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, 204 insertions, 0 deletions

diff --git a/fs/nfs/io.c b/fs/nfs/io.c
new file mode 100644
index 000000000..2faf2003f
--- /dev/null
+++ b/fs/nfs/io.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016 Trond Myklebust
+ *
+ * I/O and data path helper functionality.
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/rwsem.h>
+#include <linux/fs.h>
+#include <linux/nfs_fs.h>
+
+#include "internal.h"
+
+/**
+ * nfs_start_io_read - declare the file is being used for buffered reads
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ * On exit, the function ensures that the NFS_INO_ODIRECT flag is unset,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that buffered read operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas direct I/O
+ * operations need to wait to grab an exclusive lock in order to set
+ * NFS_INO_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
+ */
+int
+nfs_start_io_read(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	int err;
+
+	/* Be an optimist! */
+	err = down_read_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	err = down_write_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+	nfs_file_block_o_direct(nfsi);
+	downgrade_write(&inode->i_rwsem);
+
+	return 0;
+}
+
+/**
+ * nfs_end_io_read - declare that the buffered read operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void
+nfs_end_io_read(struct inode *inode)
+{
+	up_read(&inode->i_rwsem);
+}
+
+/**
+ * nfs_start_io_write - declare the file is being used for buffered writes
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ */
+int
+nfs_start_io_write(struct inode *inode)
+{
+	int err;
+
+	err = down_write_killable(&inode->i_rwsem);
+	if (!err)
+		nfs_file_block_o_direct(NFS_I(inode));
+	return err;
+}
+EXPORT_SYMBOL_GPL(nfs_start_io_write);
+
+/**
+ * nfs_end_io_write - declare that the buffered write operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered write operation is done, and release the
+ * lock on inode->i_rwsem.
+ */
+void
+nfs_end_io_write(struct inode *inode)
+{
+	up_write(&inode->i_rwsem);
+}
+EXPORT_SYMBOL_GPL(nfs_end_io_write);
+
+/* Call with exclusively locked inode->i_rwsem */
+static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode)
+{
+	if (!test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+		set_bit(NFS_INO_ODIRECT, &nfsi->flags);
+		nfs_sync_mapping(inode->i_mapping);
+	}
+}
+
+static int nfs_block_buffered_nowait(struct nfs_inode *nfsi, struct inode *inode)
+{
+	if (!test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+		if (inode->i_mapping->nrpages != 0)
+			return 1;
+		set_bit(NFS_INO_ODIRECT, &nfsi->flags);
+	}
+	return 0;
+}
+
+/**
+ * nfs_start_io_direct - declare the file is being used for direct i/o
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is about to start, and ensure
+ * that we block all buffered I/O.
+ * On exit, the function ensures that the NFS_INO_ODIRECT flag is set,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that direct I/O operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas buffered I/O
+ * operations need to wait to grab an exclusive lock in order to clear
+ * NFS_INO_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
+ */
+int
+nfs_start_io_direct(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	int err;
+
+	/* Be an optimist! */
+	err = down_read_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) != 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	err = down_write_killable(&inode->i_rwsem);
+	if (err)
+		return err;
+	nfs_block_buffered(nfsi, inode);
+	downgrade_write(&inode->i_rwsem);
+
+	return 0;
+}
+
+/**
+ * nfs_start_io_direct_nowait - non-blocking variant of nfs_start_io_direct()
+ * @inode: file inode
+ *
+ * Try to declare that a direct I/O operation is about to start without
+ * blocking.
+ * Ensure all buffered I/O is blocked.
+ * If this could not be done without blocking then returns -EAGAIN.
+ */
+int
+nfs_start_io_direct_nowait(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	if (!down_read_trylock(&inode->i_rwsem))
+		return -EAGAIN;
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags))
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path: try to flip NFS_INO_ODIRECT without blocking. */
+	if (!down_write_trylock(&inode->i_rwsem))
+		return -EAGAIN;
+	if (nfs_block_buffered_nowait(nfsi, inode)) {
+		up_write(&inode->i_rwsem);
+		return -EAGAIN;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+
+/**
+ * nfs_end_io_direct - declare that the direct i/o operation is done
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void
+nfs_end_io_direct(struct inode *inode)
+{
+	up_read(&inode->i_rwsem);
+}