From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Andy Gospodarek <gospo@broadcom.com>,
Hauke Mehrtens <hauke@hauke-m.de>,
"David S. Miller" <davem@davemloft.net>
Subject: [PATCH 4.8 04/49] bgmac: stop clearing DMA receive control register right after it is set
Date: Sat, 19 Nov 2016 10:22:56 +0100 [thread overview]
Message-ID: <20161119092037.405381748@linuxfoundation.org> (raw)
In-Reply-To: <20161119092036.698705716@linuxfoundation.org>
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;
next prev parent reply other threads:[~2016-11-19 9:24 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20161119092339epcas3p4464a1a8a19f9171b12871d8cfef3ea16@epcas3p4.samsung.com>
2016-11-19 9:22 ` [PATCH 4.8 00/49] 4.8.10-stable review Greg Kroah-Hartman
2016-11-19 9:22 ` [PATCH 4.8 01/49] dctcp: avoid bogus doubling of cwnd after loss Greg Kroah-Hartman
2016-11-19 9:22 ` [PATCH 4.8 02/49] net: clear sk_err_soft in sk_clone_lock() Greg Kroah-Hartman
2016-11-19 9:22 ` Greg Kroah-Hartman [this message]
2016-11-19 9:22 ` [PATCH 4.8 05/49] ip6_tunnel: Clear IP6CB in ip6tunnel_xmit() Greg Kroah-Hartman
2016-11-19 9:22 ` [PATCH 4.8 07/49] ipv4: allow local fragmentation in ip_finish_output_gso() Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 08/49] tcp: fix return value for partial writes Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 09/49] dccp: do not release listeners too soon Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 10/49] dccp: do not send reset to already closed sockets Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 11/49] dccp: fix out of bound access in dccp_v4_err() Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 12/49] ipv6: dccp: fix out of bound access in dccp_v6_err() Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 13/49] ipv6: dccp: add missing bind_conflict to dccp_ipv6_mapped Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 14/49] sctp: assign assoc_id earlier in __sctp_connect Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 15/49] bpf: fix htab map destruction when extra reserve is in use Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 16/49] net: icmp6_send should use dst dev to determine L3 domain Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 17/49] fib_trie: Correct /proc/net/route off by one error Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 19/49] net: icmp_route_lookup should use rt dev to determine L3 domain Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 20/49] net: __skb_flow_dissect() must cap its return value Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 21/49] ipv4: use new_gw for redirect neigh lookup Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 22/49] tcp: take care of truncations done by sk_filter() Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 24/49] mlxsw: spectrum: Fix refcount bug on span entries Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 25/49] mlxsw: spectrum_router: Correctly dump neighbour activity Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 26/49] Revert "bnx2: Reset device during driver initialization" Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 27/49] bnx2: Wait for in-flight DMA to complete at probe stage Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 28/49] sctp: change sk state only when it has assocs in sctp_shutdown Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 29/49] net: stmmac: Fix lack of link transition for fixed PHYs Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 31/49] sparc: Handle negative offsets in arch_jump_label_transform Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 32/49] sparc64: Handle extremely large kernel TSB range flushes sanely Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 33/49] sparc64: Fix illegal relative branches in hypervisor patched TLB code Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 34/49] sparc64: Fix instruction count in comment for __hypervisor_flush_tlb_pending Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 35/49] sparc64: Fix illegal relative branches in hypervisor patched TLB cross-call code Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 36/49] sparc64: Handle extremely large kernel TLB range flushes more gracefully Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 37/49] sparc64: Delete __ret_efault Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 38/49] sparc64: Prepare to move to more saner user copy exception handling Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 39/49] sparc64: Convert copy_in_user to accurate exception reporting Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 40/49] sparc64: Convert GENcopy_{from,to}_user " Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 41/49] sparc64: Convert U1copy_{from,to}_user " Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 42/49] sparc64: Convert NG4copy_{from,to}_user " Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 43/49] sparc64: Convert NGcopy_{from,to}_user " Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 44/49] sparc64: Convert NG2copy_{from,to}_user " Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 45/49] sparc64: Convert U3copy_{from,to}_user " Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 46/49] sparc64: Delete now unused user copy assembler helpers Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 47/49] sparc64: Delete now unused user copy fixup functions Greg Kroah-Hartman
2016-11-19 9:23 ` [PATCH 4.8 48/49] usb: gadget: f_fs: edit epfile->ep under lock Greg Kroah-Hartman
2016-11-19 16:21 ` [PATCH 4.8 00/49] 4.8.10-stable review Guenter Roeck
2016-11-19 16:58 ` Greg Kroah-Hartman
2016-11-21 16:32 ` Shuah Khan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20161119092037.405381748@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=davem@davemloft.net \
--cc=gospo@broadcom.com \
--cc=hauke@hauke-m.de \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).