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, 276 insertions, 0 deletions

diff --git a/drivers/bcma/host_soc.c b/drivers/bcma/host_soc.c
new file mode 100644
index 000000000..20b1816c5
--- /dev/null
+++ b/drivers/bcma/host_soc.c
@@ -0,0 +1,276 @@
+/*
+ * Broadcom specific AMBA
+ * System on Chip (SoC) Host
+ *
+ * Licensed under the GNU/GPL. See COPYING for details.
+ */
+
+#include "bcma_private.h"
+#include "scan.h"
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/bcma/bcma.h>
+#include <linux/bcma/bcma_soc.h>
+
+static u8 bcma_host_soc_read8(struct bcma_device *core, u16 offset)
+{
+	return readb(core->io_addr + offset);
+}
+
+static u16 bcma_host_soc_read16(struct bcma_device *core, u16 offset)
+{
+	return readw(core->io_addr + offset);
+}
+
+static u32 bcma_host_soc_read32(struct bcma_device *core, u16 offset)
+{
+	return readl(core->io_addr + offset);
+}
+
+static void bcma_host_soc_write8(struct bcma_device *core, u16 offset,
+				 u8 value)
+{
+	writeb(value, core->io_addr + offset);
+}
+
+static void bcma_host_soc_write16(struct bcma_device *core, u16 offset,
+				 u16 value)
+{
+	writew(value, core->io_addr + offset);
+}
+
+static void bcma_host_soc_write32(struct bcma_device *core, u16 offset,
+				 u32 value)
+{
+	writel(value, core->io_addr + offset);
+}
+
+#ifdef CONFIG_BCMA_BLOCKIO
+static void bcma_host_soc_block_read(struct bcma_device *core, void *buffer,
+				     size_t count, u16 offset, u8 reg_width)
+{
+	void __iomem *addr = core->io_addr + offset;
+
+	switch (reg_width) {
+	case sizeof(u8): {
+		u8 *buf = buffer;
+
+		while (count) {
+			*buf = __raw_readb(addr);
+			buf++;
+			count--;
+		}
+		break;
+	}
+	case sizeof(u16): {
+		__le16 *buf = buffer;
+
+		WARN_ON(count & 1);
+		while (count) {
+			*buf = (__force __le16)__raw_readw(addr);
+			buf++;
+			count -= 2;
+		}
+		break;
+	}
+	case sizeof(u32): {
+		__le32 *buf = buffer;
+
+		WARN_ON(count & 3);
+		while (count) {
+			*buf = (__force __le32)__raw_readl(addr);
+			buf++;
+			count -= 4;
+		}
+		break;
+	}
+	default:
+		WARN_ON(1);
+	}
+}
+
+static void bcma_host_soc_block_write(struct bcma_device *core,
+				      const void *buffer,
+				      size_t count, u16 offset, u8 reg_width)
+{
+	void __iomem *addr = core->io_addr + offset;
+
+	switch (reg_width) {
+	case sizeof(u8): {
+		const u8 *buf = buffer;
+
+		while (count) {
+			__raw_writeb(*buf, addr);
+			buf++;
+			count--;
+		}
+		break;
+	}
+	case sizeof(u16): {
+		const __le16 *buf = buffer;
+
+		WARN_ON(count & 1);
+		while (count) {
+			__raw_writew((__force u16)(*buf), addr);
+			buf++;
+			count -= 2;
+		}
+		break;
+	}
+	case sizeof(u32): {
+		const __le32 *buf = buffer;
+
+		WARN_ON(count & 3);
+		while (count) {
+			__raw_writel((__force u32)(*buf), addr);
+			buf++;
+			count -= 4;
+		}
+		break;
+	}
+	default:
+		WARN_ON(1);
+	}
+}
+#endif /* CONFIG_BCMA_BLOCKIO */
+
+static u32 bcma_host_soc_aread32(struct bcma_device *core, u16 offset)
+{
+	if (WARN_ONCE(!core->io_wrap, "Accessed core has no wrapper/agent\n"))
+		return ~0;
+	return readl(core->io_wrap + offset);
+}
+
+static void bcma_host_soc_awrite32(struct bcma_device *core, u16 offset,
+				  u32 value)
+{
+	if (WARN_ONCE(!core->io_wrap, "Accessed core has no wrapper/agent\n"))
+		return;
+	writel(value, core->io_wrap + offset);
+}
+
+static const struct bcma_host_ops bcma_host_soc_ops = {
+	.read8		= bcma_host_soc_read8,
+	.read16		= bcma_host_soc_read16,
+	.read32		= bcma_host_soc_read32,
+	.write8		= bcma_host_soc_write8,
+	.write16	= bcma_host_soc_write16,
+	.write32	= bcma_host_soc_write32,
+#ifdef CONFIG_BCMA_BLOCKIO
+	.block_read	= bcma_host_soc_block_read,
+	.block_write	= bcma_host_soc_block_write,
+#endif
+	.aread32	= bcma_host_soc_aread32,
+	.awrite32	= bcma_host_soc_awrite32,
+};
+
+int __init bcma_host_soc_register(struct bcma_soc *soc)
+{
+	struct bcma_bus *bus = &soc->bus;
+
+	/* iomap only first core. We have to read some register on this core
+	 * to scan the bus.
+	 */
+	bus->mmio = ioremap(BCMA_ADDR_BASE, BCMA_CORE_SIZE * 1);
+	if (!bus->mmio)
+		return -ENOMEM;
+
+	/* Host specific */
+	bus->hosttype = BCMA_HOSTTYPE_SOC;
+	bus->ops = &bcma_host_soc_ops;
+
+	/* Initialize struct, detect chip */
+	bcma_init_bus(bus);
+
+	return 0;
+}
+
+int __init bcma_host_soc_init(struct bcma_soc *soc)
+{
+	struct bcma_bus *bus = &soc->bus;
+	int err;
+
+	/* Scan bus and initialize it */
+	err = bcma_bus_early_register(bus);
+	if (err)
+		iounmap(bus->mmio);
+
+	return err;
+}
+
+#ifdef CONFIG_OF
+static int bcma_host_soc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct bcma_bus *bus;
+	int err;
+
+	/* Alloc */
+	bus = devm_kzalloc(dev, sizeof(*bus), GFP_KERNEL);
+	if (!bus)
+		return -ENOMEM;
+
+	bus->dev = dev;
+
+	/* Map MMIO */
+	bus->mmio = of_iomap(np, 0);
+	if (!bus->mmio)
+		return -ENOMEM;
+
+	/* Host specific */
+	bus->hosttype = BCMA_HOSTTYPE_SOC;
+	bus->ops = &bcma_host_soc_ops;
+
+	/* Initialize struct, detect chip */
+	bcma_init_bus(bus);
+
+	/* Register */
+	err = bcma_bus_register(bus);
+	if (err)
+		goto err_unmap_mmio;
+
+	platform_set_drvdata(pdev, bus);
+
+	return err;
+
+err_unmap_mmio:
+	iounmap(bus->mmio);
+	return err;
+}
+
+static void bcma_host_soc_remove(struct platform_device *pdev)
+{
+	struct bcma_bus *bus = platform_get_drvdata(pdev);
+
+	bcma_bus_unregister(bus);
+	iounmap(bus->mmio);
+	platform_set_drvdata(pdev, NULL);
+}
+
+static const struct of_device_id bcma_host_soc_of_match[] = {
+	{ .compatible = "brcm,bus-axi", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, bcma_host_soc_of_match);
+
+static struct platform_driver bcma_host_soc_driver = {
+	.driver = {
+		.name = "bcma-host-soc",
+		.of_match_table = bcma_host_soc_of_match,
+	},
+	.probe		= bcma_host_soc_probe,
+	.remove		= bcma_host_soc_remove,
+};
+
+int __init bcma_host_soc_register_driver(void)
+{
+	return platform_driver_register(&bcma_host_soc_driver);
+}
+
+void __exit bcma_host_soc_unregister_driver(void)
+{
+	platform_driver_unregister(&bcma_host_soc_driver);
+}
+#endif /* CONFIG_OF */