leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Browse Source 
Alexei Starovoitov says:

====================
pull-request: bpf-next 2021-03-09

The following pull-request contains BPF updates for your *net-next* tree.

We've added 90 non-merge commits during the last 17 day(s) which contain
a total of 114 files changed, 5158 insertions(+), 1288 deletions(-).

The main changes are:

1) Faster bpf_redirect_map(), from Björn.

2) skmsg cleanup, from Cong.

3) Support for floating point types in BTF, from Ilya.

4) Documentation for sys_bpf commands, from Joe.

5) Support for sk_lookup in bpf_prog_test_run, form Lorenz.

6) Enable task local storage for tracing programs, from Song.

7) bpf_for_each_map_elem() helper, from Yonghong.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller
2021-03-09 18:07:05 -08:00
parent 05a59d7979 32f91529e2
commit c1acda9807
114 changed files with 5158 additions and 1286 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/lib/bpf/Makefile
View File

@@ -158,7 +158,7 @@ $(BPF_IN_STATIC): force $(BPF_HELPER_DEFS)
$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
$(QUIET_GEN)$(srctree)/scripts/bpf_helpers_doc.py --header \
$(QUIET_GEN)$(srctree)/scripts/bpf_doc.py --header \
--file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS)
$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)

51
tools/lib/bpf/btf.c
View File

@@ -291,6 +291,7 @@ static int btf_type_size(const struct btf_type *t)
case BTF_KIND_PTR:
case BTF_KIND_TYPEDEF:
case BTF_KIND_FUNC:
case BTF_KIND_FLOAT:
return base_size;
case BTF_KIND_INT:
return base_size + sizeof(__u32);
@@ -338,6 +339,7 @@ static int btf_bswap_type_rest(struct btf_type *t)
case BTF_KIND_PTR:
case BTF_KIND_TYPEDEF:
case BTF_KIND_FUNC:
case BTF_KIND_FLOAT:
return 0;
case BTF_KIND_INT:
*(__u32 *)(t + 1) = bswap_32(*(__u32 *)(t + 1));
@@ -578,6 +580,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
case BTF_KIND_UNION:
case BTF_KIND_ENUM:
case BTF_KIND_DATASEC:
case BTF_KIND_FLOAT:
size = t->size;
goto done;
case BTF_KIND_PTR:
@@ -621,6 +624,7 @@ int btf__align_of(const struct btf *btf, __u32 id)
switch (kind) {
case BTF_KIND_INT:
case BTF_KIND_ENUM:
case BTF_KIND_FLOAT:
return min(btf_ptr_sz(btf), (size_t)t->size);
case BTF_KIND_PTR:
return btf_ptr_sz(btf);
@@ -1756,6 +1760,47 @@ int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding
return btf_commit_type(btf, sz);
}
/*
* Append new BTF_KIND_FLOAT type with:
* - *name* - non-empty, non-NULL type name;
* - *sz* - size of the type, in bytes;
* Returns:
* - >0, type ID of newly added BTF type;
* - <0, on error.
*/
int btf__add_float(struct btf *btf, const char *name, size_t byte_sz)
{
struct btf_type *t;
int sz, name_off;
/* non-empty name */
if (!name || !name[0])
return -EINVAL;
/* byte_sz must be one of the explicitly allowed values */
if (byte_sz != 2 && byte_sz != 4 && byte_sz != 8 && byte_sz != 12 &&
byte_sz != 16)
return -EINVAL;
if (btf_ensure_modifiable(btf))
return -ENOMEM;
sz = sizeof(struct btf_type);
t = btf_add_type_mem(btf, sz);
if (!t)
return -ENOMEM;
name_off = btf__add_str(btf, name);
if (name_off < 0)
return name_off;
t->name_off = name_off;
t->info = btf_type_info(BTF_KIND_FLOAT, 0, 0);
t->size = byte_sz;
return btf_commit_type(btf, sz);
}
/* it's completely legal to append BTF types with type IDs pointing forward to
* types that haven't been appended yet, so we only make sure that id looks
* sane, we can't guarantee that ID will always be valid
@@ -1883,7 +1928,7 @@ static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32
* - *byte_sz* - size of the struct, in bytes;
*
* Struct initially has no fields in it. Fields can be added by
* btf__add_field() right after btf__add_struct() succeeds.
* btf__add_field() right after btf__add_struct() succeeds.
*
* Returns:
* - >0, type ID of newly added BTF type;
@@ -3626,6 +3671,7 @@ static int btf_dedup_prep(struct btf_dedup *d)
case BTF_KIND_FWD:
case BTF_KIND_TYPEDEF:
case BTF_KIND_FUNC:
case BTF_KIND_FLOAT:
h = btf_hash_common(t);
break;
case BTF_KIND_INT:
@@ -3722,6 +3768,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
break;
case BTF_KIND_FWD:
case BTF_KIND_FLOAT:
h = btf_hash_common(t);
for_each_dedup_cand(d, hash_entry, h) {
cand_id = (__u32)(long)hash_entry->value;
@@ -3983,6 +4030,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
return btf_compat_enum(cand_type, canon_type);
case BTF_KIND_FWD:
case BTF_KIND_FLOAT:
return btf_equal_common(cand_type, canon_type);
case BTF_KIND_CONST:
@@ -4479,6 +4527,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
switch (btf_kind(t)) {
case BTF_KIND_INT:
case BTF_KIND_ENUM:
case BTF_KIND_FLOAT:
break;
case BTF_KIND_FWD:

6
tools/lib/bpf/btf.h
View File

@@ -95,6 +95,7 @@ LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding);
LIBBPF_API int btf__add_float(struct btf *btf, const char *name, size_t byte_sz);
LIBBPF_API int btf__add_ptr(struct btf *btf, int ref_type_id);
LIBBPF_API int btf__add_array(struct btf *btf,
int index_type_id, int elem_type_id, __u32 nr_elems);
@@ -294,6 +295,11 @@ static inline bool btf_is_datasec(const struct btf_type *t)
return btf_kind(t) == BTF_KIND_DATASEC;
}
static inline bool btf_is_float(const struct btf_type *t)
{
return btf_kind(t) == BTF_KIND_FLOAT;
}
static inline __u8 btf_int_encoding(const struct btf_type *t)
{
return BTF_INT_ENCODING(*(__u32 *)(t + 1));

4
tools/lib/bpf/btf_dump.c
View File

@@ -279,6 +279,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
case BTF_KIND_INT:
case BTF_KIND_ENUM:
case BTF_KIND_FWD:
case BTF_KIND_FLOAT:
break;
case BTF_KIND_VOLATILE:
@@ -453,6 +454,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
switch (btf_kind(t)) {
case BTF_KIND_INT:
case BTF_KIND_FLOAT:
tstate->order_state = ORDERED;
return 0;
@@ -1133,6 +1135,7 @@ skip_mod:
case BTF_KIND_STRUCT:
case BTF_KIND_UNION:
case BTF_KIND_TYPEDEF:
case BTF_KIND_FLOAT:
goto done;
default:
pr_warn("unexpected type in decl chain, kind:%u, id:[%u]\n",
@@ -1247,6 +1250,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
switch (kind) {
case BTF_KIND_INT:
case BTF_KIND_FLOAT:
btf_dump_emit_mods(d, decls);
name = btf_name_of(d, t->name_off);
btf_dump_printf(d, "%s", name);

105
tools/lib/bpf/libbpf.c
View File

@@ -178,6 +178,8 @@ enum kern_feature_id {
FEAT_PROG_BIND_MAP,
/* Kernel support for module BTFs */
FEAT_MODULE_BTF,
/* BTF_KIND_FLOAT support */
FEAT_BTF_FLOAT,
__FEAT_CNT,
};
@@ -188,6 +190,7 @@ enum reloc_type {
RELO_CALL,
RELO_DATA,
RELO_EXTERN,
RELO_SUBPROG_ADDR,
};
struct reloc_desc {
@@ -574,6 +577,16 @@ static bool insn_is_subprog_call(const struct bpf_insn *insn)
insn->off == 0;
}
static bool is_ldimm64(struct bpf_insn *insn)
{
return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
}
static bool insn_is_pseudo_func(struct bpf_insn *insn)
{
return is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
}
static int
bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog,
const char *name, size_t sec_idx, const char *sec_name,
@@ -1935,6 +1948,7 @@ static const char *btf_kind_str(const struct btf_type *t)
case BTF_KIND_FUNC_PROTO: return "func_proto";
case BTF_KIND_VAR: return "var";
case BTF_KIND_DATASEC: return "datasec";
case BTF_KIND_FLOAT: return "float";
default: return "unknown";
}
}
@@ -2384,15 +2398,17 @@ static bool btf_needs_sanitization(struct bpf_object *obj)
{
bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC);
bool has_datasec = kernel_supports(FEAT_BTF_DATASEC);
bool has_float = kernel_supports(FEAT_BTF_FLOAT);
bool has_func = kernel_supports(FEAT_BTF_FUNC);
return !has_func || !has_datasec || !has_func_global;
return !has_func || !has_datasec || !has_func_global || !has_float;
}
static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
{
bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC);
bool has_datasec = kernel_supports(FEAT_BTF_DATASEC);
bool has_float = kernel_supports(FEAT_BTF_FLOAT);
bool has_func = kernel_supports(FEAT_BTF_FUNC);
struct btf_type *t;
int i, j, vlen;
@@ -2445,6 +2461,13 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
} else if (!has_func_global && btf_is_func(t)) {
/* replace BTF_FUNC_GLOBAL with BTF_FUNC_STATIC */
t->info = BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0);
} else if (!has_float && btf_is_float(t)) {
/* replace FLOAT with an equally-sized empty STRUCT;
* since C compilers do not accept e.g. "float" as a
* valid struct name, make it anonymous
*/
t->name_off = 0;
t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0);
}
}
}
@@ -2974,6 +2997,23 @@ static bool sym_is_extern(const GElf_Sym *sym)
GELF_ST_TYPE(sym->st_info) == STT_NOTYPE;
}
static bool sym_is_subprog(const GElf_Sym *sym, int text_shndx)
{
int bind = GELF_ST_BIND(sym->st_info);
int type = GELF_ST_TYPE(sym->st_info);
/* in .text section */
if (sym->st_shndx != text_shndx)
return false;
/* local function */
if (bind == STB_LOCAL && type == STT_SECTION)
return true;
/* global function */
return bind == STB_GLOBAL && type == STT_FUNC;
}
static int find_extern_btf_id(const struct btf *btf, const char *ext_name)
{
const struct btf_type *t;
@@ -3395,7 +3435,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
return 0;
}
if (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) {
if (!is_ldimm64(insn)) {
pr_warn("prog '%s': invalid relo against '%s' for insns[%d].code 0x%x\n",
prog->name, sym_name, insn_idx, insn->code);
return -LIBBPF_ERRNO__RELOC;
@@ -3430,6 +3470,23 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
return -LIBBPF_ERRNO__RELOC;
}
/* loading subprog addresses */
if (sym_is_subprog(sym, obj->efile.text_shndx)) {
/* global_func: sym->st_value = offset in the section, insn->imm = 0.
* local_func: sym->st_value = 0, insn->imm = offset in the section.
*/
if ((sym->st_value % BPF_INSN_SZ) || (insn->imm % BPF_INSN_SZ)) {
pr_warn("prog '%s': bad subprog addr relo against '%s' at offset %zu+%d\n",
prog->name, sym_name, (size_t)sym->st_value, insn->imm);
return -LIBBPF_ERRNO__RELOC;
}
reloc_desc->type = RELO_SUBPROG_ADDR;
reloc_desc->insn_idx = insn_idx;
reloc_desc->sym_off = sym->st_value;
return 0;
}
type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
sym_sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, shdr_idx));
@@ -3882,6 +3939,18 @@ static int probe_kern_btf_datasec(void)
strs, sizeof(strs)));
}
static int probe_kern_btf_float(void)
{
static const char strs[] = "\0float";
__u32 types[] = {
/* float */
BTF_TYPE_FLOAT_ENC(1, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_array_mmap(void)
{
struct bpf_create_map_attr attr = {
@@ -4061,6 +4130,9 @@ static struct kern_feature_desc {
[FEAT_MODULE_BTF] = {
"module BTF support", probe_module_btf,
},
[FEAT_BTF_FLOAT] = {
"BTF_KIND_FLOAT support", probe_kern_btf_float,
},
};
static bool kernel_supports(enum kern_feature_id feat_id)
@@ -5566,11 +5638,6 @@ static void bpf_core_poison_insn(struct bpf_program *prog, int relo_idx,
insn->imm = 195896080; /* => 0xbad2310 => "bad relo" */
}
static bool is_ldimm64(struct bpf_insn *insn)
{
return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
}
static int insn_bpf_size_to_bytes(struct bpf_insn *insn)
{
switch (BPF_SIZE(insn->code)) {
@@ -6172,6 +6239,10 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
}
relo->processed = true;
break;
case RELO_SUBPROG_ADDR:
insn[0].src_reg = BPF_PSEUDO_FUNC;
/* will be handled as a follow up pass */
break;
case RELO_CALL:
/* will be handled as a follow up pass */
break;
@@ -6358,11 +6429,11 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
for (insn_idx = 0; insn_idx < prog->sec_insn_cnt; insn_idx++) {
insn = &main_prog->insns[prog->sub_insn_off + insn_idx];
if (!insn_is_subprog_call(insn))
if (!insn_is_subprog_call(insn) && !insn_is_pseudo_func(insn))
continue;
relo = find_prog_insn_relo(prog, insn_idx);
if (relo && relo->type != RELO_CALL) {
if (relo && relo->type != RELO_CALL && relo->type != RELO_SUBPROG_ADDR) {
pr_warn("prog '%s': unexpected relo for insn #%zu, type %d\n",
prog->name, insn_idx, relo->type);
return -LIBBPF_ERRNO__RELOC;
@@ -6374,8 +6445,22 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
* call always has imm = -1, but for static functions
* relocation is against STT_SECTION and insn->imm
* points to a start of a static function
*
* for subprog addr relocation, the relo->sym_off + insn->imm is
* the byte offset in the corresponding section.
*/
sub_insn_idx = relo->sym_off / BPF_INSN_SZ + insn->imm + 1;
if (relo->type == RELO_CALL)
sub_insn_idx = relo->sym_off / BPF_INSN_SZ + insn->imm + 1;
else
sub_insn_idx = (relo->sym_off + insn->imm) / BPF_INSN_SZ;
} else if (insn_is_pseudo_func(insn)) {
/*
* RELO_SUBPROG_ADDR relo is always emitted even if both
* functions are in the same section, so it shouldn't reach here.
*/
pr_warn("prog '%s': missing subprog addr relo for insn #%zu\n",
prog->name, insn_idx);
return -LIBBPF_ERRNO__RELOC;
} else {
/* if subprogram call is to a static function within
* the same ELF section, there won't be any relocation

5
tools/lib/bpf/libbpf.map
View File

@@ -350,3 +350,8 @@ LIBBPF_0.3.0 {
xsk_setup_xdp_prog;
xsk_socket__update_xskmap;
} LIBBPF_0.2.0;
LIBBPF_0.4.0 {
global:
btf__add_float;
} LIBBPF_0.3.0;

2
tools/lib/bpf/libbpf_internal.h
View File

@@ -31,6 +31,8 @@
#define BTF_MEMBER_ENC(name, type, bits_offset) (name), (type), (bits_offset)
#define BTF_PARAM_ENC(name, type) (name), (type)
#define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
#define BTF_TYPE_FLOAT_ENC(name, sz) \
BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
#ifndef likely
#define likely(x) __builtin_expect(!!(x), 1)

72
tools/lib/bpf/libbpf_util.h
View File

@@ -5,6 +5,7 @@
#define __LIBBPF_LIBBPF_UTIL_H
#include <stdbool.h>
#include <linux/compiler.h>
#ifdef __cplusplus
extern "C" {
@@ -15,29 +16,56 @@ extern "C" {
* application that uses libbpf.
*/
#if defined(__i386__) || defined(__x86_64__)
# define libbpf_smp_rmb() asm volatile("" : : : "memory")
# define libbpf_smp_wmb() asm volatile("" : : : "memory")
# define libbpf_smp_mb() \
asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc")
/* Hinders stores to be observed before older loads. */
# define libbpf_smp_rwmb() asm volatile("" : : : "memory")
# define libbpf_smp_store_release(p, v) \
do { \
asm volatile("" : : : "memory"); \
WRITE_ONCE(*p, v); \
} while (0)
# define libbpf_smp_load_acquire(p) \
({ \
typeof(*p) ___p1 = READ_ONCE(*p); \
asm volatile("" : : : "memory"); \
___p1; \
})
#elif defined(__aarch64__)
# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory")
# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
# define libbpf_smp_rwmb() libbpf_smp_mb()
#elif defined(__arm__)
/* These are only valid for armv7 and above */
# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory")
# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
# define libbpf_smp_rwmb() libbpf_smp_mb()
#else
/* Architecture missing native barrier functions. */
# define libbpf_smp_rmb() __sync_synchronize()
# define libbpf_smp_wmb() __sync_synchronize()
# define libbpf_smp_mb() __sync_synchronize()
# define libbpf_smp_rwmb() __sync_synchronize()
# define libbpf_smp_store_release(p, v) \
asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory")
# define libbpf_smp_load_acquire(p) \
({ \
typeof(*p) ___p1; \
asm volatile ("ldar %w0, %1" \
: "=r" (___p1) : "Q" (*p) : "memory"); \
___p1; \
})
#elif defined(__riscv)
# define libbpf_smp_store_release(p, v) \
do { \
asm volatile ("fence rw,w" : : : "memory"); \
WRITE_ONCE(*p, v); \
} while (0)
# define libbpf_smp_load_acquire(p) \
({ \
typeof(*p) ___p1 = READ_ONCE(*p); \
asm volatile ("fence r,rw" : : : "memory"); \
___p1; \
})
#endif
#ifndef libbpf_smp_store_release
#define libbpf_smp_store_release(p, v) \
do { \
__sync_synchronize(); \
WRITE_ONCE(*p, v); \
} while (0)
#endif
#ifndef libbpf_smp_load_acquire
#define libbpf_smp_load_acquire(p) \
({ \
typeof(*p) ___p1 = READ_ONCE(*p); \
__sync_synchronize(); \
___p1; \
})
#endif
#ifdef __cplusplus

17
tools/lib/bpf/xsk.h
View File

@@ -96,7 +96,8 @@ static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
* this function. Without this optimization it whould have been
* free_entries = r->cached_prod - r->cached_cons + r->size.
*/
r->cached_cons = *r->consumer + r->size;
r->cached_cons = libbpf_smp_load_acquire(r->consumer);
r->cached_cons += r->size;
return r->cached_cons - r->cached_prod;
}
@@ -106,7 +107,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
__u32 entries = r->cached_prod - r->cached_cons;
if (entries == 0) {
r->cached_prod = *r->producer;
r->cached_prod = libbpf_smp_load_acquire(r->producer);
entries = r->cached_prod - r->cached_cons;
}
@@ -129,9 +130,7 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb)
/* Make sure everything has been written to the ring before indicating
* this to the kernel by writing the producer pointer.
*/
libbpf_smp_wmb();
*prod->producer += nb;
libbpf_smp_store_release(prod->producer, *prod->producer + nb);
}
static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx)
@@ -139,11 +138,6 @@ static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __
__u32 entries = xsk_cons_nb_avail(cons, nb);
if (entries > 0) {
/* Make sure we do not speculatively read the data before
* we have received the packet buffers from the ring.
*/
libbpf_smp_rmb();
*idx = cons->cached_cons;
cons->cached_cons += entries;
}
@@ -161,9 +155,8 @@ static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb)
/* Make sure data has been read before indicating we are done
* with the entries by updating the consumer pointer.
*/
libbpf_smp_rwmb();
libbpf_smp_store_release(cons->consumer, *cons->consumer + nb);
*cons->consumer += nb;
}
static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)