perf/core improvements and fixes

index 8c7fe9d64e79..7be389735402 100644
@@ -143,6 +143,32 @@ struct branch_stack {
 	struct branch_entry	entries[0];
 };
 
+enum {
+	PERF_IP_FLAG_BRANCH		= 1ULL << 0,
+	PERF_IP_FLAG_CALL		= 1ULL << 1,
+	PERF_IP_FLAG_RETURN		= 1ULL << 2,
+	PERF_IP_FLAG_CONDITIONAL	= 1ULL << 3,
+	PERF_IP_FLAG_SYSCALLRET		= 1ULL << 4,
+	PERF_IP_FLAG_ASYNC		= 1ULL << 5,
+	PERF_IP_FLAG_INTERRUPT		= 1ULL << 6,
+	PERF_IP_FLAG_TX_ABORT		= 1ULL << 7,
+	PERF_IP_FLAG_TRACE_BEGIN	= 1ULL << 8,
+	PERF_IP_FLAG_TRACE_END		= 1ULL << 9,
+	PERF_IP_FLAG_IN_TX		= 1ULL << 10,
+};
+
+#define PERF_BRANCH_MASK		(\
+	PERF_IP_FLAG_BRANCH		|\
+	PERF_IP_FLAG_CALL		|\
+	PERF_IP_FLAG_RETURN		|\
+	PERF_IP_FLAG_CONDITIONAL	|\
+	PERF_IP_FLAG_SYSCALLRET		|\
+	PERF_IP_FLAG_ASYNC		|\
+	PERF_IP_FLAG_INTERRUPT		|\
+	PERF_IP_FLAG_TX_ABORT		|\
+	PERF_IP_FLAG_TRACE_BEGIN	|\
+	PERF_IP_FLAG_TRACE_END)
+
 struct perf_sample {
 	u64 ip;
 	u32 pid, tid;

172 lines not on this page · raw message

new file mode 100644
index 000000000000..7c41579aec74
@@ -0,0 +1,32 @@
+/*
+ * thread-stack.h: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_THREAD_STACK_H
+#define __PERF_THREAD_STACK_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+
+struct thread;
+struct ip_callchain;
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+			u64 to_ip, u16 insn_len, u64 trace_nr);
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+			  size_t sz, u64 ip);
+void thread_stack__free(struct thread *thread);
+
+#endif

index bf5bf858b7f6..a2157f0ef1df 100644
@@ -4,6 +4,7 @@
 #include <string.h>
 #include "session.h"
 #include "thread.h"
+#include "thread-stack.h"
 #include "util.h"
 #include "debug.h"
 #include "comm.h"

@@ -66,6 +67,8 @@ void thread__delete(struct thread *thread)
 {
 	struct comm *comm, *tmp;
 
+	thread_stack__free(thread);
+
 	if (thread->mg) {
 		map_groups__put(thread->mg);
 		thread->mg = NULL;

index d34cf5c0d0d9..160fd066a7d1 100644
@@ -8,6 +8,8 @@
 #include "symbol.h"
 #include <strlist.h>
 
+struct thread_stack;
+
 struct thread {
 	union {
 		struct rb_node	 rb_node;

@@ -26,6 +28,7 @@ struct thread {
 	u64			db_id;
 
 	void			*priv;
+	struct thread_stack	*ts;
 };
 
 struct machine;

index 85b60d2e738f..9ed59a452d1f 100644
@@ -13,23 +13,96 @@
  *
  */
 
+#include <linux/rbtree.h>
+#include <linux/list.h>
 #include "thread.h"
 #include "event.h"
+#include "machine.h"
 #include "util.h"
 #include "debug.h"
+#include "symbol.h"
+#include "comm.h"
 #include "thread-stack.h"
 
-#define STACK_GROWTH 4096
+#define CALL_PATH_BLOCK_SHIFT 8
+#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
+#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
 
+struct call_path_block {
+	struct call_path cp[CALL_PATH_BLOCK_SIZE];
+	struct list_head node;
+};
+
+/**
+ * struct call_path_root - root of all call paths.
+ * @call_path: root call path
+ * @blocks: list of blocks to store call paths
+ * @next: next free space
+ * @sz: number of spaces
+ */
+struct call_path_root {
+	struct call_path call_path;
+	struct list_head blocks;
+	size_t next;
+	size_t sz;
+};
+
+/**
+ * struct call_return_processor - provides a call-back to consume call-return
+ *                                information.
+ * @cpr: call path root
+ * @process: call-back that accepts call/return information
+ * @data: anonymous data for call-back
+ */
+struct call_return_processor {
+	struct call_path_root *cpr;
+	int (*process)(struct call_return *cr, void *data);
+	void *data;
+};
+
+#define STACK_GROWTH 2048
+
+/**
+ * struct thread_stack_entry - thread stack entry.
+ * @ret_addr: return address
+ * @timestamp: timestamp (if known)
+ * @ref: external reference (e.g. db_id of sample)
+ * @branch_count: the branch count when the entry was created
+ * @cp: call path
+ * @no_call: a 'call' was not seen
+ */
 struct thread_stack_entry {
 	u64 ret_addr;
+	u64 timestamp;
+	u64 ref;
+	u64 branch_count;
+	struct call_path *cp;
+	bool no_call;
 };
 
+/**
+ * struct thread_stack - thread stack constructed from 'call' and 'return'
+ *                       branch samples.
+ * @stack: array that holds the stack
+ * @cnt: number of entries in the stack
+ * @sz: current maximum stack size
+ * @trace_nr: current trace number
+ * @branch_count: running branch count
+ * @kernel_start: kernel start address
+ * @last_time: last timestamp
+ * @crp: call/return processor
+ * @comm: current comm
+ */
 struct thread_stack {
 	struct thread_stack_entry *stack;
 	size_t cnt;
 	size_t sz;
 	u64 trace_nr;
+	u64 branch_count;
+	u64 kernel_start;
+	u64 last_time;
+	struct call_return_processor *crp;
+	struct comm *comm;
 };
 
 static int thread_stack__grow(struct thread_stack *ts)

@@ -50,7 +123,8 @@ static int thread_stack__grow(struct thread_stack *ts)
 	return 0;
 }
 
-static struct thread_stack *thread_stack__new(void)
+static struct thread_stack *thread_stack__new(struct thread *thread,
+					      struct call_return_processor *crp)
 {
 	struct thread_stack *ts;
 

@@ -63,6 +137,12 @@ static struct thread_stack *thread_stack__new(void)
 		return NULL;
 	}
 
+	if (thread->mg && thread->mg->machine)
+		ts->kernel_start = machine__kernel_start(thread->mg->machine);
+	else
+		ts->kernel_start = 1ULL << 63;
+	ts->crp = crp;
+
 	return ts;
 }
 

@@ -104,6 +184,64 @@ static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
 	}
 }
 
+static bool thread_stack__in_kernel(struct thread_stack *ts)
+{
+	if (!ts->cnt)
+		return false;
+
+	return ts->stack[ts->cnt - 1].cp->in_kernel;
+}
+
+static int thread_stack__call_return(struct thread *thread,
+				     struct thread_stack *ts, size_t idx,
+				     u64 timestamp, u64 ref, bool no_return)
+{
+	struct call_return_processor *crp = ts->crp;
+	struct thread_stack_entry *tse;
+	struct call_return cr = {
+		.thread = thread,
+		.comm = ts->comm,
+		.db_id = 0,
+	};
+
+	tse = &ts->stack[idx];
+	cr.cp = tse->cp;
+	cr.call_time = tse->timestamp;
+	cr.return_time = timestamp;
+	cr.branch_count = ts->branch_count - tse->branch_count;
+	cr.call_ref = tse->ref;
+	cr.return_ref = ref;
+	if (tse->no_call)
+		cr.flags |= CALL_RETURN_NO_CALL;
+	if (no_return)
+		cr.flags |= CALL_RETURN_NO_RETURN;
+
+	return crp->process(&cr, crp->data);
+}
+
+static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+{
+	struct call_return_processor *crp = ts->crp;
+	int err;
+
+	if (!crp) {
+		ts->cnt = 0;
+		return 0;
+	}
+
+	while (ts->cnt) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						ts->last_time, 0, true);
+		if (err) {
+			pr_err("Error flushing thread stack!\n");
+			ts->cnt = 0;
+			return err;
+		}
+	}
+
+	return 0;
+}
+
 int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr)
 {

@@ -111,7 +249,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 		return -EINVAL;
 
 	if (!thread->ts) {
-		thread->ts = thread_stack__new();
+		thread->ts = thread_stack__new(thread, NULL);
 		if (!thread->ts) {
 			pr_warning("Out of memory: no thread stack\n");
 			return -ENOMEM;

@@ -122,13 +260,18 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 	/*
 	 * When the trace is discontinuous, the trace_nr changes.  In that case
 	 * the stack might be completely invalid.  Better to report nothing than
-	 * to report something misleading, so reset the stack count to zero.
+	 * to report something misleading, so flush the stack.
 	 */
 	if (trace_nr != thread->ts->trace_nr) {
+		if (thread->ts->trace_nr)
+			thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
-		thread->ts->cnt = 0;
 	}
 
+	/* Stop here if thread_stack__process() is in use */
+	if (thread->ts->crp)
+		return 0;
+
 	if (flags & PERF_IP_FLAG_CALL) {
 		u64 ret_addr;
 

@@ -147,9 +290,22 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 	return 0;
 }
 
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
+{
+	if (!thread || !thread->ts)
+		return;
+
+	if (trace_nr != thread->ts->trace_nr) {
+		if (thread->ts->trace_nr)
+			thread_stack__flush(thread, thread->ts);
+		thread->ts->trace_nr = trace_nr;
+	}
+}
+
 void thread_stack__free(struct thread *thread)
 {
 	if (thread->ts) {
+		thread_stack__flush(thread, thread->ts);
 		zfree(&thread->ts->stack);
 		zfree(&thread->ts);
 	}

@@ -170,3 +326,422 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
 	for (i = 1; i < chain->nr; i++)
 		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
 }
+
+static void call_path__init(struct call_path *cp, struct call_path *parent,
+			    struct symbol *sym, u64 ip, bool in_kernel)
+{
+	cp->parent = parent;
+	cp->sym = sym;
+	cp->ip = sym ? 0 : ip;
+	cp->db_id = 0;
+	cp->in_kernel = in_kernel;
+	RB_CLEAR_NODE(&cp->rb_node);
+	cp->children = RB_ROOT;
+}
+
+static struct call_path_root *call_path_root__new(void)
+{
+	struct call_path_root *cpr;
+
+	cpr = zalloc(sizeof(struct call_path_root));
+	if (!cpr)
+		return NULL;
+	call_path__init(&cpr->call_path, NULL, NULL, 0, false);
+	INIT_LIST_HEAD(&cpr->blocks);
+	return cpr;
+}
+
+static void call_path_root__free(struct call_path_root *cpr)
+{
+	struct call_path_block *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
+		list_del(&pos->node);
+		free(pos);
+	}
+	free(cpr);
+}
+
+static struct call_path *call_path__new(struct call_path_root *cpr,
+					struct call_path *parent,
+					struct symbol *sym, u64 ip,
+					bool in_kernel)
+{
+	struct call_path_block *cpb;
+	struct call_path *cp;
+	size_t n;
+
+	if (cpr->next < cpr->sz) {
+		cpb = list_last_entry(&cpr->blocks, struct call_path_block,
+				      node);
+	} else {
+		cpb = zalloc(sizeof(struct call_path_block));
+		if (!cpb)
+			return NULL;
+		list_add_tail(&cpb->node, &cpr->blocks);
+		cpr->sz += CALL_PATH_BLOCK_SIZE;
+	}
+
+	n = cpr->next++ & CALL_PATH_BLOCK_MASK;
+	cp = &cpb->cp[n];
+
+	call_path__init(cp, parent, sym, ip, in_kernel);
+
+	return cp;
+}
+
+static struct call_path *call_path__findnew(struct call_path_root *cpr,
+					    struct call_path *parent,
+					    struct symbol *sym, u64 ip, u64 ks)
+{
+	struct rb_node **p;
+	struct rb_node *node_parent = NULL;
+	struct call_path *cp;
+	bool in_kernel = ip >= ks;
+
+	if (sym)
+		ip = 0;
+
+	if (!parent)
+		return call_path__new(cpr, parent, sym, ip, in_kernel);
+
+	p = &parent->children.rb_node;
+	while (*p != NULL) {
+		node_parent = *p;
+		cp = rb_entry(node_parent, struct call_path, rb_node);
+
+		if (cp->sym == sym && cp->ip == ip)
+			return cp;
+
+		if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	cp = call_path__new(cpr, parent, sym, ip, in_kernel);
+	if (!cp)
+		return NULL;
+
+	rb_link_node(&cp->rb_node, node_parent, p);
+	rb_insert_color(&cp->rb_node, &parent->children);
+
+	return cp;
+}
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+			   void *data)
+{
+	struct call_return_processor *crp;
+
+	crp = zalloc(sizeof(struct call_return_processor));
+	if (!crp)
+		return NULL;
+	crp->cpr = call_path_root__new();
+	if (!crp->cpr)
+		goto out_free;
+	crp->process = process;
+	crp->data = data;
+	return crp;
+
+out_free:
+	free(crp);
+	return NULL;
+}
+
+void call_return_processor__free(struct call_return_processor *crp)
+{
+	if (crp) {
+		call_path_root__free(crp->cpr);
+		free(crp);
+	}
+}
+
+static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
+				 u64 timestamp, u64 ref, struct call_path *cp,
+				 bool no_call)
+{
+	struct thread_stack_entry *tse;
+	int err;
+
+	if (ts->cnt == ts->sz) {
+		err = thread_stack__grow(ts);
+		if (err)
+			return err;
+	}
+
+	tse = &ts->stack[ts->cnt++];
+	tse->ret_addr = ret_addr;
+	tse->timestamp = timestamp;
+	tse->ref = ref;
+	tse->branch_count = ts->branch_count;
+	tse->cp = cp;
+	tse->no_call = no_call;
+
+	return 0;
+}
+
+static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
+				u64 ret_addr, u64 timestamp, u64 ref,
+				struct symbol *sym)
+{
+	int err;
+
+	if (!ts->cnt)
+		return 1;
+
+	if (ts->cnt == 1) {
+		struct thread_stack_entry *tse = &ts->stack[0];
+
+		if (tse->cp->sym == sym)
+			return thread_stack__call_return(thread, ts, --ts->cnt,
+							 timestamp, ref, false);
+	}
+
+	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+		return thread_stack__call_return(thread, ts, --ts->cnt,
+						 timestamp, ref, false);
+	} else {
+		size_t i = ts->cnt - 1;
+
+		while (i--) {
+			if (ts->stack[i].ret_addr != ret_addr)
+				continue;
+			i += 1;
+			while (ts->cnt > i) {
+				err = thread_stack__call_return(thread, ts,
+								--ts->cnt,
+								timestamp, ref,
+								true);
+				if (err)
+					return err;
+			}
+			return thread_stack__call_return(thread, ts, --ts->cnt,
+							 timestamp, ref, false);
+		}
+	}
+
+	return 1;
+}
+
+static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
+				struct perf_sample *sample,
+				struct addr_location *from_al,
+				struct addr_location *to_al, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp;
+	struct symbol *sym;
+	u64 ip;
+
+	if (sample->ip) {
+		ip = sample->ip;
+		sym = from_al->sym;
+	} else if (sample->addr) {
+		ip = sample->addr;
+		sym = to_al->sym;
+	} else {
+		return 0;
+	}
+
+	cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
+				     true);
+}
+
+static int thread_stack__no_call_return(struct thread *thread,
+					struct thread_stack *ts,
+					struct perf_sample *sample,
+					struct addr_location *from_al,
+					struct addr_location *to_al, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp, *parent;
+	u64 ks = ts->kernel_start;
+	int err;
+
+	if (sample->ip >= ks && sample->addr < ks) {
+		/* Return to userspace, so pop all kernel addresses */
+		while (thread_stack__in_kernel(ts)) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							sample->time, ref,
+							true);
+			if (err)
+				return err;
+		}
+
+		/* If the stack is empty, push the userspace address */
+		if (!ts->cnt) {
+			cp = call_path__findnew(cpr, &cpr->call_path,
+						to_al->sym, sample->addr,
+						ts->kernel_start);
+			if (!cp)
+				return -ENOMEM;
+			return thread_stack__push_cp(ts, 0, sample->time, ref,
+						     cp, true);
+		}
+	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+		/* Return to userspace, so pop all kernel addresses */
+		while (thread_stack__in_kernel(ts)) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							sample->time, ref,
+							true);
+			if (err)
+				return err;
+		}
+	}
+
+	if (ts->cnt)
+		parent = ts->stack[ts->cnt - 1].cp;
+	else
+		parent = &cpr->call_path;
+
+	/* This 'return' had no 'call', so push and pop top of stack */
+	cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
+				    true);
+	if (err)
+		return err;
+
+	return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
+				    to_al->sym);
+}
+
+static int thread_stack__trace_begin(struct thread *thread,
+				     struct thread_stack *ts, u64 timestamp,
+				     u64 ref)
+{
+	struct thread_stack_entry *tse;
+	int err;
+
+	if (!ts->cnt)
+		return 0;
+
+	/* Pop trace end */
+	tse = &ts->stack[ts->cnt - 1];
+	if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						timestamp, ref, false);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int thread_stack__trace_end(struct thread_stack *ts,
+				   struct perf_sample *sample, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp;
+	u64 ret_addr;
+
+	/* No point having 'trace end' on the bottom of the stack */
+	if (!ts->cnt || (ts->cnt == 1 && ts->stack[0].ref == ref))
+		return 0;
+
+	cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	ret_addr = sample->ip + sample->insn_len;
+
+	return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
+				     false);
+}
+
+int thread_stack__process(struct thread *thread, struct comm *comm,
+			  struct perf_sample *sample,
+			  struct addr_location *from_al,
+			  struct addr_location *to_al, u64 ref,
+			  struct call_return_processor *crp)
+{
+	struct thread_stack *ts = thread->ts;
+	int err = 0;
+
+	if (ts) {
+		if (!ts->crp) {
+			/* Supersede thread_stack__event() */
+			thread_stack__free(thread);
+			thread->ts = thread_stack__new(thread, crp);
+			if (!thread->ts)
+				return -ENOMEM;
+			ts = thread->ts;
+			ts->comm = comm;
+		}
+	} else {
+		thread->ts = thread_stack__new(thread, crp);
+		if (!thread->ts)
+			return -ENOMEM;
+		ts = thread->ts;
+		ts->comm = comm;
+	}
+
+	/* Flush stack on exec */
+	if (ts->comm != comm && thread->pid_ == thread->tid) {
+		err = thread_stack__flush(thread, ts);
+		if (err)
+			return err;
+		ts->comm = comm;
+	}
+
+	/* If the stack is empty, put the current symbol on the stack */
+	if (!ts->cnt) {
+		err = thread_stack__bottom(thread, ts, sample, from_al, to_al,
+					   ref);
+		if (err)
+			return err;
+	}
+
+	ts->branch_count += 1;
+	ts->last_time = sample->time;
+
+	if (sample->flags & PERF_IP_FLAG_CALL) {
+		struct call_path_root *cpr = ts->crp->cpr;
+		struct call_path *cp;
+		u64 ret_addr;
+
+		if (!sample->ip || !sample->addr)
+			return 0;
+
+		ret_addr = sample->ip + sample->insn_len;
+		if (ret_addr == sample->addr)
+			return 0; /* Zero-length calls are excluded */
+
+		cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+					to_al->sym, sample->addr,
+					ts->kernel_start);
+		if (!cp)
+			return -ENOMEM;
+		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
+					    cp, false);
+	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
+		if (!sample->ip || !sample->addr)
+			return 0;
+
+		err = thread_stack__pop_cp(thread, ts, sample->addr,
+					   sample->time, ref, from_al->sym);
+		if (err) {
+			if (err < 0)
+				return err;
+			err = thread_stack__no_call_return(thread, ts, sample,
+							   from_al, to_al, ref);
+		}
+	} else if (sample->flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		err = thread_stack__trace_begin(thread, ts, sample->time, ref);
+	} else if (sample->flags & PERF_IP_FLAG_TRACE_END) {
+		err = thread_stack__trace_end(ts, sample, ref);
+	}
+
+	return err;
+}

93 lines not on this page · raw message

index be128b075a32..bccb83120971 100644
@@ -208,6 +208,15 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 	return 0;
 }
 
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+			   const char *name)
+{
+	if (dbe->export_branch_type)
+		return dbe->export_branch_type(dbe, branch_type, name);
+
+	return 0;
+}
+
 int db_export__sample(struct db_export *dbe, union perf_event *event,
 		      struct perf_sample *sample, struct perf_evsel *evsel,
 		      struct thread *thread, struct addr_location *al)

@@ -268,3 +277,42 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 	return 0;
 }
+
+static struct {
+	u32 branch_type;
+	const char *name;
+} branch_types[] = {
+	{0, "no branch"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "conditional jump"},
+	{PERF_IP_FLAG_BRANCH, "unconditional jump"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT,
+	 "software interrupt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT,
+	 "return from interrupt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET,
+	 "system call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET,
+	 "return from system call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "asynchronous branch"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+	 PERF_IP_FLAG_INTERRUPT, "hardware interrupt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "transaction abort"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "trace begin"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "trace end"},
+	{0, NULL}
+};
+
+int db_export__branch_types(struct db_export *dbe)
+{
+	int i, err = 0;
+
+	for (i = 0; branch_types[i].name ; i++) {
+		err = db_export__branch_type(dbe, branch_types[i].branch_type,
+					     branch_types[i].name);
+		if (err)
+			break;
+	}
+	return err;
+}

index b3643e8e5750..e4baa45ead70 100644
@@ -54,6 +54,8 @@ struct db_export {
 			  struct machine *machine);
 	int (*export_symbol)(struct db_export *dbe, struct symbol *sym,
 			     struct dso *dso);
+	int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
+				  const char *name);
 	int (*export_sample)(struct db_export *dbe, struct export_sample *es);
 	u64 evsel_last_db_id;
 	u64 machine_last_db_id;

@@ -79,8 +81,12 @@ int db_export__dso(struct db_export *dbe, struct dso *dso,
 		   struct machine *machine);
 int db_export__symbol(struct db_export *dbe, struct symbol *sym,
 		      struct dso *dso);
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+			   const char *name);
 int db_export__sample(struct db_export *dbe, union perf_event *event,
 		      struct perf_sample *sample, struct perf_evsel *evsel,
 		      struct thread *thread, struct addr_location *al);
 
+int db_export__branch_types(struct db_export *dbe);
+
 #endif

index 2fd7ee8f18c7..f3ca7798b3d0 100644
@@ -66,6 +66,7 @@ struct tables {
 	PyObject		*comm_thread_handler;
 	PyObject		*dso_handler;
 	PyObject		*symbol_handler;
+	PyObject		*branch_type_handler;
 	PyObject		*sample_handler;
 	bool			db_export_mode;
 };

@@ -664,13 +665,31 @@ static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
 	return 0;
 }
 
+static int python_export_branch_type(struct db_export *dbe, u32 branch_type,
+				     const char *name)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_s32(t, 0, branch_type);
+	tuple_set_string(t, 1, name);
+
+	call_object(tables->branch_type_handler, t, "branch_type_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
 static int python_export_sample(struct db_export *dbe,
 				struct export_sample *es)
 {
 	struct tables *tables = container_of(dbe, struct tables, dbe);
 	PyObject *t;
 
-	t = tuple_new(19);
+	t = tuple_new(21);
 
 	tuple_set_u64(t, 0, es->db_id);
 	tuple_set_u64(t, 1, es->evsel->db_id);

@@ -691,6 +710,8 @@ static int python_export_sample(struct db_export *dbe,
 	tuple_set_u64(t, 16, es->sample->weight);
 	tuple_set_u64(t, 17, es->sample->transaction);
 	tuple_set_u64(t, 18, es->sample->data_src);
+	tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
+	tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
 
 	call_object(tables->sample_handler, t, "sample_table");
 

@@ -861,6 +882,7 @@ static void set_table_handlers(struct tables *tables)
 	SET_TABLE_HANDLER(comm_thread);
 	SET_TABLE_HANDLER(dso);
 	SET_TABLE_HANDLER(symbol);
+	SET_TABLE_HANDLER(branch_type);
 	SET_TABLE_HANDLER(sample);
 }
 

@@ -910,6 +932,12 @@ static int python_start_script(const char *script, int argc, const char **argv)
 
 	set_table_handlers(tables);
 
+	if (tables->db_export_mode) {
+		err = db_export__branch_types(&tables->dbe);
+		if (err)
+			goto error;
+	}
+
 	return err;
 error:
 	Py_Finalize();

index bccb83120971..017ecbb0ec05 100644
@@ -21,6 +21,7 @@
 #include "comm.h"
 #include "symbol.h"
 #include "event.h"
+#include "thread-stack.h"
 #include "db-export.h"
 
 int db_export__init(struct db_export *dbe)

@@ -29,8 +30,10 @@ int db_export__init(struct db_export *dbe)
 	return 0;
 }
 
-void db_export__exit(struct db_export *dbe __maybe_unused)
+void db_export__exit(struct db_export *dbe)
 {
+	call_return_processor__free(dbe->crp);
+	dbe->crp = NULL;
 }
 
 int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)

@@ -270,6 +273,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 				     &es.addr_sym_db_id, &es.addr_offset);
 		if (err)
 			return err;
+		if (dbe->crp) {
+			err = thread_stack__process(thread, comm, sample, al,
+						    &addr_al, es.db_id,
+						    dbe->crp);
+			if (err)
+				return err;
+		}
 	}
 
 	if (dbe->export_sample)

@@ -316,3 +326,43 @@ int db_export__branch_types(struct db_export *dbe)
 	}
 	return err;
 }
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp)
+{
+	int err;
+
+	if (cp->db_id)
+		return 0;
+
+	if (cp->parent) {
+		err = db_export__call_path(dbe, cp->parent);
+		if (err)
+			return err;
+	}
+
+	cp->db_id = ++dbe->call_path_last_db_id;
+
+	if (dbe->export_call_path)
+		return dbe->export_call_path(dbe, cp);
+
+	return 0;
+}
+
+int db_export__call_return(struct db_export *dbe, struct call_return *cr)
+{
+	int err;
+
+	if (cr->db_id)
+		return 0;
+
+	err = db_export__call_path(dbe, cr->cp);
+	if (err)
+		return err;
+
+	cr->db_id = ++dbe->call_return_last_db_id;
+
+	if (dbe->export_call_return)
+		return dbe->export_call_return(dbe, cr);
+
+	return 0;
+}

index e4baa45ead70..dd5ac2ae97d4 100644
@@ -25,6 +25,9 @@ struct comm;
 struct dso;
 struct perf_sample;
 struct addr_location;
+struct call_return_processor;
+struct call_path;
+struct call_return;
 
 struct export_sample {
 	union perf_event	*event;

@@ -57,6 +60,10 @@ struct db_export {
 	int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
 				  const char *name);
 	int (*export_sample)(struct db_export *dbe, struct export_sample *es);
+	int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
+	int (*export_call_return)(struct db_export *dbe,
+				  struct call_return *cr);
+	struct call_return_processor *crp;
 	u64 evsel_last_db_id;
 	u64 machine_last_db_id;
 	u64 thread_last_db_id;

@@ -65,6 +72,8 @@ struct db_export {
 	u64 dso_last_db_id;
 	u64 symbol_last_db_id;
 	u64 sample_last_db_id;
+	u64 call_path_last_db_id;
+	u64 call_return_last_db_id;
 };
 
 int db_export__init(struct db_export *dbe);

@@ -89,4 +98,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 int db_export__branch_types(struct db_export *dbe);
 
+int db_export__call_path(struct db_export *dbe, struct call_path *cp);
+int db_export__call_return(struct db_export *dbe, struct call_return *cr);
+
 #endif

120 lines not on this page · raw message

index 017ecbb0ec05..c81dae399763 100644
@@ -21,17 +21,74 @@
 #include "comm.h"
 #include "symbol.h"
 #include "event.h"
+#include "util.h"
 #include "thread-stack.h"
 #include "db-export.h"
 
+struct deferred_export {
+	struct list_head node;
+	struct comm *comm;
+};
+
+static int db_export__deferred(struct db_export *dbe)
+{
+	struct deferred_export *de;
+	int err;
+
+	while (!list_empty(&dbe->deferred)) {
+		de = list_entry(dbe->deferred.next, struct deferred_export,
+				node);
+		err = dbe->export_comm(dbe, de->comm);
+		list_del(&de->node);
+		free(de);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void db_export__free_deferred(struct db_export *dbe)
+{
+	struct deferred_export *de;
+
+	while (!list_empty(&dbe->deferred)) {
+		de = list_entry(dbe->deferred.next, struct deferred_export,
+				node);
+		list_del(&de->node);
+		free(de);
+	}
+}
+
+static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
+{
+	struct deferred_export *de;
+
+	de = zalloc(sizeof(struct deferred_export));
+	if (!de)
+		return -ENOMEM;
+
+	de->comm = comm;
+	list_add_tail(&de->node, &dbe->deferred);
+
+	return 0;
+}
+
 int db_export__init(struct db_export *dbe)
 {
 	memset(dbe, 0, sizeof(struct db_export));
+	INIT_LIST_HEAD(&dbe->deferred);
 	return 0;
 }
 
+int db_export__flush(struct db_export *dbe)
+{
+	return db_export__deferred(dbe);
+}
+
 void db_export__exit(struct db_export *dbe)
 {
+	db_export__free_deferred(dbe);
 	call_return_processor__free(dbe->crp);
 	dbe->crp = NULL;
 }

@@ -115,7 +172,10 @@ int db_export__comm(struct db_export *dbe, struct comm *comm,
 	comm->db_id = ++dbe->comm_last_db_id;
 
 	if (dbe->export_comm) {
-		err = dbe->export_comm(dbe, comm);
+		if (main_thread->comm_set)
+			err = dbe->export_comm(dbe, comm);
+		else
+			err = db_export__defer_comm(dbe, comm);
 		if (err)
 			return err;
 	}

index dd5ac2ae97d4..adbd22d66798 100644
@@ -17,6 +17,7 @@
 #define __PERF_DB_EXPORT_H
 
 #include <linux/types.h>
+#include <linux/list.h>
 
 struct perf_evsel;
 struct machine;

@@ -74,9 +75,11 @@ struct db_export {
 	u64 sample_last_db_id;
 	u64 call_path_last_db_id;
 	u64 call_return_last_db_id;
+	struct list_head deferred;
 };
 
 int db_export__init(struct db_export *dbe);
+int db_export__flush(struct db_export *dbe);
 void db_export__exit(struct db_export *dbe);
 int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
 int db_export__machine(struct db_export *dbe, struct machine *machine);

index cb1d9602f418..118bc62850a8 100644
@@ -1030,7 +1030,9 @@ error:
 
 static int python_flush_script(void)
 {
-	return 0;
+	struct tables *tables = &tables_global;
+
+	return db_export__flush(&tables->dbe);
 }
 
 /*

index 0247acfdfaca..36a607cf8f50 100644
@@ -21,8 +21,10 @@ char dso__symtab_origin(const struct dso *dso)
 		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]		= 'b',
 		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]		= 'd',
 		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]		= 'K',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP]	= 'm',
 		[DSO_BINARY_TYPE__GUEST_KALLSYMS]		= 'g',
 		[DSO_BINARY_TYPE__GUEST_KMODULE]		= 'G',
+		[DSO_BINARY_TYPE__GUEST_KMODULE_COMP]		= 'M',
 		[DSO_BINARY_TYPE__GUEST_VMLINUX]		= 'V',
 	};
 

@@ -112,11 +114,13 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		break;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
+	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
 		path__join3(filename, size, symbol_conf.symfs,
 			    root_dir, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
 		__symbol__join_symfs(filename, size, dso->long_name);
 		break;
 

@@ -137,6 +141,77 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	return ret;
 }
 
+static int decompress_dummy(const char *input __maybe_unused,
+			    int output __maybe_unused)
+{
+	return -1;
+}
+
+static const struct {
+	const char *fmt;
+	int (*decompress)(const char *input, int output);
+} compressions[] = {
+	{ "gz", decompress_dummy },
+	{ NULL, },
+};
+
+bool is_supported_compression(const char *ext)
+{
+	unsigned i;
+
+	for (i = 0; compressions[i].fmt; i++) {
+		if (!strcmp(ext, compressions[i].fmt))
+			return true;
+	}
+	return false;
+}
+
+bool is_kmodule_extension(const char *ext)
+{
+	if (strncmp(ext, "ko", 2))
+		return false;
+
+	if (ext[2] == '\0' || (ext[2] == '.' && is_supported_compression(ext+3)))
+		return true;
+
+	return false;
+}
+
+bool is_kernel_module(const char *pathname, bool *compressed)
+{
+	const char *ext = strrchr(pathname, '.');
+
+	if (ext == NULL)
+		return false;
+
+	if (is_supported_compression(ext + 1)) {
+		if (compressed)
+			*compressed = true;
+		ext -= 3;
+	} else if (compressed)
+		*compressed = false;
+
+	return is_kmodule_extension(ext + 1);
+}
+
+bool decompress_to_file(const char *ext, const char *filename, int output_fd)
+{
+	unsigned i;
+
+	for (i = 0; compressions[i].fmt; i++) {
+		if (!strcmp(ext, compressions[i].fmt))
+			return !compressions[i].decompress(filename,
+							   output_fd);
+	}
+	return false;
+}
+
+bool dso__needs_decompress(struct dso *dso)
+{
+	return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
+}
+
 /*
  * Global list of open DSOs and the counter.
  */

index a316e4af321f..3782c82c6e44 100644
@@ -22,7 +22,9 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
 	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__GUEST_KMODULE_COMP,
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
 	DSO_BINARY_TYPE__KCORE,
 	DSO_BINARY_TYPE__GUEST_KCORE,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,

@@ -185,6 +187,11 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
+bool is_supported_compression(const char *ext);
+bool is_kmodule_extension(const char *ext);
+bool is_kernel_module(const char *pathname, bool *compressed);
+bool decompress_to_file(const char *ext, const char *filename, int output_fd);
+bool dso__needs_decompress(struct dso *dso);
 
 /*
  * The dso__data_* external interface provides following functions:

index 51a630301afa..946c7d62cb6e 100644
@@ -464,6 +464,7 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 {
 	struct map *map;
 	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
+	bool compressed;
 
 	if (dso == NULL)
 		return NULL;

@@ -476,6 +477,11 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
 	else
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/* _KMODULE_COMP should be next to _KMODULE */
+	if (is_kernel_module(filename, &compressed) && compressed)
+		dso->symtab_type++;
+
 	map_groups__insert(&machine->kmaps, map);
 	return map;
 }

@@ -861,8 +867,14 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
 			struct map *map;
 			char *long_name;
 
-			if (dot == NULL || strcmp(dot, ".ko"))
+			if (dot == NULL)
 				continue;
+
+			/* On some system, modules are compressed like .ko.gz */
+			if (is_supported_compression(dot + 1) &&
+			    is_kmodule_extension(dot - 2))
+				dot -= 3;
+
 			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
 				 (int)(dot - dent->d_name), dent->d_name);
 

@@ -1044,6 +1056,11 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			dot = strrchr(name, '.');
 			if (dot == NULL)
 				goto out_problem;
+			/* On some system, modules are compressed like .ko.gz */
+			if (is_supported_compression(dot + 1))
+				dot -= 3;
+			if (!is_kmodule_extension(dot + 1))
+				goto out_problem;
 			snprintf(short_module_name, sizeof(short_module_name),
 					"[%.*s]", (int)(dot - name), name);
 			strxfrchar(short_module_name, '-', '_');

index 1e23a5bfb044..efc7eb6b8f0f 100644
@@ -546,6 +546,35 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata)
 	return 0;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name,
+			      enum dso_binary_type type)
+{
+	int fd;
+	const char *ext = strrchr(name, '.');
+	char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
+
+	if ((type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
+	     type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP) ||
+	    type != dso->symtab_type)
+		return -1;
+
+	if (!ext || !is_supported_compression(ext + 1))
+		return -1;
+
+	fd = mkstemp(tmpbuf);
+	if (fd < 0)
+		return -1;
+
+	if (!decompress_to_file(ext + 1, name, fd)) {
+		close(fd);
+		fd = -1;
+	}
+
+	unlink(tmpbuf);
+
+	return fd;
+}
+
 bool symsrc__possibly_runtime(struct symsrc *ss)
 {
 	return ss->dynsym || ss->opdsec;

@@ -571,7 +600,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	Elf *elf;
 	int fd;
 
-	fd = open(name, O_RDONLY);
+	if (dso__needs_decompress(dso))
+		fd = decompress_kmodule(dso, name, type);
+	else
+		fd = open(name, O_RDONLY);
+
 	if (fd < 0)
 		return -1;
 

index 078331140d8c..c69915c9d5bc 100644
@@ -51,7 +51,9 @@ static enum dso_binary_type binary_type_symtab[] = {
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
 	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__GUEST_KMODULE_COMP,
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };

@@ -1300,7 +1302,9 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 		return dso->kernel == DSO_TYPE_GUEST_KERNEL;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
+	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
 		/*
 		 * kernel modules know their symtab type - it's set when
 		 * creating a module dso in machine__new_module().

@@ -1368,7 +1372,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		return -1;
 
 	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 
 	/*
 	 * Iterate over candidate debug images.

index a7d022e161c0..652e0098eba6 100644
@@ -93,6 +93,10 @@
 # include "test-sync-compare-and-swap.c"
 #undef main
 
+#define main main_test_zlib
+# include "test-zlib.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();

@@ -116,6 +120,7 @@ int main(int argc, char *argv[])
 	main_test_stackprotector_all();
 	main_test_libdw_dwarf_unwind();
 	main_test_sync_compare_and_swap(argc, argv);
+	main_test_zlib();
 
 	return 0;
 }

new file mode 100644
index 000000000000..e111fff6240e
@@ -0,0 +1,9 @@
+#include <zlib.h>
+
+int main(void)
+{
+	z_stream zs;
+
+	inflateInit(&zs);
+	return 0;
+}

index 36a607cf8f50..45be944d450a 100644
@@ -141,18 +141,14 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	return ret;
 }
 
-static int decompress_dummy(const char *input __maybe_unused,
-			    int output __maybe_unused)
-{
-	return -1;
-}
-
 static const struct {
 	const char *fmt;
 	int (*decompress)(const char *input, int output);
 } compressions[] = {
-	{ "gz", decompress_dummy },
-	{ NULL, },
+#ifdef HAVE_ZLIB_SUPPORT
+	{ "gz", gzip_decompress_to_file },
+#endif
+	{ NULL, NULL },
 };
 
 bool is_supported_compression(const char *ext)

index 80bfdaa0e2a4..7dc44cfe25b3 100644
@@ -351,4 +351,9 @@ void mem_bswap_32(void *src, int byte_size);
 
 const char *get_filename_for_perf_kvm(void);
 bool find_process(const char *name);
+
+#ifdef HAVE_ZLIB_SUPPORT
+int gzip_decompress_to_file(const char *input, int output_fd);
+#endif
+
 #endif /* GIT_COMPAT_UTIL_H */

78 lines not on this page · raw message

index 0ecf4a304cbc..be8d02eb97e9 100644
@@ -297,10 +297,8 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 	return err;
 }
 
-static int dsos__write_buildid_table(struct perf_header *header, int fd)
+static int perf_session__write_buildid_table(struct perf_session *session, int fd)
 {
-	struct perf_session *session = container_of(header,
-			struct perf_session, header);
 	struct rb_node *nd;
 	int err = machine__write_buildid_table(&session->machines.host, fd);
 

@@ -523,7 +521,7 @@ static int write_build_id(int fd, struct perf_header *h,
 	if (!perf_session__read_build_ids(session, true))
 		return -1;
 
-	err = dsos__write_buildid_table(h, fd);
+	err = perf_session__write_buildid_table(session, fd);
 	if (err < 0) {
 		pr_debug("failed to write buildid table\n");
 		return err;

index 2e7c68e39330..dd2a3e52ada1 100644
@@ -15,6 +15,8 @@
 #include "debug.h"
 #include "session.h"
 #include "tool.h"
+#include "header.h"
+#include "vdso.h"
 
 int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 			   union perf_event *event,

@@ -105,3 +107,335 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 			 build_id_hex, build_id_hex + 2);
 	return bf;
 }
+
+#define dsos__for_each_with_build_id(pos, head)	\
+	list_for_each_entry(pos, head, node)	\
+		if (!pos->has_build_id)		\
+			continue;		\
+		else
+
+static int write_buildid(const char *name, size_t name_len, u8 *build_id,
+			 pid_t pid, u16 misc, int fd)
+{
+	int err;
+	struct build_id_event b;
+	size_t len;
+
+	len = name_len + 1;
+	len = PERF_ALIGN(len, NAME_ALIGN);
+
+	memset(&b, 0, sizeof(b));
+	memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
+	b.pid = pid;
+	b.header.misc = misc;
+	b.header.size = sizeof(b) + len;
+
+	err = writen(fd, &b, sizeof(b));
+	if (err < 0)
+		return err;
+
+	return write_padded(fd, name, name_len + 1, len);
+}
+
+static int __dsos__write_buildid_table(struct list_head *head,
+				       struct machine *machine,
+				       pid_t pid, u16 misc, int fd)
+{
+	char nm[PATH_MAX];
+	struct dso *pos;
+
+	dsos__for_each_with_build_id(pos, head) {
+		int err;
+		const char *name;
+		size_t name_len;
+
+		if (!pos->hit)
+			continue;
+
+		if (dso__is_vdso(pos)) {
+			name = pos->short_name;
+			name_len = pos->short_name_len + 1;
+		} else if (dso__is_kcore(pos)) {
+			machine__mmap_name(machine, nm, sizeof(nm));
+			name = nm;
+			name_len = strlen(nm) + 1;
+		} else {
+			name = pos->long_name;
+			name_len = pos->long_name_len + 1;
+		}
+
+		err = write_buildid(name, name_len, pos->build_id,
+				    pid, misc, fd);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int machine__write_buildid_table(struct machine *machine, int fd)
+{
+	int err;
+	u16 kmisc = PERF_RECORD_MISC_KERNEL,
+	    umisc = PERF_RECORD_MISC_USER;
+
+	if (!machine__is_host(machine)) {
+		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+		umisc = PERF_RECORD_MISC_GUEST_USER;
+	}
+
+	err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
+					  machine->pid, kmisc, fd);
+	if (err == 0)
+		err = __dsos__write_buildid_table(&machine->user_dsos.head,
+						  machine, machine->pid, umisc,
+						  fd);
+	return err;
+}
+
+int perf_session__write_buildid_table(struct perf_session *session, int fd)
+{
+	struct rb_node *nd;
+	int err = machine__write_buildid_table(&session->machines.host, fd);
+
+	if (err)
+		return err;
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		err = machine__write_buildid_table(pos, fd);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+static int __dsos__hit_all(struct list_head *head)
+{
+	struct dso *pos;
+
+	list_for_each_entry(pos, head, node)
+		pos->hit = true;
+
+	return 0;
+}
+
+static int machine__hit_all_dsos(struct machine *machine)
+{
+	int err;
+
+	err = __dsos__hit_all(&machine->kernel_dsos.head);
+	if (err)
+		return err;
+
+	return __dsos__hit_all(&machine->user_dsos.head);
+}
+
+int dsos__hit_all(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int err;
+
+	err = machine__hit_all_dsos(&session->machines.host);
+	if (err)
+		return err;
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+		err = machine__hit_all_dsos(pos);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+			  const char *name, bool is_kallsyms, bool is_vdso)
+{
+	const size_t size = PATH_MAX;
+	char *realname, *filename = zalloc(size),
+	     *linkname = zalloc(size), *targetname;
+	int len, err = -1;
+	bool slash = is_kallsyms || is_vdso;
+
+	if (is_kallsyms) {
+		if (symbol_conf.kptr_restrict) {
+			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+			err = 0;
+			goto out_free;
+		}
+		realname = (char *) name;
+	} else
+		realname = realpath(name, NULL);
+
+	if (realname == NULL || filename == NULL || linkname == NULL)
+		goto out_free;
+
+	len = scnprintf(filename, size, "%s%s%s",
+		       debugdir, slash ? "/" : "",
+		       is_vdso ? DSO__NAME_VDSO : realname);
+	if (mkdir_p(filename, 0755))
+		goto out_free;
+
+	snprintf(filename + len, size - len, "/%s", sbuild_id);
+
+	if (access(filename, F_OK)) {
+		if (is_kallsyms) {
+			 if (copyfile("/proc/kallsyms", filename))
+				goto out_free;
+		} else if (link(realname, filename) && copyfile(name, filename))
+			goto out_free;
+	}
+
+	len = scnprintf(linkname, size, "%s/.build-id/%.2s",
+		       debugdir, sbuild_id);
+
+	if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
+		goto out_free;
+
+	snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
+	targetname = filename + strlen(debugdir) - 5;
+	memcpy(targetname, "../..", 5);
+
+	if (symlink(targetname, linkname) == 0)
+		err = 0;
+out_free:
+	if (!is_kallsyms)
+		free(realname);
+	free(filename);
+	free(linkname);
+	return err;
+}
+
+static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
+				 const char *name, const char *debugdir,
+				 bool is_kallsyms, bool is_vdso)
+{
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	build_id__sprintf(build_id, build_id_size, sbuild_id);
+
+	return build_id_cache__add_s(sbuild_id, debugdir, name,
+				     is_kallsyms, is_vdso);
+}
+
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
+{
+	const size_t size = PATH_MAX;
+	char *filename = zalloc(size),
+	     *linkname = zalloc(size);
+	int err = -1;
+
+	if (filename == NULL || linkname == NULL)
+		goto out_free;
+
+	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+		 debugdir, sbuild_id, sbuild_id + 2);
+
+	if (access(linkname, F_OK))
+		goto out_free;
+
+	if (readlink(linkname, filename, size - 1) < 0)
+		goto out_free;
+
+	if (unlink(linkname))
+		goto out_free;
+
+	/*
+	 * Since the link is relative, we must make it absolute:
+	 */
+	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+		 debugdir, sbuild_id, filename);
+
+	if (unlink(linkname))
+		goto out_free;
+
+	err = 0;
+out_free:
+	free(filename);
+	free(linkname);
+	return err;
+}
+
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+			       const char *debugdir)
+{
+	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+	bool is_vdso = dso__is_vdso(dso);
+	const char *name = dso->long_name;
+	char nm[PATH_MAX];
+
+	if (dso__is_kcore(dso)) {
+		is_kallsyms = true;
+		machine__mmap_name(machine, nm, sizeof(nm));
+		name = nm;
+	}
+	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
+				     debugdir, is_kallsyms, is_vdso);
+}
+
+static int __dsos__cache_build_ids(struct list_head *head,
+				   struct machine *machine, const char *debugdir)
+{
+	struct dso *pos;
+	int err = 0;
+
+	dsos__for_each_with_build_id(pos, head)
+		if (dso__cache_build_id(pos, machine, debugdir))
+			err = -1;
+
+	return err;
+}
+
+static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
+{
+	int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
+					  debugdir);
+	ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
+				       debugdir);
+	return ret;
+}
+
+int perf_session__cache_build_ids(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int ret;
+	char debugdir[PATH_MAX];
+
+	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
+
+	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
+		return -1;
+
+	ret = machine__cache_build_ids(&session->machines.host, debugdir);
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= machine__cache_build_ids(pos, debugdir);
+	}
+	return ret ? -1 : 0;
+}
+
+static bool machine__read_build_ids(struct machine *machine, bool with_hits)
+{
+	bool ret;
+
+	ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
+	ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
+	return ret;
+}
+
+bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
+{
+	struct rb_node *nd;
+	bool ret = machine__read_build_ids(&session->machines.host, with_hits);
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= machine__read_build_ids(pos, with_hits);
+	}
+
+	return ret;
+}

index ae392561470b..666a3bd4f64e 100644
@@ -15,4 +15,15 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
 			   struct machine *machine);
+
+int dsos__hit_all(struct perf_session *session);
+
+bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
+int perf_session__write_buildid_table(struct perf_session *session, int fd);
+int perf_session__cache_build_ids(struct perf_session *session);
+
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+			  const char *name, bool is_kallsyms, bool is_vdso);
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
+
 #endif

349 lines not on this page · raw message

index 8f5cbaea64a5..3bb90ac172a1 100644
@@ -122,10 +122,6 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
-int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-			  const char *name, bool is_kallsyms, bool is_vdso);
-int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
-
 int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
 				perf_event__handler_t process);

@@ -151,7 +147,9 @@ int perf_event__process_build_id(struct perf_tool *tool,
 				 struct perf_session *session);
 bool is_perf_magic(u64 magic);
 
-int dsos__hit_all(struct perf_session *session);
+#define NAME_ALIGN 64
+
+int write_padded(int fd, const void *bf, size_t count, size_t count_aligned);
 
 /*
  * arch specific callback

index 5091a27e6d28..582c4da155ea 100644
@@ -200,6 +200,17 @@ static int process_buildids(struct record *rec)
 	if (size == 0)
 		return 0;
 
+	/*
+	 * During this process, it'll load kernel map and replace the
+	 * dso->long_name to a real pathname it found.  In this case
+	 * we prefer the vmlinux path like
+	 *   /lib/modules/3.16.4/build/vmlinux
+	 *
+	 * rather than build-id path (in debug directory).
+	 *   $HOME/.debug/.build-id/f0/6e17aa50adf4d00b88925e03775de107611551
+	 */
+	symbol_conf.ignore_vmlinux_buildid = true;
+
 	return __perf_session__process_events(session, start,
 					      size - start,
 					      size, &build_id__mark_dso_hit_ops);

index c69915c9d5bc..c24c5b83156c 100644
@@ -1511,12 +1511,10 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter)
 {
 	int i, err = 0;
-	char *filename;
+	char *filename = NULL;
 
-	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
-		 vmlinux_path__nr_entries + 1);
-
-	filename = dso__build_id_filename(dso, NULL, 0);
+	if (!symbol_conf.ignore_vmlinux_buildid)
+		filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
 		err = dso__load_vmlinux(dso, map, filename, true, filter);
 		if (err > 0)

@@ -1524,6 +1522,9 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 		free(filename);
 	}
 
+	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
+		 vmlinux_path__nr_entries + 1);
+
 	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
 		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
 		if (err > 0)

index eb2c19bf8d90..ded3ca7266de 100644
@@ -105,6 +105,7 @@ struct symbol_conf {
 	unsigned short	nr_events;
 	bool		try_vmlinux_path,
 			ignore_vmlinux,
+			ignore_vmlinux_buildid,
 			show_kernel_path,
 			use_modules,
 			sort_by_name,

index 3e2c156d9c64..76442caca37e 100644
@@ -1269,7 +1269,7 @@ static int __event_process_build_id(struct build_id_event *bev,
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (filename[0] == '[')
+		if (!is_kernel_module(filename, NULL))
 			dso->kernel = dso_type;
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),

index 946c7d62cb6e..53f90e9c65fe 100644
@@ -1085,8 +1085,20 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		 * Should be there already, from the build-id table in
 		 * the header.
 		 */
-		struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
-						     kmmap_prefix);
+		struct dso *kernel = NULL;
+		struct dso *dso;
+
+		list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
+			if (is_kernel_module(dso->long_name, NULL))
+				continue;
+
+			kernel = dso;
+			break;
+		}
+
+		if (kernel == NULL)
+			kernel = __dsos__findnew(&machine->kernel_dsos,
+						 kmmap_prefix);
 		if (kernel == NULL)
 			goto out_problem;
 

index 53f90e9c65fe..52e94902afb1 100644
@@ -1106,6 +1106,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (__machine__create_kernel_maps(machine, kernel) < 0)
 			goto out_problem;
 
+		if (strstr(dso->long_name, "vmlinux"))
+			dso__set_short_name(dso, "[kernel.vmlinux]", false);
+
 		machine__set_kernel_mmap_len(machine, event);
 
 		/*

index 52e94902afb1..85033d80fd6a 100644
@@ -1106,8 +1106,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (__machine__create_kernel_maps(machine, kernel) < 0)
 			goto out_problem;
 
-		if (strstr(dso->long_name, "vmlinux"))
-			dso__set_short_name(dso, "[kernel.vmlinux]", false);
+		if (strstr(kernel->long_name, "vmlinux"))
+			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
 		machine__set_kernel_mmap_len(machine, event);
 

index 01ffd12dc791..40bd21488032 100644
@@ -46,4 +46,21 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
 		__bitmap_or(dst, src1, src2, nbits);
 }
 
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ */
+static inline int test_and_set_bit(int nr, unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old;
+
+	old = *p;
+	*p = old | mask;
+
+	return (old & mask) != 0;
+}
+
 #endif /* _PERF_BITOPS_H */

index dadfa7e54287..c3294163de17 100644
@@ -15,6 +15,8 @@
 #define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
 #define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
 #define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
+#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)
+#define BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
 
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\

index 0a01bac4ce02..22ebc46226e7 100644
@@ -24,6 +24,7 @@
 #include <string.h>
 #include <ctype.h>
 #include <errno.h>
+#include <linux/bitmap.h>
 
 #include "../util.h"
 #include <EXTERN.h>

@@ -57,7 +58,7 @@ INTERP my_perl;
 #define FTRACE_MAX_EVENT				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event_format *events[FTRACE_MAX_EVENT];
+static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
 
 extern struct scripting_context *scripting_context;
 

@@ -238,35 +239,15 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
-{
-	static char ev_name[256];
-	struct event_format *event;
-	int type = evsel->attr.config;
-
-	if (events[type])
-		return events[type];
-
-	events[type] = event = evsel->tp_format;
-	if (!event)
-		return NULL;
-
-	sprintf(ev_name, "%s::%s", event->system, event->name);
-
-	define_event_symbols(event, ev_name, event->print_fmt.args);
-
-	return event;
-}
-
 static void perl_process_tracepoint(struct perf_sample *sample,
 				    struct perf_evsel *evsel,
 				    struct thread *thread)
 {
+	struct event_format *event = evsel->tp_format;
 	struct format_field *field;
 	static char handler[256];
 	unsigned long long val;
 	unsigned long s, ns;
-	struct event_format *event;
 	int pid;
 	int cpu = sample->cpu;
 	void *data = sample->raw_data;

@@ -278,7 +259,6 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 		return;
 
-	event = find_cache_event(evsel);
 	if (!event)
 		die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
 

@@ -286,6 +266,9 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler, "%s::%s", event->system, event->name);
 
+	if (!test_and_set_bit(event->id, events_defined))
+		define_event_symbols(event, handler, event->print_fmt.args);
+
 	s = nsecs / NSECS_PER_SEC;
 	ns = nsecs - s * NSECS_PER_SEC;
 

index 118bc62850a8..d808a328f4dc 100644
@@ -26,6 +26,7 @@
 #include <string.h>
 #include <stdbool.h>
 #include <errno.h>
+#include <linux/bitmap.h>
 
 #include "../../perf.h"
 #include "../debug.h"

@@ -46,7 +47,7 @@ PyMODINIT_FUNC initperf_trace_context(void);
 #define FTRACE_MAX_EVENT				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event_format *events[FTRACE_MAX_EVENT];
+static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
 
 #define MAX_FIELDS	64
 #define N_COMMON_FIELDS	7

@@ -255,31 +256,6 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
-{
-	static char ev_name[256];
-	struct event_format *event;
-	int type = evsel->attr.config;
-
-	/*
- 	 * XXX: Do we really need to cache this since now we have evsel->tp_format
- 	 * cached already? Need to re-read this "cache" routine that as well calls
- 	 * define_event_symbols() :-\
- 	 */
-	if (events[type])
-		return events[type];
-
-	events[type] = event = evsel->tp_format;
-	if (!event)
-		return NULL;
-
-	sprintf(ev_name, "%s__%s", event->system, event->name);
-
-	define_event_symbols(event, ev_name, event->print_fmt.args);
-
-	return event;
-}
-
 static PyObject *get_field_numeric_entry(struct event_format *event,
 		struct format_field *field, void *data)
 {

@@ -403,12 +379,12 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct thread *thread,
 				      struct addr_location *al)
 {
+	struct event_format *event = evsel->tp_format;
 	PyObject *handler, *context, *t, *obj, *callchain;
 	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
 	unsigned long s, ns;
-	struct event_format *event;
 	unsigned n = 0;
 	int pid;
 	int cpu = sample->cpu;

@@ -420,7 +396,6 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 
-	event = find_cache_event(evsel);
 	if (!event)
 		die("ug! no event found for type %d", (int)evsel->attr.config);
 

@@ -428,6 +403,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
+	if (!test_and_set_bit(event->id, events_defined))
+		define_event_symbols(event, handler_name, event->print_fmt.args);
+
 	handler = get_handler(handler_name);
 	if (!handler) {
 		dict = PyDict_New();

index 2f9e68025ede..12b4396c7175 100644
@@ -853,8 +853,6 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_id(evsel);
 	close_cgroup(evsel->cgrp);
 	zfree(&evsel->group_name);
-	if (evsel->tp_format)
-		pevent_free_format(evsel->tp_format);
 	zfree(&evsel->name);
 	perf_evsel__object.fini(evsel);
 }