From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: kvm-ppc@vger.kernel.org, kvm@vger.kernel.org
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: [PATCH v3 16/16] powerpc/kvm: Use the PACA virt/real mode info instead of mfmsr
Date: Thu, 11 Jan 2018 15:34:13 +1100 [thread overview]
Message-ID: <20180111043413.22655-16-benh@kernel.crashing.org> (raw)
In-Reply-To: <20180111043413.22655-1-benh@kernel.crashing.org>
This shaves off a bunch of cycles from the KVM exit path
and the XIVE related hypercall.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kvm/book3s_hv_builtin.c | 5 ++---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 14 ++++++++------
2 files changed, 10 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 49a2c7825e04..5fbaa8710e0c 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -209,8 +209,7 @@ long kvmppc_h_random(struct kvm_vcpu *vcpu)
{
int r;
- /* Only need to do the expensive mfmsr() on radix */
- if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
+ if (local_paca->kvm_hstate.exit_virt)
r = powernv_get_random_long(&vcpu->arch.gpr[4]);
else
r = powernv_get_random_real_mode(&vcpu->arch.gpr[4]);
@@ -541,7 +540,7 @@ static long kvmppc_read_one_intr(bool *again)
#ifdef CONFIG_KVM_XICS
static inline bool is_rm(void)
{
- return !(mfmsr() & MSR_DR);
+ return !local_paca->kvm_hstate.exit_virt;
}
unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 1e32e188ba17..0024c449340b 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -190,8 +190,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
* we will be in virtual mode at this point, which makes it a
* little easier to get back to the caller.
*/
- mfmsr r0
- andi. r0, r0, MSR_IR /* in real mode? */
+ lbz r0,HSTATE_EXIT_VIRT(r13)
+ cmpwi r0,0
bne .Lvirt_return
/* RFI into the highmem handler */
@@ -1481,8 +1481,9 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
beq 1f
li r7, TM_SPC_PULL_OS_CTX
li r6, TM_QW1_OS
- mfmsr r0
- andi. r0, r0, MSR_DR /* in real mode? */
+ /* Are we in virtual or real mode ? */
+ lbz r0,HSTATE_EXIT_VIRT(r13)
+ cmpwi r0,0
beq 2f
ld r10, HSTATE_XIVE_TIMA_VIRT(r13)
cmpldi cr0, r10, 0
@@ -2804,8 +2805,9 @@ kvm_cede_exit:
stb r0, VCPU_CEDED(r9)
1: /* Enable XIVE escalation */
li r5, XIVE_ESB_SET_PQ_00
- mfmsr r0
- andi. r0, r0, MSR_DR /* in real mode? */
+ /* Are we in virtual or real mode ? */
+ lbz r0,HSTATE_EXIT_VIRT(r13)
+ cmpwi r0,0
beq 1f
ld r10, VCPU_XIVE_ESC_VADDR(r9)
cmpdi r10, 0
--
2.14.3
prev parent reply other threads:[~2018-01-11 4:35 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-11 4:33 [PATCH v3 01/16] powerpc/xive: Remove incorrect debug code Benjamin Herrenschmidt
2018-01-11 4:33 ` [PATCH v3 02/16] powerpc: Remove DEBUG define in 64-bit early setup code Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 03/16] powerpc: Reduce log level of "OPAL detected !" message Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 04/16] powerpc/kvm/xive: Add more debugfs queues info Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 05/16] powerpc/kvm/xive: Enable use of the new "single escalation" feature Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 06/16] powerpc/kvm/xive: Don't use existing "prodded" flag for xive escalations Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 07/16] powerpc/kvm/xive: Check DR not IR to chose real vs virt mode MMIOs Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 08/16] powerpc/kvm/xive: Make xive_pushed a byte, not a word Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 09/16] powerpc/xive: Move definition of ESB bits Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 10/16] powerpc/xive: Add interrupt flag to disable automatic EOI Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 11/16] powerpc/kvm/xive: Keep escalation interrupt masked unless ceded Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 12/16] powerpc/kvm: Make "no_xive:" label local Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 13/16] powerpc: Use the TRAP macro whenever comparing a trap number Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 14/16] powerpc: Remove useless EXC_COMMON_HV Benjamin Herrenschmidt
2018-01-11 4:34 ` [PATCH v3 15/16] powerpc/kvm: Store the MMU mode in the PACA on KVM exit Benjamin Herrenschmidt
2018-01-11 4:34 ` Benjamin Herrenschmidt [this message]
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=20180111043413.22655-16-benh@kernel.crashing.org \
--to=benh@kernel.crashing.org \
--cc=kvm-ppc@vger.kernel.org \
--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