From: Vincent Chen <vincent.chen@sifive.com>
To: anup@brainfault.org, atishp@atishpatra.org,
kvm-riscv@lists.infradead.org
Cc: paul.walmsley@sifive.com, palmer@dabbelt.com,
linux-riscv@lists.infradead.org, fu-ching.yang@sifive.com,
hsinyi.lee@sifive.com, Vincent Chen <vincent.chen@sifive.com>
Subject: [PATCH v2] RISC-V: KVM: Refine __kvm_riscv_switch_to() implementation
Date: Wed, 23 Feb 2022 09:13:31 +0800 [thread overview]
Message-ID: <20220223011331.12254-1-vincent.chen@sifive.com> (raw)
Kernel uses __kvm_riscv_switch_to() and __kvm_switch_return() to switch
the context of host kernel and guest kernel. Several CSRs belonging to the
context will be read and written during the context switch. To ensure
atomic read-modify-write control of CSR and ordering of CSR accesses, some
hardware blocks flush the pipeline when writing a CSR. In this
circumstance, grouping CSR executions together as much as possible can
reduce the performance impact of the pipeline. Therefore, this commit
reorders the CSR instructions to enhance the context switch performance..
Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Suggested-by: Hsinyi Lee <hsinyi.lee@sifive.com>
Suggested-by: Fu-Ching Yang <fu-ching.yang@sifive.com>
---
arch/riscv/kvm/vcpu_switch.S | 60 ++++++++++++++++++++----------------
1 file changed, 34 insertions(+), 26 deletions(-)
diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S
index 029a28a195c6..d74df8eb4d71 100644
--- a/arch/riscv/kvm/vcpu_switch.S
+++ b/arch/riscv/kvm/vcpu_switch.S
@@ -41,33 +41,37 @@ ENTRY(__kvm_riscv_switch_to)
REG_S s10, (KVM_ARCH_HOST_S10)(a0)
REG_S s11, (KVM_ARCH_HOST_S11)(a0)
- /* Save Host and Restore Guest SSTATUS */
+ /* Load Guest CSR values */
REG_L t0, (KVM_ARCH_GUEST_SSTATUS)(a0)
+ REG_L t1, (KVM_ARCH_GUEST_HSTATUS)(a0)
+ REG_L t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
+ la t4, __kvm_switch_return
+ REG_L t5, (KVM_ARCH_GUEST_SEPC)(a0)
+
+ /* Save Host and Restore Guest SSTATUS */
csrrw t0, CSR_SSTATUS, t0
- REG_S t0, (KVM_ARCH_HOST_SSTATUS)(a0)
/* Save Host and Restore Guest HSTATUS */
- REG_L t1, (KVM_ARCH_GUEST_HSTATUS)(a0)
csrrw t1, CSR_HSTATUS, t1
- REG_S t1, (KVM_ARCH_HOST_HSTATUS)(a0)
/* Save Host and Restore Guest SCOUNTEREN */
- REG_L t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
csrrw t2, CSR_SCOUNTEREN, t2
- REG_S t2, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
-
- /* Save Host SSCRATCH and change it to struct kvm_vcpu_arch pointer */
- csrrw t3, CSR_SSCRATCH, a0
- REG_S t3, (KVM_ARCH_HOST_SSCRATCH)(a0)
/* Save Host STVEC and change it to return path */
- la t4, __kvm_switch_return
csrrw t4, CSR_STVEC, t4
- REG_S t4, (KVM_ARCH_HOST_STVEC)(a0)
+
+ /* Save Host SSCRATCH and change it to struct kvm_vcpu_arch pointer */
+ csrrw t3, CSR_SSCRATCH, a0
/* Restore Guest SEPC */
- REG_L t0, (KVM_ARCH_GUEST_SEPC)(a0)
- csrw CSR_SEPC, t0
+ csrw CSR_SEPC, t5
+
+ /* Store Host CSR values */
+ REG_S t0, (KVM_ARCH_HOST_SSTATUS)(a0)
+ REG_S t1, (KVM_ARCH_HOST_HSTATUS)(a0)
+ REG_S t2, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
+ REG_S t3, (KVM_ARCH_HOST_SSCRATCH)(a0)
+ REG_S t4, (KVM_ARCH_HOST_STVEC)(a0)
/* Restore Guest GPRs (except A0) */
REG_L ra, (KVM_ARCH_GUEST_RA)(a0)
@@ -145,32 +149,36 @@ __kvm_switch_return:
REG_S t5, (KVM_ARCH_GUEST_T5)(a0)
REG_S t6, (KVM_ARCH_GUEST_T6)(a0)
+ /* Load Host CSR values */
+ REG_L t1, (KVM_ARCH_HOST_STVEC)(a0)
+ REG_L t2, (KVM_ARCH_HOST_SSCRATCH)(a0)
+ REG_L t3, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
+ REG_L t4, (KVM_ARCH_HOST_HSTATUS)(a0)
+ REG_L t5, (KVM_ARCH_HOST_SSTATUS)(a0)
+
/* Save Guest SEPC */
csrr t0, CSR_SEPC
- REG_S t0, (KVM_ARCH_GUEST_SEPC)(a0)
-
- /* Restore Host STVEC */
- REG_L t1, (KVM_ARCH_HOST_STVEC)(a0)
- csrw CSR_STVEC, t1
/* Save Guest A0 and Restore Host SSCRATCH */
- REG_L t2, (KVM_ARCH_HOST_SSCRATCH)(a0)
csrrw t2, CSR_SSCRATCH, t2
- REG_S t2, (KVM_ARCH_GUEST_A0)(a0)
+
+ /* Restore Host STVEC */
+ csrw CSR_STVEC, t1
/* Save Guest and Restore Host SCOUNTEREN */
- REG_L t3, (KVM_ARCH_HOST_SCOUNTEREN)(a0)
csrrw t3, CSR_SCOUNTEREN, t3
- REG_S t3, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
/* Save Guest and Restore Host HSTATUS */
- REG_L t4, (KVM_ARCH_HOST_HSTATUS)(a0)
csrrw t4, CSR_HSTATUS, t4
- REG_S t4, (KVM_ARCH_GUEST_HSTATUS)(a0)
/* Save Guest and Restore Host SSTATUS */
- REG_L t5, (KVM_ARCH_HOST_SSTATUS)(a0)
csrrw t5, CSR_SSTATUS, t5
+
+ /* Store Guest CSR values */
+ REG_S t0, (KVM_ARCH_GUEST_SEPC)(a0)
+ REG_S t2, (KVM_ARCH_GUEST_A0)(a0)
+ REG_S t3, (KVM_ARCH_GUEST_SCOUNTEREN)(a0)
+ REG_S t4, (KVM_ARCH_GUEST_HSTATUS)(a0)
REG_S t5, (KVM_ARCH_GUEST_SSTATUS)(a0)
/* Restore Host GPRs (except A0 and T0-T6) */
--
2.17.1
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
next reply other threads:[~2022-02-23 1:14 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-23 1:13 Vincent Chen [this message]
2022-02-28 6:12 ` [PATCH v2] RISC-V: KVM: Refine __kvm_riscv_switch_to() implementation Anup Patel
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=20220223011331.12254-1-vincent.chen@sifive.com \
--to=vincent.chen@sifive.com \
--cc=anup@brainfault.org \
--cc=atishp@atishpatra.org \
--cc=fu-ching.yang@sifive.com \
--cc=hsinyi.lee@sifive.com \
--cc=kvm-riscv@lists.infradead.org \
--cc=linux-riscv@lists.infradead.org \
--cc=palmer@dabbelt.com \
--cc=paul.walmsley@sifive.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