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, 250 insertions, 0 deletions

diff --git a/drivers/video/fbdev/sunxvr2500.c b/drivers/video/fbdev/sunxvr2500.c
new file mode 100644
index 000000000..b7587ff4d
--- /dev/null
+++ b/drivers/video/fbdev/sunxvr2500.c
@@ -0,0 +1,250 @@
+/* sunxvr2500.c: Sun 3DLABS XVR-2500 et al. fb driver for sparc64 systems
+ *
+ * License: GPL
+ *
+ * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
+ */
+
+#include <linux/aperture.h>
+#include <linux/kernel.h>
+#include <linux/fb.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/of.h>
+
+#include <asm/io.h>
+
+struct s3d_info {
+	struct fb_info		*info;
+	struct pci_dev		*pdev;
+
+	char __iomem		*fb_base;
+	unsigned long		fb_base_phys;
+
+	struct device_node	*of_node;
+
+	unsigned int		width;
+	unsigned int		height;
+	unsigned int		depth;
+	unsigned int		fb_size;
+
+	u32			pseudo_palette[16];
+};
+
+static int s3d_get_props(struct s3d_info *sp)
+{
+	sp->width = of_getintprop_default(sp->of_node, "width", 0);
+	sp->height = of_getintprop_default(sp->of_node, "height", 0);
+	sp->depth = of_getintprop_default(sp->of_node, "depth", 8);
+
+	if (!sp->width || !sp->height) {
+		pci_err(sp->pdev, "Critical properties missing\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int s3d_setcolreg(unsigned regno,
+			 unsigned red, unsigned green, unsigned blue,
+			 unsigned transp, struct fb_info *info)
+{
+	u32 value;
+
+	if (regno < 16) {
+		red >>= 8;
+		green >>= 8;
+		blue >>= 8;
+
+		value = (blue << 24) | (green << 16) | (red << 8);
+		((u32 *)info->pseudo_palette)[regno] = value;
+	}
+
+	return 0;
+}
+
+static const struct fb_ops s3d_ops = {
+	.owner			= THIS_MODULE,
+	FB_DEFAULT_IOMEM_OPS,
+	.fb_setcolreg		= s3d_setcolreg,
+};
+
+static int s3d_set_fbinfo(struct s3d_info *sp)
+{
+	struct fb_info *info = sp->info;
+	struct fb_var_screeninfo *var = &info->var;
+
+	info->fbops = &s3d_ops;
+	info->screen_base = sp->fb_base;
+	info->screen_size = sp->fb_size;
+
+	info->pseudo_palette = sp->pseudo_palette;
+
+	/* Fill fix common fields */
+	strscpy(info->fix.id, "s3d", sizeof(info->fix.id));
+        info->fix.smem_start = sp->fb_base_phys;
+        info->fix.smem_len = sp->fb_size;
+        info->fix.type = FB_TYPE_PACKED_PIXELS;
+	if (sp->depth == 32 || sp->depth == 24)
+		info->fix.visual = FB_VISUAL_TRUECOLOR;
+	else
+		info->fix.visual = FB_VISUAL_PSEUDOCOLOR;
+
+	var->xres = sp->width;
+	var->yres = sp->height;
+	var->xres_virtual = var->xres;
+	var->yres_virtual = var->yres;
+	var->bits_per_pixel = sp->depth;
+
+	var->red.offset = 8;
+	var->red.length = 8;
+	var->green.offset = 16;
+	var->green.length = 8;
+	var->blue.offset = 24;
+	var->blue.length = 8;
+	var->transp.offset = 0;
+	var->transp.length = 0;
+
+	if (fb_alloc_cmap(&info->cmap, 256, 0)) {
+		pci_err(sp->pdev, "Cannot allocate color map\n");
+		return -ENOMEM;
+	}
+
+        return 0;
+}
+
+static int s3d_pci_register(struct pci_dev *pdev,
+			    const struct pci_device_id *ent)
+{
+	struct fb_info *info;
+	struct s3d_info *sp;
+	int err;
+
+	err = aperture_remove_conflicting_pci_devices(pdev, "s3dfb");
+	if (err)
+		return err;
+
+	err = pci_enable_device(pdev);
+	if (err < 0) {
+		pci_err(pdev, "Cannot enable PCI device\n");
+		goto err_out;
+	}
+
+	info = framebuffer_alloc(sizeof(struct s3d_info), &pdev->dev);
+	if (!info) {
+		err = -ENOMEM;
+		goto err_disable;
+	}
+
+	sp = info->par;
+	sp->info = info;
+	sp->pdev = pdev;
+	sp->of_node = pci_device_to_OF_node(pdev);
+	if (!sp->of_node) {
+		pci_err(pdev, "Cannot find OF node\n");
+		err = -ENODEV;
+		goto err_release_fb;
+	}
+
+	sp->fb_base_phys = pci_resource_start (pdev, 1);
+
+	err = pci_request_region(pdev, 1, "s3d framebuffer");
+	if (err < 0) {
+		pci_err(pdev, "Cannot request region 1\n");
+		goto err_release_fb;
+	}
+
+	err = s3d_get_props(sp);
+	if (err)
+		goto err_release_pci;
+
+	/* XXX 'linebytes' is often wrong, it is equal to the width
+	 * XXX with depth of 32 on my XVR-2500 which is clearly not
+	 * XXX right.  So we don't try to use it.
+	 */
+	switch (sp->depth) {
+	case 8:
+		info->fix.line_length = sp->width;
+		break;
+	case 16:
+		info->fix.line_length = sp->width * 2;
+		break;
+	case 24:
+		info->fix.line_length = sp->width * 3;
+		break;
+	case 32:
+		info->fix.line_length = sp->width * 4;
+		break;
+	}
+	sp->fb_size = info->fix.line_length * sp->height;
+
+	sp->fb_base = ioremap(sp->fb_base_phys, sp->fb_size);
+	if (!sp->fb_base) {
+		err = -ENOMEM;
+		goto err_release_pci;
+	}
+
+	err = s3d_set_fbinfo(sp);
+	if (err)
+		goto err_unmap_fb;
+
+	pci_set_drvdata(pdev, info);
+
+	pci_info(pdev, "Found device\n");
+
+	err = register_framebuffer(info);
+	if (err < 0) {
+		pci_err(pdev, "Could not register framebuffer\n");
+		goto err_unmap_fb;
+	}
+
+	return 0;
+
+err_unmap_fb:
+	iounmap(sp->fb_base);
+
+err_release_pci:
+	pci_release_region(pdev, 1);
+
+err_release_fb:
+        framebuffer_release(info);
+
+err_disable:
+	pci_disable_device(pdev);
+
+err_out:
+	return err;
+}
+
+static const struct pci_device_id s3d_pci_table[] = {
+	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x002c),	},
+	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x002d),	},
+	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x002e),	},
+	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x002f),	},
+	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x0030),	},
+	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x0031),	},
+	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x0032),	},
+	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x0033),	},
+	{ 0, }
+};
+
+static struct pci_driver s3d_driver = {
+	.driver = {
+		.suppress_bind_attrs = true,
+	},
+	.name		= "s3d",
+	.id_table	= s3d_pci_table,
+	.probe		= s3d_pci_register,
+};
+
+static int __init s3d_init(void)
+{
+	if (fb_modesetting_disabled("s3d"))
+		return -ENODEV;
+
+	if (fb_get_options("s3d", NULL))
+		return -ENODEV;
+
+	return pci_register_driver(&s3d_driver);
+}
+device_initcall(s3d_init);