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, 99 insertions, 0 deletions

diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
new file mode 100644
index 000000000..bee93066a
--- /dev/null
+++ b/drivers/dax/pmem.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */
+#include <linux/memremap.h>
+#include <linux/module.h>
+#include "../nvdimm/pfn.h"
+#include "../nvdimm/nd.h"
+#include "bus.h"
+
+static struct dev_dax *__dax_pmem_probe(struct device *dev)
+{
+	struct range range;
+	int rc, id, region_id;
+	resource_size_t offset;
+	struct nd_pfn_sb *pfn_sb;
+	struct dev_dax_data data;
+	struct nd_namespace_io *nsio;
+	struct dax_region *dax_region;
+	struct dev_pagemap pgmap = { };
+	struct nd_namespace_common *ndns;
+	struct nd_dax *nd_dax = to_nd_dax(dev);
+	struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+
+	ndns = nvdimm_namespace_common_probe(dev);
+	if (IS_ERR(ndns))
+		return ERR_CAST(ndns);
+
+	/* parse the 'pfn' info block via ->rw_bytes */
+	rc = devm_namespace_enable(dev, ndns, nd_info_block_reserve());
+	if (rc)
+		return ERR_PTR(rc);
+	rc = nvdimm_setup_pfn(nd_pfn, &pgmap);
+	if (rc)
+		return ERR_PTR(rc);
+	devm_namespace_disable(dev, ndns);
+
+	/* reserve the metadata area, device-dax will reserve the data */
+	pfn_sb = nd_pfn->pfn_sb;
+	offset = le64_to_cpu(pfn_sb->dataoff);
+	nsio = to_nd_namespace_io(&ndns->dev);
+	if (!devm_request_mem_region(dev, nsio->res.start, offset,
+				dev_name(&ndns->dev))) {
+		dev_warn(dev, "could not reserve metadata\n");
+		return ERR_PTR(-EBUSY);
+	}
+
+	rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", &region_id, &id);
+	if (rc != 2)
+		return ERR_PTR(-EINVAL);
+
+	/* adjust the dax_region range to the start of data */
+	range = pgmap.range;
+	range.start += offset;
+	dax_region = alloc_dax_region(dev, region_id, &range,
+			nd_region->target_node, le32_to_cpu(pfn_sb->align),
+			IORESOURCE_DAX_STATIC);
+	if (!dax_region)
+		return ERR_PTR(-ENOMEM);
+
+	data = (struct dev_dax_data) {
+		.dax_region = dax_region,
+		.id = id,
+		.pgmap = &pgmap,
+		.size = range_len(&range),
+		.memmap_on_memory = false,
+	};
+
+	return devm_create_dev_dax(&data);
+}
+
+static int dax_pmem_probe(struct device *dev)
+{
+	return PTR_ERR_OR_ZERO(__dax_pmem_probe(dev));
+}
+
+static struct nd_device_driver dax_pmem_driver = {
+	.probe = dax_pmem_probe,
+	.drv = {
+		.name = "dax_pmem",
+	},
+	.type = ND_DRIVER_DAX_PMEM,
+};
+
+static int __init dax_pmem_init(void)
+{
+	return nd_driver_register(&dax_pmem_driver);
+}
+module_init(dax_pmem_init);
+
+static void __exit dax_pmem_exit(void)
+{
+	driver_unregister(&dax_pmem_driver.drv);
+}
+module_exit(dax_pmem_exit);
+
+MODULE_DESCRIPTION("PMEM DAX: direct access to persistent memory");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM);