From 5ff0feac88ced864f44adb145142269196fa79d9 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 6 Jun 2012 10:01:30 +0000 Subject: sky2: fix checksum bit management on some chips The newer flavors of Yukon II use a different method for receive checksum offload. This is indicated in the driver by the SKY2_HW_NEW_LE flag. On these newer chips, the BMU_ENA_RX_CHKSUM should not be set. The driver would get incorrectly toggle the bit, enabling the old checksum logic on these chips and cause a BUG_ON() assertion. If receive checksum was toggled via ethtool. Reported-by: Kirill Smelkov Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/sky2.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index cace36f2ab92..28a54451a3e5 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4381,10 +4381,12 @@ static int sky2_set_features(struct net_device *dev, netdev_features_t features) struct sky2_port *sky2 = netdev_priv(dev); netdev_features_t changed = dev->features ^ features; - if (changed & NETIF_F_RXCSUM) { - bool on = features & NETIF_F_RXCSUM; - sky2_write32(sky2->hw, Q_ADDR(rxqaddr[sky2->port], Q_CSR), - on ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM); + if ((changed & NETIF_F_RXCSUM) && + !(sky2->hw->flags & SKY2_HW_NEW_LE)) { + sky2_write32(sky2->hw, + Q_ADDR(rxqaddr[sky2->port], Q_CSR), + (features & NETIF_F_RXCSUM) + ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM); } if (changed & NETIF_F_RXHASH) -- cgit v1.2.3-59-g8ed1b From 33d5e332b9c5ce0bf3bfd44ca2127d1773b3f2ad Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Thu, 7 Jun 2012 19:25:07 +0000 Subject: stmmac: fix driver built w/ w/o both pci and platf modules The commit ba27ec66ffeb78cbf fixes the Kconfig of the driver when built as module allowing to select/unselect the PCI and Platform modules that are not anymore mutually exclusive. This patch fixes and guarantees that the driver builds on all the platforms w/ w/o PCI and when select/unselect the two stmmac supports. In case of there are some problems on both the configuration and the pci/pltf registration the module_init will fail. v2: set the CONFIG_STMMAC_PLATFORM enabled by default. I've just noticed that this can actually help on some configurations that don't enable any STMMAC options by default (e.g. SPEAr). v3: change printk level when do not register the driver. Reported-by: Fengguang Wu Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/Kconfig | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac.h | 60 ++++++++++++++++++++++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 23 +++++---- 3 files changed, 72 insertions(+), 12 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 0076f770e637..9f448279e12a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -15,6 +15,7 @@ if STMMAC_ETH config STMMAC_PLATFORM bool "STMMAC Platform bus support" depends on STMMAC_ETH + default y ---help--- This selects the platform specific bus support for the stmmac device driver. This is the driver used diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 6d07ba2c8661..94b21b409d88 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -26,6 +26,7 @@ #include #include #include +#include #include "common.h" #ifdef CONFIG_STMMAC_TIMER #include "stmmac_timer.h" @@ -95,8 +96,6 @@ extern int stmmac_mdio_register(struct net_device *ndev); extern void stmmac_set_ethtool_ops(struct net_device *netdev); extern const struct stmmac_desc_ops enh_desc_ops; extern const struct stmmac_desc_ops ndesc_ops; -extern struct pci_driver stmmac_pci_driver; -extern struct platform_driver stmmac_pltfr_driver; int stmmac_freeze(struct net_device *ndev); int stmmac_restore(struct net_device *ndev); int stmmac_resume(struct net_device *ndev); @@ -144,3 +143,60 @@ static inline int stmmac_clk_get(struct stmmac_priv *priv) return 0; } #endif /* CONFIG_HAVE_CLK */ + + +#ifdef CONFIG_STMMAC_PLATFORM +extern struct platform_driver stmmac_pltfr_driver; +static inline int stmmac_register_platform(void) +{ + int err; + + err = platform_driver_register(&stmmac_pltfr_driver); + if (err) + pr_err("stmmac: failed to register the platform driver\n"); + + return err; +} +static inline void stmmac_unregister_platform(void) +{ + platform_driver_register(&stmmac_pltfr_driver); +} +#else +static inline int stmmac_register_platform(void) +{ + pr_debug("stmmac: do not register the platf driver\n"); + + return -EINVAL; +} +static inline void stmmac_unregister_platform(void) +{ +} +#endif /* CONFIG_STMMAC_PLATFORM */ + +#ifdef CONFIG_STMMAC_PCI +extern struct pci_driver stmmac_pci_driver; +static inline int stmmac_register_pci(void) +{ + int err; + + err = pci_register_driver(&stmmac_pci_driver); + if (err) + pr_err("stmmac: failed to register the PCI driver\n"); + + return err; +} +static inline void stmmac_unregister_pci(void) +{ + pci_unregister_driver(&stmmac_pci_driver); +} +#else +static inline int stmmac_register_pci(void) +{ + pr_debug("stmmac: do not register the PCI driver\n"); + + return -EINVAL; +} +static inline void stmmac_unregister_pci(void) +{ +} +#endif /* CONFIG_STMMAC_PCI */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 363856951412..51b3b68528ee 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -42,7 +42,6 @@ #include #include #include -#include #ifdef CONFIG_STMMAC_DEBUG_FS #include #include @@ -2094,25 +2093,29 @@ int stmmac_restore(struct net_device *ndev) } #endif /* CONFIG_PM */ +/* Driver can be configured w/ and w/ both PCI and Platf drivers + * depending on the configuration selected. + */ static int __init stmmac_init(void) { - int err = 0; + int err_plt = 0; + int err_pci = 0; - err = platform_driver_register(&stmmac_pltfr_driver); + err_plt = stmmac_register_platform(); + err_pci = stmmac_register_pci(); - if (!err) { - err = pci_register_driver(&stmmac_pci_driver); - if (err) - platform_driver_unregister(&stmmac_pltfr_driver); + if ((err_pci) && (err_plt)) { + pr_err("stmmac: driver registration failed\n"); + return -EINVAL; } - return err; + return 0; } static void __exit stmmac_exit(void) { - pci_unregister_driver(&stmmac_pci_driver); - platform_driver_unregister(&stmmac_pltfr_driver); + stmmac_unregister_platform(); + stmmac_unregister_pci(); } module_init(stmmac_init); -- cgit v1.2.3-59-g8ed1b From 6a2b28ef036ab5c66fdc606fe97d9e5cb34ea409 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 8 Jun 2012 00:28:16 -0700 Subject: Revert "niu: Add support for byte queue limits." This reverts commit efa230f2c68abab817f13473077f8d0cc74f43f3. BQL doesn't work with how this driver currently only takes TX interrupts every 1/4 of the TX ring. That behavior needs to be fixed, but that's a larger non-trivial task and for now we have to revert BQL support as this makes the device currently completely unusable. Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/niu.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 703c8cce2a2c..8c726b7004d3 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -3598,7 +3598,6 @@ static int release_tx_packet(struct niu *np, struct tx_ring_info *rp, int idx) static void niu_tx_work(struct niu *np, struct tx_ring_info *rp) { struct netdev_queue *txq; - unsigned int tx_bytes; u16 pkt_cnt, tmp; int cons, index; u64 cs; @@ -3621,18 +3620,12 @@ static void niu_tx_work(struct niu *np, struct tx_ring_info *rp) netif_printk(np, tx_done, KERN_DEBUG, np->dev, "%s() pkt_cnt[%u] cons[%d]\n", __func__, pkt_cnt, cons); - tx_bytes = 0; - tmp = pkt_cnt; - while (tmp--) { - tx_bytes += rp->tx_buffs[cons].skb->len; + while (pkt_cnt--) cons = release_tx_packet(np, rp, cons); - } rp->cons = cons; smp_mb(); - netdev_tx_completed_queue(txq, pkt_cnt, tx_bytes); - out: if (unlikely(netif_tx_queue_stopped(txq) && (niu_tx_avail(rp) > NIU_TX_WAKEUP_THRESH(rp)))) { @@ -4333,7 +4326,6 @@ static void niu_free_channels(struct niu *np) struct tx_ring_info *rp = &np->tx_rings[i]; niu_free_tx_ring_info(np, rp); - netdev_tx_reset_queue(netdev_get_tx_queue(np->dev, i)); } kfree(np->tx_rings); np->tx_rings = NULL; @@ -6739,8 +6731,6 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, prod = NEXT_TX(rp, prod); } - netdev_tx_sent_queue(txq, skb->len); - if (prod < rp->prod) rp->wrap_bit ^= TX_RING_KICK_WRAP; rp->prod = prod; -- cgit v1.2.3-59-g8ed1b From aac495a8002bbf20e879572c6cf0789ab2ffb32b Mon Sep 17 00:00:00 2001 From: Stanislav Yakovlev Date: Mon, 14 May 2012 19:06:19 -0400 Subject: net/wireless: ipw2100: Fix WARN_ON occurring in wiphy_register called by ipw2100_pci_init_one The problem was found by Larry Finger: http://marc.info/?l=linux-wireless&m=133702401700614&w=2 The problem is identical to the one for ipw2200 which is already fixed: http://marc.info/?l=linux-wireless&m=133457257407196&w=2 [ 17.766431] ------------[ cut here ]------------ [ 17.766467] WARNING: at net/wireless/core.c:562 wiphy_register+0x34c/0x3c0 [cfg80211]() [ 17.766471] Hardware name: Latitude D600 [ 17.766474] Modules linked in: ipw2100(+) libipw pcmcia cfg80211 ppdev parport_pc yenta_socket sr_mod pcmcia_rsrc parport iTCO_wdt cdrom sg rfkill pcmcia_ core lib80211 tg3 video button battery ac iTCO_vendor_support joydev shpchp pcspkr pciehp pci_hotplug autofs4 radeon ttm drm_kms_helper uhci_hcd ehci_hcd rtc _cmos thermal drm hwmon i2c_algo_bit i2c_core processor usbcore usb_common ata_generic ata_piix ahci libahci libata [ 17.766525] Pid: 474, comm: modprobe Not tainted 3.4.0-rc7-wl+ #6 [ 17.766528] Call Trace: [ 17.766541] [] ? printk+0x28/0x2a [ 17.766552] [] warn_slowpath_common+0x6d/0xa0 [ 17.766563] [] ? wiphy_register+0x34c/0x3c0 [cfg80211] [ 17.766573] [] ? wiphy_register+0x34c/0x3c0 [cfg80211] [ 17.766578] [] warn_slowpath_null+0x1d/0x20 [ 17.766588] [] wiphy_register+0x34c/0x3c0 [cfg80211] [ 17.766605] [] ipw2100_wdev_init+0x196/0x1c0 [ipw2100] [ 17.766616] [] ipw2100_pci_init_one+0x2b2/0x694 [ipw2100] [ 17.766632] [] local_pci_probe+0x42/0xb0 [ 17.766637] [] pci_device_probe+0x60/0x90 [ 17.766645] [] ? sysfs_create_link+0x12/0x20 [ 17.766654] [] really_probe+0x56/0x2e0 [ 17.766659] [] ? create_dir+0x5d/0xa0 [ 17.766667] [] ? pm_runtime_barrier+0x3b/0xa0 [ 17.766672] [] driver_probe_device+0x44/0xa0 [ 17.766677] [] ? pci_match_device+0x97/0xa0 [ 17.766681] [] __driver_attach+0x89/0x90 [ 17.766686] [] ? driver_probe_device+0xa0/0xa0 [ 17.766691] [] bus_for_each_dev+0x3a/0x70 [ 17.766695] [] driver_attach+0x1c/0x30 [ 17.766699] [] ? driver_probe_device+0xa0/0xa0 [ 17.766704] [] bus_add_driver+0x187/0x280 [ 17.766710] [] ? kset_find_obj+0x2d/0x60 [ 17.766715] [] ? pci_device_probe+0x90/0x90 [ 17.766719] [] ? pci_device_probe+0x90/0x90 [ 17.766724] [] driver_register+0x65/0x110 [ 17.766729] [] __pci_register_driver+0x3d/0xa0 [ 17.766738] [] ipw2100_init+0x5c/0x1000 [ipw2100] [ 17.766743] [] do_one_initcall+0x2f/0x170 [ 17.766749] [] ? 0xe09f6fff [ 17.766757] [] sys_init_module+0xa8/0x210 [ 17.766766] [] syscall_call+0x7/0xb [ 17.766769] ---[ end trace 559898c6bb0d1c75 ]--- [ 17.767093] ipw2100: probe of 0000:02:03.0 failed with error -5 This warning appears only if we apply Ben Hutchings' fix http://marc.info/?l=linux-wireless&m=132720204412667&w=2 for the bug reported by Cesare Leonardi http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=656813 with cfg80211 warning during device registration ("cfg80211: failed to add phy80211 symlink to netdev!"). We separate device bring up and registration with network stack to avoid the problem. Signed-off-by: Stanislav Yakovlev Tested-by: Larry Finger Signed-off-by: John W. Linville --- drivers/net/wireless/ipw2x00/ipw2100.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c index 9cfae0c08707..95aa8e1683ec 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/ipw2x00/ipw2100.c @@ -1903,14 +1903,6 @@ static void ipw2100_down(struct ipw2100_priv *priv) netif_stop_queue(priv->net_dev); } -/* Called by register_netdev() */ -static int ipw2100_net_init(struct net_device *dev) -{ - struct ipw2100_priv *priv = libipw_priv(dev); - - return ipw2100_up(priv, 1); -} - static int ipw2100_wdev_init(struct net_device *dev) { struct ipw2100_priv *priv = libipw_priv(dev); @@ -6087,7 +6079,6 @@ static const struct net_device_ops ipw2100_netdev_ops = { .ndo_stop = ipw2100_close, .ndo_start_xmit = libipw_xmit, .ndo_change_mtu = libipw_change_mtu, - .ndo_init = ipw2100_net_init, .ndo_tx_timeout = ipw2100_tx_timeout, .ndo_set_mac_address = ipw2100_set_address, .ndo_validate_addr = eth_validate_addr, @@ -6329,6 +6320,10 @@ static int ipw2100_pci_init_one(struct pci_dev *pci_dev, printk(KERN_INFO DRV_NAME ": Detected Intel PRO/Wireless 2100 Network Connection\n"); + err = ipw2100_up(priv, 1); + if (err) + goto fail; + err = ipw2100_wdev_init(dev); if (err) goto fail; @@ -6338,12 +6333,7 @@ static int ipw2100_pci_init_one(struct pci_dev *pci_dev, * network device we would call ipw2100_up. This introduced a race * condition with newer hotplug configurations (network was coming * up and making calls before the device was initialized). - * - * If we called ipw2100_up before we registered the device, then the - * device name wasn't registered. So, we instead use the net_dev->init - * member to call a function that then just turns and calls ipw2100_up. - * net_dev->init is called after name allocation but before the - * notifier chain is called */ + */ err = register_netdev(dev); if (err) { printk(KERN_WARNING DRV_NAME -- cgit v1.2.3-59-g8ed1b From 0fde0a8cfd0ede7f310d6a681c8e5a7cb3e32406 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Wed, 16 May 2012 11:06:21 +0200 Subject: rtl8187: ->brightness_set can not sleep Fix: BUG: sleeping function called from invalid context at kernel/workqueue.c:2547 in_atomic(): 1, irqs_disabled(): 0, pid: 629, name: wpa_supplicant 2 locks held by wpa_supplicant/629: #0: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0x14/0x20 #1: (&trigger->leddev_list_lock){.+.?..}, at: [] led_trigger_event+0x21/0x80 Pid: 629, comm: wpa_supplicant Not tainted 3.3.0-0.rc3.git5.1.fc17.i686 Call Trace: [] __might_sleep+0x126/0x1d0 [] wait_on_work+0x2c/0x1d0 [] __cancel_work_timer+0x6a/0x120 [] cancel_delayed_work_sync+0x10/0x20 [] rtl8187_led_brightness_set+0x82/0xf0 [rtl8187] [] led_trigger_event+0x5c/0x80 [] ieee80211_led_radio+0x1d/0x40 [mac80211] [] ieee80211_stop_device+0x13/0x230 [mac80211] Removing _sync is ok, because if led_on work is currently running it will be finished before led_off work start to perform, since they are always queued on the same mac80211 local->workqueue. Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=795176 Signed-off-by: Stanislaw Gruszka Acked-by: Larry Finger Acked-by: Hin-Tak Leung Signed-off-by: John W. Linville --- drivers/net/wireless/rtl818x/rtl8187/leds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/wireless/rtl818x/rtl8187/leds.c b/drivers/net/wireless/rtl818x/rtl8187/leds.c index 2e0de2f5f0f9..c2d5b495c179 100644 --- a/drivers/net/wireless/rtl818x/rtl8187/leds.c +++ b/drivers/net/wireless/rtl818x/rtl8187/leds.c @@ -117,7 +117,7 @@ static void rtl8187_led_brightness_set(struct led_classdev *led_dev, radio_on = true; } else if (radio_on) { radio_on = false; - cancel_delayed_work_sync(&priv->led_on); + cancel_delayed_work(&priv->led_on); ieee80211_queue_delayed_work(hw, &priv->led_off, 0); } } else if (radio_on) { -- cgit v1.2.3-59-g8ed1b From 06cf5c4c5bea549235da1aace86b90d4ad0084f8 Mon Sep 17 00:00:00 2001 From: Qasim Javed Date: Tue, 5 Jun 2012 01:25:44 -0500 Subject: mac80211_hwsim: Set IEEE80211_STAT_ACK flag when userspace indicates that the frame has been acknowledged. The station fail average is not updated correctly since the IEEE80211_STAT_ACK flag is not set when using wmediumd with mac80211_hwsim. Set this flag when wmediumd indicates that the frame was successfully transmitted (eventually). Signed-off-by: Qasim Javed Signed-off-by: Javier Cardona Signed-off-by: John W. Linville --- drivers/net/wireless/mac80211_hwsim.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net') diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 4c9336cee817..a0b7cfd34685 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1555,6 +1555,7 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2, hdr = (struct ieee80211_hdr *) skb->data; mac80211_hwsim_monitor_ack(data2->hw, hdr->addr2); } + txi->flags |= IEEE80211_TX_STAT_ACK; } ieee80211_tx_status_irqsafe(data2->hw, skb); return 0; -- cgit v1.2.3-59-g8ed1b From d2c8b15d0cb486f4938ba7f2af349d9d1220cb10 Mon Sep 17 00:00:00 2001 From: Meenakshi Venkataraman Date: Tue, 5 Jun 2012 20:24:37 +0200 Subject: iwlwifi: use correct supported firmware for 6035 and 6000g2 My patch iwlwifi: use correct released ucode version did not correctly report supported firmware for the 6035 device. This patch fixes it. The minimum supported firmware version for 6035 is v6. Also correct the minimum supported firmware version for the 6000g2 series of devices. Cc: stable@kernel.org Signed-off-by: Meenakshi Venkataraman Reviewed-by: Emmanuel Grumbach Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/iwlwifi/iwl-6000.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c index 19f7ee84ae89..e5e8ada4aaf6 100644 --- a/drivers/net/wireless/iwlwifi/iwl-6000.c +++ b/drivers/net/wireless/iwlwifi/iwl-6000.c @@ -35,17 +35,20 @@ #define IWL6000_UCODE_API_MAX 6 #define IWL6050_UCODE_API_MAX 5 #define IWL6000G2_UCODE_API_MAX 6 +#define IWL6035_UCODE_API_MAX 6 /* Oldest version we won't warn about */ #define IWL6000_UCODE_API_OK 4 #define IWL6000G2_UCODE_API_OK 5 #define IWL6050_UCODE_API_OK 5 #define IWL6000G2B_UCODE_API_OK 6 +#define IWL6035_UCODE_API_OK 6 /* Lowest firmware API version supported */ #define IWL6000_UCODE_API_MIN 4 #define IWL6050_UCODE_API_MIN 4 -#define IWL6000G2_UCODE_API_MIN 4 +#define IWL6000G2_UCODE_API_MIN 5 +#define IWL6035_UCODE_API_MIN 6 /* EEPROM versions */ #define EEPROM_6000_TX_POWER_VERSION (4) @@ -227,9 +230,25 @@ const struct iwl_cfg iwl6030_2bg_cfg = { IWL_DEVICE_6030, }; +#define IWL_DEVICE_6035 \ + .fw_name_pre = IWL6030_FW_PRE, \ + .ucode_api_max = IWL6035_UCODE_API_MAX, \ + .ucode_api_ok = IWL6035_UCODE_API_OK, \ + .ucode_api_min = IWL6035_UCODE_API_MIN, \ + .device_family = IWL_DEVICE_FAMILY_6030, \ + .max_inst_size = IWL60_RTC_INST_SIZE, \ + .max_data_size = IWL60_RTC_DATA_SIZE, \ + .eeprom_ver = EEPROM_6030_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_6030_TX_POWER_VERSION, \ + .base_params = &iwl6000_g2_base_params, \ + .bt_params = &iwl6000_bt_params, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true + const struct iwl_cfg iwl6035_2agn_cfg = { .name = "Intel(R) Centrino(R) Advanced-N 6235 AGN", - IWL_DEVICE_6030, + IWL_DEVICE_6035, .ht_params = &iwl6000_ht_params, }; -- cgit v1.2.3-59-g8ed1b From e64add27e1b4874f589e550b4e0ca6715070373f Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 5 Jun 2012 20:39:32 +0200 Subject: b43: do not call ieee80211_unregister_hw if we are not registred this patch fixes kernel Oops on "rmmod b43" if firmware was not loaded: BUG: unable to handle kernel NULL pointer dereference at 0000000000000088 IP: [] drain_workqueue+0x25/0x142 PGD 153ac6067 PUD 153b82067 PMD 0 Oops: 0000 [#1] SMP Signed-off-by: Oleksij Rempel Signed-off-by: John W. Linville --- drivers/net/wireless/b43/b43.h | 4 ++++ drivers/net/wireless/b43/main.c | 19 ++++++++++++------- 2 files changed, 16 insertions(+), 7 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/wireless/b43/b43.h b/drivers/net/wireless/b43/b43.h index 67c13af6f206..c06b6cb5c91e 100644 --- a/drivers/net/wireless/b43/b43.h +++ b/drivers/net/wireless/b43/b43.h @@ -877,6 +877,10 @@ struct b43_wl { * from the mac80211 subsystem. */ u16 mac80211_initially_registered_queues; + /* Set this if we call ieee80211_register_hw() and check if we call + * ieee80211_unregister_hw(). */ + bool hw_registred; + /* We can only have one operating interface (802.11 core) * at a time. General information about this interface follows. */ diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c index 5a39b226b2e3..acd03a4f9730 100644 --- a/drivers/net/wireless/b43/main.c +++ b/drivers/net/wireless/b43/main.c @@ -2437,6 +2437,7 @@ start_ieee80211: err = ieee80211_register_hw(wl->hw); if (err) goto err_one_core_detach; + wl->hw_registred = true; b43_leds_register(wl->current_dev); goto out; @@ -5299,6 +5300,7 @@ static struct b43_wl *b43_wireless_init(struct b43_bus_dev *dev) hw->queues = modparam_qos ? B43_QOS_QUEUE_NUM : 1; wl->mac80211_initially_registered_queues = hw->queues; + wl->hw_registred = false; hw->max_rates = 2; SET_IEEE80211_DEV(hw, dev->dev); if (is_valid_ether_addr(sprom->et1mac)) @@ -5370,12 +5372,15 @@ static void b43_bcma_remove(struct bcma_device *core) * as the ieee80211 unreg will destroy the workqueue. */ cancel_work_sync(&wldev->restart_work); - /* Restore the queues count before unregistering, because firmware detect - * might have modified it. Restoring is important, so the networking - * stack can properly free resources. */ - wl->hw->queues = wl->mac80211_initially_registered_queues; - b43_leds_stop(wldev); - ieee80211_unregister_hw(wl->hw); + B43_WARN_ON(!wl); + if (wl->current_dev == wldev && wl->hw_registred) { + /* Restore the queues count before unregistering, because firmware detect + * might have modified it. Restoring is important, so the networking + * stack can properly free resources. */ + wl->hw->queues = wl->mac80211_initially_registered_queues; + b43_leds_stop(wldev); + ieee80211_unregister_hw(wl->hw); + } b43_one_core_detach(wldev->dev); @@ -5446,7 +5451,7 @@ static void b43_ssb_remove(struct ssb_device *sdev) cancel_work_sync(&wldev->restart_work); B43_WARN_ON(!wl); - if (wl->current_dev == wldev) { + if (wl->current_dev == wldev && wl->hw_registred) { /* Restore the queues count before unregistering, because firmware detect * might have modified it. Restoring is important, so the networking * stack can properly free resources. */ -- cgit v1.2.3-59-g8ed1b From d6ee27eb13beab94056e0de52d81220058ca2297 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Wed, 6 Jun 2012 09:13:36 +0200 Subject: iwlwifi: don't mess up the SCD when removing a key When we remove a key, we put a key index which was supposed to tell the fw that we are actually removing the key. But instead the fw took that index as a valid index and messed up the SRAM of the device. This memory corruption on the device mangled the data of the SCD. The impact on the user is that SCD queue 2 got stuck after having removed keys. The message is the log that was printed is: Queue 2 stuck for 10000ms This doesn't seem to fix the higher queues that get stuck from time to time. Cc: stable@vger.kernel.org [2.6.27+] Reviewed-by: Meenakshi Venkataraman Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/iwlwifi/iwl-agn-sta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-sta.c b/drivers/net/wireless/iwlwifi/iwl-agn-sta.c index aea07aab3c9e..eb6a8eaf42fc 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-sta.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-sta.c @@ -1267,7 +1267,7 @@ int iwl_remove_dynamic_key(struct iwl_priv *priv, key_flags |= STA_KEY_MULTICAST_MSK; sta_cmd.key.key_flags = key_flags; - sta_cmd.key.key_offset = WEP_INVALID_OFFSET; + sta_cmd.key.key_offset = keyconf->hw_key_idx; sta_cmd.sta.modify_mask = STA_MODIFY_KEY_MASK; sta_cmd.mode = STA_CONTROL_MODIFY_MSK; -- cgit v1.2.3-59-g8ed1b From d012d04e4d6312ea157b6cf19e9689af934f5aa7 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Wed, 6 Jun 2012 13:55:02 +0200 Subject: iwlwifi: disable the buggy chain extension feature in HW This feature has been reported to be buggy and enabled by default. We therefore need to disable it manually. Cc: stable@vger.kernel.org Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/iwlwifi/iwl-prph.h | 1 + drivers/net/wireless/iwlwifi/iwl-trans-pcie.c | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/wireless/iwlwifi/iwl-prph.h b/drivers/net/wireless/iwlwifi/iwl-prph.h index 3b1069290fa9..dfd54662e3e6 100644 --- a/drivers/net/wireless/iwlwifi/iwl-prph.h +++ b/drivers/net/wireless/iwlwifi/iwl-prph.h @@ -224,6 +224,7 @@ #define SCD_TXFACT (SCD_BASE + 0x10) #define SCD_ACTIVE (SCD_BASE + 0x14) #define SCD_QUEUECHAIN_SEL (SCD_BASE + 0xe8) +#define SCD_CHAINEXT_EN (SCD_BASE + 0x244) #define SCD_AGGR_SEL (SCD_BASE + 0x248) #define SCD_INTERRUPT_MASK (SCD_BASE + 0x108) diff --git a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c index ec6fb395b84d..79c6b91417f9 100644 --- a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c +++ b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c @@ -1058,6 +1058,11 @@ static void iwl_tx_start(struct iwl_trans *trans) iwl_write_prph(trans, SCD_DRAM_BASE_ADDR, trans_pcie->scd_bc_tbls.dma >> 10); + /* The chain extension of the SCD doesn't work well. This feature is + * enabled by default by the HW, so we need to disable it manually. + */ + iwl_write_prph(trans, SCD_CHAINEXT_EN, 0); + /* Enable DMA channel */ for (chan = 0; chan < FH_TCSR_CHNL_NUM ; chan++) iwl_write_direct32(trans, FH_TCSR_CHNL_TX_CONFIG_REG(chan), -- cgit v1.2.3-59-g8ed1b From cd8f76c0a0c6fce0b2cf23c9bd0123f91453f46d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Jun 2012 22:59:59 +0000 Subject: be2net: fix a race in be_xmit() As soon as hardware is notified of a transmit, we no longer can assume skb can be dereferenced, as TX completion might have freed the packet. Signed-off-by: Eric Dumazet Cc: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 08efd308d78a..fdb50cec6b51 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -736,6 +736,8 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, copied = make_tx_wrbs(adapter, txq, skb, wrb_cnt, dummy_wrb); if (copied) { + int gso_segs = skb_shinfo(skb)->gso_segs; + /* record the sent skb in the sent_skb table */ BUG_ON(txo->sent_skb_list[start]); txo->sent_skb_list[start] = skb; @@ -753,8 +755,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, be_txq_notify(adapter, txq->id, wrb_cnt); - be_tx_stats_update(txo, wrb_cnt, copied, - skb_shinfo(skb)->gso_segs, stopped); + be_tx_stats_update(txo, wrb_cnt, copied, gso_segs, stopped); } else { txq->head = start; dev_kfree_skb_any(skb); -- cgit v1.2.3-59-g8ed1b From f41ef2e7dc4515777810016612316c38f84275e7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 8 Jun 2012 14:07:19 +0000 Subject: netdev: fix drivers/net/phy/ kernel-doc warnings Fix kernel-doc warnings in drivers/net/phy: Warning(drivers/net/phy/mdio_bus.c:109): No description found for parameter 'mdio_bus_np' Warning(drivers/net/phy/mdio_bus.c:109): Excess function parameter 'mdio_np' description in 'of_mdio_find_bus' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- drivers/net/phy/mdio_bus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 683ef1ce5519..5061608f408c 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -96,7 +96,7 @@ static int of_mdio_bus_match(struct device *dev, void *mdio_bus_np) } /** * of_mdio_find_bus - Given an mii_bus node, find the mii_bus. - * @mdio_np: Pointer to the mii_bus. + * @mdio_bus_np: Pointer to the mii_bus. * * Returns a pointer to the mii_bus, or NULL if none found. * -- cgit v1.2.3-59-g8ed1b From 7dbb491878a2c51d372a8890fa45a8ff80358af1 Mon Sep 17 00:00:00 2001 From: françois romieu Date: Sat, 9 Jun 2012 10:53:16 +0000 Subject: r8169: avoid NAPI scheduling delay. While reworking the r8169 driver a few months ago to perform the smallest amount of work in the irq handler, I took care of avoiding any irq mask register operation in the slow work dedicated user context thread. The slow work thread scheduled an extra round of NAPI work which would ultimately set the irq mask register as required, thus keeping such irq mask operations in the NAPI handler. It would eventually race with the irq handler and delay NAPI execution for - assuming no further irq - a whole ksoftirqd period. Mildly a problem for rare link changes or corner case PCI events. The race was always lost after the last bh disabling lock had been removed from the work thread and people started wondering where those pesky "NOHZ: local_softirq_pending 08" messages came from. Actually the irq mask register _can_ be set up directly in the slow work thread. Signed-off-by: Francois Romieu Reported-by: Dave Jones Tested-by: Marc Dionne Cc: Thomas Gleixner Cc: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 9757ce3543a0..7260aa79466a 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -5889,11 +5889,7 @@ static void rtl_slow_event_work(struct rtl8169_private *tp) if (status & LinkChg) __rtl8169_check_link_status(dev, tp, tp->mmio_addr, true); - napi_disable(&tp->napi); - rtl_irq_disable(tp); - - napi_enable(&tp->napi); - napi_schedule(&tp->napi); + rtl_irq_enable_all(tp); } static void rtl_task(struct work_struct *work) -- cgit v1.2.3-59-g8ed1b From 83a27052c3376793bc879e00e6e6805d6fb7aab9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Jun 2012 22:35:24 +0000 Subject: virtio-net: fix a race on 32bit arches commit 3fa2a1df909 (virtio-net: per cpu 64 bit stats (v2)) added a race on 32bit arches. We must use separate syncp for rx and tx path as they can be run at the same time on different cpus. Thus one sequence increment can be lost and readers spin forever. Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Cc: Michael S. Tsirkin Cc: Jason Wang Acked-by: Rusty Russell Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 5214b1eceb95..f18149ae2588 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -42,7 +42,8 @@ module_param(gso, bool, 0444); #define VIRTNET_DRIVER_VERSION "1.0.0" struct virtnet_stats { - struct u64_stats_sync syncp; + struct u64_stats_sync tx_syncp; + struct u64_stats_sync rx_syncp; u64 tx_bytes; u64 tx_packets; @@ -300,10 +301,10 @@ static void receive_buf(struct net_device *dev, void *buf, unsigned int len) hdr = skb_vnet_hdr(skb); - u64_stats_update_begin(&stats->syncp); + u64_stats_update_begin(&stats->rx_syncp); stats->rx_bytes += skb->len; stats->rx_packets++; - u64_stats_update_end(&stats->syncp); + u64_stats_update_end(&stats->rx_syncp); if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { pr_debug("Needs csum!\n"); @@ -565,10 +566,10 @@ static unsigned int free_old_xmit_skbs(struct virtnet_info *vi) while ((skb = virtqueue_get_buf(vi->svq, &len)) != NULL) { pr_debug("Sent skb %p\n", skb); - u64_stats_update_begin(&stats->syncp); + u64_stats_update_begin(&stats->tx_syncp); stats->tx_bytes += skb->len; stats->tx_packets++; - u64_stats_update_end(&stats->syncp); + u64_stats_update_end(&stats->tx_syncp); tot_sgs += skb_vnet_hdr(skb)->num_sg; dev_kfree_skb_any(skb); @@ -703,12 +704,16 @@ static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev, u64 tpackets, tbytes, rpackets, rbytes; do { - start = u64_stats_fetch_begin(&stats->syncp); + start = u64_stats_fetch_begin(&stats->tx_syncp); tpackets = stats->tx_packets; tbytes = stats->tx_bytes; + } while (u64_stats_fetch_retry(&stats->tx_syncp, start)); + + do { + start = u64_stats_fetch_begin(&stats->rx_syncp); rpackets = stats->rx_packets; rbytes = stats->rx_bytes; - } while (u64_stats_fetch_retry(&stats->syncp, start)); + } while (u64_stats_fetch_retry(&stats->rx_syncp, start)); tot->rx_packets += rpackets; tot->tx_packets += tpackets; -- cgit v1.2.3-59-g8ed1b From 16b0dc29c1af9df341428f4c49ada4f626258082 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 10 Jun 2012 21:11:57 +0000 Subject: dummy: fix rcu_sched self-detected stalls Trying to "modprobe dummy numdummies=30000" triggers : INFO: rcu_sched self-detected stall on CPU { 8} (t=60000 jiffies) After this splat, RTNL is locked and reboot is needed. We must call cond_resched() to avoid this, even holding RTNL. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/dummy.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 442d91a2747b..bab0158f1cc3 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -187,8 +187,10 @@ static int __init dummy_init_module(void) rtnl_lock(); err = __rtnl_link_register(&dummy_link_ops); - for (i = 0; i < numdummies && !err; i++) + for (i = 0; i < numdummies && !err; i++) { err = dummy_init_one(); + cond_resched(); + } if (err < 0) __rtnl_link_unregister(&dummy_link_ops); rtnl_unlock(); -- cgit v1.2.3-59-g8ed1b From e30478598a8476d02e3b00caa89ce1a3b1dad54b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 10 Jun 2012 23:24:00 +0000 Subject: lpc_eth: add missing ndo_change_mtu() lpc_eth does a copy of transmitted skbs to DMA area, without checking skb lengths, so can trigger buffer overflows : memcpy(pldat->tx_buff_v + txidx * ENET_MAXF_SIZE, skb->data, len); One way to get bigger skbs is to allow MTU changes above the 1500 limit. Calling eth_change_mtu() in ndo_change_mtu() makes sure this cannot happen. Signed-off-by: Eric Dumazet Cc: Roland Stigge Cc: Kevin Wells Acked-by: Roland Stigge Signed-off-by: David S. Miller --- drivers/net/ethernet/nxp/lpc_eth.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 8d2666fcffd7..10febdc2bd1a 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1320,6 +1320,7 @@ static const struct net_device_ops lpc_netdev_ops = { .ndo_set_rx_mode = lpc_eth_set_multicast_list, .ndo_do_ioctl = lpc_eth_ioctl, .ndo_set_mac_address = lpc_set_mac_address, + .ndo_change_mtu = eth_change_mtu, }; static int lpc_eth_drv_probe(struct platform_device *pdev) -- cgit v1.2.3-59-g8ed1b From 3f16da51b0e533871d22a29682f3c3969d4f7e22 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 Jun 2012 07:21:36 +0000 Subject: lpc_eth: fix tx completion __lpc_handle_xmit() has two bugs : 1) It can leak skbs in case TXSTATUS_ERROR is set 2) It can wake up txqueue while no slot was freed. Signed-off-by: Eric Dumazet Reported-by: Roland Stigge Tested-by: Roland Stigge Cc: Kevin Wells Signed-off-by: David S. Miller --- drivers/net/ethernet/nxp/lpc_eth.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 10febdc2bd1a..083d6715335c 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -946,16 +946,16 @@ static void __lpc_handle_xmit(struct net_device *ndev) /* Update stats */ ndev->stats.tx_packets++; ndev->stats.tx_bytes += skb->len; - - /* Free buffer */ - dev_kfree_skb_irq(skb); } + dev_kfree_skb_irq(skb); txcidx = readl(LPC_ENET_TXCONSUMEINDEX(pldat->net_base)); } - if (netif_queue_stopped(ndev)) - netif_wake_queue(ndev); + if (pldat->num_used_tx_buffs <= ENET_TX_DESC/2) { + if (netif_queue_stopped(ndev)) + netif_wake_queue(ndev); + } } static int __lpc_handle_recv(struct net_device *ndev, int budget) -- cgit v1.2.3-59-g8ed1b From 883ffd6e64114495f68652721065149a2bbd9de6 Mon Sep 17 00:00:00 2001 From: Stefan Roese Date: Thu, 7 Jun 2012 23:21:05 +0000 Subject: net: stmmac: Fix clock en-/disable calls clk_{un}prepare is mandatory for platforms using common clock framework. Since these drivers are used by SPEAr platform, which supports common clock framework, add clk_{un}prepare() support for them. Otherwise the clocks are not correctly en-/disabled and ethernet support doesn't work. Signed-off-by: Stefan Roese Cc: Viresh Kumar Cc: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 94b21b409d88..dc20c56efc9d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -109,7 +109,7 @@ struct stmmac_priv *stmmac_dvr_probe(struct device *device, static inline int stmmac_clk_enable(struct stmmac_priv *priv) { if (!IS_ERR(priv->stmmac_clk)) - return clk_enable(priv->stmmac_clk); + return clk_prepare_enable(priv->stmmac_clk); return 0; } @@ -119,7 +119,7 @@ static inline void stmmac_clk_disable(struct stmmac_priv *priv) if (IS_ERR(priv->stmmac_clk)) return; - clk_disable(priv->stmmac_clk); + clk_disable_unprepare(priv->stmmac_clk); } static inline int stmmac_clk_get(struct stmmac_priv *priv) { -- cgit v1.2.3-59-g8ed1b From b7abee6ef888117f92db370620ebf116a38e3f4d Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Thu, 7 Jun 2012 12:56:54 +0000 Subject: tg3: Apply short DMA frag workaround to 5906 5906 devices also need the short DMA fragment workaround. This patch makes the necessary change. Signed-off-by: Matt Carlson Tested-by: Christian Kujau Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index edeeb516807a..e47ff8be1d7b 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -14275,7 +14275,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) } } - if (tg3_flag(tp, 5755_PLUS)) + if (tg3_flag(tp, 5755_PLUS) || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) tg3_flag_set(tp, SHORT_DMA_BUG); if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) -- cgit v1.2.3-59-g8ed1b From e3d62d7e8e05a6a4b08f4672385ae58fc0f132c4 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Thu, 7 Jun 2012 10:45:02 +0000 Subject: tilegx network driver: initial support This change adds support for the tilegx network driver based on the GXIO IORPC support in the tilegx software stack, using the on-chip mPIPE packet processing engine. Signed-off-by: Chris Metcalf Signed-off-by: David S. Miller --- drivers/net/ethernet/tile/Kconfig | 2 + drivers/net/ethernet/tile/Makefile | 4 +- drivers/net/ethernet/tile/tilegx.c | 1898 ++++++++++++++++++++++++++++++++++++ 3 files changed, 1902 insertions(+), 2 deletions(-) create mode 100644 drivers/net/ethernet/tile/tilegx.c (limited to 'drivers/net') diff --git a/drivers/net/ethernet/tile/Kconfig b/drivers/net/ethernet/tile/Kconfig index 2d9218f86bca..098b1c42b393 100644 --- a/drivers/net/ethernet/tile/Kconfig +++ b/drivers/net/ethernet/tile/Kconfig @@ -7,6 +7,8 @@ config TILE_NET depends on TILE default y select CRC32 + select TILE_GXIO_MPIPE if TILEGX + select HIGH_RES_TIMERS if TILEGX ---help--- This is a standard Linux network device driver for the on-chip Tilera Gigabit Ethernet and XAUI interfaces. diff --git a/drivers/net/ethernet/tile/Makefile b/drivers/net/ethernet/tile/Makefile index f634f142cab4..0ef9eefd3211 100644 --- a/drivers/net/ethernet/tile/Makefile +++ b/drivers/net/ethernet/tile/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_TILE_NET) += tile_net.o ifdef CONFIG_TILEGX -tile_net-objs := tilegx.o mpipe.o iorpc_mpipe.o dma_queue.o +tile_net-y := tilegx.o else -tile_net-objs := tilepro.o +tile_net-y := tilepro.o endif diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c new file mode 100644 index 000000000000..83b4b388ad49 --- /dev/null +++ b/drivers/net/ethernet/tile/tilegx.c @@ -0,0 +1,1898 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +#include +#include +#include +#include +#include /* printk() */ +#include /* kmalloc() */ +#include /* error codes */ +#include /* size_t */ +#include +#include +#include +#include /* struct device, and other headers */ +#include /* eth_type_trans */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +/* Default transmit lockup timeout period, in jiffies. */ +#define TILE_NET_TIMEOUT (5 * HZ) + +/* The maximum number of distinct channels (idesc.channel is 5 bits). */ +#define TILE_NET_CHANNELS 32 + +/* Maximum number of idescs to handle per "poll". */ +#define TILE_NET_BATCH 128 + +/* Maximum number of packets to handle per "poll". */ +#define TILE_NET_WEIGHT 64 + +/* Number of entries in each iqueue. */ +#define IQUEUE_ENTRIES 512 + +/* Number of entries in each equeue. */ +#define EQUEUE_ENTRIES 2048 + +/* Total header bytes per equeue slot. Must be big enough for 2 bytes + * of NET_IP_ALIGN alignment, plus 14 bytes (?) of L2 header, plus up to + * 60 bytes of actual TCP header. We round up to align to cache lines. + */ +#define HEADER_BYTES 128 + +/* Maximum completions per cpu per device (must be a power of two). + * ISSUE: What is the right number here? If this is too small, then + * egress might block waiting for free space in a completions array. + * ISSUE: At the least, allocate these only for initialized echannels. + */ +#define TILE_NET_MAX_COMPS 64 + +#define MAX_FRAGS (MAX_SKB_FRAGS + 1) + +/* Size of completions data to allocate. + * ISSUE: Probably more than needed since we don't use all the channels. + */ +#define COMPS_SIZE (TILE_NET_CHANNELS * sizeof(struct tile_net_comps)) + +/* Size of NotifRing data to allocate. */ +#define NOTIF_RING_SIZE (IQUEUE_ENTRIES * sizeof(gxio_mpipe_idesc_t)) + +/* Timeout to wake the per-device TX timer after we stop the queue. + * We don't want the timeout too short (adds overhead, and might end + * up causing stop/wake/stop/wake cycles) or too long (affects performance). + * For the 10 Gb NIC, 30 usec means roughly 30+ 1500-byte packets. + */ +#define TX_TIMER_DELAY_USEC 30 + +/* Timeout to wake the per-cpu egress timer to free completions. */ +#define EGRESS_TIMER_DELAY_USEC 1000 + +MODULE_AUTHOR("Tilera Corporation"); +MODULE_LICENSE("GPL"); + +/* A "packet fragment" (a chunk of memory). */ +struct frag { + void *buf; + size_t length; +}; + +/* A single completion. */ +struct tile_net_comp { + /* The "complete_count" when the completion will be complete. */ + s64 when; + /* The buffer to be freed when the completion is complete. */ + struct sk_buff *skb; +}; + +/* The completions for a given cpu and echannel. */ +struct tile_net_comps { + /* The completions. */ + struct tile_net_comp comp_queue[TILE_NET_MAX_COMPS]; + /* The number of completions used. */ + unsigned long comp_next; + /* The number of completions freed. */ + unsigned long comp_last; +}; + +/* The transmit wake timer for a given cpu and echannel. */ +struct tile_net_tx_wake { + struct hrtimer timer; + struct net_device *dev; +}; + +/* Info for a specific cpu. */ +struct tile_net_info { + /* The NAPI struct. */ + struct napi_struct napi; + /* Packet queue. */ + gxio_mpipe_iqueue_t iqueue; + /* Our cpu. */ + int my_cpu; + /* True if iqueue is valid. */ + bool has_iqueue; + /* NAPI flags. */ + bool napi_added; + bool napi_enabled; + /* Number of small sk_buffs which must still be provided. */ + unsigned int num_needed_small_buffers; + /* Number of large sk_buffs which must still be provided. */ + unsigned int num_needed_large_buffers; + /* A timer for handling egress completions. */ + struct hrtimer egress_timer; + /* True if "egress_timer" is scheduled. */ + bool egress_timer_scheduled; + /* Comps for each egress channel. */ + struct tile_net_comps *comps_for_echannel[TILE_NET_CHANNELS]; + /* Transmit wake timer for each egress channel. */ + struct tile_net_tx_wake tx_wake[TILE_NET_CHANNELS]; +}; + +/* Info for egress on a particular egress channel. */ +struct tile_net_egress { + /* The "equeue". */ + gxio_mpipe_equeue_t *equeue; + /* The headers for TSO. */ + unsigned char *headers; +}; + +/* Info for a specific device. */ +struct tile_net_priv { + /* Our network device. */ + struct net_device *dev; + /* The primary link. */ + gxio_mpipe_link_t link; + /* The primary channel, if open, else -1. */ + int channel; + /* The "loopify" egress link, if needed. */ + gxio_mpipe_link_t loopify_link; + /* The "loopify" egress channel, if open, else -1. */ + int loopify_channel; + /* The egress channel (channel or loopify_channel). */ + int echannel; + /* Total stats. */ + struct net_device_stats stats; +}; + +/* Egress info, indexed by "priv->echannel" (lazily created as needed). */ +static struct tile_net_egress egress_for_echannel[TILE_NET_CHANNELS]; + +/* Devices currently associated with each channel. + * NOTE: The array entry can become NULL after ifconfig down, but + * we do not free the underlying net_device structures, so it is + * safe to use a pointer after reading it from this array. + */ +static struct net_device *tile_net_devs_for_channel[TILE_NET_CHANNELS]; + +/* A mutex for "tile_net_devs_for_channel". */ +static DEFINE_MUTEX(tile_net_devs_for_channel_mutex); + +/* The per-cpu info. */ +static DEFINE_PER_CPU(struct tile_net_info, per_cpu_info); + +/* The "context" for all devices. */ +static gxio_mpipe_context_t context; + +/* Buffer sizes and mpipe enum codes for buffer stacks. + * See arch/tile/include/gxio/mpipe.h for the set of possible values. + */ +#define BUFFER_SIZE_SMALL_ENUM GXIO_MPIPE_BUFFER_SIZE_128 +#define BUFFER_SIZE_SMALL 128 +#define BUFFER_SIZE_LARGE_ENUM GXIO_MPIPE_BUFFER_SIZE_1664 +#define BUFFER_SIZE_LARGE 1664 + +/* The small/large "buffer stacks". */ +static int small_buffer_stack = -1; +static int large_buffer_stack = -1; + +/* Amount of memory allocated for each buffer stack. */ +static size_t buffer_stack_size; + +/* The actual memory allocated for the buffer stacks. */ +static void *small_buffer_stack_va; +static void *large_buffer_stack_va; + +/* The buckets. */ +static int first_bucket = -1; +static int num_buckets = 1; + +/* The ingress irq. */ +static int ingress_irq = -1; + +/* Text value of tile_net.cpus if passed as a module parameter. */ +static char *network_cpus_string; + +/* The actual cpus in "network_cpus". */ +static struct cpumask network_cpus_map; + +/* If "loopify=LINK" was specified, this is "LINK". */ +static char *loopify_link_name; + +/* If "tile_net.custom" was specified, this is non-NULL. */ +static char *custom_str; + +/* The "tile_net.cpus" argument specifies the cpus that are dedicated + * to handle ingress packets. + * + * The parameter should be in the form "tile_net.cpus=m-n[,x-y]", where + * m, n, x, y are integer numbers that represent the cpus that can be + * neither a dedicated cpu nor a dataplane cpu. + */ +static bool network_cpus_init(void) +{ + char buf[1024]; + int rc; + + if (network_cpus_string == NULL) + return false; + + rc = cpulist_parse_crop(network_cpus_string, &network_cpus_map); + if (rc != 0) { + pr_warn("tile_net.cpus=%s: malformed cpu list\n", + network_cpus_string); + return false; + } + + /* Remove dedicated cpus. */ + cpumask_and(&network_cpus_map, &network_cpus_map, cpu_possible_mask); + + if (cpumask_empty(&network_cpus_map)) { + pr_warn("Ignoring empty tile_net.cpus='%s'.\n", + network_cpus_string); + return false; + } + + cpulist_scnprintf(buf, sizeof(buf), &network_cpus_map); + pr_info("Linux network CPUs: %s\n", buf); + return true; +} + +module_param_named(cpus, network_cpus_string, charp, 0444); +MODULE_PARM_DESC(cpus, "cpulist of cores that handle network interrupts"); + +/* The "tile_net.loopify=LINK" argument causes the named device to + * actually use "loop0" for ingress, and "loop1" for egress. This + * allows an app to sit between the actual link and linux, passing + * (some) packets along to linux, and forwarding (some) packets sent + * out by linux. + */ +module_param_named(loopify, loopify_link_name, charp, 0444); +MODULE_PARM_DESC(loopify, "name the device to use loop0/1 for ingress/egress"); + +/* The "tile_net.custom" argument causes us to ignore the "conventional" + * classifier metadata, in particular, the "l2_offset". + */ +module_param_named(custom, custom_str, charp, 0444); +MODULE_PARM_DESC(custom, "indicates a (heavily) customized classifier"); + +/* Atomically update a statistics field. + * Note that on TILE-Gx, this operation is fire-and-forget on the + * issuing core (single-cycle dispatch) and takes only a few cycles + * longer than a regular store when the request reaches the home cache. + * No expensive bus management overhead is required. + */ +static void tile_net_stats_add(unsigned long value, unsigned long *field) +{ + BUILD_BUG_ON(sizeof(atomic_long_t) != sizeof(unsigned long)); + atomic_long_add(value, (atomic_long_t *)field); +} + +/* Allocate and push a buffer. */ +static bool tile_net_provide_buffer(bool small) +{ + int stack = small ? small_buffer_stack : large_buffer_stack; + const unsigned long buffer_alignment = 128; + struct sk_buff *skb; + int len; + + len = sizeof(struct sk_buff **) + buffer_alignment; + len += (small ? BUFFER_SIZE_SMALL : BUFFER_SIZE_LARGE); + skb = dev_alloc_skb(len); + if (skb == NULL) + return false; + + /* Make room for a back-pointer to 'skb' and guarantee alignment. */ + skb_reserve(skb, sizeof(struct sk_buff **)); + skb_reserve(skb, -(long)skb->data & (buffer_alignment - 1)); + + /* Save a back-pointer to 'skb'. */ + *(struct sk_buff **)(skb->data - sizeof(struct sk_buff **)) = skb; + + /* Make sure "skb" and the back-pointer have been flushed. */ + wmb(); + + gxio_mpipe_push_buffer(&context, stack, + (void *)va_to_tile_io_addr(skb->data)); + + return true; +} + +/* Convert a raw mpipe buffer to its matching skb pointer. */ +static struct sk_buff *mpipe_buf_to_skb(void *va) +{ + /* Acquire the associated "skb". */ + struct sk_buff **skb_ptr = va - sizeof(*skb_ptr); + struct sk_buff *skb = *skb_ptr; + + /* Paranoia. */ + if (skb->data != va) { + /* Panic here since there's a reasonable chance + * that corrupt buffers means generic memory + * corruption, with unpredictable system effects. + */ + panic("Corrupt linux buffer! va=%p, skb=%p, skb->data=%p", + va, skb, skb->data); + } + + return skb; +} + +static void tile_net_pop_all_buffers(int stack) +{ + for (;;) { + tile_io_addr_t addr = + (tile_io_addr_t)gxio_mpipe_pop_buffer(&context, stack); + if (addr == 0) + break; + dev_kfree_skb_irq(mpipe_buf_to_skb(tile_io_addr_to_va(addr))); + } +} + +/* Provide linux buffers to mPIPE. */ +static void tile_net_provide_needed_buffers(void) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + + while (info->num_needed_small_buffers != 0) { + if (!tile_net_provide_buffer(true)) + goto oops; + info->num_needed_small_buffers--; + } + + while (info->num_needed_large_buffers != 0) { + if (!tile_net_provide_buffer(false)) + goto oops; + info->num_needed_large_buffers--; + } + + return; + +oops: + /* Add a description to the page allocation failure dump. */ + pr_notice("Tile %d still needs some buffers\n", info->my_cpu); +} + +static inline bool filter_packet(struct net_device *dev, void *buf) +{ + /* Filter packets received before we're up. */ + if (dev == NULL || !(dev->flags & IFF_UP)) + return true; + + /* Filter out packets that aren't for us. */ + if (!(dev->flags & IFF_PROMISC) && + !is_multicast_ether_addr(buf) && + compare_ether_addr(dev->dev_addr, buf) != 0) + return true; + + return false; +} + +static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb, + gxio_mpipe_idesc_t *idesc, unsigned long len) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct tile_net_priv *priv = netdev_priv(dev); + + /* Encode the actual packet length. */ + skb_put(skb, len); + + skb->protocol = eth_type_trans(skb, dev); + + /* Acknowledge "good" hardware checksums. */ + if (idesc->cs && idesc->csum_seed_val == 0xFFFF) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + netif_receive_skb(skb); + + /* Update stats. */ + tile_net_stats_add(1, &priv->stats.rx_packets); + tile_net_stats_add(len, &priv->stats.rx_bytes); + + /* Need a new buffer. */ + if (idesc->size == BUFFER_SIZE_SMALL_ENUM) + info->num_needed_small_buffers++; + else + info->num_needed_large_buffers++; +} + +/* Handle a packet. Return true if "processed", false if "filtered". */ +static bool tile_net_handle_packet(gxio_mpipe_idesc_t *idesc) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct net_device *dev = tile_net_devs_for_channel[idesc->channel]; + uint8_t l2_offset; + void *va; + void *buf; + unsigned long len; + bool filter; + + /* Drop packets for which no buffer was available. + * NOTE: This happens under heavy load. + */ + if (idesc->be) { + struct tile_net_priv *priv = netdev_priv(dev); + tile_net_stats_add(1, &priv->stats.rx_dropped); + gxio_mpipe_iqueue_consume(&info->iqueue, idesc); + if (net_ratelimit()) + pr_info("Dropping packet (insufficient buffers).\n"); + return false; + } + + /* Get the "l2_offset", if allowed. */ + l2_offset = custom_str ? 0 : gxio_mpipe_idesc_get_l2_offset(idesc); + + /* Get the raw buffer VA (includes "headroom"). */ + va = tile_io_addr_to_va((unsigned long)(long)idesc->va); + + /* Get the actual packet start/length. */ + buf = va + l2_offset; + len = idesc->l2_size - l2_offset; + + /* Point "va" at the raw buffer. */ + va -= NET_IP_ALIGN; + + filter = filter_packet(dev, buf); + if (filter) { + gxio_mpipe_iqueue_drop(&info->iqueue, idesc); + } else { + struct sk_buff *skb = mpipe_buf_to_skb(va); + + /* Skip headroom, and any custom header. */ + skb_reserve(skb, NET_IP_ALIGN + l2_offset); + + tile_net_receive_skb(dev, skb, idesc, len); + } + + gxio_mpipe_iqueue_consume(&info->iqueue, idesc); + return !filter; +} + +/* Handle some packets for the current CPU. + * + * This function handles up to TILE_NET_BATCH idescs per call. + * + * ISSUE: Since we do not provide new buffers until this function is + * complete, we must initially provide enough buffers for each network + * cpu to fill its iqueue and also its batched idescs. + * + * ISSUE: The "rotting packet" race condition occurs if a packet + * arrives after the queue appears to be empty, and before the + * hypervisor interrupt is re-enabled. + */ +static int tile_net_poll(struct napi_struct *napi, int budget) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + unsigned int work = 0; + gxio_mpipe_idesc_t *idesc; + int i, n; + + /* Process packets. */ + while ((n = gxio_mpipe_iqueue_try_peek(&info->iqueue, &idesc)) > 0) { + for (i = 0; i < n; i++) { + if (i == TILE_NET_BATCH) + goto done; + if (tile_net_handle_packet(idesc + i)) { + if (++work >= budget) + goto done; + } + } + } + + /* There are no packets left. */ + napi_complete(&info->napi); + + /* Re-enable hypervisor interrupts. */ + gxio_mpipe_enable_notif_ring_interrupt(&context, info->iqueue.ring); + + /* HACK: Avoid the "rotting packet" problem. */ + if (gxio_mpipe_iqueue_try_peek(&info->iqueue, &idesc) > 0) + napi_schedule(&info->napi); + + /* ISSUE: Handle completions? */ + +done: + tile_net_provide_needed_buffers(); + + return work; +} + +/* Handle an ingress interrupt on the current cpu. */ +static irqreturn_t tile_net_handle_ingress_irq(int irq, void *unused) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + napi_schedule(&info->napi); + return IRQ_HANDLED; +} + +/* Free some completions. This must be called with interrupts blocked. */ +static int tile_net_free_comps(gxio_mpipe_equeue_t *equeue, + struct tile_net_comps *comps, + int limit, bool force_update) +{ + int n = 0; + while (comps->comp_last < comps->comp_next) { + unsigned int cid = comps->comp_last % TILE_NET_MAX_COMPS; + struct tile_net_comp *comp = &comps->comp_queue[cid]; + if (!gxio_mpipe_equeue_is_complete(equeue, comp->when, + force_update || n == 0)) + break; + dev_kfree_skb_irq(comp->skb); + comps->comp_last++; + if (++n == limit) + break; + } + return n; +} + +/* Add a completion. This must be called with interrupts blocked. + * tile_net_equeue_try_reserve() will have ensured a free completion entry. + */ +static void add_comp(gxio_mpipe_equeue_t *equeue, + struct tile_net_comps *comps, + uint64_t when, struct sk_buff *skb) +{ + int cid = comps->comp_next % TILE_NET_MAX_COMPS; + comps->comp_queue[cid].when = when; + comps->comp_queue[cid].skb = skb; + comps->comp_next++; +} + +static void tile_net_schedule_tx_wake_timer(struct net_device *dev) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct tile_net_priv *priv = netdev_priv(dev); + + hrtimer_start(&info->tx_wake[priv->echannel].timer, + ktime_set(0, TX_TIMER_DELAY_USEC * 1000UL), + HRTIMER_MODE_REL_PINNED); +} + +static enum hrtimer_restart tile_net_handle_tx_wake_timer(struct hrtimer *t) +{ + struct tile_net_tx_wake *tx_wake = + container_of(t, struct tile_net_tx_wake, timer); + netif_wake_subqueue(tx_wake->dev, smp_processor_id()); + return HRTIMER_NORESTART; +} + +/* Make sure the egress timer is scheduled. */ +static void tile_net_schedule_egress_timer(void) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + + if (!info->egress_timer_scheduled) { + hrtimer_start(&info->egress_timer, + ktime_set(0, EGRESS_TIMER_DELAY_USEC * 1000UL), + HRTIMER_MODE_REL_PINNED); + info->egress_timer_scheduled = true; + } +} + +/* The "function" for "info->egress_timer". + * + * This timer will reschedule itself as long as there are any pending + * completions expected for this tile. + */ +static enum hrtimer_restart tile_net_handle_egress_timer(struct hrtimer *t) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + unsigned long irqflags; + bool pending = false; + int i; + + local_irq_save(irqflags); + + /* The timer is no longer scheduled. */ + info->egress_timer_scheduled = false; + + /* Free all possible comps for this tile. */ + for (i = 0; i < TILE_NET_CHANNELS; i++) { + struct tile_net_egress *egress = &egress_for_echannel[i]; + struct tile_net_comps *comps = info->comps_for_echannel[i]; + if (comps->comp_last >= comps->comp_next) + continue; + tile_net_free_comps(egress->equeue, comps, -1, true); + pending = pending || (comps->comp_last < comps->comp_next); + } + + /* Reschedule timer if needed. */ + if (pending) + tile_net_schedule_egress_timer(); + + local_irq_restore(irqflags); + + return HRTIMER_NORESTART; +} + +/* Helper function for "tile_net_update()". + * "dev" (i.e. arg) is the device being brought up or down, + * or NULL if all devices are now down. + */ +static void tile_net_update_cpu(void *arg) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct net_device *dev = arg; + + if (!info->has_iqueue) + return; + + if (dev != NULL) { + if (!info->napi_added) { + netif_napi_add(dev, &info->napi, + tile_net_poll, TILE_NET_WEIGHT); + info->napi_added = true; + } + if (!info->napi_enabled) { + napi_enable(&info->napi); + info->napi_enabled = true; + } + enable_percpu_irq(ingress_irq, 0); + } else { + disable_percpu_irq(ingress_irq); + if (info->napi_enabled) { + napi_disable(&info->napi); + info->napi_enabled = false; + } + /* FIXME: Drain the iqueue. */ + } +} + +/* Helper function for tile_net_open() and tile_net_stop(). + * Always called under tile_net_devs_for_channel_mutex. + */ +static int tile_net_update(struct net_device *dev) +{ + static gxio_mpipe_rules_t rules; /* too big to fit on the stack */ + bool saw_channel = false; + int channel; + int rc; + int cpu; + + gxio_mpipe_rules_init(&rules, &context); + + for (channel = 0; channel < TILE_NET_CHANNELS; channel++) { + if (tile_net_devs_for_channel[channel] == NULL) + continue; + if (!saw_channel) { + saw_channel = true; + gxio_mpipe_rules_begin(&rules, first_bucket, + num_buckets, NULL); + gxio_mpipe_rules_set_headroom(&rules, NET_IP_ALIGN); + } + gxio_mpipe_rules_add_channel(&rules, channel); + } + + /* NOTE: This can fail if there is no classifier. + * ISSUE: Can anything else cause it to fail? + */ + rc = gxio_mpipe_rules_commit(&rules); + if (rc != 0) { + netdev_warn(dev, "gxio_mpipe_rules_commit failed: %d\n", rc); + return -EIO; + } + + /* Update all cpus, sequentially (to protect "netif_napi_add()"). */ + for_each_online_cpu(cpu) + smp_call_function_single(cpu, tile_net_update_cpu, + (saw_channel ? dev : NULL), 1); + + /* HACK: Allow packets to flow in the simulator. */ + if (saw_channel) + sim_enable_mpipe_links(0, -1); + + return 0; +} + +/* Allocate and initialize mpipe buffer stacks, and register them in + * the mPIPE TLBs, for both small and large packet sizes. + * This routine supports tile_net_init_mpipe(), below. + */ +static int init_buffer_stacks(struct net_device *dev, int num_buffers) +{ + pte_t hash_pte = pte_set_home((pte_t) { 0 }, PAGE_HOME_HASH); + int rc; + + /* Compute stack bytes; we round up to 64KB and then use + * alloc_pages() so we get the required 64KB alignment as well. + */ + buffer_stack_size = + ALIGN(gxio_mpipe_calc_buffer_stack_bytes(num_buffers), + 64 * 1024); + + /* Allocate two buffer stack indices. */ + rc = gxio_mpipe_alloc_buffer_stacks(&context, 2, 0, 0); + if (rc < 0) { + netdev_err(dev, "gxio_mpipe_alloc_buffer_stacks failed: %d\n", + rc); + return rc; + } + small_buffer_stack = rc; + large_buffer_stack = rc + 1; + + /* Allocate the small memory stack. */ + small_buffer_stack_va = + alloc_pages_exact(buffer_stack_size, GFP_KERNEL); + if (small_buffer_stack_va == NULL) { + netdev_err(dev, + "Could not alloc %zd bytes for buffer stacks\n", + buffer_stack_size); + return -ENOMEM; + } + rc = gxio_mpipe_init_buffer_stack(&context, small_buffer_stack, + BUFFER_SIZE_SMALL_ENUM, + small_buffer_stack_va, + buffer_stack_size, 0); + if (rc != 0) { + netdev_err(dev, "gxio_mpipe_init_buffer_stack: %d\n", rc); + return rc; + } + rc = gxio_mpipe_register_client_memory(&context, small_buffer_stack, + hash_pte, 0); + if (rc != 0) { + netdev_err(dev, + "gxio_mpipe_register_buffer_memory failed: %d\n", + rc); + return rc; + } + + /* Allocate the large buffer stack. */ + large_buffer_stack_va = + alloc_pages_exact(buffer_stack_size, GFP_KERNEL); + if (large_buffer_stack_va == NULL) { + netdev_err(dev, + "Could not alloc %zd bytes for buffer stacks\n", + buffer_stack_size); + return -ENOMEM; + } + rc = gxio_mpipe_init_buffer_stack(&context, large_buffer_stack, + BUFFER_SIZE_LARGE_ENUM, + large_buffer_stack_va, + buffer_stack_size, 0); + if (rc != 0) { + netdev_err(dev, "gxio_mpipe_init_buffer_stack failed: %d\n", + rc); + return rc; + } + rc = gxio_mpipe_register_client_memory(&context, large_buffer_stack, + hash_pte, 0); + if (rc != 0) { + netdev_err(dev, + "gxio_mpipe_register_buffer_memory failed: %d\n", + rc); + return rc; + } + + return 0; +} + +/* Allocate per-cpu resources (memory for completions and idescs). + * This routine supports tile_net_init_mpipe(), below. + */ +static int alloc_percpu_mpipe_resources(struct net_device *dev, + int cpu, int ring) +{ + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + int order, i, rc; + struct page *page; + void *addr; + + /* Allocate the "comps". */ + order = get_order(COMPS_SIZE); + page = homecache_alloc_pages(GFP_KERNEL, order, cpu); + if (page == NULL) { + netdev_err(dev, "Failed to alloc %zd bytes comps memory\n", + COMPS_SIZE); + return -ENOMEM; + } + addr = pfn_to_kaddr(page_to_pfn(page)); + memset(addr, 0, COMPS_SIZE); + for (i = 0; i < TILE_NET_CHANNELS; i++) + info->comps_for_echannel[i] = + addr + i * sizeof(struct tile_net_comps); + + /* If this is a network cpu, create an iqueue. */ + if (cpu_isset(cpu, network_cpus_map)) { + order = get_order(NOTIF_RING_SIZE); + page = homecache_alloc_pages(GFP_KERNEL, order, cpu); + if (page == NULL) { + netdev_err(dev, + "Failed to alloc %zd bytes iqueue memory\n", + NOTIF_RING_SIZE); + return -ENOMEM; + } + addr = pfn_to_kaddr(page_to_pfn(page)); + rc = gxio_mpipe_iqueue_init(&info->iqueue, &context, ring++, + addr, NOTIF_RING_SIZE, 0); + if (rc < 0) { + netdev_err(dev, + "gxio_mpipe_iqueue_init failed: %d\n", rc); + return rc; + } + info->has_iqueue = true; + } + + return ring; +} + +/* Initialize NotifGroup and buckets. + * This routine supports tile_net_init_mpipe(), below. + */ +static int init_notif_group_and_buckets(struct net_device *dev, + int ring, int network_cpus_count) +{ + int group, rc; + + /* Allocate one NotifGroup. */ + rc = gxio_mpipe_alloc_notif_groups(&context, 1, 0, 0); + if (rc < 0) { + netdev_err(dev, "gxio_mpipe_alloc_notif_groups failed: %d\n", + rc); + return rc; + } + group = rc; + + /* Initialize global num_buckets value. */ + if (network_cpus_count > 4) + num_buckets = 256; + else if (network_cpus_count > 1) + num_buckets = 16; + + /* Allocate some buckets, and set global first_bucket value. */ + rc = gxio_mpipe_alloc_buckets(&context, num_buckets, 0, 0); + if (rc < 0) { + netdev_err(dev, "gxio_mpipe_alloc_buckets failed: %d\n", rc); + return rc; + } + first_bucket = rc; + + /* Init group and buckets. */ + rc = gxio_mpipe_init_notif_group_and_buckets( + &context, group, ring, network_cpus_count, + first_bucket, num_buckets, + GXIO_MPIPE_BUCKET_STICKY_FLOW_LOCALITY); + if (rc != 0) { + netdev_err( + dev, + "gxio_mpipe_init_notif_group_and_buckets failed: %d\n", + rc); + return rc; + } + + return 0; +} + +/* Create an irq and register it, then activate the irq and request + * interrupts on all cores. Note that "ingress_irq" being initialized + * is how we know not to call tile_net_init_mpipe() again. + * This routine supports tile_net_init_mpipe(), below. + */ +static int tile_net_setup_interrupts(struct net_device *dev) +{ + int cpu, rc; + + rc = create_irq(); + if (rc < 0) { + netdev_err(dev, "create_irq failed: %d\n", rc); + return rc; + } + ingress_irq = rc; + tile_irq_activate(ingress_irq, TILE_IRQ_PERCPU); + rc = request_irq(ingress_irq, tile_net_handle_ingress_irq, + 0, NULL, NULL); + if (rc != 0) { + netdev_err(dev, "request_irq failed: %d\n", rc); + destroy_irq(ingress_irq); + ingress_irq = -1; + return rc; + } + + for_each_online_cpu(cpu) { + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + if (info->has_iqueue) { + gxio_mpipe_request_notif_ring_interrupt( + &context, cpu_x(cpu), cpu_y(cpu), + 1, ingress_irq, info->iqueue.ring); + } + } + + return 0; +} + +/* Undo any state set up partially by a failed call to tile_net_init_mpipe. */ +static void tile_net_init_mpipe_fail(void) +{ + int cpu; + + /* Do cleanups that require the mpipe context first. */ + if (small_buffer_stack >= 0) + tile_net_pop_all_buffers(small_buffer_stack); + if (large_buffer_stack >= 0) + tile_net_pop_all_buffers(large_buffer_stack); + + /* Destroy mpipe context so the hardware no longer owns any memory. */ + gxio_mpipe_destroy(&context); + + for_each_online_cpu(cpu) { + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + free_pages((unsigned long)(info->comps_for_echannel[0]), + get_order(COMPS_SIZE)); + info->comps_for_echannel[0] = NULL; + free_pages((unsigned long)(info->iqueue.idescs), + get_order(NOTIF_RING_SIZE)); + info->iqueue.idescs = NULL; + } + + if (small_buffer_stack_va) + free_pages_exact(small_buffer_stack_va, buffer_stack_size); + if (large_buffer_stack_va) + free_pages_exact(large_buffer_stack_va, buffer_stack_size); + + small_buffer_stack_va = NULL; + large_buffer_stack_va = NULL; + large_buffer_stack = -1; + small_buffer_stack = -1; + first_bucket = -1; +} + +/* The first time any tilegx network device is opened, we initialize + * the global mpipe state. If this step fails, we fail to open the + * device, but if it succeeds, we never need to do it again, and since + * tile_net can't be unloaded, we never undo it. + * + * Note that some resources in this path (buffer stack indices, + * bindings from init_buffer_stack, etc.) are hypervisor resources + * that are freed implicitly by gxio_mpipe_destroy(). + */ +static int tile_net_init_mpipe(struct net_device *dev) +{ + int i, num_buffers, rc; + int cpu; + int first_ring, ring; + int network_cpus_count = cpus_weight(network_cpus_map); + + if (!hash_default) { + netdev_err(dev, "Networking requires hash_default!\n"); + return -EIO; + } + + rc = gxio_mpipe_init(&context, 0); + if (rc != 0) { + netdev_err(dev, "gxio_mpipe_init failed: %d\n", rc); + return -EIO; + } + + /* Set up the buffer stacks. */ + num_buffers = + network_cpus_count * (IQUEUE_ENTRIES + TILE_NET_BATCH); + rc = init_buffer_stacks(dev, num_buffers); + if (rc != 0) + goto fail; + + /* Provide initial buffers. */ + rc = -ENOMEM; + for (i = 0; i < num_buffers; i++) { + if (!tile_net_provide_buffer(true)) { + netdev_err(dev, "Cannot allocate initial sk_bufs!\n"); + goto fail; + } + } + for (i = 0; i < num_buffers; i++) { + if (!tile_net_provide_buffer(false)) { + netdev_err(dev, "Cannot allocate initial sk_bufs!\n"); + goto fail; + } + } + + /* Allocate one NotifRing for each network cpu. */ + rc = gxio_mpipe_alloc_notif_rings(&context, network_cpus_count, 0, 0); + if (rc < 0) { + netdev_err(dev, "gxio_mpipe_alloc_notif_rings failed %d\n", + rc); + goto fail; + } + + /* Init NotifRings per-cpu. */ + first_ring = rc; + ring = first_ring; + for_each_online_cpu(cpu) { + rc = alloc_percpu_mpipe_resources(dev, cpu, ring); + if (rc < 0) + goto fail; + ring = rc; + } + + /* Initialize NotifGroup and buckets. */ + rc = init_notif_group_and_buckets(dev, first_ring, network_cpus_count); + if (rc != 0) + goto fail; + + /* Create and enable interrupts. */ + rc = tile_net_setup_interrupts(dev); + if (rc != 0) + goto fail; + + return 0; + +fail: + tile_net_init_mpipe_fail(); + return rc; +} + +/* Create persistent egress info for a given egress channel. + * Note that this may be shared between, say, "gbe0" and "xgbe0". + * ISSUE: Defer header allocation until TSO is actually needed? + */ +static int tile_net_init_egress(struct net_device *dev, int echannel) +{ + struct page *headers_page, *edescs_page, *equeue_page; + gxio_mpipe_edesc_t *edescs; + gxio_mpipe_equeue_t *equeue; + unsigned char *headers; + int headers_order, edescs_order, equeue_order; + size_t edescs_size; + int edma; + int rc = -ENOMEM; + + /* Only initialize once. */ + if (egress_for_echannel[echannel].equeue != NULL) + return 0; + + /* Allocate memory for the "headers". */ + headers_order = get_order(EQUEUE_ENTRIES * HEADER_BYTES); + headers_page = alloc_pages(GFP_KERNEL, headers_order); + if (headers_page == NULL) { + netdev_warn(dev, + "Could not alloc %zd bytes for TSO headers.\n", + PAGE_SIZE << headers_order); + goto fail; + } + headers = pfn_to_kaddr(page_to_pfn(headers_page)); + + /* Allocate memory for the "edescs". */ + edescs_size = EQUEUE_ENTRIES * sizeof(*edescs); + edescs_order = get_order(edescs_size); + edescs_page = alloc_pages(GFP_KERNEL, edescs_order); + if (edescs_page == NULL) { + netdev_warn(dev, + "Could not alloc %zd bytes for eDMA ring.\n", + edescs_size); + goto fail_headers; + } + edescs = pfn_to_kaddr(page_to_pfn(edescs_page)); + + /* Allocate memory for the "equeue". */ + equeue_order = get_order(sizeof(*equeue)); + equeue_page = alloc_pages(GFP_KERNEL, equeue_order); + if (equeue_page == NULL) { + netdev_warn(dev, + "Could not alloc %zd bytes for equeue info.\n", + PAGE_SIZE << equeue_order); + goto fail_edescs; + } + equeue = pfn_to_kaddr(page_to_pfn(equeue_page)); + + /* Allocate an edma ring. Note that in practice this can't + * fail, which is good, because we will leak an edma ring if so. + */ + rc = gxio_mpipe_alloc_edma_rings(&context, 1, 0, 0); + if (rc < 0) { + netdev_warn(dev, "gxio_mpipe_alloc_edma_rings failed: %d\n", + rc); + goto fail_equeue; + } + edma = rc; + + /* Initialize the equeue. */ + rc = gxio_mpipe_equeue_init(equeue, &context, edma, echannel, + edescs, edescs_size, 0); + if (rc != 0) { + netdev_err(dev, "gxio_mpipe_equeue_init failed: %d\n", rc); + goto fail_equeue; + } + + /* Done. */ + egress_for_echannel[echannel].equeue = equeue; + egress_for_echannel[echannel].headers = headers; + return 0; + +fail_equeue: + __free_pages(equeue_page, equeue_order); + +fail_edescs: + __free_pages(edescs_page, edescs_order); + +fail_headers: + __free_pages(headers_page, headers_order); + +fail: + return rc; +} + +/* Return channel number for a newly-opened link. */ +static int tile_net_link_open(struct net_device *dev, gxio_mpipe_link_t *link, + const char *link_name) +{ + int rc = gxio_mpipe_link_open(link, &context, link_name, 0); + if (rc < 0) { + netdev_err(dev, "Failed to open '%s'\n", link_name); + return rc; + } + rc = gxio_mpipe_link_channel(link); + if (rc < 0 || rc >= TILE_NET_CHANNELS) { + netdev_err(dev, "gxio_mpipe_link_channel bad value: %d\n", rc); + gxio_mpipe_link_close(link); + return -EINVAL; + } + return rc; +} + +/* Help the kernel activate the given network interface. */ +static int tile_net_open(struct net_device *dev) +{ + struct tile_net_priv *priv = netdev_priv(dev); + int cpu, rc; + + mutex_lock(&tile_net_devs_for_channel_mutex); + + /* Do one-time initialization the first time any device is opened. */ + if (ingress_irq < 0) { + rc = tile_net_init_mpipe(dev); + if (rc != 0) + goto fail; + } + + /* Determine if this is the "loopify" device. */ + if (unlikely((loopify_link_name != NULL) && + !strcmp(dev->name, loopify_link_name))) { + rc = tile_net_link_open(dev, &priv->link, "loop0"); + if (rc < 0) + goto fail; + priv->channel = rc; + rc = tile_net_link_open(dev, &priv->loopify_link, "loop1"); + if (rc < 0) + goto fail; + priv->loopify_channel = rc; + priv->echannel = rc; + } else { + rc = tile_net_link_open(dev, &priv->link, dev->name); + if (rc < 0) + goto fail; + priv->channel = rc; + priv->echannel = rc; + } + + /* Initialize egress info (if needed). Once ever, per echannel. */ + rc = tile_net_init_egress(dev, priv->echannel); + if (rc != 0) + goto fail; + + tile_net_devs_for_channel[priv->channel] = dev; + + rc = tile_net_update(dev); + if (rc != 0) + goto fail; + + mutex_unlock(&tile_net_devs_for_channel_mutex); + + /* Initialize the transmit wake timer for this device for each cpu. */ + for_each_online_cpu(cpu) { + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + struct tile_net_tx_wake *tx_wake = + &info->tx_wake[priv->echannel]; + + hrtimer_init(&tx_wake->timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + tx_wake->timer.function = tile_net_handle_tx_wake_timer; + tx_wake->dev = dev; + } + + for_each_online_cpu(cpu) + netif_start_subqueue(dev, cpu); + netif_carrier_on(dev); + return 0; + +fail: + if (priv->loopify_channel >= 0) { + if (gxio_mpipe_link_close(&priv->loopify_link) != 0) + netdev_warn(dev, "Failed to close loopify link!\n"); + priv->loopify_channel = -1; + } + if (priv->channel >= 0) { + if (gxio_mpipe_link_close(&priv->link) != 0) + netdev_warn(dev, "Failed to close link!\n"); + priv->channel = -1; + } + priv->echannel = -1; + tile_net_devs_for_channel[priv->channel] = NULL; + mutex_unlock(&tile_net_devs_for_channel_mutex); + + /* Don't return raw gxio error codes to generic Linux. */ + return (rc > -512) ? rc : -EIO; +} + +/* Help the kernel deactivate the given network interface. */ +static int tile_net_stop(struct net_device *dev) +{ + struct tile_net_priv *priv = netdev_priv(dev); + int cpu; + + for_each_online_cpu(cpu) { + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + struct tile_net_tx_wake *tx_wake = + &info->tx_wake[priv->echannel]; + + hrtimer_cancel(&tx_wake->timer); + netif_stop_subqueue(dev, cpu); + } + + mutex_lock(&tile_net_devs_for_channel_mutex); + tile_net_devs_for_channel[priv->channel] = NULL; + (void)tile_net_update(dev); + if (priv->loopify_channel >= 0) { + if (gxio_mpipe_link_close(&priv->loopify_link) != 0) + netdev_warn(dev, "Failed to close loopify link!\n"); + priv->loopify_channel = -1; + } + if (priv->channel >= 0) { + if (gxio_mpipe_link_close(&priv->link) != 0) + netdev_warn(dev, "Failed to close link!\n"); + priv->channel = -1; + } + priv->echannel = -1; + mutex_unlock(&tile_net_devs_for_channel_mutex); + + return 0; +} + +/* Determine the VA for a fragment. */ +static inline void *tile_net_frag_buf(skb_frag_t *f) +{ + unsigned long pfn = page_to_pfn(skb_frag_page(f)); + return pfn_to_kaddr(pfn) + f->page_offset; +} + +/* Acquire a completion entry and an egress slot, or if we can't, + * stop the queue and schedule the tx_wake timer. + */ +static s64 tile_net_equeue_try_reserve(struct net_device *dev, + struct tile_net_comps *comps, + gxio_mpipe_equeue_t *equeue, + int num_edescs) +{ + /* Try to acquire a completion entry. */ + if (comps->comp_next - comps->comp_last < TILE_NET_MAX_COMPS - 1 || + tile_net_free_comps(equeue, comps, 32, false) != 0) { + + /* Try to acquire an egress slot. */ + s64 slot = gxio_mpipe_equeue_try_reserve(equeue, num_edescs); + if (slot >= 0) + return slot; + + /* Freeing some completions gives the equeue time to drain. */ + tile_net_free_comps(equeue, comps, TILE_NET_MAX_COMPS, false); + + slot = gxio_mpipe_equeue_try_reserve(equeue, num_edescs); + if (slot >= 0) + return slot; + } + + /* Still nothing; give up and stop the queue for a short while. */ + netif_stop_subqueue(dev, smp_processor_id()); + tile_net_schedule_tx_wake_timer(dev); + return -1; +} + +/* Determine how many edesc's are needed for TSO. + * + * Sometimes, if "sendfile()" requires copying, we will be called with + * "data" containing the header and payload, with "frags" being empty. + * Sometimes, for example when using NFS over TCP, a single segment can + * span 3 fragments. This requires special care. + */ +static int tso_count_edescs(struct sk_buff *skb) +{ + struct skb_shared_info *sh = skb_shinfo(skb); + unsigned int data_len = skb->data_len; + unsigned int p_len = sh->gso_size; + long f_id = -1; /* id of the current fragment */ + long f_size = -1; /* size of the current fragment */ + long f_used = -1; /* bytes used from the current fragment */ + long n; /* size of the current piece of payload */ + int num_edescs = 0; + int segment; + + for (segment = 0; segment < sh->gso_segs; segment++) { + + unsigned int p_used = 0; + + /* One edesc for header and for each piece of the payload. */ + for (num_edescs++; p_used < p_len; num_edescs++) { + + /* Advance as needed. */ + while (f_used >= f_size) { + f_id++; + f_size = sh->frags[f_id].size; + f_used = 0; + } + + /* Use bytes from the current fragment. */ + n = p_len - p_used; + if (n > f_size - f_used) + n = f_size - f_used; + f_used += n; + p_used += n; + } + + /* The last segment may be less than gso_size. */ + data_len -= p_len; + if (data_len < p_len) + p_len = data_len; + } + + return num_edescs; +} + +/* Prepare modified copies of the skbuff headers. + * FIXME: add support for IPv6. + */ +static void tso_headers_prepare(struct sk_buff *skb, unsigned char *headers, + s64 slot) +{ + struct skb_shared_info *sh = skb_shinfo(skb); + struct iphdr *ih; + struct tcphdr *th; + unsigned int data_len = skb->data_len; + unsigned char *data = skb->data; + unsigned int ih_off, th_off, sh_len, p_len; + unsigned int isum_seed, tsum_seed, id, seq; + long f_id = -1; /* id of the current fragment */ + long f_size = -1; /* size of the current fragment */ + long f_used = -1; /* bytes used from the current fragment */ + long n; /* size of the current piece of payload */ + int segment; + + /* Locate original headers and compute various lengths. */ + ih = ip_hdr(skb); + th = tcp_hdr(skb); + ih_off = skb_network_offset(skb); + th_off = skb_transport_offset(skb); + sh_len = th_off + tcp_hdrlen(skb); + p_len = sh->gso_size; + + /* Set up seed values for IP and TCP csum and initialize id and seq. */ + isum_seed = ((0xFFFF - ih->check) + + (0xFFFF - ih->tot_len) + + (0xFFFF - ih->id)); + tsum_seed = th->check + (0xFFFF ^ htons(skb->len)); + id = ntohs(ih->id); + seq = ntohl(th->seq); + + /* Prepare all the headers. */ + for (segment = 0; segment < sh->gso_segs; segment++) { + unsigned char *buf; + unsigned int p_used = 0; + + /* Copy to the header memory for this segment. */ + buf = headers + (slot % EQUEUE_ENTRIES) * HEADER_BYTES + + NET_IP_ALIGN; + memcpy(buf, data, sh_len); + + /* Update copied ip header. */ + ih = (struct iphdr *)(buf + ih_off); + ih->tot_len = htons(sh_len + p_len - ih_off); + ih->id = htons(id); + ih->check = csum_long(isum_seed + ih->tot_len + + ih->id) ^ 0xffff; + + /* Update copied tcp header. */ + th = (struct tcphdr *)(buf + th_off); + th->seq = htonl(seq); + th->check = csum_long(tsum_seed + htons(sh_len + p_len)); + if (segment != sh->gso_segs - 1) { + th->fin = 0; + th->psh = 0; + } + + /* Skip past the header. */ + slot++; + + /* Skip past the payload. */ + while (p_used < p_len) { + + /* Advance as needed. */ + while (f_used >= f_size) { + f_id++; + f_size = sh->frags[f_id].size; + f_used = 0; + } + + /* Use bytes from the current fragment. */ + n = p_len - p_used; + if (n > f_size - f_used) + n = f_size - f_used; + f_used += n; + p_used += n; + + slot++; + } + + id++; + seq += p_len; + + /* The last segment may be less than gso_size. */ + data_len -= p_len; + if (data_len < p_len) + p_len = data_len; + } + + /* Flush the headers so they are ready for hardware DMA. */ + wmb(); +} + +/* Pass all the data to mpipe for egress. */ +static void tso_egress(struct net_device *dev, gxio_mpipe_equeue_t *equeue, + struct sk_buff *skb, unsigned char *headers, s64 slot) +{ + struct tile_net_priv *priv = netdev_priv(dev); + struct skb_shared_info *sh = skb_shinfo(skb); + unsigned int data_len = skb->data_len; + unsigned int p_len = sh->gso_size; + gxio_mpipe_edesc_t edesc_head = { { 0 } }; + gxio_mpipe_edesc_t edesc_body = { { 0 } }; + long f_id = -1; /* id of the current fragment */ + long f_size = -1; /* size of the current fragment */ + long f_used = -1; /* bytes used from the current fragment */ + long n; /* size of the current piece of payload */ + unsigned long tx_packets = 0, tx_bytes = 0; + unsigned int csum_start, sh_len; + int segment; + + /* Prepare to egress the headers: set up header edesc. */ + csum_start = skb_checksum_start_offset(skb); + sh_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + edesc_head.csum = 1; + edesc_head.csum_start = csum_start; + edesc_head.csum_dest = csum_start + skb->csum_offset; + edesc_head.xfer_size = sh_len; + + /* This is only used to specify the TLB. */ + edesc_head.stack_idx = large_buffer_stack; + edesc_body.stack_idx = large_buffer_stack; + + /* Egress all the edescs. */ + for (segment = 0; segment < sh->gso_segs; segment++) { + void *va; + unsigned char *buf; + unsigned int p_used = 0; + + /* Egress the header. */ + buf = headers + (slot % EQUEUE_ENTRIES) * HEADER_BYTES + + NET_IP_ALIGN; + edesc_head.va = va_to_tile_io_addr(buf); + gxio_mpipe_equeue_put_at(equeue, edesc_head, slot); + slot++; + + /* Egress the payload. */ + while (p_used < p_len) { + + /* Advance as needed. */ + while (f_used >= f_size) { + f_id++; + f_size = sh->frags[f_id].size; + f_used = 0; + } + + va = tile_net_frag_buf(&sh->frags[f_id]) + f_used; + + /* Use bytes from the current fragment. */ + n = p_len - p_used; + if (n > f_size - f_used) + n = f_size - f_used; + f_used += n; + p_used += n; + + /* Egress a piece of the payload. */ + edesc_body.va = va_to_tile_io_addr(va); + edesc_body.xfer_size = n; + edesc_body.bound = !(p_used < p_len); + gxio_mpipe_equeue_put_at(equeue, edesc_body, slot); + slot++; + } + + tx_packets++; + tx_bytes += sh_len + p_len; + + /* The last segment may be less than gso_size. */ + data_len -= p_len; + if (data_len < p_len) + p_len = data_len; + } + + /* Update stats. */ + tile_net_stats_add(tx_packets, &priv->stats.tx_packets); + tile_net_stats_add(tx_bytes, &priv->stats.tx_bytes); +} + +/* Do "TSO" handling for egress. + * + * Normally drivers set NETIF_F_TSO only to support hardware TSO; + * otherwise the stack uses scatter-gather to implement GSO in software. + * On our testing, enabling GSO support (via NETIF_F_SG) drops network + * performance down to around 7.5 Gbps on the 10G interfaces, although + * also dropping cpu utilization way down, to under 8%. But + * implementing "TSO" in the driver brings performance back up to line + * rate, while dropping cpu usage even further, to less than 4%. In + * practice, profiling of GSO shows that skb_segment() is what causes + * the performance overheads; we benefit in the driver from using + * preallocated memory to duplicate the TCP/IP headers. + */ +static int tile_net_tx_tso(struct sk_buff *skb, struct net_device *dev) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct tile_net_priv *priv = netdev_priv(dev); + int channel = priv->echannel; + struct tile_net_egress *egress = &egress_for_echannel[channel]; + struct tile_net_comps *comps = info->comps_for_echannel[channel]; + gxio_mpipe_equeue_t *equeue = egress->equeue; + unsigned long irqflags; + int num_edescs; + s64 slot; + + /* Determine how many mpipe edesc's are needed. */ + num_edescs = tso_count_edescs(skb); + + local_irq_save(irqflags); + + /* Try to acquire a completion entry and an egress slot. */ + slot = tile_net_equeue_try_reserve(dev, comps, equeue, num_edescs); + if (slot < 0) { + local_irq_restore(irqflags); + return NETDEV_TX_BUSY; + } + + /* Set up copies of header data properly. */ + tso_headers_prepare(skb, egress->headers, slot); + + /* Actually pass the data to the network hardware. */ + tso_egress(dev, equeue, skb, egress->headers, slot); + + /* Add a completion record. */ + add_comp(equeue, comps, slot + num_edescs - 1, skb); + + local_irq_restore(irqflags); + + /* Make sure the egress timer is scheduled. */ + tile_net_schedule_egress_timer(); + + return NETDEV_TX_OK; +} + +/* Analyze the body and frags for a transmit request. */ +static unsigned int tile_net_tx_frags(struct frag *frags, + struct sk_buff *skb, + void *b_data, unsigned int b_len) +{ + unsigned int i, n = 0; + + struct skb_shared_info *sh = skb_shinfo(skb); + + if (b_len != 0) { + frags[n].buf = b_data; + frags[n++].length = b_len; + } + + for (i = 0; i < sh->nr_frags; i++) { + skb_frag_t *f = &sh->frags[i]; + frags[n].buf = tile_net_frag_buf(f); + frags[n++].length = skb_frag_size(f); + } + + return n; +} + +/* Help the kernel transmit a packet. */ +static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct tile_net_priv *priv = netdev_priv(dev); + struct tile_net_egress *egress = &egress_for_echannel[priv->echannel]; + gxio_mpipe_equeue_t *equeue = egress->equeue; + struct tile_net_comps *comps = + info->comps_for_echannel[priv->echannel]; + unsigned int len = skb->len; + unsigned char *data = skb->data; + unsigned int num_edescs; + struct frag frags[MAX_FRAGS]; + gxio_mpipe_edesc_t edescs[MAX_FRAGS]; + unsigned long irqflags; + gxio_mpipe_edesc_t edesc = { { 0 } }; + unsigned int i; + s64 slot; + + if (skb_is_gso(skb)) + return tile_net_tx_tso(skb, dev); + + num_edescs = tile_net_tx_frags(frags, skb, data, skb_headlen(skb)); + + /* This is only used to specify the TLB. */ + edesc.stack_idx = large_buffer_stack; + + /* Prepare the edescs. */ + for (i = 0; i < num_edescs; i++) { + edesc.xfer_size = frags[i].length; + edesc.va = va_to_tile_io_addr(frags[i].buf); + edescs[i] = edesc; + } + + /* Mark the final edesc. */ + edescs[num_edescs - 1].bound = 1; + + /* Add checksum info to the initial edesc, if needed. */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + unsigned int csum_start = skb_checksum_start_offset(skb); + edescs[0].csum = 1; + edescs[0].csum_start = csum_start; + edescs[0].csum_dest = csum_start + skb->csum_offset; + } + + local_irq_save(irqflags); + + /* Try to acquire a completion entry and an egress slot. */ + slot = tile_net_equeue_try_reserve(dev, comps, equeue, num_edescs); + if (slot < 0) { + local_irq_restore(irqflags); + return NETDEV_TX_BUSY; + } + + for (i = 0; i < num_edescs; i++) + gxio_mpipe_equeue_put_at(equeue, edescs[i], slot++); + + /* Add a completion record. */ + add_comp(equeue, comps, slot - 1, skb); + + /* NOTE: Use ETH_ZLEN for short packets (e.g. 42 < 60). */ + tile_net_stats_add(1, &priv->stats.tx_packets); + tile_net_stats_add(max_t(unsigned int, len, ETH_ZLEN), + &priv->stats.tx_bytes); + + local_irq_restore(irqflags); + + /* Make sure the egress timer is scheduled. */ + tile_net_schedule_egress_timer(); + + return NETDEV_TX_OK; +} + +/* Return subqueue id on this core (one per core). */ +static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb) +{ + return smp_processor_id(); +} + +/* Deal with a transmit timeout. */ +static void tile_net_tx_timeout(struct net_device *dev) +{ + int cpu; + + for_each_online_cpu(cpu) + netif_wake_subqueue(dev, cpu); +} + +/* Ioctl commands. */ +static int tile_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +{ + return -EOPNOTSUPP; +} + +/* Get system network statistics for device. */ +static struct net_device_stats *tile_net_get_stats(struct net_device *dev) +{ + struct tile_net_priv *priv = netdev_priv(dev); + return &priv->stats; +} + +/* Change the MTU. */ +static int tile_net_change_mtu(struct net_device *dev, int new_mtu) +{ + if ((new_mtu < 68) || (new_mtu > 1500)) + return -EINVAL; + dev->mtu = new_mtu; + return 0; +} + +/* Change the Ethernet address of the NIC. + * + * The hypervisor driver does not support changing MAC address. However, + * the hardware does not do anything with the MAC address, so the address + * which gets used on outgoing packets, and which is accepted on incoming + * packets, is completely up to us. + * + * Returns 0 on success, negative on failure. + */ +static int tile_net_set_mac_address(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EINVAL; + memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + return 0; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +/* Polling 'interrupt' - used by things like netconsole to send skbs + * without having to re-enable interrupts. It's not called while + * the interrupt routine is executing. + */ +static void tile_net_netpoll(struct net_device *dev) +{ + disable_percpu_irq(ingress_irq); + tile_net_handle_ingress_irq(ingress_irq, NULL); + enable_percpu_irq(ingress_irq, 0); +} +#endif + +static const struct net_device_ops tile_net_ops = { + .ndo_open = tile_net_open, + .ndo_stop = tile_net_stop, + .ndo_start_xmit = tile_net_tx, + .ndo_select_queue = tile_net_select_queue, + .ndo_do_ioctl = tile_net_ioctl, + .ndo_get_stats = tile_net_get_stats, + .ndo_change_mtu = tile_net_change_mtu, + .ndo_tx_timeout = tile_net_tx_timeout, + .ndo_set_mac_address = tile_net_set_mac_address, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = tile_net_netpoll, +#endif +}; + +/* The setup function. + * + * This uses ether_setup() to assign various fields in dev, including + * setting IFF_BROADCAST and IFF_MULTICAST, then sets some extra fields. + */ +static void tile_net_setup(struct net_device *dev) +{ + ether_setup(dev); + dev->netdev_ops = &tile_net_ops; + dev->watchdog_timeo = TILE_NET_TIMEOUT; + dev->features |= NETIF_F_LLTX; + dev->features |= NETIF_F_HW_CSUM; + dev->features |= NETIF_F_SG; + dev->features |= NETIF_F_TSO; + dev->mtu = 1500; +} + +/* Allocate the device structure, register the device, and obtain the + * MAC address from the hypervisor. + */ +static void tile_net_dev_init(const char *name, const uint8_t *mac) +{ + int ret; + int i; + int nz_addr = 0; + struct net_device *dev; + struct tile_net_priv *priv; + + /* HACK: Ignore "loop" links. */ + if (strncmp(name, "loop", 4) == 0) + return; + + /* Allocate the device structure. Normally, "name" is a + * template, instantiated by register_netdev(), but not for us. + */ + dev = alloc_netdev_mqs(sizeof(*priv), name, tile_net_setup, + NR_CPUS, 1); + if (!dev) { + pr_err("alloc_netdev_mqs(%s) failed\n", name); + return; + } + + /* Initialize "priv". */ + priv = netdev_priv(dev); + memset(priv, 0, sizeof(*priv)); + priv->dev = dev; + priv->channel = -1; + priv->loopify_channel = -1; + priv->echannel = -1; + + /* Get the MAC address and set it in the device struct; this must + * be done before the device is opened. If the MAC is all zeroes, + * we use a random address, since we're probably on the simulator. + */ + for (i = 0; i < 6; i++) + nz_addr |= mac[i]; + + if (nz_addr) { + memcpy(dev->dev_addr, mac, 6); + dev->addr_len = 6; + } else { + random_ether_addr(dev->dev_addr); + } + + /* Register the network device. */ + ret = register_netdev(dev); + if (ret) { + netdev_err(dev, "register_netdev failed %d\n", ret); + free_netdev(dev); + return; + } +} + +/* Per-cpu module initialization. */ +static void tile_net_init_module_percpu(void *unused) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + int my_cpu = smp_processor_id(); + + info->has_iqueue = false; + + info->my_cpu = my_cpu; + + /* Initialize the egress timer. */ + hrtimer_init(&info->egress_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + info->egress_timer.function = tile_net_handle_egress_timer; +} + +/* Module initialization. */ +static int __init tile_net_init_module(void) +{ + int i; + char name[GXIO_MPIPE_LINK_NAME_LEN]; + uint8_t mac[6]; + + pr_info("Tilera Network Driver\n"); + + mutex_init(&tile_net_devs_for_channel_mutex); + + /* Initialize each CPU. */ + on_each_cpu(tile_net_init_module_percpu, NULL, 1); + + /* Find out what devices we have, and initialize them. */ + for (i = 0; gxio_mpipe_link_enumerate_mac(i, name, mac) >= 0; i++) + tile_net_dev_init(name, mac); + + if (!network_cpus_init()) + network_cpus_map = *cpu_online_mask; + + return 0; +} + +module_init(tile_net_init_module); -- cgit v1.2.3-59-g8ed1b From 8a93664df90db983cfede122f9b4ddb3a8284e52 Mon Sep 17 00:00:00 2001 From: Weiping Pan Date: Sun, 10 Jun 2012 23:00:20 +0000 Subject: bonding:record primary when modify it via sysfs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we modify primary via sysfs and it is not a valid slave, we should record it for future use, and this behavior is the same with bond_check_params(). Signed-off-by: Weiping Pan Acked-by: Nicolas de Pesloüan Signed-off-by: Jay Vosburgh Signed-off-by: David S. Miller --- drivers/net/bonding/bond_sysfs.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index aef42f045320..485bedb8278c 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -1082,8 +1082,12 @@ static ssize_t bonding_store_primary(struct device *d, } } - pr_info("%s: Unable to set %.*s as primary slave.\n", - bond->dev->name, (int)strlen(buf) - 1, buf); + strncpy(bond->params.primary, ifname, IFNAMSIZ); + bond->params.primary[IFNAMSIZ - 1] = 0; + + pr_info("%s: Recording %s as primary, " + "but it has not been enslaved to %s yet.\n", + bond->dev->name, ifname, bond->dev->name); out: write_unlock_bh(&bond->curr_slave_lock); read_unlock(&bond->lock); -- cgit v1.2.3-59-g8ed1b From 5ee31c6898ea5537fcea160999d60dc63bc0c305 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Jun 2012 06:03:51 +0000 Subject: bonding: Fix corrupted queue_mapping In the transmit path of the bonding driver, skb->cb is used to stash the skb->queue_mapping so that the bonding device can set its own queue mapping. This value becomes corrupted since the skb->cb is also used in __dev_xmit_skb. When transmitting through bonding driver, bond_select_queue is called from dev_queue_xmit. In bond_select_queue the original skb->queue_mapping is copied into skb->cb (via bond_queue_mapping) and skb->queue_mapping is overwritten with the bond driver queue. Subsequently in dev_queue_xmit, __dev_xmit_skb is called which writes the packet length into skb->cb, thereby overwriting the stashed queue mappping. In bond_dev_queue_xmit (called from hard_start_xmit), the queue mapping for the skb is set to the stashed value which is now the skb length and hence is an invalid queue for the slave device. If we want to save skb->queue_mapping into skb->cb[], best place is to add a field in struct qdisc_skb_cb, to make sure it wont conflict with other layers (eg : Qdiscc, Infiniband...) This patchs also makes sure (struct qdisc_skb_cb)->data is aligned on 8 bytes : netem qdisc for example assumes it can store an u64 in it, without misalignment penalty. Note : we only have 20 bytes left in (struct qdisc_skb_cb)->data[]. The largest user is CHOKe and it fills it. Based on a previous patch from Tom Herbert. Signed-off-by: Eric Dumazet Reported-by: Tom Herbert Cc: John Fastabend Cc: Roland Dreier Acked-by: Neil Horman Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 9 +++++---- include/net/sch_generic.h | 7 +++++-- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2ee8cf9e8a3b..b9c2ae62166d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -76,6 +76,7 @@ #include #include #include +#include #include "bonding.h" #include "bond_3ad.h" #include "bond_alb.h" @@ -381,8 +382,6 @@ struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr) return next; } -#define bond_queue_mapping(skb) (*(u16 *)((skb)->cb)) - /** * bond_dev_queue_xmit - Prepare skb for xmit. * @@ -395,7 +394,9 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, { skb->dev = slave_dev; - skb->queue_mapping = bond_queue_mapping(skb); + BUILD_BUG_ON(sizeof(skb->queue_mapping) != + sizeof(qdisc_skb_cb(skb)->bond_queue_mapping)); + skb->queue_mapping = qdisc_skb_cb(skb)->bond_queue_mapping; if (unlikely(netpoll_tx_running(slave_dev))) bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); @@ -4171,7 +4172,7 @@ static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb) /* * Save the original txq to restore before passing to the driver */ - bond_queue_mapping(skb) = skb->queue_mapping; + qdisc_skb_cb(skb)->bond_queue_mapping = skb->queue_mapping; if (unlikely(txq >= dev->real_num_tx_queues)) { do { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 55ce96b53b09..9d7d54a00e63 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -220,13 +220,16 @@ struct tcf_proto { struct qdisc_skb_cb { unsigned int pkt_len; - unsigned char data[24]; + u16 bond_queue_mapping; + u16 _pad; + unsigned char data[20]; }; static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; - BUILD_BUG_ON(sizeof(skb->cb) < sizeof(unsigned int) + sz); + + BUILD_BUG_ON(sizeof(skb->cb) < offsetof(struct qdisc_skb_cb, data) + sz); BUILD_BUG_ON(sizeof(qcb->data) < sz); } -- cgit v1.2.3-59-g8ed1b