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, 91 insertions, 2 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 2ff6bd74e435..7a80c7362a03 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -17,6 +17,7 @@
 #include "debug.h"
 #include "annotate.h"
 #include "evsel.h"
+#include "block-range.h"
 #include <regex.h>
 #include <pthread.h>
 #include <linux/bitops.h>
@@ -859,6 +860,89 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
         return percent;
 }
 
+static const char *annotate__address_color(struct block_range *br)
+{
+        double cov = block_range__coverage(br);
+
+        if (cov >= 0) {
+                /* mark red for >75% coverage */
+                if (cov > 0.75)
+                        return PERF_COLOR_RED;
+
+                /* mark dull for <1% coverage */
+                if (cov < 0.01)
+                        return PERF_COLOR_NORMAL;
+        }
+
+        return PERF_COLOR_MAGENTA;
+}
+
+static const char *annotate__asm_color(struct block_range *br)
+{
+        double cov = block_range__coverage(br);
+
+        if (cov >= 0) {
+                /* mark dull for <1% coverage */
+                if (cov < 0.01)
+                        return PERF_COLOR_NORMAL;
+        }
+
+        return PERF_COLOR_BLUE;
+}
+
+static void annotate__branch_printf(struct block_range *br, u64 addr)
+{
+        bool emit_comment = true;
+
+        if (!br)
+                return;
+
+#if 1
+        if (br->is_target && br->start == addr) {
+                struct block_range *branch = br;
+                double p;
+
+                /*
+                 * Find matching branch to our target.
+                 */
+                while (!branch->is_branch)
+                        branch = block_range__next(branch);
+
+                p = 100 *(double)br->entry / branch->coverage;
+
+                if (p > 0.1) {
+                        if (emit_comment) {
+                                emit_comment = false;
+                                printf("\t#");
+                        }
+
+                        /*
+                         * The percentage of coverage joined at this target in relation
+                         * to the next branch.
+                         */
+                        printf(" +%.2f%%", p);
+                }
+        }
+#endif
+        if (br->is_branch && br->end == addr) {
+                double p = 100*(double)br->taken / br->coverage;
+
+                if (p > 0.1) {
+                        if (emit_comment) {
+                                emit_comment = false;
+                                printf("\t#");
+                        }
+
+                        /*
+                         * The percentage of coverage leaving at this branch, and
+                         * its prediction ratio.
+                         */
+                        printf(" -%.2f%% (p:%.2f%%)", p, 100*(double)br->pred  / br->taken);
+                }
+        }
+}
+
+
 static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start,
                       struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
                       int max_lines, struct disasm_line *queue)
@@ -878,6 +962,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                 s64 offset = dl->offset;
                 const u64 addr = start + offset;
                 struct disasm_line *next;
+                struct block_range *br;
 
                 next = disasm__get_next_ip_line(&notes->src->source, dl);
 
@@ -947,8 +1032,12 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                 }
 
                 printf(" :      ");
-                color_fprintf(stdout, PERF_COLOR_MAGENTA, "  %" PRIx64 ":", addr);
-                color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line);
+
+                br = block_range__find(addr);
+                color_fprintf(stdout, annotate__address_color(br), "  %" PRIx64 ":", addr);
+                color_fprintf(stdout, annotate__asm_color(br), "%s", dl->line);
+                annotate__branch_printf(br, addr);
+                printf("\n");
 
                 if (ppercents != &percent)
                         free(ppercents);