From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- samples/seccomp/user-trap.c | 379 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 379 insertions(+) create mode 100644 samples/seccomp/user-trap.c (limited to 'samples/seccomp/user-trap.c') diff --git a/samples/seccomp/user-trap.c b/samples/seccomp/user-trap.c new file mode 100644 index 000000000..a23fec357 --- /dev/null +++ b/samples/seccomp/user-trap.c @@ -0,0 +1,379 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) + +static int seccomp(unsigned int op, unsigned int flags, void *args) +{ + errno = 0; + return syscall(__NR_seccomp, op, flags, args); +} + +static int send_fd(int sock, int fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int *fd_ptr; + char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c'; + struct iovec io = { + .iov_base = &c, + .iov_len = 1, + }; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = buf; + msg.msg_controllen = sizeof(buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(int)); + fd_ptr = (int *)CMSG_DATA(cmsg); + *fd_ptr = fd; + msg.msg_controllen = cmsg->cmsg_len; + + if (sendmsg(sock, &msg, 0) < 0) { + perror("sendmsg"); + return -1; + } + + return 0; +} + +static int recv_fd(int sock) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int *fd_ptr; + char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c'; + struct iovec io = { + .iov_base = &c, + .iov_len = 1, + }; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = buf; + msg.msg_controllen = sizeof(buf); + + if (recvmsg(sock, &msg, 0) < 0) { + perror("recvmsg"); + return -1; + } + + cmsg = CMSG_FIRSTHDR(&msg); + fd_ptr = (int *)CMSG_DATA(cmsg); + + return *fd_ptr; +} + +static int user_trap_syscall(int nr, unsigned int flags) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD+BPF_W+BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_USER_NOTIF), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + }; + + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog); +} + +static int handle_req(struct seccomp_notif *req, + struct seccomp_notif_resp *resp, int listener) +{ + char path[PATH_MAX], source[PATH_MAX], target[PATH_MAX]; + int ret = -1, mem; + + resp->id = req->id; + resp->error = -EPERM; + resp->val = 0; + + if (req->data.nr != __NR_mount) { + fprintf(stderr, "huh? trapped something besides mount? %d\n", req->data.nr); + return -1; + } + + /* Only allow bind mounts. */ + if (!(req->data.args[3] & MS_BIND)) + return 0; + + /* + * Ok, let's read the task's memory to see where they wanted their + * mount to go. + */ + snprintf(path, sizeof(path), "/proc/%d/mem", req->pid); + mem = open(path, O_RDONLY); + if (mem < 0) { + perror("open mem"); + return -1; + } + + /* + * Now we avoid a TOCTOU: we referred to a pid by its pid, but since + * the pid that made the syscall may have died, we need to confirm that + * the pid is still valid after we open its /proc/pid/mem file. We can + * ask the listener fd this as follows. + * + * Note that this check should occur *after* any task-specific + * resources are opened, to make sure that the task has not died and + * we're not wrongly reading someone else's state in order to make + * decisions. + */ + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_ID_VALID, &req->id) < 0) { + fprintf(stderr, "task died before we could map its memory\n"); + goto out; + } + + /* + * Phew, we've got the right /proc/pid/mem. Now we can read it. Note + * that to avoid another TOCTOU, we should read all of the pointer args + * before we decide to allow the syscall. + */ + if (lseek(mem, req->data.args[0], SEEK_SET) < 0) { + perror("seek"); + goto out; + } + + ret = read(mem, source, sizeof(source)); + if (ret < 0) { + perror("read"); + goto out; + } + + if (lseek(mem, req->data.args[1], SEEK_SET) < 0) { + perror("seek"); + goto out; + } + + ret = read(mem, target, sizeof(target)); + if (ret < 0) { + perror("read"); + goto out; + } + + /* + * Our policy is to only allow bind mounts inside /tmp. This isn't very + * interesting, because we could do unprivlieged bind mounts with user + * namespaces already, but you get the idea. + */ + if (!strncmp(source, "/tmp/", 5) && !strncmp(target, "/tmp/", 5)) { + if (mount(source, target, NULL, req->data.args[3], NULL) < 0) { + ret = -1; + perror("actual mount"); + goto out; + } + resp->error = 0; + } + + /* Even if we didn't allow it because of policy, generating the + * response was be a success, because we want to tell the worker EPERM. + */ + ret = 0; + +out: + close(mem); + return ret; +} + +int main(void) +{ + int sk_pair[2], ret = 1, status, listener; + pid_t worker = 0 , tracer = 0; + + if (socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair) < 0) { + perror("socketpair"); + return 1; + } + + worker = fork(); + if (worker < 0) { + perror("fork"); + goto close_pair; + } + + if (worker == 0) { + listener = user_trap_syscall(__NR_mount, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) { + perror("seccomp"); + exit(1); + } + + /* + * Drop privileges. We definitely can't mount as uid 1000. + */ + if (setuid(1000) < 0) { + perror("setuid"); + exit(1); + } + + /* + * Send the listener to the parent; also serves as + * synchronization. + */ + if (send_fd(sk_pair[1], listener) < 0) + exit(1); + close(listener); + + if (mkdir("/tmp/foo", 0755) < 0) { + perror("mkdir"); + exit(1); + } + + /* + * Try a bad mount just for grins. + */ + if (mount("/dev/sda", "/tmp/foo", NULL, 0, NULL) != -1) { + fprintf(stderr, "huh? mounted /dev/sda?\n"); + exit(1); + } + + if (errno != EPERM) { + perror("bad error from mount"); + exit(1); + } + + /* + * Ok, we expect this one to succeed. + */ + if (mount("/tmp/foo", "/tmp/foo", NULL, MS_BIND, NULL) < 0) { + perror("mount"); + exit(1); + } + + exit(0); + } + + /* + * Get the listener from the child. + */ + listener = recv_fd(sk_pair[0]); + if (listener < 0) + goto out_kill; + + /* + * Fork a task to handle the requests. This isn't strictly necessary, + * but it makes the particular writing of this sample easier, since we + * can just wait ofr the tracee to exit and kill the tracer. + */ + tracer = fork(); + if (tracer < 0) { + perror("fork"); + goto out_kill; + } + + if (tracer == 0) { + struct seccomp_notif *req; + struct seccomp_notif_resp *resp; + struct seccomp_notif_sizes sizes; + + if (seccomp(SECCOMP_GET_NOTIF_SIZES, 0, &sizes) < 0) { + perror("seccomp(GET_NOTIF_SIZES)"); + goto out_close; + } + + req = malloc(sizes.seccomp_notif); + if (!req) + goto out_close; + + resp = malloc(sizes.seccomp_notif_resp); + if (!resp) + goto out_req; + memset(resp, 0, sizes.seccomp_notif_resp); + + while (1) { + memset(req, 0, sizes.seccomp_notif); + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, req)) { + perror("ioctl recv"); + goto out_resp; + } + + if (handle_req(req, resp, listener) < 0) + goto out_resp; + + /* + * ENOENT here means that the task may have gotten a + * signal and restarted the syscall. It's up to the + * handler to decide what to do in this case, but for + * the sample code, we just ignore it. Probably + * something better should happen, like undoing the + * mount, or keeping track of the args to make sure we + * don't do it again. + */ + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, resp) < 0 && + errno != ENOENT) { + perror("ioctl send"); + goto out_resp; + } + } +out_resp: + free(resp); +out_req: + free(req); +out_close: + close(listener); + exit(1); + } + + close(listener); + + if (waitpid(worker, &status, 0) != worker) { + perror("waitpid"); + goto out_kill; + } + + if (umount2("/tmp/foo", MNT_DETACH) < 0 && errno != EINVAL) { + perror("umount2"); + goto out_kill; + } + + if (remove("/tmp/foo") < 0 && errno != ENOENT) { + perror("remove"); + exit(1); + } + + if (!WIFEXITED(status) || WEXITSTATUS(status)) { + fprintf(stderr, "worker exited nonzero\n"); + goto out_kill; + } + + ret = 0; + +out_kill: + if (tracer > 0) + kill(tracer, SIGKILL); + if (worker > 0) + kill(worker, SIGKILL); + +close_pair: + close(sk_pair[0]); + close(sk_pair[1]); + return ret; +} -- cgit v1.3.1