All of lore.kernel.org
 help / color / mirror / Atom feed
From: Laurent Desnogues <laurent.desnogues@gmail.com>
To: edgar.iglesias@xilinx.com
Cc: Peter Maydell <peter.maydell@linaro.org>,
	figlesia@xilinx.com, sstabellini@kernel.org,
	sai.pavan.boddu@xilinx.com, frasse.iglesias@gmail.com,
	alistair@alistair23.me,
	Richard Henderson <richard.henderson@linaro.org>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
	frederic.konrad@adacore.com, qemu-arm <qemu-arm@nongnu.org>,
	"Edgar E. Iglesias" <edgar.iglesias@gmail.com>
Subject: Re: [Qemu-devel] [PATCH v1 10/12] target/arm: Add the Cortex-A72
Date: Tue, 9 Oct 2018 15:40:13 +0200	[thread overview]
Message-ID: <CABoDooObRovXo+Bw9tJWHy61vhTkysJx1D7016qhYgs1=O7ztA@mail.gmail.com> (raw)
In-Reply-To: <20181009131736.GT4229@toto>

Hello,

On Tue, Oct 9, 2018 at 3:19 PM Edgar E. Iglesias
<edgar.iglesias@xilinx.com> wrote:
>
> Another A72 related thing I wanted to check with you. A month or two ago I was
> looking at an issue with Linux running very slowly on our models.
> Something that popped up was that Linux was running a couple of spectre related
> "workarounds" and "hardening" sequences on the QEMU A72s.
>
> There are a couple of bits in the ID_AARCH64_PFR0 register that
> Linux checks before enabling the sequences but I never found any
> documentation of them in the specs. Bits 56 and 60.
>
> In Linux these are refered to as:
> ID_AA64PFR0_CSV2_SHIFT
> ID_AA64PFR0_CSV3_SHIFT
>
> This is what we have in our tree:
>
>     cpu->gic_vprebits = 5;
>     define_arm_cp_regs(cpu, cortex_a57_a53_cp_reginfo);
>
>     /* Xilinx FIXUPs.  */
>     /* These indicate the BP hardening and KPTI aren't needed.  */
>     cpu->id_aa64pfr0 |= (uint64_t)1 << 56; /* BP.  */
>     cpu->id_aa64pfr0 |= (uint64_t)1 << 60; /* KPTI.  */
> }
>
> Do you know what these are?
> Should we be setting these in QEMU?

These fields are publicly documented in the system register specification:

https://developer.arm.com/products/architecture/cpu-architecture/a-profile/exploration-tools

These are ARMv8.5 fields, I don't think these should be set by default
for Cortex-A72. Of course nothing prevents you from defining a
specific CPU with these fields set to boot faster :-)  Or perhaps add
a property to override the default value of these registers?


Laurent

  reply	other threads:[~2018-10-09 13:41 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-03 15:07 [Qemu-devel] [PATCH v1 00/12] arm: Add first models of Xilinx Versal SoC Edgar E. Iglesias
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 01/12] net: cadence_gem: Disable TSU feature bit Edgar E. Iglesias
2018-10-04 17:36   ` Alistair Francis
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 02/12] net: cadence_gem: Announce availability of priority queues Edgar E. Iglesias
2018-10-04 22:14   ` Alistair
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 03/12] net: cadence_gem: Use uint32_t for 32bit descriptor words Edgar E. Iglesias
2018-10-04 22:16   ` Alistair
2018-10-05 23:09   ` Philippe Mathieu-Daudé
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 04/12] net: cadence_gem: Add macro with max number of " Edgar E. Iglesias
2018-10-04 22:16   ` Alistair
2018-10-05 23:10   ` Philippe Mathieu-Daudé
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 05/12] net: cadence_gem: Add support for extended descriptors Edgar E. Iglesias
2018-10-04 22:29   ` Alistair
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 06/12] net: cadence_gem: Add support for selecting the DMA MemoryRegion Edgar E. Iglesias
2018-10-05 22:35   ` Alistair
2018-10-05 23:14   ` Philippe Mathieu-Daudé
2018-10-08 12:26     ` Peter Maydell
2018-10-08 12:24   ` Peter Maydell
2018-10-08 19:54     ` Edgar E. Iglesias
2018-10-08 12:30   ` Peter Maydell
2018-10-08 19:55     ` Edgar E. Iglesias
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 07/12] net: cadence_gem: Implement support for 64bit descriptor addresses Edgar E. Iglesias
2018-10-05 23:12   ` Alistair
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 08/12] net: cadence_gem: Announce 64bit addressing support Edgar E. Iglesias
2018-10-04 22:32   ` Alistair
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 09/12] target-arm: powerctl: Enable HVC when starting CPUs to EL2 Edgar E. Iglesias
2018-10-08 12:41   ` Peter Maydell
2018-10-08 19:56     ` Edgar E. Iglesias
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 10/12] target/arm: Add the Cortex-A72 Edgar E. Iglesias
2018-10-08 13:10   ` Peter Maydell
2018-10-08 21:34     ` Edgar E. Iglesias
2018-10-09  9:30       ` Peter Maydell
2018-10-09 13:17         ` Edgar E. Iglesias
2018-10-09 13:40           ` Laurent Desnogues [this message]
2018-10-09 14:56             ` Edgar E. Iglesias
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 11/12] hw/arm: versal: Add a model of Xilinx Versal SoC Edgar E. Iglesias
2018-10-05 23:21   ` Philippe Mathieu-Daudé
2018-10-08 13:19   ` Peter Maydell
2018-10-08 22:25     ` Edgar E. Iglesias
2018-10-03 15:07 ` [Qemu-devel] [PATCH v1 12/12] hw/arm: versal: Add a virtual Xilinx Versal board Edgar E. Iglesias
2018-10-08 14:08 ` [Qemu-devel] [PATCH v1 00/12] arm: Add first models of Xilinx Versal SoC Peter Maydell
2018-10-09 12:57   ` Edgar E. Iglesias

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='CABoDooObRovXo+Bw9tJWHy61vhTkysJx1D7016qhYgs1=O7ztA@mail.gmail.com' \
    --to=laurent.desnogues@gmail.com \
    --cc=alistair@alistair23.me \
    --cc=edgar.iglesias@gmail.com \
    --cc=edgar.iglesias@xilinx.com \
    --cc=figlesia@xilinx.com \
    --cc=frasse.iglesias@gmail.com \
    --cc=frederic.konrad@adacore.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=sai.pavan.boddu@xilinx.com \
    --cc=sstabellini@kernel.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.