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, 197 insertions, 0 deletions

diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
new file mode 100644
index 000000000..f2d08ac24
--- /dev/null
+++ b/fs/fuse/passthrough.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FUSE passthrough to backing file.
+ *
+ * Copyright (c) 2023 CTERA Networks.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/file.h>
+#include <linux/backing-file.h>
+#include <linux/splice.h>
+
+static void fuse_file_accessed(struct file *file)
+{
+	struct inode *inode = file_inode(file);
+
+	fuse_invalidate_atime(inode);
+}
+
+static void fuse_passthrough_end_write(struct kiocb *iocb, ssize_t ret)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	fuse_write_update_attr(inode, iocb->ki_pos, ret);
+}
+
+ssize_t fuse_passthrough_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	struct fuse_file *ff = file->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	size_t count = iov_iter_count(iter);
+	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.accessed = fuse_file_accessed,
+	};
+
+
+	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu\n", __func__,
+		 backing_file, iocb->ki_pos, count);
+
+	if (!count)
+		return 0;
+
+	ret = backing_file_read_iter(backing_file, iter, iocb, iocb->ki_flags,
+				     &ctx);
+
+	return ret;
+}
+
+ssize_t fuse_passthrough_write_iter(struct kiocb *iocb,
+				    struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct fuse_file *ff = file->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	size_t count = iov_iter_count(iter);
+	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.end_write = fuse_passthrough_end_write,
+	};
+
+	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu\n", __func__,
+		 backing_file, iocb->ki_pos, count);
+
+	if (!count)
+		return 0;
+
+	inode_lock(inode);
+	ret = backing_file_write_iter(backing_file, iter, iocb, iocb->ki_flags,
+				      &ctx);
+	inode_unlock(inode);
+
+	return ret;
+}
+
+ssize_t fuse_passthrough_splice_read(struct file *in, loff_t *ppos,
+				     struct pipe_inode_info *pipe,
+				     size_t len, unsigned int flags)
+{
+	struct fuse_file *ff = in->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.accessed = fuse_file_accessed,
+	};
+	struct kiocb iocb;
+	ssize_t ret;
+
+	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu, flags=0x%x\n", __func__,
+		 backing_file, *ppos, len, flags);
+
+	init_sync_kiocb(&iocb, in);
+	iocb.ki_pos = *ppos;
+	ret = backing_file_splice_read(backing_file, &iocb, pipe, len, flags, &ctx);
+	*ppos = iocb.ki_pos;
+
+	return ret;
+}
+
+ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
+				      struct file *out, loff_t *ppos,
+				      size_t len, unsigned int flags)
+{
+	struct fuse_file *ff = out->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	struct inode *inode = file_inode(out);
+	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.end_write = fuse_passthrough_end_write,
+	};
+	struct kiocb iocb;
+
+	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu, flags=0x%x\n", __func__,
+		 backing_file, *ppos, len, flags);
+
+	inode_lock(inode);
+	init_sync_kiocb(&iocb, out);
+	iocb.ki_pos = *ppos;
+	ret = backing_file_splice_write(pipe, backing_file, &iocb, len, flags, &ctx);
+	*ppos = iocb.ki_pos;
+	inode_unlock(inode);
+
+	return ret;
+}
+
+ssize_t fuse_passthrough_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct fuse_file *ff = file->private_data;
+	struct file *backing_file = fuse_file_passthrough(ff);
+	struct backing_file_ctx ctx = {
+		.cred = ff->cred,
+		.accessed = fuse_file_accessed,
+	};
+
+	pr_debug("%s: backing_file=0x%p, start=%lu, end=%lu\n", __func__,
+		 backing_file, vma->vm_start, vma->vm_end);
+
+	return backing_file_mmap(backing_file, vma, &ctx);
+}
+
+/*
+ * Setup passthrough to a backing file.
+ *
+ * Returns an fb object with elevated refcount to be stored in fuse inode.
+ */
+struct fuse_backing *fuse_passthrough_open(struct file *file, int backing_id)
+{
+	struct fuse_file *ff = file->private_data;
+	struct fuse_conn *fc = ff->fm->fc;
+	struct fuse_backing *fb = NULL;
+	struct file *backing_file;
+	int err;
+
+	err = -EINVAL;
+	if (backing_id <= 0)
+		goto out;
+
+	err = -ENOENT;
+	fb = fuse_backing_lookup(fc, backing_id);
+	if (!fb)
+		goto out;
+
+	/* Allocate backing file per fuse file to store fuse path */
+	backing_file = backing_file_open(file, file->f_flags,
+					 &fb->file->f_path, fb->cred);
+	err = PTR_ERR(backing_file);
+	if (IS_ERR(backing_file)) {
+		fuse_backing_put(fb);
+		goto out;
+	}
+
+	err = 0;
+	ff->passthrough = backing_file;
+	ff->cred = get_cred(fb->cred);
+out:
+	pr_debug("%s: backing_id=%d, fb=0x%p, backing_file=0x%p, err=%i\n", __func__,
+		 backing_id, fb, ff->passthrough, err);
+
+	return err ? ERR_PTR(err) : fb;
+}
+
+void fuse_passthrough_release(struct fuse_file *ff, struct fuse_backing *fb)
+{
+	pr_debug("%s: fb=0x%p, backing_file=0x%p\n", __func__,
+		 fb, ff->passthrough);
+
+	fput(ff->passthrough);
+	ff->passthrough = NULL;
+	put_cred(ff->cred);
+	ff->cred = NULL;
+}