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, 147 insertions, 0 deletions

diff --git a/fs/nfsd/debugfs.c b/fs/nfsd/debugfs.c
new file mode 100644
index 000000000..386fd1c54
--- /dev/null
+++ b/fs/nfsd/debugfs.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/debugfs.h>
+
+#include "nfsd.h"
+
+static struct dentry *nfsd_top_dir __read_mostly;
+
+/*
+ * /sys/kernel/debug/nfsd/disable-splice-read
+ *
+ * Contents:
+ *   %0: NFS READ is allowed to use page splicing
+ *   %1: NFS READ uses only iov iter read
+ *
+ * The default value of this setting is zero (page splicing is
+ * allowed). This setting takes immediate effect for all NFS
+ * versions, all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_dsr_get(void *data, u64 *val)
+{
+	*val = nfsd_disable_splice_read ? 1 : 0;
+	return 0;
+}
+
+static int nfsd_dsr_set(void *data, u64 val)
+{
+	nfsd_disable_splice_read = (val > 0);
+	if (!nfsd_disable_splice_read) {
+		/*
+		 * Must use buffered I/O if splice_read is enabled.
+		 */
+		nfsd_io_cache_read = NFSD_IO_BUFFERED;
+	}
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_dsr_fops, nfsd_dsr_get, nfsd_dsr_set, "%llu\n");
+
+/*
+ * /sys/kernel/debug/nfsd/io_cache_read
+ *
+ * Contents:
+ *   %0: NFS READ will use buffered IO
+ *   %1: NFS READ will use dontcache (buffered IO w/ dropbehind)
+ *   %2: NFS READ will use direct IO
+ *
+ * This setting takes immediate effect for all NFS versions,
+ * all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_io_cache_read_get(void *data, u64 *val)
+{
+	*val = nfsd_io_cache_read;
+	return 0;
+}
+
+static int nfsd_io_cache_read_set(void *data, u64 val)
+{
+	int ret = 0;
+
+	switch (val) {
+	case NFSD_IO_BUFFERED:
+		nfsd_io_cache_read = NFSD_IO_BUFFERED;
+		break;
+	case NFSD_IO_DONTCACHE:
+	case NFSD_IO_DIRECT:
+		/*
+		 * Must disable splice_read when enabling
+		 * NFSD_IO_DONTCACHE.
+		 */
+		nfsd_disable_splice_read = true;
+		nfsd_io_cache_read = val;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_read_fops, nfsd_io_cache_read_get,
+			 nfsd_io_cache_read_set, "%llu\n");
+
+/*
+ * /sys/kernel/debug/nfsd/io_cache_write
+ *
+ * Contents:
+ *   %0: NFS WRITE will use buffered IO
+ *   %1: NFS WRITE will use dontcache (buffered IO w/ dropbehind)
+ *
+ * This setting takes immediate effect for all NFS versions,
+ * all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_io_cache_write_get(void *data, u64 *val)
+{
+	*val = nfsd_io_cache_write;
+	return 0;
+}
+
+static int nfsd_io_cache_write_set(void *data, u64 val)
+{
+	int ret = 0;
+
+	switch (val) {
+	case NFSD_IO_BUFFERED:
+	case NFSD_IO_DONTCACHE:
+	case NFSD_IO_DIRECT:
+		nfsd_io_cache_write = val;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_write_fops, nfsd_io_cache_write_get,
+			 nfsd_io_cache_write_set, "%llu\n");
+
+void nfsd_debugfs_exit(void)
+{
+	debugfs_remove_recursive(nfsd_top_dir);
+	nfsd_top_dir = NULL;
+}
+
+void nfsd_debugfs_init(void)
+{
+	nfsd_top_dir = debugfs_create_dir("nfsd", NULL);
+
+	debugfs_create_file("disable-splice-read", S_IWUSR | S_IRUGO,
+			    nfsd_top_dir, NULL, &nfsd_dsr_fops);
+
+	debugfs_create_file("io_cache_read", 0644, nfsd_top_dir, NULL,
+			    &nfsd_io_cache_read_fops);
+
+	debugfs_create_file("io_cache_write", 0644, nfsd_top_dir, NULL,
+			    &nfsd_io_cache_write_fops);
+#ifdef CONFIG_NFSD_V4
+	debugfs_create_bool("delegated_timestamps", 0644, nfsd_top_dir,
+			    &nfsd_delegts_enabled);
+#endif
+}