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, 164 insertions, 0 deletions

diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
new file mode 100644
index 000000000..67e492f4b
--- /dev/null
+++ b/fs/ocfs2/sysfile.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * sysfile.c
+ *
+ * Initialize, read, write, etc. system files.
+ *
+ * Copyright (C) 2002, 2004 Oracle.  All rights reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <linux/highmem.h>
+
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+
+#include "alloc.h"
+#include "dir.h"
+#include "inode.h"
+#include "journal.h"
+#include "sysfile.h"
+
+#include "buffer_head_io.h"
+
+static struct inode * _ocfs2_get_system_file_inode(struct ocfs2_super *osb,
+						   int type,
+						   u32 slot);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key ocfs2_sysfile_cluster_lock_key[NUM_SYSTEM_INODES];
+#endif
+
+static inline int is_global_system_inode(int type)
+{
+	return type >= OCFS2_FIRST_ONLINE_SYSTEM_INODE &&
+		type <= OCFS2_LAST_GLOBAL_SYSTEM_INODE;
+}
+
+static struct inode **get_local_system_inode(struct ocfs2_super *osb,
+					     int type,
+					     u32 slot)
+{
+	int index;
+	struct inode **local_system_inodes, **free = NULL;
+
+	BUG_ON(slot == OCFS2_INVALID_SLOT);
+	BUG_ON(type < OCFS2_FIRST_LOCAL_SYSTEM_INODE ||
+	       type > OCFS2_LAST_LOCAL_SYSTEM_INODE);
+
+	spin_lock(&osb->osb_lock);
+	local_system_inodes = osb->local_system_inodes;
+	spin_unlock(&osb->osb_lock);
+
+	if (unlikely(!local_system_inodes)) {
+		local_system_inodes =
+			kzalloc(array3_size(sizeof(struct inode *),
+					    NUM_LOCAL_SYSTEM_INODES,
+					    osb->max_slots),
+				GFP_NOFS);
+		if (!local_system_inodes) {
+			mlog_errno(-ENOMEM);
+			/*
+			 * return NULL here so that ocfs2_get_sytem_file_inodes
+			 * will try to create an inode and use it. We will try
+			 * to initialize local_system_inodes next time.
+			 */
+			return NULL;
+		}
+
+		spin_lock(&osb->osb_lock);
+		if (osb->local_system_inodes) {
+			/* Someone has initialized it for us. */
+			free = local_system_inodes;
+			local_system_inodes = osb->local_system_inodes;
+		} else
+			osb->local_system_inodes = local_system_inodes;
+		spin_unlock(&osb->osb_lock);
+		kfree(free);
+	}
+
+	index = (slot * NUM_LOCAL_SYSTEM_INODES) +
+		(type - OCFS2_FIRST_LOCAL_SYSTEM_INODE);
+
+	return &local_system_inodes[index];
+}
+
+struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
+					  int type,
+					  u32 slot)
+{
+	struct inode *inode = NULL;
+	struct inode **arr = NULL;
+
+	/* avoid the lookup if cached in local system file array */
+	if (is_global_system_inode(type)) {
+		arr = &(osb->global_system_inodes[type]);
+	} else
+		arr = get_local_system_inode(osb, type, slot);
+
+	if (arr && ((inode = *arr) != NULL)) {
+		/* get a ref in addition to the array ref */
+		inode = igrab(inode);
+		BUG_ON(!inode);
+
+		return inode;
+	}
+
+	/* this gets one ref thru iget */
+	inode = _ocfs2_get_system_file_inode(osb, type, slot);
+
+	/* add one more if putting into array for first time */
+	if (inode && arr && !*arr && !cmpxchg(&(*arr), NULL, inode)) {
+		inode = igrab(inode);
+		BUG_ON(!inode);
+	}
+	return inode;
+}
+
+static struct inode * _ocfs2_get_system_file_inode(struct ocfs2_super *osb,
+						   int type,
+						   u32 slot)
+{
+	char namebuf[40];
+	struct inode *inode = NULL;
+	u64 blkno;
+	int len, status = 0;
+
+	len = ocfs2_sprintf_system_inode_name(namebuf,
+					      sizeof(namebuf),
+					      type, slot);
+
+	status = ocfs2_lookup_ino_from_name(osb->sys_root_inode,
+					    namebuf, len, &blkno);
+	if (status < 0) {
+		goto bail;
+	}
+
+	inode = ocfs2_iget(osb, blkno, OCFS2_FI_FLAG_SYSFILE, type);
+	if (IS_ERR(inode)) {
+		mlog_errno(PTR_ERR(inode));
+		inode = NULL;
+		goto bail;
+	}
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (type == LOCAL_USER_QUOTA_SYSTEM_INODE ||
+	    type == LOCAL_GROUP_QUOTA_SYSTEM_INODE ||
+	    type == JOURNAL_SYSTEM_INODE) {
+		/* Ignore inode lock on these inodes as the lock does not
+		 * really belong to any process and lockdep cannot handle
+		 * that */
+		OCFS2_I(inode)->ip_inode_lockres.l_lockdep_map.key = NULL;
+	} else {
+		lockdep_init_map(&OCFS2_I(inode)->ip_inode_lockres.
+								l_lockdep_map,
+				 ocfs2_system_inodes[type].si_name,
+				 &ocfs2_sysfile_cluster_lock_key[type], 0);
+	}
+#endif
+bail:
+
+	return inode;
+}
+