summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/debug/kdb/kdb_main.c21
-rw-r--r--kernel/exit.c9
-rw-r--r--kernel/fork.c1
-rw-r--r--kernel/hw_breakpoint.c3
-rw-r--r--kernel/irq/proc.c2
-rw-r--r--kernel/irq_work.c4
-rw-r--r--kernel/kthread.c11
-rw-r--r--kernel/latencytop.c17
-rw-r--r--kernel/module.c12
-rw-r--r--kernel/perf_event.c172
-rw-r--r--kernel/pm_qos_params.c4
-rw-r--r--kernel/posix-cpu-timers.c12
-rw-r--r--kernel/power/Kconfig4
-rw-r--r--kernel/power/hibernate.c22
-rw-r--r--kernel/power/suspend.c5
-rw-r--r--kernel/power/swap.c55
-rw-r--r--kernel/power/user.c4
-rw-r--r--kernel/printk.c25
-rw-r--r--kernel/range.c2
-rw-r--r--kernel/rcutiny.c105
-rw-r--r--kernel/rcutiny_plugin.h433
-rw-r--r--kernel/rcutorture.c270
-rw-r--r--kernel/rcutree.c156
-rw-r--r--kernel/rcutree.h61
-rw-r--r--kernel/rcutree_plugin.h135
-rw-r--r--kernel/rcutree_trace.c12
-rw-r--r--kernel/resource.c104
-rw-r--r--kernel/sched.c393
-rw-r--r--kernel/sched_fair.c48
-rw-r--r--kernel/sched_stoptask.c4
-rw-r--r--kernel/srcu.c8
-rw-r--r--kernel/sysctl.c9
-rw-r--r--kernel/taskstats.c57
-rw-r--r--kernel/timer.c8
-rw-r--r--kernel/trace/Kconfig2
-rw-r--r--kernel/trace/blktrace.c4
-rw-r--r--kernel/trace/ring_buffer.c9
-rw-r--r--kernel/trace/trace.c30
-rw-r--r--kernel/user.c1
-rw-r--r--kernel/watchdog.c3
-rw-r--r--kernel/workqueue.c7
41 files changed, 1699 insertions, 545 deletions
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 37755d621924..a6e729766821 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -82,7 +82,7 @@ static kdbtab_t kdb_base_commands[50];
#define for_each_kdbcmd(cmd, num) \
for ((cmd) = kdb_base_commands, (num) = 0; \
num < kdb_max_commands; \
- num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++, num++)
+ num++, num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++)
typedef struct _kdbmsg {
int km_diag; /* kdb diagnostic */
@@ -646,7 +646,7 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
}
if (!s->usable)
return KDB_NOTIMP;
- s->command = kmalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
+ s->command = kzalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
if (!s->command) {
kdb_printf("Could not allocate new kdb_defcmd table for %s\n",
cmdstr);
@@ -2361,7 +2361,7 @@ static int kdb_pid(int argc, const char **argv)
*/
static int kdb_ll(int argc, const char **argv)
{
- int diag;
+ int diag = 0;
unsigned long addr;
long offset = 0;
unsigned long va;
@@ -2400,20 +2400,21 @@ static int kdb_ll(int argc, const char **argv)
char buf[80];
if (KDB_FLAG(CMD_INTERRUPT))
- return 0;
+ goto out;
sprintf(buf, "%s " kdb_machreg_fmt "\n", command, va);
diag = kdb_parse(buf);
if (diag)
- return diag;
+ goto out;
addr = va + linkoffset;
if (kdb_getword(&va, addr, sizeof(va)))
- return 0;
+ goto out;
}
- kfree(command);
- return 0;
+out:
+ kfree(command);
+ return diag;
}
static int kdb_kgdb(int argc, const char **argv)
@@ -2739,13 +2740,13 @@ int kdb_register_repeat(char *cmd,
}
if (kdb_commands) {
memcpy(new, kdb_commands,
- kdb_max_commands * sizeof(*new));
+ (kdb_max_commands - KDB_BASE_CMD_MAX) * sizeof(*new));
kfree(kdb_commands);
}
memset(new + kdb_max_commands, 0,
kdb_command_extend * sizeof(*new));
kdb_commands = new;
- kp = kdb_commands + kdb_max_commands;
+ kp = kdb_commands + kdb_max_commands - KDB_BASE_CMD_MAX;
kdb_max_commands += kdb_command_extend;
}
diff --git a/kernel/exit.c b/kernel/exit.c
index 21aa7b3001fb..676149a4ac5f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -914,6 +914,15 @@ NORET_TYPE void do_exit(long code)
if (unlikely(!tsk->pid))
panic("Attempted to kill the idle task!");
+ /*
+ * If do_exit is called because this processes oopsed, it's possible
+ * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
+ * continuing. Amongst other possible reasons, this is to prevent
+ * mm_release()->clear_child_tid() from writing to a user-controlled
+ * kernel address.
+ */
+ set_fs(USER_DS);
+
tracehook_report_exit(&code);
validate_creds_for_do_exit(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 3b159c5991b7..5447dc7defa9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -273,6 +273,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
+ clear_tsk_need_resched(tsk);
stackend = end_of_stack(tsk);
*stackend = STACK_END_MAGIC; /* for overflow detection */
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 2c9120f0afca..e5325825aeb6 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -620,7 +620,7 @@ static struct pmu perf_breakpoint = {
.read = hw_breakpoint_pmu_read,
};
-static int __init init_hw_breakpoint(void)
+int __init init_hw_breakpoint(void)
{
unsigned int **task_bp_pinned;
int cpu, err_cpu;
@@ -655,6 +655,5 @@ static int __init init_hw_breakpoint(void)
return -ENOMEM;
}
-core_initcall(init_hw_breakpoint);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 01b1d3a88983..6c8a2a9f8a7b 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -214,7 +214,7 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v)
static int irq_spurious_proc_open(struct inode *inode, struct file *file)
{
- return single_open(file, irq_spurious_proc_show, NULL);
+ return single_open(file, irq_spurious_proc_show, PDE(inode)->data);
}
static const struct file_operations irq_spurious_proc_fops = {
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index f16763ff8481..90f881904bb1 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -145,7 +145,9 @@ void irq_work_run(void)
* Clear the BUSY bit and return to the free state if
* no-one else claimed it meanwhile.
*/
- cmpxchg(&entry->next, next_flags(NULL, IRQ_WORK_BUSY), NULL);
+ (void)cmpxchg(&entry->next,
+ next_flags(NULL, IRQ_WORK_BUSY),
+ NULL);
}
}
EXPORT_SYMBOL_GPL(irq_work_run);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 2dc3786349d1..ca61bbdd44b2 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -265,6 +265,17 @@ int kthreadd(void *unused)
return 0;
}
+void __init_kthread_worker(struct kthread_worker *worker,
+ const char *name,
+ struct lock_class_key *key)
+{
+ spin_lock_init(&worker->lock);
+ lockdep_set_class_and_name(&worker->lock, key, name);
+ INIT_LIST_HEAD(&worker->work_list);
+ worker->task = NULL;
+}
+EXPORT_SYMBOL_GPL(__init_kthread_worker);
+
/**
* kthread_worker_fn - kthread function to process kthread_worker
* @worker_ptr: pointer to initialized kthread_worker
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 877fb306d415..17110a4a4fc2 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -194,14 +194,7 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
account_global_scheduler_latency(tsk, &lat);
- /*
- * short term hack; if we're > 32 we stop; future we recycle:
- */
- tsk->latency_record_count++;
- if (tsk->latency_record_count >= LT_SAVECOUNT)
- goto out_unlock;
-
- for (i = 0; i < LT_SAVECOUNT; i++) {
+ for (i = 0; i < tsk->latency_record_count; i++) {
struct latency_record *mylat;
int same = 1;
@@ -227,8 +220,14 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
}
}
+ /*
+ * short term hack; if we're > 32 we stop; future we recycle:
+ */
+ if (tsk->latency_record_count >= LT_SAVECOUNT)
+ goto out_unlock;
+
/* Allocated a new one: */
- i = tsk->latency_record_count;
+ i = tsk->latency_record_count++;
memcpy(&tsk->latency_record[i], &lat, sizeof(struct latency_record));
out_unlock:
diff --git a/kernel/module.c b/kernel/module.c
index 437a74a7524a..d190664f25ff 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2326,6 +2326,18 @@ static void find_module_sections(struct module *mod, struct load_info *info)
kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) *
mod->num_trace_events, GFP_KERNEL);
#endif
+#ifdef CONFIG_TRACING
+ mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt",
+ sizeof(*mod->trace_bprintk_fmt_start),
+ &mod->num_trace_bprintk_fmt);
+ /*
+ * This section contains pointers to allocated objects in the trace
+ * code and not scanning it leads to false positives.
+ */
+ kmemleak_scan_area(mod->trace_bprintk_fmt_start,
+ sizeof(*mod->trace_bprintk_fmt_start) *
+ mod->num_trace_bprintk_fmt, GFP_KERNEL);
+#endif
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
/* sechdrs[0].sh_size is always zero */
mod->ftrace_callsites = section_objs(info, "__mcount_loc",
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 517d827f4982..2870feee81dd 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -31,6 +31,7 @@
#include <linux/kernel_stat.h>
#include <linux/perf_event.h>
#include <linux/ftrace_event.h>
+#include <linux/hw_breakpoint.h>
#include <asm/irq_regs.h>
@@ -674,6 +675,8 @@ event_sched_in(struct perf_event *event,
event->tstamp_running += ctx->time - event->tstamp_stopped;
+ event->shadow_ctx_time = ctx->time - ctx->timestamp;
+
if (!is_software_event(event))
cpuctx->active_oncpu++;
ctx->nr_active++;
@@ -1284,8 +1287,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
{
int ctxn;
- perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
-
for_each_task_context_nr(ctxn)
perf_event_context_sched_out(task, ctxn, next);
}
@@ -1619,8 +1620,12 @@ static void rotate_ctx(struct perf_event_context *ctx)
{
raw_spin_lock(&ctx->lock);
- /* Rotate the first entry last of non-pinned groups */
- list_rotate_left(&ctx->flexible_groups);
+ /*
+ * Rotate the first entry last of non-pinned groups. Rotation might be
+ * disabled by the inheritance code.
+ */
+ if (!ctx->rotate_disable)
+ list_rotate_left(&ctx->flexible_groups);
raw_spin_unlock(&ctx->lock);
}
@@ -2232,11 +2237,6 @@ int perf_event_release_kernel(struct perf_event *event)
raw_spin_unlock_irq(&ctx->lock);
mutex_unlock(&ctx->mutex);
- mutex_lock(&event->owner->perf_event_mutex);
- list_del_init(&event->owner_entry);
- mutex_unlock(&event->owner->perf_event_mutex);
- put_task_struct(event->owner);
-
free_event(event);
return 0;
@@ -2249,9 +2249,43 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
static int perf_release(struct inode *inode, struct file *file)
{
struct perf_event *event = file->private_data;
+ struct task_struct *owner;
file->private_data = NULL;
+ rcu_read_lock();
+ owner = ACCESS_ONCE(event->owner);
+ /*
+ * Matches the smp_wmb() in perf_event_exit_task(). If we observe
+ * !owner it means the list deletion is complete and we can indeed
+ * free this event, otherwise we need to serialize on
+ * owner->perf_event_mutex.
+ */
+ smp_read_barrier_depends();
+ if (owner) {
+ /*
+ * Since delayed_put_task_struct() also drops the last
+ * task reference we can safely take a new reference
+ * while holding the rcu_read_lock().
+ */
+ get_task_struct(owner);
+ }
+ rcu_read_unlock();
+
+ if (owner) {
+ mutex_lock(&owner->perf_event_mutex);
+ /*
+ * We have to re-check the event->owner field, if it is cleared
+ * we raced with perf_event_exit_task(), acquiring the mutex
+ * ensured they're done, and we can proceed with freeing the
+ * event.
+ */
+ if (event->owner)
+ list_del_init(&event->owner_entry);
+ mutex_unlock(&owner->perf_event_mutex);
+ put_task_struct(owner);
+ }
+
return perf_event_release_kernel(event);
}
@@ -3396,7 +3430,8 @@ static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
}
static void perf_output_read_one(struct perf_output_handle *handle,
- struct perf_event *event)
+ struct perf_event *event,
+ u64 enabled, u64 running)
{
u64 read_format = event->attr.read_format;
u64 values[4];
@@ -3404,11 +3439,11 @@ static void perf_output_read_one(struct perf_output_handle *handle,
values[n++] = perf_event_count(event);
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
- values[n++] = event->total_time_enabled +
+ values[n++] = enabled +
atomic64_read(&event->child_total_time_enabled);
}
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
- values[n++] = event->total_time_running +
+ values[n++] = running +
atomic64_read(&event->child_total_time_running);
}
if (read_format & PERF_FORMAT_ID)
@@ -3421,7 +3456,8 @@ static void perf_output_read_one(struct perf_output_handle *handle,
* XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
*/
static void perf_output_read_group(struct perf_output_handle *handle,
- struct perf_event *event)
+ struct perf_event *event,
+ u64 enabled, u64 running)
{
struct perf_event *leader = event->group_leader, *sub;
u64 read_format = event->attr.read_format;
@@ -3431,10 +3467,10 @@ static void perf_output_read_group(struct perf_output_handle *handle,
values[n++] = 1 + leader->nr_siblings;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
- values[n++] = leader->total_time_enabled;
+ values[n++] = enabled;
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
- values[n++] = leader->total_time_running;
+ values[n++] = running;
if (leader != event)
leader->pmu->read(leader);
@@ -3459,13 +3495,35 @@ static void perf_output_read_group(struct perf_output_handle *handle,
}
}
+#define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
+ PERF_FORMAT_TOTAL_TIME_RUNNING)
+
static void perf_output_read(struct perf_output_handle *handle,
struct perf_event *event)
{
+ u64 enabled = 0, running = 0, now, ctx_time;
+ u64 read_format = event->attr.read_format;
+
+ /*
+ * compute total_time_enabled, total_time_running
+ * based on snapshot values taken when the event
+ * was last scheduled in.
+ *
+ * we cannot simply called update_context_time()
+ * because of locking issue as we are called in
+ * NMI context
+ */
+ if (read_format & PERF_FORMAT_TOTAL_TIMES) {
+ now = perf_clock();
+ ctx_time = event->shadow_ctx_time + now;
+ enabled = ctx_time - event->tstamp_enabled;
+ running = ctx_time - event->tstamp_running;
+ }
+
if (event->attr.read_format & PERF_FORMAT_GROUP)
- perf_output_read_group(handle, event);
+ perf_output_read_group(handle, event, enabled, running);
else
- perf_output_read_one(handle, event);
+ perf_output_read_one(handle, event, enabled, running);
}
void perf_output_sample(struct perf_output_handle *handle,
@@ -3766,6 +3824,8 @@ static void perf_event_task_event(struct perf_task_event *task_event)
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ if (cpuctx->active_pmu != pmu)
+ goto next;
perf_event_task_ctx(&cpuctx->ctx, task_event);
ctx = task_event->task_ctx;
@@ -3901,6 +3961,8 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ if (cpuctx->active_pmu != pmu)
+ goto next;
perf_event_comm_ctx(&cpuctx->ctx, comm_event);
ctxn = pmu->task_ctx_nr;
@@ -4086,6 +4148,8 @@ got_name:
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ if (cpuctx->active_pmu != pmu)
+ goto next;
perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
vma->vm_flags & VM_EXEC);
@@ -4655,7 +4719,7 @@ static int perf_swevent_init(struct perf_event *event)
break;
}
- if (event_id > PERF_COUNT_SW_MAX)
+ if (event_id >= PERF_COUNT_SW_MAX)
return -ENOENT;
if (!event->parent) {
@@ -5087,20 +5151,36 @@ static void *find_pmu_context(int ctxn)
return NULL;
}
-static void free_pmu_context(void * __percpu cpu_context)
+static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
{
- struct pmu *pmu;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct perf_cpu_context *cpuctx;
+
+ cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+
+ if (cpuctx->active_pmu == old_pmu)
+ cpuctx->active_pmu = pmu;
+ }
+}
+
+static void free_pmu_context(struct pmu *pmu)
+{
+ struct pmu *i;
mutex_lock(&pmus_lock);
/*
* Like a real lame refcount.
*/
- list_for_each_entry(pmu, &pmus, entry) {
- if (pmu->pmu_cpu_context == cpu_context)
+ list_for_each_entry(i, &pmus, entry) {
+ if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
+ update_pmu_context(i, pmu);
goto out;
+ }
}
- free_percpu(cpu_context);
+ free_percpu(pmu->pmu_cpu_context);
out:
mutex_unlock(&pmus_lock);
}
@@ -5132,6 +5212,7 @@ int perf_pmu_register(struct pmu *pmu)
cpuctx->ctx.pmu = pmu;
cpuctx->jiffies_interval = 1;
INIT_LIST_HEAD(&cpuctx->rotation_list);
+ cpuctx->active_pmu = pmu;
}
got_cpu_context:
@@ -5183,7 +5264,7 @@ void perf_pmu_unregister(struct pmu *pmu)
synchronize_rcu();
free_percpu(pmu->pmu_disable_count);
- free_pmu_context(pmu->pmu_cpu_context);
+ free_pmu_context(pmu);
}
struct pmu *perf_init_event(struct perf_event *event)
@@ -5651,7 +5732,7 @@ SYSCALL_DEFINE5(perf_event_open,
mutex_unlock(&ctx->mutex);
event->owner = current;
- get_task_struct(current);
+
mutex_lock(&current->perf_event_mutex);
list_add_tail(&event->owner_entry, &current->perf_event_list);
mutex_unlock(&current->perf_event_mutex);
@@ -5719,12 +5800,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
++ctx->generation;
mutex_unlock(&ctx->mutex);
- event->owner = current;
- get_task_struct(current);
- mutex_lock(&current->perf_event_mutex);
- list_add_tail(&event->owner_entry, &current->perf_event_list);
- mutex_unlock(&current->perf_event_mutex);
-
return event;
err_free:
@@ -5875,8 +5950,24 @@ again:
*/
void perf_event_exit_task(struct task_struct *child)
{
+ struct perf_event *event, *tmp;
int ctxn;
+ mutex_lock(&child->perf_event_mutex);
+ list_for_each_entry_safe(event, tmp, &child->perf_event_list,
+ owner_entry) {
+ list_del_init(&event->owner_entry);
+
+ /*
+ * Ensure the list deletion is visible before we clear
+ * the owner, closes a race against perf_release() where
+ * we need to serialize on the owner->perf_event_mutex.
+ */
+ smp_wmb();
+ event->owner = NULL;
+ }
+ mutex_unlock(&child->perf_event_mutex);
+
for_each_task_context_nr(ctxn)
perf_event_exit_task_context(child, ctxn);
}
@@ -6096,6 +6187,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
struct perf_event *event;
struct task_struct *parent = current;
int inherited_all = 1;
+ unsigned long flags;
int ret = 0;
child->perf_event_ctxp[ctxn] = NULL;
@@ -6136,6 +6228,15 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
break;
}
+ /*
+ * We can't hold ctx->lock when iterating the ->flexible_group list due
+ * to allocations, but we need to prevent rotation because
+ * rotate_ctx() will change the list from interrupt context.
+ */
+ raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+ parent_ctx->rotate_disable = 1;
+ raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
ret = inherit_task_group(event, parent, parent_ctx,
child, ctxn, &inherited_all);
@@ -6143,6 +6244,10 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
break;
}
+ raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+ parent_ctx->rotate_disable = 0;
+ raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
child_ctx = child->perf_event_ctxp[ctxn];
if (child_ctx && inherited_all) {
@@ -6295,6 +6400,8 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
void __init perf_event_init(void)
{
+ int ret;
+
perf_event_init_all_cpus();
init_srcu_struct(&pmus_srcu);
perf_pmu_register(&perf_swevent);
@@ -6302,4 +6409,7 @@ void __init perf_event_init(void)
perf_pmu_register(&perf_task_clock);
perf_tp_register();
perf_cpu_notifier(perf_cpu_notify);
+
+ ret = init_hw_breakpoint();
+ WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
}
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index c7a8f453919e..aeaa7f846821 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -121,10 +121,10 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
switch (o->type) {
case PM_QOS_MIN:
- return plist_last(&o->requests)->prio;
+ return plist_first(&o->requests)->prio;
case PM_QOS_MAX:
- return plist_first(&o->requests)->prio;
+ return plist_last(&o->requests)->prio;
default:
/* runtime check for not using enum */
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 6842eeba5879..05bb7173850e 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -37,13 +37,13 @@ static int check_clock(const clockid_t which_clock)
if (pid == 0)
return 0;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
p = find_task_by_vpid(pid);
if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ?
- same_thread_group(p, current) : thread_group_leader(p))) {
+ same_thread_group(p, current) : has_group_leader_pid(p))) {
error = -EINVAL;
}
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
return error;
}
@@ -390,7 +390,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
INIT_LIST_HEAD(&new_timer->it.cpu.entry);
- read_lock(&tasklist_lock);
+ rcu_read_lock();
if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
if (pid == 0) {
p = current;
@@ -404,7 +404,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
p = current->group_leader;
} else {
p = find_task_by_vpid(pid);
- if (p && !thread_group_leader(p))
+ if (p && !has_group_leader_pid(p))
p = NULL;
}
}
@@ -414,7 +414,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
} else {
ret = -EINVAL;
}
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
return ret;
}
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 29bff6117abc..a5aff3ebad38 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -246,9 +246,13 @@ config PM_OPS
depends on PM_SLEEP || PM_RUNTIME
default y
+config ARCH_HAS_OPP
+ bool
+
config PM_OPP
bool "Operating Performance Point (OPP) Layer library"
depends on PM
+ depends on ARCH_HAS_OPP
---help---
SOCs have a standard set of tuples consisting of frequency and
voltage pairs that the device will support per voltage domain. This
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 657272e91d0a..048d0b514831 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -327,7 +327,6 @@ static int create_image(int platform_mode)
int hibernation_snapshot(int platform_mode)
{
int error;
- gfp_t saved_mask;
error = platform_begin(platform_mode);
if (error)
@@ -339,7 +338,7 @@ int hibernation_snapshot(int platform_mode)
goto Close;
suspend_console();
- saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
+ pm_restrict_gfp_mask();
error = dpm_suspend_start(PMSG_FREEZE);
if (error)
goto Recover_platform;
@@ -348,7 +347,10 @@ int hibernation_snapshot(int platform_mode)
goto Recover_platform;
error = create_image(platform_mode);
- /* Control returns here after successful restore */
+ /*
+ * Control returns here (1) after the image has been created or the
+ * image creation has failed and (2) after a successful restore.
+ */
Resume_devices:
/* We may need to release the preallocated image pages here. */
@@ -357,7 +359,10 @@ int hibernation_snapshot(int platform_mode)
dpm_resume_end(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
- set_gfp_allowed_mask(saved_mask);
+
+ if (error || !in_suspend)
+ pm_restore_gfp_mask();
+
resume_console();
Close:
platform_end(platform_mode);
@@ -452,17 +457,16 @@ static int resume_target_kernel(bool platform_mode)
int hibernation_restore(int platform_mode)
{
int error;
- gfp_t saved_mask;
pm_prepare_console();
suspend_console();
- saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
+ pm_restrict_gfp_mask();
error = dpm_suspend_start(PMSG_QUIESCE);
if (!error) {
error = resume_target_kernel(platform_mode);
dpm_resume_end(PMSG_RECOVER);
}
- set_gfp_allowed_mask(saved_mask);
+ pm_restore_gfp_mask();
resume_console();
pm_restore_console();
return error;
@@ -476,7 +480,6 @@ int hibernation_restore(int platform_mode)
int hibernation_platform_enter(void)
{
int error;
- gfp_t saved_mask;
if (!hibernation_ops)
return -ENOSYS;
@@ -492,7 +495,6 @@ int hibernation_platform_enter(void)
entering_platform_hibernation = true;
suspend_console();
- saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
error = dpm_suspend_start(PMSG_HIBERNATE);
if (error) {
if (hibernation_ops->recover)
@@ -536,7 +538,6 @@ int hibernation_platform_enter(void)
Resume_devices:
entering_platform_hibernation = false;
dpm_resume_end(PMSG_RESTORE);
- set_gfp_allowed_mask(saved_mask);
resume_console();
Close:
@@ -646,6 +647,7 @@ int hibernate(void)
swsusp_free();
if (!error)
power_down();
+ pm_restore_gfp_mask();
} else {
pr_debug("PM: Image restored successfully.\n");
}
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 7335952ee473..ecf770509d0d 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -197,7 +197,6 @@ static int suspend_enter(suspend_state_t state)
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
- gfp_t saved_mask;
if (!suspend_ops)
return -ENOSYS;
@@ -208,7 +207,7 @@ int suspend_devices_and_enter(suspend_state_t state)
goto Close;
}
suspend_console();
- saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
+ pm_restrict_gfp_mask();
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
@@ -225,7 +224,7 @@ int suspend_devices_and_enter(suspend_state_t state)
suspend_test_start();
dpm_resume_end(PMSG_RESUME);
suspend_test_finish("resume devices");
- set_gfp_allowed_mask(saved_mask);
+ pm_restore_gfp_mask();
resume_console();
Close:
if (suspend_ops->end)
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index a0e4a86ccf94..8c7e4832b9be 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -6,6 +6,7 @@
*
* Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
* Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ * Copyright (C) 2010 Bojan Smojver <bojan@rexursive.com>
*
* This file is released under the GPLv2.
*
@@ -29,7 +30,7 @@
#include "power.h"
-#define HIBERNATE_SIG "LINHIB0001"
+#define HIBERNATE_SIG "S1SUSPEND"
/*
* The swap map is a data structure used for keeping track of each page
@@ -753,30 +754,43 @@ static int load_image_lzo(struct swap_map_handle *handle,
{
unsigned int m;
int error = 0;
+ struct bio *bio;
struct timeval start;
struct timeval stop;
unsigned nr_pages;
- size_t off, unc_len, cmp_len;
- unsigned char *unc, *cmp, *page;
+ size_t i, off, unc_len, cmp_len;
+ unsigned char *unc, *cmp, *page[LZO_CMP_PAGES];
- page = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
- if (!page) {
- printk(KERN_ERR "PM: Failed to allocate LZO page\n");
- return -ENOMEM;
+ for (i = 0; i < LZO_CMP_PAGES; i++) {
+ page[i] = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+ if (!page[i]) {
+ printk(KERN_ERR "PM: Failed to allocate LZO page\n");
+
+ while (i)
+ free_page((unsigned long)page[--i]);
+
+ return -ENOMEM;
+ }
}
unc = vmalloc(LZO_UNC_SIZE);
if (!unc) {
printk(KERN_ERR "PM: Failed to allocate LZO uncompressed\n");
- free_page((unsigned long)page);
+
+ for (i = 0; i < LZO_CMP_PAGES; i++)
+ free_page((unsigned long)page[i]);
+
return -ENOMEM;
}
cmp = vmalloc(LZO_CMP_SIZE);
if (!cmp) {
printk(KERN_ERR "PM: Failed to allocate LZO compressed\n");
+
vfree(unc);
- free_page((unsigned long)page);
+ for (i = 0; i < LZO_CMP_PAGES; i++)
+ free_page((unsigned long)page[i]);
+
return -ENOMEM;
}
@@ -787,6 +801,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
if (!m)
m = 1;
nr_pages = 0;
+ bio = NULL;
do_gettimeofday(&start);
error = snapshot_write_next(snapshot);
@@ -794,11 +809,11 @@ static int load_image_lzo(struct swap_map_handle *handle,
goto out_finish;
for (;;) {
- error = swap_read_page(handle, page, NULL); /* sync */
+ error = swap_read_page(handle, page[0], NULL); /* sync */
if (error)
break;
- cmp_len = *(size_t *)page;
+ cmp_len = *(size_t *)page[0];
if (unlikely(!cmp_len ||
cmp_len > lzo1x_worst_compress(LZO_UNC_SIZE))) {
printk(KERN_ERR "PM: Invalid LZO compressed length\n");
@@ -806,13 +821,20 @@ static int load_image_lzo(struct swap_map_handle *handle,
break;
}
- memcpy(cmp, page, PAGE_SIZE);
- for (off = PAGE_SIZE; off < LZO_HEADER + cmp_len; off += PAGE_SIZE) {
- error = swap_read_page(handle, page, NULL); /* sync */
+ for (off = PAGE_SIZE, i = 1;
+ off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) {
+ error = swap_read_page(handle, page[i], &bio);
if (error)
goto out_finish;
+ }
- memcpy(cmp + off, page, PAGE_SIZE);
+ error = hib_wait_on_bio_chain(&bio); /* need all data now */
+ if (error)
+ goto out_finish;
+
+ for (off = 0, i = 0;
+ off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) {
+ memcpy(cmp + off, page[i], PAGE_SIZE);
}
unc_len = LZO_UNC_SIZE;
@@ -857,7 +879,8 @@ out_finish:
vfree(cmp);
vfree(unc);
- free_page((unsigned long)page);
+ for (i = 0; i < LZO_CMP_PAGES; i++)
+ free_page((unsigned long)page[i]);
return error;
}
diff --git a/kernel/power/user.c b/kernel/power/user.c
index e819e17877ca..c36c3b9e8a84 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -137,7 +137,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
free_all_swap_pages(data->swap);
if (data->frozen)
thaw_processes();
- pm_notifier_call_chain(data->mode == O_WRONLY ?
+ pm_notifier_call_chain(data->mode == O_RDONLY ?
PM_POST_HIBERNATION : PM_POST_RESTORE);
atomic_inc(&snapshot_device_available);
@@ -263,6 +263,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
case SNAPSHOT_UNFREEZE:
if (!data->frozen || data->ready)
break;
+ pm_restore_gfp_mask();
thaw_processes();
usermodehelper_enable();
data->frozen = 0;
@@ -275,6 +276,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
error = -EPERM;
break;
}
+ pm_restore_gfp_mask();
error = hibernation_snapshot(data->platform_support);
if (!error)
error = put_user(in_suspend, (int __user *)arg);
diff --git a/kernel/printk.c b/kernel/printk.c
index b2ebaee8c377..a23315dc4498 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -261,6 +261,12 @@ static inline void boot_delay_msec(void)
}
#endif
+#ifdef CONFIG_SECURITY_DMESG_RESTRICT
+int dmesg_restrict = 1;
+#else
+int dmesg_restrict;
+#endif
+
int do_syslog(int type, char __user *buf, int len, bool from_file)
{
unsigned i, j, limit, count;
@@ -268,7 +274,20 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
char c;
int error = 0;
- error = security_syslog(type, from_file);
+ /*
+ * If this is from /proc/kmsg we only do the capabilities checks
+ * at open time.
+ */
+ if (type == SYSLOG_ACTION_OPEN || !from_file) {
+ if (dmesg_restrict && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if ((type != SYSLOG_ACTION_READ_ALL &&
+ type != SYSLOG_ACTION_SIZE_BUFFER) &&
+ !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ }
+
+ error = security_syslog(type);
if (error)
return error;
@@ -1063,13 +1082,15 @@ void printk_tick(void)
int printk_needs_cpu(int cpu)
{
+ if (unlikely(cpu_is_offline(cpu)))
+ printk_tick();
return per_cpu(printk_pending, cpu);
}
void wake_up_klogd(void)
{
if (waitqueue_active(&log_wait))
- __raw_get_cpu_var(printk_pending) = 1;
+ this_cpu_write(printk_pending, 1);
}
/**
diff --git a/kernel/range.c b/kernel/range.c
index 471b66acabb5..37fa9b99ad58 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -119,7 +119,7 @@ static int cmp_range(const void *x1, const void *x2)
int clean_sort_range(struct range *range, int az)
{
- int i, j, k = az - 1, nr_range = 0;
+ int i, j, k = az - 1, nr_range = az;
for (i = 0; i < k; i++) {
if (range[i].end)
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index d806735342ac..034493724749 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -36,31 +36,16 @@
#include <linux/time.h>
#include <linux/cpu.h>
-/* Global control variables for rcupdate callback mechanism. */
-struct rcu_ctrlblk {
- struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
- struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
- struct rcu_head **curtail; /* ->next pointer of last CB. */
-};
-
-/* Definition for rcupdate control block. */
-static struct rcu_ctrlblk rcu_sched_ctrlblk = {
- .donetail = &rcu_sched_ctrlblk.rcucblist,
- .curtail = &rcu_sched_ctrlblk.rcucblist,
-};
-
-static struct rcu_ctrlblk rcu_bh_ctrlblk = {
- .donetail = &rcu_bh_ctrlblk.rcucblist,
- .curtail = &rcu_bh_ctrlblk.rcucblist,
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-int rcu_scheduler_active __read_mostly;
-EXPORT_SYMBOL_GPL(rcu_scheduler_active);
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+/* Controls for rcu_kthread() kthread, replacing RCU_SOFTIRQ used previously. */
+static struct task_struct *rcu_kthread_task;
+static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);
+static unsigned long have_rcu_kthread_work;
+static void invoke_rcu_kthread(void);
/* Forward declarations for rcutiny_plugin.h. */
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
+struct rcu_ctrlblk;
+static void rcu_process_callbacks(struct rcu_ctrlblk *rcp);
+static int rcu_kthread(void *arg);
static void __call_rcu(struct rcu_head *head,
void (*func)(struct rcu_head *rcu),
struct rcu_ctrlblk *rcp);
@@ -123,7 +108,7 @@ void rcu_sched_qs(int cpu)
{
if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
rcu_qsctr_help(&rcu_bh_ctrlblk))
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
}
/*
@@ -132,7 +117,7 @@ void rcu_sched_qs(int cpu)
void rcu_bh_qs(int cpu)
{
if (rcu_qsctr_help(&rcu_bh_ctrlblk))
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
}
/*
@@ -152,13 +137,14 @@ void rcu_check_callbacks(int cpu, int user)
}
/*
- * Helper function for rcu_process_callbacks() that operates on the
- * specified rcu_ctrlkblk structure.
+ * Invoke the RCU callbacks on the specified rcu_ctrlkblk structure
+ * whose grace period has elapsed.
*/
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
+static void rcu_process_callbacks(struct rcu_ctrlblk *rcp)
{
struct rcu_head *next, *list;
unsigned long flags;
+ RCU_TRACE(int cb_count = 0);
/* If no RCU callbacks ready to invoke, just return. */
if (&rcp->rcucblist == rcp->donetail)
@@ -180,19 +166,58 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
+ local_bh_disable();
list->func(list);
+ local_bh_enable();
list = next;
+ RCU_TRACE(cb_count++);
}
+ RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
}
/*
- * Invoke any callbacks whose grace period has completed.
+ * This kthread invokes RCU callbacks whose grace periods have
+ * elapsed. It is awakened as needed, and takes the place of the
+ * RCU_SOFTIRQ that was used previously for this purpose.
+ * This is a kthread, but it is never stopped, at least not until
+ * the system goes down.
*/
-static void rcu_process_callbacks(struct softirq_action *unused)
+static int rcu_kthread(void *arg)
{
- __rcu_process_callbacks(&rcu_sched_ctrlblk);
- __rcu_process_callbacks(&rcu_bh_ctrlblk);
- rcu_preempt_process_callbacks();
+ unsigned long work;
+ unsigned long morework;
+ unsigned long flags;
+
+ for (;;) {
+ wait_event(rcu_kthread_wq, have_rcu_kthread_work != 0);
+ morework = rcu_boost();
+ local_irq_save(flags);
+ work = have_rcu_kthread_work;
+ have_rcu_kthread_work = morework;
+ local_irq_restore(flags);
+ if (work) {
+ rcu_process_callbacks(&rcu_sched_ctrlblk);
+ rcu_process_callbacks(&rcu_bh_ctrlblk);
+ rcu_preempt_process_callbacks();
+ }
+ schedule_timeout_interruptible(1); /* Leave CPU for others. */
+ }
+
+ return 0; /* Not reached, but needed to shut gcc up. */
+}
+
+/*
+ * Wake up rcu_kthread() to process callbacks now eligible for invocation
+ * or to boost readers.
+ */
+static void invoke_rcu_kthread(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ have_rcu_kthread_work = 1;
+ wake_up(&rcu_kthread_wq);
+ local_irq_restore(flags);
}
/*
@@ -230,6 +255,7 @@ static void __call_rcu(struct rcu_head *head,
local_irq_save(flags);
*rcp->curtail = head;
rcp->curtail = &head->next;
+ RCU_TRACE(rcp->qlen++);
local_irq_restore(flags);
}
@@ -282,7 +308,16 @@ void rcu_barrier_sched(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_sched);
-void __init rcu_init(void)
+/*
+ * Spawn the kthread that invokes RCU callbacks.
+ */
+static int __init rcu_spawn_kthreads(void)
{
- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+ struct sched_param sp;
+
+ rcu_kthread_task = kthread_run(rcu_kthread, NULL, "rcu_kthread");
+ sp.sched_priority = RCU_BOOST_PRIO;
+ sched_setscheduler_nocheck(rcu_kthread_task, SCHED_FIFO, &sp);
+ return 0;
}
+early_initcall(rcu_spawn_kthreads);
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 6ceca4f745ff..015abaea962a 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -22,6 +22,40 @@
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
+#include <linux/kthread.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#ifdef CONFIG_RCU_TRACE
+#define RCU_TRACE(stmt) stmt
+#else /* #ifdef CONFIG_RCU_TRACE */
+#define RCU_TRACE(stmt)
+#endif /* #else #ifdef CONFIG_RCU_TRACE */
+
+/* Global control variables for rcupdate callback mechanism. */
+struct rcu_ctrlblk {
+ struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
+ struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
+ struct rcu_head **curtail; /* ->next pointer of last CB. */
+ RCU_TRACE(long qlen); /* Number of pending CBs. */
+};
+
+/* Definition for rcupdate control block. */
+static struct rcu_ctrlblk rcu_sched_ctrlblk = {
+ .donetail = &rcu_sched_ctrlblk.rcucblist,
+ .curtail = &rcu_sched_ctrlblk.rcucblist,
+};
+
+static struct rcu_ctrlblk rcu_bh_ctrlblk = {
+ .donetail = &rcu_bh_ctrlblk.rcucblist,
+ .curtail = &rcu_bh_ctrlblk.rcucblist,
+};
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
#ifdef CONFIG_TINY_PREEMPT_RCU
#include <linux/delay.h>
@@ -46,17 +80,45 @@ struct rcu_preempt_ctrlblk {
struct list_head *gp_tasks;
/* Pointer to the first task blocking the */
/* current grace period, or NULL if there */
- /* is not such task. */
+ /* is no such task. */
struct list_head *exp_tasks;
/* Pointer to first task blocking the */
/* current expedited grace period, or NULL */
/* if there is no such task. If there */
/* is no current expedited grace period, */
/* then there cannot be any such task. */
+#ifdef CONFIG_RCU_BOOST
+ struct list_head *boost_tasks;
+ /* Pointer to first task that needs to be */
+ /* priority-boosted, or NULL if no priority */
+ /* boosting is needed. If there is no */
+ /* current or expedited grace period, there */
+ /* can be no such task. */
+#endif /* #ifdef CONFIG_RCU_BOOST */
u8 gpnum; /* Current grace period. */
u8 gpcpu; /* Last grace period blocked by the CPU. */
u8 completed; /* Last grace period completed. */
/* If all three are equal, RCU is idle. */
+#ifdef CONFIG_RCU_BOOST
+ s8 boosted_this_gp; /* Has boosting already happened? */
+ unsigned long boost_time; /* When to start boosting (jiffies) */
+#endif /* #ifdef CONFIG_RCU_BOOST */
+#ifdef CONFIG_RCU_TRACE
+ unsigned long n_grace_periods;
+#ifdef CONFIG_RCU_BOOST
+ unsigned long n_tasks_boosted;
+ unsigned long n_exp_boosts;
+ unsigned long n_normal_boosts;
+ unsigned long n_normal_balk_blkd_tasks;
+ unsigned long n_normal_balk_gp_tasks;
+ unsigned long n_normal_balk_boost_tasks;
+ unsigned long n_normal_balk_boosted;
+ unsigned long n_normal_balk_notyet;
+ unsigned long n_normal_balk_nos;
+ unsigned long n_exp_balk_blkd_tasks;
+ unsigned long n_exp_balk_nos;
+#endif /* #ifdef CONFIG_RCU_BOOST */
+#endif /* #ifdef CONFIG_RCU_TRACE */
};
static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = {
@@ -122,6 +184,210 @@ static int rcu_preempt_gp_in_progress(void)
}
/*
+ * Advance a ->blkd_tasks-list pointer to the next entry, instead
+ * returning NULL if at the end of the list.
+ */
+static struct list_head *rcu_next_node_entry(struct task_struct *t)
+{
+ struct list_head *np;
+
+ np = t->rcu_node_entry.next;
+ if (np == &rcu_preempt_ctrlblk.blkd_tasks)
+ np = NULL;
+ return np;
+}
+
+#ifdef CONFIG_RCU_TRACE
+
+#ifdef CONFIG_RCU_BOOST
+static void rcu_initiate_boost_trace(void);
+static void rcu_initiate_exp_boost_trace(void);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * Dump additional statistice for TINY_PREEMPT_RCU.
+ */
+static void show_tiny_preempt_stats(struct seq_file *m)
+{
+ seq_printf(m, "rcu_preempt: qlen=%ld gp=%lu g%u/p%u/c%u tasks=%c%c%c\n",
+ rcu_preempt_ctrlblk.rcb.qlen,
+ rcu_preempt_ctrlblk.n_grace_periods,
+ rcu_preempt_ctrlblk.gpnum,
+ rcu_preempt_ctrlblk.gpcpu,
+ rcu_preempt_ctrlblk.completed,
+ "T."[list_empty(&rcu_preempt_ctrlblk.blkd_tasks)],
+ "N."[!rcu_preempt_ctrlblk.gp_tasks],
+ "E."[!rcu_preempt_ctrlblk.exp_tasks]);
+#ifdef CONFIG_RCU_BOOST
+ seq_printf(m, " ttb=%c btg=",
+ "B."[!rcu_preempt_ctrlblk.boost_tasks]);
+ switch (rcu_preempt_ctrlblk.boosted_this_gp) {
+ case -1:
+ seq_puts(m, "exp");
+ break;
+ case 0:
+ seq_puts(m, "no");
+ break;
+ case 1:
+ seq_puts(m, "begun");
+ break;
+ case 2:
+ seq_puts(m, "done");
+ break;
+ default:
+ seq_printf(m, "?%d?", rcu_preempt_ctrlblk.boosted_this_gp);
+ }
+ seq_printf(m, " ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n",
+ rcu_preempt_ctrlblk.n_tasks_boosted,
+ rcu_preempt_ctrlblk.n_exp_boosts,
+ rcu_preempt_ctrlblk.n_normal_boosts,
+ (int)(jiffies & 0xffff),
+ (int)(rcu_preempt_ctrlblk.boost_time & 0xffff));
+ seq_printf(m, " %s: nt=%lu gt=%lu bt=%lu b=%lu ny=%lu nos=%lu\n",
+ "normal balk",
+ rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks,
+ rcu_preempt_ctrlblk.n_normal_balk_gp_tasks,
+ rcu_preempt_ctrlblk.n_normal_balk_boost_tasks,
+ rcu_preempt_ctrlblk.n_normal_balk_boosted,
+ rcu_preempt_ctrlblk.n_normal_balk_notyet,
+ rcu_preempt_ctrlblk.n_normal_balk_nos);
+ seq_printf(m, " exp balk: bt=%lu nos=%lu\n",
+ rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks,
+ rcu_preempt_ctrlblk.n_exp_balk_nos);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+}
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
+#ifdef CONFIG_RCU_BOOST
+
+#include "rtmutex_common.h"
+
+/*
+ * Carry out RCU priority boosting on the task indicated by ->boost_tasks,
+ * and advance ->boost_tasks to the next task in the ->blkd_tasks list.
+ */
+static int rcu_boost(void)
+{
+ unsigned long flags;
+ struct rt_mutex mtx;
+ struct list_head *np;
+ struct task_struct *t;
+
+ if (rcu_preempt_ctrlblk.boost_tasks == NULL)
+ return 0; /* Nothing to boost. */
+ raw_local_irq_save(flags);
+ rcu_preempt_ctrlblk.boosted_this_gp++;
+ t = container_of(rcu_preempt_ctrlblk.boost_tasks, struct task_struct,
+ rcu_node_entry);
+ np = rcu_next_node_entry(t);
+ rt_mutex_init_proxy_locked(&mtx, t);
+ t->rcu_boost_mutex = &mtx;
+ t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED;
+ raw_local_irq_restore(flags);
+ rt_mutex_lock(&mtx);
+ RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++);
+ rcu_preempt_ctrlblk.boosted_this_gp++;
+ rt_mutex_unlock(&mtx);
+ return rcu_preempt_ctrlblk.boost_tasks != NULL;
+}
+
+/*
+ * Check to see if it is now time to start boosting RCU readers blocking
+ * the current grace period, and, if so, tell the rcu_kthread_task to
+ * start boosting them. If there is an expedited boost in progress,
+ * we wait for it to complete.
+ *
+ * If there are no blocked readers blocking the current grace period,
+ * return 0 to let the caller know, otherwise return 1. Note that this
+ * return value is independent of whether or not boosting was done.
+ */
+static int rcu_initiate_boost(void)
+{
+ if (!rcu_preempt_blocked_readers_cgp()) {
+ RCU_TRACE(rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks++);
+ return 0;
+ }
+ if (rcu_preempt_ctrlblk.gp_tasks != NULL &&
+ rcu_preempt_ctrlblk.boost_tasks == NULL &&
+ rcu_preempt_ctrlblk.boosted_this_gp == 0 &&
+ ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time)) {
+ rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks;
+ invoke_rcu_kthread();
+ RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++);
+ } else
+ RCU_TRACE(rcu_initiate_boost_trace());
+ return 1;
+}
+
+/*
+ * Initiate boosting for an expedited grace period.
+ */
+static void rcu_initiate_expedited_boost(void)
+{
+ unsigned long flags;
+
+ raw_local_irq_save(flags);
+ if (!list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) {
+ rcu_preempt_ctrlblk.boost_tasks =
+ rcu_preempt_ctrlblk.blkd_tasks.next;
+ rcu_preempt_ctrlblk.boosted_this_gp = -1;
+ invoke_rcu_kthread();
+ RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++);
+ } else
+ RCU_TRACE(rcu_initiate_exp_boost_trace());
+ raw_local_irq_restore(flags);
+}
+
+#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000);
+
+/*
+ * Do priority-boost accounting for the start of a new grace period.
+ */
+static void rcu_preempt_boost_start_gp(void)
+{
+ rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
+ if (rcu_preempt_ctrlblk.boosted_this_gp > 0)
+ rcu_preempt_ctrlblk.boosted_this_gp = 0;
+}
+
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * If there is no RCU priority boosting, we don't boost.
+ */
+static int rcu_boost(void)
+{
+ return 0;
+}
+
+/*
+ * If there is no RCU priority boosting, we don't initiate boosting,
+ * but we do indicate whether there are blocked readers blocking the
+ * current grace period.
+ */
+static int rcu_initiate_boost(void)
+{
+ return rcu_preempt_blocked_readers_cgp();
+}
+
+/*
+ * If there is no RCU priority boosting, we don't initiate expedited boosting.
+ */
+static void rcu_initiate_expedited_boost(void)
+{
+}
+
+/*
+ * If there is no RCU priority boosting, nothing to do at grace-period start.
+ */
+static void rcu_preempt_boost_start_gp(void)
+{
+}
+
+#endif /* else #ifdef CONFIG_RCU_BOOST */
+
+/*
* Record a preemptible-RCU quiescent state for the specified CPU. Note
* that this just means that the task currently running on the CPU is
* in a quiescent state. There might be any number of tasks blocked
@@ -148,11 +414,14 @@ static void rcu_preempt_cpu_qs(void)
rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum;
current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+ /* If there is no GP then there is nothing more to do. */
+ if (!rcu_preempt_gp_in_progress())
+ return;
/*
- * If there is no GP, or if blocked readers are still blocking GP,
- * then there is nothing more to do.
+ * Check up on boosting. If there are no readers blocking the
+ * current grace period, leave.
*/
- if (!rcu_preempt_gp_in_progress() || rcu_preempt_blocked_readers_cgp())
+ if (rcu_initiate_boost())
return;
/* Advance callbacks. */
@@ -164,9 +433,9 @@ static void rcu_preempt_cpu_qs(void)
if (!rcu_preempt_blocked_readers_any())
rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail;
- /* If there are done callbacks, make RCU_SOFTIRQ process them. */
+ /* If there are done callbacks, cause them to be invoked. */
if (*rcu_preempt_ctrlblk.rcb.donetail != NULL)
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
}
/*
@@ -178,12 +447,16 @@ static void rcu_preempt_start_gp(void)
/* Official start of GP. */
rcu_preempt_ctrlblk.gpnum++;
+ RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++);
/* Any blocked RCU readers block new GP. */
if (rcu_preempt_blocked_readers_any())
rcu_preempt_ctrlblk.gp_tasks =
rcu_preempt_ctrlblk.blkd_tasks.next;
+ /* Set up for RCU priority boosting. */
+ rcu_preempt_boost_start_gp();
+
/* If there is no running reader, CPU is done with GP. */
if (!rcu_preempt_running_reader())
rcu_preempt_cpu_qs();
@@ -304,14 +577,16 @@ static void rcu_read_unlock_special(struct task_struct *t)
*/
empty = !rcu_preempt_blocked_readers_cgp();
empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL;
- np = t->rcu_node_entry.next;
- if (np == &rcu_preempt_ctrlblk.blkd_tasks)
- np = NULL;
+ np = rcu_next_node_entry(t);
list_del(&t->rcu_node_entry);
if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks)
rcu_preempt_ctrlblk.gp_tasks = np;
if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks)
rcu_preempt_ctrlblk.exp_tasks = np;
+#ifdef CONFIG_RCU_BOOST
+ if (&t->rcu_node_entry == rcu_preempt_ctrlblk.boost_tasks)
+ rcu_preempt_ctrlblk.boost_tasks = np;
+#endif /* #ifdef CONFIG_RCU_BOOST */
INIT_LIST_HEAD(&t->rcu_node_entry);
/*
@@ -331,6 +606,14 @@ static void rcu_read_unlock_special(struct task_struct *t)
if (!empty_exp && rcu_preempt_ctrlblk.exp_tasks == NULL)
rcu_report_exp_done();
}
+#ifdef CONFIG_RCU_BOOST
+ /* Unboost self if was boosted. */
+ if (special & RCU_READ_UNLOCK_BOOSTED) {
+ t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED;
+ rt_mutex_unlock(t->rcu_boost_mutex);
+ t->rcu_boost_mutex = NULL;
+ }
+#endif /* #ifdef CONFIG_RCU_BOOST */
local_irq_restore(flags);
}
@@ -374,7 +657,7 @@ static void rcu_preempt_check_callbacks(void)
rcu_preempt_cpu_qs();
if (&rcu_preempt_ctrlblk.rcb.rcucblist !=
rcu_preempt_ctrlblk.rcb.donetail)
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
if (rcu_preempt_gp_in_progress() &&
rcu_cpu_blocking_cur_gp() &&
rcu_preempt_running_reader())
@@ -383,7 +666,7 @@ static void rcu_preempt_check_callbacks(void)
/*
* TINY_PREEMPT_RCU has an extra callback-list tail pointer to
- * update, so this is invoked from __rcu_process_callbacks() to
+ * update, so this is invoked from rcu_process_callbacks() to
* handle that case. Of course, it is invoked for all flavors of
* RCU, but RCU callbacks can appear only on one of the lists, and
* neither ->nexttail nor ->donetail can possibly be NULL, so there
@@ -400,7 +683,7 @@ static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
*/
static void rcu_preempt_process_callbacks(void)
{
- __rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
+ rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
}
/*
@@ -417,6 +700,7 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
local_irq_save(flags);
*rcu_preempt_ctrlblk.nexttail = head;
rcu_preempt_ctrlblk.nexttail = &head->next;
+ RCU_TRACE(rcu_preempt_ctrlblk.rcb.qlen++);
rcu_preempt_start_gp(); /* checks to see if GP needed. */
local_irq_restore(flags);
}
@@ -532,6 +816,7 @@ void synchronize_rcu_expedited(void)
/* Wait for tail of ->blkd_tasks list to drain. */
if (rcu_preempted_readers_exp())
+ rcu_initiate_expedited_boost();
wait_event(sync_rcu_preempt_exp_wq,
!rcu_preempted_readers_exp());
@@ -572,6 +857,27 @@ void exit_rcu(void)
#else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
+#ifdef CONFIG_RCU_TRACE
+
+/*
+ * Because preemptible RCU does not exist, it is not necessary to
+ * dump out its statistics.
+ */
+static void show_tiny_preempt_stats(struct seq_file *m)
+{
+}
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
+/*
+ * Because preemptible RCU does not exist, it is never necessary to
+ * boost preempted RCU readers.
+ */
+static int rcu_boost(void)
+{
+ return 0;
+}
+
/*
* Because preemptible RCU does not exist, it never has any callbacks
* to check.
@@ -599,17 +905,116 @@ static void rcu_preempt_process_callbacks(void)
#endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-
#include <linux/kernel_stat.h>
/*
* During boot, we forgive RCU lockdep issues. After this function is
* invoked, we start taking RCU lockdep issues seriously.
*/
-void rcu_scheduler_starting(void)
+void __init rcu_scheduler_starting(void)
{
WARN_ON(nr_context_switches() > 0);
rcu_scheduler_active = 1;
}
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_RCU_BOOST
+#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
+#else /* #ifdef CONFIG_RCU_BOOST */
+#define RCU_BOOST_PRIO 1
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
+#ifdef CONFIG_RCU_TRACE
+
+#ifdef CONFIG_RCU_BOOST
+
+static void rcu_initiate_boost_trace(void)
+{
+ if (rcu_preempt_ctrlblk.gp_tasks == NULL)
+ rcu_preempt_ctrlblk.n_normal_balk_gp_tasks++;
+ else if (rcu_preempt_ctrlblk.boost_tasks != NULL)
+ rcu_preempt_ctrlblk.n_normal_balk_boost_tasks++;
+ else if (rcu_preempt_ctrlblk.boosted_this_gp != 0)
+ rcu_preempt_ctrlblk.n_normal_balk_boosted++;
+ else if (!ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))
+ rcu_preempt_ctrlblk.n_normal_balk_notyet++;
+ else
+ rcu_preempt_ctrlblk.n_normal_balk_nos++;
+}
+
+static void rcu_initiate_exp_boost_trace(void)
+{
+ if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks))
+ rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks++;
+ else
+ rcu_preempt_ctrlblk.n_exp_balk_nos++;
+}
+
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
+static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n)
+{
+ unsigned long flags;
+
+ raw_local_irq_save(flags);
+ rcp->qlen -= n;
+ raw_local_irq_restore(flags);
+}
+
+/*
+ * Dump statistics for TINY_RCU, such as they are.
+ */
+static int show_tiny_stats(struct seq_file *m, void *unused)
+{
+ show_tiny_preempt_stats(m);
+ seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen);
+ seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen);
+ return 0;
+}
+
+static int show_tiny_stats_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, show_tiny_stats, NULL);
+}
+
+static const struct file_operations show_tiny_stats_fops = {
+ .owner = THIS_MODULE,
+ .open = show_tiny_stats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static struct dentry *rcudir;
+
+static int __init rcutiny_trace_init(void)
+{
+ struct dentry *retval;
+
+ rcudir = debugfs_create_dir("rcu", NULL);
+ if (!rcudir)
+ goto free_out;
+ retval = debugfs_create_file("rcudata", 0444, rcudir,
+ NULL, &show_tiny_stats_fops);
+ if (!retval)
+ goto free_out;
+ return 0;
+free_out:
+ debugfs_remove_recursive(rcudir);
+ return 1;
+}
+
+static void __exit rcutiny_trace_cleanup(void)
+{
+ debugfs_remove_recursive(rcudir);
+}
+
+module_init(rcutiny_trace_init);
+module_exit(rcutiny_trace_cleanup);
+
+MODULE_AUTHOR("Paul E. McKenney");
+MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation");
+MODULE_LICENSE("GPL");
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 9d8e8fb2515f..89613f97ff26 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -47,6 +47,7 @@
#include <linux/srcu.h>
#include <linux/slab.h>
#include <asm/byteorder.h>
+#include <linux/sched.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and "
@@ -64,6 +65,9 @@ static int irqreader = 1; /* RCU readers from irq (timers). */
static int fqs_duration = 0; /* Duration of bursts (us), 0 to disable. */
static int fqs_holdoff = 0; /* Hold time within burst (us). */
static int fqs_stutter = 3; /* Wait time between bursts (s). */
+static int test_boost = 1; /* Test RCU prio boost: 0=no, 1=maybe, 2=yes. */
+static int test_boost_interval = 7; /* Interval between boost tests, seconds. */
+static int test_boost_duration = 4; /* Duration of each boost test, seconds. */
static char *torture_type = "rcu"; /* What RCU implementation to torture. */
module_param(nreaders, int, 0444);
@@ -88,6 +92,12 @@ module_param(fqs_holdoff, int, 0444);
MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
module_param(fqs_stutter, int, 0444);
MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
+module_param(test_boost, int, 0444);
+MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
+module_param(test_boost_interval, int, 0444);
+MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
+module_param(test_boost_duration, int, 0444);
+MODULE_PARM_DESC(test_boost_duration, "Duration of each boost test, seconds.");
module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
@@ -109,6 +119,7 @@ static struct task_struct *stats_task;
static struct task_struct *shuffler_task;
static struct task_struct *stutter_task;
static struct task_struct *fqs_task;
+static struct task_struct *boost_tasks[NR_CPUS];
#define RCU_TORTURE_PIPE_LEN 10
@@ -134,6 +145,12 @@ static atomic_t n_rcu_torture_alloc_fail;
static atomic_t n_rcu_torture_free;
static atomic_t n_rcu_torture_mberror;
static atomic_t n_rcu_torture_error;
+static long n_rcu_torture_boost_ktrerror;
+static long n_rcu_torture_boost_rterror;
+static long n_rcu_torture_boost_allocerror;
+static long n_rcu_torture_boost_afferror;
+static long n_rcu_torture_boost_failure;
+static long n_rcu_torture_boosts;
static long n_rcu_torture_timers;
static struct list_head rcu_torture_removed;
static cpumask_var_t shuffle_tmp_mask;
@@ -147,6 +164,16 @@ static int stutter_pause_test;
#endif
int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+#ifdef CONFIG_RCU_BOOST
+#define rcu_can_boost() 1
+#else /* #ifdef CONFIG_RCU_BOOST */
+#define rcu_can_boost() 0
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
+static unsigned long boost_starttime; /* jiffies of next boost test start. */
+DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */
+ /* and boost task create/destroy. */
+
/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */
#define FULLSTOP_DONTSTOP 0 /* Normal operation. */
@@ -277,6 +304,7 @@ struct rcu_torture_ops {
void (*fqs)(void);
int (*stats)(char *page);
int irq_capable;
+ int can_boost;
char *name;
};
@@ -366,6 +394,7 @@ static struct rcu_torture_ops rcu_ops = {
.fqs = rcu_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .can_boost = rcu_can_boost(),
.name = "rcu"
};
@@ -408,6 +437,7 @@ static struct rcu_torture_ops rcu_sync_ops = {
.fqs = rcu_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .can_boost = rcu_can_boost(),
.name = "rcu_sync"
};
@@ -424,6 +454,7 @@ static struct rcu_torture_ops rcu_expedited_ops = {
.fqs = rcu_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .can_boost = rcu_can_boost(),
.name = "rcu_expedited"
};
@@ -684,6 +715,110 @@ static struct rcu_torture_ops sched_expedited_ops = {
};
/*
+ * RCU torture priority-boost testing. Runs one real-time thread per
+ * CPU for moderate bursts, repeatedly registering RCU callbacks and
+ * spinning waiting for them to be invoked. If a given callback takes
+ * too long to be invoked, we assume that priority inversion has occurred.
+ */
+
+struct rcu_boost_inflight {
+ struct rcu_head rcu;
+ int inflight;
+};
+
+static void rcu_torture_boost_cb(struct rcu_head *head)
+{
+ struct rcu_boost_inflight *rbip =
+ container_of(head, struct rcu_boost_inflight, rcu);
+
+ smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
+ rbip->inflight = 0;
+}
+
+static int rcu_torture_boost(void *arg)
+{
+ unsigned long call_rcu_time;
+ unsigned long endtime;
+ unsigned long oldstarttime;
+ struct rcu_boost_inflight rbi = { .inflight = 0 };
+ struct sched_param sp;
+
+ VERBOSE_PRINTK_STRING("rcu_torture_boost started");
+
+ /* Set real-time priority. */
+ sp.sched_priority = 1;
+ if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) {
+ VERBOSE_PRINTK_STRING("rcu_torture_boost RT prio failed!");
+ n_rcu_torture_boost_rterror++;
+ }
+
+ /* Each pass through the following loop does one boost-test cycle. */
+ do {
+ /* Wait for the next test interval. */
+ oldstarttime = boost_starttime;
+ while (jiffies - oldstarttime > ULONG_MAX / 2) {
+ schedule_timeout_uninterruptible(1);
+ rcu_stutter_wait("rcu_torture_boost");
+ if (kthread_should_stop() ||
+ fullstop != FULLSTOP_DONTSTOP)
+ goto checkwait;
+ }
+
+ /* Do one boost-test interval. */
+ endtime = oldstarttime + test_boost_duration * HZ;
+ call_rcu_time = jiffies;
+ while (jiffies - endtime > ULONG_MAX / 2) {
+ /* If we don't have a callback in flight, post one. */
+ if (!rbi.inflight) {
+ smp_mb(); /* RCU core before ->inflight = 1. */
+ rbi.inflight = 1;
+ call_rcu(&rbi.rcu, rcu_torture_boost_cb);
+ if (jiffies - call_rcu_time >
+ test_boost_duration * HZ - HZ / 2) {
+ VERBOSE_PRINTK_STRING("rcu_torture_boost boosting failed");
+ n_rcu_torture_boost_failure++;
+ }
+ call_rcu_time = jiffies;
+ }
+ cond_resched();
+ rcu_stutter_wait("rcu_torture_boost");
+ if (kthread_should_stop() ||
+ fullstop != FULLSTOP_DONTSTOP)
+ goto checkwait;
+ }
+
+ /*
+ * Set the start time of the next test interval.
+ * Yes, this is vulnerable to long delays, but such
+ * delays simply cause a false negative for the next
+ * interval. Besides, we are running at RT priority,
+ * so delays should be relatively rare.
+ */
+ while (oldstarttime == boost_starttime) {
+ if (mutex_trylock(&boost_mutex)) {
+ boost_starttime = jiffies +
+ test_boost_interval * HZ;
+ n_rcu_torture_boosts++;
+ mutex_unlock(&boost_mutex);
+ break;
+ }
+ schedule_timeout_uninterruptible(1);
+ }
+
+ /* Go do the stutter. */
+checkwait: rcu_stutter_wait("rcu_torture_boost");
+ } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+
+ /* Clean up and exit. */
+ VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping");
+ rcutorture_shutdown_absorb("rcu_torture_boost");
+ while (!kthread_should_stop() || rbi.inflight)
+ schedule_timeout_uninterruptible(1);
+ smp_mb(); /* order accesses to ->inflight before stack-frame death. */
+ return 0;
+}
+
+/*
* RCU torture force-quiescent-state kthread. Repeatedly induces
* bursts of calls to force_quiescent_state(), increasing the probability
* of occurrence of some important types of race conditions.
@@ -933,7 +1068,8 @@ rcu_torture_printk(char *page)
cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
cnt += sprintf(&page[cnt],
"rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d "
- "rtmbe: %d nt: %ld",
+ "rtmbe: %d rtbke: %ld rtbre: %ld rtbae: %ld rtbafe: %ld "
+ "rtbf: %ld rtb: %ld nt: %ld",
rcu_torture_current,
rcu_torture_current_version,
list_empty(&rcu_torture_freelist),
@@ -941,8 +1077,19 @@ rcu_torture_printk(char *page)
atomic_read(&n_rcu_torture_alloc_fail),
atomic_read(&n_rcu_torture_free),
atomic_read(&n_rcu_torture_mberror),
+ n_rcu_torture_boost_ktrerror,
+ n_rcu_torture_boost_rterror,
+ n_rcu_torture_boost_allocerror,
+ n_rcu_torture_boost_afferror,
+ n_rcu_torture_boost_failure,
+ n_rcu_torture_boosts,
n_rcu_torture_timers);
- if (atomic_read(&n_rcu_torture_mberror) != 0)
+ if (atomic_read(&n_rcu_torture_mberror) != 0 ||
+ n_rcu_torture_boost_ktrerror != 0 ||
+ n_rcu_torture_boost_rterror != 0 ||
+ n_rcu_torture_boost_allocerror != 0 ||
+ n_rcu_torture_boost_afferror != 0 ||
+ n_rcu_torture_boost_failure != 0)
cnt += sprintf(&page[cnt], " !!!");
cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
if (i > 1) {
@@ -1094,22 +1241,91 @@ rcu_torture_stutter(void *arg)
}
static inline void
-rcu_torture_print_module_parms(char *tag)
+rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag)
{
printk(KERN_ALERT "%s" TORTURE_FLAG
"--- %s: nreaders=%d nfakewriters=%d "
"stat_interval=%d verbose=%d test_no_idle_hz=%d "
"shuffle_interval=%d stutter=%d irqreader=%d "
- "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d\n",
+ "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
+ "test_boost=%d/%d test_boost_interval=%d "
+ "test_boost_duration=%d\n",
torture_type, tag, nrealreaders, nfakewriters,
stat_interval, verbose, test_no_idle_hz, shuffle_interval,
- stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter);
+ stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
+ test_boost, cur_ops->can_boost,
+ test_boost_interval, test_boost_duration);
}
-static struct notifier_block rcutorture_nb = {
+static struct notifier_block rcutorture_shutdown_nb = {
.notifier_call = rcutorture_shutdown_notify,
};
+static void rcutorture_booster_cleanup(int cpu)
+{
+ struct task_struct *t;
+
+ if (boost_tasks[cpu] == NULL)
+ return;
+ mutex_lock(&boost_mutex);
+ VERBOSE_PRINTK_STRING("Stopping rcu_torture_boost task");
+ t = boost_tasks[cpu];
+ boost_tasks[cpu] = NULL;
+ mutex_unlock(&boost_mutex);
+
+ /* This must be outside of the mutex, otherwise deadlock! */
+ kthread_stop(t);
+}
+
+static int rcutorture_booster_init(int cpu)
+{
+ int retval;
+
+ if (boost_tasks[cpu] != NULL)
+ return 0; /* Already created, nothing more to do. */
+
+ /* Don't allow time recalculation while creating a new task. */
+ mutex_lock(&boost_mutex);
+ VERBOSE_PRINTK_STRING("Creating rcu_torture_boost task");
+ boost_tasks[cpu] = kthread_create(rcu_torture_boost, NULL,
+ "rcu_torture_boost");
+ if (IS_ERR(boost_tasks[cpu])) {
+ retval = PTR_ERR(boost_tasks[cpu]);
+ VERBOSE_PRINTK_STRING("rcu_torture_boost task create failed");
+ n_rcu_torture_boost_ktrerror++;
+ boost_tasks[cpu] = NULL;
+ mutex_unlock(&boost_mutex);
+ return retval;
+ }
+ kthread_bind(boost_tasks[cpu], cpu);
+ wake_up_process(boost_tasks[cpu]);
+ mutex_unlock(&boost_mutex);
+ return 0;
+}
+
+static int rcutorture_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ long cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_ONLINE:
+ case CPU_DOWN_FAILED:
+ (void)rcutorture_booster_init(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ rcutorture_booster_cleanup(cpu);
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block rcutorture_cpu_nb = {
+ .notifier_call = rcutorture_cpu_notify,
+};
+
static void
rcu_torture_cleanup(void)
{
@@ -1127,7 +1343,7 @@ rcu_torture_cleanup(void)
}
fullstop = FULLSTOP_RMMOD;
mutex_unlock(&fullstop_mutex);
- unregister_reboot_notifier(&rcutorture_nb);
+ unregister_reboot_notifier(&rcutorture_shutdown_nb);
if (stutter_task) {
VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
kthread_stop(stutter_task);
@@ -1184,6 +1400,12 @@ rcu_torture_cleanup(void)
kthread_stop(fqs_task);
}
fqs_task = NULL;
+ if ((test_boost == 1 && cur_ops->can_boost) ||
+ test_boost == 2) {
+ unregister_cpu_notifier(&rcutorture_cpu_nb);
+ for_each_possible_cpu(i)
+ rcutorture_booster_cleanup(i);
+ }
/* Wait for all RCU callbacks to fire. */
@@ -1195,9 +1417,9 @@ rcu_torture_cleanup(void)
if (cur_ops->cleanup)
cur_ops->cleanup();
if (atomic_read(&n_rcu_torture_error))
- rcu_torture_print_module_parms("End of test: FAILURE");
+ rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE");
else
- rcu_torture_print_module_parms("End of test: SUCCESS");
+ rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
}
static int __init
@@ -1242,7 +1464,7 @@ rcu_torture_init(void)
nrealreaders = nreaders;
else
nrealreaders = 2 * num_online_cpus();
- rcu_torture_print_module_parms("Start of test");
+ rcu_torture_print_module_parms(cur_ops, "Start of test");
fullstop = FULLSTOP_DONTSTOP;
/* Set up the freelist. */
@@ -1263,6 +1485,12 @@ rcu_torture_init(void)
atomic_set(&n_rcu_torture_free, 0);
atomic_set(&n_rcu_torture_mberror, 0);
atomic_set(&n_rcu_torture_error, 0);
+ n_rcu_torture_boost_ktrerror = 0;
+ n_rcu_torture_boost_rterror = 0;
+ n_rcu_torture_boost_allocerror = 0;
+ n_rcu_torture_boost_afferror = 0;
+ n_rcu_torture_boost_failure = 0;
+ n_rcu_torture_boosts = 0;
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
atomic_set(&rcu_torture_wcount[i], 0);
for_each_possible_cpu(cpu) {
@@ -1376,7 +1604,27 @@ rcu_torture_init(void)
goto unwind;
}
}
- register_reboot_notifier(&rcutorture_nb);
+ if (test_boost_interval < 1)
+ test_boost_interval = 1;
+ if (test_boost_duration < 2)
+ test_boost_duration = 2;
+ if ((test_boost == 1 && cur_ops->can_boost) ||
+ test_boost == 2) {
+ int retval;
+
+ boost_starttime = jiffies + test_boost_interval * HZ;
+ register_cpu_notifier(&rcutorture_cpu_nb);
+ for_each_possible_cpu(i) {
+ if (cpu_is_offline(i))
+ continue; /* Heuristic: CPU can go offline. */
+ retval = rcutorture_booster_init(i);
+ if (retval < 0) {
+ firsterr = retval;
+ goto unwind;
+ }
+ }
+ }
+ register_reboot_notifier(&rcutorture_shutdown_nb);
mutex_unlock(&fullstop_mutex);
return 0;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index ccdc04c47981..d0ddfea6579d 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -67,9 +67,6 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
.gpnum = -300, \
.completed = -300, \
.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname.onofflock), \
- .orphan_cbs_list = NULL, \
- .orphan_cbs_tail = &structname.orphan_cbs_list, \
- .orphan_qlen = 0, \
.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname.fqslock), \
.n_force_qs = 0, \
.n_force_qs_ngp = 0, \
@@ -620,9 +617,17 @@ static void __init check_cpu_stall_init(void)
static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
{
if (rdp->gpnum != rnp->gpnum) {
- rdp->qs_pending = 1;
- rdp->passed_quiesc = 0;
+ /*
+ * If the current grace period is waiting for this CPU,
+ * set up to detect a quiescent state, otherwise don't
+ * go looking for one.
+ */
rdp->gpnum = rnp->gpnum;
+ if (rnp->qsmask & rdp->grpmask) {
+ rdp->qs_pending = 1;
+ rdp->passed_quiesc = 0;
+ } else
+ rdp->qs_pending = 0;
}
}
@@ -681,6 +686,24 @@ __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat
/* Remember that we saw this grace-period completion. */
rdp->completed = rnp->completed;
+
+ /*
+ * If we were in an extended quiescent state, we may have
+ * missed some grace periods that others CPUs handled on
+ * our behalf. Catch up with this state to avoid noting
+ * spurious new grace periods. If another grace period
+ * has started, then rnp->gpnum will have advanced, so
+ * we will detect this later on.
+ */
+ if (ULONG_CMP_LT(rdp->gpnum, rdp->completed))
+ rdp->gpnum = rdp->completed;
+
+ /*
+ * If RCU does not need a quiescent state from this CPU,
+ * then make sure that this CPU doesn't go looking for one.
+ */
+ if ((rnp->qsmask & rdp->grpmask) == 0)
+ rdp->qs_pending = 0;
}
}
@@ -984,53 +1007,31 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
#ifdef CONFIG_HOTPLUG_CPU
/*
- * Move a dying CPU's RCU callbacks to the ->orphan_cbs_list for the
- * specified flavor of RCU. The callbacks will be adopted by the next
- * _rcu_barrier() invocation or by the CPU_DEAD notifier, whichever
- * comes first. Because this is invoked from the CPU_DYING notifier,
- * irqs are already disabled.
+ * Move a dying CPU's RCU callbacks to online CPU's callback list.
+ * Synchronization is not required because this function executes
+ * in stop_machine() context.
*/
-static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
+static void rcu_send_cbs_to_online(struct rcu_state *rsp)
{
int i;
+ /* current DYING CPU is cleared in the cpu_online_mask */
+ int receive_cpu = cpumask_any(cpu_online_mask);
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
+ struct rcu_data *receive_rdp = per_cpu_ptr(rsp->rda, receive_cpu);
if (rdp->nxtlist == NULL)
return; /* irqs disabled, so comparison is stable. */
- raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */
- *rsp->orphan_cbs_tail = rdp->nxtlist;
- rsp->orphan_cbs_tail = rdp->nxttail[RCU_NEXT_TAIL];
+
+ *receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist;
+ receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+ receive_rdp->qlen += rdp->qlen;
+ receive_rdp->n_cbs_adopted += rdp->qlen;
+ rdp->n_cbs_orphaned += rdp->qlen;
+
rdp->nxtlist = NULL;
for (i = 0; i < RCU_NEXT_SIZE; i++)
rdp->nxttail[i] = &rdp->nxtlist;
- rsp->orphan_qlen += rdp->qlen;
- rdp->n_cbs_orphaned += rdp->qlen;
rdp->qlen = 0;
- raw_spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
-}
-
-/*
- * Adopt previously orphaned RCU callbacks.
- */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
-{
- unsigned long flags;
- struct rcu_data *rdp;
-
- raw_spin_lock_irqsave(&rsp->onofflock, flags);
- rdp = this_cpu_ptr(rsp->rda);
- if (rsp->orphan_cbs_list == NULL) {
- raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
- return;
- }
- *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list;
- rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_tail;
- rdp->qlen += rsp->orphan_qlen;
- rdp->n_cbs_adopted += rsp->orphan_qlen;
- rsp->orphan_cbs_list = NULL;
- rsp->orphan_cbs_tail = &rsp->orphan_cbs_list;
- rsp->orphan_qlen = 0;
- raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
}
/*
@@ -1081,8 +1082,6 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
raw_spin_unlock_irqrestore(&rnp->lock, flags);
if (need_report & RCU_OFL_TASKS_EXP_GP)
rcu_report_exp_rnp(rsp, rnp);
-
- rcu_adopt_orphan_cbs(rsp);
}
/*
@@ -1100,11 +1099,7 @@ static void rcu_offline_cpu(int cpu)
#else /* #ifdef CONFIG_HOTPLUG_CPU */
-static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
-{
-}
-
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_send_cbs_to_online(struct rcu_state *rsp)
{
}
@@ -1440,22 +1435,11 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
*/
local_irq_save(flags);
rdp = this_cpu_ptr(rsp->rda);
- rcu_process_gp_end(rsp, rdp);
- check_for_new_grace_period(rsp, rdp);
/* Add the callback to our list. */
*rdp->nxttail[RCU_NEXT_TAIL] = head;
rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
- /* Start a new grace period if one not already started. */
- if (!rcu_gp_in_progress(rsp)) {
- unsigned long nestflag;
- struct rcu_node *rnp_root = rcu_get_root(rsp);
-
- raw_spin_lock_irqsave(&rnp_root->lock, nestflag);
- rcu_start_gp(rsp, nestflag); /* releases rnp_root->lock. */
- }
-
/*
* Force the grace period if too many callbacks or too long waiting.
* Enforce hysteresis, and don't invoke force_quiescent_state()
@@ -1464,12 +1448,27 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
* is the only one waiting for a grace period to complete.
*/
if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
- rdp->blimit = LONG_MAX;
- if (rsp->n_force_qs == rdp->n_force_qs_snap &&
- *rdp->nxttail[RCU_DONE_TAIL] != head)
- force_quiescent_state(rsp, 0);
- rdp->n_force_qs_snap = rsp->n_force_qs;
- rdp->qlen_last_fqs_check = rdp->qlen;
+
+ /* Are we ignoring a completed grace period? */
+ rcu_process_gp_end(rsp, rdp);
+ check_for_new_grace_period(rsp, rdp);
+
+ /* Start a new grace period if one not already started. */
+ if (!rcu_gp_in_progress(rsp)) {
+ unsigned long nestflag;
+ struct rcu_node *rnp_root = rcu_get_root(rsp);
+
+ raw_spin_lock_irqsave(&rnp_root->lock, nestflag);
+ rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */
+ } else {
+ /* Give the grace period a kick. */
+ rdp->blimit = LONG_MAX;
+ if (rsp->n_force_qs == rdp->n_force_qs_snap &&
+ *rdp->nxttail[RCU_DONE_TAIL] != head)
+ force_quiescent_state(rsp, 0);
+ rdp->n_force_qs_snap = rsp->n_force_qs;
+ rdp->qlen_last_fqs_check = rdp->qlen;
+ }
} else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies))
force_quiescent_state(rsp, 1);
local_irq_restore(flags);
@@ -1699,13 +1698,12 @@ static void _rcu_barrier(struct rcu_state *rsp,
* decrement rcu_barrier_cpu_count -- otherwise the first CPU
* might complete its grace period before all of the other CPUs
* did their increment, causing this function to return too
- * early.
+ * early. Note that on_each_cpu() disables irqs, which prevents
+ * any CPUs from coming online or going offline until each online
+ * CPU has queued its RCU-barrier callback.
*/
atomic_set(&rcu_barrier_cpu_count, 1);
- preempt_disable(); /* stop CPU_DYING from filling orphan_cbs_list */
- rcu_adopt_orphan_cbs(rsp);
on_each_cpu(rcu_barrier_func, (void *)call_rcu_func, 1);
- preempt_enable(); /* CPU_DYING can again fill orphan_cbs_list */
if (atomic_dec_and_test(&rcu_barrier_cpu_count))
complete(&rcu_barrier_completion);
wait_for_completion(&rcu_barrier_completion);
@@ -1831,18 +1829,13 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
case CPU_DYING:
case CPU_DYING_FROZEN:
/*
- * preempt_disable() in _rcu_barrier() prevents stop_machine(),
- * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
- * returns, all online cpus have queued rcu_barrier_func().
- * The dying CPU clears its cpu_online_mask bit and
- * moves all of its RCU callbacks to ->orphan_cbs_list
- * in the context of stop_machine(), so subsequent calls
- * to _rcu_barrier() will adopt these callbacks and only
- * then queue rcu_barrier_func() on all remaining CPUs.
+ * The whole machine is "stopped" except this CPU, so we can
+ * touch any data without introducing corruption. We send the
+ * dying CPU's callbacks to an arbitrarily chosen online CPU.
*/
- rcu_send_cbs_to_orphanage(&rcu_bh_state);
- rcu_send_cbs_to_orphanage(&rcu_sched_state);
- rcu_preempt_send_cbs_to_orphanage();
+ rcu_send_cbs_to_online(&rcu_bh_state);
+ rcu_send_cbs_to_online(&rcu_sched_state);
+ rcu_preempt_send_cbs_to_online();
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
@@ -1880,8 +1873,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
int i;
- for (i = NUM_RCU_LVLS - 1; i >= 0; i--)
+ for (i = NUM_RCU_LVLS - 1; i > 0; i--)
rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+ rsp->levelspread[0] = RCU_FANOUT_LEAF;
}
#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
static void __init rcu_init_levelspread(struct rcu_state *rsp)
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 91d4170c5c13..e8f057e44e3e 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -31,46 +31,51 @@
/*
* Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
* In theory, it should be possible to add more levels straightforwardly.
- * In practice, this has not been tested, so there is probably some
- * bug somewhere.
+ * In practice, this did work well going from three levels to four.
+ * Of course, your mileage may vary.
*/
#define MAX_RCU_LVLS 4
-#define RCU_FANOUT (CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT)
-#define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT)
-#define RCU_FANOUT_FOURTH (RCU_FANOUT_CUBE * RCU_FANOUT)
-
-#if NR_CPUS <= RCU_FANOUT
+#if CONFIG_RCU_FANOUT > 16
+#define RCU_FANOUT_LEAF 16
+#else /* #if CONFIG_RCU_FANOUT > 16 */
+#define RCU_FANOUT_LEAF (CONFIG_RCU_FANOUT)
+#endif /* #else #if CONFIG_RCU_FANOUT > 16 */
+#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
+
+#if NR_CPUS <= RCU_FANOUT_1
# define NUM_RCU_LVLS 1
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 (NR_CPUS)
# define NUM_RCU_LVL_2 0
# define NUM_RCU_LVL_3 0
# define NUM_RCU_LVL_4 0
-#elif NR_CPUS <= RCU_FANOUT_SQ
+#elif NR_CPUS <= RCU_FANOUT_2
# define NUM_RCU_LVLS 2
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_LVL_2 (NR_CPUS)
# define NUM_RCU_LVL_3 0
# define NUM_RCU_LVL_4 0
-#elif NR_CPUS <= RCU_FANOUT_CUBE
+#elif NR_CPUS <= RCU_FANOUT_3
# define NUM_RCU_LVLS 3
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
-# define NUM_RCU_LVL_3 NR_CPUS
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+# define NUM_RCU_LVL_3 (NR_CPUS)
# define NUM_RCU_LVL_4 0
-#elif NR_CPUS <= RCU_FANOUT_FOURTH
+#elif NR_CPUS <= RCU_FANOUT_4
# define NUM_RCU_LVLS 4
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
-# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
-# define NUM_RCU_LVL_4 NR_CPUS
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+# define NUM_RCU_LVL_4 (NR_CPUS)
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-#endif /* #if (NR_CPUS) <= RCU_FANOUT */
+#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
@@ -203,8 +208,8 @@ struct rcu_data {
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */
- unsigned long n_cbs_orphaned; /* RCU cbs sent to orphanage. */
- unsigned long n_cbs_adopted; /* RCU cbs adopted from orphanage. */
+ unsigned long n_cbs_orphaned; /* RCU cbs orphaned by dying CPU */
+ unsigned long n_cbs_adopted; /* RCU cbs adopted from dying CPU */
unsigned long n_force_qs_snap;
/* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
@@ -309,15 +314,7 @@ struct rcu_state {
/* End of fields guarded by root rcu_node's lock. */
raw_spinlock_t onofflock; /* exclude on/offline and */
- /* starting new GP. Also */
- /* protects the following */
- /* orphan_cbs fields. */
- struct rcu_head *orphan_cbs_list; /* list of rcu_head structs */
- /* orphaned by all CPUs in */
- /* a given leaf rcu_node */
- /* going offline. */
- struct rcu_head **orphan_cbs_tail; /* And tail pointer. */
- long orphan_qlen; /* Number of orphaned cbs. */
+ /* starting new GP. */
raw_spinlock_t fqslock; /* Only one task forcing */
/* quiescent states. */
unsigned long jiffies_force_qs; /* Time at which to invoke */
@@ -390,7 +387,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
static int rcu_preempt_pending(int cpu);
static int rcu_preempt_needs_cpu(int cpu);
static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
-static void rcu_preempt_send_cbs_to_orphanage(void);
+static void rcu_preempt_send_cbs_to_online(void);
static void __init __rcu_init_preempt(void);
static void rcu_needs_cpu_flush(void);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 71a4147473f9..a3638710dc67 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -25,6 +25,7 @@
*/
#include <linux/delay.h>
+#include <linux/stop_machine.h>
/*
* Check the RCU kernel configuration parameters and print informative
@@ -773,11 +774,11 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
}
/*
- * Move preemptable RCU's callbacks to ->orphan_cbs_list.
+ * Move preemptable RCU's callbacks from dying CPU to other online CPU.
*/
-static void rcu_preempt_send_cbs_to_orphanage(void)
+static void rcu_preempt_send_cbs_to_online(void)
{
- rcu_send_cbs_to_orphanage(&rcu_preempt_state);
+ rcu_send_cbs_to_online(&rcu_preempt_state);
}
/*
@@ -1001,7 +1002,7 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
/*
* Because there is no preemptable RCU, there are no callbacks to move.
*/
-static void rcu_preempt_send_cbs_to_orphanage(void)
+static void rcu_preempt_send_cbs_to_online(void)
{
}
@@ -1014,6 +1015,132 @@ static void __init __rcu_init_preempt(void)
#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+#ifndef CONFIG_SMP
+
+void synchronize_sched_expedited(void)
+{
+ cond_resched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#else /* #ifndef CONFIG_SMP */
+
+static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0);
+static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0);
+
+static int synchronize_sched_expedited_cpu_stop(void *data)
+{
+ /*
+ * There must be a full memory barrier on each affected CPU
+ * between the time that try_stop_cpus() is called and the
+ * time that it returns.
+ *
+ * In the current initial implementation of cpu_stop, the
+ * above condition is already met when the control reaches
+ * this point and the following smp_mb() is not strictly
+ * necessary. Do smp_mb() anyway for documentation and
+ * robustness against future implementation changes.
+ */
+ smp_mb(); /* See above comment block. */
+ return 0;
+}
+
+/*
+ * Wait for an rcu-sched grace period to elapse, but use "big hammer"
+ * approach to force grace period to end quickly. This consumes
+ * significant time on all CPUs, and is thus not recommended for
+ * any sort of common-case code.
+ *
+ * Note that it is illegal to call this function while holding any
+ * lock that is acquired by a CPU-hotplug notifier. Failing to
+ * observe this restriction will result in deadlock.
+ *
+ * This implementation can be thought of as an application of ticket
+ * locking to RCU, with sync_sched_expedited_started and
+ * sync_sched_expedited_done taking on the roles of the halves
+ * of the ticket-lock word. Each task atomically increments
+ * sync_sched_expedited_started upon entry, snapshotting the old value,
+ * then attempts to stop all the CPUs. If this succeeds, then each
+ * CPU will have executed a context switch, resulting in an RCU-sched
+ * grace period. We are then done, so we use atomic_cmpxchg() to
+ * update sync_sched_expedited_done to match our snapshot -- but
+ * only if someone else has not already advanced past our snapshot.
+ *
+ * On the other hand, if try_stop_cpus() fails, we check the value
+ * of sync_sched_expedited_done. If it has advanced past our
+ * initial snapshot, then someone else must have forced a grace period
+ * some time after we took our snapshot. In this case, our work is
+ * done for us, and we can simply return. Otherwise, we try again,
+ * but keep our initial snapshot for purposes of checking for someone
+ * doing our work for us.
+ *
+ * If we fail too many times in a row, we fall back to synchronize_sched().
+ */
+void synchronize_sched_expedited(void)
+{
+ int firstsnap, s, snap, trycount = 0;
+
+ /* Note that atomic_inc_return() implies full memory barrier. */
+ firstsnap = snap = atomic_inc_return(&sync_sched_expedited_started);
+ get_online_cpus();
+
+ /*
+ * Each pass through the following loop attempts to force a
+ * context switch on each CPU.
+ */
+ while (try_stop_cpus(cpu_online_mask,
+ synchronize_sched_expedited_cpu_stop,
+ NULL) == -EAGAIN) {
+ put_online_cpus();
+
+ /* No joy, try again later. Or just synchronize_sched(). */
+ if (trycount++ < 10)
+ udelay(trycount * num_online_cpus());
+ else {
+ synchronize_sched();
+ return;
+ }
+
+ /* Check to see if someone else did our work for us. */
+ s = atomic_read(&sync_sched_expedited_done);
+ if (UINT_CMP_GE((unsigned)s, (unsigned)firstsnap)) {
+ smp_mb(); /* ensure test happens before caller kfree */
+ return;
+ }
+
+ /*
+ * Refetching sync_sched_expedited_started allows later
+ * callers to piggyback on our grace period. We subtract
+ * 1 to get the same token that the last incrementer got.
+ * We retry after they started, so our grace period works
+ * for them, and they started after our first try, so their
+ * grace period works for us.
+ */
+ get_online_cpus();
+ snap = atomic_read(&sync_sched_expedited_started) - 1;
+ smp_mb(); /* ensure read is before try_stop_cpus(). */
+ }
+
+ /*
+ * Everyone up to our most recent fetch is covered by our grace
+ * period. Update the counter, but only if our work is still
+ * relevant -- which it won't be if someone who started later
+ * than we did beat us to the punch.
+ */
+ do {
+ s = atomic_read(&sync_sched_expedited_done);
+ if (UINT_CMP_GE((unsigned)s, (unsigned)snap)) {
+ smp_mb(); /* ensure test happens before caller kfree */
+ break;
+ }
+ } while (atomic_cmpxchg(&sync_sched_expedited_done, s, snap) != s);
+
+ put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#endif /* #else #ifndef CONFIG_SMP */
+
#if !defined(CONFIG_RCU_FAST_NO_HZ)
/*
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index d15430b9d122..c8e97853b970 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -166,13 +166,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
gpnum = rsp->gpnum;
seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x "
- "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld\n",
+ "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
rsp->completed, gpnum, rsp->signaled,
(long)(rsp->jiffies_force_qs - jiffies),
(int)(jiffies & 0xffff),
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
- rsp->n_force_qs_lh, rsp->orphan_qlen);
+ rsp->n_force_qs_lh);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
@@ -300,7 +300,7 @@ static const struct file_operations rcu_pending_fops = {
static struct dentry *rcudir;
-static int __init rcuclassic_trace_init(void)
+static int __init rcutree_trace_init(void)
{
struct dentry *retval;
@@ -337,14 +337,14 @@ free_out:
return 1;
}
-static void __exit rcuclassic_trace_cleanup(void)
+static void __exit rcutree_trace_cleanup(void)
{
debugfs_remove_recursive(rcudir);
}
-module_init(rcuclassic_trace_init);
-module_exit(rcuclassic_trace_cleanup);
+module_init(rcutree_trace_init);
+module_exit(rcutree_trace_cleanup);
MODULE_AUTHOR("Paul E. McKenney");
MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation");
diff --git a/kernel/resource.c b/kernel/resource.c
index 9fad33efd0db..798e2fae2a06 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -40,23 +40,6 @@ EXPORT_SYMBOL(iomem_resource);
static DEFINE_RWLOCK(resource_lock);
-/*
- * By default, we allocate free space bottom-up. The architecture can request
- * top-down by clearing this flag. The user can override the architecture's
- * choice with the "resource_alloc_from_bottom" kernel boot option, but that
- * should only be a debugging tool.
- */
-int resource_alloc_from_bottom = 1;
-
-static __init int setup_alloc_from_bottom(char *s)
-{
- printk(KERN_INFO
- "resource: allocating from bottom-up; please report a bug\n");
- resource_alloc_from_bottom = 1;
- return 0;
-}
-early_param("resource_alloc_from_bottom", setup_alloc_from_bottom);
-
static void *r_next(struct seq_file *m, void *v, loff_t *pos)
{
struct resource *p = v;
@@ -374,6 +357,10 @@ int __weak page_is_ram(unsigned long pfn)
return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1;
}
+void __weak arch_remove_reservations(struct resource *avail)
+{
+}
+
static resource_size_t simple_align_resource(void *data,
const struct resource *avail,
resource_size_t size,
@@ -397,74 +384,7 @@ static bool resource_contains(struct resource *res1, struct resource *res2)
}
/*
- * Find the resource before "child" in the sibling list of "root" children.
- */
-static struct resource *find_sibling_prev(struct resource *root, struct resource *child)
-{
- struct resource *this;
-
- for (this = root->child; this; this = this->sibling)
- if (this->sibling == child)
- return this;
-
- return NULL;
-}
-
-/*
* Find empty slot in the resource tree given range and alignment.
- * This version allocates from the end of the root resource first.
- */
-static int find_resource_from_top(struct resource *root, struct resource *new,
- resource_size_t size, resource_size_t min,
- resource_size_t max, resource_size_t align,
- resource_size_t (*alignf)(void *,
- const struct resource *,
- resource_size_t,
- resource_size_t),
- void *alignf_data)
-{
- struct resource *this;
- struct resource tmp, avail, alloc;
-
- tmp.start = root->end;
- tmp.end = root->end;
-
- this = find_sibling_prev(root, NULL);
- for (;;) {
- if (this) {
- if (this->end < root->end)
- tmp.start = this->end + 1;
- } else
- tmp.start = root->start;
-
- resource_clip(&tmp, min, max);
-
- /* Check for overflow after ALIGN() */
- avail = *new;
- avail.start = ALIGN(tmp.start, align);
- avail.end = tmp.end;
- if (avail.start >= tmp.start) {
- alloc.start = alignf(alignf_data, &avail, size, align);
- alloc.end = alloc.start + size - 1;
- if (resource_contains(&avail, &alloc)) {
- new->start = alloc.start;
- new->end = alloc.end;
- return 0;
- }
- }
-
- if (!this || this->start == root->start)
- break;
-
- tmp.end = this->start - 1;
- this = find_sibling_prev(root, this);
- }
- return -EBUSY;
-}
-
-/*
- * Find empty slot in the resource tree given range and alignment.
- * This version allocates from the beginning of the root resource first.
*/
static int find_resource(struct resource *root, struct resource *new,
resource_size_t size, resource_size_t min,
@@ -478,23 +398,24 @@ static int find_resource(struct resource *root, struct resource *new,
struct resource *this = root->child;
struct resource tmp = *new, avail, alloc;
+ tmp.flags = new->flags;
tmp.start = root->start;
/*
- * Skip past an allocated resource that starts at 0, since the
- * assignment of this->start - 1 to tmp->end below would cause an
- * underflow.
+ * Skip past an allocated resource that starts at 0, since the assignment
+ * of this->start - 1 to tmp->end below would cause an underflow.
*/
if (this && this->start == 0) {
tmp.start = this->end + 1;
this = this->sibling;
}
- for (;;) {
+ for(;;) {
if (this)
tmp.end = this->start - 1;
else
tmp.end = root->end;
resource_clip(&tmp, min, max);
+ arch_remove_reservations(&tmp);
/* Check for overflow after ALIGN() */
avail = *new;
@@ -509,10 +430,8 @@ static int find_resource(struct resource *root, struct resource *new,
return 0;
}
}
-
if (!this)
break;
-
tmp.start = this->end + 1;
this = this->sibling;
}
@@ -545,10 +464,7 @@ int allocate_resource(struct resource *root, struct resource *new,
alignf = simple_align_resource;
write_lock(&resource_lock);
- if (resource_alloc_from_bottom)
- err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
- else
- err = find_resource_from_top(root, new, size, min, max, align, alignf, alignf_data);
+ err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
if (err >= 0 && __request_resource(root, new))
err = -EBUSY;
write_unlock(&resource_lock);
diff --git a/kernel/sched.c b/kernel/sched.c
index aa14a56f9d03..e6f8f1254319 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -560,18 +560,8 @@ struct rq {
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-static inline
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
-{
- rq->curr->sched_class->check_preempt_curr(rq, p, flags);
- /*
- * A queue event has occurred, and we're going to schedule. In
- * this case, we can save a useless back to back clock update.
- */
- if (test_tsk_need_resched(p))
- rq->skip_clock_update = 1;
-}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
static inline int cpu_of(struct rq *rq)
{
@@ -646,22 +636,18 @@ static inline struct task_group *task_group(struct task_struct *p)
#endif /* CONFIG_CGROUP_SCHED */
-static u64 irq_time_cpu(int cpu);
-static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+static void update_rq_clock_task(struct rq *rq, s64 delta);
-inline void update_rq_clock(struct rq *rq)
+static void update_rq_clock(struct rq *rq)
{
- if (!rq->skip_clock_update) {
- int cpu = cpu_of(rq);
- u64 irq_time;
+ s64 delta;
- rq->clock = sched_clock_cpu(cpu);
- irq_time = irq_time_cpu(cpu);
- if (rq->clock - irq_time > rq->clock_task)
- rq->clock_task = rq->clock - irq_time;
+ if (rq->skip_clock_update)
+ return;
- sched_irq_time_avg_update(rq, irq_time);
- }
+ delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+ rq->clock += delta;
+ update_rq_clock_task(rq, delta);
}
/*
@@ -1934,10 +1920,9 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
* They are read and saved off onto struct rq in update_rq_clock().
* This may result in other CPU reading this CPU's irq time and can
* race with irq/account_system_vtime on this CPU. We would either get old
- * or new value (or semi updated value on 32 bit) with a side effect of
- * accounting a slice of irq time to wrong task when irq is in progress
- * while we read rq->clock. That is a worthy compromise in place of having
- * locks on each irq in account_system_time.
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
*/
static DEFINE_PER_CPU(u64, cpu_hardirq_time);
static DEFINE_PER_CPU(u64, cpu_softirq_time);
@@ -1955,19 +1940,58 @@ void disable_sched_clock_irqtime(void)
sched_clock_irqtime = 0;
}
-static u64 irq_time_cpu(int cpu)
+#ifndef CONFIG_64BIT
+static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+
+static inline void irq_time_write_begin(void)
{
- if (!sched_clock_irqtime)
- return 0;
+ __this_cpu_inc(irq_time_seq.sequence);
+ smp_wmb();
+}
+
+static inline void irq_time_write_end(void)
+{
+ smp_wmb();
+ __this_cpu_inc(irq_time_seq.sequence);
+}
+static inline u64 irq_time_read(int cpu)
+{
+ u64 irq_time;
+ unsigned seq;
+
+ do {
+ seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+ irq_time = per_cpu(cpu_softirq_time, cpu) +
+ per_cpu(cpu_hardirq_time, cpu);
+ } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
+
+ return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
}
+#endif /* CONFIG_64BIT */
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
void account_system_vtime(struct task_struct *curr)
{
unsigned long flags;
+ s64 delta;
int cpu;
- u64 now, delta;
if (!sched_clock_irqtime)
return;
@@ -1975,9 +1999,10 @@ void account_system_vtime(struct task_struct *curr)
local_irq_save(flags);
cpu = smp_processor_id();
- now = sched_clock_cpu(cpu);
- delta = now - per_cpu(irq_start_time, cpu);
- per_cpu(irq_start_time, cpu) = now;
+ delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+ __this_cpu_add(irq_start_time, delta);
+
+ irq_time_write_begin();
/*
* We do not account for softirq time from ksoftirqd here.
* We want to continue accounting softirq time to ksoftirqd thread
@@ -1985,33 +2010,55 @@ void account_system_vtime(struct task_struct *curr)
* that do not consume any time, but still wants to run.
*/
if (hardirq_count())
- per_cpu(cpu_hardirq_time, cpu) += delta;
+ __this_cpu_add(cpu_hardirq_time, delta);
else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
- per_cpu(cpu_softirq_time, cpu) += delta;
+ __this_cpu_add(cpu_softirq_time, delta);
+ irq_time_write_end();
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(account_system_vtime);
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
{
- if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
- u64 delta_irq = curr_irq_time - rq->prev_irq_time;
- rq->prev_irq_time = curr_irq_time;
- sched_rt_avg_update(rq, delta_irq);
- }
+ s64 irq_delta;
+
+ irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+ /*
+ * Since irq_time is only updated on {soft,}irq_exit, we might run into
+ * this case when a previous update_rq_clock() happened inside a
+ * {soft,}irq region.
+ *
+ * When this happens, we stop ->clock_task and only update the
+ * prev_irq_time stamp to account for the part that fit, so that a next
+ * update will consume the rest. This ensures ->clock_task is
+ * monotonic.
+ *
+ * It does however cause some slight miss-attribution of {soft,}irq
+ * time, a more accurate solution would be to update the irq_time using
+ * the current rq->clock timestamp, except that would require using
+ * atomic ops.
+ */
+ if (irq_delta > delta)
+ irq_delta = delta;
+
+ rq->prev_irq_time += irq_delta;
+ delta -= irq_delta;
+ rq->clock_task += delta;
+
+ if (irq_delta && sched_feat(NONIRQ_POWER))
+ sched_rt_avg_update(rq, irq_delta);
}
-#else
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
-static u64 irq_time_cpu(int cpu)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
{
- return 0;
+ rq->clock_task += delta;
}
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
-
-#endif
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
#include "sched_idletask.c"
#include "sched_fair.c"
@@ -2118,6 +2165,31 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
p->sched_class->prio_changed(rq, p, oldprio, running);
}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+{
+ const struct sched_class *class;
+
+ if (p->sched_class == rq->curr->sched_class) {
+ rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+ } else {
+ for_each_class(class) {
+ if (class == rq->curr->sched_class)
+ break;
+ if (class == p->sched_class) {
+ resched_task(rq->curr);
+ break;
+ }
+ }
+ }
+
+ /*
+ * A queue event has occurred, and we're going to schedule. In
+ * this case, we can save a useless back to back clock update.
+ */
+ if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
+ rq->skip_clock_update = 1;
+}
+
#ifdef CONFIG_SMP
/*
* Is this task likely cache-hot:
@@ -3104,6 +3176,15 @@ static long calc_load_fold_active(struct rq *this_rq)
return delta;
}
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+ load *= exp;
+ load += active * (FIXED_1 - exp);
+ load += 1UL << (FSHIFT - 1);
+ return load >> FSHIFT;
+}
+
#ifdef CONFIG_NO_HZ
/*
* For NO_HZ we delay the active fold to the next LOAD_FREQ update.
@@ -3133,6 +3214,128 @@ static long calc_load_fold_idle(void)
return delta;
}
+
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x: base of the power
+ * @frac_bits: fractional bits of @x
+ * @n: power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
+ */
+static unsigned long
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
+{
+ unsigned long result = 1UL << frac_bits;
+
+ if (n) for (;;) {
+ if (n & 1) {
+ result *= x;
+ result += 1UL << (frac_bits - 1);
+ result >>= frac_bits;
+ }
+ n >>= 1;
+ if (!n)
+ break;
+ x *= x;
+ x += 1UL << (frac_bits - 1);
+ x >>= frac_bits;
+ }
+
+ return result;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ * = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ * ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ * = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ * n 1 - x^(n+1)
+ * S_n := \Sum x^i = -------------
+ * i=0 1 - x
+ */
+static unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+ unsigned long active, unsigned int n)
+{
+
+ return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
+}
+
+/*
+ * NO_HZ can leave us missing all per-cpu ticks calling
+ * calc_load_account_active(), but since an idle CPU folds its delta into
+ * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
+ * in the pending idle delta if our idle period crossed a load cycle boundary.
+ *
+ * Once we've updated the global active value, we need to apply the exponential
+ * weights adjusted to the number of cycles missed.
+ */
+static void calc_global_nohz(unsigned long ticks)
+{
+ long delta, active, n;
+
+ if (time_before(jiffies, calc_load_update))
+ return;
+
+ /*
+ * If we crossed a calc_load_update boundary, make sure to fold
+ * any pending idle changes, the respective CPUs might have
+ * missed the tick driven calc_load_account_active() update
+ * due to NO_HZ.
+ */
+ delta = calc_load_fold_idle();
+ if (delta)
+ atomic_long_add(delta, &calc_load_tasks);
+
+ /*
+ * If we were idle for multiple load cycles, apply them.
+ */
+ if (ticks >= LOAD_FREQ) {
+ n = ticks / LOAD_FREQ;
+
+ active = atomic_long_read(&calc_load_tasks);
+ active = active > 0 ? active * FIXED_1 : 0;
+
+ avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+ avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+ avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+
+ calc_load_update += n * LOAD_FREQ;
+ }
+
+ /*
+ * Its possible the remainder of the above division also crosses
+ * a LOAD_FREQ period, the regular check in calc_global_load()
+ * which comes after this will take care of that.
+ *
+ * Consider us being 11 ticks before a cycle completion, and us
+ * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
+ * age us 4 cycles, and the test in calc_global_load() will
+ * pick up the final one.
+ */
+}
#else
static void calc_load_account_idle(struct rq *this_rq)
{
@@ -3142,6 +3345,10 @@ static inline long calc_load_fold_idle(void)
{
return 0;
}
+
+static void calc_global_nohz(unsigned long ticks)
+{
+}
#endif
/**
@@ -3159,24 +3366,17 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
loads[2] = (avenrun[2] + offset) << shift;
}
-static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
-{
- load *= exp;
- load += active * (FIXED_1 - exp);
- return load >> FSHIFT;
-}
-
/*
* calc_load - update the avenrun load estimates 10 ticks after the
* CPUs have updated calc_load_tasks.
*/
-void calc_global_load(void)
+void calc_global_load(unsigned long ticks)
{
- unsigned long upd = calc_load_update + 10;
long active;
- if (time_before(jiffies, upd))
+ calc_global_nohz(ticks);
+
+ if (time_before(jiffies, calc_load_update + 10))
return;
active = atomic_long_read(&calc_load_tasks);
@@ -3830,7 +4030,6 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev)
{
if (prev->se.on_rq)
update_rq_clock(rq);
- rq->skip_clock_update = 0;
prev->sched_class->put_prev_task(rq, prev);
}
@@ -3888,7 +4087,6 @@ need_resched_nonpreemptible:
hrtick_clear(rq);
raw_spin_lock_irq(&rq->lock);
- clear_tsk_need_resched(prev);
switch_count = &prev->nivcsw;
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
@@ -3920,6 +4118,8 @@ need_resched_nonpreemptible:
put_prev_task(rq, prev);
next = pick_next_task(rq);
+ clear_tsk_need_resched(prev);
+ rq->skip_clock_update = 0;
if (likely(prev != next)) {
sched_info_switch(prev, next);
@@ -6960,6 +7160,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
if (cpu != group_first_cpu(sd->groups))
return;
+ sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
+
child = sd->child;
sd->groups->cpu_power = 0;
@@ -9332,72 +9534,3 @@ struct cgroup_subsys cpuacct_subsys = {
};
#endif /* CONFIG_CGROUP_CPUACCT */
-#ifndef CONFIG_SMP
-
-void synchronize_sched_expedited(void)
-{
- barrier();
-}
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
-
-#else /* #ifndef CONFIG_SMP */
-
-static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
-
-static int synchronize_sched_expedited_cpu_stop(void *data)
-{
- /*
- * There must be a full memory barrier on each affected CPU
- * between the time that try_stop_cpus() is called and the
- * time that it returns.
- *
- * In the current initial implementation of cpu_stop, the
- * above condition is already met when the control reaches
- * this point and the following smp_mb() is not strictly
- * necessary. Do smp_mb() anyway for documentation and
- * robustness against future implementation changes.
- */
- smp_mb(); /* See above comment block. */
- return 0;
-}
-
-/*
- * Wait for an rcu-sched grace period to elapse, but use "big hammer"
- * approach to force grace period to end quickly. This consumes
- * significant time on all CPUs, and is thus not recommended for
- * any sort of common-case code.
- *
- * Note that it is illegal to call this function while holding any
- * lock that is acquired by a CPU-hotplug notifier. Failing to
- * observe this restriction will result in deadlock.
- */
-void synchronize_sched_expedited(void)
-{
- int snap, trycount = 0;
-
- smp_mb(); /* ensure prior mod happens before capturing snap. */
- snap = atomic_read(&synchronize_sched_expedited_count) + 1;
- get_online_cpus();
- while (try_stop_cpus(cpu_online_mask,
- synchronize_sched_expedited_cpu_stop,
- NULL) == -EAGAIN) {
- put_online_cpus();
- if (trycount++ < 10)
- udelay(trycount * num_online_cpus());
- else {
- synchronize_sched();
- return;
- }
- if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) {
- smp_mb(); /* ensure test happens before caller kfree */
- return;
- }
- get_online_cpus();
- }
- atomic_inc(&synchronize_sched_expedited_count);
- smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */
- put_online_cpus();
-}
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
-
-#endif /* #else #ifndef CONFIG_SMP */
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index f4f6a8326dd0..00ebd7686676 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1654,12 +1654,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
int scale = cfs_rq->nr_running >= sched_nr_latency;
- if (unlikely(rt_prio(p->prio)))
- goto preempt;
-
- if (unlikely(p->sched_class != &fair_sched_class))
- return;
-
if (unlikely(se == pse))
return;
@@ -1764,10 +1758,6 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
set_task_cpu(p, this_cpu);
activate_task(this_rq, p, 0);
check_preempt_curr(this_rq, p, 0);
-
- /* re-arm NEWIDLE balancing when moving tasks */
- src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
- this_rq->idle_stamp = 0;
}
/*
@@ -2035,13 +2025,16 @@ struct sd_lb_stats {
unsigned long this_load_per_task;
unsigned long this_nr_running;
unsigned long this_has_capacity;
+ unsigned int this_idle_cpus;
/* Statistics of the busiest group */
+ unsigned int busiest_idle_cpus;
unsigned long max_load;
unsigned long busiest_load_per_task;
unsigned long busiest_nr_running;
unsigned long busiest_group_capacity;
unsigned long busiest_has_capacity;
+ unsigned int busiest_group_weight;
int group_imb; /* Is there imbalance in this sd */
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2063,6 +2056,8 @@ struct sg_lb_stats {
unsigned long sum_nr_running; /* Nr tasks running in the group */
unsigned long sum_weighted_load; /* Weighted load of group's tasks */
unsigned long group_capacity;
+ unsigned long idle_cpus;
+ unsigned long group_weight;
int group_imb; /* Is there an imbalance in the group ? */
int group_has_capacity; /* Is there extra capacity in the group? */
};
@@ -2431,7 +2426,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
sgs->group_load += load;
sgs->sum_nr_running += rq->nr_running;
sgs->sum_weighted_load += weighted_cpuload(i);
-
+ if (idle_cpu(i))
+ sgs->idle_cpus++;
}
/*
@@ -2469,6 +2465,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
if (!sgs->group_capacity)
sgs->group_capacity = fix_small_capacity(sd, group);
+ sgs->group_weight = group->group_weight;
if (sgs->group_capacity > sgs->sum_nr_running)
sgs->group_has_capacity = 1;
@@ -2576,13 +2573,16 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
sds->this_nr_running = sgs.sum_nr_running;
sds->this_load_per_task = sgs.sum_weighted_load;
sds->this_has_capacity = sgs.group_has_capacity;
+ sds->this_idle_cpus = sgs.idle_cpus;
} else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
sds->max_load = sgs.avg_load;
sds->busiest = sg;
sds->busiest_nr_running = sgs.sum_nr_running;
+ sds->busiest_idle_cpus = sgs.idle_cpus;
sds->busiest_group_capacity = sgs.group_capacity;
sds->busiest_load_per_task = sgs.sum_weighted_load;
sds->busiest_has_capacity = sgs.group_has_capacity;
+ sds->busiest_group_weight = sgs.group_weight;
sds->group_imb = sgs.group_imb;
}
@@ -2860,8 +2860,26 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
if (sds.this_load >= sds.avg_load)
goto out_balanced;
- if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
- goto out_balanced;
+ /*
+ * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
+ * And to check for busy balance use !idle_cpu instead of
+ * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
+ * even when they are idle.
+ */
+ if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
+ if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+ goto out_balanced;
+ } else {
+ /*
+ * This cpu is idle. If the busiest group load doesn't
+ * have more tasks than the number of available cpu's and
+ * there is no imbalance between this and busiest group
+ * wrt to idle cpu's, it is balanced.
+ */
+ if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
+ sds.busiest_nr_running <= sds.busiest_group_weight)
+ goto out_balanced;
+ }
force_balance:
/* Looks like there is an imbalance. Compute it */
@@ -3197,8 +3215,10 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
next_balance = sd->last_balance + interval;
- if (pulled_task)
+ if (pulled_task) {
+ this_rq->idle_stamp = 0;
break;
+ }
}
raw_spin_lock(&this_rq->lock);
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 45bddc0c1048..2bf6b47058c1 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -19,14 +19,14 @@ select_task_rq_stop(struct rq *rq, struct task_struct *p,
static void
check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
{
- resched_task(rq->curr); /* we preempt everything */
+ /* we're never preempted */
}
static struct task_struct *pick_next_task_stop(struct rq *rq)
{
struct task_struct *stop = rq->stop;
- if (stop && stop->state == TASK_RUNNING)
+ if (stop && stop->se.on_rq)
return stop;
return NULL;
diff --git a/kernel/srcu.c b/kernel/srcu.c
index c71e07500536..98d8c1e80edb 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -31,6 +31,7 @@
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/smp.h>
+#include <linux/delay.h>
#include <linux/srcu.h>
static int init_srcu_struct_fields(struct srcu_struct *sp)
@@ -203,9 +204,14 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
* all srcu_read_lock() calls using the old counters have completed.
* Their corresponding critical sections might well be still
* executing, but the srcu_read_lock() primitives themselves
- * will have finished executing.
+ * will have finished executing. We initially give readers
+ * an arbitrarily chosen 10 microseconds to get out of their
+ * SRCU read-side critical sections, then loop waiting 1/HZ
+ * seconds per iteration.
*/
+ if (srcu_readers_active_idx(sp, idx))
+ udelay(CONFIG_SRCU_SYNCHRONIZE_DELAY);
while (srcu_readers_active_idx(sp, idx))
schedule_timeout_interruptible(1);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c33a1edb799f..5abfa1518554 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -702,6 +702,15 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &ten_thousand,
},
+ {
+ .procname = "dmesg_restrict",
+ .data = &dmesg_restrict,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
#endif
{
.procname = "ngroups_max",
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index c8231fb15708..3308fd7f1b52 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -349,25 +349,47 @@ static int parse(struct nlattr *na, struct cpumask *mask)
return ret;
}
+#ifdef CONFIG_IA64
+#define TASKSTATS_NEEDS_PADDING 1
+#endif
+
static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
{
struct nlattr *na, *ret;
int aggr;
- /* If we don't pad, we end up with alignment on a 4 byte boundary.
- * This causes lots of runtime warnings on systems requiring 8 byte
- * alignment */
- u32 pids[2] = { pid, 0 };
- int pid_size = ALIGN(sizeof(pid), sizeof(long));
-
aggr = (type == TASKSTATS_TYPE_PID)
? TASKSTATS_TYPE_AGGR_PID
: TASKSTATS_TYPE_AGGR_TGID;
+ /*
+ * The taskstats structure is internally aligned on 8 byte
+ * boundaries but the layout of the aggregrate reply, with
+ * two NLA headers and the pid (each 4 bytes), actually
+ * force the entire structure to be unaligned. This causes
+ * the kernel to issue unaligned access warnings on some
+ * architectures like ia64. Unfortunately, some software out there
+ * doesn't properly unroll the NLA packet and assumes that the start
+ * of the taskstats structure will always be 20 bytes from the start
+ * of the netlink payload. Aligning the start of the taskstats
+ * structure breaks this software, which we don't want. So, for now
+ * the alignment only happens on architectures that require it
+ * and those users will have to update to fixed versions of those
+ * packages. Space is reserved in the packet only when needed.
+ * This ifdef should be removed in several years e.g. 2012 once
+ * we can be confident that fixed versions are installed on most
+ * systems. We add the padding before the aggregate since the
+ * aggregate is already a defined type.
+ */
+#ifdef TASKSTATS_NEEDS_PADDING
+ if (nla_put(skb, TASKSTATS_TYPE_NULL, 0, NULL) < 0)
+ goto err;
+#endif
na = nla_nest_start(skb, aggr);
if (!na)
goto err;
- if (nla_put(skb, type, pid_size, pids) < 0)
+
+ if (nla_put(skb, type, sizeof(pid), &pid) < 0)
goto err;
ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats));
if (!ret)
@@ -456,6 +478,18 @@ out:
return rc;
}
+static size_t taskstats_packet_size(void)
+{
+ size_t size;
+
+ size = nla_total_size(sizeof(u32)) +
+ nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+#ifdef TASKSTATS_NEEDS_PADDING
+ size += nla_total_size(0); /* Padding for alignment */
+#endif
+ return size;
+}
+
static int cmd_attr_pid(struct genl_info *info)
{
struct taskstats *stats;
@@ -464,8 +498,7 @@ static int cmd_attr_pid(struct genl_info *info)
u32 pid;
int rc;
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
@@ -494,8 +527,7 @@ static int cmd_attr_tgid(struct genl_info *info)
u32 tgid;
int rc;
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
@@ -570,8 +602,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
/*
* Size includes space for nested attributes
*/
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
is_thread_group = !!taskstats_tgid_alloc(tsk);
if (is_thread_group) {
diff --git a/kernel/timer.c b/kernel/timer.c
index 68a9ae7679b7..353b9227c2ec 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1252,6 +1252,12 @@ unsigned long get_next_timer_interrupt(unsigned long now)
struct tvec_base *base = __get_cpu_var(tvec_bases);
unsigned long expires;
+ /*
+ * Pretend that there is no timer pending if the cpu is offline.
+ * Possible pending timers will be migrated later to an active cpu.
+ */
+ if (cpu_is_offline(smp_processor_id()))
+ return now + NEXT_TIMER_MAX_DELTA;
spin_lock(&base->lock);
if (time_before_eq(base->next_timer, base->timer_jiffies))
base->next_timer = __next_timer_interrupt(base);
@@ -1319,7 +1325,7 @@ void do_timer(unsigned long ticks)
{
jiffies_64 += ticks;
update_wall_time();
- calc_global_load();
+ calc_global_load(ticks);
}
#ifdef __ARCH_WANT_SYS_ALARM
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e04b8bcdef88..ea37e2ff4164 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -126,7 +126,7 @@ if FTRACE
config FUNCTION_TRACER
bool "Kernel Function Tracer"
depends on HAVE_FUNCTION_TRACER
- select FRAME_POINTER if (!ARM_UNWIND)
+ select FRAME_POINTER if !ARM_UNWIND && !S390
select KALLSYMS
select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index bc251ed66724..7b8ec0281548 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -168,7 +168,6 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
BLK_TC_ACT(BLK_TC_WRITE) };
-#define BLK_TC_HARDBARRIER BLK_TC_BARRIER
#define BLK_TC_RAHEAD BLK_TC_AHEAD
/* The ilog2() calls fall out because they're constant */
@@ -196,7 +195,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
return;
what |= ddir_act[rw & WRITE];
- what |= MASK_TC_BIT(rw, HARDBARRIER);
what |= MASK_TC_BIT(rw, SYNC);
what |= MASK_TC_BIT(rw, RAHEAD);
what |= MASK_TC_BIT(rw, META);
@@ -1807,8 +1805,6 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
if (rw & REQ_RAHEAD)
rwbs[i++] = 'A';
- if (rw & REQ_HARDBARRIER)
- rwbs[i++] = 'B';
if (rw & REQ_SYNC)
rwbs[i++] = 'S';
if (rw & REQ_META)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9ed509a015d8..bd1c35a4fbcc 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3853,6 +3853,13 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
/* Need to copy one event at a time */
do {
+ /* We need the size of one event, because
+ * rb_advance_reader only advances by one event,
+ * whereas rb_event_ts_length may include the size of
+ * one or two events.
+ * We have already ensured there's enough space if this
+ * is a time extend. */
+ size = rb_event_length(event);
memcpy(bpage->data + pos, rpage->data + rpos, size);
len -= size;
@@ -3867,7 +3874,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
event = rb_reader_event(cpu_buffer);
/* Always keep the time extend and data together */
size = rb_event_ts_length(event);
- } while (len > size);
+ } while (len >= size);
/* update bpage */
local_set(&bpage->commit, pos);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82d9b8106cd0..f8cf959bad45 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,7 +17,6 @@
#include <linux/writeback.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
-#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
@@ -1284,6 +1283,8 @@ void trace_dump_stack(void)
__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
}
+static DEFINE_PER_CPU(int, user_stack_count);
+
void
ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
{
@@ -1302,6 +1303,18 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
if (unlikely(in_nmi()))
return;
+ /*
+ * prevent recursion, since the user stack tracing may
+ * trigger other kernel events.
+ */
+ preempt_disable();
+ if (__this_cpu_read(user_stack_count))
+ goto out;
+
+ __this_cpu_inc(user_stack_count);
+
+
+
event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
sizeof(*entry), flags, pc);
if (!event)
@@ -1319,6 +1332,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
save_stack_trace_user(&trace);
if (!filter_check_discard(call, entry, buffer, event))
ring_buffer_unlock_commit(buffer, event);
+
+ __this_cpu_dec(user_stack_count);
+
+ out:
+ preempt_enable();
}
#ifdef UNUSED
@@ -2320,11 +2338,19 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
return count;
}
+static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+{
+ if (file->f_mode & FMODE_READ)
+ return seq_lseek(file, offset, origin);
+ else
+ return 0;
+}
+
static const struct file_operations tracing_fops = {
.open = tracing_open,
.read = seq_read,
.write = tracing_write_stub,
- .llseek = seq_lseek,
+ .llseek = tracing_seek,
.release = tracing_release,
};
diff --git a/kernel/user.c b/kernel/user.c
index 2c7d8d5914b1..5c598ca781df 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -158,6 +158,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
spin_lock_irq(&uidhash_lock);
up = uid_hash_find(uid, hashent);
if (up) {
+ put_user_ns(ns);
key_put(new->uid_keyring);
key_put(new->session_keyring);
kmem_cache_free(uid_cachep, new);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6e3c41a4024c..5b082156cd21 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -364,7 +364,8 @@ static int watchdog_nmi_enable(int cpu)
goto out_save;
}
- printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event);
+ printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n",
+ cpu, PTR_ERR(event));
return PTR_ERR(event);
/* success path */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 90db1bd1a978..e785b0f2aea5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -661,7 +661,7 @@ void wq_worker_waking_up(struct task_struct *task, unsigned int cpu)
{
struct worker *worker = kthread_data(task);
- if (likely(!(worker->flags & WORKER_NOT_RUNNING)))
+ if (!(worker->flags & WORKER_NOT_RUNNING))
atomic_inc(get_gcwq_nr_running(cpu));
}
@@ -687,7 +687,7 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task,
struct global_cwq *gcwq = get_gcwq(cpu);
atomic_t *nr_running = get_gcwq_nr_running(cpu);
- if (unlikely(worker->flags & WORKER_NOT_RUNNING))
+ if (worker->flags & WORKER_NOT_RUNNING)
return NULL;
/* this can only happen on the local cpu */
@@ -3692,7 +3692,8 @@ static int __init init_workqueues(void)
system_nrt_wq = alloc_workqueue("events_nrt", WQ_NON_REENTRANT, 0);
system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
WQ_UNBOUND_MAX_ACTIVE);
- BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq);
+ BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq ||
+ !system_unbound_wq);
return 0;
}
early_initcall(init_workqueues);