From: "Chang S. Bae" <chang.seok.bae@intel.com>
To: bp@suse.de, luto@kernel.org, tglx@linutronix.de,
mingo@kernel.org, x86@kernel.org
Cc: len.brown@intel.com, lenb@kernel.org, dave.hansen@intel.com,
thiago.macieira@intel.com, jing2.liu@intel.com,
ravi.v.shankar@intel.com, linux-kernel@vger.kernel.org,
chang.seok.bae@intel.com
Subject: [PATCH v11 23/29] x86/fpu/xstate: Skip writing zeros to signal frame for dynamic user states if in INIT-state
Date: Fri, 1 Oct 2021 15:37:22 -0700 [thread overview]
Message-ID: <20211001223728.9309-24-chang.seok.bae@intel.com> (raw)
In-Reply-To: <20211001223728.9309-1-chang.seok.bae@intel.com>
By default, for XSTATE features in the INIT-state, XSAVE writes zeros to
the uncompressed destination buffer.
E.g., if you are not using AVX-512, you will still get a bunch of zeros on
the signal stack where live AVX-512 data would go.
For permssion-required states (currently AMX state), explicitly skip this
data transfer. The result is that the user buffer for the AMX region will
not be touched by XSAVE.
[ Reading XINUSE takes about 20-30 cycles, but writing zeros consumes about
5-times or more, e.g., for XTILEDATA. ]
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Reviewed-by: Len Brown <len.brown@intel.com>
Cc: x86@kernel.org
Cc: linux-kernel@vger.kernel.org
---
Changes from v10:
* Simplify the sigframe XSAVE code: replace check for XFD STATE with
XTILECFG and later STATE.
Changes from v9:
* Use cpu_feature_enabled() instead of boot_cpu_has(). (Borislav Petkov)
Changes from v5:
* Mentioned the optimization trade-offs in the changelog. (Dave Hansen)
* Added code comment.
Changes from v4:
* Added as a new patch.
---
arch/x86/include/asm/fpu/internal.h | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 06be4c247c97..5f013fa0b205 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -355,8 +355,12 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
mask = uabi_mask & ~xfeatures_mask_user_perm();
if (sig_xstate_expanded(current)) {
- u64 cur_uabi_mask = uabi_mask & current->thread.fpu.state_mask;
+ u64 cur_uabi_mask;
+ if (cpu_feature_enabled(X86_FEATURE_XGETBV1))
+ cur_uabi_mask = uabi_mask & xgetbv(1);
+ else
+ cur_uabi_mask = uabi_mask & current->thread.fpu.state_mask;
mask |= cur_uabi_mask & xfeatures_mask_user_perm();
}
}
--
2.17.1
next prev parent reply other threads:[~2021-10-01 22:46 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-01 22:36 [PATCH v11 00/29] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 01/29] x86/fpu/xstate: Fix the state copy function to the XSTATE buffer Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 02/29] x86/fpu/xstate: Modify the initialization helper to handle both static and dynamic buffers Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 03/29] x86/fpu/xstate: Modify state copy helpers " Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 04/29] x86/fpu/xstate: Modify address finders " Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 05/29] x86/fpu/xstate: Add a new variable to indicate dynamic user states Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 06/29] x86/fpu/xstate: Add new variables to indicate dynamic XSTATE buffer size Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 07/29] x86/fpu/xstate: Calculate and remember dynamic XSTATE buffer sizes Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 08/29] x86/fpu/xstate: Convert the struct fpu 'state' field to a pointer Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 09/29] x86/fpu/xstate: Introduce helpers to manage the XSTATE buffer dynamically Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 10/29] x86/fpu/xstate: Update the XSTATE save function to support dynamic states Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 11/29] x86/fpu/xstate: Update the XSTATE buffer address finder " Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 12/29] x86/fpu/xstate: Update the XSTATE context copy function " Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 13/29] x86/fpu/xstate: Use feature disable (XFD) to protect dynamic user state Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 14/29] x86/fpu/xstate: Support ptracer-induced XSTATE buffer expansion Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 15/29] x86/arch_prctl: Create ARCH_SET_STATE_ENABLE/ARCH_GET_STATE_ENABLE Chang S. Bae
2021-10-05 0:30 ` Thomas Gleixner
2021-10-05 9:49 ` Thomas Gleixner
2021-10-05 11:23 ` Peter Zijlstra
2021-10-05 12:27 ` Thomas Gleixner
2021-10-01 22:37 ` [PATCH v11 16/29] x86/fpu/xstate: Support both legacy and expanded signal XSTATE size Chang S. Bae
2021-10-05 12:30 ` Thomas Gleixner
2021-10-05 15:19 ` Thomas Gleixner
2021-10-01 22:37 ` [PATCH v11 17/29] x86/fpu/xstate: Adjust the XSAVE feature table to address gaps in state component numbers Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 18/29] x86/fpu/xstate: Disable XSTATE support if an inconsistent state is detected Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 19/29] x86/cpufeatures/amx: Enumerate Advanced Matrix Extension (AMX) feature bits Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 20/29] x86/fpu/amx: Define AMX state components and have it used for boot-time checks Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 21/29] x86/fpu/amx: Initialize child's AMX state Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 22/29] x86/fpu/amx: Enable the AMX feature in 64-bit mode Chang S. Bae
2021-10-01 22:37 ` Chang S. Bae [this message]
2021-10-01 22:37 ` [PATCH v11 24/29] selftest/x86/amx: Test cases for the AMX state management Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 25/29] x86/insn/amx: Add TILERELEASE instruction to the opcode map Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 26/29] intel_idle/amx: Add SPR support with XTILEDATA capability Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 27/29] x86/fpu/xstate: Add a sanity check for XFD state when saving XSTATE Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 28/29] x86/arch_prctl: ARCH_GET_FEATURES_WITH_KERNEL_ASSISTANCE Chang S. Bae
2021-10-01 22:37 ` [PATCH v11 29/29] x86/arch_prctl: ARCH_SET_STATE_ENABLE_ALLOC Chang S. Bae
2021-10-01 22:47 ` [PATCH v11 00/29] x86: Support Intel Advanced Matrix Extensions Bae, Chang Seok
2021-10-01 22:50 ` Bae, Chang Seok
2021-10-03 1:05 ` Thomas Gleixner
2021-10-04 14:48 ` Bae, Chang Seok
2021-10-02 21:54 ` Thomas Gleixner
2021-10-02 22:11 ` Bae, Chang Seok
2021-10-04 13:44 ` Thomas Gleixner
2021-10-04 14:47 ` Bae, Chang Seok
2021-10-02 22:20 ` Bae, Chang Seok
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=20211001223728.9309-24-chang.seok.bae@intel.com \
--to=chang.seok.bae@intel.com \
--cc=bp@suse.de \
--cc=dave.hansen@intel.com \
--cc=jing2.liu@intel.com \
--cc=len.brown@intel.com \
--cc=lenb@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@kernel.org \
--cc=ravi.v.shankar@intel.com \
--cc=tglx@linutronix.de \
--cc=thiago.macieira@intel.com \
--cc=x86@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 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).