All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Heiko Stübner" <heiko@sntech.de>
To: Palmer Dabbelt <palmer@dabbelt.com>, Stefan O'Rear <sorear@fastmail.com>
Cc: linux-riscv@lists.infradead.org, samuel@sholland.org,
	guoren@kernel.org, christoph.muellner@vrull.eu,
	conor.dooley@microchip.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH RFC 2/2] RISC-V: add T-Head vector errata handling
Date: Thu, 22 Jun 2023 22:35:50 +0200	[thread overview]
Message-ID: <9132027.CDJkKcVGEf@diego> (raw)
In-Reply-To: <23381fc8-c297-46ed-9e11-a2643e18e4c9@app.fastmail.com>

Hi Stefan,

Am Donnerstag, 22. Juni 2023, 20:58:37 CEST schrieb Stefan O'Rear:
> On Thu, Jun 22, 2023, at 1:39 PM, Heiko Stübner wrote:
> > Am Dienstag, 13. Juni 2023, 08:35:53 CEST schrieb Stefan O'Rear:
> >> vxrm and vxsat are part of fcsr in 0.7.1, so they should already have been
> >> handled by __fstate_save and __fstate_restore, and this code is likely to
> >> misbehave (saving the new process's vxrm/vxsat in the old process's save area
> >> because float state is swapped before vector state in __switch_to).
> >
> > I'm not sure I follow your description but may be overlooking or have
> > misunderstood something.
> >
> > Somehow I way to often have trouble resolving CSR addresses, but according
> > to openSBI, FCSR has the location of 0x3
> > (#define CSR_FCSR 0x003 in include/sbi/riscv_encoding.h)
> >
> > where CSR_VXSAT and CSR_VXRM are at 0x9 and 0xa respectively.
> > (#define CSR_VXSAT 0x9 and  #define CSR_VXRM 0xa)
> >
> >
> > And looking at __fstate_save + __fstate_restore the only CSRs accessed seem
> > to be CSR_STATUS and FCSR itself.
> >
> > I definitly won't claim to be right, but don't see the issue yet.
> >
> >
> > Thanks for a hint
> > Heiko
> 
> Are you aware of "3.7. Vector Fixed-Point Fields in fcsr" in
> riscv-v-spec-0.7.1.pdf?

oh wow, thanks a lot for that pointer, now I understand your concern.

So in vector-0.7.1 fcsr[10:9] mirrors vxrm and fcsr[8] mirrors vxsat.


On a positive note, the T-Head cores seem to not implement the full
vector 0.7.1 specification after all, in the documentation I have [0]
fcsr[31:8] are declared as "0" and uppermost bits are [7:5] for the "frm"
field.

So I guess a code comment should suffice to explain :-)


Regards
Heiko


[0] https://github.com/T-head-Semi/openc906/blob/main/doc/%E7%8E%84%E9%93%81C906%E7%94%A8%E6%88%B7%E6%89%8B%E5%86%8C.pdf
16.3.1.3 浮点控制状态寄存器（FCSR） on page 334



WARNING: multiple messages have this Message-ID (diff)
From: "Heiko Stübner" <heiko@sntech.de>
To: Palmer Dabbelt <palmer@dabbelt.com>, Stefan O'Rear <sorear@fastmail.com>
Cc: linux-riscv@lists.infradead.org, samuel@sholland.org,
	guoren@kernel.org, christoph.muellner@vrull.eu,
	conor.dooley@microchip.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH RFC 2/2] RISC-V: add T-Head vector errata handling
Date: Thu, 22 Jun 2023 22:35:50 +0200	[thread overview]
Message-ID: <9132027.CDJkKcVGEf@diego> (raw)
In-Reply-To: <23381fc8-c297-46ed-9e11-a2643e18e4c9@app.fastmail.com>

Hi Stefan,

Am Donnerstag, 22. Juni 2023, 20:58:37 CEST schrieb Stefan O'Rear:
> On Thu, Jun 22, 2023, at 1:39 PM, Heiko Stübner wrote:
> > Am Dienstag, 13. Juni 2023, 08:35:53 CEST schrieb Stefan O'Rear:
> >> vxrm and vxsat are part of fcsr in 0.7.1, so they should already have been
> >> handled by __fstate_save and __fstate_restore, and this code is likely to
> >> misbehave (saving the new process's vxrm/vxsat in the old process's save area
> >> because float state is swapped before vector state in __switch_to).
> >
> > I'm not sure I follow your description but may be overlooking or have
> > misunderstood something.
> >
> > Somehow I way to often have trouble resolving CSR addresses, but according
> > to openSBI, FCSR has the location of 0x3
> > (#define CSR_FCSR 0x003 in include/sbi/riscv_encoding.h)
> >
> > where CSR_VXSAT and CSR_VXRM are at 0x9 and 0xa respectively.
> > (#define CSR_VXSAT 0x9 and  #define CSR_VXRM 0xa)
> >
> >
> > And looking at __fstate_save + __fstate_restore the only CSRs accessed seem
> > to be CSR_STATUS and FCSR itself.
> >
> > I definitly won't claim to be right, but don't see the issue yet.
> >
> >
> > Thanks for a hint
> > Heiko
> 
> Are you aware of "3.7. Vector Fixed-Point Fields in fcsr" in
> riscv-v-spec-0.7.1.pdf?

oh wow, thanks a lot for that pointer, now I understand your concern.

So in vector-0.7.1 fcsr[10:9] mirrors vxrm and fcsr[8] mirrors vxsat.


On a positive note, the T-Head cores seem to not implement the full
vector 0.7.1 specification after all, in the documentation I have [0]
fcsr[31:8] are declared as "0" and uppermost bits are [7:5] for the "frm"
field.

So I guess a code comment should suffice to explain :-)


Regards
Heiko


[0] https://github.com/T-head-Semi/openc906/blob/main/doc/%E7%8E%84%E9%93%81C906%E7%94%A8%E6%88%B7%E6%89%8B%E5%86%8C.pdf
16.3.1.3 浮点控制状态寄存器（FCSR） on page 334



_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

  reply	other threads:[~2023-06-22 20:36 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-28 21:54 [PATCH RFC 0/2] RISC-V: T-Head vector handling Heiko Stuebner
2023-02-28 21:54 ` Heiko Stuebner
2023-02-28 21:54 ` [PATCH RFC 1/2] RISC-V: define the elements of the VCSR vector CSR Heiko Stuebner
2023-02-28 21:54   ` Heiko Stuebner
2023-03-01  2:22   ` Guo Ren
2023-03-01  2:22     ` Guo Ren
2023-03-15 18:31   ` Conor Dooley
2023-03-15 18:31     ` Conor Dooley
2023-02-28 21:54 ` [PATCH RFC 2/2] RISC-V: add T-Head vector errata handling Heiko Stuebner
2023-02-28 21:54   ` Heiko Stuebner
2023-03-01  2:12   ` Guo Ren
2023-03-01  2:12     ` Guo Ren
2023-03-15 18:56   ` Conor Dooley
2023-03-15 18:56     ` Conor Dooley
2023-06-13  6:35   ` Stefan O'Rear
2023-06-13  6:35     ` Stefan O'Rear
2023-06-22 17:39     ` Heiko Stübner
2023-06-22 17:39       ` Heiko Stübner
2023-06-22 18:58       ` Stefan O'Rear
2023-06-22 18:58         ` Stefan O'Rear
2023-06-22 20:35         ` Heiko Stübner [this message]
2023-06-22 20:35           ` Heiko Stübner
2023-06-23  3:06           ` Stefan O'Rear
2023-06-23  3:06             ` Stefan O'Rear
2023-06-23 10:22             ` Heiko Stübner
2023-06-23 10:22               ` Heiko Stübner
2023-06-23 23:26               ` Heiko Stübner
2023-06-23 23:26                 ` Heiko Stübner
2023-06-24  3:23                 ` Stefan O'Rear
2023-06-24  3:23                   ` Stefan O'Rear
2023-06-23  9:12   ` Emil Renner Berthing
2023-06-23  9:12     ` Emil Renner Berthing
2023-03-01  2:21 ` [PATCH RFC 0/2] RISC-V: T-Head vector handling Guo Ren
2023-03-01  2:21   ` Guo Ren
2023-03-15  5:29 ` Palmer Dabbelt
2023-03-15  5:29   ` Palmer Dabbelt
2023-03-15  6:31   ` Heiko Stuebner
2023-03-15  6:31     ` Heiko Stuebner
2023-06-12 15:29   ` Palmer Dabbelt
2023-06-12 15:29     ` Palmer Dabbelt
2023-06-12 15:44     ` Heiko Stübner
2023-06-12 15:44       ` Heiko Stübner

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=9132027.CDJkKcVGEf@diego \
    --to=heiko@sntech.de \
    --cc=christoph.muellner@vrull.eu \
    --cc=conor.dooley@microchip.com \
    --cc=guoren@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=palmer@dabbelt.com \
    --cc=samuel@sholland.org \
    --cc=sorear@fastmail.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.