From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions When using eBPF to probe CS CALL instructions within a function, a crash can be triggered. The eBPF tool probes offset 257 of the __hrtimer_run_queues() function: <__hrtimer_run_queues+249>: nopl 0x0(%rax,%rax,1) <__hrtimer_run_queues+254>: mov %r14,%rdi <__hrtimer_run_queues+257>: cs call <__x86_indirect_thunk_r12> <__hrtimer_run_queues+263>: mov %eax,%r12d <__hrtimer_run_queues+266>: xchg %ax,%ax <__hrtimer_run_queues+268>: mov %r13,%rdi Which triggers this crash: BUG: unable to handle page fault for address: 00000000000f41c9 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P RIP: 0010:__hrtimer_run_queues+0x106/0x230 Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is at the 6th byte of the above CS CALL instruction. Since the CS CALL instruction occupies 6 bytes, the exception occurred in the middle of that call instruction. The root cause is that when using eBPF tools to probe in the middle of a function, a kprobe with INT3 is used as the underlying implementation. During single-step emulation of the original CALL instruction, int3_emulate_call() assumes that the probed CALL instruction is 5 bytes long. However, the actual CS-prefixed CALL instruction occupies 6 bytes, so it constructs an incorrect exception return address. When the CPU returns from the kprobe handler, the next instruction to be executed is at the address of the last byte of that CS CALL instruction. Coincidentally, starting from that address, the CPU fetches and decodes a completely different instruction, which ultimately triggers a kernel crash. Fix the issue by using the actual instruction length obtained from the instruction decoder when constructing the exception return address, rather than relying on the hardcoded CALL_INSN_SIZE macro. [ mingo: Refined the changelog ] Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step") Suggested-by: Masami Hiramatsu (Google) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- drivers/tty/tty_audit.c | 251 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 251 insertions(+) create mode 100644 drivers/tty/tty_audit.c (limited to 'drivers/tty/tty_audit.c') diff --git a/drivers/tty/tty_audit.c b/drivers/tty/tty_audit.c new file mode 100644 index 000000000..d014af6ab --- /dev/null +++ b/drivers/tty/tty_audit.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Creating audit events from TTY input. + * + * Copyright (C) 2007 Red Hat, Inc. All rights reserved. + * + * Authors: Miloslav Trmac + */ + +#include +#include +#include +#include "tty.h" + +#define TTY_AUDIT_BUF_SIZE 4096 + +struct tty_audit_buf { + struct mutex mutex; /* Protects all data below */ + dev_t dev; /* The TTY which the data is from */ + bool icanon; + size_t valid; + u8 *data; /* Allocated size TTY_AUDIT_BUF_SIZE */ +}; + +static struct tty_audit_buf *tty_audit_buf_ref(void) +{ + struct tty_audit_buf *buf; + + buf = current->signal->tty_audit_buf; + WARN_ON(buf == ERR_PTR(-ESRCH)); + return buf; +} + +static struct tty_audit_buf *tty_audit_buf_alloc(void) +{ + struct tty_audit_buf *buf; + + buf = kzalloc_obj(*buf); + if (!buf) + goto err; + + buf->data = kmalloc(TTY_AUDIT_BUF_SIZE, GFP_KERNEL); + if (!buf->data) + goto err_buf; + + mutex_init(&buf->mutex); + + return buf; + +err_buf: + kfree(buf); +err: + return NULL; +} + +static void tty_audit_buf_free(struct tty_audit_buf *buf) +{ + WARN_ON(buf->valid != 0); + kfree(buf->data); + kfree(buf); +} + +static void tty_audit_log(const char *description, dev_t dev, + const u8 *data, size_t size) +{ + struct audit_buffer *ab; + pid_t pid = task_pid_nr(current); + uid_t uid = from_kuid(&init_user_ns, task_uid(current)); + uid_t loginuid = from_kuid(&init_user_ns, audit_get_loginuid(current)); + unsigned int sessionid = audit_get_sessionid(current); + char name[TASK_COMM_LEN]; + + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_TTY); + if (!ab) + return; + + audit_log_format(ab, "%s pid=%u uid=%u auid=%u ses=%u major=%d minor=%d comm=", + description, pid, uid, loginuid, sessionid, + MAJOR(dev), MINOR(dev)); + get_task_comm(name, current); + audit_log_untrustedstring(ab, name); + audit_log_format(ab, " data="); + audit_log_n_hex(ab, data, size); + audit_log_end(ab); +} + +/* + * tty_audit_buf_push - Push buffered data out + * + * Generate an audit message from the contents of @buf, which is owned by + * the current task. @buf->mutex must be locked. + */ +static void tty_audit_buf_push(struct tty_audit_buf *buf) +{ + if (buf->valid == 0) + return; + if (audit_enabled == AUDIT_OFF) { + buf->valid = 0; + return; + } + tty_audit_log("tty", buf->dev, buf->data, buf->valid); + buf->valid = 0; +} + +/** + * tty_audit_exit - Handle a task exit + * + * Make sure all buffered data is written out and deallocate the buffer. + * Only needs to be called if current->signal->tty_audit_buf != %NULL. + * + * The process is single-threaded at this point; no other threads share + * current->signal. + */ +void tty_audit_exit(void) +{ + struct tty_audit_buf *buf; + + buf = xchg(¤t->signal->tty_audit_buf, ERR_PTR(-ESRCH)); + if (!buf) + return; + + tty_audit_buf_push(buf); + tty_audit_buf_free(buf); +} + +/* + * tty_audit_fork - Copy TTY audit state for a new task + * + * Set up TTY audit state in @sig from current. @sig needs no locking. + */ +void tty_audit_fork(struct signal_struct *sig) +{ + sig->audit_tty = current->signal->audit_tty; +} + +/* + * tty_audit_tiocsti - Log TIOCSTI + */ +void tty_audit_tiocsti(const struct tty_struct *tty, u8 ch) +{ + dev_t dev; + + dev = MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; + if (tty_audit_push()) + return; + + if (audit_enabled) + tty_audit_log("ioctl=TIOCSTI", dev, &ch, 1); +} + +/* + * tty_audit_push - Flush current's pending audit data + * + * Returns 0 if success, -EPERM if tty audit is disabled + */ +int tty_audit_push(void) +{ + struct tty_audit_buf *buf; + + if (~current->signal->audit_tty & AUDIT_TTY_ENABLE) + return -EPERM; + + buf = tty_audit_buf_ref(); + if (!IS_ERR_OR_NULL(buf)) { + mutex_lock(&buf->mutex); + tty_audit_buf_push(buf); + mutex_unlock(&buf->mutex); + } + return 0; +} + +/* + * tty_audit_buf_get - Get an audit buffer. + * + * Get an audit buffer, allocate it if necessary. Return %NULL + * if out of memory or ERR_PTR(-ESRCH) if tty_audit_exit() has already + * occurred. Otherwise, return a new reference to the buffer. + */ +static struct tty_audit_buf *tty_audit_buf_get(void) +{ + struct tty_audit_buf *buf; + + buf = tty_audit_buf_ref(); + if (buf) + return buf; + + buf = tty_audit_buf_alloc(); + if (buf == NULL) { + audit_log_lost("out of memory in TTY auditing"); + return NULL; + } + + /* Race to use this buffer, free it if another wins */ + if (cmpxchg(¤t->signal->tty_audit_buf, NULL, buf) != NULL) + tty_audit_buf_free(buf); + return tty_audit_buf_ref(); +} + +/* + * tty_audit_add_data - Add data for TTY auditing. + * + * Audit @data of @size from @tty, if necessary. + */ +void tty_audit_add_data(const struct tty_struct *tty, const void *data, + size_t size) +{ + struct tty_audit_buf *buf; + unsigned int audit_tty; + bool icanon = L_ICANON(tty); + dev_t dev; + + audit_tty = READ_ONCE(current->signal->audit_tty); + if (~audit_tty & AUDIT_TTY_ENABLE) + return; + + if (unlikely(size == 0)) + return; + + if (tty->driver->type == TTY_DRIVER_TYPE_PTY + && tty->driver->subtype == PTY_TYPE_MASTER) + return; + + if ((~audit_tty & AUDIT_TTY_LOG_PASSWD) && icanon && !L_ECHO(tty)) + return; + + buf = tty_audit_buf_get(); + if (IS_ERR_OR_NULL(buf)) + return; + + mutex_lock(&buf->mutex); + dev = MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; + if (buf->dev != dev || buf->icanon != icanon) { + tty_audit_buf_push(buf); + buf->dev = dev; + buf->icanon = icanon; + } + do { + size_t run; + + run = TTY_AUDIT_BUF_SIZE - buf->valid; + if (run > size) + run = size; + memcpy(buf->data + buf->valid, data, run); + buf->valid += run; + data += run; + size -= run; + if (buf->valid == TTY_AUDIT_BUF_SIZE) + tty_audit_buf_push(buf); + } while (size != 0); + mutex_unlock(&buf->mutex); +} -- cgit v1.3.1