trace_array *tr, int cpu)
+{
+ if (cpu == RING_BUFFER_ALL_CPUS) {
+ if (cpumask_empty(tr->pipe_cpumask)) {
+ cpumask_setall(tr->pipe_cpumask);
+ return 0;
+ }
+ } else if (!cpumask_test_cpu(cpu, tr->pipe_cpumask)) {
+ cpumask_set_cpu(cpu, tr->pipe_cpumask);
+ return 0;
+ }
+ return -EBUSY;
+}
+
+static void close_pipe_on_cpu(struct trace_array *tr, int cpu)
+{
+ if (cpu == RING_BUFFER_ALL_CPUS) {
+ WARN_ON(!cpumask_full(tr->pipe_cpumask));
+ cpumask_clear(tr->pipe_cpumask);
+ } else {
+ WARN_ON(!cpumask_test_cpu(cpu, tr->pipe_cpumask));
+ cpumask_clear_cpu(cpu, tr->pipe_cpumask);
+ }
+}
+
static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
+ int cpu;
int ret;
ret = tracing_check_open_get_tr(tr);
@@ -6715,13 +6755,16 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
return ret;
mutex_lock(&trace_types_lock);
+ cpu = tracing_get_cpu(inode);
+ ret = open_pipe_on_cpu(tr, cpu);
+ if (ret)
+ goto fail_pipe_on_cpu;
/* create a buffer to store the information to pass to userspace */
iter = kzalloc(sizeof(*iter), GFP_KERNEL);
if (!iter) {
ret = -ENOMEM;
- __trace_array_put(tr);
- goto out;
+ goto fail_alloc_iter;
}
trace_seq_init(&iter->seq);
@@ -6744,7 +6787,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
iter->tr = tr;
iter->array_buffer = &tr->array_buffer;
- iter->cpu_file = tracing_get_cpu(inode);
+ iter->cpu_file = cpu;
mutex_init(&iter->mutex);
filp->private_data = iter;
@@ -6754,12 +6797,15 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
nonseekable_open(inode, filp);
tr->trace_ref++;
-out:
+
mutex_unlock(&trace_types_lock);
return ret;
fail:
kfree(iter);
+fail_alloc_iter:
+ close_pipe_on_cpu(tr, cpu);
+fail_pipe_on_cpu:
__trace_array_put(tr);
mutex_unlock(&trace_types_lock);
return ret;
@@ -6776,7 +6822,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
if (iter->trace->pipe_close)
iter->trace->pipe_close(iter);
-
+ close_pipe_on_cpu(tr, iter->cpu_file);
mutex_unlock(&trace_types_lock);
free_cpumask_var(iter->started);
@@ -9440,6 +9486,9 @@ static struct trace_array *trace_array_create(const char *name)
if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL))
goto out_free_tr;
+ if (!alloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL))
+ goto out_free_tr;
+
tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
@@ -9481,6 +9530,7 @@ static struct trace_array *trace_array_create(const char *name)
out_free_tr:
ftrace_free_ftrace_ops(tr);
free_trace_buffers(tr);
+ free_cpumask_var(tr->pipe_cpumask);
free_cpumask_var(tr->tracing_cpumask);
kfree(tr->name);
kfree(tr);
@@ -9583,6 +9633,7 @@ static int __remove_instance(struct trace_array *tr)
}
kfree(tr->topts);
+ free_cpumask_var(tr->pipe_cpumask);
free_cpumask_var(tr->tracing_cpumask);
kfree(tr->name);
kfree(tr);
@@ -10380,12 +10431,14 @@ __init static int tracer_alloc_buffers(void)
if (trace_create_savedcmd() < 0)
goto out_free_temp_buffer;
+ if (!alloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL))
+ goto out_free_savedcmd;
+
/* TODO: make the number of buffers hot pluggable with CPUS */
if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
MEM_FAIL(1, "tracer: failed to allocate ring buffer!\n");
- goto out_free_savedcmd;
+ goto out_free_pipe_cpumask;
}
-
if (global_trace.buffer_disabled)
tracing_off();
@@ -10438,6 +10491,8 @@ __init static int tracer_alloc_buffers(void)
return 0;
+out_free_pipe_cpumask:
+ free_cpumask_var(global_trace.pipe_cpumask);
out_free_savedcmd:
free_saved_cmdlines_buffer(savedcmd);
out_free_temp_buffer:
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e1edc2197fc8..73eaec158473 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -377,6 +377,8 @@ struct trace_array {
struct list_head events;
struct trace_event_file *trace_marker_file;
cpumask_var_t tracing_cpumask; /* only trace on set CPUs */
+ /* one per_cpu trace_pipe can be opened by only one user */
+ cpumask_var_t pipe_cpumask;
int ref;
int trace_ref;
#ifdef CONFIG_FUNCTION_TRACER
@@ -1295,6 +1297,14 @@ static inline void trace_branch_disable(void)
/* set ring buffers to default size if not already done so */
int tracing_update_buffers(void);
+union trace_synth_field {
+ u8 as_u8;
+ u16 as_u16;
+ u32 as_u32;
+ u64 as_u64;
+ struct trace_dynamic_info as_dynamic;
+};
+
struct ftrace_event_field {
struct list_head link;
const char *name;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5d6ae4eae510..578f1f7d49a6 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -611,7 +611,6 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
{
struct trace_event_call *call = file->event_call;
struct trace_array *tr = file->tr;
- unsigned long file_flags = file->flags;
int ret = 0;
int disable;
@@ -635,6 +634,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
break;
disable = file->flags & EVENT_FILE_FL_SOFT_DISABLED;
clear_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+ /* Disable use of trace_buffered_event */
+ trace_buffered_event_disable();
} else
disable = !(file->flags & EVENT_FILE_FL_SOFT_MODE);
@@ -673,6 +674,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
if (atomic_inc_return(&file->sm_ref) > 1)
break;
set_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+ /* Enable use of trace_buffered_event */
+ trace_buffered_event_enable();
}
if (!(file->flags & EVENT_FILE_FL_ENABLED)) {
@@ -712,15 +715,6 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
break;
}
- /* Enable or disable use of trace_buffered_event */
- if ((file_flags & EVENT_FILE_FL_SOFT_DISABLED) !=
- (file->flags & EVENT_FILE_FL_SOFT_DISABLED)) {
- if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
- trace_buffered_event_enable();
- else
- trace_buffered_event_disable();
- }
-
return ret;
}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index c8c61381eba4..d06938ae0717 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6668,7 +6668,8 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
goto out_unreg;
if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
- if (save_hist_vars(hist_data))
+ ret = save_hist_vars(hist_data);
+ if (ret)
goto out_unreg;
}
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index d6a70aff2410..9897d0bfcab7 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -127,7 +127,7 @@ static bool synth_event_match(const char *system, const char *event,
struct synth_trace_event {
struct trace_entry ent;
- u64 fields[];
+ union trace_synth_field fields[];
};
static int synth_event_define_fields(struct trace_event_call *call)
@@ -321,19 +321,19 @@ static const char *synth_field_fmt(char *type)
static void print_synth_event_num_val(struct trace_seq *s,
char *print_fmt, char *name,
- int size, u64 val, char *space)
+ int size, union trace_synth_field *val, char *space)
{
switch (size) {
case 1:
- trace_seq_printf(s, print_fmt, name, (u8)val, space);
+ trace_seq_printf(s, print_fmt, name, val->as_u8, space);
break;
case 2:
- trace_seq_printf(s, print_fmt, name, (u16)val, space);
+ trace_seq_printf(s, print_fmt, name, val->as_u16, space);
break;
case 4:
- trace_seq_printf(s, print_fmt, name, (u32)val, space);
+ trace_seq_printf(s, print_fmt, name, val->as_u32, space);
break;
default:
@@ -350,7 +350,7 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
struct trace_seq *s = &iter->seq;
struct synth_trace_event *entry;
struct synth_event *se;
- unsigned int i, n_u64;
+ unsigned int i, j, n_u64;
char print_fmt[32];
const char *fmt;
@@ -374,43 +374,28 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
/* parameter values */
if (se->fields[i]->is_string) {
if (se->fields[i]->is_dynamic) {
- u32 offset, data_offset;
- char *str_field;
-
- offset = (u32)entry->fields[n_u64];
- data_offset = offset & 0xffff;
-
- str_field = (char *)entry + data_offset;
+ union trace_synth_field *data = &entry->fields[n_u64];
trace_seq_printf(s, print_fmt, se->fields[i]->name,
STR_VAR_LEN_MAX,
- str_field,
+ (char *)entry + data->as_dynamic.offset,
i == se->n_fields - 1 ? "" : " ");
n_u64++;
} else {
trace_seq_printf(s, print_fmt, se->fields[i]->name,
STR_VAR_LEN_MAX,
- (char *)&entry->fields[n_u64],
+ (char *)&entry->fields[n_u64].as_u64,
i == se->n_fields - 1 ? "" : " ");
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
}
} else if (se->fields[i]->is_stack) {
- u32 offset, data_offset, len;
- unsigned long *p, *end;
-
- offset = (u32)entry->fields[n_u64];
- data_offset = offset & 0xffff;
- len = offset >> 16;
-
- p = (void *)entry + data_offset;
- end = (void *)p + len - (sizeof(long) - 1);
+ union trace_synth_field *data = &entry->fields[n_u64];
+ unsigned long *p = (void *)entry + data->as_dynamic.offset;
trace_seq_printf(s, "%s=STACK:\n", se->fields[i]->name);
-
- for (; *p && p < end; p++)
- trace_seq_printf(s, "=> %pS\n", (void *)*p);
+ for (j = 1; j < data->as_dynamic.len / sizeof(long); j++)
+ trace_seq_printf(s, "=> %pS\n", (void *)p[j]);
n_u64++;
-
} else {
struct trace_print_flags __flags[] = {
__def_gfpflag_names, {-1, NULL} };
@@ -419,13 +404,13 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
print_synth_event_num_val(s, print_fmt,
se->fields[i]->name,
se->fields[i]->size,
- entry->fields[n_u64],
+ &entry->fields[n_u64],
space);
if (strcmp(se->fields[i]->type, "gfp_t") == 0) {
trace_seq_puts(s, " (");
trace_print_flags_seq(s, "|",
- entry->fields[n_u64],
+ entry->fields[n_u64].as_u64,
__flags);
trace_seq_putc(s, ')');
}
@@ -454,21 +439,16 @@ static unsigned int trace_string(struct synth_trace_event *entry,
int ret;
if (is_dynamic) {
- u32 data_offset;
+ union trace_synth_field *data = &entry->fields[*n_u64];
- data_offset = struct_size(entry, fields, event->n_u64);
- data_offset += data_size;
-
- len = fetch_store_strlen((unsigned long)str_val);
-
- data_offset |= len << 16;
- *(u32 *)&entry->fields[*n_u64] = data_offset;
+ data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size;
+ data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val);
ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry);
(*n_u64)++;
} else {
- str_field = (char *)&entry->fields[*n_u64];
+ str_field = (char *)&entry->fields[*n_u64].as_u64;
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
if ((unsigned long)str_val < TASK_SIZE)
@@ -492,6 +472,7 @@ static unsigned int trace_stack(struct synth_trace_event *entry,
unsigned int data_size,
unsigned int *n_u64)
{
+ union trace_synth_field *data = &entry->fields[*n_u64];
unsigned int len;
u32 data_offset;
void *data_loc;
@@ -504,10 +485,6 @@ static unsigned int trace_stack(struct synth_trace_event *entry,
break;
}
- /* Include the zero'd element if it fits */
- if (len < HIST_STACKTRACE_DEPTH)
- len++;
-
len *= sizeof(long);
/* Find the dynamic section to copy the stack into. */
@@ -515,8 +492,9 @@ static unsigned int trace_stack(struct synth_trace_event *entry,
memcpy(data_loc, stack, len);
/* Fill in the field that holds the offset/len combo */
- data_offset |= len << 16;
- *(u32 *)&entry->fields[*n_u64] = data_offset;
+
+ data->as_dynamic.offset = data_offset;
+ data->as_dynamic.len = len;
(*n_u64)++;
@@ -550,7 +528,8 @@ static notrace void trace_event_raw_event_synth(void *__data,
str_val = (char *)(long)var_ref_vals[val_idx];
if (event->dynamic_fields[i]->is_stack) {
- len = *((unsigned long *)str_val);
+ /* reserve one extra element for size */
+ len = *((unsigned long *)str_val) + 1;
len *= sizeof(unsigned long);
} else {
len = fetch_store_strlen((unsigned long)str_val);
@@ -592,19 +571,19 @@ static notrace void trace_event_raw_event_synth(void *__data,
switch (field->size) {
case 1:
- *(u8 *)&entry->fields[n_u64] = (u8)val;
+ entry->fields[n_u64].as_u8 = (u8)val;
break;
case 2:
- *(u16 *)&entry->fields[n_u64] = (u16)val;
+ entry->fields[n_u64].as_u16 = (u16)val;
break;
case 4:
- *(u32 *)&entry->fields[n_u64] = (u32)val;
+ entry->fields[n_u64].as_u32 = (u32)val;
break;
default:
- entry->fields[n_u64] = val;
+ entry->fields[n_u64].as_u64 = val;
break;
}
n_u64++;
@@ -1230,6 +1209,7 @@ EXPORT_SYMBOL_GPL(__synth_event_gen_cmd_start);
* synth_event_gen_cmd_array_start - Start synthetic event command from an array
* @cmd: A pointer to the dynevent_cmd struct representing the new event
* @name: The name of the synthetic event
+ * @mod: The module creating the event, NULL if not created from a module
* @fields: An array of type/name field descriptions
* @n_fields: The number of field descriptions contained in the fields array
*
@@ -1790,19 +1770,19 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...)
switch (field->size) {
case 1:
- *(u8 *)&state.entry->fields[n_u64] = (u8)val;
+ state.entry->fields[n_u64].as_u8 = (u8)val;
break;
case 2:
- *(u16 *)&state.entry->fields[n_u64] = (u16)val;
+ state.entry->fields[n_u64].as_u16 = (u16)val;
break;
case 4:
- *(u32 *)&state.entry->fields[n_u64] = (u32)val;
+ state.entry->fields[n_u64].as_u32 = (u32)val;
break;
default:
- state.entry->fields[n_u64] = val;
+ state.entry->fields[n_u64].as_u64 = val;
break;
}
n_u64++;
@@ -1883,19 +1863,19 @@ int synth_event_trace_array(struct trace_event_file *file, u64 *vals,
switch (field->size) {
case 1:
- *(u8 *)&state.entry->fields[n_u64] = (u8)val;
+ state.entry->fields[n_u64].as_u8 = (u8)val;
break;
case 2:
- *(u16 *)&state.entry->fields[n_u64] = (u16)val;
+ state.entry->fields[n_u64].as_u16 = (u16)val;
break;
case 4:
- *(u32 *)&state.entry->fields[n_u64] = (u32)val;
+ state.entry->fields[n_u64].as_u32 = (u32)val;
break;
default:
- state.entry->fields[n_u64] = val;
+ state.entry->fields[n_u64].as_u64 = val;
break;
}
n_u64++;
@@ -2030,19 +2010,19 @@ static int __synth_event_add_val(const char *field_name, u64 val,
} else {
switch (field->size) {
case 1:
- *(u8 *)&trace_state->entry->fields[field->offset] = (u8)val;
+ trace_state->entry->fields[field->offset].as_u8 = (u8)val;
break;
case 2:
- *(u16 *)&trace_state->entry->fields[field->offset] = (u16)val;
+ trace_state->entry->fields[field->offset].as_u16 = (u16)val;
break;
case 4:
- *(u32 *)&trace_state->entry->fields[field->offset] = (u32)val;
+ trace_state->entry->fields[field->offset].as_u32 = (u32)val;
break;
default:
- trace_state->entry->fields[field->offset] = val;
+ trace_state->entry->fields[field->offset].as_u64 = val;
break;
}
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index e535959939d3..46439e3bcec4 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -31,7 +31,9 @@ void trigger_data_free(struct event_trigger_data *data)
/**
* event_triggers_call - Call triggers associated with a trace event
* @file: The trace_event_file associated with the event
+ * @buffer: The ring buffer that the event is being written to
* @rec: The trace entry for the event, NULL for unconditional invocation
+ * @event: The event meta data in the ring buffer
*
* For each trigger associated with an event, invoke the trigger
* function registered with the associated trigger command. If rec is
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 590b3d51afae..ba37f768e2f2 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -231,7 +231,8 @@ static void irqsoff_trace_open(struct trace_iterator *iter)
{
if (is_graph(iter->tr))
graph_trace_open(iter);
-
+ else
+ iter->private = NULL;
}
static void irqsoff_trace_close(struct trace_iterator *iter)
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index b2b726bea1f9..c68a72707852 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -386,12 +386,12 @@ static const struct btf_type *find_btf_func_proto(const char *funcname)
/* Get BTF_KIND_FUNC type */
t = btf_type_by_id(btf, id);
- if (!btf_type_is_func(t))
+ if (!t || !btf_type_is_func(t))
return ERR_PTR(-ENOENT);
/* The type of BTF_KIND_FUNC is BTF_KIND_FUNC_PROTO */
t = btf_type_by_id(btf, t->type);
- if (!btf_type_is_func_proto(t))
+ if (!t || !btf_type_is_func_proto(t))
return ERR_PTR(-ENOENT);
return t;
@@ -443,7 +443,7 @@ static int parse_btf_arg(const char *varname, struct fetch_insn *code,
if (!ctx->params) {
params = find_btf_func_param(ctx->funcname, &ctx->nr_params,
ctx->flags & TPARG_FL_TPOINT);
- if (IS_ERR(params)) {
+ if (IS_ERR_OR_NULL(params)) {
trace_probe_log_err(ctx->offset, NO_BTF_ENTRY);
return PTR_ERR(params);
}
@@ -1273,7 +1273,7 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[],
params = find_btf_func_param(ctx->funcname, &nr_params,
ctx->flags & TPARG_FL_TPOINT);
- if (IS_ERR(params)) {
+ if (IS_ERR_OR_NULL(params)) {
if (args_idx != -1) {
/* $arg* requires BTF info */
trace_probe_log_err(0, NOSUP_BTFARG);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 330aee1c1a49..0469a04a355f 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -168,6 +168,8 @@ static void wakeup_trace_open(struct trace_iterator *iter)
{
if (is_graph(iter->tr))
graph_trace_open(iter);
+ else
+ iter->private = NULL;
}
static void wakeup_trace_close(struct trace_iterator *iter)
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index e5e299260d0c..bac06ee3b98b 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -131,6 +131,7 @@ EXPORT_SYMBOL_GPL(trace_seq_bitmask);
* trace_seq_vprintf - sequence printing of trace information
* @s: trace sequence descriptor
* @fmt: printf format string
+ * @args: Arguments for the format string
*
* The tracer may use either sequence operations or its own
* copy to user routines. To simplify formatting of a trace
diff --git a/kernel/trace/tracing_map.h b/kernel/trace/tracing_map.h
index 2c765ee2a4d4..99c37eeebc16 100644
--- a/kernel/trace/tracing_map.h
+++ b/kernel/trace/tracing_map.h
@@ -272,10 +272,6 @@ extern u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i);
extern u64 tracing_map_read_var(struct tracing_map_elt *elt, unsigned int i);
extern u64 tracing_map_read_var_once(struct tracing_map_elt *elt, unsigned int i);
-extern void tracing_map_set_field_descr(struct tracing_map *map,
- unsigned int i,
- unsigned int key_offset,
- tracing_map_cmp_fn_t cmp_fn);
extern int
tracing_map_sort_entries(struct tracing_map *map,
struct tracing_map_sort_key *sort_keys,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 02a8f402eeb5..800b4208dba9 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -52,6 +52,7 @@
#include <linux/sched/debug.h>
#include <linux/nmi.h>
#include <linux/kvm_para.h>
+#include <linux/delay.h>
#include "workqueue_internal.h"
@@ -338,8 +339,10 @@ static cpumask_var_t *wq_numa_possible_cpumask;
* Per-cpu work items which run for longer than the following threshold are
* automatically considered CPU intensive and excluded from concurrency
* management to prevent them from noticeably delaying other per-cpu work items.
+ * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter.
+ * The actual value is initialized in wq_cpu_intensive_thresh_init().
*/
-static unsigned long wq_cpu_intensive_thresh_us = 10000;
+static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX;
module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644);
static bool wq_disable_numa;
@@ -6513,6 +6516,42 @@ void __init workqueue_init_early(void)
!system_freezable_power_efficient_wq);
}
+static void __init wq_cpu_intensive_thresh_init(void)
+{
+ unsigned long thresh;
+ unsigned long bogo;
+
+ /* if the user set it to a specific value, keep it */
+ if (wq_cpu_intensive_thresh_us != ULONG_MAX)
+ return;
+
+ /*
+ * The default of 10ms is derived from the fact that most modern (as of
+ * 2023) processors can do a lot in 10ms and that it's just below what
+ * most consider human-perceivable. However, the kernel also runs on a
+ * lot slower CPUs including microcontrollers where the threshold is way
+ * too low.
+ *
+ * Let's scale up the threshold upto 1 second if BogoMips is below 4000.
+ * This is by no means accurate but it doesn't have to be. The mechanism
+ * is still useful even when the threshold is fully scaled up. Also, as
+ * the reports would usually be applicable to everyone, some machines
+ * operating on longer thresholds won't significantly diminish their
+ * usefulness.
+ */
+ thresh = 10 * USEC_PER_MSEC;
+
+ /* see init/calibrate.c for lpj -> BogoMIPS calculation */
+ bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1);
+ if (bogo < 4000)
+ thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC);
+
+ pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n",
+ loops_per_jiffy, bogo, thresh);
+
+ wq_cpu_intensive_thresh_us = thresh;
+}
+
/**
* workqueue_init - bring workqueue subsystem fully online
*
@@ -6528,6 +6567,8 @@ void __init workqueue_init(void)
struct worker_pool *pool;
int cpu, bkt;
+ wq_cpu_intensive_thresh_init();
+
/*
* It'd be simpler to initialize NUMA in workqueue_init_early() but
* CPU to node mapping may not be available that early on some