tg3: Make the RSS indir tbl admin configurable

This patch adds the ethtool callbacks necessary to change the rss
indirection table from userspace.  When setting the indirection table
through set_rxfh_indir, an indirection table size of zero is
interpreted to mean that the admin wants to relinquish control of the
table to the driver.  Should the number of interrupts change (e.g.
across a close / open call, or through a reset), any indirection table
values that exceed the number of RSS queues or interrupt vectors will
be automatically scaled back to values within range.

Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Reviewed-by: Benjamin Li <benli@broadcom.com>
---
 drivers/net/ethernet/broadcom/tg3.c |  126 ++++++++++++++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/tg3.h |    1 +
 2 files changed, 126 insertions(+), 1 deletions(-)

On Thu, 2011-12-15 at 16:47 -0800, Matt Carlson wrote:
> This patch adds the ethtool callbacks necessary to change the rss
> indirection table from userspace.  When setting the indirection table
> through set_rxfh_indir, an indirection table size of zero is
> interpreted to mean that the admin wants to relinquish control of the
> table to the driver.  Should the number of interrupts change (e.g.
> across a close / open call, or through a reset), any indirection table
> values that exceed the number of RSS queues or interrupt vectors will
> be automatically scaled back to values within range.
> 
> Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
> Signed-off-by: Michael Chan <mchan@broadcom.com>
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

No I didn't!

Ben.

> Reviewed-by: Benjamin Li <benli@broadcom.com>
> ---
>  drivers/net/ethernet/broadcom/tg3.c |  126 ++++++++++++++++++++++++++++++++++-
>  drivers/net/ethernet/broadcom/tg3.h |    1 +
>  2 files changed, 126 insertions(+), 1 deletions(-)
> 
> diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
> index 8bf11ca..87f70f6 100644
> --- a/drivers/net/ethernet/broadcom/tg3.c
> +++ b/drivers/net/ethernet/broadcom/tg3.c
> @@ -8229,9 +8229,19 @@ void tg3_rss_init_indir_tbl(struct tg3 *tp)
>  
>  	if (tp->irq_cnt <= 2)
>  		memset(&tp->rss_ind_tbl[0], 0, sizeof(tp->rss_ind_tbl));
> -	else
> +	else if (tg3_flag(tp, USER_INDIR_TBL)) {
> +		/* Validate table against current IRQ count */
> +		for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++) {
> +			if (tp->rss_ind_tbl[i] >= tp->irq_cnt - 1) {
> +				/* Bring the index within range */
> +				tp->rss_ind_tbl[i] = tp->rss_ind_tbl[i] %
> +						     (tp->irq_cnt - 1);
> +			}
> +		}
> +	} else {
>  		for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
>  			tp->rss_ind_tbl[i] = i % (tp->irq_cnt - 1);
> +	}
>  }
>  
>  void tg3_rss_write_indir_tbl(struct tg3 *tp)
> @@ -10719,6 +10729,117 @@ static int tg3_get_sset_count(struct net_device *dev, int sset)
>  	}
>  }
>  
> +static int tg3_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
> +			 u32 *rules __always_unused)
> +{
> +	struct tg3 *tp = netdev_priv(dev);
> +
> +	if (!tg3_flag(tp, SUPPORT_MSIX))
> +		return -EOPNOTSUPP;
> +
> +	switch (info->cmd) {
> +	case ETHTOOL_GRXRINGS:
> +		if (netif_running(tp->dev))
> +			info->data = tp->irq_cnt;
> +		else {
> +			info->data = num_online_cpus();
> +			if (info->data > TG3_IRQ_MAX_VECS_RSS)
> +				info->data = TG3_IRQ_MAX_VECS_RSS;
> +		}
> +
> +		/* The first interrupt vector only
> +		 * handles link interrupts.
> +		 */
> +		info->data -= 1;
> +		return 0;
> +
> +	default:
> +		return -EOPNOTSUPP;
> +	}
> +}
> +
> +static int tg3_get_rxfh_indir(struct net_device *dev,
> +			      struct ethtool_rxfh_indir *indir)
> +{
> +	struct tg3 *tp = netdev_priv(dev);
> +	int i;
> +
> +	if (!tg3_flag(tp, SUPPORT_MSIX))
> +		return -EOPNOTSUPP;
> +
> +	if (!indir->size) {
> +		indir->size = TG3_RSS_INDIR_TBL_SIZE;
> +		return 0;
> +	}
> +
> +	if (indir->size != TG3_RSS_INDIR_TBL_SIZE)
> +		return -EINVAL;
> +
> +	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
> +		indir->ring_index[i] = tp->rss_ind_tbl[i];
> +
> +	return 0;
> +}
> +
> +static int tg3_set_rxfh_indir(struct net_device *dev,
> +			      const struct ethtool_rxfh_indir *indir)
> +{
> +	struct tg3 *tp = netdev_priv(dev);
> +	size_t i;
> +
> +	if (!tg3_flag(tp, SUPPORT_MSIX))
> +		return -EOPNOTSUPP;
> +
> +	if (!indir->size) {
> +		tg3_flag_clear(tp, USER_INDIR_TBL);
> +		tg3_rss_init_indir_tbl(tp);
> +	} else {
> +		int limit;
> +
> +		/* Validate size and indices */
> +		if (indir->size != TG3_RSS_INDIR_TBL_SIZE)
> +			return -EINVAL;
> +
> +		if (netif_running(dev))
> +			limit = tp->irq_cnt;
> +		else {
> +			limit = num_online_cpus();
> +			if (limit > TG3_IRQ_MAX_VECS_RSS)
> +				limit = TG3_IRQ_MAX_VECS_RSS;
> +		}
> +
> +		/* The first interrupt vector only
> +		 * handles link interrupts.
> +		 */
> +		limit -= 1;
> +
> +		/* Check the indices in the table.
> +		 * Leave the existing table unmodified
> +		 * if an error is detected.
> +		 */
> +		for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
> +			if (indir->ring_index[i] >= limit)
> +				return -EINVAL;
> +
> +		tg3_flag_set(tp, USER_INDIR_TBL);
> +
> +		for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
> +			tp->rss_ind_tbl[i] = indir->ring_index[i];
> +	}
> +
> +	if (!netif_running(dev) || !tg3_flag(tp, ENABLE_RSS))
> +		return 0;
> +
> +	/* It is legal to write the indirection
> +	 * table while the device is running.
> +	 */
> +	tg3_full_lock(tp, 0);
> +	tg3_rss_write_indir_tbl(tp);
> +	tg3_full_unlock(tp);
> +
> +	return 0;
> +}
> +
>  static void tg3_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
>  {
>  	switch (stringset) {
> @@ -11949,6 +12070,9 @@ static const struct ethtool_ops tg3_ethtool_ops = {
>  	.get_coalesce		= tg3_get_coalesce,
>  	.set_coalesce		= tg3_set_coalesce,
>  	.get_sset_count		= tg3_get_sset_count,
> +	.get_rxnfc		= tg3_get_rxnfc,
> +	.get_rxfh_indir		= tg3_get_rxfh_indir,
> +	.set_rxfh_indir		= tg3_set_rxfh_indir,
>  };
>  
>  static void __devinit tg3_get_eeprom_size(struct tg3 *tp)
> diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
> index aea8f72..4800595 100644
> --- a/drivers/net/ethernet/broadcom/tg3.h
> +++ b/drivers/net/ethernet/broadcom/tg3.h
> @@ -2932,6 +2932,7 @@ enum TG3_FLAGS {
>  	TG3_FLAG_APE_HAS_NCSI,
>  	TG3_FLAG_4K_FIFO_LIMIT,
>  	TG3_FLAG_RESET_TASK_PENDING,
> +	TG3_FLAG_USER_INDIR_TBL,
>  	TG3_FLAG_5705_PLUS,
>  	TG3_FLAG_IS_5788,
>  	TG3_FLAG_5750_PLUS,

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Fri, 16 Dec 2011 03:04:34 +0000

> On Thu, 2011-12-15 at 16:47 -0800, Matt Carlson wrote:
>> This patch adds the ethtool callbacks necessary to change the rss
>> indirection table from userspace.  When setting the indirection table
>> through set_rxfh_indir, an indirection table size of zero is
>> interpreted to mean that the admin wants to relinquish control of the
>> table to the driver.  Should the number of interrupts change (e.g.
>> across a close / open call, or through a reset), any indirection table
>> values that exceed the number of RSS queues or interrupt vectors will
>> be automatically scaled back to values within range.
>> 
>> Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
>> Signed-off-by: Michael Chan <mchan@broadcom.com>
>> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
> 
> No I didn't!

Matt, really, don't do crap like this.  It's extremely rude and
completely unprofessional.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

On Thu, Dec 15, 2011 at 07:04:34PM -0800, Ben Hutchings wrote:
> On Thu, 2011-12-15 at 16:47 -0800, Matt Carlson wrote:
> > This patch adds the ethtool callbacks necessary to change the rss
> > indirection table from userspace.  When setting the indirection table
> > through set_rxfh_indir, an indirection table size of zero is
> > interpreted to mean that the admin wants to relinquish control of the
> > table to the driver.  Should the number of interrupts change (e.g.
> > across a close / open call, or through a reset), any indirection table
> > values that exceed the number of RSS queues or interrupt vectors will
> > be automatically scaled back to values within range.
> > 
> > Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
> > Signed-off-by: Michael Chan <mchan@broadcom.com>
> > Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
> 
> No I didn't!
> 
> Ben.

Sorry.  This part of procedure I'm unsure about.  I didn't want to lose
the ack of your contributions to this patch.  The SOB does imply that
you are O.K. with it as-is though, which you may or may not be aligned
with.  I apologize if I was putting words in your mouth.

What should I have done instead?  Would Dave put the SOB on your behalf
as he accepts it?

> > Reviewed-by: Benjamin Li <benli@broadcom.com>
> > ---
> >  drivers/net/ethernet/broadcom/tg3.c |  126 ++++++++++++++++++++++++++++++++++-
> >  drivers/net/ethernet/broadcom/tg3.h |    1 +
> >  2 files changed, 126 insertions(+), 1 deletions(-)
> > 
> > diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
> > index 8bf11ca..87f70f6 100644
> > --- a/drivers/net/ethernet/broadcom/tg3.c
> > +++ b/drivers/net/ethernet/broadcom/tg3.c
> > @@ -8229,9 +8229,19 @@ void tg3_rss_init_indir_tbl(struct tg3 *tp)
> >  
> >  	if (tp->irq_cnt <= 2)
> >  		memset(&tp->rss_ind_tbl[0], 0, sizeof(tp->rss_ind_tbl));
> > -	else
> > +	else if (tg3_flag(tp, USER_INDIR_TBL)) {
> > +		/* Validate table against current IRQ count */
> > +		for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++) {
> > +			if (tp->rss_ind_tbl[i] >= tp->irq_cnt - 1) {
> > +				/* Bring the index within range */
> > +				tp->rss_ind_tbl[i] = tp->rss_ind_tbl[i] %
> > +						     (tp->irq_cnt - 1);
> > +			}
> > +		}
> > +	} else {
> >  		for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
> >  			tp->rss_ind_tbl[i] = i % (tp->irq_cnt - 1);
> > +	}
> >  }
> >  
> >  void tg3_rss_write_indir_tbl(struct tg3 *tp)
> > @@ -10719,6 +10729,117 @@ static int tg3_get_sset_count(struct net_device *dev, int sset)
> >  	}
> >  }
> >  
> > +static int tg3_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
> > +			 u32 *rules __always_unused)
> > +{
> > +	struct tg3 *tp = netdev_priv(dev);
> > +
> > +	if (!tg3_flag(tp, SUPPORT_MSIX))
> > +		return -EOPNOTSUPP;
> > +
> > +	switch (info->cmd) {
> > +	case ETHTOOL_GRXRINGS:
> > +		if (netif_running(tp->dev))
> > +			info->data = tp->irq_cnt;
> > +		else {
> > +			info->data = num_online_cpus();
> > +			if (info->data > TG3_IRQ_MAX_VECS_RSS)
> > +				info->data = TG3_IRQ_MAX_VECS_RSS;
> > +		}
> > +
> > +		/* The first interrupt vector only
> > +		 * handles link interrupts.
> > +		 */
> > +		info->data -= 1;
> > +		return 0;
> > +
> > +	default:
> > +		return -EOPNOTSUPP;
> > +	}
> > +}
> > +
> > +static int tg3_get_rxfh_indir(struct net_device *dev,
> > +			      struct ethtool_rxfh_indir *indir)
> > +{
> > +	struct tg3 *tp = netdev_priv(dev);
> > +	int i;
> > +
> > +	if (!tg3_flag(tp, SUPPORT_MSIX))
> > +		return -EOPNOTSUPP;
> > +
> > +	if (!indir->size) {
> > +		indir->size = TG3_RSS_INDIR_TBL_SIZE;
> > +		return 0;
> > +	}
> > +
> > +	if (indir->size != TG3_RSS_INDIR_TBL_SIZE)
> > +		return -EINVAL;
> > +
> > +	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
> > +		indir->ring_index[i] = tp->rss_ind_tbl[i];
> > +
> > +	return 0;
> > +}
> > +
> > +static int tg3_set_rxfh_indir(struct net_device *dev,
> > +			      const struct ethtool_rxfh_indir *indir)
> > +{
> > +	struct tg3 *tp = netdev_priv(dev);
> > +	size_t i;
> > +
> > +	if (!tg3_flag(tp, SUPPORT_MSIX))
> > +		return -EOPNOTSUPP;
> > +
> > +	if (!indir->size) {
> > +		tg3_flag_clear(tp, USER_INDIR_TBL);
> > +		tg3_rss_init_indir_tbl(tp);
> > +	} else {
> > +		int limit;
> > +
> > +		/* Validate size and indices */
> > +		if (indir->size != TG3_RSS_INDIR_TBL_SIZE)
> > +			return -EINVAL;
> > +
> > +		if (netif_running(dev))
> > +			limit = tp->irq_cnt;
> > +		else {
> > +			limit = num_online_cpus();
> > +			if (limit > TG3_IRQ_MAX_VECS_RSS)
> > +				limit = TG3_IRQ_MAX_VECS_RSS;
> > +		}
> > +
> > +		/* The first interrupt vector only
> > +		 * handles link interrupts.
> > +		 */
> > +		limit -= 1;
> > +
> > +		/* Check the indices in the table.
> > +		 * Leave the existing table unmodified
> > +		 * if an error is detected.
> > +		 */
> > +		for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
> > +			if (indir->ring_index[i] >= limit)
> > +				return -EINVAL;
> > +
> > +		tg3_flag_set(tp, USER_INDIR_TBL);
> > +
> > +		for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
> > +			tp->rss_ind_tbl[i] = indir->ring_index[i];
> > +	}
> > +
> > +	if (!netif_running(dev) || !tg3_flag(tp, ENABLE_RSS))
> > +		return 0;
> > +
> > +	/* It is legal to write the indirection
> > +	 * table while the device is running.
> > +	 */
> > +	tg3_full_lock(tp, 0);
> > +	tg3_rss_write_indir_tbl(tp);
> > +	tg3_full_unlock(tp);
> > +
> > +	return 0;
> > +}
> > +
> >  static void tg3_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
> >  {
> >  	switch (stringset) {
> > @@ -11949,6 +12070,9 @@ static const struct ethtool_ops tg3_ethtool_ops = {
> >  	.get_coalesce		= tg3_get_coalesce,
> >  	.set_coalesce		= tg3_set_coalesce,
> >  	.get_sset_count		= tg3_get_sset_count,
> > +	.get_rxnfc		= tg3_get_rxnfc,
> > +	.get_rxfh_indir		= tg3_get_rxfh_indir,
> > +	.set_rxfh_indir		= tg3_set_rxfh_indir,
> >  };
> >  
> >  static void __devinit tg3_get_eeprom_size(struct tg3 *tp)
> > diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
> > index aea8f72..4800595 100644
> > --- a/drivers/net/ethernet/broadcom/tg3.h
> > +++ b/drivers/net/ethernet/broadcom/tg3.h
> > @@ -2932,6 +2932,7 @@ enum TG3_FLAGS {
> >  	TG3_FLAG_APE_HAS_NCSI,
> >  	TG3_FLAG_4K_FIFO_LIMIT,
> >  	TG3_FLAG_RESET_TASK_PENDING,
> > +	TG3_FLAG_USER_INDIR_TBL,
> >  	TG3_FLAG_5705_PLUS,
> >  	TG3_FLAG_IS_5788,
> >  	TG3_FLAG_5750_PLUS,
> 
> -- 
> Ben Hutchings, Staff Engineer, Solarflare
> Not speaking for my employer; that's the marketing department's job.
> They asked us to note that Solarflare product names are trademarked.
> 
> 

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

On Fri, 2011-12-16 at 11:19 -0800, Matt Carlson wrote:
> On Thu, Dec 15, 2011 at 07:04:34PM -0800, Ben Hutchings wrote:
> > On Thu, 2011-12-15 at 16:47 -0800, Matt Carlson wrote:
> > > This patch adds the ethtool callbacks necessary to change the rss
> > > indirection table from userspace.  When setting the indirection table
> > > through set_rxfh_indir, an indirection table size of zero is
> > > interpreted to mean that the admin wants to relinquish control of the
> > > table to the driver.  Should the number of interrupts change (e.g.
> > > across a close / open call, or through a reset), any indirection table
> > > values that exceed the number of RSS queues or interrupt vectors will
> > > be automatically scaled back to values within range.
> > > 
> > > Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
> > > Signed-off-by: Michael Chan <mchan@broadcom.com>
> > > Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
> > 
> > No I didn't!
> > 
> > Ben.
> 
> Sorry.  This part of procedure I'm unsure about.  I didn't want to lose
> the ack of your contributions to this patch.  The SOB does imply that
> you are O.K. with it as-is though, which you may or may not be aligned
> with.  I apologize if I was putting words in your mouth.
> 
> What should I have done instead?  Would Dave put the SOB on your behalf
> as he accepts it?
[...]

If you really want to credit me for the tiny change I suggested, just
put that in free-form.  But I'm afraid you'll have to respin this
completely, as David applied my changes to centralise validation and the
default policy.  I think instead of adding the USER_INDIR_TBL flag you
could reasonably reset the table to default whenever the interface is
brought up and you fail to get the wanted number of IRQs.

Ben.