Merge branch 'upstream/android-3.4' into linaro-android-3.4tracking-linaro-android-3.4-3.4-rc3-2012.04-0

4 files changed, 226 insertions, 35 deletions

diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index d6ef94a95cc8..8a83c0a5c287 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -223,11 +223,21 @@ frequency before ramping down. This is to ensure that the governor has
 seen enough historic cpu load data to determine the appropriate
 workload.  Default is 80000 uS.
 
-go_maxspeed_load: The CPU load at which to ramp to max speed.  Default
-is 85.
+hispeed_freq: An intermediate "hi speed" at which to initially ramp
+when CPU load hits the value specified in go_hispeed_load.  If load
+stays high for the amount of time specified in above_hispeed_delay,
+then speed may be bumped higher.  Default is maximum speed.
+
+go_hispeed_load: The CPU load at which to ramp to the intermediate "hi
+speed".  Default is 85%.
+
+above_hispeed_delay: Once speed is set to hispeed_freq, wait for this
+long before bumping speed higher in response to continued high load.
+Default is 20000 uS.
 
 timer_rate: Sample rate for reevaluating cpu load when the system is
-not idle.  Default is 30000 uS.
+not idle.  Default is 20000 uS.
+
 
 3. The Governor Interface in the CPUfreq Core
 =============================================
diff --git a/drivers/cpufreq/cpufreq_interactive.c b/drivers/cpufreq/cpufreq_interactive.c
index 8a5cd15512c7..fc3628dc0d56 100644
--- a/drivers/cpufreq/cpufreq_interactive.c
+++ b/drivers/cpufreq/cpufreq_interactive.c
@@ -29,6 +29,9 @@
 #include <linux/kthread.h>
 #include <linux/mutex.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/cpufreq_interactive.h>
+
 #include <asm/cputime.h>
 
 static atomic_t active_count = ATOMIC_INIT(0);
@@ -40,8 +43,8 @@ struct cpufreq_interactive_cpuinfo {
 	u64 idle_exit_time;
 	u64 timer_run_time;
 	int idling;
-	u64 freq_change_time;
-	u64 freq_change_time_in_idle;
+	u64 target_set_time;
+	u64 target_set_time_in_idle;
 	struct cpufreq_policy *policy;
 	struct cpufreq_frequency_table *freq_table;
 	unsigned int target_freq;
@@ -64,21 +67,28 @@ static struct mutex set_speed_lock;
 static u64 hispeed_freq;
 
 /* Go to hi speed when CPU load at or above this value. */
-#define DEFAULT_GO_HISPEED_LOAD 95
+#define DEFAULT_GO_HISPEED_LOAD 85
 static unsigned long go_hispeed_load;
 
 /*
  * The minimum amount of time to spend at a frequency before we can ramp down.
  */
-#define DEFAULT_MIN_SAMPLE_TIME 20 * USEC_PER_MSEC
+#define DEFAULT_MIN_SAMPLE_TIME (80 * USEC_PER_MSEC)
 static unsigned long min_sample_time;
 
 /*
  * The sample rate of the timer used to increase frequency
  */
-#define DEFAULT_TIMER_RATE 20 * USEC_PER_MSEC
+#define DEFAULT_TIMER_RATE (20 * USEC_PER_MSEC)
 static unsigned long timer_rate;
 
+/*
+ * Wait this long before raising speed above hispeed, by default a single
+ * timer interval.
+ */
+#define DEFAULT_ABOVE_HISPEED_DELAY DEFAULT_TIMER_RATE
+static unsigned long above_hispeed_delay_val;
+
 static int cpufreq_governor_interactive(struct cpufreq_policy *policy,
 		unsigned int event);
 
@@ -144,8 +154,9 @@ static void cpufreq_interactive_timer(unsigned long data)
 	else
 		cpu_load = 100 * (delta_time - delta_idle) / delta_time;
 
-	delta_idle = (unsigned int)(now_idle - pcpu->freq_change_time_in_idle);
-	delta_time = (unsigned int)(pcpu->timer_run_time - pcpu->freq_change_time);
+	delta_idle = (unsigned int)(now_idle - pcpu->target_set_time_in_idle);
+	delta_time = (unsigned int)(pcpu->timer_run_time -
+				    pcpu->target_set_time);
 
 	if ((delta_time == 0) || (delta_idle > delta_time))
 		load_since_change = 0;
@@ -162,12 +173,26 @@ static void cpufreq_interactive_timer(unsigned long data)
 		cpu_load = load_since_change;
 
 	if (cpu_load >= go_hispeed_load) {
-		if (pcpu->policy->cur == pcpu->policy->min)
+		if (pcpu->policy->cur == pcpu->policy->min) {
 			new_freq = hispeed_freq;
-		else
+		} else {
 			new_freq = pcpu->policy->max * cpu_load / 100;
+
+			if (new_freq < hispeed_freq)
+				new_freq = hispeed_freq;
+
+			if (pcpu->target_freq == hispeed_freq &&
+			    new_freq > hispeed_freq &&
+			    pcpu->timer_run_time - pcpu->target_set_time
+			    < above_hispeed_delay_val) {
+				trace_cpufreq_interactive_notyet(data, cpu_load,
+								 pcpu->target_freq,
+								 new_freq);
+				goto rearm;
+			}
+		}
 	} else {
-		new_freq = pcpu->policy->cur * cpu_load / 100;
+		new_freq = pcpu->policy->max * cpu_load / 100;
 	}
 
 	if (cpufreq_frequency_table_target(pcpu->policy, pcpu->freq_table,
@@ -180,19 +205,31 @@ static void cpufreq_interactive_timer(unsigned long data)
 
 	new_freq = pcpu->freq_table[index].frequency;
 
-	if (pcpu->target_freq == new_freq)
-		goto rearm_if_notmax;
-
 	/*
 	 * Do not scale down unless we have been at this frequency for the
 	 * minimum sample time.
 	 */
 	if (new_freq < pcpu->target_freq) {
-		if (pcpu->timer_run_time - pcpu->freq_change_time
-		    < min_sample_time)
+		if (pcpu->timer_run_time - pcpu->target_set_time
+		    < min_sample_time) {
+			trace_cpufreq_interactive_notyet(data, cpu_load,
+					 pcpu->target_freq, new_freq);
 			goto rearm;
+		}
 	}
 
+	pcpu->target_set_time_in_idle = now_idle;
+	pcpu->target_set_time = pcpu->timer_run_time;
+
+	if (pcpu->target_freq == new_freq) {
+		trace_cpufreq_interactive_already(data, cpu_load,
+						  pcpu->target_freq, new_freq);
+		goto rearm_if_notmax;
+	}
+
+	trace_cpufreq_interactive_target(data, cpu_load, pcpu->target_freq,
+					 new_freq);
+
 	if (new_freq < pcpu->target_freq) {
 		pcpu->target_freq = new_freq;
 		spin_lock_irqsave(&down_cpumask_lock, flags);
@@ -376,10 +413,8 @@ static int cpufreq_interactive_up_task(void *data)
 							max_freq,
 							CPUFREQ_RELATION_H);
 			mutex_unlock(&set_speed_lock);
-
-			pcpu->freq_change_time_in_idle =
-				get_cpu_idle_time_us(cpu,
-						     &pcpu->freq_change_time);
+			trace_cpufreq_interactive_up(cpu, pcpu->target_freq,
+						     pcpu->policy->cur);
 		}
 	}
 
@@ -423,9 +458,8 @@ static void cpufreq_interactive_freq_down(struct work_struct *work)
 						CPUFREQ_RELATION_H);
 
 		mutex_unlock(&set_speed_lock);
-		pcpu->freq_change_time_in_idle =
-			get_cpu_idle_time_us(cpu,
-					     &pcpu->freq_change_time);
+		trace_cpufreq_interactive_down(cpu, pcpu->target_freq,
+					       pcpu->policy->cur);
 	}
 }
 
@@ -497,6 +531,28 @@ static ssize_t store_min_sample_time(struct kobject *kobj,
 static struct global_attr min_sample_time_attr = __ATTR(min_sample_time, 0644,
 		show_min_sample_time, store_min_sample_time);
 
+static ssize_t show_above_hispeed_delay(struct kobject *kobj,
+					struct attribute *attr, char *buf)
+{
+	return sprintf(buf, "%lu\n", above_hispeed_delay_val);
+}
+
+static ssize_t store_above_hispeed_delay(struct kobject *kobj,
+					 struct attribute *attr,
+					 const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val;
+
+	ret = strict_strtoul(buf, 0, &val);
+	if (ret < 0)
+		return ret;
+	above_hispeed_delay_val = val;
+	return count;
+}
+
+define_one_global_rw(above_hispeed_delay);
+
 static ssize_t show_timer_rate(struct kobject *kobj,
 			struct attribute *attr, char *buf)
 {
@@ -522,6 +578,7 @@ static struct global_attr timer_rate_attr = __ATTR(timer_rate, 0644,
 static struct attribute *interactive_attributes[] = {
 	&hispeed_freq_attr.attr,
 	&go_hispeed_load_attr.attr,
+	&above_hispeed_delay.attr,
 	&min_sample_time_attr.attr,
 	&timer_rate_attr.attr,
 	NULL,
@@ -553,9 +610,9 @@ static int cpufreq_governor_interactive(struct cpufreq_policy *policy,
 			pcpu->policy = policy;
 			pcpu->target_freq = policy->cur;
 			pcpu->freq_table = freq_table;
-			pcpu->freq_change_time_in_idle =
+			pcpu->target_set_time_in_idle =
 				get_cpu_idle_time_us(j,
-					     &pcpu->freq_change_time);
+					     &pcpu->target_set_time);
 			pcpu->governor_enabled = 1;
 			smp_wmb();
 		}
@@ -642,6 +699,7 @@ static int __init cpufreq_interactive_init(void)
 
 	go_hispeed_load = DEFAULT_GO_HISPEED_LOAD;
 	min_sample_time = DEFAULT_MIN_SAMPLE_TIME;
+	above_hispeed_delay_val = DEFAULT_ABOVE_HISPEED_DELAY;
 	timer_rate = DEFAULT_TIMER_RATE;
 
 	/* Initalize per-cpu timers */
diff --git a/include/trace/events/cpufreq_interactive.h b/include/trace/events/cpufreq_interactive.h
new file mode 100644
index 000000000000..3a90d3d609ba
--- /dev/null
+++ b/include/trace/events/cpufreq_interactive.h
@@ -0,0 +1,87 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cpufreq_interactive
+
+#if !defined(_TRACE_CPUFREQ_INTERACTIVE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CPUFREQ_INTERACTIVE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(set,
+	TP_PROTO(u32 cpu_id, unsigned long targfreq,
+	         unsigned long actualfreq),
+	TP_ARGS(cpu_id, targfreq, actualfreq),
+
+	TP_STRUCT__entry(
+	    __field(          u32, cpu_id    )
+	    __field(unsigned long, targfreq   )
+	    __field(unsigned long, actualfreq )
+	   ),
+
+	TP_fast_assign(
+	    __entry->cpu_id = (u32) cpu_id;
+	    __entry->targfreq = targfreq;
+	    __entry->actualfreq = actualfreq;
+	),
+
+	TP_printk("cpu=%u targ=%lu actual=%lu",
+	      __entry->cpu_id, __entry->targfreq,
+	      __entry->actualfreq)
+);
+
+DEFINE_EVENT(set, cpufreq_interactive_up,
+	TP_PROTO(u32 cpu_id, unsigned long targfreq,
+	     unsigned long actualfreq),
+	TP_ARGS(cpu_id, targfreq, actualfreq)
+);
+
+DEFINE_EVENT(set, cpufreq_interactive_down,
+	TP_PROTO(u32 cpu_id, unsigned long targfreq,
+	     unsigned long actualfreq),
+	TP_ARGS(cpu_id, targfreq, actualfreq)
+);
+
+DECLARE_EVENT_CLASS(loadeval,
+	    TP_PROTO(unsigned long cpu_id, unsigned long load,
+		     unsigned long curfreq, unsigned long targfreq),
+	    TP_ARGS(cpu_id, load, curfreq, targfreq),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned long, cpu_id    )
+		    __field(unsigned long, load      )
+		    __field(unsigned long, curfreq   )
+		    __field(unsigned long, targfreq  )
+	    ),
+
+	    TP_fast_assign(
+		    __entry->cpu_id = cpu_id;
+		    __entry->load = load;
+		    __entry->curfreq = curfreq;
+		    __entry->targfreq = targfreq;
+	    ),
+
+	    TP_printk("cpu=%lu load=%lu cur=%lu targ=%lu",
+		      __entry->cpu_id, __entry->load, __entry->curfreq,
+		      __entry->targfreq)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_target,
+	    TP_PROTO(unsigned long cpu_id, unsigned long load,
+		     unsigned long curfreq, unsigned long targfreq),
+	    TP_ARGS(cpu_id, load, curfreq, targfreq)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_already,
+	    TP_PROTO(unsigned long cpu_id, unsigned long load,
+		     unsigned long curfreq, unsigned long targfreq),
+	    TP_ARGS(cpu_id, load, curfreq, targfreq)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_notyet,
+	    TP_PROTO(unsigned long cpu_id, unsigned long load,
+		     unsigned long curfreq, unsigned long targfreq),
+	    TP_ARGS(cpu_id, load, curfreq, targfreq)
+);
+#endif /* _TRACE_CPUFREQ_INTERACTIVE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/net/netfilter/xt_qtaguid.c b/net/netfilter/xt_qtaguid.c
index 08086d680c2c..062f582ea75e 100644
--- a/net/netfilter/xt_qtaguid.c
+++ b/net/netfilter/xt_qtaguid.c
@@ -26,6 +26,10 @@
 #include <net/tcp.h>
 #include <net/udp.h>
 
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#endif
+
 #include <linux/netfilter/xt_socket.h>
 #include "xt_qtaguid_internal.h"
 #include "xt_qtaguid_print.h"
@@ -1265,7 +1269,7 @@ static void if_tag_stat_update(const char *ifname, uid_t uid,
 	struct data_counters *uid_tag_counters;
 	struct sock_tag *sock_tag_entry;
 	struct iface_stat *iface_entry;
-	struct tag_stat *new_tag_stat;
+	struct tag_stat *new_tag_stat = NULL;
 	MT_DEBUG("qtaguid: if_tag_stat_update(ifname=%s "
 		"uid=%u sk=%p dir=%d proto=%d bytes=%d)\n",
 		 ifname, uid, sk, direction, proto, bytes);
@@ -1330,8 +1334,19 @@ static void if_tag_stat_update(const char *ifname, uid_t uid,
 	}
 
 	if (acct_tag) {
+		/* Create the child {acct_tag, uid_tag} and hook up parent. */
 		new_tag_stat = create_if_tag_stat(iface_entry, tag);
 		new_tag_stat->parent_counters = uid_tag_counters;
+	} else {
+		/*
+		 * For new_tag_stat to be still NULL here would require:
+		 *  {0, uid_tag} exists
+		 *  and {acct_tag, uid_tag} doesn't exist
+		 *  AND acct_tag == 0.
+		 * Impossible. This reassures us that new_tag_stat
+		 * below will always be assigned.
+		 */
+		BUG_ON(!new_tag_stat);
 	}
 	tag_stat_update(new_tag_stat, direction, proto, bytes);
 	spin_unlock_bh(&iface_entry->tag_stat_list_lock);
@@ -1535,6 +1550,27 @@ static struct sock *qtaguid_find_sk(const struct sk_buff *skb,
 	return sk;
 }
 
+static int ipx_proto(const struct sk_buff *skb,
+		     struct xt_action_param *par)
+{
+	int thoff, tproto;
+
+	switch (par->family) {
+	case NFPROTO_IPV6:
+		tproto = ipv6_find_hdr(skb, &thoff, -1, NULL);
+		if (tproto < 0)
+			MT_DEBUG("%s(): transport header not found in ipv6"
+				 " skb=%p\n", __func__, skb);
+		break;
+	case NFPROTO_IPV4:
+		tproto = ip_hdr(skb)->protocol;
+		break;
+	default:
+		tproto = IPPROTO_RAW;
+	}
+	return tproto;
+}
+
 static void account_for_uid(const struct sk_buff *skb,
 			    const struct sock *alternate_sk, uid_t uid,
 			    struct xt_action_param *par)
@@ -1561,15 +1597,15 @@ static void account_for_uid(const struct sk_buff *skb,
 	} else if (unlikely(!el_dev->name)) {
 		pr_info("qtaguid[%d]: no dev->name?!!\n", par->hooknum);
 	} else {
-		MT_DEBUG("qtaguid[%d]: dev name=%s type=%d\n",
-			 par->hooknum,
-			 el_dev->name,
-			 el_dev->type);
+		int proto = ipx_proto(skb, par);
+		MT_DEBUG("qtaguid[%d]: dev name=%s type=%d fam=%d proto=%d\n",
+			 par->hooknum, el_dev->name, el_dev->type,
+			 par->family, proto);
 
 		if_tag_stat_update(el_dev->name, uid,
 				skb->sk ? skb->sk : alternate_sk,
 				par->in ? IFS_RX : IFS_TX,
-				ip_hdr(skb)->protocol, skb->len);
+				proto, skb->len);
 	}
 }
 
@@ -1614,8 +1650,8 @@ static bool qtaguid_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	} else {
 		atomic64_inc(&qtu_events.match_found_sk);
 	}
-	MT_DEBUG("qtaguid[%d]: sk=%p got_sock=%d proto=%d\n",
-		par->hooknum, sk, got_sock, ip_hdr(skb)->protocol);
+	MT_DEBUG("qtaguid[%d]: sk=%p got_sock=%d fam=%d proto=%d\n",
+		 par->hooknum, sk, got_sock, par->family, ipx_proto(skb, par));
 	if (sk != NULL) {
 		MT_DEBUG("qtaguid[%d]: sk=%p->sk_socket=%p->file=%p\n",
 			par->hooknum, sk, sk->sk_socket,