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, 201 insertions, 0 deletions

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
new file mode 100644
index 000000000..1ac0b3dcc
--- /dev/null
+++ b/fs/9p/vfs_addr.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contians vfs address (mmap) ops for 9P2000.
+ *
+ *  Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/pagemap.h>
+#include <linux/sched.h>
+#include <linux/swap.h>
+#include <linux/uio.h>
+#include <linux/netfs.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <trace/events/netfs.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "cache.h"
+#include "fid.h"
+
+/*
+ * Writeback calls this when it finds a folio that needs uploading.  This isn't
+ * called if writeback only has copy-to-cache to deal with.
+ */
+static void v9fs_begin_writeback(struct netfs_io_request *wreq)
+{
+	struct p9_fid *fid;
+
+	fid = v9fs_fid_find_inode(wreq->inode, true, INVALID_UID, true);
+	if (!fid) {
+		WARN_ONCE(1, "folio expected an open fid inode->i_ino=%llx\n",
+			  wreq->inode->i_ino);
+		return;
+	}
+
+	wreq->wsize = fid->clnt->msize - P9_IOHDRSZ;
+	if (fid->iounit)
+		wreq->wsize = min(wreq->wsize, fid->iounit);
+	wreq->netfs_priv = fid;
+	wreq->io_streams[0].avail = true;
+}
+
+/*
+ * Issue a subrequest to write to the server.
+ */
+static void v9fs_issue_write(struct netfs_io_subrequest *subreq)
+{
+	struct p9_fid *fid = subreq->rreq->netfs_priv;
+	int err, len;
+
+	len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err);
+	if (len > 0)
+		__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
+	netfs_write_subrequest_terminated(subreq, len ?: err);
+}
+
+/**
+ * v9fs_issue_read - Issue a read from 9P
+ * @subreq: The read to make
+ */
+static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *rreq = subreq->rreq;
+	struct p9_fid *fid = rreq->netfs_priv;
+	char *target;
+	unsigned long long pos = subreq->start + subreq->transferred;
+	int total = 0, err, len, n;
+
+	if (S_ISLNK(rreq->inode->i_mode)) {
+		/* p9_client_readlink() must not be called for legacy protocols
+		 * 9p2000 or 9p2000.u.
+		 */
+		BUG_ON(!p9_is_proto_dotl(fid->clnt));
+		if (WARN_ON_ONCE(pos)) {
+			/* reading a link at a non null offset should
+			 * not happen
+			 */
+			err = -EIO;
+			goto fill_subreq;
+		}
+		err = p9_client_readlink(fid, &target);
+		if (err != 0)
+			goto fill_subreq;
+		len = strlen(target);
+		n = copy_to_iter(target, len, &subreq->io_iter);
+		kfree(target);
+		total = n;
+	} else {
+		total = p9_client_read(fid, pos, &subreq->io_iter, &err);
+	}
+
+fill_subreq:
+	/* if we just extended the file size, any portion not in
+	 * cache won't be on server and is zeroes */
+	if (subreq->rreq->origin != NETFS_UNBUFFERED_READ &&
+	    subreq->rreq->origin != NETFS_DIO_READ)
+		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+	if (pos + total >= i_size_read(rreq->inode))
+		__set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags);
+	if (!err && total) {
+		subreq->transferred += total;
+		__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
+	}
+
+	subreq->error = err;
+	netfs_read_subreq_terminated(subreq);
+}
+
+/**
+ * v9fs_init_request - Initialise a request
+ * @rreq: The read request
+ * @file: The file being read from
+ */
+static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file)
+{
+	struct p9_fid *fid;
+	struct dentry *dentry;
+	bool writing = (rreq->origin == NETFS_READ_FOR_WRITE ||
+			rreq->origin == NETFS_WRITETHROUGH ||
+			rreq->origin == NETFS_UNBUFFERED_WRITE ||
+			rreq->origin == NETFS_DIO_WRITE);
+
+	if (rreq->origin == NETFS_WRITEBACK)
+		return 0; /* We don't get the write handle until we find we
+			   * have actually dirty data and not just
+			   * copy-to-cache data.
+			   */
+
+	if (file) {
+		fid = file->private_data;
+		if (!fid)
+			goto no_fid;
+		p9_fid_get(fid);
+	} else if (S_ISLNK(rreq->inode->i_mode)) {
+		dentry = d_find_any_alias(rreq->inode);
+		if (!dentry)
+			goto no_fid;
+		fid = v9fs_fid_lookup(dentry);
+		dput(dentry);
+		if (IS_ERR(fid))
+			goto no_fid;
+	} else {
+		fid = v9fs_fid_find_inode(rreq->inode, writing, INVALID_UID, true);
+		if (!fid)
+			goto no_fid;
+	}
+
+	rreq->wsize = fid->clnt->msize - P9_IOHDRSZ;
+	if (fid->iounit)
+		rreq->wsize = min(rreq->wsize, fid->iounit);
+
+	/* we might need to read from a fid that was opened write-only
+	 * for read-modify-write of page cache, use the writeback fid
+	 * for that */
+	WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE && !(fid->mode & P9_ORDWR));
+	rreq->netfs_priv = fid;
+	return 0;
+
+no_fid:
+	WARN_ONCE(1, "folio expected an open fid inode->i_ino=%llx\n",
+		  rreq->inode->i_ino);
+	return -EINVAL;
+}
+
+/**
+ * v9fs_free_request - Cleanup request initialized by v9fs_init_rreq
+ * @rreq: The I/O request to clean up
+ */
+static void v9fs_free_request(struct netfs_io_request *rreq)
+{
+	struct p9_fid *fid = rreq->netfs_priv;
+
+	p9_fid_put(fid);
+}
+
+const struct netfs_request_ops v9fs_req_ops = {
+	.init_request		= v9fs_init_request,
+	.free_request		= v9fs_free_request,
+	.issue_read		= v9fs_issue_read,
+	.begin_writeback	= v9fs_begin_writeback,
+	.issue_write		= v9fs_issue_write,
+};
+
+const struct address_space_operations v9fs_addr_operations = {
+	.read_folio		= netfs_read_folio,
+	.readahead		= netfs_readahead,
+	.dirty_folio		= netfs_dirty_folio,
+	.release_folio		= netfs_release_folio,
+	.invalidate_folio	= netfs_invalidate_folio,
+	.direct_IO		= noop_direct_IO,
+	.writepages		= netfs_writepages,
+	.migrate_folio		= filemap_migrate_folio,
+};