From d3030191d3a6292408c5cf999ebcc1d10e00e9c2 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 16 Jan 2024 22:26:51 -0800 Subject: perf annotate-data: Handle array style accesses On x86, instructions for array access often looks like below. mov 0x1234(%rax,%rbx,8), %rcx Usually the first register holds the type information and the second one has the index. And the current code only looks up a variable for the first register. But it's possible to be in the other way around so it needs to check the second register if the first one failed. The stat changed like this. Annotate data type stats: total 294, ok 148 (50.3%), bad 146 (49.7%) ----------------------------------------------------------- 30 : no_sym 32 : no_mem_ops 66 : no_var 10 : no_typeinfo 8 : bad_offset Reviewed-by: Ian Rogers Cc: Stephane Eranian Cc: Masami Hiramatsu Link: https://lore.kernel.org/r/20240117062657.985479-4-namhyung@kernel.org Signed-off-by: Namhyung Kim --- tools/perf/util/annotate-data.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'tools/perf/util/annotate-data.h') diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h index 8e73096c01d1..65ddd839850f 100644 --- a/tools/perf/util/annotate-data.h +++ b/tools/perf/util/annotate-data.h @@ -7,6 +7,7 @@ #include #include +struct annotated_op_loc; struct evsel; struct map_symbol; @@ -105,7 +106,7 @@ extern struct annotated_data_stat ann_data_stat; /* Returns data type at the location (ip, reg, offset) */ struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip, - int reg, int offset); + struct annotated_op_loc *loc); /* Update type access histogram at the given offset */ int annotated_data_type__update_samples(struct annotated_data_type *adt, @@ -119,7 +120,7 @@ void annotated_data_type__tree_delete(struct rb_root *root); static inline struct annotated_data_type * find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused, - int reg __maybe_unused, int offset __maybe_unused) + struct annotated_op_loc *loc __maybe_unused) { return NULL; } -- cgit v1.2.3 From 7a54f1d83defa6dd6c25c0851191f6d3a0a42362 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 16 Jan 2024 22:26:52 -0800 Subject: perf annotate-data: Add stack operation pseudo type A typical function prologue and epilogue include multiple stack operations to save and restore the current value of registers. On x86, it looks like below: push r15 push r14 push r13 push r12 ... pop r12 pop r13 pop r14 pop r15 ret As these all touches the stack memory region, chances are high that they appear in a memory profile data. But these are not used for any real purpose yet so it'd return no types. One of my profile type shows that non neglible portion of data came from the stack operations. It also seems GCC generates more stack operations than clang. Annotate Instruction stats total 264, ok 169 (64.0%), bad 95 (36.0%) Name : Good Bad ----------------------------------------------------------- movq : 49 27 movl : 24 9 popq : 0 19 <-- here cmpl : 17 2 addq : 14 1 cmpq : 12 2 cmpxchgl : 3 7 Instead of dealing them as unknown, let's create a seperate pseudo type to represent those stack operations separately. Reviewed-by: Ian Rogers Cc: Stephane Eranian Cc: Masami Hiramatsu Link: https://lore.kernel.org/r/20240117062657.985479-5-namhyung@kernel.org Signed-off-by: Namhyung Kim --- tools/perf/util/annotate-data.h | 1 + tools/perf/util/annotate.c | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'tools/perf/util/annotate-data.h') diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h index 65ddd839850f..214c625e7bc9 100644 --- a/tools/perf/util/annotate-data.h +++ b/tools/perf/util/annotate-data.h @@ -70,6 +70,7 @@ struct annotated_data_type { }; extern struct annotated_data_type unknown_type; +extern struct annotated_data_type stackop_type; /** * struct annotated_data_stat - Debug statistics diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 3cdcdd449c86..655bd9443f5e 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -107,6 +107,14 @@ static struct ins_ops ret_ops; struct annotated_data_stat ann_data_stat; LIST_HEAD(ann_insn_stat); +/* Pseudo data types */ +struct annotated_data_type stackop_type = { + .self = { + .type_name = (char *)"(stack operation)", + .children = LIST_HEAD_INIT(stackop_type.self.children), + }, +}; + static int arch__grow_instructions(struct arch *arch) { struct ins *new_instructions; @@ -3724,6 +3732,18 @@ static struct annotated_item_stat *annotate_data_stat(struct list_head *head, return istat; } +static bool is_stack_operation(struct arch *arch, struct disasm_line *dl) +{ + if (arch__is(arch, "x86")) { + if (!strncmp(dl->ins.name, "push", 4) || + !strncmp(dl->ins.name, "pop", 3) || + !strncmp(dl->ins.name, "ret", 3)) + return true; + } + + return false; +} + /** * hist_entry__get_data_type - find data type for given hist entry * @he: hist entry @@ -3789,6 +3809,12 @@ retry: return NULL; } + if (is_stack_operation(arch, dl)) { + istat->good++; + he->mem_type_off = 0; + return &stackop_type; + } + for_each_insn_op_loc(&loc, i, op_loc) { if (!op_loc->mem_ref) continue; -- cgit v1.2.3 From 5f7cdde843dd21c7228d9ae47d985086ce165985 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 16 Jan 2024 22:26:54 -0800 Subject: perf annotate-data: Support global variables Global variables are accessed using PC-relative address so it needs to be handled separately. The PC-rel addressing is detected by using DWARF_REG_PC. On x86, %rip register would be used. The address can be calculated using the ip and offset in the instruction. But it should start from the next instruction so add calculate_pcrel_addr() to do it properly. But global variables defined in a different file would only have a declaration which doesn't include a location list. So it first tries to get the type info using the address, and then looks up the variable declarations using name. The name of global variables should be get from the symbol table. The declaration would have the type info. So extend find_var_type() to take both address and name for global variables. The stat is now looks like: Annotate data type stats: total 294, ok 153 (52.0%), bad 141 (48.0%) ----------------------------------------------------------- 30 : no_sym 32 : no_mem_ops 61 : no_var 10 : no_typeinfo 8 : bad_offset Reviewed-by: Ian Rogers Cc: Stephane Eranian Cc: Masami Hiramatsu Link: https://lore.kernel.org/r/20240117062657.985479-7-namhyung@kernel.org Signed-off-by: Namhyung Kim --- tools/perf/util/annotate-data.c | 38 ++++++++++++++++++++------- tools/perf/util/annotate-data.h | 6 +++-- tools/perf/util/annotate.c | 57 +++++++++++++++++++++++++++++++++++++++-- tools/perf/util/annotate.h | 4 +++ 4 files changed, 92 insertions(+), 13 deletions(-) (limited to 'tools/perf/util/annotate-data.h') diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c index 58c0fac42e9d..e375dd288f67 100644 --- a/tools/perf/util/annotate-data.c +++ b/tools/perf/util/annotate-data.c @@ -240,7 +240,8 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset, /* The result will be saved in @type_die */ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr, - struct annotated_op_loc *loc, Dwarf_Die *type_die) + const char *var_name, struct annotated_op_loc *loc, + Dwarf_Die *type_die) { Dwarf_Die cu_die, var_die; Dwarf_Die *scopes = NULL; @@ -258,11 +259,21 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr, reg = loc->reg1; offset = loc->offset; - if (reg == DWARF_REG_PC && - die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) { - ret = check_variable(&var_die, type_die, offset, - /*is_pointer=*/false); - goto out; + if (reg == DWARF_REG_PC) { + if (die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) { + ret = check_variable(&var_die, type_die, offset, + /*is_pointer=*/false); + loc->offset = offset; + goto out; + } + + if (var_name && die_find_variable_at(&cu_die, var_name, pc, + &var_die)) { + ret = check_variable(&var_die, type_die, 0, + /*is_pointer=*/false); + /* loc->offset will be updated by the caller */ + goto out; + } } /* Get a list of nested scopes - i.e. (inlined) functions and blocks. */ @@ -285,6 +296,7 @@ retry: /* Found a variable, see if it's correct */ ret = check_variable(&var_die, type_die, offset, reg != DWARF_REG_PC); + loc->offset = offset; goto out; } @@ -306,13 +318,21 @@ out: * @ms: map and symbol at the location * @ip: instruction address of the memory access * @loc: instruction operand location + * @addr: data address of the memory access + * @var_name: global variable name * * This functions searches the debug information of the binary to get the data - * type it accesses. The exact location is expressed by (ip, reg, offset). + * type it accesses. The exact location is expressed by (@ip, reg, offset) + * for pointer variables or (@ip, @addr) for global variables. Note that global + * variables might update the @loc->offset after finding the start of the variable. + * If it cannot find a global variable by address, it tried to fine a declaration + * of the variable using @var_name. In that case, @loc->offset won't be updated. + * * It return %NULL if not found. */ struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip, - struct annotated_op_loc *loc) + struct annotated_op_loc *loc, u64 addr, + const char *var_name) { struct annotated_data_type *result = NULL; struct dso *dso = map__dso(ms->map); @@ -332,7 +352,7 @@ struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip, * a file address for DWARF processing. */ pc = map__rip_2objdump(ms->map, ip); - if (find_data_type_die(di, pc, 0, loc, &type_die) < 0) + if (find_data_type_die(di, pc, addr, var_name, loc, &type_die) < 0) goto out; result = dso__findnew_data_type(dso, &type_die); diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h index 214c625e7bc9..1b0db8e8c40e 100644 --- a/tools/perf/util/annotate-data.h +++ b/tools/perf/util/annotate-data.h @@ -107,7 +107,8 @@ extern struct annotated_data_stat ann_data_stat; /* Returns data type at the location (ip, reg, offset) */ struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip, - struct annotated_op_loc *loc); + struct annotated_op_loc *loc, u64 addr, + const char *var_name); /* Update type access histogram at the given offset */ int annotated_data_type__update_samples(struct annotated_data_type *adt, @@ -121,7 +122,8 @@ void annotated_data_type__tree_delete(struct rb_root *root); static inline struct annotated_data_type * find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused, - struct annotated_op_loc *loc __maybe_unused) + struct annotated_op_loc *loc __maybe_unused, + u64 addr __maybe_unused, const char *var_name __maybe_unused) { return NULL; } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 655bd9443f5e..107b264fa41e 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -37,6 +37,7 @@ #include "util/sharded_mutex.h" #include "arch/common.h" #include "namespaces.h" +#include "thread.h" #include #include #include @@ -3744,6 +3745,30 @@ static bool is_stack_operation(struct arch *arch, struct disasm_line *dl) return false; } +u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset, + struct disasm_line *dl) +{ + struct annotation *notes; + struct disasm_line *next; + u64 addr; + + notes = symbol__annotation(ms->sym); + /* + * PC-relative addressing starts from the next instruction address + * But the IP is for the current instruction. Since disasm_line + * doesn't have the instruction size, calculate it using the next + * disasm_line. If it's the last one, we can use symbol's end + * address directly. + */ + if (&dl->al.node == notes->src->source.prev) + addr = ms->sym->end + offset; + else { + next = list_next_entry(dl, al.node); + addr = ip + (next->al.offset - dl->al.offset) + offset; + } + return map__rip_2objdump(ms->map, addr); +} + /** * hist_entry__get_data_type - find data type for given hist entry * @he: hist entry @@ -3763,7 +3788,9 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he) struct annotated_op_loc *op_loc; struct annotated_data_type *mem_type; struct annotated_item_stat *istat; - u64 ip = he->ip; + u64 ip = he->ip, addr = 0; + const char *var_name = NULL; + int var_offset; int i; ann_data_stat.total++; @@ -3822,12 +3849,38 @@ retry: /* Recalculate IP because of LOCK prefix or insn fusion */ ip = ms->sym->start + dl->al.offset; - mem_type = find_data_type(ms, ip, op_loc); + var_offset = op_loc->offset; + + /* PC-relative addressing */ + if (op_loc->reg1 == DWARF_REG_PC) { + struct addr_location al; + struct symbol *var; + u64 map_addr; + + addr = annotate_calc_pcrel(ms, ip, op_loc->offset, dl); + /* Kernel symbols might be relocated */ + map_addr = addr + map__reloc(ms->map); + + addr_location__init(&al); + var = thread__find_symbol_fb(he->thread, he->cpumode, + map_addr, &al); + if (var) { + var_name = var->name; + /* Calculate type offset from the start of variable */ + var_offset = map_addr - map__unmap_ip(al.map, var->start); + } + addr_location__exit(&al); + } + + mem_type = find_data_type(ms, ip, op_loc, addr, var_name); if (mem_type) istat->good++; else istat->bad++; + if (mem_type && var_name) + op_loc->offset = var_offset; + if (symbol_conf.annotate_data_sample) { annotated_data_type__update_samples(mem_type, evsel, op_loc->offset, diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index d0ff677b460c..94435607c958 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -491,4 +491,8 @@ struct annotated_item_stat { }; extern struct list_head ann_insn_stat; +/* Calculate PC-relative address */ +u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset, + struct disasm_line *dl); + #endif /* __PERF_ANNOTATE_H */ -- cgit v1.2.3