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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-04-27

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

The main changes are:

1) Add extensive BPF helper description into include/uapi/linux/bpf.h
   and a new script bpf_helpers_doc.py which allows for generating a
   man page out of it. Thus, every helper in BPF now comes with proper
   function signature, detailed description and return code explanation,
   from Quentin.

2) Migrate the BPF collect metadata tunnel tests from BPF samples over
   to the BPF selftests and further extend them with v6 vxlan, geneve
   and ipip tests, simplify the ipip tests, improve documentation and
   convert to bpf_ntoh*() / bpf_hton*() api, from William.

3) Currently, helpers that expect ARG_PTR_TO_MAP_{KEY,VALUE} can only
   access stack and packet memory. Extend this to allow such helpers
   to also use map values, which enabled use cases where value from
   a first lookup can be directly used as a key for a second lookup,
   from Paul.

4) Add a new helper bpf_skb_get_xfrm_state() for tc BPF programs in
   order to retrieve XFRM state information containing SPI, peer
   address and reqid values, from Eyal.

5) Various optimizations in nfp driver's BPF JIT in order to turn ADD
   and SUB instructions with negative immediate into the opposite
   operation with a positive immediate such that nfp can better fit
   small immediates into instructions. Savings in instruction count
   up to 4% have been observed, from Jakub.

6) Add the BPF prog's gpl_compatible flag to struct bpf_prog_info
   and add support for dumping this through bpftool, from Jiri.

7) Move the BPF sockmap samples over into BPF selftests instead since
   sockmap was rather a series of tests than sample anyway and this way
   this can be run from automated bots, from John.

8) Follow-up fix for bpf_adjust_tail() helper in order to make it work
   with generic XDP, from Nikita.

9) Some follow-up cleanups to BTF, namely, removing unused defines from
   BTF uapi header and renaming 'name' struct btf_* members into name_off
   to make it more clear they are offsets into string section, from Martin.

10) Remove test_sock_addr from TEST_GEN_PROGS in BPF selftests since
    not run directly but invoked from test_sock_addr.sh, from Yonghong.

11) Remove redundant ret assignment in sample BPF loader, from Wang.

12) Add couple of missing files to BPF selftest's gitignore, from Anders.

There are two trivial merge conflicts while pulling:

  1) Remove samples/sockmap/Makefile since all sockmap tests have been
     moved to selftests.
  2) Add both hunks from tools/testing/selftests/bpf/.gitignore to the
     file since git should ignore all of them.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2018-04-26 21:19:50 -04:00
commit 79741a38b4
31 changed files with 5362 additions and 2073 deletions

View File

@ -1214,45 +1214,83 @@ wrp_test_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
return 0;
}
static int
wrp_cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
enum br_mask br_mask, bool swap)
static const struct jmp_code_map {
enum br_mask br_mask;
bool swap;
} jmp_code_map[] = {
[BPF_JGT >> 4] = { BR_BLO, true },
[BPF_JGE >> 4] = { BR_BHS, false },
[BPF_JLT >> 4] = { BR_BLO, false },
[BPF_JLE >> 4] = { BR_BHS, true },
[BPF_JSGT >> 4] = { BR_BLT, true },
[BPF_JSGE >> 4] = { BR_BGE, false },
[BPF_JSLT >> 4] = { BR_BLT, false },
[BPF_JSLE >> 4] = { BR_BGE, true },
};
static const struct jmp_code_map *nfp_jmp_code_get(struct nfp_insn_meta *meta)
{
unsigned int op;
op = BPF_OP(meta->insn.code) >> 4;
/* br_mask of 0 is BR_BEQ which we don't use in jump code table */
if (WARN_ONCE(op >= ARRAY_SIZE(jmp_code_map) ||
!jmp_code_map[op].br_mask,
"no code found for jump instruction"))
return NULL;
return &jmp_code_map[op];
}
static int cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
const struct bpf_insn *insn = &meta->insn;
u64 imm = insn->imm; /* sign extend */
const struct jmp_code_map *code;
enum alu_op alu_op, carry_op;
u8 reg = insn->dst_reg * 2;
swreg tmp_reg;
code = nfp_jmp_code_get(meta);
if (!code)
return -EINVAL;
alu_op = meta->jump_neg_op ? ALU_OP_ADD : ALU_OP_SUB;
carry_op = meta->jump_neg_op ? ALU_OP_ADD_C : ALU_OP_SUB_C;
tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
if (!swap)
emit_alu(nfp_prog, reg_none(), reg_a(reg), ALU_OP_SUB, tmp_reg);
if (!code->swap)
emit_alu(nfp_prog, reg_none(), reg_a(reg), alu_op, tmp_reg);
else
emit_alu(nfp_prog, reg_none(), tmp_reg, ALU_OP_SUB, reg_a(reg));
emit_alu(nfp_prog, reg_none(), tmp_reg, alu_op, reg_a(reg));
tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
if (!swap)
if (!code->swap)
emit_alu(nfp_prog, reg_none(),
reg_a(reg + 1), ALU_OP_SUB_C, tmp_reg);
reg_a(reg + 1), carry_op, tmp_reg);
else
emit_alu(nfp_prog, reg_none(),
tmp_reg, ALU_OP_SUB_C, reg_a(reg + 1));
tmp_reg, carry_op, reg_a(reg + 1));
emit_br(nfp_prog, br_mask, insn->off, 0);
emit_br(nfp_prog, code->br_mask, insn->off, 0);
return 0;
}
static int
wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
enum br_mask br_mask, bool swap)
static int cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
const struct bpf_insn *insn = &meta->insn;
const struct jmp_code_map *code;
u8 areg, breg;
code = nfp_jmp_code_get(meta);
if (!code)
return -EINVAL;
areg = insn->dst_reg * 2;
breg = insn->src_reg * 2;
if (swap) {
if (code->swap) {
areg ^= breg;
breg ^= areg;
areg ^= breg;
@ -1261,7 +1299,7 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
emit_alu(nfp_prog, reg_none(), reg_a(areg), ALU_OP_SUB, reg_b(breg));
emit_alu(nfp_prog, reg_none(),
reg_a(areg + 1), ALU_OP_SUB_C, reg_b(breg + 1));
emit_br(nfp_prog, br_mask, insn->off, 0);
emit_br(nfp_prog, code->br_mask, insn->off, 0);
return 0;
}
@ -1400,7 +1438,7 @@ map_call_stack_common(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
if (!load_lm_ptr)
return 0;
emit_csr_wr(nfp_prog, stack_reg(nfp_prog), NFP_CSR_ACT_LM_ADDR0);
emit_csr_wr(nfp_prog, stack_reg(nfp_prog), NFP_CSR_ACT_LM_ADDR0);
wrp_nops(nfp_prog, 3);
return 0;
@ -2283,46 +2321,6 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
return 0;
}
static int jgt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true);
}
static int jge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false);
}
static int jlt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_imm(nfp_prog, meta, BR_BLO, false);
}
static int jle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true);
}
static int jsgt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_imm(nfp_prog, meta, BR_BLT, true);
}
static int jsge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_imm(nfp_prog, meta, BR_BGE, false);
}
static int jslt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_imm(nfp_prog, meta, BR_BLT, false);
}
static int jsle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_imm(nfp_prog, meta, BR_BGE, true);
}
static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
const struct bpf_insn *insn = &meta->insn;
@ -2392,46 +2390,6 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
return 0;
}
static int jgt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true);
}
static int jge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false);
}
static int jlt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_reg(nfp_prog, meta, BR_BLO, false);
}
static int jle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true);
}
static int jsgt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_reg(nfp_prog, meta, BR_BLT, true);
}
static int jsge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_reg(nfp_prog, meta, BR_BGE, false);
}
static int jslt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_reg(nfp_prog, meta, BR_BLT, false);
}
static int jsle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_cmp_reg(nfp_prog, meta, BR_BGE, true);
}
static int jset_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_test_reg(nfp_prog, meta, ALU_OP_AND, BR_BNE);
@ -2520,25 +2478,25 @@ static const instr_cb_t instr_cb[256] = {
[BPF_ST | BPF_MEM | BPF_DW] = mem_st8,
[BPF_JMP | BPF_JA | BPF_K] = jump,
[BPF_JMP | BPF_JEQ | BPF_K] = jeq_imm,
[BPF_JMP | BPF_JGT | BPF_K] = jgt_imm,
[BPF_JMP | BPF_JGE | BPF_K] = jge_imm,
[BPF_JMP | BPF_JLT | BPF_K] = jlt_imm,
[BPF_JMP | BPF_JLE | BPF_K] = jle_imm,
[BPF_JMP | BPF_JSGT | BPF_K] = jsgt_imm,
[BPF_JMP | BPF_JSGE | BPF_K] = jsge_imm,
[BPF_JMP | BPF_JSLT | BPF_K] = jslt_imm,
[BPF_JMP | BPF_JSLE | BPF_K] = jsle_imm,
[BPF_JMP | BPF_JGT | BPF_K] = cmp_imm,
[BPF_JMP | BPF_JGE | BPF_K] = cmp_imm,
[BPF_JMP | BPF_JLT | BPF_K] = cmp_imm,
[BPF_JMP | BPF_JLE | BPF_K] = cmp_imm,
[BPF_JMP | BPF_JSGT | BPF_K] = cmp_imm,
[BPF_JMP | BPF_JSGE | BPF_K] = cmp_imm,
[BPF_JMP | BPF_JSLT | BPF_K] = cmp_imm,
[BPF_JMP | BPF_JSLE | BPF_K] = cmp_imm,
[BPF_JMP | BPF_JSET | BPF_K] = jset_imm,
[BPF_JMP | BPF_JNE | BPF_K] = jne_imm,
[BPF_JMP | BPF_JEQ | BPF_X] = jeq_reg,
[BPF_JMP | BPF_JGT | BPF_X] = jgt_reg,
[BPF_JMP | BPF_JGE | BPF_X] = jge_reg,
[BPF_JMP | BPF_JLT | BPF_X] = jlt_reg,
[BPF_JMP | BPF_JLE | BPF_X] = jle_reg,
[BPF_JMP | BPF_JSGT | BPF_X] = jsgt_reg,
[BPF_JMP | BPF_JSGE | BPF_X] = jsge_reg,
[BPF_JMP | BPF_JSLT | BPF_X] = jslt_reg,
[BPF_JMP | BPF_JSLE | BPF_X] = jsle_reg,
[BPF_JMP | BPF_JGT | BPF_X] = cmp_reg,
[BPF_JMP | BPF_JGE | BPF_X] = cmp_reg,
[BPF_JMP | BPF_JLT | BPF_X] = cmp_reg,
[BPF_JMP | BPF_JLE | BPF_X] = cmp_reg,
[BPF_JMP | BPF_JSGT | BPF_X] = cmp_reg,
[BPF_JMP | BPF_JSGE | BPF_X] = cmp_reg,
[BPF_JMP | BPF_JSLT | BPF_X] = cmp_reg,
[BPF_JMP | BPF_JSLE | BPF_X] = cmp_reg,
[BPF_JMP | BPF_JSET | BPF_X] = jset_reg,
[BPF_JMP | BPF_JNE | BPF_X] = jne_reg,
[BPF_JMP | BPF_CALL] = call,
@ -2777,6 +2735,54 @@ static void nfp_bpf_opt_reg_init(struct nfp_prog *nfp_prog)
}
}
/* abs(insn.imm) will fit better into unrestricted reg immediate -
* convert add/sub of a negative number into a sub/add of a positive one.
*/
static void nfp_bpf_opt_neg_add_sub(struct nfp_prog *nfp_prog)
{
struct nfp_insn_meta *meta;
list_for_each_entry(meta, &nfp_prog->insns, l) {
struct bpf_insn insn = meta->insn;
if (meta->skip)
continue;
if (BPF_CLASS(insn.code) != BPF_ALU &&
BPF_CLASS(insn.code) != BPF_ALU64 &&
BPF_CLASS(insn.code) != BPF_JMP)
continue;
if (BPF_SRC(insn.code) != BPF_K)
continue;
if (insn.imm >= 0)
continue;
if (BPF_CLASS(insn.code) == BPF_JMP) {
switch (BPF_OP(insn.code)) {
case BPF_JGE:
case BPF_JSGE:
case BPF_JLT:
case BPF_JSLT:
meta->jump_neg_op = true;
break;
default:
continue;
}
} else {
if (BPF_OP(insn.code) == BPF_ADD)
insn.code = BPF_CLASS(insn.code) | BPF_SUB;
else if (BPF_OP(insn.code) == BPF_SUB)
insn.code = BPF_CLASS(insn.code) | BPF_ADD;
else
continue;
meta->insn.code = insn.code | BPF_K;
}
meta->insn.imm = -insn.imm;
}
}
/* Remove masking after load since our load guarantees this is not needed */
static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog)
{
@ -3212,6 +3218,7 @@ static int nfp_bpf_optimize(struct nfp_prog *nfp_prog)
{
nfp_bpf_opt_reg_init(nfp_prog);
nfp_bpf_opt_neg_add_sub(nfp_prog);
nfp_bpf_opt_ld_mask(nfp_prog);
nfp_bpf_opt_ld_shift(nfp_prog);
nfp_bpf_opt_ldst_gather(nfp_prog);

View File

@ -236,6 +236,7 @@ struct nfp_bpf_reg_state {
* @xadd_over_16bit: 16bit immediate is not guaranteed
* @xadd_maybe_16bit: 16bit immediate is possible
* @jmp_dst: destination info for jump instructions
* @jump_neg_op: jump instruction has inverted immediate, use ADD instead of SUB
* @func_id: function id for call instructions
* @arg1: arg1 for call instructions
* @arg2: arg2 for call instructions
@ -264,7 +265,10 @@ struct nfp_insn_meta {
bool xadd_maybe_16bit;
};
/* jump */
struct nfp_insn_meta *jmp_dst;
struct {
struct nfp_insn_meta *jmp_dst;
bool jump_neg_op;
};
/* function calls */
struct {
u32 func_id;

View File

@ -765,7 +765,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
/* recalculate len if xdp.data or xdp.data_end were
* adjusted
*/
len = xdp.data_end - xdp.data;
len = xdp.data_end - xdp.data + vi->hdr_len;
/* We can only create skb based on xdp_page. */
if (unlikely(xdp_page != page)) {
rcu_read_unlock();

File diff suppressed because it is too large Load Diff

View File

@ -6,9 +6,7 @@
#include <linux/types.h>
#define BTF_MAGIC 0xeB9F
#define BTF_MAGIC_SWAP 0x9FeB
#define BTF_VERSION 1
#define BTF_FLAGS_COMPR 0x01
struct btf_header {
__u16 magic;
@ -43,7 +41,7 @@ struct btf_header {
#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET)
struct btf_type {
__u32 name;
__u32 name_off;
/* "info" bits arrangement
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
@ -105,7 +103,7 @@ struct btf_type {
* info in "struct btf_type").
*/
struct btf_enum {
__u32 name;
__u32 name_off;
__s32 val;
};
@ -122,7 +120,7 @@ struct btf_array {
* "struct btf_type").
*/
struct btf_member {
__u32 name;
__u32 name_off;
__u32 type;
__u32 offset; /* offset in bits */
};

View File

@ -473,7 +473,7 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env,
__btf_verifier_log(log, "[%u] %s %s%s",
env->log_type_id,
btf_kind_str[kind],
btf_name_by_offset(btf, t->name),
btf_name_by_offset(btf, t->name_off),
log_details ? " " : "");
if (log_details)
@ -517,7 +517,7 @@ static void btf_verifier_log_member(struct btf_verifier_env *env,
btf_verifier_log_type(env, struct_type, NULL);
__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
btf_name_by_offset(btf, member->name),
btf_name_by_offset(btf, member->name_off),
member->type, member->offset);
if (fmt && *fmt) {
@ -1419,10 +1419,10 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
btf_verifier_log_type(env, t, NULL);
for_each_member(i, t, member) {
if (!btf_name_offset_valid(btf, member->name)) {
if (!btf_name_offset_valid(btf, member->name_off)) {
btf_verifier_log_member(env, t, member,
"Invalid member name_offset:%u",
member->name);
member->name_off);
return -EINVAL;
}
@ -1605,14 +1605,14 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
btf_verifier_log_type(env, t, NULL);
for (i = 0; i < nr_enums; i++) {
if (!btf_name_offset_valid(btf, enums[i].name)) {
if (!btf_name_offset_valid(btf, enums[i].name_off)) {
btf_verifier_log(env, "\tInvalid name_offset:%u",
enums[i].name);
enums[i].name_off);
return -EINVAL;
}
btf_verifier_log(env, "\t%s val=%d\n",
btf_name_by_offset(btf, enums[i].name),
btf_name_by_offset(btf, enums[i].name_off),
enums[i].val);
}
@ -1636,7 +1636,7 @@ static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
for (i = 0; i < nr_enums; i++) {
if (v == enums[i].val) {
seq_printf(m, "%s",
btf_name_by_offset(btf, enums[i].name));
btf_name_by_offset(btf, enums[i].name_off));
return;
}
}
@ -1687,9 +1687,9 @@ static s32 btf_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
if (!btf_name_offset_valid(env->btf, t->name)) {
if (!btf_name_offset_valid(env->btf, t->name_off)) {
btf_verifier_log(env, "[%u] Invalid name_offset:%u",
env->log_type_id, t->name);
env->log_type_id, t->name_off);
return -EINVAL;
}

View File

@ -1914,6 +1914,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
info.load_time = prog->aux->load_time;
info.created_by_uid = from_kuid_munged(current_user_ns(),
prog->aux->user->uid);
info.gpl_compatible = prog->gpl_compatible;
memcpy(info.tag, prog->tag, sizeof(prog->tag));
memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));

View File

@ -1914,7 +1914,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
if (arg_type == ARG_PTR_TO_MAP_KEY ||
arg_type == ARG_PTR_TO_MAP_VALUE) {
expected_type = PTR_TO_STACK;
if (!type_is_pkt_pointer(type) &&
if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
type != expected_type)
goto err_type;
} else if (arg_type == ARG_CONST_SIZE ||
@ -1966,14 +1966,9 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
verbose(env, "invalid map_ptr to access map->key\n");
return -EACCES;
}
if (type_is_pkt_pointer(type))
err = check_packet_access(env, regno, reg->off,
meta->map_ptr->key_size,
false);
else
err = check_stack_boundary(env, regno,
meta->map_ptr->key_size,
false, NULL);
err = check_helper_mem_access(env, regno,
meta->map_ptr->key_size, false,
NULL);
} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
@ -1983,14 +1978,9 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
verbose(env, "invalid map_ptr to access map->value\n");
return -EACCES;
}
if (type_is_pkt_pointer(type))
err = check_packet_access(env, regno, reg->off,
meta->map_ptr->value_size,
false);
else
err = check_stack_boundary(env, regno,
meta->map_ptr->value_size,
false, NULL);
err = check_helper_mem_access(env, regno,
meta->map_ptr->value_size, false,
NULL);
} else if (arg_type_is_mem_size(arg_type)) {
bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);

View File

@ -4057,8 +4057,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
* pckt.
*/
off = orig_data_end - xdp.data_end;
if (off != 0)
if (off != 0) {
skb_set_tail_pointer(skb, xdp.data_end - xdp.data);
skb->len -= off;
}
switch (act) {
case XDP_REDIRECT:

View File

@ -57,6 +57,7 @@
#include <net/sock_reuseport.h>
#include <net/busy_poll.h>
#include <net/tcp.h>
#include <net/xfrm.h>
#include <linux/bpf_trace.h>
/**
@ -3744,6 +3745,49 @@ static const struct bpf_func_proto bpf_bind_proto = {
.arg3_type = ARG_CONST_SIZE,
};
#ifdef CONFIG_XFRM
BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index,
struct bpf_xfrm_state *, to, u32, size, u64, flags)
{
const struct sec_path *sp = skb_sec_path(skb);
const struct xfrm_state *x;
if (!sp || unlikely(index >= sp->len || flags))
goto err_clear;
x = sp->xvec[index];
if (unlikely(size != sizeof(struct bpf_xfrm_state)))
goto err_clear;
to->reqid = x->props.reqid;
to->spi = x->id.spi;
to->family = x->props.family;
if (to->family == AF_INET6) {
memcpy(to->remote_ipv6, x->props.saddr.a6,
sizeof(to->remote_ipv6));
} else {
to->remote_ipv4 = x->props.saddr.a4;
}
return 0;
err_clear:
memset(to, 0, size);
return -EINVAL;
}
static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
.func = bpf_skb_get_xfrm_state,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_PTR_TO_UNINIT_MEM,
.arg4_type = ARG_CONST_SIZE,
.arg5_type = ARG_ANYTHING,
};
#endif
static const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
@ -3885,6 +3929,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_socket_cookie_proto;
case BPF_FUNC_get_socket_uid:
return &bpf_get_socket_uid_proto;
#ifdef CONFIG_XFRM
case BPF_FUNC_skb_get_xfrm_state:
return &bpf_skb_get_xfrm_state_proto;
#endif
default:
return bpf_base_func_proto(func_id);
}

View File

@ -114,7 +114,6 @@ always += sock_flags_kern.o
always += test_probe_write_user_kern.o
always += trace_output_kern.o
always += tcbpf1_kern.o
always += tcbpf2_kern.o
always += tc_l2_redirect_kern.o
always += lathist_kern.o
always += offwaketime_kern.o

View File

@ -549,7 +549,6 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
if (nr_maps < 0) {
printf("Error: Failed loading ELF maps (errno:%d):%s\n",
nr_maps, strerror(-nr_maps));
ret = 1;
goto done;
}
if (load_maps(map_data, nr_maps, fixup_map))
@ -615,7 +614,6 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
}
}
ret = 0;
done:
close(fd);
return ret;

View File

@ -1,319 +0,0 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
# In Namespace 0 (at_ns0) using native tunnel
# Overlay IP: 10.1.1.100
# local 192.16.1.100 remote 192.16.1.200
# veth0 IP: 172.16.1.100, tunnel dev <type>00
# Out of Namespace using BPF set/get on lwtunnel
# Overlay IP: 10.1.1.200
# local 172.16.1.200 remote 172.16.1.100
# veth1 IP: 172.16.1.200, tunnel dev <type>11
function config_device {
ip netns add at_ns0
ip link add veth0 type veth peer name veth1
ip link set veth0 netns at_ns0
ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip link set dev veth1 up mtu 1500
ip addr add dev veth1 172.16.1.200/24
}
function add_gre_tunnel {
# in namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local 172.16.1.100 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# out of namespace
ip link add dev $DEV type $TYPE key 2 external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
function add_ip6gretap_tunnel {
# assign ipv6 address
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# in namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
local ::11 remote ::22
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96
ip netns exec at_ns0 ip link set dev $DEV_NS up
# out of namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip addr add dev $DEV fc80::200/24
ip link set dev $DEV up
}
function add_erspan_tunnel {
# in namespace
if [ "$1" == "v1" ]; then
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local 172.16.1.100 remote 172.16.1.200 \
erspan_ver 1 erspan 123
else
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local 172.16.1.100 remote 172.16.1.200 \
erspan_ver 2 erspan_dir egress erspan_hwid 3
fi
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# out of namespace
ip link add dev $DEV type $TYPE external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
function add_ip6erspan_tunnel {
# assign ipv6 address
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# in namespace
if [ "$1" == "v1" ]; then
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local ::11 remote ::22 \
erspan_ver 1 erspan 123
else
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local ::11 remote ::22 \
erspan_ver 2 erspan_dir egress erspan_hwid 7
fi
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip link set dev $DEV_NS up
# out of namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip link set dev $DEV up
}
function add_vxlan_tunnel {
# Set static ARP entry here because iptables set-mark works
# on L3 packet, as a result not applying to ARP packets,
# causing errors at get_tunnel_{key/opt}.
# in namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE id 2 dstport 4789 gbp remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS address 52:54:00:d9:01:00 up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00
ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF
# out of namespace
ip link add dev $DEV type $TYPE external gbp dstport 4789
ip link set dev $DEV address 52:54:00:d9:02:00 up
ip addr add dev $DEV 10.1.1.200/24
arp -s 10.1.1.100 52:54:00:d9:01:00
}
function add_geneve_tunnel {
# in namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE id 2 dstport 6081 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# out of namespace
ip link add dev $DEV type $TYPE dstport 6081 external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
function add_ipip_tunnel {
# in namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE local 172.16.1.100 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# out of namespace
ip link add dev $DEV type $TYPE external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
function attach_bpf {
DEV=$1
SET_TUNNEL=$2
GET_TUNNEL=$3
tc qdisc add dev $DEV clsact
tc filter add dev $DEV egress bpf da obj tcbpf2_kern.o sec $SET_TUNNEL
tc filter add dev $DEV ingress bpf da obj tcbpf2_kern.o sec $GET_TUNNEL
}
function test_gre {
TYPE=gretap
DEV_NS=gretap00
DEV=gretap11
config_device
add_gre_tunnel
attach_bpf $DEV gre_set_tunnel gre_get_tunnel
ping -c 1 10.1.1.100
ip netns exec at_ns0 ping -c 1 10.1.1.200
cleanup
}
function test_ip6gre {
TYPE=ip6gre
DEV_NS=ip6gre00
DEV=ip6gre11
config_device
# reuse the ip6gretap function
add_ip6gretap_tunnel
attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
# underlay
ping6 -c 4 ::11
# overlay: ipv4 over ipv6
ip netns exec at_ns0 ping -c 1 10.1.1.200
ping -c 1 10.1.1.100
# overlay: ipv6 over ipv6
ip netns exec at_ns0 ping6 -c 1 fc80::200
cleanup
}
function test_ip6gretap {
TYPE=ip6gretap
DEV_NS=ip6gretap00
DEV=ip6gretap11
config_device
add_ip6gretap_tunnel
attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
# underlay
ping6 -c 4 ::11
# overlay: ipv4 over ipv6
ip netns exec at_ns0 ping -i .2 -c 1 10.1.1.200
ping -c 1 10.1.1.100
# overlay: ipv6 over ipv6
ip netns exec at_ns0 ping6 -c 1 fc80::200
cleanup
}
function test_erspan {
TYPE=erspan
DEV_NS=erspan00
DEV=erspan11
config_device
add_erspan_tunnel $1
attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel
ping -c 1 10.1.1.100
ip netns exec at_ns0 ping -c 1 10.1.1.200
cleanup
}
function test_ip6erspan {
TYPE=ip6erspan
DEV_NS=ip6erspan00
DEV=ip6erspan11
config_device
add_ip6erspan_tunnel $1
attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
ping6 -c 3 ::11
ip netns exec at_ns0 ping -c 1 10.1.1.200
cleanup
}
function test_vxlan {
TYPE=vxlan
DEV_NS=vxlan00
DEV=vxlan11
config_device
add_vxlan_tunnel
attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel
ping -c 1 10.1.1.100
ip netns exec at_ns0 ping -c 1 10.1.1.200
cleanup
}
function test_geneve {
TYPE=geneve
DEV_NS=geneve00
DEV=geneve11
config_device
add_geneve_tunnel
attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel
ping -c 1 10.1.1.100
ip netns exec at_ns0 ping -c 1 10.1.1.200
cleanup
}
function test_ipip {
TYPE=ipip
DEV_NS=ipip00
DEV=ipip11
config_device
tcpdump -nei veth1 &
cat /sys/kernel/debug/tracing/trace_pipe &
add_ipip_tunnel
ethtool -K veth1 gso off gro off rx off tx off
ip link set dev veth1 mtu 1500
attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
ping -c 1 10.1.1.100
ip netns exec at_ns0 ping -c 1 10.1.1.200
ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null
sleep 0.2
iperf -c 10.1.1.100 -n 5k -p 5200
cleanup
}
function cleanup {
set +ex
pkill iperf
ip netns delete at_ns0
ip link del veth1
ip link del ipip11
ip link del gretap11
ip link del ip6gre11
ip link del ip6gretap11
ip link del vxlan11
ip link del geneve11
ip link del erspan11
ip link del ip6erspan11
pkill tcpdump
pkill cat
set -ex
}
trap cleanup 0 2 3 6 9
cleanup
echo "Testing GRE tunnel..."
test_gre
echo "Testing IP6GRE tunnel..."
test_ip6gre
echo "Testing IP6GRETAP tunnel..."
test_ip6gretap
echo "Testing ERSPAN tunnel..."
test_erspan v1
test_erspan v2
echo "Testing IP6ERSPAN tunnel..."
test_ip6erspan v1
test_ip6erspan v2
echo "Testing VXLAN tunnel..."
test_vxlan
echo "Testing GENEVE tunnel..."
test_geneve
echo "Testing IPIP tunnel..."
test_ipip
echo "*** PASS ***"

View File

@ -1,78 +0,0 @@
# List of programs to build
hostprogs-y := sockmap
# Libbpf dependencies
LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
HOSTCFLAGS += -I$(srctree)/tools/perf
sockmap-objs := ../bpf/bpf_load.o $(LIBBPF) sockmap_user.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
always += sockmap_kern.o
HOSTLOADLIBES_sockmap += -lelf -lpthread
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
LLC ?= llc
CLANG ?= clang
# Trick to allow make to be run from this directory
all:
$(MAKE) -C ../../ $(CURDIR)/
clean:
$(MAKE) -C ../../ M=$(CURDIR) clean
@rm -f *~
$(obj)/syscall_nrs.s: $(src)/syscall_nrs.c
$(call if_changed_dep,cc_s_c)
$(obj)/syscall_nrs.h: $(obj)/syscall_nrs.s FORCE
$(call filechk,offsets,__SYSCALL_NRS_H__)
clean-files += syscall_nrs.h
FORCE:
# Verify LLVM compiler tools are available and bpf target is supported by llc
.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC)
verify_cmds: $(CLANG) $(LLC)
@for TOOL in $^ ; do \
if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \
echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\
exit 1; \
else true; fi; \
done
verify_target_bpf: verify_cmds
@if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \
echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\
echo " NOTICE: LLVM version >= 3.7.1 required" ;\
exit 2; \
else true; fi
$(src)/*.c: verify_target_bpf
# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
# But, there is no easy way to fix it, so just exclude it since it is
# useless for BPF samples.
#
# -target bpf option required with SK_MSG programs, this is to ensure
# reading 'void *' data types for data and data_end are __u64 reads.
$(obj)/%.o: $(src)/%.c
$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
-Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
-Wno-unknown-warning-option -O2 -target bpf \
-emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@

View File

@ -1,488 +0,0 @@
#Test a bunch of positive cases to verify basic functionality
for prog in "--txmsg_redir --txmsg_skb" "--txmsg_redir --txmsg_ingress" "--txmsg" "--txmsg_redir" "--txmsg_redir --txmsg_ingress" "--txmsg_drop"; do
for t in "sendmsg" "sendpage"; do
for r in 1 10 100; do
for i in 1 10 100; do
for l in 1 10 100; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
done
done
done
done
#Test max iov
t="sendmsg"
r=1
i=1024
l=1
prog="--txmsg"
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
prog="--txmsg_redir"
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
# Test max iov with 1k send
t="sendmsg"
r=1
i=1024
l=1024
prog="--txmsg"
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
prog="--txmsg_redir"
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
# Test apply with 1B
r=1
i=1024
l=1024
prog="--txmsg_apply 1"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply with larger value than send
r=1
i=8
l=1024
prog="--txmsg_apply 2048"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply with apply that never reaches limit
r=1024
i=1
l=1
prog="--txmsg_apply 2048"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply and redirect with 1B
r=1
i=1024
l=1024
prog="--txmsg_redir --txmsg_apply 1"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
prog="--txmsg_redir --txmsg_apply 1 --txmsg_ingress"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
prog="--txmsg_redir --txmsg_apply 1 --txmsg_skb"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply and redirect with larger value than send
r=1
i=8
l=1024
prog="--txmsg_redir --txmsg_apply 2048"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
prog="--txmsg_redir --txmsg_apply 2048 --txmsg_ingress"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
prog="--txmsg_redir --txmsg_apply 2048 --txmsg_skb"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply and redirect with apply that never reaches limit
r=1024
i=1
l=1
prog="--txmsg_apply 2048"
for t in "sendmsg" "sendpage"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test cork with 1B not really useful but test it anyways
r=1
i=1024
l=1024
prog="--txmsg_cork 1"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test cork with a more reasonable 100B
r=1
i=1000
l=1000
prog="--txmsg_cork 100"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test cork with larger value than send
r=1
i=8
l=1024
prog="--txmsg_cork 2048"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test cork with cork that never reaches limit
r=1024
i=1
l=1
prog="--txmsg_cork 2048"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
r=1
i=1024
l=1024
prog="--txmsg_redir --txmsg_cork 1"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test cork with a more reasonable 100B
r=1
i=1000
l=1000
prog="--txmsg_redir --txmsg_cork 100"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test cork with larger value than send
r=1
i=8
l=1024
prog="--txmsg_redir --txmsg_cork 2048"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test cork with cork that never reaches limit
r=1024
i=1
l=1
prog="--txmsg_cork 2048"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# mix and match cork and apply not really useful but valid programs
# Test apply < cork
r=100
i=1
l=5
prog="--txmsg_apply 10 --txmsg_cork 100"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Try again with larger sizes so we hit overflow case
r=100
i=1000
l=2048
prog="--txmsg_apply 4096 --txmsg_cork 8096"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply > cork
r=100
i=1
l=5
prog="--txmsg_apply 100 --txmsg_cork 10"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Again with larger sizes so we hit overflow cases
r=100
i=1000
l=2048
prog="--txmsg_apply 8096 --txmsg_cork 4096"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply = cork
r=100
i=1
l=5
prog="--txmsg_apply 10 --txmsg_cork 10"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
r=100
i=1000
l=2048
prog="--txmsg_apply 4096 --txmsg_cork 4096"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply < cork
r=100
i=1
l=5
prog="--txmsg_redir --txmsg_apply 10 --txmsg_cork 100"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Try again with larger sizes so we hit overflow case
r=100
i=1000
l=2048
prog="--txmsg_redir --txmsg_apply 4096 --txmsg_cork 8096"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply > cork
r=100
i=1
l=5
prog="--txmsg_redir --txmsg_apply 100 --txmsg_cork 10"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Again with larger sizes so we hit overflow cases
r=100
i=1000
l=2048
prog="--txmsg_redir --txmsg_apply 8096 --txmsg_cork 4096"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Test apply = cork
r=100
i=1
l=5
prog="--txmsg_redir --txmsg_apply 10 --txmsg_cork 10"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
r=100
i=1000
l=2048
prog="--txmsg_redir --txmsg_apply 4096 --txmsg_cork 4096"
for t in "sendpage" "sendmsg"; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
echo $TEST
$TEST
sleep 2
done
# Tests for bpf_msg_pull_data()
for i in `seq 99 100 1600`; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
--txmsg --txmsg_start 0 --txmsg_end $i --txmsg_cork 1600"
echo $TEST
$TEST
sleep 2
done
for i in `seq 199 100 1600`; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
--txmsg --txmsg_start 100 --txmsg_end $i --txmsg_cork 1600"
echo $TEST
$TEST
sleep 2
done
TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
--txmsg --txmsg_start 1500 --txmsg_end 1600 --txmsg_cork 1600"
echo $TEST
$TEST
sleep 2
TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
--txmsg --txmsg_start 1111 --txmsg_end 1112 --txmsg_cork 1600"
echo $TEST
$TEST
sleep 2
TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
--txmsg --txmsg_start 1111 --txmsg_end 0 --txmsg_cork 1600"
echo $TEST
$TEST
sleep 2
TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
--txmsg --txmsg_start 0 --txmsg_end 1601 --txmsg_cork 1600"
echo $TEST
$TEST
sleep 2
TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
--txmsg --txmsg_start 0 --txmsg_end 1601 --txmsg_cork 1602"
echo $TEST
$TEST
sleep 2
# Run through gamut again with start and end
for prog in "--txmsg" "--txmsg_redir" "--txmsg_drop"; do
for t in "sendmsg" "sendpage"; do
for r in 1 10 100; do
for i in 1 10 100; do
for l in 1 10 100; do
TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog --txmsg_start 1 --txmsg_end 2"
echo $TEST
$TEST
sleep 2
done
done
done
done
done
# Some specific tests to cover specific code paths
./sockmap --cgroup /mnt/cgroup2/ -t sendpage \
-r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 3
./sockmap --cgroup /mnt/cgroup2/ -t sendmsg \
-r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 3
./sockmap --cgroup /mnt/cgroup2/ -t sendpage \
-r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 5
./sockmap --cgroup /mnt/cgroup2/ -t sendmsg \
-r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 5

421
scripts/bpf_helpers_doc.py Executable file
View File

@ -0,0 +1,421 @@
#!/usr/bin/python3
# SPDX-License-Identifier: GPL-2.0-only
#
# Copyright (C) 2018 Netronome Systems, Inc.
# In case user attempts to run with Python 2.
from __future__ import print_function
import argparse
import re
import sys, os
class NoHelperFound(BaseException):
pass
class ParsingError(BaseException):
def __init__(self, line='<line not provided>', reader=None):
if reader:
BaseException.__init__(self,
'Error at file offset %d, parsing line: %s' %
(reader.tell(), line))
else:
BaseException.__init__(self, 'Error parsing line: %s' % line)
class Helper(object):
"""
An object representing the description of an eBPF helper function.
@proto: function prototype of the helper function
@desc: textual description of the helper function
@ret: description of the return value of the helper function
"""
def __init__(self, proto='', desc='', ret=''):
self.proto = proto
self.desc = desc
self.ret = ret
def proto_break_down(self):
"""
Break down helper function protocol into smaller chunks: return type,
name, distincts arguments.
"""
arg_re = re.compile('^((const )?(struct )?(\w+|...))( (\**)(\w+))?$')
res = {}
proto_re = re.compile('^(.+) (\**)(\w+)\(((([^,]+)(, )?){1,5})\)$')
capture = proto_re.match(self.proto)
res['ret_type'] = capture.group(1)
res['ret_star'] = capture.group(2)
res['name'] = capture.group(3)
res['args'] = []
args = capture.group(4).split(', ')
for a in args:
capture = arg_re.match(a)
res['args'].append({
'type' : capture.group(1),
'star' : capture.group(6),
'name' : capture.group(7)
})
return res
class HeaderParser(object):
"""
An object used to parse a file in order to extract the documentation of a
list of eBPF helper functions. All the helpers that can be retrieved are
stored as Helper object, in the self.helpers() array.
@filename: name of file to parse, usually include/uapi/linux/bpf.h in the
kernel tree
"""
def __init__(self, filename):
self.reader = open(filename, 'r')
self.line = ''
self.helpers = []
def parse_helper(self):
proto = self.parse_proto()
desc = self.parse_desc()
ret = self.parse_ret()
return Helper(proto=proto, desc=desc, ret=ret)
def parse_proto(self):
# Argument can be of shape:
# - "void"
# - "type name"
# - "type *name"
# - Same as above, with "const" and/or "struct" in front of type
# - "..." (undefined number of arguments, for bpf_trace_printk())
# There is at least one term ("void"), and at most five arguments.
p = re.compile('^ \* ((.+) \**\w+\((((const )?(struct )?(\w+|\.\.\.)( \**\w+)?)(, )?){1,5}\))$')
capture = p.match(self.line)
if not capture:
raise NoHelperFound
self.line = self.reader.readline()
return capture.group(1)
def parse_desc(self):
p = re.compile('^ \* \tDescription$')
capture = p.match(self.line)
if not capture:
# Helper can have empty description and we might be parsing another
# attribute: return but do not consume.
return ''
# Description can be several lines, some of them possibly empty, and it
# stops when another subsection title is met.
desc = ''
while True:
self.line = self.reader.readline()
if self.line == ' *\n':
desc += '\n'
else:
p = re.compile('^ \* \t\t(.*)')
capture = p.match(self.line)
if capture:
desc += capture.group(1) + '\n'
else:
break
return desc
def parse_ret(self):
p = re.compile('^ \* \tReturn$')
capture = p.match(self.line)
if not capture:
# Helper can have empty retval and we might be parsing another
# attribute: return but do not consume.
return ''
# Return value description can be several lines, some of them possibly
# empty, and it stops when another subsection title is met.
ret = ''
while True:
self.line = self.reader.readline()
if self.line == ' *\n':
ret += '\n'
else:
p = re.compile('^ \* \t\t(.*)')
capture = p.match(self.line)
if capture:
ret += capture.group(1) + '\n'
else:
break
return ret
def run(self):
# Advance to start of helper function descriptions.
offset = self.reader.read().find('* Start of BPF helper function descriptions:')
if offset == -1:
raise Exception('Could not find start of eBPF helper descriptions list')
self.reader.seek(offset)
self.reader.readline()
self.reader.readline()
self.line = self.reader.readline()
while True:
try:
helper = self.parse_helper()
self.helpers.append(helper)
except NoHelperFound:
break
self.reader.close()
print('Parsed description of %d helper function(s)' % len(self.helpers),
file=sys.stderr)
###############################################################################
class Printer(object):
"""
A generic class for printers. Printers should be created with an array of
Helper objects, and implement a way to print them in the desired fashion.
@helpers: array of Helper objects to print to standard output
"""
def __init__(self, helpers):
self.helpers = helpers
def print_header(self):
pass
def print_footer(self):
pass
def print_one(self, helper):
pass
def print_all(self):
self.print_header()
for helper in self.helpers:
self.print_one(helper)
self.print_footer()
class PrinterRST(Printer):
"""
A printer for dumping collected information about helpers as a ReStructured
Text page compatible with the rst2man program, which can be used to
generate a manual page for the helpers.
@helpers: array of Helper objects to print to standard output
"""
def print_header(self):
header = '''\
.. Copyright (C) All BPF authors and contributors from 2014 to present.
.. See git log include/uapi/linux/bpf.h in kernel tree for details.
..
.. %%%LICENSE_START(VERBATIM)
.. Permission is granted to make and distribute verbatim copies of this
.. manual provided the copyright notice and this permission notice are
.. preserved on all copies.
..
.. Permission is granted to copy and distribute modified versions of this
.. manual under the conditions for verbatim copying, provided that the
.. entire resulting derived work is distributed under the terms of a
.. permission notice identical to this one.
..
.. Since the Linux kernel and libraries are constantly changing, this
.. manual page may be incorrect or out-of-date. The author(s) assume no
.. responsibility for errors or omissions, or for damages resulting from
.. the use of the information contained herein. The author(s) may not
.. have taken the same level of care in the production of this manual,
.. which is licensed free of charge, as they might when working
.. professionally.
..
.. Formatted or processed versions of this manual, if unaccompanied by
.. the source, must acknowledge the copyright and authors of this work.
.. %%%LICENSE_END
..
.. Please do not edit this file. It was generated from the documentation
.. located in file include/uapi/linux/bpf.h of the Linux kernel sources
.. (helpers description), and from scripts/bpf_helpers_doc.py in the same
.. repository (header and footer).
===========
BPF-HELPERS
===========
-------------------------------------------------------------------------------
list of eBPF helper functions
-------------------------------------------------------------------------------
:Manual section: 7
DESCRIPTION
===========
The extended Berkeley Packet Filter (eBPF) subsystem consists in programs
written in a pseudo-assembly language, then attached to one of the several
kernel hooks and run in reaction of specific events. This framework differs
from the older, "classic" BPF (or "cBPF") in several aspects, one of them being
the ability to call special functions (or "helpers") from within a program.
These functions are restricted to a white-list of helpers defined in the
kernel.
These helpers are used by eBPF programs to interact with the system, or with
the context in which they work. For instance, they can be used to print
debugging messages, to get the time since the system was booted, to interact
with eBPF maps, or to manipulate network packets. Since there are several eBPF
program types, and that they do not run in the same context, each program type
can only call a subset of those helpers.
Due to eBPF conventions, a helper can not have more than five arguments.
Internally, eBPF programs call directly into the compiled helper functions
without requiring any foreign-function interface. As a result, calling helpers
introduces no overhead, thus offering excellent performance.
This document is an attempt to list and document the helpers available to eBPF
developers. They are sorted by chronological order (the oldest helpers in the
kernel at the top).
HELPERS
=======
'''
print(header)
def print_footer(self):
footer = '''
EXAMPLES
========
Example usage for most of the eBPF helpers listed in this manual page are
available within the Linux kernel sources, at the following locations:
* *samples/bpf/*
* *tools/testing/selftests/bpf/*
LICENSE
=======
eBPF programs can have an associated license, passed along with the bytecode
instructions to the kernel when the programs are loaded. The format for that
string is identical to the one in use for kernel modules (Dual licenses, such
as "Dual BSD/GPL", may be used). Some helper functions are only accessible to
programs that are compatible with the GNU Privacy License (GPL).
In order to use such helpers, the eBPF program must be loaded with the correct
license string passed (via **attr**) to the **bpf**\ () system call, and this
generally translates into the C source code of the program containing a line
similar to the following:
::
char ____license[] __attribute__((section("license"), used)) = "GPL";
IMPLEMENTATION
==============
This manual page is an effort to document the existing eBPF helper functions.
But as of this writing, the BPF sub-system is under heavy development. New eBPF
program or map types are added, along with new helper functions. Some helpers
are occasionally made available for additional program types. So in spite of
the efforts of the community, this page might not be up-to-date. If you want to
check by yourself what helper functions exist in your kernel, or what types of
programs they can support, here are some files among the kernel tree that you
may be interested in:
* *include/uapi/linux/bpf.h* is the main BPF header. It contains the full list
of all helper functions, as well as many other BPF definitions including most
of the flags, structs or constants used by the helpers.
* *net/core/filter.c* contains the definition of most network-related helper
functions, and the list of program types from which they can be used.
* *kernel/trace/bpf_trace.c* is the equivalent for most tracing program-related
helpers.
* *kernel/bpf/verifier.c* contains the functions used to check that valid types
of eBPF maps are used with a given helper function.
* *kernel/bpf/* directory contains other files in which additional helpers are
defined (for cgroups, sockmaps, etc.).
Compatibility between helper functions and program types can generally be found
in the files where helper functions are defined. Look for the **struct
bpf_func_proto** objects and for functions returning them: these functions
contain a list of helpers that a given program type can call. Note that the
**default:** label of the **switch ... case** used to filter helpers can call
other functions, themselves allowing access to additional helpers. The
requirement for GPL license is also in those **struct bpf_func_proto**.
Compatibility between helper functions and map types can be found in the
**check_map_func_compatibility**\ () function in file *kernel/bpf/verifier.c*.
Helper functions that invalidate the checks on **data** and **data_end**
pointers for network processing are listed in function
**bpf_helper_changes_pkt_data**\ () in file *net/core/filter.c*.
SEE ALSO
========
**bpf**\ (2),
**cgroups**\ (7),
**ip**\ (8),
**perf_event_open**\ (2),
**sendmsg**\ (2),
**socket**\ (7),
**tc-bpf**\ (8)'''
print(footer)
def print_proto(self, helper):
"""
Format function protocol with bold and italics markers. This makes RST
file less readable, but gives nice results in the manual page.
"""
proto = helper.proto_break_down()
print('**%s %s%s(' % (proto['ret_type'],
proto['ret_star'].replace('*', '\\*'),
proto['name']),
end='')
comma = ''
for a in proto['args']:
one_arg = '{}{}'.format(comma, a['type'])
if a['name']:
if a['star']:
one_arg += ' {}**\ '.format(a['star'].replace('*', '\\*'))
else:
one_arg += '** '
one_arg += '*{}*\\ **'.format(a['name'])
comma = ', '
print(one_arg, end='')
print(')**')
def print_one(self, helper):
self.print_proto(helper)
if (helper.desc):
print('\tDescription')
# Do not strip all newline characters: formatted code at the end of
# a section must be followed by a blank line.
for line in re.sub('\n$', '', helper.desc, count=1).split('\n'):
print('{}{}'.format('\t\t' if line else '', line))
if (helper.ret):
print('\tReturn')
for line in helper.ret.rstrip().split('\n'):
print('{}{}'.format('\t\t' if line else '', line))
print('')
###############################################################################
# If script is launched from scripts/ from kernel tree and can access
# ../include/uapi/linux/bpf.h, use it as a default name for the file to parse,
# otherwise the --filename argument will be required from the command line.
script = os.path.abspath(sys.argv[0])
linuxRoot = os.path.dirname(os.path.dirname(script))
bpfh = os.path.join(linuxRoot, 'include/uapi/linux/bpf.h')
argParser = argparse.ArgumentParser(description="""
Parse eBPF header file and generate documentation for eBPF helper functions.
The RST-formatted output produced can be turned into a manual page with the
rst2man utility.
""")
if (os.path.isfile(bpfh)):
argParser.add_argument('--filename', help='path to include/uapi/linux/bpf.h',
default=bpfh)
else:
argParser.add_argument('--filename', help='path to include/uapi/linux/bpf.h')
args = argParser.parse_args()
# Parse file.
headerParser = HeaderParser(args.filename)
headerParser.run()
# Print formatted output to standard output.
printer = PrinterRST(headerParser.helpers)
printer.print_all()

View File

@ -95,7 +95,7 @@ EXAMPLES
**# bpftool prog show**
::
10: xdp name some_prog tag 005a3d2123620c8b
10: xdp name some_prog tag 005a3d2123620c8b gpl
loaded_at Sep 29/20:11 uid 0
xlated 528B jited 370B memlock 4096B map_ids 10
@ -108,6 +108,7 @@ EXAMPLES
"id": 10,
"type": "xdp",
"tag": "005a3d2123620c8b",
"gpl_compatible": true,
"loaded_at": "Sep 29/20:11",
"uid": 0,
"bytes_xlated": 528,

View File

@ -235,6 +235,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
info->tag[0], info->tag[1], info->tag[2], info->tag[3],
info->tag[4], info->tag[5], info->tag[6], info->tag[7]);
jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible);
print_dev_json(info->ifindex, info->netns_dev, info->netns_ino);
if (info->load_time) {
@ -295,6 +297,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
printf("tag ");
fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino);
printf("%s", info->gpl_compatible ? " gpl" : "");
printf("\n");
if (info->load_time) {

File diff suppressed because it is too large Load Diff

View File

@ -6,9 +6,7 @@
#include <linux/types.h>
#define BTF_MAGIC 0xeB9F
#define BTF_MAGIC_SWAP 0x9FeB
#define BTF_VERSION 1
#define BTF_FLAGS_COMPR 0x01
struct btf_header {
__u16 magic;
@ -43,7 +41,7 @@ struct btf_header {
#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET)
struct btf_type {
__u32 name;
__u32 name_off;
/* "info" bits arrangement
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
@ -105,7 +103,7 @@ struct btf_type {
* info in "struct btf_type").
*/
struct btf_enum {
__u32 name;
__u32 name_off;
__s32 val;
};
@ -122,7 +120,7 @@ struct btf_array {
* "struct btf_type").
*/
struct btf_member {
__u32 name;
__u32 name_off;
__u32 type;
__u32 offset; /* offset in bits */
};

View File

@ -281,7 +281,7 @@ int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
for (i = 1; i <= btf->nr_types; i++) {
const struct btf_type *t = btf->types[i];
const char *name = btf_name_by_offset(btf, t->name);
const char *name = btf_name_by_offset(btf, t->name_off);
if (name && !strcmp(type_name, name))
return i;

View File

@ -1961,8 +1961,8 @@ BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
static void bpf_program__set_expected_attach_type(struct bpf_program *prog,
enum bpf_attach_type type)
void bpf_program__set_expected_attach_type(struct bpf_program *prog,
enum bpf_attach_type type)
{
prog->expected_attach_type = type;
}

View File

@ -193,6 +193,8 @@ int bpf_program__set_sched_act(struct bpf_program *prog);
int bpf_program__set_xdp(struct bpf_program *prog);
int bpf_program__set_perf_event(struct bpf_program *prog);
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type);
void bpf_program__set_expected_attach_type(struct bpf_program *prog,
enum bpf_attach_type type);
bool bpf_program__is_socket_filter(struct bpf_program *prog);
bool bpf_program__is_tracepoint(struct bpf_program *prog);

View File

@ -15,3 +15,4 @@ test_libbpf_open
test_sock
test_sock_addr
urandom_read
test_btf

View File

@ -24,7 +24,7 @@ urandom_read: urandom_read.c
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
test_sock test_sock_addr test_btf
test_sock test_btf test_sockmap
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
@ -32,7 +32,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
test_btf_haskv.o test_btf_nokv.o
test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
@ -40,10 +40,11 @@ TEST_PROGS := test_kmod.sh \
test_xdp_redirect.sh \
test_xdp_meta.sh \
test_offload.py \
test_sock_addr.sh
test_sock_addr.sh \
test_tunnel.sh
# Compile but not part of 'make run_tests'
TEST_GEN_PROGS_EXTENDED = test_libbpf_open
TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr
include ../lib.mk
@ -56,6 +57,7 @@ $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
$(OUTPUT)/test_sock: cgroup_helpers.c
$(OUTPUT)/test_sock_addr: cgroup_helpers.c
$(OUTPUT)/test_sockmap: cgroup_helpers.c
.PHONY: force

View File

@ -98,7 +98,9 @@ static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
(void *) BPF_FUNC_bind;
static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
(void *) BPF_FUNC_xdp_adjust_tail;
static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
int size, int flags) =
(void *) BPF_FUNC_skb_get_xfrm_state;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions

View File

@ -1,20 +1,19 @@
/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include "../../tools/testing/selftests/bpf/bpf_helpers.h"
#include "../../tools/testing/selftests/bpf/bpf_endian.h"
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io
#include <stddef.h>
#include <string.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
/* Sockmap sample program connects a client and a backend together
* using cgroups.
@ -337,5 +336,5 @@ int bpf_prog10(struct sk_msg_md *msg)
return SK_DROP;
}
int _version SEC("version") = 1;
char _license[] SEC("license") = "GPL";

View File

@ -0,0 +1,729 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
# End-to-end eBPF tunnel test suite
# The script tests BPF network tunnel implementation.
#
# Topology:
# ---------
# root namespace | at_ns0 namespace
# |
# ----------- | -----------
# | tnl dev | | | tnl dev | (overlay network)
# ----------- | -----------
# metadata-mode | native-mode
# with bpf |
# |
# ---------- | ----------
# | veth1 | --------- | veth0 | (underlay network)
# ---------- peer ----------
#
#
# Device Configuration
# --------------------
# Root namespace with metadata-mode tunnel + BPF
# Device names and addresses:
# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay)
# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay)
#
# Namespace at_ns0 with native tunnel
# Device names and addresses:
# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay)
# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay)
#
#
# End-to-end ping packet flow
# ---------------------------
# Most of the tests start by namespace creation, device configuration,
# then ping the underlay and overlay network. When doing 'ping 10.1.1.100'
# from root namespace, the following operations happen:
# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev.
# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata,
# with remote_ip=172.16.1.200 and others.
# 3) Outer tunnel header is prepended and route the packet to veth1's egress
# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0
# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet
# 6) Forward the packet to the overlay tnl dev
PING_ARG="-c 3 -w 10 -q"
ret=0
GREEN='\033[0;92m'
RED='\033[0;31m'
NC='\033[0m' # No Color
config_device()
{
ip netns add at_ns0
ip link add veth0 type veth peer name veth1
ip link set veth0 netns at_ns0
ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip link set dev veth1 up mtu 1500
ip addr add dev veth1 172.16.1.200/24
}
add_gre_tunnel()
{
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local 172.16.1.100 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# root namespace
ip link add dev $DEV type $TYPE key 2 external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
add_ip6gretap_tunnel()
{
# assign ipv6 address
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
local ::11 remote ::22
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip addr add dev $DEV fc80::200/24
ip link set dev $DEV up
}
add_erspan_tunnel()
{
# at_ns0 namespace
if [ "$1" == "v1" ]; then
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local 172.16.1.100 remote 172.16.1.200 \
erspan_ver 1 erspan 123
else
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local 172.16.1.100 remote 172.16.1.200 \
erspan_ver 2 erspan_dir egress erspan_hwid 3
fi
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# root namespace
ip link add dev $DEV type $TYPE external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
add_ip6erspan_tunnel()
{
# assign ipv6 address
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
if [ "$1" == "v1" ]; then
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local ::11 remote ::22 \
erspan_ver 1 erspan 123
else
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local ::11 remote ::22 \
erspan_ver 2 erspan_dir egress erspan_hwid 7
fi
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip link set dev $DEV up
}
add_vxlan_tunnel()
{
# Set static ARP entry here because iptables set-mark works
# on L3 packet, as a result not applying to ARP packets,
# causing errors at get_tunnel_{key/opt}.
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE \
id 2 dstport 4789 gbp remote 172.16.1.200
ip netns exec at_ns0 \
ip link set dev $DEV_NS address 52:54:00:d9:01:00 up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00
ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF
# root namespace
ip link add dev $DEV type $TYPE external gbp dstport 4789
ip link set dev $DEV address 52:54:00:d9:02:00 up
ip addr add dev $DEV 10.1.1.200/24
arp -s 10.1.1.100 52:54:00:d9:01:00
}
add_ip6vxlan_tunnel()
{
#ip netns exec at_ns0 ip -4 addr del 172.16.1.100 dev veth0
ip netns exec at_ns0 ip -6 addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
#ip -4 addr del 172.16.1.200 dev veth1
ip -6 addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE id 22 dstport 4789 \
local ::11 remote ::22
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external dstport 4789
ip addr add dev $DEV 10.1.1.200/24
ip link set dev $DEV up
}
add_geneve_tunnel()
{
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE \
id 2 dstport 6081 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# root namespace
ip link add dev $DEV type $TYPE dstport 6081 external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
add_ip6geneve_tunnel()
{
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE id 22 \
remote ::22 # geneve has no local option
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip link set dev $DEV up
}
add_ipip_tunnel()
{
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE \
local 172.16.1.100 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# root namespace
ip link add dev $DEV type $TYPE external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
add_ipip6tnl_tunnel()
{
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE \
local ::11 remote ::22
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip link set dev $DEV up
}
test_gre()
{
TYPE=gretap
DEV_NS=gretap00
DEV=gretap11
ret=0
check $TYPE
config_device
add_gre_tunnel
attach_bpf $DEV gre_set_tunnel gre_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6gre()
{
TYPE=ip6gre
DEV_NS=ip6gre00
DEV=ip6gre11
ret=0
check $TYPE
config_device
# reuse the ip6gretap function
add_ip6gretap_tunnel
attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
# underlay
ping6 $PING_ARG ::11
# overlay: ipv4 over ipv6
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
ping $PING_ARG 10.1.1.100
check_err $?
# overlay: ipv6 over ipv6
ip netns exec at_ns0 ping6 $PING_ARG fc80::200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6gretap()
{
TYPE=ip6gretap
DEV_NS=ip6gretap00
DEV=ip6gretap11
ret=0
check $TYPE
config_device
add_ip6gretap_tunnel
attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
# underlay
ping6 $PING_ARG ::11
# overlay: ipv4 over ipv6
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
ping $PING_ARG 10.1.1.100
check_err $?
# overlay: ipv6 over ipv6
ip netns exec at_ns0 ping6 $PING_ARG fc80::200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_erspan()
{
TYPE=erspan
DEV_NS=erspan00
DEV=erspan11
ret=0
check $TYPE
config_device
add_erspan_tunnel $1
attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6erspan()
{
TYPE=ip6erspan
DEV_NS=ip6erspan00
DEV=ip6erspan11
ret=0
check $TYPE
config_device
add_ip6erspan_tunnel $1
attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
ping6 $PING_ARG ::11
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_vxlan()
{
TYPE=vxlan
DEV_NS=vxlan00
DEV=vxlan11
ret=0
check $TYPE
config_device
add_vxlan_tunnel
attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6vxlan()
{
TYPE=vxlan
DEV_NS=ip6vxlan00
DEV=ip6vxlan11
ret=0
check $TYPE
config_device
add_ip6vxlan_tunnel
ip link set dev veth1 mtu 1500
attach_bpf $DEV ip6vxlan_set_tunnel ip6vxlan_get_tunnel
# underlay
ping6 $PING_ARG ::11
# ip4 over ip6
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: ip6$TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
}
test_geneve()
{
TYPE=geneve
DEV_NS=geneve00
DEV=geneve11
ret=0
check $TYPE
config_device
add_geneve_tunnel
attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6geneve()
{
TYPE=geneve
DEV_NS=ip6geneve00
DEV=ip6geneve11
ret=0
check $TYPE
config_device
add_ip6geneve_tunnel
attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: ip6$TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
}
test_ipip()
{
TYPE=ipip
DEV_NS=ipip00
DEV=ipip11
ret=0
check $TYPE
config_device
add_ipip_tunnel
ip link set dev veth1 mtu 1500
attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ipip6()
{
TYPE=ip6tnl
DEV_NS=ipip6tnl00
DEV=ipip6tnl11
ret=0
check $TYPE
config_device
add_ipip6tnl_tunnel
ip link set dev veth1 mtu 1500
attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
# underlay
ping6 $PING_ARG ::11
# ip4 over ip6
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
setup_xfrm_tunnel()
{
auth=0x$(printf '1%.0s' {1..40})
enc=0x$(printf '2%.0s' {1..32})
spi_in_to_out=0x1
spi_out_to_in=0x2
# at_ns0 namespace
# at_ns0 -> root
ip netns exec at_ns0 \
ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
spi $spi_in_to_out reqid 1 mode tunnel \
auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
ip netns exec at_ns0 \
ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \
tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
mode tunnel
# root -> at_ns0
ip netns exec at_ns0 \
ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
spi $spi_out_to_in reqid 2 mode tunnel \
auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
ip netns exec at_ns0 \
ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \
tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
mode tunnel
# address & route
ip netns exec at_ns0 \
ip addr add dev veth0 10.1.1.100/32
ip netns exec at_ns0 \
ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \
src 10.1.1.100
# root namespace
# at_ns0 -> root
ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
spi $spi_in_to_out reqid 1 mode tunnel \
auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \
tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
mode tunnel
# root -> at_ns0
ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
spi $spi_out_to_in reqid 2 mode tunnel \
auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \
tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
mode tunnel
# address & route
ip addr add dev veth1 10.1.1.200/32
ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200
}
test_xfrm_tunnel()
{
config_device
#tcpdump -nei veth1 ip &
output=$(mktemp)
cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
setup_xfrm_tunnel
tc qdisc add dev veth1 clsact
tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
sec xfrm_get_state
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
sleep 1
grep "reqid 1" $output
check_err $?
grep "spi 0x1" $output
check_err $?
grep "remote ip 0xac100164" $output
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: xfrm tunnel"${NC}
return 1
fi
echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
}
attach_bpf()
{
DEV=$1
SET=$2
GET=$3
tc qdisc add dev $DEV clsact
tc filter add dev $DEV egress bpf da obj test_tunnel_kern.o sec $SET
tc filter add dev $DEV ingress bpf da obj test_tunnel_kern.o sec $GET
}
cleanup()
{
ip netns delete at_ns0 2> /dev/null
ip link del veth1 2> /dev/null
ip link del ipip11 2> /dev/null
ip link del ipip6tnl11 2> /dev/null
ip link del gretap11 2> /dev/null
ip link del ip6gre11 2> /dev/null
ip link del ip6gretap11 2> /dev/null
ip link del vxlan11 2> /dev/null
ip link del ip6vxlan11 2> /dev/null
ip link del geneve11 2> /dev/null
ip link del ip6geneve11 2> /dev/null
ip link del erspan11 2> /dev/null
ip link del ip6erspan11 2> /dev/null
}
cleanup_exit()
{
echo "CATCH SIGKILL or SIGINT, cleanup and exit"
cleanup
exit 0
}
check()
{
ip link help $1 2>&1 | grep -q "^Usage:"
if [ $? -ne 0 ];then
echo "SKIP $1: iproute2 not support"
cleanup
return 1
fi
}
enable_debug()
{
echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control
}
check_err()
{
if [ $ret -eq 0 ]; then
ret=$1
fi
}
bpf_tunnel_test()
{
echo "Testing GRE tunnel..."
test_gre
echo "Testing IP6GRE tunnel..."
test_ip6gre
echo "Testing IP6GRETAP tunnel..."
test_ip6gretap
echo "Testing ERSPAN tunnel..."
test_erspan v2
echo "Testing IP6ERSPAN tunnel..."
test_ip6erspan v2
echo "Testing VXLAN tunnel..."
test_vxlan
echo "Testing IP6VXLAN tunnel..."
test_ip6vxlan
echo "Testing GENEVE tunnel..."
test_geneve
echo "Testing IP6GENEVE tunnel..."
test_ip6geneve
echo "Testing IPIP tunnel..."
test_ipip
echo "Testing IPIP6 tunnel..."
test_ipip6
echo "Testing IPSec tunnel..."
test_xfrm_tunnel
}
trap cleanup 0 3 6
trap cleanup_exit 2 9
cleanup
bpf_tunnel_test
exit 0

View File

@ -1,3 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2016 VMware
* Copyright (c) 2016 Facebook
*
@ -5,39 +6,41 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#define KBUILD_MODNAME "foo"
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <uapi/linux/ipv6.h>
#include <uapi/linux/in.h>
#include <uapi/linux/tcp.h>
#include <uapi/linux/filter.h>
#include <uapi/linux/pkt_cls.h>
#include <uapi/linux/erspan.h>
#include <net/ipv6.h>
#include <stddef.h>
#include <string.h>
#include <arpa/inet.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/types.h>
#include <linux/tcp.h>
#include <linux/socket.h>
#include <linux/pkt_cls.h>
#include <linux/erspan.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#define _htonl __builtin_bswap32
#define ERROR(ret) do {\
char fmt[] = "ERROR line:%d ret:%d\n";\
bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \
} while(0)
} while (0)
int _version SEC("version") = 1;
struct geneve_opt {
__be16 opt_class;
u8 type;
u8 length:5;
u8 r3:1;
u8 r2:1;
u8 r1:1;
u8 opt_data[8]; /* hard-coded to 8 byte */
__u8 type;
__u8 length:5;
__u8 r3:1;
__u8 r2:1;
__u8 r1:1;
__u8 opt_data[8]; /* hard-coded to 8 byte */
};
struct vxlan_metadata {
u32 gbp;
__u32 gbp;
};
SEC("gre_set_tunnel")
@ -86,7 +89,7 @@ int _ip6gretap_set_tunnel(struct __sk_buff *skb)
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = _htonl(0x11); /* ::11 */
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
@ -136,7 +139,8 @@ int _erspan_set_tunnel(struct __sk_buff *skb)
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX);
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
@ -147,8 +151,8 @@ int _erspan_set_tunnel(struct __sk_buff *skb)
md.version = 1;
md.u.index = bpf_htonl(123);
#else
u8 direction = 1;
u8 hwid = 7;
__u8 direction = 1;
__u8 hwid = 7;
md.version = 2;
md.u.md2.dir = direction;
@ -171,7 +175,7 @@ int _erspan_get_tunnel(struct __sk_buff *skb)
char fmt[] = "key %d remote ip 0x%x erspan version %d\n";
struct bpf_tunnel_key key;
struct erspan_metadata md;
u32 index;
__u32 index;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
@ -214,7 +218,7 @@ int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = _htonl(0x11);
key.remote_ipv6[3] = bpf_htonl(0x11);
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
@ -229,11 +233,11 @@ int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
__builtin_memset(&md, 0, sizeof(md));
#ifdef ERSPAN_V1
md.u.index = htonl(123);
md.u.index = bpf_htonl(123);
md.version = 1;
#else
u8 direction = 0;
u8 hwid = 17;
__u8 direction = 0;
__u8 hwid = 17;
md.version = 2;
md.u.md2.dir = direction;
@ -256,10 +260,11 @@ int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n";
struct bpf_tunnel_key key;
struct erspan_metadata md;
u32 index;
__u32 index;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
@ -304,7 +309,8 @@ int _vxlan_set_tunnel(struct __sk_buff *skb)
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX);
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
@ -346,6 +352,48 @@ int _vxlan_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
SEC("ip6vxlan_set_tunnel")
int _ip6vxlan_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_id = 22;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("ip6vxlan_get_tunnel")
int _ip6vxlan_get_tunnel(struct __sk_buff *skb)
{
char fmt[] = "key %d remote ip6 ::%x label %x\n";
struct bpf_tunnel_key key;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
return TC_ACT_OK;
}
SEC("geneve_set_tunnel")
int _geneve_set_tunnel(struct __sk_buff *skb)
{
@ -360,15 +408,16 @@ int _geneve_set_tunnel(struct __sk_buff *skb)
key.tunnel_ttl = 64;
__builtin_memset(&gopt, 0x0, sizeof(gopt));
gopt.opt_class = 0x102; /* Open Virtual Networking (OVN) */
gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
gopt.type = 0x08;
gopt.r1 = 0;
gopt.r2 = 0;
gopt.r3 = 0;
gopt.length = 2; /* 4-byte multiple */
*(int *) &gopt.opt_data = 0xdeadbeef;
*(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef);
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX);
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
@ -408,6 +457,71 @@ int _geneve_get_tunnel(struct __sk_buff *skb)
return TC_ACT_OK;
}
SEC("ip6geneve_set_tunnel")
int _ip6geneve_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct geneve_opt gopt;
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_id = 22;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
__builtin_memset(&gopt, 0x0, sizeof(gopt));
gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
gopt.type = 0x08;
gopt.r1 = 0;
gopt.r2 = 0;
gopt.r3 = 0;
gopt.length = 2; /* 4-byte multiple */
*(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef);
ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("ip6geneve_get_tunnel")
int _ip6geneve_get_tunnel(struct __sk_buff *skb)
{
char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n";
struct bpf_tunnel_key key;
struct geneve_opt gopt;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv4, gopt.opt_class);
return TC_ACT_OK;
}
SEC("ipip_set_tunnel")
int _ipip_set_tunnel(struct __sk_buff *skb)
{
@ -431,9 +545,9 @@ int _ipip_set_tunnel(struct __sk_buff *skb)
if (iph->protocol != IPPROTO_TCP || iph->ihl != 5)
return TC_ACT_SHOT;
if (tcp->dest == htons(5200))
if (tcp->dest == bpf_htons(5200))
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
else if (tcp->dest == htons(5201))
else if (tcp->dest == bpf_htons(5201))
key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */
else
return TC_ACT_SHOT;
@ -481,28 +595,12 @@ int _ipip6_set_tunnel(struct __sk_buff *skb)
return TC_ACT_SHOT;
}
key.remote_ipv6[0] = _htonl(0x2401db00);
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_ttl = 64;
if (iph->protocol == IPPROTO_ICMP) {
key.remote_ipv6[3] = _htonl(1);
} else {
if (iph->protocol != IPPROTO_TCP || iph->ihl != 5) {
ERROR(iph->protocol);
return TC_ACT_SHOT;
}
if (tcp->dest == htons(5200)) {
key.remote_ipv6[3] = _htonl(1);
} else if (tcp->dest == htons(5201)) {
key.remote_ipv6[3] = _htonl(2);
} else {
ERROR(tcp->dest);
return TC_ACT_SHOT;
}
}
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
@ -518,14 +616,15 @@ int _ipip6_get_tunnel(struct __sk_buff *skb)
struct bpf_tunnel_key key;
char fmt[] = "remote ip6 %x::%x\n";
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt), _htonl(key.remote_ipv6[0]),
_htonl(key.remote_ipv6[3]));
bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
bpf_htonl(key.remote_ipv6[3]));
return TC_ACT_OK;
}
@ -545,28 +644,29 @@ int _ip6ip6_set_tunnel(struct __sk_buff *skb)
return TC_ACT_SHOT;
}
key.remote_ipv6[0] = _htonl(0x2401db00);
key.remote_ipv6[0] = bpf_htonl(0x2401db00);
key.tunnel_ttl = 64;
if (iph->nexthdr == NEXTHDR_ICMP) {
key.remote_ipv6[3] = _htonl(1);
if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) {
key.remote_ipv6[3] = bpf_htonl(1);
} else {
if (iph->nexthdr != NEXTHDR_TCP) {
if (iph->nexthdr != 6 /* NEXTHDR_TCP */) {
ERROR(iph->nexthdr);
return TC_ACT_SHOT;
}
if (tcp->dest == htons(5200)) {
key.remote_ipv6[3] = _htonl(1);
} else if (tcp->dest == htons(5201)) {
key.remote_ipv6[3] = _htonl(2);
if (tcp->dest == bpf_htons(5200)) {
key.remote_ipv6[3] = bpf_htonl(1);
} else if (tcp->dest == bpf_htons(5201)) {
key.remote_ipv6[3] = bpf_htonl(2);
} else {
ERROR(tcp->dest);
return TC_ACT_SHOT;
}
}
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
@ -582,14 +682,31 @@ int _ip6ip6_get_tunnel(struct __sk_buff *skb)
struct bpf_tunnel_key key;
char fmt[] = "remote ip6 %x::%x\n";
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt), _htonl(key.remote_ipv6[0]),
_htonl(key.remote_ipv6[3]));
bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
bpf_htonl(key.remote_ipv6[3]));
return TC_ACT_OK;
}
SEC("xfrm_get_state")
int _xfrm_get_state(struct __sk_buff *skb)
{
struct bpf_xfrm_state x;
char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n";
int ret;
ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0);
if (ret < 0)
return TC_ACT_OK;
bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi),
bpf_ntohl(x.remote_ipv4));
return TC_ACT_OK;
}

View File

@ -64,6 +64,7 @@ struct bpf_test {
struct bpf_insn insns[MAX_INSNS];
int fixup_map1[MAX_FIXUPS];
int fixup_map2[MAX_FIXUPS];
int fixup_map3[MAX_FIXUPS];
int fixup_prog[MAX_FIXUPS];
int fixup_map_in_map[MAX_FIXUPS];
const char *errstr;
@ -88,6 +89,11 @@ struct test_val {
int foo[MAX_ENTRIES];
};
struct other_val {
long long foo;
long long bar;
};
static struct bpf_test tests[] = {
{
"add+sub+mul",
@ -5593,6 +5599,257 @@ static struct bpf_test tests[] = {
.errstr = "R1 min value is negative",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map lookup helper access to map",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 8 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map update helper access to map",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 10 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map update helper access to map: wrong size",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
BPF_EXIT_INSN(),
},
.fixup_map1 = { 3 },
.fixup_map3 = { 10 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=8 off=0 size=16",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map helper access to adjusted map (via const imm)",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2,
offsetof(struct other_val, bar)),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 9 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map helper access to adjusted map (via const imm): out-of-bound 1",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2,
sizeof(struct other_val) - 4),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 9 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=16 off=12 size=8",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map helper access to adjusted map (via const imm): out-of-bound 2",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 9 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=16 off=-4 size=8",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map helper access to adjusted map (via const reg)",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_MOV64_IMM(BPF_REG_3,
offsetof(struct other_val, bar)),
BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 10 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map helper access to adjusted map (via const reg): out-of-bound 1",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_MOV64_IMM(BPF_REG_3,
sizeof(struct other_val) - 4),
BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 10 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=16 off=12 size=8",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map helper access to adjusted map (via const reg): out-of-bound 2",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_MOV64_IMM(BPF_REG_3, -4),
BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 10 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=16 off=-4 size=8",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map helper access to adjusted map (via variable)",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
offsetof(struct other_val, bar), 4),
BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 11 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map helper access to adjusted map (via variable): no max check",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 10 },
.result = REJECT,
.errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map helper access to adjusted map (via variable): wrong max check",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
offsetof(struct other_val, bar) + 1, 4),
BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
BPF_LD_MAP_FD(BPF_REG_1, 0),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
},
.fixup_map3 = { 3, 11 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=16 off=9 size=8",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"map element value is preserved across register spilling",
.insns = {
@ -11533,6 +11790,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
{
int *fixup_map1 = test->fixup_map1;
int *fixup_map2 = test->fixup_map2;
int *fixup_map3 = test->fixup_map3;
int *fixup_prog = test->fixup_prog;
int *fixup_map_in_map = test->fixup_map_in_map;
@ -11556,6 +11814,14 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
} while (*fixup_map2);
}
if (*fixup_map3) {
map_fds[1] = create_map(sizeof(struct other_val), 1);
do {
prog[*fixup_map3].imm = map_fds[1];
fixup_map3++;
} while (*fixup_map3);
}
if (*fixup_prog) {
map_fds[2] = create_prog_array();
do {