perf core: Add a 'nr' field to perf_event_callchain_context

We will use it to count how many addresses are in the entry->ip[] array,
excluding PERF_CONTEXT_{KERNEL,USER,etc} entries, so that we can really
return the number of entries specified by the user via the relevant
sysctl, kernel.perf_event_max_contexts, or via the per event
perf_event_attr.sample_max_stack knob.

This way we keep the perf_sample->ip_callchain->nr meaning, that is the
number of entries, be it real addresses or PERF_CONTEXT_ entries, while
honouring the max_stack knobs, i.e. the end result will be max_stack
entries if we have at least that many entries in a given stack trace.

Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-s8teto51tdqvlfhefndtat9r@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

arch/arm/kernel/perf_callchain.c

@@ -75,7 +75,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 
 	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
 
-	while ((entry->entry->nr < entry->max_stack) &&
+	while ((entry->nr < entry->max_stack) &&
 	       tail && !((unsigned long)tail & 0x3))
 		tail = user_backtrace(tail, entry);
 }

arch/arm64/kernel/perf_callchain.c

@@ -122,7 +122,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 
 		tail = (struct frame_tail __user *)regs->regs[29];
 
-		while (entry->entry->nr < entry->max_stack &&
+		while (entry->nr < entry->max_stack &&
 		       tail && !((unsigned long)tail & 0xf))
 			tail = user_backtrace(tail, entry);
 	} else {
@@ -132,7 +132,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 
 		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
 
-		while ((entry->entry->nr < entry->max_stack) &&
+		while ((entry->nr < entry->max_stack) &&
 			tail && !((unsigned long)tail & 0x3))
 			tail = compat_user_backtrace(tail, entry);
 #endif

arch/metag/kernel/perf_callchain.c

@@ -65,7 +65,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 
 	--frame;
 
-	while ((entry->entry->nr < entry->max_stack) && frame)
+	while ((entry->nr < entry->max_stack) && frame)
 		frame = user_backtrace(frame, entry);
 }
 

arch/mips/kernel/perf_event.c

@@ -35,7 +35,7 @@ static void save_raw_perf_callchain(struct perf_callchain_entry_ctx *entry,
 		addr = *sp++;
 		if (__kernel_text_address(addr)) {
 			perf_callchain_store(entry, addr);
-			if (entry->entry->nr >= entry->max_stack)
+			if (entry->nr >= entry->max_stack)
 				break;
 		}
 	}
@@ -59,7 +59,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 	}
 	do {
 		perf_callchain_store(entry, pc);
-		if (entry->entry->nr >= entry->max_stack)
+		if (entry->nr >= entry->max_stack)
 			break;
 		pc = unwind_stack(current, &sp, pc, &ra);
 	} while (pc);

arch/powerpc/perf/callchain.c

@@ -247,7 +247,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
 
-	while (entry->entry->nr < entry->max_stack) {
+	while (entry->nr < entry->max_stack) {
 		fp = (unsigned long __user *) sp;
 		if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
 			return;
@@ -453,7 +453,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
 
-	while (entry->entry->nr < entry->max_stack) {
+	while (entry->nr < entry->max_stack) {
 		fp = (unsigned int __user *) (unsigned long) sp;
 		if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
 			return;

arch/sparc/kernel/perf_event.c

@@ -1756,7 +1756,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			}
 		}
 #endif
-	} while (entry->entry->nr < entry->max_stack);
+	} while (entry->nr < entry->max_stack);
 }
 
 static inline int
@@ -1790,7 +1790,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp + STACK_BIAS;
 		perf_callchain_store(entry, pc);
-	} while (entry->entry->nr < entry->max_stack);
+	} while (entry->nr < entry->max_stack);
 }
 
 static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
@@ -1822,7 +1822,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 			ufp = (unsigned long)sf.fp;
 		}
 		perf_callchain_store(entry, pc);
-	} while (entry->entry->nr < entry->max_stack);
+	} while (entry->nr < entry->max_stack);
 }
 
 void

arch/x86/events/core.c

@@ -2283,7 +2283,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 
 	fp = compat_ptr(ss_base + regs->bp);
 	pagefault_disable();
-	while (entry->entry->nr < entry->max_stack) {
+	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
 		frame.next_frame     = 0;
 		frame.return_address = 0;
@@ -2343,7 +2343,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 		return;
 
 	pagefault_disable();
-	while (entry->entry->nr < entry->max_stack) {
+	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;

include/linux/perf_event.h

@@ -64,6 +64,7 @@ struct perf_callchain_entry {
 struct perf_callchain_entry_ctx {
 	struct perf_callchain_entry *entry;
 	u32			    max_stack;
+	u32			    nr;
 };
 
 struct perf_raw_record {
@@ -1080,9 +1081,10 @@ extern int sysctl_perf_event_max_stack;
 
 static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip)
 {
-	struct perf_callchain_entry *entry = ctx->entry;
-	if (entry->nr < ctx->max_stack) {
+	if (ctx->nr < ctx->max_stack) {
+		struct perf_callchain_entry *entry = ctx->entry;
 		entry->ip[entry->nr++] = ip;
+		++ctx->nr;
 		return 0;
 	} else {
 		return -1; /* no more room, stop walking the stack */

kernel/events/callchain.c

@@ -196,8 +196,7 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 
 	ctx.entry     = entry;
 	ctx.max_stack = max_stack;
-
-	entry->nr = init_nr;
+	ctx.nr	      = entry->nr = init_nr;
 
 	if (kernel && !user_mode(regs)) {
 		if (add_mark)