1 files changed, 215 insertions, 36 deletions

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index d52f27f373ce..41942c2aaa18 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -20,6 +20,7 @@
 #include "thread.h"
 #include "event.h"
 #include "machine.h"
+#include "env.h"
 #include "util.h"
 #include "debug.h"
 #include "symbol.h"
@@ -29,24 +30,41 @@
 
 #define STACK_GROWTH 2048
 
+/*
+ * State of retpoline detection.
+ *
+ * RETPOLINE_NONE: no retpoline detection
+ * X86_RETPOLINE_POSSIBLE: x86 retpoline possible
+ * X86_RETPOLINE_DETECTED: x86 retpoline detected
+ */
+enum retpoline_state_t {
+	RETPOLINE_NONE,
+	X86_RETPOLINE_POSSIBLE,
+	X86_RETPOLINE_DETECTED,
+};
+
 /**
  * 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
+ * @db_id: id used for db-export
  * @cp: call path
  * @no_call: a 'call' was not seen
  * @trace_end: a 'call' but trace ended
+ * @non_call: a branch but not a 'call' to the start of a different symbol
  */
 struct thread_stack_entry {
 	u64 ret_addr;
 	u64 timestamp;
 	u64 ref;
 	u64 branch_count;
+	u64 db_id;
 	struct call_path *cp;
 	bool no_call;
 	bool trace_end;
+	bool non_call;
 };
 
 /**
@@ -62,6 +80,7 @@ struct thread_stack_entry {
  * @crp: call/return processor
  * @comm: current comm
  * @arr_sz: size of array if this is the first element of an array
+ * @rstate: used to detect retpolines
  */
 struct thread_stack {
 	struct thread_stack_entry *stack;
@@ -74,6 +93,7 @@ struct thread_stack {
 	struct call_return_processor *crp;
 	struct comm *comm;
 	unsigned int arr_sz;
+	enum retpoline_state_t rstate;
 };
 
 /*
@@ -113,10 +133,16 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
 	if (err)
 		return err;
 
-	if (thread->mg && thread->mg->machine)
-		ts->kernel_start = machine__kernel_start(thread->mg->machine);
-	else
+	if (thread->mg && thread->mg->machine) {
+		struct machine *machine = thread->mg->machine;
+		const char *arch = perf_env__arch(machine->env);
+
+		ts->kernel_start = machine__kernel_start(machine);
+		if (!strcmp(arch, "x86"))
+			ts->rstate = X86_RETPOLINE_POSSIBLE;
+	} else {
 		ts->kernel_start = 1ULL << 63;
+	}
 	ts->crp = crp;
 
 	return 0;
@@ -256,20 +282,31 @@ static int thread_stack__call_return(struct thread *thread,
 		.comm = ts->comm,
 		.db_id = 0,
 	};
+	u64 *parent_db_id;
 
 	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.db_id = tse->db_id;
 	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;
+	if (tse->non_call)
+		cr.flags |= CALL_RETURN_NON_CALL;
+
+	/*
+	 * The parent db_id must be assigned before exporting the child. Note
+	 * it is not possible to export the parent first because its information
+	 * is not yet complete because its 'return' has not yet been processed.
+	 */
+	parent_db_id = idx ? &(tse - 1)->db_id : NULL;
 
-	return crp->process(&cr, crp->data);
+	return crp->process(&cr, parent_db_id, crp->data);
 }
 
 static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
@@ -458,7 +495,7 @@ void thread_stack__sample(struct thread *thread, int cpu,
 }
 
 struct call_return_processor *
-call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data)
 {
 	struct call_return_processor *crp;
@@ -493,6 +530,9 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	struct thread_stack_entry *tse;
 	int err;
 
+	if (!cp)
+		return -ENOMEM;
+
 	if (ts->cnt == ts->sz) {
 		err = thread_stack__grow(ts);
 		if (err)
@@ -507,6 +547,8 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	tse->cp = cp;
 	tse->no_call = no_call;
 	tse->trace_end = trace_end;
+	tse->non_call = false;
+	tse->db_id = 0;
 
 	return 0;
 }
@@ -528,14 +570,16 @@ static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
 							 timestamp, ref, false);
 	}
 
-	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr &&
+	    !ts->stack[ts->cnt - 1].non_call) {
 		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)
+			if (ts->stack[i].ret_addr != ret_addr ||
+			    ts->stack[i].non_call)
 				continue;
 			i += 1;
 			while (ts->cnt > i) {
@@ -576,8 +620,6 @@ static int thread_stack__bottom(struct thread_stack *ts,
 
 	cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
 				ts->kernel_start);
-	if (!cp)
-		return -ENOMEM;
 
 	return thread_stack__push_cp(ts, ip, sample->time, ref, cp,
 				     true, false);
@@ -590,36 +632,36 @@ static int thread_stack__no_call_return(struct thread *thread,
 					struct addr_location *to_al, u64 ref)
 {
 	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *root = &cpr->call_path;
+	struct symbol *fsym = from_al->sym;
+	struct symbol *tsym = to_al->sym;
 	struct call_path *cp, *parent;
 	u64 ks = ts->kernel_start;
+	u64 addr = sample->addr;
+	u64 tm = sample->time;
+	u64 ip = sample->ip;
 	int err;
 
-	if (sample->ip >= ks && sample->addr < ks) {
+	if (ip >= ks && 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);
+							tm, 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, false);
+			cp = call_path__findnew(cpr, root, tsym, addr, ks);
+			return thread_stack__push_cp(ts, 0, tm, ref, cp, true,
+						     false);
 		}
-	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+	} else if (thread_stack__in_kernel(ts) && 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);
+							tm, ref, true);
 			if (err)
 				return err;
 		}
@@ -628,21 +670,59 @@ static int thread_stack__no_call_return(struct thread *thread,
 	if (ts->cnt)
 		parent = ts->stack[ts->cnt - 1].cp;
 	else
-		parent = &cpr->call_path;
+		parent = root;
 
-	/* 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;
+	if (parent->sym == from_al->sym) {
+		/*
+		 * At the bottom of the stack, assume the missing 'call' was
+		 * before the trace started. So, pop the current symbol and push
+		 * the 'to' symbol.
+		 */
+		if (ts->cnt == 1) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							tm, ref, false);
+			if (err)
+				return err;
+		}
+
+		if (!ts->cnt) {
+			cp = call_path__findnew(cpr, root, tsym, addr, ks);
+
+			return thread_stack__push_cp(ts, addr, tm, ref, cp,
+						     true, false);
+		}
+
+		/*
+		 * Otherwise assume the 'return' is being used as a jump (e.g.
+		 * retpoline) and just push the 'to' symbol.
+		 */
+		cp = call_path__findnew(cpr, parent, tsym, addr, ks);
+
+		err = thread_stack__push_cp(ts, 0, tm, ref, cp, true, false);
+		if (!err)
+			ts->stack[ts->cnt - 1].non_call = true;
+
+		return err;
+	}
+
+	/*
+	 * Assume 'parent' has not yet returned, so push 'to', and then push and
+	 * pop 'from'.
+	 */
+
+	cp = call_path__findnew(cpr, parent, tsym, addr, ks);
+
+	err = thread_stack__push_cp(ts, addr, tm, ref, cp, true, false);
+	if (err)
+		return err;
 
-	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
-				    true, false);
+	cp = call_path__findnew(cpr, cp, fsym, ip, ks);
+
+	err = thread_stack__push_cp(ts, ip, tm, ref, cp, true, false);
 	if (err)
 		return err;
 
-	return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
-				    to_al->sym);
+	return thread_stack__call_return(thread, ts, --ts->cnt, tm, ref, false);
 }
 
 static int thread_stack__trace_begin(struct thread *thread,
@@ -680,8 +760,6 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 
 	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;
 
@@ -689,6 +767,70 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 				     false, true);
 }
 
+static bool is_x86_retpoline(const char *name)
+{
+	const char *p = strstr(name, "__x86_indirect_thunk_");
+
+	return p == name || !strcmp(name, "__indirect_thunk_start");
+}
+
+/*
+ * x86 retpoline functions pollute the call graph. This function removes them.
+ * This does not handle function return thunks, nor is there any improvement
+ * for the handling of inline thunks or extern thunks.
+ */
+static int thread_stack__x86_retpoline(struct thread_stack *ts,
+				       struct perf_sample *sample,
+				       struct addr_location *to_al)
+{
+	struct thread_stack_entry *tse = &ts->stack[ts->cnt - 1];
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct symbol *sym = tse->cp->sym;
+	struct symbol *tsym = to_al->sym;
+	struct call_path *cp;
+
+	if (sym && is_x86_retpoline(sym->name)) {
+		/*
+		 * This is a x86 retpoline fn. It pollutes the call graph by
+		 * showing up everywhere there is an indirect branch, but does
+		 * not itself mean anything. Here the top-of-stack is removed,
+		 * by decrementing the stack count, and then further down, the
+		 * resulting top-of-stack is replaced with the actual target.
+		 * The result is that the retpoline functions will no longer
+		 * appear in the call graph. Note this only affects the call
+		 * graph, since all the original branches are left unchanged.
+		 */
+		ts->cnt -= 1;
+		sym = ts->stack[ts->cnt - 2].cp->sym;
+		if (sym && sym == tsym && to_al->addr != tsym->start) {
+			/*
+			 * Target is back to the middle of the symbol we came
+			 * from so assume it is an indirect jmp and forget it
+			 * altogether.
+			 */
+			ts->cnt -= 1;
+			return 0;
+		}
+	} else if (sym && sym == tsym) {
+		/*
+		 * Target is back to the symbol we came from so assume it is an
+		 * indirect jmp and forget it altogether.
+		 */
+		ts->cnt -= 1;
+		return 0;
+	}
+
+	cp = call_path__findnew(cpr, ts->stack[ts->cnt - 2].cp, tsym,
+				sample->addr, ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	/* Replace the top-of-stack with the actual target */
+	ts->stack[ts->cnt - 1].cp = cp;
+
+	return 0;
+}
+
 int thread_stack__process(struct thread *thread, struct comm *comm,
 			  struct perf_sample *sample,
 			  struct addr_location *from_al,
@@ -696,6 +838,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 			  struct call_return_processor *crp)
 {
 	struct thread_stack *ts = thread__stack(thread, sample->cpu);
+	enum retpoline_state_t rstate;
 	int err = 0;
 
 	if (ts && !ts->crp) {
@@ -711,6 +854,10 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		ts->comm = comm;
 	}
 
+	rstate = ts->rstate;
+	if (rstate == X86_RETPOLINE_DETECTED)
+		ts->rstate = X86_RETPOLINE_POSSIBLE;
+
 	/* Flush stack on exec */
 	if (ts->comm != comm && thread->pid_ == thread->tid) {
 		err = __thread_stack__flush(thread, ts);
@@ -745,14 +892,27 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		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, trace_end);
+
+		/*
+		 * A call to the same symbol but not the start of the symbol,
+		 * may be the start of a x86 retpoline.
+		 */
+		if (!err && rstate == X86_RETPOLINE_POSSIBLE && to_al->sym &&
+		    from_al->sym == to_al->sym &&
+		    to_al->addr != to_al->sym->start)
+			ts->rstate = X86_RETPOLINE_DETECTED;
+
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
 		if (!sample->ip || !sample->addr)
 			return 0;
 
+		/* x86 retpoline 'return' doesn't match the stack */
+		if (rstate == X86_RETPOLINE_DETECTED && ts->cnt > 2 &&
+		    ts->stack[ts->cnt - 1].ret_addr != sample->addr)
+			return thread_stack__x86_retpoline(ts, sample, to_al);
+
 		err = thread_stack__pop_cp(thread, ts, sample->addr,
 					   sample->time, ref, from_al->sym);
 		if (err) {
@@ -765,6 +925,25 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		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);
+	} else if (sample->flags & PERF_IP_FLAG_BRANCH &&
+		   from_al->sym != to_al->sym && to_al->sym &&
+		   to_al->addr == to_al->sym->start) {
+		struct call_path_root *cpr = ts->crp->cpr;
+		struct call_path *cp;
+
+		/*
+		 * The compiler might optimize a call/ret combination by making
+		 * it a jmp. Make that visible by recording on the stack a
+		 * branch to the start of a different symbol. Note, that means
+		 * when a ret pops the stack, all jmps must be popped off first.
+		 */
+		cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+					to_al->sym, sample->addr,
+					ts->kernel_start);
+		err = thread_stack__push_cp(ts, 0, sample->time, ref, cp, false,
+					    false);
+		if (!err)
+			ts->stack[ts->cnt - 1].non_call = true;
 	}
 
 	return err;