perf annotate: Add branch stack / basic block

I wanted to know the hottest path through a function and figured the
branch-stack (LBR) information should be able to help out with that.

The below uses the branch-stack to create basic blocks and generate
statistics from them.

        from    to              branch_i
        * ----> *
                |
                | block
                v
                * ----> *
                from    to      branch_i+1

The blocks are broken down into non-overlapping ranges, while tracking
if the start of each range is an entry point and/or the end of a range
is a branch.

Each block iterates all ranges it covers (while splitting where required
to exactly match the block) and increments the 'coverage' count.

For the range including the branch we increment the taken counter, as
well as the pred counter if flags.predicted.

Using these number we can find if an instruction:

 - had coverage; given by:

        br->coverage / br->sym->max_coverage

   This metric ensures each symbol has a 100% spot, which reflects the
   observation that each symbol must have a most covered/hottest
   block.

 - is a branch target: br->is_target && br->start == add

 - for targets, how much of a branch's coverages comes from it:

	target->entry / branch->coverage

 - is a branch: br->is_branch && br->end == addr

 - for branches, how often it was taken:

        br->taken / br->coverage

   after all, all execution that didn't take the branch would have
   incremented the coverage and continued onward to a later branch.

 - for branches, how often it was predicted:

        br->pred / br->taken

The coverage percentage is used to color the address and asm sections;
for low (<1%) coverage we use NORMAL (uncolored), indicating that these
instructions are not 'important'. For high coverage (>75%) we color the
address RED.

For each branch, we add an asm comment after the instruction with
information on how often it was taken and predicted.

Output looks like (sans color, which does loose a lot of the
information :/)

$ perf record --branch-filter u,any -e cycles:p ./branches 27
$ perf annotate branches

 Percent |	Source code & Disassembly of branches for cycles:pu (217 samples)
---------------------------------------------------------------------------------
         :	branches():
    0.00 :	  40057a:       push   %rbp
    0.00 :	  40057b:       mov    %rsp,%rbp
    0.00 :	  40057e:       sub    $0x20,%rsp
    0.00 :	  400582:       mov    %rdi,-0x18(%rbp)
    0.00 :	  400586:       mov    %rsi,-0x20(%rbp)
    0.00 :	  40058a:       mov    -0x18(%rbp),%rax
    0.00 :	  40058e:       mov    %rax,-0x10(%rbp)
    0.00 :	  400592:       movq   $0x0,-0x8(%rbp)
    0.00 :	  40059a:       jmpq   400656 <branches+0xdc>
    1.84 :	  40059f:       mov    -0x10(%rbp),%rax	# +100.00%
    3.23 :	  4005a3:       and    $0x1,%eax
    1.84 :	  4005a6:       test   %rax,%rax
    0.00 :	  4005a9:       je     4005bf <branches+0x45>	# -54.50% (p:42.00%)
    0.46 :	  4005ab:       mov    0x200bbe(%rip),%rax        # 601170 <acc>
   12.90 :	  4005b2:       add    $0x1,%rax
    2.30 :	  4005b6:       mov    %rax,0x200bb3(%rip)        # 601170 <acc>
    0.46 :	  4005bd:       jmp    4005d1 <branches+0x57>	# -100.00% (p:100.00%)
    0.92 :	  4005bf:       mov    0x200baa(%rip),%rax        # 601170 <acc>	# +49.54%
   13.82 :	  4005c6:       sub    $0x1,%rax
    0.46 :	  4005ca:       mov    %rax,0x200b9f(%rip)        # 601170 <acc>
    2.30 :	  4005d1:       mov    -0x10(%rbp),%rax	# +50.46%
    0.46 :	  4005d5:       mov    %rax,%rdi
    0.46 :	  4005d8:       callq  400526 <lfsr>	# -100.00% (p:100.00%)
    0.00 :	  4005dd:       mov    %rax,-0x10(%rbp)	# +100.00%
    0.92 :	  4005e1:       mov    -0x18(%rbp),%rax
    0.00 :	  4005e5:       and    $0x1,%eax
    0.00 :	  4005e8:       test   %rax,%rax
    0.00 :	  4005eb:       je     4005ff <branches+0x85>	# -100.00% (p:100.00%)
    0.00 :	  4005ed:       mov    0x200b7c(%rip),%rax        # 601170 <acc>
    0.00 :	  4005f4:       shr    $0x2,%rax
    0.00 :	  4005f8:       mov    %rax,0x200b71(%rip)        # 601170 <acc>
    0.00 :	  4005ff:       mov    -0x10(%rbp),%rax	# +100.00%
    7.37 :	  400603:       and    $0x1,%eax
    3.69 :	  400606:       test   %rax,%rax
    0.00 :	  400609:       jne    400612 <branches+0x98>	# -59.25% (p:42.99%)
    1.84 :	  40060b:       mov    $0x1,%eax
   14.29 :	  400610:       jmp    400617 <branches+0x9d>	# -100.00% (p:100.00%)
    1.38 :	  400612:       mov    $0x0,%eax	# +57.65%
   10.14 :	  400617:       test   %al,%al	# +42.35%
    0.00 :	  400619:       je     40062f <branches+0xb5>	# -57.65% (p:100.00%)
    0.46 :	  40061b:       mov    0x200b4e(%rip),%rax        # 601170 <acc>
    2.76 :	  400622:       sub    $0x1,%rax
    0.00 :	  400626:       mov    %rax,0x200b43(%rip)        # 601170 <acc>
    0.46 :	  40062d:       jmp    400641 <branches+0xc7>	# -100.00% (p:100.00%)
    0.92 :	  40062f:       mov    0x200b3a(%rip),%rax        # 601170 <acc>	# +56.13%
    2.30 :	  400636:       add    $0x1,%rax
    0.92 :	  40063a:       mov    %rax,0x200b2f(%rip)        # 601170 <acc>
    0.92 :	  400641:       mov    -0x10(%rbp),%rax	# +43.87%
    2.30 :	  400645:       mov    %rax,%rdi
    0.00 :	  400648:       callq  400526 <lfsr>	# -100.00% (p:100.00%)
    0.00 :	  40064d:       mov    %rax,-0x10(%rbp)	# +100.00%
    1.84 :	  400651:       addq   $0x1,-0x8(%rbp)
    0.92 :	  400656:       mov    -0x8(%rbp),%rax
    5.07 :	  40065a:       cmp    -0x20(%rbp),%rax
    0.00 :	  40065e:       jb     40059f <branches+0x25>	# -100.00% (p:100.00%)
    0.00 :	  400664:       nop
    0.00 :	  400665:       leaveq
    0.00 :	  400666:       retq

(Note: the --branch-filter u,any was used to avoid spurious target and
branch points due to interrupts/faults, they show up as very small -/+
annotations on 'weird' locations)

Committer note:

Please take a look at:

  http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png

To see the colors.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
[ Moved sym->max_coverage to 'struct annotate', aka symbol__annotate(sym) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 104 insertions, 0 deletions

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index f07b23011b22..ebb628332a6e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -30,6 +30,7 @@
 #include "util/tool.h"
 #include "util/data.h"
 #include "arch/common.h"
+#include "util/block-range.h"
 
 #include <dlfcn.h>
 #include <linux/bitmap.h>
@@ -46,6 +47,103 @@ struct perf_annotate {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+/*
+ * Given one basic block:
+ *
+ *	from	to		branch_i
+ *	* ----> *
+ *		|
+ *		| block
+ *		v
+ *		* ----> *
+ *		from	to	branch_i+1
+ *
+ * where the horizontal are the branches and the vertical is the executed
+ * block of instructions.
+ *
+ * We count, for each 'instruction', the number of blocks that covered it as
+ * well as count the ratio each branch is taken.
+ *
+ * We can do this without knowing the actual instruction stream by keeping
+ * track of the address ranges. We break down ranges such that there is no
+ * overlap and iterate from the start until the end.
+ *
+ * @acme: once we parse the objdump output _before_ processing the samples,
+ * we can easily fold the branch.cycles IPC bits in.
+ */
+static void process_basic_block(struct addr_map_symbol *start,
+				struct addr_map_symbol *end,
+				struct branch_flags *flags)
+{
+	struct symbol *sym = start->sym;
+	struct annotation *notes = sym ? symbol__annotation(sym) : NULL;
+	struct block_range_iter iter;
+	struct block_range *entry;
+
+	/*
+	 * Sanity; NULL isn't executable and the CPU cannot execute backwards
+	 */
+	if (!start->addr || start->addr > end->addr)
+		return;
+
+	iter = block_range__create(start->addr, end->addr);
+	if (!block_range_iter__valid(&iter))
+		return;
+
+	/*
+	 * First block in range is a branch target.
+	 */
+	entry = block_range_iter(&iter);
+	assert(entry->is_target);
+	entry->entry++;
+
+	do {
+		entry = block_range_iter(&iter);
+
+		entry->coverage++;
+		entry->sym = sym;
+
+		if (notes)
+			notes->max_coverage = max(notes->max_coverage, entry->coverage);
+
+	} while (block_range_iter__next(&iter));
+
+	/*
+	 * Last block in rage is a branch.
+	 */
+	entry = block_range_iter(&iter);
+	assert(entry->is_branch);
+	entry->taken++;
+	if (flags->predicted)
+		entry->pred++;
+}
+
+static void process_branch_stack(struct branch_stack *bs, struct addr_location *al,
+				 struct perf_sample *sample)
+{
+	struct addr_map_symbol *prev = NULL;
+	struct branch_info *bi;
+	int i;
+
+	if (!bs || !bs->nr)
+		return;
+
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return;
+
+	for (i = bs->nr - 1; i >= 0; i--) {
+		/*
+		 * XXX filter against symbol
+		 */
+		if (prev)
+			process_basic_block(prev, &bi[i].from, &bi[i].flags);
+		prev = &bi[i].to;
+	}
+
+	free(bi);
+}
+
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
@@ -72,6 +170,12 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
+	/*
+	 * XXX filtered samples can still have branch entires pointing into our
+	 * symbol and are missed.
+	 */
+	process_branch_stack(sample->branch_stack, al, sample);
+
 	sample->period = 1;
 	sample->weight = 1;