mirror of
https://github.com/torvalds/linux.git
synced 2024-11-10 14:11:52 +00:00
32019c659e
When trying to use copy_from_kernel_nofault() to read vsyscall page through a bpf program, the following oops was reported: BUG: unable to handle page fault for address: ffffffffff600000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 3231067 P4D 3231067 PUD 3233067 PMD 3235067 PTE 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 20390 Comm: test_progs ...... 6.7.0+ #58 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) ...... RIP: 0010:copy_from_kernel_nofault+0x6f/0x110 ...... Call Trace: <TASK> ? copy_from_kernel_nofault+0x6f/0x110 bpf_probe_read_kernel+0x1d/0x50 bpf_prog_2061065e56845f08_do_probe_read+0x51/0x8d trace_call_bpf+0xc5/0x1c0 perf_call_bpf_enter.isra.0+0x69/0xb0 perf_syscall_enter+0x13e/0x200 syscall_trace_enter+0x188/0x1c0 do_syscall_64+0xb5/0xe0 entry_SYSCALL_64_after_hwframe+0x6e/0x76 </TASK> ...... ---[ end trace 0000000000000000 ]--- The oops is triggered when: 1) A bpf program uses bpf_probe_read_kernel() to read from the vsyscall page and invokes copy_from_kernel_nofault() which in turn calls __get_user_asm(). 2) Because the vsyscall page address is not readable from kernel space, a page fault exception is triggered accordingly. 3) handle_page_fault() considers the vsyscall page address as a user space address instead of a kernel space address. This results in the fix-up setup by bpf not being applied and a page_fault_oops() is invoked due to SMAP. Considering handle_page_fault() has already considered the vsyscall page address as a userspace address, fix the problem by disallowing vsyscall page read for copy_from_kernel_nofault(). Originally-by: Thomas Gleixner <tglx@linutronix.de> Reported-by: syzbot+72aa0161922eba61b50e@syzkaller.appspotmail.com Closes: https://lore.kernel.org/bpf/CAG48ez06TZft=ATH1qh2c5mpS5BT8UakwNkzi6nvK5_djC-4Nw@mail.gmail.com Reported-by: xingwei lee <xrivendell7@gmail.com> Closes: https://lore.kernel.org/bpf/CABOYnLynjBoFZOf3Z4BhaZkc5hx_kHfsjiW+UWLoB=w33LvScw@mail.gmail.com Signed-off-by: Hou Tao <houtao1@huawei.com> Reviewed-by: Sohil Mehta <sohil.mehta@intel.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20240202103935.3154011-3-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
44 lines
1.1 KiB
C
44 lines
1.1 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
|
|
#include <linux/uaccess.h>
|
|
#include <linux/kernel.h>
|
|
|
|
#include <asm/vsyscall.h>
|
|
|
|
#ifdef CONFIG_X86_64
|
|
bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
|
|
{
|
|
unsigned long vaddr = (unsigned long)unsafe_src;
|
|
|
|
/*
|
|
* Do not allow userspace addresses. This disallows
|
|
* normal userspace and the userspace guard page:
|
|
*/
|
|
if (vaddr < TASK_SIZE_MAX + PAGE_SIZE)
|
|
return false;
|
|
|
|
/*
|
|
* Reading from the vsyscall page may cause an unhandled fault in
|
|
* certain cases. Though it is at an address above TASK_SIZE_MAX, it is
|
|
* usually considered as a user space address.
|
|
*/
|
|
if (is_vsyscall_vaddr(vaddr))
|
|
return false;
|
|
|
|
/*
|
|
* Allow everything during early boot before 'x86_virt_bits'
|
|
* is initialized. Needed for instruction decoding in early
|
|
* exception handlers.
|
|
*/
|
|
if (!boot_cpu_data.x86_virt_bits)
|
|
return true;
|
|
|
|
return __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits);
|
|
}
|
|
#else
|
|
bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
|
|
{
|
|
return (unsigned long)unsafe_src >= TASK_SIZE_MAX;
|
|
}
|
|
#endif
|