[PATCH] cpuidle/powernv: Populate cpuidle state details by querying the device-tree

[PATCH] cpuidle/powernv: Populate cpuidle state details by querying the device-tree

[Preeti U Murthy]

We hard code the metrics relevant for cpuidle states in the kernel today.
Instead pick them up from the device tree so that they remain relevant
and updated for the system that the kernel is running on.

Cc: linux-pm@vger.kernel.org
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: devicetree@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
---

 drivers/cpuidle/cpuidle-powernv.c |   27 ++++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index fa79392..b57681d 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -165,7 +165,8 @@ static int powernv_add_idle_states(void)
 	int nr_idle_states = 1; /* Snooze */
 	int dt_idle_states;
 	const __be32 *idle_state_flags;
-	u32 len_flags, flags;
+	const __be32 *idle_state_latency;
+	u32 len_flags, flags, latency_ns;
 	int i;
 
 	/* Currently we have snooze statically defined */
@@ -182,18 +183,32 @@ static int powernv_add_idle_states(void)
 		return nr_idle_states;
 	}
 
+	idle_state_latency = of_get_property(power_mgt,
+			"ibm,cpu-idle-state-latencies-ns", NULL);
+	if (!idle_state_latency) {
+		pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-latencies-ns\n");
+		return nr_idle_states;
+	}
+
 	dt_idle_states = len_flags / sizeof(u32);
 
 	for (i = 0; i < dt_idle_states; i++) {
 
 		flags = be32_to_cpu(idle_state_flags[i]);
+
+		/* Cpuidle accepts exit_latency in us and we estimate
+		 * target residency to be 10x exit_latency
+		 */
+		latency_ns = be32_to_cpu(idle_state_latency[i]);
 		if (flags & IDLE_USE_INST_NAP) {
 			/* Add NAP state */
 			strcpy(powernv_states[nr_idle_states].name, "Nap");
 			strcpy(powernv_states[nr_idle_states].desc, "Nap");
 			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIME_VALID;
-			powernv_states[nr_idle_states].exit_latency = 10;
-			powernv_states[nr_idle_states].target_residency = 100;
+			powernv_states[nr_idle_states].exit_latency =
+					((unsigned int)latency_ns) / 1000;
+			powernv_states[nr_idle_states].target_residency =
+					((unsigned int)latency_ns / 100);
 			powernv_states[nr_idle_states].enter = &nap_loop;
 			nr_idle_states++;
 		}
@@ -204,8 +219,10 @@ static int powernv_add_idle_states(void)
 			strcpy(powernv_states[nr_idle_states].desc, "FastSleep");
 			powernv_states[nr_idle_states].flags =
 				CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TIMER_STOP;
-			powernv_states[nr_idle_states].exit_latency = 300;
-			powernv_states[nr_idle_states].target_residency = 1000000;
+			powernv_states[nr_idle_states].exit_latency =
+					((unsigned int)latency_ns) / 1000;
+			powernv_states[nr_idle_states].target_residency =
+					((unsigned int)latency_ns / 100);
 			powernv_states[nr_idle_states].enter = &fastsleep_loop;
 			nr_idle_states++;
 		}

Re: [PATCH] cpuidle/powernv: Populate cpuidle state details by querying the device-tree

[Rafael J. Wysocki]

On Tuesday, October 14, 2014 01:23:00 PM Preeti U Murthy wrote:
> We hard code the metrics relevant for cpuidle states in the kernel today.
> Instead pick them up from the device tree so that they remain relevant
> and updated for the system that the kernel is running on.
> 
> Cc: linux-pm@vger.kernel.org
> Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
> Cc: devicetree@vger.kernel.org
> Cc: linuxppc-dev@lists.ozlabs.org
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
> Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>

Applied, thanks!

> ---
> 
>  drivers/cpuidle/cpuidle-powernv.c |   27 ++++++++++++++++++++++-----
>  1 file changed, 22 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
> index fa79392..b57681d 100644
> --- a/drivers/cpuidle/cpuidle-powernv.c
> +++ b/drivers/cpuidle/cpuidle-powernv.c
> @@ -165,7 +165,8 @@ static int powernv_add_idle_states(void)
>  	int nr_idle_states = 1; /* Snooze */
>  	int dt_idle_states;
>  	const __be32 *idle_state_flags;
> -	u32 len_flags, flags;
> +	const __be32 *idle_state_latency;
> +	u32 len_flags, flags, latency_ns;
>  	int i;
>  
>  	/* Currently we have snooze statically defined */
> @@ -182,18 +183,32 @@ static int powernv_add_idle_states(void)
>  		return nr_idle_states;
>  	}
>  
> +	idle_state_latency = of_get_property(power_mgt,
> +			"ibm,cpu-idle-state-latencies-ns", NULL);
> +	if (!idle_state_latency) {
> +		pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-latencies-ns\n");
> +		return nr_idle_states;
> +	}
> +
>  	dt_idle_states = len_flags / sizeof(u32);
>  
>  	for (i = 0; i < dt_idle_states; i++) {
>  
>  		flags = be32_to_cpu(idle_state_flags[i]);
> +
> +		/* Cpuidle accepts exit_latency in us and we estimate
> +		 * target residency to be 10x exit_latency
> +		 */
> +		latency_ns = be32_to_cpu(idle_state_latency[i]);
>  		if (flags & IDLE_USE_INST_NAP) {
>  			/* Add NAP state */
>  			strcpy(powernv_states[nr_idle_states].name, "Nap");
>  			strcpy(powernv_states[nr_idle_states].desc, "Nap");
>  			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIME_VALID;
> -			powernv_states[nr_idle_states].exit_latency = 10;
> -			powernv_states[nr_idle_states].target_residency = 100;
> +			powernv_states[nr_idle_states].exit_latency =
> +					((unsigned int)latency_ns) / 1000;
> +			powernv_states[nr_idle_states].target_residency =
> +					((unsigned int)latency_ns / 100);
>  			powernv_states[nr_idle_states].enter = &nap_loop;
>  			nr_idle_states++;
>  		}
> @@ -204,8 +219,10 @@ static int powernv_add_idle_states(void)
>  			strcpy(powernv_states[nr_idle_states].desc, "FastSleep");
>  			powernv_states[nr_idle_states].flags =
>  				CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TIMER_STOP;
> -			powernv_states[nr_idle_states].exit_latency = 300;
> -			powernv_states[nr_idle_states].target_residency = 1000000;
> +			powernv_states[nr_idle_states].exit_latency =
> +					((unsigned int)latency_ns) / 1000;
> +			powernv_states[nr_idle_states].target_residency =
> +					((unsigned int)latency_ns / 100);
>  			powernv_states[nr_idle_states].enter = &fastsleep_loop;
>  			nr_idle_states++;
>  		}
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-pm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

-- 
I speak only for myself.
Rafael J. Wysocki, Intel Open Source Technology Center.

Re: [PATCH] cpuidle/powernv: Populate cpuidle state details by querying the device-tree

[Lorenzo Pieralisi]

On Tue, Oct 14, 2014 at 08:53:00AM +0100, Preeti U Murthy wrote:
> We hard code the metrics relevant for cpuidle states in the kernel today.
> Instead pick them up from the device tree so that they remain relevant
> and updated for the system that the kernel is running on.
> 
> Cc: linux-pm@vger.kernel.org
> Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
> Cc: devicetree@vger.kernel.org
> Cc: linuxppc-dev@lists.ozlabs.org
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
> Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
> ---
> 
>  drivers/cpuidle/cpuidle-powernv.c |   27 ++++++++++++++++++++++-----
>  1 file changed, 22 insertions(+), 5 deletions(-)

Device tree properties should be documented, and these bindings are
getting very similar to the ones I have just completed for ARM,
I wonder whether we should take the generic bits out of ARM bindings (ie
exit_latency) and make those available to other architectures.

Thanks,
Lorenzo

> 
> diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
> index fa79392..b57681d 100644
> --- a/drivers/cpuidle/cpuidle-powernv.c
> +++ b/drivers/cpuidle/cpuidle-powernv.c
> @@ -165,7 +165,8 @@ static int powernv_add_idle_states(void)
>  	int nr_idle_states = 1; /* Snooze */
>  	int dt_idle_states;
>  	const __be32 *idle_state_flags;
> -	u32 len_flags, flags;
> +	const __be32 *idle_state_latency;
> +	u32 len_flags, flags, latency_ns;
>  	int i;
>  
>  	/* Currently we have snooze statically defined */
> @@ -182,18 +183,32 @@ static int powernv_add_idle_states(void)
>  		return nr_idle_states;
>  	}
>  
> +	idle_state_latency = of_get_property(power_mgt,
> +			"ibm,cpu-idle-state-latencies-ns", NULL);
> +	if (!idle_state_latency) {
> +		pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-latencies-ns\n");
> +		return nr_idle_states;
> +	}
> +
>  	dt_idle_states = len_flags / sizeof(u32);
>  
>  	for (i = 0; i < dt_idle_states; i++) {
>  
>  		flags = be32_to_cpu(idle_state_flags[i]);
> +
> +		/* Cpuidle accepts exit_latency in us and we estimate
> +		 * target residency to be 10x exit_latency
> +		 */
> +		latency_ns = be32_to_cpu(idle_state_latency[i]);
>  		if (flags & IDLE_USE_INST_NAP) {
>  			/* Add NAP state */
>  			strcpy(powernv_states[nr_idle_states].name, "Nap");
>  			strcpy(powernv_states[nr_idle_states].desc, "Nap");
>  			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIME_VALID;
> -			powernv_states[nr_idle_states].exit_latency = 10;
> -			powernv_states[nr_idle_states].target_residency = 100;
> +			powernv_states[nr_idle_states].exit_latency =
> +					((unsigned int)latency_ns) / 1000;
> +			powernv_states[nr_idle_states].target_residency =
> +					((unsigned int)latency_ns / 100);
>  			powernv_states[nr_idle_states].enter = &nap_loop;
>  			nr_idle_states++;
>  		}
> @@ -204,8 +219,10 @@ static int powernv_add_idle_states(void)
>  			strcpy(powernv_states[nr_idle_states].desc, "FastSleep");
>  			powernv_states[nr_idle_states].flags =
>  				CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TIMER_STOP;
> -			powernv_states[nr_idle_states].exit_latency = 300;
> -			powernv_states[nr_idle_states].target_residency = 1000000;
> +			powernv_states[nr_idle_states].exit_latency =
> +					((unsigned int)latency_ns) / 1000;
> +			powernv_states[nr_idle_states].target_residency =
> +					((unsigned int)latency_ns / 100);
>  			powernv_states[nr_idle_states].enter = &fastsleep_loop;
>  			nr_idle_states++;
>  		}
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-pm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 

Re: [PATCH] cpuidle/powernv: Populate cpuidle state details by querying the device-tree

[Michael Ellerman]

On Fri, 2014-10-24 at 15:30 +0100, Lorenzo Pieralisi wrote:
> On Tue, Oct 14, 2014 at 08:53:00AM +0100, Preeti U Murthy wrote:
> > We hard code the metrics relevant for cpuidle states in the kernel today.
> > Instead pick them up from the device tree so that they remain relevant
> > and updated for the system that the kernel is running on.
> 
> Device tree properties should be documented, and these bindings are
> getting very similar to the ones I have just completed for ARM,
> I wonder whether we should take the generic bits out of ARM bindings (ie
> exit_latency) and make those available to other architectures.

The firmware that emits those properties is already in the field, so it would
have been nice to use a generic binding but it's too late now.

cheers