diff options
61 files changed, 2134 insertions, 1551 deletions
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt index 7ee770b5ef5f..80a7a3454902 100644 --- a/Documentation/networking/stmmac.txt +++ b/Documentation/networking/stmmac.txt @@ -7,7 +7,7 @@ This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers (Synopsys IP blocks); it has been fully tested on STLinux platforms. Currently this network device driver is for all STM embedded MAC/GMAC -(7xxx SoCs). +(7xxx SoCs). Other platforms start using it i.e. ARM SPEAr. DWC Ether MAC 10/100/1000 Universal version 3.41a and DWC Ether MAC 10/100 Universal version 4.0 have been used for developing the first code @@ -95,9 +95,14 @@ Several information came from the platform; please refer to the driver's Header file in include/linux directory. struct plat_stmmacenet_data { - int bus_id; - int pbl; - int has_gmac; + int bus_id; + int pbl; + int clk_csr; + int has_gmac; + int enh_desc; + int tx_coe; + int bugged_jumbo; + int pmt; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(unsigned long ioaddr); #ifdef CONFIG_STM_DRIVERS @@ -114,6 +119,12 @@ Where: registers (on STM platforms); - has_gmac: GMAC core is on board (get it at run-time in the next step); - bus_id: bus identifier. +- tx_coe: core is able to perform the tx csum in HW. +- enh_desc: if sets the MAC will use the enhanced descriptor structure. +- clk_csr: CSR Clock range selection. +- bugged_jumbo: some HWs are not able to perform the csum in HW for + over-sized frames due to limited buffer sizes. Setting this + flag the csum will be done in SW on JUMBO frames. struct plat_stmmacphy_data { int bus_id; @@ -131,13 +142,28 @@ Where: - interface: physical MII interface mode; - phy_reset: hook to reset HW function. +SOURCES: +- Kconfig +- Makefile +- stmmac_main.c: main network device driver; +- stmmac_mdio.c: mdio functions; +- stmmac_ethtool.c: ethtool support; +- stmmac_timer.[ch]: timer code used for mitigating the driver dma interrupts + Only tested on ST40 platforms based. +- stmmac.h: private driver structure; +- common.h: common definitions and VFTs; +- descs.h: descriptor structure definitions; +- dwmac1000_core.c: GMAC core functions; +- dwmac1000_dma.c: dma functions for the GMAC chip; +- dwmac1000.h: specific header file for the GMAC; +- dwmac100_core: MAC 100 core and dma code; +- dwmac100_dma.c: dma funtions for the MAC chip; +- dwmac1000.h: specific header file for the MAC; +- dwmac_lib.c: generic DMA functions shared among chips +- enh_desc.c: functions for handling enhanced descriptors +- norm_desc.c: functions for handling normal descriptors + TODO: -- Continue to make the driver more generic and suitable for other Synopsys - Ethernet controllers used on other architectures (i.e. ARM). -- 10G controllers are not supported. -- MAC uses Normal descriptors and GMAC uses enhanced ones. - This is a limit that should be reviewed. MAC could want to - use the enhanced structure. -- Checksumming: Rx/Tx csum is done in HW in case of GMAC only. +- XGMAC controller is not supported. - Review the timer optimisation code to use an embedded device that seems to be available in new chip generations. diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 5674bd01d96d..de0435e63b02 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -297,8 +297,8 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu struct sk_buff *skb; struct net_device *ifp; - read_lock(&dev_base_lock); - for_each_netdev(&init_net, ifp) { + rcu_read_lock(); + for_each_netdev_rcu(&init_net, ifp) { dev_hold(ifp); if (!is_aoe_netif(ifp)) goto cont; @@ -325,7 +325,7 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu cont: dev_put(ifp); } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static void diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index a5ea1bce9689..c15fd2ea56c1 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -200,7 +200,7 @@ static int addr4_resolve(struct sockaddr_in *src_in, src_in->sin_family = AF_INET; src_in->sin_addr.s_addr = rt->rt_src; - if (rt->idev->dev->flags & IFF_LOOPBACK) { + if (rt->dst.dev->flags & IFF_LOOPBACK) { ret = rdma_translate_ip((struct sockaddr *) dst_in, addr); if (!ret) memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN); @@ -208,12 +208,12 @@ static int addr4_resolve(struct sockaddr_in *src_in, } /* If the device does ARP internally, return 'done' */ - if (rt->idev->dev->flags & IFF_NOARP) { - rdma_copy_addr(addr, rt->idev->dev, NULL); + if (rt->dst.dev->flags & IFF_NOARP) { + rdma_copy_addr(addr, rt->dst.dev, NULL); goto put; } - neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->idev->dev); + neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->dst.dev); if (!neigh || !(neigh->nud_state & NUD_VALID)) { neigh_event_send(rt->dst.neighbour, NULL); ret = -ENODATA; diff --git a/drivers/net/3c507.c b/drivers/net/3c507.c index ea9b7a098c9b..475a66d95b34 100644 --- a/drivers/net/3c507.c +++ b/drivers/net/3c507.c @@ -201,7 +201,7 @@ struct net_local { #define RX_BUF_SIZE (1518+14+18) /* packet+header+RBD */ #define RX_BUF_END (dev->mem_end - dev->mem_start) -#define TX_TIMEOUT 5 +#define TX_TIMEOUT (HZ/20) /* That's it: only 86 bytes to set up the beast, including every extra diff --git a/drivers/net/3c515.c b/drivers/net/3c515.c index cdf7226a7c43..d2bb4b254c57 100644 --- a/drivers/net/3c515.c +++ b/drivers/net/3c515.c @@ -98,7 +98,7 @@ static int rx_nocopy, rx_copy, queued_packet; #define WAIT_TX_AVAIL 200 /* Operational parameter that usually are not changed. */ -#define TX_TIMEOUT 40 /* Time in jiffies before concluding Tx hung */ +#define TX_TIMEOUT ((4*HZ)/10) /* Time in jiffies before concluding Tx hung */ /* The size here is somewhat misleading: the Corkscrew also uses the ISA aliased registers at <base>+0x400. diff --git a/drivers/net/82596.c b/drivers/net/82596.c index e2c9c5b949f9..be1f1970c842 100644 --- a/drivers/net/82596.c +++ b/drivers/net/82596.c @@ -191,7 +191,7 @@ enum commands { #define RX_SUSPEND 0x0030 #define RX_ABORT 0x0040 -#define TX_TIMEOUT 5 +#define TX_TIMEOUT (HZ/20) struct i596_reg { diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index f6668cdaac85..0a7e6cea0082 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -1533,7 +1533,7 @@ config E100 <http://support.intel.com/support/network/adapter/pro100/21397.htm> - to identify the adapter. + to identify the adapter. For the latest Intel PRO/100 network driver for Linux, see: @@ -1786,17 +1786,17 @@ config KS8842 tristate "Micrel KSZ8841/42 with generic bus interface" depends on HAS_IOMEM && DMA_ENGINE help - This platform driver is for KSZ8841(1-port) / KS8842(2-port) - ethernet switch chip (managed, VLAN, QoS) from Micrel or - Timberdale(FPGA). + This platform driver is for KSZ8841(1-port) / KS8842(2-port) + ethernet switch chip (managed, VLAN, QoS) from Micrel or + Timberdale(FPGA). config KS8851 - tristate "Micrel KS8851 SPI" - depends on SPI - select MII + tristate "Micrel KS8851 SPI" + depends on SPI + select MII select CRC32 - help - SPI driver for Micrel KS8851 SPI attached network chip. + help + SPI driver for Micrel KS8851 SPI attached network chip. config KS8851_MLL tristate "Micrel KS8851 MLL" @@ -2133,25 +2133,25 @@ config IP1000 will be called ipg. This is recommended. config IGB - tristate "Intel(R) 82575/82576 PCI-Express Gigabit Ethernet support" - depends on PCI - ---help--- - This driver supports Intel(R) 82575/82576 gigabit ethernet family of - adapters. For more information on how to identify your adapter, go - to the Adapter & Driver ID Guide at: + tristate "Intel(R) 82575/82576 PCI-Express Gigabit Ethernet support" + depends on PCI + ---help--- + This driver supports Intel(R) 82575/82576 gigabit ethernet family of + adapters. For more information on how to identify your adapter, go + to the Adapter & Driver ID Guide at: - <http://support.intel.com/support/network/adapter/pro100/21397.htm> + <http://support.intel.com/support/network/adapter/pro100/21397.htm> - For general information and support, go to the Intel support - website at: + For general information and support, go to the Intel support + website at: - <http://support.intel.com> + <http://support.intel.com> - More specific information on configuring the driver is in - <file:Documentation/networking/e1000.txt>. + More specific information on configuring the driver is in + <file:Documentation/networking/e1000.txt>. - To compile this driver as a module, choose M here. The module - will be called igb. + To compile this driver as a module, choose M here. The module + will be called igb. config IGB_DCA bool "Direct Cache Access (DCA) Support" @@ -2163,25 +2163,25 @@ config IGB_DCA is used, with the intent of lessening the impact of cache misses. config IGBVF - tristate "Intel(R) 82576 Virtual Function Ethernet support" - depends on PCI - ---help--- - This driver supports Intel(R) 82576 virtual functions. For more - information on how to identify your adapter, go to the Adapter & - Driver ID Guide at: + tristate "Intel(R) 82576 Virtual Function Ethernet support" + depends on PCI + ---help--- + This driver supports Intel(R) 82576 virtual functions. For more + information on how to identify your adapter, go to the Adapter & + Driver ID Guide at: - <http://support.intel.com/support/network/adapter/pro100/21397.htm> + <http://support.intel.com/support/network/adapter/pro100/21397.htm> - For general information and support, go to the Intel support - website at: + For general information and support, go to the Intel support + website at: - <http://support.intel.com> + <http://support.intel.com> - More specific information on configuring the driver is in - <file:Documentation/networking/e1000.txt>. + More specific information on configuring the driver is in + <file:Documentation/networking/e1000.txt>. - To compile this driver as a module, choose M here. The module - will be called igbvf. + To compile this driver as a module, choose M here. The module + will be called igbvf. source "drivers/net/ixp2000/Kconfig" @@ -2300,14 +2300,14 @@ config SKGE will be called skge. This is recommended. config SKGE_DEBUG - bool "Debugging interface" - depends on SKGE && DEBUG_FS - help - This option adds the ability to dump driver state for debugging. - The file /sys/kernel/debug/skge/ethX displays the state of the internal - transmit and receive rings. + bool "Debugging interface" + depends on SKGE && DEBUG_FS + help + This option adds the ability to dump driver state for debugging. + The file /sys/kernel/debug/skge/ethX displays the state of the internal + transmit and receive rings. - If unsure, say N. + If unsure, say N. config SKY2 tristate "SysKonnect Yukon2 support" @@ -2326,14 +2326,14 @@ config SKY2 will be called sky2. This is recommended. config SKY2_DEBUG - bool "Debugging interface" - depends on SKY2 && DEBUG_FS - help - This option adds the ability to dump driver state for debugging. - The file /sys/kernel/debug/sky2/ethX displays the state of the internal - transmit and receive rings. + bool "Debugging interface" + depends on SKY2 && DEBUG_FS + help + This option adds the ability to dump driver state for debugging. + The file /sys/kernel/debug/sky2/ethX displays the state of the internal + transmit and receive rings. - If unsure, say N. + If unsure, say N. config VIA_VELOCITY tristate "VIA Velocity support" @@ -2573,32 +2573,32 @@ config MDIO tristate config CHELSIO_T1 - tristate "Chelsio 10Gb Ethernet support" - depends on PCI + tristate "Chelsio 10Gb Ethernet support" + depends on PCI select CRC32 select MDIO - help - This driver supports Chelsio gigabit and 10-gigabit - Ethernet cards. More information about adapter features and + help + This driver supports Chelsio gigabit and 10-gigabit + Ethernet cards. More information about adapter features and performance tuning is in <file:Documentation/networking/cxgb.txt>. - For general information about Chelsio and our products, visit - our website at <http://www.chelsio.com>. + For general information about Chelsio and our products, visit + our website at <http://www.chelsio.com>. - For customer support, please visit our customer support page at - <http://www.chelsio.com/support.html>. + For customer support, please visit our customer support page at + <http://www.chelsio.com/support.html>. - Please send feedback to <linux-bugs@chelsio.com>. + Please send feedback to <linux-bugs@chelsio.com>. - To compile this driver as a module, choose M here: the module - will be called cxgb. + To compile this driver as a module, choose M here: the module + will be called cxgb. config CHELSIO_T1_1G - bool "Chelsio gigabit Ethernet support" - depends on CHELSIO_T1 - help - Enables support for Chelsio's gigabit Ethernet PCI cards. If you - are using only 10G cards say 'N' here. + bool "Chelsio gigabit Ethernet support" + depends on CHELSIO_T1 + help + Enables support for Chelsio's gigabit Ethernet PCI cards. If you + are using only 10G cards say 'N' here. config CHELSIO_T3_DEPENDS tristate @@ -2728,26 +2728,26 @@ config IXGBE_DCB If unsure, say N. config IXGBEVF - tristate "Intel(R) 82599 Virtual Function Ethernet support" - depends on PCI_MSI - ---help--- - This driver supports Intel(R) 82599 virtual functions. For more - information on how to identify your adapter, go to the Adapter & - Driver ID Guide at: + tristate "Intel(R) 82599 Virtual Function Ethernet support" + depends on PCI_MSI + ---help--- + This driver supports Intel(R) 82599 virtual functions. For more + information on how to identify your adapter, go to the Adapter & + Driver ID Guide at: - <http://support.intel.com/support/network/sb/CS-008441.htm> + <http://support.intel.com/support/network/sb/CS-008441.htm> - For general information and support, go to the Intel support - website at: + For general information and support, go to the Intel support + website at: - <http://support.intel.com> + <http://support.intel.com> - More specific information on configuring the driver is in - <file:Documentation/networking/ixgbevf.txt>. + More specific information on configuring the driver is in + <file:Documentation/networking/ixgbevf.txt>. - To compile this driver as a module, choose M here. The module - will be called ixgbevf. MSI-X interrupt support is required - for this driver to work correctly. + To compile this driver as a module, choose M here. The module + will be called ixgbevf. MSI-X interrupt support is required + for this driver to work correctly. config IXGB tristate "Intel(R) PRO/10GbE support" @@ -2772,29 +2772,38 @@ config IXGB will be called ixgb. config S2IO - tristate "S2IO 10Gbe XFrame NIC" + tristate "Exar Xframe 10Gb Ethernet Adapter" depends on PCI ---help--- - This driver supports the 10Gbe XFrame NIC of S2IO. + This driver supports Exar Corp's Xframe Series 10Gb Ethernet Adapters. + More specific information on configuring the driver is in <file:Documentation/networking/s2io.txt>. + To compile this driver as a module, choose M here. The module + will be called s2io. + config VXGE - tristate "Neterion X3100 Series 10GbE PCIe Server Adapter" + tristate "Exar X3100 Series 10GbE PCIe Server Adapter" depends on PCI && INET ---help--- - This driver supports Neterion Inc's X3100 Series 10 GbE PCIe + This driver supports Exar Corp's X3100 Series 10 GbE PCIe I/O Virtualized Server Adapter. + More specific information on configuring the driver is in <file:Documentation/networking/vxge.txt>. + To compile this driver as a module, choose M here. The module + will be called vxge. + config VXGE_DEBUG_TRACE_ALL bool "Enabling All Debug trace statments in driver" default n depends on VXGE ---help--- Say Y here if you want to enabling all the debug trace statements in - driver. By default only few debug trace statements are enabled. + the vxge driver. By default only few debug trace statements are + enabled. config MYRI10GE tristate "Myricom Myri-10G Ethernet support" @@ -2906,18 +2915,18 @@ config QLGE will be called qlge. config BNA - tristate "Brocade 1010/1020 10Gb Ethernet Driver support" - depends on PCI - ---help--- - This driver supports Brocade 1010/1020 10Gb CEE capable Ethernet - cards. - To compile this driver as a module, choose M here: the module - will be called bna. + tristate "Brocade 1010/1020 10Gb Ethernet Driver support" + depends on PCI + ---help--- + This driver supports Brocade 1010/1020 10Gb CEE capable Ethernet + cards. + To compile this driver as a module, choose M here: the module + will be called bna. - For general information and support, go to the Brocade support - website at: + For general information and support, go to the Brocade support + website at: - <http://support.brocade.com> + <http://support.brocade.com> source "drivers/net/sfc/Kconfig" @@ -3227,18 +3236,18 @@ config PPP_BSDCOMP modules once you have said "make modules". If unsure, say N. config PPP_MPPE - tristate "PPP MPPE compression (encryption) (EXPERIMENTAL)" - depends on PPP && EXPERIMENTAL - select CRYPTO - select CRYPTO_SHA1 - select CRYPTO_ARC4 - select CRYPTO_ECB - ---help--- - Support for the MPPE Encryption protocol, as employed by the - Microsoft Point-to-Point Tunneling Protocol. - - See http://pptpclient.sourceforge.net/ for information on - configuring PPTP clients and servers to utilize this method. + tristate "PPP MPPE compression (encryption) (EXPERIMENTAL)" + depends on PPP && EXPERIMENTAL + select CRYPTO + select CRYPTO_SHA1 + select CRYPTO_ARC4 + select CRYPTO_ECB + ---help--- + Support for the MPPE Encryption protocol, as employed by the + Microsoft Point-to-Point Tunneling Protocol. + + See http://pptpclient.sourceforge.net/ for information on + configuring PPTP clients and servers to utilize this method. config PPPOE tristate "PPP over Ethernet (EXPERIMENTAL)" @@ -3397,14 +3406,14 @@ config VIRTIO_NET depends on EXPERIMENTAL && VIRTIO ---help--- This is the virtual network driver for virtio. It can be used with - lguest or QEMU based VMMs (like KVM or Xen). Say Y or M. + lguest or QEMU based VMMs (like KVM or Xen). Say Y or M. config VMXNET3 - tristate "VMware VMXNET3 ethernet driver" - depends on PCI && INET - help - This driver supports VMware's vmxnet3 virtual ethernet NIC. - To compile this driver as a module, choose M here: the - module will be called vmxnet3. + tristate "VMware VMXNET3 ethernet driver" + depends on PCI && INET + help + This driver supports VMware's vmxnet3 virtual ethernet NIC. + To compile this driver as a module, choose M here: the + module will be called vmxnet3. endif # NETDEVICES diff --git a/drivers/net/arm/w90p910_ether.c b/drivers/net/arm/w90p910_ether.c index 4545d5a06c24..bfea499a3513 100644 --- a/drivers/net/arm/w90p910_ether.c +++ b/drivers/net/arm/w90p910_ether.c @@ -117,7 +117,7 @@ #define TX_DESC_SIZE 10 #define MAX_RBUFF_SZ 0x600 #define MAX_TBUFF_SZ 0x600 -#define TX_TIMEOUT 50 +#define TX_TIMEOUT (HZ/2) #define DELAY 1000 #define CAM0 0x0 diff --git a/drivers/net/at1700.c b/drivers/net/at1700.c index 89876897a6fe..871b1633f543 100644 --- a/drivers/net/at1700.c +++ b/drivers/net/at1700.c @@ -150,7 +150,7 @@ struct net_local { #define PORT_OFFSET(o) (o) -#define TX_TIMEOUT 10 +#define TX_TIMEOUT (HZ/10) /* Index to functions, as function prototypes. */ diff --git a/drivers/net/atarilance.c b/drivers/net/atarilance.c index 8cb27cb7bca1..ce0091eb06f5 100644 --- a/drivers/net/atarilance.c +++ b/drivers/net/atarilance.c @@ -116,7 +116,7 @@ MODULE_LICENSE("GPL"); #define RX_RING_LEN_BITS (RX_LOG_RING_SIZE << 5) #define RX_RING_MOD_MASK (RX_RING_SIZE - 1) -#define TX_TIMEOUT 20 +#define TX_TIMEOUT (HZ/5) /* The LANCE Rx and Tx ring descriptors. */ struct lance_rx_head { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index bdb68a600382..518844852f06 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3209,7 +3209,7 @@ out: #ifdef CONFIG_PROC_FS static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(&dev_base_lock) + __acquires(RCU) __acquires(&bond->lock) { struct bonding *bond = seq->private; @@ -3218,7 +3218,7 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) int i; /* make sure the bond won't be taken away */ - read_lock(&dev_base_lock); + rcu_read_lock(); read_lock(&bond->lock); if (*pos == 0) @@ -3248,12 +3248,12 @@ static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void bond_info_seq_stop(struct seq_file *seq, void *v) __releases(&bond->lock) - __releases(&dev_base_lock) + __releases(RCU) { struct bonding *bond = seq->private; read_unlock(&bond->lock); - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static void bond_info_show_master(struct seq_file *seq) diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c index 64c378cd0c34..74cd880c7e06 100644 --- a/drivers/net/can/mscan/mscan.c +++ b/drivers/net/can/mscan/mscan.c @@ -182,7 +182,7 @@ static int mscan_restart(struct net_device *dev) priv->can.state = CAN_STATE_ERROR_ACTIVE; WARN(!(in_8(®s->canmisc) & MSCAN_BOHOLD), - "bus-off state expected"); + "bus-off state expected\n"); out_8(®s->canmisc, MSCAN_BOHOLD); /* Re-enable receive interrupts. */ out_8(®s->canrier, MSCAN_RX_INTS_ENABLE); diff --git a/drivers/net/eepro.c b/drivers/net/eepro.c index 7c826319ee5a..9e19fbc2f176 100644 --- a/drivers/net/eepro.c +++ b/drivers/net/eepro.c @@ -302,7 +302,7 @@ struct eepro_local { #define ee_id_eepro10p0 0x10 /* ID for eepro/10+ */ #define ee_id_eepro10p1 0x31 -#define TX_TIMEOUT 40 +#define TX_TIMEOUT ((4*HZ)/10) /* Index to functions, as function prototypes. */ diff --git a/drivers/net/ks8851.c b/drivers/net/ks8851.c index 51919fcd50c2..0fa4a9887ba2 100644 --- a/drivers/net/ks8851.c +++ b/drivers/net/ks8851.c @@ -1545,6 +1545,37 @@ static int ks8851_read_selftest(struct ks8851_net *ks) /* driver bus management functions */ +#ifdef CONFIG_PM +static int ks8851_suspend(struct spi_device *spi, pm_message_t state) +{ + struct ks8851_net *ks = dev_get_drvdata(&spi->dev); + struct net_device *dev = ks->netdev; + + if (netif_running(dev)) { + netif_device_detach(dev); + ks8851_net_stop(dev); + } + + return 0; +} + +static int ks8851_resume(struct spi_device *spi) +{ + struct ks8851_net *ks = dev_get_drvdata(&spi->dev); + struct net_device *dev = ks->netdev; + + if (netif_running(dev)) { + ks8851_net_open(dev); + netif_device_attach(dev); + } + + return 0; +} +#else +#define ks8851_suspend NULL +#define ks8851_resume NULL +#endif + static int __devinit ks8851_probe(struct spi_device *spi) { struct net_device *ndev; @@ -1679,6 +1710,8 @@ static struct spi_driver ks8851_driver = { }, .probe = ks8851_probe, .remove = __devexit_p(ks8851_remove), + .suspend = ks8851_suspend, + .resume = ks8851_resume, }; static int __init ks8851_init(void) diff --git a/drivers/net/lance.c b/drivers/net/lance.c index f06296bfe293..02336edce748 100644 --- a/drivers/net/lance.c +++ b/drivers/net/lance.c @@ -207,7 +207,7 @@ tx_full and tbusy flags. #define LANCE_BUS_IF 0x16 #define LANCE_TOTAL_SIZE 0x18 -#define TX_TIMEOUT 20 +#define TX_TIMEOUT (HZ/5) /* The LANCE Rx and Tx ring descriptors. */ struct lance_rx_head { diff --git a/drivers/net/lib82596.c b/drivers/net/lib82596.c index c27f4291b350..9e042894479b 100644 --- a/drivers/net/lib82596.c +++ b/drivers/net/lib82596.c @@ -161,7 +161,7 @@ enum commands { #define RX_SUSPEND 0x0030 #define RX_ABORT 0x0040 -#define TX_TIMEOUT 5 +#define TX_TIMEOUT (HZ/20) struct i596_reg { diff --git a/drivers/net/qlge/qlge.h b/drivers/net/qlge/qlge.h index 22821398fc63..bdb8fe868539 100644 --- a/drivers/net/qlge/qlge.h +++ b/drivers/net/qlge/qlge.h @@ -16,7 +16,7 @@ */ #define DRV_NAME "qlge" #define DRV_STRING "QLogic 10 Gigabit PCI-E Ethernet Driver " -#define DRV_VERSION "v1.00.00.25.00.00-01" +#define DRV_VERSION "v1.00.00.27.00.00-01" #define WQ_ADDR_ALIGN 0x3 /* 4 byte alignment */ @@ -2221,6 +2221,7 @@ int ql_write_mpi_reg(struct ql_adapter *qdev, u32 reg, u32 data); int ql_unpause_mpi_risc(struct ql_adapter *qdev); int ql_pause_mpi_risc(struct ql_adapter *qdev); int ql_hard_reset_mpi_risc(struct ql_adapter *qdev); +int ql_soft_reset_mpi_risc(struct ql_adapter *qdev); int ql_dump_risc_ram_area(struct ql_adapter *qdev, void *buf, u32 ram_addr, int word_count); int ql_core_dump(struct ql_adapter *qdev, @@ -2236,6 +2237,7 @@ int ql_mb_set_mgmnt_traffic_ctl(struct ql_adapter *qdev, u32 control); int ql_mb_get_port_cfg(struct ql_adapter *qdev); int ql_mb_set_port_cfg(struct ql_adapter *qdev); int ql_wait_fifo_empty(struct ql_adapter *qdev); +void ql_get_dump(struct ql_adapter *qdev, void *buff); void ql_gen_reg_dump(struct ql_adapter *qdev, struct ql_reg_dump *mpi_coredump); netdev_tx_t ql_lb_send(struct sk_buff *skb, struct net_device *ndev); diff --git a/drivers/net/qlge/qlge_dbg.c b/drivers/net/qlge/qlge_dbg.c index 4747492935ef..fca804f36d61 100644 --- a/drivers/net/qlge/qlge_dbg.c +++ b/drivers/net/qlge/qlge_dbg.c @@ -1317,9 +1317,28 @@ void ql_gen_reg_dump(struct ql_adapter *qdev, status = ql_get_ets_regs(qdev, &mpi_coredump->ets[0]); if (status) return; +} + +void ql_get_dump(struct ql_adapter *qdev, void *buff) +{ + /* + * If the dump has already been taken and is stored + * in our internal buffer and if force dump is set then + * just start the spool to dump it to the log file + * and also, take a snapshot of the general regs to + * to the user's buffer or else take complete dump + * to the user's buffer if force is not set. + */ - if (test_bit(QL_FRC_COREDUMP, &qdev->flags)) + if (!test_bit(QL_FRC_COREDUMP, &qdev->flags)) { + if (!ql_core_dump(qdev, buff)) + ql_soft_reset_mpi_risc(qdev); + else + netif_err(qdev, drv, qdev->ndev, "coredump failed!\n"); + } else { + ql_gen_reg_dump(qdev, buff); ql_get_core_dump(qdev); + } } /* Coredump to messages log file using separate worker thread */ diff --git a/drivers/net/qlge/qlge_ethtool.c b/drivers/net/qlge/qlge_ethtool.c index 4892d64f4e05..8149cc9de4ca 100644 --- a/drivers/net/qlge/qlge_ethtool.c +++ b/drivers/net/qlge/qlge_ethtool.c @@ -375,7 +375,10 @@ static void ql_get_drvinfo(struct net_device *ndev, strncpy(drvinfo->bus_info, pci_name(qdev->pdev), 32); drvinfo->n_stats = 0; drvinfo->testinfo_len = 0; - drvinfo->regdump_len = 0; + if (!test_bit(QL_FRC_COREDUMP, &qdev->flags)) + drvinfo->regdump_len = sizeof(struct ql_mpi_coredump); + else + drvinfo->regdump_len = sizeof(struct ql_reg_dump); drvinfo->eedump_len = 0; } @@ -547,7 +550,12 @@ static void ql_self_test(struct net_device *ndev, static int ql_get_regs_len(struct net_device *ndev) { - return sizeof(struct ql_reg_dump); + struct ql_adapter *qdev = netdev_priv(ndev); + + if (!test_bit(QL_FRC_COREDUMP, &qdev->flags)) + return sizeof(struct ql_mpi_coredump); + else + return sizeof(struct ql_reg_dump); } static void ql_get_regs(struct net_device *ndev, @@ -555,7 +563,12 @@ static void ql_get_regs(struct net_device *ndev, { struct ql_adapter *qdev = netdev_priv(ndev); - ql_gen_reg_dump(qdev, p); + ql_get_dump(qdev, p); + qdev->core_is_dumped = 0; + if (!test_bit(QL_FRC_COREDUMP, &qdev->flags)) + regs->len = sizeof(struct ql_mpi_coredump); + else + regs->len = sizeof(struct ql_reg_dump); } static int ql_get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) diff --git a/drivers/net/qlge/qlge_mpi.c b/drivers/net/qlge/qlge_mpi.c index 0e7c7c7ee164..100a462cc916 100644 --- a/drivers/net/qlge/qlge_mpi.c +++ b/drivers/net/qlge/qlge_mpi.c @@ -87,7 +87,7 @@ exit: return status; } -static int ql_soft_reset_mpi_risc(struct ql_adapter *qdev) +int ql_soft_reset_mpi_risc(struct ql_adapter *qdev) { int status; status = ql_write_mpi_reg(qdev, 0x00001010, 1); diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index b2bcf99e6f08..7d42f9a2c068 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -363,7 +363,7 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net) /* Paranoid */ if (skb->len > IPHETH_BUF_SIZE) { - WARN(1, "%s: skb too large: %d bytes", __func__, skb->len); + WARN(1, "%s: skb too large: %d bytes\n", __func__, skb->len); dev->net->stats.tx_dropped++; dev_kfree_skb_irq(skb); return NETDEV_TX_OK; diff --git a/drivers/net/vxge/vxge-config.c b/drivers/net/vxge/vxge-config.c index 906a3ca3676b..409c2e6053d0 100644 --- a/drivers/net/vxge/vxge-config.c +++ b/drivers/net/vxge/vxge-config.c @@ -19,19 +19,7 @@ #include "vxge-traffic.h" #include "vxge-config.h" - -static enum vxge_hw_status -__vxge_hw_fifo_create( - struct __vxge_hw_vpath_handle *vpath_handle, - struct vxge_hw_fifo_attr *attr); - -static enum vxge_hw_status -__vxge_hw_fifo_abort( - struct __vxge_hw_fifo *fifoh); - -static enum vxge_hw_status -__vxge_hw_fifo_reset( - struct __vxge_hw_fifo *ringh); +#include "vxge-main.h" static enum vxge_hw_status __vxge_hw_fifo_delete( @@ -71,53 +59,15 @@ __vxge_hw_blockpool_free(struct __vxge_hw_device *hldev, u32 size, struct vxge_hw_mempool_dma *dma_object); - -static struct __vxge_hw_channel* -__vxge_hw_channel_allocate(struct __vxge_hw_vpath_handle *vph, - enum __vxge_hw_channel_type type, u32 length, - u32 per_dtr_space, void *userdata); - static void __vxge_hw_channel_free( struct __vxge_hw_channel *channel); -static enum vxge_hw_status -__vxge_hw_channel_initialize( - struct __vxge_hw_channel *channel); - -static enum vxge_hw_status -__vxge_hw_channel_reset( - struct __vxge_hw_channel *channel); - static enum vxge_hw_status __vxge_hw_ring_delete(struct __vxge_hw_vpath_handle *vp); static enum vxge_hw_status -__vxge_hw_device_fifo_config_check(struct vxge_hw_fifo_config *fifo_config); - -static enum vxge_hw_status __vxge_hw_device_config_check(struct vxge_hw_device_config *new_config); -static void -__vxge_hw_device_id_get(struct __vxge_hw_device *hldev); - -static void -__vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev); - -static enum vxge_hw_status -__vxge_hw_vpath_card_info_get( - u32 vp_id, - struct vxge_hw_vpath_reg __iomem *vpath_reg, - struct vxge_hw_device_hw_info *hw_info); - -static enum vxge_hw_status -__vxge_hw_device_initialize(struct __vxge_hw_device *hldev); - -static void -__vxge_hw_device_pci_e_init(struct __vxge_hw_device *hldev); - -static enum vxge_hw_status -__vxge_hw_device_reg_addr_get(struct __vxge_hw_device *hldev); - static enum vxge_hw_status __vxge_hw_device_register_poll( void __iomem *reg, @@ -138,9 +88,10 @@ __vxge_hw_pio_mem_write64(u64 val64, void __iomem *addr, static struct vxge_hw_mempool* __vxge_hw_mempool_create(struct __vxge_hw_device *devh, u32 memblock_size, - u32 item_size, u32 private_size, u32 items_initial, - u32 items_max, struct vxge_hw_mempool_cbs *mp_callback, - void *userdata); + u32 item_size, u32 private_size, u32 items_initial, + u32 items_max, struct vxge_hw_mempool_cbs *mp_callback, + void *userdata); + static void __vxge_hw_mempool_destroy(struct vxge_hw_mempool *mempool); static enum vxge_hw_status @@ -153,52 +104,353 @@ vxge_hw_vpath_stats_enable(struct __vxge_hw_vpath_handle *vpath_handle); static enum vxge_hw_status __vxge_hw_legacy_swapper_set(struct vxge_hw_legacy_reg __iomem *legacy_reg); -static u64 -__vxge_hw_vpath_pci_func_mode_get(u32 vp_id, - struct vxge_hw_vpath_reg __iomem *vpath_reg); - -static u32 -__vxge_hw_vpath_func_id_get(u32 vp_id, struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg); +static void +__vxge_hw_vp_terminate(struct __vxge_hw_device *devh, u32 vp_id); static enum vxge_hw_status -__vxge_hw_vpath_addr_get(u32 vp_id, struct vxge_hw_vpath_reg __iomem *vpath_reg, - u8 (macaddr)[ETH_ALEN], u8 (macaddr_mask)[ETH_ALEN]); +__vxge_hw_vpath_xmac_tx_stats_get(struct __vxge_hw_virtualpath *vpath, + struct vxge_hw_xmac_vpath_tx_stats *vpath_tx_stats); static enum vxge_hw_status -__vxge_hw_vpath_reset_check(struct __vxge_hw_virtualpath *vpath); +__vxge_hw_vpath_xmac_rx_stats_get(struct __vxge_hw_virtualpath *vpath, + struct vxge_hw_xmac_vpath_rx_stats *vpath_rx_stats); +static void +vxge_hw_vpath_set_zero_rx_frm_len(struct vxge_hw_vpath_reg __iomem *vp_reg) +{ + u64 val64; -static enum vxge_hw_status -__vxge_hw_vpath_sw_reset(struct __vxge_hw_device *devh, u32 vp_id); + val64 = readq(&vp_reg->rxmac_vcfg0); + val64 &= ~VXGE_HW_RXMAC_VCFG0_RTS_MAX_FRM_LEN(0x3fff); + writeq(val64, &vp_reg->rxmac_vcfg0); + val64 = readq(&vp_reg->rxmac_vcfg0); -static enum vxge_hw_status -__vxge_hw_vpath_fw_ver_get(u32 vp_id, struct vxge_hw_vpath_reg __iomem *vpath_reg, - struct vxge_hw_device_hw_info *hw_info); + return; +} -static enum vxge_hw_status -__vxge_hw_vpath_mac_configure(struct __vxge_hw_device *devh, u32 vp_id); +/* + * vxge_hw_vpath_wait_receive_idle - Wait for Rx to become idle + */ +int vxge_hw_vpath_wait_receive_idle(struct __vxge_hw_device *hldev, u32 vp_id) +{ + struct vxge_hw_vpath_reg __iomem *vp_reg; + struct __vxge_hw_virtualpath *vpath; + u64 val64, rxd_count, rxd_spat; + int count = 0, total_count = 0; -static void -__vxge_hw_vp_terminate(struct __vxge_hw_device *devh, u32 vp_id); + vpath = &hldev->virtual_paths[vp_id]; + vp_reg = vpath->vp_reg; -static enum vxge_hw_status -__vxge_hw_vpath_stats_access(struct __vxge_hw_virtualpath *vpath, - u32 operation, u32 offset, u64 *stat); + vxge_hw_vpath_set_zero_rx_frm_len(vp_reg); -static enum vxge_hw_status -__vxge_hw_vpath_xmac_tx_stats_get(struct __vxge_hw_virtualpath *vpath, - struct vxge_hw_xmac_vpath_tx_stats *vpath_tx_stats); + /* Check that the ring controller for this vpath has enough free RxDs + * to send frames to the host. This is done by reading the + * PRC_RXD_DOORBELL_VPn register and comparing the read value to the + * RXD_SPAT value for the vpath. + */ + val64 = readq(&vp_reg->prc_cfg6); + rxd_spat = VXGE_HW_PRC_CFG6_GET_RXD_SPAT(val64) + 1; + /* Use a factor of 2 when comparing rxd_count against rxd_spat for some + * leg room. + */ + rxd_spat *= 2; + + do { + mdelay(1); + + rxd_count = readq(&vp_reg->prc_rxd_doorbell); + + /* Check that the ring controller for this vpath does + * not have any frame in its pipeline. + */ + val64 = readq(&vp_reg->frm_in_progress_cnt); + if ((rxd_count <= rxd_spat) || (val64 > 0)) + count = 0; + else + count++; + total_count++; + } while ((count < VXGE_HW_MIN_SUCCESSIVE_IDLE_COUNT) && + (total_count < VXGE_HW_MAX_POLLING_COUNT)); + + if (total_count >= VXGE_HW_MAX_POLLING_COUNT) + printk(KERN_ALERT "%s: Still Receiving traffic. Abort wait\n", + __func__); + + return total_count; +} + +/* vxge_hw_device_wait_receive_idle - This function waits until all frames + * stored in the frame buffer for each vpath assigned to the given + * function (hldev) have been sent to the host. + */ +void vxge_hw_device_wait_receive_idle(struct __vxge_hw_device *hldev) +{ + int i, total_count = 0; + + for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) { + if (!(hldev->vpaths_deployed & vxge_mBIT(i))) + continue; + + total_count += vxge_hw_vpath_wait_receive_idle(hldev, i); + if (total_count >= VXGE_HW_MAX_POLLING_COUNT) + break; + } +} static enum vxge_hw_status -__vxge_hw_vpath_xmac_rx_stats_get(struct __vxge_hw_virtualpath *vpath, - struct vxge_hw_xmac_vpath_rx_stats *vpath_rx_stats); +vxge_hw_vpath_fw_api(struct __vxge_hw_virtualpath *vpath, u32 action, + u32 fw_memo, u32 offset, u64 *data0, u64 *data1, + u64 *steer_ctrl) +{ + struct vxge_hw_vpath_reg __iomem *vp_reg; + enum vxge_hw_status status; + u64 val64; + u32 retry = 0, max_retry = 100; + + vp_reg = vpath->vp_reg; + + if (vpath->vp_open) { + max_retry = 3; + spin_lock(&vpath->lock); + } + + writeq(*data0, &vp_reg->rts_access_steer_data0); + writeq(*data1, &vp_reg->rts_access_steer_data1); + wmb(); + + val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(action) | + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(fw_memo) | + VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(offset) | + VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | + *steer_ctrl; + + status = __vxge_hw_pio_mem_write64(val64, + &vp_reg->rts_access_steer_ctrl, + VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, + VXGE_HW_DEF_DEVICE_POLL_MILLIS); + + /* The __vxge_hw_device_register_poll can udelay for a significant + * amount of time, blocking other proccess from the CPU. If it delays + * for ~5secs, a NMI error can occur. A way around this is to give up + * the processor via msleep, but this is not allowed is under lock. + * So, only allow it to sleep for ~4secs if open. Otherwise, delay for + * 1sec and sleep for 10ms until the firmware operation has completed + * or timed-out. + */ + while ((status != VXGE_HW_OK) && retry++ < max_retry) { + if (!vpath->vp_open) + msleep(20); + status = __vxge_hw_device_register_poll( + &vp_reg->rts_access_steer_ctrl, + VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, + VXGE_HW_DEF_DEVICE_POLL_MILLIS); + } + + if (status != VXGE_HW_OK) + goto out; + + val64 = readq(&vp_reg->rts_access_steer_ctrl); + if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) { + *data0 = readq(&vp_reg->rts_access_steer_data0); + *data1 = readq(&vp_reg->rts_access_steer_data1); + *steer_ctrl = val64; + } else + status = VXGE_HW_FAIL; + +out: + if (vpath->vp_open) + spin_unlock(&vpath->lock); + return status; +} + +enum vxge_hw_status +vxge_hw_upgrade_read_version(struct __vxge_hw_device *hldev, u32 *major, + u32 *minor, u32 *build) +{ + u64 data0 = 0, data1 = 0, steer_ctrl = 0; + struct __vxge_hw_virtualpath *vpath; + enum vxge_hw_status status; + + vpath = &hldev->virtual_paths[hldev->first_vp_id]; + + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_FW_UPGRADE_ACTION, + VXGE_HW_FW_UPGRADE_MEMO, + VXGE_HW_FW_UPGRADE_OFFSET_READ, + &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) + return status; + + *major = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MAJOR(data0); + *minor = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MINOR(data0); + *build = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_BUILD(data0); + + return status; +} + +enum vxge_hw_status vxge_hw_flash_fw(struct __vxge_hw_device *hldev) +{ + u64 data0 = 0, data1 = 0, steer_ctrl = 0; + struct __vxge_hw_virtualpath *vpath; + enum vxge_hw_status status; + u32 ret; + + vpath = &hldev->virtual_paths[hldev->first_vp_id]; + + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_FW_UPGRADE_ACTION, + VXGE_HW_FW_UPGRADE_MEMO, + VXGE_HW_FW_UPGRADE_OFFSET_COMMIT, + &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) { + vxge_debug_init(VXGE_ERR, "%s: FW upgrade failed", __func__); + goto exit; + } + + ret = VXGE_HW_RTS_ACCESS_STEER_CTRL_GET_ACTION(steer_ctrl) & 0x7F; + if (ret != 1) { + vxge_debug_init(VXGE_ERR, "%s: FW commit failed with error %d", + __func__, ret); + status = VXGE_HW_FAIL; + } + +exit: + return status; +} + +enum vxge_hw_status +vxge_update_fw_image(struct __vxge_hw_device *hldev, const u8 *fwdata, int size) +{ + u64 data0 = 0, data1 = 0, steer_ctrl = 0; + struct __vxge_hw_virtualpath *vpath; + enum vxge_hw_status status; + int ret_code, sec_code; + + vpath = &hldev->virtual_paths[hldev->first_vp_id]; + + /* send upgrade start command */ + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_FW_UPGRADE_ACTION, + VXGE_HW_FW_UPGRADE_MEMO, + VXGE_HW_FW_UPGRADE_OFFSET_START, + &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) { + vxge_debug_init(VXGE_ERR, " %s: Upgrade start cmd failed", + __func__); + return status; + } + + /* Transfer fw image to adapter 16 bytes at a time */ + for (; size > 0; size -= VXGE_HW_FW_UPGRADE_BLK_SIZE) { + steer_ctrl = 0; + + /* The next 128bits of fwdata to be loaded onto the adapter */ + data0 = *((u64 *)fwdata); + data1 = *((u64 *)fwdata + 1); + + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_FW_UPGRADE_ACTION, + VXGE_HW_FW_UPGRADE_MEMO, + VXGE_HW_FW_UPGRADE_OFFSET_SEND, + &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) { + vxge_debug_init(VXGE_ERR, "%s: Upgrade send failed", + __func__); + goto out; + } + + ret_code = VXGE_HW_UPGRADE_GET_RET_ERR_CODE(data0); + switch (ret_code) { + case VXGE_HW_FW_UPGRADE_OK: + /* All OK, send next 16 bytes. */ + break; + case VXGE_FW_UPGRADE_BYTES2SKIP: + /* skip bytes in the stream */ + fwdata += (data0 >> 8) & 0xFFFFFFFF; + break; + case VXGE_HW_FW_UPGRADE_DONE: + goto out; + case VXGE_HW_FW_UPGRADE_ERR: + sec_code = VXGE_HW_UPGRADE_GET_SEC_ERR_CODE(data0); + switch (sec_code) { + case VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_1: + case VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_7: + printk(KERN_ERR + "corrupted data from .ncf file\n"); + break; + case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_3: + case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_4: + case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_5: + case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_6: + case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_8: + printk(KERN_ERR "invalid .ncf file\n"); + break; + case VXGE_HW_FW_UPGRADE_ERR_BUFFER_OVERFLOW: + printk(KERN_ERR "buffer overflow\n"); + break; + case VXGE_HW_FW_UPGRADE_ERR_FAILED_TO_FLASH: + printk(KERN_ERR "failed to flash the image\n"); + break; + case VXGE_HW_FW_UPGRADE_ERR_GENERIC_ERROR_UNKNOWN: + printk(KERN_ERR + "generic error. Unknown error type\n"); + break; + default: + printk(KERN_ERR "Unknown error of type %d\n", + sec_code); + break; + } + status = VXGE_HW_FAIL; + goto out; + default: + printk(KERN_ERR "Unknown FW error: %d\n", ret_code); + status = VXGE_HW_FAIL; + goto out; + } + /* point to next 16 bytes */ + fwdata += VXGE_HW_FW_UPGRADE_BLK_SIZE; + } +out: + return status; +} + +enum vxge_hw_status +vxge_hw_vpath_eprom_img_ver_get(struct __vxge_hw_device *hldev, + struct eprom_image *img) +{ + u64 data0 = 0, data1 = 0, steer_ctrl = 0; + struct __vxge_hw_virtualpath *vpath; + enum vxge_hw_status status; + int i; + + vpath = &hldev->virtual_paths[hldev->first_vp_id]; + + for (i = 0; i < VXGE_HW_MAX_ROM_IMAGES; i++) { + data0 = VXGE_HW_RTS_ACCESS_STEER_ROM_IMAGE_INDEX(i); + data1 = steer_ctrl = 0; + + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, + VXGE_HW_FW_API_GET_EPROM_REV, + 0, &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) + break; + + img[i].is_valid = VXGE_HW_GET_EPROM_IMAGE_VALID(data0); + img[i].index = VXGE_HW_GET_EPROM_IMAGE_INDEX(data0); + img[i].type = VXGE_HW_GET_EPROM_IMAGE_TYPE(data0); + img[i].version = VXGE_HW_GET_EPROM_IMAGE_REV(data0); + } + + return status; +} /* * __vxge_hw_channel_allocate - Allocate memory for channel * This function allocates required memory for the channel and various arrays * in the channel */ -struct __vxge_hw_channel* +static struct __vxge_hw_channel * __vxge_hw_channel_allocate(struct __vxge_hw_vpath_handle *vph, enum __vxge_hw_channel_type type, u32 length, u32 per_dtr_space, void *userdata) @@ -269,7 +521,7 @@ exit0: * This function deallocates memory from the channel and various arrays * in the channel */ -void __vxge_hw_channel_free(struct __vxge_hw_channel *channel) +static void __vxge_hw_channel_free(struct __vxge_hw_channel *channel) { kfree(channel->work_arr); kfree(channel->free_arr); @@ -283,7 +535,7 @@ void __vxge_hw_channel_free(struct __vxge_hw_channel *channel) * This function initializes a channel by properly setting the * various references */ -enum vxge_hw_status +static enum vxge_hw_status __vxge_hw_channel_initialize(struct __vxge_hw_channel *channel) { u32 i; @@ -318,7 +570,7 @@ __vxge_hw_channel_initialize(struct __vxge_hw_channel *channel) * __vxge_hw_channel_reset - Resets a channel * This function resets a channel by properly setting the various references */ -enum vxge_hw_status +static enum vxge_hw_status __vxge_hw_channel_reset(struct __vxge_hw_channel *channel) { u32 i; @@ -345,8 +597,7 @@ __vxge_hw_channel_reset(struct __vxge_hw_channel *channel) * Initialize certain PCI/PCI-X configuration registers * with recommended values. Save config space for future hw resets. */ -void -__vxge_hw_device_pci_e_init(struct __vxge_hw_device *hldev) +static void __vxge_hw_device_pci_e_init(struct __vxge_hw_device *hldev) { u16 cmd = 0; @@ -390,7 +641,7 @@ __vxge_hw_device_register_poll(void __iomem *reg, u64 mask, u32 max_millis) return ret; } - /* __vxge_hw_device_vpath_reset_in_prog_check - Check if vpath reset +/* __vxge_hw_device_vpath_reset_in_prog_check - Check if vpath reset * in progress * This routine checks the vpath reset in progress register is turned zero */ @@ -435,7 +686,7 @@ exit: * register location pointers in the device object. It waits until the ric is * completed initializing registers. */ -enum vxge_hw_status +static enum vxge_hw_status __vxge_hw_device_reg_addr_get(struct __vxge_hw_device *hldev) { u64 val64; @@ -496,26 +747,6 @@ exit: } /* - * __vxge_hw_device_id_get - * This routine returns sets the device id and revision numbers into the device - * structure - */ -void __vxge_hw_device_id_get(struct __vxge_hw_device *hldev) -{ - u64 val64; - - val64 = readq(&hldev->common_reg->titan_asic_id); - hldev->device_id = - (u16)VXGE_HW_TITAN_ASIC_ID_GET_INITIAL_DEVICE_ID(val64); - - hldev->major_revision = - (u8)VXGE_HW_TITAN_ASIC_ID_GET_INITIAL_MAJOR_REVISION(val64); - - hldev->minor_revision = - (u8)VXGE_HW_TITAN_ASIC_ID_GET_INITIAL_MINOR_REVISION(val64); -} - -/* * __vxge_hw_device_access_rights_get: Get Access Rights of the driver * This routine returns the Access Rights of the driver */ @@ -568,10 +799,25 @@ __vxge_hw_device_is_privilaged(u32 host_type, u32 func_id) } /* + * __vxge_hw_vpath_func_id_get - Get the function id of the vpath. + * Returns the function number of the vpath. + */ +static u32 +__vxge_hw_vpath_func_id_get(struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg) +{ + u64 val64; + + val64 = readq(&vpmgmt_reg->vpath_to_func_map_cfg1); + + return + (u32)VXGE_HW_VPATH_TO_FUNC_MAP_CFG1_GET_VPATH_TO_FUNC_MAP_CFG1(val64); +} + +/* * __vxge_hw_device_host_info_get * This routine returns the host type assignments */ -void __vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev) +static void __vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev) { u64 val64; u32 i; @@ -584,16 +830,18 @@ void __vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev) hldev->vpath_assignments = readq(&hldev->common_reg->vpath_assignments); for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) { - if (!(hldev->vpath_assignments & vxge_mBIT(i))) continue; hldev->func_id = - __vxge_hw_vpath_func_id_get(i, hldev->vpmgmt_reg[i]); + __vxge_hw_vpath_func_id_get(hldev->vpmgmt_reg[i]); hldev->access_rights = __vxge_hw_device_access_rights_get( hldev->host_type, hldev->func_id); + hldev->virtual_paths[i].vp_open = VXGE_HW_VP_NOT_OPEN; + hldev->virtual_paths[i].vp_reg = hldev->vpath_reg[i]; + hldev->first_vp_id = i; break; } @@ -634,7 +882,8 @@ __vxge_hw_verify_pci_e_info(struct __vxge_hw_device *hldev) * __vxge_hw_device_initialize * Initialize Titan-V hardware. */ -enum vxge_hw_status __vxge_hw_device_initialize(struct __vxge_hw_device *hldev) +static enum vxge_hw_status +__vxge_hw_device_initialize(struct __vxge_hw_device *hldev) { enum vxge_hw_status status = VXGE_HW_OK; @@ -650,6 +899,196 @@ exit: return status; } +/* + * __vxge_hw_vpath_fw_ver_get - Get the fw version + * Returns FW Version + */ +static enum vxge_hw_status +__vxge_hw_vpath_fw_ver_get(struct __vxge_hw_virtualpath *vpath, + struct vxge_hw_device_hw_info *hw_info) +{ + struct vxge_hw_device_version *fw_version = &hw_info->fw_version; + struct vxge_hw_device_date *fw_date = &hw_info->fw_date; + struct vxge_hw_device_version *flash_version = &hw_info->flash_version; + struct vxge_hw_device_date *flash_date = &hw_info->flash_date; + u64 data0, data1 = 0, steer_ctrl = 0; + enum vxge_hw_status status; + + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_ENTRY, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, + 0, &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) + goto exit; + + fw_date->day = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_DAY(data0); + fw_date->month = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MONTH(data0); + fw_date->year = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_YEAR(data0); + + snprintf(fw_date->date, VXGE_HW_FW_STRLEN, "%2.2d/%2.2d/%4.4d", + fw_date->month, fw_date->day, fw_date->year); + + fw_version->major = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MAJOR(data0); + fw_version->minor = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MINOR(data0); + fw_version->build = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_BUILD(data0); + + snprintf(fw_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d", + fw_version->major, fw_version->minor, fw_version->build); + + flash_date->day = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_DAY(data1); + flash_date->month = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MONTH(data1); + flash_date->year = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_YEAR(data1); + + snprintf(flash_date->date, VXGE_HW_FW_STRLEN, "%2.2d/%2.2d/%4.4d", + flash_date->month, flash_date->day, flash_date->year); + + flash_version->major = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MAJOR(data1); + flash_version->minor = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MINOR(data1); + flash_version->build = + (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_BUILD(data1); + + snprintf(flash_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d", + flash_version->major, flash_version->minor, + flash_version->build); + +exit: + return status; +} + +/* + * __vxge_hw_vpath_card_info_get - Get the serial numbers, + * part number and product description. + */ +static enum vxge_hw_status +__vxge_hw_vpath_card_info_get(struct __vxge_hw_virtualpath *vpath, + struct vxge_hw_device_hw_info *hw_info) +{ + enum vxge_hw_status status; + u64 data0, data1 = 0, steer_ctrl = 0; + u8 *serial_number = hw_info->serial_number; + u8 *part_number = hw_info->part_number; + u8 *product_desc = hw_info->product_desc; + u32 i, j = 0; + + data0 = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_SERIAL_NUMBER; + + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, + 0, &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) + return status; + + ((u64 *)serial_number)[0] = be64_to_cpu(data0); + ((u64 *)serial_number)[1] = be64_to_cpu(data1); + + data0 = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PART_NUMBER; + data1 = steer_ctrl = 0; + + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, + 0, &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) + return status; + + ((u64 *)part_number)[0] = be64_to_cpu(data0); + ((u64 *)part_number)[1] = be64_to_cpu(data1); + + for (i = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_0; + i <= VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_3; i++) { + data0 = i; + data1 = steer_ctrl = 0; + + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, + 0, &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) + return status; + + ((u64 *)product_desc)[j++] = be64_to_cpu(data0); + ((u64 *)product_desc)[j++] = be64_to_cpu(data1); + } + + return status; +} + +/* + * __vxge_hw_vpath_pci_func_mode_get - Get the pci mode + * Returns pci function mode + */ +static enum vxge_hw_status +__vxge_hw_vpath_pci_func_mode_get(struct __vxge_hw_virtualpath *vpath, + struct vxge_hw_device_hw_info *hw_info) +{ + u64 data0, data1 = 0, steer_ctrl = 0; + enum vxge_hw_status status; + + data0 = 0; + + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_FW_API_GET_FUNC_MODE, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, + 0, &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) + return status; + + hw_info->function_mode = VXGE_HW_GET_FUNC_MODE_VAL(data0); + return status; +} + +/* + * __vxge_hw_vpath_addr_get - Get the hw address entry for this vpath + * from MAC address table. + */ +static enum vxge_hw_status +__vxge_hw_vpath_addr_get(struct __vxge_hw_virtualpath *vpath, + u8 *macaddr, u8 *macaddr_mask) +{ + u64 action = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_FIRST_ENTRY, + data0 = 0, data1 = 0, steer_ctrl = 0; + enum vxge_hw_status status; + int i; + + do { + status = vxge_hw_vpath_fw_api(vpath, action, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA, + 0, &data0, &data1, &steer_ctrl); + if (status != VXGE_HW_OK) + goto exit; + + data0 = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(data0); + data1 = VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_DA_MAC_ADDR_MASK( + data1); + + for (i = ETH_ALEN; i > 0; i--) { + macaddr[i - 1] = (u8) (data0 & 0xFF); + data0 >>= 8; + + macaddr_mask[i - 1] = (u8) (data1 & 0xFF); + data1 >>= 8; + } + + action = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_NEXT_ENTRY; + data0 = 0, data1 = 0, steer_ctrl = 0; + + } while (!is_valid_ether_addr(macaddr)); +exit: + return status; +} + /** * vxge_hw_device_hw_info_get - Get the hw information * Returns the vpath mask that has the bits set for each vpath allocated @@ -665,9 +1104,9 @@ vxge_hw_device_hw_info_get(void __iomem *bar0, struct vxge_hw_toc_reg __iomem *toc; struct vxge_hw_mrpcim_reg __iomem *mrpcim_reg; struct vxge_hw_common_reg __iomem *common_reg; - struct vxge_hw_vpath_reg __iomem *vpath_reg; struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg; enum vxge_hw_status status; + struct __vxge_hw_virtualpath vpath; memset(hw_info, 0, sizeof(struct vxge_hw_device_hw_info)); @@ -702,7 +1141,7 @@ vxge_hw_device_hw_info_get(void __iomem *bar0, vpmgmt_reg = (struct vxge_hw_vpmgmt_reg __iomem *) (bar0 + val64); - hw_info->func_id = __vxge_hw_vpath_func_id_get(i, vpmgmt_reg); + hw_info->func_id = __vxge_hw_vpath_func_id_get(vpmgmt_reg); if (__vxge_hw_device_access_rights_get(hw_info->host_type, hw_info->func_id) & VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM) { @@ -718,16 +1157,19 @@ vxge_hw_device_hw_info_get(void __iomem *bar0, val64 = readq(&toc->toc_vpath_pointer[i]); - vpath_reg = (struct vxge_hw_vpath_reg __iomem *)(bar0 + val64); + vpath.vp_reg = (struct vxge_hw_vpath_reg __iomem *) + (bar0 + val64); + vpath.vp_open = 0; - hw_info->function_mode = - __vxge_hw_vpath_pci_func_mode_get(i, vpath_reg); + status = __vxge_hw_vpath_pci_func_mode_get(&vpath, hw_info); + if (status != VXGE_HW_OK) + goto exit; - status = __vxge_hw_vpath_fw_ver_get(i, vpath_reg, hw_info); + status = __vxge_hw_vpath_fw_ver_get(&vpath, hw_info); if (status != VXGE_HW_OK) goto exit; - status = __vxge_hw_vpath_card_info_get(i, vpath_reg, hw_info); + status = __vxge_hw_vpath_card_info_get(&vpath, hw_info); if (status != VXGE_HW_OK) goto exit; @@ -735,14 +1177,15 @@ vxge_hw_device_hw_info_get(void __iomem *bar0, } for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) { - if (!((hw_info->vpath_mask) & vxge_mBIT(i))) continue; val64 = readq(&toc->toc_vpath_pointer[i]); - vpath_reg = (struct vxge_hw_vpath_reg __iomem *)(bar0 + val64); + vpath.vp_reg = (struct vxge_hw_vpath_reg __iomem *) + (bar0 + val64); + vpath.vp_open = 0; - status = __vxge_hw_vpath_addr_get(i, vpath_reg, + status = __vxge_hw_vpath_addr_get(&vpath, hw_info->mac_addrs[i], hw_info->mac_addr_masks[i]); if (status != VXGE_HW_OK) @@ -806,7 +1249,6 @@ vxge_hw_device_initialize( vfree(hldev); goto exit; } - __vxge_hw_device_id_get(hldev); __vxge_hw_device_host_info_get(hldev); @@ -814,7 +1256,6 @@ vxge_hw_device_initialize( nblocks++; for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) { - if (!(hldev->vpath_assignments & vxge_mBIT(i))) continue; @@ -839,7 +1280,6 @@ vxge_hw_device_initialize( } status = __vxge_hw_device_initialize(hldev); - if (status != VXGE_HW_OK) { vxge_hw_device_terminate(hldev); goto exit; @@ -876,7 +1316,6 @@ vxge_hw_device_stats_get(struct __vxge_hw_device *hldev, enum vxge_hw_status status = VXGE_HW_OK; for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) { - if (!(hldev->vpaths_deployed & vxge_mBIT(i)) || (hldev->virtual_paths[i].vp_open == VXGE_HW_VP_NOT_OPEN)) @@ -1165,7 +1604,6 @@ exit: * It can be used to set or reset Pause frame generation or reception * support of the NIC. */ - enum vxge_hw_status vxge_hw_device_setpause_data(struct __vxge_hw_device *hldev, u32 port, u32 tx, u32 rx) { @@ -1409,7 +1847,6 @@ exit: /* * __vxge_hw_ring_create - Create a Ring * This function creates Ring and initializes it. - * */ static enum vxge_hw_status __vxge_hw_ring_create(struct __vxge_hw_vpath_handle *vp, @@ -1845,7 +2282,7 @@ static void __vxge_hw_mempool_destroy(struct vxge_hw_mempool *mempool) * __vxge_hw_device_fifo_config_check - Check fifo configuration. * Check the fifo configuration */ -enum vxge_hw_status +static enum vxge_hw_status __vxge_hw_device_fifo_config_check(struct vxge_hw_fifo_config *fifo_config) { if ((fifo_config->fifo_blocks < VXGE_HW_MIN_FIFO_BLOCKS) || @@ -1893,7 +2330,7 @@ __vxge_hw_device_vpath_config_check(struct vxge_hw_vp_config *vp_config) * __vxge_hw_device_config_check - Check device configuration. * Check the device configuration */ -enum vxge_hw_status +static enum vxge_hw_status __vxge_hw_device_config_check(struct vxge_hw_device_config *new_config) { u32 i; @@ -2453,7 +2890,7 @@ __vxge_hw_fifo_mempool_item_alloc( * __vxge_hw_fifo_create - Create a FIFO * This function creates FIFO and initializes it. */ -enum vxge_hw_status +static enum vxge_hw_status __vxge_hw_fifo_create(struct __vxge_hw_vpath_handle *vp, struct vxge_hw_fifo_attr *attr) { @@ -2617,7 +3054,8 @@ static enum vxge_hw_status __vxge_hw_fifo_reset(struct __vxge_hw_fifo *fifo) * __vxge_hw_fifo_delete - Removes the FIFO * This function freeup the memory pool and removes the FIFO */ -enum vxge_hw_status __vxge_hw_fifo_delete(struct __vxge_hw_vpath_handle *vp) +static enum vxge_hw_status +__vxge_hw_fifo_delete(struct __vxge_hw_vpath_handle *vp) { struct __vxge_hw_fifo *fifo = vp->vpath->fifoh; @@ -2675,297 +3113,6 @@ exit: return status; } -/* - * __vxge_hw_vpath_func_id_get - Get the function id of the vpath. - * Returns the function number of the vpath. - */ -static u32 -__vxge_hw_vpath_func_id_get(u32 vp_id, - struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg) -{ - u64 val64; - - val64 = readq(&vpmgmt_reg->vpath_to_func_map_cfg1); - - return - (u32)VXGE_HW_VPATH_TO_FUNC_MAP_CFG1_GET_VPATH_TO_FUNC_MAP_CFG1(val64); -} - -/* - * __vxge_hw_read_rts_ds - Program RTS steering critieria - */ -static inline void -__vxge_hw_read_rts_ds(struct vxge_hw_vpath_reg __iomem *vpath_reg, - u64 dta_struct_sel) -{ - writeq(0, &vpath_reg->rts_access_steer_ctrl); - wmb(); - writeq(dta_struct_sel, &vpath_reg->rts_access_steer_data0); - writeq(0, &vpath_reg->rts_access_steer_data1); - wmb(); -} - - -/* - * __vxge_hw_vpath_card_info_get - Get the serial numbers, - * part number and product description. - */ -static enum vxge_hw_status -__vxge_hw_vpath_card_info_get( - u32 vp_id, - struct vxge_hw_vpath_reg __iomem *vpath_reg, - struct vxge_hw_device_hw_info *hw_info) -{ - u32 i, j; - u64 val64; - u64 data1 = 0ULL; - u64 data2 = 0ULL; - enum vxge_hw_status status = VXGE_HW_OK; - u8 *serial_number = hw_info->serial_number; - u8 *part_number = hw_info->part_number; - u8 *product_desc = hw_info->product_desc; - - __vxge_hw_read_rts_ds(vpath_reg, - VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_SERIAL_NUMBER); - - val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION( - VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL( - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | - VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0); - - status = __vxge_hw_pio_mem_write64(val64, - &vpath_reg->rts_access_steer_ctrl, - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, - VXGE_HW_DEF_DEVICE_POLL_MILLIS); - - if (status != VXGE_HW_OK) - return status; - - val64 = readq(&vpath_reg->rts_access_steer_ctrl); - - if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) { - data1 = readq(&vpath_reg->rts_access_steer_data0); - ((u64 *)serial_number)[0] = be64_to_cpu(data1); - - data2 = readq(&vpath_reg->rts_access_steer_data1); - ((u64 *)serial_number)[1] = be64_to_cpu(data2); - status = VXGE_HW_OK; - } else - *serial_number = 0; - - __vxge_hw_read_rts_ds(vpath_reg, - VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PART_NUMBER); - - val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION( - VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL( - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | - VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0); - - status = __vxge_hw_pio_mem_write64(val64, - &vpath_reg->rts_access_steer_ctrl, - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, - VXGE_HW_DEF_DEVICE_POLL_MILLIS); - - if (status != VXGE_HW_OK) - return status; - - val64 = readq(&vpath_reg->rts_access_steer_ctrl); - - if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) { - - data1 = readq(&vpath_reg->rts_access_steer_data0); - ((u64 *)part_number)[0] = be64_to_cpu(data1); - - data2 = readq(&vpath_reg->rts_access_steer_data1); - ((u64 *)part_number)[1] = be64_to_cpu(data2); - - status = VXGE_HW_OK; - - } else - *part_number = 0; - - j = 0; - - for (i = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_0; - i <= VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_3; i++) { - - __vxge_hw_read_rts_ds(vpath_reg, i); - - val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION( - VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL( - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | - VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0); - - status = __vxge_hw_pio_mem_write64(val64, - &vpath_reg->rts_access_steer_ctrl, - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, - VXGE_HW_DEF_DEVICE_POLL_MILLIS); - - if (status != VXGE_HW_OK) - return status; - - val64 = readq(&vpath_reg->rts_access_steer_ctrl); - - if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) { - - data1 = readq(&vpath_reg->rts_access_steer_data0); - ((u64 *)product_desc)[j++] = be64_to_cpu(data1); - - data2 = readq(&vpath_reg->rts_access_steer_data1); - ((u64 *)product_desc)[j++] = be64_to_cpu(data2); - - status = VXGE_HW_OK; - } else - *product_desc = 0; - } - - return status; -} - -/* - * __vxge_hw_vpath_fw_ver_get - Get the fw version - * Returns FW Version - */ -static enum vxge_hw_status -__vxge_hw_vpath_fw_ver_get( - u32 vp_id, - struct vxge_hw_vpath_reg __iomem *vpath_reg, - struct vxge_hw_device_hw_info *hw_info) -{ - u64 val64; - u64 data1 = 0ULL; - u64 data2 = 0ULL; - struct vxge_hw_device_version *fw_version = &hw_info->fw_version; - struct vxge_hw_device_date *fw_date = &hw_info->fw_date; - struct vxge_hw_device_version *flash_version = &hw_info->flash_version; - struct vxge_hw_device_date *flash_date = &hw_info->flash_date; - enum vxge_hw_status status = VXGE_HW_OK; - - val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION( - VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_ENTRY) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL( - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | - VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0); - - status = __vxge_hw_pio_mem_write64(val64, - &vpath_reg->rts_access_steer_ctrl, - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, - VXGE_HW_DEF_DEVICE_POLL_MILLIS); - - if (status != VXGE_HW_OK) - goto exit; - - val64 = readq(&vpath_reg->rts_access_steer_ctrl); - - if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) { - - data1 = readq(&vpath_reg->rts_access_steer_data0); - data2 = readq(&vpath_reg->rts_access_steer_data1); - - fw_date->day = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_DAY( - data1); - fw_date->month = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MONTH( - data1); - fw_date->year = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_YEAR( - data1); - - snprintf(fw_date->date, VXGE_HW_FW_STRLEN, "%2.2d/%2.2d/%4.4d", - fw_date->month, fw_date->day, fw_date->year); - - fw_version->major = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MAJOR(data1); - fw_version->minor = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MINOR(data1); - fw_version->build = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_BUILD(data1); - - snprintf(fw_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d", - fw_version->major, fw_version->minor, fw_version->build); - - flash_date->day = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_DAY(data2); - flash_date->month = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MONTH(data2); - flash_date->year = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_YEAR(data2); - - snprintf(flash_date->date, VXGE_HW_FW_STRLEN, - "%2.2d/%2.2d/%4.4d", - flash_date->month, flash_date->day, flash_date->year); - - flash_version->major = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MAJOR(data2); - flash_version->minor = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MINOR(data2); - flash_version->build = - (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_BUILD(data2); - - snprintf(flash_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d", - flash_version->major, flash_version->minor, - flash_version->build); - - status = VXGE_HW_OK; - - } else - status = VXGE_HW_FAIL; -exit: - return status; -} - -/* - * __vxge_hw_vpath_pci_func_mode_get - Get the pci mode - * Returns pci function mode - */ -static u64 -__vxge_hw_vpath_pci_func_mode_get( - u32 vp_id, - struct vxge_hw_vpath_reg __iomem *vpath_reg) -{ - u64 val64; - u64 data1 = 0ULL; - enum vxge_hw_status status = VXGE_HW_OK; - - __vxge_hw_read_rts_ds(vpath_reg, - VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PCI_MODE); - - val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION( - VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL( - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | - VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0); - - status = __vxge_hw_pio_mem_write64(val64, - &vpath_reg->rts_access_steer_ctrl, - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, - VXGE_HW_DEF_DEVICE_POLL_MILLIS); - - if (status != VXGE_HW_OK) - goto exit; - - val64 = readq(&vpath_reg->rts_access_steer_ctrl); - - if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) { - data1 = readq(&vpath_reg->rts_access_steer_data0); - status = VXGE_HW_OK; - } else { - data1 = 0; - status = VXGE_HW_FAIL; - } -exit: - return data1; -} - /** * vxge_hw_device_flick_link_led - Flick (blink) link LED. * @hldev: HW device. @@ -2974,37 +3121,24 @@ exit: * Flicker the link LED. */ enum vxge_hw_status -vxge_hw_device_flick_link_led(struct __vxge_hw_device *hldev, - u64 on_off) +vxge_hw_device_flick_link_led(struct __vxge_hw_device *hldev, u64 on_off) { - u64 val64; - enum vxge_hw_status status = VXGE_HW_OK; - struct vxge_hw_vpath_reg __iomem *vp_reg; + struct __vxge_hw_virtualpath *vpath; + u64 data0, data1 = 0, steer_ctrl = 0; + enum vxge_hw_status status; if (hldev == NULL) { status = VXGE_HW_ERR_INVALID_DEVICE; goto exit; } - vp_reg = hldev->vpath_reg[hldev->first_vp_id]; - - writeq(0, &vp_reg->rts_access_steer_ctrl); - wmb(); - writeq(on_off, &vp_reg->rts_access_steer_data0); - writeq(0, &vp_reg->rts_access_steer_data1); - wmb(); + vpath = &hldev->virtual_paths[hldev->first_vp_id]; - val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION( - VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LED_CONTROL) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL( - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | - VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0); - - status = __vxge_hw_pio_mem_write64(val64, - &vp_reg->rts_access_steer_ctrl, - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, - VXGE_HW_DEF_DEVICE_POLL_MILLIS); + data0 = on_off; + status = vxge_hw_vpath_fw_api(vpath, + VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LED_CONTROL, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, + 0, &data0, &data1, &steer_ctrl); exit: return status; } @@ -3013,63 +3147,38 @@ exit: * __vxge_hw_vpath_rts_table_get - Get the entries from RTS access tables */ enum vxge_hw_status -__vxge_hw_vpath_rts_table_get( - struct __vxge_hw_vpath_handle *vp, - u32 action, u32 rts_table, u32 offset, u64 *data1, u64 *data2) +__vxge_hw_vpath_rts_table_get(struct __vxge_hw_vpath_handle *vp, + u32 action, u32 rts_table, u32 offset, + u64 *data0, u64 *data1) { - u64 val64; - struct __vxge_hw_virtualpath *vpath; - struct vxge_hw_vpath_reg __iomem *vp_reg; - - enum vxge_hw_status status = VXGE_HW_OK; + enum vxge_hw_status status; + u64 steer_ctrl = 0; if (vp == NULL) { status = VXGE_HW_ERR_INVALID_HANDLE; goto exit; } - vpath = vp->vpath; - vp_reg = vpath->vp_reg; - - val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(action) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(rts_table) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | - VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(offset); - if ((rts_table == - VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT) || + VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT) || (rts_table == - VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT) || + VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT) || (rts_table == - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MASK) || + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MASK) || (rts_table == - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_KEY)) { - val64 = val64 | VXGE_HW_RTS_ACCESS_STEER_CTRL_TABLE_SEL; + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_KEY)) { + steer_ctrl = VXGE_HW_RTS_ACCESS_STEER_CTRL_TABLE_SEL; } - status = __vxge_hw_pio_mem_write64(val64, - &vp_reg->rts_access_steer_ctrl, - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, - vpath->hldev->config.device_poll_millis); - + status = vxge_hw_vpath_fw_api(vp->vpath, action, rts_table, offset, + data0, data1, &steer_ctrl); if (status != VXGE_HW_OK) goto exit; - val64 = readq(&vp_reg->rts_access_steer_ctrl); - - if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) { - - *data1 = readq(&vp_reg->rts_access_steer_data0); - - if ((rts_table == - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) || - (rts_table == - VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT)) { - *data2 = readq(&vp_reg->rts_access_steer_data1); - } - status = VXGE_HW_OK; - } else - status = VXGE_HW_FAIL; + if ((rts_table != VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) || + (rts_table != + VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT)) + *data1 = 0; exit: return status; } @@ -3078,107 +3187,27 @@ exit: * __vxge_hw_vpath_rts_table_set - Set the entries of RTS access tables */ enum vxge_hw_status -__vxge_hw_vpath_rts_table_set( - struct __vxge_hw_vpath_handle *vp, u32 action, u32 rts_table, - u32 offset, u64 data1, u64 data2) +__vxge_hw_vpath_rts_table_set(struct __vxge_hw_vpath_handle *vp, u32 action, + u32 rts_table, u32 offset, u64 steer_data0, + u64 steer_data1) { - u64 val64; - struct __vxge_hw_virtualpath *vpath; - enum vxge_hw_status status = VXGE_HW_OK; - struct vxge_hw_vpath_reg __iomem *vp_reg; + u64 data0, data1 = 0, steer_ctrl = 0; + enum vxge_hw_status status; if (vp == NULL) { status = VXGE_HW_ERR_INVALID_HANDLE; goto exit; } - vpath = vp->vpath; - vp_reg = vpath->vp_reg; - - writeq(data1, &vp_reg->rts_access_steer_data0); - wmb(); + data0 = steer_data0; if ((rts_table == VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) || (rts_table == - VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT)) { - writeq(data2, &vp_reg->rts_access_steer_data1); - wmb(); - } - - val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(action) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(rts_table) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | - VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(offset); - - status = __vxge_hw_pio_mem_write64(val64, - &vp_reg->rts_access_steer_ctrl, - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, - vpath->hldev->config.device_poll_millis); - - if (status != VXGE_HW_OK) - goto exit; - - val64 = readq(&vp_reg->rts_access_steer_ctrl); - - if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) - status = VXGE_HW_OK; - else - status = VXGE_HW_FAIL; -exit: - return status; -} - -/* - * __vxge_hw_vpath_addr_get - Get the hw address entry for this vpath - * from MAC address table. - */ -static enum vxge_hw_status -__vxge_hw_vpath_addr_get( - u32 vp_id, struct vxge_hw_vpath_reg __iomem *vpath_reg, - u8 (macaddr)[ETH_ALEN], u8 (macaddr_mask)[ETH_ALEN]) -{ - u32 i; - u64 val64; - u64 data1 = 0ULL; - u64 data2 = 0ULL; - enum vxge_hw_status status = VXGE_HW_OK; - - val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION( - VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_FIRST_ENTRY) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL( - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) | - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE | - VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0); - - status = __vxge_hw_pio_mem_write64(val64, - &vpath_reg->rts_access_steer_ctrl, - VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE, - VXGE_HW_DEF_DEVICE_POLL_MILLIS); - - if (status != VXGE_HW_OK) - goto exit; - - val64 = readq(&vpath_reg->rts_access_steer_ctrl); - - if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) { + VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT)) + data1 = steer_data1; - data1 = readq(&vpath_reg->rts_access_steer_data0); - data2 = readq(&vpath_reg->rts_access_steer_data1); - - data1 = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(data1); - data2 = VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_DA_MAC_ADDR_MASK( - data2); - - for (i = ETH_ALEN; i > 0; i--) { - macaddr[i-1] = (u8)(data1 & 0xFF); - data1 >>= 8; - - macaddr_mask[i-1] = (u8)(data2 & 0xFF); - data2 >>= 8; - } - status = VXGE_HW_OK; - } else - status = VXGE_HW_FAIL; + status = vxge_hw_vpath_fw_api(vp->vpath, action, rts_table, offset, + &data0, &data1, &steer_ctrl); exit: return status; } @@ -3204,6 +3233,8 @@ enum vxge_hw_status vxge_hw_vpath_rts_rth_set( VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_ENTRY, VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_GEN_CFG, 0, &data0, &data1); + if (status != VXGE_HW_OK) + goto exit; data0 &= ~(VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_BUCKET_SIZE(0xf) | VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ALG_SEL(0x3)); @@ -4117,6 +4148,7 @@ __vxge_hw_vp_initialize(struct __vxge_hw_device *hldev, u32 vp_id, vpath = &hldev->virtual_paths[vp_id]; + spin_lock_init(&hldev->virtual_paths[vp_id].lock); vpath->vp_id = vp_id; vpath->vp_open = VXGE_HW_VP_OPEN; vpath->hldev = hldev; @@ -4127,14 +4159,12 @@ __vxge_hw_vp_initialize(struct __vxge_hw_device *hldev, u32 vp_id, __vxge_hw_vpath_reset(hldev, vp_id); status = __vxge_hw_vpath_reset_check(vpath); - if (status != VXGE_HW_OK) { memset(vpath, 0, sizeof(struct __vxge_hw_virtualpath)); goto exit; } status = __vxge_hw_vpath_mgmt_read(hldev, vpath); - if (status != VXGE_HW_OK) { memset(vpath, 0, sizeof(struct __vxge_hw_virtualpath)); goto exit; @@ -4148,7 +4178,6 @@ __vxge_hw_vp_initialize(struct __vxge_hw_device *hldev, u32 vp_id, hldev->tim_int_mask1, vp_id); status = __vxge_hw_vpath_initialize(hldev, vp_id); - if (status != VXGE_HW_OK) __vxge_hw_vp_terminate(hldev, vp_id); exit: @@ -4335,16 +4364,18 @@ vpath_open_exit1: void vxge_hw_vpath_rx_doorbell_init(struct __vxge_hw_vpath_handle *vp) { - struct __vxge_hw_virtualpath *vpath = NULL; + struct __vxge_hw_virtualpath *vpath = vp->vpath; + struct __vxge_hw_ring *ring = vpath->ringh; + struct vxgedev *vdev = netdev_priv(vpath->hldev->ndev); u64 new_count, val64, val164; - struct __vxge_hw_ring *ring; - vpath = vp->vpath; - ring = vpath->ringh; + if (vdev->titan1) { + new_count = readq(&vpath->vp_reg->rxdmem_size); + new_count &= 0x1fff; + } else + new_count = ring->config->ring_blocks * VXGE_HW_BLOCK_SIZE / 8; - new_count = readq(&vpath->vp_reg->rxdmem_size); - new_count &= 0x1fff; - val164 = (VXGE_HW_RXDMEM_SIZE_PRC_RXDMEM_SIZE(new_count)); + val164 = VXGE_HW_RXDMEM_SIZE_PRC_RXDMEM_SIZE(new_count); writeq(VXGE_HW_PRC_RXD_DOORBELL_NEW_QW_CNT(val164), &vpath->vp_reg->prc_rxd_doorbell); @@ -4414,7 +4445,9 @@ enum vxge_hw_status vxge_hw_vpath_close(struct __vxge_hw_vpath_handle *vp) __vxge_hw_vp_terminate(devh, vp_id); + spin_lock(&vpath->lock); vpath->vp_open = VXGE_HW_VP_NOT_OPEN; + spin_unlock(&vpath->lock); vpath_close_exit: return status; @@ -4810,7 +4843,7 @@ static void vxge_os_dma_free(struct pci_dev *pdev, const void *vaddr, * __vxge_hw_blockpool_create - Create block pool */ -enum vxge_hw_status +static enum vxge_hw_status __vxge_hw_blockpool_create(struct __vxge_hw_device *hldev, struct __vxge_hw_blockpool *blockpool, u32 pool_size, @@ -4910,7 +4943,7 @@ blockpool_create_exit: * __vxge_hw_blockpool_destroy - Deallocates the block pool */ -void __vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool *blockpool) +static void __vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool *blockpool) { struct __vxge_hw_device *hldev; @@ -5076,7 +5109,7 @@ exit: * Allocates a block of memory of given size, either from block pool * or by calling vxge_os_dma_malloc() */ -void * +static void * __vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size, struct vxge_hw_mempool_dma *dma_object) { @@ -5140,7 +5173,7 @@ exit: * __vxge_hw_blockpool_free - Frees the memory allcoated with __vxge_hw_blockpool_malloc */ -void +static void __vxge_hw_blockpool_free(struct __vxge_hw_device *devh, void *memblock, u32 size, struct vxge_hw_mempool_dma *dma_object) @@ -5192,7 +5225,7 @@ __vxge_hw_blockpool_free(struct __vxge_hw_device *devh, * __vxge_hw_blockpool_block_allocate - Allocates a block from block pool * This function allocates a block from block pool or from the system */ -struct __vxge_hw_blockpool_entry * +static struct __vxge_hw_blockpool_entry * __vxge_hw_blockpool_block_allocate(struct __vxge_hw_device *devh, u32 size) { struct __vxge_hw_blockpool_entry *entry = NULL; @@ -5227,7 +5260,7 @@ __vxge_hw_blockpool_block_allocate(struct __vxge_hw_device *devh, u32 size) * * This function frees a block from block pool */ -void +static void __vxge_hw_blockpool_block_free(struct __vxge_hw_device *devh, struct __vxge_hw_blockpool_entry *entry) { diff --git a/drivers/net/vxge/vxge-config.h b/drivers/net/vxge/vxge-config.h index 5c00861b6c2c..5b2c8313426d 100644 --- a/drivers/net/vxge/vxge-config.h +++ b/drivers/net/vxge/vxge-config.h @@ -20,13 +20,6 @@ #define VXGE_CACHE_LINE_SIZE 128 #endif -#define vxge_os_vaprintf(level, mask, fmt, ...) { \ - char buff[255]; \ - snprintf(buff, 255, fmt, __VA_ARGS__); \ - printk(buff); \ - printk("\n"); \ -} - #ifndef VXGE_ALIGN #define VXGE_ALIGN(adrs, size) \ (((size) - (((u64)adrs) & ((size)-1))) & ((size)-1)) @@ -36,8 +29,16 @@ #define VXGE_HW_MAX_MTU 9600 #define VXGE_HW_DEFAULT_MTU 1500 -#ifdef VXGE_DEBUG_ASSERT +#define VXGE_HW_MAX_ROM_IMAGES 8 + +struct eprom_image { + u8 is_valid:1; + u8 index; + u8 type; + u16 version; +}; +#ifdef VXGE_DEBUG_ASSERT /** * vxge_assert * @test: C-condition to check @@ -48,16 +49,13 @@ * compilation * time. */ -#define vxge_assert(test) { \ - if (!(test)) \ - vxge_os_bug("bad cond: "#test" at %s:%d\n", \ - __FILE__, __LINE__); } +#define vxge_assert(test) BUG_ON(!(test)) #else #define vxge_assert(test) #endif /* end of VXGE_DEBUG_ASSERT */ /** - * enum enum vxge_debug_level + * enum vxge_debug_level * @VXGE_NONE: debug disabled * @VXGE_ERR: all errors going to be logged out * @VXGE_TRACE: all errors plus all kind of verbose tracing print outs @@ -159,6 +157,47 @@ enum vxge_hw_device_link_state { }; /** + * enum enum vxge_hw_fw_upgrade_code - FW upgrade return codes. + * @VXGE_HW_FW_UPGRADE_OK: All OK send next 16 bytes + * @VXGE_HW_FW_UPGRADE_DONE: upload completed + * @VXGE_HW_FW_UPGRADE_ERR: upload error + * @VXGE_FW_UPGRADE_BYTES2SKIP: skip bytes in the stream + * + */ +enum vxge_hw_fw_upgrade_code { + VXGE_HW_FW_UPGRADE_OK = 0, + VXGE_HW_FW_UPGRADE_DONE = 1, + VXGE_HW_FW_UPGRADE_ERR = 2, + VXGE_FW_UPGRADE_BYTES2SKIP = 3 +}; + +/** + * enum enum vxge_hw_fw_upgrade_err_code - FW upgrade error codes. + * @VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_1: corrupt data + * @VXGE_HW_FW_UPGRADE_ERR_BUFFER_OVERFLOW: buffer overflow + * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_3: invalid .ncf file + * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_4: invalid .ncf file + * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_5: invalid .ncf file + * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_6: invalid .ncf file + * @VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_7: corrupt data + * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_8: invalid .ncf file + * @VXGE_HW_FW_UPGRADE_ERR_GENERIC_ERROR_UNKNOWN: generic error unknown type + * @VXGE_HW_FW_UPGRADE_ERR_FAILED_TO_FLASH: failed to flash image check failed + */ +enum vxge_hw_fw_upgrade_err_code { + VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_1 = 1, + VXGE_HW_FW_UPGRADE_ERR_BUFFER_OVERFLOW = 2, + VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_3 = 3, + VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_4 = 4, + VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_5 = 5, + VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_6 = 6, + VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_7 = 7, + VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_8 = 8, + VXGE_HW_FW_UPGRADE_ERR_GENERIC_ERROR_UNKNOWN = 9, + VXGE_HW_FW_UPGRADE_ERR_FAILED_TO_FLASH = 10 +}; + +/** * struct vxge_hw_device_date - Date Format * @day: Day * @month: Month @@ -465,7 +504,6 @@ struct vxge_hw_device_config { * See also: vxge_hw_driver_initialize(). */ struct vxge_hw_uld_cbs { - void (*link_up)(struct __vxge_hw_device *devh); void (*link_down)(struct __vxge_hw_device *devh); void (*crit_err)(struct __vxge_hw_device *devh, @@ -652,6 +690,7 @@ struct __vxge_hw_virtualpath { struct vxge_hw_vpath_stats_hw_info *hw_stats; struct vxge_hw_vpath_stats_hw_info *hw_stats_sav; struct vxge_hw_vpath_stats_sw_info *sw_stats; + spinlock_t lock; }; /* @@ -674,9 +713,6 @@ struct __vxge_hw_vpath_handle{ /** * struct __vxge_hw_device - Hal device object * @magic: Magic Number - * @device_id: PCI Device Id of the adapter - * @major_revision: PCI Device major revision - * @minor_revision: PCI Device minor revision * @bar0: BAR0 virtual address. * @pdev: Physical device handle * @config: Confguration passed by the LL driver at initialization @@ -688,9 +724,6 @@ struct __vxge_hw_device { u32 magic; #define VXGE_HW_DEVICE_MAGIC 0x12345678 #define VXGE_HW_DEVICE_DEAD 0xDEADDEAD - u16 device_id; - u8 major_revision; - u8 minor_revision; void __iomem *bar0; struct pci_dev *pdev; struct net_device *ndev; @@ -731,6 +764,7 @@ struct __vxge_hw_device { u32 debug_level; u32 level_err; u32 level_trace; + u16 eprom_versions[VXGE_HW_MAX_ROM_IMAGES]; }; #define VXGE_HW_INFO_LEN 64 @@ -1413,12 +1447,12 @@ enum vxge_hw_rth_algoritms { * See also: vxge_hw_vpath_rts_rth_set(), vxge_hw_vpath_rts_rth_get(). */ struct vxge_hw_rth_hash_types { - u8 hash_type_tcpipv4_en; - u8 hash_type_ipv4_en; - u8 hash_type_tcpipv6_en; - u8 hash_type_ipv6_en; - u8 hash_type_tcpipv6ex_en; - u8 hash_type_ipv6ex_en; + u8 hash_type_tcpipv4_en:1, + hash_type_ipv4_en:1, + hash_type_tcpipv6_en:1, + hash_type_ipv6_en:1, + hash_type_tcpipv6ex_en:1, + hash_type_ipv6ex_en:1; }; void vxge_hw_device_debug_set( @@ -2000,7 +2034,7 @@ enum vxge_hw_status vxge_hw_vpath_strip_fcs_check(struct __vxge_hw_device *hldev, u64 vpath_mask); /** - * vxge_debug + * vxge_debug_ll * @level: level of debug verbosity. * @mask: mask for the debug * @buf: Circular buffer for tracing @@ -2012,26 +2046,13 @@ vxge_hw_vpath_strip_fcs_check(struct __vxge_hw_device *hldev, u64 vpath_mask); * may be compiled out if DEBUG macro was never defined. * See also: enum vxge_debug_level{}. */ - -#define vxge_trace_aux(level, mask, fmt, ...) \ -{\ - vxge_os_vaprintf(level, mask, fmt, __VA_ARGS__);\ -} - -#define vxge_debug(module, level, mask, fmt, ...) { \ -if ((level >= VXGE_TRACE && ((module & VXGE_DEBUG_TRACE_MASK) == module)) || \ - (level >= VXGE_ERR && ((module & VXGE_DEBUG_ERR_MASK) == module))) {\ - if ((mask & VXGE_DEBUG_MASK) == mask)\ - vxge_trace_aux(level, mask, fmt, __VA_ARGS__); \ -} \ -} - #if (VXGE_COMPONENT_LL & VXGE_DEBUG_MODULE_MASK) -#define vxge_debug_ll(level, mask, fmt, ...) \ -{\ - vxge_debug(VXGE_COMPONENT_LL, level, mask, fmt, __VA_ARGS__);\ -} - +#define vxge_debug_ll(level, mask, fmt, ...) do { \ + if ((level >= VXGE_ERR && VXGE_COMPONENT_LL & VXGE_DEBUG_ERR_MASK) || \ + (level >= VXGE_TRACE && VXGE_COMPONENT_LL & VXGE_DEBUG_TRACE_MASK))\ + if ((mask & VXGE_DEBUG_MASK) == mask) \ + printk(fmt "\n", __VA_ARGS__); \ +} while (0) #else #define vxge_debug_ll(level, mask, fmt, ...) #endif @@ -2051,4 +2072,26 @@ enum vxge_hw_status vxge_hw_vpath_rts_rth_set( enum vxge_hw_status __vxge_hw_device_is_privilaged(u32 host_type, u32 func_id); + +#define VXGE_HW_MIN_SUCCESSIVE_IDLE_COUNT 5 +#define VXGE_HW_MAX_POLLING_COUNT 100 + +void +vxge_hw_device_wait_receive_idle(struct __vxge_hw_device *hldev); + +enum vxge_hw_status +vxge_hw_upgrade_read_version(struct __vxge_hw_device *hldev, u32 *major, + u32 *minor, u32 *build); + +enum vxge_hw_status vxge_hw_flash_fw(struct __vxge_hw_device *hldev); + +enum vxge_hw_status +vxge_update_fw_image(struct __vxge_hw_device *hldev, const u8 *filebuf, + int size); + +enum vxge_hw_status +vxge_hw_vpath_eprom_img_ver_get(struct __vxge_hw_device *hldev, + struct eprom_image *eprom_image_data); + +int vxge_hw_vpath_wait_receive_idle(struct __vxge_hw_device *hldev, u32 vp_id); #endif diff --git a/drivers/net/vxge/vxge-ethtool.c b/drivers/net/vxge/vxge-ethtool.c index b67746eef923..09f721e10517 100644 --- a/drivers/net/vxge/vxge-ethtool.c +++ b/drivers/net/vxge/vxge-ethtool.c @@ -11,7 +11,7 @@ * Virtualized Server Adapter. * Copyright(c) 2002-2010 Exar Corp. ******************************************************************************/ -#include<linux/ethtool.h> +#include <linux/ethtool.h> #include <linux/slab.h> #include <linux/pci.h> #include <linux/etherdevice.h> @@ -29,7 +29,6 @@ * Return value: * 0 on success. */ - static int vxge_ethtool_sset(struct net_device *dev, struct ethtool_cmd *info) { /* We currently only support 10Gb/FULL */ @@ -79,10 +78,9 @@ static int vxge_ethtool_gset(struct net_device *dev, struct ethtool_cmd *info) * Returns driver specefic information like name, version etc.. to ethtool. */ static void vxge_ethtool_gdrvinfo(struct net_device *dev, - struct ethtool_drvinfo *info) + struct ethtool_drvinfo *info) { - struct vxgedev *vdev; - vdev = (struct vxgedev *)netdev_priv(dev); + struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev); strlcpy(info->driver, VXGE_DRIVER_NAME, sizeof(VXGE_DRIVER_NAME)); strlcpy(info->version, DRV_VERSION, sizeof(DRV_VERSION)); strlcpy(info->fw_version, vdev->fw_version, VXGE_HW_FW_STRLEN); @@ -104,15 +102,14 @@ static void vxge_ethtool_gdrvinfo(struct net_device *dev, * buffer area. */ static void vxge_ethtool_gregs(struct net_device *dev, - struct ethtool_regs *regs, void *space) + struct ethtool_regs *regs, void *space) { int index, offset; enum vxge_hw_status status; u64 reg; - u64 *reg_space = (u64 *) space; + u64 *reg_space = (u64 *)space; struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev); - struct __vxge_hw_device *hldev = (struct __vxge_hw_device *) - pci_get_drvdata(vdev->pdev); + struct __vxge_hw_device *hldev = vdev->devh; regs->len = sizeof(struct vxge_hw_vpath_reg) * vdev->no_of_vpath; regs->version = vdev->pdev->subsystem_device; @@ -148,8 +145,7 @@ static void vxge_ethtool_gregs(struct net_device *dev, static int vxge_ethtool_idnic(struct net_device *dev, u32 data) { struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev); - struct __vxge_hw_device *hldev = (struct __vxge_hw_device *) - pci_get_drvdata(vdev->pdev); + struct __vxge_hw_device *hldev = vdev->devh; vxge_hw_device_flick_link_led(hldev, VXGE_FLICKER_ON); msleep_interruptible(data ? (data * HZ) : VXGE_MAX_FLICKER_TIME); @@ -168,11 +164,10 @@ static int vxge_ethtool_idnic(struct net_device *dev, u32 data) * void */ static void vxge_ethtool_getpause_data(struct net_device *dev, - struct ethtool_pauseparam *ep) + struct ethtool_pauseparam *ep) { struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev); - struct __vxge_hw_device *hldev = (struct __vxge_hw_device *) - pci_get_drvdata(vdev->pdev); + struct __vxge_hw_device *hldev = vdev->devh; vxge_hw_device_getpause_data(hldev, 0, &ep->tx_pause, &ep->rx_pause); } @@ -188,11 +183,10 @@ static void vxge_ethtool_getpause_data(struct net_device *dev, * int, returns 0 on Success */ static int vxge_ethtool_setpause_data(struct net_device *dev, - struct ethtool_pauseparam *ep) + struct ethtool_pauseparam *ep) { struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev); - struct __vxge_hw_device *hldev = (struct __vxge_hw_device *) - pci_get_drvdata(vdev->pdev); + struct __vxge_hw_device *hldev = vdev->devh; vxge_hw_device_setpause_data(hldev, 0, ep->tx_pause, ep->rx_pause); @@ -209,9 +203,8 @@ static void vxge_get_ethtool_stats(struct net_device *dev, enum vxge_hw_status status; enum vxge_hw_status swstatus; struct vxge_vpath *vpath = NULL; - struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev); - struct __vxge_hw_device *hldev = vdev->devh; + struct __vxge_hw_device *hldev = vdev->devh; struct vxge_hw_xmac_stats *xmac_stats; struct vxge_hw_device_stats_sw_info *sw_stats; struct vxge_hw_device_stats_hw_info *hw_stats; @@ -574,8 +567,8 @@ static void vxge_get_ethtool_stats(struct net_device *dev, kfree(hw_stats); } -static void vxge_ethtool_get_strings(struct net_device *dev, - u32 stringset, u8 *data) +static void vxge_ethtool_get_strings(struct net_device *dev, u32 stringset, + u8 *data) { int stat_size = 0; int i, j; @@ -1119,6 +1112,59 @@ static int vxge_ethtool_get_sset_count(struct net_device *dev, int sset) } } +static int vxge_set_flags(struct net_device *dev, u32 data) +{ + struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev); + enum vxge_hw_status status; + + if (data & ~ETH_FLAG_RXHASH) + return -EOPNOTSUPP; + + if (!!(data & ETH_FLAG_RXHASH) == vdev->devh->config.rth_en) + return 0; + + if (netif_running(dev) || (vdev->config.rth_steering == NO_STEERING)) + return -EINVAL; + + vdev->devh->config.rth_en = !!(data & ETH_FLAG_RXHASH); + + /* Enabling RTH requires some of the logic in vxge_device_register and a + * vpath reset. Due to these restrictions, only allow modification + * while the interface is down. + */ + status = vxge_reset_all_vpaths(vdev); + if (status != VXGE_HW_OK) { + vdev->devh->config.rth_en = !vdev->devh->config.rth_en; + return -EFAULT; + } + + if (vdev->devh->config.rth_en) + dev->features |= NETIF_F_RXHASH; + else + dev->features &= ~NETIF_F_RXHASH; + + return 0; +} + +static int vxge_fw_flash(struct net_device *dev, struct ethtool_flash *parms) +{ + struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev); + + if (vdev->max_vpath_supported != VXGE_HW_MAX_VIRTUAL_PATHS) { + printk(KERN_INFO "Single Function Mode is required to flash the" + " firmware\n"); + return -EINVAL; + } + + if (netif_running(dev)) { + printk(KERN_INFO "Interface %s must be down to flash the " + "firmware\n", dev->name); + return -EBUSY; + } + + return vxge_fw_upgrade(vdev, parms->data, 1); +} + static const struct ethtool_ops vxge_ethtool_ops = { .get_settings = vxge_ethtool_gset, .set_settings = vxge_ethtool_sset, @@ -1140,6 +1186,8 @@ static const struct ethtool_ops vxge_ethtool_ops = { .phys_id = vxge_ethtool_idnic, .get_sset_count = vxge_ethtool_get_sset_count, .get_ethtool_stats = vxge_get_ethtool_stats, + .set_flags = vxge_set_flags, + .flash_device = vxge_fw_flash, }; void vxge_initialize_ethtool_ops(struct net_device *ndev) diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c index 813829f3d024..3f2d6ed13d3e 100644 --- a/drivers/net/vxge/vxge-main.c +++ b/drivers/net/vxge/vxge-main.c @@ -50,6 +50,8 @@ #include <net/ip.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <linux/firmware.h> +#include <linux/net_tstamp.h> #include "vxge-main.h" #include "vxge-reg.h" @@ -90,7 +92,6 @@ static int vxge_mac_list_add(struct vxge_vpath *vpath, struct macInfo *mac); static int vxge_mac_list_del(struct vxge_vpath *vpath, struct macInfo *mac); static enum vxge_hw_status vxge_restore_vpath_vid_table(struct vxge_vpath *vpath); static enum vxge_hw_status vxge_restore_vpath_mac_addr(struct vxge_vpath *vpath); -static enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev); static inline int is_vxge_card_up(struct vxgedev *vdev) { @@ -369,7 +370,7 @@ vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr, u8 t_code, void *userdata) { struct vxge_ring *ring = (struct vxge_ring *)userdata; - struct net_device *dev = ring->ndev; + struct net_device *dev = ring->ndev; unsigned int dma_sizes; void *first_dtr = NULL; int dtr_cnt = 0; @@ -513,6 +514,23 @@ vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr, else skb_checksum_none_assert(skb); + + if (ring->rx_hwts) { + struct skb_shared_hwtstamps *skb_hwts; + u32 ns = *(u32 *)(skb->head + pkt_length); + + skb_hwts = skb_hwtstamps(skb); + skb_hwts->hwtstamp = ns_to_ktime(ns); + skb_hwts->syststamp.tv64 = 0; + } + + /* rth_hash_type and rth_it_hit are non-zero regardless of + * whether rss is enabled. Only the rth_value is zero/non-zero + * if rss is disabled/enabled, so key off of that. + */ + if (ext_info.rth_value) + skb->rxhash = ext_info.rth_value; + vxge_rx_complete(ring, skb, ext_info.vlan, pkt_length, &ext_info); @@ -670,7 +688,7 @@ static int vxge_learn_mac(struct vxgedev *vdev, u8 *mac_header) struct vxge_vpath *vpath = NULL; struct __vxge_hw_device *hldev; - hldev = (struct __vxge_hw_device *) pci_get_drvdata(vdev->pdev); + hldev = (struct __vxge_hw_device *)pci_get_drvdata(vdev->pdev); mac_address = (u8 *)&mac_addr; memcpy(mac_address, mac_header, ETH_ALEN); @@ -1094,7 +1112,7 @@ static void vxge_set_multicast(struct net_device *dev) /* Delete previous MC's */ for (i = 0; i < mcast_cnt; i++) { list_for_each_safe(entry, next, list_head) { - mac_entry = (struct vxge_mac_addrs *) entry; + mac_entry = (struct vxge_mac_addrs *)entry; /* Copy the mac address to delete */ mac_address = (u8 *)&mac_entry->macaddr; memcpy(mac_info.macaddr, mac_address, ETH_ALEN); @@ -1137,7 +1155,7 @@ _set_all_mcast: /* Delete previous MC's */ for (i = 0; i < mcast_cnt; i++) { list_for_each_safe(entry, next, list_head) { - mac_entry = (struct vxge_mac_addrs *) entry; + mac_entry = (struct vxge_mac_addrs *)entry; /* Copy the mac address to delete */ mac_address = (u8 *)&mac_entry->macaddr; memcpy(mac_info.macaddr, mac_address, ETH_ALEN); @@ -1184,7 +1202,7 @@ static int vxge_set_mac_addr(struct net_device *dev, void *p) { struct sockaddr *addr = p; struct vxgedev *vdev; - struct __vxge_hw_device *hldev; + struct __vxge_hw_device *hldev; enum vxge_hw_status status = VXGE_HW_OK; struct macInfo mac_info_new, mac_info_old; int vpath_idx = 0; @@ -1292,8 +1310,13 @@ static void vxge_vpath_intr_enable(struct vxgedev *vdev, int vp_id) static void vxge_vpath_intr_disable(struct vxgedev *vdev, int vp_id) { struct vxge_vpath *vpath = &vdev->vpaths[vp_id]; + struct __vxge_hw_device *hldev; int msix_id; + hldev = (struct __vxge_hw_device *)pci_get_drvdata(vdev->pdev); + + vxge_hw_vpath_wait_receive_idle(hldev, vpath->device_id); + vxge_hw_vpath_intr_disable(vpath->handle); if (vdev->config.intr_type == INTA) @@ -1423,6 +1446,7 @@ static int do_vxge_reset(struct vxgedev *vdev, int event) } if (event == VXGE_LL_FULL_RESET) { + vxge_hw_device_wait_receive_idle(vdev->devh); vxge_hw_device_intr_disable(vdev->devh); switch (vdev->cric_err_event) { @@ -1608,7 +1632,7 @@ static int vxge_poll_inta(struct napi_struct *napi, int budget) int budget_org = budget; struct vxge_ring *ring; - struct __vxge_hw_device *hldev = (struct __vxge_hw_device *) + struct __vxge_hw_device *hldev = (struct __vxge_hw_device *) pci_get_drvdata(vdev->pdev); for (i = 0; i < vdev->no_of_vpath; i++) { @@ -1645,7 +1669,7 @@ static int vxge_poll_inta(struct napi_struct *napi, int budget) */ static void vxge_netpoll(struct net_device *dev) { - struct __vxge_hw_device *hldev; + struct __vxge_hw_device *hldev; struct vxgedev *vdev; vdev = (struct vxgedev *)netdev_priv(dev); @@ -1689,15 +1713,6 @@ static enum vxge_hw_status vxge_rth_configure(struct vxgedev *vdev) mtable[index] = index % vdev->no_of_vpath; } - /* Fill RTH hash types */ - hash_types.hash_type_tcpipv4_en = vdev->config.rth_hash_type_tcpipv4; - hash_types.hash_type_ipv4_en = vdev->config.rth_hash_type_ipv4; - hash_types.hash_type_tcpipv6_en = vdev->config.rth_hash_type_tcpipv6; - hash_types.hash_type_ipv6_en = vdev->config.rth_hash_type_ipv6; - hash_types.hash_type_tcpipv6ex_en = - vdev->config.rth_hash_type_tcpipv6ex; - hash_types.hash_type_ipv6ex_en = vdev->config.rth_hash_type_ipv6ex; - /* set indirection table, bucket-to-vpath mapping */ status = vxge_hw_vpath_rts_rth_itable_set(vdev->vp_handles, vdev->no_of_vpath, @@ -1710,12 +1725,21 @@ static enum vxge_hw_status vxge_rth_configure(struct vxgedev *vdev) return status; } + /* Fill RTH hash types */ + hash_types.hash_type_tcpipv4_en = vdev->config.rth_hash_type_tcpipv4; + hash_types.hash_type_ipv4_en = vdev->config.rth_hash_type_ipv4; + hash_types.hash_type_tcpipv6_en = vdev->config.rth_hash_type_tcpipv6; + hash_types.hash_type_ipv6_en = vdev->config.rth_hash_type_ipv6; + hash_types.hash_type_tcpipv6ex_en = + vdev->config.rth_hash_type_tcpipv6ex; + hash_types.hash_type_ipv6ex_en = vdev->config.rth_hash_type_ipv6ex; + /* - * Because the itable_set() method uses the active_table field - * for the target virtual path the RTH config should be updated - * for all VPATHs. The h/w only uses the lowest numbered VPATH - * when steering frames. - */ + * Because the itable_set() method uses the active_table field + * for the target virtual path the RTH config should be updated + * for all VPATHs. The h/w only uses the lowest numbered VPATH + * when steering frames. + */ for (index = 0; index < vdev->no_of_vpath; index++) { status = vxge_hw_vpath_rts_rth_set( vdev->vpaths[index].handle, @@ -1797,7 +1821,7 @@ static int vxge_mac_list_del(struct vxge_vpath *vpath, struct macInfo *mac) { struct list_head *entry, *next; u64 del_mac = 0; - u8 *mac_address = (u8 *) (&del_mac); + u8 *mac_address = (u8 *)(&del_mac); /* Copy the mac address to delete from the list */ memcpy(mac_address, mac->macaddr, ETH_ALEN); @@ -1928,7 +1952,7 @@ static enum vxge_hw_status vxge_restore_vpath_mac_addr(struct vxge_vpath *vpath) } /* reset vpaths */ -static enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev) +enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev) { enum vxge_hw_status status = VXGE_HW_OK; struct vxge_vpath *vpath; @@ -1988,8 +2012,23 @@ static int vxge_open_vpaths(struct vxgedev *vdev) for (i = 0; i < vdev->no_of_vpath; i++) { vpath = &vdev->vpaths[i]; - vxge_assert(vpath->is_configured); + + if (!vdev->titan1) { + struct vxge_hw_vp_config *vcfg; + vcfg = &vdev->devh->config.vp_config[vpath->device_id]; + + vcfg->rti.urange_a = RTI_T1A_RX_URANGE_A; + vcfg->rti.urange_b = RTI_T1A_RX_URANGE_B; + vcfg->rti.urange_c = RTI_T1A_RX_URANGE_C; + vcfg->tti.uec_a = TTI_T1A_TX_UFC_A; + vcfg->tti.uec_b = TTI_T1A_TX_UFC_B; + vcfg->tti.uec_c = TTI_T1A_TX_UFC_C(vdev->mtu); + vcfg->tti.uec_d = TTI_T1A_TX_UFC_D(vdev->mtu); + vcfg->tti.ltimer_val = VXGE_T1A_TTI_LTIMER_VAL; + vcfg->tti.rtimer_val = VXGE_T1A_TTI_RTIMER_VAL; + } + attr.vp_id = vpath->device_id; attr.fifo_attr.callback = vxge_xmit_compl; attr.fifo_attr.txdl_term = vxge_tx_term; @@ -2024,6 +2063,7 @@ static int vxge_open_vpaths(struct vxgedev *vdev) vdev->config.fifo_indicate_max_pkts; vpath->ring.rx_vector_no = 0; vpath->ring.rx_csum = vdev->rx_csum; + vpath->ring.rx_hwts = vdev->rx_hwts; vpath->is_open = 1; vdev->vp_handles[i] = vpath->handle; vpath->ring.gro_enable = vdev->config.gro_enable; @@ -2062,7 +2102,7 @@ static irqreturn_t vxge_isr_napi(int irq, void *dev_id) struct __vxge_hw_device *hldev; u64 reason; enum vxge_hw_status status; - struct vxgedev *vdev = (struct vxgedev *) dev_id;; + struct vxgedev *vdev = (struct vxgedev *)dev_id; vxge_debug_intr(VXGE_TRACE, "%s:%d", __func__, __LINE__); @@ -2073,7 +2113,7 @@ static irqreturn_t vxge_isr_napi(int irq, void *dev_id) return IRQ_NONE; if (unlikely(!is_vxge_card_up(vdev))) - return IRQ_NONE; + return IRQ_HANDLED; status = vxge_hw_device_begin_irq(hldev, vdev->exec_mode, &reason); @@ -2301,8 +2341,8 @@ static void vxge_rem_msix_isr(struct vxgedev *vdev) static void vxge_rem_isr(struct vxgedev *vdev) { - struct __vxge_hw_device *hldev; - hldev = (struct __vxge_hw_device *) pci_get_drvdata(vdev->pdev); + struct __vxge_hw_device *hldev; + hldev = (struct __vxge_hw_device *)pci_get_drvdata(vdev->pdev); #ifdef CONFIG_PCI_MSI if (vdev->config.intr_type == MSI_X) { @@ -2543,7 +2583,7 @@ vxge_open(struct net_device *dev) "%s: %s:%d", dev->name, __func__, __LINE__); vdev = (struct vxgedev *)netdev_priv(dev); - hldev = (struct __vxge_hw_device *) pci_get_drvdata(vdev->pdev); + hldev = (struct __vxge_hw_device *)pci_get_drvdata(vdev->pdev); function_mode = vdev->config.device_hw_info.function_mode; /* make sure you have link off by default every time Nic is @@ -2598,6 +2638,8 @@ vxge_open(struct net_device *dev) goto out2; } } + printk(KERN_INFO "%s: Receive Hashing Offload %s\n", dev->name, + hldev->config.rth_en ? "enabled" : "disabled"); for (i = 0; i < vdev->no_of_vpath; i++) { vpath = &vdev->vpaths[i]; @@ -2683,9 +2725,10 @@ vxge_open(struct net_device *dev) vxge_os_timer(vdev->vp_reset_timer, vxge_poll_vp_reset, vdev, (HZ/2)); - if (vdev->vp_lockup_timer.function == NULL) - vxge_os_timer(vdev->vp_lockup_timer, - vxge_poll_vp_lockup, vdev, (HZ/2)); + /* There is no need to check for RxD leak and RxD lookup on Titan1A */ + if (vdev->titan1 && vdev->vp_lockup_timer.function == NULL) + vxge_os_timer(vdev->vp_lockup_timer, vxge_poll_vp_lockup, vdev, + HZ / 2); set_bit(__VXGE_STATE_CARD_UP, &vdev->state); @@ -2768,7 +2811,7 @@ static int do_vxge_close(struct net_device *dev, int do_io) dev->name, __func__, __LINE__); vdev = (struct vxgedev *)netdev_priv(dev); - hldev = (struct __vxge_hw_device *) pci_get_drvdata(vdev->pdev); + hldev = (struct __vxge_hw_device *)pci_get_drvdata(vdev->pdev); if (unlikely(!is_vxge_card_up(vdev))) return 0; @@ -2778,7 +2821,6 @@ static int do_vxge_close(struct net_device *dev, int do_io) while (test_and_set_bit(__VXGE_STATE_RESET_CARD, &vdev->state)) msleep(50); - clear_bit(__VXGE_STATE_CARD_UP, &vdev->state); if (do_io) { /* Put the vpath back in normal mode */ vpath_vector = vxge_mBIT(vdev->vpaths[0].device_id); @@ -2818,10 +2860,17 @@ static int do_vxge_close(struct net_device *dev, int do_io) smp_wmb(); } - del_timer_sync(&vdev->vp_lockup_timer); + + if (vdev->titan1) + del_timer_sync(&vdev->vp_lockup_timer); del_timer_sync(&vdev->vp_reset_timer); + if (do_io) + vxge_hw_device_wait_receive_idle(hldev); + + clear_bit(__VXGE_STATE_CARD_UP, &vdev->state); + /* Disable napi */ if (vdev->config.intr_type != MSI_X) napi_disable(&vdev->napi); @@ -2838,8 +2887,6 @@ static int do_vxge_close(struct net_device *dev, int do_io) if (do_io) vxge_hw_device_intr_disable(vdev->devh); - mdelay(1000); - vxge_rem_isr(vdev); vxge_napi_del_all(vdev); @@ -2954,6 +3001,101 @@ vxge_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats) return net_stats; } +static enum vxge_hw_status vxge_timestamp_config(struct vxgedev *vdev, + int enable) +{ + enum vxge_hw_status status; + u64 val64; + + /* Timestamp is passed to the driver via the FCS, therefore we + * must disable the FCS stripping by the adapter. Since this is + * required for the driver to load (due to a hardware bug), + * there is no need to do anything special here. + */ + if (enable) + val64 = VXGE_HW_XMAC_TIMESTAMP_EN | + VXGE_HW_XMAC_TIMESTAMP_USE_LINK_ID(0) | + VXGE_HW_XMAC_TIMESTAMP_INTERVAL(0); + else + val64 = 0; + + status = vxge_hw_mgmt_reg_write(vdev->devh, + vxge_hw_mgmt_reg_type_mrpcim, + 0, + offsetof(struct vxge_hw_mrpcim_reg, + xmac_timestamp), + val64); + vxge_hw_device_flush_io(vdev->devh); + return status; +} + +static int vxge_hwtstamp_ioctl(struct vxgedev *vdev, void __user *data) +{ + struct hwtstamp_config config; + enum vxge_hw_status status; + int i; + + if (copy_from_user(&config, data, sizeof(config))) + return -EFAULT; + + /* reserved for future extensions */ + if (config.flags) + return -EINVAL; + + /* Transmit HW Timestamp not supported */ + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + break; + case HWTSTAMP_TX_ON: + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + status = vxge_timestamp_config(vdev, 0); + if (status != VXGE_HW_OK) + return -EFAULT; + + vdev->rx_hwts = 0; + config.rx_filter = HWTSTAMP_FILTER_NONE; + break; + + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + status = vxge_timestamp_config(vdev, 1); + if (status != VXGE_HW_OK) + return -EFAULT; + + vdev->rx_hwts = 1; + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + + default: + return -ERANGE; + } + + for (i = 0; i < vdev->no_of_vpath; i++) + vdev->vpaths[i].ring.rx_hwts = vdev->rx_hwts; + + if (copy_to_user(data, &config, sizeof(config))) + return -EFAULT; + + return 0; +} + /** * vxge_ioctl * @dev: Device pointer. @@ -2966,7 +3108,20 @@ vxge_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats) */ static int vxge_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { - return -EOPNOTSUPP; + struct vxgedev *vdev = netdev_priv(dev); + int ret; + + switch (cmd) { + case SIOCSHWTSTAMP: + ret = vxge_hwtstamp_ioctl(vdev, rq->ifr_data); + if (ret) + return ret; + break; + default: + return -EOPNOTSUPP; + } + + return 0; } /** @@ -3125,6 +3280,19 @@ static const struct net_device_ops vxge_netdev_ops = { #endif }; +static int __devinit vxge_device_revision(struct vxgedev *vdev) +{ + int ret; + u8 revision; + + ret = pci_read_config_byte(vdev->pdev, PCI_REVISION_ID, &revision); + if (ret) + return -EIO; + + vdev->titan1 = (revision == VXGE_HW_TITAN1_PCI_REVISION); + return 0; +} + static int __devinit vxge_device_register(struct __vxge_hw_device *hldev, struct vxge_config *config, int high_dma, int no_of_vpath, @@ -3163,6 +3331,11 @@ static int __devinit vxge_device_register(struct __vxge_hw_device *hldev, vdev->pdev = hldev->pdev; memcpy(&vdev->config, config, sizeof(struct vxge_config)); vdev->rx_csum = 1; /* Enable Rx CSUM by default. */ + vdev->rx_hwts = 0; + + ret = vxge_device_revision(vdev); + if (ret < 0) + goto _out1; SET_NETDEV_DEV(ndev, &vdev->pdev->dev); @@ -3178,6 +3351,11 @@ static int __devinit vxge_device_register(struct __vxge_hw_device *hldev, vxge_initialize_ethtool_ops(ndev); + if (vdev->config.rth_steering != NO_STEERING) { + ndev->features |= NETIF_F_RXHASH; + hldev->config.rth_en = VXGE_HW_RTH_ENABLE; + } + /* Allocate memory for vpath */ vdev->vpaths = kzalloc((sizeof(struct vxge_vpath)) * no_of_vpath, GFP_KERNEL); @@ -3227,6 +3405,7 @@ static int __devinit vxge_device_register(struct __vxge_hw_device *hldev, "%s: Ethernet device registered", ndev->name); + hldev->ndev = ndev; *vdev_out = vdev; /* Resetting the Device stats */ @@ -3261,36 +3440,29 @@ _out0: * * This function will unregister and free network device */ -static void -vxge_device_unregister(struct __vxge_hw_device *hldev) +static void vxge_device_unregister(struct __vxge_hw_device *hldev) { struct vxgedev *vdev; struct net_device *dev; char buf[IFNAMSIZ]; -#if ((VXGE_DEBUG_INIT & VXGE_DEBUG_MASK) || \ - (VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK)) - u32 level_trace; -#endif dev = hldev->ndev; vdev = netdev_priv(dev); -#if ((VXGE_DEBUG_INIT & VXGE_DEBUG_MASK) || \ - (VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK)) - level_trace = vdev->level_trace; -#endif - vxge_debug_entryexit(level_trace, - "%s: %s:%d", vdev->ndev->name, __func__, __LINE__); - memcpy(buf, vdev->ndev->name, IFNAMSIZ); + vxge_debug_entryexit(vdev->level_trace, "%s: %s:%d", vdev->ndev->name, + __func__, __LINE__); + + memcpy(buf, dev->name, IFNAMSIZ); /* in 2.6 will call stop() if device is up */ unregister_netdev(dev); flush_scheduled_work(); - vxge_debug_init(level_trace, "%s: ethernet device unregistered", buf); - vxge_debug_entryexit(level_trace, - "%s: %s:%d Exiting...", buf, __func__, __LINE__); + vxge_debug_init(vdev->level_trace, "%s: ethernet device unregistered", + buf); + vxge_debug_entryexit(vdev->level_trace, "%s: %s:%d Exiting...", buf, + __func__, __LINE__); } /* @@ -3813,8 +3985,8 @@ static int vxge_pm_resume(struct pci_dev *pdev) static pci_ers_result_t vxge_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state) { - struct __vxge_hw_device *hldev = - (struct __vxge_hw_device *) pci_get_drvdata(pdev); + struct __vxge_hw_device *hldev = + (struct __vxge_hw_device *)pci_get_drvdata(pdev); struct net_device *netdev = hldev->ndev; netif_device_detach(netdev); @@ -3843,8 +4015,8 @@ static pci_ers_result_t vxge_io_error_detected(struct pci_dev *pdev, */ static pci_ers_result_t vxge_io_slot_reset(struct pci_dev *pdev) { - struct __vxge_hw_device *hldev = - (struct __vxge_hw_device *) pci_get_drvdata(pdev); + struct __vxge_hw_device *hldev = + (struct __vxge_hw_device *)pci_get_drvdata(pdev); struct net_device *netdev = hldev->ndev; struct vxgedev *vdev = netdev_priv(netdev); @@ -3869,8 +4041,8 @@ static pci_ers_result_t vxge_io_slot_reset(struct pci_dev *pdev) */ static void vxge_io_resume(struct pci_dev *pdev) { - struct __vxge_hw_device *hldev = - (struct __vxge_hw_device *) pci_get_drvdata(pdev); + struct __vxge_hw_device *hldev = + (struct __vxge_hw_device *)pci_get_drvdata(pdev); struct net_device *netdev = hldev->ndev; if (netif_running(netdev)) { @@ -3914,6 +4086,142 @@ static inline u32 vxge_get_num_vfs(u64 function_mode) return num_functions; } +int vxge_fw_upgrade(struct vxgedev *vdev, char *fw_name, int override) +{ + struct __vxge_hw_device *hldev = vdev->devh; + u32 maj, min, bld, cmaj, cmin, cbld; + enum vxge_hw_status status; + const struct firmware *fw; + int ret; + + ret = request_firmware(&fw, fw_name, &vdev->pdev->dev); + if (ret) { + vxge_debug_init(VXGE_ERR, "%s: Firmware file '%s' not found", + VXGE_DRIVER_NAME, fw_name); + goto out; + } + + /* Load the new firmware onto the adapter */ + status = vxge_update_fw_image(hldev, fw->data, fw->size); + if (status != VXGE_HW_OK) { + vxge_debug_init(VXGE_ERR, + "%s: FW image download to adapter failed '%s'.", + VXGE_DRIVER_NAME, fw_name); + ret = -EIO; + goto out; + } + + /* Read the version of the new firmware */ + status = vxge_hw_upgrade_read_version(hldev, &maj, &min, &bld); + if (status != VXGE_HW_OK) { + vxge_debug_init(VXGE_ERR, + "%s: Upgrade read version failed '%s'.", + VXGE_DRIVER_NAME, fw_name); + ret = -EIO; + goto out; + } + + cmaj = vdev->config.device_hw_info.fw_version.major; + cmin = vdev->config.device_hw_info.fw_version.minor; + cbld = vdev->config.device_hw_info.fw_version.build; + /* It's possible the version in /lib/firmware is not the latest version. + * If so, we could get into a loop of trying to upgrade to the latest + * and flashing the older version. + */ + if (VXGE_FW_VER(maj, min, bld) == VXGE_FW_VER(cmaj, cmin, cbld) && + !override) { + ret = -EINVAL; + goto out; + } + + printk(KERN_NOTICE "Upgrade to firmware version %d.%d.%d commencing\n", + maj, min, bld); + + /* Flash the adapter with the new firmware */ + status = vxge_hw_flash_fw(hldev); + if (status != VXGE_HW_OK) { + vxge_debug_init(VXGE_ERR, "%s: Upgrade commit failed '%s'.", + VXGE_DRIVER_NAME, fw_name); + ret = -EIO; + goto out; + } + + printk(KERN_NOTICE "Upgrade of firmware successful! Adapter must be " + "hard reset before using, thus requiring a system reboot or a " + "hotplug event.\n"); + +out: + return ret; +} + +static int vxge_probe_fw_update(struct vxgedev *vdev) +{ + u32 maj, min, bld; + int ret, gpxe = 0; + char *fw_name; + + maj = vdev->config.device_hw_info.fw_version.major; + min = vdev->config.device_hw_info.fw_version.minor; + bld = vdev->config.device_hw_info.fw_version.build; + + if (VXGE_FW_VER(maj, min, bld) == VXGE_CERT_FW_VER) + return 0; + + /* Ignore the build number when determining if the current firmware is + * "too new" to load the driver + */ + if (VXGE_FW_VER(maj, min, 0) > VXGE_CERT_FW_VER) { + vxge_debug_init(VXGE_ERR, "%s: Firmware newer than last known " + "version, unable to load driver\n", + VXGE_DRIVER_NAME); + return -EINVAL; + } + + /* Firmware 1.4.4 and older cannot be upgraded, and is too ancient to + * work with this driver. + */ + if (VXGE_FW_VER(maj, min, bld) <= VXGE_FW_DEAD_VER) { + vxge_debug_init(VXGE_ERR, "%s: Firmware %d.%d.%d cannot be " + "upgraded\n", VXGE_DRIVER_NAME, maj, min, bld); + return -EINVAL; + } + + /* If file not specified, determine gPXE or not */ + if (VXGE_FW_VER(maj, min, bld) >= VXGE_EPROM_FW_VER) { + int i; + for (i = 0; i < VXGE_HW_MAX_ROM_IMAGES; i++) + if (vdev->devh->eprom_versions[i]) { + gpxe = 1; + break; + } + } + if (gpxe) + fw_name = "vxge/X3fw-pxe.ncf"; + else + fw_name = "vxge/X3fw.ncf"; + + ret = vxge_fw_upgrade(vdev, fw_name, 0); + /* -EINVAL and -ENOENT are not fatal errors for flashing firmware on + * probe, so ignore them + */ + if (ret != -EINVAL && ret != -ENOENT) + return -EIO; + else + ret = 0; + + if (VXGE_FW_VER(VXGE_CERT_FW_VER_MAJOR, VXGE_CERT_FW_VER_MINOR, 0) > + VXGE_FW_VER(maj, min, 0)) { + vxge_debug_init(VXGE_ERR, "%s: Firmware %d.%d.%d is too old to" + " be used with this driver.\n" + "Please get the latest version from " + "ftp://ftp.s2io.com/pub/X3100-Drivers/FIRMWARE", + VXGE_DRIVER_NAME, maj, min, bld); + return -EINVAL; + } + + return ret; +} + /** * vxge_probe * @pdev : structure containing the PCI related information of the device. @@ -3928,7 +4236,7 @@ static inline u32 vxge_get_num_vfs(u64 function_mode) static int __devinit vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) { - struct __vxge_hw_device *hldev; + struct __vxge_hw_device *hldev; enum vxge_hw_status status; int ret; int high_dma = 0; @@ -4072,16 +4380,6 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) goto _exit3; } - if (ll_config->device_hw_info.fw_version.major != - VXGE_DRIVER_FW_VERSION_MAJOR) { - vxge_debug_init(VXGE_ERR, - "%s: Incorrect firmware version." - "Please upgrade the firmware to version 1.x.x", - VXGE_DRIVER_NAME); - ret = -EINVAL; - goto _exit3; - } - vpath_mask = ll_config->device_hw_info.vpath_mask; if (vpath_mask == 0) { vxge_debug_ll_config(VXGE_TRACE, @@ -4145,11 +4443,37 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) goto _exit3; } + if (VXGE_FW_VER(ll_config->device_hw_info.fw_version.major, + ll_config->device_hw_info.fw_version.minor, + ll_config->device_hw_info.fw_version.build) >= + VXGE_EPROM_FW_VER) { + struct eprom_image img[VXGE_HW_MAX_ROM_IMAGES]; + + status = vxge_hw_vpath_eprom_img_ver_get(hldev, img); + if (status != VXGE_HW_OK) { + vxge_debug_init(VXGE_ERR, "%s: Reading of EPROM failed", + VXGE_DRIVER_NAME); + /* This is a non-fatal error, continue */ + } + + for (i = 0; i < VXGE_HW_MAX_ROM_IMAGES; i++) { + hldev->eprom_versions[i] = img[i].version; + if (!img[i].is_valid) + break; + vxge_debug_init(VXGE_TRACE, "%s: EPROM %d, version " + "%d.%d.%d.%d\n", VXGE_DRIVER_NAME, i, + VXGE_EPROM_IMG_MAJOR(img[i].version), + VXGE_EPROM_IMG_MINOR(img[i].version), + VXGE_EPROM_IMG_FIX(img[i].version), + VXGE_EPROM_IMG_BUILD(img[i].version)); + } + } + /* if FCS stripping is not disabled in MAC fail driver load */ - if (vxge_hw_vpath_strip_fcs_check(hldev, vpath_mask) != VXGE_HW_OK) { - vxge_debug_init(VXGE_ERR, - "%s: FCS stripping is not disabled in MAC" - " failing driver load", VXGE_DRIVER_NAME); + status = vxge_hw_vpath_strip_fcs_check(hldev, vpath_mask); + if (status != VXGE_HW_OK) { + vxge_debug_init(VXGE_ERR, "%s: FCS stripping is enabled in MAC" + " failing driver load", VXGE_DRIVER_NAME); ret = -EINVAL; goto _exit4; } @@ -4163,28 +4487,32 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) ll_config->fifo_indicate_max_pkts = VXGE_FIFO_INDICATE_MAX_PKTS; ll_config->addr_learn_en = addr_learn_en; ll_config->rth_algorithm = RTH_ALG_JENKINS; - ll_config->rth_hash_type_tcpipv4 = VXGE_HW_RING_HASH_TYPE_TCP_IPV4; - ll_config->rth_hash_type_ipv4 = VXGE_HW_RING_HASH_TYPE_NONE; - ll_config->rth_hash_type_tcpipv6 = VXGE_HW_RING_HASH_TYPE_NONE; - ll_config->rth_hash_type_ipv6 = VXGE_HW_RING_HASH_TYPE_NONE; - ll_config->rth_hash_type_tcpipv6ex = VXGE_HW_RING_HASH_TYPE_NONE; - ll_config->rth_hash_type_ipv6ex = VXGE_HW_RING_HASH_TYPE_NONE; + ll_config->rth_hash_type_tcpipv4 = 1; + ll_config->rth_hash_type_ipv4 = 0; + ll_config->rth_hash_type_tcpipv6 = 0; + ll_config->rth_hash_type_ipv6 = 0; + ll_config->rth_hash_type_tcpipv6ex = 0; + ll_config->rth_hash_type_ipv6ex = 0; ll_config->rth_bkt_sz = RTH_BUCKET_SIZE; ll_config->tx_pause_enable = VXGE_PAUSE_CTRL_ENABLE; ll_config->rx_pause_enable = VXGE_PAUSE_CTRL_ENABLE; - if (vxge_device_register(hldev, ll_config, high_dma, no_of_vpath, - &vdev)) { + ret = vxge_device_register(hldev, ll_config, high_dma, no_of_vpath, + &vdev); + if (ret) { ret = -EINVAL; goto _exit4; } + ret = vxge_probe_fw_update(vdev); + if (ret) + goto _exit5; + vxge_hw_device_debug_set(hldev, VXGE_TRACE, VXGE_COMPONENT_LL); VXGE_COPY_DEBUG_INFO_TO_LL(vdev, vxge_hw_device_error_level_get(hldev), vxge_hw_device_trace_level_get(hldev)); /* set private HW device info */ - hldev->ndev = vdev->ndev; vdev->mtu = VXGE_HW_DEFAULT_MTU; vdev->bar0 = attr.bar0; vdev->max_vpath_supported = max_vpath_supported; @@ -4286,7 +4614,7 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) "%s: mac_addr_list : memory allocation failed", vdev->ndev->name); ret = -EPERM; - goto _exit5; + goto _exit6; } macaddr = (u8 *)&entry->macaddr; memcpy(macaddr, vdev->ndev->dev_addr, ETH_ALEN); @@ -4326,10 +4654,10 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) kfree(ll_config); return 0; -_exit5: +_exit6: for (i = 0; i < vdev->no_of_vpath; i++) vxge_free_mac_add_list(&vdev->vpaths[i]); - +_exit5: vxge_device_unregister(hldev); _exit4: pci_disable_sriov(pdev); @@ -4354,34 +4682,25 @@ _exit0: * Description: This function is called by the Pci subsystem to release a * PCI device and free up all resource held up by the device. */ -static void __devexit -vxge_remove(struct pci_dev *pdev) +static void __devexit vxge_remove(struct pci_dev *pdev) { - struct __vxge_hw_device *hldev; + struct __vxge_hw_device *hldev; struct vxgedev *vdev = NULL; struct net_device *dev; int i = 0; -#if ((VXGE_DEBUG_INIT & VXGE_DEBUG_MASK) || \ - (VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK)) - u32 level_trace; -#endif - hldev = (struct __vxge_hw_device *) pci_get_drvdata(pdev); + hldev = (struct __vxge_hw_device *)pci_get_drvdata(pdev); if (hldev == NULL) return; + dev = hldev->ndev; vdev = netdev_priv(dev); -#if ((VXGE_DEBUG_INIT & VXGE_DEBUG_MASK) || \ - (VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK)) - level_trace = vdev->level_trace; -#endif - vxge_debug_entryexit(level_trace, - "%s:%d", __func__, __LINE__); + vxge_debug_entryexit(vdev->level_trace, "%s:%d", __func__, __LINE__); - vxge_debug_init(level_trace, - "%s : removing PCI device...", __func__); + vxge_debug_init(vdev->level_trace, "%s : removing PCI device...", + __func__); vxge_device_unregister(hldev); for (i = 0; i < vdev->no_of_vpath; i++) { @@ -4399,16 +4718,16 @@ vxge_remove(struct pci_dev *pdev) /* we are safe to free it now */ free_netdev(dev); - vxge_debug_init(level_trace, - "%s:%d Device unregistered", __func__, __LINE__); + vxge_debug_init(vdev->level_trace, "%s:%d Device unregistered", + __func__, __LINE__); vxge_hw_device_terminate(hldev); pci_disable_device(pdev); pci_release_regions(pdev); pci_set_drvdata(pdev, NULL); - vxge_debug_entryexit(level_trace, - "%s:%d Exiting...", __func__, __LINE__); + vxge_debug_entryexit(vdev->level_trace, "%s:%d Exiting...", __func__, + __LINE__); } static struct pci_error_handlers vxge_err_handler = { diff --git a/drivers/net/vxge/vxge-main.h b/drivers/net/vxge/vxge-main.h index de64536cb7d0..953cb0ded3e1 100644 --- a/drivers/net/vxge/vxge-main.h +++ b/drivers/net/vxge/vxge-main.h @@ -29,6 +29,9 @@ #define PCI_DEVICE_ID_TITAN_WIN 0x5733 #define PCI_DEVICE_ID_TITAN_UNI 0x5833 +#define VXGE_HW_TITAN1_PCI_REVISION 1 +#define VXGE_HW_TITAN1A_PCI_REVISION 2 + #define VXGE_USE_DEFAULT 0xffffffff #define VXGE_HW_VPATH_MSIX_ACTIVE 4 #define VXGE_ALARM_MSIX_ID 2 @@ -53,11 +56,13 @@ #define VXGE_TTI_BTIMER_VAL 250000 -#define VXGE_TTI_LTIMER_VAL 1000 -#define VXGE_TTI_RTIMER_VAL 0 -#define VXGE_RTI_BTIMER_VAL 250 -#define VXGE_RTI_LTIMER_VAL 100 -#define VXGE_RTI_RTIMER_VAL 0 +#define VXGE_TTI_LTIMER_VAL 1000 +#define VXGE_T1A_TTI_LTIMER_VAL 80 +#define VXGE_TTI_RTIMER_VAL 0 +#define VXGE_T1A_TTI_RTIMER_VAL 400 +#define VXGE_RTI_BTIMER_VAL 250 +#define VXGE_RTI_LTIMER_VAL 100 +#define VXGE_RTI_RTIMER_VAL 0 #define VXGE_FIFO_INDICATE_MAX_PKTS VXGE_DEF_FIFO_LENGTH #define VXGE_ISR_POLLING_CNT 8 #define VXGE_MAX_CONFIG_DEV 0xFF @@ -76,14 +81,32 @@ #define TTI_TX_UFC_B 40 #define TTI_TX_UFC_C 60 #define TTI_TX_UFC_D 100 +#define TTI_T1A_TX_UFC_A 30 +#define TTI_T1A_TX_UFC_B 80 +/* Slope - (max_mtu - min_mtu)/(max_mtu_ufc - min_mtu_ufc) */ +/* Slope - 93 */ +/* 60 - 9k Mtu, 140 - 1.5k mtu */ +#define TTI_T1A_TX_UFC_C(mtu) (60 + ((VXGE_HW_MAX_MTU - mtu) / 93)) + +/* Slope - 37 */ +/* 100 - 9k Mtu, 300 - 1.5k mtu */ +#define TTI_T1A_TX_UFC_D(mtu) (100 + ((VXGE_HW_MAX_MTU - mtu) / 37)) + + +#define RTI_RX_URANGE_A 5 +#define RTI_RX_URANGE_B 15 +#define RTI_RX_URANGE_C 40 +#define RTI_T1A_RX_URANGE_A 1 +#define RTI_T1A_RX_URANGE_B 20 +#define RTI_T1A_RX_URANGE_C 50 +#define RTI_RX_UFC_A 1 +#define RTI_RX_UFC_B 5 +#define RTI_RX_UFC_C 10 +#define RTI_RX_UFC_D 15 +#define RTI_T1A_RX_UFC_B 20 +#define RTI_T1A_RX_UFC_C 50 +#define RTI_T1A_RX_UFC_D 60 -#define RTI_RX_URANGE_A 5 -#define RTI_RX_URANGE_B 15 -#define RTI_RX_URANGE_C 40 -#define RTI_RX_UFC_A 1 -#define RTI_RX_UFC_B 5 -#define RTI_RX_UFC_C 10 -#define RTI_RX_UFC_D 15 /* Milli secs timer period */ #define VXGE_TIMER_DELAY 10000 @@ -145,15 +168,15 @@ struct vxge_config { int addr_learn_en; - int rth_steering; - int rth_algorithm; - int rth_hash_type_tcpipv4; - int rth_hash_type_ipv4; - int rth_hash_type_tcpipv6; - int rth_hash_type_ipv6; - int rth_hash_type_tcpipv6ex; - int rth_hash_type_ipv6ex; - int rth_bkt_sz; + u32 rth_steering:2, + rth_algorithm:2, + rth_hash_type_tcpipv4:1, + rth_hash_type_ipv4:1, + rth_hash_type_tcpipv6:1, + rth_hash_type_ipv6:1, + rth_hash_type_tcpipv6ex:1, + rth_hash_type_ipv6ex:1, + rth_bkt_sz:8; int rth_jhash_golden_ratio; int tx_steering_type; int fifo_indicate_max_pkts; @@ -248,8 +271,9 @@ struct vxge_ring { */ int driver_id; - /* copy of the flag indicating whether rx_csum is to be used */ - u32 rx_csum; + /* copy of the flag indicating whether rx_csum is to be used */ + u32 rx_csum:1, + rx_hwts:1; int pkts_processed; int budget; @@ -327,7 +351,9 @@ struct vxgedev { u16 all_multi_flg; /* A flag indicating whether rx_csum is to be used or not. */ - u32 rx_csum; + u32 rx_csum:1, + rx_hwts:1, + titan1:1; struct vxge_msix_entry *vxge_entries; struct msix_entry *entries; @@ -387,8 +413,6 @@ struct vxge_tx_priv { static int p = val; \ module_param(p, int, 0) -#define vxge_os_bug(fmt...) { printk(fmt); BUG(); } - #define vxge_os_timer(timer, handle, arg, exp) do { \ init_timer(&timer); \ timer.function = handle; \ @@ -397,6 +421,11 @@ struct vxge_tx_priv { } while (0); extern void vxge_initialize_ethtool_ops(struct net_device *ndev); + +enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev); + +int vxge_fw_upgrade(struct vxgedev *vdev, char *fw_name, int override); + /** * #define VXGE_DEBUG_INIT: debug for initialization functions * #define VXGE_DEBUG_TX : debug transmit related functions diff --git a/drivers/net/vxge/vxge-reg.h b/drivers/net/vxge/vxge-reg.h index 3dd5c9615ef9..3e658b175947 100644 --- a/drivers/net/vxge/vxge-reg.h +++ b/drivers/net/vxge/vxge-reg.h @@ -49,6 +49,33 @@ #define VXGE_HW_TITAN_VPMGMT_REG_SPACES 17 #define VXGE_HW_TITAN_VPATH_REG_SPACES 17 +#define VXGE_HW_FW_API_GET_EPROM_REV 31 + +#define VXGE_EPROM_IMG_MAJOR(val) (u32) vxge_bVALn(val, 48, 4) +#define VXGE_EPROM_IMG_MINOR(val) (u32) vxge_bVALn(val, 52, 4) +#define VXGE_EPROM_IMG_FIX(val) (u32) vxge_bVALn(val, 56, 4) +#define VXGE_EPROM_IMG_BUILD(val) (u32) vxge_bVALn(val, 60, 4) + +#define VXGE_HW_GET_EPROM_IMAGE_INDEX(val) vxge_bVALn(val, 16, 8) +#define VXGE_HW_GET_EPROM_IMAGE_VALID(val) vxge_bVALn(val, 31, 1) +#define VXGE_HW_GET_EPROM_IMAGE_TYPE(val) vxge_bVALn(val, 40, 8) +#define VXGE_HW_GET_EPROM_IMAGE_REV(val) vxge_bVALn(val, 48, 16) +#define VXGE_HW_RTS_ACCESS_STEER_ROM_IMAGE_INDEX(val) vxge_vBIT(val, 16, 8) + +#define VXGE_HW_FW_API_GET_FUNC_MODE 29 +#define VXGE_HW_GET_FUNC_MODE_VAL(val) (val & 0xFF) + +#define VXGE_HW_FW_UPGRADE_MEMO 13 +#define VXGE_HW_FW_UPGRADE_ACTION 16 +#define VXGE_HW_FW_UPGRADE_OFFSET_START 2 +#define VXGE_HW_FW_UPGRADE_OFFSET_SEND 3 +#define VXGE_HW_FW_UPGRADE_OFFSET_COMMIT 4 +#define VXGE_HW_FW_UPGRADE_OFFSET_READ 5 + +#define VXGE_HW_FW_UPGRADE_BLK_SIZE 16 +#define VXGE_HW_UPGRADE_GET_RET_ERR_CODE(val) (val & 0xff) +#define VXGE_HW_UPGRADE_GET_SEC_ERR_CODE(val) ((val >> 8) & 0xff) + #define VXGE_HW_ASIC_MODE_RESERVED 0 #define VXGE_HW_ASIC_MODE_NO_IOV 1 #define VXGE_HW_ASIC_MODE_SR_IOV 2 @@ -165,13 +192,13 @@ #define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_ETYPE 2 #define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_PN 3 #define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_GEN_CFG 5 -#define VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT 6 +#define VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT 6 #define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_JHASH_CFG 7 #define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MASK 8 #define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_KEY 9 #define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_QOS 10 #define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DS 11 -#define VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT 12 +#define VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT 12 #define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO 13 #define VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(bits) \ @@ -437,6 +464,7 @@ #define VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_BUILD(bits) \ vxge_bVALn(bits, 48, 16) #define VXGE_HW_RTS_ACCESS_STEER_DATA1_FLASH_VER_BUILD vxge_vBIT(val, 48, 16) +#define VXGE_HW_RTS_ACCESS_STEER_CTRL_GET_ACTION(bits) vxge_bVALn(bits, 0, 8) #define VXGE_HW_SRPCIM_TO_VPATH_ALARM_REG_GET_PPIF_SRPCIM_TO_VPATH_ALARM(bits)\ vxge_bVALn(bits, 0, 18) @@ -3998,6 +4026,7 @@ struct vxge_hw_vpath_reg { #define VXGE_HW_PRC_CFG6_L4_CPC_TRSFR_CODE_EN vxge_mBIT(9) #define VXGE_HW_PRC_CFG6_RXD_CRXDT(val) vxge_vBIT(val, 23, 9) #define VXGE_HW_PRC_CFG6_RXD_SPAT(val) vxge_vBIT(val, 36, 9) +#define VXGE_HW_PRC_CFG6_GET_RXD_SPAT(val) vxge_bVALn(val, 36, 9) /*0x00a78*/ u64 prc_cfg7; #define VXGE_HW_PRC_CFG7_SCATTER_MODE(val) vxge_vBIT(val, 6, 2) #define VXGE_HW_PRC_CFG7_SMART_SCAT_EN vxge_mBIT(11) diff --git a/drivers/net/vxge/vxge-traffic.h b/drivers/net/vxge/vxge-traffic.h index 9890d4d596d0..1fceee876228 100644 --- a/drivers/net/vxge/vxge-traffic.h +++ b/drivers/net/vxge/vxge-traffic.h @@ -1904,34 +1904,6 @@ enum vxge_hw_ring_tcode { VXGE_HW_RING_T_CODE_MULTI_ERR = 0xF }; -/** - * enum enum vxge_hw_ring_hash_type - RTH hash types - * @VXGE_HW_RING_HASH_TYPE_NONE: No Hash - * @VXGE_HW_RING_HASH_TYPE_TCP_IPV4: TCP IPv4 - * @VXGE_HW_RING_HASH_TYPE_UDP_IPV4: UDP IPv4 - * @VXGE_HW_RING_HASH_TYPE_IPV4: IPv4 - * @VXGE_HW_RING_HASH_TYPE_TCP_IPV6: TCP IPv6 - * @VXGE_HW_RING_HASH_TYPE_UDP_IPV6: UDP IPv6 - * @VXGE_HW_RING_HASH_TYPE_IPV6: IPv6 - * @VXGE_HW_RING_HASH_TYPE_TCP_IPV6_EX: TCP IPv6 extension - * @VXGE_HW_RING_HASH_TYPE_UDP_IPV6_EX: UDP IPv6 extension - * @VXGE_HW_RING_HASH_TYPE_IPV6_EX: IPv6 extension - * - * RTH hash types - */ -enum vxge_hw_ring_hash_type { - VXGE_HW_RING_HASH_TYPE_NONE = 0x0, - VXGE_HW_RING_HASH_TYPE_TCP_IPV4 = 0x1, - VXGE_HW_RING_HASH_TYPE_UDP_IPV4 = 0x2, - VXGE_HW_RING_HASH_TYPE_IPV4 = 0x3, - VXGE_HW_RING_HASH_TYPE_TCP_IPV6 = 0x4, - VXGE_HW_RING_HASH_TYPE_UDP_IPV6 = 0x5, - VXGE_HW_RING_HASH_TYPE_IPV6 = 0x6, - VXGE_HW_RING_HASH_TYPE_TCP_IPV6_EX = 0x7, - VXGE_HW_RING_HASH_TYPE_UDP_IPV6_EX = 0x8, - VXGE_HW_RING_HASH_TYPE_IPV6_EX = 0x9 -}; - enum vxge_hw_status vxge_hw_ring_rxd_reserve( struct __vxge_hw_ring *ring_handle, void **rxdh); diff --git a/drivers/net/vxge/vxge-version.h b/drivers/net/vxge/vxge-version.h index 53fefe137368..f05bb2f55e73 100644 --- a/drivers/net/vxge/vxge-version.h +++ b/drivers/net/vxge/vxge-version.h @@ -16,7 +16,34 @@ #define VXGE_VERSION_MAJOR "2" #define VXGE_VERSION_MINOR "0" -#define VXGE_VERSION_FIX "9" -#define VXGE_VERSION_BUILD "20840" +#define VXGE_VERSION_FIX "10" +#define VXGE_VERSION_BUILD "21808" #define VXGE_VERSION_FOR "k" + +#define VXGE_FW_VER(maj, min, bld) (((maj) << 16) + ((min) << 8) + (bld)) + +#define VXGE_DEAD_FW_VER_MAJOR 1 +#define VXGE_DEAD_FW_VER_MINOR 4 +#define VXGE_DEAD_FW_VER_BUILD 4 + +#define VXGE_FW_DEAD_VER VXGE_FW_VER(VXGE_DEAD_FW_VER_MAJOR, \ + VXGE_DEAD_FW_VER_MINOR, \ + VXGE_DEAD_FW_VER_BUILD) + +#define VXGE_EPROM_FW_VER_MAJOR 1 +#define VXGE_EPROM_FW_VER_MINOR 6 +#define VXGE_EPROM_FW_VER_BUILD 1 + +#define VXGE_EPROM_FW_VER VXGE_FW_VER(VXGE_EPROM_FW_VER_MAJOR, \ + VXGE_EPROM_FW_VER_MINOR, \ + VXGE_EPROM_FW_VER_BUILD) + +#define VXGE_CERT_FW_VER_MAJOR 1 +#define VXGE_CERT_FW_VER_MINOR 8 +#define VXGE_CERT_FW_VER_BUILD 1 + +#define VXGE_CERT_FW_VER VXGE_FW_VER(VXGE_CERT_FW_VER_MAJOR, \ + VXGE_CERT_FW_VER_MINOR, \ + VXGE_CERT_FW_VER_BUILD) + #endif diff --git a/drivers/net/znet.c b/drivers/net/znet.c index c3a329204511..ae07b3dfbcc1 100644 --- a/drivers/net/znet.c +++ b/drivers/net/znet.c @@ -124,7 +124,7 @@ MODULE_LICENSE("GPL"); #define TX_BUF_SIZE 8192 #define DMA_BUF_SIZE (RX_BUF_SIZE + 16) /* 8k + 16 bytes for trailers */ -#define TX_TIMEOUT 10 +#define TX_TIMEOUT (HZ/10) struct znet_private { int rx_dma, tx_dma; diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 93fc2449af10..7d164670f264 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -167,10 +167,10 @@ struct ip_sf_socklist { */ struct ip_mc_socklist { - struct ip_mc_socklist *next; + struct ip_mc_socklist __rcu *next_rcu; struct ip_mreqn multi; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ - struct ip_sf_socklist *sflist; + struct ip_sf_socklist __rcu *sflist; struct rcu_head rcu; }; @@ -186,11 +186,14 @@ struct ip_sf_list { struct ip_mc_list { struct in_device *interface; __be32 multiaddr; + unsigned int sfmode; struct ip_sf_list *sources; struct ip_sf_list *tomb; - unsigned int sfmode; unsigned long sfcount[2]; - struct ip_mc_list *next; + union { + struct ip_mc_list *next; + struct ip_mc_list __rcu *next_rcu; + }; struct timer_list timer; int users; atomic_t refcnt; @@ -201,6 +204,7 @@ struct ip_mc_list { char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; + struct rcu_head rcu; }; /* V3 exponential field decoding */ diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index ccd5b07d678d..380ba6bc5db1 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -52,9 +52,8 @@ struct in_device { atomic_t refcnt; int dead; struct in_ifaddr *ifa_list; /* IP ifaddr chain */ - rwlock_t mc_list_lock; - struct ip_mc_list *mc_list; /* IP multicast filter chain */ - int mc_count; /* Number of installed mcasts */ + struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ + int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d8fd2c23a1b9..578debb801f4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -951,7 +951,7 @@ struct net_device { #endif void *atalk_ptr; /* AppleTalk link */ struct in_device __rcu *ip_ptr; /* IPv4 specific data */ - void *dn_ptr; /* DECnet specific data */ + struct dn_dev __rcu *dn_ptr; /* DECnet specific data */ struct inet6_dev __rcu *ip6_ptr; /* IPv6 specific data */ void *ec_ptr; /* Econet specific data */ void *ax25_ptr; /* AX.25 specific data */ diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h index 0916bbf3bdff..b9e32db03f20 100644 --- a/include/net/dn_dev.h +++ b/include/net/dn_dev.h @@ -5,13 +5,14 @@ struct dn_dev; struct dn_ifaddr { - struct dn_ifaddr *ifa_next; + struct dn_ifaddr __rcu *ifa_next; struct dn_dev *ifa_dev; __le16 ifa_local; __le16 ifa_address; __u8 ifa_flags; __u8 ifa_scope; char ifa_label[IFNAMSIZ]; + struct rcu_head rcu; }; #define DN_DEV_S_RU 0 /* Run - working normally */ @@ -83,7 +84,7 @@ struct dn_dev_parms { struct dn_dev { - struct dn_ifaddr *ifa_list; + struct dn_ifaddr __rcu *ifa_list; struct net_device *dev; struct dn_dev_parms parms; char use_long; @@ -171,19 +172,27 @@ extern int unregister_dnaddr_notifier(struct notifier_block *nb); static inline int dn_dev_islocal(struct net_device *dev, __le16 addr) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; + int res = 0; + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db == NULL) { printk(KERN_DEBUG "dn_dev_islocal: Called for non DECnet device\n"); - return 0; + goto out; } - for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) - if ((addr ^ ifa->ifa_local) == 0) - return 1; - - return 0; + for (ifa = rcu_dereference(dn_db->ifa_list); + ifa != NULL; + ifa = rcu_dereference(ifa->ifa_next)) + if ((addr ^ ifa->ifa_local) == 0) { + res = 1; + break; + } +out: + rcu_read_unlock(); + return res; } #endif /* _NET_DN_DEV_H */ diff --git a/include/net/dn_route.h b/include/net/dn_route.h index ccadab3aa3f6..9b185df265fb 100644 --- a/include/net/dn_route.h +++ b/include/net/dn_route.h @@ -80,6 +80,16 @@ struct dn_route { unsigned rt_type; }; +static inline bool dn_is_input_route(struct dn_route *rt) +{ + return rt->fl.iif != 0; +} + +static inline bool dn_is_output_route(struct dn_route *rt) +{ + return rt->fl.iif == 0; +} + extern void dn_route_init(void); extern void dn_route_cleanup(void); diff --git a/include/net/dst.h b/include/net/dst.h index ffe9cb719c0e..a5bd72646d65 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -94,10 +94,10 @@ struct dst_entry { int __use; unsigned long lastuse; union { - struct dst_entry *next; - struct rtable __rcu *rt_next; - struct rt6_info *rt6_next; - struct dn_route *dn_next; + struct dst_entry *next; + struct rtable __rcu *rt_next; + struct rt6_info *rt6_next; + struct dn_route __rcu *dn_next; }; }; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 1989cfd7405f..8945f9fb192a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -141,7 +141,7 @@ struct inet_sock { nodefrag:1; int mc_index; __be32 mc_addr; - struct ip_mc_socklist *mc_list; + struct ip_mc_socklist __rcu *mc_list; struct { unsigned int flags; unsigned int fragsize; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 55590ab16b3e..815b2ce9f4a4 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -96,16 +96,16 @@ struct neighbour { struct neigh_parms *parms; unsigned long confirmed; unsigned long updated; - __u8 flags; - __u8 nud_state; - __u8 type; - __u8 dead; + rwlock_t lock; atomic_t refcnt; struct sk_buff_head arp_queue; struct timer_list timer; unsigned long used; atomic_t probes; - rwlock_t lock; + __u8 flags; + __u8 nud_state; + __u8 type; + __u8 dead; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))]; struct hh_cache *hh; diff --git a/include/net/route.h b/include/net/route.h index 7e5e73bfa4de..5cd46d1c0e14 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -55,8 +55,6 @@ struct rtable { /* Cache lookup keys */ struct flowi fl; - struct in_device *idev; - int rt_genid; unsigned rt_flags; __u16 rt_type; @@ -73,6 +71,16 @@ struct rtable { struct inet_peer *peer; /* long-living peer info */ }; +static inline bool rt_is_input_route(struct rtable *rt) +{ + return rt->fl.iif != 0; +} + +static inline bool rt_is_output_route(struct rtable *rt) +{ + return rt->fl.iif == 0; +} + struct ip_rt_acct { __u32 o_bytes; __u32 o_packets; diff --git a/net/core/dev.c b/net/core/dev.c index 0dd54a69dace..5968c822c999 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1817,8 +1817,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) dev->ethtool_ops->get_drvinfo(dev, &info); - WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d " - "ip_summed=%d", + WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d ip_summed=%d\n", info.driver, dev ? dev->features : 0L, skb->sk ? skb->sk->sk_route_caps : 0L, skb->len, skb->data_len, skb->ip_summed); diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 92a6fcb40d7d..abaf241c7353 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -1,7 +1,8 @@ /* * net/dccp/ackvec.c * - * An implementation of the DCCP protocol + * An implementation of Ack Vectors for the DCCP protocol + * Copyright (c) 2007 University of Aberdeen, Scotland, UK * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net> * * This program is free software; you can redistribute it and/or modify it @@ -23,173 +24,93 @@ static struct kmem_cache *dccp_ackvec_slab; static struct kmem_cache *dccp_ackvec_record_slab; -static struct dccp_ackvec_record *dccp_ackvec_record_new(void) +struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) { - struct dccp_ackvec_record *avr = - kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC); - - if (avr != NULL) - INIT_LIST_HEAD(&avr->avr_node); + struct dccp_ackvec *av = kmem_cache_zalloc(dccp_ackvec_slab, priority); - return avr; + if (av != NULL) { + av->av_buf_head = av->av_buf_tail = DCCPAV_MAX_ACKVEC_LEN - 1; + INIT_LIST_HEAD(&av->av_records); + } + return av; } -static void dccp_ackvec_record_delete(struct dccp_ackvec_record *avr) +static void dccp_ackvec_purge_records(struct dccp_ackvec *av) { - if (unlikely(avr == NULL)) - return; - /* Check if deleting a linked record */ - WARN_ON(!list_empty(&avr->avr_node)); - kmem_cache_free(dccp_ackvec_record_slab, avr); + struct dccp_ackvec_record *cur, *next; + + list_for_each_entry_safe(cur, next, &av->av_records, avr_node) + kmem_cache_free(dccp_ackvec_record_slab, cur); + INIT_LIST_HEAD(&av->av_records); } -static void dccp_ackvec_insert_avr(struct dccp_ackvec *av, - struct dccp_ackvec_record *avr) +void dccp_ackvec_free(struct dccp_ackvec *av) { - /* - * AVRs are sorted by seqno. Since we are sending them in order, we - * just add the AVR at the head of the list. - * -sorbo. - */ - if (!list_empty(&av->av_records)) { - const struct dccp_ackvec_record *head = - list_entry(av->av_records.next, - struct dccp_ackvec_record, - avr_node); - BUG_ON(before48(avr->avr_ack_seqno, head->avr_ack_seqno)); + if (likely(av != NULL)) { + dccp_ackvec_purge_records(av); + kmem_cache_free(dccp_ackvec_slab, av); } - - list_add(&avr->avr_node, &av->av_records); } -int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) +/** + * dccp_ackvec_update_records - Record information about sent Ack Vectors + * @av: Ack Vector records to update + * @seqno: Sequence number of the packet carrying the Ack Vector just sent + * @nonce_sum: The sum of all buffer nonces contained in the Ack Vector + */ +int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seqno, u8 nonce_sum) { - struct dccp_sock *dp = dccp_sk(sk); - struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; - /* Figure out how many options do we need to represent the ackvec */ - const u8 nr_opts = DIV_ROUND_UP(av->av_vec_len, DCCP_SINGLE_OPT_MAXLEN); - u16 len = av->av_vec_len + 2 * nr_opts, i; - u32 elapsed_time; - const unsigned char *tail, *from; - unsigned char *to; struct dccp_ackvec_record *avr; - suseconds_t delta; - - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) - return -1; - - delta = ktime_us_delta(ktime_get_real(), av->av_time); - elapsed_time = delta / 10; - if (elapsed_time != 0 && - dccp_insert_option_elapsed_time(skb, elapsed_time)) - return -1; - - avr = dccp_ackvec_record_new(); + avr = kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC); if (avr == NULL) - return -1; - - DCCP_SKB_CB(skb)->dccpd_opt_len += len; - - to = skb_push(skb, len); - len = av->av_vec_len; - from = av->av_buf + av->av_buf_head; - tail = av->av_buf + DCCP_MAX_ACKVEC_LEN; - - for (i = 0; i < nr_opts; ++i) { - int copylen = len; - - if (len > DCCP_SINGLE_OPT_MAXLEN) - copylen = DCCP_SINGLE_OPT_MAXLEN; - - *to++ = DCCPO_ACK_VECTOR_0; - *to++ = copylen + 2; - - /* Check if buf_head wraps */ - if (from + copylen > tail) { - const u16 tailsize = tail - from; - - memcpy(to, from, tailsize); - to += tailsize; - len -= tailsize; - copylen -= tailsize; - from = av->av_buf; - } - - memcpy(to, from, copylen); - from += copylen; - to += copylen; - len -= copylen; - } + return -ENOBUFS; + avr->avr_ack_seqno = seqno; + avr->avr_ack_ptr = av->av_buf_head; + avr->avr_ack_ackno = av->av_buf_ackno; + avr->avr_ack_nonce = nonce_sum; + avr->avr_ack_runlen = dccp_ackvec_runlen(av->av_buf + av->av_buf_head); /* - * From RFC 4340, A.2: - * - * For each acknowledgement it sends, the HC-Receiver will add an - * acknowledgement record. ack_seqno will equal the HC-Receiver - * sequence number it used for the ack packet; ack_ptr will equal - * buf_head; ack_ackno will equal buf_ackno; and ack_nonce will - * equal buf_nonce. + * When the buffer overflows, we keep no more than one record. This is + * the simplest way of disambiguating sender-Acks dating from before the + * overflow from sender-Acks which refer to after the overflow; a simple + * solution is preferable here since we are handling an exception. */ - avr->avr_ack_seqno = DCCP_SKB_CB(skb)->dccpd_seq; - avr->avr_ack_ptr = av->av_buf_head; - avr->avr_ack_ackno = av->av_buf_ackno; - avr->avr_ack_nonce = av->av_buf_nonce; - avr->avr_sent_len = av->av_vec_len; - - dccp_ackvec_insert_avr(av, avr); + if (av->av_overflow) + dccp_ackvec_purge_records(av); + /* + * Since GSS is incremented for each packet, the list is automatically + * arranged in descending order of @ack_seqno. + */ + list_add(&avr->avr_node, &av->av_records); - dccp_pr_debug("%s ACK Vector 0, len=%d, ack_seqno=%llu, " - "ack_ackno=%llu\n", - dccp_role(sk), avr->avr_sent_len, + dccp_pr_debug("Added Vector, ack_seqno=%llu, ack_ackno=%llu (rl=%u)\n", (unsigned long long)avr->avr_ack_seqno, - (unsigned long long)avr->avr_ack_ackno); + (unsigned long long)avr->avr_ack_ackno, + avr->avr_ack_runlen); return 0; } -struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) -{ - struct dccp_ackvec *av = kmem_cache_alloc(dccp_ackvec_slab, priority); - - if (av != NULL) { - av->av_buf_head = DCCP_MAX_ACKVEC_LEN - 1; - av->av_buf_ackno = UINT48_MAX + 1; - av->av_buf_nonce = 0; - av->av_time = ktime_set(0, 0); - av->av_vec_len = 0; - INIT_LIST_HEAD(&av->av_records); - } - - return av; -} - -void dccp_ackvec_free(struct dccp_ackvec *av) +/* + * Buffer index and length computation using modulo-buffersize arithmetic. + * Note that, as pointers move from right to left, head is `before' tail. + */ +static inline u16 __ackvec_idx_add(const u16 a, const u16 b) { - if (unlikely(av == NULL)) - return; - - if (!list_empty(&av->av_records)) { - struct dccp_ackvec_record *avr, *next; - - list_for_each_entry_safe(avr, next, &av->av_records, avr_node) { - list_del_init(&avr->avr_node); - dccp_ackvec_record_delete(avr); - } - } - - kmem_cache_free(dccp_ackvec_slab, av); + return (a + b) % DCCPAV_MAX_ACKVEC_LEN; } -static inline u8 dccp_ackvec_state(const struct dccp_ackvec *av, - const u32 index) +static inline u16 __ackvec_idx_sub(const u16 a, const u16 b) { - return av->av_buf[index] & DCCP_ACKVEC_STATE_MASK; + return __ackvec_idx_add(a, DCCPAV_MAX_ACKVEC_LEN - b); } -static inline u8 dccp_ackvec_len(const struct dccp_ackvec *av, - const u32 index) +u16 dccp_ackvec_buflen(const struct dccp_ackvec *av) { - return av->av_buf[index] & DCCP_ACKVEC_LEN_MASK; + if (unlikely(av->av_overflow)) + return DCCPAV_MAX_ACKVEC_LEN; + return __ackvec_idx_sub(av->av_buf_tail, av->av_buf_head); } /* @@ -204,7 +125,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, long gap; long new_head; - if (av->av_vec_len + packets > DCCP_MAX_ACKVEC_LEN) + if (av->av_vec_len + packets > DCCPAV_MAX_ACKVEC_LEN) return -ENOBUFS; gap = packets - 1; @@ -212,18 +133,18 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, if (new_head < 0) { if (gap > 0) { - memset(av->av_buf, DCCP_ACKVEC_STATE_NOT_RECEIVED, + memset(av->av_buf, DCCPAV_NOT_RECEIVED, gap + new_head + 1); gap = -new_head; } - new_head += DCCP_MAX_ACKVEC_LEN; + new_head += DCCPAV_MAX_ACKVEC_LEN; } av->av_buf_head = new_head; if (gap > 0) memset(av->av_buf + av->av_buf_head + 1, - DCCP_ACKVEC_STATE_NOT_RECEIVED, gap); + DCCPAV_NOT_RECEIVED, gap); av->av_buf[av->av_buf_head] = state; av->av_vec_len += packets; @@ -236,6 +157,8 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, const u64 ackno, const u8 state) { + u8 *cur_head = av->av_buf + av->av_buf_head, + *buf_end = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; /* * Check at the right places if the buffer is full, if it is, tell the * caller to start dropping packets till the HC-Sender acks our ACK @@ -260,7 +183,7 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, /* See if this is the first ackno being inserted */ if (av->av_vec_len == 0) { - av->av_buf[av->av_buf_head] = state; + *cur_head = state; av->av_vec_len = 1; } else if (after48(ackno, av->av_buf_ackno)) { const u64 delta = dccp_delta_seqno(av->av_buf_ackno, ackno); @@ -269,10 +192,9 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, * Look if the state of this packet is the same as the * previous ackno and if so if we can bump the head len. */ - if (delta == 1 && - dccp_ackvec_state(av, av->av_buf_head) == state && - dccp_ackvec_len(av, av->av_buf_head) < DCCP_ACKVEC_LEN_MASK) - av->av_buf[av->av_buf_head]++; + if (delta == 1 && dccp_ackvec_state(cur_head) == state && + dccp_ackvec_runlen(cur_head) < DCCPAV_MAX_RUNLEN) + *cur_head += 1; else if (dccp_ackvec_set_buf_head_state(av, delta, state)) return -ENOBUFS; } else { @@ -285,21 +207,17 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, * could reduce the complexity of this scan.) */ u64 delta = dccp_delta_seqno(ackno, av->av_buf_ackno); - u32 index = av->av_buf_head; while (1) { - const u8 len = dccp_ackvec_len(av, index); - const u8 av_state = dccp_ackvec_state(av, index); + const u8 len = dccp_ackvec_runlen(cur_head); /* * valid packets not yet in av_buf have a reserved * entry, with a len equal to 0. */ - if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED && - len == 0 && delta == 0) { /* Found our - reserved seat! */ + if (*cur_head == DCCPAV_NOT_RECEIVED && delta == 0) { dccp_pr_debug("Found %llu reserved seat!\n", (unsigned long long)ackno); - av->av_buf[index] = state; + *cur_head = state; goto out; } /* len == 0 means one packet */ @@ -307,13 +225,12 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, goto out_duplicate; delta -= len + 1; - if (++index == DCCP_MAX_ACKVEC_LEN) - index = 0; + if (++cur_head == buf_end) + cur_head = av->av_buf; } } av->av_buf_ackno = ackno; - av->av_time = ktime_get_real(); out: return 0; @@ -333,13 +250,13 @@ static void dccp_ackvec_throw_record(struct dccp_ackvec *av, if (av->av_buf_head <= avr->avr_ack_ptr) av->av_vec_len = avr->avr_ack_ptr - av->av_buf_head; else - av->av_vec_len = DCCP_MAX_ACKVEC_LEN - 1 - + av->av_vec_len = DCCPAV_MAX_ACKVEC_LEN - 1 - av->av_buf_head + avr->avr_ack_ptr; /* free records */ list_for_each_entry_safe_from(avr, next, &av->av_records, avr_node) { - list_del_init(&avr->avr_node); - dccp_ackvec_record_delete(avr); + list_del(&avr->avr_node); + kmem_cache_free(dccp_ackvec_record_slab, avr); } } @@ -357,7 +274,7 @@ void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, if (ackno == avr->avr_ack_seqno) { dccp_pr_debug("%s ACK packet 0, len=%d, ack_seqno=%llu, " "ack_ackno=%llu, ACKED!\n", - dccp_role(sk), 1, + dccp_role(sk), avr->avr_ack_runlen, (unsigned long long)avr->avr_ack_seqno, (unsigned long long)avr->avr_ack_ackno); dccp_ackvec_throw_record(av, avr); @@ -387,7 +304,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, */ avr = list_entry(av->av_records.next, struct dccp_ackvec_record, avr_node); while (i--) { - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; + const u8 rl = dccp_ackvec_runlen(vector); u64 ackno_end_rl; dccp_set_seqno(&ackno_end_rl, *ackno - rl); @@ -404,8 +321,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, break; found: if (between48(avr->avr_ack_seqno, ackno_end_rl, *ackno)) { - const u8 state = *vector & DCCP_ACKVEC_STATE_MASK; - if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED) { + if (dccp_ackvec_state(vector) != DCCPAV_NOT_RECEIVED) { dccp_pr_debug("%s ACK vector 0, len=%d, " "ack_seqno=%llu, ack_ackno=%llu, " "ACKED!\n", @@ -448,10 +364,9 @@ int __init dccp_ackvec_init(void) if (dccp_ackvec_slab == NULL) goto out_err; - dccp_ackvec_record_slab = - kmem_cache_create("dccp_ackvec_record", - sizeof(struct dccp_ackvec_record), - 0, SLAB_HWCACHE_ALIGN, NULL); + dccp_ackvec_record_slab = kmem_cache_create("dccp_ackvec_record", + sizeof(struct dccp_ackvec_record), + 0, SLAB_HWCACHE_ALIGN, NULL); if (dccp_ackvec_record_slab == NULL) goto out_destroy_slab; diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index 7ea557b7c6b1..23880be8fc29 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -3,9 +3,9 @@ /* * net/dccp/ackvec.h * - * An implementation of the DCCP protocol + * An implementation of Ack Vectors for the DCCP protocol + * Copyright (c) 2007 University of Aberdeen, Scotland, UK * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@mandriva.com> - * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. @@ -13,75 +13,89 @@ #include <linux/dccp.h> #include <linux/compiler.h> -#include <linux/ktime.h> #include <linux/list.h> #include <linux/types.h> -/* We can spread an ack vector across multiple options */ -#define DCCP_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * 2) +/* + * Ack Vector buffer space is static, in multiples of %DCCP_SINGLE_OPT_MAXLEN, + * the maximum size of a single Ack Vector. Setting %DCCPAV_NUM_ACKVECS to 1 + * will be sufficient for most cases of low Ack Ratios, using a value of 2 gives + * more headroom if Ack Ratio is higher or when the sender acknowledges slowly. + * The maximum value is bounded by the u16 types for indices and functions. + */ +#define DCCPAV_NUM_ACKVECS 2 +#define DCCPAV_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * DCCPAV_NUM_ACKVECS) /* Estimated minimum average Ack Vector length - used for updating MPS */ #define DCCPAV_MIN_OPTLEN 16 -#define DCCP_ACKVEC_STATE_RECEIVED 0 -#define DCCP_ACKVEC_STATE_ECN_MARKED (1 << 6) -#define DCCP_ACKVEC_STATE_NOT_RECEIVED (3 << 6) +enum dccp_ackvec_states { + DCCPAV_RECEIVED = 0x00, + DCCPAV_ECN_MARKED = 0x40, + DCCPAV_RESERVED = 0x80, + DCCPAV_NOT_RECEIVED = 0xC0 +}; +#define DCCPAV_MAX_RUNLEN 0x3F -#define DCCP_ACKVEC_STATE_MASK 0xC0 /* 11000000 */ -#define DCCP_ACKVEC_LEN_MASK 0x3F /* 00111111 */ +static inline u8 dccp_ackvec_runlen(const u8 *cell) +{ + return *cell & DCCPAV_MAX_RUNLEN; +} -/** struct dccp_ackvec - ack vector - * - * This data structure is the one defined in RFC 4340, Appendix A. - * - * @av_buf_head - circular buffer head - * @av_buf_tail - circular buffer tail - * @av_buf_ackno - ack # of the most recent packet acknowledgeable in the - * buffer (i.e. %av_buf_head) - * @av_buf_nonce - the one-bit sum of the ECN Nonces on all packets acked - * by the buffer with State 0 - * - * Additionally, the HC-Receiver must keep some information about the - * Ack Vectors it has recently sent. For each packet sent carrying an - * Ack Vector, it remembers four variables: +static inline u8 dccp_ackvec_state(const u8 *cell) +{ + return *cell & ~DCCPAV_MAX_RUNLEN; +} + +/** struct dccp_ackvec - Ack Vector main data structure * - * @av_records - list of dccp_ackvec_record - * @av_ack_nonce - the one-bit sum of the ECN Nonces for all State 0. + * This implements a fixed-size circular buffer within an array and is largely + * based on Appendix A of RFC 4340. * - * @av_time - the time in usecs - * @av_buf - circular buffer of acknowledgeable packets + * @av_buf: circular buffer storage area + * @av_buf_head: head index; begin of live portion in @av_buf + * @av_buf_tail: tail index; first index _after_ the live portion in @av_buf + * @av_buf_ackno: highest seqno of acknowledgeable packet recorded in @av_buf + * @av_tail_ackno: lowest seqno of acknowledgeable packet recorded in @av_buf + * @av_buf_nonce: ECN nonce sums, each covering subsequent segments of up to + * %DCCP_SINGLE_OPT_MAXLEN cells in the live portion of @av_buf + * @av_overflow: if 1 then buf_head == buf_tail indicates buffer wraparound + * @av_records: list of %dccp_ackvec_record (Ack Vectors sent previously) + * @av_veclen: length of the live portion of @av_buf */ struct dccp_ackvec { - u64 av_buf_ackno; - struct list_head av_records; - ktime_t av_time; + u8 av_buf[DCCPAV_MAX_ACKVEC_LEN]; u16 av_buf_head; + u16 av_buf_tail; + u64 av_buf_ackno:48; + u64 av_tail_ackno:48; + bool av_buf_nonce[DCCPAV_NUM_ACKVECS]; + u8 av_overflow:1; + struct list_head av_records; u16 av_vec_len; - u8 av_buf_nonce; - u8 av_ack_nonce; - u8 av_buf[DCCP_MAX_ACKVEC_LEN]; }; -/** struct dccp_ackvec_record - ack vector record +/** struct dccp_ackvec_record - Records information about sent Ack Vectors * - * ACK vector record as defined in Appendix A of spec. + * These list entries define the additional information which the HC-Receiver + * keeps about recently-sent Ack Vectors; again refer to RFC 4340, Appendix A. * - * The list is sorted by avr_ack_seqno + * @avr_node: the list node in @av_records + * @avr_ack_seqno: sequence number of the packet the Ack Vector was sent on + * @avr_ack_ackno: the Ack number that this record/Ack Vector refers to + * @avr_ack_ptr: pointer into @av_buf where this record starts + * @avr_ack_runlen: run length of @avr_ack_ptr at the time of sending + * @avr_ack_nonce: the sum of @av_buf_nonce's at the time this record was sent * - * @avr_node - node in av_records - * @avr_ack_seqno - sequence number of the packet this record was sent on - * @avr_ack_ackno - sequence number being acknowledged - * @avr_ack_ptr - pointer into av_buf where this record starts - * @avr_ack_nonce - av_ack_nonce at the time this record was sent - * @avr_sent_len - lenght of the record in av_buf + * The list as a whole is sorted in descending order by @avr_ack_seqno. */ struct dccp_ackvec_record { struct list_head avr_node; - u64 avr_ack_seqno; - u64 avr_ack_ackno; + u64 avr_ack_seqno:48; + u64 avr_ack_ackno:48; u16 avr_ack_ptr; - u16 avr_sent_len; - u8 avr_ack_nonce; + u8 avr_ack_runlen; + u8 avr_ack_nonce:1; }; struct sock; @@ -102,10 +116,11 @@ extern int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, u64 *ackno, const u8 opt, const u8 *value, const u8 len); -extern int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb); +extern int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seq, u8 sum); +extern u16 dccp_ackvec_buflen(const struct dccp_ackvec *av); -static inline int dccp_ackvec_pending(const struct dccp_ackvec *av) +static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av) { - return av->av_vec_len; + return av->av_overflow == 0 && av->av_buf_head == av->av_buf_tail; } #endif /* _ACKVEC_H */ diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 6576eae9e779..cb1b4a0d1877 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -513,8 +513,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) &vector, &veclen)) != -1) { /* go through this ack vector */ while (veclen--) { - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; - u64 ackno_end_rl = SUB48(ackno, rl); + u64 ackno_end_rl = SUB48(ackno, dccp_ackvec_runlen(vector)); ccid2_pr_debug("ackvec start:%llu end:%llu\n", (unsigned long long)ackno, @@ -537,17 +536,15 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * run length */ while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) { - const u8 state = *vector & - DCCP_ACKVEC_STATE_MASK; + const u8 state = dccp_ackvec_state(vector); /* new packet received or marked */ - if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED && + if (state != DCCPAV_NOT_RECEIVED && !seqp->ccid2s_acked) { - if (state == - DCCP_ACKVEC_STATE_ECN_MARKED) { + if (state == DCCPAV_ECN_MARKED) ccid2_congestion_event(sk, seqp); - } else + else ccid2_new_ack(sk, seqp, &maxincr); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index a8ed459508b2..19fafd597465 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -457,12 +457,15 @@ static inline void dccp_update_gss(struct sock *sk, u64 seq) dp->dccps_awh = dp->dccps_gss; } +static inline int dccp_ackvec_pending(const struct sock *sk) +{ + return dccp_sk(sk)->dccps_hc_rx_ackvec != NULL && + !dccp_ackvec_is_empty(dccp_sk(sk)->dccps_hc_rx_ackvec); +} + static inline int dccp_ack_pending(const struct sock *sk) { - const struct dccp_sock *dp = dccp_sk(sk); - return (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) || - inet_csk_ack_scheduled(sk); + return dccp_ackvec_pending(sk) || inet_csk_ack_scheduled(sk); } extern int dccp_feat_finalise_settings(struct dccp_sock *dp); diff --git a/net/dccp/input.c b/net/dccp/input.c index 265985370fa1..c7aeeba859d4 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -378,8 +378,7 @@ int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - DCCP_ACKVEC_STATE_RECEIVED)) + DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED)) goto discard; dccp_deliver_input_to_ccids(sk, skb); @@ -637,8 +636,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - DCCP_ACKVEC_STATE_RECEIVED)) + DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED)) goto discard; dccp_deliver_input_to_ccids(sk, skb); diff --git a/net/dccp/options.c b/net/dccp/options.c index cd3061813009..5adeeed5e0d2 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -340,6 +340,7 @@ static inline int dccp_elapsed_time_len(const u32 elapsed_time) return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4; } +/* FIXME: This function is currently not used anywhere */ int dccp_insert_option_elapsed_time(struct sk_buff *skb, u32 elapsed_time) { const int elapsed_time_len = dccp_elapsed_time_len(elapsed_time); @@ -424,6 +425,67 @@ static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp, return 0; } +static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; + const u16 buflen = dccp_ackvec_buflen(av); + /* Figure out how many options do we need to represent the ackvec */ + const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN); + u16 len = buflen + 2 * nr_opts; + u8 i, nonce = 0; + const unsigned char *tail, *from; + unsigned char *to; + + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + return -1; + + DCCP_SKB_CB(skb)->dccpd_opt_len += len; + + to = skb_push(skb, len); + len = buflen; + from = av->av_buf + av->av_buf_head; + tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; + + for (i = 0; i < nr_opts; ++i) { + int copylen = len; + + if (len > DCCP_SINGLE_OPT_MAXLEN) + copylen = DCCP_SINGLE_OPT_MAXLEN; + + /* + * RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via + * its type; ack_nonce is the sum of all individual buf_nonce's. + */ + nonce ^= av->av_buf_nonce[i]; + + *to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i]; + *to++ = copylen + 2; + + /* Check if buf_head wraps */ + if (from + copylen > tail) { + const u16 tailsize = tail - from; + + memcpy(to, from, tailsize); + to += tailsize; + len -= tailsize; + copylen -= tailsize; + from = av->av_buf; + } + + memcpy(to, from, copylen); + from += copylen; + to += copylen; + len -= copylen; + } + /* + * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340. + */ + if (dccp_ackvec_update_records(av, DCCP_SKB_CB(skb)->dccpd_seq, nonce)) + return -ENOBUFS; + return 0; +} + /** * dccp_insert_option_mandatory - Mandatory option (5.8.2) * Note that since we are using skb_push, this function needs to be called @@ -519,8 +581,7 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb) if (dccp_insert_option_timestamp(skb)) return -1; - } else if (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) && + } else if (dccp_ackvec_pending(sk) && dccp_insert_option_ackvec(sk, skb)) { return -1; } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index a76b78de679f..9ecef9968c39 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1848,7 +1848,7 @@ unsigned dn_mss_from_pmtu(struct net_device *dev, int mtu) { unsigned mss = 230 - DN_MAX_NSP_DATA_HEADER; if (dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); mtu -= LL_RESERVED_SPACE(dev); if (dn_db->use_long) mtu -= 21; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 4c409b46aa35..0ba15633c418 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -267,7 +267,7 @@ static int dn_forwarding_proc(ctl_table *table, int write, if (table->extra1 == NULL) return -EINVAL; - dn_db = dev->dn_ptr; + dn_db = rcu_dereference_raw(dev->dn_ptr); old = dn_db->parms.forwarding; err = proc_dointvec(table, write, buffer, lenp, ppos); @@ -332,14 +332,19 @@ static struct dn_ifaddr *dn_dev_alloc_ifa(void) return ifa; } -static __inline__ void dn_dev_free_ifa(struct dn_ifaddr *ifa) +static void dn_dev_free_ifa_rcu(struct rcu_head *head) { - kfree(ifa); + kfree(container_of(head, struct dn_ifaddr, rcu)); } -static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr **ifap, int destroy) +static void dn_dev_free_ifa(struct dn_ifaddr *ifa) { - struct dn_ifaddr *ifa1 = *ifap; + call_rcu(&ifa->rcu, dn_dev_free_ifa_rcu); +} + +static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr __rcu **ifap, int destroy) +{ + struct dn_ifaddr *ifa1 = rtnl_dereference(*ifap); unsigned char mac_addr[6]; struct net_device *dev = dn_db->dev; @@ -373,7 +378,9 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) ASSERT_RTNL(); /* Check for duplicates */ - for(ifa1 = dn_db->ifa_list; ifa1; ifa1 = ifa1->ifa_next) { + for (ifa1 = rtnl_dereference(dn_db->ifa_list); + ifa1 != NULL; + ifa1 = rtnl_dereference(ifa1->ifa_next)) { if (ifa1->ifa_local == ifa->ifa_local) return -EEXIST; } @@ -386,7 +393,7 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) } ifa->ifa_next = dn_db->ifa_list; - dn_db->ifa_list = ifa; + rcu_assign_pointer(dn_db->ifa_list, ifa); dn_ifaddr_notify(RTM_NEWADDR, ifa); blocking_notifier_call_chain(&dnaddr_chain, NETDEV_UP, ifa); @@ -396,7 +403,7 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) static int dn_dev_set_ifa(struct net_device *dev, struct dn_ifaddr *ifa) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); int rv; if (dn_db == NULL) { @@ -425,7 +432,8 @@ int dn_dev_ioctl(unsigned int cmd, void __user *arg) struct sockaddr_dn *sdn = (struct sockaddr_dn *)&ifr->ifr_addr; struct dn_dev *dn_db; struct net_device *dev; - struct dn_ifaddr *ifa = NULL, **ifap = NULL; + struct dn_ifaddr *ifa = NULL; + struct dn_ifaddr __rcu **ifap = NULL; int ret = 0; if (copy_from_user(ifr, arg, DN_IFREQ_SIZE)) @@ -454,8 +462,10 @@ int dn_dev_ioctl(unsigned int cmd, void __user *arg) goto done; } - if ((dn_db = dev->dn_ptr) != NULL) { - for (ifap = &dn_db->ifa_list; (ifa=*ifap) != NULL; ifap = &ifa->ifa_next) + if ((dn_db = rtnl_dereference(dev->dn_ptr)) != NULL) { + for (ifap = &dn_db->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; + ifap = &ifa->ifa_next) if (strcmp(ifr->ifr_name, ifa->ifa_label) == 0) break; } @@ -558,7 +568,7 @@ static struct dn_dev *dn_dev_by_index(int ifindex) dev = __dev_get_by_index(&init_net, ifindex); if (dev) - dn_dev = dev->dn_ptr; + dn_dev = rtnl_dereference(dev->dn_ptr); return dn_dev; } @@ -576,7 +586,8 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct nlattr *tb[IFA_MAX+1]; struct dn_dev *dn_db; struct ifaddrmsg *ifm; - struct dn_ifaddr *ifa, **ifap; + struct dn_ifaddr *ifa; + struct dn_ifaddr __rcu **ifap; int err = -EINVAL; if (!net_eq(net, &init_net)) @@ -592,7 +603,9 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) goto errout; err = -EADDRNOTAVAIL; - for (ifap = &dn_db->ifa_list; (ifa = *ifap); ifap = &ifa->ifa_next) { + for (ifap = &dn_db->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; + ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && nla_memcmp(tb[IFA_LOCAL], &ifa->ifa_local, 2)) continue; @@ -632,7 +645,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if ((dev = __dev_get_by_index(&init_net, ifm->ifa_index)) == NULL) return -ENODEV; - if ((dn_db = dev->dn_ptr) == NULL) { + if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL) { dn_db = dn_dev_create(dev, &err); if (!dn_db) return err; @@ -748,11 +761,11 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) skip_naddr = 0; } - if ((dn_db = dev->dn_ptr) == NULL) + if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL) goto cont; - for (ifa = dn_db->ifa_list, dn_idx = 0; ifa; - ifa = ifa->ifa_next, dn_idx++) { + for (ifa = rtnl_dereference(dn_db->ifa_list), dn_idx = 0; ifa; + ifa = rtnl_dereference(ifa->ifa_next), dn_idx++) { if (dn_idx < skip_naddr) continue; @@ -773,21 +786,22 @@ done: static int dn_dev_get_first(struct net_device *dev, __le16 *addr) { - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; int rv = -ENODEV; + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db == NULL) goto out; - rtnl_lock(); - ifa = dn_db->ifa_list; + ifa = rcu_dereference(dn_db->ifa_list); if (ifa != NULL) { *addr = ifa->ifa_local; rv = 0; } - rtnl_unlock(); out: + rcu_read_unlock(); return rv; } @@ -823,7 +837,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) struct endnode_hello_message *msg; struct sk_buff *skb = NULL; __le16 *pktlen; - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if ((skb = dn_alloc_skb(NULL, sizeof(*msg), GFP_ATOMIC)) == NULL) return; @@ -889,7 +903,7 @@ static int dn_am_i_a_router(struct dn_neigh *dn, struct dn_dev *dn_db, struct dn static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) { int n; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; struct sk_buff *skb; size_t size; @@ -960,7 +974,7 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) static void dn_send_brd_hello(struct net_device *dev, struct dn_ifaddr *ifa) { - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.forwarding == 0) dn_send_endnode_hello(dev, ifa); @@ -998,7 +1012,7 @@ static void dn_send_ptp_hello(struct net_device *dev, struct dn_ifaddr *ifa) static int dn_eth_up(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.forwarding == 0) dev_mc_add(dev, dn_rt_all_end_mcast); @@ -1012,7 +1026,7 @@ static int dn_eth_up(struct net_device *dev) static void dn_eth_down(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.forwarding == 0) dev_mc_del(dev, dn_rt_all_end_mcast); @@ -1025,12 +1039,16 @@ static void dn_dev_set_timer(struct net_device *dev); static void dn_dev_timer_func(unsigned long arg) { struct net_device *dev = (struct net_device *)arg; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db->t3 <= dn_db->parms.t2) { if (dn_db->parms.timer3) { - for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) { + for (ifa = rcu_dereference(dn_db->ifa_list); + ifa; + ifa = rcu_dereference(ifa->ifa_next)) { if (!(ifa->ifa_flags & IFA_F_SECONDARY)) dn_db->parms.timer3(dev, ifa); } @@ -1039,13 +1057,13 @@ static void dn_dev_timer_func(unsigned long arg) } else { dn_db->t3 -= dn_db->parms.t2; } - + rcu_read_unlock(); dn_dev_set_timer(dev); } static void dn_dev_set_timer(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.t2 > dn_db->parms.t3) dn_db->parms.t2 = dn_db->parms.t3; @@ -1077,8 +1095,8 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) return NULL; memcpy(&dn_db->parms, p, sizeof(struct dn_dev_parms)); - smp_wmb(); - dev->dn_ptr = dn_db; + + rcu_assign_pointer(dev->dn_ptr, dn_db); dn_db->dev = dev; init_timer(&dn_db->timer); @@ -1086,7 +1104,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) dn_db->neigh_parms = neigh_parms_alloc(dev, &dn_neigh_table); if (!dn_db->neigh_parms) { - dev->dn_ptr = NULL; + rcu_assign_pointer(dev->dn_ptr, NULL); kfree(dn_db); return NULL; } @@ -1125,7 +1143,7 @@ void dn_dev_up(struct net_device *dev) struct dn_ifaddr *ifa; __le16 addr = decnet_address; int maybe_default = 0; - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK)) return; @@ -1176,7 +1194,7 @@ void dn_dev_up(struct net_device *dev) static void dn_dev_delete(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); if (dn_db == NULL) return; @@ -1204,13 +1222,13 @@ static void dn_dev_delete(struct net_device *dev) void dn_dev_down(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); struct dn_ifaddr *ifa; if (dn_db == NULL) return; - while((ifa = dn_db->ifa_list) != NULL) { + while ((ifa = rtnl_dereference(dn_db->ifa_list)) != NULL) { dn_dev_del_ifa(dn_db, &dn_db->ifa_list, 0); dn_dev_free_ifa(ifa); } @@ -1270,7 +1288,7 @@ static inline int is_dn_dev(struct net_device *dev) } static void *dn_dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(rcu) + __acquires(RCU) { int i; struct net_device *dev; @@ -1313,7 +1331,7 @@ static void *dn_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void dn_dev_seq_stop(struct seq_file *seq, void *v) - __releases(rcu) + __releases(RCU) { rcu_read_unlock(); } @@ -1340,7 +1358,7 @@ static int dn_dev_seq_show(struct seq_file *seq, void *v) struct net_device *dev = v; char peer_buf[DN_ASCBUF_LEN]; char router_buf[DN_ASCBUF_LEN]; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference(dev->dn_ptr); seq_printf(seq, "%-8s %1s %04u %04u %04lu %04lu" " %04hu %03d %02x %-10s %-7s %-7s\n", diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 4ab96c15166d..0ef0a81bcd72 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -610,10 +610,12 @@ static void dn_fib_del_ifaddr(struct dn_ifaddr *ifa) /* Scan device list */ rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { - dn_db = dev->dn_ptr; + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db == NULL) continue; - for(ifa2 = dn_db->ifa_list; ifa2; ifa2 = ifa2->ifa_next) { + for (ifa2 = rcu_dereference(dn_db->ifa_list); + ifa2 != NULL; + ifa2 = rcu_dereference(ifa2->ifa_next)) { if (ifa2->ifa_local == ifa->ifa_local) { found_it = 1; break; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index a085dbcf5c7f..602dade7e9a3 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -391,7 +391,7 @@ int dn_neigh_router_hello(struct sk_buff *skb) write_lock(&neigh->lock); neigh->used = jiffies; - dn_db = (struct dn_dev *)neigh->dev->dn_ptr; + dn_db = rcu_dereference(neigh->dev->dn_ptr); if (!(neigh->nud_state & NUD_PERMANENT)) { neigh->updated = jiffies; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index df0f3e54ff8a..474d54dd08c2 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -93,7 +93,7 @@ struct dn_rt_hash_bucket { - struct dn_route *chain; + struct dn_route __rcu *chain; spinlock_t lock; }; @@ -157,15 +157,17 @@ static inline void dnrt_drop(struct dn_route *rt) static void dn_dst_check_expire(unsigned long dummy) { int i; - struct dn_route *rt, **rtp; + struct dn_route *rt; + struct dn_route __rcu **rtp; unsigned long now = jiffies; unsigned long expire = 120 * HZ; - for(i = 0; i <= dn_rt_hash_mask; i++) { + for (i = 0; i <= dn_rt_hash_mask; i++) { rtp = &dn_rt_hash_table[i].chain; spin_lock(&dn_rt_hash_table[i].lock); - while((rt=*rtp) != NULL) { + while ((rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { if (atomic_read(&rt->dst.__refcnt) || (now - rt->dst.lastuse) < expire) { rtp = &rt->dst.dn_next; @@ -186,17 +188,19 @@ static void dn_dst_check_expire(unsigned long dummy) static int dn_dst_gc(struct dst_ops *ops) { - struct dn_route *rt, **rtp; + struct dn_route *rt; + struct dn_route __rcu **rtp; int i; unsigned long now = jiffies; unsigned long expire = 10 * HZ; - for(i = 0; i <= dn_rt_hash_mask; i++) { + for (i = 0; i <= dn_rt_hash_mask; i++) { spin_lock_bh(&dn_rt_hash_table[i].lock); rtp = &dn_rt_hash_table[i].chain; - while((rt=*rtp) != NULL) { + while ((rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { if (atomic_read(&rt->dst.__refcnt) || (now - rt->dst.lastuse) < expire) { rtp = &rt->dst.dn_next; @@ -227,7 +231,7 @@ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) { u32 min_mtu = 230; struct dn_dev *dn = dst->neighbour ? - (struct dn_dev *)dst->neighbour->dev->dn_ptr : NULL; + rcu_dereference_raw(dst->neighbour->dev->dn_ptr) : NULL; if (dn && dn->use_long == 0) min_mtu -= 6; @@ -277,13 +281,15 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route **rp) { - struct dn_route *rth, **rthp; + struct dn_route *rth; + struct dn_route __rcu **rthp; unsigned long now = jiffies; rthp = &dn_rt_hash_table[hash].chain; spin_lock_bh(&dn_rt_hash_table[hash].lock); - while((rth = *rthp) != NULL) { + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(&dn_rt_hash_table[hash].lock))) != NULL) { if (compare_keys(&rth->fl, &rt->fl)) { /* Put it first */ *rthp = rth->dst.dn_next; @@ -315,15 +321,15 @@ static void dn_run_flush(unsigned long dummy) int i; struct dn_route *rt, *next; - for(i = 0; i < dn_rt_hash_mask; i++) { + for (i = 0; i < dn_rt_hash_mask; i++) { spin_lock_bh(&dn_rt_hash_table[i].lock); - if ((rt = xchg(&dn_rt_hash_table[i].chain, NULL)) == NULL) + if ((rt = xchg((struct dn_route **)&dn_rt_hash_table[i].chain, NULL)) == NULL) goto nothing_to_declare; - for(; rt; rt=next) { - next = rt->dst.dn_next; - rt->dst.dn_next = NULL; + for(; rt; rt = next) { + next = rcu_dereference_raw(rt->dst.dn_next); + RCU_INIT_POINTER(rt->dst.dn_next, NULL); dst_free((struct dst_entry *)rt); } @@ -458,15 +464,16 @@ static int dn_return_long(struct sk_buff *skb) */ static int dn_route_rx_packet(struct sk_buff *skb) { - struct dn_skb_cb *cb = DN_SKB_CB(skb); + struct dn_skb_cb *cb; int err; if ((err = dn_route_input(skb)) == 0) return dst_input(skb); + cb = DN_SKB_CB(skb); if (decnet_debug_level & 4) { char *devname = skb->dev ? skb->dev->name : "???"; - struct dn_skb_cb *cb = DN_SKB_CB(skb); + printk(KERN_DEBUG "DECnet: dn_route_rx_packet: rt_flags=0x%02x dev=%s len=%d src=0x%04hx dst=0x%04hx err=%d type=%d\n", (int)cb->rt_flags, devname, skb->len, @@ -573,7 +580,7 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type struct dn_skb_cb *cb; unsigned char flags = 0; __u16 len = le16_to_cpu(*(__le16 *)skb->data); - struct dn_dev *dn = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn = rcu_dereference(dev->dn_ptr); unsigned char padlen = 0; if (!net_eq(dev_net(dev), &init_net)) @@ -728,7 +735,7 @@ static int dn_forward(struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); struct dst_entry *dst = skb_dst(skb); - struct dn_dev *dn_db = dst->dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference(dst->dev->dn_ptr); struct dn_route *rt; struct neighbour *neigh = dst->neighbour; int header_len; @@ -835,13 +842,16 @@ static inline int dn_match_addr(__le16 addr1, __le16 addr2) static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int scope) { __le16 saddr = 0; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; int best_match = 0; int ret; - read_lock(&dev_base_lock); - for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) { + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); + for (ifa = rcu_dereference(dn_db->ifa_list); + ifa != NULL; + ifa = rcu_dereference(ifa->ifa_next)) { if (ifa->ifa_scope > scope) continue; if (!daddr) { @@ -854,7 +864,7 @@ static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int if (best_match == 0) saddr = ifa->ifa_local; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); return saddr; } @@ -1020,7 +1030,7 @@ source_ok: err = -ENODEV; if (dev_out == NULL) goto out; - dn_db = dev_out->dn_ptr; + dn_db = rcu_dereference_raw(dev_out->dn_ptr); /* Possible improvement - check all devices for local addr */ if (dn_dev_islocal(dev_out, fl.fld_dst)) { dev_put(dev_out); @@ -1171,7 +1181,7 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowi *fl if ((flp->fld_dst == rt->fl.fld_dst) && (flp->fld_src == rt->fl.fld_src) && (flp->mark == rt->fl.mark) && - (rt->fl.iif == 0) && + dn_is_output_route(rt) && (rt->fl.oif == flp->oif)) { dst_use(&rt->dst, jiffies); rcu_read_unlock_bh(); @@ -1233,7 +1243,7 @@ static int dn_route_input_slow(struct sk_buff *skb) dev_hold(in_dev); - if ((dn_db = in_dev->dn_ptr) == NULL) + if ((dn_db = rcu_dereference(in_dev->dn_ptr)) == NULL) goto out; /* Zero source addresses are not allowed */ @@ -1502,7 +1512,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0, expires, rt->dst.error) < 0) goto rtattr_failure; - if (rt->fl.iif) + if (dn_is_input_route(rt)) RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fl.iif); nlh->nlmsg_len = skb_tail_pointer(skb) - b; @@ -1677,15 +1687,15 @@ static struct dn_route *dn_rt_cache_get_next(struct seq_file *seq, struct dn_rou { struct dn_rt_cache_iter_state *s = seq->private; - rt = rt->dst.dn_next; - while(!rt) { + rt = rcu_dereference_bh(rt->dst.dn_next); + while (!rt) { rcu_read_unlock_bh(); if (--s->bucket < 0) break; rcu_read_lock_bh(); - rt = dn_rt_hash_table[s->bucket].chain; + rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain); } - return rcu_dereference_bh(rt); + return rt; } static void *dn_rt_cache_seq_start(struct seq_file *seq, loff_t *pos) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 96bc7f9475a3..c6e2affafbd3 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -506,8 +506,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) struct net_device *dev = NULL; rcu_read_lock(); - if (rt->fl.iif && - net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) + if (rt_is_input_route(rt) && + net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) dev = dev_get_by_index_rcu(net, rt->fl.iif); if (dev) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3c53c2d89e3b..0f0e0f0279b8 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -149,11 +149,17 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); + +static void ip_mc_list_reclaim(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_mc_list, rcu)); +} + static void ip_ma_put(struct ip_mc_list *im) { if (atomic_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); - kfree(im); + call_rcu(&im->rcu, ip_mc_list_reclaim); } } @@ -163,7 +169,7 @@ static void ip_ma_put(struct ip_mc_list *im) * Timer management */ -static __inline__ void igmp_stop_timer(struct ip_mc_list *im) +static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) @@ -496,14 +502,24 @@ empty_source: return skb; } +#define for_each_pmc_rcu(in_dev, pmc) \ + for (pmc = rcu_dereference(in_dev->mc_list); \ + pmc != NULL; \ + pmc = rcu_dereference(pmc->next_rcu)) + +#define for_each_pmc_rtnl(in_dev, pmc) \ + for (pmc = rtnl_dereference(in_dev->mc_list); \ + pmc != NULL; \ + pmc = rtnl_dereference(pmc->next_rcu)) + static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; int type; if (!pmc) { - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; spin_lock_bh(&pmc->lock); @@ -514,7 +530,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -556,7 +572,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) struct sk_buff *skb = NULL; int type, dtype; - read_lock(&in_dev->mc_list_lock); + rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ @@ -593,7 +609,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; @@ -616,7 +632,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) } spin_unlock_bh(&pmc->lock); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); if (!skb) return; @@ -813,14 +829,14 @@ static void igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return; - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im!=NULL; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, @@ -906,8 +922,8 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * - Use the igmp->igmp_code field as the maximum * delay possible */ - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im!=NULL; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) @@ -925,7 +941,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (changed) igmp_mod_timer(im, max_delay); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } /* called in rcu_read_lock() section */ @@ -961,7 +977,7 @@ int igmp_rcv(struct sk_buff *skb) case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ - if (skb_rtable(skb)->fl.iif == 0) + if (rt_is_output_route(skb_rtable(skb))) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || @@ -1110,8 +1126,8 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) kfree(pmc); } /* clear dead sources, too */ - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf, *psf_next; spin_lock_bh(&pmc->lock); @@ -1123,7 +1139,7 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) kfree(psf); } } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } #endif @@ -1209,7 +1225,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - for (im=in_dev->mc_list; im; im=im->next) { + for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0); @@ -1217,7 +1233,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) } } - im = kmalloc(sizeof(*im), GFP_KERNEL); + im = kzalloc(sizeof(*im), GFP_KERNEL); if (!im) goto out; @@ -1227,26 +1243,18 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) im->multiaddr = addr; /* initial mode is (EX, empty) */ im->sfmode = MCAST_EXCLUDE; - im->sfcount[MCAST_INCLUDE] = 0; im->sfcount[MCAST_EXCLUDE] = 1; - im->sources = NULL; - im->tomb = NULL; - im->crcount = 0; atomic_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST - im->tm_running = 0; setup_timer(&im->timer, &igmp_timer_expire, (unsigned long)im); im->unsolicit_count = IGMP_Unsolicited_Report_Count; - im->reporter = 0; - im->gsquery = 0; #endif - im->loaded = 0; - write_lock_bh(&in_dev->mc_list_lock); - im->next = in_dev->mc_list; - in_dev->mc_list = im; + + im->next_rcu = in_dev->mc_list; in_dev->mc_count++; - write_unlock_bh(&in_dev->mc_list_lock); + rcu_assign_pointer(in_dev->mc_list, im); + #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im->multiaddr); #endif @@ -1287,17 +1295,18 @@ EXPORT_SYMBOL(ip_mc_rejoin_group); void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { - struct ip_mc_list *i, **ip; + struct ip_mc_list *i; + struct ip_mc_list __rcu **ip; ASSERT_RTNL(); - for (ip=&in_dev->mc_list; (i=*ip)!=NULL; ip=&i->next) { + for (ip = &in_dev->mc_list; + (i = rtnl_dereference(*ip)) != NULL; + ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { - write_lock_bh(&in_dev->mc_list_lock); - *ip = i->next; + *ip = i->next_rcu; in_dev->mc_count--; - write_unlock_bh(&in_dev->mc_list_lock); igmp_group_dropped(i); if (!in_dev->dead) @@ -1316,34 +1325,34 @@ EXPORT_SYMBOL(ip_mc_dec_group); void ip_mc_unmap(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i = in_dev->mc_list; i; i = i->next) - igmp_group_dropped(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i = in_dev->mc_list; i; i = i->next) - igmp_group_added(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_added(pmc); } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i=in_dev->mc_list; i; i=i->next) - igmp_group_dropped(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST in_dev->mr_ifc_count = 0; @@ -1374,7 +1383,6 @@ void ip_mc_init_dev(struct in_device *in_dev) in_dev->mr_qrv = IGMP_Unsolicited_Report_Count; #endif - rwlock_init(&in_dev->mc_list_lock); spin_lock_init(&in_dev->mc_tomb_lock); } @@ -1382,14 +1390,14 @@ void ip_mc_init_dev(struct in_device *in_dev) void ip_mc_up(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); - for (i=in_dev->mc_list; i; i=i->next) - igmp_group_added(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_added(pmc); } /* @@ -1405,17 +1413,13 @@ void ip_mc_destroy_dev(struct in_device *in_dev) /* Deactivate timers */ ip_mc_down(in_dev); - write_lock_bh(&in_dev->mc_list_lock); - while ((i = in_dev->mc_list) != NULL) { - in_dev->mc_list = i->next; + while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { + in_dev->mc_list = i->next_rcu; in_dev->mc_count--; - write_unlock_bh(&in_dev->mc_list_lock); + igmp_group_dropped(i); ip_ma_put(i); - - write_lock_bh(&in_dev->mc_list_lock); } - write_unlock_bh(&in_dev->mc_list_lock); } /* RTNL is locked */ @@ -1513,18 +1517,18 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!in_dev) return -ENODEV; - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif @@ -1685,18 +1689,18 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!in_dev) return -ENODEV; - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); @@ -1793,7 +1797,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) err = -EADDRINUSE; ifindex = imr->imr_ifindex; - for (i = inet->mc_list; i; i = i->next) { + for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; @@ -1807,7 +1811,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); - iml->next = inet->mc_list; + iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = MCAST_EXCLUDE; rcu_assign_pointer(inet->mc_list, iml); @@ -1821,17 +1825,14 @@ EXPORT_SYMBOL(ip_mc_join_group); static void ip_sf_socklist_reclaim(struct rcu_head *rp) { - struct ip_sf_socklist *psf; - - psf = container_of(rp, struct ip_sf_socklist, rcu); + kfree(container_of(rp, struct ip_sf_socklist, rcu)); /* sk_omem_alloc should have been decreased by the caller*/ - kfree(psf); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { - struct ip_sf_socklist *psf = iml->sflist; + struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (psf == NULL) { @@ -1851,11 +1852,8 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, static void ip_mc_socklist_reclaim(struct rcu_head *rp) { - struct ip_mc_socklist *iml; - - iml = container_of(rp, struct ip_mc_socklist, rcu); + kfree(container_of(rp, struct ip_mc_socklist, rcu)); /* sk_omem_alloc should have been decreased by the caller*/ - kfree(iml); } @@ -1866,7 +1864,8 @@ static void ip_mc_socklist_reclaim(struct rcu_head *rp) int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); - struct ip_mc_socklist *iml, **imlp; + struct ip_mc_socklist *iml; + struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; @@ -1876,7 +1875,9 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) rtnl_lock(); in_dev = ip_mc_find_dev(net, imr); ifindex = imr->imr_ifindex; - for (imlp = &inet->mc_list; (iml = *imlp) != NULL; imlp = &iml->next) { + for (imlp = &inet->mc_list; + (iml = rtnl_dereference(*imlp)) != NULL; + imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { @@ -1888,7 +1889,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) (void) ip_mc_leave_src(sk, iml, in_dev); - rcu_assign_pointer(*imlp, iml->next); + *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); @@ -1934,7 +1935,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) @@ -1958,7 +1959,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct pmc->sfmode = omode; } - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ @@ -2077,7 +2078,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) goto done; } - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; @@ -2107,7 +2108,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); @@ -2155,7 +2156,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, } err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; @@ -2163,7 +2164,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); rtnl_unlock(); if (!psl) { len = 0; @@ -2208,7 +2209,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; @@ -2216,7 +2217,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, if (!pmc) /* must have a prior join */ goto done; gsf->gf_fmode = pmc->sfmode; - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); rtnl_unlock(); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; @@ -2257,7 +2258,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) goto out; rcu_read_lock(); - for (pmc=rcu_dereference(inet->mc_list); pmc; pmc=rcu_dereference(pmc->next)) { + for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && pmc->multi.imr_ifindex == dif) break; @@ -2265,7 +2266,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) ret = inet->mc_all; if (!pmc) goto unlock; - psl = pmc->sflist; + psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; @@ -2300,10 +2301,10 @@ void ip_mc_drop_socket(struct sock *sk) return; rtnl_lock(); - while ((iml = inet->mc_list) != NULL) { + while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; - rcu_assign_pointer(inet->mc_list, iml->next); + inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev != NULL) @@ -2321,8 +2322,8 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p struct ip_sf_list *psf; int rv = 0; - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } @@ -2343,7 +2344,7 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p } else rv = 1; /* unspecified source; tentatively allow */ } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return rv; } @@ -2369,13 +2370,11 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; - read_lock(&in_dev->mc_list_lock); - im = in_dev->mc_list; + im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } - read_unlock(&in_dev->mc_list_lock); } return im; } @@ -2383,11 +2382,9 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); - im = im->next; - while (!im) { - if (likely(state->in_dev != NULL)) - read_unlock(&state->in_dev->mc_list_lock); + im = rcu_dereference(im->next_rcu); + while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; @@ -2396,8 +2393,7 @@ static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_li state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; - read_lock(&state->in_dev->mc_list_lock); - im = state->in_dev->mc_list; + im = rcu_dereference(state->in_dev->mc_list); } return im; } @@ -2433,10 +2429,8 @@ static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); - if (likely(state->in_dev != NULL)) { - read_unlock(&state->in_dev->mc_list_lock); - state->in_dev = NULL; - } + + state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } @@ -2458,7 +2452,7 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v) querier = "NONE"; #endif - if (state->in_dev->mc_list == im) { + if (rcu_dereference(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } @@ -2517,8 +2511,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) idev = __in_dev_get_rcu(state->dev); if (unlikely(idev == NULL)) continue; - read_lock(&idev->mc_list_lock); - im = idev->mc_list; + im = rcu_dereference(idev->mc_list); if (likely(im != NULL)) { spin_lock_bh(&im->lock); psf = im->sources; @@ -2529,7 +2522,6 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) } spin_unlock_bh(&im->lock); } - read_unlock(&idev->mc_list_lock); } return psf; } @@ -2543,9 +2535,6 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) - read_unlock(&state->idev->mc_list_lock); - state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; @@ -2554,8 +2543,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; - read_lock(&state->idev->mc_list_lock); - state->im = state->idev->mc_list; + state->im = rcu_dereference(state->idev->mc_list); } if (!state->im) break; @@ -2601,10 +2589,7 @@ static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) spin_unlock_bh(&state->im->lock); state->im = NULL; } - if (likely(state->idev != NULL)) { - read_unlock(&state->idev->mc_list_lock); - state->idev = NULL; - } + state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 70ff77f02eee..cab2057d5430 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -634,7 +634,7 @@ static int ipgre_rcv(struct sk_buff *skb) #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { /* Looped back packet, drop it! */ - if (skb_rtable(skb)->fl.iif == 0) + if (rt_is_output_route(skb_rtable(skb))) goto drop; tunnel->dev->stats.multicast++; skb->pkt_type = PACKET_BROADCAST; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 86dd5691af46..ef2b0089e0ea 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1654,7 +1654,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, if (mrt->vif_table[vif].dev != skb->dev) { int true_vifi; - if (skb_rtable(skb)->fl.iif == 0) { + if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... * diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 987bf9adb318..66610ea3c87b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -140,13 +140,15 @@ static unsigned long expires_ljiffies; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static void ipv4_dst_destroy(struct dst_entry *dst); -static void ipv4_dst_ifdown(struct dst_entry *dst, - struct net_device *dev, int how); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu); static int rt_garbage_collect(struct dst_ops *ops); +static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, + int how) +{ +} static struct dst_ops ipv4_dst_ops = { .family = AF_INET, @@ -621,7 +623,7 @@ static inline int rt_fast_clean(struct rtable *rth) /* Kill broadcast/multicast entries very aggresively, if they collide in hash table with more useful entries */ return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && - rth->fl.iif && rth->dst.rt_next; + rt_is_input_route(rth) && rth->dst.rt_next; } static inline int rt_valuable(struct rtable *rth) @@ -666,7 +668,7 @@ static inline u32 rt_score(struct rtable *rt) if (rt_valuable(rt)) score |= (1<<31); - if (!rt->fl.iif || + if (rt_is_output_route(rt) || !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL))) score |= (1<<30); @@ -1124,7 +1126,7 @@ restart: */ rt->dst.flags |= DST_NOCACHE; - if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { + if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { int err = arp_bind_neighbour(&rt->dst); if (err) { if (net_ratelimit()) @@ -1222,7 +1224,7 @@ restart: /* Try to bind route to arp only if it is output route or unicast forwarding path. */ - if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { + if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { int err = arp_bind_neighbour(&rt->dst); if (err) { spin_unlock_bh(rt_hash_lock_addr(hash)); @@ -1404,7 +1406,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, if (rth->fl.fl4_dst != daddr || rth->fl.fl4_src != skeys[i] || rth->fl.oif != ikeys[k] || - rth->fl.iif != 0 || + rt_is_input_route(rth) || rt_is_expired(rth) || !net_eq(dev_net(rth->dst.dev), net)) { rthp = &rth->dst.rt_next; @@ -1433,8 +1435,6 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, rt->dst.child = NULL; if (rt->dst.dev) dev_hold(rt->dst.dev); - if (rt->idev) - in_dev_hold(rt->idev); rt->dst.obsolete = -1; rt->dst.lastuse = jiffies; rt->dst.path = &rt->dst; @@ -1666,7 +1666,7 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, rth->rt_dst != daddr || rth->rt_src != iph->saddr || rth->fl.oif != ikeys[k] || - rth->fl.iif != 0 || + rt_is_input_route(rth) || dst_metric_locked(&rth->dst, RTAX_MTU) || !net_eq(dev_net(rth->dst.dev), net) || rt_is_expired(rth)) @@ -1728,33 +1728,13 @@ static void ipv4_dst_destroy(struct dst_entry *dst) { struct rtable *rt = (struct rtable *) dst; struct inet_peer *peer = rt->peer; - struct in_device *idev = rt->idev; if (peer) { rt->peer = NULL; inet_putpeer(peer); } - - if (idev) { - rt->idev = NULL; - in_dev_put(idev); - } } -static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int how) -{ - struct rtable *rt = (struct rtable *) dst; - struct in_device *idev = rt->idev; - if (dev != dev_net(dev)->loopback_dev && idev && idev->dev == dev) { - struct in_device *loopback_idev = - in_dev_get(dev_net(dev)->loopback_dev); - if (loopback_idev) { - rt->idev = loopback_idev; - in_dev_put(idev); - } - } -} static void ipv4_link_failure(struct sk_buff *skb) { @@ -1790,7 +1770,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) __be32 src; struct fib_result res; - if (rt->fl.iif == 0) + if (rt_is_output_route(rt)) src = rt->rt_src; else { rcu_read_lock(); @@ -1910,7 +1890,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->fl.iif = dev->ifindex; rth->dst.dev = init_net.loopback_dev; dev_hold(rth->dst.dev); - rth->idev = in_dev_get(rth->dst.dev); rth->fl.oif = 0; rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; @@ -2050,7 +2029,6 @@ static int __mkroute_input(struct sk_buff *skb, rth->fl.iif = in_dev->dev->ifindex; rth->dst.dev = (out_dev)->dev; dev_hold(rth->dst.dev); - rth->idev = in_dev_get(rth->dst.dev); rth->fl.oif = 0; rth->rt_spec_dst= spec_dst; @@ -2231,7 +2209,6 @@ local_input: rth->fl.iif = dev->ifindex; rth->dst.dev = net->loopback_dev; dev_hold(rth->dst.dev); - rth->idev = in_dev_get(rth->dst.dev); rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; rth->dst.input= ip_local_deliver; @@ -2417,9 +2394,6 @@ static int __mkroute_output(struct rtable **result, if (!rth) return -ENOBUFS; - in_dev_hold(in_dev); - rth->idev = in_dev; - atomic_set(&rth->dst.__refcnt, 1); rth->dst.flags= DST_HOST; if (IN_DEV_CONF_GET(in_dev, NOXFRM)) @@ -2695,7 +2669,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, rth = rcu_dereference_bh(rth->dst.rt_next)) { if (rth->fl.fl4_dst == flp->fl4_dst && rth->fl.fl4_src == flp->fl4_src && - rth->fl.iif == 0 && + rt_is_output_route(rth) && rth->fl.oif == flp->oif && rth->fl.mark == flp->mark && !((rth->fl.fl4_tos ^ flp->fl4_tos) & @@ -2759,9 +2733,6 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi rt->fl = ort->fl; - rt->idev = ort->idev; - if (rt->idev) - in_dev_hold(rt->idev); rt->rt_genid = rt_genid(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; @@ -2853,7 +2824,7 @@ static int rt_fill_info(struct net *net, if (rt->dst.tclassid) NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid); #endif - if (rt->fl.iif) + if (rt_is_input_route(rt)) NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst); else if (rt->rt_src != rt->fl.fl4_src) NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src); @@ -2878,7 +2849,7 @@ static int rt_fill_info(struct net *net, } } - if (rt->fl.iif) { + if (rt_is_input_route(rt)) { #ifdef CONFIG_IP_MROUTE __be32 dst = rt->rt_dst; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 081419969485..2bb46d55f40c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1193,7 +1193,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), - KERN_INFO "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", + "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); #endif @@ -1477,10 +1477,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), - KERN_INFO "recvmsg bug: copied %X " - "seq %X rcvnxt %X fl %X\n", *seq, - TCP_SKB_CB(skb)->seq, tp->rcv_nxt, - flags)) + "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n", + *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, + flags)) break; offset = *seq - TCP_SKB_CB(skb)->seq; @@ -1490,10 +1489,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto found_ok_skb; if (tcp_hdr(skb)->fin) goto found_fin_ok; - WARN(!(flags & MSG_PEEK), KERN_INFO "recvmsg bug 2: " - "copied %X seq %X rcvnxt %X fl %X\n", - *seq, TCP_SKB_CB(skb)->seq, - tp->rcv_nxt, flags); + WARN(!(flags & MSG_PEEK), + "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n", + *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } /* Well, if we have backlog, try to process it now yet. */ diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 4464f3bff6a7..dd1fd8c473fc 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -80,10 +80,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.dst.dev = dev; dev_hold(dev); - xdst->u.rt.idev = in_dev_get(dev); - if (!xdst->u.rt.idev) - return -ENODEV; - xdst->u.rt.peer = rt->peer; if (rt->peer) atomic_inc(&rt->peer->refcnt); @@ -189,8 +185,6 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (likely(xdst->u.rt.idev)) - in_dev_put(xdst->u.rt.idev); if (likely(xdst->u.rt.peer)) inet_putpeer(xdst->u.rt.peer); xfrm_dst_destroy(xdst); @@ -199,27 +193,9 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int unregister) { - struct xfrm_dst *xdst; - if (!unregister) return; - xdst = (struct xfrm_dst *)dst; - if (xdst->u.rt.idev->dev == dev) { - struct in_device *loopback_idev = - in_dev_get(dev_net(dev)->loopback_dev); - BUG_ON(!loopback_idev); - - do { - in_dev_put(xdst->u.rt.idev); - xdst->u.rt.idev = loopback_idev; - in_dev_hold(loopback_idev); - xdst = (struct xfrm_dst *)xdst->u.dst.child; - } while (xdst->u.dst.xfrm); - - __in_dev_put(loopback_idev); - } - xfrm_dst_ifdown(dst, dev); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index de04ea39cde8..10bd39c0ae2d 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -169,7 +169,7 @@ __ip_vs_reroute_locally(struct sk_buff *skb) struct net *net = dev_net(dev); struct iphdr *iph = ip_hdr(skb); - if (rt->fl.iif) { + if (rt_is_input_route(rt)) { unsigned long orefdst = skb->_skb_refdst; if (ip_route_input(skb, iph->daddr, iph->saddr, @@ -552,7 +552,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #endif /* From world but DNAT to loopback address? */ - if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) { + if (local && ipv4_is_loopback(rt->rt_dst) && + rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " "stopping DNAT to loopback address"); goto tx_error_put; @@ -1165,7 +1166,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #endif /* From world but DNAT to loopback address? */ - if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) { + if (local && ipv4_is_loopback(rt->rt_dst) && + rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI4\n", __func__, &cp->daddr.ip); diff --git a/net/socket.c b/net/socket.c index 3ca2fd9e3720..c898df76e924 100644 --- a/net/socket.c +++ b/net/socket.c @@ -156,7 +156,7 @@ static const struct file_operations socket_file_ops = { */ static DEFINE_SPINLOCK(net_family_lock); -static const struct net_proto_family *net_families[NPROTO] __read_mostly; +static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly; /* * Statistics counters of the socket lists @@ -1200,7 +1200,7 @@ int __sock_create(struct net *net, int family, int type, int protocol, * requested real, full-featured networking support upon configuration. * Otherwise module support will break! */ - if (net_families[family] == NULL) + if (rcu_access_pointer(net_families[family]) == NULL) request_module("net-pf-%d", family); #endif @@ -2332,10 +2332,11 @@ int sock_register(const struct net_proto_family *ops) } spin_lock(&net_family_lock); - if (net_families[ops->family]) + if (rcu_dereference_protected(net_families[ops->family], + lockdep_is_held(&net_family_lock))) err = -EEXIST; else { - net_families[ops->family] = ops; + rcu_assign_pointer(net_families[ops->family], ops); err = 0; } spin_unlock(&net_family_lock); @@ -2363,7 +2364,7 @@ void sock_unregister(int family) BUG_ON(family < 0 || family >= NPROTO); spin_lock(&net_family_lock); - net_families[family] = NULL; + rcu_assign_pointer(net_families[family], NULL); spin_unlock(&net_family_lock); synchronize_rcu(); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3c95304a0817..7ff31c60186a 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -316,7 +316,8 @@ static void unix_write_space(struct sock *sk) if (unix_writable(sk)) { wq = rcu_dereference(sk->sk_wq); if (wq_has_sleeper(wq)) - wake_up_interruptible_sync(&wq->wait); + wake_up_interruptible_sync_poll(&wq->wait, + POLLOUT | POLLWRNORM | POLLWRBAND); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); @@ -1710,7 +1711,8 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, goto out_unlock; } - wake_up_interruptible_sync(&u->peer_wait); + wake_up_interruptible_sync_poll(&u->peer_wait, + POLLOUT | POLLWRNORM | POLLWRBAND); if (msg->msg_name) unix_copy_addr(msg, skb->sk); @@ -2072,13 +2074,12 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sk->sk_shutdown & RCV_SHUTDOWN)) + if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; /* Connection-based need to check for termination and startup */ @@ -2090,20 +2091,19 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, return mask; } - /* writable? */ - writable = unix_writable(sk); - if (writable) { - other = unix_peer_get(sk); - if (other) { - if (unix_peer(other) != sk) { - sock_poll_wait(file, &unix_sk(other)->peer_wait, - wait); - if (unix_recvq_full(other)) - writable = 0; - } + /* No write status requested, avoid expensive OUT tests. */ + if (wait && !(wait->key & (POLLWRBAND | POLLWRNORM | POLLOUT))) + return mask; - sock_put(other); + writable = unix_writable(sk); + other = unix_peer_get(sk); + if (other) { + if (unix_peer(other) != sk) { + sock_poll_wait(file, &unix_sk(other)->peer_wait, wait); + if (unix_recvq_full(other)) + writable = 0; } + sock_put(other); } if (writable) |