kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Radim Krčmář" <rkrcmar@redhat.com>
To: Jan Kiszka <jan.kiszka@siemens.com>
Cc: kvm <kvm@vger.kernel.org>, Joel Schopp <joel.schopp@amd.com>
Subject: Re: [RFC][PATCH] KVM: SVM: Sync g_pat with guest-written PAT value
Date: Mon, 20 Apr 2015 19:16:36 +0200	[thread overview]
Message-ID: <20150420171635.GC26491@potion.brq.redhat.com> (raw)
In-Reply-To: <20150420161401.GB26491@potion.brq.redhat.com>

2015-04-20 18:14+0200, Radim Krčmář:
> Tested-by: Radim Krčmář <rkrcmar@redhat.com>

Uncached accesses were roughly 20x slower.
In case anyone wanted to reproduce, I used this as a kvm-unit-test:

---
#include "processor.h"

#define NR_TOP_LOOPS 24
#define NR_MEM_LOOPS 10
#define MEM_ELEMENTS 1024

static volatile u64 pat_test_memory[MEM_ELEMENTS];

static void flush_tlb(void)
{
	write_cr3(read_cr3());
}

static void set_pat(u64 val)
{
	wrmsr(0x277, val);
	flush_tlb();

}

static u64 time_memory_accesses(void)
{
	u64 tsc_before = rdtsc();

	for (unsigned loop = 0; loop < NR_MEM_LOOPS; loop++)
		for (unsigned i = 0; i < MEM_ELEMENTS; i++)
			pat_test_memory[i]++;

	return rdtsc() - tsc_before;
}

int main(int argc, char **argv)
{
	unsigned error = 0;

	for (unsigned loop = 0; loop < NR_TOP_LOOPS; loop++) {
		u64 time_uc, time_wb;

		set_pat(0);
		time_uc = time_memory_accesses();

		set_pat(0x0606060606060606ULL);
		time_wb = time_memory_accesses();

		if (time_uc < time_wb * 4)
			error++;

		printf("%02d uc: %10lld wb: %8lld\n", loop, time_uc, time_wb);
	}

	report("guest PAT", !error);

	return report_summary();
}

  reply	other threads:[~2015-04-20 17:16 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-04-13  5:16 KVM: How does is PAT emulation supposed to work? Jan Kiszka
2015-04-13  6:58 ` [RFC][PATCH] KVM: SVM: Sync g_pat with guest-written PAT value Jan Kiszka
2015-04-17 16:59   ` Radim Krčmář
2015-04-20 16:14   ` Radim Krčmář
2015-04-20 17:16     ` Radim Krčmář [this message]
2015-04-20 17:21       ` Jan Kiszka
2015-04-20 17:33         ` Radim Krčmář
2015-04-20 17:37           ` Jan Kiszka
2015-04-20 17:45             ` Jan Kiszka
2015-04-20 18:33               ` Radim Krčmář
2015-04-20 18:41                 ` Jan Kiszka
2015-04-21 12:10                   ` Radim Krčmář
2015-04-21 12:11                   ` Paolo Bonzini
2015-04-20 17:22       ` Radim Krčmář
2015-04-20 17:25     ` [PATCH v2] " Jan Kiszka
2015-04-20 17:35       ` Radim Krčmář
2015-04-21 11:09       ` Paolo Bonzini
2015-04-21 11:25         ` Jan Kiszka
2015-04-21 11:32           ` Paolo Bonzini
2015-04-21 11:56             ` Jan Kiszka
2015-04-21 12:12               ` Paolo Bonzini
2015-04-21 12:21         ` Radim Krčmář
2015-05-24 15:28           ` Jan Kiszka
2016-02-09 19:25             ` Jan Kiszka
2015-04-17 16:43 ` KVM: How does is PAT emulation supposed to work? Radim Krčmář
2015-04-17 17:12   ` Jan Kiszka
2015-04-17 20:28     ` Radim Krčmář

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=20150420171635.GC26491@potion.brq.redhat.com \
    --to=rkrcmar@redhat.com \
    --cc=jan.kiszka@siemens.com \
    --cc=joel.schopp@amd.com \
    --cc=kvm@vger.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).