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, 229 insertions, 0 deletions

diff --git a/drivers/soundwire/amd_init.c b/drivers/soundwire/amd_init.c
new file mode 100644
index 000000000..8e419ddfa
--- /dev/null
+++ b/drivers/soundwire/amd_init.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+/*
+ * SoundWire AMD Manager Initialize routines
+ *
+ * Initializes and creates SDW devices based on ACPI and Hardware values
+ *
+ * Copyright 2024 Advanced Micro Devices, Inc.
+ */
+
+#include <linux/acpi.h>
+#include <linux/cleanup.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "amd_init.h"
+
+#define ACP_PAD_PULLDOWN_CTRL				0x0001448
+#define ACP_SW_PAD_KEEPER_EN				0x0001454
+#define AMD_SDW0_PAD_CTRL_MASK				0x60
+#define AMD_SDW1_PAD_CTRL_MASK				5
+#define AMD_SDW_PAD_CTRL_MASK		(AMD_SDW0_PAD_CTRL_MASK | AMD_SDW1_PAD_CTRL_MASK)
+#define AMD_SDW0_PAD_EN					1
+#define AMD_SDW1_PAD_EN					0x10
+#define AMD_SDW_PAD_EN			(AMD_SDW0_PAD_EN | AMD_SDW1_PAD_EN)
+
+static int amd_enable_sdw_pads(void __iomem *mmio, u32 link_mask, struct device *dev)
+{
+	u32 pad_keeper_en, pad_pulldown_ctrl_mask;
+
+	switch (link_mask) {
+	case 1:
+		pad_keeper_en = AMD_SDW0_PAD_EN;
+		pad_pulldown_ctrl_mask = AMD_SDW0_PAD_CTRL_MASK;
+		break;
+	case 2:
+		pad_keeper_en = AMD_SDW1_PAD_EN;
+		pad_pulldown_ctrl_mask = AMD_SDW1_PAD_CTRL_MASK;
+		break;
+	case 3:
+		pad_keeper_en = AMD_SDW_PAD_EN;
+		pad_pulldown_ctrl_mask = AMD_SDW_PAD_CTRL_MASK;
+		break;
+	default:
+		dev_err(dev, "No SDW Links are enabled\n");
+		return -ENODEV;
+	}
+
+	amd_updatel(mmio, ACP_SW_PAD_KEEPER_EN, pad_keeper_en, pad_keeper_en);
+	amd_updatel(mmio, ACP_PAD_PULLDOWN_CTRL, pad_pulldown_ctrl_mask, 0);
+
+	return 0;
+}
+
+static int sdw_amd_cleanup(struct sdw_amd_ctx *ctx)
+{
+	int i;
+
+	for (i = 0; i < ctx->count; i++) {
+		if (!(ctx->link_mask & BIT(i)))
+			continue;
+		platform_device_unregister(ctx->pdev[i]);
+	}
+
+	return 0;
+}
+
+static struct sdw_amd_ctx *sdw_amd_probe_controller(struct sdw_amd_res *res)
+{
+	struct sdw_amd_ctx *ctx;
+	struct acpi_device *adev;
+	struct acp_sdw_pdata sdw_pdata[2];
+	struct platform_device_info pdevinfo[2];
+	u32 link_mask;
+	int count, index;
+	int ret;
+
+	if (!res)
+		return NULL;
+
+	adev = acpi_fetch_acpi_dev(res->handle);
+	if (!adev)
+		return NULL;
+
+	if (!res->count)
+		return NULL;
+
+	count = res->count;
+	dev_dbg(&adev->dev, "Creating %d SDW Link devices\n", count);
+	ret = amd_enable_sdw_pads(res->mmio_base, res->link_mask, res->parent);
+	if (ret)
+		return NULL;
+
+	/*
+	 * we need to alloc/free memory manually and can't use devm:
+	 * this routine may be called from a workqueue, and not from
+	 * the parent .probe.
+	 * If devm_ was used, the memory might never be freed on errors.
+	 */
+	ctx = kzalloc_obj(*ctx);
+	if (!ctx)
+		return NULL;
+
+	ctx->count = count;
+	ctx->link_mask = res->link_mask;
+	struct resource *sdw_res __free(kfree) = kzalloc_obj(*sdw_res);
+	if (!sdw_res) {
+		kfree(ctx);
+		return NULL;
+	}
+	sdw_res->flags = IORESOURCE_MEM;
+	sdw_res->start = res->addr;
+	sdw_res->end = res->addr + res->reg_range;
+	memset(&pdevinfo, 0, sizeof(pdevinfo));
+	link_mask = ctx->link_mask;
+	for (index = 0; index < count; index++) {
+		if (!(link_mask & BIT(index)))
+			continue;
+
+		sdw_pdata[index].instance = index;
+		sdw_pdata[index].acp_sdw_lock = res->acp_lock;
+		sdw_pdata[index].acp_rev = res->acp_rev;
+		pdevinfo[index].name = "amd_sdw_manager";
+		pdevinfo[index].id = index;
+		pdevinfo[index].parent = res->parent;
+		pdevinfo[index].num_res = 1;
+		pdevinfo[index].res = sdw_res;
+		pdevinfo[index].data = &sdw_pdata[index];
+		pdevinfo[index].size_data = sizeof(struct acp_sdw_pdata);
+		pdevinfo[index].fwnode = acpi_fwnode_handle(adev);
+		ctx->pdev[index] = platform_device_register_full(&pdevinfo[index]);
+		if (IS_ERR(ctx->pdev[index]))
+			goto err;
+	}
+	return ctx;
+err:
+	while (index--) {
+		if (!(link_mask & BIT(index)))
+			continue;
+
+		platform_device_unregister(ctx->pdev[index]);
+	}
+
+	kfree(ctx);
+	return NULL;
+}
+
+static int sdw_amd_startup(struct sdw_amd_ctx *ctx)
+{
+	struct amd_sdw_manager *amd_manager;
+	int i, ret;
+
+	/* Startup SDW Manager devices */
+	for (i = 0; i < ctx->count; i++) {
+		if (!(ctx->link_mask & BIT(i)))
+			continue;
+		amd_manager = dev_get_drvdata(&ctx->pdev[i]->dev);
+		ret = amd_sdw_manager_start(amd_manager);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+int sdw_amd_probe(struct sdw_amd_res *res, struct sdw_amd_ctx **sdw_ctx)
+{
+	*sdw_ctx = sdw_amd_probe_controller(res);
+	if (!*sdw_ctx)
+		return -ENODEV;
+
+	return sdw_amd_startup(*sdw_ctx);
+}
+EXPORT_SYMBOL_NS(sdw_amd_probe, "SOUNDWIRE_AMD_INIT");
+
+void sdw_amd_exit(struct sdw_amd_ctx *ctx)
+{
+	sdw_amd_cleanup(ctx);
+	kfree(ctx->peripherals);
+	kfree(ctx);
+}
+EXPORT_SYMBOL_NS(sdw_amd_exit, "SOUNDWIRE_AMD_INIT");
+
+int sdw_amd_get_slave_info(struct sdw_amd_ctx *ctx)
+{
+	struct amd_sdw_manager *amd_manager;
+	struct sdw_bus *bus;
+	struct sdw_slave *slave;
+	struct list_head *node;
+	int index;
+	int i = 0;
+	int num_slaves = 0;
+
+	for (index = 0; index < ctx->count; index++) {
+		if (!(ctx->link_mask & BIT(index)))
+			continue;
+		amd_manager = dev_get_drvdata(&ctx->pdev[index]->dev);
+		if (!amd_manager)
+			return -ENODEV;
+		bus = &amd_manager->bus;
+		/* Calculate number of slaves */
+		list_for_each(node, &bus->slaves)
+			num_slaves++;
+	}
+
+	ctx->peripherals = kmalloc_flex(*ctx->peripherals, array, num_slaves);
+	if (!ctx->peripherals)
+		return -ENOMEM;
+	ctx->peripherals->num_peripherals = num_slaves;
+	for (index = 0; index < ctx->count; index++) {
+		if (!(ctx->link_mask & BIT(index)))
+			continue;
+		amd_manager = dev_get_drvdata(&ctx->pdev[index]->dev);
+		if (amd_manager) {
+			bus = &amd_manager->bus;
+			list_for_each_entry(slave, &bus->slaves, node) {
+				ctx->peripherals->array[i] = slave;
+				i++;
+			}
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL_NS(sdw_amd_get_slave_info, "SOUNDWIRE_AMD_INIT");
+
+MODULE_AUTHOR("Vijendar.Mukunda@amd.com");
+MODULE_DESCRIPTION("AMD SoundWire Init Library");
+MODULE_LICENSE("Dual BSD/GPL");