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, 233 insertions, 0 deletions

diff --git a/samples/vfio-mdev/mdpy-fb.c b/samples/vfio-mdev/mdpy-fb.c
new file mode 100644
index 000000000..149af7f59
--- /dev/null
+++ b/samples/vfio-mdev/mdpy-fb.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Framebuffer driver for mdpy (mediated virtual pci display device).
+ *
+ * See mdpy-defs.h for device specs
+ *
+ *   (c) Gerd Hoffmann <kraxel@redhat.com>
+ *
+ * Using some code snippets from simplefb and cirrusfb.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include <linux/errno.h>
+#include <linux/fb.h>
+#include <linux/io.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <drm/drm_fourcc.h>
+#include "mdpy-defs.h"
+
+static const struct fb_fix_screeninfo mdpy_fb_fix = {
+	.id		= "mdpy-fb",
+	.type		= FB_TYPE_PACKED_PIXELS,
+	.visual		= FB_VISUAL_TRUECOLOR,
+	.accel		= FB_ACCEL_NONE,
+};
+
+static const struct fb_var_screeninfo mdpy_fb_var = {
+	.height		= -1,
+	.width		= -1,
+	.activate	= FB_ACTIVATE_NOW,
+	.vmode		= FB_VMODE_NONINTERLACED,
+
+	.bits_per_pixel = 32,
+	.transp.offset	= 24,
+	.red.offset	= 16,
+	.green.offset	= 8,
+	.blue.offset	= 0,
+	.transp.length	= 8,
+	.red.length	= 8,
+	.green.length	= 8,
+	.blue.length	= 8,
+};
+
+#define PSEUDO_PALETTE_SIZE 16
+
+struct mdpy_fb_par {
+	u32 palette[PSEUDO_PALETTE_SIZE];
+};
+
+static int mdpy_fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
+			      u_int transp, struct fb_info *info)
+{
+	u32 *pal = info->pseudo_palette;
+	u32 cr = red >> (16 - info->var.red.length);
+	u32 cg = green >> (16 - info->var.green.length);
+	u32 cb = blue >> (16 - info->var.blue.length);
+	u32 value, mask;
+
+	if (regno >= PSEUDO_PALETTE_SIZE)
+		return -EINVAL;
+
+	value = (cr << info->var.red.offset) |
+		(cg << info->var.green.offset) |
+		(cb << info->var.blue.offset);
+	if (info->var.transp.length > 0) {
+		mask = (1 << info->var.transp.length) - 1;
+		mask <<= info->var.transp.offset;
+		value |= mask;
+	}
+	pal[regno] = value;
+
+	return 0;
+}
+
+static void mdpy_fb_destroy(struct fb_info *info)
+{
+	if (info->screen_base)
+		iounmap(info->screen_base);
+}
+
+static const struct fb_ops mdpy_fb_ops = {
+	.owner		= THIS_MODULE,
+	FB_DEFAULT_IOMEM_OPS,
+	.fb_destroy	= mdpy_fb_destroy,
+	.fb_setcolreg	= mdpy_fb_setcolreg,
+};
+
+static int mdpy_fb_probe(struct pci_dev *pdev,
+			 const struct pci_device_id *ent)
+{
+	struct fb_info *info;
+	struct mdpy_fb_par *par;
+	u32 format, width, height;
+	int ret;
+
+	ret = pci_enable_device(pdev);
+	if (ret < 0)
+		return ret;
+
+	ret = pci_request_regions(pdev, "mdpy-fb");
+	if (ret < 0)
+		goto err_disable_dev;
+
+	pci_read_config_dword(pdev, MDPY_FORMAT_OFFSET, &format);
+	pci_read_config_dword(pdev, MDPY_WIDTH_OFFSET,	&width);
+	pci_read_config_dword(pdev, MDPY_HEIGHT_OFFSET, &height);
+	if (format != DRM_FORMAT_XRGB8888) {
+		pci_err(pdev, "format mismatch (0x%x != 0x%x)\n",
+			format, DRM_FORMAT_XRGB8888);
+		ret = -EINVAL;
+		goto err_release_regions;
+	}
+	if (width < 100	 || width > 10000) {
+		pci_err(pdev, "width (%d) out of range\n", width);
+		ret = -EINVAL;
+		goto err_release_regions;
+	}
+	if (height < 100 || height > 10000) {
+		pci_err(pdev, "height (%d) out of range\n", height);
+		ret = -EINVAL;
+		goto err_release_regions;
+	}
+	pci_info(pdev, "mdpy found: %dx%d framebuffer\n",
+		 width, height);
+
+	info = framebuffer_alloc(sizeof(struct mdpy_fb_par), &pdev->dev);
+	if (!info) {
+		ret = -ENOMEM;
+		goto err_release_regions;
+	}
+	pci_set_drvdata(pdev, info);
+	par = info->par;
+
+	info->fix = mdpy_fb_fix;
+	info->fix.smem_start = pci_resource_start(pdev, 0);
+	info->fix.smem_len = pci_resource_len(pdev, 0);
+	info->fix.line_length = width * 4;
+
+	info->var = mdpy_fb_var;
+	info->var.xres = width;
+	info->var.yres = height;
+	info->var.xres_virtual = width;
+	info->var.yres_virtual = height;
+
+	info->screen_size = info->fix.smem_len;
+	info->screen_base = ioremap(info->fix.smem_start,
+				    info->screen_size);
+	if (!info->screen_base) {
+		pci_err(pdev, "ioremap(pcibar) failed\n");
+		ret = -EIO;
+		goto err_release_fb;
+	}
+
+	info->fbops = &mdpy_fb_ops;
+	info->pseudo_palette = par->palette;
+
+	ret = register_framebuffer(info);
+	if (ret < 0) {
+		pci_err(pdev, "mdpy-fb device register failed: %d\n", ret);
+		goto err_unmap;
+	}
+
+	pci_info(pdev, "fb%d registered\n", info->node);
+	return 0;
+
+err_unmap:
+	iounmap(info->screen_base);
+
+err_release_fb:
+	framebuffer_release(info);
+
+err_release_regions:
+	pci_release_regions(pdev);
+
+err_disable_dev:
+	pci_disable_device(pdev);
+
+	return ret;
+}
+
+static void mdpy_fb_remove(struct pci_dev *pdev)
+{
+	struct fb_info *info = pci_get_drvdata(pdev);
+
+	unregister_framebuffer(info);
+	iounmap(info->screen_base);
+	framebuffer_release(info);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+static struct pci_device_id mdpy_fb_pci_table[] = {
+	{
+		.vendor	   = MDPY_PCI_VENDOR_ID,
+		.device	   = MDPY_PCI_DEVICE_ID,
+		.subvendor = MDPY_PCI_SUBVENDOR_ID,
+		.subdevice = MDPY_PCI_SUBDEVICE_ID,
+	}, {
+		/* end of list */
+	}
+};
+
+static struct pci_driver mdpy_fb_pci_driver = {
+	.name		= "mdpy-fb",
+	.id_table	= mdpy_fb_pci_table,
+	.probe		= mdpy_fb_probe,
+	.remove		= mdpy_fb_remove,
+};
+
+static int __init mdpy_fb_init(void)
+{
+	int ret;
+
+	ret = pci_register_driver(&mdpy_fb_pci_driver);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+module_init(mdpy_fb_init);
+
+MODULE_DEVICE_TABLE(pci, mdpy_fb_pci_table);
+MODULE_DESCRIPTION("Framebuffer driver for mdpy (mediated virtual pci display device)");
+MODULE_LICENSE("GPL v2");