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, 190 insertions, 0 deletions

diff --git a/fs/smb/client/smb1misc.c b/fs/smb/client/smb1misc.c
new file mode 100644
index 000000000..cdfbbff24
--- /dev/null
+++ b/fs/smb/client/smb1misc.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ *
+ *   Copyright (C) International Business Machines  Corp., 2002,2008
+ *   Author(s): Steve French (sfrench@us.ibm.com)
+ *
+ */
+
+#include "smb1proto.h"
+#include "smberr.h"
+#include "nterr.h"
+#include "cifs_debug.h"
+
+/* NB: MID can not be set if treeCon not passed in, in that
+   case it is responsibility of caller to set the mid */
+unsigned int
+header_assemble(struct smb_hdr *buffer, char smb_command,
+		const struct cifs_tcon *treeCon, int word_count
+		/* length of fixed section (word count) in two byte units  */)
+{
+	unsigned int in_len;
+	char *temp = (char *) buffer;
+
+	memset(temp, 0, 256); /* bigger than MAX_CIFS_HDR_SIZE */
+
+	in_len = (2 * word_count) + sizeof(struct smb_hdr) +
+		2 /* for bcc field itself */;
+
+	buffer->Protocol[0] = 0xFF;
+	buffer->Protocol[1] = 'S';
+	buffer->Protocol[2] = 'M';
+	buffer->Protocol[3] = 'B';
+	buffer->Command = smb_command;
+	buffer->Flags = 0x00;	/* case sensitive */
+	buffer->Flags2 = SMBFLG2_KNOWS_LONG_NAMES;
+	buffer->Pid = cpu_to_le16((__u16)current->tgid);
+	buffer->PidHigh = cpu_to_le16((__u16)(current->tgid >> 16));
+	if (treeCon) {
+		buffer->Tid = treeCon->tid;
+		if (treeCon->ses) {
+			if (treeCon->ses->capabilities & CAP_UNICODE)
+				buffer->Flags2 |= SMBFLG2_UNICODE;
+			if (treeCon->ses->capabilities & CAP_STATUS32)
+				buffer->Flags2 |= SMBFLG2_ERR_STATUS;
+
+			/* Uid is not converted */
+			buffer->Uid = treeCon->ses->Suid;
+			if (treeCon->ses->server)
+				buffer->Mid = get_next_mid(treeCon->ses->server);
+		}
+		if (treeCon->Flags & SMB_SHARE_IS_IN_DFS)
+			buffer->Flags2 |= SMBFLG2_DFS;
+		if (treeCon->nocase)
+			buffer->Flags  |= SMBFLG_CASELESS;
+		if ((treeCon->ses) && (treeCon->ses->server))
+			if (treeCon->ses->server->sign)
+				buffer->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
+	}
+
+/*  endian conversion of flags is now done just before sending */
+	buffer->WordCount = (char) word_count;
+	return in_len;
+}
+
+bool
+is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
+{
+	struct smb_hdr *buf = (struct smb_hdr *)buffer;
+	struct smb_com_lock_req *pSMB = (struct smb_com_lock_req *)buf;
+	struct TCP_Server_Info *pserver;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
+	struct cifsInodeInfo *pCifsInode;
+	struct cifsFileInfo *netfile;
+
+	cifs_dbg(FYI, "Checking for oplock break or dnotify response\n");
+	if ((pSMB->hdr.Command == SMB_COM_NT_TRANSACT) &&
+	   (pSMB->hdr.Flags & SMBFLG_RESPONSE)) {
+		struct smb_com_transaction_change_notify_rsp *pSMBr =
+			(struct smb_com_transaction_change_notify_rsp *)buf;
+		struct file_notify_information *pnotify;
+		__u32 data_offset = 0;
+		/* total_read excludes the RFC1002 preamble */
+		size_t len = srv->total_read;
+
+		if (get_bcc(buf) > sizeof(struct file_notify_information)) {
+			data_offset = le32_to_cpu(pSMBr->DataOffset);
+
+			if (data_offset >
+			    len - sizeof(struct file_notify_information)) {
+				cifs_dbg(FYI, "Invalid data_offset %u\n",
+					 data_offset);
+				return true;
+			}
+			pnotify = (struct file_notify_information *)
+				((char *)&pSMBr->hdr.Protocol + data_offset);
+			cifs_dbg(FYI, "dnotify on %s Action: 0x%x\n",
+				 pnotify->FileName, pnotify->Action);
+			/*   cifs_dump_mem("Rcvd notify Data: ",buf,
+				sizeof(struct smb_hdr)+60); */
+			return true;
+		}
+		if (pSMBr->hdr.Status.CifsError) {
+			cifs_dbg(FYI, "notify err 0x%x\n",
+				 pSMBr->hdr.Status.CifsError);
+			return true;
+		}
+		return false;
+	}
+	if (pSMB->hdr.Command != SMB_COM_LOCKING_ANDX)
+		return false;
+	if (pSMB->hdr.Flags & SMBFLG_RESPONSE) {
+		/* no sense logging error on invalid handle on oplock
+		   break - harmless race between close request and oplock
+		   break response is expected from time to time writing out
+		   large dirty files cached on the client */
+		if ((NT_STATUS_INVALID_HANDLE) ==
+		   le32_to_cpu(pSMB->hdr.Status.CifsError)) {
+			cifs_dbg(FYI, "Invalid handle on oplock break\n");
+			return true;
+		} else if (ERRbadfid ==
+		   le16_to_cpu(pSMB->hdr.Status.DosError.Error)) {
+			return true;
+		} else {
+			return false; /* on valid oplock brk we get "request" */
+		}
+	}
+	if (pSMB->hdr.WordCount != 8)
+		return false;
+
+	cifs_dbg(FYI, "oplock type 0x%x level 0x%x\n",
+		 pSMB->LockType, pSMB->OplockLevel);
+	if (!(pSMB->LockType & LOCKING_ANDX_OPLOCK_RELEASE))
+		return false;
+
+	/* If server is a channel, select the primary channel */
+	pserver = SERVER_IS_CHAN(srv) ? srv->primary_server : srv;
+
+	/* look up tcon based on tid & uid */
+	spin_lock(&cifs_tcp_ses_lock);
+	list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+		if (cifs_ses_exiting(ses))
+			continue;
+		list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+			if (tcon->tid != buf->Tid)
+				continue;
+
+			cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks);
+			spin_lock(&tcon->open_file_lock);
+			list_for_each_entry(netfile, &tcon->openFileList, tlist) {
+				if (pSMB->Fid != netfile->fid.netfid)
+					continue;
+
+				cifs_dbg(FYI, "file id match, oplock break\n");
+				pCifsInode = CIFS_I(d_inode(netfile->dentry));
+
+				set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK,
+					&pCifsInode->flags);
+
+				netfile->oplock_epoch = 0;
+				netfile->oplock_level = pSMB->OplockLevel;
+				netfile->oplock_break_cancelled = false;
+				cifs_queue_oplock_break(netfile);
+
+				spin_unlock(&tcon->open_file_lock);
+				spin_unlock(&cifs_tcp_ses_lock);
+				return true;
+			}
+			spin_unlock(&tcon->open_file_lock);
+			spin_unlock(&cifs_tcp_ses_lock);
+			cifs_dbg(FYI, "No matching file for oplock break\n");
+			return true;
+		}
+	}
+	spin_unlock(&cifs_tcp_ses_lock);
+	cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
+	return true;
+}
+
+/*
+ * calculate the size of the SMB message based on the fixed header
+ * portion, the number of word parameters and the data portion of the message
+ */
+unsigned int
+smbCalcSize(void *buf)
+{
+	struct smb_hdr *ptr = buf;
+	return (sizeof(struct smb_hdr) + (2 * ptr->WordCount) +
+		2 /* size of the bcc field */ + get_bcc(ptr));
+}