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, 180 insertions, 0 deletions

diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c
new file mode 100644
index 000000000..62972f0ff
--- /dev/null
+++ b/fs/squashfs/export.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * export.c
+ */
+
+/*
+ * This file implements code to make Squashfs filesystems exportable (NFS etc.)
+ *
+ * The export code uses an inode lookup table to map inode numbers passed in
+ * filehandles to an inode location on disk.  This table is stored compressed
+ * into metadata blocks.  A second index table is used to locate these.  This
+ * second index table for speed of access (and because it is small) is read at
+ * mount time and cached in memory.
+ *
+ * The inode lookup table is used only by the export code, inode disk
+ * locations are directly encoded in directories, enabling direct access
+ * without an intermediate lookup for all operations except the export ops.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/dcache.h>
+#include <linux/exportfs.h>
+#include <linux/slab.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/*
+ * Look-up inode number (ino) in table, returning the inode location.
+ */
+static long long squashfs_inode_lookup(struct super_block *sb, int ino_num)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	int blk = SQUASHFS_LOOKUP_BLOCK(ino_num - 1);
+	int offset = SQUASHFS_LOOKUP_BLOCK_OFFSET(ino_num - 1);
+	u64 start;
+	__le64 ino;
+	int err;
+
+	TRACE("Entered squashfs_inode_lookup, inode_number = %d\n", ino_num);
+
+	if (ino_num == 0 || (ino_num - 1) >= msblk->inodes)
+		return -EINVAL;
+
+	start = le64_to_cpu(msblk->inode_lookup_table[blk]);
+
+	err = squashfs_read_metadata(sb, &ino, &start, &offset, sizeof(ino));
+	if (err < 0)
+		return err;
+
+	TRACE("squashfs_inode_lookup, inode = 0x%llx\n",
+		(u64) le64_to_cpu(ino));
+
+	return le64_to_cpu(ino);
+}
+
+
+static struct dentry *squashfs_export_iget(struct super_block *sb,
+	unsigned int ino_num)
+{
+	long long ino;
+	struct dentry *dentry = ERR_PTR(-ENOENT);
+
+	TRACE("Entered squashfs_export_iget\n");
+
+	ino = squashfs_inode_lookup(sb, ino_num);
+	if (ino >= 0)
+		dentry = d_obtain_alias(squashfs_iget(sb, ino, ino_num));
+
+	return dentry;
+}
+
+
+static struct dentry *squashfs_fh_to_dentry(struct super_block *sb,
+		struct fid *fid, int fh_len, int fh_type)
+{
+	if ((fh_type != FILEID_INO32_GEN && fh_type != FILEID_INO32_GEN_PARENT)
+			|| fh_len < 2)
+		return NULL;
+
+	return squashfs_export_iget(sb, fid->i32.ino);
+}
+
+
+static struct dentry *squashfs_fh_to_parent(struct super_block *sb,
+		struct fid *fid, int fh_len, int fh_type)
+{
+	if (fh_type != FILEID_INO32_GEN_PARENT || fh_len < 4)
+		return NULL;
+
+	return squashfs_export_iget(sb, fid->i32.parent_ino);
+}
+
+
+static struct dentry *squashfs_get_parent(struct dentry *child)
+{
+	struct inode *inode = d_inode(child);
+	unsigned int parent_ino = squashfs_i(inode)->parent;
+
+	return squashfs_export_iget(inode->i_sb, parent_ino);
+}
+
+
+/*
+ * Read uncompressed inode lookup table indexes off disk into memory
+ */
+__le64 *squashfs_read_inode_lookup_table(struct super_block *sb,
+		u64 lookup_table_start, u64 next_table, unsigned int inodes)
+{
+	unsigned int length = SQUASHFS_LOOKUP_BLOCK_BYTES(inodes);
+	unsigned int indexes = SQUASHFS_LOOKUP_BLOCKS(inodes);
+	int n;
+	__le64 *table;
+	u64 start, end;
+
+	TRACE("In read_inode_lookup_table, length %d\n", length);
+
+	/* Sanity check values */
+
+	/* there should always be at least one inode */
+	if (inodes == 0)
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * The computed size of the lookup table (length bytes) should exactly
+	 * match the table start and end points
+	 */
+	if (length != (next_table - lookup_table_start))
+		return ERR_PTR(-EINVAL);
+
+	table = squashfs_read_table(sb, lookup_table_start, length);
+	if (IS_ERR(table))
+		return table;
+
+	/*
+	 * table0], table[1], ... table[indexes - 1] store the locations
+	 * of the compressed inode lookup blocks.  Each entry should be
+	 * less than the next (i.e. table[0] < table[1]), and the difference
+	 * between them should be SQUASHFS_METADATA_SIZE or less.
+	 * table[indexes - 1] should  be less than lookup_table_start, and
+	 * again the difference should be SQUASHFS_METADATA_SIZE or less
+	 */
+	for (n = 0; n < (indexes - 1); n++) {
+		start = le64_to_cpu(table[n]);
+		end = le64_to_cpu(table[n + 1]);
+
+		if (start >= end
+		    || (end - start) >
+		    (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
+			kfree(table);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	start = le64_to_cpu(table[indexes - 1]);
+	if (start >= lookup_table_start ||
+	    (lookup_table_start - start) >
+	    (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
+		kfree(table);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return table;
+}
+
+
+const struct export_operations squashfs_export_ops = {
+	.encode_fh = generic_encode_ino32_fh,
+	.fh_to_dentry = squashfs_fh_to_dentry,
+	.fh_to_parent = squashfs_fh_to_parent,
+	.get_parent = squashfs_get_parent
+};