Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1525938

[PATCH 4.8 04/49] bgmac: stop clearing DMA receive control register right after it is set

Show all headers | View raw

4.8-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andy Gospodarek <gospo@broadcom.com>


[ Upstream commit fcdefccac976ee51dd6071832b842d8fb41c479c ]

Current bgmac code initializes some DMA settings in the receive control
register for some hardware and then immediately clears those settings.
Not clearing those settings results in ~420Mbps *improvement* in
throughput; this system can now receive frames at line-rate on Broadcom
5871x hardware compared to ~520Mbps today.  I also tested a few other
values but found there to be no discernible difference in CPU
utilization even if burst size and prefetching values are different.

On the hardware tested there was no need to keep the code that cleared
all but bits 16-17, but since there is a wide variety of hardware that
used this driver (I did not look at all hardware docs for hardware using
this IP block), I find it wise to move this call up and clear bits just
after reading the default value from the hardware rather than completely
removing it.

This is a good candidate for -stable >=3.14 since that is when the code
that was supposed to improve performance (but did not) was introduced.

Signed-off-by: Andy Gospodarek <gospo@broadcom.com>
Fixes: 56ceecde1f29 ("bgmac: initialize the DMA controller of core...")
Cc: Hauke Mehrtens <hauke@hauke-m.de>
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/broadcom/bgmac.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -307,6 +307,10 @@ static void bgmac_dma_rx_enable(struct b
 	u32 ctl;
 
 	ctl = bgmac_read(bgmac, ring->mmio_base + BGMAC_DMA_RX_CTL);
+
+	/* preserve ONLY bits 16-17 from current hardware value */
+	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
+
 	if (bgmac->feature_flags & BGMAC_FEAT_RX_MASK_SETUP) {
 		ctl &= ~BGMAC_DMA_RX_BL_MASK;
 		ctl |= BGMAC_DMA_RX_BL_128 << BGMAC_DMA_RX_BL_SHIFT;
@@ -317,7 +321,6 @@ static void bgmac_dma_rx_enable(struct b
 		ctl &= ~BGMAC_DMA_RX_PT_MASK;
 		ctl |= BGMAC_DMA_RX_PT_1 << BGMAC_DMA_RX_PT_SHIFT;
 	}
-	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
 	ctl |= BGMAC_DMA_RX_ENABLE;
 	ctl |= BGMAC_DMA_RX_PARITY_DISABLE;
 	ctl |= BGMAC_DMA_RX_OVERFLOW_CONT;

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH 4.8 00/49] 4.8.10-stable review Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
  [PATCH 4.8 07/49] ipv4: allow local fragmentation in ip_finish_output_gso() Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
  [PATCH 4.8 42/49] sparc64: Convert NG4copy_{from,to}_user to accurate exception reporting. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
  [PATCH 4.8 36/49] sparc64: Handle extremely large kernel TLB range flushes more gracefully. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
  [PATCH 4.8 43/49] sparc64: Convert NGcopy_{from,to}_user to accurate exception reporting. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
  [PATCH 4.8 24/49] mlxsw: spectrum: Fix refcount bug on span entries Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
  [PATCH 4.8 33/49] sparc64: Fix illegal relative branches in hypervisor patched TLB code. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:30 +0100
  [PATCH 4.8 37/49] sparc64: Delete __ret_efault. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 04/49] bgmac: stop clearing DMA receive control register right after it is set Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 11/49] dccp: fix out of bound access in dccp_v4_err() Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 32/49] sparc64: Handle extremely large kernel TSB range flushes sanely. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 02/49] net: clear sk_err_soft in sk_clone_lock() Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 28/49] sctp: change sk state only when it has assocs in sctp_shutdown Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 10/49] dccp: do not send reset to already closed sockets Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 38/49] sparc64: Prepare to move to more saner user copy exception handling. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 09/49] dccp: do not release listeners too soon Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 40/49] sparc64: Convert GENcopy_{from,to}_user to accurate exception reporting. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 15/49] bpf: fix htab map destruction when extra reserve is in use Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  [PATCH 4.8 13/49] ipv6: dccp: add missing bind_conflict to dccp_ipv6_mapped Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 10:40 +0100
  Re: [PATCH 4.8 00/49] 4.8.10-stable review Guenter Roeck <linux@roeck-us.net> - 2016-11-19 17:30 +0100
    Re: [PATCH 4.8 00/49] 4.8.10-stable review Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2016-11-19 18:00 +0100
  Re: [PATCH 4.8 00/49] 4.8.10-stable review Shuah Khan <shuah.kh@samsung.com> - 2016-11-21 17:40 +0100

csiph-web