diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 11:56:19 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 11:56:19 -0800 |
commit | 5bbcc0f595fadb4cac0eddc4401035ec0bd95b09 (patch) | |
tree | 3b65e490cc36a6c6fecac1fa24d9e0ac9ced4455 /tools/lib/bpf | |
parent | 892204e06cb9e89fbc4b299a678f9ca358e97cac (diff) | |
parent | 50895b9de1d3e0258e015e8e55128d835d9a9f19 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Maintain the TCP retransmit queue using an rbtree, with 1GB
windows at 100Gb this really has become necessary. From Eric
Dumazet.
2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.
3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
Lunn.
4) Add meter action support to openvswitch, from Andy Zhou.
5) Add a data meta pointer for BPF accessible packets, from Daniel
Borkmann.
6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.
7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.
8) More work to move the RTNL mutex down, from Florian Westphal.
9) Add 'bpftool' utility, to help with bpf program introspection.
From Jakub Kicinski.
10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
Dangaard Brouer.
11) Support 'blocks' of transformations in the packet scheduler which
can span multiple network devices, from Jiri Pirko.
12) TC flower offload support in cxgb4, from Kumar Sanghvi.
13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
Leitner.
14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.
15) Add RED qdisc offloadability, and use it in mlxsw driver. From
Nogah Frankel.
16) eBPF based device controller for cgroup v2, from Roman Gushchin.
17) Add some fundamental tracepoints for TCP, from Song Liu.
18) Remove garbage collection from ipv6 route layer, this is a
significant accomplishment. From Wei Wang.
19) Add multicast route offload support to mlxsw, from Yotam Gigi"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
tcp: highest_sack fix
geneve: fix fill_info when link down
bpf: fix lockdep splat
net: cdc_ncm: GetNtbFormat endian fix
openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
netem: remove unnecessary 64 bit modulus
netem: use 64 bit divide by rate
tcp: Namespace-ify sysctl_tcp_default_congestion_control
net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
ipv6: set all.accept_dad to 0 by default
uapi: fix linux/tls.h userspace compilation error
usbnet: ipheth: prevent TX queue timeouts when device not ready
vhost_net: conditionally enable tx polling
uapi: fix linux/rxrpc.h userspace compilation errors
net: stmmac: fix LPI transitioning for dwmac4
atm: horizon: Fix irq release error
net-sysfs: trigger netlink notification on ifalias change via sysfs
openvswitch: Using kfree_rcu() to simplify the code
openvswitch: Make local function ovs_nsh_key_attr_size() static
openvswitch: Fix return value check in ovs_meter_cmd_features()
...
Diffstat (limited to 'tools/lib/bpf')
-rw-r--r-- | tools/lib/bpf/bpf.c | 89 | ||||
-rw-r--r-- | tools/lib/bpf/bpf.h | 27 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.c | 179 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.h | 1 |
4 files changed, 220 insertions, 76 deletions
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 1d6907d379c9..5128677e4117 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -46,6 +46,8 @@ # endif #endif +#define min(x, y) ((x) < (y) ? (x) : (y)) + static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; @@ -57,10 +59,11 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, return syscall(__NR_bpf, cmd, attr, size); } -int bpf_create_map_node(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags, - int node) +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node) { + __u32 name_len = name ? strlen(name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -70,6 +73,8 @@ int bpf_create_map_node(enum bpf_map_type map_type, int key_size, attr.value_size = value_size; attr.max_entries = max_entries; attr.map_flags = map_flags; + memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (node >= 0) { attr.map_flags |= BPF_F_NUMA_NODE; attr.numa_node = node; @@ -81,14 +86,23 @@ int bpf_create_map_node(enum bpf_map_type map_type, int key_size, int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags) { - return bpf_create_map_node(map_type, key_size, value_size, + return bpf_create_map_node(map_type, NULL, key_size, value_size, max_entries, map_flags, -1); } -int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, +int bpf_create_map_name(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags) +{ + return bpf_create_map_node(map_type, name, key_size, value_size, + max_entries, map_flags, -1); +} + +int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node) { + __u32 name_len = name ? strlen(name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -99,6 +113,8 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, attr.inner_map_fd = inner_map_fd; attr.max_entries = max_entries; attr.map_flags = map_flags; + memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (node >= 0) { attr.map_flags |= BPF_F_NUMA_NODE; attr.numa_node = node; @@ -107,19 +123,24 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } -int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, __u32 map_flags) +int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags) { - return bpf_create_map_in_map_node(map_type, key_size, inner_map_fd, - max_entries, map_flags, -1); + return bpf_create_map_in_map_node(map_type, name, key_size, + inner_map_fd, max_entries, map_flags, + -1); } -int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, - size_t insns_cnt, const char *license, - __u32 kern_version, char *log_buf, size_t log_buf_sz) +int bpf_load_program_name(enum bpf_prog_type type, const char *name, + const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz) { int fd; union bpf_attr attr; + __u32 name_len = name ? strlen(name) : 0; bzero(&attr, sizeof(attr)); attr.prog_type = type; @@ -130,6 +151,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, attr.log_size = 0; attr.log_level = 0; attr.kern_version = kern_version; + memcpy(attr.prog_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); if (fd >= 0 || !log_buf || !log_buf_sz) @@ -143,6 +165,15 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } +int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz) +{ + return bpf_load_program_name(type, NULL, insns, insns_cnt, license, + kern_version, log_buf, log_buf_sz); +} + int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, int strict_alignment, const char *license, __u32 kern_version, @@ -260,6 +291,38 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type) return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); } +int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.target_fd = target_fd; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + + return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); +} + +int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, + __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt) +{ + union bpf_attr attr; + int ret; + + bzero(&attr, sizeof(attr)); + attr.query.target_fd = target_fd; + attr.query.attach_type = type; + attr.query.query_flags = query_flags; + attr.query.prog_cnt = *prog_cnt; + attr.query.prog_ids = ptr_to_u64(prog_ids); + + ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr)); + if (attach_flags) + *attach_flags = attr.query.attach_flags; + *prog_cnt = attr.query.prog_cnt; + return ret; +} + int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, __u32 *duration) diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index b8ea5843c39e..6534889e2b2f 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -24,19 +24,28 @@ #include <linux/bpf.h> #include <stddef.h> -int bpf_create_map_node(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags, - int node); +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node); +int bpf_create_map_name(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags); int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags); -int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, +int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node); -int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, __u32 map_flags); +int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags); /* Recommend log buffer size */ #define BPF_LOG_BUF_SIZE 65536 +int bpf_load_program_name(enum bpf_prog_type type, const char *name, + const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz); int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, @@ -57,6 +66,7 @@ int bpf_obj_get(const char *pathname); int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); +int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, __u32 *duration); @@ -65,5 +75,6 @@ int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); int bpf_prog_get_fd_by_id(__u32 id); int bpf_map_get_fd_by_id(__u32 id); int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); - +int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, + __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); #endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 35f6dfcdc565..5aa45f89da93 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -171,6 +171,7 @@ int libbpf_strerror(int err, char *buf, size_t size) struct bpf_program { /* Index in elf obj file, for relocation use. */ int idx; + char *name; char *section_name; struct bpf_insn *insns; size_t insns_cnt; @@ -283,6 +284,7 @@ static void bpf_program__exit(struct bpf_program *prog) prog->clear_priv = NULL; bpf_program__unload(prog); + zfree(&prog->name); zfree(&prog->section_name); zfree(&prog->insns); zfree(&prog->reloc_desc); @@ -293,26 +295,27 @@ static void bpf_program__exit(struct bpf_program *prog) } static int -bpf_program__init(void *data, size_t size, char *name, int idx, - struct bpf_program *prog) +bpf_program__init(void *data, size_t size, char *section_name, int idx, + struct bpf_program *prog) { if (size < sizeof(struct bpf_insn)) { - pr_warning("corrupted section '%s'\n", name); + pr_warning("corrupted section '%s'\n", section_name); return -EINVAL; } bzero(prog, sizeof(*prog)); - prog->section_name = strdup(name); + prog->section_name = strdup(section_name); if (!prog->section_name) { - pr_warning("failed to alloc name for prog %s\n", - name); + pr_warning("failed to alloc name for prog under section %s\n", + section_name); goto errout; } prog->insns = malloc(size); if (!prog->insns) { - pr_warning("failed to alloc insns for %s\n", name); + pr_warning("failed to alloc insns for prog under section %s\n", + section_name); goto errout; } prog->insns_cnt = size / sizeof(struct bpf_insn); @@ -331,12 +334,12 @@ errout: static int bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, - char *name, int idx) + char *section_name, int idx) { struct bpf_program prog, *progs; int nr_progs, err; - err = bpf_program__init(data, size, name, idx, &prog); + err = bpf_program__init(data, size, section_name, idx, &prog); if (err) return err; @@ -350,8 +353,8 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, * is still valid, so don't need special treat for * bpf_close_object(). */ - pr_warning("failed to alloc a new program '%s'\n", - name); + pr_warning("failed to alloc a new program under section '%s'\n", + section_name); bpf_program__exit(&prog); return -ENOMEM; } @@ -364,6 +367,54 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, return 0; } +static int +bpf_object__init_prog_names(struct bpf_object *obj) +{ + Elf_Data *symbols = obj->efile.symbols; + struct bpf_program *prog; + size_t pi, si; + + for (pi = 0; pi < obj->nr_programs; pi++) { + char *name = NULL; + + prog = &obj->programs[pi]; + + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; + si++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, si, &sym)) + continue; + if (sym.st_shndx != prog->idx) + continue; + + name = elf_strptr(obj->efile.elf, + obj->efile.strtabidx, + sym.st_name); + if (!name) { + pr_warning("failed to get sym name string for prog %s\n", + prog->section_name); + return -LIBBPF_ERRNO__LIBELF; + } + } + + if (!name) { + pr_warning("failed to find sym for prog %s\n", + prog->section_name); + return -EINVAL; + } + + prog->name = strdup(name); + if (!prog->name) { + pr_warning("failed to allocate memory for prog sym %s\n", + name); + return -ENOMEM; + } + } + + return 0; +} + static struct bpf_object *bpf_object__new(const char *path, void *obj_buf, size_t obj_buf_sz) @@ -528,31 +579,6 @@ bpf_object__init_kversion(struct bpf_object *obj, return 0; } -static int -bpf_object__validate_maps(struct bpf_object *obj) -{ - int i; - - /* - * If there's only 1 map, the only error case should have been - * catched in bpf_object__init_maps(). - */ - if (!obj->maps || !obj->nr_maps || (obj->nr_maps == 1)) - return 0; - - for (i = 1; i < obj->nr_maps; i++) { - const struct bpf_map *a = &obj->maps[i - 1]; - const struct bpf_map *b = &obj->maps[i]; - - if (b->offset - a->offset < sizeof(struct bpf_map_def)) { - pr_warning("corrupted map section in %s: map \"%s\" too small\n", - obj->path, a->name); - return -EINVAL; - } - } - return 0; -} - static int compare_bpf_map(const void *_a, const void *_b) { const struct bpf_map *a = _a; @@ -564,7 +590,7 @@ static int compare_bpf_map(const void *_a, const void *_b) static int bpf_object__init_maps(struct bpf_object *obj) { - int i, map_idx, nr_maps = 0; + int i, map_idx, map_def_sz, nr_maps = 0; Elf_Scn *scn; Elf_Data *data; Elf_Data *symbols = obj->efile.symbols; @@ -607,6 +633,15 @@ bpf_object__init_maps(struct bpf_object *obj) if (!nr_maps) return 0; + /* Assume equally sized map definitions */ + map_def_sz = data->d_size / nr_maps; + if (!data->d_size || (data->d_size % nr_maps) != 0) { + pr_warning("unable to determine map definition size " + "section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; + } + obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); if (!obj->maps) { pr_warning("alloc maps for object failed\n"); @@ -639,7 +674,7 @@ bpf_object__init_maps(struct bpf_object *obj) obj->efile.strtabidx, sym.st_name); obj->maps[map_idx].offset = sym.st_value; - if (sym.st_value + sizeof(struct bpf_map_def) > data->d_size) { + if (sym.st_value + map_def_sz > data->d_size) { pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", obj->path, map_name); return -EINVAL; @@ -653,12 +688,40 @@ bpf_object__init_maps(struct bpf_object *obj) pr_debug("map %d is \"%s\"\n", map_idx, obj->maps[map_idx].name); def = (struct bpf_map_def *)(data->d_buf + sym.st_value); - obj->maps[map_idx].def = *def; + /* + * If the definition of the map in the object file fits in + * bpf_map_def, copy it. Any extra fields in our version + * of bpf_map_def will default to zero as a result of the + * calloc above. + */ + if (map_def_sz <= sizeof(struct bpf_map_def)) { + memcpy(&obj->maps[map_idx].def, def, map_def_sz); + } else { + /* + * Here the map structure being read is bigger than what + * we expect, truncate if the excess bits are all zero. + * If they are not zero, reject this map as + * incompatible. + */ + char *b; + for (b = ((char *)def) + sizeof(struct bpf_map_def); + b < ((char *)def) + map_def_sz; b++) { + if (*b != 0) { + pr_warning("maps section in %s: \"%s\" " + "has unrecognized, non-zero " + "options\n", + obj->path, map_name); + return -EINVAL; + } + } + memcpy(&obj->maps[map_idx].def, def, + sizeof(struct bpf_map_def)); + } map_idx++; } qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); - return bpf_object__validate_maps(obj); + return 0; } static int bpf_object__elf_collect(struct bpf_object *obj) @@ -766,8 +829,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj) pr_warning("Corrupted ELF file: index of strtab invalid\n"); return LIBBPF_ERRNO__FORMAT; } - if (obj->efile.maps_shndx >= 0) + if (obj->efile.maps_shndx >= 0) { err = bpf_object__init_maps(obj); + if (err) + goto out; + } + err = bpf_object__init_prog_names(obj); out: return err; } @@ -870,11 +937,12 @@ bpf_object__create_maps(struct bpf_object *obj) struct bpf_map_def *def = &obj->maps[i].def; int *pfd = &obj->maps[i].fd; - *pfd = bpf_create_map(def->type, - def->key_size, - def->value_size, - def->max_entries, - 0); + *pfd = bpf_create_map_name(def->type, + obj->maps[i].name, + def->key_size, + def->value_size, + def->max_entries, + def->map_flags); if (*pfd < 0) { size_t j; int err = *pfd; @@ -982,7 +1050,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) } static int -load_program(enum bpf_prog_type type, struct bpf_insn *insns, +load_program(enum bpf_prog_type type, const char *name, struct bpf_insn *insns, int insns_cnt, char *license, u32 kern_version, int *pfd) { int ret; @@ -995,8 +1063,8 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns, if (!log_buf) pr_warning("Alloc log buffer for bpf loader error, continue without log\n"); - ret = bpf_load_program(type, insns, insns_cnt, license, - kern_version, log_buf, BPF_LOG_BUF_SIZE); + ret = bpf_load_program_name(type, name, insns, insns_cnt, license, + kern_version, log_buf, BPF_LOG_BUF_SIZE); if (ret >= 0) { *pfd = ret; @@ -1021,9 +1089,9 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns, if (type != BPF_PROG_TYPE_KPROBE) { int fd; - fd = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns, - insns_cnt, license, kern_version, - NULL, 0); + fd = bpf_load_program_name(BPF_PROG_TYPE_KPROBE, name, + insns, insns_cnt, license, + kern_version, NULL, 0); if (fd >= 0) { close(fd); ret = -LIBBPF_ERRNO__PROGTYPE; @@ -1067,8 +1135,8 @@ bpf_program__load(struct bpf_program *prog, pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n", prog->section_name, prog->instances.nr); } - err = load_program(prog->type, prog->insns, prog->insns_cnt, - license, kern_version, &fd); + err = load_program(prog->type, prog->name, prog->insns, + prog->insns_cnt, license, kern_version, &fd); if (!err) prog->instances.fds[0] = fd; goto out; @@ -1096,7 +1164,8 @@ bpf_program__load(struct bpf_program *prog, continue; } - err = load_program(prog->type, result.new_insn_ptr, + err = load_program(prog->type, prog->name, + result.new_insn_ptr, result.new_insn_cnt, license, kern_version, &fd); diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 7959086eb9c9..6e20003109e0 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -207,6 +207,7 @@ struct bpf_map_def { unsigned int key_size; unsigned int value_size; unsigned int max_entries; + unsigned int map_flags; }; /* |