From: Oliver Upton <oliver.upton@linux.dev>
To: kvmarm@lists.linux.dev
Cc: Marc Zyngier <maz@kernel.org>, Joey Gouly <joey.gouly@arm.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
Zenghui Yu <yuzenghui@huawei.com>,
Mingwei Zhang <mizhang@google.com>,
Colton Lewis <coltonlewis@google.com>,
Alexandru Elisei <alexandru.elisei@arm.com>,
Oliver Upton <oliver.upton@linux.dev>
Subject: [PATCH v2 16/16] KVM: arm64: Avoid reading ID_AA64DFR0_EL1 for debug save/restore
Date: Fri, 15 Nov 2024 14:49:24 -0800 [thread overview]
Message-ID: <20241115224924.2132364-17-oliver.upton@linux.dev> (raw)
In-Reply-To: <20241115224924.2132364-1-oliver.upton@linux.dev>
Similar to other per-CPU profiling/debug features we handle, store the
number of breakpoints/watchpoints in kvm_host_data to avoid reading the
ID register 4 times on every guest entry/exit. And if you're in the
nested virt business that's quite a few avoidable exits to the L0
hypervisor.
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
arch/arm64/include/asm/kvm_host.h | 4 ++++
arch/arm64/kvm/debug.c | 3 +++
arch/arm64/kvm/hyp/include/hyp/debug-sr.h | 17 ++++-------------
3 files changed, 11 insertions(+), 13 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 60bbca22c492..8bc0ec151684 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -661,6 +661,10 @@ struct kvm_host_data {
/* Number of programmable event counters (PMCR_EL0.N) for this CPU */
unsigned int nr_event_counters;
+
+ /* Number of debug breakpoints/watchpoints for this CPU (minus 1) */
+ unsigned int debug_brps;
+ unsigned int debug_wrps;
};
struct kvm_host_psci_config {
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 91e272dc7215..46dbeabd6833 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -63,6 +63,9 @@ void kvm_init_host_debug_data(void)
*host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N,
read_sysreg(pmcr_el0));
+ *host_data_ptr(debug_brps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr0);
+ *host_data_ptr(debug_wrps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr0);
+
if (has_vhe())
return;
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index c14586d87361..502a5b73ee70 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -106,12 +106,8 @@ static struct kvm_guest_debug_arch *__vcpu_debug_regs(struct kvm_vcpu *vcpu)
static void __debug_save_state(struct kvm_guest_debug_arch *dbg,
struct kvm_cpu_context *ctxt)
{
- u64 aa64dfr0;
- int brps, wrps;
-
- aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
- brps = (aa64dfr0 >> 12) & 0xf;
- wrps = (aa64dfr0 >> 20) & 0xf;
+ int brps = *host_data_ptr(debug_brps);
+ int wrps = *host_data_ptr(debug_wrps);
save_debug(dbg->dbg_bcr, dbgbcr, brps);
save_debug(dbg->dbg_bvr, dbgbvr, brps);
@@ -124,13 +120,8 @@ static void __debug_save_state(struct kvm_guest_debug_arch *dbg,
static void __debug_restore_state(struct kvm_guest_debug_arch *dbg,
struct kvm_cpu_context *ctxt)
{
- u64 aa64dfr0;
- int brps, wrps;
-
- aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
-
- brps = (aa64dfr0 >> 12) & 0xf;
- wrps = (aa64dfr0 >> 20) & 0xf;
+ int brps = *host_data_ptr(debug_brps);
+ int wrps = *host_data_ptr(debug_wrps);
restore_debug(dbg->dbg_bcr, dbgbcr, brps);
restore_debug(dbg->dbg_bvr, dbgbvr, brps);
--
2.39.5
next prev parent reply other threads:[~2024-11-15 22:50 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-15 22:49 [PATCH v2 00/16] KVM: arm64: Debug cleanups Oliver Upton
2024-11-15 22:49 ` [PATCH v2 01/16] KVM: arm64: Drop MDSCR_EL1_DEBUG_MASK Oliver Upton
2024-11-15 22:49 ` [PATCH v2 02/16] KVM: arm64: Get rid of __kvm_get_mdcr_el2() and related warts Oliver Upton
2024-11-28 19:35 ` Colton Lewis
2024-11-29 7:26 ` Oliver Upton
2024-11-15 22:49 ` [PATCH v2 03/16] KVM: arm64: Track presence of SPE/TRBE in kvm_host_data instead of vCPU Oliver Upton
2024-11-22 11:15 ` James Clark
2024-11-15 22:49 ` [PATCH v2 04/16] KVM: arm64: Move host SME/SVE tracking flags to host data Oliver Upton
2024-11-15 22:49 ` [PATCH v2 05/16] KVM: arm64: Evaluate debug owner at vcpu_load() Oliver Upton
2024-11-15 22:49 ` [PATCH v2 06/16] KVM: arm64: Clean up KVM_SET_GUEST_DEBUG handler Oliver Upton
2024-11-15 22:49 ` [PATCH v2 07/16] KVM: arm64: Select debug state to save/restore based on debug owner Oliver Upton
2024-11-15 22:49 ` [PATCH v2 08/16] KVM: arm64: Remove debug tracepoints Oliver Upton
2024-11-15 22:49 ` [PATCH v2 09/16] KVM: arm64: Remove vestiges of debug_ptr Oliver Upton
2024-11-15 22:49 ` [PATCH v2 10/16] KVM: arm64: Use debug_owner to track if debug regs need save/restore Oliver Upton
2024-11-15 22:49 ` [PATCH v2 11/16] KVM: arm64: Reload vCPU for accesses to OSLAR_EL1 Oliver Upton
2024-11-15 22:49 ` [PATCH v2 12/16] KVM: arm64: Compute MDCR_EL2 at vcpu_load() Oliver Upton
2024-11-15 22:49 ` [PATCH v2 13/16] KVM: arm64: Don't hijack guest context MDSCR_EL1 Oliver Upton
2024-11-15 22:49 ` [PATCH v2 14/16] KVM: arm64: Manage software step state at load/put Oliver Upton
2024-11-15 22:49 ` [PATCH v2 15/16] KVM: arm64: nv: Honor MDCR_EL2.TDE routing for debug exceptions Oliver Upton
2024-11-15 22:49 ` Oliver Upton [this message]
2024-11-22 11:08 ` [PATCH v2 00/16] KVM: arm64: Debug cleanups James Clark
2024-11-30 3:08 ` Oliver Upton
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=20241115224924.2132364-17-oliver.upton@linux.dev \
--to=oliver.upton@linux.dev \
--cc=alexandru.elisei@arm.com \
--cc=coltonlewis@google.com \
--cc=joey.gouly@arm.com \
--cc=kvmarm@lists.linux.dev \
--cc=maz@kernel.org \
--cc=mizhang@google.com \
--cc=suzuki.poulose@arm.com \
--cc=yuzenghui@huawei.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