All of lore.kernel.org
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: Xin Li <xin3.li@intel.com>,
	linux-kernel@vger.kernel.org, x86@kernel.org,
	kvm@vger.kernel.org
Cc: mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
	hpa@zytor.com, peterz@infradead.org, andrew.cooper3@citrix.com,
	seanjc@google.com, pbonzini@redhat.com, ravi.v.shankar@intel.com,
	jiangshanlai@gmail.com, shan.kang@intel.com
Subject: Re: [PATCH v8 05/33] x86/traps: add external_interrupt() to dispatch external interrupts
Date: Mon, 05 Jun 2023 19:52:11 +0200	[thread overview]
Message-ID: <87wn0h4x10.ffs@tglx> (raw)
In-Reply-To: <87ttvm6s2v.ffs@tglx>

On Mon, Jun 05 2023 at 13:56, Thomas Gleixner wrote:
> On Mon, Apr 10 2023 at 01:14, Xin Li wrote:
> How is this supposed to work once the vector space gets extended in a
> later version of FRED?
>
> Can we please think about this _now_ and not rewrite all of this two
> years down the road? 
>
> Even if that's not fully specified yet, here is the obvious question:
>
>  What are we going to do with the system vectors. Are they going to
>  stay just in the middle of the expanded vector space?
>
> That would be completely non-sensical as we'd end up with yet another
> segmentation of the vector space.
>
> So the obvious solution is to segment the vector space in the following
> way:
>
>   0  - 31   Exceptions/traps        - Cannot be moved
>  32         IRQ_MOVE_CLEANUP_VECTOR
>  33  - X    System vectors including APIC_SPURIOUS
>  X+1 - MAX  External interrupts
>
> This spares the IRQ_MOVE_CLEANUP_VECTOR hackery. It requires to move the
> ISA vectors, but that's not rocket science.

Which we just discussed completely away. :)

> That makes the external interrupt vector space trivially expandable, no?

So there is a theoretical problem here that device interrupts could
starve system vectors due to the priority scheme. Needs some thought.

That whole APIC priority muck is pretty useless as long as CR8 writes
are slower than sti/cli. When I tested that last (Broadwell) they were
significantly slower.

Also it's unclear how that expansion vector space is handled
vs. priorities.

Ideally event delivery would be FIFO because that's the only guarantee
for preventing starvation without having to configure priorities (which
is mostly a wrong guess anyway).

Thanks,

        tglx

  reply	other threads:[~2023-06-05 17:52 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-04-10  8:14 [PATCH v8 00/33] x86: enable FRED for x86-64 Xin Li
2023-04-10  8:14 ` [PATCH v8 01/33] x86/traps: let common_interrupt() handle IRQ_MOVE_CLEANUP_VECTOR Xin Li
2023-05-07 11:59   ` Borislav Petkov
2023-06-03 19:19     ` Li, Xin3
2023-06-03 20:51   ` Thomas Gleixner
2023-06-05 17:07     ` Thomas Gleixner
2023-06-05 17:09       ` H. Peter Anvin
2023-06-06 20:09         ` Thomas Gleixner
2023-06-06 23:16           ` Li, Xin3
2023-06-19  8:00           ` Li, Xin3
2023-06-19 14:22             ` Thomas Gleixner
2023-06-19 18:47               ` Li, Xin3
2023-06-19 19:16                 ` H. Peter Anvin
2023-06-20  0:04                   ` Li, Xin3
2023-04-10  8:14 ` [PATCH v8 02/33] x86/fred: make unions for the cs and ss fields in struct pt_regs Xin Li
2023-06-03  9:48   ` Borislav Petkov
2023-06-05 12:07   ` Thomas Gleixner
2023-06-05 17:12     ` H. Peter Anvin
2023-06-05 17:29       ` Thomas Gleixner
2023-04-10  8:14 ` [PATCH v8 03/33] x86/traps: add a system interrupt table for system interrupt dispatch Xin Li
2023-06-05  8:34   ` Thomas Gleixner
2023-06-06  8:05     ` Li, Xin3
2023-06-05  8:38   ` Thomas Gleixner
2023-06-05  8:39   ` Thomas Gleixner
2023-04-10  8:14 ` [PATCH v8 04/33] x86/traps: add install_system_interrupt_handler() Xin Li
2023-06-05  8:57   ` Thomas Gleixner
2023-06-06  5:46     ` Li, Xin3
2023-04-10  8:14 ` [PATCH v8 05/33] x86/traps: add external_interrupt() to dispatch external interrupts Xin Li
2023-06-05 11:56   ` Thomas Gleixner
2023-06-05 17:52     ` Thomas Gleixner [this message]
2023-06-19 19:16     ` Li, Xin3
2023-06-19 21:13       ` Thomas Gleixner
2023-06-20  0:16         ` Li, Xin3
2023-04-10  8:14 ` [PATCH v8 06/33] x86/cpufeature: add the cpu feature bit for FRED Xin Li
2023-04-10  8:14 ` [PATCH v8 07/33] x86/opcode: add ERETU, ERETS instructions to x86-opcode-map Xin Li
2023-04-10  8:14 ` [PATCH v8 08/33] x86/objtool: teach objtool about ERETU and ERETS Xin Li
2023-04-10  8:14 ` [PATCH v8 09/33] x86/cpu: add X86_CR4_FRED macro Xin Li
2023-06-05 12:01   ` Thomas Gleixner
2023-06-05 17:06     ` H. Peter Anvin
2023-06-05 17:19     ` H. Peter Anvin
2023-04-10  8:14 ` [PATCH v8 10/33] x86/fred: add Kconfig option for FRED (CONFIG_X86_FRED) Xin Li
2023-04-10  8:14 ` [PATCH v8 11/33] x86/fred: if CONFIG_X86_FRED is disabled, disable FRED support Xin Li
2023-04-10  8:14 ` [PATCH v8 12/33] x86/cpu: add MSR numbers for FRED configuration Xin Li
2023-04-10  8:14 ` [PATCH v8 13/33] x86/fred: header file for event types Xin Li
2023-04-10  8:14 ` [PATCH v8 14/33] x86/fred: header file with FRED definitions Xin Li
2023-04-10  8:14 ` [PATCH v8 15/33] x86/fred: reserve space for the FRED stack frame Xin Li
2023-04-10  8:14 ` [PATCH v8 16/33] x86/fred: add a page fault entry stub for FRED Xin Li
2023-04-10  8:14 ` [PATCH v8 17/33] x86/fred: add a debug " Xin Li
2023-04-10  8:14 ` [PATCH v8 18/33] x86/fred: add a NMI " Xin Li
2023-04-10  8:14 ` [PATCH v8 19/33] x86/fred: add a machine check " Xin Li
2023-04-10  8:14 ` [PATCH v8 20/33] x86/fred: FRED entry/exit and dispatch code Xin Li
2023-06-05 13:21   ` Thomas Gleixner
2023-04-10  8:14 ` [PATCH v8 21/33] x86/fred: FRED initialization code Xin Li
2023-06-05 12:15   ` Thomas Gleixner
2023-06-05 13:41   ` Thomas Gleixner
2023-04-10  8:14 ` [PATCH v8 22/33] x86/fred: update MSR_IA32_FRED_RSP0 during task switch Xin Li
2023-04-10  8:14 ` [PATCH v8 23/33] x86/fred: let ret_from_fork() jmp to fred_exit_user when FRED is enabled Xin Li
2023-04-10  8:14 ` [PATCH v8 24/33] x86/fred: disallow the swapgs instruction " Xin Li
2023-06-05 13:47   ` Thomas Gleixner
2023-04-10  8:14 ` [PATCH v8 25/33] x86/fred: no ESPFIX needed " Xin Li
2023-04-10  8:14 ` [PATCH v8 26/33] x86/fred: allow single-step trap and NMI when starting a new thread Xin Li
2023-06-05 13:50   ` Thomas Gleixner
2023-06-05 13:52     ` Thomas Gleixner
2023-04-10  8:14 ` [PATCH v8 27/33] x86/fred: fixup fault on ERETU by jumping to fred_entrypoint_user Xin Li
2023-04-10  8:14 ` [PATCH v8 28/33] x86/ia32: do not modify the DPL bits for a null selector Xin Li
2023-04-10  8:14 ` [PATCH v8 29/33] x86/fred: allow FRED systems to use interrupt vectors 0x10-0x1f Xin Li
2023-06-05 14:06   ` Thomas Gleixner
2023-06-05 16:55     ` H. Peter Anvin
2023-04-10  8:14 ` [PATCH v8 30/33] x86/fred: allow dynamic stack frame size Xin Li
2023-06-05 14:11   ` Thomas Gleixner
2023-06-06  6:18     ` Li, Xin3
2023-06-06 13:27       ` Thomas Gleixner
2023-06-06 23:08         ` H. Peter Anvin
2023-04-10  8:14 ` [PATCH v8 31/33] x86/fred: BUG() when ERETU with %rsp not equal to that when the ring 3 event was just delivered Xin Li
2023-06-05 14:15   ` Thomas Gleixner
2023-06-05 16:42     ` H. Peter Anvin
2023-06-05 17:16       ` Thomas Gleixner
2023-04-10  8:14 ` [PATCH v8 32/33] x86/fred: disable FRED by default in its early stage Xin Li
2023-04-10  8:14 ` [PATCH v8 33/33] KVM: x86/vmx: refactor VMX_DO_EVENT_IRQOFF to generate FRED stack frames Xin Li
2023-04-10 21:50   ` Sean Christopherson
2023-04-11  5:06     ` Li, Xin3
2023-04-11 18:34       ` Sean Christopherson
2023-04-11 22:50         ` Li, Xin3
2023-04-12 18:26     ` Li, Xin3
2023-04-12 19:37       ` Sean Christopherson
2023-04-10 18:37 ` [PATCH v8 00/33] x86: enable FRED for x86-64 Dave Hansen
2023-04-10 19:14   ` Li, Xin3
2023-04-10 19:32     ` Borislav Petkov
2023-04-10 19:38       ` Dave Hansen
2023-04-10 20:52         ` Li, Xin3
2023-04-11  4:14       ` Li, Xin3
2023-04-10 18:49 ` Dave Hansen
2023-04-10 19:16   ` Li, Xin3
2023-06-05 17:11     ` Thomas Gleixner
2023-06-05 17:22 ` H. Peter Anvin
2023-06-05 17:32   ` 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=87wn0h4x10.ffs@tglx \
    --to=tglx@linutronix.de \
    --cc=andrew.cooper3@citrix.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=jiangshanlai@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=ravi.v.shankar@intel.com \
    --cc=seanjc@google.com \
    --cc=shan.kang@intel.com \
    --cc=x86@kernel.org \
    --cc=xin3.li@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 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.