From: Dave Hansen <dave.hansen@intel.com>
To: Babu Moger <babu.moger@amd.com>,
linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org
Cc: tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
x86@kernel.org, hpa@zytor.com, dave.hansen@linux.intel.com,
luto@kernel.org, peterz@infradead.org, shuah@kernel.org,
jroedel@suse.de, ubizjak@gmail.com, viro@zeniv.linux.org.uk,
jpa@git.mail.kapsi.fi, fenghua.yu@intel.com,
kan.liang@linux.intel.com, akpm@linux-foundation.org,
rppt@kernel.org, Fan_Yang@sjtu.edu.cn, anshuman.khandual@arm.com,
b.thiel@posteo.de, jgross@suse.com, keescook@chromium.org,
seanjc@google.com, mh@glandium.org, sashal@kernel.org,
krisman@collabora.com, chang.seok.bae@intel.com,
0x7f454c46@gmail.com, jhubbard@nvidia.com,
sandipan@linux.ibm.com, ziy@nvidia.com,
kirill.shutemov@linux.intel.com, suxingxing@loongson.cn,
harish@linux.ibm.com, rong.a.chen@intel.com, linuxram@us.ibm.com,
bauerman@linux.ibm.com, dave.kleikamp@oracle.com
Subject: Re: x86/fpu/xsave: protection key test failures
Date: Tue, 25 May 2021 15:18:53 -0700 [thread overview]
Message-ID: <7a407363-e074-aa84-3ca1-909b497122aa@intel.com> (raw)
In-Reply-To: <b2e0324a-9125-bb34-9e76-81817df27c48@amd.com>
On 5/25/21 2:37 PM, Babu Moger wrote:
> My suspicion at this point is towards the selftest tool protection_keys.c.
> I will keep looking. Any feedback would be much appreciated to debug further.
The pkey selftest code that pokes at the signal stack is rather hackish.
If I had to guess, I'd suspect that PKRU ends up in there in a slightly
different place than on Intel CPUs.
One oddity is that xfeatures seems to lose its pkey bit somewhere:
> protection_keys-17350 [035] 59275.834197: x86_fpu_copy_src: x86/fpu: 0xffff93d7595e2dc0 load: 0 xfeatures: 202 xcomp_bv: 8000000000000207
> protection_keys-17350 [035] 59275.834197: x86_fpu_copy_dst: x86/fpu: 0xffff93d722877800 load: 0 xfeatures: 2 xcomp_bv: 8000000000000207
The only legitimate way that can happen (on Intel at least) is an XRSTOR
that brings PKRU back to the init state. That would destroy all
meaningful PKRU state, unless PKRU=0, which it almost never does on Linux.
What values do PKRU and the shadow have when the test fails? Is PKRU 0?
Any idea how xfeatures&0x200 got clear?
next prev parent reply other threads:[~2021-05-25 22:18 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-25 21:37 x86/fpu/xsave: protection key test failures Babu Moger
2021-05-25 22:18 ` Dave Hansen [this message]
2021-05-25 22:22 ` Dave Kleikamp
2021-05-25 22:28 ` Dave Hansen
2021-05-26 0:03 ` Babu Moger
2021-05-26 0:20 ` Dave Hansen
2021-05-26 15:25 ` Babu Moger
2021-05-26 15:50 ` Dave Kleikamp
2021-05-26 16:06 ` Dave Hansen
2021-05-26 17:03 ` Babu Moger
2021-05-26 0:36 ` Andy Lutomirski
2021-05-26 21:14 ` Babu Moger
2021-05-26 21:17 ` Andy Lutomirski
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=7a407363-e074-aa84-3ca1-909b497122aa@intel.com \
--to=dave.hansen@intel.com \
--cc=0x7f454c46@gmail.com \
--cc=Fan_Yang@sjtu.edu.cn \
--cc=akpm@linux-foundation.org \
--cc=anshuman.khandual@arm.com \
--cc=b.thiel@posteo.de \
--cc=babu.moger@amd.com \
--cc=bauerman@linux.ibm.com \
--cc=bp@alien8.de \
--cc=chang.seok.bae@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=dave.kleikamp@oracle.com \
--cc=fenghua.yu@intel.com \
--cc=harish@linux.ibm.com \
--cc=hpa@zytor.com \
--cc=jgross@suse.com \
--cc=jhubbard@nvidia.com \
--cc=jpa@git.mail.kapsi.fi \
--cc=jroedel@suse.de \
--cc=kan.liang@linux.intel.com \
--cc=keescook@chromium.org \
--cc=kirill.shutemov@linux.intel.com \
--cc=krisman@collabora.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linuxram@us.ibm.com \
--cc=luto@kernel.org \
--cc=mh@glandium.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rong.a.chen@intel.com \
--cc=rppt@kernel.org \
--cc=sandipan@linux.ibm.com \
--cc=sashal@kernel.org \
--cc=seanjc@google.com \
--cc=shuah@kernel.org \
--cc=suxingxing@loongson.cn \
--cc=tglx@linutronix.de \
--cc=ubizjak@gmail.com \
--cc=viro@zeniv.linux.org.uk \
--cc=x86@kernel.org \
--cc=ziy@nvidia.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