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, 232 insertions, 0 deletions

diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c
new file mode 100644
index 000000000..b3cf59954
--- /dev/null
+++ b/drivers/misc/open-dice.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 - Google LLC
+ * Author: David Brazdil <dbrazdil@google.com>
+ * Author: Song Guo <songguo@google.com>
+ *
+ * Driver for Open Profile for DICE.
+ *
+ * This driver takes ownership of a reserved memory region containing data
+ * generated by the Open Profile for DICE measured boot protocol. The memory
+ * contents are not interpreted by the kernel but can be mapped into a userspace
+ * process via a misc device. Userspace can also request a wipe of the memory.
+ *
+ * Userspace can access the data with (w/o error handling):
+ *
+ *     fd = open("/dev/open-dice0", O_RDWR);
+ *     read(fd, &size, sizeof(unsigned long));
+ *     data = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
+ *     write(fd, NULL, 0); // wipe
+ *     close(fd);
+ */
+
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/platform_device.h>
+
+#define DRIVER_NAME "open-dice"
+
+struct open_dice_drvdata {
+	struct mutex lock;
+	char name[16];
+	phys_addr_t mem_base;
+	resource_size_t mem_size;
+	struct miscdevice misc;
+};
+
+static inline struct open_dice_drvdata *to_open_dice_drvdata(struct file *filp)
+{
+	return container_of(filp->private_data, struct open_dice_drvdata, misc);
+}
+
+static int open_dice_wipe(struct open_dice_drvdata *drvdata)
+{
+	void *kaddr;
+
+	mutex_lock(&drvdata->lock);
+	kaddr = devm_memremap(drvdata->misc.this_device, drvdata->mem_base,
+			      drvdata->mem_size, MEMREMAP_WC);
+	if (IS_ERR(kaddr)) {
+		mutex_unlock(&drvdata->lock);
+		return PTR_ERR(kaddr);
+	}
+
+	memset(kaddr, 0, drvdata->mem_size);
+	devm_memunmap(drvdata->misc.this_device, kaddr);
+	mutex_unlock(&drvdata->lock);
+	return 0;
+}
+
+/*
+ * Copies the size of the reserved memory region to the user-provided buffer.
+ */
+static ssize_t open_dice_read(struct file *filp, char __user *ptr, size_t len,
+			      loff_t *off)
+{
+	unsigned long val = to_open_dice_drvdata(filp)->mem_size;
+
+	return simple_read_from_buffer(ptr, len, off, &val, sizeof(val));
+}
+
+/*
+ * Triggers a wipe of the reserved memory region. The user-provided pointer
+ * is never dereferenced.
+ */
+static ssize_t open_dice_write(struct file *filp, const char __user *ptr,
+			       size_t len, loff_t *off)
+{
+	if (open_dice_wipe(to_open_dice_drvdata(filp)))
+		return -EIO;
+
+	/* Consume the input buffer. */
+	return len;
+}
+
+/*
+ * Creates a mapping of the reserved memory region in user address space.
+ */
+static int open_dice_mmap_prepare(struct vm_area_desc *desc)
+{
+	struct file *filp = desc->file;
+	struct open_dice_drvdata *drvdata = to_open_dice_drvdata(filp);
+
+	if (vma_desc_test(desc, VMA_MAYSHARE_BIT)) {
+		/* Do not allow userspace to modify the underlying data. */
+		if (vma_desc_test(desc, VMA_WRITE_BIT))
+			return -EPERM;
+		/* Ensure userspace cannot acquire VM_WRITE later. */
+		vma_desc_clear_flags(desc, VMA_MAYWRITE_BIT);
+	}
+
+	/* Create write-combine mapping so all clients observe a wipe. */
+	desc->page_prot = pgprot_writecombine(desc->page_prot);
+	vma_desc_set_flags(desc, VMA_DONTCOPY_BIT, VMA_DONTDUMP_BIT);
+	mmap_action_simple_ioremap(desc, drvdata->mem_base,
+				   drvdata->mem_size);
+	return 0;
+}
+
+static const struct file_operations open_dice_fops = {
+	.owner = THIS_MODULE,
+	.read = open_dice_read,
+	.write = open_dice_write,
+	.mmap_prepare = open_dice_mmap_prepare,
+};
+
+static int __init open_dice_probe(struct platform_device *pdev)
+{
+	static unsigned int dev_idx;
+	struct device *dev = &pdev->dev;
+	struct open_dice_drvdata *drvdata;
+	phys_addr_t mem_base;
+	resource_size_t mem_size;
+	int ret;
+
+	if (dev->of_node) {
+		struct reserved_mem *rmem = of_reserved_mem_lookup(dev->of_node);
+
+		if (!rmem) {
+			dev_err(dev, "failed to lookup reserved memory\n");
+			return -EINVAL;
+		}
+		mem_base = rmem->base;
+		mem_size = rmem->size;
+	} else if (is_acpi_node(dev->fwnode)) {
+		struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+		if (!res) {
+			dev_err(dev, "failed to get MMIO resource\n");
+			return -EINVAL;
+		}
+		mem_base = res->start;
+		mem_size = resource_size(res);
+	} else {
+		dev_err(dev, "device not supported (no DT or ACPI node)\n");
+		return -EINVAL;
+	}
+
+	if (!mem_size || (mem_size > ULONG_MAX)) {
+		dev_err(dev, "invalid memory region size\n");
+		return -EINVAL;
+	}
+
+	if (!PAGE_ALIGNED(mem_base) || !PAGE_ALIGNED(mem_size)) {
+		dev_err(dev, "memory region must be page-aligned\n");
+		return -EINVAL;
+	}
+
+	drvdata = devm_kmalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	*drvdata = (struct open_dice_drvdata){
+		.mem_base = mem_base,
+		.mem_size = mem_size,
+		.misc = (struct miscdevice){
+			.parent	= dev,
+			.name	= drvdata->name,
+			.minor	= MISC_DYNAMIC_MINOR,
+			.fops	= &open_dice_fops,
+			.mode	= 0600,
+		},
+	};
+	mutex_init(&drvdata->lock);
+
+	/* Index overflow check not needed, misc_register() will fail. */
+	snprintf(drvdata->name, sizeof(drvdata->name), DRIVER_NAME"%u", dev_idx++);
+
+	ret = misc_register(&drvdata->misc);
+	if (ret) {
+		dev_err(dev, "failed to register misc device '%s': %d\n",
+			drvdata->name, ret);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, drvdata);
+	return 0;
+}
+
+static void open_dice_remove(struct platform_device *pdev)
+{
+	struct open_dice_drvdata *drvdata = platform_get_drvdata(pdev);
+
+	misc_deregister(&drvdata->misc);
+}
+
+static const struct of_device_id open_dice_of_match[] = {
+	{ .compatible = "google,open-dice" },
+	{ }
+};
+
+static struct platform_driver open_dice_driver = {
+	.remove = open_dice_remove,
+	.driver = {
+		.name = DRIVER_NAME,
+		.of_match_table = open_dice_of_match,
+	},
+};
+
+static int __init open_dice_init(void)
+{
+	int ret = platform_driver_probe(&open_dice_driver, open_dice_probe);
+
+	/* DICE regions are optional. Succeed even with zero instances. */
+	return (ret == -ENODEV) ? 0 : ret;
+}
+
+static void __exit open_dice_exit(void)
+{
+	platform_driver_unregister(&open_dice_driver);
+}
+
+module_init(open_dice_init);
+module_exit(open_dice_exit);
+
+MODULE_DESCRIPTION("Driver for Open Profile for DICE.");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("David Brazdil <dbrazdil@google.com>");
+MODULE_AUTHOR("Song Guo <songguo@google.com>");