From: Paul Mackerras <paulus@ozlabs.org>
To: wei.guo.simon@gmail.com
Cc: linuxppc-dev@lists.ozlabs.org, kvm@vger.kernel.org,
kvm-ppc@vger.kernel.org
Subject: Re: [PATCH 17/26] KVM: PPC: Book3S PR: add math support for PR KVM HTM
Date: Tue, 23 Jan 2018 18:29:27 +1100 [thread overview]
Message-ID: <20180123072927.GI3924@fergus.ozlabs.ibm.com> (raw)
In-Reply-To: <1515665499-31710-18-git-send-email-wei.guo.simon@gmail.com>
On Thu, Jan 11, 2018 at 06:11:30PM +0800, wei.guo.simon@gmail.com wrote:
> ines: 219
>
> From: Simon Guo <wei.guo.simon@gmail.com>
>
> The math registers will be saved into vcpu->arch.fp/vr and corresponding
> vcpu->arch.fp_tm/vr_tm area.
>
> We flush or giveup the math regs into vcpu->arch.fp/vr before saving
> transaction. After transaction is restored, the math regs will be loaded
> back into regs.
It looks to me that you are loading up the math regs on every vcpu
load, not just those with an active transaction. That seems like
overkill.
> If there is a FP/VEC/VSX unavailable exception during transaction active
> state, the math checkpoint content might be incorrect and we need to do
> treclaim./load the correct checkpoint val/trechkpt. sequence to retry the
> transaction.
I would prefer a simpler approach where just before entering the
guest, we check if the guest MSR TM bit is set, and if so we make sure
that whichever math regs are enabled in the guest MSR are actually
loaded on the CPU, that is, that guest_owned_ext has the same bits set
as the guest MSR. Then we never have to handle a FP/VEC/VSX
unavailable interrupt with a transaction active (other than by simply
passing it on to the guest).
Paul.
next prev parent reply other threads:[~2018-01-23 7:29 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-11 10:11 [PATCH 00/26] KVM: PPC: Book3S PR: Transaction memory support on PR KVM wei.guo.simon
2018-01-11 10:11 ` [PATCH 01/26] KVM: PPC: Book3S PR: Move kvmppc_save_tm/kvmppc_restore_tm to separate file wei.guo.simon
2018-01-11 10:11 ` [PATCH 02/26] KVM: PPC: Book3S PR: add new parameter (guest MSR) for kvmppc_save_tm()/kvmppc_restore_tm() wei.guo.simon
2018-01-23 5:42 ` Paul Mackerras
2018-01-30 2:33 ` Simon Guo
2018-01-11 10:11 ` [PATCH 03/26] KVM: PPC: Book3S PR: turn on FP/VSX/VMX MSR bits in kvmppc_save_tm() wei.guo.simon
2018-01-11 10:11 ` [PATCH 04/26] KVM: PPC: Book3S PR: add C function wrapper for _kvmppc_save/restore_tm() wei.guo.simon
2018-01-23 5:49 ` Paul Mackerras
2018-01-30 2:38 ` Simon Guo
2018-01-11 10:11 ` [PATCH 05/26] KVM: PPC: Book3S PR: In PR KVM suspends Transactional state when inject an interrupt wei.guo.simon
2018-01-11 10:11 ` [PATCH 06/26] KVM: PPC: Book3S PR: PR KVM pass through MSR TM/TS bits to shadow_msr wei.guo.simon
2018-01-11 10:11 ` [PATCH 07/26] KVM: PPC: Book3S PR: add TEXASR related macros wei.guo.simon
2018-01-23 5:50 ` Paul Mackerras
2018-01-11 10:11 ` [PATCH 08/26] KVM: PPC: Book3S PR: Sync TM bits to shadow msr for problem state guest wei.guo.simon
2018-01-11 10:11 ` [PATCH 09/26] KVM: PPC: Book3S PR: implement RFID TM behavior to suppress change from S0 to N0 wei.guo.simon
2018-01-11 10:11 ` [PATCH 10/26] KVM: PPC: Book3S PR: set MSR HV bit accordingly for PPC970 and others wei.guo.simon
2018-01-23 5:51 ` Paul Mackerras
2018-01-11 10:11 ` [PATCH 11/26] KVM: PPC: Book3S PR: prevent TS bits change in kvmppc_interrupt_pr() wei.guo.simon
2018-01-11 10:11 ` [PATCH 12/26] powerpc: export symbol msr_check_and_set() wei.guo.simon
2018-01-11 10:11 ` [PATCH 13/26] KVM: PPC: Book3S PR: adds new kvmppc_copyto_vcpu_tm/kvmppc_copyfrom_vcpu_tm API for PR KVM wei.guo.simon
2018-01-23 5:52 ` Paul Mackerras
2018-01-30 2:15 ` Simon Guo
2018-01-11 10:11 ` [PATCH 14/26] KVM: PPC: Book3S PR: export tm_enable()/tm_disable/tm_abort() APIs wei.guo.simon
2018-01-11 10:11 ` [PATCH 15/26] KVM: PPC: Book3S PR: add kvmppc_save/restore_tm_sprs() APIs wei.guo.simon
2018-01-11 10:11 ` [PATCH 16/26] KVM: PPC: Book3S PR: add transaction memory save/restore skeleton for PR KVM wei.guo.simon
2018-01-23 6:04 ` Paul Mackerras
2018-01-30 2:57 ` Simon Guo
2018-01-11 10:11 ` [PATCH 17/26] KVM: PPC: Book3S PR: add math support for PR KVM HTM wei.guo.simon
2018-01-23 7:29 ` Paul Mackerras [this message]
2018-01-30 3:00 ` Simon Guo
2018-01-11 10:11 ` [PATCH 18/26] KVM: PPC: Book3S PR: make mtspr/mfspr emulation behavior based on active TM SPRs wei.guo.simon
2018-01-23 8:17 ` Paul Mackerras
2018-01-30 3:02 ` Simon Guo
2018-01-11 10:11 ` [PATCH 19/26] KVM: PPC: Book3S PR: always fail transaction in guest privilege state wei.guo.simon
2018-01-23 8:30 ` Paul Mackerras
2018-01-30 3:11 ` Simon Guo
2018-01-11 10:11 ` [PATCH 20/26] KVM: PPC: Book3S PR: enable NV reg restore for reading TM SPR at " wei.guo.simon
2018-01-23 9:08 ` Paul Mackerras
2018-01-11 10:11 ` [PATCH 21/26] KVM: PPC: Book3S PR: adds emulation for treclaim wei.guo.simon
2018-01-23 9:23 ` Paul Mackerras
2018-01-30 3:18 ` Simon Guo
2018-01-11 10:11 ` [PATCH 22/26] KVM: PPC: Book3S PR: add emulation for trechkpt in PR KVM wei.guo.simon
2018-01-23 9:36 ` Paul Mackerras
2018-01-30 3:13 ` Simon Guo
2018-01-11 10:11 ` [PATCH 23/26] KVM: PPC: Book3S PR: add emulation for tabort. for privilege guest wei.guo.simon
2018-01-23 9:44 ` Paul Mackerras
2018-01-30 3:24 ` Simon Guo
2018-01-11 10:11 ` [PATCH 24/26] KVM: PPC: Book3S PR: add guard code to prevent returning to guest with PR=0 and Transactional state wei.guo.simon
2018-01-11 10:11 ` [PATCH 25/26] KVM: PPC: Book3S PR: Support TAR handling for PR KVM HTM wei.guo.simon
2018-01-24 4:02 ` Paul Mackerras
2018-01-30 3:26 ` Simon Guo
2018-01-11 10:11 ` [PATCH 26/26] KVM: PPC: Book3S PR: enable HTM for PR KVM for KVM_CHECK_EXTENSION ioctl wei.guo.simon
2018-01-11 13:56 ` [PATCH 00/26] KVM: PPC: Book3S PR: Transaction memory support on PR KVM Gustavo Romero
2018-01-11 22:04 ` Benjamin Herrenschmidt
2018-01-12 2:41 ` Simon Guo
2018-01-23 5:38 ` Paul Mackerras
2018-01-23 7:16 ` Paul Mackerras
2018-01-27 13:10 ` Simon Guo
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=20180123072927.GI3924@fergus.ozlabs.ibm.com \
--to=paulus@ozlabs.org \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=wei.guo.simon@gmail.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;
as well as URLs for NNTP newsgroup(s).