x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

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) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 217 insertions, 0 deletions

diff --git a/fs/ext2/file.c b/fs/ext2/file.c
new file mode 100644
index 000000000..b9020df7d
--- /dev/null
+++ b/fs/ext2/file.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/ext2/file.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/fs/minix/file.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext2 fs regular file handling primitives
+ *
+ *  64-bit file support on 64-bit platforms by Jakub Jelinek
+ * 	(jj@sunsite.ms.mff.cuni.cz)
+ */
+
+#include <linux/time.h>
+#include <linux/pagemap.h>
+#include <linux/filelock.h>
+#include <linux/quotaops.h>
+#include <linux/iomap.h>
+#include <linux/uio.h>
+#include <linux/buffer_head.h>
+#include "ext2.h"
+#include "xattr.h"
+#include "acl.h"
+#include "trace.h"
+
+
+/*
+ * Called when filp is released. This happens when all file descriptors
+ * for a single struct file are closed. Note that different open() calls
+ * for the same file yield different struct file structures.
+ */
+static int ext2_release_file (struct inode * inode, struct file * filp)
+{
+	if (filp->f_mode & FMODE_WRITE) {
+		mutex_lock(&EXT2_I(inode)->truncate_mutex);
+		ext2_discard_reservation(inode);
+		mutex_unlock(&EXT2_I(inode)->truncate_mutex);
+	}
+	return 0;
+}
+
+static ssize_t ext2_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	ssize_t ret;
+
+	trace_ext2_dio_read_begin(iocb, to, 0);
+	inode_lock_shared(inode);
+	ret = iomap_dio_rw(iocb, to, &ext2_iomap_ops, NULL, 0, NULL, 0);
+	inode_unlock_shared(inode);
+	trace_ext2_dio_read_end(iocb, to, ret);
+
+	return ret;
+}
+
+static int ext2_dio_write_end_io(struct kiocb *iocb, ssize_t size,
+				 int error, unsigned int flags)
+{
+	loff_t pos = iocb->ki_pos;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (error)
+		goto out;
+
+	/*
+	 * If we are extending the file, we have to update i_size here before
+	 * page cache gets invalidated in iomap_dio_rw(). This prevents racing
+	 * buffered reads from zeroing out too much from page cache pages.
+	 * Note that all extending writes always happens synchronously with
+	 * inode lock held by ext2_dio_write_iter(). So it is safe to update
+	 * inode size here for extending file writes.
+	 */
+	pos += size;
+	if (pos > i_size_read(inode)) {
+		i_size_write(inode, pos);
+		mark_inode_dirty(inode);
+	}
+out:
+	trace_ext2_dio_write_endio(iocb, size, error);
+	return error;
+}
+
+static const struct iomap_dio_ops ext2_dio_write_ops = {
+	.end_io = ext2_dio_write_end_io,
+};
+
+static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	ssize_t ret;
+	unsigned int flags = 0;
+	unsigned long blocksize = inode->i_sb->s_blocksize;
+	loff_t offset = iocb->ki_pos;
+	loff_t count = iov_iter_count(from);
+	ssize_t status = 0;
+
+	trace_ext2_dio_write_begin(iocb, from, 0);
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out_unlock;
+
+	ret = kiocb_modified(iocb);
+	if (ret)
+		goto out_unlock;
+
+	/* use IOMAP_DIO_FORCE_WAIT for unaligned or extending writes */
+	if (iocb->ki_pos + iov_iter_count(from) > i_size_read(inode) ||
+	   (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(from), blocksize)))
+		flags |= IOMAP_DIO_FORCE_WAIT;
+
+	ret = iomap_dio_rw(iocb, from, &ext2_iomap_ops, &ext2_dio_write_ops,
+			   flags, NULL, 0);
+
+	/* ENOTBLK is magic return value for fallback to buffered-io */
+	if (ret == -ENOTBLK)
+		ret = 0;
+
+	if (ret < 0 && ret != -EIOCBQUEUED)
+		ext2_write_failed(inode->i_mapping, offset + count);
+
+	/* handle case for partial write and for fallback to buffered write */
+	if (ret >= 0 && iov_iter_count(from)) {
+		loff_t pos, endbyte;
+		int ret2;
+
+		iocb->ki_flags &= ~IOCB_DIRECT;
+		pos = iocb->ki_pos;
+		status = generic_perform_write(iocb, from);
+		if (unlikely(status < 0)) {
+			ret = status;
+			goto out_unlock;
+		}
+
+		ret += status;
+		endbyte = pos + status - 1;
+		ret2 = filemap_write_and_wait_range(inode->i_mapping, pos,
+						    endbyte);
+		if (!ret2) {
+			invalidate_mapping_pages(inode->i_mapping,
+						 pos >> PAGE_SHIFT,
+						 endbyte >> PAGE_SHIFT);
+			if (ret > 0)
+				ret = generic_write_sync(iocb, ret);
+		} else {
+			ret = ret2;
+		}
+	}
+
+out_unlock:
+	inode_unlock(inode);
+	if (status)
+		trace_ext2_dio_write_buff_end(iocb, from, status);
+	trace_ext2_dio_write_end(iocb, from, ret);
+	return ret;
+}
+
+static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext2_dio_read_iter(iocb, to);
+
+	return generic_file_read_iter(iocb, to);
+}
+
+static ssize_t ext2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext2_dio_write_iter(iocb, from);
+
+	return generic_file_write_iter(iocb, from);
+}
+
+static int ext2_file_open(struct inode *inode, struct file *filp)
+{
+	filp->f_mode |= FMODE_CAN_ODIRECT;
+	return dquot_file_open(inode, filp);
+}
+
+const struct file_operations ext2_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read_iter	= ext2_file_read_iter,
+	.write_iter	= ext2_file_write_iter,
+	.unlocked_ioctl = ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
+	.mmap_prepare	= generic_file_mmap_prepare,
+	.open		= ext2_file_open,
+	.release	= ext2_release_file,
+	.fsync		= simple_fsync,
+	.get_unmapped_area = thp_get_unmapped_area,
+	.splice_read	= filemap_splice_read,
+	.splice_write	= iter_file_splice_write,
+	.setlease	= generic_setlease,
+};
+
+const struct inode_operations ext2_file_inode_operations = {
+	.listxattr	= ext2_listxattr,
+	.getattr	= ext2_getattr,
+	.setattr	= ext2_setattr,
+	.get_inode_acl	= ext2_get_acl,
+	.set_acl	= ext2_set_acl,
+	.fiemap		= ext2_fiemap,
+	.fileattr_get	= ext2_fileattr_get,
+	.fileattr_set	= ext2_fileattr_set,
+};