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, 283 insertions, 0 deletions

diff --git a/drivers/mfd/janz-cmodio.c b/drivers/mfd/janz-cmodio.c
new file mode 100644
index 000000000..add3bc041
--- /dev/null
+++ b/drivers/mfd/janz-cmodio.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Janz CMOD-IO MODULbus Carrier Board PCI Driver
+ *
+ * Copyright (c) 2010 Ira W. Snyder <iws@ovro.caltech.edu>
+ *
+ * Lots of inspiration and code was copied from drivers/mfd/sm501.c
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/mfd/core.h>
+
+#include <linux/mfd/janz.h>
+
+#define DRV_NAME "janz-cmodio"
+
+/* Size of each MODULbus module in PCI BAR4 */
+#define CMODIO_MODULBUS_SIZE	0x200
+
+/* Maximum number of MODULbus modules on a CMOD-IO carrier board */
+#define CMODIO_MAX_MODULES	4
+
+/* Module Parameters */
+static unsigned int num_modules = CMODIO_MAX_MODULES;
+static char *modules[CMODIO_MAX_MODULES] = {
+	"empty", "empty", "empty", "empty",
+};
+
+module_param_array(modules, charp, &num_modules, S_IRUGO);
+MODULE_PARM_DESC(modules, "MODULbus modules attached to the carrier board");
+
+/* Unique Device Id */
+static unsigned int cmodio_id;
+
+struct cmodio_device {
+	/* Parent PCI device */
+	struct pci_dev *pdev;
+
+	/* PLX control registers */
+	struct janz_cmodio_onboard_regs __iomem *ctrl;
+
+	/* hex switch position */
+	u8 hex;
+
+	/* mfd-core API */
+	struct mfd_cell cells[CMODIO_MAX_MODULES];
+	struct resource resources[3 * CMODIO_MAX_MODULES];
+	struct janz_platform_data pdata[CMODIO_MAX_MODULES];
+};
+
+/*
+ * Subdevices using the mfd-core API
+ */
+
+static int cmodio_setup_subdevice(struct cmodio_device *priv,
+					    char *name, unsigned int devno,
+					    unsigned int modno)
+{
+	struct janz_platform_data *pdata;
+	struct mfd_cell *cell;
+	struct resource *res;
+	struct pci_dev *pci;
+
+	pci = priv->pdev;
+	cell = &priv->cells[devno];
+	res = &priv->resources[devno * 3];
+	pdata = &priv->pdata[devno];
+
+	cell->name = name;
+	cell->resources = res;
+	cell->num_resources = 3;
+
+	/* Setup the subdevice ID -- must be unique */
+	cell->id = cmodio_id++;
+
+	/* Add platform data */
+	pdata->modno = modno;
+	cell->platform_data = pdata;
+	cell->pdata_size = sizeof(*pdata);
+
+	/* MODULbus registers -- PCI BAR3 is big-endian MODULbus access */
+	res->flags = IORESOURCE_MEM;
+	res->parent = &pci->resource[3];
+	res->start = pci->resource[3].start + (CMODIO_MODULBUS_SIZE * modno);
+	res->end = res->start + CMODIO_MODULBUS_SIZE - 1;
+	res++;
+
+	/* PLX Control Registers -- PCI BAR4 is interrupt and other registers */
+	res->flags = IORESOURCE_MEM;
+	res->parent = &pci->resource[4];
+	res->start = pci->resource[4].start;
+	res->end = pci->resource[4].end;
+	res++;
+
+	/*
+	 * IRQ
+	 *
+	 * The start and end fields are used as an offset to the irq_base
+	 * parameter passed into the mfd_add_devices() function call. All
+	 * devices share the same IRQ.
+	 */
+	res->flags = IORESOURCE_IRQ;
+	res->parent = NULL;
+	res->start = 0;
+	res->end = 0;
+	res++;
+
+	return 0;
+}
+
+/* Probe each submodule using kernel parameters */
+static int cmodio_probe_submodules(struct cmodio_device *priv)
+{
+	struct pci_dev *pdev = priv->pdev;
+	unsigned int num_probed = 0;
+	char *name;
+	int i;
+
+	for (i = 0; i < num_modules; i++) {
+		name = modules[i];
+		if (!strcmp(name, "") || !strcmp(name, "empty"))
+			continue;
+
+		dev_dbg(&priv->pdev->dev, "MODULbus %d: name %s\n", i, name);
+		cmodio_setup_subdevice(priv, name, num_probed, i);
+		num_probed++;
+	}
+
+	/* print an error message if no modules were probed */
+	if (num_probed == 0) {
+		dev_err(&priv->pdev->dev, "no MODULbus modules specified, "
+					  "please set the ``modules'' kernel "
+					  "parameter according to your "
+					  "hardware configuration\n");
+		return -ENODEV;
+	}
+
+	return mfd_add_devices(&pdev->dev, 0, priv->cells,
+			       num_probed, NULL, pdev->irq, NULL);
+}
+
+/*
+ * SYSFS Attributes
+ */
+
+static ssize_t modulbus_number_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct cmodio_device *priv = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%x\n", priv->hex);
+}
+
+static DEVICE_ATTR_RO(modulbus_number);
+
+static struct attribute *cmodio_sysfs_attrs[] = {
+	&dev_attr_modulbus_number.attr,
+	NULL,
+};
+
+static const struct attribute_group cmodio_sysfs_attr_group = {
+	.attrs = cmodio_sysfs_attrs,
+};
+
+/*
+ * PCI Driver
+ */
+
+static int cmodio_pci_probe(struct pci_dev *dev,
+				      const struct pci_device_id *id)
+{
+	struct cmodio_device *priv;
+	int ret;
+
+	priv = devm_kzalloc(&dev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	pci_set_drvdata(dev, priv);
+	priv->pdev = dev;
+
+	/* Hardware Initialization */
+	ret = pci_enable_device(dev);
+	if (ret) {
+		dev_err(&dev->dev, "unable to enable device\n");
+		return ret;
+	}
+
+	pci_set_master(dev);
+	ret = pci_request_regions(dev, DRV_NAME);
+	if (ret) {
+		dev_err(&dev->dev, "unable to request regions\n");
+		goto out_pci_disable_device;
+	}
+
+	/* Onboard configuration registers */
+	priv->ctrl = pci_ioremap_bar(dev, 4);
+	if (!priv->ctrl) {
+		dev_err(&dev->dev, "unable to remap onboard regs\n");
+		ret = -ENOMEM;
+		goto out_pci_release_regions;
+	}
+
+	/* Read the hex switch on the carrier board */
+	priv->hex = ioread8(&priv->ctrl->int_enable);
+
+	/* Add the MODULbus number (hex switch value) to the device's sysfs */
+	ret = sysfs_create_group(&dev->dev.kobj, &cmodio_sysfs_attr_group);
+	if (ret) {
+		dev_err(&dev->dev, "unable to create sysfs attributes\n");
+		goto out_unmap_ctrl;
+	}
+
+	/*
+	 * Disable all interrupt lines, each submodule will enable its
+	 * own interrupt line if needed
+	 */
+	iowrite8(0xf, &priv->ctrl->int_disable);
+
+	/* Register drivers for all submodules */
+	ret = cmodio_probe_submodules(priv);
+	if (ret) {
+		dev_err(&dev->dev, "unable to probe submodules\n");
+		goto out_sysfs_remove_group;
+	}
+
+	return 0;
+
+out_sysfs_remove_group:
+	sysfs_remove_group(&dev->dev.kobj, &cmodio_sysfs_attr_group);
+out_unmap_ctrl:
+	iounmap(priv->ctrl);
+out_pci_release_regions:
+	pci_release_regions(dev);
+out_pci_disable_device:
+	pci_disable_device(dev);
+
+	return ret;
+}
+
+static void cmodio_pci_remove(struct pci_dev *dev)
+{
+	struct cmodio_device *priv = pci_get_drvdata(dev);
+
+	mfd_remove_devices(&dev->dev);
+	sysfs_remove_group(&dev->dev.kobj, &cmodio_sysfs_attr_group);
+	iounmap(priv->ctrl);
+	pci_release_regions(dev);
+	pci_disable_device(dev);
+}
+
+#define PCI_VENDOR_ID_JANZ		0x13c3
+
+/* The list of devices that this module will support */
+static const struct pci_device_id cmodio_pci_ids[] = {
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_JANZ, 0x0101 },
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050, PCI_VENDOR_ID_JANZ, 0x0100 },
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_JANZ, 0x0201 },
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_JANZ, 0x0202 },
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050, PCI_VENDOR_ID_JANZ, 0x0201 },
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050, PCI_VENDOR_ID_JANZ, 0x0202 },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, cmodio_pci_ids);
+
+static struct pci_driver cmodio_pci_driver = {
+	.name     = DRV_NAME,
+	.id_table = cmodio_pci_ids,
+	.probe    = cmodio_pci_probe,
+	.remove   = cmodio_pci_remove,
+};
+
+module_pci_driver(cmodio_pci_driver);
+
+MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>");
+MODULE_DESCRIPTION("Janz CMOD-IO PCI MODULbus Carrier Board Driver");
+MODULE_LICENSE("GPL");