--- /dev/null
+STMicroelectronics SoC DWMAC glue layer controller
+
+The device node has following properties.
+
+Required properties:
+ - compatible : Can be "st,stih415-dwmac", "st,stih416-dwmac" or
+ "st,stid127-dwmac".
+ - reg : Offset of the glue configuration register map in system
+ configuration regmap pointed by st,syscon property and size.
+
+ - reg-names : Should be "sti-ethconf".
+
+ - st,syscon : Should be phandle to system configuration node which
+ encompases this glue registers.
+
+ - st,tx-retime-src: On STi Parts for Giga bit speeds, 125Mhz clocks can be
+ wired up in from different sources. One via TXCLK pin and other via CLK_125
+ pin. This wiring is totally board dependent. However the retiming glue
+ logic should be configured accordingly. Possible values for this property
+
+ "txclk" - if 125Mhz clock is wired up via txclk line.
+ "clk_125" - if 125Mhz clock is wired up via clk_125 line.
+
+ This property is only valid for Giga bit setup( GMII, RGMII), and it is
+ un-used for non-giga bit (MII and RMII) setups. Also note that internal
+ clockgen can not generate stable 125Mhz clock.
+
+ - st,ext-phyclk: This boolean property indicates who is generating the clock
+ for tx and rx. This property is only valid for RMII case where the clock can
+ be generated from the MAC or PHY.
+
+ - clock-names: should be "sti-ethclk".
+ - clocks: Should point to ethernet clockgen which can generate phyclk.
+
+
+Example:
+
+ethernet0: dwmac@fe810000 {
+ device_type = "network";
+ compatible = "st,stih416-dwmac", "snps,dwmac", "snps,dwmac-3.710";
+ reg = <0xfe810000 0x8000>, <0x8bc 0x4>;
+ reg-names = "stmmaceth", "sti-ethconf";
+ interrupts = <0 133 0>, <0 134 0>, <0 135 0>;
+ interrupt-names = "macirq", "eth_wake_irq", "eth_lpi";
+ phy-mode = "mii";
+
+ st,syscon = <&syscfg_rear>;
+
+ snps,pbl = <32>;
+ snps,mixed-burst;
+
+ resets = <&softreset STIH416_ETH0_SOFTRESET>;
+ reset-names = "stmmaceth";
+ pinctrl-0 = <&pinctrl_mii0>;
+ pinctrl-names = "default";
+ clocks = <&CLK_S_GMAC0_PHY>;
+ clock-names = "stmmaceth";
+};
+++ /dev/null
-The 3Com Etherlink Plus (3c505) driver.
-
-This driver now uses DMA. There is currently no support for PIO operation.
-The default DMA channel is 6; this is _not_ autoprobed, so you must
-make sure you configure it correctly. If loading the driver as a
-module, you can do this with "modprobe 3c505 dma=n". If the driver is
-linked statically into the kernel, you must either use an "ether="
-statement on the command line, or change the definition of ELP_DMA in 3c505.h.
-
-The driver will warn you if it has to fall back on the compiled in
-default DMA channel.
-
-If no base address is given at boot time, the driver will autoprobe
-ports 0x300, 0x280 and 0x310 (in that order). If no IRQ is given, the driver
-will try to probe for it.
-
-The driver can be used as a loadable module.
-
-Theoretically, one instance of the driver can now run multiple cards,
-in the standard way (when loading a module, say "modprobe 3c505
-io=0x300,0x340 irq=10,11 dma=6,7" or whatever). I have not tested
-this, though.
-
-The driver may now support revision 2 hardware; the dependency on
-being able to read the host control register has been removed. This
-is also untested, since I don't have a suitable card.
-
-Known problems:
- I still see "DMA upload timed out" messages from time to time. These
-seem to be fairly non-fatal though.
- The card is old and slow.
-
-To do:
- Improve probe/setup code
- Test multicast and promiscuous operation
-
-Authors:
- The driver is mainly written by Craig Southeren, email
- <craigs@ineluki.apana.org.au>.
- Parts of the driver (adapting the driver to 1.1.4+ kernels,
- IRQ/address detection, some changes) and this README by
- Juha Laiho <jlaiho@ichaos.nullnet.fi>.
- DMA mode, more fixes, etc, by Philip Blundell <pjb27@cam.ac.uk>
- Multicard support, Software configurable DMA, etc., by
- Christopher Collins <ccollins@pcug.org.au>
This adds a specialized tap character device driver that is based
on the MAC-VLAN network interface, called macvtap. A macvtap device
can be added in the same way as a macvlan device, using 'type
- macvlan', and then be accessed through the tap user space interface.
+ macvtap', and then be accessed through the tap user space interface.
To compile this driver as a module, choose M here: the module
will be called macvtap.
bond_set_carrier(bond);
if (USES_PRIMARY(bond->params.mode)) {
+ block_netpoll_tx();
write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
+ unblock_netpoll_tx();
}
pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
if (bond->primary_slave == new_slave)
bond->primary_slave = NULL;
if (bond->curr_active_slave == new_slave) {
+ block_netpoll_tx();
write_lock_bh(&bond->curr_slave_lock);
bond_change_active_slave(bond, NULL);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
+ unblock_netpoll_tx();
}
slave_disable_netpoll(new_slave);
pr_info("%s: Primary slave changed to %s, reselecting active slave.\n",
bond->dev->name, bond->primary_slave ? slave_dev->name :
"none");
+
+ block_netpoll_tx();
write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
+ unblock_netpoll_tx();
break;
case NETDEV_FEAT_CHANGE:
bond_compute_features(bond);
stmmac device driver. This driver is used for A20/A31
GMAC ethernet controller.
+config DWMAC_STI
+ bool "STi GMAC support"
+ depends on STMMAC_PLATFORM && ARCH_STI
+ default y
+ ---help---
+ Support for ethernet controller on STi SOCs.
+
+ This selects STi SoC glue layer support for the stmmac
+ device driver. This driver is used on for the STi series
+ SOCs GMAC ethernet controller.
+
config STMMAC_PCI
bool "STMMAC PCI bus support"
depends on STMMAC_ETH && PCI
stmmac-$(CONFIG_STMMAC_PLATFORM) += stmmac_platform.o
stmmac-$(CONFIG_STMMAC_PCI) += stmmac_pci.o
stmmac-$(CONFIG_DWMAC_SUNXI) += dwmac-sunxi.o
+stmmac-$(CONFIG_DWMAC_STI) += dwmac-sti.o
stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \
chain_mode.o dwmac_lib.o dwmac1000_core.o dwmac1000_dma.o \
dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o \
--- /dev/null
+/**
+ * dwmac-sti.c - STMicroelectronics DWMAC Specific Glue layer
+ *
+ * Copyright (C) 2003-2014 STMicroelectronics (R&D) Limited
+ * Author: Srinivas Kandagatla <srinivas.kandagatla@st.com>
+ *
+ *
+ * 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/kernel.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/stmmac.h>
+#include <linux/phy.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+
+/**
+ * STi GMAC glue logic.
+ * --------------------
+ *
+ * _
+ * | \
+ * --------|0 \ ETH_SEL_INTERNAL_NOTEXT_PHYCLK
+ * phyclk | |___________________________________________
+ * | | | (phyclk-in)
+ * --------|1 / |
+ * int-clk |_ / |
+ * | _
+ * | | \
+ * |_______|1 \ ETH_SEL_TX_RETIME_CLK
+ * | |___________________________
+ * | | (tx-retime-clk)
+ * _______|0 /
+ * | |_ /
+ * _ |
+ * | \ |
+ * --------|0 \ |
+ * clk_125 | |__|
+ * | | ETH_SEL_TXCLK_NOT_CLK125
+ * --------|1 /
+ * txclk |_ /
+ *
+ *
+ * ETH_SEL_INTERNAL_NOTEXT_PHYCLK is valid only for RMII where PHY can
+ * generate 50MHz clock or MAC can generate it.
+ * This bit is configured by "st,ext-phyclk" property.
+ *
+ * ETH_SEL_TXCLK_NOT_CLK125 is only valid for gigabit modes, where the 125Mhz
+ * clock either comes from clk-125 pin or txclk pin. This configuration is
+ * totally driven by the board wiring. This bit is configured by
+ * "st,tx-retime-src" property.
+ *
+ * TXCLK configuration is different for different phy interface modes
+ * and changes according to link speed in modes like RGMII.
+ *
+ * Below table summarizes the clock requirement and clock sources for
+ * supported phy interface modes with link speeds.
+ * ________________________________________________
+ *| PHY_MODE | 1000 Mbit Link | 100 Mbit Link |
+ * ------------------------------------------------
+ *| MII | n/a | 25Mhz |
+ *| | | txclk |
+ * ------------------------------------------------
+ *| GMII | 125Mhz | 25Mhz |
+ *| | clk-125/txclk | txclk |
+ * ------------------------------------------------
+ *| RGMII | 125Mhz | 25Mhz |
+ *| | clk-125/txclk | clkgen |
+ * ------------------------------------------------
+ *| RMII | n/a | 25Mhz |
+ *| | |clkgen/phyclk-in |
+ * ------------------------------------------------
+ *
+ * TX lines are always retimed with a clk, which can vary depending
+ * on the board configuration. Below is the table of these bits
+ * in eth configuration register depending on source of retime clk.
+ *
+ *---------------------------------------------------------------
+ * src | tx_rt_clk | int_not_ext_phyclk | txclk_n_clk125|
+ *---------------------------------------------------------------
+ * txclk | 0 | n/a | 1 |
+ *---------------------------------------------------------------
+ * ck_125| 0 | n/a | 0 |
+ *---------------------------------------------------------------
+ * phyclk| 1 | 0 | n/a |
+ *---------------------------------------------------------------
+ * clkgen| 1 | 1 | n/a |
+ *---------------------------------------------------------------
+ */
+
+ /* Register definition */
+
+ /* 3 bits [8:6]
+ * [6:6] ETH_SEL_TXCLK_NOT_CLK125
+ * [7:7] ETH_SEL_INTERNAL_NOTEXT_PHYCLK
+ * [8:8] ETH_SEL_TX_RETIME_CLK
+ *
+ */
+
+#define TX_RETIME_SRC_MASK GENMASK(8, 6)
+#define ETH_SEL_TX_RETIME_CLK BIT(8)
+#define ETH_SEL_INTERNAL_NOTEXT_PHYCLK BIT(7)
+#define ETH_SEL_TXCLK_NOT_CLK125 BIT(6)
+
+#define ENMII_MASK GENMASK(5, 5)
+#define ENMII BIT(5)
+
+/**
+ * 3 bits [4:2]
+ * 000-GMII/MII
+ * 001-RGMII
+ * 010-SGMII
+ * 100-RMII
+*/
+#define MII_PHY_SEL_MASK GENMASK(4, 2)
+#define ETH_PHY_SEL_RMII BIT(4)
+#define ETH_PHY_SEL_SGMII BIT(3)
+#define ETH_PHY_SEL_RGMII BIT(2)
+#define ETH_PHY_SEL_GMII 0x0
+#define ETH_PHY_SEL_MII 0x0
+
+#define IS_PHY_IF_MODE_RGMII(iface) (iface == PHY_INTERFACE_MODE_RGMII || \
+ iface == PHY_INTERFACE_MODE_RGMII_ID || \
+ iface == PHY_INTERFACE_MODE_RGMII_RXID || \
+ iface == PHY_INTERFACE_MODE_RGMII_TXID)
+
+#define IS_PHY_IF_MODE_GBIT(iface) (IS_PHY_IF_MODE_RGMII(iface) || \
+ iface == PHY_INTERFACE_MODE_GMII)
+
+struct sti_dwmac {
+ int interface;
+ bool ext_phyclk;
+ bool is_tx_retime_src_clk_125;
+ struct clk *clk;
+ int reg;
+ struct device *dev;
+ struct regmap *regmap;
+};
+
+static u32 phy_intf_sels[] = {
+ [PHY_INTERFACE_MODE_MII] = ETH_PHY_SEL_MII,
+ [PHY_INTERFACE_MODE_GMII] = ETH_PHY_SEL_GMII,
+ [PHY_INTERFACE_MODE_RGMII] = ETH_PHY_SEL_RGMII,
+ [PHY_INTERFACE_MODE_RGMII_ID] = ETH_PHY_SEL_RGMII,
+ [PHY_INTERFACE_MODE_SGMII] = ETH_PHY_SEL_SGMII,
+ [PHY_INTERFACE_MODE_RMII] = ETH_PHY_SEL_RMII,
+};
+
+enum {
+ TX_RETIME_SRC_NA = 0,
+ TX_RETIME_SRC_TXCLK = 1,
+ TX_RETIME_SRC_CLK_125,
+ TX_RETIME_SRC_PHYCLK,
+ TX_RETIME_SRC_CLKGEN,
+};
+
+static const char *const tx_retime_srcs[] = {
+ [TX_RETIME_SRC_NA] = "",
+ [TX_RETIME_SRC_TXCLK] = "txclk",
+ [TX_RETIME_SRC_CLK_125] = "clk_125",
+ [TX_RETIME_SRC_PHYCLK] = "phyclk",
+ [TX_RETIME_SRC_CLKGEN] = "clkgen",
+};
+
+static u32 tx_retime_val[] = {
+ [TX_RETIME_SRC_TXCLK] = ETH_SEL_TXCLK_NOT_CLK125,
+ [TX_RETIME_SRC_CLK_125] = 0x0,
+ [TX_RETIME_SRC_PHYCLK] = ETH_SEL_TX_RETIME_CLK,
+ [TX_RETIME_SRC_CLKGEN] = ETH_SEL_TX_RETIME_CLK |
+ ETH_SEL_INTERNAL_NOTEXT_PHYCLK,
+};
+
+static void setup_retime_src(struct sti_dwmac *dwmac, u32 spd)
+{
+ u32 src = 0, freq = 0;
+
+ if (spd == SPEED_100) {
+ if (dwmac->interface == PHY_INTERFACE_MODE_MII ||
+ dwmac->interface == PHY_INTERFACE_MODE_GMII) {
+ src = TX_RETIME_SRC_TXCLK;
+ } else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) {
+ if (dwmac->ext_phyclk) {
+ src = TX_RETIME_SRC_PHYCLK;
+ } else {
+ src = TX_RETIME_SRC_CLKGEN;
+ freq = 50000000;
+ }
+
+ } else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) {
+ src = TX_RETIME_SRC_CLKGEN;
+ freq = 25000000;
+ }
+
+ if (src == TX_RETIME_SRC_CLKGEN && dwmac->clk)
+ clk_set_rate(dwmac->clk, freq);
+
+ } else if (spd == SPEED_1000) {
+ if (dwmac->is_tx_retime_src_clk_125)
+ src = TX_RETIME_SRC_CLK_125;
+ else
+ src = TX_RETIME_SRC_TXCLK;
+ }
+
+ regmap_update_bits(dwmac->regmap, dwmac->reg,
+ TX_RETIME_SRC_MASK, tx_retime_val[src]);
+}
+
+static void sti_dwmac_exit(struct platform_device *pdev, void *priv)
+{
+ struct sti_dwmac *dwmac = priv;
+
+ if (dwmac->clk)
+ clk_disable_unprepare(dwmac->clk);
+}
+
+static void sti_fix_mac_speed(void *priv, unsigned int spd)
+{
+ struct sti_dwmac *dwmac = priv;
+
+ setup_retime_src(dwmac, spd);
+
+ return;
+}
+
+static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
+ struct platform_device *pdev)
+{
+ struct resource *res;
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ struct regmap *regmap;
+ int err;
+
+ if (!np)
+ return -EINVAL;
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sti-ethconf");
+ if (!res)
+ return -ENODATA;
+
+ regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon");
+ if (IS_ERR(regmap))
+ return PTR_ERR(regmap);
+
+ dwmac->dev = dev;
+ dwmac->interface = of_get_phy_mode(np);
+ dwmac->regmap = regmap;
+ dwmac->reg = res->start;
+ dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk");
+ dwmac->is_tx_retime_src_clk_125 = false;
+
+ if (IS_PHY_IF_MODE_GBIT(dwmac->interface)) {
+ const char *rs;
+
+ err = of_property_read_string(np, "st,tx-retime-src", &rs);
+ if (err < 0) {
+ dev_err(dev, "st,tx-retime-src not specified\n");
+ return err;
+ }
+
+ if (!strcasecmp(rs, "clk_125"))
+ dwmac->is_tx_retime_src_clk_125 = true;
+ }
+
+ dwmac->clk = devm_clk_get(dev, "sti-ethclk");
+
+ if (IS_ERR(dwmac->clk))
+ dwmac->clk = NULL;
+
+ return 0;
+}
+
+static int sti_dwmac_init(struct platform_device *pdev, void *priv)
+{
+ struct sti_dwmac *dwmac = priv;
+ struct regmap *regmap = dwmac->regmap;
+ int iface = dwmac->interface;
+ u32 reg = dwmac->reg;
+ u32 val, spd;
+
+ if (dwmac->clk)
+ clk_prepare_enable(dwmac->clk);
+
+ regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, phy_intf_sels[iface]);
+
+ val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII;
+ regmap_update_bits(regmap, reg, ENMII_MASK, val);
+
+ if (IS_PHY_IF_MODE_GBIT(iface))
+ spd = SPEED_1000;
+ else
+ spd = SPEED_100;
+
+ setup_retime_src(dwmac, spd);
+
+ return 0;
+}
+
+static void *sti_dwmac_setup(struct platform_device *pdev)
+{
+ struct sti_dwmac *dwmac;
+ int ret;
+
+ dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL);
+ if (!dwmac)
+ return ERR_PTR(-ENOMEM);
+
+ ret = sti_dwmac_parse_data(dwmac, pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Unable to parse OF data\n");
+ return ERR_PTR(ret);
+ }
+
+ return dwmac;
+}
+
+const struct stmmac_of_data sti_gmac_data = {
+ .fix_mac_speed = sti_fix_mac_speed,
+ .setup = sti_dwmac_setup,
+ .init = sti_dwmac_init,
+ .exit = sti_dwmac_exit,
+};
#ifdef CONFIG_DWMAC_SUNXI
extern const struct stmmac_of_data sun7i_gmac_data;
#endif
+#ifdef CONFIG_DWMAC_STI
+extern const struct stmmac_of_data sti_gmac_data;
+#endif
extern struct platform_driver stmmac_pltfr_driver;
static inline int stmmac_register_platform(void)
{
static const struct of_device_id stmmac_dt_ids[] = {
#ifdef CONFIG_DWMAC_SUNXI
{ .compatible = "allwinner,sun7i-a20-gmac", .data = &sun7i_gmac_data},
+#endif
+#ifdef CONFIG_DWMAC_STI
+ { .compatible = "st,stih415-dwmac", .data = &sti_gmac_data},
+ { .compatible = "st,stih416-dwmac", .data = &sti_gmac_data},
+ { .compatible = "st,stih127-dwmac", .data = &sti_gmac_data},
#endif
/* SoC specific glue layers should come before generic bindings */
{ .compatible = "st,spear600-gmac"},
#include <linux/netdevice.h>
#include <linux/of_mdio.h>
#include <linux/of_platform.h>
+#include <linux/of_irq.h>
#include <linux/of_address.h>
#include <linux/skbuff.h>
#include <linux/spinlock.h>
size += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
packets++;
- lp->tx_bd_ci = ++lp->tx_bd_ci % TX_BD_NUM;
+ ++lp->tx_bd_ci;
+ lp->tx_bd_ci %= TX_BD_NUM;
cur_p = &lp->tx_bd_v[lp->tx_bd_ci];
status = cur_p->status;
}
skb_headlen(skb), DMA_TO_DEVICE);
for (ii = 0; ii < num_frag; ii++) {
- lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM;
+ ++lp->tx_bd_tail;
+ lp->tx_bd_tail %= TX_BD_NUM;
cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
frag = &skb_shinfo(skb)->frags[ii];
cur_p->phys = dma_map_single(ndev->dev.parent,
tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
/* Start the transfer */
axienet_dma_out32(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p);
- lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM;
+ ++lp->tx_bd_tail;
+ lp->tx_bd_tail %= TX_BD_NUM;
return NETDEV_TX_OK;
}
cur_p->status = 0;
cur_p->sw_id_offset = (u32) new_skb;
- lp->rx_bd_ci = ++lp->rx_bd_ci % RX_BD_NUM;
+ ++lp->rx_bd_ci;
+ lp->rx_bd_ci %= RX_BD_NUM;
cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
}
dev->priv_flags |= IFF_MACVLAN;
err = netdev_upper_dev_link(lowerdev, dev);
if (err)
- goto destroy_port;
-
+ goto unregister_netdev;
list_add_tail_rcu(&vlan->list, &port->vlans);
netif_stacked_transfer_operstate(lowerdev, dev);
return 0;
+unregister_netdev:
+ unregister_netdevice(dev);
destroy_port:
port->count -= 1;
if (!port->count)
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev);
-netdev_features_t netif_skb_features(struct sk_buff *skb);
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+ const struct net_device *dev);
+static inline netdev_features_t netif_skb_features(struct sk_buff *skb)
+{
+ return netif_skb_dev_features(skb, skb->dev);
+}
static inline bool net_gso_ok(netdev_features_t features, int gso_type)
{
{
return !skb->head_frag || skb_cloned(skb);
}
+
+/**
+ * skb_gso_network_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_network_seglen is used to determine the real size of the
+ * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
+ *
+ * The MAC/L2 header is not accounted for.
+ */
+static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
+{
+ unsigned int hdr_len = skb_transport_header(skb) -
+ skb_network_header(skb);
+ return hdr_len + skb_gso_transport_seglen(skb);
+}
#endif /* __KERNEL__ */
#endif /* _LINUX_SKBUFF_H */
* 2. No high memory really exists on this machine.
*/
-static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
int i;
}
static netdev_features_t harmonize_features(struct sk_buff *skb,
- netdev_features_t features)
+ const struct net_device *dev,
+ netdev_features_t features)
{
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, skb_network_protocol(skb))) {
features &= ~NETIF_F_ALL_CSUM;
- } else if (illegal_highdma(skb->dev, skb)) {
+ } else if (illegal_highdma(dev, skb)) {
features &= ~NETIF_F_SG;
}
return features;
}
-netdev_features_t netif_skb_features(struct sk_buff *skb)
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+ const struct net_device *dev)
{
__be16 protocol = skb->protocol;
- netdev_features_t features = skb->dev->features;
+ netdev_features_t features = dev->features;
- if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+ if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
features &= ~NETIF_F_GSO_MASK;
if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
} else if (!vlan_tx_tag_present(skb)) {
- return harmonize_features(skb, features);
+ return harmonize_features(skb, dev, features);
}
- features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+ features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX);
if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
- return harmonize_features(skb, features);
+ return harmonize_features(skb, dev, features);
}
-EXPORT_SYMBOL(netif_skb_features);
+EXPORT_SYMBOL(netif_skb_dev_features);
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
dev->ifindex = ifm->ifi_index;
- if (ops->newlink)
+ if (ops->newlink) {
err = ops->newlink(net, dev, tb, data);
- else
+ /* Drivers should call free_netdev() in ->destructor
+ * and unregister it on failure so that device could be
+ * finally freed in rtnl_unlock.
+ */
+ if (err < 0)
+ goto out;
+ } else {
err = register_netdevice(dev);
-
- if (err < 0) {
- free_netdev(dev);
- goto out;
+ if (err < 0) {
+ free_netdev(dev);
+ goto out;
+ }
}
-
err = rtnl_configure_link(dev, ifm);
if (err < 0)
unregister_netdevice(dev);
#include <net/route.h>
#include <net/xfrm.h>
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+ return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+ !skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu || skb->local_df)
+ return false;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+ unsigned int mtu;
+
+ if (skb->local_df || !skb_is_gso(skb))
+ return false;
+
+ mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
+
+ /* if seglen > mtu, do software segmentation for IP fragmentation on
+ * output. DF bit cannot be set since ip_forward would have sent
+ * icmp error.
+ */
+ return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ netdev_features_t features;
+ struct sk_buff *segs;
+ int ret = 0;
+
+ features = netif_skb_dev_features(skb, dst->dev);
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR(segs)) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ consume_skb(skb);
+
+ do {
+ struct sk_buff *nskb = segs->next;
+ int err;
+
+ segs->next = NULL;
+ err = dst_output(segs);
+
+ if (err && ret == 0)
+ ret = err;
+ segs = nskb;
+ } while (segs);
+
+ return ret;
+}
+
static int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
if (unlikely(opt->optlen))
ip_forward_options(skb);
+ if (ip_gso_exceeds_dst_mtu(skb))
+ return ip_forward_finish_gso(skb);
+
return dst_output(skb);
}
IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
- if (unlikely(skb->len > mtu && !skb_is_gso(skb) &&
- (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+ if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
return mtu;
}
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu || skb->local_df)
+ return false;
+
+ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+ return true;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
- (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+ if (ip6_pkt_too_big(skb, mtu)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
},
{
.procname = "cookie_hmac_alg",
+ .data = &init_net.sctp.sctp_hmac_alg,
.maxlen = 8,
.mode = 0644,
.proc_handler = proc_sctp_do_hmac_alg,
int sctp_sysctl_net_register(struct net *net)
{
- struct ctl_table *table;
- int i;
+ struct ctl_table *table = sctp_net_table;
+
+ if (!net_eq(net, &init_net)) {
+ int i;
- table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
- if (!table)
- return -ENOMEM;
+ table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
- for (i = 0; table[i].data; i++)
- table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+ for (i = 0; table[i].data; i++)
+ table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+ }
net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
return 0;
struct tipc_skb_cb {
void *handle;
+ bool deferred;
};
#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
u32 hdr_size;
u32 min_hdr_size;
+ /* If this packet comes from the defer queue, the skb has already
+ * been validated
+ */
+ if (unlikely(TIPC_SKB_CB(buf)->deferred))
+ return 1;
+
if (unlikely(buf->len < MIN_H_SIZE))
return 0;
&l_ptr->newest_deferred_in, buf)) {
l_ptr->deferred_inqueue_sz++;
l_ptr->stats.deferred_recv++;
+ TIPC_SKB_CB(buf)->deferred = true;
if ((l_ptr->deferred_inqueue_sz % 16) == 1)
tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
} else