Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	include/net/ipip.h

The changes made to ipip.h in 'net' were already included
in 'net-next' before that header was moved to another location.

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 161 insertions, 93 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index b0cd86501c30..59412d037eed 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4434,12 +4434,15 @@ static void perf_event_task_event(struct perf_task_event *task_event)
                         if (ctxn < 0)
                                 goto next;
                         ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+                        if (ctx)
+                                perf_event_task_ctx(ctx, task_event);
                 }
-                if (ctx)
-                        perf_event_task_ctx(ctx, task_event);
 next:
                 put_cpu_ptr(pmu->pmu_cpu_context);
         }
+        if (task_event->task_ctx)
+                perf_event_task_ctx(task_event->task_ctx, task_event);
+
         rcu_read_unlock();
 }
 
@@ -5647,6 +5650,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
                 event->attr.sample_period = NSEC_PER_SEC / freq;
                 hwc->sample_period = event->attr.sample_period;
                 local64_set(&hwc->period_left, hwc->sample_period);
+                hwc->last_period = hwc->sample_period;
                 event->attr.freq = 0;
         }
 }
diff --git a/kernel/printk.c b/kernel/printk.c
index 0b31715f335a..abbdd9e2ac82 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -63,8 +63,6 @@ void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
 #define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */
 #define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */
 
-DECLARE_WAIT_QUEUE_HEAD(log_wait);
-
 int console_printk[4] = {
         DEFAULT_CONSOLE_LOGLEVEL,       /* console_loglevel */
         DEFAULT_MESSAGE_LOGLEVEL,       /* default_message_loglevel */
@@ -224,6 +222,7 @@ struct log {
 static DEFINE_RAW_SPINLOCK(logbuf_lock);
 
 #ifdef CONFIG_PRINTK
+DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
 static u64 syslog_seq;
 static u32 syslog_idx;
@@ -1957,45 +1956,6 @@ int is_console_locked(void)
         return console_locked;
 }
 
-/*
- * Delayed printk version, for scheduler-internal messages:
- */
-#define PRINTK_BUF_SIZE         512
-
-#define PRINTK_PENDING_WAKEUP   0x01
-#define PRINTK_PENDING_SCHED    0x02
-
-static DEFINE_PER_CPU(int, printk_pending);
-static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
-
-static void wake_up_klogd_work_func(struct irq_work *irq_work)
-{
-        int pending = __this_cpu_xchg(printk_pending, 0);
-
-        if (pending & PRINTK_PENDING_SCHED) {
-                char *buf = __get_cpu_var(printk_sched_buf);
-                printk(KERN_WARNING "[sched_delayed] %s", buf);
-        }
-
-        if (pending & PRINTK_PENDING_WAKEUP)
-                wake_up_interruptible(&log_wait);
-}
-
-static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
-        .func = wake_up_klogd_work_func,
-        .flags = IRQ_WORK_LAZY,
-};
-
-void wake_up_klogd(void)
-{
-        preempt_disable();
-        if (waitqueue_active(&log_wait)) {
-                this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
-                irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
-        }
-        preempt_enable();
-}
-
 static void console_cont_flush(char *text, size_t size)
 {
         unsigned long flags;
@@ -2458,6 +2418,44 @@ static int __init printk_late_init(void)
 late_initcall(printk_late_init);
 
 #if defined CONFIG_PRINTK
+/*
+ * Delayed printk version, for scheduler-internal messages:
+ */
+#define PRINTK_BUF_SIZE         512
+
+#define PRINTK_PENDING_WAKEUP   0x01
+#define PRINTK_PENDING_SCHED    0x02
+
+static DEFINE_PER_CPU(int, printk_pending);
+static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
+
+static void wake_up_klogd_work_func(struct irq_work *irq_work)
+{
+        int pending = __this_cpu_xchg(printk_pending, 0);
+
+        if (pending & PRINTK_PENDING_SCHED) {
+                char *buf = __get_cpu_var(printk_sched_buf);
+                printk(KERN_WARNING "[sched_delayed] %s", buf);
+        }
+
+        if (pending & PRINTK_PENDING_WAKEUP)
+                wake_up_interruptible(&log_wait);
+}
+
+static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
+        .func = wake_up_klogd_work_func,
+        .flags = IRQ_WORK_LAZY,
+};
+
+void wake_up_klogd(void)
+{
+        preempt_disable();
+        if (waitqueue_active(&log_wait)) {
+                this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
+                irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+        }
+        preempt_enable();
+}
 
 int printk_sched(const char *fmt, ...)
 {
diff --git a/kernel/sys.c b/kernel/sys.c
index 81f56445fba9..39c9c4a2949f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2185,9 +2185,8 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
 
 char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
 
-static int __orderly_poweroff(void)
+static int __orderly_poweroff(bool force)
 {
-        int argc;
         char **argv;
         static char *envp[] = {
                 "HOME=/",
@@ -2196,20 +2195,40 @@ static int __orderly_poweroff(void)
         };
         int ret;
 
-        argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
-        if (argv == NULL) {
+        argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL);
+        if (argv) {
+                ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+                argv_free(argv);
+        } else {
                 printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
-                       __func__, poweroff_cmd);
-                return -ENOMEM;
+                                         __func__, poweroff_cmd);
+                ret = -ENOMEM;
         }
 
-        ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_WAIT_EXEC,
-                                      NULL, NULL, NULL);
-        argv_free(argv);
+        if (ret && force) {
+                printk(KERN_WARNING "Failed to start orderly shutdown: "
+                                        "forcing the issue\n");
+                /*
+                 * I guess this should try to kick off some daemon to sync and
+                 * poweroff asap.  Or not even bother syncing if we're doing an
+                 * emergency shutdown?
+                 */
+                emergency_sync();
+                kernel_power_off();
+        }
 
         return ret;
 }
 
+static bool poweroff_force;
+
+static void poweroff_work_func(struct work_struct *work)
+{
+        __orderly_poweroff(poweroff_force);
+}
+
+static DECLARE_WORK(poweroff_work, poweroff_work_func);
+
 /**
  * orderly_poweroff - Trigger an orderly system poweroff
  * @force: force poweroff if command execution fails
@@ -2219,21 +2238,9 @@ static int __orderly_poweroff(void)
  */
 int orderly_poweroff(bool force)
 {
-        int ret = __orderly_poweroff();
-
-        if (ret && force) {
-                printk(KERN_WARNING "Failed to start orderly shutdown: "
-                       "forcing the issue\n");
-
-                /*
-                 * I guess this should try to kick off some daemon to sync and
-                 * poweroff asap.  Or not even bother syncing if we're doing an
-                 * emergency shutdown?
-                 */
-                emergency_sync();
-                kernel_power_off();
-        }
-
-        return ret;
+        if (force) /* do not override the pending "true" */
+                poweroff_force = true;
+        schedule_work(&poweroff_work);
+        return 0;
 }
 EXPORT_SYMBOL_GPL(orderly_poweroff);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 2fb8cb88df8d..7f32fe0e52cd 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -67,7 +67,8 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
  */
 int tick_check_broadcast_device(struct clock_event_device *dev)
 {
-        if ((tick_broadcast_device.evtdev &&
+        if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
+            (tick_broadcast_device.evtdev &&
              tick_broadcast_device.evtdev->rating >= dev->rating) ||
              (dev->features & CLOCK_EVT_FEAT_C3STOP))
                 return 0;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ab25b88aae56..6893d5a2bf08 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3104,8 +3104,8 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
                                         continue;
                         }
 
-                        hlist_del(&entry->node);
-                        call_rcu(&entry->rcu, ftrace_free_entry_rcu);
+                        hlist_del_rcu(&entry->node);
+                        call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu);
                 }
         }
         __disable_ftrace_function_probe();
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1f835a83cb2c..4f1dade56981 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -704,7 +704,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 void
 update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
-        struct ring_buffer *buf = tr->buffer;
+        struct ring_buffer *buf;
 
         if (trace_stop_count)
                 return;
@@ -719,6 +719,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
         arch_spin_lock(&ftrace_max_lock);
 
+        buf = tr->buffer;
         tr->buffer = max_tr.buffer;
         max_tr.buffer = buf;
 
@@ -2880,11 +2881,25 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
         return -EINVAL;
 }
 
-static void set_tracer_flags(unsigned int mask, int enabled)
+/* Some tracers require overwrite to stay enabled */
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
+{
+        if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set)
+                return -1;
+
+        return 0;
+}
+
+int set_tracer_flag(unsigned int mask, int enabled)
 {
         /* do nothing if flag is already set */
         if (!!(trace_flags & mask) == !!enabled)
-                return;
+                return 0;
+
+        /* Give the tracer a chance to approve the change */
+        if (current_trace->flag_changed)
+                if (current_trace->flag_changed(current_trace, mask, !!enabled))
+                        return -EINVAL;
 
         if (enabled)
                 trace_flags |= mask;
@@ -2894,18 +2909,24 @@ static void set_tracer_flags(unsigned int mask, int enabled)
         if (mask == TRACE_ITER_RECORD_CMD)
                 trace_event_enable_cmd_record(enabled);
 
-        if (mask == TRACE_ITER_OVERWRITE)
+        if (mask == TRACE_ITER_OVERWRITE) {
                 ring_buffer_change_overwrite(global_trace.buffer, enabled);
+#ifdef CONFIG_TRACER_MAX_TRACE
+                ring_buffer_change_overwrite(max_tr.buffer, enabled);
+#endif
+        }
 
         if (mask == TRACE_ITER_PRINTK)
                 trace_printk_start_stop_comm(enabled);
+
+        return 0;
 }
 
 static int trace_set_options(char *option)
 {
         char *cmp;
         int neg = 0;
-        int ret = 0;
+        int ret = -ENODEV;
         int i;
 
         cmp = strstrip(option);
@@ -2915,19 +2936,20 @@ static int trace_set_options(char *option)
                 cmp += 2;
         }
 
+        mutex_lock(&trace_types_lock);
+
         for (i = 0; trace_options[i]; i++) {
                 if (strcmp(cmp, trace_options[i]) == 0) {
-                        set_tracer_flags(1 << i, !neg);
+                        ret = set_tracer_flag(1 << i, !neg);
                         break;
                 }
         }
 
         /* If no option could be set, test the specific tracer options */
-        if (!trace_options[i]) {
-                mutex_lock(&trace_types_lock);
+        if (!trace_options[i])
                 ret = set_tracer_option(current_trace, cmp, neg);
-                mutex_unlock(&trace_types_lock);
-        }
+
+        mutex_unlock(&trace_types_lock);
 
         return ret;
 }
@@ -2937,6 +2959,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
                         size_t cnt, loff_t *ppos)
 {
         char buf[64];
+        int ret;
 
         if (cnt >= sizeof(buf))
                 return -EINVAL;
@@ -2946,7 +2969,9 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 
         buf[cnt] = 0;
 
-        trace_set_options(buf);
+        ret = trace_set_options(buf);
+        if (ret < 0)
+                return ret;
 
         *ppos += cnt;
 
@@ -3250,6 +3275,9 @@ static int tracing_set_tracer(const char *buf)
                 goto out;
 
         trace_branch_disable();
+
+        current_trace->enabled = false;
+
         if (current_trace->reset)
                 current_trace->reset(tr);
 
@@ -3294,6 +3322,7 @@ static int tracing_set_tracer(const char *buf)
         }
 
         current_trace = t;
+        current_trace->enabled = true;
         trace_branch_enable(tr);
  out:
         mutex_unlock(&trace_types_lock);
@@ -4780,7 +4809,13 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
         if (val != 0 && val != 1)
                 return -EINVAL;
-        set_tracer_flags(1 << index, val);
+
+        mutex_lock(&trace_types_lock);
+        ret = set_tracer_flag(1 << index, val);
+        mutex_unlock(&trace_types_lock);
+
+        if (ret < 0)
+                return ret;
 
         *ppos += cnt;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 57d7e5397d56..2081971367ea 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -283,11 +283,15 @@ struct tracer {
         enum print_line_t       (*print_line)(struct trace_iterator *iter);
         /* If you handled the flag setting, return 0 */
         int                     (*set_flag)(u32 old_flags, u32 bit, int set);
+        /* Return 0 if OK with change, else return non-zero */
+        int                     (*flag_changed)(struct tracer *tracer,
+                                                u32 mask, int set);
         struct tracer           *next;
         struct tracer_flags     *flags;
         bool                    print_max;
         bool                    use_max_tr;
         bool                    allocated_snapshot;
+        bool                    enabled;
 };
 
 
@@ -943,6 +947,8 @@ extern const char *__stop___trace_bprintk_fmt[];
 
 void trace_printk_init_buffers(void);
 void trace_printk_start_comm(void);
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
+int set_tracer_flag(unsigned int mask, int enabled);
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)     \
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 713a2cac4881..443b25b43b4f 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -32,7 +32,7 @@ enum {
 
 static int trace_type __read_mostly;
 
-static int save_lat_flag;
+static int save_flags;
 
 static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
 static int start_irqsoff_tracer(struct trace_array *tr, int graph);
@@ -558,8 +558,11 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
 {
-        save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-        trace_flags |= TRACE_ITER_LATENCY_FMT;
+        save_flags = trace_flags;
+
+        /* non overwrite screws up the latency tracers */
+        set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+        set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
 
         tracing_max_latency = 0;
         irqsoff_trace = tr;
@@ -573,10 +576,13 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
+        int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+        int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
         stop_irqsoff_tracer(tr, is_graph());
 
-        if (!save_lat_flag)
-                trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+        set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+        set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void irqsoff_tracer_start(struct trace_array *tr)
@@ -609,6 +615,7 @@ static struct tracer irqsoff_tracer __read_mostly =
         .print_line     = irqsoff_print_line,
         .flags          = &tracer_flags,
         .set_flag       = irqsoff_set_flag,
+        .flag_changed   = trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_irqsoff,
 #endif
@@ -642,6 +649,7 @@ static struct tracer preemptoff_tracer __read_mostly =
         .print_line     = irqsoff_print_line,
         .flags          = &tracer_flags,
         .set_flag       = irqsoff_set_flag,
+        .flag_changed   = trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_preemptoff,
 #endif
@@ -677,6 +685,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
         .print_line     = irqsoff_print_line,
         .flags          = &tracer_flags,
         .set_flag       = irqsoff_set_flag,
+        .flag_changed   = trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_preemptirqsoff,
 #endif
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 75aa97fbe1a1..fde652c9a511 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -36,7 +36,7 @@ static void __wakeup_reset(struct trace_array *tr);
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
 static void wakeup_graph_return(struct ftrace_graph_ret *trace);
 
-static int save_lat_flag;
+static int save_flags;
 
 #define TRACE_DISPLAY_GRAPH     1
 
@@ -540,8 +540,11 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
-        save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-        trace_flags |= TRACE_ITER_LATENCY_FMT;
+        save_flags = trace_flags;
+
+        /* non overwrite screws up the latency tracers */
+        set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+        set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
 
         tracing_max_latency = 0;
         wakeup_trace = tr;
@@ -563,12 +566,15 @@ static int wakeup_rt_tracer_init(struct trace_array *tr)
 
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
+        int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+        int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
         stop_wakeup_tracer(tr);
         /* make sure we put back any tasks we are tracing */
         wakeup_reset(tr);
 
-        if (!save_lat_flag)
-                trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+        set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+        set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void wakeup_tracer_start(struct trace_array *tr)
@@ -594,6 +600,7 @@ static struct tracer wakeup_tracer __read_mostly =
         .print_line     = wakeup_print_line,
         .flags          = &tracer_flags,
         .set_flag       = wakeup_set_flag,
+        .flag_changed   = trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_wakeup,
 #endif
@@ -615,6 +622,7 @@ static struct tracer wakeup_rt_tracer __read_mostly =
         .print_line     = wakeup_print_line,
         .flags          = &tracer_flags,
         .set_flag       = wakeup_set_flag,
+        .flag_changed   = trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_wakeup,
 #endif