From 9ee0c7b8654346d60c823babe4b3747357a30477 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 12 Dec 2024 19:40:55 -0800 Subject: [PATCH 01/16] 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 02/16] 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 03/16] 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 04/16] 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 05/16] 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=$(dpkg-architecture -qDEB_HOST_ARCH) -- 2.51.0 From 54956567a055345d17438f08c895c68aff3f4cf2 Mon Sep 17 00:00:00 2001 From: Nicolas Schier Date: Thu, 12 Dec 2024 14:05:29 +0100 Subject: [PATCH 06/16] kbuild: deb-pkg: Do not install maint scripts for arch 'um' Stop installing Debian maintainer scripts when building a user-mode-linux Debian package. Debian maintainer scripts are used for e.g. requesting rebuilds of initrd, rebuilding DKMS modules and updating of grub configuration. As all of this is not relevant for UML but also may lead to failures while processing the kernel hooks, do no more install maintainer scripts for the UML package. Suggested-by: Masahiro Yamada Signed-off-by: Nicolas Schier Signed-off-by: Masahiro Yamada --- scripts/package/builddeb | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/scripts/package/builddeb b/scripts/package/builddeb index fb686fd3266f..ad7aba0f268e 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -63,6 +63,12 @@ install_linux_image () { esac cp "$(${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 07/16] 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 08/16] 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 09/16] 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 10/16] 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 11/16] 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 From 6c432b56a16a0727561211a137f37ec47f96f1d0 Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Fri, 27 Dec 2024 15:47:45 +0100 Subject: [PATCH 12/16] verification/dot2k: Fix template directory detection dot2k can be run as installed (e.g. make install) or from the kernel tree. In the former case it looks for templates in a known location; in the latter, the PWD has to be `/tools/verification` to properly import python modules. The current version looks for the template in a wrong directory in this latter case. This patch adjusts the directory where dot2k looks for templates if run from the kernel tree (i.e. not installed). Additionally we fix a few simple pylint warnings in boolean expressions. Cc: Juri Lelli Cc: Thomas Gleixner Cc: John Kacur Link: https://lore.kernel.org/20241227144752.362911-2-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- tools/verification/dot2/dot2k.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/verification/dot2/dot2k.py b/tools/verification/dot2/dot2k.py index 016550fccf1f..f6d02e3406a3 100644 --- a/tools/verification/dot2/dot2k.py +++ b/tools/verification/dot2/dot2k.py @@ -14,14 +14,14 @@ import os class dot2k(Dot2c): monitor_types = { "global" : 1, "per_cpu" : 2, "per_task" : 3 } - monitor_templates_dir = "dot2k/rv_templates/" + monitor_templates_dir = "dot2/dot2k_templates/" monitor_type = "per_cpu" def __init__(self, file_path, MonitorType): super().__init__(file_path) self.monitor_type = self.monitor_types.get(MonitorType) - if self.monitor_type == None: + if self.monitor_type is None: raise Exception("Unknown monitor type: %s" % MonitorType) self.monitor_type = MonitorType @@ -31,7 +31,7 @@ class dot2k(Dot2c): def __fill_rv_templates_dir(self): - if os.path.exists(self.monitor_templates_dir) == True: + if os.path.exists(self.monitor_templates_dir): return if platform.system() != "Linux": @@ -39,11 +39,11 @@ class dot2k(Dot2c): kernel_path = "/lib/modules/%s/build/tools/verification/dot2/dot2k_templates/" % (platform.release()) - if os.path.exists(kernel_path) == True: + if os.path.exists(kernel_path): self.monitor_templates_dir = kernel_path return - if os.path.exists("/usr/share/dot2/dot2k_templates/") == True: + if os.path.exists("/usr/share/dot2/dot2k_templates/"): self.monitor_templates_dir = "/usr/share/dot2/dot2k_templates/" return @@ -98,7 +98,7 @@ class dot2k(Dot2c): def fill_main_c(self): main_c = self.main_c min_type = self.get_minimun_type() - nr_events = self.events.__len__() + nr_events = len(self.events) tracepoint_handlers = self.fill_tracepoint_handlers_skel() tracepoint_attach = self.fill_tracepoint_attach_probe() tracepoint_detach = self.fill_tracepoint_detach_helper() @@ -160,8 +160,8 @@ class dot2k(Dot2c): def __get_main_name(self): path = "%s/%s" % (self.name, "main.c") - if os.path.exists(path) == False: - return "main.c" + if not os.path.exists(path): + return "main.c" return "__main.c" def print_files(self): -- 2.51.0 From ca08e071c59d96cb1db19b20ba70e9db7b9d5791 Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Fri, 27 Dec 2024 15:47:46 +0100 Subject: [PATCH 13/16] verification/dot2k: Unify main.c templates dot2k has 3 templates, one per monitor type, but the only difference among them is the `DECLARE_DA_MON_*` call, keeping 3 almost identical templates requires more work whenever we introduce a change. This patch removes the 3 dot2k templates and replaces them with a generic one, we then adjust the model type from the script. Cc: Juri Lelli Cc: Thomas Gleixner Cc: John Kacur Link: https://lore.kernel.org/20241227144752.362911-3-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- tools/verification/dot2/dot2k.py | 7 +- .../dot2k_templates/{main_global.c => main.c} | 2 +- .../dot2/dot2k_templates/main_per_cpu.c | 91 ------------------- .../dot2/dot2k_templates/main_per_task.c | 91 ------------------- 4 files changed, 7 insertions(+), 184 deletions(-) rename tools/verification/dot2/dot2k_templates/{main_global.c => main.c} (97%) delete mode 100644 tools/verification/dot2/dot2k_templates/main_per_cpu.c delete mode 100644 tools/verification/dot2/dot2k_templates/main_per_task.c diff --git a/tools/verification/dot2/dot2k.py b/tools/verification/dot2/dot2k.py index f6d02e3406a3..15d6f7048f8d 100644 --- a/tools/verification/dot2/dot2k.py +++ b/tools/verification/dot2/dot2k.py @@ -26,7 +26,7 @@ class dot2k(Dot2c): self.monitor_type = MonitorType self.__fill_rv_templates_dir() - self.main_c = self.__open_file(self.monitor_templates_dir + "main_" + MonitorType + ".c") + self.main_c = self.__open_file(self.monitor_templates_dir + "main.c") self.enum_suffix = "_%s" % self.name def __fill_rv_templates_dir(self): @@ -69,6 +69,9 @@ class dot2k(Dot2c): # cut off the last \n return string[:-1] + def fill_monitor_type(self): + return self.monitor_type.upper() + def fill_tracepoint_handlers_skel(self): buff = [] for event in self.events: @@ -97,12 +100,14 @@ class dot2k(Dot2c): def fill_main_c(self): main_c = self.main_c + monitor_type = self.fill_monitor_type() min_type = self.get_minimun_type() nr_events = len(self.events) tracepoint_handlers = self.fill_tracepoint_handlers_skel() tracepoint_attach = self.fill_tracepoint_attach_probe() tracepoint_detach = self.fill_tracepoint_detach_helper() + main_c = main_c.replace("MONITOR_TYPE", monitor_type) main_c = main_c.replace("MIN_TYPE", min_type) main_c = main_c.replace("MODEL_NAME", self.name) main_c = main_c.replace("NR_EVENTS", str(nr_events)) diff --git a/tools/verification/dot2/dot2k_templates/main_global.c b/tools/verification/dot2/dot2k_templates/main.c similarity index 97% rename from tools/verification/dot2/dot2k_templates/main_global.c rename to tools/verification/dot2/dot2k_templates/main.c index a5658bfb9044..2419a6f89cd8 100644 --- a/tools/verification/dot2/dot2k_templates/main_global.c +++ b/tools/verification/dot2/dot2k_templates/main.c @@ -28,7 +28,7 @@ * The rv monitor reference is needed for the monitor declaration. */ static struct rv_monitor rv_MODEL_NAME; -DECLARE_DA_MON_GLOBAL(MODEL_NAME, MIN_TYPE); +DECLARE_DA_MON_MONITOR_TYPE(MODEL_NAME, MIN_TYPE); /* * This is the instrumentation part of the monitor. diff --git a/tools/verification/dot2/dot2k_templates/main_per_cpu.c b/tools/verification/dot2/dot2k_templates/main_per_cpu.c deleted file mode 100644 index 03539a97633f..000000000000 --- a/tools/verification/dot2/dot2k_templates/main_per_cpu.c +++ /dev/null @@ -1,91 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include - -#define MODULE_NAME "MODEL_NAME" - -/* - * XXX: include required tracepoint headers, e.g., - * #include - */ -#include - -/* - * This is the self-generated part of the monitor. Generally, there is no need - * to touch this section. - */ -#include "MODEL_NAME.h" - -/* - * Declare the deterministic automata monitor. - * - * The rv monitor reference is needed for the monitor declaration. - */ -static struct rv_monitor rv_MODEL_NAME; -DECLARE_DA_MON_PER_CPU(MODEL_NAME, MIN_TYPE); - -/* - * This is the instrumentation part of the monitor. - * - * This is the section where manual work is required. Here the kernel events - * are translated into model's event. - * - */ -TRACEPOINT_HANDLERS_SKEL -static int enable_MODEL_NAME(void) -{ - int retval; - - retval = da_monitor_init_MODEL_NAME(); - if (retval) - return retval; - -TRACEPOINT_ATTACH - - return 0; -} - -static void disable_MODEL_NAME(void) -{ - rv_MODEL_NAME.enabled = 0; - -TRACEPOINT_DETACH - - da_monitor_destroy_MODEL_NAME(); -} - -/* - * This is the monitor register section. - */ -static struct rv_monitor rv_MODEL_NAME = { - .name = "MODEL_NAME", - .description = "auto-generated MODEL_NAME", - .enable = enable_MODEL_NAME, - .disable = disable_MODEL_NAME, - .reset = da_monitor_reset_all_MODEL_NAME, - .enabled = 0, -}; - -static int __init register_MODEL_NAME(void) -{ - rv_register_monitor(&rv_MODEL_NAME); - return 0; -} - -static void __exit unregister_MODEL_NAME(void) -{ - rv_unregister_monitor(&rv_MODEL_NAME); -} - -module_init(register_MODEL_NAME); -module_exit(unregister_MODEL_NAME); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("dot2k: auto-generated"); -MODULE_DESCRIPTION("MODEL_NAME"); diff --git a/tools/verification/dot2/dot2k_templates/main_per_task.c b/tools/verification/dot2/dot2k_templates/main_per_task.c deleted file mode 100644 index ffd92af87a86..000000000000 --- a/tools/verification/dot2/dot2k_templates/main_per_task.c +++ /dev/null @@ -1,91 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include - -#define MODULE_NAME "MODEL_NAME" - -/* - * XXX: include required tracepoint headers, e.g., - * #include - */ -#include - -/* - * This is the self-generated part of the monitor. Generally, there is no need - * to touch this section. - */ -#include "MODEL_NAME.h" - -/* - * Declare the deterministic automata monitor. - * - * The rv monitor reference is needed for the monitor declaration. - */ -static struct rv_monitor rv_MODEL_NAME; -DECLARE_DA_MON_PER_TASK(MODEL_NAME, MIN_TYPE); - -/* - * This is the instrumentation part of the monitor. - * - * This is the section where manual work is required. Here the kernel events - * are translated into model's event. - * - */ -TRACEPOINT_HANDLERS_SKEL -static int enable_MODEL_NAME(void) -{ - int retval; - - retval = da_monitor_init_MODEL_NAME(); - if (retval) - return retval; - -TRACEPOINT_ATTACH - - return 0; -} - -static void disable_MODEL_NAME(void) -{ - rv_MODEL_NAME.enabled = 0; - -TRACEPOINT_DETACH - - da_monitor_destroy_MODEL_NAME(); -} - -/* - * This is the monitor register section. - */ -static struct rv_monitor rv_MODEL_NAME = { - .name = "MODEL_NAME", - .description = "auto-generated MODEL_NAME", - .enable = enable_MODEL_NAME, - .disable = disable_MODEL_NAME, - .reset = da_monitor_reset_all_MODEL_NAME, - .enabled = 0, -}; - -static int __init register_MODEL_NAME(void) -{ - rv_register_monitor(&rv_MODEL_NAME); - return 0; -} - -static void __exit unregister_MODEL_NAME(void) -{ - rv_unregister_monitor(&rv_MODEL_NAME); -} - -module_init(register_MODEL_NAME); -module_exit(unregister_MODEL_NAME); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("dot2k: auto-generated"); -MODULE_DESCRIPTION("MODEL_NAME"); -- 2.51.0 From 91f3407e13b89b7391ebc5b6143fd22edd901041 Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Fri, 27 Dec 2024 15:47:47 +0100 Subject: [PATCH 14/16] verification/dot2k: More robust template variables The dot2k templates currently have variables that are automatically filled by the script marked as an uppercase VARIABLE. This requires some care while adding new variables to avoid using valid keywords and get them unexpectedly substituted. This patch switches the variables to the %%VARIABLE%% notation to make the pattern substitution more robust. Cc: Juri Lelli Cc: Thomas Gleixner Cc: John Kacur Link: https://lore.kernel.org/20241227144752.362911-4-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- tools/verification/dot2/dot2k.py | 14 +++--- .../verification/dot2/dot2k_templates/main.c | 50 +++++++++---------- 2 files changed, 32 insertions(+), 32 deletions(-) diff --git a/tools/verification/dot2/dot2k.py b/tools/verification/dot2/dot2k.py index 15d6f7048f8d..c88b3c011706 100644 --- a/tools/verification/dot2/dot2k.py +++ b/tools/verification/dot2/dot2k.py @@ -107,13 +107,13 @@ class dot2k(Dot2c): tracepoint_attach = self.fill_tracepoint_attach_probe() tracepoint_detach = self.fill_tracepoint_detach_helper() - main_c = main_c.replace("MONITOR_TYPE", monitor_type) - main_c = main_c.replace("MIN_TYPE", min_type) - main_c = main_c.replace("MODEL_NAME", self.name) - main_c = main_c.replace("NR_EVENTS", str(nr_events)) - main_c = main_c.replace("TRACEPOINT_HANDLERS_SKEL", tracepoint_handlers) - main_c = main_c.replace("TRACEPOINT_ATTACH", tracepoint_attach) - main_c = main_c.replace("TRACEPOINT_DETACH", tracepoint_detach) + main_c = main_c.replace("%%MONITOR_TYPE%%", monitor_type) + main_c = main_c.replace("%%MIN_TYPE%%", min_type) + main_c = main_c.replace("%%MODEL_NAME%%", self.name) + main_c = main_c.replace("%%NR_EVENTS%%", str(nr_events)) + main_c = main_c.replace("%%TRACEPOINT_HANDLERS_SKEL%%", tracepoint_handlers) + main_c = main_c.replace("%%TRACEPOINT_ATTACH%%", tracepoint_attach) + main_c = main_c.replace("%%TRACEPOINT_DETACH%%", tracepoint_detach) return main_c diff --git a/tools/verification/dot2/dot2k_templates/main.c b/tools/verification/dot2/dot2k_templates/main.c index 2419a6f89cd8..4a05fef7f3c7 100644 --- a/tools/verification/dot2/dot2k_templates/main.c +++ b/tools/verification/dot2/dot2k_templates/main.c @@ -8,7 +8,7 @@ #include #include -#define MODULE_NAME "MODEL_NAME" +#define MODULE_NAME "%%MODEL_NAME%%" /* * XXX: include required tracepoint headers, e.g., @@ -20,15 +20,15 @@ * This is the self-generated part of the monitor. Generally, there is no need * to touch this section. */ -#include "MODEL_NAME.h" +#include "%%MODEL_NAME%%.h" /* * Declare the deterministic automata monitor. * * The rv monitor reference is needed for the monitor declaration. */ -static struct rv_monitor rv_MODEL_NAME; -DECLARE_DA_MON_MONITOR_TYPE(MODEL_NAME, MIN_TYPE); +static struct rv_monitor rv_%%MODEL_NAME%%; +DECLARE_DA_MON_%%MONITOR_TYPE%%(%%MODEL_NAME%%, %%MIN_TYPE%%); /* * This is the instrumentation part of the monitor. @@ -37,55 +37,55 @@ DECLARE_DA_MON_MONITOR_TYPE(MODEL_NAME, MIN_TYPE); * are translated into model's event. * */ -TRACEPOINT_HANDLERS_SKEL -static int enable_MODEL_NAME(void) +%%TRACEPOINT_HANDLERS_SKEL%% +static int enable_%%MODEL_NAME%%(void) { int retval; - retval = da_monitor_init_MODEL_NAME(); + retval = da_monitor_init_%%MODEL_NAME%%(); if (retval) return retval; -TRACEPOINT_ATTACH +%%TRACEPOINT_ATTACH%% return 0; } -static void disable_MODEL_NAME(void) +static void disable_%%MODEL_NAME%%(void) { - rv_MODEL_NAME.enabled = 0; + rv_%%MODEL_NAME%%.enabled = 0; -TRACEPOINT_DETACH +%%TRACEPOINT_DETACH%% - da_monitor_destroy_MODEL_NAME(); + da_monitor_destroy_%%MODEL_NAME%%(); } /* * This is the monitor register section. */ -static struct rv_monitor rv_MODEL_NAME = { - .name = "MODEL_NAME", - .description = "auto-generated MODEL_NAME", - .enable = enable_MODEL_NAME, - .disable = disable_MODEL_NAME, - .reset = da_monitor_reset_all_MODEL_NAME, +static struct rv_monitor rv_%%MODEL_NAME%% = { + .name = "%%MODEL_NAME%%", + .description = "auto-generated %%MODEL_NAME%%", + .enable = enable_%%MODEL_NAME%%, + .disable = disable_%%MODEL_NAME%%, + .reset = da_monitor_reset_all_%%MODEL_NAME%%, .enabled = 0, }; -static int __init register_MODEL_NAME(void) +static int __init register_%%MODEL_NAME%%(void) { - rv_register_monitor(&rv_MODEL_NAME); + rv_register_monitor(&rv_%%MODEL_NAME%%); return 0; } -static void __exit unregister_MODEL_NAME(void) +static void __exit unregister_%%MODEL_NAME%%(void) { - rv_unregister_monitor(&rv_MODEL_NAME); + rv_unregister_monitor(&rv_%%MODEL_NAME%%); } -module_init(register_MODEL_NAME); -module_exit(unregister_MODEL_NAME); +module_init(register_%%MODEL_NAME%%); +module_exit(unregister_%%MODEL_NAME%%); MODULE_LICENSE("GPL"); MODULE_AUTHOR("dot2k: auto-generated"); -MODULE_DESCRIPTION("MODEL_NAME"); +MODULE_DESCRIPTION("%%MODEL_NAME%%"); -- 2.51.0 From 64b3e5f0d45329bc593e13b64dcdcf836da006cd Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Fri, 27 Dec 2024 15:47:48 +0100 Subject: [PATCH 15/16] verification/dot2k: Add support for name and description options The dot2k command includes options to set a model name with -n and a description with -D, however those are not used in practice. This patch allows to specify a custom model name (by default the name of the dot file without extension) and a description which overrides the one in the C file. Cc: Juri Lelli Cc: Thomas Gleixner Cc: John Kacur Link: https://lore.kernel.org/20241227144752.362911-5-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- tools/verification/dot2/automata.py | 4 ++-- tools/verification/dot2/dot2c.py | 4 ++-- tools/verification/dot2/dot2k | 6 +----- tools/verification/dot2/dot2k.py | 8 +++++--- tools/verification/dot2/dot2k_templates/main.c | 4 ++-- 5 files changed, 12 insertions(+), 14 deletions(-) diff --git a/tools/verification/dot2/automata.py b/tools/verification/dot2/automata.py index bdeb98baa8b0..f6921cf3c914 100644 --- a/tools/verification/dot2/automata.py +++ b/tools/verification/dot2/automata.py @@ -19,9 +19,9 @@ class Automata: invalid_state_str = "INVALID_STATE" - def __init__(self, file_path): + def __init__(self, file_path, model_name=None): self.__dot_path = file_path - self.name = self.__get_model_name() + self.name = model_name or self.__get_model_name() self.__dot_lines = self.__open_dot() self.states, self.initial_state, self.final_states = self.__get_state_variables() self.events = self.__get_event_variables() diff --git a/tools/verification/dot2/dot2c.py b/tools/verification/dot2/dot2c.py index 87d8a1e1470c..fa2816ac7b61 100644 --- a/tools/verification/dot2/dot2c.py +++ b/tools/verification/dot2/dot2c.py @@ -22,8 +22,8 @@ class Dot2c(Automata): struct_automaton_def = "automaton" var_automaton_def = "aut" - def __init__(self, file_path): - super().__init__(file_path) + def __init__(self, file_path, model_name=None): + super().__init__(file_path, model_name) self.line_length = 100 def __buff_to_string(self, buff): diff --git a/tools/verification/dot2/dot2k b/tools/verification/dot2/dot2k index d4d7e52d549e..827b62b8d5e1 100644 --- a/tools/verification/dot2/dot2k +++ b/tools/verification/dot2/dot2k @@ -25,16 +25,12 @@ if __name__ == '__main__': print("Opening and parsing the dot file %s" % params.dot_file) try: - monitor=dot2k(params.dot_file, params.monitor_type) + monitor=dot2k(params.dot_file, params.monitor_type, vars(params)) except Exception as e: print('Error: '+ str(e)) print("Sorry : :-(") sys.exit(1) - # easier than using argparse action. - if params.model_name != None: - print(params.model_name) - print("Writing the monitor into the directory %s" % monitor.name) monitor.print_files() print("Almost done, checklist") diff --git a/tools/verification/dot2/dot2k.py b/tools/verification/dot2/dot2k.py index c88b3c011706..d48ad86a035a 100644 --- a/tools/verification/dot2/dot2k.py +++ b/tools/verification/dot2/dot2k.py @@ -17,17 +17,18 @@ class dot2k(Dot2c): monitor_templates_dir = "dot2/dot2k_templates/" monitor_type = "per_cpu" - def __init__(self, file_path, MonitorType): - super().__init__(file_path) + def __init__(self, file_path, MonitorType, extra_params={}): + super().__init__(file_path, extra_params.get("model_name")) self.monitor_type = self.monitor_types.get(MonitorType) if self.monitor_type is None: - raise Exception("Unknown monitor type: %s" % MonitorType) + raise ValueError("Unknown monitor type: %s" % MonitorType) self.monitor_type = MonitorType self.__fill_rv_templates_dir() self.main_c = self.__open_file(self.monitor_templates_dir + "main.c") self.enum_suffix = "_%s" % self.name + self.description = extra_params.get("description", self.name) or "auto-generated" def __fill_rv_templates_dir(self): @@ -114,6 +115,7 @@ class dot2k(Dot2c): main_c = main_c.replace("%%TRACEPOINT_HANDLERS_SKEL%%", tracepoint_handlers) main_c = main_c.replace("%%TRACEPOINT_ATTACH%%", tracepoint_attach) main_c = main_c.replace("%%TRACEPOINT_DETACH%%", tracepoint_detach) + main_c = main_c.replace("%%DESCRIPTION%%", self.description) return main_c diff --git a/tools/verification/dot2/dot2k_templates/main.c b/tools/verification/dot2/dot2k_templates/main.c index 4a05fef7f3c7..704617168578 100644 --- a/tools/verification/dot2/dot2k_templates/main.c +++ b/tools/verification/dot2/dot2k_templates/main.c @@ -65,7 +65,7 @@ static void disable_%%MODEL_NAME%%(void) */ static struct rv_monitor rv_%%MODEL_NAME%% = { .name = "%%MODEL_NAME%%", - .description = "auto-generated %%MODEL_NAME%%", + .description = "%%DESCRIPTION%%", .enable = enable_%%MODEL_NAME%%, .disable = disable_%%MODEL_NAME%%, .reset = da_monitor_reset_all_%%MODEL_NAME%%, @@ -88,4 +88,4 @@ module_exit(unregister_%%MODEL_NAME%%); MODULE_LICENSE("GPL"); MODULE_AUTHOR("dot2k: auto-generated"); -MODULE_DESCRIPTION("%%MODEL_NAME%%"); +MODULE_DESCRIPTION("%%MODEL_NAME%%: %%DESCRIPTION%%"); -- 2.51.0 From bc3d482dcc062963e7dc20565be2a887e5fc9a2d Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Fri, 27 Dec 2024 15:47:49 +0100 Subject: [PATCH 16/16] rv: Simplify manual steps in monitor creation While creating a new monitor in RV, besides generating code from dot2k, there are a few manual steps which can be tedious and error prone, like adding the tracepoints, makefile lines and kconfig. This patch restructures the existing monitors to keep some files in the monitor's folder itself, which can be automatically generated by future versions of dot2k. Monitors have now their own Kconfig and tracepoint snippets. For simplicity, the main tracepoint definition, is moved to the RV directory, it defines only the tracepoint classes and includes the monitor-specific tracepoints, which reside in the monitor directory. Tracepoints and Kconfig no longer need to be copied and adapted from existing ones but only need to be included in the main files. The Makefile remains untouched since there's little advantage in having a separated Makefile for each monitor with a single line and including it in the main RV Makefile. Cc: Juri Lelli Cc: Thomas Gleixner Cc: John Kacur Link: https://lore.kernel.org/20241227144752.362911-6-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/Kconfig | 25 ++----------------- kernel/trace/rv/Makefile | 2 ++ kernel/trace/rv/monitors/wip/Kconfig | 12 +++++++++ kernel/trace/rv/monitors/wip/wip.c | 2 +- kernel/trace/rv/monitors/wip/wip_trace.h | 15 +++++++++++ kernel/trace/rv/monitors/wwnr/Kconfig | 11 ++++++++ kernel/trace/rv/monitors/wwnr/wwnr.c | 2 +- kernel/trace/rv/monitors/wwnr/wwnr_trace.h | 16 ++++++++++++ kernel/trace/rv/rv.c | 2 +- .../events/rv.h => kernel/trace/rv/rv_trace.h | 24 ++++-------------- 10 files changed, 66 insertions(+), 45 deletions(-) create mode 100644 kernel/trace/rv/monitors/wip/Kconfig create mode 100644 kernel/trace/rv/monitors/wip/wip_trace.h create mode 100644 kernel/trace/rv/monitors/wwnr/Kconfig create mode 100644 kernel/trace/rv/monitors/wwnr/wwnr_trace.h rename include/trace/events/rv.h => kernel/trace/rv/rv_trace.h (79%) diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 831779607e84..1cca47531f00 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -25,30 +25,9 @@ menuconfig RV For further information, see: Documentation/trace/rv/runtime-verification.rst -config RV_MON_WIP - depends on RV - depends on PREEMPT_TRACER - select DA_MON_EVENTS_IMPLICIT - bool "wip monitor" - help - Enable wip (wakeup in preemptive) sample monitor that illustrates - the usage of per-cpu monitors, and one limitation of the - preempt_disable/enable events. - - For further information, see: - Documentation/trace/rv/monitor_wip.rst +source "kernel/trace/rv/monitors/wip/Kconfig" -config RV_MON_WWNR - depends on RV - select DA_MON_EVENTS_ID - bool "wwnr monitor" - help - Enable wwnr (wakeup while not running) sample monitor, this is a - sample monitor that illustrates the usage of per-task monitor. - The model is borken on purpose: it serves to test reactors. - - For further information, see: - Documentation/trace/rv/monitor_wwnr.rst +source "kernel/trace/rv/monitors/wwnr/Kconfig" config RV_REACTORS bool "Runtime verification reactors" diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index 963d14875b45..645434146a88 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +ccflags-y += -I $(src) # needed for trace events + obj-$(CONFIG_RV) += rv.o obj-$(CONFIG_RV_MON_WIP) += monitors/wip/wip.o obj-$(CONFIG_RV_MON_WWNR) += monitors/wwnr/wwnr.o diff --git a/kernel/trace/rv/monitors/wip/Kconfig b/kernel/trace/rv/monitors/wip/Kconfig new file mode 100644 index 000000000000..3ef664b5cd90 --- /dev/null +++ b/kernel/trace/rv/monitors/wip/Kconfig @@ -0,0 +1,12 @@ +config RV_MON_WIP + depends on RV + depends on PREEMPT_TRACER + select DA_MON_EVENTS_IMPLICIT + bool "wip monitor" + help + Enable wip (wakeup in preemptive) sample monitor that illustrates + the usage of per-cpu monitors, and one limitation of the + preempt_disable/enable events. + + For further information, see: + Documentation/trace/rv/monitor_wip.rst diff --git a/kernel/trace/rv/monitors/wip/wip.c b/kernel/trace/rv/monitors/wip/wip.c index b2b49a27e886..db7389157c87 100644 --- a/kernel/trace/rv/monitors/wip/wip.c +++ b/kernel/trace/rv/monitors/wip/wip.c @@ -10,7 +10,7 @@ #define MODULE_NAME "wip" -#include +#include #include #include diff --git a/kernel/trace/rv/monitors/wip/wip_trace.h b/kernel/trace/rv/monitors/wip/wip_trace.h new file mode 100644 index 000000000000..aa2162f47a4c --- /dev/null +++ b/kernel/trace/rv/monitors/wip/wip_trace.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_WIP +DEFINE_EVENT(event_da_monitor, event_wip, + TP_PROTO(char *state, char *event, char *next_state, bool final_state), + TP_ARGS(state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor, error_wip, + TP_PROTO(char *state, char *event), + TP_ARGS(state, event)); +#endif /* CONFIG_RV_MON_WIP */ diff --git a/kernel/trace/rv/monitors/wwnr/Kconfig b/kernel/trace/rv/monitors/wwnr/Kconfig new file mode 100644 index 000000000000..ee741aa6d6b8 --- /dev/null +++ b/kernel/trace/rv/monitors/wwnr/Kconfig @@ -0,0 +1,11 @@ +config RV_MON_WWNR + depends on RV + select DA_MON_EVENTS_ID + bool "wwnr monitor" + help + Enable wwnr (wakeup while not running) sample monitor, this is a + sample monitor that illustrates the usage of per-task monitor. + The model is borken on purpose: it serves to test reactors. + + For further information, see: + Documentation/trace/rv/monitor_wwnr.rst diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.c b/kernel/trace/rv/monitors/wwnr/wwnr.c index 0e43dd2db685..3b16994a9984 100644 --- a/kernel/trace/rv/monitors/wwnr/wwnr.c +++ b/kernel/trace/rv/monitors/wwnr/wwnr.c @@ -10,7 +10,7 @@ #define MODULE_NAME "wwnr" -#include +#include #include #include "wwnr.h" diff --git a/kernel/trace/rv/monitors/wwnr/wwnr_trace.h b/kernel/trace/rv/monitors/wwnr/wwnr_trace.h new file mode 100644 index 000000000000..fc97ec7476ad --- /dev/null +++ b/kernel/trace/rv/monitors/wwnr/wwnr_trace.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_WWNR +/* id is the pid of the task */ +DEFINE_EVENT(event_da_monitor_id, event_wwnr, + TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), + TP_ARGS(id, state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor_id, error_wwnr, + TP_PROTO(int id, char *state, char *event), + TP_ARGS(id, state, event)); +#endif /* CONFIG_RV_MON_WWNR */ diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 279c70e1bd74..8657fc8806e7 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -145,7 +145,7 @@ #ifdef CONFIG_DA_MON_EVENTS #define CREATE_TRACE_POINTS -#include +#include #endif #include "rv.h" diff --git a/include/trace/events/rv.h b/kernel/trace/rv/rv_trace.h similarity index 79% rename from include/trace/events/rv.h rename to kernel/trace/rv/rv_trace.h index 56592da9301c..3442dc59490f 100644 --- a/include/trace/events/rv.h +++ b/kernel/trace/rv/rv_trace.h @@ -57,15 +57,8 @@ DECLARE_EVENT_CLASS(error_da_monitor, __entry->state) ); -#ifdef CONFIG_RV_MON_WIP -DEFINE_EVENT(event_da_monitor, event_wip, - TP_PROTO(char *state, char *event, char *next_state, bool final_state), - TP_ARGS(state, event, next_state, final_state)); - -DEFINE_EVENT(error_da_monitor, error_wip, - TP_PROTO(char *state, char *event), - TP_ARGS(state, event)); -#endif /* CONFIG_RV_MON_WIP */ +#include + #endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */ #ifdef CONFIG_DA_MON_EVENTS_ID @@ -123,20 +116,13 @@ DECLARE_EVENT_CLASS(error_da_monitor_id, __entry->state) ); -#ifdef CONFIG_RV_MON_WWNR -/* id is the pid of the task */ -DEFINE_EVENT(event_da_monitor_id, event_wwnr, - TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), - TP_ARGS(id, state, event, next_state, final_state)); - -DEFINE_EVENT(error_da_monitor_id, error_wwnr, - TP_PROTO(int id, char *state, char *event), - TP_ARGS(id, state, event)); -#endif /* CONFIG_RV_MON_WWNR */ +#include #endif /* CONFIG_DA_MON_EVENTS_ID */ #endif /* _TRACE_RV_H */ /* This part ust be outside protection */ #undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE rv_trace #include -- 2.51.0