diff mbox series

[v3,net-next,2/2] net: mscc: ocelot: use bulk reads for stats

Message ID 20220125071531.1181948-3-colin.foster@in-advantage.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series use bulk reads for ocelot statistics | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers success CCed 7 of 7 maintainers
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning WARNING: line length of 82 exceeds 80 columns WARNING: line length of 88 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Colin Foster Jan. 25, 2022, 7:15 a.m. UTC 
Create and utilize bulk regmap reads instead of single access for gathering
stats. The background reading of statistics happens frequently, and over
a few contiguous memory regions.

High speed PCIe buses and MMIO access will probably see negligible
performance increase. Lower speed buses like SPI and I2C could see
significant performance increase, since the bus configuration and register
access times account for a large percentage of data transfer time.

Signed-off-by: Colin Foster <colin.foster@in-advantage.com>
---
 drivers/net/ethernet/mscc/ocelot.c | 76 +++++++++++++++++++++++++-----
 include/soc/mscc/ocelot.h          |  8 ++++
 2 files changed, 71 insertions(+), 13 deletions(-)

Comments

Jakub Kicinski Jan. 27, 2022, 2:34 a.m. UTC | #1 
On Mon, 24 Jan 2022 23:15:31 -0800 Colin Foster wrote:
> Create and utilize bulk regmap reads instead of single access for gathering
> stats. The background reading of statistics happens frequently, and over
> a few contiguous memory regions.
> 
> High speed PCIe buses and MMIO access will probably see negligible
> performance increase. Lower speed buses like SPI and I2C could see
> significant performance increase, since the bus configuration and register
> access times account for a large percentage of data transfer time.
> 
> Signed-off-by: Colin Foster <colin.foster@in-advantage.com>

> +static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
> +{
> +	struct ocelot_stats_region *region = NULL;
> +	unsigned int last;
> +	int i;
> +
> +	INIT_LIST_HEAD(&ocelot->stats_regions);
> +
> +	for (i = 0; i < ocelot->num_stats; i++) {
> +		if (region && ocelot->stats_layout[i].offset == last + 1) {
> +			region->count++;
> +		} else {
> +			region = devm_kzalloc(ocelot->dev, sizeof(*region),
> +					      GFP_KERNEL);
> +			if (!region)
> +				return -ENOMEM;
> +
> +			region->offset = ocelot->stats_layout[i].offset;
> +			region->count = 1;
> +			list_add_tail(&region->node, &ocelot->stats_regions);
> +		}
> +
> +		last = ocelot->stats_layout[i].offset;
> +	}
> +
> +	list_for_each_entry(region, &ocelot->stats_regions, node) {
> +		region->buf = devm_kzalloc(ocelot->dev,
> +					   region->count * sizeof(*region->buf),
> +					   GFP_KERNEL);

devm_kcalloc()

> +

unnecessary new line

> +		if (!region->buf)
> +			return -ENOMEM;
Colin Foster Jan. 27, 2022, 4:30 p.m. UTC | #2 
Hi Jakub,

On Wed, Jan 26, 2022 at 06:34:36PM -0800, Jakub Kicinski wrote:
> On Mon, 24 Jan 2022 23:15:31 -0800 Colin Foster wrote:
> > Create and utilize bulk regmap reads instead of single access for gathering
> > stats. The background reading of statistics happens frequently, and over
> > a few contiguous memory regions.
> > 
> > High speed PCIe buses and MMIO access will probably see negligible
> > performance increase. Lower speed buses like SPI and I2C could see
> > significant performance increase, since the bus configuration and register
> > access times account for a large percentage of data transfer time.
> > 
> > Signed-off-by: Colin Foster <colin.foster@in-advantage.com>
> 
> > +static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
> > +{
> > +	struct ocelot_stats_region *region = NULL;
> > +	unsigned int last;
> > +	int i;
> > +
> > +	INIT_LIST_HEAD(&ocelot->stats_regions);
> > +
> > +	for (i = 0; i < ocelot->num_stats; i++) {
> > +		if (region && ocelot->stats_layout[i].offset == last + 1) {
> > +			region->count++;
> > +		} else {
> > +			region = devm_kzalloc(ocelot->dev, sizeof(*region),
> > +					      GFP_KERNEL);
> > +			if (!region)
> > +				return -ENOMEM;
> > +
> > +			region->offset = ocelot->stats_layout[i].offset;
> > +			region->count = 1;
> > +			list_add_tail(&region->node, &ocelot->stats_regions);
> > +		}
> > +
> > +		last = ocelot->stats_layout[i].offset;
> > +	}
> > +
> > +	list_for_each_entry(region, &ocelot->stats_regions, node) {
> > +		region->buf = devm_kzalloc(ocelot->dev,
> > +					   region->count * sizeof(*region->buf),
> > +					   GFP_KERNEL);
> 
> devm_kcalloc()

Good catch. I'll probably give it another day for review and resubmit 
tomrrow. 

> 
> > +
> 
> unnecessary new line
> 
> > +		if (!region->buf)
> > +			return -ENOMEM;
Vladimir Oltean Jan. 31, 2022, 10:22 a.m. UTC | #3 
On Mon, Jan 24, 2022 at 11:15:31PM -0800, Colin Foster wrote:
> Create and utilize bulk regmap reads instead of single access for gathering
> stats. The background reading of statistics happens frequently, and over
> a few contiguous memory regions.
> 
> High speed PCIe buses and MMIO access will probably see negligible
> performance increase. Lower speed buses like SPI and I2C could see
> significant performance increase, since the bus configuration and register
> access times account for a large percentage of data transfer time.
> 
> Signed-off-by: Colin Foster <colin.foster@in-advantage.com>
> ---
>  drivers/net/ethernet/mscc/ocelot.c | 76 +++++++++++++++++++++++++-----
>  include/soc/mscc/ocelot.h          |  8 ++++
>  2 files changed, 71 insertions(+), 13 deletions(-)
> 
> diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
> index 455293aa6343..bf466eaeba3d 100644
> --- a/drivers/net/ethernet/mscc/ocelot.c
> +++ b/drivers/net/ethernet/mscc/ocelot.c
> @@ -1737,32 +1737,40 @@ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data)
>  }
>  EXPORT_SYMBOL(ocelot_get_strings);
>  
> -static void ocelot_update_stats(struct ocelot *ocelot)
> +static int ocelot_update_stats(struct ocelot *ocelot)
>  {
> -	int i, j;
> +	struct ocelot_stats_region *region;
> +	int i, j, err = 0;
>  
>  	mutex_lock(&ocelot->stats_lock);
>  
>  	for (i = 0; i < ocelot->num_phys_ports; i++) {
> +		unsigned int idx = 0;

It is usual to leave a blank line between variable declarations and code.

>  		/* Configure the port to read the stats from */
>  		ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(i), SYS_STAT_CFG);
>  
> -		for (j = 0; j < ocelot->num_stats; j++) {
> -			u32 val;
> -			unsigned int idx = i * ocelot->num_stats + j;
> +		list_for_each_entry(region, &ocelot->stats_regions, node) {
> +			err = ocelot_bulk_read_rix(ocelot, SYS_COUNT_RX_OCTETS,

I'd be tempted to pass SYS << TARGET_OFFSET here.

> +						   region->offset, region->buf,
> +						   region->count);
> +			if (err)
> +				goto out;
>  
> -			val = ocelot_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
> -					      ocelot->stats_layout[j].offset);
> +			for (j = 0; j < region->count; j++) {
> +				if (region->buf[j] < (ocelot->stats[idx + j] & U32_MAX))
> +					ocelot->stats[idx + j] += (u64)1 << 32;
>  
> -			if (val < (ocelot->stats[idx] & U32_MAX))
> -				ocelot->stats[idx] += (u64)1 << 32;
> +				ocelot->stats[idx + j] = (ocelot->stats[idx + j] &
> +							~(u64)U32_MAX) + region->buf[j];
> +			}
>  
> -			ocelot->stats[idx] = (ocelot->stats[idx] &
> -					      ~(u64)U32_MAX) + val;
> +			idx += region->count;
>  		}
>  	}
>  
> +out:
>  	mutex_unlock(&ocelot->stats_lock);
> +	return err;
>  }
>  
>  static void ocelot_check_stats_work(struct work_struct *work)
> @@ -1779,10 +1787,11 @@ static void ocelot_check_stats_work(struct work_struct *work)
>  
>  void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data)
>  {
> -	int i;
> +	int i, err;
>  
>  	/* check and update now */
> -	ocelot_update_stats(ocelot);
> +	err = ocelot_update_stats(ocelot);
> +	WARN_ONCE(err, "Error %d updating ethtool stats\n", err);
>  
>  	/* Copy all counters */
>  	for (i = 0; i < ocelot->num_stats; i++)
> @@ -1799,6 +1808,43 @@ int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset)
>  }
>  EXPORT_SYMBOL(ocelot_get_sset_count);
>  
> +static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
> +{
> +	struct ocelot_stats_region *region = NULL;
> +	unsigned int last;
> +	int i;
> +
> +	INIT_LIST_HEAD(&ocelot->stats_regions);
> +
> +	for (i = 0; i < ocelot->num_stats; i++) {
> +		if (region && ocelot->stats_layout[i].offset == last + 1) {
> +			region->count++;
> +		} else {
> +			region = devm_kzalloc(ocelot->dev, sizeof(*region),
> +					      GFP_KERNEL);
> +			if (!region)
> +				return -ENOMEM;
> +
> +			region->offset = ocelot->stats_layout[i].offset;
> +			region->count = 1;
> +			list_add_tail(&region->node, &ocelot->stats_regions);
> +		}
> +
> +		last = ocelot->stats_layout[i].offset;
> +	}
> +
> +	list_for_each_entry(region, &ocelot->stats_regions, node) {
> +		region->buf = devm_kzalloc(ocelot->dev,
> +					   region->count * sizeof(*region->buf),
> +					   GFP_KERNEL);
> +
> +		if (!region->buf)
> +			return -ENOMEM;
> +	}
> +
> +	return 0;
> +}
> +
>  int ocelot_get_ts_info(struct ocelot *ocelot, int port,
>  		       struct ethtool_ts_info *info)
>  {
> @@ -2799,6 +2845,10 @@ int ocelot_init(struct ocelot *ocelot)
>  				 ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
>  				 ANA_CPUQ_8021_CFG, i);
>  
> +	ret = ocelot_prepare_stats_regions(ocelot);
> +	if (ret)
> +		return ret;
> +

Destroy ocelot->stats_queue and ocelot->owq.

>  	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
>  	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
>  			   OCELOT_STATS_CHECK_DELAY);
> diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
> index b66e5abe04a7..837450fdea57 100644
> --- a/include/soc/mscc/ocelot.h
> +++ b/include/soc/mscc/ocelot.h
> @@ -542,6 +542,13 @@ struct ocelot_stat_layout {
>  	char name[ETH_GSTRING_LEN];
>  };
>  
> +struct ocelot_stats_region {
> +	struct list_head node;
> +	u32 offset;
> +	int count;
> +	u32 *buf;
> +};
> +
>  enum ocelot_tag_prefix {
>  	OCELOT_TAG_PREFIX_DISABLED	= 0,
>  	OCELOT_TAG_PREFIX_NONE,
> @@ -673,6 +680,7 @@ struct ocelot {
>  	struct regmap_field		*regfields[REGFIELD_MAX];
>  	const u32 *const		*map;
>  	const struct ocelot_stat_layout	*stats_layout;
> +	struct list_head		stats_regions;
>  	unsigned int			num_stats;
>  
>  	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
> -- 
> 2.25.1
>
Colin Foster Jan. 31, 2022, 3:51 p.m. UTC | #4 
Hi Vladimir,

Thanks for the feedback. I already submitted v4, so I'll put these into
v5 this week.

On Mon, Jan 31, 2022 at 10:22:55AM +0000, Vladimir Oltean wrote:
> On Mon, Jan 24, 2022 at 11:15:31PM -0800, Colin Foster wrote:
> > Create and utilize bulk regmap reads instead of single access for gathering
> > stats. The background reading of statistics happens frequently, and over
> > a few contiguous memory regions.
> > 
> > High speed PCIe buses and MMIO access will probably see negligible
> > performance increase. Lower speed buses like SPI and I2C could see
> > significant performance increase, since the bus configuration and register
> > access times account for a large percentage of data transfer time.
> > 
> > Signed-off-by: Colin Foster <colin.foster@in-advantage.com>
> > ---
> >  drivers/net/ethernet/mscc/ocelot.c | 76 +++++++++++++++++++++++++-----
> >  include/soc/mscc/ocelot.h          |  8 ++++
> >  2 files changed, 71 insertions(+), 13 deletions(-)
> > 
> > diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
> > index 455293aa6343..bf466eaeba3d 100644
> > --- a/drivers/net/ethernet/mscc/ocelot.c
> > +++ b/drivers/net/ethernet/mscc/ocelot.c
> > @@ -1737,32 +1737,40 @@ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data)
> >  }
> >  EXPORT_SYMBOL(ocelot_get_strings);
> >  
> > -static void ocelot_update_stats(struct ocelot *ocelot)
> > +static int ocelot_update_stats(struct ocelot *ocelot)
> >  {
> > -	int i, j;
> > +	struct ocelot_stats_region *region;
> > +	int i, j, err = 0;
> >  
> >  	mutex_lock(&ocelot->stats_lock);
> >  
> >  	for (i = 0; i < ocelot->num_phys_ports; i++) {
> > +		unsigned int idx = 0;
> 
> It is usual to leave a blank line between variable declarations and code.
> 
> >  		/* Configure the port to read the stats from */
> >  		ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(i), SYS_STAT_CFG);
> >  
> > -		for (j = 0; j < ocelot->num_stats; j++) {
> > -			u32 val;
> > -			unsigned int idx = i * ocelot->num_stats + j;
> > +		list_for_each_entry(region, &ocelot->stats_regions, node) {
> > +			err = ocelot_bulk_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
> 
> I'd be tempted to pass SYS << TARGET_OFFSET here.

I'll take another look at this.

> 
> > +						   region->offset, region->buf,
> > +						   region->count);
> > +			if (err)
> > +				goto out;
> >  
> > -			val = ocelot_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
> > -					      ocelot->stats_layout[j].offset);
> > +			for (j = 0; j < region->count; j++) {
> > +				if (region->buf[j] < (ocelot->stats[idx + j] & U32_MAX))
> > +					ocelot->stats[idx + j] += (u64)1 << 32;
> >  
> > -			if (val < (ocelot->stats[idx] & U32_MAX))
> > -				ocelot->stats[idx] += (u64)1 << 32;
> > +				ocelot->stats[idx + j] = (ocelot->stats[idx + j] &
> > +							~(u64)U32_MAX) + region->buf[j];
> > +			}
> >  
> > -			ocelot->stats[idx] = (ocelot->stats[idx] &
> > -					      ~(u64)U32_MAX) + val;
> > +			idx += region->count;
> >  		}
> >  	}
> >  
> > +out:
> >  	mutex_unlock(&ocelot->stats_lock);
> > +	return err;
> >  }
> >  
> >  static void ocelot_check_stats_work(struct work_struct *work)
> > @@ -1779,10 +1787,11 @@ static void ocelot_check_stats_work(struct work_struct *work)
> >  
> >  void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data)
> >  {
> > -	int i;
> > +	int i, err;
> >  
> >  	/* check and update now */
> > -	ocelot_update_stats(ocelot);
> > +	err = ocelot_update_stats(ocelot);
> > +	WARN_ONCE(err, "Error %d updating ethtool stats\n", err);
> >  
> >  	/* Copy all counters */
> >  	for (i = 0; i < ocelot->num_stats; i++)
> > @@ -1799,6 +1808,43 @@ int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset)
> >  }
> >  EXPORT_SYMBOL(ocelot_get_sset_count);
> >  
> > +static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
> > +{
> > +	struct ocelot_stats_region *region = NULL;
> > +	unsigned int last;
> > +	int i;
> > +
> > +	INIT_LIST_HEAD(&ocelot->stats_regions);
> > +
> > +	for (i = 0; i < ocelot->num_stats; i++) {
> > +		if (region && ocelot->stats_layout[i].offset == last + 1) {
> > +			region->count++;
> > +		} else {
> > +			region = devm_kzalloc(ocelot->dev, sizeof(*region),
> > +					      GFP_KERNEL);
> > +			if (!region)
> > +				return -ENOMEM;
> > +
> > +			region->offset = ocelot->stats_layout[i].offset;
> > +			region->count = 1;
> > +			list_add_tail(&region->node, &ocelot->stats_regions);
> > +		}
> > +
> > +		last = ocelot->stats_layout[i].offset;
> > +	}
> > +
> > +	list_for_each_entry(region, &ocelot->stats_regions, node) {
> > +		region->buf = devm_kzalloc(ocelot->dev,
> > +					   region->count * sizeof(*region->buf),
> > +					   GFP_KERNEL);
> > +
> > +		if (!region->buf)
> > +			return -ENOMEM;
> > +	}
> > +
> > +	return 0;
> > +}
> > +
> >  int ocelot_get_ts_info(struct ocelot *ocelot, int port,
> >  		       struct ethtool_ts_info *info)
> >  {
> > @@ -2799,6 +2845,10 @@ int ocelot_init(struct ocelot *ocelot)
> >  				 ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
> >  				 ANA_CPUQ_8021_CFG, i);
> >  
> > +	ret = ocelot_prepare_stats_regions(ocelot);
> > +	if (ret)
> > +		return ret;
> > +
> 
> Destroy ocelot->stats_queue and ocelot->owq.

Wow, good catch!

> 
> >  	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
> >  	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
> >  			   OCELOT_STATS_CHECK_DELAY);
> > diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
> > index b66e5abe04a7..837450fdea57 100644
> > --- a/include/soc/mscc/ocelot.h
> > +++ b/include/soc/mscc/ocelot.h
> > @@ -542,6 +542,13 @@ struct ocelot_stat_layout {
> >  	char name[ETH_GSTRING_LEN];
> >  };
> >  
> > +struct ocelot_stats_region {
> > +	struct list_head node;
> > +	u32 offset;
> > +	int count;
> > +	u32 *buf;
> > +};
> > +
> >  enum ocelot_tag_prefix {
> >  	OCELOT_TAG_PREFIX_DISABLED	= 0,
> >  	OCELOT_TAG_PREFIX_NONE,
> > @@ -673,6 +680,7 @@ struct ocelot {
> >  	struct regmap_field		*regfields[REGFIELD_MAX];
> >  	const u32 *const		*map;
> >  	const struct ocelot_stat_layout	*stats_layout;
> > +	struct list_head		stats_regions;
> >  	unsigned int			num_stats;
> >  
> >  	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
> > -- 
> > 2.25.1
> >
Colin Foster Feb. 8, 2022, 4:35 a.m. UTC | #5 
Hi Vladimir,

I'm sending out v5 shortly. Sorry I seem to have forgotten to respond.
All changes made, except the SYS << TARGET_OFFSET. The macros for *_rix
use reg##_RSZ for expansion.

On Mon, Jan 31, 2022 at 10:22:55AM +0000, Vladimir Oltean wrote:
> On Mon, Jan 24, 2022 at 11:15:31PM -0800, Colin Foster wrote:
[ ... ]
> >  	mutex_lock(&ocelot->stats_lock);
> >  
> >  	for (i = 0; i < ocelot->num_phys_ports; i++) {
> > +		unsigned int idx = 0;
> 
> It is usual to leave a blank line between variable declarations and code.
> 
> >  		/* Configure the port to read the stats from */
> >  		ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(i), SYS_STAT_CFG);
> >  
> > -		for (j = 0; j < ocelot->num_stats; j++) {
> > -			u32 val;
> > -			unsigned int idx = i * ocelot->num_stats + j;
> > +		list_for_each_entry(region, &ocelot->stats_regions, node) {
> > +			err = ocelot_bulk_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
> 
> I'd be tempted to pass SYS << TARGET_OFFSET here.

Expands to SYS_COUNT_RX_OCTETS_RSZ, defined in
include/soc/mscc/ocelot_sys.h.

> 
> > +						   region->offset, region->buf,
> > +						   region->count);
[ ... ]
> > +@ -2799,6 +2845,10 @@ int ocelot_init(struct ocelot *ocelot)
> >  				 ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
> >  				 ANA_CPUQ_8021_CFG, i);
> >  
> > +	ret = ocelot_prepare_stats_regions(ocelot);
> > +	if (ret)
> > +		return ret;
> > +
> 
> Destroy ocelot->stats_queue and ocelot->owq.
> 
> >  	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
> >  	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
> >  			   OCELOT_STATS_CHECK_DELAY);
> > diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
> > index b66e5abe04a7..837450fdea57 100644
> > --- a/include/soc/mscc/ocelot.h
> > +++ b/include/soc/mscc/ocelot.h
> > @@ -542,6 +542,13 @@ struct ocelot_stat_layout {
> >  	char name[ETH_GSTRING_LEN];
> >  };
> >  
> > +struct ocelot_stats_region {
> > +	struct list_head node;
> > +	u32 offset;
> > +	int count;
> > +	u32 *buf;
> > +};
> > +
> >  enum ocelot_tag_prefix {
> >  	OCELOT_TAG_PREFIX_DISABLED	= 0,
> >  	OCELOT_TAG_PREFIX_NONE,
> > @@ -673,6 +680,7 @@ struct ocelot {
> >  	struct regmap_field		*regfields[REGFIELD_MAX];
> >  	const u32 *const		*map;
> >  	const struct ocelot_stat_layout	*stats_layout;
> > +	struct list_head		stats_regions;
> >  	unsigned int			num_stats;
> >  
> >  	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
> > -- 
> > 2.25.1
> >
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 455293aa6343..bf466eaeba3d 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1737,32 +1737,40 @@  void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data)
 }
 EXPORT_SYMBOL(ocelot_get_strings);
 
-static void ocelot_update_stats(struct ocelot *ocelot)
+static int ocelot_update_stats(struct ocelot *ocelot)
 {
-	int i, j;
+	struct ocelot_stats_region *region;
+	int i, j, err = 0;
 
 	mutex_lock(&ocelot->stats_lock);
 
 	for (i = 0; i < ocelot->num_phys_ports; i++) {
+		unsigned int idx = 0;
 		/* Configure the port to read the stats from */
 		ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(i), SYS_STAT_CFG);
 
-		for (j = 0; j < ocelot->num_stats; j++) {
-			u32 val;
-			unsigned int idx = i * ocelot->num_stats + j;
+		list_for_each_entry(region, &ocelot->stats_regions, node) {
+			err = ocelot_bulk_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
+						   region->offset, region->buf,
+						   region->count);
+			if (err)
+				goto out;
 
-			val = ocelot_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
-					      ocelot->stats_layout[j].offset);
+			for (j = 0; j < region->count; j++) {
+				if (region->buf[j] < (ocelot->stats[idx + j] & U32_MAX))
+					ocelot->stats[idx + j] += (u64)1 << 32;
 
-			if (val < (ocelot->stats[idx] & U32_MAX))
-				ocelot->stats[idx] += (u64)1 << 32;
+				ocelot->stats[idx + j] = (ocelot->stats[idx + j] &
+							~(u64)U32_MAX) + region->buf[j];
+			}
 
-			ocelot->stats[idx] = (ocelot->stats[idx] &
-					      ~(u64)U32_MAX) + val;
+			idx += region->count;
 		}
 	}
 
+out:
 	mutex_unlock(&ocelot->stats_lock);
+	return err;
 }
 
 static void ocelot_check_stats_work(struct work_struct *work)
@@ -1779,10 +1787,11 @@  static void ocelot_check_stats_work(struct work_struct *work)
 
 void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data)
 {
-	int i;
+	int i, err;
 
 	/* check and update now */
-	ocelot_update_stats(ocelot);
+	err = ocelot_update_stats(ocelot);
+	WARN_ONCE(err, "Error %d updating ethtool stats\n", err);
 
 	/* Copy all counters */
 	for (i = 0; i < ocelot->num_stats; i++)
@@ -1799,6 +1808,43 @@  int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset)
 }
 EXPORT_SYMBOL(ocelot_get_sset_count);
 
+static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
+{
+	struct ocelot_stats_region *region = NULL;
+	unsigned int last;
+	int i;
+
+	INIT_LIST_HEAD(&ocelot->stats_regions);
+
+	for (i = 0; i < ocelot->num_stats; i++) {
+		if (region && ocelot->stats_layout[i].offset == last + 1) {
+			region->count++;
+		} else {
+			region = devm_kzalloc(ocelot->dev, sizeof(*region),
+					      GFP_KERNEL);
+			if (!region)
+				return -ENOMEM;
+
+			region->offset = ocelot->stats_layout[i].offset;
+			region->count = 1;
+			list_add_tail(&region->node, &ocelot->stats_regions);
+		}
+
+		last = ocelot->stats_layout[i].offset;
+	}
+
+	list_for_each_entry(region, &ocelot->stats_regions, node) {
+		region->buf = devm_kzalloc(ocelot->dev,
+					   region->count * sizeof(*region->buf),
+					   GFP_KERNEL);
+
+		if (!region->buf)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 int ocelot_get_ts_info(struct ocelot *ocelot, int port,
 		       struct ethtool_ts_info *info)
 {
@@ -2799,6 +2845,10 @@  int ocelot_init(struct ocelot *ocelot)
 				 ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
 				 ANA_CPUQ_8021_CFG, i);
 
+	ret = ocelot_prepare_stats_regions(ocelot);
+	if (ret)
+		return ret;
+
 	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index b66e5abe04a7..837450fdea57 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -542,6 +542,13 @@  struct ocelot_stat_layout {
 	char name[ETH_GSTRING_LEN];
 };
 
+struct ocelot_stats_region {
+	struct list_head node;
+	u32 offset;
+	int count;
+	u32 *buf;
+};
+
 enum ocelot_tag_prefix {
 	OCELOT_TAG_PREFIX_DISABLED	= 0,
 	OCELOT_TAG_PREFIX_NONE,
@@ -673,6 +680,7 @@  struct ocelot {
 	struct regmap_field		*regfields[REGFIELD_MAX];
 	const u32 *const		*map;
 	const struct ocelot_stat_layout	*stats_layout;
+	struct list_head		stats_regions;
 	unsigned int			num_stats;
 
 	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];