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

3 files changed, 325 insertions, 0 deletions

diff --git a/drivers/tc/Makefile b/drivers/tc/Makefile
new file mode 100644
index 000000000..6cccaf1f6
--- /dev/null
+++ b/drivers/tc/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the linux kernel.
+#
+
+# Object file lists.
+
+obj-$(CONFIG_TC) += tc.o tc-driver.o
diff --git a/drivers/tc/tc-driver.c b/drivers/tc/tc-driver.c
new file mode 100644
index 000000000..2f6d14759
--- /dev/null
+++ b/drivers/tc/tc-driver.c
@@ -0,0 +1,109 @@
+/*
+ *	TURBOchannel driver services.
+ *
+ *	Copyright (c) 2005  James Simmons
+ *	Copyright (c) 2006  Maciej W. Rozycki
+ *
+ *	Loosely based on drivers/dio/dio-driver.c and
+ *	drivers/pci/pci-driver.c.
+ *
+ *	This file is subject to the terms and conditions of the GNU
+ *	General Public License.  See the file "COPYING" in the main
+ *	directory of this archive for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/tc.h>
+
+/**
+ * tc_register_driver - register a new TC driver
+ * @drv: the driver structure to register
+ *
+ * Adds the driver structure to the list of registered drivers
+ * Returns a negative value on error, otherwise 0.
+ * If no error occurred, the driver remains registered even if
+ * no device was claimed during registration.
+ */
+int tc_register_driver(struct tc_driver *tdrv)
+{
+	return driver_register(&tdrv->driver);
+}
+EXPORT_SYMBOL(tc_register_driver);
+
+/**
+ * tc_unregister_driver - unregister a TC driver
+ * @drv: the driver structure to unregister
+ *
+ * Deletes the driver structure from the list of registered TC drivers,
+ * gives it a chance to clean up by calling its remove() function for
+ * each device it was responsible for, and marks those devices as
+ * driverless.
+ */
+void tc_unregister_driver(struct tc_driver *tdrv)
+{
+	driver_unregister(&tdrv->driver);
+}
+EXPORT_SYMBOL(tc_unregister_driver);
+
+/**
+ * tc_match_device - tell if a TC device structure has a matching
+ *                   TC device ID structure
+ * @tdrv: the TC driver to earch for matching TC device ID strings
+ * @tdev: the TC device structure to match against
+ *
+ * Used by a driver to check whether a TC device present in the
+ * system is in its list of supported devices.  Returns the matching
+ * tc_device_id structure or %NULL if there is no match.
+ */
+static const struct tc_device_id *tc_match_device(const struct tc_driver *tdrv,
+						  struct tc_dev *tdev)
+{
+	const struct tc_device_id *id = tdrv->id_table;
+
+	if (id) {
+		while (id->name[0] || id->vendor[0]) {
+			if (strcmp(tdev->name, id->name) == 0 &&
+			    strcmp(tdev->vendor, id->vendor) == 0)
+				return id;
+			id++;
+		}
+	}
+	return NULL;
+}
+
+/**
+ * tc_bus_match - Tell if a device structure has a matching
+ *                TC device ID structure
+ * @dev: the device structure to match against
+ * @drv: the device driver to search for matching TC device ID strings
+ *
+ * Used by a driver to check whether a TC device present in the
+ * system is in its list of supported devices.  Returns 1 if there
+ * is a match or 0 otherwise.
+ */
+static int tc_bus_match(struct device *dev, const struct device_driver *drv)
+{
+	struct tc_dev *tdev = to_tc_dev(dev);
+	const struct tc_driver *tdrv = to_tc_driver(drv);
+	const struct tc_device_id *id;
+
+	id = tc_match_device(tdrv, tdev);
+	if (id)
+		return 1;
+
+	return 0;
+}
+
+const struct bus_type tc_bus_type = {
+	.name	= "tc",
+	.match	= tc_bus_match,
+};
+EXPORT_SYMBOL(tc_bus_type);
+
+static int __init tc_driver_init(void)
+{
+	return bus_register(&tc_bus_type);
+}
+
+postcore_initcall(tc_driver_init);
diff --git a/drivers/tc/tc.c b/drivers/tc/tc.c
new file mode 100644
index 000000000..ebc835cf1
--- /dev/null
+++ b/drivers/tc/tc.c
@@ -0,0 +1,208 @@
+/*
+ *	TURBOchannel bus services.
+ *
+ *	Copyright (c) Harald Koerfgen, 1998
+ *	Copyright (c) 2001, 2003, 2005, 2006, 2018  Maciej W. Rozycki
+ *	Copyright (c) 2005  James Simmons
+ *
+ *	This file is subject to the terms and conditions of the GNU
+ *	General Public License.  See the file "COPYING" in the main
+ *	directory of this archive for more details.
+ */
+#include <linux/compiler.h>
+#include <linux/dma-mapping.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/tc.h>
+#include <linux/types.h>
+
+#include <asm/io.h>
+
+static struct tc_bus tc_bus = {
+	.name = "TURBOchannel",
+};
+
+/*
+ * Probing for TURBOchannel modules.
+ */
+static void __init tc_bus_add_devices(struct tc_bus *tbus)
+{
+	resource_size_t slotsize = tbus->info.slot_size << 20;
+	resource_size_t extslotsize = tbus->ext_slot_size;
+	resource_size_t slotaddr;
+	resource_size_t extslotaddr;
+	resource_size_t devsize;
+	void __iomem *module;
+	struct tc_dev *tdev;
+	int i, slot, err;
+	u8 pattern[4];
+	long offset;
+
+	for (slot = 0; slot < tbus->num_tcslots; slot++) {
+		slotaddr = tbus->slot_base + slot * slotsize;
+		extslotaddr = tbus->ext_slot_base + slot * extslotsize;
+		module = ioremap(slotaddr, slotsize);
+		BUG_ON(!module);
+
+		offset = TC_OLDCARD;
+
+		err = 0;
+		err |= tc_preadb(pattern + 0, module + offset + TC_PATTERN0);
+		err |= tc_preadb(pattern + 1, module + offset + TC_PATTERN1);
+		err |= tc_preadb(pattern + 2, module + offset + TC_PATTERN2);
+		err |= tc_preadb(pattern + 3, module + offset + TC_PATTERN3);
+		if (err)
+			goto out_err;
+
+		if (pattern[0] != 0x55 || pattern[1] != 0x00 ||
+		    pattern[2] != 0xaa || pattern[3] != 0xff) {
+			offset = TC_NEWCARD;
+
+			err = 0;
+			err |= tc_preadb(pattern + 0,
+					 module + offset + TC_PATTERN0);
+			err |= tc_preadb(pattern + 1,
+					 module + offset + TC_PATTERN1);
+			err |= tc_preadb(pattern + 2,
+					 module + offset + TC_PATTERN2);
+			err |= tc_preadb(pattern + 3,
+					 module + offset + TC_PATTERN3);
+			if (err)
+				goto out_err;
+		}
+
+		if (pattern[0] != 0x55 || pattern[1] != 0x00 ||
+		    pattern[2] != 0xaa || pattern[3] != 0xff)
+			goto out_err;
+
+		/* Found a board, allocate it an entry in the list */
+		tdev = kzalloc_obj(*tdev);
+		if (!tdev) {
+			pr_err("tc%x: unable to allocate tc_dev\n", slot);
+			goto out_err;
+		}
+		dev_set_name(&tdev->dev, "tc%x", slot);
+		tdev->bus = tbus;
+		tdev->dev.parent = &tbus->dev;
+		tdev->dev.bus = &tc_bus_type;
+		tdev->slot = slot;
+
+		/* TURBOchannel has 34-bit DMA addressing (16GiB space). */
+		tdev->dma_mask = DMA_BIT_MASK(34);
+		tdev->dev.dma_mask = &tdev->dma_mask;
+		tdev->dev.coherent_dma_mask = DMA_BIT_MASK(34);
+
+		for (i = 0; i < 8; i++) {
+			tdev->firmware[i] =
+				readb(module + offset + TC_FIRM_VER + 4 * i);
+			tdev->vendor[i] =
+				readb(module + offset + TC_VENDOR + 4 * i);
+			tdev->name[i] =
+				readb(module + offset + TC_MODULE + 4 * i);
+		}
+		tdev->firmware[8] = 0;
+		tdev->vendor[8] = 0;
+		tdev->name[8] = 0;
+
+		pr_info("%s: %s %s %s\n", dev_name(&tdev->dev), tdev->vendor,
+			tdev->name, tdev->firmware);
+
+		devsize = readb(module + offset + TC_SLOT_SIZE);
+		devsize <<= 22;
+		if (devsize <= slotsize) {
+			tdev->resource.start = slotaddr;
+			tdev->resource.end = slotaddr + devsize - 1;
+		} else if (devsize <= extslotsize) {
+			tdev->resource.start = extslotaddr;
+			tdev->resource.end = extslotaddr + devsize - 1;
+		} else {
+			pr_err("%s: Cannot provide slot space "
+			       "(%ldMiB required, up to %ldMiB supported)\n",
+			       dev_name(&tdev->dev), (long)(devsize >> 20),
+			       (long)(max(slotsize, extslotsize) >> 20));
+			kfree(tdev);
+			goto out_err;
+		}
+		tdev->resource.name = tdev->name;
+		tdev->resource.flags = IORESOURCE_MEM;
+
+		tc_device_get_irq(tdev);
+
+		if (device_register(&tdev->dev)) {
+			put_device(&tdev->dev);
+			goto out_err;
+		}
+		list_add_tail(&tdev->node, &tbus->devices);
+
+out_err:
+		iounmap(module);
+	}
+}
+
+/*
+ * The main entry.
+ */
+static int __init tc_init(void)
+{
+	/* Initialize the TURBOchannel bus */
+	if (tc_bus_get_info(&tc_bus))
+		goto out_err;
+
+	INIT_LIST_HEAD(&tc_bus.devices);
+	dev_set_name(&tc_bus.dev, "tc");
+	if (device_register(&tc_bus.dev))
+		goto out_err_device;
+
+	if (tc_bus.info.slot_size) {
+		unsigned int tc_clock = tc_get_speed(&tc_bus) / 100000;
+
+		pr_info("tc: TURBOchannel rev. %d at %u.%u MHz "
+			"(with%s parity)\n", tc_bus.info.revision,
+			tc_clock / 10, tc_clock % 10,
+			tc_bus.info.parity ? "" : "out");
+
+		tc_bus.resource[0].start = tc_bus.slot_base;
+		tc_bus.resource[0].end = tc_bus.slot_base +
+					 (tc_bus.info.slot_size << 20) *
+					 tc_bus.num_tcslots - 1;
+		tc_bus.resource[0].name = tc_bus.name;
+		tc_bus.resource[0].flags = IORESOURCE_MEM;
+		if (request_resource(&iomem_resource,
+				     &tc_bus.resource[0]) < 0) {
+			pr_err("tc: Cannot reserve resource\n");
+			goto out_err_device;
+		}
+		if (tc_bus.ext_slot_size) {
+			tc_bus.resource[1].start = tc_bus.ext_slot_base;
+			tc_bus.resource[1].end = tc_bus.ext_slot_base +
+						 tc_bus.ext_slot_size *
+						 tc_bus.num_tcslots - 1;
+			tc_bus.resource[1].name = tc_bus.name;
+			tc_bus.resource[1].flags = IORESOURCE_MEM;
+			if (request_resource(&iomem_resource,
+					     &tc_bus.resource[1]) < 0) {
+				pr_err("tc: Cannot reserve resource\n");
+				goto out_err_resource;
+			}
+		}
+
+		tc_bus_add_devices(&tc_bus);
+	}
+
+	return 0;
+
+out_err_resource:
+	release_resource(&tc_bus.resource[0]);
+out_err_device:
+	put_device(&tc_bus.dev);
+out_err:
+	return 0;
+}
+
+subsys_initcall(tc_init);