From: "Tian, Kevin" <kevin.tian@intel.com>
To: Thomas Gleixner <tglx@linutronix.de>,
"Zhong, Yang" <yang.zhong@intel.com>,
"x86@kernel.org" <x86@kernel.org>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"mingo@redhat.com" <mingo@redhat.com>,
"bp@alien8.de" <bp@alien8.de>,
"dave.hansen@linux.intel.com" <dave.hansen@linux.intel.com>,
"pbonzini@redhat.com" <pbonzini@redhat.com>
Cc: "Christopherson,, Sean" <seanjc@google.com>,
"Nakajima, Jun" <jun.nakajima@intel.com>,
"jing2.liu@linux.intel.com" <jing2.liu@linux.intel.com>,
"Liu, Jing2" <jing2.liu@intel.com>,
"Zhong, Yang" <yang.zhong@intel.com>
Subject: RE: [PATCH 15/19] kvm: x86: Save and restore guest XFD_ERR properly
Date: Sun, 12 Dec 2021 01:50:21 +0000 [thread overview]
Message-ID: <BL1PR11MB5271FDCE84F4D25D0241D5998C739@BL1PR11MB5271.namprd11.prod.outlook.com> (raw)
In-Reply-To: <87zgp7uv6g.ffs@tglx>
> From: Thomas Gleixner <tglx@linutronix.de>
> Sent: Saturday, December 11, 2021 9:29 PM
>
> Kevin,
>
> On Sat, Dec 11 2021 at 03:07, Kevin Tian wrote:
> >> From: Thomas Gleixner <tglx@linutronix.de>
> >> #NM in the guest is slow path, right? So why are you trying to optimize
> >> for it?
> >
> > This is really good information. The current logic is obviously
> > based on the assumption that #NM is frequently triggered.
>
> More context.
>
> When an application want's to use AMX, it invokes the prctl() which
> grants permission. If permission is granted then still the kernel FPU
> state buffers are default size and XFD is armed.
>
> When a thread of that process issues the first AMX (tile) instruction,
> then #NM is raised.
>
> The #NM handler does:
>
> 1) Read MSR_XFD_ERR. If 0, goto regular #NM
>
> 2) Write MSR_XFD_ERR to 0
>
> 3) Check whether the process has permission granted. If not,
> raise SIGILL and return.
>
> 4) Allocate and install a larger FPU state buffer for the task.
> If allocation fails, raise SIGSEGV and return.
>
> 5) Disarm XFD for that task
>
> That means one thread takes at max. one AMX/XFD related #NM during its
> lifetime, which means two VMEXITs.
>
> If there are other XFD controlled facilities in the future, then it will
> be NR_USED_XFD_CONTROLLED_FACILITIES * 2 VMEXITs per thread which
> uses
> them. Not the end of the world either.
>
> Looking at the targeted application space it's pretty unlikely that
> tasks which utilize AMX are going to be so short lived that the overhead
> of these VMEXITs really matters.
>
> This of course can be revisited when there is a sane use case, but
> optimizing for it prematurely does not buy us anything else than
> pointless complexity.
I get all above.
I guess the original open is also about the frequency of #NM not due
to XFD. For Linux guest looks it's not a problem since CR0.TS is not set
now when math emulation is not required:
DEFINE_IDTENTRY(exc_device_not_available)
{
...
/* This should not happen. */
if (WARN(cr0 & X86_CR0_TS, "CR0.TS was set")) {
/* Try to fix it up and carry on. */
write_cr0(cr0 & ~X86_CR0_TS);
} else {
/*
* Something terrible happened, and we're better off trying
* to kill the task than getting stuck in a never-ending
* loop of #NM faults.
*/
die("unexpected #NM exception", regs, 0);
}
}
It may affect guest which still uses CR0.TS to do lazy save. But likely
modern OSes all move to eager save approach so always trapping #NM
should be fine.
Is this understanding correct?
Thanks
Kevin
next prev parent reply other threads:[~2021-12-12 1:50 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-08 0:03 [PATCH 00/19] AMX Support in KVM Yang Zhong
2021-12-08 0:03 ` [PATCH 01/19] x86/fpu: Extend prctl() with guest permissions Yang Zhong
2021-12-14 0:16 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 02/19] x86/fpu: Prepare KVM for dynamically enabled states Yang Zhong
2021-12-13 9:12 ` Paolo Bonzini
2021-12-13 12:00 ` Thomas Gleixner
2021-12-13 12:45 ` Paolo Bonzini
2021-12-13 19:50 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 03/19] kvm: x86: Fix xstate_required_size() to follow XSTATE alignment rule Yang Zhong
2021-12-08 0:03 ` [PATCH 04/19] kvm: x86: Check guest xstate permissions when KVM_SET_CPUID2 Yang Zhong
2021-12-08 0:03 ` [PATCH 05/19] x86/fpu: Move xfd initialization out of __fpstate_reset() to the callers Yang Zhong
2021-12-10 22:33 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 06/19] x86/fpu: Add reallocation mechanims for KVM Yang Zhong
2021-12-08 0:03 ` [PATCH 07/19] kvm: x86: Propagate fpstate reallocation error to userspace Yang Zhong
2021-12-10 15:44 ` Paolo Bonzini
2021-12-08 0:03 ` [PATCH 08/19] x86/fpu: Move xfd_update_state() to xstate.c and export symbol Yang Zhong
2021-12-10 22:44 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 09/19] kvm: x86: Prepare reallocation check Yang Zhong
2021-12-13 9:16 ` Paolo Bonzini
2021-12-14 7:06 ` Tian, Kevin
2021-12-14 10:16 ` Paolo Bonzini
2021-12-14 14:41 ` Liu, Jing2
2021-12-15 7:09 ` Tian, Kevin
2021-12-08 0:03 ` [PATCH 10/19] kvm: x86: Emulate WRMSR of guest IA32_XFD Yang Zhong
2021-12-10 16:02 ` Paolo Bonzini
2021-12-13 7:51 ` Liu, Jing2
2021-12-13 9:01 ` Paolo Bonzini
2021-12-14 10:26 ` Yang Zhong
2021-12-14 11:24 ` Paolo Bonzini
2021-12-10 23:09 ` Thomas Gleixner
2021-12-13 15:06 ` Paolo Bonzini
2021-12-13 19:45 ` Thomas Gleixner
2021-12-13 21:23 ` Thomas Gleixner
2021-12-14 7:16 ` Tian, Kevin
2021-12-08 0:03 ` [PATCH 11/19] kvm: x86: Check fpstate reallocation in XSETBV emulation Yang Zhong
2021-12-08 0:03 ` [PATCH 12/19] x86/fpu: Prepare KVM for bringing XFD state back in-sync Yang Zhong
2021-12-10 23:11 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 13/19] kvm: x86: Disable WRMSR interception for IA32_XFD on demand Yang Zhong
2021-12-08 7:23 ` Liu, Jing2
2021-12-08 0:03 ` [PATCH 14/19] x86/fpu: Prepare for KVM XFD_ERR handling Yang Zhong
2021-12-10 16:16 ` Paolo Bonzini
2021-12-10 23:20 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 15/19] kvm: x86: Save and restore guest XFD_ERR properly Yang Zhong
2021-12-10 16:23 ` Paolo Bonzini
2021-12-10 22:01 ` Paolo Bonzini
2021-12-12 13:10 ` Yang Zhong
2021-12-11 0:10 ` Thomas Gleixner
2021-12-11 1:31 ` Paolo Bonzini
2021-12-11 3:23 ` Tian, Kevin
2021-12-11 13:10 ` Thomas Gleixner
2021-12-11 3:07 ` Tian, Kevin
2021-12-11 13:29 ` Thomas Gleixner
2021-12-12 1:50 ` Tian, Kevin [this message]
2021-12-12 9:10 ` Paolo Bonzini
2021-12-08 0:03 ` [PATCH 16/19] kvm: x86: Introduce KVM_{G|S}ET_XSAVE2 ioctl Yang Zhong
2021-12-10 16:25 ` Paolo Bonzini
2021-12-10 16:30 ` Paolo Bonzini
2021-12-10 22:13 ` Paolo Bonzini
2021-12-13 8:23 ` Wang, Wei W
2021-12-13 9:24 ` Paolo Bonzini
2021-12-14 6:06 ` Wang, Wei W
2021-12-14 6:18 ` Paolo Bonzini
2021-12-15 2:39 ` Wang, Wei W
2021-12-15 13:42 ` Paolo Bonzini
2021-12-16 8:25 ` Wang, Wei W
2021-12-16 10:28 ` Paolo Bonzini
2021-12-20 17:54 ` State Component 18 and Palette 1 (Re: [PATCH 16/19] kvm: x86: Introduce KVM_{G|S}ET_XSAVE2 ioctl) Nakajima, Jun
2021-12-22 14:44 ` Paolo Bonzini
2021-12-22 23:47 ` Nakajima, Jun
2021-12-22 14:52 ` Dave Hansen
2021-12-22 23:51 ` Nakajima, Jun
2021-12-13 10:10 ` [PATCH 16/19] kvm: x86: Introduce KVM_{G|S}ET_XSAVE2 ioctl Thomas Gleixner
2021-12-13 10:43 ` Paolo Bonzini
2021-12-13 12:40 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 17/19] docs: virt: api.rst: Document the new KVM_{G, S}ET_XSAVE2 ioctls Yang Zhong
2021-12-08 0:03 ` [PATCH 18/19] kvm: x86: AMX XCR0 support for guest Yang Zhong
2021-12-10 16:30 ` Paolo Bonzini
2021-12-08 0:03 ` [PATCH 19/19] kvm: x86: Add AMX CPUIDs support Yang Zhong
2021-12-10 21:52 ` Paolo Bonzini
2021-12-11 21:20 ` [PATCH 00/19] AMX Support in KVM Thomas Gleixner
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=BL1PR11MB5271FDCE84F4D25D0241D5998C739@BL1PR11MB5271.namprd11.prod.outlook.com \
--to=kevin.tian@intel.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=jing2.liu@intel.com \
--cc=jing2.liu@linux.intel.com \
--cc=jun.nakajima@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
--cc=yang.zhong@intel.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).