diff mbox series

eal: generic counter based loop for CPU freq calculation

Message ID 20200608213417.9764-1-honnappa.nagarahalli@arm.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series eal: generic counter based loop for CPU freq calculation |

Checks

Context Check Description
ci/iol-broadcom-Performance success Performance Testing PASS
ci/iol-intel-Performance success Performance Testing PASS
ci/iol-nxp-Performance success Performance Testing PASS
ci/Intel-compilation success Compilation OK
ci/travis-robot success Travis build: passed
ci/iol-mellanox-Performance success Performance Testing PASS
ci/iol-testing success Testing PASS
ci/checkpatch success coding style OK

Commit Message

Honnappa Nagarahalli June 8, 2020, 9:34 p.m. UTC 
  get_tsc_freq uses 'nanosleep' system call to calculate the CPU
frequency. However, 'nanosleep' results in the process getting
un-scheduled. The kernel saves and restores the PMU state. This
ensures that the PMU cycles are not counted towards a sleeping
process. When RTE_ARM_EAL_RDTSC_USE_PMU is defined, this results
in incorrect CPU frequency calculation. This logic is replaced
with generic counter based loop.

Bugzilla ID: 450
Fixes: af75078fece3 ("first public release")
Cc: stable@dpdk.org

Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>

---
 lib/librte_eal/arm/include/rte_cycles_64.h | 45 +++++++++++++++++++---
 lib/librte_eal/arm/rte_cycles.c            | 24 ++++++++++--
 2 files changed, 61 insertions(+), 8 deletions(-)

Comments

Jerin Jacob June 24, 2020, 12:50 p.m. UTC | #1 
On Tue, Jun 9, 2020 at 3:04 AM Honnappa Nagarahalli
<honnappa.nagarahalli@arm.com> wrote:
>
> get_tsc_freq uses 'nanosleep' system call to calculate the CPU
> frequency. However, 'nanosleep' results in the process getting
> un-scheduled. The kernel saves and restores the PMU state. This
> ensures that the PMU cycles are not counted towards a sleeping
> process. When RTE_ARM_EAL_RDTSC_USE_PMU is defined, this results
> in incorrect CPU frequency calculation. This logic is replaced
> with generic counter based loop.
>
> Bugzilla ID: 450
> Fixes: af75078fece3 ("first public release")

The Fix looks good to me.

The Fixes is not correct. It should be the patch where
RTE_ARM_EAL_RDTSC_USE_PMU got introduced.


> Cc: stable@dpdk.org
>
> Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> Reviewed-by: Phil Yang <phil.yang@arm.com>
>
> ---
>  lib/librte_eal/arm/include/rte_cycles_64.h | 45 +++++++++++++++++++---
>  lib/librte_eal/arm/rte_cycles.c            | 24 ++++++++++--
>  2 files changed, 61 insertions(+), 8 deletions(-)
>
> diff --git a/lib/librte_eal/arm/include/rte_cycles_64.h b/lib/librte_eal/arm/include/rte_cycles_64.h
> index da557b6a1..6fc352036 100644
> --- a/lib/librte_eal/arm/include/rte_cycles_64.h
> +++ b/lib/librte_eal/arm/include/rte_cycles_64.h
> @@ -11,6 +11,36 @@ extern "C" {
>
>  #include "generic/rte_cycles.h"
>
> +/** Read generic counter frequency */
> +static inline uint64_t

I prefer to have __rte_allways_inline

> +__rte_rd_generic_cntr_freq(void)

I think, the generic counter is confusing, I think, since the symbol
is exposed due to placed in
header file, it is better to change, __rte_arm64_cntfrq()

> +{
> +       uint64_t freq;
> +
> +       asm volatile("mrs %0, cntfrq_el0" : "=r" (freq));
> +       return freq;
> +}
> +
> +/** Read generic counter */
> +static inline uint64_t

Likewise, __rte_arm64_cntvct()


> +__rte_rd_generic_cntr(void)
> +{
> +       uint64_t tsc;
> +
> +       asm volatile("mrs %0, cntvct_el0" : "=r" (tsc));
> +       return tsc;
> +}
> +
> +static inline uint64_t
> +__rte_rd_generic_cntr_precise(void)

__rte_arm64_cntfrq_precise()

> +{
> +       uint64_t tsc;
> +
> +       asm volatile("isb" : : : "memory");
> +       asm volatile("mrs %0, cntvct_el0" : "=r" (tsc));
> +       return tsc;
> +}
> +
>  /**
>   * Read the time base register.
>   *
> @@ -25,10 +55,7 @@ extern "C" {
>  static inline uint64_t
>  rte_rdtsc(void)
>  {
> -       uint64_t tsc;
> -
> -       asm volatile("mrs %0, cntvct_el0" : "=r" (tsc));
> -       return tsc;
> +       return __rte_rd_generic_cntr();
>  }
>  #else
>  /**
> @@ -49,14 +76,22 @@ rte_rdtsc(void)
>   * asm volatile("msr pmcr_el0, %0" : : "r" (val));
>   *
>   */
> +
> +/** Read PMU cycle counter */
>  static inline uint64_t
> -rte_rdtsc(void)
> +__rte_rd_pmu_cycle_cntr(void)
>  {
>         uint64_t tsc;
>
>         asm volatile("mrs %0, pmccntr_el0" : "=r"(tsc));
>         return tsc;
>  }
> +
> +static inline uint64_t
> +rte_rdtsc(void)
> +{
> +       return __rte_rd_pmu_cycle_cntr();
> +}
>  #endif
>
>  static inline uint64_t
> diff --git a/lib/librte_eal/arm/rte_cycles.c b/lib/librte_eal/arm/rte_cycles.c
> index 3500d523e..92c87a8a4 100644
> --- a/lib/librte_eal/arm/rte_cycles.c
> +++ b/lib/librte_eal/arm/rte_cycles.c
> @@ -3,14 +3,32 @@
>   */
>
>  #include "eal_private.h"
> +#include "rte_cycles.h"
>
>  uint64_t
>  get_tsc_freq_arch(void)
>  {
>  #if defined RTE_ARCH_ARM64 && !defined RTE_ARM_EAL_RDTSC_USE_PMU
> -       uint64_t freq;
> -       asm volatile("mrs %0, cntfrq_el0" : "=r" (freq));
> -       return freq;
> +       return __rte_rd_generic_cntr_freq();
> +#elif defined RTE_ARCH_ARM64 && defined RTE_ARM_EAL_RDTSC_USE_PMU
> +       /* Use the generic counter ticks to calculate the PMU
> +        * cycle frequency.
> +        */
> +       uint64_t gcnt_ticks;
> +       uint64_t start_ticks, cur_ticks;
> +       uint64_t start_pmu_cycles, end_pmu_cycles;
> +
> +       /* Number of ticks for 1/10 second */
> +       gcnt_ticks = __rte_rd_generic_cntr_freq() / 10;
> +
> +       start_ticks = __rte_rd_generic_cntr_precise();
> +       start_pmu_cycles = rte_rdtsc_precise();
> +       do {
> +               cur_ticks = __rte_rd_generic_cntr();
> +       } while ((cur_ticks - start_ticks) < gcnt_ticks);
> +       end_pmu_cycles = rte_rdtsc_precise();
> +
> +       return ((end_pmu_cycles - start_pmu_cycles) * 10);

Good thought. On the plus side, it will reduce the boot time by .9 sec.

>  #else
>         return 0;

With above changes:

Acked-by: Jerin Jacob <jerinj@marvell.com>



>  #endif
> --
> 2.17.1
>
Pavan Nikhilesh Bhagavatula June 24, 2020, 3:09 p.m. UTC | #2 
>Subject: [dpdk-dev] [PATCH] eal: generic counter based loop for CPU
>freq calculation
>
>get_tsc_freq uses 'nanosleep' system call to calculate the CPU
>frequency. However, 'nanosleep' results in the process getting
>un-scheduled. The kernel saves and restores the PMU state. This
>ensures that the PMU cycles are not counted towards a sleeping
>process. When RTE_ARM_EAL_RDTSC_USE_PMU is defined, this results
>in incorrect CPU frequency calculation. This logic is replaced
>with generic counter based loop.
>
>Bugzilla ID: 450
>Fixes: af75078fece3 ("first public release")
>Cc: stable@dpdk.org
>
>Signed-off-by: Honnappa Nagarahalli
><honnappa.nagarahalli@arm.com>
>Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
>Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>Reviewed-by: Phil Yang <phil.yang@arm.com>
>
>---
> lib/librte_eal/arm/include/rte_cycles_64.h | 45
>+++++++++++++++++++---
> lib/librte_eal/arm/rte_cycles.c            | 24 ++++++++++--
> 2 files changed, 61 insertions(+), 8 deletions(-)
>

<Snip>

>
> uint64_t
> get_tsc_freq_arch(void)
> {
> #if defined RTE_ARCH_ARM64 && !defined
>RTE_ARM_EAL_RDTSC_USE_PMU
>-	uint64_t freq;
>-	asm volatile("mrs %0, cntfrq_el0" : "=r" (freq));
>-	return freq;
>+	return __rte_rd_generic_cntr_freq();
>+#elif defined RTE_ARCH_ARM64 && defined
>RTE_ARM_EAL_RDTSC_USE_PMU
>+	/* Use the generic counter ticks to calculate the PMU
>+	 * cycle frequency.
>+	 */
>+	uint64_t gcnt_ticks;
>+	uint64_t start_ticks, cur_ticks;
>+	uint64_t start_pmu_cycles, end_pmu_cycles;
>+
>+	/* Number of ticks for 1/10 second */
>+	gcnt_ticks = __rte_rd_generic_cntr_freq() / 10;
>+
>+	start_ticks = __rte_rd_generic_cntr_precise();
>+	start_pmu_cycles = rte_rdtsc_precise();
>+	do {
>+		cur_ticks = __rte_rd_generic_cntr();
>+	} while ((cur_ticks - start_ticks) < gcnt_ticks);
>+	end_pmu_cycles = rte_rdtsc_precise();
>+
>+	return ((end_pmu_cycles - start_pmu_cycles) * 10);

I think we need to round this of to the next multiple of 10.
Sometimes it is off by one
EAL: TSC frequency is ~2399999 KHz

Similar to http://git.dpdk.org/dpdk/tree/lib/librte_eal/common/eal_common_timer.c#n54

Pavan.

> #else
> 	return 0;
> #endif
>--
>2.17.1
Honnappa Nagarahalli June 26, 2020, 8:46 p.m. UTC | #3 
Hi Jerin,
	Thanks for the comments.

> -----Original Message-----
> From: Jerin Jacob <jerinjacobk@gmail.com>
> Sent: Wednesday, June 24, 2020 7:51 AM
> To: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> Cc: dpdk-dev <dev@dpdk.org>; jerinj@marvell.com;
> hemant.agrawal@nxp.com; Akhil.goyal@nxp.com; ogerlitz@mellanox.com;
> Ajit Khaparde (ajit.khaparde@broadcom.com)
> <ajit.khaparde@broadcom.com>; ruigeng.wang@arm.com; Dharmik Thakkar
> <Dharmik.Thakkar@arm.com>; Phil Yang <Phil.Yang@arm.com>; dpdk stable
> <stable@dpdk.org>
> Subject: Re: [dpdk-dev] [PATCH] eal: generic counter based loop for CPU freq
> calculation
> 
> On Tue, Jun 9, 2020 at 3:04 AM Honnappa Nagarahalli
> <honnappa.nagarahalli@arm.com> wrote:
> >
> > get_tsc_freq uses 'nanosleep' system call to calculate the CPU
> > frequency. However, 'nanosleep' results in the process getting
> > un-scheduled. The kernel saves and restores the PMU state. This
> > ensures that the PMU cycles are not counted towards a sleeping
> > process. When RTE_ARM_EAL_RDTSC_USE_PMU is defined, this results in
> > incorrect CPU frequency calculation. This logic is replaced with
> > generic counter based loop.
> >
> > Bugzilla ID: 450
> > Fixes: af75078fece3 ("first public release")
> 
> The Fix looks good to me.
> 
> The Fixes is not correct. It should be the patch where
> RTE_ARM_EAL_RDTSC_USE_PMU got introduced.
Ok, will dig that out.

> 
> 
> > Cc: stable@dpdk.org
> >
> > Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> > Reviewed-by: Phil Yang <phil.yang@arm.com>
> >
> > ---
> >  lib/librte_eal/arm/include/rte_cycles_64.h | 45 +++++++++++++++++++---
> >  lib/librte_eal/arm/rte_cycles.c            | 24 ++++++++++--
> >  2 files changed, 61 insertions(+), 8 deletions(-)
> >
> > diff --git a/lib/librte_eal/arm/include/rte_cycles_64.h
> > b/lib/librte_eal/arm/include/rte_cycles_64.h
> > index da557b6a1..6fc352036 100644
> > --- a/lib/librte_eal/arm/include/rte_cycles_64.h
> > +++ b/lib/librte_eal/arm/include/rte_cycles_64.h
> > @@ -11,6 +11,36 @@ extern "C" {
> >
> >  #include "generic/rte_cycles.h"
> >
> > +/** Read generic counter frequency */ static inline uint64_t
> 
> I prefer to have __rte_allways_inline
> 
> > +__rte_rd_generic_cntr_freq(void)
> 
> I think, the generic counter is confusing, I think, since the symbol is exposed
> due to placed in header file, it is better to change, __rte_arm64_cntfrq()
Ok, makes sense.

> 
> > +{
> > +       uint64_t freq;
> > +
> > +       asm volatile("mrs %0, cntfrq_el0" : "=r" (freq));
> > +       return freq;
> > +}
> > +
> > +/** Read generic counter */
> > +static inline uint64_t
> 
> Likewise, __rte_arm64_cntvct()
> 
> 
> > +__rte_rd_generic_cntr(void)
> > +{
> > +       uint64_t tsc;
> > +
> > +       asm volatile("mrs %0, cntvct_el0" : "=r" (tsc));
> > +       return tsc;
> > +}
> > +
> > +static inline uint64_t
> > +__rte_rd_generic_cntr_precise(void)
> 
> __rte_arm64_cntfrq_precise()
> 
> > +{
> > +       uint64_t tsc;
> > +
> > +       asm volatile("isb" : : : "memory");
> > +       asm volatile("mrs %0, cntvct_el0" : "=r" (tsc));
> > +       return tsc;
> > +}
> > +
> >  /**
> >   * Read the time base register.
> >   *
> > @@ -25,10 +55,7 @@ extern "C" {
> >  static inline uint64_t
> >  rte_rdtsc(void)
> >  {
> > -       uint64_t tsc;
> > -
> > -       asm volatile("mrs %0, cntvct_el0" : "=r" (tsc));
> > -       return tsc;
> > +       return __rte_rd_generic_cntr();
> >  }
> >  #else
> >  /**
> > @@ -49,14 +76,22 @@ rte_rdtsc(void)
> >   * asm volatile("msr pmcr_el0, %0" : : "r" (val));
> >   *
> >   */
> > +
> > +/** Read PMU cycle counter */
> >  static inline uint64_t
> > -rte_rdtsc(void)
> > +__rte_rd_pmu_cycle_cntr(void)
I will change this to __rte_arm64_pmccntr

> >  {
> >         uint64_t tsc;
> >
> >         asm volatile("mrs %0, pmccntr_el0" : "=r"(tsc));
> >         return tsc;
> >  }
> > +
> > +static inline uint64_t
> > +rte_rdtsc(void)
> > +{
> > +       return __rte_rd_pmu_cycle_cntr(); }
> >  #endif
> >
> >  static inline uint64_t
> > diff --git a/lib/librte_eal/arm/rte_cycles.c
> > b/lib/librte_eal/arm/rte_cycles.c index 3500d523e..92c87a8a4 100644
> > --- a/lib/librte_eal/arm/rte_cycles.c
> > +++ b/lib/librte_eal/arm/rte_cycles.c
> > @@ -3,14 +3,32 @@
> >   */
> >
> >  #include "eal_private.h"
> > +#include "rte_cycles.h"
> >
> >  uint64_t
> >  get_tsc_freq_arch(void)
> >  {
> >  #if defined RTE_ARCH_ARM64 && !defined
> RTE_ARM_EAL_RDTSC_USE_PMU
> > -       uint64_t freq;
> > -       asm volatile("mrs %0, cntfrq_el0" : "=r" (freq));
> > -       return freq;
> > +       return __rte_rd_generic_cntr_freq(); #elif defined
> > +RTE_ARCH_ARM64 && defined RTE_ARM_EAL_RDTSC_USE_PMU
> > +       /* Use the generic counter ticks to calculate the PMU
> > +        * cycle frequency.
> > +        */
> > +       uint64_t gcnt_ticks;
> > +       uint64_t start_ticks, cur_ticks;
> > +       uint64_t start_pmu_cycles, end_pmu_cycles;
> > +
> > +       /* Number of ticks for 1/10 second */
> > +       gcnt_ticks = __rte_rd_generic_cntr_freq() / 10;
> > +
> > +       start_ticks = __rte_rd_generic_cntr_precise();
> > +       start_pmu_cycles = rte_rdtsc_precise();
> > +       do {
> > +               cur_ticks = __rte_rd_generic_cntr();
> > +       } while ((cur_ticks - start_ticks) < gcnt_ticks);
> > +       end_pmu_cycles = rte_rdtsc_precise();
> > +
> > +       return ((end_pmu_cycles - start_pmu_cycles) * 10);
> 
> Good thought. On the plus side, it will reduce the boot time by .9 sec.
> 
> >  #else
> >         return 0;
> 
> With above changes:
> 
> Acked-by: Jerin Jacob <jerinj@marvell.com>
> 
> 
> 
> >  #endif
> > --
> > 2.17.1
> >
diff mbox series

Patch

diff --git a/lib/librte_eal/arm/include/rte_cycles_64.h b/lib/librte_eal/arm/include/rte_cycles_64.h
index da557b6a1..6fc352036 100644
--- a/lib/librte_eal/arm/include/rte_cycles_64.h
+++ b/lib/librte_eal/arm/include/rte_cycles_64.h
@@ -11,6 +11,36 @@  extern "C" {
 
 #include "generic/rte_cycles.h"
 
+/** Read generic counter frequency */
+static inline uint64_t
+__rte_rd_generic_cntr_freq(void)
+{
+	uint64_t freq;
+
+	asm volatile("mrs %0, cntfrq_el0" : "=r" (freq));
+	return freq;
+}
+
+/** Read generic counter */
+static inline uint64_t
+__rte_rd_generic_cntr(void)
+{
+	uint64_t tsc;
+
+	asm volatile("mrs %0, cntvct_el0" : "=r" (tsc));
+	return tsc;
+}
+
+static inline uint64_t
+__rte_rd_generic_cntr_precise(void)
+{
+	uint64_t tsc;
+
+	asm volatile("isb" : : : "memory");
+	asm volatile("mrs %0, cntvct_el0" : "=r" (tsc));
+	return tsc;
+}
+
 /**
  * Read the time base register.
  *
@@ -25,10 +55,7 @@  extern "C" {
 static inline uint64_t
 rte_rdtsc(void)
 {
-	uint64_t tsc;
-
-	asm volatile("mrs %0, cntvct_el0" : "=r" (tsc));
-	return tsc;
+	return __rte_rd_generic_cntr();
 }
 #else
 /**
@@ -49,14 +76,22 @@  rte_rdtsc(void)
  * asm volatile("msr pmcr_el0, %0" : : "r" (val));
  *
  */
+
+/** Read PMU cycle counter */
 static inline uint64_t
-rte_rdtsc(void)
+__rte_rd_pmu_cycle_cntr(void)
 {
 	uint64_t tsc;
 
 	asm volatile("mrs %0, pmccntr_el0" : "=r"(tsc));
 	return tsc;
 }
+
+static inline uint64_t
+rte_rdtsc(void)
+{
+	return __rte_rd_pmu_cycle_cntr();
+}
 #endif
 
 static inline uint64_t
diff --git a/lib/librte_eal/arm/rte_cycles.c b/lib/librte_eal/arm/rte_cycles.c
index 3500d523e..92c87a8a4 100644
--- a/lib/librte_eal/arm/rte_cycles.c
+++ b/lib/librte_eal/arm/rte_cycles.c
@@ -3,14 +3,32 @@ 
  */
 
 #include "eal_private.h"
+#include "rte_cycles.h"
 
 uint64_t
 get_tsc_freq_arch(void)
 {
 #if defined RTE_ARCH_ARM64 && !defined RTE_ARM_EAL_RDTSC_USE_PMU
-	uint64_t freq;
-	asm volatile("mrs %0, cntfrq_el0" : "=r" (freq));
-	return freq;
+	return __rte_rd_generic_cntr_freq();
+#elif defined RTE_ARCH_ARM64 && defined RTE_ARM_EAL_RDTSC_USE_PMU
+	/* Use the generic counter ticks to calculate the PMU
+	 * cycle frequency.
+	 */
+	uint64_t gcnt_ticks;
+	uint64_t start_ticks, cur_ticks;
+	uint64_t start_pmu_cycles, end_pmu_cycles;
+
+	/* Number of ticks for 1/10 second */
+	gcnt_ticks = __rte_rd_generic_cntr_freq() / 10;
+
+	start_ticks = __rte_rd_generic_cntr_precise();
+	start_pmu_cycles = rte_rdtsc_precise();
+	do {
+		cur_ticks = __rte_rd_generic_cntr();
+	} while ((cur_ticks - start_ticks) < gcnt_ticks);
+	end_pmu_cycles = rte_rdtsc_precise();
+
+	return ((end_pmu_cycles - start_pmu_cycles) * 10);
 #else
 	return 0;
 #endif