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, 97 insertions, 0 deletions

diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c
new file mode 100644
index 000000000..0b14d004a
--- /dev/null
+++ b/fs/ubifs/crypto.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "ubifs.h"
+
+static int ubifs_crypt_get_context(struct inode *inode, void *ctx, size_t len)
+{
+	return ubifs_xattr_get(inode, UBIFS_XATTR_NAME_ENCRYPTION_CONTEXT,
+			       ctx, len);
+}
+
+static int ubifs_crypt_set_context(struct inode *inode, const void *ctx,
+				   size_t len, void *fs_data)
+{
+	/*
+	 * Creating an encryption context is done unlocked since we
+	 * operate on a new inode which is not visible to other users
+	 * at this point. So, no need to check whether inode is locked.
+	 */
+	return ubifs_xattr_set(inode, UBIFS_XATTR_NAME_ENCRYPTION_CONTEXT,
+			       ctx, len, 0, false);
+}
+
+static bool ubifs_crypt_empty_dir(struct inode *inode)
+{
+	return ubifs_check_dir_empty(inode) == 0;
+}
+
+/**
+ * ubifs_encrypt - Encrypt data.
+ * @inode: inode which refers to the data node
+ * @dn: data node to encrypt
+ * @in_len: length of data to be compressed
+ * @out_len: allocated memory size for the data area of @dn
+ * @block: logical block number of the block
+ *
+ * This function encrypt a possibly-compressed data in the data node.
+ * The encrypted data length will store in @out_len.
+ */
+int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn,
+		  unsigned int in_len, unsigned int *out_len, int block)
+{
+	struct ubifs_info *c = inode->i_sb->s_fs_info;
+	void *p = &dn->data;
+	unsigned int pad_len = round_up(in_len, UBIFS_CIPHER_BLOCK_SIZE);
+	int err;
+
+	ubifs_assert(c, pad_len <= *out_len);
+	dn->compr_size = cpu_to_le16(in_len);
+
+	/* pad to full block cipher length */
+	if (pad_len != in_len)
+		memset(p + in_len, 0, pad_len - in_len);
+
+	err = fscrypt_encrypt_block_inplace(inode, virt_to_page(p), pad_len,
+					    offset_in_page(p), block);
+	if (err) {
+		ubifs_err(c, "fscrypt_encrypt_block_inplace() failed: %d", err);
+		return err;
+	}
+	*out_len = pad_len;
+
+	return 0;
+}
+
+int ubifs_decrypt(const struct inode *inode, struct ubifs_data_node *dn,
+		  unsigned int *out_len, int block)
+{
+	struct ubifs_info *c = inode->i_sb->s_fs_info;
+	int err;
+	unsigned int clen = le16_to_cpu(dn->compr_size);
+	unsigned int dlen = *out_len;
+
+	if (clen <= 0 || clen > UBIFS_BLOCK_SIZE || clen > dlen) {
+		ubifs_err(c, "bad compr_size: %i", clen);
+		return -EINVAL;
+	}
+
+	ubifs_assert(c, dlen <= UBIFS_BLOCK_SIZE);
+	err = fscrypt_decrypt_block_inplace(inode, virt_to_page(&dn->data),
+					    dlen, offset_in_page(&dn->data),
+					    block);
+	if (err) {
+		ubifs_err(c, "fscrypt_decrypt_block_inplace() failed: %d", err);
+		return err;
+	}
+	*out_len = clen;
+
+	return 0;
+}
+
+const struct fscrypt_operations ubifs_crypt_operations = {
+	.inode_info_offs	= (int)offsetof(struct ubifs_inode, i_crypt_info) -
+				  (int)offsetof(struct ubifs_inode, vfs_inode),
+	.legacy_key_prefix	= "ubifs:",
+	.get_context		= ubifs_crypt_get_context,
+	.set_context		= ubifs_crypt_set_context,
+	.empty_dir		= ubifs_crypt_empty_dir,
+};