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, 148 insertions, 0 deletions

diff --git a/drivers/net/mdio/mdio-thunder.c b/drivers/net/mdio/mdio-thunder.c
new file mode 100644
index 000000000..a3047f725
--- /dev/null
+++ b/drivers/net/mdio/mdio-thunder.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2009-2016 Cavium, Inc.
+ */
+
+#include <linux/acpi.h>
+#include <linux/gfp.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_mdio.h>
+#include <linux/pci.h>
+#include <linux/phy.h>
+
+#include "mdio-cavium.h"
+
+struct thunder_mdiobus_nexus {
+	void __iomem *bar0;
+	struct cavium_mdiobus *buses[4];
+};
+
+static int thunder_mdiobus_pci_probe(struct pci_dev *pdev,
+				     const struct pci_device_id *ent)
+{
+	struct device_node *node;
+	struct thunder_mdiobus_nexus *nexus;
+	int err;
+	int i;
+
+	nexus = devm_kzalloc(&pdev->dev, sizeof(*nexus), GFP_KERNEL);
+	if (!nexus)
+		return -ENOMEM;
+
+	pci_set_drvdata(pdev, nexus);
+
+	err = pcim_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to enable PCI device\n");
+		pci_set_drvdata(pdev, NULL);
+		return err;
+	}
+
+	err = pcim_request_all_regions(pdev, KBUILD_MODNAME);
+	if (err) {
+		dev_err(&pdev->dev, "pcim_request_all_regions failed\n");
+		goto err_disable_device;
+	}
+
+	nexus->bar0 = pcim_iomap(pdev, 0, pci_resource_len(pdev, 0));
+	if (!nexus->bar0) {
+		err = -ENOMEM;
+		goto err_disable_device;
+	}
+
+	i = 0;
+	device_for_each_child_node_scoped(&pdev->dev, fwn) {
+		struct resource r;
+		struct mii_bus *mii_bus;
+		struct cavium_mdiobus *bus;
+		union cvmx_smix_en smi_en;
+
+		/* If it is not an OF node we cannot handle it yet, so
+		 * exit the loop.
+		 */
+		node = to_of_node(fwn);
+		if (!node)
+			break;
+
+		err = of_address_to_resource(node, 0, &r);
+		if (err) {
+			dev_err(&pdev->dev,
+				"Couldn't translate address for \"%pOFn\"\n",
+				node);
+			break;
+		}
+
+		mii_bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*bus));
+		if (!mii_bus)
+			break;
+		bus = mii_bus->priv;
+		bus->mii_bus = mii_bus;
+
+		nexus->buses[i] = bus;
+		i++;
+
+		bus->register_base = nexus->bar0 +
+			r.start - pci_resource_start(pdev, 0);
+
+		smi_en.u64 = 0;
+		smi_en.s.en = 1;
+		oct_mdio_writeq(smi_en.u64, bus->register_base + SMI_EN);
+		bus->mii_bus->name = KBUILD_MODNAME;
+		snprintf(bus->mii_bus->id, MII_BUS_ID_SIZE, "%llx", r.start);
+		bus->mii_bus->parent = &pdev->dev;
+		bus->mii_bus->read = cavium_mdiobus_read_c22;
+		bus->mii_bus->write = cavium_mdiobus_write_c22;
+		bus->mii_bus->read_c45 = cavium_mdiobus_read_c45;
+		bus->mii_bus->write_c45 = cavium_mdiobus_write_c45;
+
+		err = of_mdiobus_register(bus->mii_bus, node);
+		if (err)
+			dev_err(&pdev->dev, "of_mdiobus_register failed\n");
+
+		dev_info(&pdev->dev, "Added bus at %llx\n", r.start);
+		if (i >= ARRAY_SIZE(nexus->buses))
+			break;
+	}
+	return 0;
+
+err_disable_device:
+	pci_set_drvdata(pdev, NULL);
+	return err;
+}
+
+static void thunder_mdiobus_pci_remove(struct pci_dev *pdev)
+{
+	int i;
+	struct thunder_mdiobus_nexus *nexus = pci_get_drvdata(pdev);
+
+	for (i = 0; i < ARRAY_SIZE(nexus->buses); i++) {
+		struct cavium_mdiobus *bus = nexus->buses[i];
+
+		if (!bus)
+			continue;
+
+		mdiobus_unregister(bus->mii_bus);
+		oct_mdio_writeq(0, bus->register_base + SMI_EN);
+	}
+	pci_set_drvdata(pdev, NULL);
+}
+
+static const struct pci_device_id thunder_mdiobus_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, 0xa02b) },
+	{ 0, } /* End of table. */
+};
+MODULE_DEVICE_TABLE(pci, thunder_mdiobus_id_table);
+
+static struct pci_driver thunder_mdiobus_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = thunder_mdiobus_id_table,
+	.probe = thunder_mdiobus_pci_probe,
+	.remove = thunder_mdiobus_pci_remove,
+};
+
+module_pci_driver(thunder_mdiobus_driver);
+
+MODULE_DESCRIPTION("Cavium ThunderX MDIO bus driver");
+MODULE_LICENSE("GPL v2");