xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Jan Beulich <jbeulich@suse.com>
To: paul@xen.org
Cc: xen-devel@lists.xenproject.org
Subject: Re: [PATCH v3 19/22] x86emul: support TILELOADD{,T1} and TILESTORE
Date: Thu, 29 Apr 2021 11:40:02 +0200	[thread overview]
Message-ID: <4f129a52-06ce-ab14-3e70-a7c78b64d344@suse.com> (raw)
In-Reply-To: <3c1d6f14-b091-6244-0ef0-3925601c770d@xen.org>

On 26.04.2021 09:12, Paul Durrant wrote:
> On 22/04/2021 16:11, Jan Beulich wrote:
>> On 22.04.2021 17:06, Jan Beulich wrote:
>>> On 22.04.2021 16:55, Jan Beulich wrote:
>>>> +        do {
>>>> +            /* Limit rows to just as many to cover the next one to access. */
>>>> +            cfg->start_row = i;
>>>> +            cfg->rows[modrm_reg] = i + 1;
>>>> +            write_tilecfg(cfg);
>>>> +
>>>> +            if ( vex.pfx != vex_f3 )
>>>> +                rc = ops->read(ea.mem.seg,
>>>> +                               truncate_ea(ea.mem.off + i * ea.val),
>>>> +                               row, cfg->colsb[modrm_reg], ctxt);
>>>> +
>>>> +            invoke_stub("", "", "=m" (dummy) : "a" (row));
>>>> +
>>>> +            if ( vex.pfx == vex_f3 )
>>>> +                rc = ops->write(ea.mem.seg,
>>>> +                                truncate_ea(ea.mem.off + i * ea.val),
>>>> +                                row, cfg->colsb[modrm_reg], ctxt);
>>>> +        } while ( rc == X86EMUL_OKAY && ++i < n );
>>>
>>> in principle tiles could have rows larger than 64 bytes without any
>>> separate CPUID feature flag qualifying this. struct hvm_mmio_cache,
>>> otoh, is having a fixed-size 64-byte buffer right now. Therefore I'm
>>> wondering whether we'd want to switch to dynamically allocating that
>>> to the minimum of 64 bytes and the size of a tile row, just as a
>>> precautionary measure.
>>
>> Actually, as it occurred to me only after sending, enlarging tile size
>> would under almost all circumstances require a new XSTATE component,
>> which we'd need to enable first. I consider it less likely that they'd
>> permit a wider range of layouts without increasing tile size. But we
>> might still want to play safe.
>>
> 
> I guess on-demand reallocation to a larger size would be fine. Certainly 
> we want to be sure we don't overflow.

Okay, I've added a patch doing not just this, but (perhaps even more
important) also increase struct hvmemul_cache's capacity on such
hardware.

Jan


  reply	other threads:[~2021-04-29  9:40 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-22 14:38 [PATCH v3 00/22] xvmalloc() / x86 xstate area / x86 CPUID / AMX+XFD Jan Beulich
2021-04-22 14:43 ` [PATCH v3 01/22] mm: introduce xvmalloc() et al and use for grant table allocations Jan Beulich
2021-05-03 11:31   ` Roger Pau Monné
2021-05-03 13:50     ` Jan Beulich
2021-05-03 14:54       ` Roger Pau Monné
2021-05-03 15:21         ` Jan Beulich
2021-05-03 16:39           ` Roger Pau Monné
2021-04-22 14:44 ` [PATCH v3 02/22] x86/xstate: use xvzalloc() for save area allocation Jan Beulich
2021-05-05 13:29   ` Roger Pau Monné
2021-04-22 14:44 ` [PATCH v3 03/22] x86/xstate: re-size save area when CPUID policy changes Jan Beulich
2021-05-03 13:57   ` Andrew Cooper
2021-05-03 14:22     ` Jan Beulich
2021-05-11 16:41       ` Andrew Cooper
2021-05-17  7:33         ` Jan Beulich
2021-04-22 14:45 ` [PATCH v3 04/22] x86/xstate: re-use valid_xcr0() for boot-time checks Jan Beulich
2021-05-03 11:53   ` Andrew Cooper
2021-04-22 14:45 ` [PATCH v3 05/22] x86/xstate: drop xstate_offsets[] and xstate_sizes[] Jan Beulich
2021-05-03 16:10   ` Andrew Cooper
2021-05-04  7:57     ` Jan Beulich
2021-04-22 14:46 ` [PATCH v3 06/22] x86/xstate: replace xsave_cntxt_size and drop XCNTXT_MASK Jan Beulich
2021-04-22 14:47 ` [PATCH v3 07/22] x86/xstate: avoid accounting for unsupported components Jan Beulich
2021-04-22 14:47 ` [PATCH v3 08/22] x86: use xvmalloc() for extended context buffer allocations Jan Beulich
2021-04-22 14:48 ` [PATCH v3 09/22] x86/xstate: enable AMX components Jan Beulich
2021-04-22 14:50 ` [PATCH v3 10/22] x86/CPUID: adjust extended leaves out of range clearing Jan Beulich
2021-04-22 14:50 ` [PATCH v3 11/22] x86/CPUID: move bounding of max_{,sub}leaf fields to library code Jan Beulich
2021-04-22 14:51 ` [PATCH v3 12/22] x86/CPUID: enable AMX leaves Jan Beulich
2021-04-22 14:52 ` [PATCH v3 13/22] x86: XFD enabling Jan Beulich
2021-04-22 14:53 ` [PATCH v3 14/22] x86emul: introduce X86EMUL_FPU_{tilecfg,tile} Jan Beulich
2021-04-22 14:53 ` [PATCH v3 15/22] x86emul: support TILERELEASE Jan Beulich
2021-04-22 14:53 ` [PATCH v3 16/22] x86: introduce struct for TILECFG register Jan Beulich
2021-04-22 14:54 ` [PATCH v3 17/22] x86emul: support {LD,ST}TILECFG Jan Beulich
2021-04-22 14:55 ` [PATCH v3 18/22] x86emul: support TILEZERO Jan Beulich
2021-04-22 14:55 ` [PATCH v3 19/22] x86emul: support TILELOADD{,T1} and TILESTORE Jan Beulich
2021-04-22 15:06   ` Jan Beulich
2021-04-22 15:11     ` Jan Beulich
2021-04-26  7:12       ` Paul Durrant
2021-04-29  9:40         ` Jan Beulich [this message]
2021-04-22 14:56 ` [PATCH v3 20/22] x86emul: support tile multiplication insns Jan Beulich
2021-04-22 14:57 ` [PATCH v3 21/22] x86emul: test AMX insns Jan Beulich
2021-04-22 14:57 ` [PATCH v3 22/22] x86: permit guests to use AMX and XFD 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=4f129a52-06ce-ab14-3e70-a7c78b64d344@suse.com \
    --to=jbeulich@suse.com \
    --cc=paul@xen.org \
    --cc=xen-devel@lists.xenproject.org \
    --subject='Re: [PATCH v3 19/22] x86emul: support TILELOADD{,T1} and TILESTORE' \
    /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

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).