kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alexander Graf <agraf-l3A5Bk7waGM@public.gmane.org>
To: kvm-ppc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: Linuxppc-dev
	<linuxppc-dev-mnsaURCQ41sdnm+yROfE0A@public.gmane.org>,
	KVM list <kvm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: [PATCH 11/35] KVM: PPC: Revert "KVM: PPC: Use kernel hash function"
Date: Tue, 31 Aug 2010 04:31:52 +0200	[thread overview]
Message-ID: <1283221937-21006-12-git-send-email-agraf@suse.de> (raw)
In-Reply-To: <1283221937-21006-1-git-send-email-agraf-l3A5Bk7waGM@public.gmane.org>

It turns out the in-kernel hash function is sub-optimal for our subtle
hash inputs where every bit is significant. So let's revert to the original
hash functions.

This reverts commit 05340ab4f9a6626f7a2e8f9fe5397c61d494f445.

Signed-off-by: Alexander Graf <agraf-l3A5Bk7waGM@public.gmane.org>
---
 arch/powerpc/kvm/book3s_32_mmu_host.c |   10 ++++++++--
 arch/powerpc/kvm/book3s_64_mmu_host.c |   11 +++++++++--
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 343452c..57dddeb 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -19,7 +19,6 @@
  */
 
 #include <linux/kvm_host.h>
-#include <linux/hash.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -77,7 +76,14 @@ void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
  * a hash, so we don't waste cycles on looping */
 static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
 {
-	return hash_64(gvsid, SID_MAP_BITS);
+	return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK));
 }
 
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 321c931..e7c4d00 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -20,7 +20,6 @@
  */
 
 #include <linux/kvm_host.h>
-#include <linux/hash.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -44,9 +43,17 @@ void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
  * a hash, so we don't waste cycles on looping */
 static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
 {
-	return hash_64(gvsid, SID_MAP_BITS);
+	return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK));
 }
 
+
 static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 {
 	struct kvmppc_sid_map *map;
-- 
1.6.0.2

  parent reply	other threads:[~2010-08-31  2:31 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-08-31  2:31 [PULL 00/35] KVM: PPC: End-August patch queue Alexander Graf
2010-08-31  2:31 ` [PATCH 01/35] KVM: PPC: Move EXIT_DEBUG partially to tracepoints Alexander Graf
2010-08-31  2:31 ` [PATCH 02/35] KVM: PPC: Move book3s_64 mmu map debug print to trace point Alexander Graf
2010-08-31  2:31 ` [PATCH 07/35] KVM: PPC: Preload magic page when in kernel mode Alexander Graf
2010-08-31  2:31 ` [PATCH 08/35] KVM: PPC: Don't flush PTEs on NX/RO hit Alexander Graf
2010-08-31  2:31 ` [PATCH 10/35] KVM: PPC: Move slb debugging to tracepoints Alexander Graf
     [not found] ` <1283221937-21006-1-git-send-email-agraf-l3A5Bk7waGM@public.gmane.org>
2010-08-31  2:31   ` [PATCH 03/35] KVM: PPC: Add tracepoint for generic mmu map Alexander Graf
2010-08-31  2:31   ` [PATCH 04/35] KVM: PPC: Move pte invalidate debug code to tracepoint Alexander Graf
2010-08-31  2:31   ` [PATCH 05/35] KVM: PPC: Fix sid map search after flush Alexander Graf
2010-08-31  2:31   ` [PATCH 06/35] KVM: PPC: Add tracepoints for generic spte flushes Alexander Graf
2010-08-31  2:31   ` [PATCH 09/35] KVM: PPC: Make invalidation code more reliable Alexander Graf
2010-08-31  2:31   ` Alexander Graf [this message]
2010-08-31  2:31   ` [PATCH 12/35] KVM: PPC: Remove unused define Alexander Graf
2010-08-31  2:31   ` [PATCH 16/35] KVM: PPC: Put segment registers in shared page Alexander Graf
2010-08-31  2:32   ` [PATCH 19/35] KVM: PPC: Update int_pending also on dequeue Alexander Graf
2010-08-31  2:32   ` [PATCH 21/35] KVM: PPC: Force enable nap on KVM Alexander Graf
2010-08-31  2:32   ` [PATCH 24/35] KVM: PPC: initialize IVORs in addition to IVPR Alexander Graf
2010-08-31  2:32   ` [PATCH 29/35] KVM: PPC: Fix CONFIG_KVM_GUEST && !CONFIG_KVM case Alexander Graf
2010-08-31  2:32   ` [PATCH 33/35] KVM: PPC: e500_tlb: Fix a minor copy-paste tracing bug Alexander Graf
2010-08-31  2:32   ` [PATCH 35/35] KVM: PPC: Add documentation for magic page enhancements Alexander Graf
2010-08-31  2:31 ` [PATCH 13/35] KVM: PPC: Add feature bitmap for magic page Alexander Graf
2010-08-31  2:31 ` [PATCH 14/35] KVM: PPC: Move BAT handling code into spr handler Alexander Graf
2010-08-31  2:31 ` [PATCH 15/35] KVM: PPC: Interpret SR registers on demand Alexander Graf
2010-08-31  2:31 ` [PATCH 17/35] KVM: PPC: Add mtsrin PV code Alexander Graf
2010-08-31  2:31 ` [PATCH 18/35] KVM: PPC: Make PV mtmsr work with r30 and r31 Alexander Graf
2010-08-31  2:32 ` [PATCH 20/35] KVM: PPC: Make PV mtmsrd L=1 " Alexander Graf
2010-08-31  2:32 ` [PATCH 22/35] KVM: PPC: Implement correct SID mapping on Book3s_32 Alexander Graf
2010-08-31  2:32 ` [PATCH 23/35] KVM: PPC: Don't put MSR_POW in MSR Alexander Graf
2010-08-31  2:32 ` [PATCH 25/35] KVM: PPC: fix compilation of "dump tlbs" debug function Alexander Graf
2010-08-31  2:32 ` [PATCH 26/35] KVM: PPC: allow ppc440gp to pass the compatibility check Alexander Graf
2010-08-31  2:32 ` [PATCH 27/35] KVM: PPC: Enable napping only for Book3s_64 Alexander Graf
2010-08-31  2:32 ` [PATCH 28/35] KVM: PPC: Implement Level interrupts on Book3S Alexander Graf
2010-08-31  2:32 ` [PATCH 30/35] KVM: PPC: Expose level based interrupt cap Alexander Graf
2010-08-31  2:32 ` [PATCH 31/35] KVM: PPC: Implement level interrupts for BookE Alexander Graf
2010-08-31  2:32 ` [PATCH 32/35] KVM: PPC: Document KVM_INTERRUPT ioctl Alexander Graf
2010-08-31  2:32 ` [PATCH 34/35] KVM: PPC: Fix compile error in e500_tlb.c Alexander Graf
2010-09-01  7:50 ` [PULL 00/35] KVM: PPC: End-August patch queue Avi Kivity

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=1283221937-21006-12-git-send-email-agraf@suse.de \
    --to=agraf-l3a5bk7wagm@public.gmane.org \
    --cc=kvm-ppc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=kvm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linuxppc-dev-mnsaURCQ41sdnm+yROfE0A@public.gmane.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).