From: Zachary Amsden <zamsden@redhat.com>
To: avi@redhat.com, mtosatti@redhat.com, glommer@redhat.com,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Zachary Amsden <zamsden@redhat.com>
Subject: [PATCH 10/17] Make KVM clock computation work for other scales
Date: Mon, 14 Jun 2010 21:34:12 -1000 [thread overview]
Message-ID: <1276587259-32319-11-git-send-email-zamsden@redhat.com> (raw)
In-Reply-To: <1276587259-32319-1-git-send-email-zamsden@redhat.com>
The math in kvm_get_time_scale relies on the fact that
NSEC_PER_SEC < 2^32. To use the same function to compute
arbitrary time scales, we must extend the first reduction
step to shrink the base rate to a 32-bit value, and
possibly reduce the scaled rate into a 32-bit as well.
Note we must take care to avoid an arithmetic overflow
when scaling up the tps32 value (this could not happen
with the fixed scaled value of NSEC_PER_SEC, but can
happen with scaled rates above 2^31.
Signed-off-by: Zachary Amsden <zamsden@redhat.com>
---
arch/x86/kvm/x86.c | 26 +++++++++++++++-----------
1 files changed, 15 insertions(+), 11 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 05c559d..52d7d34 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -882,31 +882,35 @@ static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
return quotient;
}
-static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
+static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
+ s8 *pshift, u32 *pmultiplier)
{
- uint64_t nsecs = 1000000000LL;
+ uint64_t scaled64;
int32_t shift = 0;
uint64_t tps64;
uint32_t tps32;
- tps64 = tsc_khz * 1000LL;
- while (tps64 > nsecs*2) {
+ tps64 = base_khz * 1000LL;
+ scaled64 = scaled_khz * 1000LL;
+ while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000UL) {
tps64 >>= 1;
shift--;
}
tps32 = (uint32_t)tps64;
- while (tps32 <= (uint32_t)nsecs) {
- tps32 <<= 1;
+ while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000UL) {
+ if (scaled64 & 0xffffffff00000000UL || tps32 & 0x80000000)
+ scaled64 >>= 1;
+ else
+ tps32 <<= 1;
shift++;
}
- hv_clock->tsc_shift = shift;
- hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);
+ *pshift = shift;
+ *pmultiplier = div_frac(scaled64, tps32);
- pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n",
- __func__, tsc_khz, hv_clock->tsc_shift,
- hv_clock->tsc_to_system_mul);
+ pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n",
+ __func__, base_khz, scaled_khz, shift, *pmultiplier);
}
static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
--
1.7.1
next prev parent reply other threads:[~2010-06-15 7:36 UTC|newest]
Thread overview: 70+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-06-15 7:34 TSC cleanups, fixes, documentation for KVM Zachary Amsden
2010-06-15 7:34 ` [PATCH 01/17] Eliminate duplicated timer code Zachary Amsden
2010-06-16 13:07 ` Glauber Costa
2010-06-15 7:34 ` [PATCH 02/17] Make cpu_tsc_khz updates use local CPU Zachary Amsden
2010-06-15 8:02 ` Avi Kivity
2010-06-15 7:34 ` [PATCH 03/17] Unify vendor TSC logic Zachary Amsden
2010-06-16 8:10 ` Jason Wang
2010-06-16 13:22 ` Glauber Costa
2010-06-17 8:03 ` Jason Wang
2010-06-16 18:42 ` Zachary Amsden
2010-06-17 8:15 ` Jason Wang
2010-06-17 20:30 ` Zachary Amsden
2010-06-15 7:34 ` [PATCH 04/17] Fix deep C-state TSC desynchronization Zachary Amsden
2010-06-15 8:09 ` Avi Kivity
2010-06-15 8:14 ` Zachary Amsden
2010-06-16 8:10 ` Jason Wang
2010-06-16 18:43 ` Zachary Amsden
2010-06-16 13:24 ` Glauber Costa
2010-06-16 19:20 ` Zachary Amsden
2010-06-15 7:34 ` [PATCH 05/17] Keep SMP VMs more in sync on unstable TSC Zachary Amsden
2010-06-15 8:11 ` Avi Kivity
2010-06-16 8:11 ` Jason Wang
2010-06-16 13:32 ` Glauber Costa
2010-06-16 21:15 ` Zachary Amsden
2010-06-15 7:34 ` [PATCH 06/17] Rename KVM_REQ_KVMCLOCK_UPDATE Zachary Amsden
2010-06-15 7:34 ` [PATCH 07/17] Perform hardware_enable in CPU_STARTING callback Zachary Amsden
2010-06-15 7:34 ` [PATCH 08/17] Add clock sync request to hardware enable Zachary Amsden
2010-06-15 8:24 ` Avi Kivity
2010-06-15 7:34 ` [PATCH 09/17] Move scale_delta into common header Zachary Amsden
2010-06-15 7:34 ` Zachary Amsden [this message]
2010-06-15 7:34 ` [PATCH 11/17] Fix a possible backwards warp of kvmclock Zachary Amsden
2010-06-15 8:40 ` Avi Kivity
2010-06-15 20:37 ` Zachary Amsden
2010-06-15 23:47 ` Marcelo Tosatti
2010-06-16 0:21 ` Zachary Amsden
2010-06-16 0:39 ` Marcelo Tosatti
2010-06-16 8:11 ` Jason Wang
2010-06-16 13:58 ` Glauber Costa
2010-06-16 14:13 ` Avi Kivity
2010-06-16 14:58 ` Glauber Costa
2010-06-16 22:38 ` Zachary Amsden
2010-06-16 19:36 ` Zachary Amsden
2010-06-15 7:34 ` [PATCH 12/17] Add helper function get_kernel_ns Zachary Amsden
2010-06-15 8:41 ` Avi Kivity
2010-06-15 21:03 ` Zachary Amsden
2010-06-15 21:13 ` john stultz
2010-06-16 8:12 ` Jason Wang
2010-06-16 14:03 ` Glauber Costa
2010-06-15 7:34 ` [PATCH 13/17] Add TSC offset tracking Zachary Amsden
2010-06-15 8:44 ` Avi Kivity
2010-06-15 7:34 ` [PATCH 14/17] Fix SVM VMCB reset Zachary Amsden
2010-06-15 7:34 ` [PATCH 15/17] Fix AMD C1 TSC desynchronization Zachary Amsden
2010-06-15 8:47 ` Avi Kivity
2010-06-15 9:21 ` Zachary Amsden
2010-06-15 14:46 ` Roedel, Joerg
2010-06-15 7:34 ` [PATCH 16/17] TSC reset compensation Zachary Amsden
2010-06-15 8:51 ` Avi Kivity
2010-06-15 20:32 ` Zachary Amsden
2010-06-16 0:27 ` Marcelo Tosatti
2010-06-16 0:32 ` Zachary Amsden
2010-06-16 13:52 ` Glauber Costa
2010-06-16 22:36 ` Zachary Amsden
2010-06-15 7:34 ` [PATCH 17/17] Add timekeeping documentation Zachary Amsden
2010-06-15 8:51 ` Avi Kivity
2010-06-15 20:27 ` Randy Dunlap
2010-06-16 23:59 ` Zachary Amsden
2010-06-17 8:55 ` Andi Kleen
2010-06-17 21:14 ` Zachary Amsden
2010-06-18 7:49 ` Andi Kleen
2010-06-18 16:33 ` Zachary Amsden
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=1276587259-32319-11-git-send-email-zamsden@redhat.com \
--to=zamsden@redhat.com \
--cc=avi@redhat.com \
--cc=glommer@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@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
all inboxes | Powered by JetHome®