linux/tools/perf/util/annotate.h

225 lines
5.8 KiB
C
Raw Normal View History

#ifndef __PERF_ANNOTATE_H
#define __PERF_ANNOTATE_H
#include <stdbool.h>
#include <stdint.h>
#include <linux/types.h>
#include "symbol.h"
#include "hist.h"
#include "sort.h"
#include <linux/list.h>
#include <linux/rbtree.h>
#include <pthread.h>
perf annotate: Remove duplicate 'name' field from disasm_line The disasm_line::name field is always equal to ins::name, being used just to locate the instruction's ins_ops from the per-arch instructions table. Eliminate this duplication, nuking that field and instead make ins__find() return an ins_ops, store it in disasm_line::ins.ops, and keep just in disasm_line::ins.name what was in disasm_line::name, this way we end up not keeping a reference to entries in the per-arch instructions table. This in turn will help supporting multiple ways to manage the per-arch instructions table, allowing resorting that array, for instance, when the entries will move after references to its addresses were made. The same problem is avoided when one grows the array with realloc. So architectures simply keeping a constant array will work as well as architectures building the table using regular expressions or other logic that involves resorting the table. Reviewed-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Chris Riyder <chris.ryder@arm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kim Phillips <kim.phillips@arm.com> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Pawel Moll <pawel.moll@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Russell King <rmk+kernel@arm.linux.org.uk> Cc: Taeung Song <treeze.taeung@gmail.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-vr899azvabnw9gtuepuqfd9t@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-11-24 22:16:06 +08:00
struct ins_ops;
struct ins {
const char *name;
struct ins_ops *ops;
};
struct ins_operands {
char *raw;
struct {
char *raw;
char *name;
u64 addr;
perf annotate: Fix jump target outside of function address range If jump target is outside of function range, perf is not handling it correctly. Especially when target address is lesser than function start address, target offset will be negative. But, target address declared to be unsigned, converts negative number into 2's complement. See below example. Here target of 'jumpq' instruction at 34cf8 is 34ac0 which is lesser than function start address(34cf0). 34ac0 - 34cf0 = -0x230 = 0xfffffffffffffdd0 Objdump output: 0000000000034cf0 <__sigaction>: __GI___sigaction(): 34cf0: lea -0x20(%rdi),%eax 34cf3: cmp -bashx1,%eax 34cf6: jbe 34d00 <__sigaction+0x10> 34cf8: jmpq 34ac0 <__GI___libc_sigaction> 34cfd: nopl (%rax) 34d00: mov 0x386161(%rip),%rax # 3bae68 <_DYNAMIC+0x2e8> 34d07: movl -bashx16,%fs:(%rax) 34d0e: mov -bashxffffffff,%eax 34d13: retq perf annotate before applying patch: __GI___sigaction /usr/lib64/libc-2.22.so lea -0x20(%rdi),%eax cmp -bashx1,%eax v jbe 10 v jmpq fffffffffffffdd0 nop 10: mov _DYNAMIC+0x2e8,%rax movl -bashx16,%fs:(%rax) mov -bashxffffffff,%eax retq perf annotate after applying patch: __GI___sigaction /usr/lib64/libc-2.22.so lea -0x20(%rdi),%eax cmp -bashx1,%eax v jbe 10 ^ jmpq 34ac0 <__GI___libc_sigaction> nop 10: mov _DYNAMIC+0x2e8,%rax movl -bashx16,%fs:(%rax) mov -bashxffffffff,%eax retq Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Chris Riyder <chris.ryder@arm.com> Cc: Kim Phillips <kim.phillips@arm.com> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Taeung Song <treeze.taeung@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/1480953407-7605-3-git-send-email-ravi.bangoria@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-12-05 23:56:47 +08:00
s64 offset;
bool offset_avail;
} target;
union {
struct {
char *raw;
char *name;
u64 addr;
} source;
struct {
perf annotate: Remove duplicate 'name' field from disasm_line The disasm_line::name field is always equal to ins::name, being used just to locate the instruction's ins_ops from the per-arch instructions table. Eliminate this duplication, nuking that field and instead make ins__find() return an ins_ops, store it in disasm_line::ins.ops, and keep just in disasm_line::ins.name what was in disasm_line::name, this way we end up not keeping a reference to entries in the per-arch instructions table. This in turn will help supporting multiple ways to manage the per-arch instructions table, allowing resorting that array, for instance, when the entries will move after references to its addresses were made. The same problem is avoided when one grows the array with realloc. So architectures simply keeping a constant array will work as well as architectures building the table using regular expressions or other logic that involves resorting the table. Reviewed-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Chris Riyder <chris.ryder@arm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kim Phillips <kim.phillips@arm.com> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Pawel Moll <pawel.moll@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Russell King <rmk+kernel@arm.linux.org.uk> Cc: Taeung Song <treeze.taeung@gmail.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-vr899azvabnw9gtuepuqfd9t@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-11-24 22:16:06 +08:00
struct ins ins;
struct ins_operands *ops;
} locked;
};
};
struct arch;
struct ins_ops {
void (*free)(struct ins_operands *ops);
int (*parse)(struct arch *arch, struct ins_operands *ops, struct map *map);
int (*scnprintf)(struct ins *ins, char *bf, size_t size,
struct ins_operands *ops);
};
bool ins__is_jump(const struct ins *ins);
bool ins__is_call(const struct ins *ins);
bool ins__is_ret(const struct ins *ins);
bool ins__is_lock(const struct ins *ins);
int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
perf annotate: Check for fused instructions Macro fusion merges two instructions to a single micro-op. Intel core platform performs this hardware optimization under limited circumstances. For example, CMP + JCC can be "fused" and executed /retired together. While with sampling this can result in the sample sometimes being on the JCC and sometimes on the CMP. So for the fused instruction pair, they could be considered together. On Nehalem, fused instruction pairs: cmp/test + jcc. On other new CPU: cmp/test/add/sub/and/inc/dec + jcc. This patch adds an x86-specific function which checks if 2 instructions are in a "fused" pair. For non-x86 arch, the function is just NULL. Changelog: v4: Move the CPU model checking to symbol__disassemble and save the CPU family/model in arch structure. It avoids checking every time when jump arrow printed. v3: Add checking for Nehalem (CMP, TEST). For other newer Intel CPUs just check it by default (CMP, TEST, ADD, SUB, AND, INC, DEC). v2: Remove the original weak function. Arnaldo points out that doing it as a weak function that will be overridden by the host arch doesn't work. So now it's implemented as an arch-specific function. Committer fix: Do not access evsel->evlist->env->cpuid, ->env can be null, introduce perf_evsel__env_cpuid(), just like perf_evsel__env_arch(), also used in this function call. The original patch was segfaulting 'perf top' + annotation. But this essentially disables this fused instructions augmentation in 'perf top', the right thing is to get the cpuid from the running kernel, left for a later patch tho. Signed-off-by: Yao Jin <yao.jin@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1499403995-19857-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-07 13:06:34 +08:00
bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
struct annotation;
struct disasm_line {
struct list_head node;
s64 offset;
char *line;
perf annotate: Remove duplicate 'name' field from disasm_line The disasm_line::name field is always equal to ins::name, being used just to locate the instruction's ins_ops from the per-arch instructions table. Eliminate this duplication, nuking that field and instead make ins__find() return an ins_ops, store it in disasm_line::ins.ops, and keep just in disasm_line::ins.name what was in disasm_line::name, this way we end up not keeping a reference to entries in the per-arch instructions table. This in turn will help supporting multiple ways to manage the per-arch instructions table, allowing resorting that array, for instance, when the entries will move after references to its addresses were made. The same problem is avoided when one grows the array with realloc. So architectures simply keeping a constant array will work as well as architectures building the table using regular expressions or other logic that involves resorting the table. Reviewed-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Chris Riyder <chris.ryder@arm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kim Phillips <kim.phillips@arm.com> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Pawel Moll <pawel.moll@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Russell King <rmk+kernel@arm.linux.org.uk> Cc: Taeung Song <treeze.taeung@gmail.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-vr899azvabnw9gtuepuqfd9t@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-11-24 22:16:06 +08:00
struct ins ins;
int line_nr;
float ipc;
u64 cycles;
struct ins_operands ops;
};
static inline bool disasm_line__has_offset(const struct disasm_line *dl)
{
perf annotate: Fix jump target outside of function address range If jump target is outside of function range, perf is not handling it correctly. Especially when target address is lesser than function start address, target offset will be negative. But, target address declared to be unsigned, converts negative number into 2's complement. See below example. Here target of 'jumpq' instruction at 34cf8 is 34ac0 which is lesser than function start address(34cf0). 34ac0 - 34cf0 = -0x230 = 0xfffffffffffffdd0 Objdump output: 0000000000034cf0 <__sigaction>: __GI___sigaction(): 34cf0: lea -0x20(%rdi),%eax 34cf3: cmp -bashx1,%eax 34cf6: jbe 34d00 <__sigaction+0x10> 34cf8: jmpq 34ac0 <__GI___libc_sigaction> 34cfd: nopl (%rax) 34d00: mov 0x386161(%rip),%rax # 3bae68 <_DYNAMIC+0x2e8> 34d07: movl -bashx16,%fs:(%rax) 34d0e: mov -bashxffffffff,%eax 34d13: retq perf annotate before applying patch: __GI___sigaction /usr/lib64/libc-2.22.so lea -0x20(%rdi),%eax cmp -bashx1,%eax v jbe 10 v jmpq fffffffffffffdd0 nop 10: mov _DYNAMIC+0x2e8,%rax movl -bashx16,%fs:(%rax) mov -bashxffffffff,%eax retq perf annotate after applying patch: __GI___sigaction /usr/lib64/libc-2.22.so lea -0x20(%rdi),%eax cmp -bashx1,%eax v jbe 10 ^ jmpq 34ac0 <__GI___libc_sigaction> nop 10: mov _DYNAMIC+0x2e8,%rax movl -bashx16,%fs:(%rax) mov -bashxffffffff,%eax retq Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Chris Riyder <chris.ryder@arm.com> Cc: Kim Phillips <kim.phillips@arm.com> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Taeung Song <treeze.taeung@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/1480953407-7605-3-git-send-email-ravi.bangoria@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-12-05 23:56:47 +08:00
return dl->ops.target.offset_avail;
}
struct sym_hist_entry {
u64 nr_samples;
u64 period;
};
void disasm_line__free(struct disasm_line *dl);
struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos);
int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
size_t disasm__fprintf(struct list_head *head, FILE *fp);
double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
s64 end, const char **path, struct sym_hist_entry *sample);
struct sym_hist {
u64 nr_samples;
struct sym_hist_entry addr[0];
};
struct cyc_hist {
u64 start;
u64 cycles;
u64 cycles_aggr;
u32 num;
u32 num_aggr;
u8 have_start;
/* 1 byte padding */
u16 reset;
};
struct source_line_samples {
double percent;
double percent_sum;
2017-03-28 20:12:05 +08:00
u64 nr;
};
struct source_line {
struct rb_node node;
char *path;
int nr_pcnt;
struct source_line_samples samples[1];
};
/** struct annotated_source - symbols with hits have this attached as in sannotation
*
* @histogram: Array of addr hit histograms per event being monitored
* @lines: If 'print_lines' is specified, per source code line percentages
* @source: source parsed from a disassembler like objdump -dS
* @cyc_hist: Average cycles per basic block
*
* lines is allocated, percentages calculated and all sorted by percentage
* when the annotation is about to be presented, so the percentages are for
* one of the entries in the histogram array, i.e. for the event/counter being
* presented. It is deallocated right after symbol__{tui,tty,etc}_annotate
* returns.
*/
struct annotated_source {
struct list_head source;
struct source_line *lines;
int nr_histograms;
size_t sizeof_sym_hist;
struct cyc_hist *cycles_hist;
struct sym_hist histograms[0];
};
struct annotation {
pthread_mutex_t lock;
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>
2016-09-06 03:08:12 +08:00
u64 max_coverage;
struct annotated_source *src;
};
static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
{
return (((void *)&notes->src->histograms) +
(notes->src->sizeof_sym_hist * idx));
}
static inline struct annotation *symbol__annotation(struct symbol *sym)
{
return (void *)sym - symbol_conf.priv_size;
}
int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
int evidx);
int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
struct addr_map_symbol *start,
unsigned cycles);
int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
int evidx, u64 addr);
int symbol__alloc_hist(struct symbol *sym);
void symbol__annotate_zero_histograms(struct symbol *sym);
int symbol__disassemble(struct symbol *sym, struct map *map,
const char *arch_name, size_t privsize,
perf annotate: Check for fused instructions Macro fusion merges two instructions to a single micro-op. Intel core platform performs this hardware optimization under limited circumstances. For example, CMP + JCC can be "fused" and executed /retired together. While with sampling this can result in the sample sometimes being on the JCC and sometimes on the CMP. So for the fused instruction pair, they could be considered together. On Nehalem, fused instruction pairs: cmp/test + jcc. On other new CPU: cmp/test/add/sub/and/inc/dec + jcc. This patch adds an x86-specific function which checks if 2 instructions are in a "fused" pair. For non-x86 arch, the function is just NULL. Changelog: v4: Move the CPU model checking to symbol__disassemble and save the CPU family/model in arch structure. It avoids checking every time when jump arrow printed. v3: Add checking for Nehalem (CMP, TEST). For other newer Intel CPUs just check it by default (CMP, TEST, ADD, SUB, AND, INC, DEC). v2: Remove the original weak function. Arnaldo points out that doing it as a weak function that will be overridden by the host arch doesn't work. So now it's implemented as an arch-specific function. Committer fix: Do not access evsel->evlist->env->cpuid, ->env can be null, introduce perf_evsel__env_cpuid(), just like perf_evsel__env_arch(), also used in this function call. The original patch was segfaulting 'perf top' + annotation. But this essentially disables this fused instructions augmentation in 'perf top', the right thing is to get the cpuid from the running kernel, left for a later patch tho. Signed-off-by: Yao Jin <yao.jin@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1499403995-19857-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-07 13:06:34 +08:00
struct arch **parch, char *cpuid);
enum symbol_disassemble_errno {
SYMBOL_ANNOTATE_ERRNO__SUCCESS = 0,
/*
* Choose an arbitrary negative big number not to clash with standard
* errno since SUS requires the errno has distinct positive values.
* See 'Issue 6' in the link below.
*
* http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
*/
__SYMBOL_ANNOTATE_ERRNO__START = -10000,
SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX = __SYMBOL_ANNOTATE_ERRNO__START,
__SYMBOL_ANNOTATE_ERRNO__END,
};
int symbol__strerror_disassemble(struct symbol *sym, struct map *map,
int errnum, char *buf, size_t buflen);
int symbol__annotate_printf(struct symbol *sym, struct map *map,
struct perf_evsel *evsel, bool full_paths,
int min_pcnt, int max_lines, int context);
void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
void disasm__purge(struct list_head *head);
bool ui__has_annotation(void);
int symbol__tty_annotate(struct symbol *sym, struct map *map,
struct perf_evsel *evsel, bool print_lines,
bool full_paths, int min_pcnt, int max_lines);
#ifdef HAVE_SLANG_SUPPORT
int symbol__tui_annotate(struct symbol *sym, struct map *map,
struct perf_evsel *evsel,
struct hist_browser_timer *hbt);
#else
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
struct map *map __maybe_unused,
struct perf_evsel *evsel __maybe_unused,
struct hist_browser_timer *hbt
__maybe_unused)
{
return 0;
}
#endif
extern const char *disassembler_style;
#endif /* __PERF_ANNOTATE_H */