perf core: Allow setting up max frame stack depth via sysctl

The default remains 127, which is good for most cases, and not even hit
most of the time, but then for some cases, as reported by Brendan, 1024+
deep frames are appearing on the radar for things like groovy, ruby.

And in some workloads putting a _lower_ cap on this may make sense. One
that is per event still needs to be put in place tho.

The new file is:

  # cat /proc/sys/kernel/perf_event_max_stack
  127

Chaging it:

  # echo 256 > /proc/sys/kernel/perf_event_max_stack
  # cat /proc/sys/kernel/perf_event_max_stack
  256

But as soon as there is some event using callchains we get:

  # echo 512 > /proc/sys/kernel/perf_event_max_stack
  -bash: echo: write error: Device or resource busy
  #

Because we only allocate the callchain percpu data structures when there
is a user, which allows for changing the max easily, its just a matter
of having no callchain users at that point.

Reported-and-Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/r/20160426002928.GB16708@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

8 files changed, 15 insertions, 15 deletions

diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
index 4e02ae5950ff..27563befa8a2 100644
--- a/arch/arm/kernel/perf_callchain.c
+++ b/arch/arm/kernel/perf_callchain.c
@@ -75,7 +75,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
 
-	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+	while ((entry->nr < sysctl_perf_event_max_stack) &&
 	       tail && !((unsigned long)tail & 0x3))
 		tail = user_backtrace(tail, entry);
 }
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index ff4665462a02..32c3c6e70119 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -122,7 +122,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 
 		tail = (struct frame_tail __user *)regs->regs[29];
 
-		while (entry->nr < PERF_MAX_STACK_DEPTH &&
+		while (entry->nr < sysctl_perf_event_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 *entry,
 
 		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
 
-		while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+		while ((entry->nr < sysctl_perf_event_max_stack) &&
 			tail && !((unsigned long)tail & 0x3))
 			tail = compat_user_backtrace(tail, entry);
 #endif
diff --git a/arch/metag/kernel/perf_callchain.c b/arch/metag/kernel/perf_callchain.c
index 315633461a94..252abc12a5a3 100644
--- a/arch/metag/kernel/perf_callchain.c
+++ b/arch/metag/kernel/perf_callchain.c
@@ -65,7 +65,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	--frame;
 
-	while ((entry->nr < PERF_MAX_STACK_DEPTH) && frame)
+	while ((entry->nr < sysctl_perf_event_max_stack) && frame)
 		frame = user_backtrace(frame, entry);
 }
 
diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c
index c1cf9c6c3f77..5021c546ad07 100644
--- a/arch/mips/kernel/perf_event.c
+++ b/arch/mips/kernel/perf_event.c
@@ -35,7 +35,7 @@ static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
 		addr = *sp++;
 		if (__kernel_text_address(addr)) {
 			perf_callchain_store(entry, addr);
-			if (entry->nr >= PERF_MAX_STACK_DEPTH)
+			if (entry->nr >= sysctl_perf_event_max_stack)
 				break;
 		}
 	}
@@ -59,7 +59,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 	}
 	do {
 		perf_callchain_store(entry, pc);
-		if (entry->nr >= PERF_MAX_STACK_DEPTH)
+		if (entry->nr >= sysctl_perf_event_max_stack)
 			break;
 		pc = unwind_stack(current, &sp, pc, &ra);
 	} while (pc);
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index e04a6752b399..22d9015c1acc 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -247,7 +247,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
 
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_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 *entry,
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
 
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_max_stack) {
 		fp = (unsigned int __user *) (unsigned long) sp;
 		if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
 			return;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 6596f66ce112..a4b8b5aed21c 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1756,7 +1756,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			}
 		}
 #endif
-	} while (entry->nr < PERF_MAX_STACK_DEPTH);
+	} while (entry->nr < sysctl_perf_event_max_stack);
 }
 
 static inline int
@@ -1790,7 +1790,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp + STACK_BIAS;
 		perf_callchain_store(entry, pc);
-	} while (entry->nr < PERF_MAX_STACK_DEPTH);
+	} while (entry->nr < sysctl_perf_event_max_stack);
 }
 
 static void perf_callchain_user_32(struct perf_callchain_entry *entry,
@@ -1822,7 +1822,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 			ufp = (unsigned long)sf.fp;
 		}
 		perf_callchain_store(entry, pc);
-	} while (entry->nr < PERF_MAX_STACK_DEPTH);
+	} while (entry->nr < sysctl_perf_event_max_stack);
 }
 
 void
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 041e442a3e28..41d93d0e972b 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2277,7 +2277,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 
 	fp = compat_ptr(ss_base + regs->bp);
 	pagefault_disable();
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_max_stack) {
 		unsigned long bytes;
 		frame.next_frame     = 0;
 		frame.return_address = 0;
@@ -2337,7 +2337,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		return;
 
 	pagefault_disable();
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_max_stack) {
 		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 54f01188c29c..a6b00b3af429 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -332,14 +332,14 @@ static int callchain_trace(struct stackframe *frame, void *data)
 void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			   struct pt_regs *regs)
 {
-	xtensa_backtrace_kernel(regs, PERF_MAX_STACK_DEPTH,
+	xtensa_backtrace_kernel(regs, sysctl_perf_event_max_stack,
 				callchain_trace, NULL, entry);
 }
 
 void perf_callchain_user(struct perf_callchain_entry *entry,
 			 struct pt_regs *regs)
 {
-	xtensa_backtrace_user(regs, PERF_MAX_STACK_DEPTH,
+	xtensa_backtrace_user(regs, sysctl_perf_event_max_stack,
 			      callchain_trace, entry);
 }