From d888b7af7c149c115dd6ac772cc11c375da3e17c Mon Sep 17 00:00:00 2001 From: Zijian Zhang Date: Tue, 10 Dec 2024 01:20:39 +0000 Subject: [PATCH 01/16] tcp_bpf: Add sk_rmem_alloc related logic for tcp_bpf ingress redirection When we do sk_psock_verdict_apply->sk_psock_skb_ingress, an sk_msg will be created out of the skb, and the rmem accounting of the sk_msg will be handled by the skb. For skmsgs in __SK_REDIRECT case of tcp_bpf_send_verdict, when redirecting to the ingress of a socket, although we sk_rmem_schedule and add sk_msg to the ingress_msg of sk_redir, we do not update sk_rmem_alloc. As a result, except for the global memory limit, the rmem of sk_redir is nearly unlimited. Thus, add sk_rmem_alloc related logic to limit the recv buffer. Since the function sk_msg_recvmsg and __sk_psock_purge_ingress_msg are used in these two paths. We use "msg->skb" to test whether the sk_msg is skb backed up. If it's not, we shall do the memory accounting explicitly. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Zijian Zhang Signed-off-by: Daniel Borkmann Reviewed-by: John Fastabend Link: https://lore.kernel.org/bpf/20241210012039.1669389-3-zijianzhang@bytedance.com --- include/linux/skmsg.h | 11 ++++++++--- net/core/skmsg.c | 6 +++++- net/ipv4/tcp_bpf.c | 4 +++- 3 files changed, 16 insertions(+), 5 deletions(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index d9b03e0746e7..2cbe0c22a32f 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -317,17 +317,22 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void sk_psock_queue_msg(struct sk_psock *psock, +static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { + bool ret; + spin_lock_bh(&psock->ingress_lock); - if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); - else { + ret = true; + } else { sk_msg_free(psock->sk, msg); kfree(msg); + ret = false; } spin_unlock_bh(&psock->ingress_lock); + return ret; } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index e90fbab703b2..8ad7e6755fd6 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -445,8 +445,10 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - if (!msg_rx->skb) + if (!msg_rx->skb) { sk_mem_uncharge(sk, copy); + atomic_sub(copy, &sk->sk_rmem_alloc); + } msg_rx->sg.size -= copy; if (!sge->length) { @@ -772,6 +774,8 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock) list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) { list_del(&msg->list); + if (!msg->skb) + atomic_sub(msg->sg.size, &psock->sk->sk_rmem_alloc); sk_msg_free(psock->sk, msg); kfree(msg); } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index b21ea634909c..392678ae80f4 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -56,6 +56,7 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, } sk_mem_charge(sk, size); + atomic_add(size, &sk->sk_rmem_alloc); sk_msg_xfer(tmp, msg, i, size); copied += size; if (sge->length) @@ -74,7 +75,8 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - sk_psock_queue_msg(psock, tmp); + if (!sk_psock_queue_msg(psock, tmp)) + atomic_sub(copied, &sk->sk_rmem_alloc); sk_psock_data_ready(sk, psock); } else { sk_msg_free(sk, tmp); -- 2.51.0 From 8600058ba28a7b07660ddcd150372d72fb3bc895 Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Fri, 20 Dec 2024 15:06:47 -0600 Subject: [PATCH 02/16] of: Add coreboot firmware to excluded default cells list Google Juniper and other Chromebook platforms have a very old bootloader which populates /firmware node without proper address/size-cells leading to warnings: Missing '#address-cells' in /firmware WARNING: CPU: 0 PID: 1 at drivers/of/base.c:106 of_bus_n_addr_cells+0x90/0xf0 Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.12.0 #1 933ab9971ff4d5dc58cb378a96f64c7f72e3454d Hardware name: Google juniper sku16 board (DT) ... Missing '#size-cells' in /firmware WARNING: CPU: 0 PID: 1 at drivers/of/base.c:133 of_bus_n_size_cells+0x90/0xf0 Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Tainted: G W 6.12.0 #1 933ab9971ff4d5dc58cb378a96f64c7f72e3454d Tainted: [W]=WARN Hardware name: Google juniper sku16 board (DT) These platform won't receive updated bootloader/firmware, so add an exclusion for platforms with a "coreboot" compatible node. While this is wider than necessary, that's the easiest fix and it doesn't doesn't matter if we miss checking other platforms using coreboot. We may revisit this later and address with a fixup to the DT itself. Reported-by: Sasha Levin Closes: https://lore.kernel.org/all/Z0NUdoG17EwuCigT@sashalap/ Cc: AngeloGioacchino Del Regno Cc: Matthias Brugger Cc: Chen-Yu Tsai Cc: Krzysztof Kozlowski Signed-off-by: Rob Herring (Arm) --- drivers/of/base.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/of/base.c b/drivers/of/base.c index 44b1c8bf9cc0..e6ef31c4940f 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -88,7 +88,8 @@ static bool __of_node_is_type(const struct device_node *np, const char *type) } #define EXCLUDED_DEFAULT_CELLS_PLATFORMS ( \ - IS_ENABLED(CONFIG_SPARC) \ + IS_ENABLED(CONFIG_SPARC) || \ + of_find_compatible_node(NULL, NULL, "coreboot") \ ) int of_bus_n_addr_cells(struct device_node *np) -- 2.51.0 From fdf478d236dcf0f1f68534df5d456ced625195bd Mon Sep 17 00:00:00 2001 From: Levi Zim Date: Sat, 30 Nov 2024 21:38:22 +0800 Subject: [PATCH 03/16] skmsg: Return copied bytes in sk_msg_memcopy_from_iter MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Previously sk_msg_memcopy_from_iter returns the copied bytes from the last copy_from_iter{,_nocache} call upon success. This commit changes it to return the total number of copied bytes on success. Signed-off-by: Levi Zim Signed-off-by: Daniel Borkmann Tested-by: Björn Töpel Reviewed-by: John Fastabend Link: https://lore.kernel.org/bpf/20241130-tcp-bpf-sendmsg-v1-1-bae583d014f3@outlook.com --- net/core/skmsg.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 8ad7e6755fd6..61f3f3d4e528 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -369,8 +369,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes) { int ret = -ENOSPC, i = msg->sg.curr; + u32 copy, buf_size, copied = 0; struct scatterlist *sge; - u32 copy, buf_size; void *to; do { @@ -397,6 +397,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, goto out; } bytes -= copy; + copied += copy; if (!bytes) break; msg->sg.copybreak = 0; @@ -404,7 +405,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, } while (i != msg->sg.end); out: msg->sg.curr = i; - return ret; + return (ret < 0) ? ret : copied; } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -- 2.51.0 From 5153a75ef34b3f7478ca918044d0f05eed8fb3f9 Mon Sep 17 00:00:00 2001 From: Levi Zim Date: Sat, 30 Nov 2024 21:38:23 +0800 Subject: [PATCH 04/16] tcp_bpf: Fix copied value in tcp_bpf_sendmsg MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit bpf kselftest sockhash::test_txmsg_cork_hangs in test_sockmap.c triggers a kernel NULL pointer dereference: BUG: kernel NULL pointer dereference, address: 0000000000000008 ? __die_body+0x6e/0xb0 ? __die+0x8b/0xa0 ? page_fault_oops+0x358/0x3c0 ? local_clock+0x19/0x30 ? lock_release+0x11b/0x440 ? kernelmode_fixup_or_oops+0x54/0x60 ? __bad_area_nosemaphore+0x4f/0x210 ? mmap_read_unlock+0x13/0x30 ? bad_area_nosemaphore+0x16/0x20 ? do_user_addr_fault+0x6fd/0x740 ? prb_read_valid+0x1d/0x30 ? exc_page_fault+0x55/0xd0 ? asm_exc_page_fault+0x2b/0x30 ? splice_to_socket+0x52e/0x630 ? shmem_file_splice_read+0x2b1/0x310 direct_splice_actor+0x47/0x70 splice_direct_to_actor+0x133/0x300 ? do_splice_direct+0x90/0x90 do_splice_direct+0x64/0x90 ? __ia32_sys_tee+0x30/0x30 do_sendfile+0x214/0x300 __se_sys_sendfile64+0x8e/0xb0 __x64_sys_sendfile64+0x25/0x30 x64_sys_call+0xb82/0x2840 do_syscall_64+0x75/0x110 entry_SYSCALL_64_after_hwframe+0x4b/0x53 This is caused by tcp_bpf_sendmsg() returning a larger value(12289) than size (8192), which causes the while loop in splice_to_socket() to release an uninitialized pipe buf. The underlying cause is that this code assumes sk_msg_memcopy_from_iter() will copy all bytes upon success but it actually might only copy part of it. This commit changes it to use the real copied bytes. Signed-off-by: Levi Zim Signed-off-by: Daniel Borkmann Tested-by: Björn Töpel Reviewed-by: John Fastabend Link: https://lore.kernel.org/bpf/20241130-tcp-bpf-sendmsg-v1-2-bae583d014f3@outlook.com --- net/ipv4/tcp_bpf.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 392678ae80f4..47f65b1b70ca 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -495,7 +495,7 @@ more_data: static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_msg tmp, *msg_tx = NULL; - int copied = 0, err = 0; + int copied = 0, err = 0, ret = 0; struct sk_psock *psock; long timeo; int flags; @@ -538,14 +538,14 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) copy = msg_tx->sg.size - osize; } - err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, + ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, copy); - if (err < 0) { + if (ret < 0) { sk_msg_trim(sk, msg_tx, osize); goto out_err; } - copied += copy; + copied += ret; if (psock->cork_bytes) { if (size > psock->cork_bytes) psock->cork_bytes = 0; -- 2.51.0 From 9ecc4d858b92c1bb0673ad9c327298e600c55659 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 12 Dec 2024 19:40:54 -0800 Subject: [PATCH 05/16] bpf: Check negative offsets in __bpf_skb_min_len() skb_network_offset() and skb_transport_offset() can be negative when they are called after we pull the transport header, for example, when we use eBPF sockmap at the point of ->sk_data_ready(). __bpf_skb_min_len() uses an unsigned int to get these offsets, this leads to a very large number which then causes bpf_skb_change_tail() failed unexpectedly. Fix this by using a signed int to get these offsets and ensure the minimum is at least zero. Fixes: 5293efe62df8 ("bpf: add bpf_skb_change_tail helper") Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20241213034057.246437-2-xiyou.wangcong@gmail.com --- net/core/filter.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 21131ec25f24..834614071727 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3734,13 +3734,22 @@ static const struct bpf_func_proto bpf_skb_adjust_room_proto = { static u32 __bpf_skb_min_len(const struct sk_buff *skb) { - u32 min_len = skb_network_offset(skb); + int offset = skb_network_offset(skb); + u32 min_len = 0; - if (skb_transport_header_was_set(skb)) - min_len = skb_transport_offset(skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) - min_len = skb_checksum_start_offset(skb) + - skb->csum_offset + sizeof(__sum16); + if (offset > 0) + min_len = offset; + if (skb_transport_header_was_set(skb)) { + offset = skb_transport_offset(skb); + if (offset > 0) + min_len = offset; + } + if (skb->ip_summed == CHECKSUM_PARTIAL) { + offset = skb_checksum_start_offset(skb) + + skb->csum_offset + sizeof(__sum16); + if (offset > 0) + min_len = offset; + } return min_len; } -- 2.51.0 From 9ee0c7b8654346d60c823babe4b3747357a30477 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 12 Dec 2024 19:40:55 -0800 Subject: [PATCH 06/16] selftests/bpf: Add a BPF selftest for bpf_skb_change_tail() As requested by Daniel, we need to add a selftest to cover bpf_skb_change_tail() cases in skb_verdict. Here we test trimming, growing and error cases, and validate its expected return values and the expected sizes of the payload. Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20241213034057.246437-3-xiyou.wangcong@gmail.com --- .../selftests/bpf/prog_tests/sockmap_basic.c | 51 +++++++++++++++++++ .../bpf/progs/test_sockmap_change_tail.c | 40 +++++++++++++++ 2 files changed, 91 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 248754296d97..884ad87783d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -12,6 +12,7 @@ #include "test_sockmap_progs_query.skel.h" #include "test_sockmap_pass_prog.skel.h" #include "test_sockmap_drop_prog.skel.h" +#include "test_sockmap_change_tail.skel.h" #include "bpf_iter_sockmap.skel.h" #include "sockmap_helpers.h" @@ -643,6 +644,54 @@ out: test_sockmap_drop_prog__destroy(drop); } +static void test_sockmap_skb_verdict_change_tail(void) +{ + struct test_sockmap_change_tail *skel; + int err, map, verdict; + int c1, p1, sent, recvd; + int zero = 0; + char buf[2]; + + skel = test_sockmap_change_tail__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1); + if (!ASSERT_OK(err, "create_pair()")) + goto out; + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + sent = xsend(p1, "Tr", 2, 0); + ASSERT_EQ(sent, 2, "xsend(p1)"); + recvd = recv(c1, buf, 2, 0); + ASSERT_EQ(recvd, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + sent = xsend(p1, "G", 1, 0); + ASSERT_EQ(sent, 1, "xsend(p1)"); + recvd = recv(c1, buf, 2, 0); + ASSERT_EQ(recvd, 2, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + sent = xsend(p1, "E", 1, 0); + ASSERT_EQ(sent, 1, "xsend(p1)"); + recvd = recv(c1, buf, 1, 0); + ASSERT_EQ(recvd, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + +out_close: + close(c1); + close(p1); +out: + test_sockmap_change_tail__destroy(skel); +} + static void test_sockmap_skb_verdict_peek_helper(int map) { int err, c1, p1, zero = 0, sent, recvd, avail; @@ -1058,6 +1107,8 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_fionread(true); if (test__start_subtest("sockmap skb_verdict fionread on drop")) test_sockmap_skb_verdict_fionread(false); + if (test__start_subtest("sockmap skb_verdict change tail")) + test_sockmap_skb_verdict_change_tail(); if (test__start_subtest("sockmap skb_verdict msg_f_peek")) test_sockmap_skb_verdict_peek(); if (test__start_subtest("sockmap skb_verdict msg_f_peek with link")) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c new file mode 100644 index 000000000000..2796dd8545eb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 ByteDance */ +#include +#include + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +long change_tail_ret = 1; + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + char *data, *data_end; + + bpf_skb_pull_data(skb, 1); + data = (char *)(unsigned long)skb->data; + data_end = (char *)(unsigned long)skb->data_end; + + if (data + 1 > data_end) + return SK_PASS; + + if (data[0] == 'T') { /* Trim the packet */ + change_tail_ret = bpf_skb_change_tail(skb, skb->len - 1, 0); + return SK_PASS; + } else if (data[0] == 'G') { /* Grow the packet */ + change_tail_ret = bpf_skb_change_tail(skb, skb->len + 1, 0); + return SK_PASS; + } else if (data[0] == 'E') { /* Error */ + change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + return SK_PASS; + } + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; -- 2.51.0 From 472759c9f5377912c7483cca5da847888a27cecc Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 12 Dec 2024 19:40:56 -0800 Subject: [PATCH 07/16] selftests/bpf: Introduce socket_helpers.h for TC tests Pull socket helpers out of sockmap_helpers.h so that they can be reused for TC tests as well. This prepares for the next patch. Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20241213034057.246437-4-xiyou.wangcong@gmail.com --- .../selftests/bpf/prog_tests/socket_helpers.h | 394 ++++++++++++++++++ .../bpf/prog_tests/sockmap_helpers.h | 385 +---------------- 2 files changed, 395 insertions(+), 384 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/socket_helpers.h diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h new file mode 100644 index 000000000000..1bdfb79ef009 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h @@ -0,0 +1,394 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __SOCKET_HELPERS__ +#define __SOCKET_HELPERS__ + +#include + +/* include/linux/net.h */ +#define SOCK_TYPE_MASK 0xf + +#define IO_TIMEOUT_SEC 30 +#define MAX_STRERR_LEN 256 + +/* workaround for older vm_sockets.h */ +#ifndef VMADDR_CID_LOCAL +#define VMADDR_CID_LOCAL 1 +#endif + +/* include/linux/cleanup.h */ +#define __get_and_null(p, nullvalue) \ + ({ \ + __auto_type __ptr = &(p); \ + __auto_type __val = *__ptr; \ + *__ptr = nullvalue; \ + __val; \ + }) + +#define take_fd(fd) __get_and_null(fd, -EBADF) + +/* Wrappers that fail the test on error and report it. */ + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + + +#define xaccept_nonblock(fd, addr, len) \ + ({ \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +static inline void close_fd(int *fd) +{ + if (*fd >= 0) + xclose(*fd); +} + +#define __close_fd __attribute__((cleanup(close_fd))) + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static inline void init_addr_loopback4(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static inline void init_addr_loopback6(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); + + addr->svm_family = AF_VSOCK; + addr->svm_port = VMADDR_PORT_ANY; + addr->svm_cid = VMADDR_CID_LOCAL; + *len = sizeof(*addr); +} + +static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + case AF_VSOCK: + init_addr_loopback_vsock(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static inline int socket_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len = 0; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + if (sotype & SOCK_DGRAM) + return s; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static inline int socket_loopback(int family, int sotype) +{ + return socket_loopback_reuseport(family, sotype, -1); +} + +static inline int poll_connect(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set wfds; + int r, eval; + socklen_t esize = sizeof(eval); + + FD_ZERO(&wfds); + FD_SET(fd, &wfds); + + r = select(fd + 1, NULL, &wfds, NULL, &timeout); + if (r == 0) + errno = ETIME; + if (r != 1) + return -1; + + if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0) + return -1; + if (eval != 0) { + errno = eval; + return -1; + } + + return 0; +} + +static inline int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static inline int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + + +static inline int create_pair(int family, int sotype, int *p0, int *p1) +{ + __close_fd int s, c = -1, p = -1; + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int err; + + s = socket_loopback(family, sotype); + if (s < 0) + return s; + + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + c = xsocket(family, sotype, 0); + if (c < 0) + return c; + + err = connect(c, sockaddr(&addr), len); + if (err) { + if (errno != EINPROGRESS) { + FAIL_ERRNO("connect"); + return err; + } + + err = poll_connect(c, IO_TIMEOUT_SEC); + if (err) { + FAIL_ERRNO("poll_connect"); + return err; + } + } + + switch (sotype & SOCK_TYPE_MASK) { + case SOCK_DGRAM: + err = xgetsockname(c, sockaddr(&addr), &len); + if (err) + return err; + + err = xconnect(s, sockaddr(&addr), len); + if (err) + return err; + + *p0 = take_fd(s); + break; + case SOCK_STREAM: + case SOCK_SEQPACKET: + p = xaccept_nonblock(s, NULL, NULL); + if (p < 0) + return p; + + *p0 = take_fd(p); + break; + default: + FAIL("Unsupported socket type %#x", sotype); + return -EOPNOTSUPP; + } + + *p1 = take_fd(c); + return 0; +} + +static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, + int *p0, int *p1) +{ + int err; + + err = create_pair(family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + + return err; +} + +#endif // __SOCKET_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h index 38e35c72bdaa..3e5571dd578d 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -1,139 +1,12 @@ #ifndef __SOCKMAP_HELPERS__ #define __SOCKMAP_HELPERS__ -#include +#include "socket_helpers.h" -/* include/linux/net.h */ -#define SOCK_TYPE_MASK 0xf - -#define IO_TIMEOUT_SEC 30 -#define MAX_STRERR_LEN 256 #define MAX_TEST_NAME 80 -/* workaround for older vm_sockets.h */ -#ifndef VMADDR_CID_LOCAL -#define VMADDR_CID_LOCAL 1 -#endif - #define __always_unused __attribute__((__unused__)) -/* include/linux/cleanup.h */ -#define __get_and_null(p, nullvalue) \ - ({ \ - __auto_type __ptr = &(p); \ - __auto_type __val = *__ptr; \ - *__ptr = nullvalue; \ - __val; \ - }) - -#define take_fd(fd) __get_and_null(fd, -EBADF) - -#define _FAIL(errnum, fmt...) \ - ({ \ - error_at_line(0, (errnum), __func__, __LINE__, fmt); \ - CHECK_FAIL(true); \ - }) -#define FAIL(fmt...) _FAIL(0, fmt) -#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) -#define FAIL_LIBBPF(err, msg) \ - ({ \ - char __buf[MAX_STRERR_LEN]; \ - libbpf_strerror((err), __buf, sizeof(__buf)); \ - FAIL("%s: %s", (msg), __buf); \ - }) - -/* Wrappers that fail the test on error and report it. */ - -#define xaccept_nonblock(fd, addr, len) \ - ({ \ - int __ret = \ - accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("accept"); \ - __ret; \ - }) - -#define xbind(fd, addr, len) \ - ({ \ - int __ret = bind((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("bind"); \ - __ret; \ - }) - -#define xclose(fd) \ - ({ \ - int __ret = close((fd)); \ - if (__ret == -1) \ - FAIL_ERRNO("close"); \ - __ret; \ - }) - -#define xconnect(fd, addr, len) \ - ({ \ - int __ret = connect((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("connect"); \ - __ret; \ - }) - -#define xgetsockname(fd, addr, len) \ - ({ \ - int __ret = getsockname((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockname"); \ - __ret; \ - }) - -#define xgetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = getsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockopt(" #name ")"); \ - __ret; \ - }) - -#define xlisten(fd, backlog) \ - ({ \ - int __ret = listen((fd), (backlog)); \ - if (__ret == -1) \ - FAIL_ERRNO("listen"); \ - __ret; \ - }) - -#define xsetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = setsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("setsockopt(" #name ")"); \ - __ret; \ - }) - -#define xsend(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = send((fd), (buf), (len), (flags)); \ - if (__ret == -1) \ - FAIL_ERRNO("send"); \ - __ret; \ - }) - -#define xrecv_nonblock(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ - IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("recv"); \ - __ret; \ - }) - -#define xsocket(family, sotype, flags) \ - ({ \ - int __ret = socket(family, sotype, flags); \ - if (__ret == -1) \ - FAIL_ERRNO("socket"); \ - __ret; \ - }) - #define xbpf_map_delete_elem(fd, key) \ ({ \ int __ret = bpf_map_delete_elem((fd), (key)); \ @@ -193,130 +66,6 @@ __ret; \ }) -static inline void close_fd(int *fd) -{ - if (*fd >= 0) - xclose(*fd); -} - -#define __close_fd __attribute__((cleanup(close_fd))) - -static inline int poll_connect(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set wfds; - int r, eval; - socklen_t esize = sizeof(eval); - - FD_ZERO(&wfds); - FD_SET(fd, &wfds); - - r = select(fd + 1, NULL, &wfds, NULL, &timeout); - if (r == 0) - errno = ETIME; - if (r != 1) - return -1; - - if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0) - return -1; - if (eval != 0) { - errno = eval; - return -1; - } - - return 0; -} - -static inline int poll_read(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set rfds; - int r; - - FD_ZERO(&rfds); - FD_SET(fd, &rfds); - - r = select(fd + 1, &rfds, NULL, NULL, &timeout); - if (r == 0) - errno = ETIME; - - return r == 1 ? 0 : -1; -} - -static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return accept(fd, addr, len); -} - -static inline int recv_timeout(int fd, void *buf, size_t len, int flags, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return recv(fd, buf, len, flags); -} - -static inline void init_addr_loopback4(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); - - addr4->sin_family = AF_INET; - addr4->sin_port = 0; - addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - *len = sizeof(*addr4); -} - -static inline void init_addr_loopback6(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); - - addr6->sin6_family = AF_INET6; - addr6->sin6_port = 0; - addr6->sin6_addr = in6addr_loopback; - *len = sizeof(*addr6); -} - -static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); - - addr->svm_family = AF_VSOCK; - addr->svm_port = VMADDR_PORT_ANY; - addr->svm_cid = VMADDR_CID_LOCAL; - *len = sizeof(*addr); -} - -static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, - socklen_t *len) -{ - switch (family) { - case AF_INET: - init_addr_loopback4(ss, len); - return; - case AF_INET6: - init_addr_loopback6(ss, len); - return; - case AF_VSOCK: - init_addr_loopback_vsock(ss, len); - return; - default: - FAIL("unsupported address family %d", family); - } -} - -static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) -{ - return (struct sockaddr *)ss; -} - static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) { u64 value; @@ -334,136 +83,4 @@ static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); } -static inline int enable_reuseport(int s, int progfd) -{ - int err, one = 1; - - err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); - if (err) - return -1; - err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, - sizeof(progfd)); - if (err) - return -1; - - return 0; -} - -static inline int socket_loopback_reuseport(int family, int sotype, int progfd) -{ - struct sockaddr_storage addr; - socklen_t len = 0; - int err, s; - - init_addr_loopback(family, &addr, &len); - - s = xsocket(family, sotype, 0); - if (s == -1) - return -1; - - if (progfd >= 0) - enable_reuseport(s, progfd); - - err = xbind(s, sockaddr(&addr), len); - if (err) - goto close; - - if (sotype & SOCK_DGRAM) - return s; - - err = xlisten(s, SOMAXCONN); - if (err) - goto close; - - return s; -close: - xclose(s); - return -1; -} - -static inline int socket_loopback(int family, int sotype) -{ - return socket_loopback_reuseport(family, sotype, -1); -} - -static inline int create_pair(int family, int sotype, int *p0, int *p1) -{ - __close_fd int s, c = -1, p = -1; - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); - int err; - - s = socket_loopback(family, sotype); - if (s < 0) - return s; - - err = xgetsockname(s, sockaddr(&addr), &len); - if (err) - return err; - - c = xsocket(family, sotype, 0); - if (c < 0) - return c; - - err = connect(c, sockaddr(&addr), len); - if (err) { - if (errno != EINPROGRESS) { - FAIL_ERRNO("connect"); - return err; - } - - err = poll_connect(c, IO_TIMEOUT_SEC); - if (err) { - FAIL_ERRNO("poll_connect"); - return err; - } - } - - switch (sotype & SOCK_TYPE_MASK) { - case SOCK_DGRAM: - err = xgetsockname(c, sockaddr(&addr), &len); - if (err) - return err; - - err = xconnect(s, sockaddr(&addr), len); - if (err) - return err; - - *p0 = take_fd(s); - break; - case SOCK_STREAM: - case SOCK_SEQPACKET: - p = xaccept_nonblock(s, NULL, NULL); - if (p < 0) - return p; - - *p0 = take_fd(p); - break; - default: - FAIL("Unsupported socket type %#x", sotype); - return -EOPNOTSUPP; - } - - *p1 = take_fd(c); - return 0; -} - -static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, - int *p0, int *p1) -{ - int err; - - err = create_pair(family, sotype, c0, p0); - if (err) - return err; - - err = create_pair(family, sotype, c1, p1); - if (err) { - close(*c0); - close(*p0); - } - - return err; -} - #endif // __SOCKMAP_HELPERS__ -- 2.51.0 From 4a58963d10fa3cb654b859e3f9a8aecbcf9f4982 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 12 Dec 2024 19:40:57 -0800 Subject: [PATCH 08/16] selftests/bpf: Test bpf_skb_change_tail() in TC ingress Similarly to the previous test, we also need a test case to cover positive offsets as well, TC is an excellent hook for this. Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Tested-by: Zijian Zhang Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20241213034057.246437-5-xiyou.wangcong@gmail.com --- .../selftests/bpf/prog_tests/tc_change_tail.c | 62 ++++++++++ .../selftests/bpf/progs/test_tc_change_tail.c | 106 ++++++++++++++++++ 2 files changed, 168 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/tc_change_tail.c create mode 100644 tools/testing/selftests/bpf/progs/test_tc_change_tail.c diff --git a/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c new file mode 100644 index 000000000000..74752233e779 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include + +#include "test_tc_change_tail.skel.h" +#include "socket_helpers.h" + +#define LO_IFINDEX 1 + +void test_tc_change_tail(void) +{ + LIBBPF_OPTS(bpf_tcx_opts, tcx_opts); + struct test_tc_change_tail *skel = NULL; + struct bpf_link *link; + int c1, p1; + char buf[2]; + int ret; + + skel = test_tc_change_tail__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tc_change_tail__open_and_load")) + return; + + link = bpf_program__attach_tcx(skel->progs.change_tail, LO_IFINDEX, + &tcx_opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_tcx")) + goto destroy; + + skel->links.change_tail = link; + ret = create_pair(AF_INET, SOCK_DGRAM, &c1, &p1); + if (!ASSERT_OK(ret, "create_pair")) + goto destroy; + + ret = xsend(p1, "Tr", 2, 0); + ASSERT_EQ(ret, 2, "xsend(p1)"); + ret = recv(c1, buf, 2, 0); + ASSERT_EQ(ret, 2, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + ret = xsend(p1, "G", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 2, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + ret = xsend(p1, "E", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 1, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + + ret = xsend(p1, "Z", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 1, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + + close(c1); + close(p1); +destroy: + test_tc_change_tail__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c new file mode 100644 index 000000000000..28edafe803f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include + +long change_tail_ret = 1; + +static __always_inline struct iphdr *parse_ip_header(struct __sk_buff *skb, int *ip_proto) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = data; + struct iphdr *iph; + + /* Verify Ethernet header */ + if ((void *)(data + sizeof(*eth)) > data_end) + return NULL; + + /* Skip Ethernet header to get to IP header */ + iph = (void *)(data + sizeof(struct ethhdr)); + + /* Verify IP header */ + if ((void *)(data + sizeof(struct ethhdr) + sizeof(*iph)) > data_end) + return NULL; + + /* Basic IP header validation */ + if (iph->version != 4) /* Only support IPv4 */ + return NULL; + + if (iph->ihl < 5) /* Minimum IP header length */ + return NULL; + + *ip_proto = iph->protocol; + return iph; +} + +static __always_inline struct udphdr *parse_udp_header(struct __sk_buff *skb, struct iphdr *iph) +{ + void *data_end = (void *)(long)skb->data_end; + void *hdr = (void *)iph; + struct udphdr *udp; + + /* Calculate UDP header position */ + udp = hdr + (iph->ihl * 4); + hdr = (void *)udp; + + /* Verify UDP header bounds */ + if ((void *)(hdr + sizeof(*udp)) > data_end) + return NULL; + + return udp; +} + +SEC("tc/ingress") +int change_tail(struct __sk_buff *skb) +{ + int len = skb->len; + struct udphdr *udp; + struct iphdr *iph; + void *data_end; + char *payload; + int ip_proto; + + bpf_skb_pull_data(skb, len); + + data_end = (void *)(long)skb->data_end; + iph = parse_ip_header(skb, &ip_proto); + if (!iph) + return TCX_PASS; + + if (ip_proto != IPPROTO_UDP) + return TCX_PASS; + + udp = parse_udp_header(skb, iph); + if (!udp) + return TCX_PASS; + + payload = (char *)udp + (sizeof(struct udphdr)); + if (payload + 1 > (char *)data_end) + return TCX_PASS; + + if (payload[0] == 'T') { /* Trim the packet */ + change_tail_ret = bpf_skb_change_tail(skb, len - 1, 0); + if (!change_tail_ret) + bpf_skb_change_tail(skb, len, 0); + return TCX_PASS; + } else if (payload[0] == 'G') { /* Grow the packet */ + change_tail_ret = bpf_skb_change_tail(skb, len + 1, 0); + if (!change_tail_ret) + bpf_skb_change_tail(skb, len, 0); + return TCX_PASS; + } else if (payload[0] == 'E') { /* Error */ + change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + return TCX_PASS; + } else if (payload[0] == 'Z') { /* Zero */ + change_tail_ret = bpf_skb_change_tail(skb, 0, 0); + return TCX_PASS; + } + return TCX_DROP; +} + +char _license[] SEC("license") = "GPL"; -- 2.51.0 From d67393f4d28ef0544eaf382f1123dcaf56495dc9 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 5 Dec 2024 14:20:43 +0100 Subject: [PATCH 09/16] kbuild: Drop support for include/asm- in headers_check.pl "include/asm-" was replaced by "arch//include/asm" a long time ago. All assembler header files are now included using "#include ", so there is no longer a need to rewrite paths. Signed-off-by: Geert Uytterhoeven Signed-off-by: Masahiro Yamada --- usr/include/Makefile | 2 +- usr/include/headers_check.pl | 9 ++------- 2 files changed, 3 insertions(+), 8 deletions(-) diff --git a/usr/include/Makefile b/usr/include/Makefile index 771e32872b2a..6c6de1b1622b 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -78,7 +78,7 @@ quiet_cmd_hdrtest = HDRTEST $< cmd_hdrtest = \ $(CC) $(c_flags) -fsyntax-only -x c /dev/null \ $(if $(filter-out $(no-header-test), $*.h), -include $< -include $<); \ - $(PERL) $(src)/headers_check.pl $(obj) $(SRCARCH) $<; \ + $(PERL) $(src)/headers_check.pl $(obj) $<; \ touch $@ $(obj)/%.hdrtest: $(obj)/%.h FORCE diff --git a/usr/include/headers_check.pl b/usr/include/headers_check.pl index b6aec5e4365f..2b70bfa5558e 100755 --- a/usr/include/headers_check.pl +++ b/usr/include/headers_check.pl @@ -3,9 +3,8 @@ # # headers_check.pl execute a number of trivial consistency checks # -# Usage: headers_check.pl dir arch [files...] +# Usage: headers_check.pl dir [files...] # dir: dir to look for included files -# arch: architecture # files: list of files to check # # The script reads the supplied files line by line and: @@ -23,7 +22,7 @@ use warnings; use strict; use File::Basename; -my ($dir, $arch, @files) = @ARGV; +my ($dir, @files) = @ARGV; my $ret = 0; my $line; @@ -54,10 +53,6 @@ sub check_include my $inc = $1; my $found; $found = stat($dir . "/" . $inc); - if (!$found) { - $inc =~ s#asm/#asm-$arch/#; - $found = stat($dir . "/" . $inc); - } if (!$found) { printf STDERR "$filename:$lineno: included file '$inc' is not exported\n"; $ret = 1; -- 2.51.0 From a34e92d2e831729f0ed5df20d15b4df419cd0ba4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 3 Dec 2024 20:14:45 +0900 Subject: [PATCH 10/16] kbuild: deb-pkg: add debarch for ARCH=um 'make ARCH=um bindeb-pkg' shows the following warning. $ make ARCH=um bindeb-pkg [snip] GEN debian ** ** ** WARNING ** ** ** Your architecture doesn't have its equivalent Debian userspace architecture defined! Falling back to the current host architecture (amd64). Please add support for um to ./scripts/package/mkdebian ... This commit hard-codes i386/amd64 because UML is only supported for x86. Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- scripts/package/mkdebian | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 4ffcc70f8e31..b038a1380b8a 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -70,6 +70,13 @@ set_debarch() { debarch=sh4$(if_enabled_echo CONFIG_CPU_BIG_ENDIAN eb) fi ;; + um) + if is_enabled CONFIG_64BIT; then + debarch=amd64 + else + debarch=i386 + fi + ;; esac if [ -z "$debarch" ]; then debarch=$(dpkg-architecture -qDEB_HOST_ARCH) -- 2.51.0 From 54956567a055345d17438f08c895c68aff3f4cf2 Mon Sep 17 00:00:00 2001 From: Nicolas Schier Date: Thu, 12 Dec 2024 14:05:29 +0100 Subject: [PATCH 11/16] kbuild: deb-pkg: Do not install maint scripts for arch 'um' Stop installing Debian maintainer scripts when building a user-mode-linux Debian package. Debian maintainer scripts are used for e.g. requesting rebuilds of initrd, rebuilding DKMS modules and updating of grub configuration. As all of this is not relevant for UML but also may lead to failures while processing the kernel hooks, do no more install maintainer scripts for the UML package. Suggested-by: Masahiro Yamada Signed-off-by: Nicolas Schier Signed-off-by: Masahiro Yamada --- scripts/package/builddeb | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/scripts/package/builddeb b/scripts/package/builddeb index fb686fd3266f..ad7aba0f268e 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -63,6 +63,12 @@ install_linux_image () { esac cp "$(${MAKE} -s -f ${srctree}/Makefile image_name)" "${pdir}/${installed_image_path}" + if [ "${ARCH}" != um ]; then + install_maint_scripts "${pdir}" + fi +} + +install_maint_scripts () { # Install the maintainer scripts # Note: hook scripts under /etc/kernel are also executed by official Debian # kernel packages, as well as kernel packages built using make-kpkg. -- 2.51.0 From 9435dc77a33fa20afec7cd35ceaae5f7f42dbbe2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 13 Dec 2024 00:46:15 +0900 Subject: [PATCH 12/16] modpost: distinguish same module paths from different dump files Since commit 13b25489b6f8 ("kbuild: change working directory to external module directory with M="), module paths are always relative to the top of the external module tree. The module paths recorded in Module.symvers are no longer globally unique when they are passed via KBUILD_EXTRA_SYMBOLS for building other external modules, which may result in false-positive "exported twice" errors. Such errors should not occur because external modules should be able to override in-tree modules. To address this, record the dump file path in struct module and check it when searching for a module. Fixes: 13b25489b6f8 ("kbuild: change working directory to external module directory with M=") Reported-by: Jon Hunter Closes: https://lore.kernel.org/all/eb21a546-a19c-40df-b821-bbba80f19a3d@nvidia.com/ Signed-off-by: Masahiro Yamada Tested-by: Jon Hunter --- scripts/mod/modpost.c | 17 +++++++++-------- scripts/mod/modpost.h | 3 ++- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index fb787a5715f5..94ee49207a45 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -155,12 +155,13 @@ char *get_line(char **stringp) /* A list of all modules we processed */ LIST_HEAD(modules); -static struct module *find_module(const char *modname) +static struct module *find_module(const char *filename, const char *modname) { struct module *mod; list_for_each_entry(mod, &modules, list) { - if (strcmp(mod->name, modname) == 0) + if (!strcmp(mod->dump_file, filename) && + !strcmp(mod->name, modname)) return mod; } return NULL; @@ -2030,10 +2031,10 @@ static void read_dump(const char *fname) continue; } - mod = find_module(modname); + mod = find_module(fname, modname); if (!mod) { mod = new_module(modname, strlen(modname)); - mod->from_dump = true; + mod->dump_file = fname; } s = sym_add_exported(symname, mod, gpl_only, namespace); sym_set_crc(s, crc); @@ -2052,7 +2053,7 @@ static void write_dump(const char *fname) struct symbol *sym; list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; list_for_each_entry(sym, &mod->exported_symbols, list) { if (trim_unused_exports && !sym->used) @@ -2076,7 +2077,7 @@ static void write_namespace_deps_files(const char *fname) list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || list_empty(&mod->missing_namespaces)) + if (mod->dump_file || list_empty(&mod->missing_namespaces)) continue; buf_printf(&ns_deps_buf, "%s.ko:", mod->name); @@ -2194,7 +2195,7 @@ int main(int argc, char **argv) read_symbols_from_files(files_source); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || mod->is_vmlinux) + if (mod->dump_file || mod->is_vmlinux) continue; check_modname_len(mod); @@ -2205,7 +2206,7 @@ int main(int argc, char **argv) handle_white_list_exports(unused_exports_white_list); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; if (mod->is_vmlinux) diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 49848fcbe2a1..8b72c227ebf4 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -95,14 +95,15 @@ struct module_alias { /** * struct module - represent a module (vmlinux or *.ko) * + * @dump_file: path to the .symvers file if loaded from a file * @aliases: list head for module_aliases */ struct module { struct list_head list; struct list_head exported_symbols; struct list_head unresolved_symbols; + const char *dump_file; bool is_gpl_compatible; - bool from_dump; /* true if module was loaded from *.symvers */ bool is_vmlinux; bool seen; bool has_init; -- 2.51.0 From e84a3bf7f4aa669c05e3884497774148ac111468 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 17 Dec 2024 10:19:04 -0500 Subject: [PATCH 13/16] staging: gpib: Fix allyesconfig build failures My tests run an allyesconfig build and it failed with the following errors: LD [M] samples/kfifo/dma-example.ko ld.lld: error: undefined symbol: nec7210_board_reset ld.lld: error: undefined symbol: nec7210_read ld.lld: error: undefined symbol: nec7210_write It appears that some modules call the function nec7210_board_reset() that is defined in nec7210.c. In an allyesconfig build, these other modules are built in. But the file that holds nec7210_board_reset() has: obj-m += nec7210.o Where that "-m" means it only gets built as a module. With the other modules built in, they have no access to nec7210_board_reset() and the build fails. This isn't the only function. After fixing that one, I hit another: ld.lld: error: undefined symbol: push_gpib_event ld.lld: error: undefined symbol: gpib_match_device_path Where push_gpib_event() was also used outside of the file it was defined in, and that file too only was built as a module. Since the directory that nec7210.c is only traversed when CONFIG_GPIB_NEC7210 is set, and the directory with gpib_common.c is only traversed when CONFIG_GPIB_COMMON is set, use those configs as the option to build those modules. When it is an allyesconfig, then they will both be built in and their functions will be available to the other modules that are also built in. Fixes: 3ba84ac69b53e ("staging: gpib: Add nec7210 GPIB chip driver") Fixes: 9dde4559e9395 ("staging: gpib: Add GPIB common core driver") Signed-off-by: Steven Rostedt (Google) Reviewed-by: Palmer Dabbelt Signed-off-by: Linus Torvalds --- drivers/staging/gpib/common/Makefile | 2 +- drivers/staging/gpib/nec7210/Makefile | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/gpib/common/Makefile b/drivers/staging/gpib/common/Makefile index 0c4c77bea75b..460586edb574 100644 --- a/drivers/staging/gpib/common/Makefile +++ b/drivers/staging/gpib/common/Makefile @@ -1,5 +1,5 @@ -obj-m += gpib_common.o +obj-$(CONFIG_GPIB_COMMON) += gpib_common.o gpib_common-objs := gpib_os.o iblib.o diff --git a/drivers/staging/gpib/nec7210/Makefile b/drivers/staging/gpib/nec7210/Makefile index 8d4d90f21109..64330f2e89d1 100644 --- a/drivers/staging/gpib/nec7210/Makefile +++ b/drivers/staging/gpib/nec7210/Makefile @@ -1,4 +1,4 @@ -obj-m += nec7210.o +obj-$(CONFIG_GPIB_NEC7210) += nec7210.o -- 2.51.0 From 37d1d99b8806b24ffe4a2b453620df932994a5c0 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 17 Dec 2024 08:05:40 +0100 Subject: [PATCH 14/16] KVM: VMX: don't include '' directly The header clearly states that it does not want to be included directly, only via ''. Replace the include accordingly. Signed-off-by: Wolfram Sang Message-ID: <20241217070539.2433-2-wsa+renesas@sang-engineering.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/posted_intr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 1715d2ab07be..ad9116a99bcc 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -2,7 +2,7 @@ #ifndef __KVM_X86_VMX_POSTED_INTR_H #define __KVM_X86_VMX_POSTED_INTR_H -#include +#include #include void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); -- 2.51.0 From 398b7b6cb9e046f137a188670da12f790492b56b Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 19 Dec 2024 07:43:20 -0500 Subject: [PATCH 15/16] KVM: x86: let it be known that ignore_msrs is a bad idea When running KVM with ignore_msrs=1 and report_ignored_msrs=0, the user has no clue that that the guest is being lied to. This may cause bug reports such as https://gitlab.com/qemu-project/qemu/-/issues/2571, where enabling a CPUID bit in QEMU caused Linux guests to try reading MSR_CU_DEF_ERR; and being lied about the existence of MSR_CU_DEF_ERR caused the guest to assume other things about the local APIC which were not true: Sep 14 12:02:53 kernel: mce: [Firmware Bug]: Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly. Sep 14 12:02:53 kernel: unchecked MSR access error: RDMSR from 0x852 at rIP: 0xffffffffb548ffa7 (native_read_msr+0x7/0x40) Sep 14 12:02:53 kernel: Call Trace: ... Sep 14 12:02:53 kernel: native_apic_msr_read+0x20/0x30 Sep 14 12:02:53 kernel: setup_APIC_eilvt+0x47/0x110 Sep 14 12:02:53 kernel: mce_amd_feature_init+0x485/0x4e0 ... Sep 14 12:02:53 kernel: [Firmware Bug]: cpu 0, try to use APIC520 (LVT offset 2) for vector 0xf4, but the register is already in use for vector 0x0 on this cpu Without reported_ignored_msrs=0 at least the host kernel log will contain enough information to avoid going on a wild goose chase. But if reports about individual MSR accesses are being silenced too, at least complain loudly the first time a VM is started. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8160baf3838..12fa68a06966 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12724,6 +12724,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); + if (ignore_msrs && !report_ignored_msrs) { + pr_warn_once("Running KVM with ignore_msrs=1 and report_ignored_msrs=0 is not a\n" + "a supported configuration. Lying to the guest about the existence of MSRs\n" + "may cause the guest operating system to hang or produce errors. If a guest\n" + "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); + } + return 0; out_uninit_mmu: -- 2.51.0 From 4bbf9020becbfd8fc2c3da790855b7042fad455b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 22 Dec 2024 13:22:21 -0800 Subject: [PATCH 16/16] Linux 6.13-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e5b8a8832c0c..5c9b1d2d59b4 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* -- 2.51.0