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, 165 insertions, 0 deletions

diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
new file mode 100644
index 000000000..f93b68c48
--- /dev/null
+++ b/fs/nilfs2/file.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * NILFS regular file handling primitives including fsync().
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * Written by Amagai Yoshiji and Ryusuke Konishi.
+ */
+
+#include <linux/fs.h>
+#include <linux/filelock.h>
+#include <linux/mm.h>
+#include <linux/writeback.h>
+#include "nilfs.h"
+#include "segment.h"
+
+int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	/*
+	 * Called from fsync() system call
+	 * This is the only entry point that can catch write and synch
+	 * timing for both data blocks and intermediate blocks.
+	 *
+	 * This function should be implemented when the writeback function
+	 * will be implemented.
+	 */
+	struct the_nilfs *nilfs;
+	struct inode *inode = file->f_mapping->host;
+	int err = 0;
+
+	if (nilfs_inode_dirty(inode)) {
+		if (datasync)
+			err = nilfs_construct_dsync_segment(inode->i_sb, inode,
+							    start, end);
+		else
+			err = nilfs_construct_segment(inode->i_sb);
+	}
+
+	nilfs = inode->i_sb->s_fs_info;
+	if (!err)
+		err = nilfs_flush_device(nilfs);
+
+	return err;
+}
+
+static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio = page_folio(vmf->page);
+	struct inode *inode = file_inode(vma->vm_file);
+	struct nilfs_transaction_info ti;
+	struct buffer_head *bh, *head;
+	int ret = 0;
+
+	if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
+		return VM_FAULT_SIGBUS; /* -ENOSPC */
+
+	sb_start_pagefault(inode->i_sb);
+	folio_lock(folio);
+	if (folio->mapping != inode->i_mapping ||
+	    folio_pos(folio) >= i_size_read(inode) ||
+	    !folio_test_uptodate(folio)) {
+		folio_unlock(folio);
+		ret = -EFAULT;	/* make the VM retry the fault */
+		goto out;
+	}
+
+	/*
+	 * check to see if the folio is mapped already (no holes)
+	 */
+	if (folio_test_mappedtodisk(folio))
+		goto mapped;
+
+	head = folio_buffers(folio);
+	if (head) {
+		int fully_mapped = 1;
+
+		bh = head;
+		do {
+			if (!buffer_mapped(bh)) {
+				fully_mapped = 0;
+				break;
+			}
+		} while (bh = bh->b_this_page, bh != head);
+
+		if (fully_mapped) {
+			folio_set_mappedtodisk(folio);
+			goto mapped;
+		}
+	}
+	folio_unlock(folio);
+
+	/*
+	 * fill hole blocks
+	 */
+	ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
+	/* never returns -ENOMEM, but may return -ENOSPC */
+	if (unlikely(ret))
+		goto out;
+
+	file_update_time(vma->vm_file);
+	ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
+	if (ret) {
+		nilfs_transaction_abort(inode->i_sb);
+		goto out;
+	}
+	nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
+	nilfs_transaction_commit(inode->i_sb);
+
+ mapped:
+	/*
+	 * Since checksumming including data blocks is performed to determine
+	 * the validity of the log to be written and used for recovery, it is
+	 * necessary to wait for writeback to finish here, regardless of the
+	 * stable write requirement of the backing device.
+	 */
+	folio_wait_writeback(folio);
+ out:
+	sb_end_pagefault(inode->i_sb);
+	return vmf_fs_error(ret);
+}
+
+static const struct vm_operations_struct nilfs_file_vm_ops = {
+	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
+	.page_mkwrite	= nilfs_page_mkwrite,
+};
+
+static int nilfs_file_mmap_prepare(struct vm_area_desc *desc)
+{
+	file_accessed(desc->file);
+	desc->vm_ops = &nilfs_file_vm_ops;
+	return 0;
+}
+
+/*
+ * We have mostly NULL's here: the current defaults are ok for
+ * the nilfs filesystem.
+ */
+const struct file_operations nilfs_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
+	.unlocked_ioctl	= nilfs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= nilfs_compat_ioctl,
+#endif	/* CONFIG_COMPAT */
+	.mmap_prepare	= nilfs_file_mmap_prepare,
+	.open		= generic_file_open,
+	/* .release	= nilfs_release_file, */
+	.fsync		= nilfs_sync_file,
+	.splice_read	= filemap_splice_read,
+	.splice_write   = iter_file_splice_write,
+	.setlease	= generic_setlease,
+};
+
+const struct inode_operations nilfs_file_inode_operations = {
+	.setattr	= nilfs_setattr,
+	.permission     = nilfs_permission,
+	.fiemap		= nilfs_fiemap,
+	.fileattr_get	= nilfs_fileattr_get,
+	.fileattr_set	= nilfs_fileattr_set,
+};
+
+/* end of file */