[PATCH] bcm43xx-softmac: optimization of DMA bitfields.]
John, Please pull this patch by MB for the wireless-2.6 tree. It replaces the one sent earlier today. Somehow, I managed to mangle it by deleting a semicolon. Larry This patch depends on the 64bit DMA patch, which is already submitted for inclusion. Convert the bitfields in the bcm43xx DMA code to properly aligned u8 booleans. These flags are accessed in the DMA hotpath, so it's a good idea to waste a few bytes of memory for the sake of speed by not requiring masking (and probably shifting) of the bitfields. Signed-off-by: Michael Buesch <[EMAIL PROTECTED]> Signed-Off-By: Larry Finger <[EMAIL PROTECTED]> Index: wireless-2.6/drivers/net/wireless/bcm43xx/bcm43xx_dma.h === --- wireless-2.6.orig/drivers/net/wireless/bcm43xx/bcm43xx_dma.h 2006-08-16 12:47:27.0 +0200 +++ wireless-2.6/drivers/net/wireless/bcm43xx/bcm43xx_dma.h 2006-08-16 12:49:43.0 +0200 @@ -235,9 +235,12 @@ u16 mmio_base; /* DMA controller index number (0-5). */ int index; - u8 tx:1,/* TRUE, if this is a TX ring. */ - dma64:1, /* TRUE, if 64-bit DMA is enabled (FALSE if 32bit). */ - suspended:1; /* TRUE, if transfers are suspended on this ring. */ + /* Boolean. Is this a TX ring? */ + u8 tx; + /* Boolean. 64bit DMA if true, 32bit DMA otherwise. */ + u8 dma64; + /* Boolean. Are transfers suspended on this ring? */ + u8 suspended; struct bcm43xx_private *bcm; #ifdef CONFIG_BCM43XX_DEBUG /* Maximum number of used slots. */ - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH] bcm43xx-softmac: optimization of DMA bitfields.]
On Wednesday 16 August 2006 17:52, Larry Finger wrote: > Johannes Berg wrote: > > On Wed, 2006-08-16 at 10:36 -0500, Larry Finger wrote: > >> + /* Boolean. Is this a TX ring? */ > >> + u8 tx > >> + /* Boolean. 64bit DMA if true, 32bit DMA otherwise. */ > >> + u8 dma64; > > > > does that compile? > > > > johannes > > > > Yes, it did here. Did you have a problem? You removed a ; by mistake. Look, it's there in my original patch (which was compile tested). -- Greetings Michael. - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH] bcm43xx-softmac: optimization of DMA bitfields.]
Michael Buesch wrote: > On Wednesday 16 August 2006 17:52, Larry Finger wrote: >> Johannes Berg wrote: >>> On Wed, 2006-08-16 at 10:36 -0500, Larry Finger wrote: + /* Boolean. Is this a TX ring? */ + u8 tx + /* Boolean. 64bit DMA if true, 32bit DMA otherwise. */ + u8 dma64; >>> does that compile? >>> >>> johannes >>> >> Yes, it did here. Did you have a problem? > > You removed a ; by mistake. > Look, it's there in my original patch (which was compile tested). > I saw that just after I sent the response to Johannes. I don't know how that ; got deleted, but a revised version will be on to John soon. Larry - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH] bcm43xx-softmac: optimization of DMA bitfields.]
Johannes Berg wrote: > On Wed, 2006-08-16 at 10:36 -0500, Larry Finger wrote: >> +/* Boolean. Is this a TX ring? */ >> +u8 tx >> +/* Boolean. 64bit DMA if true, 32bit DMA otherwise. */ >> +u8 dma64; > > does that compile? > > johannes > Yes, it did here. Did you have a problem? Larry - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH] bcm43xx-softmac: optimization of DMA bitfields.]
John, Please pull this patch for the wireless-2.6 tree. This patch depends on the 64bit DMA patch, which is already submitted for inclusion. Convert the bitfields in the bcm43xx DMA code to properly aligned u8 booleans. These flags are accessed in the DMA hotpath, so it's a good idea to waste a few bytes of memory for the sake of speed by not requiring masking (and probably shifting) of the bitfields. Signed-off-by: Michael Buesch <[EMAIL PROTECTED]> Signed-Off-By: Larry Finger <[EMAIL PROTECTED]> Index: wireless-2.6/drivers/net/wireless/bcm43xx/bcm43xx_dma.h === --- wireless-2.6.orig/drivers/net/wireless/bcm43xx/bcm43xx_dma.h 2006-08-16 12:47:27.0 +0200 +++ wireless-2.6/drivers/net/wireless/bcm43xx/bcm43xx_dma.h 2006-08-16 12:49:43.0 +0200 @@ -235,9 +235,12 @@ u16 mmio_base; /* DMA controller index number (0-5). */ int index; - u8 tx:1,/* TRUE, if this is a TX ring. */ - dma64:1, /* TRUE, if 64-bit DMA is enabled (FALSE if 32bit). */ - suspended:1; /* TRUE, if transfers are suspended on this ring. */ + /* Boolean. Is this a TX ring? */ + u8 tx + /* Boolean. 64bit DMA if true, 32bit DMA otherwise. */ + u8 dma64; + /* Boolean. Are transfers suspended on this ring? */ + u8 suspended; struct bcm43xx_private *bcm; #ifdef CONFIG_BCM43XX_DEBUG /* Maximum number of used slots. */ - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH] bcm43xx-softmac: optimization of DMA bitfields.]
On Wed, 2006-08-16 at 10:36 -0500, Larry Finger wrote: > + /* Boolean. Is this a TX ring? */ > + u8 tx > + /* Boolean. 64bit DMA if true, 32bit DMA otherwise. */ > + u8 dma64; does that compile? johannes - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html