Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Rohan G Thomas <rohan.g.thomas@intel.com>
To:     "David S . Miller" <davem@davemloft.net>,
        Alexandre Torgue <alexandre.torgue@foss.st.com>,
        Jose Abreu <joabreu@synopsys.com>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        Maxime Coquelin <mcoquelin.stm32@gmail.com>,
        Rob Herring <robh+dt@kernel.org>,
        Krzysztof Kozlowski <krzysztof.kozlowski+dt@linaro.org>,
        Conor Dooley <conor+dt@kernel.org>
Cc:     netdev@vger.kernel.org, linux-stm32@st-md-mailman.stormreply.com,
        linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org,
        Rohan G Thomas <rohan.g.thomas@intel.com>
Subject: [PATCH net-next v2 2/2] net: stmmac: Tx coe sw fallback
Date:   Sat, 12 Aug 2023 03:00:32 +0800
Message-Id: <20230811190032.13391-3-rohan.g.thomas@intel.com>
In-Reply-To: <20230811190032.13391-1-rohan.g.thomas@intel.com>
References: <20230810150328.19704-1-rohan.g.thomas@intel.com>
 <20230811190032.13391-1-rohan.g.thomas@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add sw fallback of tx checksum calculation for those tx queues that
don't support tx checksum offloading. Because, some DWMAC IPs support
tx checksum offloading only for a few initial tx queues, starting
from tx queue 0.

Signed-off-by: Rohan G Thomas <rohan.g.thomas@intel.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h  |  2 ++
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 19 +++++++++++++++++++
 .../ethernet/stmicro/stmmac/stmmac_platform.c |  4 ++++
 include/linux/stmmac.h                        |  1 +
 4 files changed, 26 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 3401e888a9f6..f526bcaaaf64 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -219,6 +219,8 @@ struct stmmac_priv {
 	int hwts_tx_en;
 	bool tx_path_in_lpi_mode;
 	bool tso;
+	bool tx_q_coe_lmt;
+	u32 tx_q_with_coe;
 	int sph;
 	int sph_cap;
 	u32 sarc_type;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fcab363d8dfa..cb8d2c159832 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4409,6 +4409,17 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	WARN_ON(tx_q->tx_skbuff[first_entry]);
 
 	csum_insertion = (skb->ip_summed == CHECKSUM_PARTIAL);
+	/* Some DWMAC IPs support tx coe only for a few initial tx queues,
+	 * starting from tx queue 0. So checksum offloading for those queues
+	 * that don't support tx coe needs to fallback to software checksum
+	 * calculation.
+	 */
+	if (csum_insertion && priv->tx_q_coe_lmt &&
+	    queue >= priv->tx_q_with_coe) {
+		if (unlikely(skb_checksum_help(skb)))
+			goto dma_map_err;
+		csum_insertion = !csum_insertion;
+	}
 
 	if (likely(priv->extend_desc))
 		desc = (struct dma_desc *)(tx_q->dma_etx + entry);
@@ -7386,6 +7397,14 @@ int stmmac_dvr_probe(struct device *device,
 		dev_info(priv->device, "SPH feature enabled\n");
 	}
 
+	if (priv->plat->tx_coe &&
+	    priv->plat->tx_queues_with_coe < priv->plat->tx_queues_to_use) {
+		priv->tx_q_coe_lmt = true;
+		priv->tx_q_with_coe = priv->plat->tx_queues_with_coe;
+		dev_info(priv->device, "TX COE limited to %u tx queues\n",
+			 priv->tx_q_with_coe);
+	}
+
 	/* Ideally our host DMA address width is the same as for the
 	 * device. However, it may differ and then we have to use our
 	 * host DMA width for allocation and the device DMA width for
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index be8e79c7aa34..0138b7c9c7ab 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -225,6 +225,10 @@ static int stmmac_mtl_setup(struct platform_device *pdev,
 				 &plat->tx_queues_to_use))
 		plat->tx_queues_to_use = 1;
 
+	if (of_property_read_u32(tx_node, "snps,tx-queues-with-coe",
+				 &plat->tx_queues_with_coe))
+		plat->tx_queues_with_coe = plat->tx_queues_to_use;
+
 	if (of_property_read_bool(tx_node, "snps,tx-sched-wrr"))
 		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR;
 	else if (of_property_read_bool(tx_node, "snps,tx-sched-wfq"))
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 652404c03944..795c10d19c1c 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -252,6 +252,7 @@ struct plat_stmmacenet_data {
 	u32 host_dma_width;
 	u32 rx_queues_to_use;
 	u32 tx_queues_to_use;
+	u32 tx_queues_with_coe;
 	u8 rx_sched_algorithm;
 	u8 tx_sched_algorithm;
 	struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
-- 
2.19.0