* [PATCH net-next v13 3/3] net: hisilicon: new hip04 ethernet driver
From: Ding Tianhong @ 2015-01-14 6:34 UTC (permalink / raw)
To: arnd, robh+dt, davem, grant.likely, agraf
Cc: sergei.shtylyov, linux-arm-kernel, eric.dumazet, xuwei5,
zhangfei.gao, netdev, devicetree, linux
In-Reply-To: <1421217254-12008-1-git-send-email-dingtianhong@huawei.com>
Support Hisilicon hip04 ethernet driver, including 100M / 1000M controller.
The controller has no tx done interrupt, reclaim xmitted buffer in the poll.
v13: Fix the problem of alignment parameters for function and checkpatch warming.
v12: According Alex's suggestion, modify the changelog and add MODULE_DEVICE_TABLE
for hip04 ethernet.
v11: Add ethtool support for tx coalecse getting and setting, the xmit_more
is not supported for this patch, but I think it could work for hip04,
will support it later after some tests for performance better.
Here are some performance test results by ping and iperf(add tx_coalesce_frames/users),
it looks that the performance and latency is more better by tx_coalesce_frames/usecs.
- Before:
$ ping 192.168.1.1 ...
=== 192.168.1.1 ping statistics ===
24 packets transmitted, 24 received, 0% packet loss, time 22999ms
rtt min/avg/max/mdev = 0.180/0.202/0.403/0.043 ms
$ iperf -c 192.168.1.1 ...
[ ID] Interval Transfer Bandwidth
[ 3] 0.0- 1.0 sec 115 MBytes 945 Mbits/sec
- After:
$ ping 192.168.1.1 ...
=== 192.168.1.1 ping statistics ===
24 packets transmitted, 24 received, 0% packet loss, time 22999ms
rtt min/avg/max/mdev = 0.178/0.190/0.380/0.041 ms
$ iperf -c 192.168.1.1 ...
[ ID] Interval Transfer Bandwidth
[ 3] 0.0- 1.0 sec 115 MBytes 965 Mbits/sec
v10: According David Miller and Arnd Bergmann's suggestion, add some modification
for v9 version
- drop the workqueue
- batch cleanup based on tx_coalesce_frames/usecs for better throughput
- use a reasonable default tx timeout (200us, could be shorted
based on measurements) with a range timer
- fix napi poll function return value
- use a lockless queue for cleanup
Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
drivers/net/ethernet/hisilicon/Makefile | 2 +-
drivers/net/ethernet/hisilicon/hip04_eth.c | 969 +++++++++++++++++++++++++++++
2 files changed, 970 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/ethernet/hisilicon/hip04_eth.c
diff --git a/drivers/net/ethernet/hisilicon/Makefile b/drivers/net/ethernet/hisilicon/Makefile
index 40115a7..6c14540 100644
--- a/drivers/net/ethernet/hisilicon/Makefile
+++ b/drivers/net/ethernet/hisilicon/Makefile
@@ -3,4 +3,4 @@
#
obj-$(CONFIG_HIX5HD2_GMAC) += hix5hd2_gmac.o
-obj-$(CONFIG_HIP04_ETH) += hip04_mdio.o
+obj-$(CONFIG_HIP04_ETH) += hip04_mdio.o hip04_eth.o
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
new file mode 100644
index 0000000..525214e
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -0,0 +1,969 @@
+
+/* Copyright (c) 2014 Linaro Ltd.
+ * Copyright (c) 2014 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/etherdevice.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/ktime.h>
+#include <linux/of_address.h>
+#include <linux/phy.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+
+#define PPE_CFG_RX_ADDR 0x100
+#define PPE_CFG_POOL_GRP 0x300
+#define PPE_CFG_RX_BUF_SIZE 0x400
+#define PPE_CFG_RX_FIFO_SIZE 0x500
+#define PPE_CURR_BUF_CNT 0xa200
+
+#define GE_DUPLEX_TYPE 0x08
+#define GE_MAX_FRM_SIZE_REG 0x3c
+#define GE_PORT_MODE 0x40
+#define GE_PORT_EN 0x44
+#define GE_SHORT_RUNTS_THR_REG 0x50
+#define GE_TX_LOCAL_PAGE_REG 0x5c
+#define GE_TRANSMIT_CONTROL_REG 0x60
+#define GE_CF_CRC_STRIP_REG 0x1b0
+#define GE_MODE_CHANGE_REG 0x1b4
+#define GE_RECV_CONTROL_REG 0x1e0
+#define GE_STATION_MAC_ADDRESS 0x210
+#define PPE_CFG_CPU_ADD_ADDR 0x580
+#define PPE_CFG_MAX_FRAME_LEN_REG 0x408
+#define PPE_CFG_BUS_CTRL_REG 0x424
+#define PPE_CFG_RX_CTRL_REG 0x428
+#define PPE_CFG_RX_PKT_MODE_REG 0x438
+#define PPE_CFG_QOS_VMID_GEN 0x500
+#define PPE_CFG_RX_PKT_INT 0x538
+#define PPE_INTEN 0x600
+#define PPE_INTSTS 0x608
+#define PPE_RINT 0x604
+#define PPE_CFG_STS_MODE 0x700
+#define PPE_HIS_RX_PKT_CNT 0x804
+
+/* REG_INTERRUPT */
+#define RCV_INT BIT(10)
+#define RCV_NOBUF BIT(8)
+#define RCV_DROP BIT(7)
+#define TX_DROP BIT(6)
+#define DEF_INT_ERR (RCV_NOBUF | RCV_DROP | TX_DROP)
+#define DEF_INT_MASK (RCV_INT | DEF_INT_ERR)
+
+/* TX descriptor config */
+#define TX_FREE_MEM BIT(0)
+#define TX_READ_ALLOC_L3 BIT(1)
+#define TX_FINISH_CACHE_INV BIT(2)
+#define TX_CLEAR_WB BIT(4)
+#define TX_L3_CHECKSUM BIT(5)
+#define TX_LOOP_BACK BIT(11)
+
+/* RX error */
+#define RX_PKT_DROP BIT(0)
+#define RX_L2_ERR BIT(1)
+#define RX_PKT_ERR (RX_PKT_DROP | RX_L2_ERR)
+
+#define SGMII_SPEED_1000 0x08
+#define SGMII_SPEED_100 0x07
+#define SGMII_SPEED_10 0x06
+#define MII_SPEED_100 0x01
+#define MII_SPEED_10 0x00
+
+#define GE_DUPLEX_FULL BIT(0)
+#define GE_DUPLEX_HALF 0x00
+#define GE_MODE_CHANGE_EN BIT(0)
+
+#define GE_TX_AUTO_NEG BIT(5)
+#define GE_TX_ADD_CRC BIT(6)
+#define GE_TX_SHORT_PAD_THROUGH BIT(7)
+
+#define GE_RX_STRIP_CRC BIT(0)
+#define GE_RX_STRIP_PAD BIT(3)
+#define GE_RX_PAD_EN BIT(4)
+
+#define GE_AUTO_NEG_CTL BIT(0)
+
+#define GE_RX_INT_THRESHOLD BIT(6)
+#define GE_RX_TIMEOUT 0x04
+
+#define GE_RX_PORT_EN BIT(1)
+#define GE_TX_PORT_EN BIT(2)
+
+#define PPE_CFG_STS_RX_PKT_CNT_RC BIT(12)
+
+#define PPE_CFG_RX_PKT_ALIGN BIT(18)
+#define PPE_CFG_QOS_VMID_MODE BIT(14)
+#define PPE_CFG_QOS_VMID_GRP_SHIFT 8
+
+#define PPE_CFG_RX_FIFO_FSFU BIT(11)
+#define PPE_CFG_RX_DEPTH_SHIFT 16
+#define PPE_CFG_RX_START_SHIFT 0
+#define PPE_CFG_RX_CTRL_ALIGN_SHIFT 11
+
+#define PPE_CFG_BUS_LOCAL_REL BIT(14)
+#define PPE_CFG_BUS_BIG_ENDIEN BIT(0)
+
+#define RX_DESC_NUM 128
+#define TX_DESC_NUM 256
+#define TX_NEXT(N) (((N) + 1) & (TX_DESC_NUM-1))
+#define RX_NEXT(N) (((N) + 1) & (RX_DESC_NUM-1))
+
+#define GMAC_PPE_RX_PKT_MAX_LEN 379
+#define GMAC_MAX_PKT_LEN 1516
+#define GMAC_MIN_PKT_LEN 31
+#define RX_BUF_SIZE 1600
+#define RESET_TIMEOUT 1000
+#define TX_TIMEOUT (6 * HZ)
+
+#define DRV_NAME "hip04-ether"
+#define DRV_VERSION "v1.0"
+
+#define HIP04_MAX_TX_COALESCE_USECS 200
+#define HIP04_MIN_TX_COALESCE_USECS 100
+#define HIP04_MAX_TX_COALESCE_FRAMES 200
+#define HIP04_MIN_TX_COALESCE_FRAMES 100
+
+struct tx_desc {
+ u32 send_addr;
+ u32 send_size;
+ u32 next_addr;
+ u32 cfg;
+ u32 wb_addr;
+} __aligned(64);
+
+struct rx_desc {
+ u16 reserved_16;
+ u16 pkt_len;
+ u32 reserve1[3];
+ u32 pkt_err;
+ u32 reserve2[4];
+};
+
+struct hip04_priv {
+ void __iomem *base;
+ int phy_mode;
+ int chan;
+ unsigned int port;
+ unsigned int speed;
+ unsigned int duplex;
+ unsigned int reg_inten;
+
+ struct napi_struct napi;
+ struct net_device *ndev;
+
+ struct tx_desc *tx_desc;
+ dma_addr_t tx_desc_dma;
+ struct sk_buff *tx_skb[TX_DESC_NUM];
+ dma_addr_t tx_phys[TX_DESC_NUM];
+ unsigned int tx_head;
+
+ int tx_coalesce_frames;
+ int tx_coalesce_usecs;
+ struct hrtimer tx_coalesce_timer;
+
+ unsigned char *rx_buf[RX_DESC_NUM];
+ dma_addr_t rx_phys[RX_DESC_NUM];
+ unsigned int rx_head;
+ unsigned int rx_buf_size;
+
+ struct device_node *phy_node;
+ struct phy_device *phy;
+ struct regmap *map;
+ struct work_struct tx_timeout_task;
+
+ /* written only by tx cleanup */
+ unsigned int tx_tail ____cacheline_aligned_in_smp;
+};
+
+static inline unsigned int tx_count(unsigned int head, unsigned int tail)
+{
+ return (head - tail) % (TX_DESC_NUM - 1);
+}
+
+static void hip04_config_port(struct net_device *ndev, u32 speed, u32 duplex)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ u32 val;
+
+ priv->speed = speed;
+ priv->duplex = duplex;
+
+ switch (priv->phy_mode) {
+ case PHY_INTERFACE_MODE_SGMII:
+ if (speed == SPEED_1000)
+ val = SGMII_SPEED_1000;
+ else if (speed == SPEED_100)
+ val = SGMII_SPEED_100;
+ else
+ val = SGMII_SPEED_10;
+ break;
+ case PHY_INTERFACE_MODE_MII:
+ if (speed == SPEED_100)
+ val = MII_SPEED_100;
+ else
+ val = MII_SPEED_10;
+ break;
+ default:
+ netdev_warn(ndev, "not supported mode\n");
+ val = MII_SPEED_10;
+ break;
+ }
+ writel_relaxed(val, priv->base + GE_PORT_MODE);
+
+ val = duplex ? GE_DUPLEX_FULL : GE_DUPLEX_HALF;
+ writel_relaxed(val, priv->base + GE_DUPLEX_TYPE);
+
+ val = GE_MODE_CHANGE_EN;
+ writel_relaxed(val, priv->base + GE_MODE_CHANGE_REG);
+}
+
+static void hip04_reset_ppe(struct hip04_priv *priv)
+{
+ u32 val, tmp, timeout = 0;
+
+ do {
+ regmap_read(priv->map, priv->port * 4 + PPE_CURR_BUF_CNT, &val);
+ regmap_read(priv->map, priv->port * 4 + PPE_CFG_RX_ADDR, &tmp);
+ if (timeout++ > RESET_TIMEOUT)
+ break;
+ } while (val & 0xfff);
+}
+
+static void hip04_config_fifo(struct hip04_priv *priv)
+{
+ u32 val;
+
+ val = readl_relaxed(priv->base + PPE_CFG_STS_MODE);
+ val |= PPE_CFG_STS_RX_PKT_CNT_RC;
+ writel_relaxed(val, priv->base + PPE_CFG_STS_MODE);
+
+ val = BIT(priv->port);
+ regmap_write(priv->map, priv->port * 4 + PPE_CFG_POOL_GRP, val);
+
+ val = priv->port << PPE_CFG_QOS_VMID_GRP_SHIFT;
+ val |= PPE_CFG_QOS_VMID_MODE;
+ writel_relaxed(val, priv->base + PPE_CFG_QOS_VMID_GEN);
+
+ val = RX_BUF_SIZE;
+ regmap_write(priv->map, priv->port * 4 + PPE_CFG_RX_BUF_SIZE, val);
+
+ val = RX_DESC_NUM << PPE_CFG_RX_DEPTH_SHIFT;
+ val |= PPE_CFG_RX_FIFO_FSFU;
+ val |= priv->chan << PPE_CFG_RX_START_SHIFT;
+ regmap_write(priv->map, priv->port * 4 + PPE_CFG_RX_FIFO_SIZE, val);
+
+ val = NET_IP_ALIGN << PPE_CFG_RX_CTRL_ALIGN_SHIFT;
+ writel_relaxed(val, priv->base + PPE_CFG_RX_CTRL_REG);
+
+ val = PPE_CFG_RX_PKT_ALIGN;
+ writel_relaxed(val, priv->base + PPE_CFG_RX_PKT_MODE_REG);
+
+ val = PPE_CFG_BUS_LOCAL_REL | PPE_CFG_BUS_BIG_ENDIEN;
+ writel_relaxed(val, priv->base + PPE_CFG_BUS_CTRL_REG);
+
+ val = GMAC_PPE_RX_PKT_MAX_LEN;
+ writel_relaxed(val, priv->base + PPE_CFG_MAX_FRAME_LEN_REG);
+
+ val = GMAC_MAX_PKT_LEN;
+ writel_relaxed(val, priv->base + GE_MAX_FRM_SIZE_REG);
+
+ val = GMAC_MIN_PKT_LEN;
+ writel_relaxed(val, priv->base + GE_SHORT_RUNTS_THR_REG);
+
+ val = readl_relaxed(priv->base + GE_TRANSMIT_CONTROL_REG);
+ val |= GE_TX_AUTO_NEG | GE_TX_ADD_CRC | GE_TX_SHORT_PAD_THROUGH;
+ writel_relaxed(val, priv->base + GE_TRANSMIT_CONTROL_REG);
+
+ val = GE_RX_STRIP_CRC;
+ writel_relaxed(val, priv->base + GE_CF_CRC_STRIP_REG);
+
+ val = readl_relaxed(priv->base + GE_RECV_CONTROL_REG);
+ val |= GE_RX_STRIP_PAD | GE_RX_PAD_EN;
+ writel_relaxed(val, priv->base + GE_RECV_CONTROL_REG);
+
+ val = GE_AUTO_NEG_CTL;
+ writel_relaxed(val, priv->base + GE_TX_LOCAL_PAGE_REG);
+}
+
+static void hip04_mac_enable(struct net_device *ndev)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ u32 val;
+
+ /* enable tx & rx */
+ val = readl_relaxed(priv->base + GE_PORT_EN);
+ val |= GE_RX_PORT_EN | GE_TX_PORT_EN;
+ writel_relaxed(val, priv->base + GE_PORT_EN);
+
+ /* clear rx int */
+ val = RCV_INT;
+ writel_relaxed(val, priv->base + PPE_RINT);
+
+ /* config recv int */
+ val = GE_RX_INT_THRESHOLD | GE_RX_TIMEOUT;
+ writel_relaxed(val, priv->base + PPE_CFG_RX_PKT_INT);
+
+ /* enable interrupt */
+ priv->reg_inten = DEF_INT_MASK;
+ writel_relaxed(priv->reg_inten, priv->base + PPE_INTEN);
+}
+
+static void hip04_mac_disable(struct net_device *ndev)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ u32 val;
+
+ /* disable int */
+ priv->reg_inten &= ~(DEF_INT_MASK);
+ writel_relaxed(priv->reg_inten, priv->base + PPE_INTEN);
+
+ /* disable tx & rx */
+ val = readl_relaxed(priv->base + GE_PORT_EN);
+ val &= ~(GE_RX_PORT_EN | GE_TX_PORT_EN);
+ writel_relaxed(val, priv->base + GE_PORT_EN);
+}
+
+static void hip04_set_xmit_desc(struct hip04_priv *priv, dma_addr_t phys)
+{
+ writel(phys, priv->base + PPE_CFG_CPU_ADD_ADDR);
+}
+
+static void hip04_set_recv_desc(struct hip04_priv *priv, dma_addr_t phys)
+{
+ regmap_write(priv->map, priv->port * 4 + PPE_CFG_RX_ADDR, phys);
+}
+
+static u32 hip04_recv_cnt(struct hip04_priv *priv)
+{
+ return readl(priv->base + PPE_HIS_RX_PKT_CNT);
+}
+
+static void hip04_update_mac_address(struct net_device *ndev)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+
+ writel_relaxed(((ndev->dev_addr[0] << 8) | (ndev->dev_addr[1])),
+ priv->base + GE_STATION_MAC_ADDRESS);
+ writel_relaxed(((ndev->dev_addr[2] << 24) | (ndev->dev_addr[3] << 16) |
+ (ndev->dev_addr[4] << 8) | (ndev->dev_addr[5])),
+ priv->base + GE_STATION_MAC_ADDRESS + 4);
+}
+
+static int hip04_set_mac_address(struct net_device *ndev, void *addr)
+{
+ eth_mac_addr(ndev, addr);
+ hip04_update_mac_address(ndev);
+ return 0;
+}
+
+static int hip04_tx_reclaim(struct net_device *ndev, bool force)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ unsigned tx_tail = priv->tx_tail;
+ struct tx_desc *desc;
+ unsigned int bytes_compl = 0, pkts_compl = 0;
+ unsigned int count;
+
+ smp_rmb();
+ count = tx_count(ACCESS_ONCE(priv->tx_head), tx_tail);
+ if (count == 0)
+ goto out;
+
+ while (count) {
+ desc = &priv->tx_desc[tx_tail];
+ if (desc->send_addr != 0) {
+ if (force)
+ desc->send_addr = 0;
+ else
+ break;
+ }
+
+ if (priv->tx_phys[tx_tail]) {
+ dma_unmap_single(&ndev->dev, priv->tx_phys[tx_tail],
+ priv->tx_skb[tx_tail]->len,
+ DMA_TO_DEVICE);
+ priv->tx_phys[tx_tail] = 0;
+ }
+ pkts_compl++;
+ bytes_compl += priv->tx_skb[tx_tail]->len;
+ dev_kfree_skb(priv->tx_skb[tx_tail]);
+ priv->tx_skb[tx_tail] = NULL;
+ tx_tail = TX_NEXT(tx_tail);
+ count--;
+ }
+
+ priv->tx_tail = tx_tail;
+ smp_wmb(); /* Ensure tx_tail visible to xmit */
+
+out:
+ if (pkts_compl || bytes_compl)
+ netdev_completed_queue(ndev, pkts_compl, bytes_compl);
+
+ if (unlikely(netif_queue_stopped(ndev)) && (count < (TX_DESC_NUM - 1)))
+ netif_wake_queue(ndev);
+
+ return count;
+}
+
+static int hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ struct net_device_stats *stats = &ndev->stats;
+ unsigned int tx_head = priv->tx_head, count;
+ struct tx_desc *desc = &priv->tx_desc[tx_head];
+ dma_addr_t phys;
+
+ smp_rmb();
+ count = tx_count(tx_head, ACCESS_ONCE(priv->tx_tail));
+ if (count == (TX_DESC_NUM - 1)) {
+ netif_stop_queue(ndev);
+ return NETDEV_TX_BUSY;
+ }
+
+ phys = dma_map_single(&ndev->dev, skb->data, skb->len, DMA_TO_DEVICE);
+ if (dma_mapping_error(&ndev->dev, phys)) {
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+
+ priv->tx_skb[tx_head] = skb;
+ priv->tx_phys[tx_head] = phys;
+ desc->send_addr = cpu_to_be32(phys);
+ desc->send_size = cpu_to_be32(skb->len);
+ desc->cfg = cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV);
+ phys = priv->tx_desc_dma + tx_head * sizeof(struct tx_desc);
+ desc->wb_addr = cpu_to_be32(phys);
+ skb_tx_timestamp(skb);
+
+ hip04_set_xmit_desc(priv, phys);
+ priv->tx_head = TX_NEXT(tx_head);
+ count++;
+ netdev_sent_queue(ndev, skb->len);
+
+ stats->tx_bytes += skb->len;
+ stats->tx_packets++;
+
+ /* Ensure tx_head update visible to tx reclaim */
+ smp_wmb();
+
+ /* queue is getting full, better start cleaning up now */
+ if (count >= priv->tx_coalesce_frames) {
+ if (napi_schedule_prep(&priv->napi)) {
+ /* disable rx interrupt and timer */
+ priv->reg_inten &= ~(RCV_INT);
+ writel_relaxed(DEF_INT_MASK & ~RCV_INT,
+ priv->base + PPE_INTEN);
+ hrtimer_cancel(&priv->tx_coalesce_timer);
+ __napi_schedule(&priv->napi);
+ }
+ } else if (!hrtimer_is_queued(&priv->tx_coalesce_timer)) {
+ /* cleanup not pending yet, start a new timer */
+ hrtimer_start_expires(&priv->tx_coalesce_timer,
+ HRTIMER_MODE_REL);
+ }
+
+ return NETDEV_TX_OK;
+}
+
+static int hip04_rx_poll(struct napi_struct *napi, int budget)
+{
+ struct hip04_priv *priv = container_of(napi, struct hip04_priv, napi);
+ struct net_device *ndev = priv->ndev;
+ struct net_device_stats *stats = &ndev->stats;
+ unsigned int cnt = hip04_recv_cnt(priv);
+ struct rx_desc *desc;
+ struct sk_buff *skb;
+ unsigned char *buf;
+ bool last = false;
+ dma_addr_t phys;
+ int rx = 0;
+ int tx_remaining;
+ u16 len;
+ u32 err;
+
+ while (cnt && !last) {
+ buf = priv->rx_buf[priv->rx_head];
+ skb = build_skb(buf, priv->rx_buf_size);
+ if (unlikely(!skb))
+ net_dbg_ratelimited("build_skb failed\n");
+
+ dma_unmap_single(&ndev->dev, priv->rx_phys[priv->rx_head],
+ RX_BUF_SIZE, DMA_FROM_DEVICE);
+ priv->rx_phys[priv->rx_head] = 0;
+
+ desc = (struct rx_desc *)skb->data;
+ len = be16_to_cpu(desc->pkt_len);
+ err = be32_to_cpu(desc->pkt_err);
+
+ if (0 == len) {
+ dev_kfree_skb_any(skb);
+ last = true;
+ } else if ((err & RX_PKT_ERR) || (len >= GMAC_MAX_PKT_LEN)) {
+ dev_kfree_skb_any(skb);
+ stats->rx_dropped++;
+ stats->rx_errors++;
+ } else {
+ skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+ skb_put(skb, len);
+ skb->protocol = eth_type_trans(skb, ndev);
+ napi_gro_receive(&priv->napi, skb);
+ stats->rx_packets++;
+ stats->rx_bytes += len;
+ rx++;
+ }
+
+ buf = netdev_alloc_frag(priv->rx_buf_size);
+ if (!buf)
+ goto done;
+ phys = dma_map_single(&ndev->dev, buf,
+ RX_BUF_SIZE, DMA_FROM_DEVICE);
+ if (dma_mapping_error(&ndev->dev, phys))
+ goto done;
+ priv->rx_buf[priv->rx_head] = buf;
+ priv->rx_phys[priv->rx_head] = phys;
+ hip04_set_recv_desc(priv, phys);
+
+ priv->rx_head = RX_NEXT(priv->rx_head);
+ if (rx >= budget)
+ goto done;
+
+ if (--cnt == 0)
+ cnt = hip04_recv_cnt(priv);
+ }
+
+ if (!(priv->reg_inten & RCV_INT)) {
+ /* enable rx interrupt */
+ priv->reg_inten |= RCV_INT;
+ writel_relaxed(priv->reg_inten, priv->base + PPE_INTEN);
+ }
+ napi_complete(napi);
+done:
+ /* clean up tx descriptors and start a new timer if necessary */
+ tx_remaining = hip04_tx_reclaim(ndev, false);
+ if (rx < budget && tx_remaining)
+ hrtimer_start_expires(&priv->tx_coalesce_timer, HRTIMER_MODE_REL);
+
+ return rx;
+}
+
+static irqreturn_t hip04_mac_interrupt(int irq, void *dev_id)
+{
+ struct net_device *ndev = (struct net_device *)dev_id;
+ struct hip04_priv *priv = netdev_priv(ndev);
+ struct net_device_stats *stats = &ndev->stats;
+ u32 ists = readl_relaxed(priv->base + PPE_INTSTS);
+
+ if (!ists)
+ return IRQ_NONE;
+
+ writel_relaxed(DEF_INT_MASK, priv->base + PPE_RINT);
+
+ if (unlikely(ists & DEF_INT_ERR)) {
+ if (ists & (RCV_NOBUF | RCV_DROP))
+ stats->rx_errors++;
+ stats->rx_dropped++;
+ netdev_err(ndev, "rx drop\n");
+ if (ists & TX_DROP) {
+ stats->tx_dropped++;
+ netdev_err(ndev, "tx drop\n");
+ }
+ }
+
+ if (ists & RCV_INT && napi_schedule_prep(&priv->napi)) {
+ /* disable rx interrupt */
+ priv->reg_inten &= ~(RCV_INT);
+ writel_relaxed(DEF_INT_MASK & ~RCV_INT, priv->base + PPE_INTEN);
+ hrtimer_cancel(&priv->tx_coalesce_timer);
+ __napi_schedule(&priv->napi);
+ }
+
+ return IRQ_HANDLED;
+}
+
+enum hrtimer_restart tx_done(struct hrtimer *hrtimer)
+{
+ struct hip04_priv *priv;
+
+ priv = container_of(hrtimer, struct hip04_priv, tx_coalesce_timer);
+
+ if (napi_schedule_prep(&priv->napi)) {
+ /* disable rx interrupt */
+ priv->reg_inten &= ~(RCV_INT);
+ writel_relaxed(DEF_INT_MASK & ~RCV_INT, priv->base + PPE_INTEN);
+ __napi_schedule(&priv->napi);
+ }
+
+ return HRTIMER_NORESTART;
+}
+
+static void hip04_adjust_link(struct net_device *ndev)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ struct phy_device *phy = priv->phy;
+
+ if ((priv->speed != phy->speed) || (priv->duplex != phy->duplex)) {
+ hip04_config_port(ndev, phy->speed, phy->duplex);
+ phy_print_status(phy);
+ }
+}
+
+static int hip04_mac_open(struct net_device *ndev)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ int i;
+
+ priv->rx_head = 0;
+ priv->tx_head = 0;
+ priv->tx_tail = 0;
+ hip04_reset_ppe(priv);
+
+ for (i = 0; i < RX_DESC_NUM; i++) {
+ dma_addr_t phys;
+
+ phys = dma_map_single(&ndev->dev, priv->rx_buf[i],
+ RX_BUF_SIZE, DMA_FROM_DEVICE);
+ if (dma_mapping_error(&ndev->dev, phys))
+ return -EIO;
+
+ priv->rx_phys[i] = phys;
+ hip04_set_recv_desc(priv, phys);
+ }
+
+ if (priv->phy)
+ phy_start(priv->phy);
+
+ netdev_reset_queue(ndev);
+ netif_start_queue(ndev);
+ hip04_mac_enable(ndev);
+ napi_enable(&priv->napi);
+
+ return 0;
+}
+
+static int hip04_mac_stop(struct net_device *ndev)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ int i;
+
+ napi_disable(&priv->napi);
+ netif_stop_queue(ndev);
+ hip04_mac_disable(ndev);
+ hip04_tx_reclaim(ndev, true);
+ hip04_reset_ppe(priv);
+
+ if (priv->phy)
+ phy_stop(priv->phy);
+
+ for (i = 0; i < RX_DESC_NUM; i++) {
+ if (priv->rx_phys[i]) {
+ dma_unmap_single(&ndev->dev, priv->rx_phys[i],
+ RX_BUF_SIZE, DMA_FROM_DEVICE);
+ priv->rx_phys[i] = 0;
+ }
+ }
+
+ return 0;
+}
+
+static void hip04_timeout(struct net_device *ndev)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+
+ schedule_work(&priv->tx_timeout_task);
+}
+
+static void hip04_tx_timeout_task(struct work_struct *work)
+{
+ struct hip04_priv *priv;
+
+ priv = container_of(work, struct hip04_priv, tx_timeout_task);
+ hip04_mac_stop(priv->ndev);
+ hip04_mac_open(priv->ndev);
+}
+
+static struct net_device_stats *hip04_get_stats(struct net_device *ndev)
+{
+ return &ndev->stats;
+}
+
+static int hip04_get_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec)
+{
+ struct hip04_priv *priv = netdev_priv(netdev);
+
+ ec->tx_coalesce_usecs = priv->tx_coalesce_usecs;
+ ec->tx_max_coalesced_frames = priv->tx_coalesce_frames;
+
+ return 0;
+}
+
+static int hip04_set_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec)
+{
+ struct hip04_priv *priv = netdev_priv(netdev);
+
+ /* Check not supported parameters */
+ if ((ec->rx_max_coalesced_frames) || (ec->rx_coalesce_usecs_irq) ||
+ (ec->rx_max_coalesced_frames_irq) || (ec->tx_coalesce_usecs_irq) ||
+ (ec->use_adaptive_rx_coalesce) || (ec->use_adaptive_tx_coalesce) ||
+ (ec->pkt_rate_low) || (ec->rx_coalesce_usecs_low) ||
+ (ec->rx_max_coalesced_frames_low) || (ec->tx_coalesce_usecs_high) ||
+ (ec->tx_max_coalesced_frames_low) || (ec->pkt_rate_high) ||
+ (ec->tx_coalesce_usecs_low) || (ec->rx_coalesce_usecs_high) ||
+ (ec->rx_max_coalesced_frames_high) || (ec->rx_coalesce_usecs) ||
+ (ec->tx_max_coalesced_frames_irq) ||
+ (ec->stats_block_coalesce_usecs) ||
+ (ec->tx_max_coalesced_frames_high) || (ec->rate_sample_interval))
+ return -EOPNOTSUPP;
+
+ if ((ec->tx_coalesce_usecs > HIP04_MAX_TX_COALESCE_USECS ||
+ ec->tx_coalesce_usecs < HIP04_MIN_TX_COALESCE_USECS) ||
+ (ec->tx_max_coalesced_frames > HIP04_MAX_TX_COALESCE_FRAMES ||
+ ec->tx_max_coalesced_frames < HIP04_MIN_TX_COALESCE_FRAMES))
+ return -EINVAL;
+
+ priv->tx_coalesce_usecs = ec->tx_coalesce_usecs;
+ priv->tx_coalesce_frames = ec->tx_max_coalesced_frames;
+
+ return 0;
+}
+
+static void hip04_get_drvinfo(struct net_device *netdev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
+}
+
+static struct ethtool_ops hip04_ethtool_ops = {
+ .get_coalesce = hip04_get_coalesce,
+ .set_coalesce = hip04_set_coalesce,
+ .get_drvinfo = hip04_get_drvinfo,
+};
+
+static struct net_device_ops hip04_netdev_ops = {
+ .ndo_open = hip04_mac_open,
+ .ndo_stop = hip04_mac_stop,
+ .ndo_get_stats = hip04_get_stats,
+ .ndo_start_xmit = hip04_mac_start_xmit,
+ .ndo_set_mac_address = hip04_set_mac_address,
+ .ndo_tx_timeout = hip04_timeout,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = eth_change_mtu,
+};
+
+static int hip04_alloc_ring(struct net_device *ndev, struct device *d)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ int i;
+
+ priv->tx_desc = dma_alloc_coherent(d,
+ TX_DESC_NUM * sizeof(struct tx_desc),
+ &priv->tx_desc_dma, GFP_KERNEL);
+ if (!priv->tx_desc)
+ return -ENOMEM;
+
+ priv->rx_buf_size = RX_BUF_SIZE +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ for (i = 0; i < RX_DESC_NUM; i++) {
+ priv->rx_buf[i] = netdev_alloc_frag(priv->rx_buf_size);
+ if (!priv->rx_buf[i])
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void hip04_free_ring(struct net_device *ndev, struct device *d)
+{
+ struct hip04_priv *priv = netdev_priv(ndev);
+ int i;
+
+ for (i = 0; i < RX_DESC_NUM; i++)
+ if (priv->rx_buf[i])
+ put_page(virt_to_head_page(priv->rx_buf[i]));
+
+ for (i = 0; i < TX_DESC_NUM; i++)
+ if (priv->tx_skb[i])
+ dev_kfree_skb_any(priv->tx_skb[i]);
+
+ dma_free_coherent(d, TX_DESC_NUM * sizeof(struct tx_desc),
+ priv->tx_desc, priv->tx_desc_dma);
+}
+
+static int hip04_mac_probe(struct platform_device *pdev)
+{
+ struct device *d = &pdev->dev;
+ struct device_node *node = d->of_node;
+ struct of_phandle_args arg;
+ struct net_device *ndev;
+ struct hip04_priv *priv;
+ struct resource *res;
+ unsigned int irq;
+ ktime_t txtime;
+ int ret;
+
+ ndev = alloc_etherdev(sizeof(struct hip04_priv));
+ if (!ndev)
+ return -ENOMEM;
+
+ priv = netdev_priv(ndev);
+ priv->ndev = ndev;
+ platform_set_drvdata(pdev, ndev);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ priv->base = devm_ioremap_resource(d, res);
+ if (IS_ERR(priv->base)) {
+ ret = PTR_ERR(priv->base);
+ goto init_fail;
+ }
+
+ ret = of_parse_phandle_with_fixed_args(node, "port-handle", 2, 0, &arg);
+ if (ret < 0) {
+ dev_warn(d, "no port-handle\n");
+ goto init_fail;
+ }
+
+ priv->port = arg.args[0];
+ priv->chan = arg.args[1] * RX_DESC_NUM;
+
+ hrtimer_init(&priv->tx_coalesce_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+
+ /* BQL will try to keep the TX queue as short as possible, but it can't
+ * be faster than tx_coalesce_usecs, so we need a fast timeout here,
+ * but also long enough to gather up enough frames to ensure we don't
+ * get more interrupts than necessary.
+ * 200us is enough for 16 frames of 1500 bytes at gigabit ethernet rate
+ */
+ priv->tx_coalesce_frames = TX_DESC_NUM * 3 / 4;
+ priv->tx_coalesce_usecs = 200;
+ /* allow timer to fire after half the time at the earliest */
+ txtime = ktime_set(0, priv->tx_coalesce_usecs * NSEC_PER_USEC / 2);
+ hrtimer_set_expires_range(&priv->tx_coalesce_timer, txtime, txtime);
+ priv->tx_coalesce_timer.function = tx_done;
+
+ priv->map = syscon_node_to_regmap(arg.np);
+ if (IS_ERR(priv->map)) {
+ dev_warn(d, "no syscon hisilicon,hip04-ppe\n");
+ ret = PTR_ERR(priv->map);
+ goto init_fail;
+ }
+
+ priv->phy_mode = of_get_phy_mode(node);
+ if (priv->phy_mode < 0) {
+ dev_warn(d, "not find phy-mode\n");
+ ret = -EINVAL;
+ goto init_fail;
+ }
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq <= 0) {
+ ret = -EINVAL;
+ goto init_fail;
+ }
+
+ ret = devm_request_irq(d, irq, hip04_mac_interrupt,
+ 0, pdev->name, ndev);
+ if (ret) {
+ netdev_err(ndev, "devm_request_irq failed\n");
+ goto init_fail;
+ }
+
+ priv->phy_node = of_parse_phandle(node, "phy-handle", 0);
+ if (priv->phy_node) {
+ priv->phy = of_phy_connect(ndev, priv->phy_node,
+ &hip04_adjust_link,
+ 0, priv->phy_mode);
+ if (!priv->phy) {
+ ret = -EPROBE_DEFER;
+ goto init_fail;
+ }
+ }
+
+ INIT_WORK(&priv->tx_timeout_task, hip04_tx_timeout_task);
+
+ ether_setup(ndev);
+ ndev->netdev_ops = &hip04_netdev_ops;
+ ndev->ethtool_ops = &hip04_ethtool_ops;
+ ndev->watchdog_timeo = TX_TIMEOUT;
+ ndev->priv_flags |= IFF_UNICAST_FLT;
+ ndev->irq = irq;
+ netif_napi_add(ndev, &priv->napi, hip04_rx_poll, NAPI_POLL_WEIGHT);
+ SET_NETDEV_DEV(ndev, &pdev->dev);
+
+ hip04_reset_ppe(priv);
+ if (priv->phy_mode == PHY_INTERFACE_MODE_MII)
+ hip04_config_port(ndev, SPEED_100, DUPLEX_FULL);
+
+ hip04_config_fifo(priv);
+ random_ether_addr(ndev->dev_addr);
+ hip04_update_mac_address(ndev);
+
+ ret = hip04_alloc_ring(ndev, d);
+ if (ret) {
+ netdev_err(ndev, "alloc ring fail\n");
+ goto alloc_fail;
+ }
+
+ ret = register_netdev(ndev);
+ if (ret) {
+ free_netdev(ndev);
+ goto alloc_fail;
+ }
+
+ return 0;
+
+alloc_fail:
+ hip04_free_ring(ndev, d);
+init_fail:
+ of_node_put(priv->phy_node);
+ free_netdev(ndev);
+ return ret;
+}
+
+static int hip04_remove(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct hip04_priv *priv = netdev_priv(ndev);
+ struct device *d = &pdev->dev;
+
+ if (priv->phy)
+ phy_disconnect(priv->phy);
+
+ hip04_free_ring(ndev, d);
+ unregister_netdev(ndev);
+ free_irq(ndev->irq, ndev);
+ of_node_put(priv->phy_node);
+ cancel_work_sync(&priv->tx_timeout_task);
+ free_netdev(ndev);
+
+ return 0;
+}
+
+static const struct of_device_id hip04_mac_match[] = {
+ { .compatible = "hisilicon,hip04-mac" },
+ { }
+};
+
+MODULE_DEVICE_TABLE(of, hip04_mac_match);
+
+static struct platform_driver hip04_mac_driver = {
+ .probe = hip04_mac_probe,
+ .remove = hip04_remove,
+ .driver = {
+ .name = DRV_NAME,
+ .owner = THIS_MODULE,
+ .of_match_table = hip04_mac_match,
+ },
+};
+module_platform_driver(hip04_mac_driver);
+
+MODULE_DESCRIPTION("HISILICON P04 Ethernet driver");
--
1.8.0
^ permalink raw reply related
* Re: net_test_tools: add ipv6 support for kbench_mod
From: David Miller @ 2015-01-14 6:35 UTC (permalink / raw)
To: shli; +Cc: netdev, kafai
In-Reply-To: <20150114054548.GA2683397@devbig257.prn2.facebook.com>
From: Shaohua Li <shli@fb.com>
Date: Tue, 13 Jan 2015 21:45:48 -0800
> This patch adds ipv6 support for kbench_mod test module
This doesn't even link because ip6_route_input is not an
exported symbol.
So you either didn't test this, or it depends upon custom
kernel changes which you didn't mention.
Either way I can't apply this, sorry.
^ permalink raw reply
* [PATCH net-next v13 0/3] add hisilicon hip04 ethernet driver
From: Ding Tianhong @ 2015-01-14 6:34 UTC (permalink / raw)
To: arnd, robh+dt, davem, grant.likely, agraf
Cc: sergei.shtylyov, linux-arm-kernel, eric.dumazet, xuwei5,
zhangfei.gao, netdev, devicetree, linux
v13:
- Fix the problem of alignment parameters for function and checkpatch warming.
v12:
- According Alex's suggestion, modify the changelog and add MODULE_DEVICE_TABLE
for hip04 ethernet.
v11:
- Add ethtool support for tx coalecse getting and setting, the xmit_more
is not supported for this patch, but I think it could work for hip04,
will support it later after some tests for performance better.
Here are some performance test results by ping and iperf(add tx_coalesce_frames/users),
it looks that the performance and latency is more better by tx_coalesce_frames/usecs.
- Before:
$ ping 192.168.1.1 ...
=== 192.168.1.1 ping statistics ===
24 packets transmitted, 24 received, 0% packet loss, time 22999ms
rtt min/avg/max/mdev = 0.180/0.202/0.403/0.043 ms
$ iperf -c 192.168.1.1 ...
[ ID] Interval Transfer Bandwidth
[ 3] 0.0- 1.0 sec 115 MBytes 945 Mbits/sec
- After:
$ ping 192.168.1.1 ...
=== 192.168.1.1 ping statistics ===
24 packets transmitted, 24 received, 0% packet loss, time 22999ms
rtt min/avg/max/mdev = 0.178/0.190/0.380/0.041 ms
$ iperf -c 192.168.1.1 ...
[ ID] Interval Transfer Bandwidth
[ 3] 0.0- 1.0 sec 115 MBytes 965 Mbits/sec
v10:
- According Arnd's suggestion, remove the skb_orphan and use the hrtimer
for the cleanup of the TX queue and add some modification for the hip04
drivers.
1) drop the broken skb_orphan call
2) drop the workqueue
3) batch cleanup based on tx_coalesce_frames/usecs for better throughput
4) use a reasonable default tx timeout (200us, could be shorted
based on measurements) with a range timer
5) fix napi poll function return value
6) use a lockless queue for cleanup
v9:
- There is no tx completion interrupts to free DMAd Tx packets, it means taht
we rely on new tx packets arriving to run the destructors of completed packets,
which open up space in their sockets's send queues. Sometimes we don't get such
new packets causing Tx to stall, a single UDP transmitter is a good example of
this situation, so we need a clean up workqueue to reclaims completed packets,
the workqueue will only free the last packets which is already stay for several jiffies.
Also fix some format cleanups.
v8:
- Use poll to reclaim xmitted buffer as workaround since no tx done interrupt
v7:
- Remove select NET_CORE in 0002
v6:
- Suggest by Russell: Use netdev_sent_queue & netdev_completed_queue to solve latency issue
Also shorten the period of timer, which is used to wakeup the queue since no
tx completed interrupt.
v5:
- no big change, fix typo
v4:
- Modify accoringly to the suggetion from Arnd, Florian, Eric, David
Use of_parse_phandle_with_fixed_args & syscon_node_to_regmap get ppe info
Add skb_orphan() and tx_timer for reclaim since no tx_finished interrupt
Update timeout, and move of_phy_connect to probe to reuse open/stop
v3:
- Suggest from Arnd, use syscon & regmap_write/read to replace static void __iomem *ppebase.
Modify hisilicon-hip04-net.txt accrordingly to suggestion from Florian and Sergei.
v2:
- Got many suggestions from Russell, Arnd, Florian, Mark and Sergei
Remove memcpy, use dma_map/unmap_single, use dma_alloc_coherent rather than dma_pool, etc.
Refer property in ethernet.txt, change ppe description, etc.
Ding Tianhong (1):
net: hisilicon: new hip04 ethernet driver
Zhangfei Gao (2):
Documentation: add Device tree bindings for Hisilicon hip04 ethernet
net: hisilicon: new hip04 MDIO driver
.../bindings/net/hisilicon-hip04-net.txt | 88 ++
drivers/net/ethernet/hisilicon/Kconfig | 9 +
drivers/net/ethernet/hisilicon/Makefile | 1 +
drivers/net/ethernet/hisilicon/hip04_eth.c | 969 +++++++++++++++++++++
drivers/net/ethernet/hisilicon/hip04_mdio.c | 186 ++++
5 files changed, 1253 insertions(+)
create mode 100644 Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt
create mode 100644 drivers/net/ethernet/hisilicon/hip04_eth.c
create mode 100644 drivers/net/ethernet/hisilicon/hip04_mdio.c
--
1.8.0
^ permalink raw reply
* [PATCH net-next v13 2/3] net: hisilicon: new hip04 MDIO driver
From: Ding Tianhong @ 2015-01-14 6:34 UTC (permalink / raw)
To: arnd, robh+dt, davem, grant.likely, agraf
Cc: sergei.shtylyov, linux-arm-kernel, eric.dumazet, xuwei5,
zhangfei.gao, netdev, devicetree, linux
In-Reply-To: <1421217254-12008-1-git-send-email-dingtianhong@huawei.com>
From: Zhangfei Gao <zhangfei.gao@linaro.org>
Hisilicon hip04 platform mdio driver
Reuse Marvell phy drivers/net/phy/marvell.c
Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
drivers/net/ethernet/hisilicon/Kconfig | 9 ++
drivers/net/ethernet/hisilicon/Makefile | 1 +
drivers/net/ethernet/hisilicon/hip04_mdio.c | 186 ++++++++++++++++++++++++++++
3 files changed, 196 insertions(+)
create mode 100644 drivers/net/ethernet/hisilicon/hip04_mdio.c
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index e942173..a54d897 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -24,4 +24,13 @@ config HIX5HD2_GMAC
help
This selects the hix5hd2 mac family network device.
+config HIP04_ETH
+ tristate "HISILICON P04 Ethernet support"
+ select PHYLIB
+ select MARVELL_PHY
+ select MFD_SYSCON
+ ---help---
+ If you wish to compile a kernel for a hardware with hisilicon p04 SoC and
+ want to use the internal ethernet then you should answer Y to this.
+
endif # NET_VENDOR_HISILICON
diff --git a/drivers/net/ethernet/hisilicon/Makefile b/drivers/net/ethernet/hisilicon/Makefile
index 9175e846..40115a7 100644
--- a/drivers/net/ethernet/hisilicon/Makefile
+++ b/drivers/net/ethernet/hisilicon/Makefile
@@ -3,3 +3,4 @@
#
obj-$(CONFIG_HIX5HD2_GMAC) += hix5hd2_gmac.o
+obj-$(CONFIG_HIP04_ETH) += hip04_mdio.o
diff --git a/drivers/net/ethernet/hisilicon/hip04_mdio.c b/drivers/net/ethernet/hisilicon/hip04_mdio.c
new file mode 100644
index 0000000..b3bac25
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hip04_mdio.c
@@ -0,0 +1,186 @@
+/* Copyright (c) 2014 Linaro Ltd.
+ * Copyright (c) 2014 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/of_mdio.h>
+#include <linux/delay.h>
+
+#define MDIO_CMD_REG 0x0
+#define MDIO_ADDR_REG 0x4
+#define MDIO_WDATA_REG 0x8
+#define MDIO_RDATA_REG 0xc
+#define MDIO_STA_REG 0x10
+
+#define MDIO_START BIT(14)
+#define MDIO_R_VALID BIT(1)
+#define MDIO_READ (BIT(12) | BIT(11) | MDIO_START)
+#define MDIO_WRITE (BIT(12) | BIT(10) | MDIO_START)
+
+struct hip04_mdio_priv {
+ void __iomem *base;
+};
+
+#define WAIT_TIMEOUT 10
+static int hip04_mdio_wait_ready(struct mii_bus *bus)
+{
+ struct hip04_mdio_priv *priv = bus->priv;
+ int i;
+
+ for (i = 0; readl_relaxed(priv->base + MDIO_CMD_REG) & MDIO_START; i++) {
+ if (i == WAIT_TIMEOUT)
+ return -ETIMEDOUT;
+ msleep(20);
+ }
+
+ return 0;
+}
+
+static int hip04_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
+{
+ struct hip04_mdio_priv *priv = bus->priv;
+ u32 val;
+ int ret;
+
+ ret = hip04_mdio_wait_ready(bus);
+ if (ret < 0)
+ goto out;
+
+ val = regnum | (mii_id << 5) | MDIO_READ;
+ writel_relaxed(val, priv->base + MDIO_CMD_REG);
+
+ ret = hip04_mdio_wait_ready(bus);
+ if (ret < 0)
+ goto out;
+
+ val = readl_relaxed(priv->base + MDIO_STA_REG);
+ if (val & MDIO_R_VALID) {
+ dev_err(bus->parent, "SMI bus read not valid\n");
+ ret = -ENODEV;
+ goto out;
+ }
+
+ val = readl_relaxed(priv->base + MDIO_RDATA_REG);
+ ret = val & 0xFFFF;
+out:
+ return ret;
+}
+
+static int hip04_mdio_write(struct mii_bus *bus, int mii_id,
+ int regnum, u16 value)
+{
+ struct hip04_mdio_priv *priv = bus->priv;
+ u32 val;
+ int ret;
+
+ ret = hip04_mdio_wait_ready(bus);
+ if (ret < 0)
+ goto out;
+
+ writel_relaxed(value, priv->base + MDIO_WDATA_REG);
+ val = regnum | (mii_id << 5) | MDIO_WRITE;
+ writel_relaxed(val, priv->base + MDIO_CMD_REG);
+out:
+ return ret;
+}
+
+static int hip04_mdio_reset(struct mii_bus *bus)
+{
+ int temp, i;
+
+ for (i = 0; i < PHY_MAX_ADDR; i++) {
+ hip04_mdio_write(bus, i, 22, 0);
+ temp = hip04_mdio_read(bus, i, MII_BMCR);
+ if (temp < 0)
+ continue;
+
+ temp |= BMCR_RESET;
+ if (hip04_mdio_write(bus, i, MII_BMCR, temp) < 0)
+ continue;
+ }
+
+ mdelay(500);
+ return 0;
+}
+
+static int hip04_mdio_probe(struct platform_device *pdev)
+{
+ struct resource *r;
+ struct mii_bus *bus;
+ struct hip04_mdio_priv *priv;
+ int ret;
+
+ bus = mdiobus_alloc_size(sizeof(struct hip04_mdio_priv));
+ if (!bus) {
+ dev_err(&pdev->dev, "Cannot allocate MDIO bus\n");
+ return -ENOMEM;
+ }
+
+ bus->name = "hip04_mdio_bus";
+ bus->read = hip04_mdio_read;
+ bus->write = hip04_mdio_write;
+ bus->reset = hip04_mdio_reset;
+ snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(&pdev->dev));
+ bus->parent = &pdev->dev;
+ priv = bus->priv;
+
+ r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ priv->base = devm_ioremap_resource(&pdev->dev, r);
+ if (IS_ERR(priv->base)) {
+ ret = PTR_ERR(priv->base);
+ goto out_mdio;
+ }
+
+ ret = of_mdiobus_register(bus, pdev->dev.of_node);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "Cannot register MDIO bus (%d)\n", ret);
+ goto out_mdio;
+ }
+
+ platform_set_drvdata(pdev, bus);
+
+ return 0;
+
+out_mdio:
+ mdiobus_free(bus);
+ return ret;
+}
+
+static int hip04_mdio_remove(struct platform_device *pdev)
+{
+ struct mii_bus *bus = platform_get_drvdata(pdev);
+
+ mdiobus_unregister(bus);
+ mdiobus_free(bus);
+
+ return 0;
+}
+
+static const struct of_device_id hip04_mdio_match[] = {
+ { .compatible = "hisilicon,hip04-mdio" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, hip04_mdio_match);
+
+static struct platform_driver hip04_mdio_driver = {
+ .probe = hip04_mdio_probe,
+ .remove = hip04_mdio_remove,
+ .driver = {
+ .name = "hip04-mdio",
+ .owner = THIS_MODULE,
+ .of_match_table = hip04_mdio_match,
+ },
+};
+
+module_platform_driver(hip04_mdio_driver);
+
+MODULE_DESCRIPTION("HISILICON P04 MDIO interface driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:hip04-mdio");
--
1.8.0
^ permalink raw reply related
* [PATCH net-next] bridge: fix setlink/dellink notifications
From: roopa @ 2015-01-14 6:48 UTC (permalink / raw)
To: netdev, shemminger, vyasevic, john.fastabend, tgraf, jhs, sfeldma,
jiri
Cc: wkok
From: Roopa Prabhu <roopa@cumulusnetworks.com>
problems with bridge getlink/setlink notifications today:
- bridge setlink generates two notifications to userspace
- one from the bridge driver
- one from rtnetlink.c (rtnl_bridge_notify)
- dellink generates one notification from rtnetlink.c. Which
means bridge setlink and dellink notifications are not
consistent
- Looking at the code it appears,
If both BRIDGE_FLAGS_MASTER and BRIDGE_FLAGS_SELF were set,
the size calculation in rtnl_bridge_notify can be wrong.
Example: if you set both BRIDGE_FLAGS_MASTER and BRIDGE_FLAGS_SELF
in a setlink request to rocker dev, rtnl_bridge_notify will
allocate skb for one set of bridge attributes, but,
both the bridge driver and rocker dev will try to add
attributes resulting in twice the number of attributes
being added to the skb. (rocker dev calls ndo_dflt_bridge_getlink)
There are multiple options:
1) Generate one notification including all attributes from master and self:
But, I don't think it will work, because both master and self may use
the same attributes/policy. Cannot pack the same set of attributes in a
single notification from both master and slave (duplicate attributes).
2) Generate one notification from master and the other notification from
self (This seems to be ideal):
For master: the master driver will send notification (bridge in this
example)
For self: the self driver will send notification (rocker in the above
example. It can use helpers from rtnetlink.c to do so. Like the
ndo_dflt_bridge_getlink api).
This patch implements 2) (leaving the 'rtnl_bridge_notify' around to be used
with 'self').
CC'ing others who might be affected by this change for review.
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
net/bridge/br_netlink.c | 2 ++
net/core/rtnetlink.c | 32 ++++++++++++++++----------------
2 files changed, 18 insertions(+), 16 deletions(-)
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 9f5eb55..169783a 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -432,6 +432,8 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh)
err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
afspec, RTM_DELLINK);
+ if (err == 0)
+ br_ifinfo_notify(RTM_DELLINK, p);
return err;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d06107d..4ac79ff 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2876,13 +2876,6 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags)
goto errout;
}
- if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) &&
- br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
- err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0);
- if (err < 0)
- goto errout;
- }
-
if ((flags & BRIDGE_FLAGS_SELF) &&
dev->netdev_ops->ndo_bridge_getlink) {
err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0);
@@ -2958,16 +2951,19 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
err = -EOPNOTSUPP;
else
err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
-
- if (!err)
+ if (!err) {
flags &= ~BRIDGE_FLAGS_SELF;
+
+ /* Generate event to notify upper layer of bridge
+ * change
+ */
+ if (!err)
+ err = rtnl_bridge_notify(dev, oflags);
+ }
}
if (have_flags)
memcpy(nla_data(attr), &flags, sizeof(flags));
- /* Generate event to notify upper layer of bridge change */
- if (!err)
- err = rtnl_bridge_notify(dev, oflags);
out:
return err;
}
@@ -3032,15 +3028,19 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
else
err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh);
- if (!err)
+ if (!err) {
flags &= ~BRIDGE_FLAGS_SELF;
+
+ /* Generate event to notify upper layer of bridge
+ * change
+ */
+ err = rtnl_bridge_notify(dev, oflags);
+ }
+
}
if (have_flags)
memcpy(nla_data(attr), &flags, sizeof(flags));
- /* Generate event to notify upper layer of bridge change */
- if (!err)
- err = rtnl_bridge_notify(dev, oflags);
out:
return err;
}
--
1.7.10.4
^ permalink raw reply related
* [PATCH net 0/3]tg3: synchronize_irq() should be called without taking locks
From: Prashant Sreedharan @ 2015-01-14 6:30 UTC (permalink / raw)
To: davem; +Cc: netdev, mchan, peter, Prashant Sreedharan
Prashant Sreedharan (3):
tg3_timer() should grab tp->lock before checking for tp->irq_sync
tg3_reset_task() needs to use rtnl_lock to synchronize
Release tp->lock before invoking synchronize_irq()
Our QA team is validating this patch set, we need few days before merging
drivers/net/ethernet/broadcom/tg3.c | 23 ++++++++++++++++++++---
1 files changed, 20 insertions(+), 3 deletions(-)
^ permalink raw reply
* [PATCH net 1/3]tg3: tg3_timer() should grab tp->lock before checking for tp->irq_sync
From: Prashant Sreedharan @ 2015-01-14 6:31 UTC (permalink / raw)
To: davem; +Cc: netdev, peter, Prashant Sreedharan, Michael Chan
This is to avoid the race between tg3_timer() and the execution paths
which does not invoke tg3_timer_stop() and releases tp->lock before
calling synchronize_irq()
Signed-off-by: Prashant Sreedharan <prashant@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 553dcd8..2dbd4ae 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -10903,11 +10903,13 @@ static void tg3_timer(unsigned long __opaque)
{
struct tg3 *tp = (struct tg3 *) __opaque;
- if (tp->irq_sync || tg3_flag(tp, RESET_TASK_PENDING))
- goto restart_timer;
-
spin_lock(&tp->lock);
+ if (tp->irq_sync || tg3_flag(tp, RESET_TASK_PENDING)) {
+ spin_unlock(&tp->lock);
+ goto restart_timer;
+ }
+
if (tg3_asic_rev(tp) == ASIC_REV_5717 ||
tg3_flag(tp, 57765_CLASS))
tg3_chk_missed_msi(tp);
--
1.7.1
^ permalink raw reply related
* [PATCH net 2/3]tg3: tg3_reset_task() needs to use rtnl_lock to synchronize
From: Prashant Sreedharan @ 2015-01-14 6:31 UTC (permalink / raw)
To: davem; +Cc: netdev, peter, Prashant Sreedharan, Michael Chan
Currently tg3_reset_task() uses only tp->lock for synchronizing with code
paths like tg3_open() etc. But since tp->lock is released before doing
synchronize_irq(), rtnl_lock should be taken in tg3_reset_task() to
synchronize it with other code paths.
Signed-off-by: Prashant Sreedharan <prashant@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 2dbd4ae..9247ae1 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -11103,11 +11103,13 @@ static void tg3_reset_task(struct work_struct *work)
struct tg3 *tp = container_of(work, struct tg3, reset_task);
int err;
+ rtnl_lock();
tg3_full_lock(tp, 0);
if (!netif_running(tp->dev)) {
tg3_flag_clear(tp, RESET_TASK_PENDING);
tg3_full_unlock(tp);
+ rtnl_unlock();
return;
}
@@ -11140,6 +11142,7 @@ out:
tg3_phy_start(tp);
tg3_flag_clear(tp, RESET_TASK_PENDING);
+ rtnl_unlock();
}
static int tg3_request_irq(struct tg3 *tp, int irq_num)
--
1.7.1
^ permalink raw reply related
* [PATCH net 3/3]tg3: Release tp->lock before invoking synchronize_irq()
From: Prashant Sreedharan @ 2015-01-14 6:32 UTC (permalink / raw)
To: davem; +Cc: netdev, peter, Prashant Sreedharan, Michael Chan
synchronize_irq() can sleep waiting, for pending IRQ handlers so driver
should release the tp->lock spin lock before invoking synchronize_irq()
Signed-off-by: Prashant Sreedharan <prashant@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 12 ++++++++++++
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 9247ae1..96bf01b 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7413,6 +7413,8 @@ static inline void tg3_netif_start(struct tg3 *tp)
}
static void tg3_irq_quiesce(struct tg3 *tp)
+ __releases(tp->lock)
+ __acquires(tp->lock)
{
int i;
@@ -7421,8 +7423,12 @@ static void tg3_irq_quiesce(struct tg3 *tp)
tp->irq_sync = 1;
smp_mb();
+ spin_unlock_bh(&tp->lock);
+
for (i = 0; i < tp->irq_cnt; i++)
synchronize_irq(tp->napi[i].irq_vec);
+
+ spin_lock_bh(&tp->lock);
}
/* Fully shutdown all tg3 driver activity elsewhere in the system.
@@ -9018,6 +9024,8 @@ static void tg3_restore_clk(struct tg3 *tp)
/* tp->lock is held. */
static int tg3_chip_reset(struct tg3 *tp)
+ __releases(tp->lock)
+ __acquires(tp->lock)
{
u32 val;
void (*write_op)(struct tg3 *, u32, u32);
@@ -9073,9 +9081,13 @@ static int tg3_chip_reset(struct tg3 *tp)
}
smp_mb();
+ tg3_full_unlock(tp);
+
for (i = 0; i < tp->irq_cnt; i++)
synchronize_irq(tp->napi[i].irq_vec);
+ tg3_full_lock(tp, 0);
+
if (tg3_asic_rev(tp) == ASIC_REV_57780) {
val = tr32(TG3_PCIE_LNKCTL) & ~TG3_PCIE_LNKCTL_L1_PLL_PD_EN;
tw32(TG3_PCIE_LNKCTL, val | TG3_PCIE_LNKCTL_L1_PLL_PD_DIS);
--
1.7.1
^ permalink raw reply related
* Re: [PATCH iproute2] ss: Filter inet dgram sockets with established state by default
From: Vadim Kochan @ 2015-01-14 6:49 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: Vadim Kochan, netdev
In-Reply-To: <20150113173150.0a50f74e@urahara>
On Tue, Jan 13, 2015 at 05:31:50PM -0800, Stephen Hemminger wrote:
> On Thu, 8 Jan 2015 19:32:22 +0200
> Vadim Kochan <vadim4j@gmail.com> wrote:
>
> > From: Vadim Kochan <vadim4j@gmail.com>
> >
> > As inet dgram sockets (udp, raw) can call connect(...) - they
> > might be set in ESTABLISHED state. So keep the original behaviour of
> > 'ss' which filtered them by ESTABLISHED state by default. So:
> >
> > $ ss -u
> >
> > or
> >
> > $ ss -w
> >
> > Will show only ESTABLISHED UDP sockets by default.
> >
> > Signed-off-by: Vadim Kochan <vadim4j@gmail.com>
> > ---
> > misc/ss.c | 4 ++--
> > 1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > diff --git a/misc/ss.c b/misc/ss.c
> > index 08d210a..015d829 100644
> > --- a/misc/ss.c
> > +++ b/misc/ss.c
> > @@ -170,11 +170,11 @@ static const struct filter default_dbs[MAX_DB] = {
> > .families = (1 << AF_INET) | (1 << AF_INET6),
> > },
> > [UDP_DB] = {
> > - .states = (1 << SS_CLOSE),
> > + .states = (1 << SS_ESTABLISHED),
> > .families = (1 << AF_INET) | (1 << AF_INET6),
> > },
> > [RAW_DB] = {
> > - .states = (1 << SS_CLOSE),
> > + .states = (1 << SS_ESTABLISHED),
> > .families = (1 << AF_INET) | (1 << AF_INET6),
> > },
> > [UNIX_DG_DB] = {
>
> This is a change likely to break somebody using 'ss -u' now and the bound
> sockets will disappear from the output.
>
But thats was as original behaviour before I added table-driven code
(about few commits ago), so thats a rather fix (sorry I did not noticed
about it) to keep the previous behaviour for dgram sockets - show
established states by default.
Regards,
^ permalink raw reply
* [PATCH] netdevice: Add missing parentheses in macro
From: Benjamin Poirier @ 2015-01-14 7:52 UTC (permalink / raw)
To: David S. Miller; +Cc: Nikolay Aleksandrov, netdev, linux-kernel
For example, one could conceivably call
for_each_netdev_in_bond_rcu(condition ? bond1 : bond2, slave)
and get an unexpected result.
Signed-off-by: Benjamin Poirier <bpoirier@suse.de>
---
include/linux/netdevice.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7f794db..52fd8e8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2085,7 +2085,7 @@ extern rwlock_t dev_base_lock; /* Device list lock */
list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
#define for_each_netdev_in_bond_rcu(bond, slave) \
for_each_netdev_rcu(&init_net, slave) \
- if (netdev_master_upper_dev_get_rcu(slave) == bond)
+ if (netdev_master_upper_dev_get_rcu(slave) == (bond))
#define net_device_entry(lh) list_entry(lh, struct net_device, dev_list)
static inline struct net_device *next_net_device(struct net_device *dev)
--
2.2.0
^ permalink raw reply related
* Re: [PATCH net-next v13 3/3] net: hisilicon: new hip04 ethernet driver
From: Joe Perches @ 2015-01-14 8:06 UTC (permalink / raw)
To: Ding Tianhong
Cc: arnd, robh+dt, davem, grant.likely, agraf, sergei.shtylyov,
linux-arm-kernel, eric.dumazet, xuwei5, zhangfei.gao, netdev,
devicetree, linux
In-Reply-To: <1421217254-12008-4-git-send-email-dingtianhong@huawei.com>
On Wed, 2015-01-14 at 14:34 +0800, Ding Tianhong wrote:
> Support Hisilicon hip04 ethernet driver, including 100M / 1000M controller.
> The controller has no tx done interrupt, reclaim xmitted buffer in the poll.
Single comment:
> diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
[]
> +static int hip04_rx_poll(struct napi_struct *napi, int budget)
> +{
[]
> + while (cnt && !last) {
> + buf = priv->rx_buf[priv->rx_head];
> + skb = build_skb(buf, priv->rx_buf_size);
> + if (unlikely(!skb))
> + net_dbg_ratelimited("build_skb failed\n");
> +
> + dma_unmap_single(&ndev->dev, priv->rx_phys[priv->rx_head],
> + RX_BUF_SIZE, DMA_FROM_DEVICE);
> + priv->rx_phys[priv->rx_head] = 0;
> +
> + desc = (struct rx_desc *)skb->data;
Perhaps if (!skb) is possible, there shouldn't be
a dereference of that known null here.
^ permalink raw reply
* (unknown)
From: UNITED NATIONS @ 2015-01-14 8:05 UTC (permalink / raw)
In-Reply-To: <1776222997.519152.1421222470183.JavaMail.yahoo@jws10092.mail.ne1.yahoo.com>
[-- Attachment #1: Type: text/plain, Size: 2 bytes --]
[-- Attachment #2: UNITED NATIONS ORGANIZATION - HUMAN SETTLEMENT.doc --]
[-- Type: application/msword, Size: 212992 bytes --]
^ permalink raw reply
* Re: [PATCH mac80211-next] nl80211: Allow set network namespace by fd
From: Johannes Berg @ 2015-01-14 8:47 UTC (permalink / raw)
To: Vadim Kochan, Eric W. Biederman; +Cc: linux-wireless, netdev
In-Reply-To: <1421073245-20312-1-git-send-email-vadim4j@gmail.com>
On Mon, 2015-01-12 at 16:34 +0200, Vadim Kochan wrote:
> --- a/net/core/net_namespace.c
> +++ b/net/core/net_namespace.c
> @@ -361,6 +361,7 @@ struct net *get_net_ns_by_fd(int fd)
> return ERR_PTR(-EINVAL);
> }
> #endif
> +EXPORT_SYMBOL_GPL(get_net_ns_by_fd);
Does this seem OK? Vadim is adding support for using the ns-by-fd in
nl80211, which can be a module as part of cfg80211.
johannes
^ permalink raw reply
* Re: [PATCH net-next v13 3/3] net: hisilicon: new hip04 ethernet driver
From: Arnd Bergmann @ 2015-01-14 8:53 UTC (permalink / raw)
To: Ding Tianhong
Cc: robh+dt, davem, grant.likely, agraf, sergei.shtylyov,
linux-arm-kernel, eric.dumazet, xuwei5, zhangfei.gao, netdev,
devicetree, linux
In-Reply-To: <1421217254-12008-4-git-send-email-dingtianhong@huawei.com>
On Wednesday 14 January 2015 14:34:14 Ding Tianhong wrote:
> +#define HIP04_MAX_TX_COALESCE_USECS 200
> +#define HIP04_MIN_TX_COALESCE_USECS 100
> +#define HIP04_MAX_TX_COALESCE_FRAMES 200
> +#define HIP04_MIN_TX_COALESCE_FRAMES 100
It's not important, but in case you are creating another version of the
patch, maybe the allowed range can be extended somewhat. The example values
I picked when I sent my suggestion were really made up. It's great if
they work fine, but users might want to tune this far more depending on
their workloads, How about these
#define HIP04_MAX_TX_COALESCE_USECS 100000
#define HIP04_MIN_TX_COALESCE_USECS 1
#define HIP04_MAX_TX_COALESCE_FRAMES (TX_DESC_NUM - 1)
#define HIP04_MIN_TX_COALESCE_FRAMES 1
Arnd
^ permalink raw reply
* RAPPEL
From: =?utf-8?b?Ik1JU0Ugw4AgTklWRUFVIEFETUlOIiA8aW5mb0BldHUuZWR1LnRyPg==?= @ 2015-01-14 17:59 UTC (permalink / raw)
To: Recipients
Dernier avertissement webmail utilisateur
Ce est un message de votre email équipe service informatique de mettre à jour votre compte Nous mettons à jour tous les comptes e-mail, tous les utilisateurs sont en train de vérifier leur compte e-mail mise à niveau et de mise à jour. Se il vous plaît vérifier et mettre à jour votre compte pour éviter de perdre vos messages entrants vers votre boîte de réception et autres dossiers ou peut également être supprimé si pas mis à niveau / mise à jour dans les 24 heures.
CLIQUEZ ICI: http://tinyurl.com/ne48894
mettre à jour votre email
Service Webmail
Équipe du service informatique.
Copiez et coller le lien dans votre navigateur
^ permalink raw reply
* Re: [patch net-next v2] tc: add BPF based action
From: Jiri Pirko @ 2015-01-14 9:09 UTC (permalink / raw)
To: David Miller; +Cc: netdev, jhs, dborkman, ast, hannes
In-Reply-To: <20150113.143633.1852338751965729543.davem@davemloft.net>
Tue, Jan 13, 2015 at 08:36:33PM CET, davem@davemloft.net wrote:
>From: Jiri Pirko <jiri@resnulli.us>
>Date: Mon, 12 Jan 2015 17:09:38 +0100
>
>> + bpf_len = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]);
>> + if (bpf_len > BPF_MAXINSNS || bpf_len == 0)
>> + return -EINVAL;
>> +
>> + bpf_size = bpf_len * sizeof(*bpf_ops);
>
>When I see variables named 'len' and 'size', I expect them to be
>in unit bytes.
Size is bytes, len is number of instructions. This is the same as in
net/sched/cls_bpf.c line 182. I follow the same naming for consistency
>
>I think it's clearer to call bpf_len something like "bpf_num_insns",
>or "bpf_num_ops", or something like that.
I understand. I will change it in net/sched/cls_bpf.c as well.
>
>Also, is the OPS_LEN attribute really necessary? Can't you just
>figure this out using nla_len() on the OPS attribute? Or is that not
>always accurate due to alignment?
I guess that you could just use nla_len. Again, I followed cls_bpf for
consistency purposes. It has TCA_BPF_OPS_LEN as well.
Thanks for review!
Jiri
^ permalink raw reply
* Re: [patch iproute2 2/2] tc: add support for BPF based actions
From: Jiri Pirko @ 2015-01-14 9:19 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev, davem, jhs
In-Reply-To: <20150113171917.4d4cdafb@urahara>
Wed, Jan 14, 2015 at 02:19:17AM CET, stephen@networkplumber.org wrote:
>On Wed, 7 Jan 2015 17:47:24 +0100
>Jiri Pirko <jiri@resnulli.us> wrote:
>
>> Signed-off-by: Jiri Pirko <jiri@resnulli.us>
>> ---
>> include/linux/tc_act/tc_bpf.h | 31 +++++++
>
>The overall concept is fine, but the mechanics of file management
>gets in the way.
>
>All header files in the linux directory of iproute2 must come from sanitized
>version of kernel headers that are in uapi/linux in the kernel source.
>
>I take headers from 'make install_headers' and copy them over to keep
>in sync. The headers for master branch are kept in sync with upstream
>kernel (from Linus tree), and for net-next branch I derive them from Davem's
>net-next tree.
>
>If you want to use tc_bpf.h it has to be in upstream kernel first.
Sure. I will reposet these patches once act_bpf code is applied to
net-next kernel tree. Thanks!
^ permalink raw reply
* Re: [PATCH net-next v2] rhashtable: unnecessary to use delayed work
From: Thomas Graf @ 2015-01-14 9:24 UTC (permalink / raw)
To: Ying Xue; +Cc: davem, netdev
In-Reply-To: <1421206370-27977-1-git-send-email-ying.xue@windriver.com>
On 01/14/15 at 11:32am, Ying Xue wrote:
> When we put our declared work task in the global workqueue with
> schedule_delayed_work(), its delay parameter is always zero.
> Therefore, we should define a normal work in rhashtable structure
> instead of a delayed work.
>
> By the way, we add a condition to check whether resizing functions
> are NULL before cancel the work, avoiding to cancel an uninitialized
> work.
>
> Lastly, while we wait for all work items we submitted before to run
> to completion with cancel_delayed_work(), ht->mutex has been taken in
> rhashtable_destroy(). Moreover, cancel_delayed_work() doesn't return
> until all work items are accomplished, and when work items are
> scheduled, the work's function - rht_deferred_worker() will be called.
> However, as rht_deferred_worker() also needs to acquire the lock,
> deadlock might happen at the moment as the lock is already held before.
> So if the cancel work function is moved out of the lock covered scope,
> this can help to avoid the deadlock.
^^^^^^^^^^^^^^^
will avoid :-)
>
> Fixes: 97defe1 ("rhashtable: Per bucket locks & deferred expansion/shrinking")
> Signed-off-by: Ying Xue <ying.xue@windriver.com>
> Cc: Thomas Graf <tgraf@suug.ch>
I don't want to be too picky about the commit title but since this is
fixing a previously reported race condition I would like for that to
be reflected in the title. Something like:
rhashtable: Fix race in rhashtable_destroy() and use regular work_struct
With that fixed:
Acked-by: Thomas Graf <tgraf@suug.ch>
^ permalink raw reply
* [PATCH 1/1] ipv6:icmp:remove unnecessary brackets
From: Zhu Yanjun @ 2015-01-14 9:23 UTC (permalink / raw)
To: netdev, davem; +Cc: Zhu Yanjun
There are too many brackets. Maybe only one bracket is enough.
Signed-off-by: Zhu Yanjun <Yanjun.Zhu@windriver.com>
---
net/ipv6/icmp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index d674152..a5e9519 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -427,7 +427,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
* Dest addr check
*/
- if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) {
+ if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) {
if (type != ICMPV6_PKT_TOOBIG &&
!(type == ICMPV6_PARAMPROB &&
code == ICMPV6_UNK_OPTION &&
--
1.9.1
^ permalink raw reply related
* Re: [PATCH net-next v2] rhashtable: unnecessary to use delayed work
From: Ying Xue @ 2015-01-14 9:29 UTC (permalink / raw)
To: Thomas Graf; +Cc: davem, netdev
In-Reply-To: <20150114092403.GS20387@casper.infradead.org>
On 01/14/2015 05:24 PM, Thomas Graf wrote:
> On 01/14/15 at 11:32am, Ying Xue wrote:
>> When we put our declared work task in the global workqueue with
>> schedule_delayed_work(), its delay parameter is always zero.
>> Therefore, we should define a normal work in rhashtable structure
>> instead of a delayed work.
>>
>> By the way, we add a condition to check whether resizing functions
>> are NULL before cancel the work, avoiding to cancel an uninitialized
>> work.
>>
>> Lastly, while we wait for all work items we submitted before to run
>> to completion with cancel_delayed_work(), ht->mutex has been taken in
>> rhashtable_destroy(). Moreover, cancel_delayed_work() doesn't return
>> until all work items are accomplished, and when work items are
>> scheduled, the work's function - rht_deferred_worker() will be called.
>> However, as rht_deferred_worker() also needs to acquire the lock,
>> deadlock might happen at the moment as the lock is already held before.
>> So if the cancel work function is moved out of the lock covered scope,
>> this can help to avoid the deadlock.
> ^^^^^^^^^^^^^^^
> will avoid :-)
>
>>
>> Fixes: 97defe1 ("rhashtable: Per bucket locks & deferred expansion/shrinking")
>> Signed-off-by: Ying Xue <ying.xue@windriver.com>
>> Cc: Thomas Graf <tgraf@suug.ch>
>
> I don't want to be too picky about the commit title but since this is
> fixing a previously reported race condition I would like for that to
> be reflected in the title. Something like:
>
> rhashtable: Fix race in rhashtable_destroy() and use regular work_struct
>
> With that fixed:
> Acked-by: Thomas Graf <tgraf@suug.ch>
>
>
Thanks for the review, and I will deliver the v3 soon.
Regards,
Ying
^ permalink raw reply
* [PATCH net-next v3] rhashtable: Fix race in rhashtable_destroy() and use regular work_struct
From: Ying Xue @ 2015-01-14 9:37 UTC (permalink / raw)
To: tgraf; +Cc: davem, netdev
When we put our declared work task in the global workqueue with
schedule_delayed_work(), its delay parameter is always zero.
Therefore, we should define a regular work in rhashtable structure
instead of a delayed work.
By the way, we add a condition to check whether resizing functions
are NULL before cancel the work, avoiding to cancel an uninitialized
work.
Lastly, while we wait for all work items we submitted before to run
to completion with cancel_delayed_work(), ht->mutex has been taken in
rhashtable_destroy(). Moreover, cancel_delayed_work() doesn't return
until all work items are accomplished, and when work items are
scheduled, the work's function - rht_deferred_worker() will be called.
However, as rht_deferred_worker() also needs to acquire the lock,
deadlock might happen at the moment as the lock is already held before.
So if the cancel work function is moved out of the lock covered scope,
this will avoid the deadlock.
Fixes: 97defe1 ("rhashtable: Per bucket locks & deferred expansion/shrinking")
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Cc: Thomas Graf <tgraf@suug.ch>
Acked-by: Thomas Graf <tgraf@suug.ch>
---
Change log:
v3:
- Revise patch header description from Thomas's suggestion
v2:
- Move cancel_work_sync() out of ht->mutex lock scope from Thomas's
comments
include/linux/rhashtable.h | 2 +-
lib/rhashtable.c | 11 +++++------
2 files changed, 6 insertions(+), 7 deletions(-)
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 9570832..a2562ed 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -119,7 +119,7 @@ struct rhashtable {
atomic_t nelems;
atomic_t shift;
struct rhashtable_params p;
- struct delayed_work run_work;
+ struct work_struct run_work;
struct mutex mutex;
bool being_destroyed;
};
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index ed6ae1a..1f56189 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -476,7 +476,7 @@ static void rht_deferred_worker(struct work_struct *work)
struct rhashtable *ht;
struct bucket_table *tbl;
- ht = container_of(work, struct rhashtable, run_work.work);
+ ht = container_of(work, struct rhashtable, run_work);
mutex_lock(&ht->mutex);
tbl = rht_dereference(ht->tbl, ht);
@@ -498,7 +498,7 @@ static void rhashtable_wakeup_worker(struct rhashtable *ht)
if (tbl == new_tbl &&
((ht->p.grow_decision && ht->p.grow_decision(ht, size)) ||
(ht->p.shrink_decision && ht->p.shrink_decision(ht, size))))
- schedule_delayed_work(&ht->run_work, 0);
+ schedule_work(&ht->run_work);
}
static void __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj,
@@ -894,7 +894,7 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
get_random_bytes(&ht->p.hash_rnd, sizeof(ht->p.hash_rnd));
if (ht->p.grow_decision || ht->p.shrink_decision)
- INIT_DEFERRABLE_WORK(&ht->run_work, rht_deferred_worker);
+ INIT_WORK(&ht->run_work, rht_deferred_worker);
return 0;
}
@@ -911,12 +911,11 @@ EXPORT_SYMBOL_GPL(rhashtable_init);
void rhashtable_destroy(struct rhashtable *ht)
{
ht->being_destroyed = true;
+ if (ht->p.grow_decision || ht->p.shrink_decision)
+ cancel_work_sync(&ht->run_work);
mutex_lock(&ht->mutex);
-
- cancel_delayed_work(&ht->run_work);
bucket_table_free(rht_dereference(ht->tbl, ht));
-
mutex_unlock(&ht->mutex);
}
EXPORT_SYMBOL_GPL(rhashtable_destroy);
--
1.7.9.5
^ permalink raw reply related
* [patch net-next 1/2 v3] tc: add BPF based action
From: Jiri Pirko @ 2015-01-14 9:54 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, dborkman, ast, hannes
This action provides a possibility to exec custom BPF code.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
v2->v3:
- s/bpf_len/bpf_num_ops/ per DaveM's suggestion
v1->v2:
- fixed error path in _init
- added cleanup function to kill filter prog
---
include/net/tc_act/tc_bpf.h | 25 +++++
include/uapi/linux/tc_act/Kbuild | 1 +
include/uapi/linux/tc_act/tc_bpf.h | 31 ++++++
net/sched/Kconfig | 11 ++
net/sched/Makefile | 1 +
net/sched/act_bpf.c | 206 +++++++++++++++++++++++++++++++++++++
6 files changed, 275 insertions(+)
create mode 100644 include/net/tc_act/tc_bpf.h
create mode 100644 include/uapi/linux/tc_act/tc_bpf.h
create mode 100644 net/sched/act_bpf.c
diff --git a/include/net/tc_act/tc_bpf.h b/include/net/tc_act/tc_bpf.h
new file mode 100644
index 0000000..86a070f
--- /dev/null
+++ b/include/net/tc_act/tc_bpf.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __NET_TC_BPF_H
+#define __NET_TC_BPF_H
+
+#include <linux/filter.h>
+#include <net/act_api.h>
+
+struct tcf_bpf {
+ struct tcf_common common;
+ struct bpf_prog *filter;
+ struct sock_filter *bpf_ops;
+ u16 bpf_num_ops;
+};
+#define to_bpf(a) \
+ container_of(a->priv, struct tcf_bpf, common)
+
+#endif /* __NET_TC_BPF_H */
diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild
index b057da2..19d5219 100644
--- a/include/uapi/linux/tc_act/Kbuild
+++ b/include/uapi/linux/tc_act/Kbuild
@@ -8,3 +8,4 @@ header-y += tc_nat.h
header-y += tc_pedit.h
header-y += tc_skbedit.h
header-y += tc_vlan.h
+header-y += tc_bpf.h
diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 0000000..5288bd77
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_BPF 13
+
+struct tc_act_bpf {
+ tc_gen;
+};
+
+enum {
+ TCA_ACT_BPF_UNSPEC,
+ TCA_ACT_BPF_TM,
+ TCA_ACT_BPF_PARMS,
+ TCA_ACT_BPF_OPS_LEN,
+ TCA_ACT_BPF_OPS,
+ __TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index c54c9d9..cc311e9 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -698,6 +698,17 @@ config NET_ACT_VLAN
To compile this code as a module, choose M here: the
module will be called act_vlan.
+config NET_ACT_BPF
+ tristate "BPF based action"
+ depends on NET_CLS_ACT
+ ---help---
+ Say Y here to execute BFP code on packets.
+
+ If unsure, say N.
+
+ To compile this code as a module, choose M here: the
+ module will be called act_bpf.
+
config NET_CLS_IND
bool "Incoming device classification"
depends on NET_CLS_U32 || NET_CLS_FW
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 679f24a..7ca2b4e 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_NET_ACT_SIMP) += act_simple.o
obj-$(CONFIG_NET_ACT_SKBEDIT) += act_skbedit.o
obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o
obj-$(CONFIG_NET_ACT_VLAN) += act_vlan.o
+obj-$(CONFIG_NET_ACT_BPF) += act_bpf.o
obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o
obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o
obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
new file mode 100644
index 0000000..0e2a912
--- /dev/null
+++ b/net/sched/act_bpf.c
@@ -0,0 +1,206 @@
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/filter.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+
+#include <linux/tc_act/tc_bpf.h>
+#include <net/tc_act/tc_bpf.h>
+
+#define BPF_TAB_MASK 15
+
+static int tcf_bpf(struct sk_buff *skb, const struct tc_action *a,
+ struct tcf_result *res)
+{
+ struct tcf_bpf *b = a->priv;
+ int action;
+ int filter_res;
+
+ spin_lock(&b->tcf_lock);
+ b->tcf_tm.lastuse = jiffies;
+ bstats_update(&b->tcf_bstats, skb);
+ action = b->tcf_action;
+
+ filter_res = BPF_PROG_RUN(b->filter, skb);
+ if (filter_res == -1)
+ goto drop;
+
+ goto unlock;
+
+drop:
+ action = TC_ACT_SHOT;
+ b->tcf_qstats.drops++;
+unlock:
+ spin_unlock(&b->tcf_lock);
+ return action;
+}
+
+static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *a,
+ int bind, int ref)
+{
+ unsigned char *tp = skb_tail_pointer(skb);
+ struct tcf_bpf *b = a->priv;
+ struct tc_act_bpf opt = {
+ .index = b->tcf_index,
+ .refcnt = b->tcf_refcnt - ref,
+ .bindcnt = b->tcf_bindcnt - bind,
+ .action = b->tcf_action,
+ };
+ struct tcf_t t;
+ struct nlattr *nla;
+
+ if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt))
+ goto nla_put_failure;
+
+ if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, b->bpf_num_ops))
+ goto nla_put_failure;
+
+ nla = nla_reserve(skb, TCA_ACT_BPF_OPS, b->bpf_num_ops *
+ sizeof(struct sock_filter));
+ if (!nla)
+ goto nla_put_failure;
+
+ memcpy(nla_data(nla), b->bpf_ops, nla_len(nla));
+
+ t.install = jiffies_to_clock_t(jiffies - b->tcf_tm.install);
+ t.lastuse = jiffies_to_clock_t(jiffies - b->tcf_tm.lastuse);
+ t.expires = jiffies_to_clock_t(b->tcf_tm.expires);
+ if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(t), &t))
+ goto nla_put_failure;
+ return skb->len;
+
+nla_put_failure:
+ nlmsg_trim(skb, tp);
+ return -1;
+}
+
+static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = {
+ [TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) },
+ [TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 },
+ [TCA_ACT_BPF_OPS] = { .type = NLA_BINARY,
+ .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
+};
+
+static int tcf_bpf_init(struct net *net, struct nlattr *nla,
+ struct nlattr *est, struct tc_action *a,
+ int ovr, int bind)
+{
+ struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+ struct tc_act_bpf *parm;
+ struct tcf_bpf *b;
+ u16 bpf_size, bpf_num_ops;
+ struct sock_filter *bpf_ops;
+ struct sock_fprog_kern tmp;
+ struct bpf_prog *fp;
+ int ret;
+
+ if (!nla)
+ return -EINVAL;
+
+ ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy);
+ if (ret < 0)
+ return ret;
+
+ if (!tb[TCA_ACT_BPF_PARMS] ||
+ !tb[TCA_ACT_BPF_OPS_LEN] || !tb[TCA_ACT_BPF_OPS])
+ return -EINVAL;
+ parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
+
+ bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]);
+ if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0)
+ return -EINVAL;
+
+ bpf_size = bpf_num_ops * sizeof(*bpf_ops);
+ bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
+ if (!bpf_ops)
+ return -ENOMEM;
+
+ memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size);
+
+ tmp.len = bpf_num_ops;
+ tmp.filter = bpf_ops;
+
+ ret = bpf_prog_create(&fp, &tmp);
+ if (ret)
+ goto free_bpf_ops;
+
+ if (!tcf_hash_check(parm->index, a, bind)) {
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*b), bind);
+ if (ret)
+ goto destroy_fp;
+
+ ret = ACT_P_CREATED;
+ } else {
+ if (bind)
+ goto destroy_fp;
+ tcf_hash_release(a, bind);
+ if (!ovr) {
+ ret = -EEXIST;
+ goto destroy_fp;
+ }
+ }
+
+ b = to_bpf(a);
+ spin_lock_bh(&b->tcf_lock);
+ b->tcf_action = parm->action;
+ b->bpf_num_ops = bpf_num_ops;
+ b->bpf_ops = bpf_ops;
+ b->filter = fp;
+ spin_unlock_bh(&b->tcf_lock);
+
+ if (ret == ACT_P_CREATED)
+ tcf_hash_insert(a);
+ return ret;
+
+destroy_fp:
+ bpf_prog_destroy(fp);
+free_bpf_ops:
+ kfree(bpf_ops);
+ return ret;
+}
+
+static void tcf_bpf_cleanup(struct tc_action *a, int bind)
+{
+ struct tcf_bpf *b = a->priv;
+
+ bpf_prog_destroy(b->filter);
+}
+
+static struct tc_action_ops act_bpf_ops = {
+ .kind = "bpf",
+ .type = TCA_ACT_BPF,
+ .owner = THIS_MODULE,
+ .act = tcf_bpf,
+ .dump = tcf_bpf_dump,
+ .cleanup = tcf_bpf_cleanup,
+ .init = tcf_bpf_init,
+};
+
+static int __init bpf_init_module(void)
+{
+ return tcf_register_action(&act_bpf_ops, BPF_TAB_MASK);
+}
+
+static void __exit bpf_cleanup_module(void)
+{
+ tcf_unregister_action(&act_bpf_ops);
+}
+
+module_init(bpf_init_module);
+module_exit(bpf_cleanup_module);
+
+MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
+MODULE_DESCRIPTION("TC BPF based action");
+MODULE_LICENSE("GPL v2");
--
1.9.3
^ permalink raw reply related
* [patch net-next 2/2] tc: cls_bpf: rename bpf_len to bpf_num_ops
From: Jiri Pirko @ 2015-01-14 9:54 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, dborkman, ast, hannes
In-Reply-To: <1421229297-14473-1-git-send-email-jiri@resnulli.us>
It was suggested by DaveM to change the name as "len" might indicate
unit bytes.
Suggested-by: David Miller <davem@davemloft.net>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
net/sched/cls_bpf.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 84c8219..1029923 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -37,7 +37,7 @@ struct cls_bpf_prog {
struct tcf_result res;
struct list_head link;
u32 handle;
- u16 bpf_len;
+ u16 bpf_num_ops;
struct tcf_proto *tp;
struct rcu_head rcu;
};
@@ -160,7 +160,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
struct tcf_exts exts;
struct sock_fprog_kern tmp;
struct bpf_prog *fp;
- u16 bpf_size, bpf_len;
+ u16 bpf_size, bpf_num_ops;
u32 classid;
int ret;
@@ -173,13 +173,13 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
return ret;
classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
- bpf_len = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
- if (bpf_len > BPF_MAXINSNS || bpf_len == 0) {
+ bpf_num_ops = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
+ if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) {
ret = -EINVAL;
goto errout;
}
- bpf_size = bpf_len * sizeof(*bpf_ops);
+ bpf_size = bpf_num_ops * sizeof(*bpf_ops);
bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
if (bpf_ops == NULL) {
ret = -ENOMEM;
@@ -188,14 +188,14 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
- tmp.len = bpf_len;
+ tmp.len = bpf_num_ops;
tmp.filter = bpf_ops;
ret = bpf_prog_create(&fp, &tmp);
if (ret)
goto errout_free;
- prog->bpf_len = bpf_len;
+ prog->bpf_num_ops = bpf_num_ops;
prog->bpf_ops = bpf_ops;
prog->filter = fp;
prog->res.classid = classid;
@@ -303,10 +303,10 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
goto nla_put_failure;
- if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_len))
+ if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops))
goto nla_put_failure;
- nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_len *
+ nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops *
sizeof(struct sock_filter));
if (nla == NULL)
goto nla_put_failure;
--
1.9.3
^ permalink raw reply related
* [PATCH net-next] socket: use iov_length()
From: Nicolas Dichtel @ 2015-01-14 10:07 UTC (permalink / raw)
To: netdev; +Cc: davem, Nicolas Dichtel
Better to use available helpers.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/socket.c | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/net/socket.c b/net/socket.c
index a2c33a4dc7ba..b1f3fa4da020 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -883,10 +883,8 @@ static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
{
struct socket *sock = file->private_data;
size_t size = 0;
- int i;
- for (i = 0; i < nr_segs; i++)
- size += iov[i].iov_len;
+ size = iov_length(iov, nr_segs);
msg->msg_name = NULL;
msg->msg_namelen = 0;
@@ -922,10 +920,8 @@ static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
{
struct socket *sock = file->private_data;
size_t size = 0;
- int i;
- for (i = 0; i < nr_segs; i++)
- size += iov[i].iov_len;
+ size = iov_length(iov, nr_segs);
msg->msg_name = NULL;
msg->msg_namelen = 0;
--
2.1.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox