From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Kirsher Subject: [net-next-2.6 PATCH 2/4] e1000e: reduce writes of RX producer ptr Date: Wed, 05 May 2010 17:02:49 -0700 Message-ID: <20100506000247.8042.97827.stgit@localhost.localdomain> References: <20100506000221.8042.64794.stgit@localhost.localdomain> Mime-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, gospo@redhat.com, Tom Herbert , Bruce Allan , Jeff Kirsher To: davem@davemloft.net Return-path: Received: from qmta03.emeryville.ca.mail.comcast.net ([76.96.30.32]:52733 "EHLO qmta03.emeryville.ca.mail.comcast.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752412Ab0EFADI (ORCPT ); Wed, 5 May 2010 20:03:08 -0400 In-Reply-To: <20100506000221.8042.64794.stgit@localhost.localdomain> Sender: netdev-owner@vger.kernel.org List-ID: From: Tom Herbert Reduce number of writes to RX producer pointer. When alloc'ing RX buffers, only write the RX producer pointer once every E1000_RX_BUFFER_WRITE (16) buffers created. Signed-off-by: Tom Herbert Acked-by: Bruce Allan Signed-off-by: Jeff Kirsher --- drivers/net/e1000e/netdev.c | 57 +++++++++++++++++-------------------------- 1 files changed, 23 insertions(+), 34 deletions(-) diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 1eb9b59..b767dbb 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -548,26 +548,23 @@ map_skb: rx_desc = E1000_RX_DESC(*rx_ring, i); rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma); + if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) { + /* + * Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, adapter->hw.hw_addr + rx_ring->tail); + } i++; if (i == rx_ring->count) i = 0; buffer_info = &rx_ring->buffer_info[i]; } - if (rx_ring->next_to_use != i) { - rx_ring->next_to_use = i; - if (i-- == 0) - i = (rx_ring->count - 1); - - /* - * Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). - */ - wmb(); - writel(i, adapter->hw.hw_addr + rx_ring->tail); - } + rx_ring->next_to_use = i; } /** @@ -649,6 +646,17 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, rx_desc->read.buffer_addr[0] = cpu_to_le64(buffer_info->dma); + if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) { + /* + * Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i<<1, adapter->hw.hw_addr + rx_ring->tail); + } + i++; if (i == rx_ring->count) i = 0; @@ -656,26 +664,7 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, } no_buffers: - if (rx_ring->next_to_use != i) { - rx_ring->next_to_use = i; - - if (!(i--)) - i = (rx_ring->count - 1); - - /* - * Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). - */ - wmb(); - /* - * Hardware increments by 16 bytes, but packet split - * descriptors are 32 bytes...so we increment tail - * twice as much. - */ - writel(i<<1, adapter->hw.hw_addr + rx_ring->tail); - } + rx_ring->next_to_use = i; } /**