public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Gleb Natapov <gleb@redhat.com>
To: Avi Kivity <avi@redhat.com>
Cc: mtosatti@redhat.com, kvm@vger.kernel.org
Subject: Re: [PATCH v2 28/30] KVM: x86 emulator: restart string instruction without going back to a guest.
Date: Sun, 14 Mar 2010 20:06:25 +0200	[thread overview]
Message-ID: <20100314180625.GB5406@redhat.com> (raw)
In-Reply-To: <4B9D1545.2020902@redhat.com>

On Sun, Mar 14, 2010 at 06:56:37PM +0200, Avi Kivity wrote:
> On 03/14/2010 06:21 PM, Gleb Natapov wrote:
> >Currently when string instruction is only partially complete we go back
> >to a guest mode, guest tries to reexecute instruction and exits again
> >and at this point emulation continues. Avoid all of this by restarting
> >instruction without going back to a guest mode, but return to a guest
> >mode on each page boundary to allow interrupt injection. Pending
> >exception causes immediate guest entry too.
> >
> >@@ -2913,6 +2917,8 @@ writeback:
> >  		c->dst.ptr = (unsigned long *)
> >  			register_address(c, es_base(ctxt),
> >  					 c->regs[VCPU_REGS_RDI]);
> >+		if (!(c->regs[VCPU_REGS_RDI]&  ~PAGE_MASK))
> >+			ctxt->restart = false;
> >  	}
> 
> What if rdi is odd and operand size != 1?
> 
Will change to if ((c->regs[VCPU_REGS_RDI]&  ~PAGE_MASK) < c->dst.bytes)

> Suggest simply reentering every N executions.
> 
This restart mechanism is, in fact, needed for ins read ahead to work.
After reading ahead from IO port we need to avoid entering decoder
until entire cache is consumed otherwise decoder will clear cache and
data will be lost. So we can't just enter guest in arbitrary times, only
when read ahead cache is empty. Since read ahead is never done across
page boundary this is save place to re-enter guest.

--
			Gleb.

  reply	other threads:[~2010-03-14 18:06 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-03-14 16:20 [PATCH v2 00/30] emulator cleanup Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 01/30] KVM: x86 emulator: Fix DstAcc decoding Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 02/30] KVM: x86 emulator: fix RCX access during rep emulation Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 03/30] KVM: x86 emulator: check return value against correct define Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 04/30] KVM: Remove pointer to rflags from realmode_set_cr parameters Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 05/30] KVM: Provide callback to get/set control registers in emulator ops Gleb Natapov
2010-03-15 13:06   ` Andre Przywara
2010-03-15 13:11     ` Gleb Natapov
2010-03-15 13:13     ` Avi Kivity
2010-03-14 16:20 ` [PATCH v2 06/30] KVM: remove realmode_lmsw function Gleb Natapov
2010-03-15 11:02   ` Andre Przywara
2010-03-15 11:41     ` Avi Kivity
2010-03-14 16:20 ` [PATCH v2 07/30] KVM: Provide x86_emulate_ctxt callback to get current cpl Gleb Natapov
2010-03-15 13:16   ` Andre Przywara
2010-03-15 13:21     ` Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 08/30] KVM: Provide current eip as part of emulator context Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 09/30] KVM: x86 emulator: fix mov r/m, sreg emulation Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 10/30] KVM: x86 emulator: fix 0f 01 /5 emulation Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 11/30] KVM: x86 emulator: 0f (20|21|22|23) ignore mod bits Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 12/30] KVM: x86 emulator: inject #UD on access to non-existing CR Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 13/30] KVM: x86 emulator: fix mov dr to inject #UD when needed Gleb Natapov
2010-03-14 16:20 ` [PATCH v2 14/30] KVM: x86 emulator: fix return values of syscall/sysenter/sysexit emulations Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 15/30] KVM: x86 emulator: do not call writeback if msr access fails Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 16/30] KVM: x86 emulator: If LOCK prefix is used dest arg should be memory Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 17/30] KVM: x86 emulator: cleanup grp3 return value Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 18/30] KVM: x86 emulator: Provide more callbacks for x86 emulator Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 19/30] KVM: x86 emulator: Emulate task switch in emulator.c Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 20/30] KVM: x86 emulator: Use load_segment_descriptor() instead of kvm_load_segment_descriptor() Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 21/30] KVM: Use task switch from emulator.c Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 22/30] KVM: x86 emulator: populate OP_MEM operand during decoding Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 23/30] KVM: x86 emulator: add decoding of X,Y parameters from Intel SDM Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 24/30] KVM: x86 emulator: during rep emulation decrement ECX only if emulation succeeded Gleb Natapov
2010-03-14 16:42   ` Avi Kivity
2010-03-14 16:21 ` [PATCH v2 25/30] KVM: x86 emulator: fix in/out emulation Gleb Natapov
2010-03-14 16:54   ` Avi Kivity
2010-03-14 17:35     ` Gleb Natapov
2010-03-15  7:41       ` Avi Kivity
2010-03-15  7:44         ` Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 26/30] KVM: x86 emulator: Move string pio emulation into emulator.c Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 27/30] KVM: x86 emulator: remove saved_eip Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 28/30] KVM: x86 emulator: restart string instruction without going back to a guest Gleb Natapov
2010-03-14 16:56   ` Avi Kivity
2010-03-14 18:06     ` Gleb Natapov [this message]
2010-03-15  7:44       ` Avi Kivity
2010-03-15  9:44         ` Gleb Natapov
2010-03-15  9:56           ` Avi Kivity
2010-03-15 10:07             ` Gleb Natapov
2010-03-15 10:15               ` Avi Kivity
2010-03-15 10:19                 ` Gleb Natapov
2010-03-15 10:24                   ` Avi Kivity
2010-03-15 10:33                     ` Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 29/30] KVM: x86 emulator: introduce pio in string read ahead Gleb Natapov
2010-03-14 16:21 ` [PATCH v2 30/30] KVM: small kvm_arch_vcpu_ioctl_run() cleanup Gleb Natapov

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=20100314180625.GB5406@redhat.com \
    --to=gleb@redhat.com \
    --cc=avi@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=mtosatti@redhat.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