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, 168 insertions, 0 deletions

diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c
new file mode 100644
index 000000000..9f66bbcd3
--- /dev/null
+++ b/fs/smb/client/fscache.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ *   CIFS filesystem cache interface
+ *
+ *   Copyright (c) 2010 Novell, Inc.
+ *   Author(s): Suresh Jayaraman <sjayaraman@suse.de>
+ *
+ */
+#include "fscache.h"
+#include "cifsglob.h"
+#include "cifs_debug.h"
+#include "cifs_fs_sb.h"
+#include "cifsproto.h"
+
+/*
+ * Key for fscache inode.  [!] Contents must match comparisons in cifs_find_inode().
+ */
+struct cifs_fscache_inode_key {
+
+	__le64  uniqueid;	/* server inode number */
+	__le64  createtime;	/* creation time on server */
+	u8	type;		/* S_IFMT file type */
+} __packed;
+
+static void cifs_fscache_fill_volume_coherency(
+	struct cifs_tcon *tcon,
+	struct cifs_fscache_volume_coherency_data *cd)
+{
+	memset(cd, 0, sizeof(*cd));
+	cd->resource_id		= cpu_to_le64(tcon->resource_id);
+	cd->vol_create_time	= tcon->vol_create_time;
+	cd->vol_serial_number	= cpu_to_le32(tcon->vol_serial_number);
+}
+
+int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon)
+{
+	struct cifs_fscache_volume_coherency_data cd;
+	struct TCP_Server_Info *server = tcon->ses->server;
+	struct fscache_volume *vcookie;
+	const struct sockaddr *sa = (struct sockaddr *)&server->dstaddr;
+	char *sharename;
+	char *key;
+	int ret = -ENOMEM;
+
+	if (tcon->fscache_acquired)
+		return 0;
+
+	mutex_lock(&tcon->fscache_lock);
+	if (tcon->fscache_acquired) {
+		mutex_unlock(&tcon->fscache_lock);
+		return 0;
+	}
+	tcon->fscache_acquired = true;
+
+	tcon->fscache = NULL;
+	switch (sa->sa_family) {
+	case AF_INET:
+	case AF_INET6:
+		break;
+	default:
+		mutex_unlock(&tcon->fscache_lock);
+		cifs_dbg(VFS, "Unknown network family '%d'\n", sa->sa_family);
+		return -EINVAL;
+	}
+
+	memset(&key, 0, sizeof(key));
+
+	sharename = extract_sharename(tcon->tree_name);
+	if (IS_ERR(sharename)) {
+		mutex_unlock(&tcon->fscache_lock);
+		cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__);
+		return PTR_ERR(sharename);
+	}
+
+	strreplace(sharename, '/', ';');
+
+	key = kasprintf(GFP_KERNEL, "cifs,%pISpc,%s", sa, sharename);
+	if (!key)
+		goto out;
+
+	cifs_fscache_fill_volume_coherency(tcon, &cd);
+	vcookie = fscache_acquire_volume(key,
+					 NULL, /* preferred_cache */
+					 &cd, sizeof(cd));
+	cifs_dbg(FYI, "%s: (%s/0x%p)\n", __func__, key, vcookie);
+	if (IS_ERR(vcookie)) {
+		if (vcookie != ERR_PTR(-EBUSY)) {
+			ret = PTR_ERR(vcookie);
+			goto out_2;
+		}
+		pr_err("Cache volume key already in use (%s)\n", key);
+		vcookie = NULL;
+		trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+				    netfs_trace_tcon_ref_see_fscache_collision);
+	} else {
+		trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+				    netfs_trace_tcon_ref_see_fscache_okay);
+	}
+
+	tcon->fscache = vcookie;
+	ret = 0;
+out_2:
+	kfree(key);
+out:
+	kfree(sharename);
+	mutex_unlock(&tcon->fscache_lock);
+	return ret;
+}
+
+void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon)
+{
+	struct cifs_fscache_volume_coherency_data cd;
+
+	cifs_dbg(FYI, "%s: (0x%p)\n", __func__, tcon->fscache);
+
+	cifs_fscache_fill_volume_coherency(tcon, &cd);
+	fscache_relinquish_volume(tcon->fscache, &cd, false);
+	tcon->fscache = NULL;
+	trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+			    netfs_trace_tcon_ref_see_fscache_relinq);
+}
+
+void cifs_fscache_get_inode_cookie(struct inode *inode)
+{
+	struct cifs_fscache_inode_coherency_data cd;
+	struct cifs_fscache_inode_key key;
+	struct cifsInodeInfo *cifsi = CIFS_I(inode);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+
+	key.uniqueid	= cpu_to_le64(cifsi->uniqueid);
+	key.createtime	= cpu_to_le64(cifsi->createtime);
+	key.type	= (inode->i_mode & S_IFMT) >> 12;
+	cifs_fscache_fill_coherency(&cifsi->netfs.inode, &cd);
+
+	cifsi->netfs.cache =
+		fscache_acquire_cookie(tcon->fscache, 0,
+				       &key, sizeof(key),
+				       &cd, sizeof(cd),
+				       i_size_read(&cifsi->netfs.inode));
+	if (cifsi->netfs.cache)
+		mapping_set_release_always(inode->i_mapping);
+}
+
+void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update)
+{
+	if (update) {
+		struct cifs_fscache_inode_coherency_data cd;
+		loff_t i_size = i_size_read(inode);
+
+		cifs_fscache_fill_coherency(inode, &cd);
+		fscache_unuse_cookie(cifs_inode_cookie(inode), &cd, &i_size);
+	} else {
+		fscache_unuse_cookie(cifs_inode_cookie(inode), NULL, NULL);
+	}
+}
+
+void cifs_fscache_release_inode_cookie(struct inode *inode)
+{
+	struct cifsInodeInfo *cifsi = CIFS_I(inode);
+	struct fscache_cookie *cookie = cifs_inode_cookie(inode);
+
+	if (cookie) {
+		cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cookie);
+		fscache_relinquish_cookie(cookie, false);
+		cifsi->netfs.cache = NULL;
+	}
+}