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, 146 insertions, 0 deletions

diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
new file mode 100644
index 000000000..1646bbee2
--- /dev/null
+++ b/fs/squashfs/lz4_wrapper.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2013, 2014
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ */
+
+#include <linux/bio.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/lz4.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs.h"
+#include "decompressor.h"
+#include "page_actor.h"
+
+#define LZ4_LEGACY	1
+
+struct lz4_comp_opts {
+	__le32 version;
+	__le32 flags;
+};
+
+struct squashfs_lz4 {
+	void *input;
+	void *output;
+};
+
+
+static void *lz4_comp_opts(struct squashfs_sb_info *msblk,
+	void *buff, int len)
+{
+	struct lz4_comp_opts *comp_opts = buff;
+
+	/* LZ4 compressed filesystems always have compression options */
+	if (comp_opts == NULL || len < sizeof(*comp_opts))
+		return ERR_PTR(-EIO);
+
+	if (le32_to_cpu(comp_opts->version) != LZ4_LEGACY) {
+		/* LZ4 format currently used by the kernel is the 'legacy'
+		 * format */
+		ERROR("Unknown LZ4 version\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return NULL;
+}
+
+
+static void *lz4_init(struct squashfs_sb_info *msblk, void *buff)
+{
+	int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE);
+	struct squashfs_lz4 *stream;
+
+	stream = kzalloc_obj(*stream);
+	if (stream == NULL)
+		goto failed;
+	stream->input = vmalloc(block_size);
+	if (stream->input == NULL)
+		goto failed2;
+	stream->output = vmalloc(block_size);
+	if (stream->output == NULL)
+		goto failed3;
+
+	return stream;
+
+failed3:
+	vfree(stream->input);
+failed2:
+	kfree(stream);
+failed:
+	ERROR("Failed to initialise LZ4 decompressor\n");
+	return ERR_PTR(-ENOMEM);
+}
+
+
+static void lz4_free(void *strm)
+{
+	struct squashfs_lz4 *stream = strm;
+
+	if (stream) {
+		vfree(stream->input);
+		vfree(stream->output);
+	}
+	kfree(stream);
+}
+
+
+static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
+	struct bio *bio, int offset, int length,
+	struct squashfs_page_actor *output)
+{
+	struct bvec_iter_all iter_all = {};
+	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct squashfs_lz4 *stream = strm;
+	void *buff = stream->input, *data;
+	int bytes = length, res;
+
+	while (bio_next_segment(bio, &iter_all)) {
+		int avail = min(bytes, ((int)bvec->bv_len) - offset);
+
+		data = bvec_virt(bvec);
+		memcpy(buff, data + offset, avail);
+		buff += avail;
+		bytes -= avail;
+		offset = 0;
+	}
+
+	res = LZ4_decompress_safe(stream->input, stream->output,
+		length, output->length);
+
+	if (res < 0)
+		return -EIO;
+
+	bytes = res;
+	data = squashfs_first_page(output);
+	buff = stream->output;
+	while (data) {
+		if (bytes <= PAGE_SIZE) {
+			if (!IS_ERR(data))
+				memcpy(data, buff, bytes);
+			break;
+		}
+		if (!IS_ERR(data))
+			memcpy(data, buff, PAGE_SIZE);
+		buff += PAGE_SIZE;
+		bytes -= PAGE_SIZE;
+		data = squashfs_next_page(output);
+	}
+	squashfs_finish_page(output);
+
+	return res;
+}
+
+const struct squashfs_decompressor squashfs_lz4_comp_ops = {
+	.init = lz4_init,
+	.comp_opts = lz4_comp_opts,
+	.free = lz4_free,
+	.decompress = lz4_uncompress,
+	.id = LZ4_COMPRESSION,
+	.name = "lz4",
+	.alloc_buffer = 0,
+	.supported = 1
+};