Merge branch 'perfcounters-fixes-for-linus' of git://git.kernel.org/p…

…ub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (27 commits)
  perf_counter: Zero dead bytes from ftrace raw samples size alignment
  perf_counter: Subtract the buffer size field from the event record size
  perf_counter: Require CAP_SYS_ADMIN for raw tracepoint data
  perf_counter: Correct PERF_SAMPLE_RAW output
  perf tools: callchain: Fix bad rounding of minimum rate
  perf_counter tools: Fix libbfd detection for systems with libz dependency
  perf: "Longum est iter per praecepta, breve et efficax per exempla"
  perf_counter: Fix a race on perf_counter_ctx
  perf_counter: Fix tracepoint sampling to be part of generic sampling
  perf_counter: Work around gcc warning by initializing tracepoint record unconditionally
  perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode
  perf tools: callchain: Fix 'perf report' display to be callchain by default
  perf tools: callchain: Fix spurious 'perf report' warnings: ignore empty callchains
  perf record: Fix the -A UI for empty or non-existent perf.data
  perf util: Fix do_read() to fail on EOF instead of busy-looping
  perf list: Fix the output to not include tracepoints without an id
  perf_counter/powerpc: Fix oops on cpus without perf_counter hardware support
  perf stat: Fix tool option consistency: rename -S/--scale to -c/--scale
  perf report: Add debug help for the finding of symbol bugs - show the symtab origin (DSO, build-id, kernel, etc)
  perf report: Fix per task mult-counter stat reporting
  ...

arch/powerpc/kernel/perf_counter.c

@@ -518,6 +518,8 @@ void hw_perf_disable(void)
 	struct cpu_hw_counters *cpuhw;
 	unsigned long flags;
 
+	if (!ppmu)
+		return;
 	local_irq_save(flags);
 	cpuhw = &__get_cpu_var(cpu_hw_counters);
 
@@ -572,6 +574,8 @@ void hw_perf_enable(void)
 	int n_lim;
 	int idx;
 
+	if (!ppmu)
+		return;
 	local_irq_save(flags);
 	cpuhw = &__get_cpu_var(cpu_hw_counters);
 	if (!cpuhw->disabled) {
@@ -737,6 +741,8 @@ int hw_perf_group_sched_in(struct perf_counter *group_leader,
 	long i, n, n0;
 	struct perf_counter *sub;
 
+	if (!ppmu)
+		return 0;
 	cpuhw = &__get_cpu_var(cpu_hw_counters);
 	n0 = cpuhw->n_counters;
 	n = collect_events(group_leader, ppmu->n_counter - n0,
@@ -1281,6 +1287,8 @@ void hw_perf_counter_setup(int cpu)
 {
 	struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu);
 
+	if (!ppmu)
+		return;
 	memset(cpuhw, 0, sizeof(*cpuhw));
 	cpuhw->mmcr[0] = MMCR0_FC;
 }

include/linux/perf_counter.h

@@ -121,7 +121,7 @@ enum perf_counter_sample_format {
 	PERF_SAMPLE_CPU				= 1U << 7,
 	PERF_SAMPLE_PERIOD			= 1U << 8,
 	PERF_SAMPLE_STREAM_ID			= 1U << 9,
-	PERF_SAMPLE_TP_RECORD			= 1U << 10,
+	PERF_SAMPLE_RAW				= 1U << 10,
 
 	PERF_SAMPLE_MAX = 1U << 11,		/* non-ABI */
 };
@@ -369,6 +369,8 @@ enum perf_event_type {
 	 *
 	 *	{ u64			nr,
 	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
 	 * };
 	 */
 	PERF_EVENT_SAMPLE		= 9,
@@ -414,9 +416,9 @@ struct perf_callchain_entry {
 	__u64				ip[PERF_MAX_STACK_DEPTH];
 };
 
-struct perf_tracepoint_record {
-	int				size;
-	char				*record;
+struct perf_raw_record {
+	u32				size;
+	void				*data;
 };
 
 struct task_struct;
@@ -687,7 +689,7 @@ struct perf_sample_data {
 	struct pt_regs			*regs;
 	u64				addr;
 	u64				period;
-	void				*private;
+	struct perf_raw_record		*raw;
 };
 
 extern int perf_counter_overflow(struct perf_counter *counter, int nmi,

include/trace/ftrace.h

@@ -637,12 +637,20 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  *	pc = preempt_count();
  *
  *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
- *	__entry_size = __data_size + sizeof(*entry);
+ *
+ *	// Below we want to get the aligned size by taking into account
+ *	// the u32 field that will later store the buffer size
+ *	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
+ *			     sizeof(u64));
+ *	__entry_size -= sizeof(u32);
  *
  *	do {
  *		char raw_data[__entry_size]; <- allocate our sample in the stack
  *		struct trace_entry *ent;
  *
+ *		zero dead bytes from alignment to avoid stack leak to userspace:
+ *
+ *		*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
  *		entry = (struct ftrace_raw_<call> *)raw_data;
  *		ent = &entry->ent;
  *		tracing_generic_entry_update(ent, irq_flags, pc);
@@ -685,12 +693,15 @@ static void ftrace_profile_##call(proto)				\
 	pc = preempt_count();						\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
-	__entry_size = ALIGN(__data_size + sizeof(*entry), sizeof(u64));\
+	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
+			     sizeof(u64));				\
+	__entry_size -= sizeof(u32);					\
 									\
 	do {								\
 		char raw_data[__entry_size];				\
 		struct trace_entry *ent;				\
 									\
+		*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;	\
 		entry = (struct ftrace_raw_##call *)raw_data;		\
 		ent = &entry->ent;					\
 		tracing_generic_entry_update(ent, irq_flags, pc);	\