summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/stackmap.c8
-rw-r--r--kernel/cgroup.c63
-rw-r--r--kernel/events/callchain.c35
-rw-r--r--kernel/events/core.c911
-rw-r--r--kernel/events/internal.h10
-rw-r--r--kernel/events/ring_buffer.c128
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/locking/lockdep.c2
-rw-r--r--kernel/locking/locktorture.c25
-rw-r--r--kernel/locking/qspinlock_stat.h24
-rw-r--r--kernel/locking/rwsem-spinlock.c19
-rw-r--r--kernel/locking/rwsem-xadd.c38
-rw-r--r--kernel/locking/rwsem.c19
-rw-r--r--kernel/rcu/Makefile1
-rw-r--r--kernel/rcu/rcuperf.c655
-rw-r--r--kernel/rcu/rcutorture.c29
-rw-r--r--kernel/rcu/tree.c302
-rw-r--r--kernel/rcu/tree.h20
-rw-r--r--kernel/rcu/tree_plugin.h37
-rw-r--r--kernel/rcu/tree_trace.c13
-rw-r--r--kernel/rcu/update.c4
-rw-r--r--kernel/signal.c29
-rw-r--r--kernel/sysctl.c12
-rw-r--r--kernel/time/tick-sched.c4
-rw-r--r--kernel/torture.c4
-rw-r--r--kernel/trace/trace_event_perf.c3
-rw-r--r--kernel/workqueue.c11
27 files changed, 2122 insertions, 286 deletions
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 499d9e933f8e..f5a19548be12 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -66,7 +66,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
value_size < 8 || value_size % 8 ||
- value_size / 8 > PERF_MAX_STACK_DEPTH)
+ value_size / 8 > sysctl_perf_event_max_stack)
return ERR_PTR(-EINVAL);
/* hash table size must be power of 2 */
@@ -124,8 +124,8 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
struct perf_callchain_entry *trace;
struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
u32 max_depth = map->value_size / 8;
- /* stack_map_alloc() checks that max_depth <= PERF_MAX_STACK_DEPTH */
- u32 init_nr = PERF_MAX_STACK_DEPTH - max_depth;
+ /* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
+ u32 init_nr = sysctl_perf_event_max_stack - max_depth;
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
u32 hash, id, trace_nr, trace_len;
bool user = flags & BPF_F_USER_STACK;
@@ -143,7 +143,7 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
return -EFAULT;
/* get_perf_callchain() guarantees that trace->nr >= init_nr
- * and trace-nr <= PERF_MAX_STACK_DEPTH, so trace_nr <= max_depth
+ * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
*/
trace_nr = trace->nr - init_nr;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 909a7d31ffd3..86cb5c6e8932 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1215,6 +1215,41 @@ static void cgroup_destroy_root(struct cgroup_root *root)
cgroup_free_root(root);
}
+/*
+ * look up cgroup associated with current task's cgroup namespace on the
+ * specified hierarchy
+ */
+static struct cgroup *
+current_cgns_cgroup_from_root(struct cgroup_root *root)
+{
+ struct cgroup *res = NULL;
+ struct css_set *cset;
+
+ lockdep_assert_held(&css_set_lock);
+
+ rcu_read_lock();
+
+ cset = current->nsproxy->cgroup_ns->root_cset;
+ if (cset == &init_css_set) {
+ res = &root->cgrp;
+ } else {
+ struct cgrp_cset_link *link;
+
+ list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
+ struct cgroup *c = link->cgrp;
+
+ if (c->root == root) {
+ res = c;
+ break;
+ }
+ }
+ }
+ rcu_read_unlock();
+
+ BUG_ON(!res);
+ return res;
+}
+
/* look up cgroup associated with given css_set on the specified hierarchy */
static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
struct cgroup_root *root)
@@ -1593,6 +1628,33 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
return 0;
}
+static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
+ struct kernfs_root *kf_root)
+{
+ int len = 0;
+ char *buf = NULL;
+ struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root);
+ struct cgroup *ns_cgroup;
+
+ buf = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ spin_lock_bh(&css_set_lock);
+ ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot);
+ len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX);
+ spin_unlock_bh(&css_set_lock);
+
+ if (len >= PATH_MAX)
+ len = -ERANGE;
+ else if (len > 0) {
+ seq_escape(sf, buf, " \t\n\\");
+ len = 0;
+ }
+ kfree(buf);
+ return len;
+}
+
static int cgroup_show_options(struct seq_file *seq,
struct kernfs_root *kf_root)
{
@@ -5433,6 +5495,7 @@ static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
.mkdir = cgroup_mkdir,
.rmdir = cgroup_rmdir,
.rename = cgroup_rename,
+ .show_path = cgroup_show_path,
};
static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 343c22f5e867..b9325e7dcba1 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -18,6 +18,14 @@ struct callchain_cpus_entries {
struct perf_callchain_entry *cpu_entries[0];
};
+int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
+
+static inline size_t perf_callchain_entry__sizeof(void)
+{
+ return (sizeof(struct perf_callchain_entry) +
+ sizeof(__u64) * sysctl_perf_event_max_stack);
+}
+
static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
static atomic_t nr_callchain_events;
static DEFINE_MUTEX(callchain_mutex);
@@ -73,7 +81,7 @@ static int alloc_callchain_buffers(void)
if (!entries)
return -ENOMEM;
- size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
+ size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS;
for_each_possible_cpu(cpu) {
entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
@@ -147,7 +155,8 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
cpu = smp_processor_id();
- return &entries->cpu_entries[cpu][*rctx];
+ return (((void *)entries->cpu_entries[cpu]) +
+ (*rctx * perf_callchain_entry__sizeof()));
}
static void
@@ -215,3 +224,25 @@ exit_put:
return entry;
}
+
+int perf_event_max_stack_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int new_value = sysctl_perf_event_max_stack, ret;
+ struct ctl_table new_table = *table;
+
+ new_table.data = &new_value;
+ ret = proc_dointvec_minmax(&new_table, write, buffer, lenp, ppos);
+ if (ret || !write)
+ return ret;
+
+ mutex_lock(&callchain_mutex);
+ if (atomic_read(&nr_callchain_events))
+ ret = -EBUSY;
+ else
+ sysctl_perf_event_max_stack = new_value;
+
+ mutex_unlock(&callchain_mutex);
+
+ return ret;
+}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c0ded2416615..050a290c72c7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -44,6 +44,8 @@
#include <linux/compat.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/namei.h>
+#include <linux/parser.h>
#include "internal.h"
@@ -1927,8 +1929,13 @@ event_sched_in(struct perf_event *event,
if (event->state <= PERF_EVENT_STATE_OFF)
return 0;
- event->state = PERF_EVENT_STATE_ACTIVE;
- event->oncpu = smp_processor_id();
+ WRITE_ONCE(event->oncpu, smp_processor_id());
+ /*
+ * Order event::oncpu write to happen before the ACTIVE state
+ * is visible.
+ */
+ smp_wmb();
+ WRITE_ONCE(event->state, PERF_EVENT_STATE_ACTIVE);
/*
* Unthrottle events, since we scheduled we might have missed several
@@ -2360,6 +2367,112 @@ void perf_event_enable(struct perf_event *event)
}
EXPORT_SYMBOL_GPL(perf_event_enable);
+struct stop_event_data {
+ struct perf_event *event;
+ unsigned int restart;
+};
+
+static int __perf_event_stop(void *info)
+{
+ struct stop_event_data *sd = info;
+ struct perf_event *event = sd->event;
+
+ /* if it's already INACTIVE, do nothing */
+ if (READ_ONCE(event->state) != PERF_EVENT_STATE_ACTIVE)
+ return 0;
+
+ /* matches smp_wmb() in event_sched_in() */
+ smp_rmb();
+
+ /*
+ * There is a window with interrupts enabled before we get here,
+ * so we need to check again lest we try to stop another CPU's event.
+ */
+ if (READ_ONCE(event->oncpu) != smp_processor_id())
+ return -EAGAIN;
+
+ event->pmu->stop(event, PERF_EF_UPDATE);
+
+ /*
+ * May race with the actual stop (through perf_pmu_output_stop()),
+ * but it is only used for events with AUX ring buffer, and such
+ * events will refuse to restart because of rb::aux_mmap_count==0,
+ * see comments in perf_aux_output_begin().
+ *
+ * Since this is happening on a event-local CPU, no trace is lost
+ * while restarting.
+ */
+ if (sd->restart)
+ event->pmu->start(event, PERF_EF_START);
+
+ return 0;
+}
+
+static int perf_event_restart(struct perf_event *event)
+{
+ struct stop_event_data sd = {
+ .event = event,
+ .restart = 1,
+ };
+ int ret = 0;
+
+ do {
+ if (READ_ONCE(event->state) != PERF_EVENT_STATE_ACTIVE)
+ return 0;
+
+ /* matches smp_wmb() in event_sched_in() */
+ smp_rmb();
+
+ /*
+ * We only want to restart ACTIVE events, so if the event goes
+ * inactive here (event->oncpu==-1), there's nothing more to do;
+ * fall through with ret==-ENXIO.
+ */
+ ret = cpu_function_call(READ_ONCE(event->oncpu),
+ __perf_event_stop, &sd);
+ } while (ret == -EAGAIN);
+
+ return ret;
+}
+
+/*
+ * In order to contain the amount of racy and tricky in the address filter
+ * configuration management, it is a two part process:
+ *
+ * (p1) when userspace mappings change as a result of (1) or (2) or (3) below,
+ * we update the addresses of corresponding vmas in
+ * event::addr_filters_offs array and bump the event::addr_filters_gen;
+ * (p2) when an event is scheduled in (pmu::add), it calls
+ * perf_event_addr_filters_sync() which calls pmu::addr_filters_sync()
+ * if the generation has changed since the previous call.
+ *
+ * If (p1) happens while the event is active, we restart it to force (p2).
+ *
+ * (1) perf_addr_filters_apply(): adjusting filters' offsets based on
+ * pre-existing mappings, called once when new filters arrive via SET_FILTER
+ * ioctl;
+ * (2) perf_addr_filters_adjust(): adjusting filters' offsets based on newly
+ * registered mapping, called for every new mmap(), with mm::mmap_sem down
+ * for reading;
+ * (3) perf_event_addr_filters_exec(): clearing filters' offsets in the process
+ * of exec.
+ */
+void perf_event_addr_filters_sync(struct perf_event *event)
+{
+ struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+
+ if (!has_addr_filter(event))
+ return;
+
+ raw_spin_lock(&ifh->lock);
+ if (event->addr_filters_gen != event->hw.addr_filters_gen) {
+ event->pmu->addr_filters_sync(event);
+ event->hw.addr_filters_gen = event->addr_filters_gen;
+ }
+ raw_spin_unlock(&ifh->lock);
+}
+EXPORT_SYMBOL_GPL(perf_event_addr_filters_sync);
+
static int _perf_event_refresh(struct perf_event *event, int refresh)
{
/*
@@ -3209,16 +3322,6 @@ out:
put_ctx(clone_ctx);
}
-void perf_event_exec(void)
-{
- int ctxn;
-
- rcu_read_lock();
- for_each_task_context_nr(ctxn)
- perf_event_enable_on_exec(ctxn);
- rcu_read_unlock();
-}
-
struct perf_read_data {
struct perf_event *event;
bool group;
@@ -3720,6 +3823,9 @@ static bool exclusive_event_installable(struct perf_event *event,
return true;
}
+static void perf_addr_filters_splice(struct perf_event *event,
+ struct list_head *head);
+
static void _free_event(struct perf_event *event)
{
irq_work_sync(&event->pending);
@@ -3747,6 +3853,8 @@ static void _free_event(struct perf_event *event)
}
perf_event_free_bpf_prog(event);
+ perf_addr_filters_splice(event, NULL);
+ kfree(event->addr_filters_offs);
if (event->destroy)
event->destroy(event);
@@ -4343,6 +4451,19 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
case PERF_EVENT_IOC_SET_BPF:
return perf_event_set_bpf_prog(event, arg);
+ case PERF_EVENT_IOC_PAUSE_OUTPUT: {
+ struct ring_buffer *rb;
+
+ rcu_read_lock();
+ rb = rcu_dereference(event->rb);
+ if (!rb || !rb->nr_pages) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+ rb_toggle_paused(rb, !!arg);
+ rcu_read_unlock();
+ return 0;
+ }
default:
return -ENOTTY;
}
@@ -4659,6 +4780,8 @@ static void perf_mmap_open(struct vm_area_struct *vma)
event->pmu->event_mapped(event);
}
+static void perf_pmu_output_stop(struct perf_event *event);
+
/*
* A buffer can be mmap()ed multiple times; either directly through the same
* event, or through other events by use of perf_event_set_output().
@@ -4686,10 +4809,22 @@ static void perf_mmap_close(struct vm_area_struct *vma)
*/
if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff &&
atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) {
+ /*
+ * Stop all AUX events that are writing to this buffer,
+ * so that we can free its AUX pages and corresponding PMU
+ * data. Note that after rb::aux_mmap_count dropped to zero,
+ * they won't start any more (see perf_aux_output_begin()).
+ */
+ perf_pmu_output_stop(event);
+
+ /* now it's safe to free the pages */
atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
vma->vm_mm->pinned_vm -= rb->aux_mmap_locked;
+ /* this has to be the last one */
rb_free_aux(rb);
+ WARN_ON_ONCE(atomic_read(&rb->aux_refcount));
+
mutex_unlock(&event->mmap_mutex);
}
@@ -5630,9 +5765,13 @@ void perf_prepare_sample(struct perf_event_header *header,
}
}
-void perf_event_output(struct perf_event *event,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+static void __always_inline
+__perf_event_output(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs,
+ int (*output_begin)(struct perf_output_handle *,
+ struct perf_event *,
+ unsigned int))
{
struct perf_output_handle handle;
struct perf_event_header header;
@@ -5642,7 +5781,7 @@ void perf_event_output(struct perf_event *event,
perf_prepare_sample(&header, data, event, regs);
- if (perf_output_begin(&handle, event, header.size))
+ if (output_begin(&handle, event, header.size))
goto exit;
perf_output_sample(&handle, &header, data, event);
@@ -5653,6 +5792,30 @@ exit:
rcu_read_unlock();
}
+void
+perf_event_output_forward(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ __perf_event_output(event, data, regs, perf_output_begin_forward);
+}
+
+void
+perf_event_output_backward(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ __perf_event_output(event, data, regs, perf_output_begin_backward);
+}
+
+void
+perf_event_output(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ __perf_event_output(event, data, regs, perf_output_begin);
+}
+
/*
* read event_id
*/
@@ -5698,15 +5861,18 @@ typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data);
static void
perf_event_aux_ctx(struct perf_event_context *ctx,
perf_event_aux_output_cb output,
- void *data)
+ void *data, bool all)
{
struct perf_event *event;
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
- if (event->state < PERF_EVENT_STATE_INACTIVE)
- continue;
- if (!event_filter_match(event))
- continue;
+ if (!all) {
+ if (event->state < PERF_EVENT_STATE_INACTIVE)
+ continue;
+ if (!event_filter_match(event))
+ continue;
+ }
+
output(event, data);
}
}
@@ -5717,7 +5883,7 @@ perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data,
{
rcu_read_lock();
preempt_disable();
- perf_event_aux_ctx(task_ctx, output, data);
+ perf_event_aux_ctx(task_ctx, output, data, false);
preempt_enable();
rcu_read_unlock();
}
@@ -5747,13 +5913,13 @@ perf_event_aux(perf_event_aux_output_cb output, void *data,
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
if (cpuctx->unique_pmu != pmu)
goto next;
- perf_event_aux_ctx(&cpuctx->ctx, output, data);
+ perf_event_aux_ctx(&cpuctx->ctx, output, data, false);
ctxn = pmu->task_ctx_nr;
if (ctxn < 0)
goto next;
ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
if (ctx)
- perf_event_aux_ctx(ctx, output, data);
+ perf_event_aux_ctx(ctx, output, data, false);
next:
put_cpu_ptr(pmu->pmu_cpu_context);
}
@@ -5761,6 +5927,134 @@ next:
}
/*
+ * Clear all file-based filters at exec, they'll have to be
+ * re-instated when/if these objects are mmapped again.
+ */
+static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
+{
+ struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+ struct perf_addr_filter *filter;
+ unsigned int restart = 0, count = 0;
+ unsigned long flags;
+
+ if (!has_addr_filter(event))
+ return;
+
+ raw_spin_lock_irqsave(&ifh->lock, flags);
+ list_for_each_entry(filter, &ifh->list, entry) {
+ if (filter->inode) {
+ event->addr_filters_offs[count] = 0;
+ restart++;
+ }
+
+ count++;
+ }
+
+ if (restart)
+ event->addr_filters_gen++;
+ raw_spin_unlock_irqrestore(&ifh->lock, flags);
+
+ if (restart)
+ perf_event_restart(event);
+}
+
+void perf_event_exec(void)
+{
+ struct perf_event_context *ctx;
+ int ctxn;
+
+ rcu_read_lock();
+ for_each_task_context_nr(ctxn) {
+ ctx = current->perf_event_ctxp[ctxn];
+ if (!ctx)
+ continue;
+
+ perf_event_enable_on_exec(ctxn);
+
+ perf_event_aux_ctx(ctx, perf_event_addr_filters_exec, NULL,
+ true);
+ }
+ rcu_read_unlock();
+}
+
+struct remote_output {
+ struct ring_buffer *rb;
+ int err;
+};
+
+static void __perf_event_output_stop(struct perf_event *event, void *data)
+{
+ struct perf_event *parent = event->parent;
+ struct remote_output *ro = data;
+ struct ring_buffer *rb = ro->rb;
+ struct stop_event_data sd = {
+ .event = event,
+ };
+
+ if (!has_aux(event))
+ return;
+
+ if (!parent)
+ parent = event;
+
+ /*
+ * In case of inheritance, it will be the parent that links to the
+ * ring-buffer, but it will be the child that's actually using it:
+ */
+ if (rcu_dereference(parent->rb) == rb)
+ ro->err = __perf_event_stop(&sd);
+}
+
+static int __perf_pmu_output_stop(void *info)
+{
+ struct perf_event *event = info;
+ struct pmu *pmu = event->pmu;
+ struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ struct remote_output ro = {
+ .rb = event->rb,
+ };
+
+ rcu_read_lock();
+ perf_event_aux_ctx(&cpuctx->ctx, __perf_event_output_stop, &ro, false);
+ if (cpuctx->task_ctx)
+ perf_event_aux_ctx(cpuctx->task_ctx, __perf_event_output_stop,
+ &ro, false);
+ rcu_read_unlock();
+
+ return ro.err;
+}
+
+static void perf_pmu_output_stop(struct perf_event *event)
+{
+ struct perf_event *iter;
+ int err, cpu;
+
+restart:
+ rcu_read_lock();
+ list_for_each_entry_rcu(iter, &event->rb->event_list, rb_entry) {
+ /*
+ * For per-CPU events, we need to make sure that neither they
+ * nor their children are running; for cpu==-1 events it's
+ * sufficient to stop the event itself if it's active, since
+ * it can't have children.
+ */
+ cpu = iter->cpu;
+ if (cpu == -1)
+ cpu = READ_ONCE(iter->oncpu);
+
+ if (cpu == -1)
+ continue;
+
+ err = cpu_function_call(cpu, __perf_pmu_output_stop, event);
+ if (err == -EAGAIN) {
+ rcu_read_unlock();
+ goto restart;
+ }
+ }
+ rcu_read_unlock();
+}
+
+/*
* task tracking -- fork/exit
*
* enabled by: attr.comm | attr.mmap | attr.mmap2 | attr.mmap_data | attr.task
@@ -6169,6 +6463,87 @@ got_name:
kfree(buf);
}
+/*
+ * Whether this @filter depends on a dynamic object which is not loaded
+ * yet or its load addresses are not known.
+ */
+static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter)
+{
+ return filter->filter && filter->inode;
+}
+
+/*
+ * Check whether inode and address range match filter criteria.
+ */
+static bool perf_addr_filter_match(struct perf_addr_filter *filter,
+ struct file *file, unsigned long offset,
+ unsigned long size)
+{
+ if (filter->inode != file->f_inode)
+ return false;
+
+ if (filter->offset > offset + size)
+ return false;
+
+ if (filter->offset + filter->size < offset)
+ return false;
+
+ return true;
+}
+
+static void __perf_addr_filters_adjust(struct perf_event *event, void *data)
+{
+ struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+ struct vm_area_struct *vma = data;
+ unsigned long off = vma->vm_pgoff << PAGE_SHIFT, flags;
+ struct file *file = vma->vm_file;
+ struct perf_addr_filter *filter;
+ unsigned int restart = 0, count = 0;
+
+ if (!has_addr_filter(event))
+ return;
+
+ if (!file)
+ return;
+
+ raw_spin_lock_irqsave(&ifh->lock, flags);
+ list_for_each_entry(filter, &ifh->list, entry) {
+ if (perf_addr_filter_match(filter, file, off,
+ vma->vm_end - vma->vm_start)) {
+ event->addr_filters_offs[count] = vma->vm_start;
+ restart++;
+ }
+
+ count++;
+ }
+
+ if (restart)
+ event->addr_filters_gen++;
+ raw_spin_unlock_irqrestore(&ifh->lock, flags);
+
+ if (restart)
+ perf_event_restart(event);
+}
+
+/*
+ * Adjust all task's events' filters to the new vma
+ */
+static void perf_addr_filters_adjust(struct vm_area_struct *vma)
+{
+ struct perf_event_context *ctx;
+ int ctxn;
+
+ rcu_read_lock();
+ for_each_task_context_nr(ctxn) {
+ ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+ if (!ctx)
+ continue;
+
+ perf_event_aux_ctx(ctx, __perf_addr_filters_adjust, vma, true);
+ }
+ rcu_read_unlock();
+}
+
void perf_event_mmap(struct vm_area_struct *vma)
{
struct perf_mmap_event mmap_event;
@@ -6200,6 +6575,7 @@ void perf_event_mmap(struct vm_area_struct *vma)
/* .flags (attr_mmap2 only) */
};
+ perf_addr_filters_adjust(vma);
perf_event_mmap_event(&mmap_event);
}
@@ -6491,10 +6867,7 @@ static int __perf_event_overflow(struct perf_event *event,
irq_work_queue(&event->pending);
}
- if (event->overflow_handler)
- event->overflow_handler(event, data, regs);
- else
- perf_event_output(event, data, regs);
+ event->overflow_handler(event, data, regs);
if (*perf_event_fasync(event) && event->pending_kill) {
event->pending_wakeup = 1;
@@ -7081,24 +7454,6 @@ static inline void perf_tp_register(void)
perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT);
}
-static int perf_event_set_filter(struct perf_event *event, void __user *arg)
-{
- char *filter_str;
- int ret;
-
- if (event->attr.type != PERF_TYPE_TRACEPOINT)
- return -EINVAL;
-
- filter_str = strndup_user(arg, PAGE_SIZE);
- if (IS_ERR(filter_str))
- return PTR_ERR(filter_str);
-
- ret = ftrace_profile_set_filter(event, event->attr.config, filter_str);
-
- kfree(filter_str);
- return ret;
-}
-
static void perf_event_free_filter(struct perf_event *event)
{
ftrace_profile_free_filter(event);
@@ -7153,11 +7508,6 @@ static inline void perf_tp_register(void)
{
}
-static int perf_event_set_filter(struct perf_event *event, void __user *arg)
-{
- return -ENOENT;
-}
-
static void perf_event_free_filter(struct perf_event *event)
{
}
@@ -7186,6 +7536,387 @@ void perf_bp_event(struct perf_event *bp, void *data)
#endif
/*
+ * Allocate a new address filter
+ */
+static struct perf_addr_filter *
+perf_addr_filter_new(struct perf_event *event, struct list_head *filters)
+{
+ int node = cpu_to_node(event->cpu == -1 ? 0 : event->cpu);
+ struct perf_addr_filter *filter;
+
+ filter = kzalloc_node(sizeof(*filter), GFP_KERNEL, node);
+ if (!filter)
+ return NULL;
+
+ INIT_LIST_HEAD(&filter->entry);
+ list_add_tail(&filter->entry, filters);
+
+ return filter;
+}
+
+static void free_filters_list(struct list_head *filters)
+{
+ struct perf_addr_filter *filter, *iter;
+
+ list_for_each_entry_safe(filter, iter, filters, entry) {
+ if (filter->inode)
+ iput(filter->inode);
+ list_del(&filter->entry);
+ kfree(filter);
+ }
+}
+
+/*
+ * Free existing address filters and optionally install new ones
+ */
+static void perf_addr_filters_splice(struct perf_event *event,
+ struct list_head *head)
+{
+ unsigned long flags;
+ LIST_HEAD(list);
+
+ if (!has_addr_filter(event))
+ return;
+
+ /* don't bother with children, they don't have their own filters */
+ if (event->parent)
+ return;
+
+ raw_spin_lock_irqsave(&event->addr_filters.lock, flags);
+
+ list_splice_init(&event->addr_filters.list, &list);
+ if (head)
+ list_splice(head, &event->addr_filters.list);
+
+ raw_spin_unlock_irqrestore(&event->addr_filters.lock, flags);
+
+ free_filters_list(&list);
+}
+
+/*
+ * Scan through mm's vmas and see if one of them matches the
+ * @filter; if so, adjust filter's address range.
+ * Called with mm::mmap_sem down for reading.
+ */
+static unsigned long perf_addr_filter_apply(struct perf_addr_filter *filter,
+ struct mm_struct *mm)
+{
+ struct vm_area_struct *vma;
+
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ struct file *file = vma->vm_file;
+ unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
+ unsigned long vma_size = vma->vm_end - vma->vm_start;
+
+ if (!file)
+ continue;
+
+ if (!perf_addr_filter_match(filter, file, off, vma_size))
+ continue;
+
+ return vma->vm_start;
+ }
+
+ return 0;
+}
+
+/*
+ * Update event's address range filters based on the
+ * task's existing mappings, if any.
+ */
+static void perf_event_addr_filters_apply(struct perf_event *event)
+{
+ struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+ struct task_struct *task = READ_ONCE(event->ctx->task);
+ struct perf_addr_filter *filter;
+ struct mm_struct *mm = NULL;
+ unsigned int count = 0;
+ unsigned long flags;
+
+ /*
+ * We may observe TASK_TOMBSTONE, which means that the event tear-down
+ * will stop on the parent's child_mutex that our caller is also holding
+ */
+ if (task == TASK_TOMBSTONE)
+ return;
+
+ mm = get_task_mm(event->ctx->task);
+ if (!mm)
+ goto restart;
+
+ down_read(&mm->mmap_sem);
+
+ raw_spin_lock_irqsave(&ifh->lock, flags);
+ list_for_each_entry(filter, &ifh->list, entry) {
+ event->addr_filters_offs[count] = 0;
+
+ if (perf_addr_filter_needs_mmap(filter))
+ event->addr_filters_offs[count] =
+ perf_addr_filter_apply(filter, mm);
+
+ count++;
+ }
+
+ event->addr_filters_gen++;
+ raw_spin_unlock_irqrestore(&ifh->lock, flags);
+
+ up_read(&mm->mmap_sem);
+
+ mmput(mm);
+
+restart:
+ perf_event_restart(event);
+}
+
+/*
+ * Address range filtering: limiting the data to certain
+ * instruction address ranges. Filters are ioctl()ed to us from
+ * userspace as ascii strings.
+ *
+ * Filter string format:
+ *
+ * ACTION RANGE_SPEC
+ * where ACTION is one of the
+ * * "filter": limit the trace to this region
+ * * "start": start tracing from this address
+ * * "stop": stop tracing at this address/region;
+ * RANGE_SPEC is
+ * * for kernel addresses: <start address>[/<size>]
+ * * for object files: <start address>[/<size>]@</path/to/object/file>
+ *
+ * if <size> is not specified, the range is treated as a single address.
+ */
+enum {
+ IF_ACT_FILTER,
+ IF_ACT_START,
+ IF_ACT_STOP,
+ IF_SRC_FILE,
+ IF_SRC_KERNEL,
+ IF_SRC_FILEADDR,
+ IF_SRC_KERNELADDR,
+};
+
+enum {
+ IF_STATE_ACTION = 0,
+ IF_STATE_SOURCE,
+ IF_STATE_END,
+};
+
+static const match_table_t if_tokens = {
+ { IF_ACT_FILTER, "filter" },
+ { IF_ACT_START, "start" },
+ { IF_ACT_STOP, "stop" },
+ { IF_SRC_FILE, "%u/%u@%s" },
+ { IF_SRC_KERNEL, "%u/%u" },
+ { IF_SRC_FILEADDR, "%u@%s" },
+ { IF_SRC_KERNELADDR, "%u" },
+};
+
+/*
+ * Address filter string parser
+ */
+static int
+perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
+ struct list_head *filters)
+{
+ struct perf_addr_filter *filter = NULL;
+ char *start, *orig, *filename = NULL;
+ struct path path;
+ substring_t args[MAX_OPT_ARGS];
+ int state = IF_STATE_ACTION, token;
+ unsigned int kernel = 0;
+ int ret = -EINVAL;
+
+ orig = fstr = kstrdup(fstr, GFP_KERNEL);
+ if (!fstr)
+ return -ENOMEM;
+
+ while ((start = strsep(&fstr, " ,\n")) != NULL) {
+ ret = -EINVAL;
+
+ if (!*start)
+ continue;
+
+ /* filter definition begins */
+ if (state == IF_STATE_ACTION) {
+ filter = perf_addr_filter_new(event, filters);
+ if (!filter)
+ goto fail;
+ }
+
+ token = match_token(start, if_tokens, args);
+ switch (token) {
+ case IF_ACT_FILTER:
+ case IF_ACT_START:
+ filter->filter = 1;
+
+ case IF_ACT_STOP:
+ if (state != IF_STATE_ACTION)
+ goto fail;
+
+ state = IF_STATE_SOURCE;
+ break;
+
+ case IF_SRC_KERNELADDR:
+ case IF_SRC_KERNEL:
+ kernel = 1;
+
+ case IF_SRC_FILEADDR:
+ case IF_SRC_FILE:
+ if (state != IF_STATE_SOURCE)
+ goto fail;
+
+ if (token == IF_SRC_FILE || token == IF_SRC_KERNEL)
+ filter->range = 1;
+
+ *args[0].to = 0;
+ ret = kstrtoul(args[0].from, 0, &filter->offset);
+ if (ret)
+ goto fail;
+
+ if (filter->range) {
+ *args[1].to = 0;
+ ret = kstrtoul(args[1].from, 0, &filter->size);
+ if (ret)
+ goto fail;
+ }
+
+ if (token == IF_SRC_FILE) {
+ filename = match_strdup(&args[2]);
+ if (!filename) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+ }
+
+ state = IF_STATE_END;
+ break;
+
+ default:
+ goto fail;
+ }
+
+ /*
+ * Filter definition is fully parsed, validate and install it.
+ * Make sure that it doesn't contradict itself or the event's
+ * attribute.
+ */
+ if (state == IF_STATE_END) {
+ if (kernel && event->attr.exclude_kernel)
+ goto fail;
+
+ if (!kernel) {
+ if (!filename)
+ goto fail;
+
+ /* look up the path and grab its inode */
+ ret = kern_path(filename, LOOKUP_FOLLOW, &path);
+ if (ret)
+ goto fail_free_name;
+
+ filter->inode = igrab(d_inode(path.dentry));
+ path_put(&path);
+ kfree(filename);
+ filename = NULL;
+
+ ret = -EINVAL;
+ if (!filter->inode ||
+ !S_ISREG(filter->inode->i_mode))
+ /* free_filters_list() will iput() */
+ goto fail;
+ }
+
+ /* ready to consume more filters */
+ state = IF_STATE_ACTION;
+ filter = NULL;
+ }
+ }
+
+ if (state != IF_STATE_ACTION)
+ goto fail;
+
+ kfree(orig);
+
+ return 0;
+
+fail_free_name:
+ kfree(filename);
+fail:
+ free_filters_list(filters);
+ kfree(orig);
+
+ return ret;
+}
+
+static int
+perf_event_set_addr_filter(struct perf_event *event, char *filter_str)
+{
+ LIST_HEAD(filters);
+ int ret;
+
+ /*
+ * Since this is called in perf_ioctl() path, we're already holding
+ * ctx::mutex.
+ */
+ lockdep_assert_held(&event->ctx->mutex);
+
+ if (WARN_ON_ONCE(event->parent))
+ return -EINVAL;
+
+ /*
+ * For now, we only support filtering in per-task events; doing so
+ * for CPU-wide events requires additional context switching trickery,
+ * since same object code will be mapped at different virtual
+ * addresses in different processes.
+ */
+ if (!event->ctx->task)
+ return -EOPNOTSUPP;
+
+ ret = perf_event_parse_addr_filter(event, filter_str, &filters);
+ if (ret)
+ return ret;
+
+ ret = event->pmu->addr_filters_validate(&filters);
+ if (ret) {
+ free_filters_list(&filters);
+ return ret;
+ }
+
+ /* remove existing filters, if any */
+ perf_addr_filters_splice(event, &filters);
+
+ /* install new filters */
+ perf_event_for_each_child(event, perf_event_addr_filters_apply);
+
+ return ret;
+}
+
+static int perf_event_set_filter(struct perf_event *event, void __user *arg)
+{
+ char *filter_str;
+ int ret = -EINVAL;
+
+ if ((event->attr.type != PERF_TYPE_TRACEPOINT ||
+ !IS_ENABLED(CONFIG_EVENT_TRACING)) &&
+ !has_addr_filter(event))
+ return -EINVAL;
+
+ filter_str = strndup_user(arg, PAGE_SIZE);
+ if (IS_ERR(filter_str))
+ return PTR_ERR(filter_str);
+
+ if (IS_ENABLED(CONFIG_EVENT_TRACING) &&
+ event->attr.type == PERF_TYPE_TRACEPOINT)
+ ret = ftrace_profile_set_filter(event, event->attr.config,
+ filter_str);
+ else if (has_addr_filter(event))
+ ret = perf_event_set_addr_filter(event, filter_str);
+
+ kfree(filter_str);
+ return ret;
+}
+
+/*
* hrtimer based swevent callback
*/
@@ -7542,6 +8273,20 @@ static void free_pmu_context(struct pmu *pmu)
out:
mutex_unlock(&pmus_lock);
}
+
+/*
+ * Let userspace know that this PMU supports address range filtering:
+ */
+static ssize_t nr_addr_filters_show(struct device *dev,
+ struct device_attribute *attr,
+ char *page)
+{
+ struct pmu *pmu = dev_get_drvdata(dev);
+
+ return snprintf(page, PAGE_SIZE - 1, "%d\n", pmu->nr_addr_filters);
+}
+DEVICE_ATTR_RO(nr_addr_filters);
+
static struct idr pmu_idr;
static ssize_t
@@ -7643,9 +8388,19 @@ static int pmu_dev_alloc(struct pmu *pmu)
if (ret)
goto free_dev;
+ /* For PMUs with address filters, throw in an extra attribute: */
+ if (pmu->nr_addr_filters)
+ ret = device_create_file(pmu->dev, &dev_attr_nr_addr_filters);
+
+ if (ret)
+ goto del_dev;
+
out:
return ret;
+del_dev:
+ device_del(pmu->dev);
+
free_dev:
put_device(pmu->dev);
goto out;
@@ -7685,6 +8440,21 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
}
skip_type:
+ if (pmu->task_ctx_nr == perf_hw_context) {
+ static int hw_context_taken = 0;
+
+ /*
+ * Other than systems with heterogeneous CPUs, it never makes
+ * sense for two PMUs to share perf_hw_context. PMUs which are
+ * uncore must use perf_invalid_context.
+ */
+ if (WARN_ON_ONCE(hw_context_taken &&
+ !(pmu->capabilities & PERF_PMU_CAP_HETEROGENEOUS_CPUS)))
+ pmu->task_ctx_nr = perf_invalid_context;
+
+ hw_context_taken = 1;
+ }
+
pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr);
if (pmu->pmu_cpu_context)
goto got_cpu_context;
@@ -7772,6 +8542,8 @@ void perf_pmu_unregister(struct pmu *pmu)
free_percpu(pmu->pmu_disable_count);
if (pmu->type >= PERF_TYPE_MAX)
idr_remove(&pmu_idr, pmu->type);
+ if (pmu->nr_addr_filters)
+ device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
device_del(pmu->dev);
put_device(pmu->dev);
free_pmu_context(pmu);
@@ -7965,6 +8737,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
INIT_LIST_HEAD(&event->sibling_list);
INIT_LIST_HEAD(&event->rb_entry);
INIT_LIST_HEAD(&event->active_entry);
+ INIT_LIST_HEAD(&event->addr_filters.list);
INIT_HLIST_NODE(&event->hlist_entry);
@@ -7972,6 +8745,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
init_irq_work(&event->pending, perf_pending_event);
mutex_init(&event->mmap_mutex);
+ raw_spin_lock_init(&event->addr_filters.lock);
atomic_long_set(&event->refcount, 1);
event->cpu = cpu;
@@ -8006,8 +8780,16 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
context = parent_event->overflow_handler_context;
}
- event->overflow_handler = overflow_handler;
- event->overflow_handler_context = context;
+ if (overflow_handler) {
+ event->overflow_handler = overflow_handler;
+ event->overflow_handler_context = context;
+ } else if (is_write_backward(event)){
+ event->overflow_handler = perf_event_output_backward;
+ event->overflow_handler_context = NULL;
+ } else {
+ event->overflow_handler = perf_event_output_forward;
+ event->overflow_handler_context = NULL;
+ }
perf_event__state_init(event);
@@ -8048,11 +8830,22 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
if (err)
goto err_pmu;
+ if (has_addr_filter(event)) {
+ event->addr_filters_offs = kcalloc(pmu->nr_addr_filters,
+ sizeof(unsigned long),
+ GFP_KERNEL);
+ if (!event->addr_filters_offs)
+ goto err_per_task;
+
+ /* force hw sync on the address filters */
+ event->addr_filters_gen = 1;
+ }
+
if (!event->parent) {
if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
err = get_callchain_buffers();
if (err)
- goto err_per_task;
+ goto err_addr_filters;
}
}
@@ -8061,6 +8854,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
return event;
+err_addr_filters:
+ kfree(event->addr_filters_offs);
+
err_per_task:
exclusive_event_destroy(event);
@@ -8240,6 +9036,13 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
goto out;
/*
+ * Either writing ring buffer from beginning or from end.
+ * Mixing is not allowed.
+ */
+ if (is_write_backward(output_event) != is_write_backward(event))
+ goto out;
+
+ /*
* If both events generate aux data, they must be on the same PMU
*/
if (has_aux(event) && has_aux(output_event) &&
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 4199b6d193f5..05f9f6d626df 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -11,13 +11,13 @@
struct ring_buffer {
atomic_t refcount;
struct rcu_head rcu_head;
- struct irq_work irq_work;
#ifdef CONFIG_PERF_USE_VMALLOC
struct work_struct work;
int page_order; /* allocation order */
#endif
int nr_pages; /* nr of data pages */
int overwrite; /* can overwrite itself */
+ int paused; /* can write into ring buffer */
atomic_t poll; /* POLL_ for wakeups */
@@ -65,6 +65,14 @@ static inline void rb_free_rcu(struct rcu_head *rcu_head)
rb_free(rb);
}
+static inline void rb_toggle_paused(struct ring_buffer *rb, bool pause)
+{
+ if (!pause && rb->nr_pages)
+ rb->paused = 0;
+ else
+ rb->paused = 1;
+}
+
extern struct ring_buffer *
rb_alloc(int nr_pages, long watermark, int cpu, int flags);
extern void perf_event_wakeup(struct perf_event *event);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index c61f0cbd308b..ae9b90dc9a5a 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -102,8 +102,21 @@ out:
preempt_enable();
}
-int perf_output_begin(struct perf_output_handle *handle,
- struct perf_event *event, unsigned int size)
+static bool __always_inline
+ring_buffer_has_space(unsigned long head, unsigned long tail,
+ unsigned long data_size, unsigned int size,
+ bool backward)
+{
+ if (!backward)
+ return CIRC_SPACE(head, tail, data_size) >= size;
+ else
+ return CIRC_SPACE(tail, head, data_size) >= size;
+}
+
+static int __always_inline
+__perf_output_begin(struct perf_output_handle *handle,
+ struct perf_event *event, unsigned int size,
+ bool backward)
{
struct ring_buffer *rb;
unsigned long tail, offset, head;
@@ -125,8 +138,11 @@ int perf_output_begin(struct perf_output_handle *handle,
if (unlikely(!rb))
goto out;
- if (unlikely(!rb->nr_pages))
+ if (unlikely(rb->paused)) {
+ if (rb->nr_pages)
+ local_inc(&rb->lost);
goto out;
+ }
handle->rb = rb;
handle->event = event;
@@ -143,9 +159,12 @@ int perf_output_begin(struct perf_output_handle *handle,
do {
tail = READ_ONCE(rb->user_page->data_tail);
offset = head = local_read(&rb->head);
- if (!rb->overwrite &&
- unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
- goto fail;
+ if (!rb->overwrite) {
+ if (unlikely(!ring_buffer_has_space(head, tail,
+ perf_data_size(rb),
+ size, backward)))
+ goto fail;
+ }
/*
* The above forms a control dependency barrier separating the
@@ -159,9 +178,17 @@ int perf_output_begin(struct perf_output_handle *handle,
* See perf_output_put_handle().
*/
- head += size;
+ if (!backward)
+ head += size;
+ else
+ head -= size;
} while (local_cmpxchg(&rb->head, offset, head) != offset);
+ if (backward) {
+ offset = head;
+ head = (u64)(-head);
+ }
+
/*
* We rely on the implied barrier() by local_cmpxchg() to ensure
* none of the data stores below can be lifted up by the compiler.
@@ -203,6 +230,26 @@ out:
return -ENOSPC;
}
+int perf_output_begin_forward(struct perf_output_handle *handle,
+ struct perf_event *event, unsigned int size)
+{
+ return __perf_output_begin(handle, event, size, false);
+}
+
+int perf_output_begin_backward(struct perf_output_handle *handle,
+ struct perf_event *event, unsigned int size)
+{
+ return __perf_output_begin(handle, event, size, true);
+}
+
+int perf_output_begin(struct perf_output_handle *handle,
+ struct perf_event *event, unsigned int size)
+{
+
+ return __perf_output_begin(handle, event, size,
+ unlikely(is_write_backward(event)));
+}
+
unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len)
{
@@ -221,8 +268,6 @@ void perf_output_end(struct perf_output_handle *handle)
rcu_read_unlock();
}
-static void rb_irq_work(struct irq_work *work);
-
static void
ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
{
@@ -243,16 +288,13 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
INIT_LIST_HEAD(&rb->event_list);
spin_lock_init(&rb->event_lock);
- init_irq_work(&rb->irq_work, rb_irq_work);
-}
-static void ring_buffer_put_async(struct ring_buffer *rb)
-{
- if (!atomic_dec_and_test(&rb->refcount))
- return;
-
- rb->rcu_head.next = (void *)rb;
- irq_work_queue(&rb->irq_work);
+ /*
+ * perf_output_begin() only checks rb->paused, therefore
+ * rb->paused must be true if we have no pages for output.
+ */
+ if (!rb->nr_pages)
+ rb->paused = 1;
}
/*
@@ -264,6 +306,10 @@ static void ring_buffer_put_async(struct ring_buffer *rb)
* The ordering is similar to that of perf_output_{begin,end}, with
* the exception of (B), which should be taken care of by the pmu
* driver, since ordering rules will differ depending on hardware.
+ *
+ * Call this from pmu::start(); see the comment in perf_aux_output_end()
+ * about its use in pmu callbacks. Both can also be called from the PMI
+ * handler if needed.
*/
void *perf_aux_output_begin(struct perf_output_handle *handle,
struct perf_event *event)
@@ -288,6 +334,13 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
goto err;
/*
+ * If rb::aux_mmap_count is zero (and rb_has_aux() above went through),
+ * the aux buffer is in perf_mmap_close(), about to get freed.
+ */
+ if (!atomic_read(&rb->aux_mmap_count))
+ goto err_put;
+
+ /*
* Nesting is not supported for AUX area, make sure nested
* writers are caught early
*/
@@ -328,10 +381,11 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
return handle->rb->aux_priv;
err_put:
+ /* can't be last */
rb_free_aux(rb);
err:
- ring_buffer_put_async(rb);
+ ring_buffer_put(rb);
handle->event = NULL;
return NULL;
@@ -342,11 +396,16 @@ err:
* aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the
* pmu driver's responsibility to observe ordering rules of the hardware,
* so that all the data is externally visible before this is called.
+ *
+ * Note: this has to be called from pmu::stop() callback, as the assumption
+ * of the AUX buffer management code is that after pmu::stop(), the AUX
+ * transaction must be stopped and therefore drop the AUX reference count.
*/
void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
bool truncated)
{
struct ring_buffer *rb = handle->rb;
+ bool wakeup = truncated;
unsigned long aux_head;
u64 flags = 0;
@@ -375,14 +434,22 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) {
- perf_output_wakeup(handle);
+ wakeup = true;
local_add(rb->aux_watermark, &rb->aux_wakeup);
}
+
+ if (wakeup) {
+ if (truncated)
+ handle->event->pending_disable = 1;
+ perf_output_wakeup(handle);
+ }
+
handle->event = NULL;
local_set(&rb->aux_nest, 0);
+ /* can't be last */
rb_free_aux(rb);
- ring_buffer_put_async(rb);
+ ring_buffer_put(rb);
}
/*
@@ -463,6 +530,14 @@ static void __rb_free_aux(struct ring_buffer *rb)
{
int pg;
+ /*
+ * Should never happen, the last reference should be dropped from
+ * perf_mmap_close() path, which first stops aux transactions (which
+ * in turn are the atomic holders of aux_refcount) and then does the
+ * last rb_free_aux().
+ */
+ WARN_ON_ONCE(in_atomic());
+
if (rb->aux_priv) {
rb->free_aux(rb->aux_priv);
rb->free_aux = NULL;
@@ -574,18 +649,7 @@ out:
void rb_free_aux(struct ring_buffer *rb)
{
if (atomic_dec_and_test(&rb->aux_refcount))
- irq_work_queue(&rb->irq_work);
-}
-
-static void rb_irq_work(struct irq_work *work)
-{
- struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work);
-
- if (!atomic_read(&rb->aux_refcount))
__rb_free_aux(rb);
-
- if (rb->rcu_head.next == (void *)rb)
- call_rcu(&rb->rcu_head, rb_free_rcu);
}
#ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/kernel/fork.c b/kernel/fork.c
index d277e83ed3e0..3e8451527cbe 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1494,7 +1494,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
* sigaltstack should be cleared when sharing the same VM
*/
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
- p->sas_ss_sp = p->sas_ss_size = 0;
+ sas_ss_reset(p);
/*
* Syscall tracing and stepping should be turned off in the
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 68bc6a654ca3..81f1a7107c0e 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -709,7 +709,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
* yet. Otherwise we look it up. We cache the result in the lock object
* itself, so actual lookup of the hash should be once per lock object.
*/
-static inline struct lock_class *
+static struct lock_class *
register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
{
struct lockdep_subclass_key *key;
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 8ef1919d63b2..f8c5af52a131 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -75,12 +75,7 @@ struct lock_stress_stats {
long n_lock_acquired;
};
-#if defined(MODULE)
-#define LOCKTORTURE_RUNNABLE_INIT 1
-#else
-#define LOCKTORTURE_RUNNABLE_INIT 0
-#endif
-int torture_runnable = LOCKTORTURE_RUNNABLE_INIT;
+int torture_runnable = IS_ENABLED(MODULE);
module_param(torture_runnable, int, 0444);
MODULE_PARM_DESC(torture_runnable, "Start locktorture at module init");
@@ -394,12 +389,12 @@ static void torture_rtmutex_boost(struct torture_random_state *trsp)
if (!rt_task(current)) {
/*
- * (1) Boost priority once every ~50k operations. When the
+ * Boost priority once every ~50k operations. When the
* task tries to take the lock, the rtmutex it will account
* for the new priority, and do any corresponding pi-dance.
*/
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * factor))) {
+ if (trsp && !(torture_random(trsp) %
+ (cxt.nrealwriters_stress * factor))) {
policy = SCHED_FIFO;
param.sched_priority = MAX_RT_PRIO - 1;
} else /* common case, do nothing */
@@ -748,6 +743,15 @@ static void lock_torture_cleanup(void)
if (torture_cleanup_begin())
return;
+ /*
+ * Indicates early cleanup, meaning that the test has not run,
+ * such as when passing bogus args when loading the module. As
+ * such, only perform the underlying torture-specific cleanups,
+ * and avoid anything related to locktorture.
+ */
+ if (!cxt.lwsa)
+ goto end;
+
if (writer_tasks) {
for (i = 0; i < cxt.nrealwriters_stress; i++)
torture_stop_kthread(lock_torture_writer,
@@ -776,6 +780,7 @@ static void lock_torture_cleanup(void)
else
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: SUCCESS");
+end:
torture_cleanup_end();
}
@@ -870,6 +875,7 @@ static int __init lock_torture_init(void)
VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory");
firsterr = -ENOMEM;
kfree(cxt.lwsa);
+ cxt.lwsa = NULL;
goto unwind;
}
@@ -878,6 +884,7 @@ static int __init lock_torture_init(void)
cxt.lrsa[i].n_lock_acquired = 0;
}
}
+
lock_torture_print_module_parms(cxt.cur_ops, "Start of test");
/* Prepare torture context. */
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index d734b7502001..22e025309845 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -191,8 +191,6 @@ static ssize_t qstat_write(struct file *file, const char __user *user_buf,
for (i = 0 ; i < qstat_num; i++)
WRITE_ONCE(ptr[i], 0);
- for (i = 0 ; i < qstat_num; i++)
- WRITE_ONCE(ptr[i], 0);
}
return count;
}
@@ -214,10 +212,8 @@ static int __init init_qspinlock_stat(void)
struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL);
int i;
- if (!d_qstat) {
- pr_warn("Could not create 'qlockstat' debugfs directory\n");
- return 0;
- }
+ if (!d_qstat)
+ goto out;
/*
* Create the debugfs files
@@ -227,12 +223,20 @@ static int __init init_qspinlock_stat(void)
* performance.
*/
for (i = 0; i < qstat_num; i++)
- debugfs_create_file(qstat_names[i], 0400, d_qstat,
- (void *)(long)i, &fops_qstat);
+ if (!debugfs_create_file(qstat_names[i], 0400, d_qstat,
+ (void *)(long)i, &fops_qstat))
+ goto fail_undo;
+
+ if (!debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat,
+ (void *)(long)qstat_reset_cnts, &fops_qstat))
+ goto fail_undo;
- debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat,
- (void *)(long)qstat_reset_cnts, &fops_qstat);
return 0;
+fail_undo:
+ debugfs_remove_recursive(d_qstat);
+out:
+ pr_warn("Could not create 'qlockstat' debugfs entries\n");
+ return -ENOMEM;
}
fs_initcall(init_qspinlock_stat);
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 3a5048572065..1591f6b3539f 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -191,11 +191,12 @@ int __down_read_trylock(struct rw_semaphore *sem)
/*
* get a write lock on the semaphore
*/
-void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
+int __sched __down_write_common(struct rw_semaphore *sem, int state)
{
struct rwsem_waiter waiter;
struct task_struct *tsk;
unsigned long flags;
+ int ret = 0;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
@@ -215,21 +216,33 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
*/
if (sem->count == 0)
break;
- set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ if (signal_pending_state(state, current)) {
+ ret = -EINTR;
+ goto out;
+ }
+ set_task_state(tsk, state);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
schedule();
raw_spin_lock_irqsave(&sem->wait_lock, flags);
}
/* got the lock */
sem->count = -1;
+out:
list_del(&waiter.list);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ return ret;
}
void __sched __down_write(struct rw_semaphore *sem)
{
- __down_write_nested(sem, 0);
+ __down_write_common(sem, TASK_UNINTERRUPTIBLE);
+}
+
+int __sched __down_write_killable(struct rw_semaphore *sem)
+{
+ return __down_write_common(sem, TASK_KILLABLE);
}
/*
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index a4d4de05b2d1..09e30c6225e5 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -433,12 +433,13 @@ static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
/*
* Wait until we successfully acquire the write lock
*/
-__visible
-struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
+static inline struct rw_semaphore *
+__rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
{
long count;
bool waiting = true; /* any queued threads before us */
struct rwsem_waiter waiter;
+ struct rw_semaphore *ret = sem;
/* undo write bias from down_write operation, stop active locking */
count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem);
@@ -478,7 +479,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
/* wait until we successfully acquire the lock */
- set_current_state(TASK_UNINTERRUPTIBLE);
+ set_current_state(state);
while (true) {
if (rwsem_try_write_lock(count, sem))
break;
@@ -486,21 +487,48 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
/* Block until there are no active lockers. */
do {
+ if (signal_pending_state(state, current))
+ goto out_nolock;
+
schedule();
- set_current_state(TASK_UNINTERRUPTIBLE);
+ set_current_state(state);
} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
raw_spin_lock_irq(&sem->wait_lock);
}
__set_current_state(TASK_RUNNING);
+ list_del(&waiter.list);
+ raw_spin_unlock_irq(&sem->wait_lock);
+ return ret;
+
+out_nolock:
+ __set_current_state(TASK_RUNNING);
+ raw_spin_lock_irq(&sem->wait_lock);
list_del(&waiter.list);
+ if (list_empty(&sem->wait_list))
+ rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem);
+ else
+ __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
raw_spin_unlock_irq(&sem->wait_lock);
- return sem;
+ return ERR_PTR(-EINTR);
+}
+
+__visible struct rw_semaphore * __sched
+rwsem_down_write_failed(struct rw_semaphore *sem)
+{
+ return __rwsem_down_write_failed_common(sem, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(rwsem_down_write_failed);
+__visible struct rw_semaphore * __sched
+rwsem_down_write_failed_killable(struct rw_semaphore *sem)
+{
+ return __rwsem_down_write_failed_common(sem, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(rwsem_down_write_failed_killable);
+
/*
* handle waking up a waiter on the semaphore
* - up_read/up_write has decremented the active part of count if we come here
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 205be0ce34de..c817216c1615 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -55,6 +55,25 @@ void __sched down_write(struct rw_semaphore *sem)
EXPORT_SYMBOL(down_write);
/*
+ * lock for writing
+ */
+int __sched down_write_killable(struct rw_semaphore *sem)
+{
+ might_sleep();
+ rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
+
+ if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
+ rwsem_release(&sem->dep_map, 1, _RET_IP_);
+ return -EINTR;
+ }
+
+ rwsem_set_owner(sem);
+ return 0;
+}
+
+EXPORT_SYMBOL(down_write_killable);
+
+/*
* trylock for writing -- returns 1 if successful, 0 if contention
*/
int down_write_trylock(struct rw_semaphore *sem)
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 032b2c015beb..18dfc485225c 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -5,6 +5,7 @@ KCOV_INSTRUMENT := n
obj-y += update.o sync.o
obj-$(CONFIG_SRCU) += srcu.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
+obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
obj-$(CONFIG_TREE_RCU) += tree.o
obj-$(CONFIG_PREEMPT_RCU) += tree.o
obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
new file mode 100644
index 000000000000..3cee0d8393ed
--- /dev/null
+++ b/kernel/rcu/rcuperf.c
@@ -0,0 +1,655 @@
+/*
+ * Read-Copy Update module-based performance-test facility
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2015
+ *
+ * Authors: Paul E. McKenney <paulmck@us.ibm.com>
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/rcupdate.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/freezer.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
+#include <asm/byteorder.h>
+#include <linux/torture.h>
+#include <linux/vmalloc.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
+
+#define PERF_FLAG "-perf:"
+#define PERFOUT_STRING(s) \
+ pr_alert("%s" PERF_FLAG s "\n", perf_type)
+#define VERBOSE_PERFOUT_STRING(s) \
+ do { if (verbose) pr_alert("%s" PERF_FLAG " %s\n", perf_type, s); } while (0)
+#define VERBOSE_PERFOUT_ERRSTRING(s) \
+ do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0)
+
+torture_param(bool, gp_exp, true, "Use expedited GP wait primitives");
+torture_param(int, holdoff, 10, "Holdoff time before test start (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, false, "Shutdown at end of performance tests.");
+torture_param(bool, verbose, true, "Enable verbose debugging printk()s");
+
+static char *perf_type = "rcu";
+module_param(perf_type, charp, 0444);
+MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, rcu_bh, ...)");
+
+static int nrealreaders;
+static int nrealwriters;
+static struct task_struct **writer_tasks;
+static struct task_struct **reader_tasks;
+static struct task_struct *shutdown_task;
+
+static u64 **writer_durations;
+static int *writer_n_durations;
+static atomic_t n_rcu_perf_reader_started;
+static atomic_t n_rcu_perf_writer_started;
+static atomic_t n_rcu_perf_writer_finished;
+static wait_queue_head_t shutdown_wq;
+static u64 t_rcu_perf_writer_started;
+static u64 t_rcu_perf_writer_finished;
+static unsigned long b_rcu_perf_writer_started;
+static unsigned long b_rcu_perf_writer_finished;
+
+static int rcu_perf_writer_state;
+#define RTWS_INIT 0
+#define RTWS_EXP_SYNC 1
+#define RTWS_SYNC 2
+#define RTWS_IDLE 2
+#define RTWS_STOPPING 3
+
+#define MAX_MEAS 10000
+#define MIN_MEAS 100
+
+#if defined(MODULE) || defined(CONFIG_RCU_PERF_TEST_RUNNABLE)
+#define RCUPERF_RUNNABLE_INIT 1
+#else
+#define RCUPERF_RUNNABLE_INIT 0
+#endif
+static int perf_runnable = RCUPERF_RUNNABLE_INIT;
+module_param(perf_runnable, int, 0444);
+MODULE_PARM_DESC(perf_runnable, "Start rcuperf at boot");
+
+/*
+ * Operations vector for selecting different types of tests.
+ */
+
+struct rcu_perf_ops {
+ int ptype;
+ void (*init)(void);
+ void (*cleanup)(void);
+ int (*readlock)(void);
+ void (*readunlock)(int idx);
+ unsigned long (*started)(void);
+ unsigned long (*completed)(void);
+ unsigned long (*exp_completed)(void);
+ void (*sync)(void);
+ void (*exp_sync)(void);
+ const char *name;
+};
+
+static struct rcu_perf_ops *cur_ops;
+
+/*
+ * Definitions for rcu perf testing.
+ */
+
+static int rcu_perf_read_lock(void) __acquires(RCU)
+{
+ rcu_read_lock();
+ return 0;
+}
+
+static void rcu_perf_read_unlock(int idx) __releases(RCU)
+{
+ rcu_read_unlock();
+}
+
+static unsigned long __maybe_unused rcu_no_completed(void)
+{
+ return 0;
+}
+
+static void rcu_sync_perf_init(void)
+{
+}
+
+static struct rcu_perf_ops rcu_ops = {
+ .ptype = RCU_FLAVOR,
+ .init = rcu_sync_perf_init,
+ .readlock = rcu_perf_read_lock,
+ .readunlock = rcu_perf_read_unlock,
+ .started = rcu_batches_started,
+ .completed = rcu_batches_completed,
+ .exp_completed = rcu_exp_batches_completed,
+ .sync = synchronize_rcu,
+ .exp_sync = synchronize_rcu_expedited,
+ .name = "rcu"
+};
+
+/*
+ * Definitions for rcu_bh perf testing.
+ */
+
+static int rcu_bh_perf_read_lock(void) __acquires(RCU_BH)
+{
+ rcu_read_lock_bh();
+ return 0;
+}
+
+static void rcu_bh_perf_read_unlock(int idx) __releases(RCU_BH)
+{
+ rcu_read_unlock_bh();
+}
+
+static struct rcu_perf_ops rcu_bh_ops = {
+ .ptype = RCU_BH_FLAVOR,
+ .init = rcu_sync_perf_init,
+ .readlock = rcu_bh_perf_read_lock,
+ .readunlock = rcu_bh_perf_read_unlock,
+ .started = rcu_batches_started_bh,
+ .completed = rcu_batches_completed_bh,
+ .exp_completed = rcu_exp_batches_completed_sched,
+ .sync = synchronize_rcu_bh,
+ .exp_sync = synchronize_rcu_bh_expedited,
+ .name = "rcu_bh"
+};
+
+/*
+ * Definitions for srcu perf testing.
+ */
+
+DEFINE_STATIC_SRCU(srcu_ctl_perf);
+static struct srcu_struct *srcu_ctlp = &srcu_ctl_perf;
+
+static int srcu_perf_read_lock(void) __acquires(srcu_ctlp)
+{
+ return srcu_read_lock(srcu_ctlp);
+}
+
+static void srcu_perf_read_unlock(int idx) __releases(srcu_ctlp)
+{
+ srcu_read_unlock(srcu_ctlp, idx);
+}
+
+static unsigned long srcu_perf_completed(void)
+{
+ return srcu_batches_completed(srcu_ctlp);
+}
+
+static void srcu_perf_synchronize(void)
+{
+ synchronize_srcu(srcu_ctlp);
+}
+
+static void srcu_perf_synchronize_expedited(void)
+{
+ synchronize_srcu_expedited(srcu_ctlp);
+}
+
+static struct rcu_perf_ops srcu_ops = {
+ .ptype = SRCU_FLAVOR,
+ .init = rcu_sync_perf_init,
+ .readlock = srcu_perf_read_lock,
+ .readunlock = srcu_perf_read_unlock,
+ .started = NULL,
+ .completed = srcu_perf_completed,
+ .exp_completed = srcu_perf_completed,
+ .sync = srcu_perf_synchronize,
+ .exp_sync = srcu_perf_synchronize_expedited,
+ .name = "srcu"
+};
+
+/*
+ * Definitions for sched perf testing.
+ */
+
+static int sched_perf_read_lock(void)
+{
+ preempt_disable();
+ return 0;
+}
+
+static void sched_perf_read_unlock(int idx)
+{
+ preempt_enable();
+}
+
+static struct rcu_perf_ops sched_ops = {
+ .ptype = RCU_SCHED_FLAVOR,
+ .init = rcu_sync_perf_init,
+ .readlock = sched_perf_read_lock,
+ .readunlock = sched_perf_read_unlock,
+ .started = rcu_batches_started_sched,
+ .completed = rcu_batches_completed_sched,
+ .exp_completed = rcu_exp_batches_completed_sched,
+ .sync = synchronize_sched,
+ .exp_sync = synchronize_sched_expedited,
+ .name = "sched"
+};
+
+#ifdef CONFIG_TASKS_RCU
+
+/*
+ * Definitions for RCU-tasks perf testing.
+ */
+
+static int tasks_perf_read_lock(void)
+{
+ return 0;
+}
+
+static void tasks_perf_read_unlock(int idx)
+{
+}
+
+static struct rcu_perf_ops tasks_ops = {
+ .ptype = RCU_TASKS_FLAVOR,
+ .init = rcu_sync_perf_init,
+ .readlock = tasks_perf_read_lock,
+ .readunlock = tasks_perf_read_unlock,
+ .started = rcu_no_completed,
+ .completed = rcu_no_completed,
+ .sync = synchronize_rcu_tasks,
+ .exp_sync = synchronize_rcu_tasks,
+ .name = "tasks"
+};
+
+#define RCUPERF_TASKS_OPS &tasks_ops,
+
+static bool __maybe_unused torturing_tasks(void)
+{
+ return cur_ops == &tasks_ops;
+}
+
+#else /* #ifdef CONFIG_TASKS_RCU */
+
+#define RCUPERF_TASKS_OPS
+
+static bool __maybe_unused torturing_tasks(void)
+{
+ return false;
+}
+
+#endif /* #else #ifdef CONFIG_TASKS_RCU */
+
+/*
+ * If performance tests complete, wait for shutdown to commence.
+ */
+static void rcu_perf_wait_shutdown(void)
+{
+ cond_resched_rcu_qs();
+ if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters)
+ return;
+ while (!torture_must_stop())
+ schedule_timeout_uninterruptible(1);
+}
+
+/*
+ * RCU perf reader kthread. Repeatedly does empty RCU read-side
+ * critical section, minimizing update-side interference.
+ */
+static int
+rcu_perf_reader(void *arg)
+{
+ unsigned long flags;
+ int idx;
+ long me = (long)arg;
+
+ VERBOSE_PERFOUT_STRING("rcu_perf_reader task started");
+ set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+ set_user_nice(current, MAX_NICE);
+ atomic_inc(&n_rcu_perf_reader_started);
+
+ do {
+ local_irq_save(flags);
+ idx = cur_ops->readlock();
+ cur_ops->readunlock(idx);
+ local_irq_restore(flags);
+ rcu_perf_wait_shutdown();
+ } while (!torture_must_stop());
+ torture_kthread_stopping("rcu_perf_reader");
+ return 0;
+}
+
+/*
+ * RCU perf writer kthread. Repeatedly does a grace period.
+ */
+static int
+rcu_perf_writer(void *arg)
+{
+ int i = 0;
+ int i_max;
+ long me = (long)arg;
+ struct sched_param sp;
+ bool started = false, done = false, alldone = false;
+ u64 t;
+ u64 *wdp;
+ u64 *wdpp = writer_durations[me];
+
+ VERBOSE_PERFOUT_STRING("rcu_perf_writer task started");
+ WARN_ON(rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp);
+ WARN_ON(rcu_gp_is_normal() && gp_exp);
+ WARN_ON(!wdpp);
+ set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+ sp.sched_priority = 1;
+ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+
+ if (holdoff)
+ schedule_timeout_uninterruptible(holdoff * HZ);
+
+ t = ktime_get_mono_fast_ns();
+ if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) {
+ t_rcu_perf_writer_started = t;
+ if (gp_exp) {
+ b_rcu_perf_writer_started =
+ cur_ops->exp_completed() / 2;
+ } else {
+ b_rcu_perf_writer_started =
+ cur_ops->completed();
+ }
+ }
+
+ do {
+ wdp = &wdpp[i];
+ *wdp = ktime_get_mono_fast_ns();
+ if (gp_exp) {
+ rcu_perf_writer_state = RTWS_EXP_SYNC;
+ cur_ops->exp_sync();
+ } else {
+ rcu_perf_writer_state = RTWS_SYNC;
+ cur_ops->sync();
+ }
+ rcu_perf_writer_state = RTWS_IDLE;
+ t = ktime_get_mono_fast_ns();
+ *wdp = t - *wdp;
+ i_max = i;
+ if (!started &&
+ atomic_read(&n_rcu_perf_writer_started) >= nrealwriters)
+ started = true;
+ if (!done && i >= MIN_MEAS) {
+ done = true;
+ sp.sched_priority = 0;
+ sched_setscheduler_nocheck(current,
+ SCHED_NORMAL, &sp);
+ pr_alert("%s" PERF_FLAG
+ "rcu_perf_writer %ld has %d measurements\n",
+ perf_type, me, MIN_MEAS);
+ if (atomic_inc_return(&n_rcu_perf_writer_finished) >=
+ nrealwriters) {
+ schedule_timeout_interruptible(10);
+ rcu_ftrace_dump(DUMP_ALL);
+ PERFOUT_STRING("Test complete");
+ t_rcu_perf_writer_finished = t;
+ if (gp_exp) {
+ b_rcu_perf_writer_finished =
+ cur_ops->exp_completed() / 2;
+ } else {
+ b_rcu_perf_writer_finished =
+ cur_ops->completed();
+ }
+ if (shutdown) {
+ smp_mb(); /* Assign before wake. */
+ wake_up(&shutdown_wq);
+ }
+ }
+ }
+ if (done && !alldone &&
+ atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters)
+ alldone = true;
+ if (started && !alldone && i < MAX_MEAS - 1)
+ i++;
+ rcu_perf_wait_shutdown();
+ } while (!torture_must_stop());
+ rcu_perf_writer_state = RTWS_STOPPING;
+ writer_n_durations[me] = i_max;
+ torture_kthread_stopping("rcu_perf_writer");
+ return 0;
+}
+
+static inline void
+rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
+{
+ pr_alert("%s" PERF_FLAG
+ "--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n",
+ perf_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
+}
+
+static void
+rcu_perf_cleanup(void)
+{
+ int i;
+ int j;
+ int ngps = 0;
+ u64 *wdp;
+ u64 *wdpp;
+
+ if (torture_cleanup_begin())
+ return;
+
+ if (reader_tasks) {
+ for (i = 0; i < nrealreaders; i++)
+ torture_stop_kthread(rcu_perf_reader,
+ reader_tasks[i]);
+ kfree(reader_tasks);
+ }
+
+ if (writer_tasks) {
+ for (i = 0; i < nrealwriters; i++) {
+ torture_stop_kthread(rcu_perf_writer,
+ writer_tasks[i]);
+ if (!writer_n_durations)
+ continue;
+ j = writer_n_durations[i];
+ pr_alert("%s%s writer %d gps: %d\n",
+ perf_type, PERF_FLAG, i, j);
+ ngps += j;
+ }
+ pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n",
+ perf_type, PERF_FLAG,
+ t_rcu_perf_writer_started, t_rcu_perf_writer_finished,
+ t_rcu_perf_writer_finished -
+ t_rcu_perf_writer_started,
+ ngps,
+ b_rcu_perf_writer_finished -
+ b_rcu_perf_writer_started);
+ for (i = 0; i < nrealwriters; i++) {
+ if (!writer_durations)
+ break;
+ if (!writer_n_durations)
+ continue;
+ wdpp = writer_durations[i];
+ if (!wdpp)
+ continue;
+ for (j = 0; j <= writer_n_durations[i]; j++) {
+ wdp = &wdpp[j];
+ pr_alert("%s%s %4d writer-duration: %5d %llu\n",
+ perf_type, PERF_FLAG,
+ i, j, *wdp);
+ if (j % 100 == 0)
+ schedule_timeout_uninterruptible(1);
+ }
+ kfree(writer_durations[i]);
+ }
+ kfree(writer_tasks);
+ kfree(writer_durations);
+ kfree(writer_n_durations);
+ }
+
+ /* Do flavor-specific cleanup operations. */
+ if (cur_ops->cleanup != NULL)
+ cur_ops->cleanup();
+
+ torture_cleanup_end();
+}
+
+/*
+ * Return the number if non-negative. If -1, the number of CPUs.
+ * If less than -1, that much less than the number of CPUs, but
+ * at least one.
+ */
+static int compute_real(int n)
+{
+ int nr;
+
+ if (n >= 0) {
+ nr = n;
+ } else {
+ nr = num_online_cpus() + 1 + n;
+ if (nr <= 0)
+ nr = 1;
+ }
+ return nr;
+}
+
+/*
+ * RCU perf shutdown kthread. Just waits to be awakened, then shuts
+ * down system.
+ */
+static int
+rcu_perf_shutdown(void *arg)
+{
+ do {
+ wait_event(shutdown_wq,
+ atomic_read(&n_rcu_perf_writer_finished) >=
+ nrealwriters);
+ } while (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters);
+ smp_mb(); /* Wake before output. */
+ rcu_perf_cleanup();
+ kernel_power_off();
+ return -EINVAL;
+}
+
+static int __init
+rcu_perf_init(void)
+{
+ long i;
+ int firsterr = 0;
+ static struct rcu_perf_ops *perf_ops[] = {
+ &rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops,
+ RCUPERF_TASKS_OPS
+ };
+
+ if (!torture_init_begin(perf_type, verbose, &perf_runnable))
+ return -EBUSY;
+
+ /* Process args and tell the world that the perf'er is on the job. */
+ for (i = 0; i < ARRAY_SIZE(perf_ops); i++) {
+ cur_ops = perf_ops[i];
+ if (strcmp(perf_type, cur_ops->name) == 0)
+ break;
+ }
+ if (i == ARRAY_SIZE(perf_ops)) {
+ pr_alert("rcu-perf: invalid perf type: \"%s\"\n",
+ perf_type);
+ pr_alert("rcu-perf types:");
+ for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
+ pr_alert(" %s", perf_ops[i]->name);
+ pr_alert("\n");
+ firsterr = -EINVAL;
+ goto unwind;
+ }
+ if (cur_ops->init)
+ cur_ops->init();
+
+ nrealwriters = compute_real(nwriters);
+ nrealreaders = compute_real(nreaders);
+ atomic_set(&n_rcu_perf_reader_started, 0);
+ atomic_set(&n_rcu_perf_writer_started, 0);
+ atomic_set(&n_rcu_perf_writer_finished, 0);
+ rcu_perf_print_module_parms(cur_ops, "Start of test");
+
+ /* Start up the kthreads. */
+
+ if (shutdown) {
+ init_waitqueue_head(&shutdown_wq);
+ firsterr = torture_create_kthread(rcu_perf_shutdown, NULL,
+ shutdown_task);
+ if (firsterr)
+ goto unwind;
+ schedule_timeout_uninterruptible(1);
+ }
+ reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
+ GFP_KERNEL);
+ if (reader_tasks == NULL) {
+ VERBOSE_PERFOUT_ERRSTRING("out of memory");
+ firsterr = -ENOMEM;
+ goto unwind;
+ }
+ for (i = 0; i < nrealreaders; i++) {
+ firsterr = torture_create_kthread(rcu_perf_reader, (void *)i,
+ reader_tasks[i]);
+ if (firsterr)
+ goto unwind;
+ }
+ while (atomic_read(&n_rcu_perf_reader_started) < nrealreaders)
+ schedule_timeout_uninterruptible(1);
+ writer_tasks = kcalloc(nrealwriters, sizeof(reader_tasks[0]),
+ GFP_KERNEL);
+ writer_durations = kcalloc(nrealwriters, sizeof(*writer_durations),
+ GFP_KERNEL);
+ writer_n_durations =
+ kcalloc(nrealwriters, sizeof(*writer_n_durations),
+ GFP_KERNEL);
+ if (!writer_tasks || !writer_durations || !writer_n_durations) {
+ VERBOSE_PERFOUT_ERRSTRING("out of memory");
+ firsterr = -ENOMEM;
+ goto unwind;
+ }
+ for (i = 0; i < nrealwriters; i++) {
+ writer_durations[i] =
+ kcalloc(MAX_MEAS, sizeof(*writer_durations[i]),
+ GFP_KERNEL);
+ if (!writer_durations[i])
+ goto unwind;
+ firsterr = torture_create_kthread(rcu_perf_writer, (void *)i,
+ writer_tasks[i]);
+ if (firsterr)
+ goto unwind;
+ }
+ torture_init_end();
+ return 0;
+
+unwind:
+ torture_init_end();
+ rcu_perf_cleanup();
+ return firsterr;
+}
+
+module_init(rcu_perf_init);
+module_exit(rcu_perf_cleanup);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 250ea67c1615..084a28a732eb 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -130,8 +130,8 @@ static struct rcu_torture __rcu *rcu_torture_current;
static unsigned long rcu_torture_current_version;
static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
static DEFINE_SPINLOCK(rcu_torture_lock);
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) = { 0 };
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) = { 0 };
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count);
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch);
static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1];
static atomic_t n_rcu_torture_alloc;
static atomic_t n_rcu_torture_alloc_fail;
@@ -916,7 +916,7 @@ rcu_torture_fqs(void *arg)
static int
rcu_torture_writer(void *arg)
{
- bool can_expedite = !rcu_gp_is_expedited();
+ bool can_expedite = !rcu_gp_is_expedited() && !rcu_gp_is_normal();
int expediting = 0;
unsigned long gp_snap;
bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal;
@@ -932,7 +932,7 @@ rcu_torture_writer(void *arg)
VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
if (!can_expedite) {
pr_alert("%s" TORTURE_FLAG
- " Grace periods expedited from boot/sysfs for %s,\n",
+ " GP expediting controlled from boot/sysfs for %s,\n",
torture_type, cur_ops->name);
pr_alert("%s" TORTURE_FLAG
" Disabled dynamic grace-period expediting.\n",
@@ -1082,17 +1082,6 @@ rcu_torture_fakewriter(void *arg)
return 0;
}
-static void rcutorture_trace_dump(void)
-{
- static atomic_t beenhere = ATOMIC_INIT(0);
-
- if (atomic_read(&beenhere))
- return;
- if (atomic_xchg(&beenhere, 1) != 0)
- return;
- ftrace_dump(DUMP_ALL);
-}
-
/*
* RCU torture reader from timer handler. Dereferences rcu_torture_current,
* incrementing the corresponding element of the pipeline array. The
@@ -1142,7 +1131,7 @@ static void rcu_torture_timer(unsigned long unused)
if (pipe_count > 1) {
do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
started, completed);
- rcutorture_trace_dump();
+ rcu_ftrace_dump(DUMP_ALL);
}
__this_cpu_inc(rcu_torture_count[pipe_count]);
completed = completed - started;
@@ -1215,7 +1204,7 @@ rcu_torture_reader(void *arg)
if (pipe_count > 1) {
do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
ts, started, completed);
- rcutorture_trace_dump();
+ rcu_ftrace_dump(DUMP_ALL);
}
__this_cpu_inc(rcu_torture_count[pipe_count]);
completed = completed - started;
@@ -1333,7 +1322,7 @@ rcu_torture_stats_print(void)
rcu_torture_writer_state,
gpnum, completed, flags);
show_rcu_gp_kthreads();
- rcutorture_trace_dump();
+ rcu_ftrace_dump(DUMP_ALL);
}
rtcv_snap = rcu_torture_current_version;
}
@@ -1489,7 +1478,9 @@ static int rcu_torture_barrier_cbs(void *arg)
* The above smp_load_acquire() ensures barrier_phase load
* is ordered before the folloiwng ->call().
*/
+ local_irq_disable(); /* Just to test no-irq call_rcu(). */
cur_ops->call(&rcu, rcu_torture_barrier_cbf);
+ local_irq_enable();
if (atomic_dec_and_test(&barrier_cbs_count))
wake_up(&barrier_wq);
} while (!torture_must_stop());
@@ -1596,7 +1587,7 @@ static int rcutorture_cpu_notify(struct notifier_block *self,
{
long cpu = (long)hcpu;
- switch (action) {
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
case CPU_DOWN_FAILED:
(void)rcutorture_booster_init(cpu);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9a535a86e732..c7f1bc4f817c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -102,6 +102,8 @@ struct rcu_state sname##_state = { \
.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
.name = RCU_STATE_NAME(sname), \
.abbr = sabbr, \
+ .exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \
+ .exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \
}
RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
@@ -370,6 +372,21 @@ void rcu_all_qs(void)
rcu_momentary_dyntick_idle();
local_irq_restore(flags);
}
+ if (unlikely(raw_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))) {
+ /*
+ * Yes, we just checked a per-CPU variable with preemption
+ * enabled, so we might be migrated to some other CPU at
+ * this point. That is OK because in that case, the
+ * migration will supply the needed quiescent state.
+ * We might end up needlessly disabling preemption and
+ * invoking rcu_sched_qs() on the destination CPU, but
+ * the probability and cost are both quite low, so this
+ * should not be a problem in practice.
+ */
+ preempt_disable();
+ rcu_sched_qs();
+ preempt_enable();
+ }
this_cpu_inc(rcu_qs_ctr);
barrier(); /* Avoid RCU read-side critical sections leaking up. */
}
@@ -385,9 +402,11 @@ module_param(qlowmark, long, 0444);
static ulong jiffies_till_first_fqs = ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;
+static bool rcu_kick_kthreads;
module_param(jiffies_till_first_fqs, ulong, 0644);
module_param(jiffies_till_next_fqs, ulong, 0644);
+module_param(rcu_kick_kthreads, bool, 0644);
/*
* How long the grace period must be before we start recruiting
@@ -460,6 +479,28 @@ unsigned long rcu_batches_completed_bh(void)
EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
/*
+ * Return the number of RCU expedited batches completed thus far for
+ * debug & stats. Odd numbers mean that a batch is in progress, even
+ * numbers mean idle. The value returned will thus be roughly double
+ * the cumulative batches since boot.
+ */
+unsigned long rcu_exp_batches_completed(void)
+{
+ return rcu_state_p->expedited_sequence;
+}
+EXPORT_SYMBOL_GPL(rcu_exp_batches_completed);
+
+/*
+ * Return the number of RCU-sched expedited batches completed thus far
+ * for debug & stats. Similar to rcu_exp_batches_completed().
+ */
+unsigned long rcu_exp_batches_completed_sched(void)
+{
+ return rcu_sched_state.expedited_sequence;
+}
+EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched);
+
+/*
* Force a quiescent state.
*/
void rcu_force_quiescent_state(void)
@@ -637,7 +678,7 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
idle_task(smp_processor_id());
trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
- ftrace_dump(DUMP_ORIG);
+ rcu_ftrace_dump(DUMP_ORIG);
WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
current->pid, current->comm,
idle->pid, idle->comm); /* must be idle task! */
@@ -799,7 +840,7 @@ static void rcu_eqs_exit_common(long long oldval, int user)
trace_rcu_dyntick(TPS("Error on exit: not idle task"),
oldval, rdtp->dynticks_nesting);
- ftrace_dump(DUMP_ORIG);
+ rcu_ftrace_dump(DUMP_ORIG);
WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
current->pid, current->comm,
idle->pid, idle->comm); /* must be idle task! */
@@ -1224,8 +1265,10 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
rsp->gp_flags,
gp_state_getname(rsp->gp_state), rsp->gp_state,
rsp->gp_kthread ? rsp->gp_kthread->state : ~0);
- if (rsp->gp_kthread)
+ if (rsp->gp_kthread) {
sched_show_task(rsp->gp_kthread);
+ wake_up_process(rsp->gp_kthread);
+ }
}
}
@@ -1249,6 +1292,25 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
}
}
+/*
+ * If too much time has passed in the current grace period, and if
+ * so configured, go kick the relevant kthreads.
+ */
+static void rcu_stall_kick_kthreads(struct rcu_state *rsp)
+{
+ unsigned long j;
+
+ if (!rcu_kick_kthreads)
+ return;
+ j = READ_ONCE(rsp->jiffies_kick_kthreads);
+ if (time_after(jiffies, j) && rsp->gp_kthread) {
+ WARN_ONCE(1, "Kicking %s grace-period kthread\n", rsp->name);
+ rcu_ftrace_dump(DUMP_ALL);
+ wake_up_process(rsp->gp_kthread);
+ WRITE_ONCE(rsp->jiffies_kick_kthreads, j + HZ);
+ }
+}
+
static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
{
int cpu;
@@ -1260,6 +1322,11 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
struct rcu_node *rnp = rcu_get_root(rsp);
long totqlen = 0;
+ /* Kick and suppress, if so configured. */
+ rcu_stall_kick_kthreads(rsp);
+ if (rcu_cpu_stall_suppress)
+ return;
+
/* Only let one CPU complain about others per time interval. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -1333,6 +1400,11 @@ static void print_cpu_stall(struct rcu_state *rsp)
struct rcu_node *rnp = rcu_get_root(rsp);
long totqlen = 0;
+ /* Kick and suppress, if so configured. */
+ rcu_stall_kick_kthreads(rsp);
+ if (rcu_cpu_stall_suppress)
+ return;
+
/*
* OK, time to rat on ourselves...
* See Documentation/RCU/stallwarn.txt for info on how to debug
@@ -1377,8 +1449,10 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
unsigned long js;
struct rcu_node *rnp;
- if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
+ if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
+ !rcu_gp_in_progress(rsp))
return;
+ rcu_stall_kick_kthreads(rsp);
j = jiffies;
/*
@@ -2117,8 +2191,11 @@ static int __noreturn rcu_gp_kthread(void *arg)
}
ret = 0;
for (;;) {
- if (!ret)
+ if (!ret) {
rsp->jiffies_force_qs = jiffies + j;
+ WRITE_ONCE(rsp->jiffies_kick_kthreads,
+ jiffies + 3 * j);
+ }
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("fqswait"));
@@ -2144,6 +2221,15 @@ static int __noreturn rcu_gp_kthread(void *arg)
TPS("fqsend"));
cond_resched_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
+ ret = 0; /* Force full wait till next FQS. */
+ j = jiffies_till_next_fqs;
+ if (j > HZ) {
+ j = HZ;
+ jiffies_till_next_fqs = HZ;
+ } else if (j < 1) {
+ j = 1;
+ jiffies_till_next_fqs = 1;
+ }
} else {
/* Deal with stray signal. */
cond_resched_rcu_qs();
@@ -2152,14 +2238,12 @@ static int __noreturn rcu_gp_kthread(void *arg)
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("fqswaitsig"));
- }
- j = jiffies_till_next_fqs;
- if (j > HZ) {
- j = HZ;
- jiffies_till_next_fqs = HZ;
- } else if (j < 1) {
- j = 1;
- jiffies_till_next_fqs = 1;
+ ret = 1; /* Keep old FQS timing. */
+ j = jiffies;
+ if (time_after(jiffies, rsp->jiffies_force_qs))
+ j = 1;
+ else
+ j = rsp->jiffies_force_qs - j;
}
}
@@ -3376,8 +3460,12 @@ static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
}
static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
{
+ unsigned long s;
+
smp_mb(); /* Caller's modifications seen first by other CPUs. */
- return rcu_seq_snap(&rsp->expedited_sequence);
+ s = rcu_seq_snap(&rsp->expedited_sequence);
+ trace_rcu_exp_grace_period(rsp->name, s, TPS("snap"));
+ return s;
}
static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
{
@@ -3469,7 +3557,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
* for the current expedited grace period. Works only for preemptible
* RCU -- other RCU implementation use other means.
*
- * Caller must hold the root rcu_node's exp_funnel_mutex.
+ * Caller must hold the rcu_state's exp_mutex.
*/
static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
@@ -3485,8 +3573,8 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
* recursively up the tree. (Calm down, calm down, we do the recursion
* iteratively!)
*
- * Caller must hold the root rcu_node's exp_funnel_mutex and the
- * specified rcu_node structure's ->lock.
+ * Caller must hold the rcu_state's exp_mutex and the specified rcu_node
+ * structure's ->lock.
*/
static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
bool wake, unsigned long flags)
@@ -3523,7 +3611,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
* Report expedited quiescent state for specified node. This is a
* lock-acquisition wrapper function for __rcu_report_exp_rnp().
*
- * Caller must hold the root rcu_node's exp_funnel_mutex.
+ * Caller must hold the rcu_state's exp_mutex.
*/
static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
struct rcu_node *rnp, bool wake)
@@ -3536,8 +3624,8 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
/*
* Report expedited quiescent state for multiple CPUs, all covered by the
- * specified leaf rcu_node structure. Caller must hold the root
- * rcu_node's exp_funnel_mutex.
+ * specified leaf rcu_node structure. Caller must hold the rcu_state's
+ * exp_mutex.
*/
static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
unsigned long mask, bool wake)
@@ -3555,7 +3643,6 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
/*
* Report expedited quiescent state for specified rcu_data (CPU).
- * Caller must hold the root rcu_node's exp_funnel_mutex.
*/
static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
bool wake)
@@ -3564,15 +3651,11 @@ static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
}
/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
-static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp,
- struct rcu_data *rdp,
- atomic_long_t *stat, unsigned long s)
+static bool sync_exp_work_done(struct rcu_state *rsp, atomic_long_t *stat,
+ unsigned long s)
{
if (rcu_exp_gp_seq_done(rsp, s)) {
- if (rnp)
- mutex_unlock(&rnp->exp_funnel_mutex);
- else if (rdp)
- mutex_unlock(&rdp->exp_funnel_mutex);
+ trace_rcu_exp_grace_period(rsp->name, s, TPS("done"));
/* Ensure test happens before caller kfree(). */
smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(stat);
@@ -3582,59 +3665,65 @@ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp,
}
/*
- * Funnel-lock acquisition for expedited grace periods. Returns a
- * pointer to the root rcu_node structure, or NULL if some other
- * task did the expedited grace period for us.
+ * Funnel-lock acquisition for expedited grace periods. Returns true
+ * if some other task completed an expedited grace period that this task
+ * can piggy-back on, and with no mutex held. Otherwise, returns false
+ * with the mutex held, indicating that the caller must actually do the
+ * expedited grace period.
*/
-static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
+static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
{
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
- struct rcu_node *rnp0;
- struct rcu_node *rnp1 = NULL;
+ struct rcu_node *rnp = rdp->mynode;
+ struct rcu_node *rnp_root = rcu_get_root(rsp);
+
+ /* Low-contention fastpath. */
+ if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s) &&
+ (rnp == rnp_root ||
+ ULONG_CMP_LT(READ_ONCE(rnp_root->exp_seq_rq), s)) &&
+ !mutex_is_locked(&rsp->exp_mutex) &&
+ mutex_trylock(&rsp->exp_mutex))
+ goto fastpath;
/*
- * First try directly acquiring the root lock in order to reduce
- * latency in the common case where expedited grace periods are
- * rare. We check mutex_is_locked() to avoid pathological levels of
- * memory contention on ->exp_funnel_mutex in the heavy-load case.
+ * Each pass through the following loop works its way up
+ * the rcu_node tree, returning if others have done the work or
+ * otherwise falls through to acquire rsp->exp_mutex. The mapping
+ * from CPU to rcu_node structure can be inexact, as it is just
+ * promoting locality and is not strictly needed for correctness.
*/
- rnp0 = rcu_get_root(rsp);
- if (!mutex_is_locked(&rnp0->exp_funnel_mutex)) {
- if (mutex_trylock(&rnp0->exp_funnel_mutex)) {
- if (sync_exp_work_done(rsp, rnp0, NULL,
- &rdp->expedited_workdone0, s))
- return NULL;
- return rnp0;
+ for (; rnp != NULL; rnp = rnp->parent) {
+ if (sync_exp_work_done(rsp, &rdp->exp_workdone1, s))
+ return true;
+
+ /* Work not done, either wait here or go up. */
+ spin_lock(&rnp->exp_lock);
+ if (ULONG_CMP_GE(rnp->exp_seq_rq, s)) {
+
+ /* Someone else doing GP, so wait for them. */
+ spin_unlock(&rnp->exp_lock);
+ trace_rcu_exp_funnel_lock(rsp->name, rnp->level,
+ rnp->grplo, rnp->grphi,
+ TPS("wait"));
+ wait_event(rnp->exp_wq[(s >> 1) & 0x3],
+ sync_exp_work_done(rsp,
+ &rdp->exp_workdone2, s));
+ return true;
}
+ rnp->exp_seq_rq = s; /* Followers can wait on us. */
+ spin_unlock(&rnp->exp_lock);
+ trace_rcu_exp_funnel_lock(rsp->name, rnp->level, rnp->grplo,
+ rnp->grphi, TPS("nxtlvl"));
}
-
- /*
- * Each pass through the following loop works its way
- * up the rcu_node tree, returning if others have done the
- * work or otherwise falls through holding the root rnp's
- * ->exp_funnel_mutex. The mapping from CPU to rcu_node structure
- * can be inexact, as it is just promoting locality and is not
- * strictly needed for correctness.
- */
- if (sync_exp_work_done(rsp, NULL, NULL, &rdp->expedited_workdone1, s))
- return NULL;
- mutex_lock(&rdp->exp_funnel_mutex);
- rnp0 = rdp->mynode;
- for (; rnp0 != NULL; rnp0 = rnp0->parent) {
- if (sync_exp_work_done(rsp, rnp1, rdp,
- &rdp->expedited_workdone2, s))
- return NULL;
- mutex_lock(&rnp0->exp_funnel_mutex);
- if (rnp1)
- mutex_unlock(&rnp1->exp_funnel_mutex);
- else
- mutex_unlock(&rdp->exp_funnel_mutex);
- rnp1 = rnp0;
+ mutex_lock(&rsp->exp_mutex);
+fastpath:
+ if (sync_exp_work_done(rsp, &rdp->exp_workdone3, s)) {
+ mutex_unlock(&rsp->exp_mutex);
+ return true;
}
- if (sync_exp_work_done(rsp, rnp1, rdp,
- &rdp->expedited_workdone3, s))
- return NULL;
- return rnp1;
+ rcu_exp_gp_seq_start(rsp);
+ trace_rcu_exp_grace_period(rsp->name, s, TPS("start"));
+ return false;
}
/* Invoked on each online non-idle CPU for expedited quiescent state. */
@@ -3649,6 +3738,11 @@ static void sync_sched_exp_handler(void *data)
if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
return;
+ if (rcu_is_cpu_rrupt_from_idle()) {
+ rcu_report_exp_rdp(&rcu_sched_state,
+ this_cpu_ptr(&rcu_sched_data), true);
+ return;
+ }
__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
resched_cpu(smp_processor_id());
}
@@ -3773,7 +3867,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
rsp->name);
ndetected = 0;
rcu_for_each_leaf_node(rsp, rnp) {
- ndetected = rcu_print_task_exp_stall(rnp);
+ ndetected += rcu_print_task_exp_stall(rnp);
mask = 1;
for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
struct rcu_data *rdp;
@@ -3783,7 +3877,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
ndetected++;
rdp = per_cpu_ptr(rsp->rda, cpu);
pr_cont(" %d-%c%c%c", cpu,
- "O."[cpu_online(cpu)],
+ "O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rnp->expmaskinit)],
"N."[!!(rdp->grpmask & rnp->expmaskinitnext)]);
}
@@ -3792,7 +3886,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
jiffies - jiffies_start, rsp->expedited_sequence,
rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]);
- if (!ndetected) {
+ if (ndetected) {
pr_err("blocking rcu_node structures:");
rcu_for_each_node_breadth_first(rsp, rnp) {
if (rnp == rnp_root)
@@ -3818,6 +3912,41 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
}
}
+/*
+ * Wait for the current expedited grace period to complete, and then
+ * wake up everyone who piggybacked on the just-completed expedited
+ * grace period. Also update all the ->exp_seq_rq counters as needed
+ * in order to avoid counter-wrap problems.
+ */
+static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
+{
+ struct rcu_node *rnp;
+
+ synchronize_sched_expedited_wait(rsp);
+ rcu_exp_gp_seq_end(rsp);
+ trace_rcu_exp_grace_period(rsp->name, s, TPS("end"));
+
+ /*
+ * Switch over to wakeup mode, allowing the next GP, but -only- the
+ * next GP, to proceed.
+ */
+ mutex_lock(&rsp->exp_wake_mutex);
+ mutex_unlock(&rsp->exp_mutex);
+
+ rcu_for_each_node_breadth_first(rsp, rnp) {
+ if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) {
+ spin_lock(&rnp->exp_lock);
+ /* Recheck, avoid hang in case someone just arrived. */
+ if (ULONG_CMP_LT(rnp->exp_seq_rq, s))
+ rnp->exp_seq_rq = s;
+ spin_unlock(&rnp->exp_lock);
+ }
+ wake_up_all(&rnp->exp_wq[(rsp->expedited_sequence >> 1) & 0x3]);
+ }
+ trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake"));
+ mutex_unlock(&rsp->exp_wake_mutex);
+}
+
/**
* synchronize_sched_expedited - Brute-force RCU-sched grace period
*
@@ -3837,7 +3966,6 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
void synchronize_sched_expedited(void)
{
unsigned long s;
- struct rcu_node *rnp;
struct rcu_state *rsp = &rcu_sched_state;
/* If only one CPU, this is automatically a grace period. */
@@ -3852,17 +3980,14 @@ void synchronize_sched_expedited(void)
/* Take a snapshot of the sequence number. */
s = rcu_exp_gp_seq_snap(rsp);
-
- rnp = exp_funnel_lock(rsp, s);
- if (rnp == NULL)
+ if (exp_funnel_lock(rsp, s))
return; /* Someone else did our work for us. */
- rcu_exp_gp_seq_start(rsp);
+ /* Initialize the rcu_node tree in preparation for the wait. */
sync_rcu_exp_select_cpus(rsp, sync_sched_exp_handler);
- synchronize_sched_expedited_wait(rsp);
- rcu_exp_gp_seq_end(rsp);
- mutex_unlock(&rnp->exp_funnel_mutex);
+ /* Wait and clean up, including waking everyone. */
+ rcu_exp_wait_wake(rsp, s);
}
EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
@@ -4162,7 +4287,6 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
rdp->cpu = cpu;
rdp->rsp = rsp;
- mutex_init(&rdp->exp_funnel_mutex);
rcu_boot_init_nocb_percpu_data(rdp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
@@ -4420,10 +4544,8 @@ static void __init rcu_init_one(struct rcu_state *rsp)
{
static const char * const buf[] = RCU_NODE_NAME_INIT;
static const char * const fqs[] = RCU_FQS_NAME_INIT;
- static const char * const exp[] = RCU_EXP_NAME_INIT;
static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
- static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS];
static u8 fl_mask = 0x1;
int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */
@@ -4482,9 +4604,11 @@ static void __init rcu_init_one(struct rcu_state *rsp)
rnp->level = i;
INIT_LIST_HEAD(&rnp->blkd_tasks);
rcu_init_one_nocb(rnp);
- mutex_init(&rnp->exp_funnel_mutex);
- lockdep_set_class_and_name(&rnp->exp_funnel_mutex,
- &rcu_exp_class[i], exp[i]);
+ init_waitqueue_head(&rnp->exp_wq[0]);
+ init_waitqueue_head(&rnp->exp_wq[1]);
+ init_waitqueue_head(&rnp->exp_wq[2]);
+ init_waitqueue_head(&rnp->exp_wq[3]);
+ spin_lock_init(&rnp->exp_lock);
}
}
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index df668c0f9e64..e3959f5e6ddf 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -70,7 +70,6 @@
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 }
# define RCU_NODE_NAME_INIT { "rcu_node_0" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" }
-# define RCU_EXP_NAME_INIT { "rcu_node_exp_0" }
#elif NR_CPUS <= RCU_FANOUT_2
# define RCU_NUM_LVLS 2
# define NUM_RCU_LVL_0 1
@@ -79,7 +78,6 @@
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" }
-# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1" }
#elif NR_CPUS <= RCU_FANOUT_3
# define RCU_NUM_LVLS 3
# define NUM_RCU_LVL_0 1
@@ -89,7 +87,6 @@
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
-# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" }
#elif NR_CPUS <= RCU_FANOUT_4
# define RCU_NUM_LVLS 4
# define NUM_RCU_LVL_0 1
@@ -100,7 +97,6 @@
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
-# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" }
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
@@ -252,7 +248,9 @@ struct rcu_node {
/* Counts of upcoming no-CB GP requests. */
raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
- struct mutex exp_funnel_mutex ____cacheline_internodealigned_in_smp;
+ spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
+ unsigned long exp_seq_rq;
+ wait_queue_head_t exp_wq[4];
} ____cacheline_internodealigned_in_smp;
/*
@@ -387,11 +385,9 @@ struct rcu_data {
#ifdef CONFIG_RCU_FAST_NO_HZ
struct rcu_head oom_head;
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
- struct mutex exp_funnel_mutex;
- atomic_long_t expedited_workdone0; /* # done by others #0. */
- atomic_long_t expedited_workdone1; /* # done by others #1. */
- atomic_long_t expedited_workdone2; /* # done by others #2. */
- atomic_long_t expedited_workdone3; /* # done by others #3. */
+ atomic_long_t exp_workdone1; /* # done by others #1. */
+ atomic_long_t exp_workdone2; /* # done by others #2. */
+ atomic_long_t exp_workdone3; /* # done by others #3. */
/* 7) Callback offloading. */
#ifdef CONFIG_RCU_NOCB_CPU
@@ -505,6 +501,8 @@ struct rcu_state {
/* _rcu_barrier(). */
/* End of fields guarded by barrier_mutex. */
+ struct mutex exp_mutex; /* Serialize expedited GP. */
+ struct mutex exp_wake_mutex; /* Serialize wakeup. */
unsigned long expedited_sequence; /* Take a ticket. */
atomic_long_t expedited_normal; /* # fallbacks to normal. */
atomic_t expedited_need_qs; /* # CPUs left to check in. */
@@ -513,6 +511,8 @@ struct rcu_state {
unsigned long jiffies_force_qs; /* Time at which to invoke */
/* force_quiescent_state(). */
+ unsigned long jiffies_kick_kthreads; /* Time at which to kick */
+ /* kthreads, if configured. */
unsigned long n_force_qs; /* Number of calls to */
/* force_quiescent_state(). */
unsigned long n_force_qs_lh; /* ~Number of calls leaving */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index efdf7b61ce12..ff1cd4e1188d 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -722,18 +722,22 @@ static void sync_rcu_exp_handler(void *info)
* synchronize_rcu_expedited - Brute-force RCU grace period
*
* Wait for an RCU-preempt grace period, but expedite it. The basic
- * idea is to invoke synchronize_sched_expedited() to push all the tasks to
- * the ->blkd_tasks lists and wait for this list to drain. This consumes
- * significant time on all CPUs and is unfriendly to real-time workloads,
- * so is thus not recommended for any sort of common-case code.
- * In fact, if you are using synchronize_rcu_expedited() in a loop,
- * please restructure your code to batch your updates, and then Use a
- * single synchronize_rcu() instead.
+ * idea is to IPI all non-idle non-nohz online CPUs. The IPI handler
+ * checks whether the CPU is in an RCU-preempt critical section, and
+ * if so, it sets a flag that causes the outermost rcu_read_unlock()
+ * to report the quiescent state. On the other hand, if the CPU is
+ * not in an RCU read-side critical section, the IPI handler reports
+ * the quiescent state immediately.
+ *
+ * Although this is a greate improvement over previous expedited
+ * implementations, it is still unfriendly to real-time workloads, so is
+ * thus not recommended for any sort of common-case code. In fact, if
+ * you are using synchronize_rcu_expedited() in a loop, please restructure
+ * your code to batch your updates, and then Use a single synchronize_rcu()
+ * instead.
*/
void synchronize_rcu_expedited(void)
{
- struct rcu_node *rnp;
- struct rcu_node *rnp_unlock;
struct rcu_state *rsp = rcu_state_p;
unsigned long s;
@@ -744,23 +748,14 @@ void synchronize_rcu_expedited(void)
}
s = rcu_exp_gp_seq_snap(rsp);
-
- rnp_unlock = exp_funnel_lock(rsp, s);
- if (rnp_unlock == NULL)
+ if (exp_funnel_lock(rsp, s))
return; /* Someone else did our work for us. */
- rcu_exp_gp_seq_start(rsp);
-
/* Initialize the rcu_node tree in preparation for the wait. */
sync_rcu_exp_select_cpus(rsp, sync_rcu_exp_handler);
- /* Wait for snapshotted ->blkd_tasks lists to drain. */
- rnp = rcu_get_root(rsp);
- synchronize_sched_expedited_wait(rsp);
-
- /* Clean up and exit. */
- rcu_exp_gp_seq_end(rsp);
- mutex_unlock(&rnp_unlock->exp_funnel_mutex);
+ /* Wait for ->blkd_tasks lists to drain, then wake everyone up. */
+ rcu_exp_wait_wake(rsp, s);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 1088e64f01ad..86782f9a4604 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -185,17 +185,16 @@ static int show_rcuexp(struct seq_file *m, void *v)
int cpu;
struct rcu_state *rsp = (struct rcu_state *)m->private;
struct rcu_data *rdp;
- unsigned long s0 = 0, s1 = 0, s2 = 0, s3 = 0;
+ unsigned long s1 = 0, s2 = 0, s3 = 0;
for_each_possible_cpu(cpu) {
rdp = per_cpu_ptr(rsp->rda, cpu);
- s0 += atomic_long_read(&rdp->expedited_workdone0);
- s1 += atomic_long_read(&rdp->expedited_workdone1);
- s2 += atomic_long_read(&rdp->expedited_workdone2);
- s3 += atomic_long_read(&rdp->expedited_workdone3);
+ s1 += atomic_long_read(&rdp->exp_workdone1);
+ s2 += atomic_long_read(&rdp->exp_workdone2);
+ s3 += atomic_long_read(&rdp->exp_workdone3);
}
- seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n",
- rsp->expedited_sequence, s0, s1, s2, s3,
+ seq_printf(m, "s=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n",
+ rsp->expedited_sequence, s1, s2, s3,
atomic_long_read(&rsp->expedited_normal),
atomic_read(&rsp->expedited_need_qs),
rsp->expedited_sequence / 2);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index ca828b41c938..3ccdc8eebc5a 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -67,7 +67,7 @@ static int rcu_normal_after_boot;
module_param(rcu_normal_after_boot, int, 0);
#endif /* #ifndef CONFIG_TINY_RCU */
-#if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT)
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
* rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
*
@@ -111,7 +111,7 @@ int rcu_read_lock_sched_held(void)
return 0;
if (debug_locks)
lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
- return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
+ return lockdep_opinion || !preemptible();
}
EXPORT_SYMBOL(rcu_read_lock_sched_held);
#endif
diff --git a/kernel/signal.c b/kernel/signal.c
index aa9bf00749c1..ab122a2cee41 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3099,12 +3099,14 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
oss.ss_sp = (void __user *) current->sas_ss_sp;
oss.ss_size = current->sas_ss_size;
- oss.ss_flags = sas_ss_flags(sp);
+ oss.ss_flags = sas_ss_flags(sp) |
+ (current->sas_ss_flags & SS_FLAG_BITS);
if (uss) {
void __user *ss_sp;
size_t ss_size;
- int ss_flags;
+ unsigned ss_flags;
+ int ss_mode;
error = -EFAULT;
if (!access_ok(VERIFY_READ, uss, sizeof(*uss)))
@@ -3119,18 +3121,13 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
if (on_sig_stack(sp))
goto out;
+ ss_mode = ss_flags & ~SS_FLAG_BITS;
error = -EINVAL;
- /*
- * Note - this code used to test ss_flags incorrectly:
- * old code may have been written using ss_flags==0
- * to mean ss_flags==SS_ONSTACK (as this was the only
- * way that worked) - this fix preserves that older
- * mechanism.
- */
- if (ss_flags != SS_DISABLE && ss_flags != SS_ONSTACK && ss_flags != 0)
+ if (ss_mode != SS_DISABLE && ss_mode != SS_ONSTACK &&
+ ss_mode != 0)
goto out;
- if (ss_flags == SS_DISABLE) {
+ if (ss_mode == SS_DISABLE) {
ss_size = 0;
ss_sp = NULL;
} else {
@@ -3141,6 +3138,7 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
current->sas_ss_sp = (unsigned long) ss_sp;
current->sas_ss_size = ss_size;
+ current->sas_ss_flags = ss_flags;
}
error = 0;
@@ -3171,9 +3169,14 @@ int restore_altstack(const stack_t __user *uss)
int __save_altstack(stack_t __user *uss, unsigned long sp)
{
struct task_struct *t = current;
- return __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) |
- __put_user(sas_ss_flags(sp), &uss->ss_flags) |
+ int err = __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) |
+ __put_user(t->sas_ss_flags, &uss->ss_flags) |
__put_user(t->sas_ss_size, &uss->ss_size);
+ if (err)
+ return err;
+ if (t->sas_ss_flags & SS_AUTODISARM)
+ sas_ss_reset(t);
+ return 0;
}
#ifdef CONFIG_COMPAT
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 725587f10667..c8b318663525 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -130,6 +130,9 @@ static int one_thousand = 1000;
#ifdef CONFIG_PRINTK
static int ten_thousand = 10000;
#endif
+#ifdef CONFIG_PERF_EVENTS
+static int six_hundred_forty_kb = 640 * 1024;
+#endif
/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
@@ -1144,6 +1147,15 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &one_hundred,
},
+ {
+ .procname = "perf_event_max_stack",
+ .data = NULL, /* filled in by handler */
+ .maxlen = sizeof(sysctl_perf_event_max_stack),
+ .mode = 0644,
+ .proc_handler = perf_event_max_stack_handler,
+ .extra1 = &zero,
+ .extra2 = &six_hundred_forty_kb,
+ },
#endif
#ifdef CONFIG_KMEMCHECK
{
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 31872bc53bc4..536ada80f6dd 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -262,7 +262,7 @@ static void tick_nohz_dep_set_all(atomic_t *dep,
{
int prev;
- prev = atomic_fetch_or(dep, BIT(bit));
+ prev = atomic_fetch_or(BIT(bit), dep);
if (!prev)
tick_nohz_full_kick_all();
}
@@ -292,7 +292,7 @@ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
ts = per_cpu_ptr(&tick_cpu_sched, cpu);
- prev = atomic_fetch_or(&ts->tick_dep_mask, BIT(bit));
+ prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask);
if (!prev) {
preempt_disable();
/* Perf needs local kick that is NMI safe */
diff --git a/kernel/torture.c b/kernel/torture.c
index 44aa462d033f..fa0bdeee17ac 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -451,6 +451,7 @@ static int torture_shutdown(void *arg)
torture_shutdown_hook();
else
VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping.");
+ ftrace_dump(DUMP_ALL);
kernel_power_off(); /* Shut down the system. */
return 0;
}
@@ -602,8 +603,9 @@ bool torture_init_begin(char *ttype, bool v, int *runnable)
{
mutex_lock(&fullstop_mutex);
if (torture_type != NULL) {
- pr_alert("torture_init_begin: refusing %s init: %s running",
+ pr_alert("torture_init_begin: Refusing %s init: %s running.\n",
ttype, torture_type);
+ pr_alert("torture_init_begin: One torture test at a time!\n");
mutex_unlock(&fullstop_mutex);
return false;
}
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 00df25fd86ef..e11108f1d197 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -47,6 +47,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event,
if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (!is_sampling_event(p_event))
+ return 0;
+
/*
* We don't allow user space callchains for function trace
* event, due to issues with page faults while tracing page
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 3bfdff06eea7..5f5068e94003 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4554,6 +4554,17 @@ static void rebind_workers(struct worker_pool *pool)
pool->attrs->cpumask) < 0);
spin_lock_irq(&pool->lock);
+
+ /*
+ * XXX: CPU hotplug notifiers are weird and can call DOWN_FAILED
+ * w/o preceding DOWN_PREPARE. Work around it. CPU hotplug is
+ * being reworked and this can go away in time.
+ */
+ if (!(pool->flags & POOL_DISASSOCIATED)) {
+ spin_unlock_irq(&pool->lock);
+ return;
+ }
+
pool->flags &= ~POOL_DISASSOCIATED;
for_each_pool_worker(worker, pool) {
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-11 08:49:03 +0000