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, 288 insertions, 0 deletions

diff --git a/drivers/video/fbdev/sbuslib.c b/drivers/video/fbdev/sbuslib.c
new file mode 100644
index 000000000..dd2002d08
--- /dev/null
+++ b/drivers/video/fbdev/sbuslib.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+/* sbuslib.c: Helper library for SBUS framebuffer drivers.
+ *
+ * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ */
+
+#include <linux/compat.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fb.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <linux/of.h>
+
+#include <asm/fbio.h>
+
+#include "sbuslib.h"
+
+void sbusfb_fill_var(struct fb_var_screeninfo *var, struct device_node *dp,
+		     int bpp)
+{
+	memset(var, 0, sizeof(*var));
+
+	var->xres = of_getintprop_default(dp, "width", 1152);
+	var->yres = of_getintprop_default(dp, "height", 900);
+	var->xres_virtual = var->xres;
+	var->yres_virtual = var->yres;
+	var->bits_per_pixel = bpp;
+}
+
+EXPORT_SYMBOL(sbusfb_fill_var);
+
+static unsigned long sbusfb_mmapsize(long size, unsigned long fbsize)
+{
+	if (size == SBUS_MMAP_EMPTY) return 0;
+	if (size >= 0) return size;
+	return fbsize * (-size);
+}
+
+int sbusfb_mmap_helper(const struct sbus_mmap_map *map,
+		       unsigned long physbase,
+		       unsigned long fbsize,
+		       unsigned long iospace,
+		       struct vm_area_struct *vma)
+{
+	unsigned int size, page, r, map_size;
+	unsigned long map_offset = 0;
+	unsigned long off;
+	int i;
+
+	if (!(vma->vm_flags & (VM_SHARED | VM_MAYSHARE)))
+		return -EINVAL;
+
+	size = vma->vm_end - vma->vm_start;
+	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT))
+		return -EINVAL;
+
+	off = vma->vm_pgoff << PAGE_SHIFT;
+
+	/* VM_IO | VM_DONTEXPAND | VM_DONTDUMP are set by remap_pfn_range() */
+
+	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	/* Each page, see which map applies */
+	for (page = 0; page < size; ){
+		map_size = 0;
+		for (i = 0; map[i].size; i++)
+			if (map[i].voff == off+page) {
+				map_size = sbusfb_mmapsize(map[i].size, fbsize);
+#ifdef __sparc_v9__
+#define POFF_MASK	(PAGE_MASK|0x1UL)
+#else
+#define POFF_MASK	(PAGE_MASK)
+#endif
+				map_offset = (physbase + map[i].poff) & POFF_MASK;
+				break;
+			}
+		if (!map_size) {
+			page += PAGE_SIZE;
+			continue;
+		}
+		if (page + map_size > size)
+			map_size = size - page;
+		r = io_remap_pfn_range(vma,
+					vma->vm_start + page,
+					MK_IOSPACE_PFN(iospace,
+						map_offset >> PAGE_SHIFT),
+					map_size,
+					vma->vm_page_prot);
+		if (r)
+			return -EAGAIN;
+		page += map_size;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(sbusfb_mmap_helper);
+
+int sbusfb_ioctl_helper(unsigned long cmd, unsigned long arg,
+			struct fb_info *info,
+			int type, int fb_depth, unsigned long fb_size)
+{
+	switch(cmd) {
+	case FBIOGTYPE: {
+		struct fbtype __user *f = (struct fbtype __user *) arg;
+
+		if (put_user(type, &f->fb_type) ||
+		    put_user(info->var.yres, &f->fb_height) ||
+		    put_user(info->var.xres, &f->fb_width) ||
+		    put_user(fb_depth, &f->fb_depth) ||
+		    put_user(0, &f->fb_cmsize) ||
+		    put_user(fb_size, &f->fb_cmsize))
+			return -EFAULT;
+		return 0;
+	}
+	case FBIOPUTCMAP_SPARC: {
+		struct fbcmap __user *c = (struct fbcmap __user *) arg;
+		struct fb_cmap cmap;
+		u16 red, green, blue;
+		u8 red8, green8, blue8;
+		unsigned char __user *ured;
+		unsigned char __user *ugreen;
+		unsigned char __user *ublue;
+		unsigned int index, count, i;
+
+		if (get_user(index, &c->index) ||
+		    get_user(count, &c->count) ||
+		    get_user(ured, &c->red) ||
+		    get_user(ugreen, &c->green) ||
+		    get_user(ublue, &c->blue))
+			return -EFAULT;
+
+		cmap.len = 1;
+		cmap.red = &red;
+		cmap.green = &green;
+		cmap.blue = &blue;
+		cmap.transp = NULL;
+		for (i = 0; i < count; i++) {
+			int err;
+
+			if (get_user(red8, &ured[i]) ||
+			    get_user(green8, &ugreen[i]) ||
+			    get_user(blue8, &ublue[i]))
+				return -EFAULT;
+
+			red = red8 << 8;
+			green = green8 << 8;
+			blue = blue8 << 8;
+
+			cmap.start = index + i;
+			err = fb_set_cmap(&cmap, info);
+			if (err)
+				return err;
+		}
+		return 0;
+	}
+	case FBIOGETCMAP_SPARC: {
+		struct fbcmap __user *c = (struct fbcmap __user *) arg;
+		unsigned char __user *ured;
+		unsigned char __user *ugreen;
+		unsigned char __user *ublue;
+		struct fb_cmap *cmap = &info->cmap;
+		unsigned int index, count, i;
+		u8 red, green, blue;
+
+		if (get_user(index, &c->index) ||
+		    get_user(count, &c->count) ||
+		    get_user(ured, &c->red) ||
+		    get_user(ugreen, &c->green) ||
+		    get_user(ublue, &c->blue))
+			return -EFAULT;
+
+		if (index > cmap->len || count > cmap->len - index)
+			return -EINVAL;
+
+		for (i = 0; i < count; i++) {
+			red = cmap->red[index + i] >> 8;
+			green = cmap->green[index + i] >> 8;
+			blue = cmap->blue[index + i] >> 8;
+			if (put_user(red, &ured[i]) ||
+			    put_user(green, &ugreen[i]) ||
+			    put_user(blue, &ublue[i]))
+				return -EFAULT;
+		}
+		return 0;
+	}
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL(sbusfb_ioctl_helper);
+
+#ifdef CONFIG_COMPAT
+int sbusfb_compat_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case FBIOGTYPE:
+	case FBIOSATTR:
+	case FBIOGATTR:
+	case FBIOSVIDEO:
+	case FBIOGVIDEO:
+	case FBIOSCURSOR32:
+	case FBIOGCURSOR32:	/* This is not implemented yet.
+				   Later it should be converted... */
+	case FBIOSCURPOS:
+	case FBIOGCURPOS:
+	case FBIOGCURMAX:
+		return info->fbops->fb_ioctl(info, cmd, arg);
+	case FBIOPUTCMAP32:
+	case FBIOPUTCMAP_SPARC: {
+		struct fbcmap32 c;
+		struct fb_cmap cmap;
+		u16 red, green, blue;
+		u8 red8, green8, blue8;
+		unsigned char __user *ured;
+		unsigned char __user *ugreen;
+		unsigned char __user *ublue;
+		unsigned int i;
+
+		if (copy_from_user(&c, compat_ptr(arg), sizeof(c)))
+			return -EFAULT;
+		ured = compat_ptr(c.red);
+		ugreen = compat_ptr(c.green);
+		ublue = compat_ptr(c.blue);
+
+		cmap.len = 1;
+		cmap.red = &red;
+		cmap.green = &green;
+		cmap.blue = &blue;
+		cmap.transp = NULL;
+		for (i = 0; i < c.count; i++) {
+			int err;
+
+			if (get_user(red8, &ured[i]) ||
+			    get_user(green8, &ugreen[i]) ||
+			    get_user(blue8, &ublue[i]))
+				return -EFAULT;
+
+			red = red8 << 8;
+			green = green8 << 8;
+			blue = blue8 << 8;
+
+			cmap.start = c.index + i;
+			err = fb_set_cmap(&cmap, info);
+			if (err)
+				return err;
+		}
+		return 0;
+	}
+	case FBIOGETCMAP32: {
+		struct fbcmap32 c;
+		unsigned char __user *ured;
+		unsigned char __user *ugreen;
+		unsigned char __user *ublue;
+		struct fb_cmap *cmap = &info->cmap;
+		unsigned int index, i;
+		u8 red, green, blue;
+
+		if (copy_from_user(&c, compat_ptr(arg), sizeof(c)))
+			return -EFAULT;
+		index = c.index;
+		ured = compat_ptr(c.red);
+		ugreen = compat_ptr(c.green);
+		ublue = compat_ptr(c.blue);
+
+		if (index > cmap->len || c.count > cmap->len - index)
+			return -EINVAL;
+
+		for (i = 0; i < c.count; i++) {
+			red = cmap->red[index + i] >> 8;
+			green = cmap->green[index + i] >> 8;
+			blue = cmap->blue[index + i] >> 8;
+			if (put_user(red, &ured[i]) ||
+			    put_user(green, &ugreen[i]) ||
+			    put_user(blue, &ublue[i]))
+				return -EFAULT;
+		}
+		return 0;
+	}
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+EXPORT_SYMBOL(sbusfb_compat_ioctl);
+#endif