From: Jan Beulich <jbeulich@suse.com>
To: Andrew Cooper <amc96@srcf.net>,
Andrew Cooper <andrew.cooper3@citrix.com>
Cc: "Roger Pau Monné" <roger.pau@citrix.com>, "Wei Liu" <wl@xen.org>,
"Jun Nakajima" <jun.nakajima@intel.com>,
"Kevin Tian" <kevin.tian@intel.com>,
Xen-devel <xen-devel@lists.xenproject.org>
Subject: Re: [PATCH v2 4/4] x86/spec-ctrl: Fix NMI race condition with VT-x MSR_SPEC_CTRL handling
Date: Thu, 20 Jan 2022 13:11:51 +0100 [thread overview]
Message-ID: <9415e194-3c31-b7cb-3a6a-3ab6aa432908@suse.com> (raw)
In-Reply-To: <914f2264-d424-e42b-31ac-1832224cc1d9@srcf.net>
On 20.01.2022 12:55, Andrew Cooper wrote:
> On 20/01/2022 08:14, Jan Beulich wrote:
>> On 19.01.2022 18:00, Andrew Cooper wrote:
>>> On 19/01/2022 13:42, Jan Beulich wrote:
>>>> On 17.01.2022 19:34, Andrew Cooper wrote:
>>>>> --- a/xen/arch/x86/hvm/vmx/entry.S
>>>>> +++ b/xen/arch/x86/hvm/vmx/entry.S
>>>>> @@ -35,7 +35,14 @@ ENTRY(vmx_asm_vmexit_handler)
>>>>>
>>>>> /* SPEC_CTRL_ENTRY_FROM_VMX Req: b=curr %rsp=regs/cpuinfo, Clob: acd */
>>>>> ALTERNATIVE "", DO_OVERWRITE_RSB, X86_FEATURE_SC_RSB_HVM
>>>>> - ALTERNATIVE "", DO_SPEC_CTRL_ENTRY_FROM_HVM, X86_FEATURE_SC_MSR_HVM
>>>>> +
>>>>> + .macro restore_spec_ctrl
>>>>> + mov $MSR_SPEC_CTRL, %ecx
>>>>> + movzbl CPUINFO_xen_spec_ctrl(%rsp), %eax
>>>>> + xor %edx, %edx
>>>>> + wrmsr
>>>>> + .endm
>>>>> + ALTERNATIVE "", restore_spec_ctrl, X86_FEATURE_SC_MSR_HVM
>>>>> /* WARNING! `ret`, `call *`, `jmp *` not safe before this point. */
>>>>>
>>>>> /* Hardware clears MSR_DEBUGCTL on VMExit. Reinstate it if debugging Xen. */
>>>>> @@ -82,8 +89,7 @@ UNLIKELY_END(realmode)
>>>>> mov VCPUMSR_spec_ctrl_raw(%rax), %eax
>>>>>
>>>>> /* WARNING! `ret`, `call *`, `jmp *` not safe beyond this point. */
>>>>> - /* SPEC_CTRL_EXIT_TO_VMX Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */
>>>>> - ALTERNATIVE "", DO_SPEC_CTRL_EXIT_TO_GUEST, X86_FEATURE_SC_MSR_HVM
>>>>> + /* SPEC_CTRL_EXIT_TO_VMX Req: %rsp=regs/cpuinfo Clob: */
>>>>> ALTERNATIVE "", __stringify(verw CPUINFO_verw_sel(%rsp)), X86_FEATURE_SC_VERW_HVM
>>>> I notice you did update this clobber remark, but what about the one further
>>>> up in context?
>>> What about it? It still clobbers %eax, %ecx and %edx.
>> Oh, sorry - I did look at DO_OVERWRITE_RSB only, not paying attention
>> to the now open-coded 2nd part, which - due to the blank line - doesn't
>> appear connected to the comment anymore.
>
> Yeah - it's a little harder now that it isn't a single line. The
> req/clob information really is most useful at the start of the block,
> because that's where it is important to get the context correct.
>
> Can I take this as an R-by then?
Please do; I should have said so earlier on.
Jan
next prev parent reply other threads:[~2022-01-20 12:12 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-17 18:34 [PATCH v2 0/4] x86/spec-ctrl: Fix NMI race condition Andrew Cooper
2022-01-17 18:34 ` [PATCH v2 1/4] x86/guest: Introduce {get,set}_reg() infrastructure Andrew Cooper
2022-01-19 13:28 ` Jan Beulich
2022-01-19 18:00 ` Andrew Cooper
2022-01-17 18:34 ` [PATCH v2 2/4] x86/msr: Split MSR_SPEC_CTRL handling Andrew Cooper
2022-01-19 13:30 ` Jan Beulich
2022-01-17 18:34 ` [PATCH v2 3/4] x86/spec-ctrl: Drop SPEC_CTRL_{ENTRY_FROM,EXIT_TO}_HVM Andrew Cooper
2022-01-17 18:34 ` [PATCH v2 4/4] x86/spec-ctrl: Fix NMI race condition with VT-x MSR_SPEC_CTRL handling Andrew Cooper
2022-01-19 13:42 ` Jan Beulich
2022-01-19 17:00 ` Andrew Cooper
2022-01-20 8:14 ` Jan Beulich
2022-01-20 11:55 ` Andrew Cooper
2022-01-20 12:11 ` Jan Beulich [this message]
2022-01-21 7:56 ` Jan Beulich
2022-01-17 19:25 ` [PATCH v2 5/4] x86/hvm: Drop hvm_{get,set}_guest_bndcfgs() and use {get,set}_regs() instead Andrew Cooper
2022-01-19 13:50 ` Jan Beulich
2022-01-19 16:53 ` Andrew Cooper
2022-01-20 8:20 ` Jan Beulich
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=9415e194-3c31-b7cb-3a6a-3ab6aa432908@suse.com \
--to=jbeulich@suse.com \
--cc=amc96@srcf.net \
--cc=andrew.cooper3@citrix.com \
--cc=jun.nakajima@intel.com \
--cc=kevin.tian@intel.com \
--cc=roger.pau@citrix.com \
--cc=wl@xen.org \
--cc=xen-devel@lists.xenproject.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.