Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 80c804bf authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'bpf-get-stackid' 

Alexei Starovoitov says:

====================
bpf_get_stackid() and stack_trace map

This patch set introduces new map type to store stack traces and
corresponding bpf_get_stackid() helper.
BPF programs already can walk the stack via unrolled loop
of bpf_probe_read()s which is ok for simple analysis, but it's
not efficient and limited to <30 frames after that the programs
don't fit into MAX_BPF_STACK. With bpf_get_stackid() helper
the programs can collect up to PERF_MAX_STACK_DEPTH both
user and kernel frames.
Using stack traces as a key in a map turned out to be very useful
for generating flame graphs, off-cpu graphs, waker and chain graphs.
Patch 3 is a simplified version of 'offwaketime' tool which is
described in detail here:
http://brendangregg.com/blog/2016-02-01/linux-wakeup-offwake-profiling.html



Earlier version of this patch were using save_stack_trace() helper,
but 'unreliable' frames add to much noise and two equiavlent
stack traces produce different 'stackid's.
Using lockdep style of storing frames with MAX_STACK_TRACE_ENTRIES is
great for lockdep, but not acceptable for bpf, since the stack_trace
map needs to be freed when user Ctrl-C the tool.
The ftrace style with per_cpu(struct ftrace_stack) is great, but it's
tightly coupled with ftrace ring buffer and has the same 'unreliable'
noise. perf_event's perf_callchain() mechanism is also very efficient
and it only needed minor generalization which is done in patch 1
to be used by bpf stack_trace maps.
Peter, please take a look at patch 1.
If you're ok with it, I'd like to take the whole set via net-next.

Patch 1 - generalization of perf_callchain()
Patch 2 - stack_trace map done as lock-less hashtable without link list
  to avoid spinlock on insertion which is critical path when
  bpf_get_stackid() helper is called for every task switch event
Patch 3 - offwaketime example

After the patch the 'perf report' for artificial 'sched_bench'
benchmark that doing pthread_cond_wait/signal and 'offwaketime'
example is running in the background:
 16.35%  swapper      [kernel.vmlinux]    [k] intel_idle
  2.18%  sched_bench  [kernel.vmlinux]    [k] __switch_to
  2.18%  sched_bench  libpthread-2.12.so  [.] pthread_cond_signal@@GLIBC_2.3.2
  1.72%  sched_bench  libpthread-2.12.so  [.] pthread_mutex_unlock
  1.53%  sched_bench  [kernel.vmlinux]    [k] bpf_get_stackid
  1.44%  sched_bench  [kernel.vmlinux]    [k] entry_SYSCALL_64
  1.39%  sched_bench  [kernel.vmlinux]    [k] __call_rcu.constprop.73
  1.13%  sched_bench  libpthread-2.12.so  [.] pthread_mutex_lock
  1.07%  sched_bench  libpthread-2.12.so  [.] pthread_cond_wait@@GLIBC_2.3.2
  1.07%  sched_bench  [kernel.vmlinux]    [k] hash_futex
  1.05%  sched_bench  [kernel.vmlinux]    [k] do_futex
  1.05%  sched_bench  [kernel.vmlinux]    [k] get_futex_key_refs.isra.13

The hotest part of bpf_get_stackid() is inlined jhash2, so we may consider
using some faster hash in the future, but it's good enough for now.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 6b83d28a a6ffe7b9

arch/x86/include/asm/stacktrace.h

+1 −1
Original line number Diff line number Diff line
@@ -37,7 +37,7 @@ print_context_stack_bp(struct thread_info *tinfo, 
/* Generic stack tracer with callbacks */



struct stacktrace_ops {

	void (*address)(void *data, unsigned long address, int reliable);

	int (*address)(void *data, unsigned long address, int reliable);

	/* On negative return stop dumping */

	int (*stack)(void *data, char *name);

	walk_stack_t	walk_stack;

arch/x86/kernel/cpu/perf_event.c

+2 −2
Original line number Diff line number Diff line
@@ -2180,11 +2180,11 @@ static int backtrace_stack(void *data, char *name) 
	return 0;

}



static void backtrace_address(void *data, unsigned long addr, int reliable)

static int backtrace_address(void *data, unsigned long addr, int reliable)

{

	struct perf_callchain_entry *entry = data;



	perf_callchain_store(entry, addr);

	return perf_callchain_store(entry, addr);

}



static const struct stacktrace_ops backtrace_ops = {

arch/x86/kernel/dumpstack.c

+4 −2
Original line number Diff line number Diff line
@@ -135,7 +135,8 @@ print_context_stack_bp(struct thread_info *tinfo, 
		if (!__kernel_text_address(addr))

			break;



		ops->address(data, addr, 1);

		if (ops->address(data, addr, 1))

			break;

		frame = frame->next_frame;

		ret_addr = &frame->return_address;

		print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
@@ -154,10 +155,11 @@ static int print_trace_stack(void *data, char *name) 
/*

 * Print one address/symbol entries per line.

 */

static void print_trace_address(void *data, unsigned long addr, int reliable)

static int print_trace_address(void *data, unsigned long addr, int reliable)

{

	touch_nmi_watchdog();

	printk_stack_address(addr, reliable, data);

	return 0;

}



static const struct stacktrace_ops print_trace_ops = {

arch/x86/kernel/stacktrace.c

+11 −7
Original line number Diff line number Diff line
@@ -14,30 +14,34 @@ static int save_stack_stack(void *data, char *name) 
	return 0;

}



static void

static int

__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched)

{

	struct stack_trace *trace = data;

#ifdef CONFIG_FRAME_POINTER

	if (!reliable)

		return;

		return 0;

#endif

	if (nosched && in_sched_functions(addr))

		return;

		return 0;

	if (trace->skip > 0) {

		trace->skip--;

		return;

		return 0;

	}

	if (trace->nr_entries < trace->max_entries)

	if (trace->nr_entries < trace->max_entries) {

		trace->entries[trace->nr_entries++] = addr;

		return 0;

	} else {

		return -1; /* no more room, stop walking the stack */

	}

}



static void save_stack_address(void *data, unsigned long addr, int reliable)

static int save_stack_address(void *data, unsigned long addr, int reliable)

{

	return __save_stack_address(data, addr, reliable, false);

}



static void

static int

save_stack_address_nosched(void *data, unsigned long addr, int reliable)

{

	return __save_stack_address(data, addr, reliable, true);

arch/x86/oprofile/backtrace.c

+2 −1
Original line number Diff line number Diff line
@@ -23,12 +23,13 @@ static int backtrace_stack(void *data, char *name) 
	return 0;

}



static void backtrace_address(void *data, unsigned long addr, int reliable)

static int backtrace_address(void *data, unsigned long addr, int reliable)

{

	unsigned int *depth = data;



	if ((*depth)--)

		oprofile_add_trace(addr);

	return 0;

}



static struct stacktrace_ops backtrace_ops = {