From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions 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) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- drivers/char/uv_mmtimer.c | 220 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 220 insertions(+) create mode 100644 drivers/char/uv_mmtimer.c (limited to 'drivers/char/uv_mmtimer.c') diff --git a/drivers/char/uv_mmtimer.c b/drivers/char/uv_mmtimer.c new file mode 100644 index 000000000..956ebe208 --- /dev/null +++ b/drivers/char/uv_mmtimer.c @@ -0,0 +1,220 @@ +/* + * Timer device implementation for SGI UV platform. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 2009 Silicon Graphics, Inc. All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +MODULE_AUTHOR("Dimitri Sivanich "); +MODULE_DESCRIPTION("SGI UV Memory Mapped RTC Timer"); +MODULE_LICENSE("GPL"); + +/* name of the device, usually in /dev */ +#define UV_MMTIMER_NAME "mmtimer" +#define UV_MMTIMER_DESC "SGI UV Memory Mapped RTC Timer" +#define UV_MMTIMER_VERSION "1.0" + +static long uv_mmtimer_ioctl(struct file *file, unsigned int cmd, + unsigned long arg); +static int uv_mmtimer_mmap(struct file *file, struct vm_area_struct *vma); + +/* + * Period in femtoseconds (10^-15 s) + */ +static unsigned long uv_mmtimer_femtoperiod; + +static const struct file_operations uv_mmtimer_fops = { + .owner = THIS_MODULE, + .mmap = uv_mmtimer_mmap, + .unlocked_ioctl = uv_mmtimer_ioctl, + .llseek = noop_llseek, +}; + +/** + * uv_mmtimer_ioctl - ioctl interface for /dev/uv_mmtimer + * @file: file structure for the device + * @cmd: command to execute + * @arg: optional argument to command + * + * Executes the command specified by @cmd. Returns 0 for success, < 0 for + * failure. + * + * Valid commands: + * + * %MMTIMER_GETOFFSET - Should return the offset (relative to the start + * of the page where the registers are mapped) for the counter in question. + * + * %MMTIMER_GETRES - Returns the resolution of the clock in femto (10^-15) + * seconds + * + * %MMTIMER_GETFREQ - Copies the frequency of the clock in Hz to the address + * specified by @arg + * + * %MMTIMER_GETBITS - Returns the number of bits in the clock's counter + * + * %MMTIMER_MMAPAVAIL - Returns 1 if registers can be mmap'd into userspace + * + * %MMTIMER_GETCOUNTER - Gets the current value in the counter and places it + * in the address specified by @arg. + */ +static long uv_mmtimer_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + int ret = 0; + + switch (cmd) { + case MMTIMER_GETOFFSET: /* offset of the counter */ + /* + * Starting with HUB rev 2.0, the UV RTC register is + * replicated across all cachelines of it's own page. + * This allows faster simultaneous reads from a given socket. + * + * The offset returned is in 64 bit units. + */ + if (uv_get_min_hub_revision_id() == 1) + ret = 0; + else + ret = ((uv_blade_processor_id() * L1_CACHE_BYTES) % + PAGE_SIZE) / 8; + break; + + case MMTIMER_GETRES: /* resolution of the clock in 10^-15 s */ + if (copy_to_user((unsigned long __user *)arg, + &uv_mmtimer_femtoperiod, sizeof(unsigned long))) + ret = -EFAULT; + break; + + case MMTIMER_GETFREQ: /* frequency in Hz */ + if (copy_to_user((unsigned long __user *)arg, + &sn_rtc_cycles_per_second, + sizeof(unsigned long))) + ret = -EFAULT; + break; + + case MMTIMER_GETBITS: /* number of bits in the clock */ + ret = hweight64(UVH_RTC_REAL_TIME_CLOCK_MASK); + break; + + case MMTIMER_MMAPAVAIL: + ret = 1; + break; + + case MMTIMER_GETCOUNTER: + if (copy_to_user((unsigned long __user *)arg, + (unsigned long *)uv_local_mmr_address(UVH_RTC), + sizeof(unsigned long))) + ret = -EFAULT; + break; + default: + ret = -ENOTTY; + break; + } + return ret; +} + +/** + * uv_mmtimer_mmap - maps the clock's registers into userspace + * @file: file structure for the device + * @vma: VMA to map the registers into + * + * Calls remap_pfn_range() to map the clock's registers into + * the calling process' address space. + */ +static int uv_mmtimer_mmap(struct file *file, struct vm_area_struct *vma) +{ + unsigned long uv_mmtimer_addr; + + if (vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EINVAL; + + if (vma->vm_flags & VM_WRITE) + return -EPERM; + + if (PAGE_SIZE > (1 << 16)) + return -ENOSYS; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + uv_mmtimer_addr = UV_LOCAL_MMR_BASE | UVH_RTC; + uv_mmtimer_addr &= ~(PAGE_SIZE - 1); + uv_mmtimer_addr &= 0xfffffffffffffffUL; + + if (remap_pfn_range(vma, vma->vm_start, uv_mmtimer_addr >> PAGE_SHIFT, + PAGE_SIZE, vma->vm_page_prot)) { + printk(KERN_ERR "remap_pfn_range failed in uv_mmtimer_mmap\n"); + return -EAGAIN; + } + + return 0; +} + +static struct miscdevice uv_mmtimer_miscdev = { + MISC_DYNAMIC_MINOR, + UV_MMTIMER_NAME, + &uv_mmtimer_fops +}; + + +/** + * uv_mmtimer_init - device initialization routine + * + * Does initial setup for the uv_mmtimer device. + */ +static int __init uv_mmtimer_init(void) +{ + if (!is_uv_system()) { + printk(KERN_ERR "%s: Hardware unsupported\n", UV_MMTIMER_NAME); + return -1; + } + + /* + * Sanity check the cycles/sec variable + */ + if (sn_rtc_cycles_per_second < 100000) { + printk(KERN_ERR "%s: unable to determine clock frequency\n", + UV_MMTIMER_NAME); + return -1; + } + + uv_mmtimer_femtoperiod = ((unsigned long)1E15 + + sn_rtc_cycles_per_second / 2) / + sn_rtc_cycles_per_second; + + if (misc_register(&uv_mmtimer_miscdev)) { + printk(KERN_ERR "%s: failed to register device\n", + UV_MMTIMER_NAME); + return -1; + } + + printk(KERN_INFO "%s: v%s, %ld MHz\n", UV_MMTIMER_DESC, + UV_MMTIMER_VERSION, + sn_rtc_cycles_per_second/(unsigned long)1E6); + + return 0; +} + +module_init(uv_mmtimer_init); -- cgit v1.3.1