linux-kernel - Re: [PATCH v5 28/34] x86/fred: fixup fault on ERETU by jumping to fred_entrypoint

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <D3DB8A8F-7293-4715-AAB6-213F00CB521C@zytor.com>
Date:   Fri, 17 Mar 2023 14:00:16 -0700
From:   "H. Peter Anvin" <hpa@...or.com>
To:     andrew.cooper3@...rix.com, Lai Jiangshan <jiangshanlai@...il.com>,
        Xin Li <xin3.li@...el.com>
CC:     linux-kernel@...r.kernel.org, x86@...nel.org, kvm@...r.kernel.org,
        tglx@...utronix.de, mingo@...hat.com, bp@...en8.de,
        dave.hansen@...ux.intel.com, peterz@...radead.org,
        seanjc@...gle.com, pbonzini@...hat.com, ravi.v.shankar@...el.com
Subject: Re: [PATCH v5 28/34] x86/fred: fixup fault on ERETU by jumping to fred_entrypoint_user

On March 17, 2023 2:55:44 AM PDT, andrew.cooper3@...rix.com wrote:
>On 17/03/2023 9:39 am, Lai Jiangshan wrote:
>>> +#ifdef CONFIG_X86_FRED
>>> +static bool ex_handler_eretu(const struct exception_table_entry *fixup,
>>> +                            struct pt_regs *regs, unsigned long error_code)
>>> +{
>>> +       struct pt_regs *uregs = (struct pt_regs *)(regs->sp - offsetof(struct pt_regs, ip));
>>> +       unsigned short ss = uregs->ss;
>>> +       unsigned short cs = uregs->cs;
>>> +
>>> +       fred_info(uregs)->edata = fred_event_data(regs);
>>> +       uregs->ssx = regs->ssx;
>>> +       uregs->ss = ss;
>>> +       uregs->csx = regs->csx;
>>> +       uregs->current_stack_level = 0;
>>> +       uregs->cs = cs;
>> Hello
>>
>> If the ERETU instruction had tried to return from NMI to ring3 and just faulted,
>> is NMI still blocked?
>>
>> We know that IRET unconditionally enables NMI, but I can't find any clue in the
>> FRED's manual.
>>
>> In the pseudocode of ERETU in the manual, it seems that NMI is only enabled when
>> ERETU succeeds with bit28 in csx set.  If so, this code will fail to reenable
>> NMI if bit28 is not explicitly re-set in csx.
>
>IRET clearing NMI blocking is the source of an immense amount of grief,
>and ultimately the reason why Linux and others can't use supervisor
>shadow stacks at the moment.
>
>Changing this property, so NMIs only get unblocked on successful
>execution of an ERET{S,U}, was a key demand of the FRED spec.
>
>i.e. until you have successfully ERET*'d, you're still logically in the
>NMI handler and NMIs need to remain blocked even when handling the #GP
>from a bad ERET.
>
>~Andrew

This is correct.