From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sinan Kaya Date: Wed, 21 Mar 2018 14:56:05 -0400 Subject: [Intel-wired-lan] [PATCH REPOST v4 1/7] i40e/i40evf: Eliminate duplicate barriers on weakly-ordered archs In-Reply-To: <1521658572-26354-1-git-send-email-okaya@codeaurora.org> References: <1521658572-26354-1-git-send-email-okaya@codeaurora.org> Message-ID: <1521658572-26354-2-git-send-email-okaya@codeaurora.org> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: intel-wired-lan@osuosl.org List-ID: Code includes wmb() followed by writel(). writel() already has a barrier on some architectures like arm64. This ends up CPU observing two barriers back to back before executing the register write. Since code already has an explicit barrier call, changing writel() to writel_relaxed(). Signed-off-by: Sinan Kaya Reviewed-by: Alexander Duyck --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 8 ++++---- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index e554aa6cf..9455869 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -185,7 +185,7 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, /* Mark the data descriptor to be watched */ first->next_to_watch = tx_desc; - writel(tx_ring->next_to_use, tx_ring->tail); + writel_relaxed(tx_ring->next_to_use, tx_ring->tail); return 0; dma_fail: @@ -1375,7 +1375,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + writel_relaxed(val, rx_ring->tail); } /** @@ -2258,7 +2258,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ wmb(); - writel(xdp_ring->next_to_use, xdp_ring->tail); + writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail); } rx_ring->skb = skb; @@ -3286,7 +3286,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { - writel(i, tx_ring->tail); + writel_relaxed(i, tx_ring->tail); /* we need this if more than one processor can write to our tail * at a time, it synchronizes IO on IA64/Altix systems diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 357d605..56eea20 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -667,7 +667,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + writel_relaxed(val, rx_ring->tail); } /** @@ -2243,7 +2243,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { - writel(i, tx_ring->tail); + writel_relaxed(i, tx_ring->tail); /* we need this if more than one processor can write to our tail * at a time, it synchronizes IO on IA64/Altix systems -- 2.7.4 From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sinan Kaya Subject: [PATCH REPOST v4 1/7] i40e/i40evf: Eliminate duplicate barriers on weakly-ordered archs Date: Wed, 21 Mar 2018 14:56:05 -0400 Message-ID: <1521658572-26354-2-git-send-email-okaya@codeaurora.org> References: <1521658572-26354-1-git-send-email-okaya@codeaurora.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1521658572-26354-1-git-send-email-okaya@codeaurora.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=m.gmane.org@lists.infradead.org To: jeffrey.t.kirsher@intel.com Cc: sulrich@codeaurora.org, netdev@vger.kernel.org, timur@codeaurora.org, linux-kernel@vger.kernel.org, Sinan Kaya , intel-wired-lan@lists.osuosl.org, linux-arm-msm@vger.kernel.org, linux-arm-kernel@lists.infradead.org List-Id: linux-arm-msm@vger.kernel.org Code includes wmb() followed by writel(). writel() already has a barrier on some architectures like arm64. This ends up CPU observing two barriers back to back before executing the register write. Since code already has an explicit barrier call, changing writel() to writel_relaxed(). Signed-off-by: Sinan Kaya Reviewed-by: Alexander Duyck --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 8 ++++---- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index e554aa6cf..9455869 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -185,7 +185,7 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, /* Mark the data descriptor to be watched */ first->next_to_watch = tx_desc; - writel(tx_ring->next_to_use, tx_ring->tail); + writel_relaxed(tx_ring->next_to_use, tx_ring->tail); return 0; dma_fail: @@ -1375,7 +1375,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + writel_relaxed(val, rx_ring->tail); } /** @@ -2258,7 +2258,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ wmb(); - writel(xdp_ring->next_to_use, xdp_ring->tail); + writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail); } rx_ring->skb = skb; @@ -3286,7 +3286,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { - writel(i, tx_ring->tail); + writel_relaxed(i, tx_ring->tail); /* we need this if more than one processor can write to our tail * at a time, it synchronizes IO on IA64/Altix systems diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 357d605..56eea20 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -667,7 +667,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + writel_relaxed(val, rx_ring->tail); } /** @@ -2243,7 +2243,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { - writel(i, tx_ring->tail); + writel_relaxed(i, tx_ring->tail); /* we need this if more than one processor can write to our tail * at a time, it synchronizes IO on IA64/Altix systems -- 2.7.4 From mboxrd@z Thu Jan 1 00:00:00 1970 From: okaya@codeaurora.org (Sinan Kaya) Date: Wed, 21 Mar 2018 14:56:05 -0400 Subject: [PATCH REPOST v4 1/7] i40e/i40evf: Eliminate duplicate barriers on weakly-ordered archs In-Reply-To: <1521658572-26354-1-git-send-email-okaya@codeaurora.org> References: <1521658572-26354-1-git-send-email-okaya@codeaurora.org> Message-ID: <1521658572-26354-2-git-send-email-okaya@codeaurora.org> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Code includes wmb() followed by writel(). writel() already has a barrier on some architectures like arm64. This ends up CPU observing two barriers back to back before executing the register write. Since code already has an explicit barrier call, changing writel() to writel_relaxed(). Signed-off-by: Sinan Kaya Reviewed-by: Alexander Duyck --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 8 ++++---- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index e554aa6cf..9455869 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -185,7 +185,7 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, /* Mark the data descriptor to be watched */ first->next_to_watch = tx_desc; - writel(tx_ring->next_to_use, tx_ring->tail); + writel_relaxed(tx_ring->next_to_use, tx_ring->tail); return 0; dma_fail: @@ -1375,7 +1375,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + writel_relaxed(val, rx_ring->tail); } /** @@ -2258,7 +2258,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ wmb(); - writel(xdp_ring->next_to_use, xdp_ring->tail); + writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail); } rx_ring->skb = skb; @@ -3286,7 +3286,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { - writel(i, tx_ring->tail); + writel_relaxed(i, tx_ring->tail); /* we need this if more than one processor can write to our tail * at a time, it synchronizes IO on IA64/Altix systems diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 357d605..56eea20 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -667,7 +667,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + writel_relaxed(val, rx_ring->tail); } /** @@ -2243,7 +2243,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { - writel(i, tx_ring->tail); + writel_relaxed(i, tx_ring->tail); /* we need this if more than one processor can write to our tail * at a time, it synchronizes IO on IA64/Altix systems -- 2.7.4 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753051AbeCUS4b (ORCPT ); Wed, 21 Mar 2018 14:56:31 -0400 Received: from smtp.codeaurora.org ([198.145.29.96]:58676 "EHLO smtp.codeaurora.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752783AbeCUS4W (ORCPT ); Wed, 21 Mar 2018 14:56:22 -0400 DMARC-Filter: OpenDMARC Filter v1.3.2 smtp.codeaurora.org D509760314 Authentication-Results: pdx-caf-mail.web.codeaurora.org; dmarc=none (p=none dis=none) header.from=codeaurora.org Authentication-Results: pdx-caf-mail.web.codeaurora.org; spf=none smtp.mailfrom=okaya@codeaurora.org From: Sinan Kaya To: jeffrey.t.kirsher@intel.com Cc: netdev@vger.kernel.org, timur@codeaurora.org, sulrich@codeaurora.org, linux-arm-msm@vger.kernel.org, linux-arm-kernel@lists.infradead.org, Sinan Kaya , intel-wired-lan@lists.osuosl.org, linux-kernel@vger.kernel.org Subject: [PATCH REPOST v4 1/7] i40e/i40evf: Eliminate duplicate barriers on weakly-ordered archs Date: Wed, 21 Mar 2018 14:56:05 -0400 Message-Id: <1521658572-26354-2-git-send-email-okaya@codeaurora.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1521658572-26354-1-git-send-email-okaya@codeaurora.org> References: <1521658572-26354-1-git-send-email-okaya@codeaurora.org> MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Code includes wmb() followed by writel(). writel() already has a barrier on some architectures like arm64. This ends up CPU observing two barriers back to back before executing the register write. Since code already has an explicit barrier call, changing writel() to writel_relaxed(). Signed-off-by: Sinan Kaya Reviewed-by: Alexander Duyck --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 8 ++++---- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index e554aa6cf..9455869 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -185,7 +185,7 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, /* Mark the data descriptor to be watched */ first->next_to_watch = tx_desc; - writel(tx_ring->next_to_use, tx_ring->tail); + writel_relaxed(tx_ring->next_to_use, tx_ring->tail); return 0; dma_fail: @@ -1375,7 +1375,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + writel_relaxed(val, rx_ring->tail); } /** @@ -2258,7 +2258,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ wmb(); - writel(xdp_ring->next_to_use, xdp_ring->tail); + writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail); } rx_ring->skb = skb; @@ -3286,7 +3286,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { - writel(i, tx_ring->tail); + writel_relaxed(i, tx_ring->tail); /* we need this if more than one processor can write to our tail * at a time, it synchronizes IO on IA64/Altix systems diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 357d605..56eea20 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -667,7 +667,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + writel_relaxed(val, rx_ring->tail); } /** @@ -2243,7 +2243,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { - writel(i, tx_ring->tail); + writel_relaxed(i, tx_ring->tail); /* we need this if more than one processor can write to our tail * at a time, it synchronizes IO on IA64/Altix systems -- 2.7.4