Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   "Vineeth Pillai (Google)" <vineeth@bitbyteword.org>
To:     Ben Segall <bsegall@google.com>, Borislav Petkov <bp@alien8.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        "H . Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@redhat.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Mel Gorman <mgorman@suse.de>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Andy Lutomirski <luto@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Sean Christopherson <seanjc@google.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Valentin Schneider <vschneid@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Vitaly Kuznetsov <vkuznets@redhat.com>,
        Wanpeng Li <wanpengli@tencent.com>
Cc:     "Vineeth Pillai (Google)" <vineeth@bitbyteword.org>,
        Suleiman Souhlal <suleiman@google.com>,
        Masami Hiramatsu <mhiramat@google.com>, kvm@vger.kernel.org,
        linux-kernel@vger.kernel.org, x86@kernel.org,
        Joel Fernandes <joel@joelfernandes.org>
Subject: [RFC PATCH 8/8] irq: boost/unboost in irq/nmi entry/exit and softirq
Date:   Wed, 13 Dec 2023 21:47:25 -0500
Message-ID: <20231214024727.3503870-9-vineeth@bitbyteword.org>
In-Reply-To: <20231214024727.3503870-1-vineeth@bitbyteword.org>
References: <20231214024727.3503870-1-vineeth@bitbyteword.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

The host proactively boosts the VCPU threads during irq/nmi injection.
However, the host is unaware of posted interrupts, and therefore, the
guest should request a boost if it has not already been boosted.

Similarly, guest should request an unboost on irq/nmi/softirq exit if
the vcpu doesn't need the boost any more.

Co-developed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
---
 kernel/entry/common.c | 30 ++++++++++++++++++++++++++++++
 kernel/softirq.c      | 11 +++++++++++
 2 files changed, 41 insertions(+)

diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index fae56faac0b0..c69912b71725 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -327,6 +327,13 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 		.exit_rcu = false,
 	};
 
+#ifdef CONFIG_PARAVIRT_SCHED
+	instrumentation_begin();
+	if (pv_sched_enabled())
+		pv_sched_boost_vcpu_lazy();
+	instrumentation_end();
+#endif
+
 	if (user_mode(regs)) {
 		irqentry_enter_from_user_mode(regs);
 		return ret;
@@ -452,6 +459,18 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 		if (state.exit_rcu)
 			ct_irq_exit();
 	}
+
+#ifdef CONFIG_PARAVIRT_SCHED
+	instrumentation_begin();
+	/*
+	 * On irq exit, request a deboost from hypervisor if no softirq pending
+	 * and current task is not RT and !need_resched.
+	 */
+	if (pv_sched_enabled() && !local_softirq_pending() &&
+			!need_resched() && !task_is_realtime(current))
+		pv_sched_unboost_vcpu();
+	instrumentation_end();
+#endif
 }
 
 irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
@@ -469,6 +488,11 @@ irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
 	kmsan_unpoison_entry_regs(regs);
 	trace_hardirqs_off_finish();
 	ftrace_nmi_enter();
+
+#ifdef CONFIG_PARAVIRT_SCHED
+	if (pv_sched_enabled())
+		pv_sched_boost_vcpu_lazy();
+#endif
 	instrumentation_end();
 
 	return irq_state;
@@ -482,6 +506,12 @@ void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
 		trace_hardirqs_on_prepare();
 		lockdep_hardirqs_on_prepare();
 	}
+
+#ifdef CONFIG_PARAVIRT_SCHED
+	if (pv_sched_enabled() && !in_hardirq() && !local_softirq_pending() &&
+			!need_resched() && !task_is_realtime(current))
+		pv_sched_unboost_vcpu();
+#endif
 	instrumentation_end();
 
 	ct_nmi_exit();
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 807b34ccd797..90a127615e16 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -530,6 +530,11 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 	in_hardirq = lockdep_softirq_start();
 	account_softirq_enter(current);
 
+#ifdef CONFIG_PARAVIRT_SCHED
+	if (pv_sched_enabled())
+		pv_sched_boost_vcpu_lazy();
+#endif
+
 restart:
 	/* Reset the pending bitmask before enabling irqs */
 	set_softirq_pending(0);
@@ -577,6 +582,12 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 		wakeup_softirqd();
 	}
 
+#ifdef CONFIG_PARAVIRT_SCHED
+	if (pv_sched_enabled() && !need_resched() &&
+			!task_is_realtime(current))
+		pv_sched_unboost_vcpu();
+#endif
+
 	account_softirq_exit(current);
 	lockdep_softirq_end(in_hardirq);
 	softirq_handle_end();
-- 
2.43.0