From patchwork Wed Jan 10 17:57:41 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Martin KaFai Lau X-Patchwork-Id: 13516375 X-Patchwork-Delegate: bpf@iogearbox.net Received: from out-178.mta0.migadu.com (out-178.mta0.migadu.com [91.218.175.178]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1B8AD4D582 for ; Wed, 10 Jan 2024 17:58:15 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="sFZgsaPi" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1704909494; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=b5T3r0NssF4RI3XvtYVL/0+1cTH/zLzAkT+ZxPtR2LU=; b=sFZgsaPiYqYSsaEEKbPG1L8ck1qzdpQhdHfKwDD1vDaJRcM2vUousEy2GtjYBvRyATOdkl OhqYM+uOcwOKiK2kMOL8O08SntXu9g+hfZ1RCrESSqfl5nn8QmXUw97yXnowLes61yWLJd jgOMQeZ6gglYudeDFMnYmuAwglwiD7I= From: Martin KaFai Lau To: bpf@vger.kernel.org Cc: 'Alexei Starovoitov ' , 'Andrii Nakryiko ' , 'Daniel Borkmann ' , netdev@vger.kernel.org, kernel-team@meta.com, Aditi Ghag Subject: [PATCH v2 bpf 1/3] bpf: iter_udp: Retry with a larger batch size without going back to the previous bucket Date: Wed, 10 Jan 2024 09:57:41 -0800 Message-Id: <20240110175743.2220907-2-martin.lau@linux.dev> In-Reply-To: <20240110175743.2220907-1-martin.lau@linux.dev> References: <20240110175743.2220907-1-martin.lau@linux.dev> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Migadu-Flow: FLOW_OUT X-Patchwork-Delegate: bpf@iogearbox.net From: Martin KaFai Lau The current logic is to use a default size 16 to batch the whole bucket. If it is too small, it will retry with a larger batch size. The current code accidentally does a state->bucket-- before retrying. This goes back to retry with the previous bucket which has already been done. This patch fixed it. It is hard to create a selftest. I added a WARN_ON(state->bucket < 0), forced a particular port to be hashed to the first bucket, created >16 sockets, and observed the for-loop went back to the "-1" bucket. Cc: Aditi Ghag Fixes: c96dac8d369f ("bpf: udp: Implement batching for sockets iterator") Signed-off-by: Martin KaFai Lau Acked-by: Yonghong Song --- net/ipv4/udp.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 89e5a806b82e..978b83d3c094 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -3213,7 +3213,6 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq) /* After allocating a larger batch, retry one more time to grab * the whole bucket. */ - state->bucket--; goto again; } done: From patchwork Wed Jan 10 17:57:42 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Martin KaFai Lau X-Patchwork-Id: 13516376 X-Patchwork-Delegate: bpf@iogearbox.net Received: from out-182.mta0.migadu.com (out-182.mta0.migadu.com [91.218.175.182]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id DB81C4D58B for ; Wed, 10 Jan 2024 17:58:18 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="UOuj70b/" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1704909496; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=geOk+k4lSB856WtrsBiOm/y0L8/K5oIjOClzz5xkay4=; b=UOuj70b/CcNeWQtJ0hBlczcjTvO+kUFAzeExtLLyj8tKDY/ON/4BwCHbs7du5iXNRRACG6 DT8rvtkblBjR56bswopW/RGgtGEYD6V2xUUmHN4GQ6cPwyHQ827YWjcnBvZXdd67wf3ORC QdmyW1+hmJufLLrYFeghG9deiXXSYb8= From: Martin KaFai Lau To: bpf@vger.kernel.org Cc: 'Alexei Starovoitov ' , 'Andrii Nakryiko ' , 'Daniel Borkmann ' , netdev@vger.kernel.org, kernel-team@meta.com, Aditi Ghag Subject: [PATCH v2 bpf 2/3] bpf: Avoid iter->offset making backward progress in bpf_iter_udp Date: Wed, 10 Jan 2024 09:57:42 -0800 Message-Id: <20240110175743.2220907-3-martin.lau@linux.dev> In-Reply-To: <20240110175743.2220907-1-martin.lau@linux.dev> References: <20240110175743.2220907-1-martin.lau@linux.dev> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Migadu-Flow: FLOW_OUT X-Patchwork-Delegate: bpf@iogearbox.net From: Martin KaFai Lau There is a bug in the bpf_iter_udp_batch() function that stops the userspace from making forward progress. The case that triggers the bug is the userspace passed in a very small read buffer. When the bpf prog does bpf_seq_printf, the userspace read buffer is not enough to capture the whole bucket. When the read buffer is not large enough, the kernel will remember the offset of the bucket in iter->offset such that the next userspace read() can continue from where it left off. The kernel will skip the number (== "iter->offset") of sockets in the next read(). However, the code directly decrements the "--iter->offset". This is incorrect because the next read() may not consume the whole bucket either and then the next-next read() will start from offset 0. The net effect is the userspace will keep reading from the beginning of a bucket and the process will never finish. "iter->offset" must always go forward until the whole bucket is consumed. This patch fixes it by using a local variable "resume_offset" and "resume_bucket". "iter->offset" is always reset to 0 before it may be used. "iter->offset" will be advanced to the "resume_offset" when it continues from the "resume_bucket" (i.e. "state->bucket == resume_bucket"). This brings it closer to the bpf_iter_tcp's offset handling which does not suffer the same bug. Cc: Aditi Ghag Fixes: c96dac8d369f ("bpf: udp: Implement batching for sockets iterator") Signed-off-by: Martin KaFai Lau Acked-by: Yonghong Song --- net/ipv4/udp.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 978b83d3c094..04c534a9ef89 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -3137,16 +3137,18 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq) struct bpf_udp_iter_state *iter = seq->private; struct udp_iter_state *state = &iter->state; struct net *net = seq_file_net(seq); + int resume_bucket, resume_offset; struct udp_table *udptable; unsigned int batch_sks = 0; bool resized = false; struct sock *sk; + resume_bucket = state->bucket; + resume_offset = iter->offset; + /* The current batch is done, so advance the bucket. */ - if (iter->st_bucket_done) { + if (iter->st_bucket_done) state->bucket++; - iter->offset = 0; - } udptable = udp_get_table_seq(seq, net); @@ -3166,19 +3168,19 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq) for (; state->bucket <= udptable->mask; state->bucket++) { struct udp_hslot *hslot2 = &udptable->hash2[state->bucket]; - if (hlist_empty(&hslot2->head)) { - iter->offset = 0; + if (hlist_empty(&hslot2->head)) continue; - } + iter->offset = 0; spin_lock_bh(&hslot2->lock); udp_portaddr_for_each_entry(sk, &hslot2->head) { if (seq_sk_match(seq, sk)) { /* Resume from the last iterated socket at the * offset in the bucket before iterator was stopped. */ - if (iter->offset) { - --iter->offset; + if (state->bucket == resume_bucket && + iter->offset < resume_offset) { + ++iter->offset; continue; } if (iter->end_sk < iter->max_sk) { @@ -3192,9 +3194,6 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq) if (iter->end_sk) break; - - /* Reset the current bucket's offset before moving to the next bucket. */ - iter->offset = 0; } /* All done: no batch made. */ From patchwork Wed Jan 10 17:57:43 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Martin KaFai Lau X-Patchwork-Id: 13516377 X-Patchwork-Delegate: bpf@iogearbox.net Received: from out-175.mta0.migadu.com (out-175.mta0.migadu.com [91.218.175.175]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id C06DF4D5A2 for ; Wed, 10 Jan 2024 17:58:20 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="abSUvrYR" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1704909499; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=/TqyhV/+ZfZt3bXyHnNZb5GhEzYR5DhpCLEnS5l8nlc=; b=abSUvrYRm+WNqQCi4UqtTMRefoXEku90ngbFt9rERmw5HHJhZ6FR9M6dTg8hfPle8i2Cin +8C9t8CdNYQMSbXJg1+S/m5Qz2z027kvZO48yAT01lv/77dmdJ/75oceRXVmBQyZpXfMYB 0fR3erzqjUVk0jgcIa8Kyn7Lo4bqTDw= From: Martin KaFai Lau To: bpf@vger.kernel.org Cc: 'Alexei Starovoitov ' , 'Andrii Nakryiko ' , 'Daniel Borkmann ' , netdev@vger.kernel.org, kernel-team@meta.com Subject: [PATCH v2 bpf 3/3] selftests/bpf: Test udp and tcp iter batching Date: Wed, 10 Jan 2024 09:57:43 -0800 Message-Id: <20240110175743.2220907-4-martin.lau@linux.dev> In-Reply-To: <20240110175743.2220907-1-martin.lau@linux.dev> References: <20240110175743.2220907-1-martin.lau@linux.dev> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Migadu-Flow: FLOW_OUT X-Patchwork-Delegate: bpf@iogearbox.net From: Martin KaFai Lau The patch adds a test to exercise the bpf_iter_udp batching logic. It specifically tests the case that there are multiple so_reuseport udp_sk in a bucket of the udp_table. The test creates two sets of so_reuseport sockets and each set on a different port. Meaning there will be two buckets in the udp_table. The test does the following: 1. read() 3 out of 4 sockets in the first bucket. 2. close() all sockets in the first bucket. This will ensure the current bucket's offset in the kernel does not affect the read() of the following bucket. 3. read() all 4 sockets in the second bucket. The test also reads one udp_sk at a time from the bpf_iter_udp prog. The true case in "do_test(..., bool onebyone)". This is the buggy case that the previous patch fixed. It also tests the "false" case in "do_test(..., bool onebyone)", meaning the userspace reads the whole bucket. There is no bug in this case but adding this test also while at it. Considering the way to have multiple tcp_sk in the same bucket is similar (by using so_reuseport), this patch also tests the bpf_iter_tcp even though the bpf_iter_tcp batching logic works correctly. Both IP v4 and v6 are exercising the same bpf_iter batching code path, so only v6 is tested. Signed-off-by: Martin KaFai Lau Acked-by: Yonghong Song --- .../bpf/prog_tests/sock_iter_batch.c | 130 ++++++++++++++++++ .../selftests/bpf/progs/bpf_tracing_net.h | 3 + .../selftests/bpf/progs/sock_iter_batch.c | 121 ++++++++++++++++ 3 files changed, 254 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c create mode 100644 tools/testing/selftests/bpf/progs/sock_iter_batch.c diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c new file mode 100644 index 000000000000..55b1f3f3d862 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024 Meta + +#include +#include "network_helpers.h" +#include "sock_iter_batch.skel.h" + +#define TEST_NS "sock_iter_batch_netns" + +static const int nr_soreuse = 4; + +static void do_test(int sock_type, bool onebyone) +{ + int err, i, nread, to_read, total_read, iter_fd = -1; + int first_idx, second_idx, indices[nr_soreuse]; + struct bpf_link *link = NULL; + struct sock_iter_batch *skel; + int *fds[2] = {}; + + skel = sock_iter_batch__open(); + if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open")) + return; + + /* Prepare 2 buckets of sockets in the kernel hashtable */ + for (i = 0; i < ARRAY_SIZE(fds); i++) { + fds[i] = start_reuseport_server(AF_INET6, sock_type, "::1", 0, 0, + nr_soreuse); + if (!ASSERT_OK_PTR(fds[i], "start_reuseport_server")) + goto done; + skel->rodata->ports[i] = ntohs(get_socket_local_port(*fds[i])); + } + + err = sock_iter_batch__load(skel); + if (!ASSERT_OK(err, "sock_iter_batch__load")) + goto done; + + link = bpf_program__attach_iter(sock_type == SOCK_STREAM ? + skel->progs.iter_tcp_soreuse : + skel->progs.iter_udp_soreuse, + NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter")) + goto done; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create")) + goto done; + + /* Test reading a bucket (either from fds[0] or fds[1]). + * Only read "nr_soreuse - 1" number of sockets + * from a bucket and leave one socket out from + * that bucket on purpose. + */ + to_read = (nr_soreuse - 1) * sizeof(*indices); + total_read = 0; + first_idx = -1; + do { + nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); + if (nread <= 0 || nread % sizeof(*indices)) + break; + total_read += nread; + + if (first_idx == -1) + first_idx = indices[0]; + for (i = 0; i < nread / sizeof(*indices); i++) + ASSERT_EQ(indices[i], first_idx, "first_idx"); + } while (total_read < to_read); + ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread"); + ASSERT_EQ(total_read, to_read, "total_read"); + + free_fds(fds[first_idx], nr_soreuse); + fds[first_idx] = NULL; + + /* Read the "whole" second bucket */ + to_read = nr_soreuse * sizeof(*indices); + total_read = 0; + second_idx = !first_idx; + do { + nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); + if (nread <= 0 || nread % sizeof(*indices)) + break; + total_read += nread; + + for (i = 0; i < nread / sizeof(*indices); i++) + ASSERT_EQ(indices[i], second_idx, "second_idx"); + } while (total_read <= to_read); + ASSERT_EQ(nread, 0, "nread"); + /* Both so_reuseport ports should be in different buckets, so + * total_read must equal to the expected to_read. + * + * For a very unlikely case, both ports collide at the same bucket, + * the bucket offset (i.e. 3) will be skipped and it cannot + * expect the to_read number of bytes. + */ + if (skel->bss->bucket[0] != skel->bss->bucket[1]) + ASSERT_EQ(total_read, to_read, "total_read"); + +done: + for (i = 0; i < ARRAY_SIZE(fds); i++) + free_fds(fds[i], nr_soreuse); + if (iter_fd != -1) + close(iter_fd); + bpf_link__destroy(link); + sock_iter_batch__destroy(skel); +} + +void test_sock_iter_batch(void) +{ + struct nstoken *nstoken = NULL; + + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); + SYS(done, "ip netns add %s", TEST_NS); + SYS(done, "ip -net %s link set dev lo up", TEST_NS); + + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto done; + + if (test__start_subtest("tcp")) { + do_test(SOCK_STREAM, true); + do_test(SOCK_STREAM, false); + } + if (test__start_subtest("udp")) { + do_test(SOCK_DGRAM, true); + do_test(SOCK_DGRAM, false); + } + close_netns(nstoken); + +done: + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 0b793a102791..8cc2e869b34b 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -71,6 +71,8 @@ #define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr #define inet_dport sk.__sk_common.skc_dport +#define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] + #define ir_loc_addr req.__req_common.skc_rcv_saddr #define ir_num req.__req_common.skc_num #define ir_rmt_addr req.__req_common.skc_daddr @@ -84,6 +86,7 @@ #define sk_rmem_alloc sk_backlog.rmem_alloc #define sk_refcnt __sk_common.skc_refcnt #define sk_state __sk_common.skc_state +#define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_flags __sk_common.skc_flags diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c new file mode 100644 index 000000000000..cc2181f95046 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024 Meta + +#include "vmlinux.h" +#include +#include +#include +#include "bpf_tracing_net.h" +#include "bpf_kfuncs.h" + +/* __always_inline to avoid the unused function warning for jhash() */ +#define ATTR __always_inline +#include "test_jhash.h" + +static u32 jhash2(const u32 *k, u32 length, u32 initval) +{ + u32 a, b, c; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; + + /* Handle most of the key */ + while (length > 3) { + a += k[0]; + b += k[1]; + c += k[2]; + __jhash_mix(a, b, c); + length -= 3; + k += 3; + } + + /* Handle the last 3 u32's */ + switch (length) { + case 3: c += k[2]; + case 2: b += k[1]; + case 1: a += k[0]; + __jhash_final(a, b, c); + break; + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +static bool ipv6_addr_loopback(const struct in6_addr *a) +{ + return (a->s6_addr32[0] | a->s6_addr32[1] | + a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0; +} + +volatile const __u16 ports[2]; +unsigned int bucket[2]; + +SEC("iter/tcp") +int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) +{ + struct sock *sk = (struct sock *)ctx->sk_common; + struct inet_hashinfo *hinfo; + unsigned int hash; + struct net *net; + int idx; + + if (!sk) + return 0; + + sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_family != AF_INET6 || + sk->sk_state != TCP_LISTEN || + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + return 0; + + if (sk->sk_num == ports[0]) + idx = 0; + else if (sk->sk_num == ports[1]) + idx = 1; + else + return 0; + + net = sk->sk_net.net; + hash = jhash2(sk->sk_v6_rcv_saddr.s6_addr32, 4, net->hash_mix); + hash ^= sk->sk_num; + hinfo = net->ipv4.tcp_death_row.hashinfo; + bucket[idx] = hash & hinfo->lhash2_mask; + bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + + return 0; +} + +#define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk) + +SEC("iter/udp") +int iter_udp_soreuse(struct bpf_iter__udp *ctx) +{ + struct sock *sk = (struct sock *)ctx->udp_sk; + struct udp_table *udptable; + int idx; + + if (!sk) + return 0; + + sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_family != AF_INET6 || + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + return 0; + + if (sk->sk_num == ports[0]) + idx = 0; + else if (sk->sk_num == ports[1]) + idx = 1; + else + return 0; + + udptable = sk->sk_net.net->ipv4.udp_table; + bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask; + bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + + return 0; +} + +char _license[] SEC("license") = "GPL";