From b580563e38487d9db8e94080149644da71c533c1 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 16 Nov 2015 12:10:09 +0000 Subject: bpf tools: Load a program with different instances using preprocessor This patch is a preparation for BPF prologue support which allows generating a series of BPF bytecode for fetching kernel data before calling program code. With the newly introduced multiple instances support, perf is able to create different prologues for different kprobe points. Before this patch, a bpf_program can be loaded into kernel only once, and get the only resulting fd. What this patch does is to allow creating and loading different variants of one bpf_program, then fetching their fds. Here we describe the basic idea in this patch. The detailed description of the newly introduced APIs can be found in comments in the patch body. The key of this patch is the new mechanism in bpf_program__load(). Instead of loading BPF program into kernel directly, it calls a 'pre-processor' to generate program instances which would be finally loaded into the kernel based on the original code. To enable the generation of multiple instances, libbpf passes an index to the pre-processor so it know which instance is being loaded. Pre-processor should be called from libbpf's user (perf) using bpf_program__set_prep(). The number of instances and the relationship between indices and the target instance should be clear when calling bpf_program__set_prep(). To retrieve a fd for a specific instance of a program, bpf_program__nth_fd() is introduced. It returns the resulting fd according to index. Signed-off-by: He Kuang Cc: Alexei Starovoitov Cc: He Kuang Cc: Masami Hiramatsu Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447675815-166222-8-git-send-email-wangnan0@huawei.com Signed-off-by: Wang Nan [ Enclosed multi-line if/else blocks with {}, (*func_ptr)() -> func_ptr() ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/libbpf.h | 64 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) (limited to 'tools/lib/bpf/libbpf.h') diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c9a9aef2806c..949df4b346cf 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -88,6 +88,70 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy); int bpf_program__fd(struct bpf_program *prog); +struct bpf_insn; + +/* + * Libbpf allows callers to adjust BPF programs before being loaded + * into kernel. One program in an object file can be transform into + * multiple variants to be attached to different code. + * + * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd + * are APIs for this propose. + * + * - bpf_program_prep_t: + * It defines 'preprocessor', which is a caller defined function + * passed to libbpf through bpf_program__set_prep(), and will be + * called before program is loaded. The processor should adjust + * the program one time for each instances according to the number + * passed to it. + * + * - bpf_program__set_prep: + * Attachs a preprocessor to a BPF program. The number of instances + * whould be created is also passed through this function. + * + * - bpf_program__nth_fd: + * After the program is loaded, get resuling fds from bpf program for + * each instances. + * + * If bpf_program__set_prep() is not used, the program whould be loaded + * without adjustment during bpf_object__load(). The program has only + * one instance. In this case bpf_program__fd(prog) is equal to + * bpf_program__nth_fd(prog, 0). + */ + +struct bpf_prog_prep_result { + /* + * If not NULL, load new instruction array. + * If set to NULL, don't load this instance. + */ + struct bpf_insn *new_insn_ptr; + int new_insn_cnt; + + /* If not NULL, result fd is set to it */ + int *pfd; +}; + +/* + * Parameters of bpf_program_prep_t: + * - prog: The bpf_program being loaded. + * - n: Index of instance being generated. + * - insns: BPF instructions array. + * - insns_cnt:Number of instructions in insns. + * - res: Output parameter, result of transformation. + * + * Return value: + * - Zero: pre-processing success. + * - Non-zero: pre-processing, stop loading. + */ +typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, + struct bpf_insn *insns, int insns_cnt, + struct bpf_prog_prep_result *res); + +int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, + bpf_program_prep_t prep); + +int bpf_program__nth_fd(struct bpf_program *prog, int n); + /* * We don't need __attribute__((packed)) now since it is * unnecessary for 'bpf_map_def' because they are all aligned. -- cgit v1.2.3 From 9d759a9b4ac2690077d8b21258e6e95c3e34bfa9 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 27 Nov 2015 08:47:35 +0000 Subject: tools lib bpf: Collect map definition in bpf_object This patch collects more information from maps sections in BPF object files into 'struct bpf_object', enables later patches access those information (such as the type and size of the map). In this patch, a new handler 'struct bpf_map' is extracted in parallel with bpf_object and bpf_program. Its iterator and accessor is also created. Signed-off-by: Wang Nan Cc: Alexei Starovoitov Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1448614067-197576-2-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/libbpf.c | 187 +++++++++++++++++++++++++++++++++---------------- tools/lib/bpf/libbpf.h | 21 ++++++ 2 files changed, 148 insertions(+), 60 deletions(-) (limited to 'tools/lib/bpf/libbpf.h') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e3f4c3379f14..f50982579aa8 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -163,22 +163,24 @@ struct bpf_program { bpf_program_clear_priv_t clear_priv; }; +struct bpf_map { + int fd; + struct bpf_map_def def; + void *priv; + bpf_map_clear_priv_t clear_priv; +}; + static LIST_HEAD(bpf_objects_list); struct bpf_object { char license[64]; u32 kern_version; - void *maps_buf; - size_t maps_buf_sz; struct bpf_program *programs; size_t nr_programs; - int *map_fds; - /* - * This field is required because maps_buf will be freed and - * maps_buf_sz will be set to 0 after loaded. - */ - size_t nr_map_fds; + struct bpf_map *maps; + size_t nr_maps; + bool loaded; /* @@ -489,21 +491,38 @@ static int bpf_object__init_maps(struct bpf_object *obj, void *data, size_t size) { - if (size == 0) { + size_t nr_maps; + int i; + + nr_maps = size / sizeof(struct bpf_map_def); + if (!data || !nr_maps) { pr_debug("%s doesn't need map definition\n", obj->path); return 0; } - obj->maps_buf = malloc(size); - if (!obj->maps_buf) { - pr_warning("malloc maps failed: %s\n", obj->path); + pr_debug("maps in %s: %zd bytes\n", obj->path, size); + + obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); + if (!obj->maps) { + pr_warning("alloc maps for object failed\n"); return -ENOMEM; } + obj->nr_maps = nr_maps; + + for (i = 0; i < nr_maps; i++) { + struct bpf_map_def *def = &obj->maps[i].def; - obj->maps_buf_sz = size; - memcpy(obj->maps_buf, data, size); - pr_debug("maps in %s: %ld bytes\n", obj->path, (long)size); + /* + * fill all fd with -1 so won't close incorrect + * fd (fd=0 is stdin) when failure (zclose won't close + * negative fd)). + */ + obj->maps[i].fd = -1; + + /* Save map definition into obj->maps */ + *def = ((struct bpf_map_def *)data)[i]; + } return 0; } @@ -688,37 +707,15 @@ static int bpf_object__create_maps(struct bpf_object *obj) { unsigned int i; - size_t nr_maps; - int *pfd; - - nr_maps = obj->maps_buf_sz / sizeof(struct bpf_map_def); - if (!obj->maps_buf || !nr_maps) { - pr_debug("don't need create maps for %s\n", - obj->path); - return 0; - } - obj->map_fds = malloc(sizeof(int) * nr_maps); - if (!obj->map_fds) { - pr_warning("realloc perf_bpf_map_fds failed\n"); - return -ENOMEM; - } - obj->nr_map_fds = nr_maps; - - /* fill all fd with -1 */ - memset(obj->map_fds, -1, sizeof(int) * nr_maps); + for (i = 0; i < obj->nr_maps; i++) { + struct bpf_map_def *def = &obj->maps[i].def; + int *pfd = &obj->maps[i].fd; - pfd = obj->map_fds; - for (i = 0; i < nr_maps; i++) { - struct bpf_map_def def; - - def = *(struct bpf_map_def *)(obj->maps_buf + - i * sizeof(struct bpf_map_def)); - - *pfd = bpf_create_map(def.type, - def.key_size, - def.value_size, - def.max_entries); + *pfd = bpf_create_map(def->type, + def->key_size, + def->value_size, + def->max_entries); if (*pfd < 0) { size_t j; int err = *pfd; @@ -726,22 +723,17 @@ bpf_object__create_maps(struct bpf_object *obj) pr_warning("failed to create map: %s\n", strerror(errno)); for (j = 0; j < i; j++) - zclose(obj->map_fds[j]); - obj->nr_map_fds = 0; - zfree(&obj->map_fds); + zclose(obj->maps[j].fd); return err; } pr_debug("create map: fd=%d\n", *pfd); - pfd++; } - zfree(&obj->maps_buf); - obj->maps_buf_sz = 0; return 0; } static int -bpf_program__relocate(struct bpf_program *prog, int *map_fds) +bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) { int i; @@ -761,7 +753,7 @@ bpf_program__relocate(struct bpf_program *prog, int *map_fds) return -LIBBPF_ERRNO__RELOC; } insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; - insns[insn_idx].imm = map_fds[map_idx]; + insns[insn_idx].imm = obj->maps[map_idx].fd; } zfree(&prog->reloc_desc); @@ -780,7 +772,7 @@ bpf_object__relocate(struct bpf_object *obj) for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; - err = bpf_program__relocate(prog, obj->map_fds); + err = bpf_program__relocate(prog, obj); if (err) { pr_warning("failed to relocate '%s'\n", prog->section_name); @@ -804,8 +796,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) Elf_Data *data = obj->efile.reloc[i].data; int idx = shdr->sh_info; struct bpf_program *prog; - size_t nr_maps = obj->maps_buf_sz / - sizeof(struct bpf_map_def); + size_t nr_maps = obj->nr_maps; if (shdr->sh_type != SHT_REL) { pr_warning("internal error at %d\n", __LINE__); @@ -1050,10 +1041,8 @@ int bpf_object__unload(struct bpf_object *obj) if (!obj) return -EINVAL; - for (i = 0; i < obj->nr_map_fds; i++) - zclose(obj->map_fds[i]); - zfree(&obj->map_fds); - obj->nr_map_fds = 0; + for (i = 0; i < obj->nr_maps; i++) + zclose(obj->maps[i].fd); for (i = 0; i < obj->nr_programs; i++) bpf_program__unload(&obj->programs[i]); @@ -1096,7 +1085,15 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object__unload(obj); - zfree(&obj->maps_buf); + for (i = 0; i < obj->nr_maps; i++) { + if (obj->maps[i].clear_priv) + obj->maps[i].clear_priv(&obj->maps[i], + obj->maps[i].priv); + obj->maps[i].priv = NULL; + obj->maps[i].clear_priv = NULL; + } + zfree(&obj->maps); + obj->nr_maps = 0; if (obj->programs && obj->nr_programs) { for (i = 0; i < obj->nr_programs; i++) @@ -1251,3 +1248,73 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n) return fd; } + +int bpf_map__get_fd(struct bpf_map *map) +{ + if (!map) + return -EINVAL; + + return map->fd; +} + +int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef) +{ + if (!map || !pdef) + return -EINVAL; + + *pdef = map->def; + return 0; +} + +int bpf_map__set_private(struct bpf_map *map, void *priv, + bpf_map_clear_priv_t clear_priv) +{ + if (!map) + return -EINVAL; + + if (map->priv) { + if (map->clear_priv) + map->clear_priv(map, map->priv); + } + + map->priv = priv; + map->clear_priv = clear_priv; + return 0; +} + +int bpf_map__get_private(struct bpf_map *map, void **ppriv) +{ + if (!map) + return -EINVAL; + + if (ppriv) + *ppriv = map->priv; + return 0; +} + +struct bpf_map * +bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +{ + size_t idx; + struct bpf_map *s, *e; + + if (!obj || !obj->maps) + return NULL; + + s = obj->maps; + e = obj->maps + obj->nr_maps; + + if (prev == NULL) + return s; + + if ((prev < s) || (prev >= e)) { + pr_warning("error in %s: map handler doesn't belong to object\n", + __func__); + return NULL; + } + + idx = (prev - obj->maps) + 1; + if (idx >= obj->nr_maps) + return NULL; + return &obj->maps[idx]; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 949df4b346cf..ef631255dfaa 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -165,4 +165,25 @@ struct bpf_map_def { unsigned int max_entries; }; +/* + * There is another 'struct bpf_map' in include/linux/map.h. However, + * it is not a uapi header so no need to consider name clash. + */ +struct bpf_map; + +struct bpf_map * +bpf_map__next(struct bpf_map *map, struct bpf_object *obj); +#define bpf_map__for_each(pos, obj) \ + for ((pos) = bpf_map__next(NULL, (obj)); \ + (pos) != NULL; \ + (pos) = bpf_map__next((pos), (obj))) + +int bpf_map__get_fd(struct bpf_map *map); +int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef); + +typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); +int bpf_map__set_private(struct bpf_map *map, void *priv, + bpf_map_clear_priv_t clear_priv); +int bpf_map__get_private(struct bpf_map *map, void **ppriv); + #endif -- cgit v1.2.3 From 561bbccac72d08babafaa33fd7fa9100ec4c9fb6 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 27 Nov 2015 08:47:36 +0000 Subject: tools lib bpf: Extract and collect map names from BPF object file This patch collects name of maps in BPF object files and saves them into 'maps' field in 'struct bpf_object'. 'bpf_object__get_map_by_name' is introduced to retrive fd and definitions of a map through its name. Signed-off-by: He Kuang Cc: Alexei Starovoitov Cc: He Kuang Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1448614067-197576-3-git-send-email-wangnan0@huawei.com Signed-off-by: Wang Nan Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/libbpf.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++--- tools/lib/bpf/libbpf.h | 3 +++ 2 files changed, 65 insertions(+), 3 deletions(-) (limited to 'tools/lib/bpf/libbpf.h') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index f50982579aa8..a298614ad091 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -165,6 +165,7 @@ struct bpf_program { struct bpf_map { int fd; + char *name; struct bpf_map_def def; void *priv; bpf_map_clear_priv_t clear_priv; @@ -526,12 +527,46 @@ bpf_object__init_maps(struct bpf_object *obj, void *data, return 0; } +static void +bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx) +{ + int i; + Elf_Data *symbols = obj->efile.symbols; + + if (!symbols || maps_shndx < 0) + return; + + for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + GElf_Sym sym; + size_t map_idx; + const char *map_name; + + if (!gelf_getsym(symbols, i, &sym)) + continue; + if (sym.st_shndx != maps_shndx) + continue; + + map_name = elf_strptr(obj->efile.elf, + obj->efile.ehdr.e_shstrndx, + sym.st_name); + map_idx = sym.st_value / sizeof(struct bpf_map_def); + if (map_idx >= obj->nr_maps) { + pr_warning("index of map \"%s\" is buggy: %zu > %zu\n", + map_name, map_idx, obj->nr_maps); + continue; + } + obj->maps[map_idx].name = strdup(map_name); + pr_debug("map %zu is \"%s\"\n", map_idx, + obj->maps[map_idx].name); + } +} + static int bpf_object__elf_collect(struct bpf_object *obj) { Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Scn *scn = NULL; - int idx = 0, err = 0; + int idx = 0, err = 0, maps_shndx = -1; /* Elf is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { @@ -581,10 +616,11 @@ static int bpf_object__elf_collect(struct bpf_object *obj) err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); - else if (strcmp(name, "maps") == 0) + else if (strcmp(name, "maps") == 0) { err = bpf_object__init_maps(obj, data->d_buf, data->d_size); - else if (sh.sh_type == SHT_SYMTAB) { + maps_shndx = idx; + } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", obj->path); @@ -625,6 +661,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj) if (err) goto out; } + + if (maps_shndx >= 0) + bpf_object__init_maps_name(obj, maps_shndx); out: return err; } @@ -1086,6 +1125,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__unload(obj); for (i = 0; i < obj->nr_maps; i++) { + zfree(&obj->maps[i].name); if (obj->maps[i].clear_priv) obj->maps[i].clear_priv(&obj->maps[i], obj->maps[i].priv); @@ -1266,6 +1306,13 @@ int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef) return 0; } +const char *bpf_map__get_name(struct bpf_map *map) +{ + if (!map) + return NULL; + return map->name; +} + int bpf_map__set_private(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv) { @@ -1318,3 +1365,15 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) return NULL; return &obj->maps[idx]; } + +struct bpf_map * +bpf_object__get_map_by_name(struct bpf_object *obj, const char *name) +{ + struct bpf_map *pos; + + bpf_map__for_each(pos, obj) { + if (strcmp(pos->name, name) == 0) + return pos; + } + return NULL; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index ef631255dfaa..a51594c7b518 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -170,6 +170,8 @@ struct bpf_map_def { * it is not a uapi header so no need to consider name clash. */ struct bpf_map; +struct bpf_map * +bpf_object__get_map_by_name(struct bpf_object *obj, const char *name); struct bpf_map * bpf_map__next(struct bpf_map *map, struct bpf_object *obj); @@ -180,6 +182,7 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); int bpf_map__get_fd(struct bpf_map *map); int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef); +const char *bpf_map__get_name(struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); int bpf_map__set_private(struct bpf_map *map, void *priv, -- cgit v1.2.3