Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
To:     Nathan Lynch <nathanl@linux.ibm.com>,
        Michael Ellerman <mpe@ellerman.id.au>,
        Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>,
        Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>,
        "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>,
        Tyrel Datwyler <tyreld@linux.ibm.com>
Cc:     linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org,
        "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Subject: [PATCH v3 2/6] powerpc/idle: Add accessor function to always read latest idle PURR
Date:   Wed, 11 Mar 2020 15:07:37 +0530
Message-Id: <1583919461-27405-3-git-send-email-ego@linux.vnet.ibm.com>
In-Reply-To: <1583919461-27405-1-git-send-email-ego@linux.vnet.ibm.com>
References: <1583919461-27405-1-git-send-email-ego@linux.vnet.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>

Currently when CPU goes idle, we take a snapshot of PURR via
pseries_idle_prolog() which is used at the CPU idle exit to compute
the idle PURR cycles via the function pseries_idle_epilog().  Thus,
the value of idle PURR cycle thus read before pseries_idle_prolog() and
after pseries_idle_epilog() is always correct.

However, if we were to read the idle PURR cycles from an interrupt
context between pseries_idle_prolog() and pseries_idle_epilog() (this will
be done in a future patch), then, the value of the idle PURR thus read
will not include the cycles spent in the most recent idle period.

This patch addresses the issue by providing accessor function to read
the idle PURR such such that it includes the cycles spent in the most
recent idle period, if we read it between pseries_idle_prolog() and
pseries_idle_epilog(). In order to achieve it, the patch saves the
snapshot of PURR in pseries_idle_prolog() in a per-cpu variable,
instead of on the stack, so that it can be accessed from an interrupt
context.

Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/idle.h        | 46 +++++++++++++++++++++++++++-------
 arch/powerpc/platforms/pseries/setup.c |  7 +++---
 drivers/cpuidle/cpuidle-pseries.c      | 15 +++++------
 3 files changed, 46 insertions(+), 22 deletions(-)

diff --git a/arch/powerpc/include/asm/idle.h b/arch/powerpc/include/asm/idle.h
index e838ea5..7552823 100644
--- a/arch/powerpc/include/asm/idle.h
+++ b/arch/powerpc/include/asm/idle.h
@@ -3,10 +3,27 @@
 #define _ASM_POWERPC_IDLE_H
 #include <asm/runlatch.h>
 
-static inline void pseries_idle_prolog(unsigned long *in_purr)
+DECLARE_PER_CPU(u64, idle_entry_purr_snap);
+
+static inline void snapshot_purr_idle_entry(void)
+{
+	*this_cpu_ptr(&idle_entry_purr_snap) = mfspr(SPRN_PURR);
+}
+
+static inline void update_idle_purr_accounting(void)
+{
+	u64 wait_cycles;
+	u64 in_purr = *this_cpu_ptr(&idle_entry_purr_snap);
+
+	wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
+	wait_cycles += mfspr(SPRN_PURR) - in_purr;
+	get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+}
+
+static inline void pseries_idle_prolog(void)
 {
 	ppc64_runlatch_off();
-	*in_purr = mfspr(SPRN_PURR);
+	snapshot_purr_idle_entry();
 	/*
 	 * Indicate to the HV that we are idle. Now would be
 	 * a good time to find other work to dispatch.
@@ -14,15 +31,26 @@ static inline void pseries_idle_prolog(unsigned long *in_purr)
 	get_lppaca()->idle = 1;
 }
 
-static inline void pseries_idle_epilog(unsigned long in_purr)
+static inline void pseries_idle_epilog(void)
 {
-	u64 wait_cycles;
-
-	wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
-	wait_cycles += mfspr(SPRN_PURR) - in_purr;
-	get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+	update_idle_purr_accounting();
 	get_lppaca()->idle = 0;
-
 	ppc64_runlatch_on();
 }
+
+static inline u64 read_this_idle_purr(void)
+{
+	/*
+	 * If we are reading from an idle context, update the
+	 * idle-purr cycles corresponding to the last idle period.
+	 * Since the idle context is not yet over, take a fresh
+	 * snapshot of the idle-purr.
+	 */
+	if (unlikely(get_lppaca()->idle == 1)) {
+		update_idle_purr_accounting();
+		snapshot_purr_idle_entry();
+	}
+
+	return be64_to_cpu(get_lppaca()->wait_state_cycles);
+}
 #endif
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 2f53e6b..4905c96 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -318,10 +318,9 @@ static int alloc_dispatch_log_kmem_cache(void)
 }
 machine_early_initcall(pseries, alloc_dispatch_log_kmem_cache);
 
+DEFINE_PER_CPU(u64, idle_entry_purr_snap);
 static void pseries_lpar_idle(void)
 {
-	unsigned long in_purr;
-
 	/*
 	 * Default handler to go into low thread priority and possibly
 	 * low power mode by ceding processor to hypervisor
@@ -331,7 +330,7 @@ static void pseries_lpar_idle(void)
 		return;
 
 	/* Indicate to hypervisor that we are idle. */
-	pseries_idle_prolog(&in_purr);
+	pseries_idle_prolog();
 
 	/*
 	 * Yield the processor to the hypervisor.  We return if
@@ -342,7 +341,7 @@ static void pseries_lpar_idle(void)
 	 */
 	cede_processor();
 
-	pseries_idle_epilog(in_purr);
+	pseries_idle_epilog();
 }
 
 /*
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 46d5e05..6513ef2 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -36,12 +36,11 @@ static int snooze_loop(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			int index)
 {
-	unsigned long in_purr;
 	u64 snooze_exit_time;
 
 	set_thread_flag(TIF_POLLING_NRFLAG);
 
-	pseries_idle_prolog(&in_purr);
+	pseries_idle_prolog();
 	local_irq_enable();
 	snooze_exit_time = get_tb() + snooze_timeout;
 
@@ -65,7 +64,7 @@ static int snooze_loop(struct cpuidle_device *dev,
 
 	local_irq_disable();
 
-	pseries_idle_epilog(in_purr);
+	pseries_idle_epilog();
 
 	return index;
 }
@@ -91,9 +90,8 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv,
 				int index)
 {
-	unsigned long in_purr;
 
-	pseries_idle_prolog(&in_purr);
+	pseries_idle_prolog();
 	get_lppaca()->donate_dedicated_cpu = 1;
 
 	HMT_medium();
@@ -102,7 +100,7 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
 	local_irq_disable();
 	get_lppaca()->donate_dedicated_cpu = 0;
 
-	pseries_idle_epilog(in_purr);
+	pseries_idle_epilog();
 
 	return index;
 }
@@ -111,9 +109,8 @@ static int shared_cede_loop(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			int index)
 {
-	unsigned long in_purr;
 
-	pseries_idle_prolog(&in_purr);
+	pseries_idle_prolog();
 
 	/*
 	 * Yield the processor to the hypervisor.  We return if
@@ -125,7 +122,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
 	check_and_cede_processor();
 
 	local_irq_disable();
-	pseries_idle_epilog(in_purr);
+	pseries_idle_epilog();
 
 	return index;
 }
-- 
1.9.4