From: Christian Borntraeger <borntraeger@de.ibm.com>
To: "Paolo Bonzini" <pbonzini@redhat.com>,
"Radim Krčmář" <rkrcmar@redhat.com>
Cc: KVM <kvm@vger.kernel.org>,
Cornelia Huck <cornelia.huck@de.ibm.com>,
linux-s390 <linux-s390@vger.kernel.org>,
Christian Borntraeger <borntraeger@de.ibm.com>,
Fan Zhang <zhangfan@linux.vnet.ibm.com>
Subject: [GIT PULL 08/11] KVM: s390: lazy enable RI
Date: Thu, 8 Sep 2016 14:00:20 +0200 [thread overview]
Message-ID: <1473336023-15522-9-git-send-email-borntraeger@de.ibm.com> (raw)
In-Reply-To: <1473336023-15522-1-git-send-email-borntraeger@de.ibm.com>
From: Fan Zhang <zhangfan@linux.vnet.ibm.com>
Only enable runtime instrumentation if the guest issues an RI related
instruction or if userspace changes the riccb to a valid state.
This makes entry/exit a tiny bit faster.
Initial patch by Christian Borntraeger
Signed-off-by: Fan Zhang <zhangfan@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
arch/s390/kvm/intercept.c | 1 +
arch/s390/kvm/kvm-s390.c | 15 +++++++++++++--
arch/s390/kvm/kvm-s390.h | 1 +
arch/s390/kvm/priv.c | 21 +++++++++++++++++++++
4 files changed, 36 insertions(+), 2 deletions(-)
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index dfd0ca2..1cab8a1 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -29,6 +29,7 @@ static const intercept_handler_t instruction_handlers[256] = {
[0x01] = kvm_s390_handle_01,
[0x82] = kvm_s390_handle_lpsw,
[0x83] = kvm_s390_handle_diag,
+ [0xaa] = kvm_s390_handle_aa,
[0xae] = kvm_s390_handle_sigp,
[0xb2] = kvm_s390_handle_b2,
[0xb6] = kvm_s390_handle_stctl,
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index dead20a..892abf4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1938,8 +1938,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->eca |= 1;
if (sclp.has_sigpif)
vcpu->arch.sie_block->eca |= 0x10000000U;
- if (test_kvm_facility(vcpu->kvm, 64))
- vcpu->arch.sie_block->ecb3 |= 0x01;
if (test_kvm_facility(vcpu->kvm, 129)) {
vcpu->arch.sie_block->eca |= 0x00020000;
vcpu->arch.sie_block->ecd |= 0x20000000;
@@ -2694,6 +2692,19 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
kvm_clear_async_pf_completion_queue(vcpu);
}
+ /*
+ * If userspace sets the riccb (e.g. after migration) to a valid state,
+ * we should enable RI here instead of doing the lazy enablement.
+ */
+ if ((kvm_run->kvm_dirty_regs & KVM_SYNC_RICCB) &&
+ test_kvm_facility(vcpu->kvm, 64)) {
+ struct runtime_instr_cb *riccb =
+ (struct runtime_instr_cb *) &kvm_run->s.regs.riccb;
+
+ if (riccb->valid)
+ vcpu->arch.sie_block->ecb3 |= 0x01;
+ }
+
kvm_run->kvm_dirty_regs = 0;
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index c3d4f16..9995cab 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -245,6 +245,7 @@ static inline void kvm_s390_retry_instr(struct kvm_vcpu *vcpu)
/* implemented in priv.c */
int is_valid_psw(psw_t *psw);
+int kvm_s390_handle_aa(struct kvm_vcpu *vcpu);
int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
int kvm_s390_handle_01(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 4616038..e184353 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -32,6 +32,24 @@
#include "kvm-s390.h"
#include "trace.h"
+static int handle_ri(struct kvm_vcpu *vcpu)
+{
+ if (test_kvm_facility(vcpu->kvm, 64)) {
+ vcpu->arch.sie_block->ecb3 |= 0x01;
+ kvm_s390_retry_instr(vcpu);
+ return 0;
+ } else
+ return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
+}
+
+int kvm_s390_handle_aa(struct kvm_vcpu *vcpu)
+{
+ if ((vcpu->arch.sie_block->ipa & 0xf) <= 4)
+ return handle_ri(vcpu);
+ else
+ return -EOPNOTSUPP;
+}
+
/* Handle SCK (SET CLOCK) interception */
static int handle_set_clock(struct kvm_vcpu *vcpu)
{
@@ -1093,6 +1111,9 @@ static int handle_stctg(struct kvm_vcpu *vcpu)
static const intercept_handler_t eb_handlers[256] = {
[0x2f] = handle_lctlg,
[0x25] = handle_stctg,
+ [0x60] = handle_ri,
+ [0x61] = handle_ri,
+ [0x62] = handle_ri,
};
int kvm_s390_handle_eb(struct kvm_vcpu *vcpu)
--
2.5.5
next prev parent reply other threads:[~2016-09-08 12:00 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-08 12:00 [GIT PULL 00/11] KVM: s390: features and fixes for 4.9 (via kvm/next) Christian Borntraeger
2016-09-08 12:00 ` [GIT PULL 01/11] KVM: s390: generate facility mask from readable list Christian Borntraeger
2016-09-08 12:00 ` [GIT PULL 02/11] KVM: s390: factor out actual delivery of machine checks Christian Borntraeger
2016-09-08 12:00 ` [GIT PULL 03/11] KVM: s390: split store status and machine check handling Christian Borntraeger
2016-09-08 12:00 ` [GIT PULL 04/11] KVM: s390: fix delivery of vector regs during machine checks Christian Borntraeger
2016-09-08 12:00 ` [GIT PULL 05/11] KVM: s390: write external damage code on " Christian Borntraeger
2016-09-08 12:00 ` [GIT PULL 06/11] KVM: s390: guestdbg: separate defines for per code Christian Borntraeger
2016-09-08 12:00 ` [GIT PULL 07/11] KVM: s390: gaccess: simplify translation exception handling Christian Borntraeger
2016-09-08 12:00 ` Christian Borntraeger [this message]
2016-09-08 12:00 ` [GIT PULL 09/11] KVM: s390: allow 255 VCPUs when sca entries aren't used Christian Borntraeger
2016-09-08 12:00 ` [GIT PULL 10/11] KVM: s390: Improve determination of sizes in kvm_s390_import_bp_data() Christian Borntraeger
2016-09-08 12:00 ` [GIT PULL 11/11] KVM: s390: Use memdup_user() rather than duplicating code Christian Borntraeger
2016-09-08 13:36 ` [GIT PULL 00/11] KVM: s390: features and fixes for 4.9 (via kvm/next) Paolo Bonzini
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=1473336023-15522-9-git-send-email-borntraeger@de.ibm.com \
--to=borntraeger@de.ibm.com \
--cc=cornelia.huck@de.ibm.com \
--cc=kvm@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=rkrcmar@redhat.com \
--cc=zhangfan@linux.vnet.ibm.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