From ce7240e445303de3ca66e6d08f17a2ec278a5bf6 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 17 Jul 2012 17:06:20 +0100 Subject: 8250: three way resolve of the 8250 diffs This resolves the differences between the original 8250 patch, the revised 8250 patch and the independant clean up of the octeon driver (to use platform devices properly yay!) Signed-off-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/sgi/ioc3-eth.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index ac149d99f78f..fcb5b0e0f260 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -1147,15 +1147,17 @@ static void __devinit ioc3_8250_register(struct ioc3_uartregs __iomem *uart) { #define COSMISC_CONSTANT 6 - struct uart_port port = { - .irq = 0, - .flags = UPF_SKIP_TEST | UPF_BOOT_AUTOCONF, - .iotype = UPIO_MEM, - .regshift = 0, - .uartclk = (22000000 << 1) / COSMISC_CONSTANT, - - .membase = (unsigned char __iomem *) uart, - .mapbase = (unsigned long) uart, + struct uart_8250_port port = { + .port = { + .irq = 0, + .flags = UPF_SKIP_TEST | UPF_BOOT_AUTOCONF, + .iotype = UPIO_MEM, + .regshift = 0, + .uartclk = (22000000 << 1) / COSMISC_CONSTANT, + + .membase = (unsigned char __iomem *) uart, + .mapbase = (unsigned long) uart, + } }; unsigned char lcr; @@ -1164,7 +1166,7 @@ static void __devinit ioc3_8250_register(struct ioc3_uartregs __iomem *uart) uart->iu_scr = COSMISC_CONSTANT, uart->iu_lcr = lcr; uart->iu_lcr; - serial8250_register_port(&port); + serial8250_register_8250_port(&port); } static void __devinit ioc3_serial_probe(struct pci_dev *pdev, struct ioc3 *ioc3) -- cgit v1.2.3 From f07454fe2d6c233366a79aa13a638f69755745a5 Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Mon, 30 Jul 2012 10:17:13 +0000 Subject: drivers: net: ethernet: cpsw: Add SOC dependency support for cpsw dependent modules cpsw is dependent on davinci_cpdma and davinci_mdio, so adding SOC support for dependent modules Signed-off-by: Mugunthan V N Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 1b173a6145d6..b26cbda5efa9 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -32,7 +32,7 @@ config TI_DAVINCI_EMAC config TI_DAVINCI_MDIO tristate "TI DaVinci MDIO Support" - depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 ) + depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 || SOC_AM33XX ) select PHYLIB ---help--- This driver supports TI's DaVinci MDIO module. @@ -42,7 +42,7 @@ config TI_DAVINCI_MDIO config TI_DAVINCI_CPDMA tristate "TI DaVinci CPDMA Support" - depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 ) + depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 || SOC_AM33XX ) ---help--- This driver supports TI's DaVinci CPDMA dma engine. -- cgit v1.2.3 From 2eb32b0a6f9d73fafc6b2c00ac0b705de13ae143 Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Mon, 30 Jul 2012 10:17:14 +0000 Subject: drivers: net: ethernet: cpsw: Add device tree support to CPSW This patch adds device tree support for cpsw driver Signed-off-by: Mugunthan V N Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/cpsw.txt | 104 +++++++++++++++ drivers/net/ethernet/ti/cpsw.c | 174 ++++++++++++++++++++++++- 2 files changed, 272 insertions(+), 6 deletions(-) create mode 100644 Documentation/devicetree/bindings/net/cpsw.txt (limited to 'drivers/net/ethernet') diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt new file mode 100644 index 000000000000..acca48c4246d --- /dev/null +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -0,0 +1,104 @@ +TI SoC Ethernet Switch Controller Device Tree Bindings +------------------------------------------------------ + +Required properties: +- compatible : Should be "ti,cpsw" +- reg : physical base address and size of the cpsw + registers map +- interrupts : property with a value describing the interrupt + number +- interrupt-parent : The parent interrupt controller +- cpdma_channels : Specifies number of channels in CPDMA +- host_port_no : Specifies host port shift +- cpdma_reg_ofs : Specifies CPDMA submodule register offset +- ale_reg_ofs : Specifies ALE submodule register offset +- ale_entries : Specifies No of entries ALE can hold +- host_port_reg_ofs : Specifies host port register offset +- hw_stats_reg_ofs : Specifies hardware statistics register offset +- bd_ram_ofs : Specifies internal desciptor RAM offset +- bd_ram_size : Specifies internal descriptor RAM size +- rx_descs : Specifies number of Rx descriptors +- mac_control : Specifies Default MAC control register content + for the specific platform +- slaves : Specifies number for slaves +- slave_reg_ofs : Specifies slave register offset +- sliver_reg_ofs : Specifies slave sliver register offset +- phy_id : Specifies slave phy id +- mac-address : Specifies slave MAC address + +Optional properties: +- ti,hwmods : Must be "cpgmac0" +- no_bd_ram : Must be 0 or 1 + +Note: "ti,hwmods" field is used to fetch the base address and irq +resources from TI, omap hwmod data base during device registration. +Future plan is to migrate hwmod data base contents into device tree +blob so that, all the required data will be used from device tree dts +file. + +Examples: + + mac: ethernet@4A100000 { + compatible = "ti,cpsw"; + reg = <0x4A100000 0x1000>; + interrupts = <55 0x4>; + interrupt-parent = <&intc>; + cpdma_channels = 8; + host_port_no = 0; + cpdma_reg_ofs = 0x800; + ale_reg_ofs = 0xd00; + ale_entries = 1024; + host_port_reg_ofs = 0x108; + hw_stats_reg_ofs = 0x900; + bd_ram_ofs = 0x2000; + bd_ram_size = 0x2000; + no_bd_ram = 0; + rx_descs = 64; + mac_control = 0x20; + slaves = 2; + slave@0 { + slave_reg_ofs = 0x208; + sliver_reg_ofs = 0xd80; + phy_id = "davinci_mdio-0:00" + mac-address = [00 04 9F 01 1B B8]; + }; + slave@1 { + slave_reg_ofs = 0x208; + sliver_reg_ofs = 0xd80; + phy_id = "davinci_mdio-0:01" + mac-address = [00 04 9F 01 1B B9]; + }; + }; + +(or) + + mac: ethernet@4A100000 { + compatible = "ti,cpsw"; + ti,hwmods = "cpgmac0"; + cpdma_channels = 8; + host_port_no = 0; + cpdma_reg_ofs = 0x800; + ale_reg_ofs = 0xd00; + ale_entries = 1024; + host_port_reg_ofs = 0x108; + hw_stats_reg_ofs = 0x900; + bd_ram_ofs = 0x2000; + bd_ram_size = 0x2000; + no_bd_ram = 0; + rx_descs = 64; + mac_control = 0x20; + slaves = 2; + slave@0 { + slave_reg_ofs = 0x208; + sliver_reg_ofs = 0xd80; + phy_id = "davinci_mdio-0:00" + mac-address = [00 04 9F 01 1B B8]; + }; + slave@1 { + slave_reg_ofs = 0x208; + sliver_reg_ofs = 0xd80; + phy_id = "davinci_mdio-0:01" + mac-address = [00 04 9F 01 1B B9]; + }; + + }; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 1e5d85b06e71..0cbc0e59252c 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -28,6 +28,9 @@ #include #include #include +#include +#include +#include #include @@ -709,6 +712,158 @@ static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv) slave->sliver = regs + data->sliver_reg_ofs; } +static int cpsw_probe_dt(struct cpsw_platform_data *data, + struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct device_node *slave_node; + int i = 0, ret; + u32 prop; + + if (!node) + return -EINVAL; + + if (of_property_read_u32(node, "slaves", &prop)) { + pr_err("Missing slaves property in the DT.\n"); + return -EINVAL; + } + data->slaves = prop; + + data->slave_data = kzalloc(sizeof(struct cpsw_slave_data) * + data->slaves, GFP_KERNEL); + if (!data->slave_data) { + pr_err("Could not allocate slave memory.\n"); + return -EINVAL; + } + + data->no_bd_ram = of_property_read_bool(node, "no_bd_ram"); + + if (of_property_read_u32(node, "cpdma_channels", &prop)) { + pr_err("Missing cpdma_channels property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->channels = prop; + + if (of_property_read_u32(node, "host_port_no", &prop)) { + pr_err("Missing host_port_no property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->host_port_num = prop; + + if (of_property_read_u32(node, "cpdma_reg_ofs", &prop)) { + pr_err("Missing cpdma_reg_ofs property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->cpdma_reg_ofs = prop; + + if (of_property_read_u32(node, "cpdma_sram_ofs", &prop)) { + pr_err("Missing cpdma_sram_ofs property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->cpdma_sram_ofs = prop; + + if (of_property_read_u32(node, "ale_reg_ofs", &prop)) { + pr_err("Missing ale_reg_ofs property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->ale_reg_ofs = prop; + + if (of_property_read_u32(node, "ale_entries", &prop)) { + pr_err("Missing ale_entries property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->ale_entries = prop; + + if (of_property_read_u32(node, "host_port_reg_ofs", &prop)) { + pr_err("Missing host_port_reg_ofs property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->host_port_reg_ofs = prop; + + if (of_property_read_u32(node, "hw_stats_reg_ofs", &prop)) { + pr_err("Missing hw_stats_reg_ofs property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->hw_stats_reg_ofs = prop; + + if (of_property_read_u32(node, "bd_ram_ofs", &prop)) { + pr_err("Missing bd_ram_ofs property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->bd_ram_ofs = prop; + + if (of_property_read_u32(node, "bd_ram_size", &prop)) { + pr_err("Missing bd_ram_size property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->bd_ram_size = prop; + + if (of_property_read_u32(node, "rx_descs", &prop)) { + pr_err("Missing rx_descs property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->rx_descs = prop; + + if (of_property_read_u32(node, "mac_control", &prop)) { + pr_err("Missing mac_control property in the DT.\n"); + ret = -EINVAL; + goto error_ret; + } + data->mac_control = prop; + + for_each_child_of_node(node, slave_node) { + struct cpsw_slave_data *slave_data = data->slave_data + i; + const char *phy_id = NULL; + const void *mac_addr = NULL; + + if (of_property_read_string(slave_node, "phy_id", &phy_id)) { + pr_err("Missing slave[%d] phy_id property\n", i); + ret = -EINVAL; + goto error_ret; + } + slave_data->phy_id = phy_id; + + if (of_property_read_u32(slave_node, "slave_reg_ofs", &prop)) { + pr_err("Missing slave[%d] slave_reg_ofs property\n", i); + ret = -EINVAL; + goto error_ret; + } + slave_data->slave_reg_ofs = prop; + + if (of_property_read_u32(slave_node, "sliver_reg_ofs", + &prop)) { + pr_err("Missing slave[%d] sliver_reg_ofs property\n", + i); + ret = -EINVAL; + goto error_ret; + } + slave_data->sliver_reg_ofs = prop; + + mac_addr = of_get_mac_address(slave_node); + if (mac_addr) + memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); + + i++; + } + + return 0; + +error_ret: + kfree(data->slave_data); + return ret; +} + static int __devinit cpsw_probe(struct platform_device *pdev) { struct cpsw_platform_data *data = pdev->dev.platform_data; @@ -720,11 +875,6 @@ static int __devinit cpsw_probe(struct platform_device *pdev) struct resource *res; int ret = 0, i, k = 0; - if (!data) { - pr_err("platform data missing\n"); - return -ENODEV; - } - ndev = alloc_etherdev(sizeof(struct cpsw_priv)); if (!ndev) { pr_err("error allocating net_device\n"); @@ -734,13 +884,19 @@ static int __devinit cpsw_probe(struct platform_device *pdev) platform_set_drvdata(pdev, ndev); priv = netdev_priv(ndev); spin_lock_init(&priv->lock); - priv->data = *data; priv->pdev = pdev; priv->ndev = ndev; priv->dev = &ndev->dev; priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); priv->rx_packet_max = max(rx_packet_max, 128); + if (cpsw_probe_dt(&priv->data, pdev)) { + pr_err("cpsw: platform data missing\n"); + ret = -ENODEV; + goto clean_ndev_ret; + } + data = &priv->data; + if (is_valid_ether_addr(data->slave_data[0].mac_addr)) { memcpy(priv->mac_addr, data->slave_data[0].mac_addr, ETH_ALEN); pr_info("Detected MACID = %pM", priv->mac_addr); @@ -996,11 +1152,17 @@ static const struct dev_pm_ops cpsw_pm_ops = { .resume = cpsw_resume, }; +static const struct of_device_id cpsw_of_mtable[] = { + { .compatible = "ti,cpsw", }, + { /* sentinel */ }, +}; + static struct platform_driver cpsw_driver = { .driver = { .name = "cpsw", .owner = THIS_MODULE, .pm = &cpsw_pm_ops, + .of_match_table = of_match_ptr(cpsw_of_mtable), }, .probe = cpsw_probe, .remove = __devexit_p(cpsw_remove), -- cgit v1.2.3 From ec03e6a89e5168c92581a769681207c29ad2030f Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Mon, 6 Aug 2012 05:05:57 +0000 Subject: drivers: net: ethernet: davince_mdio: device tree implementation device tree implementation for davinci mdio driver Signed-off-by: Mugunthan V N Signed-off-by: David S. Miller --- .../devicetree/bindings/net/davinci-mdio.txt | 33 +++++++++++++++++ drivers/net/ethernet/ti/davinci_mdio.c | 41 +++++++++++++++++++--- 2 files changed, 70 insertions(+), 4 deletions(-) create mode 100644 Documentation/devicetree/bindings/net/davinci-mdio.txt (limited to 'drivers/net/ethernet') diff --git a/Documentation/devicetree/bindings/net/davinci-mdio.txt b/Documentation/devicetree/bindings/net/davinci-mdio.txt new file mode 100644 index 000000000000..72efaaf764f7 --- /dev/null +++ b/Documentation/devicetree/bindings/net/davinci-mdio.txt @@ -0,0 +1,33 @@ +TI SoC Davinci MDIO Controller Device Tree Bindings +--------------------------------------------------- + +Required properties: +- compatible : Should be "ti,davinci_mdio" +- reg : physical base address and size of the davinci mdio + registers map +- bus_freq : Mdio Bus frequency + +Optional properties: +- ti,hwmods : Must be "davinci_mdio" + +Note: "ti,hwmods" field is used to fetch the base address and irq +resources from TI, omap hwmod data base during device registration. +Future plan is to migrate hwmod data base contents into device tree +blob so that, all the required data will be used from device tree dts +file. + +Examples: + + mdio: davinci_mdio@4A101000 { + compatible = "ti,cpsw"; + reg = <0x4A101000 0x1000>; + bus_freq = <1000000>; + }; + +(or) + + mdio: davinci_mdio@4A101000 { + compatible = "ti,cpsw"; + ti,hwmods = "davinci_mdio"; + bus_freq = <1000000>; + }; diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c index cd7ee204e94a..573f3be5f421 100644 --- a/drivers/net/ethernet/ti/davinci_mdio.c +++ b/drivers/net/ethernet/ti/davinci_mdio.c @@ -36,6 +36,8 @@ #include #include #include +#include +#include /* * This timeout definition is a worst-case ultra defensive measure against @@ -289,6 +291,25 @@ static int davinci_mdio_write(struct mii_bus *bus, int phy_id, return 0; } +static int davinci_mdio_probe_dt(struct mdio_platform_data *data, + struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + u32 prop; + + if (!node) + return -EINVAL; + + if (of_property_read_u32(node, "bus_freq", &prop)) { + pr_err("Missing bus_freq property in the DT.\n"); + return -EINVAL; + } + data->bus_freq = prop; + + return 0; +} + + static int __devinit davinci_mdio_probe(struct platform_device *pdev) { struct mdio_platform_data *pdata = pdev->dev.platform_data; @@ -304,8 +325,6 @@ static int __devinit davinci_mdio_probe(struct platform_device *pdev) return -ENOMEM; } - data->pdata = pdata ? (*pdata) : default_pdata; - data->bus = mdiobus_alloc(); if (!data->bus) { dev_err(dev, "failed to alloc mii bus\n"); @@ -313,14 +332,22 @@ static int __devinit davinci_mdio_probe(struct platform_device *pdev) goto bail_out; } + if (dev->of_node) { + if (davinci_mdio_probe_dt(&data->pdata, pdev)) + data->pdata = default_pdata; + snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s", pdev->name); + } else { + data->pdata = pdata ? (*pdata) : default_pdata; + snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s-%x", + pdev->name, pdev->id); + } + data->bus->name = dev_name(dev); data->bus->read = davinci_mdio_read, data->bus->write = davinci_mdio_write, data->bus->reset = davinci_mdio_reset, data->bus->parent = dev; data->bus->priv = data; - snprintf(data->bus->id, MII_BUS_ID_SIZE, "%s-%x", - pdev->name, pdev->id); pm_runtime_enable(&pdev->dev); pm_runtime_get_sync(&pdev->dev); @@ -454,11 +481,17 @@ static const struct dev_pm_ops davinci_mdio_pm_ops = { .resume = davinci_mdio_resume, }; +static const struct of_device_id davinci_mdio_of_mtable[] = { + { .compatible = "ti,davinci_mdio", }, + { /* sentinel */ }, +}; + static struct platform_driver davinci_mdio_driver = { .driver = { .name = "davinci_mdio", .owner = THIS_MODULE, .pm = &davinci_mdio_pm_ops, + .of_match_table = of_match_ptr(davinci_mdio_of_mtable), }, .probe = davinci_mdio_probe, .remove = __devexit_p(davinci_mdio_remove), -- cgit v1.2.3 From afaa9459de639591ff3318fd215a813c8d794759 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:08:12 +0000 Subject: ixgbe: Remove code that was initializing Rx page offset This change reverts an earlier patch that introduced ixgbe_init_rx_page_offset. The idea behind the function was to provide some variation in the starting offset for the page in order to reduce hot-spots in the cache. However it doesn't appear to provide any significant benefit in the testing I have done. It has however been a source of several bugs, and it blocks us from being able to use 2K fragments on larger page sizes. So the decision I made was to remove it. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Peter P Waskiewicz Jr --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 27 +-------------------------- 1 file changed, 1 insertion(+), 26 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 4326f74f7137..f7351c6fa3b5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1167,7 +1167,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, } bi->dma = dma; - bi->page_offset ^= ixgbe_rx_bufsz(rx_ring); + bi->page_offset = 0; return true; } @@ -4129,27 +4129,6 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0)); } -/** - * ixgbe_init_rx_page_offset - initialize page offset values for Rx buffers - * @rx_ring: ring to setup - * - * On many IA platforms the L1 cache has a critical stride of 4K, this - * results in each receive buffer starting in the same cache set. To help - * reduce the pressure on this cache set we can interleave the offsets so - * that only every other buffer will be in the same cache set. - **/ -static void ixgbe_init_rx_page_offset(struct ixgbe_ring *rx_ring) -{ - struct ixgbe_rx_buffer *rx_buffer = rx_ring->rx_buffer_info; - u16 i; - - for (i = 0; i < rx_ring->count; i += 2) { - rx_buffer[0].page_offset = 0; - rx_buffer[1].page_offset = ixgbe_rx_bufsz(rx_ring); - rx_buffer = &rx_buffer[2]; - } -} - /** * ixgbe_clean_rx_ring - Free Rx Buffers per Queue * @rx_ring: ring to free buffers from @@ -4195,8 +4174,6 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; memset(rx_ring->rx_buffer_info, 0, size); - ixgbe_init_rx_page_offset(rx_ring); - /* Zero out the descriptor ring */ memset(rx_ring->desc, 0, rx_ring->size); @@ -4646,8 +4623,6 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring) rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; - ixgbe_init_rx_page_offset(rx_ring); - return 0; err: vfree(rx_ring->rx_buffer_info); -- cgit v1.2.3 From 0549ae20b77d411aefb5271c2c494b9c3f02d972 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:08:18 +0000 Subject: ixgbe: combine ixgbe_add_rx_frag and ixgbe_can_reuse_page This patch combines ixgbe_add_rx_frag and ixgbe_can_reuse_page into a single function. The main motivation behind this is to make better use of the values so that we don't have to load them from memory and into registers twice. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Peter P Waskiewicz Jr --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 73 +++++++++++++-------------- 1 file changed, 34 insertions(+), 39 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f7351c6fa3b5..6a8c48443676 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1559,34 +1559,18 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, return false; } -/** - * ixgbe_can_reuse_page - determine if we can reuse a page - * @rx_buffer: pointer to rx_buffer containing the page we want to reuse - * - * Returns true if page can be reused in another Rx buffer - **/ -static inline bool ixgbe_can_reuse_page(struct ixgbe_rx_buffer *rx_buffer) -{ - struct page *page = rx_buffer->page; - - /* if we are only owner of page and it is local we can reuse it */ - return likely(page_count(page) == 1) && - likely(page_to_nid(page) == numa_node_id()); -} - /** * ixgbe_reuse_rx_page - page flip buffer and store it back on the ring * @rx_ring: rx descriptor ring to store buffers on * @old_buff: donor buffer to have page reused * - * Syncronizes page for reuse by the adapter + * Synchronizes page for reuse by the adapter **/ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *old_buff) { struct ixgbe_rx_buffer *new_buff; u16 nta = rx_ring->next_to_alloc; - u16 bufsz = ixgbe_rx_bufsz(rx_ring); new_buff = &rx_ring->rx_buffer_info[nta]; @@ -1597,17 +1581,13 @@ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring, /* transfer page from old buffer to new buffer */ new_buff->page = old_buff->page; new_buff->dma = old_buff->dma; - - /* flip page offset to other buffer and store to new_buff */ - new_buff->page_offset = old_buff->page_offset ^ bufsz; + new_buff->page_offset = old_buff->page_offset; /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma, - new_buff->page_offset, bufsz, + new_buff->page_offset, + ixgbe_rx_bufsz(rx_ring), DMA_FROM_DEVICE); - - /* bump ref count on page before it is given to the stack */ - get_page(new_buff->page); } /** @@ -1617,20 +1597,38 @@ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring, * @rx_desc: descriptor containing length of buffer written by hardware * @skb: sk_buff to place the data into * - * This function is based on skb_add_rx_frag. I would have used that - * function however it doesn't handle the truesize case correctly since we - * are allocating more memory than might be used for a single receive. + * This function will add the data contained in rx_buffer->page to the skb. + * This is done either through a direct copy if the data in the buffer is + * less than the skb header size, otherwise it will just attach the page as + * a frag to the skb. + * + * The function will then update the page offset if necessary and return + * true if the buffer can be reused by the adapter. **/ -static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, +static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - struct sk_buff *skb, int size) + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { - skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, - rx_buffer->page, rx_buffer->page_offset, - size); - skb->len += size; - skb->data_len += size; - skb->truesize += ixgbe_rx_bufsz(rx_ring); + struct page *page = rx_buffer->page; + unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); + unsigned int truesize = ixgbe_rx_bufsz(rx_ring); + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + rx_buffer->page_offset, size, truesize); + + /* if we are only owner of page and it is local we can reuse it */ + if (unlikely(page_count(page) != 1) || + unlikely(page_to_nid(page) != numa_node_id())) + return false; + + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= truesize; + + /* bump ref count on page before it is given to the stack */ + get_page(page); + + return true; } /** @@ -1731,10 +1729,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } /* pull page into skb */ - ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, - le16_to_cpu(rx_desc->wb.upper.length)); - - if (ixgbe_can_reuse_page(rx_buffer)) { + if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { /* hand second half of page back to the ring */ ixgbe_reuse_rx_page(rx_ring, rx_buffer); } else if (IXGBE_CB(skb)->dma == rx_buffer->dma) { -- cgit v1.2.3 From 09816fbea96ae81eac82dee2d52f29ea7241678d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:08:23 +0000 Subject: ixgbe: Only use double buffering if page size is less than 8K This change makes it so that we do not use double buffering if the page size is larger than 4K. Instead we will simply walk through the page using up to 3K per receive, and if we receive less than we only move the offset by that amount. We will free the page when there is no longer any space left that we can use instead of checking the page count to see if we can cycle back to the start. The main motivation behind this is to avoid the unnecessary truesize cost for using a half page when most packets are 2K or smaller. With this new approach the largest possible truesize for a page fragment will be 3K when PAGE_SIZE is larger than 4K. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Peter P Waskiewicz Jr --- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 24 ++++++++++++---- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 40 ++++++++++++++++++--------- 2 files changed, 45 insertions(+), 19 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index b9623e9ea895..fd2bc697a92b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -78,6 +78,9 @@ /* Supported Rx Buffer Sizes */ #define IXGBE_RXBUFFER_256 256 /* Used for skb receive header */ +#define IXGBE_RXBUFFER_2K 2048 +#define IXGBE_RXBUFFER_3K 3072 +#define IXGBE_RXBUFFER_4K 4096 #define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ /* @@ -293,16 +296,25 @@ struct ixgbe_ring_feature { * this is twice the size of a half page we need to double the page order * for FCoE enabled Rx queues. */ -#if defined(IXGBE_FCOE) && (PAGE_SIZE < 8192) -static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring) +static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring) { - return test_bit(__IXGBE_RX_FCOE, &ring->state) ? 1 : 0; +#ifdef IXGBE_FCOE + if (test_bit(__IXGBE_RX_FCOE, &ring->state)) + return (PAGE_SIZE < 8192) ? IXGBE_RXBUFFER_4K : + IXGBE_RXBUFFER_3K; +#endif + return IXGBE_RXBUFFER_2K; } -#else -#define ixgbe_rx_pg_order(_ring) 0 + +static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring) +{ +#ifdef IXGBE_FCOE + if (test_bit(__IXGBE_RX_FCOE, &ring->state)) + return (PAGE_SIZE < 8192) ? 1 : 0; #endif + return 0; +} #define ixgbe_rx_pg_size(_ring) (PAGE_SIZE << ixgbe_rx_pg_order(_ring)) -#define ixgbe_rx_bufsz(_ring) ((PAGE_SIZE / 2) << ixgbe_rx_pg_order(_ring)) struct ixgbe_ring_container { struct ixgbe_ring *ring; /* pointer to linked list of rings */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6a8c48443676..9305e9a5a761 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1612,21 +1612,45 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, { struct page *page = rx_buffer->page; unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); +#if (PAGE_SIZE < 8192) unsigned int truesize = ixgbe_rx_bufsz(rx_ring); +#else + unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); + unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) - + ixgbe_rx_bufsz(rx_ring); +#endif skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, rx_buffer->page_offset, size, truesize); - /* if we are only owner of page and it is local we can reuse it */ - if (unlikely(page_count(page) != 1) || - unlikely(page_to_nid(page) != numa_node_id())) + /* avoid re-using remote pages */ + if (unlikely(page_to_nid(page) != numa_node_id())) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely(page_count(page) != 1)) return false; /* flip page offset to other buffer */ rx_buffer->page_offset ^= truesize; + /* + * since we are the only owner of the page and we need to + * increment it, just set the value to 2 in order to avoid + * an unecessary locked operation + */ + atomic_set(&page->_count, 2); +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += truesize; + + if (rx_buffer->page_offset > last_offset) + return false; + /* bump ref count on page before it is given to the stack */ get_page(page); +#endif return true; } @@ -2863,11 +2887,7 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; /* configure the packet buffer length */ -#if PAGE_SIZE > IXGBE_MAX_RXBUFFER - srrctl |= IXGBE_MAX_RXBUFFER >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; -#else srrctl |= ixgbe_rx_bufsz(rx_ring) >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; -#endif /* configure descriptor type */ srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; @@ -2975,13 +2995,7 @@ static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter, * total size of max desc * buf_len is not greater * than 65536 */ -#if (PAGE_SIZE <= 8192) rscctrl |= IXGBE_RSCCTL_MAXDESC_16; -#elif (PAGE_SIZE <= 16384) - rscctrl |= IXGBE_RSCCTL_MAXDESC_8; -#else - rscctrl |= IXGBE_RSCCTL_MAXDESC_4; -#endif IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(reg_idx), rscctrl); } -- cgit v1.2.3 From 42073d91a214587717c36a697436bad0f60c4384 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:08:28 +0000 Subject: ixgbe: Have the CPU take ownership of the buffers sooner This patch makes it so that we will always have ownership of the buffers by the time we get to ixgbe_add_rx_frag. This is necessary as I am planning to add a copy-break to ixgbe_add_rx_frag and in order for that to function correctly we need the CPU to have ownership of the buffer. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Peter P Waskiewicz Jr --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 52 +++++++++++++++++++-------- 1 file changed, 38 insertions(+), 14 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 9305e9a5a761..b0020fcf0505 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1457,6 +1457,36 @@ static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring, return true; } +/** + * ixgbe_dma_sync_frag - perform DMA sync for first frag of SKB + * @rx_ring: rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being updated + * + * This function provides a basic DMA sync up for the first fragment of an + * skb. The reason for doing this is that the first fragment cannot be + * unmapped until we have reached the end of packet descriptor for a buffer + * chain. + */ +static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, + struct sk_buff *skb) +{ + /* if the page was released unmap it, else just sync our portion */ + if (unlikely(IXGBE_CB(skb)->page_released)) { + dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma, + ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE); + IXGBE_CB(skb)->page_released = false; + } else { + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + + dma_sync_single_range_for_cpu(rx_ring->dev, + IXGBE_CB(skb)->dma, + frag->page_offset, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + } + IXGBE_CB(skb)->dma = 0; +} + /** * ixgbe_cleanup_headers - Correct corrupted or empty headers * @rx_ring: rx descriptor ring packet is being transacted on @@ -1484,20 +1514,6 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, unsigned char *va; unsigned int pull_len; - /* if the page was released unmap it, else just sync our portion */ - if (unlikely(IXGBE_CB(skb)->page_released)) { - dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma, - ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE); - IXGBE_CB(skb)->page_released = false; - } else { - dma_sync_single_range_for_cpu(rx_ring->dev, - IXGBE_CB(skb)->dma, - frag->page_offset, - ixgbe_rx_bufsz(rx_ring), - DMA_FROM_DEVICE); - } - IXGBE_CB(skb)->dma = 0; - /* verify that the packet does not have any known errors */ if (unlikely(ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FRAME_ERR_MASK) && @@ -1742,8 +1758,16 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, * after the writeback. Only unmap it when EOP is * reached */ + if (likely(ixgbe_test_staterr(rx_desc, + IXGBE_RXD_STAT_EOP))) + goto dma_sync; + IXGBE_CB(skb)->dma = rx_buffer->dma; } else { + if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) + ixgbe_dma_sync_frag(rx_ring, skb); + +dma_sync: /* we are reusing so sync this buffer for CPU use */ dma_sync_single_range_for_cpu(rx_ring->dev, rx_buffer->dma, -- cgit v1.2.3 From 19861ce24f2ea9d9db7b96814de9ca8d522cbe40 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:08:33 +0000 Subject: ixgbe: Make pull tail function separate from rest of cleanup_headers This change creates a separate function for functionality similar to pskb_pull_tail. The main motivation for moving it to a separate function is so that later I can just skip this function in the case where we have already copied the buffer into skb->head. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Peter P Waskiewicz Jr --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 94 ++++++++++++++++----------- 1 file changed, 57 insertions(+), 37 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index b0020fcf0505..d9269737409a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1457,6 +1457,61 @@ static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring, return true; } +/** + * ixgbe_pull_tail - ixgbe specific version of skb_pull_tail + * @rx_ring: rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being adjusted + * + * This function is an ixgbe specific version of __pskb_pull_tail. The + * main difference between this version and the original function is that + * this function can make several assumptions about the state of things + * that allow for significant optimizations versus the standard function. + * As a result we can do things like drop a frag and maintain an accurate + * truesize for the skb. + */ +static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, + struct sk_buff *skb) +{ + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + unsigned char *va; + unsigned int pull_len; + + /* + * it is valid to use page_address instead of kmap since we are + * working with pages allocated out of the lomem pool per + * alloc_page(GFP_ATOMIC) + */ + va = skb_frag_address(frag); + + /* + * we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = skb_frag_size(frag); + if (pull_len > IXGBE_RX_HDR_SIZE) + pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); + + /* update all of the pointers */ + skb_frag_size_sub(frag, pull_len); + frag->page_offset += pull_len; + skb->data_len -= pull_len; + skb->tail += pull_len; + + /* + * if we sucked the frag empty then we should free it, + * if there are other frags here something is screwed up in hardware + */ + if (skb_frag_size(frag) == 0) { + BUG_ON(skb_shinfo(skb)->nr_frags != 1); + skb_shinfo(skb)->nr_frags = 0; + __skb_frag_unref(frag); + skb->truesize -= ixgbe_rx_bufsz(rx_ring); + } +} + /** * ixgbe_dma_sync_frag - perform DMA sync for first frag of SKB * @rx_ring: rx descriptor ring packet is being transacted on @@ -1509,10 +1564,7 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; struct net_device *netdev = rx_ring->netdev; - unsigned char *va; - unsigned int pull_len; /* verify that the packet does not have any known errors */ if (unlikely(ixgbe_test_staterr(rx_desc, @@ -1522,40 +1574,8 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, return true; } - /* - * it is valid to use page_address instead of kmap since we are - * working with pages allocated out of the lomem pool per - * alloc_page(GFP_ATOMIC) - */ - va = skb_frag_address(frag); - - /* - * we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = skb_frag_size(frag); - if (pull_len > IXGBE_RX_HDR_SIZE) - pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); - - /* update all of the pointers */ - skb_frag_size_sub(frag, pull_len); - frag->page_offset += pull_len; - skb->data_len -= pull_len; - skb->tail += pull_len; - - /* - * if we sucked the frag empty then we should free it, - * if there are other frags here something is screwed up in hardware - */ - if (skb_frag_size(frag) == 0) { - BUG_ON(skb_shinfo(skb)->nr_frags != 1); - skb_shinfo(skb)->nr_frags = 0; - __skb_frag_unref(frag); - skb->truesize -= ixgbe_rx_bufsz(rx_ring); - } + /* place header in linear portion of buffer */ + ixgbe_pull_tail(rx_ring, skb); #ifdef IXGBE_FCOE /* do not attempt to pad FCoE Frames as this will disrupt DDP */ -- cgit v1.2.3 From cf3fe7aca03e14db107d649c5699a48bec054583 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:08:39 +0000 Subject: ixgbe: Copybreak sooner to avoid get_page/put_page and offset change overhead This change makes it so that if only the first 256 bytes of a buffer are used we just copy the data out and leave the offset and page count unchanged. There are multiple advantages to this. First it allows us to reuse the page much more in the case of pages larger than 4K. It also allows us to avoid some expensive atomic operations in the form of get_page/put_page. In perf I have seen CPU utilization for put_page drop from 3.5% to 1.8% as a result of this patch when doing small packet routing, and packet rates increased by about 3%. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Peter P Waskiewicz Jr --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 32 ++++++++++++++------------- 1 file changed, 17 insertions(+), 15 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d9269737409a..d11fac53a792 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1487,9 +1487,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, * we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len = skb_frag_size(frag); - if (pull_len > IXGBE_RX_HDR_SIZE) - pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE); + pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); @@ -1499,17 +1497,6 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, frag->page_offset += pull_len; skb->data_len -= pull_len; skb->tail += pull_len; - - /* - * if we sucked the frag empty then we should free it, - * if there are other frags here something is screwed up in hardware - */ - if (skb_frag_size(frag) == 0) { - BUG_ON(skb_shinfo(skb)->nr_frags != 1); - skb_shinfo(skb)->nr_frags = 0; - __skb_frag_unref(frag); - skb->truesize -= ixgbe_rx_bufsz(rx_ring); - } } /** @@ -1575,7 +1562,8 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, } /* place header in linear portion of buffer */ - ixgbe_pull_tail(rx_ring, skb); + if (skb_is_nonlinear(skb)) + ixgbe_pull_tail(rx_ring, skb); #ifdef IXGBE_FCOE /* do not attempt to pad FCoE Frames as this will disrupt DDP */ @@ -1656,6 +1644,20 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, ixgbe_rx_bufsz(rx_ring); #endif + if ((size <= IXGBE_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) { + unsigned char *va = page_address(page) + rx_buffer->page_offset; + + memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); + + /* we can reuse buffer as-is, just make sure it is local */ + if (likely(page_to_nid(page) == numa_node_id())) + return true; + + /* this page cannot be reused so discard it */ + put_page(page); + return false; + } + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, rx_buffer->page_offset, size, truesize); -- cgit v1.2.3 From 18806c9ea28320d5368fd43318506a7d33cc952c Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:08:44 +0000 Subject: ixgbe: Make allocating skb and placing data in it a separate function This patch creates a function named ixgbe_fetch_rx_buffer. The sole purpose of this function is to retrieve a single buffer off of the ring and to place it in an skb. The advantage to doing this is that it helps improve the readability since I can decrease the indentation and for the code in this section. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Peter P Waskiewicz Jr --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 166 ++++++++++++++------------ 1 file changed, 89 insertions(+), 77 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d11fac53a792..9e72ae6d8492 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1693,6 +1693,89 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, return true; } +static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc) +{ + struct ixgbe_rx_buffer *rx_buffer; + struct sk_buff *skb; + struct page *page; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + page = rx_buffer->page; + prefetchw(page); + + skb = rx_buffer->skb; + + if (likely(!skb)) { + void *page_addr = page_address(page) + + rx_buffer->page_offset; + + /* prefetch first cache line of first page */ + prefetch(page_addr); +#if L1_CACHE_BYTES < 128 + prefetch(page_addr + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = netdev_alloc_skb_ip_align(rx_ring->netdev, + IXGBE_RX_HDR_SIZE); + if (unlikely(!skb)) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + return NULL; + } + + /* + * we will be copying header into skb->data in + * pskb_may_pull so it is in our interest to prefetch + * it now to avoid a possible cache miss + */ + prefetchw(skb->data); + + /* + * Delay unmapping of the first packet. It carries the + * header information, HW may still access the header + * after the writeback. Only unmap it when EOP is + * reached + */ + if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) + goto dma_sync; + + IXGBE_CB(skb)->dma = rx_buffer->dma; + } else { + if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) + ixgbe_dma_sync_frag(rx_ring, skb); + +dma_sync: + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + } + + /* pull page into skb */ + if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { + /* hand second half of page back to the ring */ + ixgbe_reuse_rx_page(rx_ring, rx_buffer); + } else if (IXGBE_CB(skb)->dma == rx_buffer->dma) { + /* the page has been released from the ring */ + IXGBE_CB(skb)->page_released = true; + } else { + /* we are not reusing the buffer so unmap it */ + dma_unmap_page(rx_ring->dev, rx_buffer->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE); + } + + /* clear contents of buffer_info */ + rx_buffer->skb = NULL; + rx_buffer->dma = 0; + rx_buffer->page = NULL; + + return skb; +} + /** * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @q_vector: structure containing interrupt and ring information @@ -1718,11 +1801,8 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, u16 cleaned_count = ixgbe_desc_unused(rx_ring); do { - struct ixgbe_rx_buffer *rx_buffer; union ixgbe_adv_rx_desc *rx_desc; struct sk_buff *skb; - struct page *page; - u16 ntc; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) { @@ -1730,9 +1810,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, cleaned_count = 0; } - ntc = rx_ring->next_to_clean; - rx_desc = IXGBE_RX_DESC(rx_ring, ntc); - rx_buffer = &rx_ring->rx_buffer_info[ntc]; + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean); if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD)) break; @@ -1744,78 +1822,12 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ rmb(); - page = rx_buffer->page; - prefetchw(page); - - skb = rx_buffer->skb; - - if (likely(!skb)) { - void *page_addr = page_address(page) + - rx_buffer->page_offset; - - /* prefetch first cache line of first page */ - prefetch(page_addr); -#if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); -#endif - - /* allocate a skb to store the frags */ - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - IXGBE_RX_HDR_SIZE); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_rx_buff_failed++; - break; - } - - /* - * we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - - /* - * Delay unmapping of the first packet. It carries the - * header information, HW may still access the header - * after the writeback. Only unmap it when EOP is - * reached - */ - if (likely(ixgbe_test_staterr(rx_desc, - IXGBE_RXD_STAT_EOP))) - goto dma_sync; + /* retrieve a buffer from the ring */ + skb = ixgbe_fetch_rx_buffer(rx_ring, rx_desc); - IXGBE_CB(skb)->dma = rx_buffer->dma; - } else { - if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) - ixgbe_dma_sync_frag(rx_ring, skb); - -dma_sync: - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - ixgbe_rx_bufsz(rx_ring), - DMA_FROM_DEVICE); - } - - /* pull page into skb */ - if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { - /* hand second half of page back to the ring */ - ixgbe_reuse_rx_page(rx_ring, rx_buffer); - } else if (IXGBE_CB(skb)->dma == rx_buffer->dma) { - /* the page has been released from the ring */ - IXGBE_CB(skb)->page_released = true; - } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, - ixgbe_rx_pg_size(rx_ring), - DMA_FROM_DEVICE); - } - - /* clear contents of buffer_info */ - rx_buffer->skb = NULL; - rx_buffer->dma = 0; - rx_buffer->page = NULL; + /* exit if we failed to retrieve a buffer */ + if (!skb) + break; ixgbe_get_rsc_cnt(rx_ring, rx_desc, skb); -- cgit v1.2.3 From 5a02cbd10d37889d8214e82d57ccc70307edf805 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:08:51 +0000 Subject: ixgbe: Roll RSC code into non-EOP code This change moves the RSC code into the non-EOP descriptor handling function. The main motivation behind this change is to help reduce the overhead in the non-RSC case. Previously the non-RSC path code would always be checking for append count even if RSC had been disabled. Now this code is completely skipped in a single conditional check instead of having to make two separate checks. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Peter P Waskiewicz Jr --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 51 ++++++++++----------------- 1 file changed, 19 insertions(+), 32 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 9e72ae6d8492..aa37b84592b3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1320,29 +1320,6 @@ static unsigned int ixgbe_get_headlen(unsigned char *data, return max_len; } -static void ixgbe_get_rsc_cnt(struct ixgbe_ring *rx_ring, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) -{ - __le32 rsc_enabled; - u32 rsc_cnt; - - if (!ring_is_rsc_enabled(rx_ring)) - return; - - rsc_enabled = rx_desc->wb.lower.lo_dword.data & - cpu_to_le32(IXGBE_RXDADV_RSCCNT_MASK); - - /* If this is an RSC frame rsc_cnt should be non-zero */ - if (!rsc_enabled) - return; - - rsc_cnt = le32_to_cpu(rsc_enabled); - rsc_cnt >>= IXGBE_RXDADV_RSCCNT_SHIFT; - - IXGBE_CB(skb)->append_cnt += rsc_cnt - 1; -} - static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring, struct sk_buff *skb) { @@ -1440,16 +1417,28 @@ static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring, prefetch(IXGBE_RX_DESC(rx_ring, ntc)); - if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) - return false; + /* update RSC append count if present */ + if (ring_is_rsc_enabled(rx_ring)) { + __le32 rsc_enabled = rx_desc->wb.lower.lo_dword.data & + cpu_to_le32(IXGBE_RXDADV_RSCCNT_MASK); + + if (unlikely(rsc_enabled)) { + u32 rsc_cnt = le32_to_cpu(rsc_enabled); + + rsc_cnt >>= IXGBE_RXDADV_RSCCNT_SHIFT; + IXGBE_CB(skb)->append_cnt += rsc_cnt - 1; - /* append_cnt indicates packet is RSC, if so fetch nextp */ - if (IXGBE_CB(skb)->append_cnt) { - ntc = le32_to_cpu(rx_desc->wb.upper.status_error); - ntc &= IXGBE_RXDADV_NEXTP_MASK; - ntc >>= IXGBE_RXDADV_NEXTP_SHIFT; + /* update ntc based on RSC value */ + ntc = le32_to_cpu(rx_desc->wb.upper.status_error); + ntc &= IXGBE_RXDADV_NEXTP_MASK; + ntc >>= IXGBE_RXDADV_NEXTP_SHIFT; + } } + /* if we are the last buffer then there is nothing else to do */ + if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) + return false; + /* place skb in next buffer to be received */ rx_ring->rx_buffer_info[ntc].skb = skb; rx_ring->rx_stats.non_eop_descs++; @@ -1829,8 +1818,6 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, if (!skb) break; - ixgbe_get_rsc_cnt(rx_ring, rx_desc, skb); - cleaned_count++; /* place incomplete frames back on ring for completion */ -- cgit v1.2.3 From 62748b7bde84618f06b5c7a8733ae87776ec36c5 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:09:01 +0000 Subject: ixgbe: Rewrite code related to configuring IFCS bit in Tx descriptor This change updates the code related to configuring the transmit frame checksum. Specifically I have updated the code so that we can only skip inserting the checksum in the case that we are not performing some other offload that will modify the frame data. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Peter P Waskiewicz Jr --- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 1 + drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 16 ++++++++++------ 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index fd2bc697a92b..bffcf1f2357a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -107,6 +107,7 @@ #define IXGBE_TX_FLAGS_FSO (u32)(1 << 6) #define IXGBE_TX_FLAGS_TXSW (u32)(1 << 7) #define IXGBE_TX_FLAGS_TSTAMP (u32)(1 << 8) +#define IXGBE_TX_FLAGS_NO_IFCS (u32)(1 << 9) #define IXGBE_TX_FLAGS_VLAN_MASK 0xffff0000 #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 #define IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT 29 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index aa37b84592b3..fa0d6e1561c1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5903,9 +5903,12 @@ static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring, u32 type_tucmd = 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { - if (!(first->tx_flags & IXGBE_TX_FLAGS_HW_VLAN) && - !(first->tx_flags & IXGBE_TX_FLAGS_TXSW)) - return; + if (!(first->tx_flags & IXGBE_TX_FLAGS_HW_VLAN)) { + if (unlikely(skb->no_fcs)) + first->tx_flags |= IXGBE_TX_FLAGS_NO_IFCS; + if (!(first->tx_flags & IXGBE_TX_FLAGS_TXSW)) + return; + } } else { u8 l4_hdr = 0; switch (first->protocol) { @@ -5967,7 +5970,6 @@ static __le32 ixgbe_tx_cmd_type(u32 tx_flags) { /* set type for advanced descriptor with frame checksum insertion */ __le32 cmd_type = cpu_to_le32(IXGBE_ADVTXD_DTYP_DATA | - IXGBE_ADVTXD_DCMD_IFCS | IXGBE_ADVTXD_DCMD_DEXT); /* set HW vlan bit if vlan is present */ @@ -5987,6 +5989,10 @@ static __le32 ixgbe_tx_cmd_type(u32 tx_flags) #endif cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_TSE); + /* insert frame checksum */ + if (!(tx_flags & IXGBE_TX_FLAGS_NO_IFCS)) + cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_IFCS); + return cmd_type; } @@ -6092,8 +6098,6 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring, if (likely(!data_len)) break; - if (unlikely(skb->no_fcs)) - cmd_type &= ~(cpu_to_le32(IXGBE_ADVTXD_DCMD_IFCS)); tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(size); i++; -- cgit v1.2.3 From 43829731dd372d04d6706c51052b9dabab9ca356 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 20 Aug 2012 14:51:24 -0700 Subject: workqueue: deprecate flush[_delayed]_work_sync() flush[_delayed]_work_sync() are now spurious. Mark them deprecated and convert all users to flush[_delayed]_work(). If you're cc'd and wondering what's going on: Now all workqueues are non-reentrant and the regular flushes guarantee that the work item is not pending or running on any CPU on return, so there's no reason to use the sync flushes at all and they're going away. This patch doesn't make any functional difference. Signed-off-by: Tejun Heo Cc: Russell King Cc: Paul Mundt Cc: Ian Campbell Cc: Jens Axboe Cc: Mattia Dongili Cc: Kent Yoder Cc: David Airlie Cc: Jiri Kosina Cc: Karsten Keil Cc: Bryan Wu Cc: Benjamin Herrenschmidt Cc: Alasdair Kergon Cc: Mauro Carvalho Chehab Cc: Florian Tobias Schandinat Cc: David Woodhouse Cc: "David S. Miller" Cc: linux-wireless@vger.kernel.org Cc: Anton Vorontsov Cc: Sangbeom Kim Cc: "James E.J. Bottomley" Cc: Greg Kroah-Hartman Cc: Eric Van Hensbergen Cc: Takashi Iwai Cc: Steven Whitehouse Cc: Petr Vandrovec Cc: Mark Fasheh Cc: Christoph Hellwig Cc: Avi Kivity --- arch/arm/mach-pxa/sharpsl_pm.c | 4 ++-- arch/arm/plat-omap/mailbox.c | 2 +- arch/sh/drivers/push-switch.c | 2 +- drivers/block/xen-blkfront.c | 4 ++-- drivers/cdrom/gdrom.c | 2 +- drivers/char/sonypi.c | 2 +- drivers/char/tpm/tpm.c | 4 ++-- drivers/gpu/drm/exynos/exynos_drm_g2d.c | 2 +- drivers/gpu/drm/nouveau/nouveau_gpio.c | 2 +- drivers/gpu/drm/radeon/radeon_irq_kms.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_fb.c | 2 +- drivers/hid/hid-picolcd.c | 2 +- drivers/input/touchscreen/wm831x-ts.c | 2 +- drivers/isdn/mISDN/hwchannel.c | 4 ++-- drivers/leds/leds-lm3533.c | 6 +++--- drivers/leds/leds-lp8788.c | 2 +- drivers/leds/leds-wm8350.c | 2 +- drivers/macintosh/ams/ams-core.c | 2 +- drivers/md/dm-mpath.c | 2 +- drivers/md/dm-raid1.c | 2 +- drivers/md/dm-stripe.c | 2 +- drivers/media/dvb/dvb-core/dvb_net.c | 4 ++-- drivers/media/dvb/mantis/mantis_evm.c | 2 +- drivers/media/dvb/mantis/mantis_uart.c | 2 +- drivers/media/video/bt8xx/bttv-driver.c | 2 +- drivers/media/video/cx18/cx18-driver.c | 2 +- drivers/media/video/cx231xx/cx231xx-cards.c | 2 +- drivers/media/video/cx23885/cx23885-input.c | 6 +++--- drivers/media/video/cx88/cx88-mpeg.c | 2 +- drivers/media/video/em28xx/em28xx-cards.c | 2 +- drivers/media/video/omap24xxcam.c | 6 +++--- drivers/media/video/saa7134/saa7134-core.c | 2 +- drivers/media/video/saa7134/saa7134-empress.c | 2 +- drivers/media/video/tm6000/tm6000-cards.c | 2 +- drivers/mfd/menelaus.c | 4 ++-- drivers/misc/ioc4.c | 2 +- drivers/mtd/mtdoops.c | 4 ++-- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 2 +- drivers/net/ethernet/neterion/vxge/vxge-main.c | 2 +- drivers/net/ethernet/sun/cassini.c | 2 +- drivers/net/ethernet/sun/niu.c | 2 +- drivers/net/wireless/hostap/hostap_ap.c | 4 ++-- drivers/net/wireless/hostap/hostap_hw.c | 10 +++++----- drivers/power/collie_battery.c | 2 +- drivers/power/tosa_battery.c | 2 +- drivers/power/wm97xx_battery.c | 2 +- drivers/power/z2_battery.c | 2 +- drivers/regulator/core.c | 2 +- drivers/scsi/arcmsr/arcmsr_hba.c | 4 ++-- drivers/scsi/ipr.c | 2 +- drivers/scsi/pmcraid.c | 2 +- drivers/scsi/qla2xxx/qla_target.c | 2 +- drivers/tty/hvc/hvsi.c | 2 +- drivers/tty/ipwireless/hardware.c | 2 +- drivers/tty/ipwireless/network.c | 4 ++-- drivers/tty/serial/kgdboc.c | 2 +- drivers/tty/serial/omap-serial.c | 2 +- drivers/tty/tty_ldisc.c | 6 +++--- drivers/usb/atm/speedtch.c | 2 +- drivers/usb/atm/ueagle-atm.c | 2 +- drivers/usb/gadget/u_ether.c | 2 +- drivers/usb/host/ohci-hcd.c | 2 +- drivers/usb/otg/isp1301_omap.c | 2 +- fs/affs/super.c | 2 +- fs/gfs2/lock_dlm.c | 2 +- fs/gfs2/super.c | 2 +- fs/hfs/inode.c | 2 +- fs/ncpfs/inode.c | 6 +++--- fs/ocfs2/cluster/quorum.c | 2 +- fs/xfs/xfs_super.c | 2 +- fs/xfs/xfs_sync.c | 2 +- include/linux/workqueue.h | 4 ++-- net/9p/trans_fd.c | 2 +- net/dsa/dsa.c | 2 +- sound/i2c/other/ak4113.c | 2 +- sound/i2c/other/ak4114.c | 2 +- sound/pci/oxygen/oxygen_lib.c | 8 ++++---- sound/soc/codecs/wm8350.c | 2 +- sound/soc/codecs/wm8753.c | 2 +- sound/soc/soc-core.c | 6 +++--- virt/kvm/eventfd.c | 2 +- 81 files changed, 111 insertions(+), 111 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c index bdf4cb88ca0a..7875ad6456bd 100644 --- a/arch/arm/mach-pxa/sharpsl_pm.c +++ b/arch/arm/mach-pxa/sharpsl_pm.c @@ -579,8 +579,8 @@ static int sharpsl_ac_check(void) static int sharpsl_pm_suspend(struct platform_device *pdev, pm_message_t state) { sharpsl_pm.flags |= SHARPSL_SUSPENDED; - flush_delayed_work_sync(&toggle_charger); - flush_delayed_work_sync(&sharpsl_bat); + flush_delayed_work(&toggle_charger); + flush_delayed_work(&sharpsl_bat); if (sharpsl_pm.charge_mode == CHRG_ON) sharpsl_pm.flags |= SHARPSL_DO_OFFLINE_CHRG; diff --git a/arch/arm/plat-omap/mailbox.c b/arch/arm/plat-omap/mailbox.c index 5e13c3884aa4..42377ef9ea3d 100644 --- a/arch/arm/plat-omap/mailbox.c +++ b/arch/arm/plat-omap/mailbox.c @@ -310,7 +310,7 @@ static void omap_mbox_fini(struct omap_mbox *mbox) omap_mbox_disable_irq(mbox, IRQ_RX); free_irq(mbox->irq, mbox); tasklet_kill(&mbox->txq->tasklet); - flush_work_sync(&mbox->rxq->work); + flush_work(&mbox->rxq->work); mbox_queue_free(mbox->txq); mbox_queue_free(mbox->rxq); } diff --git a/arch/sh/drivers/push-switch.c b/arch/sh/drivers/push-switch.c index 637b79b09657..5bfb341cc5c4 100644 --- a/arch/sh/drivers/push-switch.c +++ b/arch/sh/drivers/push-switch.c @@ -107,7 +107,7 @@ static int switch_drv_remove(struct platform_device *pdev) device_remove_file(&pdev->dev, &dev_attr_switch); platform_set_drvdata(pdev, NULL); - flush_work_sync(&psw->work); + flush_work(&psw->work); del_timer_sync(&psw->debounce); free_irq(irq, pdev); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 2c2d2e5c1597..007db8986e84 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -670,7 +670,7 @@ static void xlvbd_release_gendisk(struct blkfront_info *info) spin_unlock_irqrestore(&info->io_lock, flags); /* Flush gnttab callback work. Must be done with no locks held. */ - flush_work_sync(&info->work); + flush_work(&info->work); del_gendisk(info->gd); @@ -719,7 +719,7 @@ static void blkif_free(struct blkfront_info *info, int suspend) spin_unlock_irq(&info->io_lock); /* Flush gnttab callback work. Must be done with no locks held. */ - flush_work_sync(&info->work); + flush_work(&info->work); /* Free resources associated with old device channel. */ if (info->ring_ref != GRANT_INVALID_REF) { diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 3ceaf006e7f0..75d485afe56c 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -840,7 +840,7 @@ probe_fail_no_mem: static int __devexit remove_gdrom(struct platform_device *devptr) { - flush_work_sync(&work); + flush_work(&work); blk_cleanup_queue(gd.gdrom_rq); free_irq(HW_EVENT_GDROM_CMD, &gd); free_irq(HW_EVENT_GDROM_DMA, &gd); diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c index f87780502b41..320debbe32fa 100644 --- a/drivers/char/sonypi.c +++ b/drivers/char/sonypi.c @@ -1433,7 +1433,7 @@ static int __devexit sonypi_remove(struct platform_device *dev) sonypi_disable(); synchronize_irq(sonypi_device.irq); - flush_work_sync(&sonypi_device.input_work); + flush_work(&sonypi_device.input_work); if (useinput) { input_unregister_device(sonypi_device.input_key_dev); diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c index 817f0ee202b6..3af9f4d1a23f 100644 --- a/drivers/char/tpm/tpm.c +++ b/drivers/char/tpm/tpm.c @@ -1172,7 +1172,7 @@ int tpm_release(struct inode *inode, struct file *file) struct tpm_chip *chip = file->private_data; del_singleshot_timer_sync(&chip->user_read_timer); - flush_work_sync(&chip->work); + flush_work(&chip->work); file->private_data = NULL; atomic_set(&chip->data_pending, 0); kfree(chip->data_buffer); @@ -1225,7 +1225,7 @@ ssize_t tpm_read(struct file *file, char __user *buf, int rc; del_singleshot_timer_sync(&chip->user_read_timer); - flush_work_sync(&chip->work); + flush_work(&chip->work); ret_size = atomic_read(&chip->data_pending); atomic_set(&chip->data_pending, 0); if (ret_size > 0) { /* relay data */ diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index d2d88f22a037..a40808e51338 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -908,7 +908,7 @@ static int g2d_suspend(struct device *dev) /* FIXME: good range? */ usleep_range(500, 1000); - flush_work_sync(&g2d->runqueue_work); + flush_work(&g2d->runqueue_work); return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_gpio.c b/drivers/gpu/drm/nouveau/nouveau_gpio.c index 82c19e82ff02..0fe4e17c461d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gpio.c +++ b/drivers/gpu/drm/nouveau/nouveau_gpio.c @@ -302,7 +302,7 @@ nouveau_gpio_isr_del(struct drm_device *dev, int idx, u8 tag, u8 line, spin_unlock_irqrestore(&pgpio->lock, flags); list_for_each_entry_safe(isr, tmp, &tofree, head) { - flush_work_sync(&isr->work); + flush_work(&isr->work); kfree(isr); } } diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c index afaa1727abd2..50b596ec7b7e 100644 --- a/drivers/gpu/drm/radeon/radeon_irq_kms.c +++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c @@ -277,7 +277,7 @@ void radeon_irq_kms_fini(struct radeon_device *rdev) if (rdev->msi_enabled) pci_disable_msi(rdev->pdev); } - flush_work_sync(&rdev->hotplug_work); + flush_work(&rdev->hotplug_work); } /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 3c447bf317cb..a32f2e96dd02 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -594,7 +594,7 @@ int vmw_fb_off(struct vmw_private *vmw_priv) par->dirty.active = false; spin_unlock_irqrestore(&par->dirty.lock, flags); - flush_delayed_work_sync(&info->deferred_work); + flush_delayed_work(&info->deferred_work); par->bo_ptr = NULL; ttm_bo_kunmap(&par->map); diff --git a/drivers/hid/hid-picolcd.c b/drivers/hid/hid-picolcd.c index 27c8ebdfad01..3e90dee30ff6 100644 --- a/drivers/hid/hid-picolcd.c +++ b/drivers/hid/hid-picolcd.c @@ -2737,7 +2737,7 @@ static void __exit picolcd_exit(void) { hid_unregister_driver(&picolcd_driver); #ifdef CONFIG_HID_PICOLCD_FB - flush_work_sync(&picolcd_fb_cleanup); + flush_work(&picolcd_fb_cleanup); WARN_ON(fb_pending); #endif } diff --git a/drivers/input/touchscreen/wm831x-ts.c b/drivers/input/touchscreen/wm831x-ts.c index e83410721e38..52abb98a8ae5 100644 --- a/drivers/input/touchscreen/wm831x-ts.c +++ b/drivers/input/touchscreen/wm831x-ts.c @@ -221,7 +221,7 @@ static void wm831x_ts_input_close(struct input_dev *idev) synchronize_irq(wm831x_ts->pd_irq); /* Make sure the IRQ completion work is quiesced */ - flush_work_sync(&wm831x_ts->pd_data_work); + flush_work(&wm831x_ts->pd_data_work); /* If we ended up with the pen down then make sure we revert back * to pen detection state for the next time we start up. diff --git a/drivers/isdn/mISDN/hwchannel.c b/drivers/isdn/mISDN/hwchannel.c index ef34fd40867c..4b85f7279f18 100644 --- a/drivers/isdn/mISDN/hwchannel.c +++ b/drivers/isdn/mISDN/hwchannel.c @@ -116,7 +116,7 @@ mISDN_freedchannel(struct dchannel *ch) } skb_queue_purge(&ch->squeue); skb_queue_purge(&ch->rqueue); - flush_work_sync(&ch->workq); + flush_work(&ch->workq); return 0; } EXPORT_SYMBOL(mISDN_freedchannel); @@ -157,7 +157,7 @@ mISDN_freebchannel(struct bchannel *ch) mISDN_clear_bchannel(ch); skb_queue_purge(&ch->rqueue); ch->rcount = 0; - flush_work_sync(&ch->workq); + flush_work(&ch->workq); return 0; } EXPORT_SYMBOL(mISDN_freebchannel); diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c index f56b6e7ffdac..f6837b99908c 100644 --- a/drivers/leds/leds-lm3533.c +++ b/drivers/leds/leds-lm3533.c @@ -737,7 +737,7 @@ err_sysfs_remove: sysfs_remove_group(&led->cdev.dev->kobj, &lm3533_led_attribute_group); err_unregister: led_classdev_unregister(&led->cdev); - flush_work_sync(&led->work); + flush_work(&led->work); return ret; } @@ -751,7 +751,7 @@ static int __devexit lm3533_led_remove(struct platform_device *pdev) lm3533_ctrlbank_disable(&led->cb); sysfs_remove_group(&led->cdev.dev->kobj, &lm3533_led_attribute_group); led_classdev_unregister(&led->cdev); - flush_work_sync(&led->work); + flush_work(&led->work); return 0; } @@ -765,7 +765,7 @@ static void lm3533_led_shutdown(struct platform_device *pdev) lm3533_ctrlbank_disable(&led->cb); lm3533_led_set(&led->cdev, LED_OFF); /* disable blink */ - flush_work_sync(&led->work); + flush_work(&led->work); } static struct platform_driver lm3533_led_driver = { diff --git a/drivers/leds/leds-lp8788.c b/drivers/leds/leds-lp8788.c index 53bd136f1ef0..cb76bc46a021 100644 --- a/drivers/leds/leds-lp8788.c +++ b/drivers/leds/leds-lp8788.c @@ -172,7 +172,7 @@ static int __devexit lp8788_led_remove(struct platform_device *pdev) struct lp8788_led *led = platform_get_drvdata(pdev); led_classdev_unregister(&led->led_dev); - flush_work_sync(&led->work); + flush_work(&led->work); return 0; } diff --git a/drivers/leds/leds-wm8350.c b/drivers/leds/leds-wm8350.c index 918d4baff1c7..4c62113f7a77 100644 --- a/drivers/leds/leds-wm8350.c +++ b/drivers/leds/leds-wm8350.c @@ -275,7 +275,7 @@ static int wm8350_led_remove(struct platform_device *pdev) struct wm8350_led *led = platform_get_drvdata(pdev); led_classdev_unregister(&led->cdev); - flush_work_sync(&led->work); + flush_work(&led->work); wm8350_led_disable(led); regulator_put(led->dcdc); regulator_put(led->isink); diff --git a/drivers/macintosh/ams/ams-core.c b/drivers/macintosh/ams/ams-core.c index 5c6a2d876562..36a4fdddd64a 100644 --- a/drivers/macintosh/ams/ams-core.c +++ b/drivers/macintosh/ams/ams-core.c @@ -226,7 +226,7 @@ void ams_sensor_detach(void) * We do this after ams_info.exit(), because an interrupt might * have arrived before disabling them. */ - flush_work_sync(&ams_info.worker); + flush_work(&ams_info.worker); /* Remove device */ of_device_unregister(ams_info.of_dev); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index d8abb90a6c2f..bb18eafcc85a 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -944,7 +944,7 @@ static void flush_multipath_work(struct multipath *m) flush_workqueue(kmpath_handlerd); multipath_wait_for_pg_init_completion(m); flush_workqueue(kmultipathd); - flush_work_sync(&m->trigger_event); + flush_work(&m->trigger_event); } static void multipath_dtr(struct dm_target *ti) diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index bc5ddba8045b..fd61f98ee1f6 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1146,7 +1146,7 @@ static void mirror_dtr(struct dm_target *ti) del_timer_sync(&ms->timer); flush_workqueue(ms->kmirrord_wq); - flush_work_sync(&ms->trigger_event); + flush_work(&ms->trigger_event); dm_kcopyd_client_destroy(ms->kcopyd_client); destroy_workqueue(ms->kmirrord_wq); free_context(ms, ti, ms->nr_mirrors); diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index a087bf2a8d66..e2f876539743 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -199,7 +199,7 @@ static void stripe_dtr(struct dm_target *ti) for (i = 0; i < sc->stripes; i++) dm_put_device(ti, sc->stripe[i].dev); - flush_work_sync(&sc->trigger_event); + flush_work(&sc->trigger_event); kfree(sc); } diff --git a/drivers/media/dvb/dvb-core/dvb_net.c b/drivers/media/dvb/dvb-core/dvb_net.c index 8766ce8c354d..c2117688aa23 100644 --- a/drivers/media/dvb/dvb-core/dvb_net.c +++ b/drivers/media/dvb/dvb-core/dvb_net.c @@ -1329,8 +1329,8 @@ static int dvb_net_remove_if(struct dvb_net *dvbnet, unsigned long num) return -EBUSY; dvb_net_stop(net); - flush_work_sync(&priv->set_multicast_list_wq); - flush_work_sync(&priv->restart_net_feed_wq); + flush_work(&priv->set_multicast_list_wq); + flush_work(&priv->restart_net_feed_wq); printk("dvb_net: removed network interface %s\n", net->name); unregister_netdev(net); dvbnet->state[num]=0; diff --git a/drivers/media/dvb/mantis/mantis_evm.c b/drivers/media/dvb/mantis/mantis_evm.c index 71ce52875c38..909ff54868a3 100644 --- a/drivers/media/dvb/mantis/mantis_evm.c +++ b/drivers/media/dvb/mantis/mantis_evm.c @@ -111,7 +111,7 @@ void mantis_evmgr_exit(struct mantis_ca *ca) struct mantis_pci *mantis = ca->ca_priv; dprintk(MANTIS_DEBUG, 1, "Mantis Host I/F Event manager exiting"); - flush_work_sync(&ca->hif_evm_work); + flush_work(&ca->hif_evm_work); mantis_hif_exit(ca); mantis_pcmcia_exit(ca); } diff --git a/drivers/media/dvb/mantis/mantis_uart.c b/drivers/media/dvb/mantis/mantis_uart.c index 18340dafa426..85e977861b4a 100644 --- a/drivers/media/dvb/mantis/mantis_uart.c +++ b/drivers/media/dvb/mantis/mantis_uart.c @@ -183,6 +183,6 @@ void mantis_uart_exit(struct mantis_pci *mantis) { /* disable interrupt */ mmwrite(mmread(MANTIS_UART_CTL) & 0xffef, MANTIS_UART_CTL); - flush_work_sync(&mantis->uart_work); + flush_work(&mantis->uart_work); } EXPORT_SYMBOL_GPL(mantis_uart_exit); diff --git a/drivers/media/video/bt8xx/bttv-driver.c b/drivers/media/video/bt8xx/bttv-driver.c index b58ff87db771..2ce7179a3864 100644 --- a/drivers/media/video/bt8xx/bttv-driver.c +++ b/drivers/media/video/bt8xx/bttv-driver.c @@ -196,7 +196,7 @@ static void request_modules(struct bttv *dev) static void flush_request_modules(struct bttv *dev) { - flush_work_sync(&dev->request_module_wk); + flush_work(&dev->request_module_wk); } #else #define request_modules(dev) diff --git a/drivers/media/video/cx18/cx18-driver.c b/drivers/media/video/cx18/cx18-driver.c index 7e5ffd6f5178..75c890907920 100644 --- a/drivers/media/video/cx18/cx18-driver.c +++ b/drivers/media/video/cx18/cx18-driver.c @@ -272,7 +272,7 @@ static void request_modules(struct cx18 *dev) static void flush_request_modules(struct cx18 *dev) { - flush_work_sync(&dev->request_module_wk); + flush_work(&dev->request_module_wk); } #else #define request_modules(dev) diff --git a/drivers/media/video/cx231xx/cx231xx-cards.c b/drivers/media/video/cx231xx/cx231xx-cards.c index 02d4d36735d3..b84ebc54d91b 100644 --- a/drivers/media/video/cx231xx/cx231xx-cards.c +++ b/drivers/media/video/cx231xx/cx231xx-cards.c @@ -1002,7 +1002,7 @@ static void request_modules(struct cx231xx *dev) static void flush_request_modules(struct cx231xx *dev) { - flush_work_sync(&dev->request_module_wk); + flush_work(&dev->request_module_wk); } #else #define request_modules(dev) diff --git a/drivers/media/video/cx23885/cx23885-input.c b/drivers/media/video/cx23885/cx23885-input.c index ce765e3f77bd..bcbf7faf1bab 100644 --- a/drivers/media/video/cx23885/cx23885-input.c +++ b/drivers/media/video/cx23885/cx23885-input.c @@ -231,9 +231,9 @@ static void cx23885_input_ir_stop(struct cx23885_dev *dev) v4l2_subdev_call(dev->sd_ir, ir, rx_s_parameters, ¶ms); v4l2_subdev_call(dev->sd_ir, ir, rx_g_parameters, ¶ms); } - flush_work_sync(&dev->cx25840_work); - flush_work_sync(&dev->ir_rx_work); - flush_work_sync(&dev->ir_tx_work); + flush_work(&dev->cx25840_work); + flush_work(&dev->ir_rx_work); + flush_work(&dev->ir_tx_work); } static void cx23885_input_ir_close(struct rc_dev *rc) diff --git a/drivers/media/video/cx88/cx88-mpeg.c b/drivers/media/video/cx88/cx88-mpeg.c index cd5386ee210c..c04fb618e10b 100644 --- a/drivers/media/video/cx88/cx88-mpeg.c +++ b/drivers/media/video/cx88/cx88-mpeg.c @@ -70,7 +70,7 @@ static void request_modules(struct cx8802_dev *dev) static void flush_request_modules(struct cx8802_dev *dev) { - flush_work_sync(&dev->request_module_wk); + flush_work(&dev->request_module_wk); } #else #define request_modules(dev) diff --git a/drivers/media/video/em28xx/em28xx-cards.c b/drivers/media/video/em28xx/em28xx-cards.c index ca62b9981380..f7831e73f077 100644 --- a/drivers/media/video/em28xx/em28xx-cards.c +++ b/drivers/media/video/em28xx/em28xx-cards.c @@ -2900,7 +2900,7 @@ static void request_modules(struct em28xx *dev) static void flush_request_modules(struct em28xx *dev) { - flush_work_sync(&dev->request_module_wk); + flush_work(&dev->request_module_wk); } #else #define request_modules(dev) diff --git a/drivers/media/video/omap24xxcam.c b/drivers/media/video/omap24xxcam.c index e5015b0d5508..8d7283bbd431 100644 --- a/drivers/media/video/omap24xxcam.c +++ b/drivers/media/video/omap24xxcam.c @@ -1198,7 +1198,7 @@ static int vidioc_streamoff(struct file *file, void *fh, enum v4l2_buf_type i) atomic_inc(&cam->reset_disable); - flush_work_sync(&cam->sensor_reset_work); + flush_work(&cam->sensor_reset_work); rval = videobuf_streamoff(q); if (!rval) { @@ -1512,7 +1512,7 @@ static int omap24xxcam_release(struct file *file) atomic_inc(&cam->reset_disable); - flush_work_sync(&cam->sensor_reset_work); + flush_work(&cam->sensor_reset_work); /* stop streaming capture */ videobuf_streamoff(&fh->vbq); @@ -1536,7 +1536,7 @@ static int omap24xxcam_release(struct file *file) * not be scheduled anymore since streaming is already * disabled.) */ - flush_work_sync(&cam->sensor_reset_work); + flush_work(&cam->sensor_reset_work); mutex_lock(&cam->mutex); if (atomic_dec_return(&cam->users) == 0) { diff --git a/drivers/media/video/saa7134/saa7134-core.c b/drivers/media/video/saa7134/saa7134-core.c index 5fbb4e49495c..f2b37e05b964 100644 --- a/drivers/media/video/saa7134/saa7134-core.c +++ b/drivers/media/video/saa7134/saa7134-core.c @@ -170,7 +170,7 @@ static void request_submodules(struct saa7134_dev *dev) static void flush_request_submodules(struct saa7134_dev *dev) { - flush_work_sync(&dev->request_module_wk); + flush_work(&dev->request_module_wk); } #else diff --git a/drivers/media/video/saa7134/saa7134-empress.c b/drivers/media/video/saa7134/saa7134-empress.c index dde361a9194e..4df79c656909 100644 --- a/drivers/media/video/saa7134/saa7134-empress.c +++ b/drivers/media/video/saa7134/saa7134-empress.c @@ -556,7 +556,7 @@ static int empress_fini(struct saa7134_dev *dev) if (NULL == dev->empress_dev) return 0; - flush_work_sync(&dev->empress_workqueue); + flush_work(&dev->empress_workqueue); video_unregister_device(dev->empress_dev); dev->empress_dev = NULL; return 0; diff --git a/drivers/media/video/tm6000/tm6000-cards.c b/drivers/media/video/tm6000/tm6000-cards.c index 034659b13174..307d8c5fb7cd 100644 --- a/drivers/media/video/tm6000/tm6000-cards.c +++ b/drivers/media/video/tm6000/tm6000-cards.c @@ -1074,7 +1074,7 @@ static void request_modules(struct tm6000_core *dev) static void flush_request_modules(struct tm6000_core *dev) { - flush_work_sync(&dev->request_module_wk); + flush_work(&dev->request_module_wk); } #else #define request_modules(dev) diff --git a/drivers/mfd/menelaus.c b/drivers/mfd/menelaus.c index cb4910ac4d12..55d589981412 100644 --- a/drivers/mfd/menelaus.c +++ b/drivers/mfd/menelaus.c @@ -1259,7 +1259,7 @@ static int menelaus_probe(struct i2c_client *client, return 0; fail2: free_irq(client->irq, menelaus); - flush_work_sync(&menelaus->work); + flush_work(&menelaus->work); fail1: kfree(menelaus); return err; @@ -1270,7 +1270,7 @@ static int __exit menelaus_remove(struct i2c_client *client) struct menelaus_chip *menelaus = i2c_get_clientdata(client); free_irq(client->irq, menelaus); - flush_work_sync(&menelaus->work); + flush_work(&menelaus->work); kfree(menelaus); the_menelaus = NULL; return 0; diff --git a/drivers/misc/ioc4.c b/drivers/misc/ioc4.c index df03dd3bd0e2..6a7710603a90 100644 --- a/drivers/misc/ioc4.c +++ b/drivers/misc/ioc4.c @@ -487,7 +487,7 @@ static void __exit ioc4_exit(void) { /* Ensure ioc4_load_modules() has completed before exiting */ - flush_work_sync(&ioc4_load_modules_work); + flush_work(&ioc4_load_modules_work); pci_unregister_driver(&ioc4_driver); } diff --git a/drivers/mtd/mtdoops.c b/drivers/mtd/mtdoops.c index 551e316e4454..438737a1f59a 100644 --- a/drivers/mtd/mtdoops.c +++ b/drivers/mtd/mtdoops.c @@ -387,8 +387,8 @@ static void mtdoops_notify_remove(struct mtd_info *mtd) printk(KERN_WARNING "mtdoops: could not unregister kmsg_dumper\n"); cxt->mtd = NULL; - flush_work_sync(&cxt->work_erase); - flush_work_sync(&cxt->work_write); + flush_work(&cxt->work_erase); + flush_work(&cxt->work_write); } diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 6505070abcfa..089ed134369b 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -1394,7 +1394,7 @@ static int offload_close(struct t3cdev *tdev) sysfs_remove_group(&tdev->lldev->dev.kobj, &offload_attr_group); /* Flush work scheduled while releasing TIDs */ - flush_work_sync(&td->tid_release_task); + flush_work(&td->tid_release_task); tdev->lldev = NULL; cxgb3_set_dummy_ops(tdev); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index de2190443510..30ce10bc9149 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -3521,7 +3521,7 @@ static void vxge_device_unregister(struct __vxge_hw_device *hldev) strncpy(buf, dev->name, IFNAMSIZ); - flush_work_sync(&vdev->reset_task); + flush_work(&vdev->reset_task); /* in 2.6 will call stop() if device is up */ unregister_netdev(dev); diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index ce4df61b4b56..c8251be104d6 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -3890,7 +3890,7 @@ static int cas_change_mtu(struct net_device *dev, int new_mtu) schedule_work(&cp->reset_task); #endif - flush_work_sync(&cp->reset_task); + flush_work(&cp->reset_task); return 0; } diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index c2a0fe393267..710f35395195 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9932,7 +9932,7 @@ static int niu_suspend(struct pci_dev *pdev, pm_message_t state) if (!netif_running(dev)) return 0; - flush_work_sync(&np->reset_task); + flush_work(&np->reset_task); niu_netif_stop(np); del_timer_sync(&np->timer); diff --git a/drivers/net/wireless/hostap/hostap_ap.c b/drivers/net/wireless/hostap/hostap_ap.c index e1f410277242..c6ea995750db 100644 --- a/drivers/net/wireless/hostap/hostap_ap.c +++ b/drivers/net/wireless/hostap/hostap_ap.c @@ -860,10 +860,10 @@ void hostap_free_data(struct ap_data *ap) return; } - flush_work_sync(&ap->add_sta_proc_queue); + flush_work(&ap->add_sta_proc_queue); #ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT - flush_work_sync(&ap->wds_oper_queue); + flush_work(&ap->wds_oper_queue); if (ap->crypt) ap->crypt->deinit(ap->crypt_priv); ap->crypt = ap->crypt_priv = NULL; diff --git a/drivers/net/wireless/hostap/hostap_hw.c b/drivers/net/wireless/hostap/hostap_hw.c index 50f87b60b0bd..8e7000fd4414 100644 --- a/drivers/net/wireless/hostap/hostap_hw.c +++ b/drivers/net/wireless/hostap/hostap_hw.c @@ -3311,13 +3311,13 @@ static void prism2_free_local_data(struct net_device *dev) unregister_netdev(local->dev); - flush_work_sync(&local->reset_queue); - flush_work_sync(&local->set_multicast_list_queue); - flush_work_sync(&local->set_tim_queue); + flush_work(&local->reset_queue); + flush_work(&local->set_multicast_list_queue); + flush_work(&local->set_tim_queue); #ifndef PRISM2_NO_STATION_MODES - flush_work_sync(&local->info_queue); + flush_work(&local->info_queue); #endif - flush_work_sync(&local->comms_qual_update); + flush_work(&local->comms_qual_update); lib80211_crypt_info_free(&local->crypt_info); diff --git a/drivers/power/collie_battery.c b/drivers/power/collie_battery.c index 74c6b23aeabf..b19bfe400f8c 100644 --- a/drivers/power/collie_battery.c +++ b/drivers/power/collie_battery.c @@ -290,7 +290,7 @@ static struct gpio collie_batt_gpios[] = { static int collie_bat_suspend(struct ucb1x00_dev *dev, pm_message_t state) { /* flush all pending status updates */ - flush_work_sync(&bat_work); + flush_work(&bat_work); return 0; } diff --git a/drivers/power/tosa_battery.c b/drivers/power/tosa_battery.c index 28bbe7e094e3..51199b5ce221 100644 --- a/drivers/power/tosa_battery.c +++ b/drivers/power/tosa_battery.c @@ -327,7 +327,7 @@ static struct gpio tosa_bat_gpios[] = { static int tosa_bat_suspend(struct platform_device *dev, pm_message_t state) { /* flush all pending status updates */ - flush_work_sync(&bat_work); + flush_work(&bat_work); return 0; } diff --git a/drivers/power/wm97xx_battery.c b/drivers/power/wm97xx_battery.c index d2d4c08c681c..1245fe1f48c3 100644 --- a/drivers/power/wm97xx_battery.c +++ b/drivers/power/wm97xx_battery.c @@ -146,7 +146,7 @@ static irqreturn_t wm97xx_chrg_irq(int irq, void *data) #ifdef CONFIG_PM static int wm97xx_bat_suspend(struct device *dev) { - flush_work_sync(&bat_work); + flush_work(&bat_work); return 0; } diff --git a/drivers/power/z2_battery.c b/drivers/power/z2_battery.c index 8c9a607ea77a..5757d0d6782f 100644 --- a/drivers/power/z2_battery.c +++ b/drivers/power/z2_battery.c @@ -276,7 +276,7 @@ static int z2_batt_suspend(struct device *dev) struct i2c_client *client = to_i2c_client(dev); struct z2_charger *charger = i2c_get_clientdata(client); - flush_work_sync(&charger->bat_work); + flush_work(&charger->bat_work); return 0; } diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index f092588a078c..1d2b70017a8d 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -3335,7 +3335,7 @@ void regulator_unregister(struct regulator_dev *rdev) regulator_put(rdev->supply); mutex_lock(®ulator_list_mutex); debugfs_remove_recursive(rdev->debugfs); - flush_work_sync(&rdev->disable_work.work); + flush_work(&rdev->disable_work.work); WARN_ON(rdev->open_count); unset_regulator_supplies(rdev); list_del(&rdev->list); diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index def24a1079ad..33c52bc2c7b4 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -999,7 +999,7 @@ static void arcmsr_remove(struct pci_dev *pdev) int poll_count = 0; arcmsr_free_sysfs_attr(acb); scsi_remove_host(host); - flush_work_sync(&acb->arcmsr_do_message_isr_bh); + flush_work(&acb->arcmsr_do_message_isr_bh); del_timer_sync(&acb->eternal_timer); arcmsr_disable_outbound_ints(acb); arcmsr_stop_adapter_bgrb(acb); @@ -1045,7 +1045,7 @@ static void arcmsr_shutdown(struct pci_dev *pdev) (struct AdapterControlBlock *)host->hostdata; del_timer_sync(&acb->eternal_timer); arcmsr_disable_outbound_ints(acb); - flush_work_sync(&acb->arcmsr_do_message_isr_bh); + flush_work(&acb->arcmsr_do_message_isr_bh); arcmsr_stop_adapter_bgrb(acb); arcmsr_flush_adapter_cache(acb); } diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 467dc38246f9..2ffeb9afd1b7 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -9020,7 +9020,7 @@ static void __ipr_remove(struct pci_dev *pdev) spin_unlock_irqrestore(ioa_cfg->host->host_lock, host_lock_flags); wait_event(ioa_cfg->reset_wait_q, !ioa_cfg->in_reset_reload); - flush_work_sync(&ioa_cfg->work_q); + flush_work(&ioa_cfg->work_q); spin_lock_irqsave(ioa_cfg->host->host_lock, host_lock_flags); spin_lock(&ipr_driver_lock); diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index ea8a0b47d66d..af763eab2039 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -5459,7 +5459,7 @@ static void __devexit pmcraid_remove(struct pci_dev *pdev) pmcraid_shutdown(pdev); pmcraid_disable_interrupts(pinstance, ~0); - flush_work_sync(&pinstance->worker_q); + flush_work(&pinstance->worker_q); pmcraid_kill_tasklets(pinstance); pmcraid_unregister_interrupt_handler(pinstance); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 5b30132960c7..bddc97c5c8e9 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -969,7 +969,7 @@ void qlt_stop_phase1(struct qla_tgt *tgt) spin_unlock_irqrestore(&ha->hardware_lock, flags); mutex_unlock(&ha->tgt.tgt_mutex); - flush_delayed_work_sync(&tgt->sess_del_work); + flush_delayed_work(&tgt->sess_del_work); ql_dbg(ql_dbg_tgt_mgt, vha, 0xf009, "Waiting for sess works (tgt %p)", tgt); diff --git a/drivers/tty/hvc/hvsi.c b/drivers/tty/hvc/hvsi.c index 6f5bc49c441f..1f8e8b37ed23 100644 --- a/drivers/tty/hvc/hvsi.c +++ b/drivers/tty/hvc/hvsi.c @@ -765,7 +765,7 @@ static void hvsi_flush_output(struct hvsi_struct *hp) /* 'writer' could still be pending if it didn't see n_outbuf = 0 yet */ cancel_delayed_work_sync(&hp->writer); - flush_work_sync(&hp->handshaker); + flush_work(&hp->handshaker); /* * it's also possible that our timeout expired and hvsi_write_worker diff --git a/drivers/tty/ipwireless/hardware.c b/drivers/tty/ipwireless/hardware.c index 0aeb5a38d296..b4ba0670dc54 100644 --- a/drivers/tty/ipwireless/hardware.c +++ b/drivers/tty/ipwireless/hardware.c @@ -1729,7 +1729,7 @@ void ipwireless_hardware_free(struct ipw_hardware *hw) ipwireless_stop_interrupts(hw); - flush_work_sync(&hw->work_rx); + flush_work(&hw->work_rx); for (i = 0; i < NL_NUM_OF_ADDRESSES; i++) if (hw->packet_assembler[i] != NULL) diff --git a/drivers/tty/ipwireless/network.c b/drivers/tty/ipwireless/network.c index 57c8b481113f..90ea902ff191 100644 --- a/drivers/tty/ipwireless/network.c +++ b/drivers/tty/ipwireless/network.c @@ -430,8 +430,8 @@ void ipwireless_network_free(struct ipw_network *network) network->shutting_down = 1; ipwireless_ppp_close(network); - flush_work_sync(&network->work_go_online); - flush_work_sync(&network->work_go_offline); + flush_work(&network->work_go_online); + flush_work(&network->work_go_offline); ipwireless_stop_interrupts(network->hardware); ipwireless_associate_network(network->hardware, NULL); diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c index 2b42a01a81c6..ebabf929f460 100644 --- a/drivers/tty/serial/kgdboc.c +++ b/drivers/tty/serial/kgdboc.c @@ -122,7 +122,7 @@ static void kgdboc_unregister_kbd(void) i--; } } - flush_work_sync(&kgdboc_restore_input_work); + flush_work(&kgdboc_restore_input_work); } #else /* ! CONFIG_KDB_KEYBOARD */ #define kgdboc_register_kbd(x) 0 diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index d3cda0cb2df0..0952d71bdf28 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1205,7 +1205,7 @@ static int serial_omap_suspend(struct device *dev) if (up) { uart_suspend_port(&serial_omap_reg, &up->port); - flush_work_sync(&up->qos_work); + flush_work(&up->qos_work); } return 0; diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 6f99c9959f0c..ac5be812dbe3 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -523,9 +523,9 @@ static int tty_ldisc_halt(struct tty_struct *tty) */ static void tty_ldisc_flush_works(struct tty_struct *tty) { - flush_work_sync(&tty->hangup_work); - flush_work_sync(&tty->SAK_work); - flush_work_sync(&tty->buf.work); + flush_work(&tty->hangup_work); + flush_work(&tty->SAK_work); + flush_work(&tty->buf.work); } /** diff --git a/drivers/usb/atm/speedtch.c b/drivers/usb/atm/speedtch.c index 975e9c6691d6..807627b36cc8 100644 --- a/drivers/usb/atm/speedtch.c +++ b/drivers/usb/atm/speedtch.c @@ -718,7 +718,7 @@ static void speedtch_atm_stop(struct usbatm_data *usbatm, struct atm_dev *atm_de del_timer_sync(&instance->resubmit_timer); usb_free_urb(int_urb); - flush_work_sync(&instance->status_check_work); + flush_work(&instance->status_check_work); } static int speedtch_pre_reset(struct usb_interface *intf) diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c index d7e422dc0ef7..9d1a044504e8 100644 --- a/drivers/usb/atm/ueagle-atm.c +++ b/drivers/usb/atm/ueagle-atm.c @@ -2234,7 +2234,7 @@ static void uea_stop(struct uea_softc *sc) usb_free_urb(sc->urb_int); /* flush the work item, when no one can schedule it */ - flush_work_sync(&sc->task); + flush_work(&sc->task); release_firmware(sc->dsp_firm); uea_leaves(INS_TO_USBDEV(sc)); diff --git a/drivers/usb/gadget/u_ether.c b/drivers/usb/gadget/u_ether.c index 90e82e288eb9..f1e5fbf5c2c7 100644 --- a/drivers/usb/gadget/u_ether.c +++ b/drivers/usb/gadget/u_ether.c @@ -834,7 +834,7 @@ void gether_cleanup(void) return; unregister_netdev(the_dev->net); - flush_work_sync(&the_dev->work); + flush_work(&the_dev->work); free_netdev(the_dev->net); the_dev = NULL; diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 2b1e8d84c873..2364098ea83c 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -893,7 +893,7 @@ static void ohci_stop (struct usb_hcd *hcd) ohci_dump (ohci, 1); if (quirk_nec(ohci)) - flush_work_sync(&ohci->nec_work); + flush_work(&ohci->nec_work); ohci_usb_reset (ohci); ohci_writel (ohci, OHCI_INTR_MIE, &ohci->regs->intrdisable); diff --git a/drivers/usb/otg/isp1301_omap.c b/drivers/usb/otg/isp1301_omap.c index 7a88667742b6..720df35561c9 100644 --- a/drivers/usb/otg/isp1301_omap.c +++ b/drivers/usb/otg/isp1301_omap.c @@ -1230,7 +1230,7 @@ static int __exit isp1301_remove(struct i2c_client *i2c) isp->timer.data = 0; set_bit(WORK_STOP, &isp->todo); del_timer_sync(&isp->timer); - flush_work_sync(&isp->work); + flush_work(&isp->work); put_device(&i2c->dev); the_transceiver = NULL; diff --git a/fs/affs/super.c b/fs/affs/super.c index c70f1e5fc024..022cecb0757d 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -551,7 +551,7 @@ affs_remount(struct super_block *sb, int *flags, char *data) return -EINVAL; } - flush_delayed_work_sync(&sbi->sb_work); + flush_delayed_work(&sbi->sb_work); replace_mount_options(sb, new_opts); sbi->s_flags = mount_flags; diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 4a38db739ca0..0fb6539b0c8c 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -1289,7 +1289,7 @@ static void gdlm_unmount(struct gfs2_sbd *sdp) spin_lock(&ls->ls_recover_spin); set_bit(DFL_UNMOUNT, &ls->ls_recover_flags); spin_unlock(&ls->ls_recover_spin); - flush_delayed_work_sync(&sdp->sd_control_work); + flush_delayed_work(&sdp->sd_control_work); /* mounted_lock and control_lock will be purged in dlm recovery */ release: diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index fc3168f47a14..867700aba536 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1572,7 +1572,7 @@ out: clear_inode(inode); gfs2_dir_hash_inval(ip); ip->i_gl->gl_object = NULL; - flush_delayed_work_sync(&ip->i_gl->gl_work); + flush_delayed_work(&ip->i_gl->gl_work); gfs2_glock_add_to_lru(ip->i_gl); gfs2_glock_put(ip->i_gl); ip->i_gl = NULL; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index ee1bc55677f1..553909395270 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -644,7 +644,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end, /* sync the superblock to buffers */ sb = inode->i_sb; - flush_delayed_work_sync(&HFS_SB(sb)->mdb_work); + flush_delayed_work(&HFS_SB(sb)->mdb_work); /* .. finally sync the buffers to disk */ err = sync_blockdev(sb->s_bdev); if (!ret) diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 333df07ae3bd..eaa74323663a 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -314,11 +314,11 @@ static void ncp_stop_tasks(struct ncp_server *server) { release_sock(sk); del_timer_sync(&server->timeout_tm); - flush_work_sync(&server->rcv.tq); + flush_work(&server->rcv.tq); if (sk->sk_socket->type == SOCK_STREAM) - flush_work_sync(&server->tx.tq); + flush_work(&server->tx.tq); else - flush_work_sync(&server->timeout_tq); + flush_work(&server->timeout_tq); } static int ncp_show_options(struct seq_file *seq, struct dentry *root) diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c index 8f9cea1597af..c19897d0fe14 100644 --- a/fs/ocfs2/cluster/quorum.c +++ b/fs/ocfs2/cluster/quorum.c @@ -327,5 +327,5 @@ void o2quo_exit(void) { struct o2quo_state *qs = &o2quo_state; - flush_work_sync(&qs->qs_work); + flush_work(&qs->qs_work); } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index bdaf4cb9f4a2..e8e6be439bcd 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -953,7 +953,7 @@ xfs_fs_sync_fs( * We schedule xfssyncd now (now that the disk is * active) instead of later (when it might not be). */ - flush_delayed_work_sync(&mp->m_sync_work); + flush_delayed_work(&mp->m_sync_work); } return 0; diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c index 96548176db80..9500caf15acf 100644 --- a/fs/xfs/xfs_sync.c +++ b/fs/xfs/xfs_sync.c @@ -475,7 +475,7 @@ xfs_flush_inodes( struct xfs_mount *mp = ip->i_mount; queue_work(xfs_syncd_wq, &mp->m_flush_work); - flush_work_sync(&mp->m_flush_work); + flush_work(&mp->m_flush_work); } STATIC void diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 855fcdaa2d72..a351be7c3e91 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -460,13 +460,13 @@ static inline bool __cancel_delayed_work(struct delayed_work *work) } /* used to be different but now identical to flush_work(), deprecated */ -static inline bool flush_work_sync(struct work_struct *work) +static inline bool __deprecated flush_work_sync(struct work_struct *work) { return flush_work(work); } /* used to be different but now identical to flush_delayed_work(), deprecated */ -static inline bool flush_delayed_work_sync(struct delayed_work *dwork) +static inline bool __deprecated flush_delayed_work_sync(struct delayed_work *dwork) { return flush_delayed_work(dwork); } diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 6449bae15702..505f0ce3f10b 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1083,7 +1083,7 @@ int p9_trans_fd_init(void) void p9_trans_fd_exit(void) { - flush_work_sync(&p9_poll_work); + flush_work(&p9_poll_work); v9fs_unregister_trans(&p9_tcp_trans); v9fs_unregister_trans(&p9_unix_trans); v9fs_unregister_trans(&p9_fd_trans); diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 88e7c2f3fa0d..45295ca09571 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -370,7 +370,7 @@ static int dsa_remove(struct platform_device *pdev) if (dst->link_poll_needed) del_timer_sync(&dst->link_poll_timer); - flush_work_sync(&dst->link_poll_work); + flush_work(&dst->link_poll_work); for (i = 0; i < dst->pd->nr_chips; i++) { struct dsa_switch *ds = dst->ds[i]; diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c index dde5c9c92132..ef68d710d08c 100644 --- a/sound/i2c/other/ak4113.c +++ b/sound/i2c/other/ak4113.c @@ -141,7 +141,7 @@ void snd_ak4113_reinit(struct ak4113 *chip) { chip->init = 1; mb(); - flush_delayed_work_sync(&chip->work); + flush_delayed_work(&chip->work); ak4113_init_regs(chip); /* bring up statistics / event queing */ chip->init = 0; diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c index fdf3c1b65e38..816e7d225fb0 100644 --- a/sound/i2c/other/ak4114.c +++ b/sound/i2c/other/ak4114.c @@ -154,7 +154,7 @@ void snd_ak4114_reinit(struct ak4114 *chip) { chip->init = 1; mb(); - flush_delayed_work_sync(&chip->work); + flush_delayed_work(&chip->work); ak4114_init_regs(chip); /* bring up statistics / event queing */ chip->init = 0; diff --git a/sound/pci/oxygen/oxygen_lib.c b/sound/pci/oxygen/oxygen_lib.c index ab8738e21ad1..e9fa2d07951d 100644 --- a/sound/pci/oxygen/oxygen_lib.c +++ b/sound/pci/oxygen/oxygen_lib.c @@ -573,8 +573,8 @@ static void oxygen_card_free(struct snd_card *card) oxygen_shutdown(chip); if (chip->irq >= 0) free_irq(chip->irq, chip); - flush_work_sync(&chip->spdif_input_bits_work); - flush_work_sync(&chip->gpio_work); + flush_work(&chip->spdif_input_bits_work); + flush_work(&chip->gpio_work); chip->model.cleanup(chip); kfree(chip->model_data); mutex_destroy(&chip->mutex); @@ -751,8 +751,8 @@ static int oxygen_pci_suspend(struct device *dev) spin_unlock_irq(&chip->reg_lock); synchronize_irq(chip->irq); - flush_work_sync(&chip->spdif_input_bits_work); - flush_work_sync(&chip->gpio_work); + flush_work(&chip->spdif_input_bits_work); + flush_work(&chip->gpio_work); chip->interrupt_mask = saved_interrupt_mask; pci_disable_device(pci); diff --git a/sound/soc/codecs/wm8350.c b/sound/soc/codecs/wm8350.c index d26c8ae4e6d9..a4cae060bf26 100644 --- a/sound/soc/codecs/wm8350.c +++ b/sound/soc/codecs/wm8350.c @@ -1601,7 +1601,7 @@ static int wm8350_codec_remove(struct snd_soc_codec *codec) /* if there was any work waiting then we run it now and * wait for its completion */ - flush_delayed_work_sync(&codec->dapm.delayed_work); + flush_delayed_work(&codec->dapm.delayed_work); wm8350_set_bias_level(codec, SND_SOC_BIAS_OFF); diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c index 13bff87ddcf5..2e4a775ae560 100644 --- a/sound/soc/codecs/wm8753.c +++ b/sound/soc/codecs/wm8753.c @@ -1509,7 +1509,7 @@ static int wm8753_probe(struct snd_soc_codec *codec) /* power down chip */ static int wm8753_remove(struct snd_soc_codec *codec) { - flush_delayed_work_sync(&codec->dapm.delayed_work); + flush_delayed_work(&codec->dapm.delayed_work); wm8753_set_bias_level(codec, SND_SOC_BIAS_OFF); return 0; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index f219b2f7ee68..f6eec782c61e 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -591,7 +591,7 @@ int snd_soc_suspend(struct device *dev) /* close any waiting streams and save state */ for (i = 0; i < card->num_rtd; i++) { - flush_delayed_work_sync(&card->rtd[i].delayed_work); + flush_delayed_work(&card->rtd[i].delayed_work); card->rtd[i].codec->dapm.suspend_bias_level = card->rtd[i].codec->dapm.bias_level; } @@ -1846,7 +1846,7 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card) /* make sure any delayed work runs */ for (i = 0; i < card->num_rtd; i++) { struct snd_soc_pcm_runtime *rtd = &card->rtd[i]; - flush_delayed_work_sync(&rtd->delayed_work); + flush_delayed_work(&rtd->delayed_work); } /* remove auxiliary devices */ @@ -1890,7 +1890,7 @@ int snd_soc_poweroff(struct device *dev) * now, we're shutting down so no imminent restart. */ for (i = 0; i < card->num_rtd; i++) { struct snd_soc_pcm_runtime *rtd = &card->rtd[i]; - flush_delayed_work_sync(&rtd->delayed_work); + flush_delayed_work(&rtd->delayed_work); } snd_soc_dapm_shutdown(card); diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 7d7e2aaffece..67a35e90384c 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -90,7 +90,7 @@ irqfd_shutdown(struct work_struct *work) * We know no new events will be scheduled at this point, so block * until all previously outstanding events have completed */ - flush_work_sync(&irqfd->inject); + flush_work(&irqfd->inject); /* * It is now safe to release the object's resources -- cgit v1.2.3 From e86fd89188abcc3288ca760a064000054110b2bb Mon Sep 17 00:00:00 2001 From: Bruce W Allan Date: Thu, 26 Jul 2012 02:30:59 +0000 Subject: e1000e: implement 82577/579 MDI setting support In order for e1000e to support MDI setting support via ethtool this code is needed to allow setting the MDI state via software. This is in regards to the related ethtool patch and fixes bugzilla.kernel.org bug 11998 Signed-off-by: Bruce W Allan Signed-off-by: Jesse Brandeburg Tested-by: Aaron Brown aaron.f.brown@intel.com Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/phy.c | 31 +++++++++++++++++++++++++++++-- 1 file changed, 29 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index b860d4f7ea2a..fc62a3f3a5be 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -84,8 +84,9 @@ static const u16 e1000_igp_2_cable_length_table[] = { #define I82577_PHY_STATUS2_SPEED_1000MBPS 0x0200 /* I82577 PHY Control 2 */ -#define I82577_PHY_CTRL2_AUTO_MDIX 0x0400 -#define I82577_PHY_CTRL2_FORCE_MDI_MDIX 0x0200 +#define I82577_PHY_CTRL2_MANUAL_MDIX 0x0200 +#define I82577_PHY_CTRL2_AUTO_MDI_MDIX 0x0400 +#define I82577_PHY_CTRL2_MDIX_CFG_MASK 0x0600 /* I82577 PHY Diagnostics Status */ #define I82577_DSTATUS_CABLE_LENGTH 0x03FC @@ -702,6 +703,32 @@ s32 e1000_copper_link_setup_82577(struct e1000_hw *hw) if (ret_val) return ret_val; + /* Set MDI/MDIX mode */ + ret_val = e1e_rphy(hw, I82577_PHY_CTRL_2, &phy_data); + if (ret_val) + return ret_val; + phy_data &= ~I82577_PHY_CTRL2_MDIX_CFG_MASK; + /* + * Options: + * 0 - Auto (default) + * 1 - MDI mode + * 2 - MDI-X mode + */ + switch (hw->phy.mdix) { + case 1: + break; + case 2: + phy_data |= I82577_PHY_CTRL2_MANUAL_MDIX; + break; + case 0: + default: + phy_data |= I82577_PHY_CTRL2_AUTO_MDI_MDIX; + break; + } + ret_val = e1e_wphy(hw, I82577_PHY_CTRL_2, phy_data); + if (ret_val) + return ret_val; + return e1000_set_master_slave_mode(hw); } -- cgit v1.2.3 From 1b556783abe92d3bfedf0d0eb3af2319947739ae Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 26 Jul 2012 02:31:04 +0000 Subject: igb: implement 580 MDI setting support In order for igb to support MDI setting support via ethtool this code is needed to allow setting the MDI state via software. This is in regards to the related ethtool patch Signed-off-by: Jesse Brandeburg Tested-by: Aaron Brown aaron.f.brown@intel.com Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/e1000_phy.c | 29 +++++++++++++++++++++++++++-- drivers/net/ethernet/intel/igb/e1000_phy.h | 5 +++-- 2 files changed, 30 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c index 7be98b6f1052..3404bc79f4ca 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.c +++ b/drivers/net/ethernet/intel/igb/e1000_phy.c @@ -464,6 +464,32 @@ s32 igb_copper_link_setup_82580(struct e1000_hw *hw) phy_data |= I82580_CFG_ENABLE_DOWNSHIFT; ret_val = phy->ops.write_reg(hw, I82580_CFG_REG, phy_data); + if (ret_val) + goto out; + + /* Set MDI/MDIX mode */ + ret_val = phy->ops.read_reg(hw, I82580_PHY_CTRL_2, &phy_data); + if (ret_val) + goto out; + phy_data &= ~I82580_PHY_CTRL2_MDIX_CFG_MASK; + /* + * Options: + * 0 - Auto (default) + * 1 - MDI mode + * 2 - MDI-X mode + */ + switch (hw->phy.mdix) { + case 1: + break; + case 2: + phy_data |= I82580_PHY_CTRL2_MANUAL_MDIX; + break; + case 0: + default: + phy_data |= I82580_PHY_CTRL2_AUTO_MDI_MDIX; + break; + } + ret_val = hw->phy.ops.write_reg(hw, I82580_PHY_CTRL_2, phy_data); out: return ret_val; @@ -2246,8 +2272,7 @@ s32 igb_phy_force_speed_duplex_82580(struct e1000_hw *hw) if (ret_val) goto out; - phy_data &= ~I82580_PHY_CTRL2_AUTO_MDIX; - phy_data &= ~I82580_PHY_CTRL2_FORCE_MDI_MDIX; + phy_data &= ~I82580_PHY_CTRL2_MDIX_CFG_MASK; ret_val = phy->ops.write_reg(hw, I82580_PHY_CTRL_2, phy_data); if (ret_val) diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.h b/drivers/net/ethernet/intel/igb/e1000_phy.h index 34e40619f16b..6ac3299bfcb9 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.h +++ b/drivers/net/ethernet/intel/igb/e1000_phy.h @@ -111,8 +111,9 @@ s32 igb_check_polarity_m88(struct e1000_hw *hw); #define I82580_PHY_STATUS2_SPEED_100MBPS 0x0100 /* I82580 PHY Control 2 */ -#define I82580_PHY_CTRL2_AUTO_MDIX 0x0400 -#define I82580_PHY_CTRL2_FORCE_MDI_MDIX 0x0200 +#define I82580_PHY_CTRL2_MANUAL_MDIX 0x0200 +#define I82580_PHY_CTRL2_AUTO_MDI_MDIX 0x0400 +#define I82580_PHY_CTRL2_MDIX_CFG_MASK 0x0600 /* I82580 PHY Diagnostics Status */ #define I82580_DSTATUS_CABLE_LENGTH 0x03FC -- cgit v1.2.3 From c819bbd5eca29aa0d4f35612b7c795c23d38efc3 Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 26 Jul 2012 02:31:09 +0000 Subject: e1000: configure and read MDI settings This is the implementation in e1000 to allow ethtool to force MDI state, allowing users to work around some improperly behaving switches. Forcing in this driver is for now only allowed when auto-neg is enabled. To use must have the matching version of ethtool app that supports this functionality. Signed-off-by: Jesse Brandeburg CC: Tushar Dave Tested-by: Aaron Brown aaron.f.brown@intel.com Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000/e1000_ethtool.c | 39 ++++++++++++++++++++++++ drivers/net/ethernet/intel/e1000/e1000_main.c | 4 +++ 2 files changed, 43 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 736a7d987db5..9089d00f1421 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -174,6 +174,20 @@ static int e1000_get_settings(struct net_device *netdev, ecmd->autoneg = ((hw->media_type == e1000_media_type_fiber) || hw->autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE; + + /* MDI-X => 1; MDI => 0 */ + if ((hw->media_type == e1000_media_type_copper) && + netif_carrier_ok(netdev)) + ecmd->eth_tp_mdix = (!!adapter->phy_info.mdix_mode ? + ETH_TP_MDI_X : + ETH_TP_MDI); + else + ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID; + + if (hw->mdix == AUTO_ALL_MODES) + ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + else + ecmd->eth_tp_mdix_ctrl = hw->mdix; return 0; } @@ -183,6 +197,22 @@ static int e1000_set_settings(struct net_device *netdev, struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + /* + * MDI setting is only allowed when autoneg enabled because + * some hardware doesn't allow MDI setting when speed or + * duplex is forced. + */ + if (ecmd->eth_tp_mdix_ctrl) { + if (hw->media_type != e1000_media_type_copper) + return -EOPNOTSUPP; + + if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && + (ecmd->autoneg != AUTONEG_ENABLE)) { + e_err(drv, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); + return -EINVAL; + } + } + while (test_and_set_bit(__E1000_RESETTING, &adapter->flags)) msleep(1); @@ -199,12 +229,21 @@ static int e1000_set_settings(struct net_device *netdev, ecmd->advertising = hw->autoneg_advertised; } else { u32 speed = ethtool_cmd_speed(ecmd); + /* calling this overrides forced MDI setting */ if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) { clear_bit(__E1000_RESETTING, &adapter->flags); return -EINVAL; } } + /* MDI-X => 2; MDI => 1; Auto => 3 */ + if (ecmd->eth_tp_mdix_ctrl) { + if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) + hw->mdix = AUTO_ALL_MODES; + else + hw->mdix = ecmd->eth_tp_mdix_ctrl; + } + /* reset the link */ if (netif_running(adapter->netdev)) { diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 3bfbb8df8989..0ae2fcfa5124 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -4939,6 +4939,10 @@ int e1000_set_spd_dplx(struct e1000_adapter *adapter, u32 spd, u8 dplx) default: goto err_inval; } + + /* clear MDI, MDI(-X) override is only allowed when autoneg enabled */ + hw->mdix = AUTO_ALL_MODES; + return 0; err_inval: -- cgit v1.2.3 From 4e8186b68fb944ad9e7fd4080cd8bd8f10eb7cbd Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 26 Jul 2012 02:31:14 +0000 Subject: e1000e: implement MDI/MDI-X control Some users report issues with link failing when connected to certain switches. This gives the user the ability to control the MDI state from the driver, allowing users to work around some improperly behaving switches. Forcing in this driver is for now only allowed when auto-neg is enabled. This is in regards to the related ethtool app patch and bugzilla.kernel.org bug 11998 Signed-off-by: Jesse Brandeburg CC: bruce.w.allan@intel.com CC: n.poppelier@xs4all.nl CC: bastien@durel.org CC: jsveiga@it.eng.br Tested-by: Aaron Brown aaron.f.brown@intel.com Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/ethtool.c | 41 +++++++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 0349e2478df8..2e76f06720fd 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -199,6 +199,11 @@ static int e1000_get_settings(struct net_device *netdev, else ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID; + if (hw->phy.mdix == AUTO_ALL_MODES) + ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + else + ecmd->eth_tp_mdix_ctrl = hw->phy.mdix; + return 0; } @@ -241,6 +246,10 @@ static int e1000_set_spd_dplx(struct e1000_adapter *adapter, u32 spd, u8 dplx) default: goto err_inval; } + + /* clear MDI, MDI(-X) override is only allowed when autoneg enabled */ + adapter->hw.phy.mdix = AUTO_ALL_MODES; + return 0; err_inval: @@ -264,6 +273,22 @@ static int e1000_set_settings(struct net_device *netdev, return -EINVAL; } + /* + * MDI setting is only allowed when autoneg enabled because + * some hardware doesn't allow MDI setting when speed or + * duplex is forced. + */ + if (ecmd->eth_tp_mdix_ctrl) { + if (hw->phy.media_type != e1000_media_type_copper) + return -EOPNOTSUPP; + + if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && + (ecmd->autoneg != AUTONEG_ENABLE)) { + e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); + return -EINVAL; + } + } + while (test_and_set_bit(__E1000_RESETTING, &adapter->state)) usleep_range(1000, 2000); @@ -282,20 +307,32 @@ static int e1000_set_settings(struct net_device *netdev, hw->fc.requested_mode = e1000_fc_default; } else { u32 speed = ethtool_cmd_speed(ecmd); + /* calling this overrides forced MDI setting */ if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) { clear_bit(__E1000_RESETTING, &adapter->state); return -EINVAL; } } + /* MDI-X => 2; MDI => 1; Auto => 3 */ + if (ecmd->eth_tp_mdix_ctrl) { + /* + * fix up the value for auto (3 => 0) as zero is mapped + * internally to auto + */ + if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) + hw->phy.mdix = AUTO_ALL_MODES; + else + hw->phy.mdix = ecmd->eth_tp_mdix_ctrl; + } + /* reset the link */ if (netif_running(adapter->netdev)) { e1000e_down(adapter); e1000e_up(adapter); - } else { + } else e1000e_reset(adapter); - } clear_bit(__E1000_RESETTING, &adapter->state); return 0; -- cgit v1.2.3 From 8376dad0c877bc691b2feadd3390a162aa3c3bd9 Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 26 Jul 2012 02:31:19 +0000 Subject: igb: update to allow reading/setting MDI state This is the implementation for igb to allow forcing MDI state via ethtool, allowing users to work around some improperly behaving switches. Forcing in this driver is for now only allowed when auto-neg is enabled. Signed-off-by: Jesse Brandeburg CC: Carolyn Wyborny Tested-by: Aaron Brown aaron.f.brown@intel.com Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_ethtool.c | 42 ++++++++++++++++++++++++++++ drivers/net/ethernet/intel/igb/igb_main.c | 4 +++ 2 files changed, 46 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index a19c84cad0e9..cf0e9fb45cbd 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -198,6 +198,19 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) } ecmd->autoneg = hw->mac.autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE; + + /* MDI-X => 2; MDI =>1; Invalid =>0 */ + if (hw->phy.media_type == e1000_media_type_copper) + ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X : + ETH_TP_MDI; + else + ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID; + + if (hw->phy.mdix == AUTO_ALL_MODES) + ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + else + ecmd->eth_tp_mdix_ctrl = hw->phy.mdix; + return 0; } @@ -214,6 +227,22 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) return -EINVAL; } + /* + * MDI setting is only allowed when autoneg enabled because + * some hardware doesn't allow MDI setting when speed or + * duplex is forced. + */ + if (ecmd->eth_tp_mdix_ctrl) { + if (hw->phy.media_type != e1000_media_type_copper) + return -EOPNOTSUPP; + + if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && + (ecmd->autoneg != AUTONEG_ENABLE)) { + dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); + return -EINVAL; + } + } + while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) msleep(1); @@ -227,12 +256,25 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) hw->fc.requested_mode = e1000_fc_default; } else { u32 speed = ethtool_cmd_speed(ecmd); + /* calling this overrides forced MDI setting */ if (igb_set_spd_dplx(adapter, speed, ecmd->duplex)) { clear_bit(__IGB_RESETTING, &adapter->state); return -EINVAL; } } + /* MDI-X => 2; MDI => 1; Auto => 3 */ + if (ecmd->eth_tp_mdix_ctrl) { + /* + * fix up the value for auto (3 => 0) as zero is mapped + * internally to auto + */ + if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) + hw->phy.mdix = AUTO_ALL_MODES; + else + hw->phy.mdix = ecmd->eth_tp_mdix_ctrl; + } + /* reset the link */ if (netif_running(adapter->netdev)) { igb_down(adapter); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b7c2d5050572..d4f47a0f6689 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6676,6 +6676,10 @@ int igb_set_spd_dplx(struct igb_adapter *adapter, u32 spd, u8 dplx) default: goto err_inval; } + + /* clear MDI, MDI(-X) override is only allowed when autoneg enabled */ + adapter->hw.phy.mdix = AUTO_ALL_MODES; + return 0; err_inval: -- cgit v1.2.3 From 203b42f7317494ae5e5efc7be6fb7f29c927f102 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 21 Aug 2012 13:18:23 -0700 Subject: workqueue: make deferrable delayed_work initializer names consistent Initalizers for deferrable delayed_work are confused. * __DEFERRED_WORK_INITIALIZER() * DECLARE_DEFERRED_WORK() * INIT_DELAYED_WORK_DEFERRABLE() Rename them to * __DEFERRABLE_WORK_INITIALIZER() * DECLARE_DEFERRABLE_WORK() * INIT_DEFERRABLE_WORK() This patch doesn't cause any functional changes. Signed-off-by: Tejun Heo --- arch/powerpc/platforms/cell/cpufreq_spudemand.c | 2 +- drivers/cpufreq/cpufreq_conservative.c | 2 +- drivers/cpufreq/cpufreq_ondemand.c | 2 +- drivers/devfreq/devfreq.c | 2 +- drivers/net/ethernet/mellanox/mlx4/sense.c | 2 +- drivers/power/ab8500_btemp.c | 2 +- drivers/power/ab8500_charger.c | 8 ++++---- drivers/power/ab8500_fg.c | 8 ++++---- drivers/power/abx500_chargalg.c | 4 ++-- drivers/power/max17040_battery.c | 2 +- drivers/video/omap2/displays/panel-taal.c | 6 +++--- drivers/video/omap2/dss/dsi.c | 4 ++-- include/linux/workqueue.h | 8 ++++---- mm/slab.c | 2 +- mm/vmstat.c | 2 +- net/core/neighbour.c | 2 +- net/ipv4/inetpeer.c | 2 +- net/sunrpc/cache.c | 2 +- 18 files changed, 31 insertions(+), 31 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c index 23bc9db4317e..82607d621aca 100644 --- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c +++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c @@ -76,7 +76,7 @@ static void spu_gov_work(struct work_struct *work) static void spu_gov_init_work(struct spu_gov_info_struct *info) { int delay = usecs_to_jiffies(info->poll_int); - INIT_DELAYED_WORK_DEFERRABLE(&info->work, spu_gov_work); + INIT_DEFERRABLE_WORK(&info->work, spu_gov_work); schedule_delayed_work_on(info->policy->cpu, &info->work, delay); } diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 235a340e81f2..55f0354864e2 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -466,7 +466,7 @@ static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info) delay -= jiffies % delay; dbs_info->enable = 1; - INIT_DELAYED_WORK_DEFERRABLE(&dbs_info->work, do_dbs_timer); + INIT_DEFERRABLE_WORK(&dbs_info->work, do_dbs_timer); schedule_delayed_work_on(dbs_info->cpu, &dbs_info->work, delay); } diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 836e9b062e5e..14c1af5a264f 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -644,7 +644,7 @@ static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info) delay -= jiffies % delay; dbs_info->sample_type = DBS_NORMAL_SAMPLE; - INIT_DELAYED_WORK_DEFERRABLE(&dbs_info->work, do_dbs_timer); + INIT_DEFERRABLE_WORK(&dbs_info->work, do_dbs_timer); schedule_delayed_work_on(dbs_info->cpu, &dbs_info->work, delay); } diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 70c31d43fff3..b146d76f04cf 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -607,7 +607,7 @@ static int __init devfreq_start_polling(void) mutex_lock(&devfreq_list_lock); polling = false; devfreq_wq = create_freezable_workqueue("devfreq_wq"); - INIT_DELAYED_WORK_DEFERRABLE(&devfreq_work, devfreq_monitor); + INIT_DEFERRABLE_WORK(&devfreq_work, devfreq_monitor); mutex_unlock(&devfreq_list_lock); devfreq_monitor(&devfreq_work.work); diff --git a/drivers/net/ethernet/mellanox/mlx4/sense.c b/drivers/net/ethernet/mellanox/mlx4/sense.c index 802498293528..37b23780a4d8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/sense.c +++ b/drivers/net/ethernet/mellanox/mlx4/sense.c @@ -153,5 +153,5 @@ void mlx4_sense_init(struct mlx4_dev *dev) for (port = 1; port <= dev->caps.num_ports; port++) sense->do_sense_port[port] = 1; - INIT_DELAYED_WORK_DEFERRABLE(&sense->sense_poll, mlx4_sense_port); + INIT_DEFERRABLE_WORK(&sense->sense_poll, mlx4_sense_port); } diff --git a/drivers/power/ab8500_btemp.c b/drivers/power/ab8500_btemp.c index bba3ccac72fe..3041514f4d3f 100644 --- a/drivers/power/ab8500_btemp.c +++ b/drivers/power/ab8500_btemp.c @@ -1018,7 +1018,7 @@ static int __devinit ab8500_btemp_probe(struct platform_device *pdev) } /* Init work for measuring temperature periodically */ - INIT_DELAYED_WORK_DEFERRABLE(&di->btemp_periodic_work, + INIT_DEFERRABLE_WORK(&di->btemp_periodic_work, ab8500_btemp_periodic_work); /* Identify the battery */ diff --git a/drivers/power/ab8500_charger.c b/drivers/power/ab8500_charger.c index d4f0c98428cb..0701dbc2b7e1 100644 --- a/drivers/power/ab8500_charger.c +++ b/drivers/power/ab8500_charger.c @@ -2618,9 +2618,9 @@ static int __devinit ab8500_charger_probe(struct platform_device *pdev) } /* Init work for HW failure check */ - INIT_DELAYED_WORK_DEFERRABLE(&di->check_hw_failure_work, + INIT_DEFERRABLE_WORK(&di->check_hw_failure_work, ab8500_charger_check_hw_failure_work); - INIT_DELAYED_WORK_DEFERRABLE(&di->check_usbchgnotok_work, + INIT_DEFERRABLE_WORK(&di->check_usbchgnotok_work, ab8500_charger_check_usbchargernotok_work); /* @@ -2632,10 +2632,10 @@ static int __devinit ab8500_charger_probe(struct platform_device *pdev) * watchdog have to be kicked by the charger driver * when the AC charger is disabled */ - INIT_DELAYED_WORK_DEFERRABLE(&di->kick_wd_work, + INIT_DEFERRABLE_WORK(&di->kick_wd_work, ab8500_charger_kick_watchdog_work); - INIT_DELAYED_WORK_DEFERRABLE(&di->check_vbat_work, + INIT_DEFERRABLE_WORK(&di->check_vbat_work, ab8500_charger_check_vbat_work); /* Init work for charger detection */ diff --git a/drivers/power/ab8500_fg.c b/drivers/power/ab8500_fg.c index bf022255994c..5c9e7c263c38 100644 --- a/drivers/power/ab8500_fg.c +++ b/drivers/power/ab8500_fg.c @@ -2516,19 +2516,19 @@ static int __devinit ab8500_fg_probe(struct platform_device *pdev) INIT_WORK(&di->fg_acc_cur_work, ab8500_fg_acc_cur_work); /* Init work for reinitialising the fg algorithm */ - INIT_DELAYED_WORK_DEFERRABLE(&di->fg_reinit_work, + INIT_DEFERRABLE_WORK(&di->fg_reinit_work, ab8500_fg_reinit_work); /* Work delayed Queue to run the state machine */ - INIT_DELAYED_WORK_DEFERRABLE(&di->fg_periodic_work, + INIT_DEFERRABLE_WORK(&di->fg_periodic_work, ab8500_fg_periodic_work); /* Work to check low battery condition */ - INIT_DELAYED_WORK_DEFERRABLE(&di->fg_low_bat_work, + INIT_DEFERRABLE_WORK(&di->fg_low_bat_work, ab8500_fg_low_bat_work); /* Init work for HW failure check */ - INIT_DELAYED_WORK_DEFERRABLE(&di->fg_check_hw_failure_work, + INIT_DEFERRABLE_WORK(&di->fg_check_hw_failure_work, ab8500_fg_check_hw_failure_work); /* Initialize OVV, and other registers */ diff --git a/drivers/power/abx500_chargalg.c b/drivers/power/abx500_chargalg.c index 804b88c760d6..4d302803ffcc 100644 --- a/drivers/power/abx500_chargalg.c +++ b/drivers/power/abx500_chargalg.c @@ -1848,9 +1848,9 @@ static int __devinit abx500_chargalg_probe(struct platform_device *pdev) } /* Init work for chargalg */ - INIT_DELAYED_WORK_DEFERRABLE(&di->chargalg_periodic_work, + INIT_DEFERRABLE_WORK(&di->chargalg_periodic_work, abx500_chargalg_periodic_work); - INIT_DELAYED_WORK_DEFERRABLE(&di->chargalg_wd_work, + INIT_DEFERRABLE_WORK(&di->chargalg_wd_work, abx500_chargalg_wd_work); /* Init work for chargalg */ diff --git a/drivers/power/max17040_battery.c b/drivers/power/max17040_battery.c index c284143cfcd7..58e67830143c 100644 --- a/drivers/power/max17040_battery.c +++ b/drivers/power/max17040_battery.c @@ -232,7 +232,7 @@ static int __devinit max17040_probe(struct i2c_client *client, max17040_reset(client); max17040_get_version(client); - INIT_DELAYED_WORK_DEFERRABLE(&chip->work, max17040_work); + INIT_DEFERRABLE_WORK(&chip->work, max17040_work); schedule_delayed_work(&chip->work, MAX17040_DELAY); return 0; diff --git a/drivers/video/omap2/displays/panel-taal.c b/drivers/video/omap2/displays/panel-taal.c index 3f5acc7771da..6b5e6e0e202f 100644 --- a/drivers/video/omap2/displays/panel-taal.c +++ b/drivers/video/omap2/displays/panel-taal.c @@ -906,7 +906,7 @@ static int taal_probe(struct omap_dss_device *dssdev) r = -ENOMEM; goto err_wq; } - INIT_DELAYED_WORK_DEFERRABLE(&td->esd_work, taal_esd_work); + INIT_DEFERRABLE_WORK(&td->esd_work, taal_esd_work); INIT_DELAYED_WORK(&td->ulps_work, taal_ulps_work); dev_set_drvdata(&dssdev->dev, td); @@ -962,8 +962,8 @@ static int taal_probe(struct omap_dss_device *dssdev) goto err_irq; } - INIT_DELAYED_WORK_DEFERRABLE(&td->te_timeout_work, - taal_te_timeout_work_callback); + INIT_DEFERRABLE_WORK(&td->te_timeout_work, + taal_te_timeout_work_callback); dev_dbg(&dssdev->dev, "Using GPIO TE\n"); } diff --git a/drivers/video/omap2/dss/dsi.c b/drivers/video/omap2/dss/dsi.c index b07e8864f82f..fd40f2625051 100644 --- a/drivers/video/omap2/dss/dsi.c +++ b/drivers/video/omap2/dss/dsi.c @@ -4863,8 +4863,8 @@ static int __init omap_dsihw_probe(struct platform_device *dsidev) mutex_init(&dsi->lock); sema_init(&dsi->bus_lock, 1); - INIT_DELAYED_WORK_DEFERRABLE(&dsi->framedone_timeout_work, - dsi_framedone_timeout_work_callback); + INIT_DEFERRABLE_WORK(&dsi->framedone_timeout_work, + dsi_framedone_timeout_work_callback); #ifdef DSI_CATCH_MISSING_TE init_timer(&dsi->te_timer); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 26c5b4c63861..49a9c51f9ee3 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -139,7 +139,7 @@ struct execute_work { 0, (unsigned long)&(n)), \ } -#define __DEFERRED_WORK_INITIALIZER(n, f) { \ +#define __DEFERRABLE_WORK_INITIALIZER(n, f) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = TIMER_DEFERRED_INITIALIZER(delayed_work_timer_fn, \ 0, (unsigned long)&(n)), \ @@ -151,8 +151,8 @@ struct execute_work { #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f) -#define DECLARE_DEFERRED_WORK(n, f) \ - struct delayed_work n = __DEFERRED_WORK_INITIALIZER(n, f) +#define DECLARE_DEFERRABLE_WORK(n, f) \ + struct delayed_work n = __DEFERRABLE_WORK_INITIALIZER(n, f) /* * initialize a work item's function pointer @@ -232,7 +232,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } (_work)->timer.data = (unsigned long)(_work); \ } while (0) -#define INIT_DELAYED_WORK_DEFERRABLE(_work, _func) \ +#define INIT_DEFERRABLE_WORK(_work, _func) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ init_timer_deferrable(&(_work)->timer); \ diff --git a/mm/slab.c b/mm/slab.c index f8b0d539b482..35b5cb0da554 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -900,7 +900,7 @@ static void __cpuinit start_cpu_timer(int cpu) */ if (keventd_up() && reap_work->work.func == NULL) { init_reap_node(cpu); - INIT_DELAYED_WORK_DEFERRABLE(reap_work, cache_reap); + INIT_DEFERRABLE_WORK(reap_work, cache_reap); schedule_delayed_work_on(cpu, reap_work, __round_jiffies_relative(HZ, cpu)); } diff --git a/mm/vmstat.c b/mm/vmstat.c index df7a6748231d..b3e3b9d525d0 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1157,7 +1157,7 @@ static void __cpuinit start_cpu_timer(int cpu) { struct delayed_work *work = &per_cpu(vmstat_work, cpu); - INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update); + INIT_DEFERRABLE_WORK(work, vmstat_update); schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu)); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 117afaf51268..112c6e2266e9 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1545,7 +1545,7 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl) panic("cannot allocate neighbour cache hashes"); rwlock_init(&tbl->lock); - INIT_DELAYED_WORK_DEFERRABLE(&tbl->gc_work, neigh_periodic_work); + INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl); skb_queue_head_init_class(&tbl->proxy_queue, diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e1e0a4e8fd34..7b55c8648d4b 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -194,7 +194,7 @@ void __init inet_initpeers(void) 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); - INIT_DELAYED_WORK_DEFERRABLE(&gc_work, inetpeer_gc_worker); + INIT_DEFERRABLE_WORK(&gc_work, inetpeer_gc_worker); } static int addr_compare(const struct inetpeer_addr *a, diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2afd2a84dc35..2a68bb3db772 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1635,7 +1635,7 @@ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net) void __init cache_initialize(void) { - INIT_DELAYED_WORK_DEFERRABLE(&cache_cleaner, do_cache_clean); + INIT_DEFERRABLE_WORK(&cache_cleaner, do_cache_clean); } int cache_register_net(struct cache_detail *cd, struct net *net) -- cgit v1.2.3 From 62f87c0e31d646d5501edf4f7feb07d0ad689d80 Mon Sep 17 00:00:00 2001 From: Yijing Wang Date: Tue, 24 Jul 2012 17:20:03 +0800 Subject: PCI: Introduce pci_pcie_type(dev) to replace pci_dev->pcie_type Introduce an inline function pci_pcie_type(dev) to extract PCIe device type from pci_dev->pcie_flags_reg field, and prepare for removing pci_dev->pcie_type. Signed-off-by: Yijing Wang Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas --- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- drivers/iommu/intel-iommu.c | 6 ++-- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- .../net/ethernet/qlogic/netxen/netxen_nic_main.c | 2 +- drivers/pci/iov.c | 6 ++-- drivers/pci/pci.c | 26 +++++++------- drivers/pci/pcie/aer/aer_inject.c | 2 +- drivers/pci/pcie/aer/aerdrv.c | 7 ++-- drivers/pci/pcie/aer/aerdrv_acpi.c | 2 +- drivers/pci/pcie/aer/aerdrv_core.c | 2 +- drivers/pci/pcie/aspm.c | 42 +++++++++++----------- drivers/pci/pcie/pme.c | 6 ++-- drivers/pci/pcie/portdrv_bus.c | 2 +- drivers/pci/pcie/portdrv_core.c | 4 +-- drivers/pci/pcie/portdrv_pci.c | 8 ++--- drivers/pci/probe.c | 9 ++--- drivers/pci/search.c | 2 +- 17 files changed, 67 insertions(+), 63 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 9cda6a1ad0cf..b46e1dadc882 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -855,7 +855,7 @@ static void __devinit pnv_ioda_setup_PEs(struct pci_bus *bus) if (pe == NULL) continue; /* Leaving the PCIe domain ... single PE# */ - if (dev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) + if (pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE) pnv_ioda_setup_bus_PE(dev, pe); else if (dev->subordinate) pnv_ioda_setup_PEs(dev->subordinate); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 7469b5346643..8b5075d6dd5a 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2350,7 +2350,7 @@ static int iommu_should_identity_map(struct pci_dev *pdev, int startup) return 0; if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI) return 0; - } else if (pdev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) + } else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE) return 0; /* @@ -3545,10 +3545,10 @@ found: struct pci_dev *bridge = bus->self; if (!bridge || !pci_is_pcie(bridge) || - bridge->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) + pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE) return 0; - if (bridge->pcie_type == PCI_EXP_TYPE_ROOT_PORT) { + if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) { for (i = 0; i < atsru->devices_cnt; i++) if (atsru->devices[i] == bridge) return 1; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 4326f74f7137..976570d4c939 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7527,7 +7527,7 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, goto skip_bad_vf_detection; bdev = pdev->bus->self; - while (bdev && (bdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT)) + while (bdev && (pci_pcie_type(bdev) != PCI_EXP_TYPE_ROOT_PORT)) bdev = bdev->bus->self; if (!bdev) diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 342b3a79bd0f..01d6141cedd9 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1382,7 +1382,7 @@ static void netxen_mask_aer_correctable(struct netxen_adapter *adapter) adapter->ahw.board_type != NETXEN_BRDTYPE_P3_10G_TP) return; - if (root->pcie_type != PCI_EXP_TYPE_ROOT_PORT) + if (pci_pcie_type(root) != PCI_EXP_TYPE_ROOT_PORT) return; aer_pos = pci_find_ext_capability(root, PCI_EXT_CAP_ID_ERR); diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 74bbaf82638d..aeccc911abb8 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -433,8 +433,8 @@ static int sriov_init(struct pci_dev *dev, int pos) struct resource *res; struct pci_dev *pdev; - if (dev->pcie_type != PCI_EXP_TYPE_RC_END && - dev->pcie_type != PCI_EXP_TYPE_ENDPOINT) + if (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_END && + pci_pcie_type(dev) != PCI_EXP_TYPE_ENDPOINT) return -ENODEV; pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl); @@ -503,7 +503,7 @@ found: iov->self = dev; pci_read_config_dword(dev, pos + PCI_SRIOV_CAP, &iov->cap); pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link); - if (dev->pcie_type == PCI_EXP_TYPE_RC_END) + if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) iov->link = PCI_DEVFN(PCI_SLOT(dev->devfn), iov->link); if (pdev) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index f3ea977a5b1b..28eb55b77ee9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -885,7 +885,7 @@ static struct pci_cap_saved_state *pci_find_saved_cap( static int pci_save_pcie_state(struct pci_dev *dev) { - int pos, i = 0; + int type, pos, i = 0; struct pci_cap_saved_state *save_state; u16 *cap; u16 flags; @@ -903,13 +903,14 @@ static int pci_save_pcie_state(struct pci_dev *dev) pci_read_config_word(dev, pos + PCI_EXP_FLAGS, &flags); - if (pcie_cap_has_devctl(dev->pcie_type, flags)) + type = pci_pcie_type(dev); + if (pcie_cap_has_devctl(type, flags)) pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &cap[i++]); - if (pcie_cap_has_lnkctl(dev->pcie_type, flags)) + if (pcie_cap_has_lnkctl(type, flags)) pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, &cap[i++]); - if (pcie_cap_has_sltctl(dev->pcie_type, flags)) + if (pcie_cap_has_sltctl(type, flags)) pci_read_config_word(dev, pos + PCI_EXP_SLTCTL, &cap[i++]); - if (pcie_cap_has_rtctl(dev->pcie_type, flags)) + if (pcie_cap_has_rtctl(type, flags)) pci_read_config_word(dev, pos + PCI_EXP_RTCTL, &cap[i++]); pos = pci_pcie_cap2(dev); @@ -924,7 +925,7 @@ static int pci_save_pcie_state(struct pci_dev *dev) static void pci_restore_pcie_state(struct pci_dev *dev) { - int i = 0, pos; + int i = 0, pos, type; struct pci_cap_saved_state *save_state; u16 *cap; u16 flags; @@ -937,13 +938,14 @@ static void pci_restore_pcie_state(struct pci_dev *dev) pci_read_config_word(dev, pos + PCI_EXP_FLAGS, &flags); - if (pcie_cap_has_devctl(dev->pcie_type, flags)) + type = pci_pcie_type(dev); + if (pcie_cap_has_devctl(type, flags)) pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, cap[i++]); - if (pcie_cap_has_lnkctl(dev->pcie_type, flags)) + if (pcie_cap_has_lnkctl(type, flags)) pci_write_config_word(dev, pos + PCI_EXP_LNKCTL, cap[i++]); - if (pcie_cap_has_sltctl(dev->pcie_type, flags)) + if (pcie_cap_has_sltctl(type, flags)) pci_write_config_word(dev, pos + PCI_EXP_SLTCTL, cap[i++]); - if (pcie_cap_has_rtctl(dev->pcie_type, flags)) + if (pcie_cap_has_rtctl(type, flags)) pci_write_config_word(dev, pos + PCI_EXP_RTCTL, cap[i++]); pos = pci_pcie_cap2(dev); @@ -2459,8 +2461,8 @@ bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags) acs_flags &= (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC | PCI_ACS_DT); - if (pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM || - pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT || + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM || + pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT || pdev->multifunction) { pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS); if (!pos) diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index 52229863e9fe..4e24cb8a94ae 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -288,7 +288,7 @@ static struct pci_dev *pcie_find_root_port(struct pci_dev *dev) while (1) { if (!pci_is_pcie(dev)) break; - if (dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT) + if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) return dev; if (!dev->bus->self) break; diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c index 58ad7917553c..f7c62453ae00 100644 --- a/drivers/pci/pcie/aer/aerdrv.c +++ b/drivers/pci/pcie/aer/aerdrv.c @@ -81,10 +81,11 @@ bool pci_aer_available(void) static int set_device_error_reporting(struct pci_dev *dev, void *data) { bool enable = *((bool *)data); + int type = pci_pcie_type(dev); - if ((dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT) || - (dev->pcie_type == PCI_EXP_TYPE_UPSTREAM) || - (dev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM)) { + if ((type == PCI_EXP_TYPE_ROOT_PORT) || + (type == PCI_EXP_TYPE_UPSTREAM) || + (type == PCI_EXP_TYPE_DOWNSTREAM)) { if (enable) pci_enable_pcie_error_reporting(dev); else diff --git a/drivers/pci/pcie/aer/aerdrv_acpi.c b/drivers/pci/pcie/aer/aerdrv_acpi.c index 124f20ff11b2..5194a7d41730 100644 --- a/drivers/pci/pcie/aer/aerdrv_acpi.c +++ b/drivers/pci/pcie/aer/aerdrv_acpi.c @@ -60,7 +60,7 @@ static int aer_hest_parse(struct acpi_hest_header *hest_hdr, void *data) p = (struct acpi_hest_aer_common *)(hest_hdr + 1); if (p->flags & ACPI_HEST_GLOBAL) { if ((pci_is_pcie(info->pci_dev) && - info->pci_dev->pcie_type == pcie_type) || bridge) + pci_pcie_type(info->pci_dev) == pcie_type) || bridge) ff = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST); } else if (hest_match_pci(p, info->pci_dev)) diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index 0ca053538146..f55153489854 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -465,7 +465,7 @@ static pci_ers_result_t reset_link(struct pci_dev *dev) if (driver && driver->reset_link) { status = driver->reset_link(udev); - } else if (udev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM) { + } else if (pci_pcie_type(udev) == PCI_EXP_TYPE_DOWNSTREAM) { status = default_downstream_reset_link(udev); } else { dev_printk(KERN_DEBUG, &dev->dev, diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index b500840a143b..25916034c0ae 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -412,7 +412,7 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) * do ASPM for now. */ list_for_each_entry(child, &linkbus->devices, bus_list) { - if (child->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) { + if (pci_pcie_type(child) == PCI_EXP_TYPE_PCI_BRIDGE) { link->aspm_disable = ASPM_STATE_ALL; break; } @@ -425,8 +425,8 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) struct aspm_latency *acceptable = &link->acceptable[PCI_FUNC(child->devfn)]; - if (child->pcie_type != PCI_EXP_TYPE_ENDPOINT && - child->pcie_type != PCI_EXP_TYPE_LEG_END) + if (pci_pcie_type(child) != PCI_EXP_TYPE_ENDPOINT && + pci_pcie_type(child) != PCI_EXP_TYPE_LEG_END) continue; pos = pci_pcie_cap(child); @@ -552,7 +552,7 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) INIT_LIST_HEAD(&link->children); INIT_LIST_HEAD(&link->link); link->pdev = pdev; - if (pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM) { + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM) { struct pcie_link_state *parent; parent = pdev->bus->parent->self->link_state; if (!parent) { @@ -585,12 +585,12 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev) if (!pci_is_pcie(pdev) || pdev->link_state) return; - if (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT && - pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) + if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT && + pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) return; /* VIA has a strange chipset, root port is under a bridge */ - if (pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT && + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT && pdev->bus->self) return; @@ -647,8 +647,8 @@ static void pcie_update_aspm_capable(struct pcie_link_state *root) if (link->root != root) continue; list_for_each_entry(child, &linkbus->devices, bus_list) { - if ((child->pcie_type != PCI_EXP_TYPE_ENDPOINT) && - (child->pcie_type != PCI_EXP_TYPE_LEG_END)) + if ((pci_pcie_type(child) != PCI_EXP_TYPE_ENDPOINT) && + (pci_pcie_type(child) != PCI_EXP_TYPE_LEG_END)) continue; pcie_aspm_check_latency(child); } @@ -663,8 +663,8 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) if (!pci_is_pcie(pdev) || !parent || !parent->link_state) return; - if ((parent->pcie_type != PCI_EXP_TYPE_ROOT_PORT) && - (parent->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)) + if ((pci_pcie_type(parent) != PCI_EXP_TYPE_ROOT_PORT) && + (pci_pcie_type(parent) != PCI_EXP_TYPE_DOWNSTREAM)) return; down_read(&pci_bus_sem); @@ -704,8 +704,8 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev) if (aspm_disabled || !pci_is_pcie(pdev) || !link) return; - if ((pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT) && - (pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)) + if ((pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) && + (pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM)) return; /* * Devices changed PM state, we should recheck if latency @@ -729,8 +729,8 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev) if (aspm_policy != POLICY_POWERSAVE) return; - if ((pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT) && - (pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)) + if ((pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) && + (pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM)) return; down_read(&pci_bus_sem); @@ -757,8 +757,8 @@ static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem, if (!pci_is_pcie(pdev)) return; - if (pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT || - pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM) + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT || + pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM) parent = pdev; if (!parent || !parent->link_state) return; @@ -933,8 +933,8 @@ void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev) struct pcie_link_state *link_state = pdev->link_state; if (!pci_is_pcie(pdev) || - (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT && - pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) || !link_state) + (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT && + pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) || !link_state) return; if (link_state->aspm_support) @@ -950,8 +950,8 @@ void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev) struct pcie_link_state *link_state = pdev->link_state; if (!pci_is_pcie(pdev) || - (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT && - pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) || !link_state) + (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT && + pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) || !link_state) return; if (link_state->aspm_support) diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c index 001f1b78f39c..30897bf05b58 100644 --- a/drivers/pci/pcie/pme.c +++ b/drivers/pci/pcie/pme.c @@ -120,7 +120,7 @@ static bool pcie_pme_from_pci_bridge(struct pci_bus *bus, u8 devfn) if (!dev) return false; - if (pci_is_pcie(dev) && dev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) { + if (pci_is_pcie(dev) && pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE) { down_read(&pci_bus_sem); if (pcie_pme_walk_bus(bus)) found = true; @@ -335,13 +335,13 @@ static void pcie_pme_mark_devices(struct pci_dev *port) struct pci_dev *dev; /* Check if this is a root port event collector. */ - if (port->pcie_type != PCI_EXP_TYPE_RC_EC || !bus) + if (pci_pcie_type(port) != PCI_EXP_TYPE_RC_EC || !bus) return; down_read(&pci_bus_sem); list_for_each_entry(dev, &bus->devices, bus_list) if (pci_is_pcie(dev) - && dev->pcie_type == PCI_EXP_TYPE_RC_END) + && pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) pcie_pme_set_native(dev, NULL); up_read(&pci_bus_sem); } diff --git a/drivers/pci/pcie/portdrv_bus.c b/drivers/pci/pcie/portdrv_bus.c index 18bf90f748f6..67be55a7f260 100644 --- a/drivers/pci/pcie/portdrv_bus.c +++ b/drivers/pci/pcie/portdrv_bus.c @@ -38,7 +38,7 @@ static int pcie_port_bus_match(struct device *dev, struct device_driver *drv) return 0; if ((driver->port_type != PCIE_ANY_PORT) && - (driver->port_type != pciedev->port->pcie_type)) + (driver->port_type != pci_pcie_type(pciedev->port))) return 0; return 1; diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 75915b30ad19..bf320a9419f4 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -298,7 +298,7 @@ static int get_port_device_capability(struct pci_dev *dev) services |= PCIE_PORT_SERVICE_VC; /* Root ports are capable of generating PME too */ if ((cap_mask & PCIE_PORT_SERVICE_PME) - && dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT) { + && pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) { services |= PCIE_PORT_SERVICE_PME; /* * Disable PME interrupt on this port in case it's been enabled @@ -336,7 +336,7 @@ static int pcie_device_init(struct pci_dev *pdev, int service, int irq) device->release = release_pcie_device; /* callback to free pcie dev */ dev_set_name(device, "%s:pcie%02x", pci_name(pdev), - get_descriptor_id(pdev->pcie_type, service)); + get_descriptor_id(pci_pcie_type(pdev), service)); device->parent = &pdev->dev; device_enable_async_suspend(device); diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c index 3a7eefcb270a..24d1463e688b 100644 --- a/drivers/pci/pcie/portdrv_pci.c +++ b/drivers/pci/pcie/portdrv_pci.c @@ -95,7 +95,7 @@ static int pcie_port_resume_noirq(struct device *dev) * which breaks ACPI-based runtime wakeup on PCI Express, so clear those * bits now just in case (shouldn't hurt). */ - if(pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT) + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) pcie_clear_root_pme_status(pdev); return 0; } @@ -186,9 +186,9 @@ static int __devinit pcie_portdrv_probe(struct pci_dev *dev, int status; if (!pci_is_pcie(dev) || - ((dev->pcie_type != PCI_EXP_TYPE_ROOT_PORT) && - (dev->pcie_type != PCI_EXP_TYPE_UPSTREAM) && - (dev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM))) + ((pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) && + (pci_pcie_type(dev) != PCI_EXP_TYPE_UPSTREAM) && + (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM))) return -ENODEV; if (!dev->irq && dev->pin) { diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ba4d8550503c..1d52a43eb086 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1384,9 +1384,9 @@ static int only_one_child(struct pci_bus *bus) if (!parent || !pci_is_pcie(parent)) return 0; - if (parent->pcie_type == PCI_EXP_TYPE_ROOT_PORT) + if (pci_pcie_type(parent) == PCI_EXP_TYPE_ROOT_PORT) return 1; - if (parent->pcie_type == PCI_EXP_TYPE_DOWNSTREAM && + if (pci_pcie_type(parent) == PCI_EXP_TYPE_DOWNSTREAM && !pci_has_flag(PCI_SCAN_ALL_PCIE_DEVS)) return 1; return 0; @@ -1463,7 +1463,7 @@ static int pcie_find_smpss(struct pci_dev *dev, void *data) */ if (dev->is_hotplug_bridge && (!list_is_singular(&dev->bus->devices) || (dev->bus->self && - dev->bus->self->pcie_type != PCI_EXP_TYPE_ROOT_PORT))) + pci_pcie_type(dev->bus->self) != PCI_EXP_TYPE_ROOT_PORT))) *smpss = 0; if (*smpss > dev->pcie_mpss) @@ -1479,7 +1479,8 @@ static void pcie_write_mps(struct pci_dev *dev, int mps) if (pcie_bus_config == PCIE_BUS_PERFORMANCE) { mps = 128 << dev->pcie_mpss; - if (dev->pcie_type != PCI_EXP_TYPE_ROOT_PORT && dev->bus->self) + if (pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT && + dev->bus->self) /* For "Performance", the assumption is made that * downstream communication will never be larger than * the MRRS. So, the MPS only needs to be configured diff --git a/drivers/pci/search.c b/drivers/pci/search.c index 993d4a0a2469..621b162ceb69 100644 --- a/drivers/pci/search.c +++ b/drivers/pci/search.c @@ -41,7 +41,7 @@ pci_find_upstream_pcie_bridge(struct pci_dev *pdev) continue; } /* PCI device should connect to a PCIe bridge */ - if (pdev->pcie_type != PCI_EXP_TYPE_PCI_BRIDGE) { + if (pci_pcie_type(pdev) != PCI_EXP_TYPE_PCI_BRIDGE) { /* Busted hardware? */ WARN_ON_ONCE(1); return NULL; -- cgit v1.2.3 From 7d7903b2a2e0c87151f8891e67c4c36a86f3fe83 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Tue, 24 Jul 2012 17:20:16 +0800 Subject: r8169: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify r8169 driver. Signed-off-by: Jiang Liu Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/realtek/r8169.c | 44 ++++++++---------------------------- 1 file changed, 9 insertions(+), 35 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index b47d5b35024e..410496817de8 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -833,15 +833,8 @@ static void rtl_unlock_work(struct rtl8169_private *tp) static void rtl_tx_performance_tweak(struct pci_dev *pdev, u16 force) { - int cap = pci_pcie_cap(pdev); - - if (cap) { - u16 ctl; - - pci_read_config_word(pdev, cap + PCI_EXP_DEVCTL, &ctl); - ctl = (ctl & ~PCI_EXP_DEVCTL_READRQ) | force; - pci_write_config_word(pdev, cap + PCI_EXP_DEVCTL, ctl); - } + pcie_capability_clear_and_set_word(pdev, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_READRQ, force); } struct rtl_cond { @@ -4739,28 +4732,14 @@ static void rtl_ephy_init(struct rtl8169_private *tp, const struct ephy_info *e, static void rtl_disable_clock_request(struct pci_dev *pdev) { - int cap = pci_pcie_cap(pdev); - - if (cap) { - u16 ctl; - - pci_read_config_word(pdev, cap + PCI_EXP_LNKCTL, &ctl); - ctl &= ~PCI_EXP_LNKCTL_CLKREQ_EN; - pci_write_config_word(pdev, cap + PCI_EXP_LNKCTL, ctl); - } + pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CLKREQ_EN); } static void rtl_enable_clock_request(struct pci_dev *pdev) { - int cap = pci_pcie_cap(pdev); - - if (cap) { - u16 ctl; - - pci_read_config_word(pdev, cap + PCI_EXP_LNKCTL, &ctl); - ctl |= PCI_EXP_LNKCTL_CLKREQ_EN; - pci_write_config_word(pdev, cap + PCI_EXP_LNKCTL, ctl); - } + pcie_capability_set_word(pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CLKREQ_EN); } #define R8168_CPCMD_QUIRK_MASK (\ @@ -5405,14 +5384,9 @@ static void rtl_hw_start_8101(struct net_device *dev) tp->event_slow &= ~RxFIFOOver; if (tp->mac_version == RTL_GIGA_MAC_VER_13 || - tp->mac_version == RTL_GIGA_MAC_VER_16) { - int cap = pci_pcie_cap(pdev); - - if (cap) { - pci_write_config_word(pdev, cap + PCI_EXP_DEVCTL, - PCI_EXP_DEVCTL_NOSNOOP_EN); - } - } + tp->mac_version == RTL_GIGA_MAC_VER_16) + pcie_capability_write_word(pdev, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_NOSNOOP_EN); RTL_W8(Cfg9346, Cfg9346_Unlock); -- cgit v1.2.3 From 8200bc72a88cbb63ee13d7f9f16ec4f7249c2ec2 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 22 Aug 2012 10:29:42 -0600 Subject: r8169: Preserve other Device Control bits when setting NOSNOOP_EN Previously, when we turned on the "Enable No Snoop Bit," we cleared all the other Device Control bits, including error reporting enables, Max_Payload_Size, Max_Read_Request_Size, etc. This patch preserves all the other bits. Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/realtek/r8169.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 410496817de8..a7cc56007b33 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -5385,8 +5385,8 @@ static void rtl_hw_start_8101(struct net_device *dev) if (tp->mac_version == RTL_GIGA_MAC_VER_13 || tp->mac_version == RTL_GIGA_MAC_VER_16) - pcie_capability_write_word(pdev, PCI_EXP_DEVCTL, - PCI_EXP_DEVCTL_NOSNOOP_EN); + pcie_capability_set_word(pdev, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_NOSNOOP_EN); RTL_W8(Cfg9346, Cfg9346_Unlock); -- cgit v1.2.3 From 2a80eebcbf3e0f2cc7df6aced54058fbdff37518 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 20 Aug 2012 13:26:51 -0600 Subject: bnx2x: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify bnx2x driver. [bhelgaas: split bnx2x and tg3 into separate patches] Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 25 +++++------------------- 1 file changed, 5 insertions(+), 20 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index dd451c3dd83d..281cf3f7bc20 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -1162,14 +1162,9 @@ static int bnx2x_send_final_clnup(struct bnx2x *bp, u8 clnup_func, static u8 bnx2x_is_pcie_pending(struct pci_dev *dev) { - int pos; u16 status; - pos = pci_pcie_cap(dev); - if (!pos) - return false; - - pci_read_config_word(dev, pos + PCI_EXP_DEVSTA, &status); + pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &status); return status & PCI_EXP_DEVSTA_TRPND; } @@ -6149,8 +6144,7 @@ static void bnx2x_init_pxp(struct bnx2x *bp) u16 devctl; int r_order, w_order; - pci_read_config_word(bp->pdev, - pci_pcie_cap(bp->pdev) + PCI_EXP_DEVCTL, &devctl); + pcie_capability_read_word(bp->pdev, PCI_EXP_DEVCTL, &devctl); DP(NETIF_MSG_HW, "read 0x%x from devctl\n", devctl); w_order = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5); if (bp->mrrs == -1) @@ -9386,15 +9380,10 @@ static int __devinit bnx2x_prev_mark_path(struct bnx2x *bp) static bool __devinit bnx2x_can_flr(struct bnx2x *bp) { - int pos; u32 cap; struct pci_dev *dev = bp->pdev; - pos = pci_pcie_cap(dev); - if (!pos) - return false; - - pci_read_config_dword(dev, pos + PCI_EXP_DEVCAP, &cap); + pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); if (!(cap & PCI_EXP_DEVCAP_FLR)) return false; @@ -9403,7 +9392,7 @@ static bool __devinit bnx2x_can_flr(struct bnx2x *bp) static int __devinit bnx2x_do_flr(struct bnx2x *bp) { - int i, pos; + int i; u16 status; struct pci_dev *dev = bp->pdev; @@ -9411,16 +9400,12 @@ static int __devinit bnx2x_do_flr(struct bnx2x *bp) if (bnx2x_can_flr(bp)) return -ENOTTY; - pos = pci_pcie_cap(dev); - if (!pos) - return -ENOTTY; - /* Wait for Transaction Pending bit clean */ for (i = 0; i < 4; i++) { if (i) msleep((1 << (i - 1)) * 100); - pci_read_config_word(dev, pos + PCI_EXP_DEVSTA, &status); + pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &status); if (!(status & PCI_EXP_DEVSTA_TRPND)) goto clear; } -- cgit v1.2.3 From 0f49bfbd0f2ee6d57398ba5fcf39de6b566c43bb Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 20 Aug 2012 13:28:20 -0600 Subject: tg3: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify tg3 driver. [bhelgaas: split bnx2x and tg3 into separate patches] Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/broadcom/tg3.c | 50 ++++++++++--------------------------- 1 file changed, 13 insertions(+), 37 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index bf906c51d82a..8325fd8d4e5b 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -3653,17 +3653,9 @@ static int tg3_power_down_prepare(struct tg3 *tp) tg3_enable_register_access(tp); /* Restore the CLKREQ setting. */ - if (tg3_flag(tp, CLKREQ_BUG)) { - u16 lnkctl; - - pci_read_config_word(tp->pdev, - pci_pcie_cap(tp->pdev) + PCI_EXP_LNKCTL, - &lnkctl); - lnkctl |= PCI_EXP_LNKCTL_CLKREQ_EN; - pci_write_config_word(tp->pdev, - pci_pcie_cap(tp->pdev) + PCI_EXP_LNKCTL, - lnkctl); - } + if (tg3_flag(tp, CLKREQ_BUG)) + pcie_capability_set_word(tp->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CLKREQ_EN); misc_host_ctrl = tr32(TG3PCI_MISC_HOST_CTRL); tw32(TG3PCI_MISC_HOST_CTRL, @@ -4434,20 +4426,13 @@ relink: /* Prevent send BD corruption. */ if (tg3_flag(tp, CLKREQ_BUG)) { - u16 oldlnkctl, newlnkctl; - - pci_read_config_word(tp->pdev, - pci_pcie_cap(tp->pdev) + PCI_EXP_LNKCTL, - &oldlnkctl); if (tp->link_config.active_speed == SPEED_100 || tp->link_config.active_speed == SPEED_10) - newlnkctl = oldlnkctl & ~PCI_EXP_LNKCTL_CLKREQ_EN; + pcie_capability_clear_word(tp->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CLKREQ_EN); else - newlnkctl = oldlnkctl | PCI_EXP_LNKCTL_CLKREQ_EN; - if (newlnkctl != oldlnkctl) - pci_write_config_word(tp->pdev, - pci_pcie_cap(tp->pdev) + - PCI_EXP_LNKCTL, newlnkctl); + pcie_capability_set_word(tp->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CLKREQ_EN); } if (current_link_up != netif_carrier_ok(tp->dev)) { @@ -8054,7 +8039,7 @@ static int tg3_chip_reset(struct tg3 *tp) udelay(120); - if (tg3_flag(tp, PCI_EXPRESS) && pci_pcie_cap(tp->pdev)) { + if (tg3_flag(tp, PCI_EXPRESS) && pci_is_pcie(tp->pdev)) { u16 val16; if (tp->pci_chip_rev_id == CHIPREV_ID_5750_A0) { @@ -8071,24 +8056,17 @@ static int tg3_chip_reset(struct tg3 *tp) } /* Clear the "no snoop" and "relaxed ordering" bits. */ - pci_read_config_word(tp->pdev, - pci_pcie_cap(tp->pdev) + PCI_EXP_DEVCTL, - &val16); - val16 &= ~(PCI_EXP_DEVCTL_RELAX_EN | - PCI_EXP_DEVCTL_NOSNOOP_EN); + val16 = PCI_EXP_DEVCTL_RELAX_EN | PCI_EXP_DEVCTL_NOSNOOP_EN; /* * Older PCIe devices only support the 128 byte * MPS setting. Enforce the restriction. */ if (!tg3_flag(tp, CPMU_PRESENT)) - val16 &= ~PCI_EXP_DEVCTL_PAYLOAD; - pci_write_config_word(tp->pdev, - pci_pcie_cap(tp->pdev) + PCI_EXP_DEVCTL, - val16); + val16 |= PCI_EXP_DEVCTL_PAYLOAD; + pcie_capability_clear_word(tp->pdev, PCI_EXP_DEVCTL, val16); /* Clear error status */ - pci_write_config_word(tp->pdev, - pci_pcie_cap(tp->pdev) + PCI_EXP_DEVSTA, + pcie_capability_write_word(tp->pdev, PCI_EXP_DEVSTA, PCI_EXP_DEVSTA_CED | PCI_EXP_DEVSTA_NFED | PCI_EXP_DEVSTA_FED | @@ -14565,9 +14543,7 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) tg3_flag_set(tp, PCI_EXPRESS); - pci_read_config_word(tp->pdev, - pci_pcie_cap(tp->pdev) + PCI_EXP_LNKCTL, - &lnkctl); + pcie_capability_read_word(tp->pdev, PCI_EXP_LNKCTL, &lnkctl); if (lnkctl & PCI_EXP_LNKCTL_CLKREQ_EN) { if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) { -- cgit v1.2.3 From f8c0fcacfe2e2fd4ee3eadd790959323097004fd Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 20 Aug 2012 13:30:43 -0600 Subject: e1000e: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify e1000e driver. [bhelgaas: split e1000e and igb into separate patches] Signed-off-by: Jiang Liu Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas Acked-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 27 ++++++++------------------- 1 file changed, 8 insertions(+), 19 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 95b245310f17..9f474b2cc819 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5570,16 +5570,15 @@ static void e1000_complete_shutdown(struct pci_dev *pdev, bool sleep, */ if (adapter->flags & FLAG_IS_QUAD_PORT) { struct pci_dev *us_dev = pdev->bus->self; - int pos = pci_pcie_cap(us_dev); u16 devctl; - pci_read_config_word(us_dev, pos + PCI_EXP_DEVCTL, &devctl); - pci_write_config_word(us_dev, pos + PCI_EXP_DEVCTL, - (devctl & ~PCI_EXP_DEVCTL_CERE)); + pcie_capability_read_word(us_dev, PCI_EXP_DEVCTL, &devctl); + pcie_capability_write_word(us_dev, PCI_EXP_DEVCTL, + (devctl & ~PCI_EXP_DEVCTL_CERE)); e1000_power_off(pdev, sleep, wake); - pci_write_config_word(us_dev, pos + PCI_EXP_DEVCTL, devctl); + pcie_capability_write_word(us_dev, PCI_EXP_DEVCTL, devctl); } else { e1000_power_off(pdev, sleep, wake); } @@ -5593,25 +5592,15 @@ static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) #else static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) { - int pos; - u16 reg16; - /* * Both device and parent should have the same ASPM setting. * Disable ASPM in downstream component first and then upstream. */ - pos = pci_pcie_cap(pdev); - pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16); - reg16 &= ~state; - pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16); - - if (!pdev->bus->self) - return; + pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, state); - pos = pci_pcie_cap(pdev->bus->self); - pci_read_config_word(pdev->bus->self, pos + PCI_EXP_LNKCTL, ®16); - reg16 &= ~state; - pci_write_config_word(pdev->bus->self, pos + PCI_EXP_LNKCTL, reg16); + if (pdev->bus->self) + pcie_capability_clear_word(pdev->bus->self, PCI_EXP_LNKCTL, + state); } #endif static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state) -- cgit v1.2.3 From 23d028cc86f6136e357980323dfe958eade547b4 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 20 Aug 2012 13:32:20 -0600 Subject: igb: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify igb driver. [bhelgaas: split e1000e and igb into separate patches] Signed-off-by: Jiang Liu Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas Acked-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b7c2d5050572..9a379d9c07fa 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6539,28 +6539,20 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value) { struct igb_adapter *adapter = hw->back; - u16 cap_offset; - cap_offset = adapter->pdev->pcie_cap; - if (!cap_offset) + if (pcie_capability_read_word(adapter->pdev, reg, value)) return -E1000_ERR_CONFIG; - pci_read_config_word(adapter->pdev, cap_offset + reg, value); - return 0; } s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value) { struct igb_adapter *adapter = hw->back; - u16 cap_offset; - cap_offset = adapter->pdev->pcie_cap; - if (!cap_offset) + if (pcie_capability_write_word(adapter->pdev, reg, *value)) return -E1000_ERR_CONFIG; - pci_write_config_word(adapter->pdev, cap_offset + reg, *value); - return 0; } -- cgit v1.2.3 From d892aa00bc89c977acc71dc10aa79c2984710c12 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Tue, 24 Jul 2012 17:20:19 +0800 Subject: vxge: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify vxge driver. Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/neterion/vxge/vxge-config.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 32d06824fe3e..c2e420a84d22 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -757,7 +757,7 @@ __vxge_hw_verify_pci_e_info(struct __vxge_hw_device *hldev) u16 lnk; /* Get the negotiated link width and speed from PCI config space */ - pci_read_config_word(dev, dev->pcie_cap + PCI_EXP_LNKSTA, &lnk); + pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnk); if ((lnk & PCI_EXP_LNKSTA_CLS) != 1) return VXGE_HW_ERR_INVALID_PCI_INFO; @@ -1982,7 +1982,7 @@ u16 vxge_hw_device_link_width_get(struct __vxge_hw_device *hldev) struct pci_dev *dev = hldev->pdev; u16 lnk; - pci_read_config_word(dev, dev->pcie_cap + PCI_EXP_LNKSTA, &lnk); + pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnk); return (lnk & VXGE_HW_PCI_EXP_LNKCAP_LNK_WIDTH) >> 4; } -- cgit v1.2.3 From fadd1daa0b62bccb10acab6d693b9de990671456 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Tue, 24 Jul 2012 17:20:20 +0800 Subject: mlx4: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify mlx4 driver. Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/mellanox/mlx4/reset.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/reset.c b/drivers/net/ethernet/mellanox/mlx4/reset.c index 11e7c1cb99bf..dd1b5093d8b1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/reset.c +++ b/drivers/net/ethernet/mellanox/mlx4/reset.c @@ -141,16 +141,16 @@ int mlx4_reset(struct mlx4_dev *dev) /* Now restore the PCI headers */ if (pcie_cap) { devctl = hca_header[(pcie_cap + PCI_EXP_DEVCTL) / 4]; - if (pci_write_config_word(dev->pdev, pcie_cap + PCI_EXP_DEVCTL, - devctl)) { + if (pcie_capability_write_word(dev->pdev, PCI_EXP_DEVCTL, + devctl)) { err = -ENODEV; mlx4_err(dev, "Couldn't restore HCA PCI Express " "Device Control register, aborting.\n"); goto out; } linkctl = hca_header[(pcie_cap + PCI_EXP_LNKCTL) / 4]; - if (pci_write_config_word(dev->pdev, pcie_cap + PCI_EXP_LNKCTL, - linkctl)) { + if (pcie_capability_write_word(dev->pdev, PCI_EXP_LNKCTL, + linkctl)) { err = -ENODEV; mlx4_err(dev, "Couldn't restore HCA PCI Express " "Link control register, aborting.\n"); -- cgit v1.2.3 From 56cda12986a243a66b9714f9ccac884e2faea38e Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Tue, 24 Jul 2012 17:20:21 +0800 Subject: niu: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify niu driver. Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/sun/niu.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index c2a0fe393267..3208dca66758 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9762,9 +9762,8 @@ static int __devinit niu_pci_init_one(struct pci_dev *pdev, union niu_parent_id parent_id; struct net_device *dev; struct niu *np; - int err, pos; + int err; u64 dma_mask; - u16 val16; niu_driver_version(); @@ -9787,8 +9786,7 @@ static int __devinit niu_pci_init_one(struct pci_dev *pdev, goto err_out_disable_pdev; } - pos = pci_pcie_cap(pdev); - if (pos <= 0) { + if (!pci_is_pcie(pdev)) { dev_err(&pdev->dev, "Cannot find PCI Express capability, aborting\n"); goto err_out_free_res; } @@ -9813,14 +9811,11 @@ static int __devinit niu_pci_init_one(struct pci_dev *pdev, goto err_out_free_dev; } - pci_read_config_word(pdev, pos + PCI_EXP_DEVCTL, &val16); - val16 &= ~PCI_EXP_DEVCTL_NOSNOOP_EN; - val16 |= (PCI_EXP_DEVCTL_CERE | - PCI_EXP_DEVCTL_NFERE | - PCI_EXP_DEVCTL_FERE | - PCI_EXP_DEVCTL_URRE | - PCI_EXP_DEVCTL_RELAX_EN); - pci_write_config_word(pdev, pos + PCI_EXP_DEVCTL, val16); + pcie_capability_clear_and_set_word(pdev, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_NOSNOOP_EN, + PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | + PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE | + PCI_EXP_DEVCTL_RELAX_EN); dma_mask = DMA_BIT_MASK(44); err = pci_set_dma_mask(pdev, dma_mask); -- cgit v1.2.3 From 9503e255763da2e6b5b0d0d9dfa104e1ca8d035a Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Tue, 24 Jul 2012 17:20:22 +0800 Subject: myri10ge: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify myri10ge driver. [bhelgaas: fix myri10ge_toggle_relaxed() return value] Signed-off-by: Jiang Liu Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 31 ++++++------------------ 1 file changed, 8 insertions(+), 23 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index fa85cf1353fd..83516e3369c9 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -1078,22 +1078,16 @@ static int myri10ge_reset(struct myri10ge_priv *mgp) #ifdef CONFIG_MYRI10GE_DCA static int myri10ge_toggle_relaxed(struct pci_dev *pdev, int on) { - int ret, cap, err; + int ret; u16 ctl; - cap = pci_pcie_cap(pdev); - if (!cap) - return 0; - - err = pci_read_config_word(pdev, cap + PCI_EXP_DEVCTL, &ctl); - if (err) - return 0; + pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &ctl); ret = (ctl & PCI_EXP_DEVCTL_RELAX_EN) >> 4; if (ret != on) { ctl &= ~PCI_EXP_DEVCTL_RELAX_EN; ctl |= (on << 4); - pci_write_config_word(pdev, cap + PCI_EXP_DEVCTL, ctl); + pcie_capability_write_word(pdev, PCI_EXP_DEVCTL, ctl); } return ret; } @@ -3192,18 +3186,13 @@ static void myri10ge_enable_ecrc(struct myri10ge_priv *mgp) struct device *dev = &mgp->pdev->dev; int cap; unsigned err_cap; - u16 val; - u8 ext_type; int ret; if (!myri10ge_ecrc_enable || !bridge) return; /* check that the bridge is a root port */ - cap = pci_pcie_cap(bridge); - pci_read_config_word(bridge, cap + PCI_CAP_FLAGS, &val); - ext_type = (val & PCI_EXP_FLAGS_TYPE) >> 4; - if (ext_type != PCI_EXP_TYPE_ROOT_PORT) { + if (pci_pcie_type(bridge) != PCI_EXP_TYPE_ROOT_PORT) { if (myri10ge_ecrc_enable > 1) { struct pci_dev *prev_bridge, *old_bridge = bridge; @@ -3218,11 +3207,8 @@ static void myri10ge_enable_ecrc(struct myri10ge_priv *mgp) " to force ECRC\n"); return; } - cap = pci_pcie_cap(bridge); - pci_read_config_word(bridge, - cap + PCI_CAP_FLAGS, &val); - ext_type = (val & PCI_EXP_FLAGS_TYPE) >> 4; - } while (ext_type != PCI_EXP_TYPE_ROOT_PORT); + } while (pci_pcie_type(bridge) != + PCI_EXP_TYPE_ROOT_PORT); dev_info(dev, "Forcing ECRC on non-root port %s" @@ -3335,11 +3321,10 @@ static void myri10ge_select_firmware(struct myri10ge_priv *mgp) int overridden = 0; if (myri10ge_force_firmware == 0) { - int link_width, exp_cap; + int link_width; u16 lnk; - exp_cap = pci_pcie_cap(mgp->pdev); - pci_read_config_word(mgp->pdev, exp_cap + PCI_EXP_LNKSTA, &lnk); + pcie_capability_read_word(mgp->pdev, PCI_EXP_LNKSTA, &lnk); link_width = (lnk >> 4) & 0x3f; /* Check to see if Link is less than 8 or if the -- cgit v1.2.3 From c772b44e32ea8255e5d0ffaac0a7b76043b14565 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 20 Aug 2012 13:51:20 -0600 Subject: cxgb3: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify cxgb3 driver. [bhelgaas: split cxgb3 and cxgb4 into separate patches] Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/chelsio/cxgb3/t3_hw.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c index bff8a3cdd3df..aef45d3113ba 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c @@ -3289,22 +3289,18 @@ static void config_pcie(struct adapter *adap) unsigned int log2_width, pldsize; unsigned int fst_trn_rx, fst_trn_tx, acklat, rpllmt; - pci_read_config_word(adap->pdev, - adap->pdev->pcie_cap + PCI_EXP_DEVCTL, - &val); + pcie_capability_read_word(adap->pdev, PCI_EXP_DEVCTL, &val); pldsize = (val & PCI_EXP_DEVCTL_PAYLOAD) >> 5; pci_read_config_word(adap->pdev, 0x2, &devid); if (devid == 0x37) { - pci_write_config_word(adap->pdev, - adap->pdev->pcie_cap + PCI_EXP_DEVCTL, - val & ~PCI_EXP_DEVCTL_READRQ & - ~PCI_EXP_DEVCTL_PAYLOAD); + pcie_capability_write_word(adap->pdev, PCI_EXP_DEVCTL, + val & ~PCI_EXP_DEVCTL_READRQ & + ~PCI_EXP_DEVCTL_PAYLOAD); pldsize = 0; } - pci_read_config_word(adap->pdev, adap->pdev->pcie_cap + PCI_EXP_LNKCTL, - &val); + pcie_capability_read_word(adap->pdev, PCI_EXP_LNKCTL, &val); fst_trn_tx = G_NUMFSTTRNSEQ(t3_read_reg(adap, A_PCIE_PEX_CTRL0)); fst_trn_rx = adap->params.rev == 0 ? fst_trn_tx : @@ -3425,15 +3421,13 @@ out_err: static void get_pci_mode(struct adapter *adapter, struct pci_params *p) { static unsigned short speed_map[] = { 33, 66, 100, 133 }; - u32 pci_mode, pcie_cap; + u32 pci_mode; - pcie_cap = pci_pcie_cap(adapter->pdev); - if (pcie_cap) { + if (pci_is_pcie(adapter->pdev)) { u16 val; p->variant = PCI_VARIANT_PCIE; - pci_read_config_word(adapter->pdev, pcie_cap + PCI_EXP_LNKSTA, - &val); + pcie_capability_read_word(adapter->pdev, PCI_EXP_LNKSTA, &val); p->width = (val >> 4) & 0x3f; return; } -- cgit v1.2.3 From e5c8ae5fcaadc7947ce3a8e0f82134e56fe4e15b Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 20 Aug 2012 13:53:19 -0600 Subject: cxgb4: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify cxgb4 driver. Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 10 +--------- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 6 ++---- 2 files changed, 3 insertions(+), 13 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 5ed49af23d6a..4a20821511e7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3694,15 +3694,7 @@ static void __devinit print_port_info(const struct net_device *dev) static void __devinit enable_pcie_relaxed_ordering(struct pci_dev *dev) { - u16 v; - int pos; - - pos = pci_pcie_cap(dev); - if (pos > 0) { - pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &v); - v |= PCI_EXP_DEVCTL_RELAX_EN; - pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, v); - } + pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN); } /* diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index fa947dfa4c30..af1601323173 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -2741,11 +2741,9 @@ static void __devinit get_pci_mode(struct adapter *adapter, struct pci_params *p) { u16 val; - u32 pcie_cap = pci_pcie_cap(adapter->pdev); - if (pcie_cap) { - pci_read_config_word(adapter->pdev, pcie_cap + PCI_EXP_LNKSTA, - &val); + if (pci_is_pcie(adapter->pdev)) { + pcie_capability_read_word(adapter->pdev, PCI_EXP_LNKSTA, &val); p->speed = val & PCI_EXP_LNKSTA_CLS; p->width = (val & PCI_EXP_LNKSTA_NLW) >> 4; } -- cgit v1.2.3 From eb0ff56366c38b87c048a624407bc699bf06d43f Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Tue, 24 Jul 2012 17:20:24 +0800 Subject: atl1c: Use PCI Express Capability accessors Use PCI Express Capability access functions to simplify atl1c driver. Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 1bf5bbfe778e..8892e2b64498 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -149,7 +149,7 @@ static void atl1c_reset_pcie(struct atl1c_hw *hw, u32 flag) data &= ~(PCI_ERR_UNC_DLP | PCI_ERR_UNC_FCP); pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, data); /* clear error status */ - pci_write_config_word(pdev, pci_pcie_cap(pdev) + PCI_EXP_DEVSTA, + pcie_capability_write_word(pdev, PCI_EXP_DEVSTA, PCI_EXP_DEVSTA_NFED | PCI_EXP_DEVSTA_FED | PCI_EXP_DEVSTA_CED | -- cgit v1.2.3 From 9f35a7342cff0be72e3c038ea972e07662ca1ce8 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Mon, 20 Aug 2012 09:26:39 +0000 Subject: net/fsl: introduce Freescale 10G MDIO driver Similar to fsl_pq_mdio.c, this driver is for the 10G MDIO controller on Freescale Frame Manager Ethernet controllers. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/Kconfig | 7 + drivers/net/ethernet/freescale/Makefile | 1 + drivers/net/ethernet/freescale/xgmac_mdio.c | 274 ++++++++++++++++++++++++++++ 3 files changed, 282 insertions(+) create mode 100644 drivers/net/ethernet/freescale/xgmac_mdio.c (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index 3574e1499dfc..feff51664dcf 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -62,6 +62,13 @@ config FSL_PQ_MDIO ---help--- This driver supports the MDIO bus used by the gianfar and UCC drivers. +config FSL_XGMAC_MDIO + tristate "Freescale XGMAC MDIO" + depends on FSL_SOC + select PHYLIB + ---help--- + This driver supports the MDIO bus on the Fman 10G Ethernet MACs. + config UCC_GETH tristate "Freescale QE Gigabit Ethernet" depends on QUICC_ENGINE diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile index 1752488c9ee5..3d1839afff65 100644 --- a/drivers/net/ethernet/freescale/Makefile +++ b/drivers/net/ethernet/freescale/Makefile @@ -9,6 +9,7 @@ ifeq ($(CONFIG_FEC_MPC52xx_MDIO),y) endif obj-$(CONFIG_FS_ENET) += fs_enet/ obj-$(CONFIG_FSL_PQ_MDIO) += fsl_pq_mdio.o +obj-$(CONFIG_FSL_XGMAC_MDIO) += xgmac_mdio.o obj-$(CONFIG_GIANFAR) += gianfar_driver.o obj-$(CONFIG_PTP_1588_CLOCK_GIANFAR) += gianfar_ptp.o gianfar_driver-objs := gianfar.o \ diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c new file mode 100644 index 000000000000..1afb5ea2a984 --- /dev/null +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -0,0 +1,274 @@ +/* + * QorIQ 10G MDIO Controller + * + * Copyright 2012 Freescale Semiconductor, Inc. + * + * Authors: Andy Fleming + * Timur Tabi + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* Number of microseconds to wait for a register to respond */ +#define TIMEOUT 1000 + +struct tgec_mdio_controller { + __be32 reserved[12]; + __be32 mdio_stat; /* MDIO configuration and status */ + __be32 mdio_ctl; /* MDIO control */ + __be32 mdio_data; /* MDIO data */ + __be32 mdio_addr; /* MDIO address */ +} __packed; + +#define MDIO_STAT_CLKDIV(x) (((x>>1) & 0xff) << 8) +#define MDIO_STAT_BSY (1 << 0) +#define MDIO_STAT_RD_ER (1 << 1) +#define MDIO_CTL_DEV_ADDR(x) (x & 0x1f) +#define MDIO_CTL_PORT_ADDR(x) ((x & 0x1f) << 5) +#define MDIO_CTL_PRE_DIS (1 << 10) +#define MDIO_CTL_SCAN_EN (1 << 11) +#define MDIO_CTL_POST_INC (1 << 14) +#define MDIO_CTL_READ (1 << 15) + +#define MDIO_DATA(x) (x & 0xffff) +#define MDIO_DATA_BSY (1 << 31) + +/* + * Wait untill the MDIO bus is free + */ +static int xgmac_wait_until_free(struct device *dev, + struct tgec_mdio_controller __iomem *regs) +{ + uint32_t status; + + /* Wait till the bus is free */ + status = spin_event_timeout( + !((in_be32(®s->mdio_stat)) & MDIO_STAT_BSY), TIMEOUT, 0); + if (!status) { + dev_err(dev, "timeout waiting for bus to be free\n"); + return -ETIMEDOUT; + } + + return 0; +} + +/* + * Wait till the MDIO read or write operation is complete + */ +static int xgmac_wait_until_done(struct device *dev, + struct tgec_mdio_controller __iomem *regs) +{ + uint32_t status; + + /* Wait till the MDIO write is complete */ + status = spin_event_timeout( + !((in_be32(®s->mdio_data)) & MDIO_DATA_BSY), TIMEOUT, 0); + if (!status) { + dev_err(dev, "timeout waiting for operation to complete\n"); + return -ETIMEDOUT; + } + + return 0; +} + +/* + * Write value to the PHY for this device to the register at regnum,waiting + * until the write is done before it returns. All PHY configuration has to be + * done through the TSEC1 MIIM regs. + */ +static int xgmac_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value) +{ + struct tgec_mdio_controller __iomem *regs = bus->priv; + uint16_t dev_addr = regnum >> 16; + int ret; + + /* Setup the MII Mgmt clock speed */ + out_be32(®s->mdio_stat, MDIO_STAT_CLKDIV(100)); + + ret = xgmac_wait_until_free(&bus->dev, regs); + if (ret) + return ret; + + /* Set the port and dev addr */ + out_be32(®s->mdio_ctl, + MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr)); + + /* Set the register address */ + out_be32(®s->mdio_addr, regnum & 0xffff); + + ret = xgmac_wait_until_free(&bus->dev, regs); + if (ret) + return ret; + + /* Write the value to the register */ + out_be32(®s->mdio_data, MDIO_DATA(value)); + + ret = xgmac_wait_until_done(&bus->dev, regs); + if (ret) + return ret; + + return 0; +} + +/* + * Reads from register regnum in the PHY for device dev, returning the value. + * Clears miimcom first. All PHY configuration has to be done through the + * TSEC1 MIIM regs. + */ +static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +{ + struct tgec_mdio_controller __iomem *regs = bus->priv; + uint16_t dev_addr = regnum >> 16; + uint32_t mdio_ctl; + uint16_t value; + int ret; + + /* Setup the MII Mgmt clock speed */ + out_be32(®s->mdio_stat, MDIO_STAT_CLKDIV(100)); + + ret = xgmac_wait_until_free(&bus->dev, regs); + if (ret) + return ret; + + /* Set the Port and Device Addrs */ + mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); + out_be32(®s->mdio_ctl, mdio_ctl); + + /* Set the register address */ + out_be32(®s->mdio_addr, regnum & 0xffff); + + ret = xgmac_wait_until_free(&bus->dev, regs); + if (ret) + return ret; + + /* Initiate the read */ + out_be32(®s->mdio_ctl, mdio_ctl | MDIO_CTL_READ); + + ret = xgmac_wait_until_done(&bus->dev, regs); + if (ret) + return ret; + + /* Return all Fs if nothing was there */ + if (in_be32(®s->mdio_stat) & MDIO_STAT_RD_ER) { + dev_err(&bus->dev, "MDIO read error\n"); + return 0xffff; + } + + value = in_be32(®s->mdio_data) & 0xffff; + dev_dbg(&bus->dev, "read %04x\n", value); + + return value; +} + +/* Reset the MIIM registers, and wait for the bus to free */ +static int xgmac_mdio_reset(struct mii_bus *bus) +{ + struct tgec_mdio_controller __iomem *regs = bus->priv; + int ret; + + mutex_lock(&bus->mdio_lock); + + /* Setup the MII Mgmt clock speed */ + out_be32(®s->mdio_stat, MDIO_STAT_CLKDIV(100)); + + ret = xgmac_wait_until_free(&bus->dev, regs); + + mutex_unlock(&bus->mdio_lock); + + return ret; +} + +static int __devinit xgmac_mdio_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct mii_bus *bus; + struct resource res; + int ret; + + ret = of_address_to_resource(np, 0, &res); + if (ret) { + dev_err(&pdev->dev, "could not obtain address\n"); + return ret; + } + + bus = mdiobus_alloc_size(PHY_MAX_ADDR * sizeof(int)); + if (!bus) + return -ENOMEM; + + bus->name = "Freescale XGMAC MDIO Bus"; + bus->read = xgmac_mdio_read; + bus->write = xgmac_mdio_write; + bus->reset = xgmac_mdio_reset; + bus->irq = bus->priv; + bus->parent = &pdev->dev; + snprintf(bus->id, MII_BUS_ID_SIZE, "%llx", (unsigned long long)res.start); + + /* Set the PHY base address */ + bus->priv = of_iomap(np, 0); + if (!bus->priv) { + ret = -ENOMEM; + goto err_ioremap; + } + + ret = of_mdiobus_register(bus, np); + if (ret) { + dev_err(&pdev->dev, "cannot register MDIO bus\n"); + goto err_registration; + } + + dev_set_drvdata(&pdev->dev, bus); + + return 0; + +err_registration: + iounmap(bus->priv); + +err_ioremap: + mdiobus_free(bus); + + return ret; +} + +static int __devexit xgmac_mdio_remove(struct platform_device *pdev) +{ + struct mii_bus *bus = dev_get_drvdata(&pdev->dev); + + mdiobus_unregister(bus); + iounmap(bus->priv); + mdiobus_free(bus); + + return 0; +} + +static struct of_device_id xgmac_mdio_match[] = { + { + .compatible = "fsl,fman-xmdio", + }, + {}, +}; +MODULE_DEVICE_TABLE(of, xgmac_mdio_match); + +static struct platform_driver xgmac_mdio_driver = { + .driver = { + .name = "fsl-fman_xmdio", + .of_match_table = xgmac_mdio_match, + }, + .probe = xgmac_mdio_probe, + .remove = xgmac_mdio_remove, +}; + +module_platform_driver(xgmac_mdio_driver); + +MODULE_DESCRIPTION("Freescale QorIQ 10G MDIO Controller"); +MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From d68bb7e1a65f2604156958ae03a556b6a207514b Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Wed, 22 Aug 2012 21:28:19 +0000 Subject: w5100: using eth_hw_addr_random() for random MAC and set device flag Using eth_hw_addr_random() to generate a random Ethernet address (MAC) to be used by a net device and set addr_assign_type. Not need to duplicating its implementation. spatch with a semantic match is used to found this problem. (http://coccinelle.lip6.fr/) Signed-off-by: Wei Yongjun Signed-off-by: David S. Miller --- drivers/net/ethernet/wiznet/w5100.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index a5826a3111a6..2c08bf6e7bf3 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -637,8 +637,7 @@ static int __devinit w5100_hw_probe(struct platform_device *pdev) if (data && is_valid_ether_addr(data->mac_addr)) { memcpy(ndev->dev_addr, data->mac_addr, ETH_ALEN); } else { - eth_random_addr(ndev->dev_addr); - ndev->addr_assign_type |= NET_ADDR_RANDOM; + eth_hw_addr_random(ndev); } mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); -- cgit v1.2.3 From 1f7c9ae7a014d994c01a7dd59333f2fcef2aba58 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Wed, 22 Aug 2012 21:28:40 +0000 Subject: w5300: using eth_hw_addr_random() for random MAC and set device flag Using eth_hw_addr_random() to generate a random Ethernet address (MAC) to be used by a net device and set addr_assign_type. Not need to duplicating its implementation. spatch with a semantic match is used to found this problem. (http://coccinelle.lip6.fr/) Signed-off-by: Wei Yongjun Signed-off-by: David S. Miller --- drivers/net/ethernet/wiznet/w5300.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c index bdd8891c215a..88943d90c765 100644 --- a/drivers/net/ethernet/wiznet/w5300.c +++ b/drivers/net/ethernet/wiznet/w5300.c @@ -557,8 +557,7 @@ static int __devinit w5300_hw_probe(struct platform_device *pdev) if (data && is_valid_ether_addr(data->mac_addr)) { memcpy(ndev->dev_addr, data->mac_addr, ETH_ALEN); } else { - eth_random_addr(ndev->dev_addr); - ndev->addr_assign_type |= NET_ADDR_RANDOM; + eth_hw_addr_random(ndev); } mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); -- cgit v1.2.3 From 7668ff9c2ad7d354655e23afa836a92d54d2ea63 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 17 May 2012 20:52:20 +0100 Subject: sfc: Refactor struct efx_tx_buffer to use a flags field Add a flags field to struct efx_tx_buffer, replacing the continuation and map_single booleans. Since a single descriptor cannot be both a TSO header and the last descriptor for an skb, unionise efx_tx_buffer::{skb,tsoh} and add flags for validity of these fields. Clear all flags in free buffers (whereas previously the continuation flag would be set). Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/net_driver.h | 27 ++++++------ drivers/net/ethernet/sfc/nic.c | 4 +- drivers/net/ethernet/sfc/tx.c | 78 ++++++++++++++++------------------- 3 files changed, 53 insertions(+), 56 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index cd9c0a989692..0ac01fa6e63c 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -91,29 +91,30 @@ struct efx_special_buffer { }; /** - * struct efx_tx_buffer - An Efx TX buffer - * @skb: The associated socket buffer. - * Set only on the final fragment of a packet; %NULL for all other - * fragments. When this fragment completes, then we can free this - * skb. - * @tsoh: The associated TSO header structure, or %NULL if this - * buffer is not a TSO header. + * struct efx_tx_buffer - buffer state for a TX descriptor + * @skb: When @flags & %EFX_TX_BUF_SKB, the associated socket buffer to be + * freed when descriptor completes + * @tsoh: When @flags & %EFX_TX_BUF_TSOH, the associated TSO header structure. * @dma_addr: DMA address of the fragment. + * @flags: Flags for allocation and DMA mapping type * @len: Length of this fragment. * This field is zero when the queue slot is empty. - * @continuation: True if this fragment is not the end of a packet. - * @unmap_single: True if dma_unmap_single should be used. * @unmap_len: Length of this fragment to unmap */ struct efx_tx_buffer { - const struct sk_buff *skb; - struct efx_tso_header *tsoh; + union { + const struct sk_buff *skb; + struct efx_tso_header *tsoh; + }; dma_addr_t dma_addr; + unsigned short flags; unsigned short len; - bool continuation; - bool unmap_single; unsigned short unmap_len; }; +#define EFX_TX_BUF_CONT 1 /* not last descriptor of packet */ +#define EFX_TX_BUF_SKB 2 /* buffer is last part of skb */ +#define EFX_TX_BUF_TSOH 4 /* buffer is TSO header */ +#define EFX_TX_BUF_MAP_SINGLE 8 /* buffer was mapped with dma_map_single() */ /** * struct efx_tx_queue - An Efx TX queue diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index 326d799762d6..aa113709831d 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -401,8 +401,10 @@ void efx_nic_push_buffers(struct efx_tx_queue *tx_queue) ++tx_queue->write_count; /* Create TX descriptor ring entry */ + BUILD_BUG_ON(EFX_TX_BUF_CONT != 1); EFX_POPULATE_QWORD_4(*txd, - FSF_AZ_TX_KER_CONT, buffer->continuation, + FSF_AZ_TX_KER_CONT, + buffer->flags & EFX_TX_BUF_CONT, FSF_AZ_TX_KER_BYTE_COUNT, buffer->len, FSF_AZ_TX_KER_BUF_REGION, 0, FSF_AZ_TX_KER_BUF_ADDR, buffer->dma_addr); diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 18713436b443..24c82f3ce0f3 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -39,25 +39,25 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue, struct device *dma_dev = &tx_queue->efx->pci_dev->dev; dma_addr_t unmap_addr = (buffer->dma_addr + buffer->len - buffer->unmap_len); - if (buffer->unmap_single) + if (buffer->flags & EFX_TX_BUF_MAP_SINGLE) dma_unmap_single(dma_dev, unmap_addr, buffer->unmap_len, DMA_TO_DEVICE); else dma_unmap_page(dma_dev, unmap_addr, buffer->unmap_len, DMA_TO_DEVICE); buffer->unmap_len = 0; - buffer->unmap_single = false; } - if (buffer->skb) { + if (buffer->flags & EFX_TX_BUF_SKB) { (*pkts_compl)++; (*bytes_compl) += buffer->skb->len; dev_kfree_skb_any((struct sk_buff *) buffer->skb); - buffer->skb = NULL; netif_vdbg(tx_queue->efx, tx_done, tx_queue->efx->net_dev, "TX queue %d transmission id %x complete\n", tx_queue->queue, tx_queue->read_count); } + + buffer->flags &= EFX_TX_BUF_TSOH; } /** @@ -89,14 +89,14 @@ static void efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, static void efx_tsoh_free(struct efx_tx_queue *tx_queue, struct efx_tx_buffer *buffer) { - if (buffer->tsoh) { + if (buffer->flags & EFX_TX_BUF_TSOH) { if (likely(!buffer->tsoh->unmap_len)) { buffer->tsoh->next = tx_queue->tso_headers_free; tx_queue->tso_headers_free = buffer->tsoh; } else { efx_tsoh_heap_free(tx_queue, buffer->tsoh); } - buffer->tsoh = NULL; + buffer->flags &= ~EFX_TX_BUF_TSOH; } } @@ -163,7 +163,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) unsigned int len, unmap_len = 0, fill_level, insert_ptr; dma_addr_t dma_addr, unmap_addr = 0; unsigned int dma_len; - bool unmap_single; + unsigned short dma_flags; int q_space, i = 0; netdev_tx_t rc = NETDEV_TX_OK; @@ -190,7 +190,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) * since this is more efficient on machines with sparse * memory. */ - unmap_single = true; + dma_flags = EFX_TX_BUF_MAP_SINGLE; dma_addr = dma_map_single(dma_dev, skb->data, len, PCI_DMA_TODEVICE); /* Process all fragments */ @@ -234,10 +234,8 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask; buffer = &tx_queue->buffer[insert_ptr]; efx_tsoh_free(tx_queue, buffer); - EFX_BUG_ON_PARANOID(buffer->tsoh); - EFX_BUG_ON_PARANOID(buffer->skb); + EFX_BUG_ON_PARANOID(buffer->flags); EFX_BUG_ON_PARANOID(buffer->len); - EFX_BUG_ON_PARANOID(!buffer->continuation); EFX_BUG_ON_PARANOID(buffer->unmap_len); dma_len = efx_max_tx_len(efx, dma_addr); @@ -247,13 +245,14 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) /* Fill out per descriptor fields */ buffer->len = dma_len; buffer->dma_addr = dma_addr; + buffer->flags = EFX_TX_BUF_CONT; len -= dma_len; dma_addr += dma_len; ++tx_queue->insert_count; } while (len); /* Transfer ownership of the unmapping to the final buffer */ - buffer->unmap_single = unmap_single; + buffer->flags = EFX_TX_BUF_CONT | dma_flags; buffer->unmap_len = unmap_len; unmap_len = 0; @@ -264,14 +263,14 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) len = skb_frag_size(fragment); i++; /* Map for DMA */ - unmap_single = false; + dma_flags = 0; dma_addr = skb_frag_dma_map(dma_dev, fragment, 0, len, DMA_TO_DEVICE); } /* Transfer ownership of the skb to the final buffer */ buffer->skb = skb; - buffer->continuation = false; + buffer->flags = EFX_TX_BUF_SKB | dma_flags; netdev_tx_sent_queue(tx_queue->core_txq, skb->len); @@ -302,7 +301,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) /* Free the fragment we were mid-way through pushing */ if (unmap_len) { - if (unmap_single) + if (dma_flags & EFX_TX_BUF_MAP_SINGLE) dma_unmap_single(dma_dev, unmap_addr, unmap_len, DMA_TO_DEVICE); else @@ -340,7 +339,6 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue, } efx_dequeue_buffer(tx_queue, buffer, pkts_compl, bytes_compl); - buffer->continuation = true; buffer->len = 0; ++tx_queue->read_count; @@ -484,7 +482,7 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue) { struct efx_nic *efx = tx_queue->efx; unsigned int entries; - int i, rc; + int rc; /* Create the smallest power-of-two aligned ring */ entries = max(roundup_pow_of_two(efx->txq_entries), EFX_MIN_DMAQ_SIZE); @@ -500,8 +498,6 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue) GFP_KERNEL); if (!tx_queue->buffer) return -ENOMEM; - for (i = 0; i <= tx_queue->ptr_mask; ++i) - tx_queue->buffer[i].continuation = true; /* Allocate hardware ring */ rc = efx_nic_probe_tx(tx_queue); @@ -546,7 +542,6 @@ void efx_release_tx_buffers(struct efx_tx_queue *tx_queue) unsigned int pkts_compl = 0, bytes_compl = 0; buffer = &tx_queue->buffer[tx_queue->read_count & tx_queue->ptr_mask]; efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl); - buffer->continuation = true; buffer->len = 0; ++tx_queue->read_count; @@ -631,7 +626,7 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) * @in_len: Remaining length in current SKB fragment * @unmap_len: Length of SKB fragment * @unmap_addr: DMA address of SKB fragment - * @unmap_single: DMA single vs page mapping flag + * @dma_flags: TX buffer flags for DMA mapping - %EFX_TX_BUF_MAP_SINGLE or 0 * @protocol: Network protocol (after any VLAN header) * @header_len: Number of bytes of header * @full_packet_size: Number of bytes to put in each outgoing segment @@ -651,7 +646,7 @@ struct tso_state { unsigned in_len; unsigned unmap_len; dma_addr_t unmap_addr; - bool unmap_single; + unsigned short dma_flags; __be16 protocol; unsigned header_len; @@ -833,9 +828,7 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue, efx_tsoh_free(tx_queue, buffer); EFX_BUG_ON_PARANOID(buffer->len); EFX_BUG_ON_PARANOID(buffer->unmap_len); - EFX_BUG_ON_PARANOID(buffer->skb); - EFX_BUG_ON_PARANOID(!buffer->continuation); - EFX_BUG_ON_PARANOID(buffer->tsoh); + EFX_BUG_ON_PARANOID(buffer->flags); buffer->dma_addr = dma_addr; @@ -845,7 +838,8 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue, if (dma_len >= len) break; - buffer->len = dma_len; /* Don't set the other members */ + buffer->len = dma_len; + buffer->flags = EFX_TX_BUF_CONT; dma_addr += dma_len; len -= dma_len; } @@ -873,12 +867,11 @@ static void efx_tso_put_header(struct efx_tx_queue *tx_queue, efx_tsoh_free(tx_queue, buffer); EFX_BUG_ON_PARANOID(buffer->len); EFX_BUG_ON_PARANOID(buffer->unmap_len); - EFX_BUG_ON_PARANOID(buffer->skb); - EFX_BUG_ON_PARANOID(!buffer->continuation); - EFX_BUG_ON_PARANOID(buffer->tsoh); + EFX_BUG_ON_PARANOID(buffer->flags); buffer->len = len; buffer->dma_addr = tsoh->dma_addr; buffer->tsoh = tsoh; + buffer->flags = EFX_TX_BUF_TSOH | EFX_TX_BUF_CONT; ++tx_queue->insert_count; } @@ -896,11 +889,11 @@ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue) buffer = &tx_queue->buffer[tx_queue->insert_count & tx_queue->ptr_mask]; efx_tsoh_free(tx_queue, buffer); - EFX_BUG_ON_PARANOID(buffer->skb); + EFX_BUG_ON_PARANOID(buffer->flags & EFX_TX_BUF_SKB); if (buffer->unmap_len) { unmap_addr = (buffer->dma_addr + buffer->len - buffer->unmap_len); - if (buffer->unmap_single) + if (buffer->flags & EFX_TX_BUF_MAP_SINGLE) dma_unmap_single(&tx_queue->efx->pci_dev->dev, unmap_addr, buffer->unmap_len, DMA_TO_DEVICE); @@ -911,7 +904,7 @@ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue) buffer->unmap_len = 0; } buffer->len = 0; - buffer->continuation = true; + buffer->flags = 0; } } @@ -938,7 +931,7 @@ static void tso_start(struct tso_state *st, const struct sk_buff *skb) st->out_len = skb->len - st->header_len; st->unmap_len = 0; - st->unmap_single = false; + st->dma_flags = 0; } static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx, @@ -947,7 +940,7 @@ static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx, st->unmap_addr = skb_frag_dma_map(&efx->pci_dev->dev, frag, 0, skb_frag_size(frag), DMA_TO_DEVICE); if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) { - st->unmap_single = false; + st->dma_flags = 0; st->unmap_len = skb_frag_size(frag); st->in_len = skb_frag_size(frag); st->dma_addr = st->unmap_addr; @@ -965,7 +958,7 @@ static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx, st->unmap_addr = dma_map_single(&efx->pci_dev->dev, skb->data + hl, len, DMA_TO_DEVICE); if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) { - st->unmap_single = true; + st->dma_flags = EFX_TX_BUF_MAP_SINGLE; st->unmap_len = len; st->in_len = len; st->dma_addr = st->unmap_addr; @@ -990,7 +983,7 @@ static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue, struct tso_state *st) { struct efx_tx_buffer *buffer; - int n, end_of_packet, rc; + int n, rc; if (st->in_len == 0) return 0; @@ -1008,17 +1001,18 @@ static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue, rc = efx_tx_queue_insert(tx_queue, st->dma_addr, n, &buffer); if (likely(rc == 0)) { - if (st->out_len == 0) + if (st->out_len == 0) { /* Transfer ownership of the skb */ buffer->skb = skb; - - end_of_packet = st->out_len == 0 || st->packet_space == 0; - buffer->continuation = !end_of_packet; + buffer->flags = EFX_TX_BUF_SKB; + } else if (st->packet_space != 0) { + buffer->flags = EFX_TX_BUF_CONT; + } if (st->in_len == 0) { /* Transfer ownership of the DMA mapping */ buffer->unmap_len = st->unmap_len; - buffer->unmap_single = st->unmap_single; + buffer->flags |= st->dma_flags; st->unmap_len = 0; } } @@ -1195,7 +1189,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, unwind: /* Free the DMA mapping we were in the process of writing out */ if (state.unmap_len) { - if (state.unmap_single) + if (state.dma_flags & EFX_TX_BUF_MAP_SINGLE) dma_unmap_single(&efx->pci_dev->dev, state.unmap_addr, state.unmap_len, DMA_TO_DEVICE); else -- cgit v1.2.3 From 14bf718fb97efe9ff649c317e7d87a3617b13e7c Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 22 May 2012 01:27:58 +0100 Subject: sfc: Stop TX queues before they fill up We now have a definite upper bound on the number of descriptors per skb; use that to stop the queue when the next packet might not fit. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 10 ++ drivers/net/ethernet/sfc/net_driver.h | 5 + drivers/net/ethernet/sfc/tx.c | 212 ++++++++++++++++------------------ 3 files changed, 112 insertions(+), 115 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 65a8d49106a4..3b3f08489a5e 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -630,6 +630,16 @@ static void efx_start_datapath(struct efx_nic *efx) efx->rx_buffer_order = get_order(efx->rx_buffer_len + sizeof(struct efx_rx_page_state)); + /* We must keep at least one descriptor in a TX ring empty. + * We could avoid this when the queue size does not exactly + * match the hardware ring size, but it's not that important. + * Therefore we stop the queue when one more skb might fill + * the ring completely. We wake it when half way back to + * empty. + */ + efx->txq_stop_thresh = efx->txq_entries - efx_tx_max_skb_descs(efx); + efx->txq_wake_thresh = efx->txq_stop_thresh / 2; + /* Initialise the channels */ efx_for_each_channel(channel, efx) { efx_for_each_channel_tx_queue(tx_queue, channel) diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 0ac01fa6e63c..28a6d6258692 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -665,6 +665,8 @@ struct vfdi_status; * should be allocated for this NIC * @rxq_entries: Size of receive queues requested by user. * @txq_entries: Size of transmit queues requested by user. + * @txq_stop_thresh: TX queue fill level at or above which we stop it. + * @txq_wake_thresh: TX queue fill level at or below which we wake it. * @tx_dc_base: Base qword address in SRAM of TX queue descriptor caches * @rx_dc_base: Base qword address in SRAM of RX queue descriptor caches * @sram_lim_qw: Qword address limit of SRAM @@ -775,6 +777,9 @@ struct efx_nic { unsigned rxq_entries; unsigned txq_entries; + unsigned int txq_stop_thresh; + unsigned int txq_wake_thresh; + unsigned tx_dc_base; unsigned rx_dc_base; unsigned sram_lim_qw; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 24c82f3ce0f3..330d9111a339 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -22,14 +22,6 @@ #include "nic.h" #include "workarounds.h" -/* - * TX descriptor ring full threshold - * - * The tx_queue descriptor ring fill-level must fall below this value - * before we restart the netif queue - */ -#define EFX_TXQ_THRESHOLD(_efx) ((_efx)->txq_entries / 2u) - static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue, struct efx_tx_buffer *buffer, unsigned int *pkts_compl, @@ -138,6 +130,56 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx) return max_descs; } +/* Get partner of a TX queue, seen as part of the same net core queue */ +static struct efx_tx_queue *efx_tx_queue_partner(struct efx_tx_queue *tx_queue) +{ + if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD) + return tx_queue - EFX_TXQ_TYPE_OFFLOAD; + else + return tx_queue + EFX_TXQ_TYPE_OFFLOAD; +} + +static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1) +{ + /* We need to consider both queues that the net core sees as one */ + struct efx_tx_queue *txq2 = efx_tx_queue_partner(txq1); + struct efx_nic *efx = txq1->efx; + unsigned int fill_level; + + fill_level = max(txq1->insert_count - txq1->old_read_count, + txq2->insert_count - txq2->old_read_count); + if (likely(fill_level < efx->txq_stop_thresh)) + return; + + /* We used the stale old_read_count above, which gives us a + * pessimistic estimate of the fill level (which may even + * validly be >= efx->txq_entries). Now try again using + * read_count (more likely to be a cache miss). + * + * If we read read_count and then conditionally stop the + * queue, it is possible for the completion path to race with + * us and complete all outstanding descriptors in the middle, + * after which there will be no more completions to wake it. + * Therefore we stop the queue first, then read read_count + * (with a memory barrier to ensure the ordering), then + * restart the queue if the fill level turns out to be low + * enough. + */ + netif_tx_stop_queue(txq1->core_txq); + smp_mb(); + txq1->old_read_count = ACCESS_ONCE(txq1->read_count); + txq2->old_read_count = ACCESS_ONCE(txq2->read_count); + + fill_level = max(txq1->insert_count - txq1->old_read_count, + txq2->insert_count - txq2->old_read_count); + EFX_BUG_ON_PARANOID(fill_level >= efx->txq_entries); + if (likely(fill_level < efx->txq_stop_thresh)) { + smp_mb(); + if (likely(!efx->loopback_selftest)) + netif_tx_start_queue(txq1->core_txq); + } +} + /* * Add a socket buffer to a TX queue * @@ -151,7 +193,7 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx) * This function is split out from efx_hard_start_xmit to allow the * loopback test to direct packets via specific TX queues. * - * Returns NETDEV_TX_OK or NETDEV_TX_BUSY + * Returns NETDEV_TX_OK. * You must hold netif_tx_lock() to call this function. */ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) @@ -160,12 +202,11 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) struct device *dma_dev = &efx->pci_dev->dev; struct efx_tx_buffer *buffer; skb_frag_t *fragment; - unsigned int len, unmap_len = 0, fill_level, insert_ptr; + unsigned int len, unmap_len = 0, insert_ptr; dma_addr_t dma_addr, unmap_addr = 0; unsigned int dma_len; unsigned short dma_flags; - int q_space, i = 0; - netdev_tx_t rc = NETDEV_TX_OK; + int i = 0; EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count); @@ -183,9 +224,6 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) return NETDEV_TX_OK; } - fill_level = tx_queue->insert_count - tx_queue->old_read_count; - q_space = efx->txq_entries - 1 - fill_level; - /* Map for DMA. Use dma_map_single rather than dma_map_page * since this is more efficient on machines with sparse * memory. @@ -205,32 +243,6 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) /* Add to TX queue, splitting across DMA boundaries */ do { - if (unlikely(q_space-- <= 0)) { - /* It might be that completions have - * happened since the xmit path last - * checked. Update the xmit path's - * copy of read_count. - */ - netif_tx_stop_queue(tx_queue->core_txq); - /* This memory barrier protects the - * change of queue state from the access - * of read_count. */ - smp_mb(); - tx_queue->old_read_count = - ACCESS_ONCE(tx_queue->read_count); - fill_level = (tx_queue->insert_count - - tx_queue->old_read_count); - q_space = efx->txq_entries - 1 - fill_level; - if (unlikely(q_space-- <= 0)) { - rc = NETDEV_TX_BUSY; - goto unwind; - } - smp_mb(); - if (likely(!efx->loopback_selftest)) - netif_tx_start_queue( - tx_queue->core_txq); - } - insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask; buffer = &tx_queue->buffer[insert_ptr]; efx_tsoh_free(tx_queue, buffer); @@ -277,6 +289,8 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) /* Pass off to hardware */ efx_nic_push_buffers(tx_queue); + efx_tx_maybe_stop_queue(tx_queue); + return NETDEV_TX_OK; dma_err: @@ -288,7 +302,6 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) /* Mark the packet as transmitted, and free the SKB ourselves */ dev_kfree_skb_any(skb); - unwind: /* Work backwards until we hit the original insert pointer value */ while (tx_queue->insert_count != tx_queue->write_count) { unsigned int pkts_compl = 0, bytes_compl = 0; @@ -309,7 +322,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) DMA_TO_DEVICE); } - return rc; + return NETDEV_TX_OK; } /* Remove packets from the TX queue @@ -448,6 +461,7 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) { unsigned fill_level; struct efx_nic *efx = tx_queue->efx; + struct efx_tx_queue *txq2; unsigned int pkts_compl = 0, bytes_compl = 0; EFX_BUG_ON_PARANOID(index > tx_queue->ptr_mask); @@ -455,15 +469,18 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) efx_dequeue_buffers(tx_queue, index, &pkts_compl, &bytes_compl); netdev_tx_completed_queue(tx_queue->core_txq, pkts_compl, bytes_compl); - /* See if we need to restart the netif queue. This barrier - * separates the update of read_count from the test of the - * queue state. */ + /* See if we need to restart the netif queue. This memory + * barrier ensures that we write read_count (inside + * efx_dequeue_buffers()) before reading the queue status. + */ smp_mb(); if (unlikely(netif_tx_queue_stopped(tx_queue->core_txq)) && likely(efx->port_enabled) && likely(netif_device_present(efx->net_dev))) { - fill_level = tx_queue->insert_count - tx_queue->read_count; - if (fill_level < EFX_TXQ_THRESHOLD(efx)) + txq2 = efx_tx_queue_partner(tx_queue); + fill_level = max(tx_queue->insert_count - tx_queue->read_count, + txq2->insert_count - txq2->read_count); + if (fill_level <= efx->txq_wake_thresh) netif_tx_wake_queue(tx_queue->core_txq); } @@ -776,47 +793,19 @@ efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, struct efx_tso_header *tsoh) * @len: Length of fragment * @final_buffer: The final buffer inserted into the queue * - * Push descriptors onto the TX queue. Return 0 on success or 1 if - * @tx_queue full. + * Push descriptors onto the TX queue. */ -static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue, - dma_addr_t dma_addr, unsigned len, - struct efx_tx_buffer **final_buffer) +static void efx_tx_queue_insert(struct efx_tx_queue *tx_queue, + dma_addr_t dma_addr, unsigned len, + struct efx_tx_buffer **final_buffer) { struct efx_tx_buffer *buffer; struct efx_nic *efx = tx_queue->efx; - unsigned dma_len, fill_level, insert_ptr; - int q_space; + unsigned dma_len, insert_ptr; EFX_BUG_ON_PARANOID(len <= 0); - fill_level = tx_queue->insert_count - tx_queue->old_read_count; - /* -1 as there is no way to represent all descriptors used */ - q_space = efx->txq_entries - 1 - fill_level; - while (1) { - if (unlikely(q_space-- <= 0)) { - /* It might be that completions have happened - * since the xmit path last checked. Update - * the xmit path's copy of read_count. - */ - netif_tx_stop_queue(tx_queue->core_txq); - /* This memory barrier protects the change of - * queue state from the access of read_count. */ - smp_mb(); - tx_queue->old_read_count = - ACCESS_ONCE(tx_queue->read_count); - fill_level = (tx_queue->insert_count - - tx_queue->old_read_count); - q_space = efx->txq_entries - 1 - fill_level; - if (unlikely(q_space-- <= 0)) { - *final_buffer = NULL; - return 1; - } - smp_mb(); - netif_tx_start_queue(tx_queue->core_txq); - } - insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask; buffer = &tx_queue->buffer[insert_ptr]; ++tx_queue->insert_count; @@ -847,7 +836,6 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue, EFX_BUG_ON_PARANOID(!len); buffer->len = len; *final_buffer = buffer; - return 0; } @@ -975,20 +963,19 @@ static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx, * @st: TSO state * * Form descriptors for the current fragment, until we reach the end - * of fragment or end-of-packet. Return 0 on success, 1 if not enough - * space in @tx_queue. + * of fragment or end-of-packet. */ -static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue, - const struct sk_buff *skb, - struct tso_state *st) +static void tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue, + const struct sk_buff *skb, + struct tso_state *st) { struct efx_tx_buffer *buffer; - int n, rc; + int n; if (st->in_len == 0) - return 0; + return; if (st->packet_space == 0) - return 0; + return; EFX_BUG_ON_PARANOID(st->in_len <= 0); EFX_BUG_ON_PARANOID(st->packet_space <= 0); @@ -999,26 +986,24 @@ static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue, st->out_len -= n; st->in_len -= n; - rc = efx_tx_queue_insert(tx_queue, st->dma_addr, n, &buffer); - if (likely(rc == 0)) { - if (st->out_len == 0) { - /* Transfer ownership of the skb */ - buffer->skb = skb; - buffer->flags = EFX_TX_BUF_SKB; - } else if (st->packet_space != 0) { - buffer->flags = EFX_TX_BUF_CONT; - } + efx_tx_queue_insert(tx_queue, st->dma_addr, n, &buffer); - if (st->in_len == 0) { - /* Transfer ownership of the DMA mapping */ - buffer->unmap_len = st->unmap_len; - buffer->flags |= st->dma_flags; - st->unmap_len = 0; - } + if (st->out_len == 0) { + /* Transfer ownership of the skb */ + buffer->skb = skb; + buffer->flags = EFX_TX_BUF_SKB; + } else if (st->packet_space != 0) { + buffer->flags = EFX_TX_BUF_CONT; + } + + if (st->in_len == 0) { + /* Transfer ownership of the DMA mapping */ + buffer->unmap_len = st->unmap_len; + buffer->flags |= st->dma_flags; + st->unmap_len = 0; } st->dma_addr += n; - return rc; } @@ -1112,13 +1097,13 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, * * Add socket buffer @skb to @tx_queue, doing TSO or return != 0 if * @skb was not enqueued. In all cases @skb is consumed. Return - * %NETDEV_TX_OK or %NETDEV_TX_BUSY. + * %NETDEV_TX_OK. */ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb) { struct efx_nic *efx = tx_queue->efx; - int frag_i, rc, rc2 = NETDEV_TX_OK; + int frag_i, rc; struct tso_state state; /* Find the packet protocol and sanity-check it */ @@ -1150,11 +1135,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, goto mem_err; while (1) { - rc = tso_fill_packet_with_fragment(tx_queue, skb, &state); - if (unlikely(rc)) { - rc2 = NETDEV_TX_BUSY; - goto unwind; - } + tso_fill_packet_with_fragment(tx_queue, skb, &state); /* Move onto the next fragment? */ if (state.in_len == 0) { @@ -1178,6 +1159,8 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, /* Pass off to hardware */ efx_nic_push_buffers(tx_queue); + efx_tx_maybe_stop_queue(tx_queue); + tx_queue->tso_bursts++; return NETDEV_TX_OK; @@ -1186,7 +1169,6 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, "Out of memory for TSO headers, or DMA mapping error\n"); dev_kfree_skb_any(skb); - unwind: /* Free the DMA mapping we were in the process of writing out */ if (state.unmap_len) { if (state.dma_flags & EFX_TX_BUF_MAP_SINGLE) @@ -1198,7 +1180,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, } efx_enqueue_unwind(tx_queue); - return rc2; + return NETDEV_TX_OK; } -- cgit v1.2.3 From f7251a9ce936f1006fbfdef63dbe42ae5e0fee7c Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 17 May 2012 18:40:54 +0100 Subject: sfc: Simplify TSO header buffer allocation TSO header buffers contain a control structure immediately followed by the packet headers, and are kept on a free list when not in use. This complicates buffer management and tends to result in cache read misses when we recycle such buffers (particularly if DMA-coherent memory requires caches to be disabled). Replace the free list with a simple mapping by descriptor index. We know that there is always a payload descriptor between any two descriptors with TSO header buffers, so we can allocate only one such buffer for each two descriptors. While we're at it, use a standard error code for allocation failure, not -1. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/net_driver.h | 13 +- drivers/net/ethernet/sfc/nic.c | 2 +- drivers/net/ethernet/sfc/tx.c | 315 ++++++++++++---------------------- 3 files changed, 112 insertions(+), 218 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 28a6d6258692..a4fe9a786ef8 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -94,7 +94,8 @@ struct efx_special_buffer { * struct efx_tx_buffer - buffer state for a TX descriptor * @skb: When @flags & %EFX_TX_BUF_SKB, the associated socket buffer to be * freed when descriptor completes - * @tsoh: When @flags & %EFX_TX_BUF_TSOH, the associated TSO header structure. + * @heap_buf: When @flags & %EFX_TX_BUF_HEAP, the associated heap buffer to be + * freed when descriptor completes. * @dma_addr: DMA address of the fragment. * @flags: Flags for allocation and DMA mapping type * @len: Length of this fragment. @@ -104,7 +105,7 @@ struct efx_special_buffer { struct efx_tx_buffer { union { const struct sk_buff *skb; - struct efx_tso_header *tsoh; + void *heap_buf; }; dma_addr_t dma_addr; unsigned short flags; @@ -113,7 +114,7 @@ struct efx_tx_buffer { }; #define EFX_TX_BUF_CONT 1 /* not last descriptor of packet */ #define EFX_TX_BUF_SKB 2 /* buffer is last part of skb */ -#define EFX_TX_BUF_TSOH 4 /* buffer is TSO header */ +#define EFX_TX_BUF_HEAP 4 /* buffer was allocated with kmalloc() */ #define EFX_TX_BUF_MAP_SINGLE 8 /* buffer was mapped with dma_map_single() */ /** @@ -134,6 +135,7 @@ struct efx_tx_buffer { * @channel: The associated channel * @core_txq: The networking core TX queue structure * @buffer: The software buffer ring + * @tsoh_page: Array of pages of TSO header buffers * @txd: The hardware descriptor ring * @ptr_mask: The size of the ring minus 1. * @initialised: Has hardware queue been initialised? @@ -157,9 +159,6 @@ struct efx_tx_buffer { * variable indicates that the queue is full. This is to * avoid cache-line ping-pong between the xmit path and the * completion path. - * @tso_headers_free: A list of TSO headers allocated for this TX queue - * that are not in use, and so available for new TSO sends. The list - * is protected by the TX queue lock. * @tso_bursts: Number of times TSO xmit invoked by kernel * @tso_long_headers: Number of packets with headers too long for standard * blocks @@ -176,6 +175,7 @@ struct efx_tx_queue { struct efx_channel *channel; struct netdev_queue *core_txq; struct efx_tx_buffer *buffer; + struct efx_buffer *tsoh_page; struct efx_special_buffer txd; unsigned int ptr_mask; bool initialised; @@ -188,7 +188,6 @@ struct efx_tx_queue { unsigned int insert_count ____cacheline_aligned_in_smp; unsigned int write_count; unsigned int old_read_count; - struct efx_tso_header *tso_headers_free; unsigned int tso_bursts; unsigned int tso_long_headers; unsigned int tso_packets; diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index aa113709831d..cdff40b65729 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -298,7 +298,7 @@ efx_free_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer) /************************************************************************** * * Generic buffer handling - * These buffers are used for interrupt status and MAC stats + * These buffers are used for interrupt status, MAC stats, etc. * **************************************************************************/ diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 330d9111a339..61bc0ed718e3 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -47,51 +47,16 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue, netif_vdbg(tx_queue->efx, tx_done, tx_queue->efx->net_dev, "TX queue %d transmission id %x complete\n", tx_queue->queue, tx_queue->read_count); + } else if (buffer->flags & EFX_TX_BUF_HEAP) { + kfree(buffer->heap_buf); } - buffer->flags &= EFX_TX_BUF_TSOH; + buffer->len = 0; + buffer->flags = 0; } -/** - * struct efx_tso_header - a DMA mapped buffer for packet headers - * @next: Linked list of free ones. - * The list is protected by the TX queue lock. - * @dma_unmap_len: Length to unmap for an oversize buffer, or 0. - * @dma_addr: The DMA address of the header below. - * - * This controls the memory used for a TSO header. Use TSOH_DATA() - * to find the packet header data. Use TSOH_SIZE() to calculate the - * total size required for a given packet header length. TSO headers - * in the free list are exactly %TSOH_STD_SIZE bytes in size. - */ -struct efx_tso_header { - union { - struct efx_tso_header *next; - size_t unmap_len; - }; - dma_addr_t dma_addr; -}; - static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb); -static void efx_fini_tso(struct efx_tx_queue *tx_queue); -static void efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, - struct efx_tso_header *tsoh); - -static void efx_tsoh_free(struct efx_tx_queue *tx_queue, - struct efx_tx_buffer *buffer) -{ - if (buffer->flags & EFX_TX_BUF_TSOH) { - if (likely(!buffer->tsoh->unmap_len)) { - buffer->tsoh->next = tx_queue->tso_headers_free; - tx_queue->tso_headers_free = buffer->tsoh; - } else { - efx_tsoh_heap_free(tx_queue, buffer->tsoh); - } - buffer->flags &= ~EFX_TX_BUF_TSOH; - } -} - static inline unsigned efx_max_tx_len(struct efx_nic *efx, dma_addr_t dma_addr) @@ -245,7 +210,6 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) do { insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask; buffer = &tx_queue->buffer[insert_ptr]; - efx_tsoh_free(tx_queue, buffer); EFX_BUG_ON_PARANOID(buffer->flags); EFX_BUG_ON_PARANOID(buffer->len); EFX_BUG_ON_PARANOID(buffer->unmap_len); @@ -309,7 +273,6 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask; buffer = &tx_queue->buffer[insert_ptr]; efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl); - buffer->len = 0; } /* Free the fragment we were mid-way through pushing */ @@ -352,7 +315,6 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue, } efx_dequeue_buffer(tx_queue, buffer, pkts_compl, bytes_compl); - buffer->len = 0; ++tx_queue->read_count; read_ptr = tx_queue->read_count & tx_queue->ptr_mask; @@ -495,6 +457,21 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) } } +/* Size of page-based TSO header buffers. Larger blocks must be + * allocated from the heap. + */ +#define TSOH_STD_SIZE 128 +#define TSOH_PER_PAGE (PAGE_SIZE / TSOH_STD_SIZE) + +/* At most half the descriptors in the queue at any time will refer to + * a TSO header buffer, since they must always be followed by a + * payload descriptor referring to an skb. + */ +static unsigned int efx_tsoh_page_count(struct efx_tx_queue *tx_queue) +{ + return DIV_ROUND_UP(tx_queue->ptr_mask + 1, 2 * TSOH_PER_PAGE); +} + int efx_probe_tx_queue(struct efx_tx_queue *tx_queue) { struct efx_nic *efx = tx_queue->efx; @@ -516,14 +493,27 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue) if (!tx_queue->buffer) return -ENOMEM; + if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD) { + tx_queue->tsoh_page = + kcalloc(efx_tsoh_page_count(tx_queue), + sizeof(tx_queue->tsoh_page[0]), GFP_KERNEL); + if (!tx_queue->tsoh_page) { + rc = -ENOMEM; + goto fail1; + } + } + /* Allocate hardware ring */ rc = efx_nic_probe_tx(tx_queue); if (rc) - goto fail; + goto fail2; return 0; - fail: +fail2: + kfree(tx_queue->tsoh_page); + tx_queue->tsoh_page = NULL; +fail1: kfree(tx_queue->buffer); tx_queue->buffer = NULL; return rc; @@ -559,7 +549,6 @@ void efx_release_tx_buffers(struct efx_tx_queue *tx_queue) unsigned int pkts_compl = 0, bytes_compl = 0; buffer = &tx_queue->buffer[tx_queue->read_count & tx_queue->ptr_mask]; efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl); - buffer->len = 0; ++tx_queue->read_count; } @@ -580,13 +569,12 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) efx_nic_fini_tx(tx_queue); efx_release_tx_buffers(tx_queue); - - /* Free up TSO header cache */ - efx_fini_tso(tx_queue); } void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) { + int i; + if (!tx_queue->buffer) return; @@ -594,6 +582,14 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) "destroying TX queue %d\n", tx_queue->queue); efx_nic_remove_tx(tx_queue); + if (tx_queue->tsoh_page) { + for (i = 0; i < efx_tsoh_page_count(tx_queue); i++) + efx_nic_free_buffer(tx_queue->efx, + &tx_queue->tsoh_page[i]); + kfree(tx_queue->tsoh_page); + tx_queue->tsoh_page = NULL; + } + kfree(tx_queue->buffer); tx_queue->buffer = NULL; } @@ -616,17 +612,6 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) #define TSOH_OFFSET NET_IP_ALIGN #endif -#define TSOH_BUFFER(tsoh) ((u8 *)(tsoh + 1) + TSOH_OFFSET) - -/* Total size of struct efx_tso_header, buffer and padding */ -#define TSOH_SIZE(hdr_len) \ - (sizeof(struct efx_tso_header) + TSOH_OFFSET + hdr_len) - -/* Size of blocks on free list. Larger blocks must be allocated from - * the heap. - */ -#define TSOH_STD_SIZE 128 - #define PTR_DIFF(p1, p2) ((u8 *)(p1) - (u8 *)(p2)) #define ETH_HDR_LEN(skb) (skb_network_header(skb) - (skb)->data) #define SKB_TCP_OFF(skb) PTR_DIFF(tcp_hdr(skb), (skb)->data) @@ -699,91 +684,43 @@ static __be16 efx_tso_check_protocol(struct sk_buff *skb) return protocol; } - -/* - * Allocate a page worth of efx_tso_header structures, and string them - * into the tx_queue->tso_headers_free linked list. Return 0 or -ENOMEM. - */ -static int efx_tsoh_block_alloc(struct efx_tx_queue *tx_queue) +static u8 *efx_tsoh_get_buffer(struct efx_tx_queue *tx_queue, + struct efx_tx_buffer *buffer, unsigned int len) { - struct device *dma_dev = &tx_queue->efx->pci_dev->dev; - struct efx_tso_header *tsoh; - dma_addr_t dma_addr; - u8 *base_kva, *kva; + u8 *result; - base_kva = dma_alloc_coherent(dma_dev, PAGE_SIZE, &dma_addr, GFP_ATOMIC); - if (base_kva == NULL) { - netif_err(tx_queue->efx, tx_err, tx_queue->efx->net_dev, - "Unable to allocate page for TSO headers\n"); - return -ENOMEM; - } - - /* dma_alloc_coherent() allocates pages. */ - EFX_BUG_ON_PARANOID(dma_addr & (PAGE_SIZE - 1u)); - - for (kva = base_kva; kva < base_kva + PAGE_SIZE; kva += TSOH_STD_SIZE) { - tsoh = (struct efx_tso_header *)kva; - tsoh->dma_addr = dma_addr + (TSOH_BUFFER(tsoh) - base_kva); - tsoh->next = tx_queue->tso_headers_free; - tx_queue->tso_headers_free = tsoh; - } - - return 0; -} - - -/* Free up a TSO header, and all others in the same page. */ -static void efx_tsoh_block_free(struct efx_tx_queue *tx_queue, - struct efx_tso_header *tsoh, - struct device *dma_dev) -{ - struct efx_tso_header **p; - unsigned long base_kva; - dma_addr_t base_dma; + EFX_BUG_ON_PARANOID(buffer->len); + EFX_BUG_ON_PARANOID(buffer->flags); + EFX_BUG_ON_PARANOID(buffer->unmap_len); - base_kva = (unsigned long)tsoh & PAGE_MASK; - base_dma = tsoh->dma_addr & PAGE_MASK; + if (likely(len <= TSOH_STD_SIZE - TSOH_OFFSET)) { + unsigned index = + (tx_queue->insert_count & tx_queue->ptr_mask) / 2; + struct efx_buffer *page_buf = + &tx_queue->tsoh_page[index / TSOH_PER_PAGE]; + unsigned offset = + TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + TSOH_OFFSET; - p = &tx_queue->tso_headers_free; - while (*p != NULL) { - if (((unsigned long)*p & PAGE_MASK) == base_kva) - *p = (*p)->next; - else - p = &(*p)->next; - } + if (unlikely(!page_buf->addr) && + efx_nic_alloc_buffer(tx_queue->efx, page_buf, PAGE_SIZE)) + return NULL; - dma_free_coherent(dma_dev, PAGE_SIZE, (void *)base_kva, base_dma); -} + result = (u8 *)page_buf->addr + offset; + buffer->dma_addr = page_buf->dma_addr + offset; + buffer->flags = EFX_TX_BUF_CONT; + } else { + tx_queue->tso_long_headers++; -static struct efx_tso_header * -efx_tsoh_heap_alloc(struct efx_tx_queue *tx_queue, size_t header_len) -{ - struct efx_tso_header *tsoh; - - tsoh = kmalloc(TSOH_SIZE(header_len), GFP_ATOMIC | GFP_DMA); - if (unlikely(!tsoh)) - return NULL; - - tsoh->dma_addr = dma_map_single(&tx_queue->efx->pci_dev->dev, - TSOH_BUFFER(tsoh), header_len, - DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&tx_queue->efx->pci_dev->dev, - tsoh->dma_addr))) { - kfree(tsoh); - return NULL; + buffer->heap_buf = kmalloc(TSOH_OFFSET + len, GFP_ATOMIC); + if (unlikely(!buffer->heap_buf)) + return NULL; + result = (u8 *)buffer->heap_buf + TSOH_OFFSET; + buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_HEAP; } - tsoh->unmap_len = header_len; - return tsoh; -} + buffer->len = len; -static void -efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, struct efx_tso_header *tsoh) -{ - dma_unmap_single(&tx_queue->efx->pci_dev->dev, - tsoh->dma_addr, tsoh->unmap_len, - DMA_TO_DEVICE); - kfree(tsoh); + return result; } /** @@ -814,7 +751,6 @@ static void efx_tx_queue_insert(struct efx_tx_queue *tx_queue, tx_queue->read_count >= efx->txq_entries); - efx_tsoh_free(tx_queue, buffer); EFX_BUG_ON_PARANOID(buffer->len); EFX_BUG_ON_PARANOID(buffer->unmap_len); EFX_BUG_ON_PARANOID(buffer->flags); @@ -846,53 +782,42 @@ static void efx_tx_queue_insert(struct efx_tx_queue *tx_queue, * a single fragment, and we know it doesn't cross a page boundary. It * also allows us to not worry about end-of-packet etc. */ -static void efx_tso_put_header(struct efx_tx_queue *tx_queue, - struct efx_tso_header *tsoh, unsigned len) +static int efx_tso_put_header(struct efx_tx_queue *tx_queue, + struct efx_tx_buffer *buffer, u8 *header) { - struct efx_tx_buffer *buffer; - - buffer = &tx_queue->buffer[tx_queue->insert_count & tx_queue->ptr_mask]; - efx_tsoh_free(tx_queue, buffer); - EFX_BUG_ON_PARANOID(buffer->len); - EFX_BUG_ON_PARANOID(buffer->unmap_len); - EFX_BUG_ON_PARANOID(buffer->flags); - buffer->len = len; - buffer->dma_addr = tsoh->dma_addr; - buffer->tsoh = tsoh; - buffer->flags = EFX_TX_BUF_TSOH | EFX_TX_BUF_CONT; + if (unlikely(buffer->flags & EFX_TX_BUF_HEAP)) { + buffer->dma_addr = dma_map_single(&tx_queue->efx->pci_dev->dev, + header, buffer->len, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(&tx_queue->efx->pci_dev->dev, + buffer->dma_addr))) { + kfree(buffer->heap_buf); + buffer->len = 0; + buffer->flags = 0; + return -ENOMEM; + } + buffer->unmap_len = buffer->len; + buffer->flags |= EFX_TX_BUF_MAP_SINGLE; + } ++tx_queue->insert_count; + return 0; } -/* Remove descriptors put into a tx_queue. */ +/* Remove buffers put into a tx_queue. None of the buffers must have + * an skb attached. + */ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue) { struct efx_tx_buffer *buffer; - dma_addr_t unmap_addr; /* Work backwards until we hit the original insert pointer value */ while (tx_queue->insert_count != tx_queue->write_count) { --tx_queue->insert_count; buffer = &tx_queue->buffer[tx_queue->insert_count & tx_queue->ptr_mask]; - efx_tsoh_free(tx_queue, buffer); - EFX_BUG_ON_PARANOID(buffer->flags & EFX_TX_BUF_SKB); - if (buffer->unmap_len) { - unmap_addr = (buffer->dma_addr + buffer->len - - buffer->unmap_len); - if (buffer->flags & EFX_TX_BUF_MAP_SINGLE) - dma_unmap_single(&tx_queue->efx->pci_dev->dev, - unmap_addr, buffer->unmap_len, - DMA_TO_DEVICE); - else - dma_unmap_page(&tx_queue->efx->pci_dev->dev, - unmap_addr, buffer->unmap_len, - DMA_TO_DEVICE); - buffer->unmap_len = 0; - } - buffer->len = 0; - buffer->flags = 0; + efx_dequeue_buffer(tx_queue, buffer, NULL, NULL); } } @@ -1014,35 +939,24 @@ static void tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue, * @st: TSO state * * Generate a new header and prepare for the new packet. Return 0 on - * success, or -1 if failed to alloc header. + * success, or -%ENOMEM if failed to alloc header. */ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, const struct sk_buff *skb, struct tso_state *st) { - struct efx_tso_header *tsoh; + struct efx_tx_buffer *buffer = + &tx_queue->buffer[tx_queue->insert_count & tx_queue->ptr_mask]; struct tcphdr *tsoh_th; unsigned ip_length; u8 *header; + int rc; - /* Allocate a DMA-mapped header buffer. */ - if (likely(TSOH_SIZE(st->header_len) <= TSOH_STD_SIZE)) { - if (tx_queue->tso_headers_free == NULL) { - if (efx_tsoh_block_alloc(tx_queue)) - return -1; - } - EFX_BUG_ON_PARANOID(!tx_queue->tso_headers_free); - tsoh = tx_queue->tso_headers_free; - tx_queue->tso_headers_free = tsoh->next; - tsoh->unmap_len = 0; - } else { - tx_queue->tso_long_headers++; - tsoh = efx_tsoh_heap_alloc(tx_queue, st->header_len); - if (unlikely(!tsoh)) - return -1; - } + /* Allocate and insert a DMA-mapped header buffer. */ + header = efx_tsoh_get_buffer(tx_queue, buffer, st->header_len); + if (!header) + return -ENOMEM; - header = TSOH_BUFFER(tsoh); tsoh_th = (struct tcphdr *)(header + SKB_TCP_OFF(skb)); /* Copy and update the headers. */ @@ -1078,12 +992,13 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, tsoh_iph->payload_len = htons(ip_length - sizeof(*tsoh_iph)); } + rc = efx_tso_put_header(tx_queue, buffer, header); + if (unlikely(rc)) + return rc; + st->packet_space = skb_shinfo(skb)->gso_size; ++tx_queue->tso_packets; - /* Form a descriptor for this header. */ - efx_tso_put_header(tx_queue, tsoh, st->header_len); - return 0; } @@ -1182,23 +1097,3 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, efx_enqueue_unwind(tx_queue); return NETDEV_TX_OK; } - - -/* - * Free up all TSO datastructures associated with tx_queue. This - * routine should be called only once the tx_queue is both empty and - * will no longer be used. - */ -static void efx_fini_tso(struct efx_tx_queue *tx_queue) -{ - unsigned i; - - if (tx_queue->buffer) { - for (i = 0; i <= tx_queue->ptr_mask; ++i) - efx_tsoh_free(tx_queue, &tx_queue->buffer[i]); - } - - while (tx_queue->tso_headers_free != NULL) - efx_tsoh_block_free(tx_queue, tx_queue->tso_headers_free, - &tx_queue->efx->pci_dev->dev); -} -- cgit v1.2.3 From 53cb13c680b98c637d95dd731b01bc284b3aa33d Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 19 Jun 2012 20:03:41 +0100 Subject: sfc: Replace tso_state::full_packet_space with ip_base_len We only use tso_state::full_packet_space to calculate the IPv4 tot_len or IPv6 payload_len, not to set tso_state::packet_space. Replace it with an ip_base_len field holding the value of tot_len or payload_len before including the TCP payload, which is much more useful when constructing the new headers. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/tx.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 61bc0ed718e3..d9dbebc9f819 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -631,7 +631,7 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) * @dma_flags: TX buffer flags for DMA mapping - %EFX_TX_BUF_MAP_SINGLE or 0 * @protocol: Network protocol (after any VLAN header) * @header_len: Number of bytes of header - * @full_packet_size: Number of bytes to put in each outgoing segment + * @ip_base_len: IPv4 tot_len or IPv6 payload_len, before TCP payload * * The state used during segmentation. It is put into this data structure * just to make it easy to pass into inline functions. @@ -652,7 +652,7 @@ struct tso_state { __be16 protocol; unsigned header_len; - int full_packet_size; + unsigned int ip_base_len; }; @@ -830,12 +830,14 @@ static void tso_start(struct tso_state *st, const struct sk_buff *skb) */ st->header_len = ((tcp_hdr(skb)->doff << 2u) + PTR_DIFF(tcp_hdr(skb), skb->data)); - st->full_packet_size = st->header_len + skb_shinfo(skb)->gso_size; - if (st->protocol == htons(ETH_P_IP)) + if (st->protocol == htons(ETH_P_IP)) { + st->ip_base_len = st->header_len - ETH_HDR_LEN(skb); st->ipv4_id = ntohs(ip_hdr(skb)->id); - else + } else { + st->ip_base_len = tcp_hdr(skb)->doff << 2u; st->ipv4_id = 0; + } st->seqnum = ntohl(tcp_hdr(skb)->seq); EFX_BUG_ON_PARANOID(tcp_hdr(skb)->urg); @@ -966,15 +968,16 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, st->seqnum += skb_shinfo(skb)->gso_size; if (st->out_len > skb_shinfo(skb)->gso_size) { /* This packet will not finish the TSO burst. */ - ip_length = st->full_packet_size - ETH_HDR_LEN(skb); + st->packet_space = skb_shinfo(skb)->gso_size; tsoh_th->fin = 0; tsoh_th->psh = 0; } else { /* This packet will be the last in the TSO burst. */ - ip_length = st->header_len - ETH_HDR_LEN(skb) + st->out_len; + st->packet_space = st->out_len; tsoh_th->fin = tcp_hdr(skb)->fin; tsoh_th->psh = tcp_hdr(skb)->psh; } + ip_length = st->ip_base_len + st->packet_space; if (st->protocol == htons(ETH_P_IP)) { struct iphdr *tsoh_iph = @@ -989,14 +992,13 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, struct ipv6hdr *tsoh_iph = (struct ipv6hdr *)(header + SKB_IPV6_OFF(skb)); - tsoh_iph->payload_len = htons(ip_length - sizeof(*tsoh_iph)); + tsoh_iph->payload_len = htons(ip_length); } rc = efx_tso_put_header(tx_queue, buffer, header); if (unlikely(rc)) return rc; - st->packet_space = skb_shinfo(skb)->gso_size; ++tx_queue->tso_packets; return 0; -- cgit v1.2.3 From 9714284f83387d330496758e5c10a649fd9a677d Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 22 Jun 2012 02:44:01 +0100 Subject: sfc: Stash header offsets for TSO in struct tso_state Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/tx.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index d9dbebc9f819..ebca75ed78dc 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -613,10 +613,6 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) #endif #define PTR_DIFF(p1, p2) ((u8 *)(p1) - (u8 *)(p2)) -#define ETH_HDR_LEN(skb) (skb_network_header(skb) - (skb)->data) -#define SKB_TCP_OFF(skb) PTR_DIFF(tcp_hdr(skb), (skb)->data) -#define SKB_IPV4_OFF(skb) PTR_DIFF(ip_hdr(skb), (skb)->data) -#define SKB_IPV6_OFF(skb) PTR_DIFF(ipv6_hdr(skb), (skb)->data) /** * struct tso_state - TSO state for an SKB @@ -630,6 +626,8 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) * @unmap_addr: DMA address of SKB fragment * @dma_flags: TX buffer flags for DMA mapping - %EFX_TX_BUF_MAP_SINGLE or 0 * @protocol: Network protocol (after any VLAN header) + * @ip_off: Offset of IP header + * @tcp_off: Offset of TCP header * @header_len: Number of bytes of header * @ip_base_len: IPv4 tot_len or IPv6 payload_len, before TCP payload * @@ -651,6 +649,8 @@ struct tso_state { unsigned short dma_flags; __be16 protocol; + unsigned int ip_off; + unsigned int tcp_off; unsigned header_len; unsigned int ip_base_len; }; @@ -825,17 +825,14 @@ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue) /* Parse the SKB header and initialise state. */ static void tso_start(struct tso_state *st, const struct sk_buff *skb) { - /* All ethernet/IP/TCP headers combined size is TCP header size - * plus offset of TCP header relative to start of packet. - */ - st->header_len = ((tcp_hdr(skb)->doff << 2u) - + PTR_DIFF(tcp_hdr(skb), skb->data)); - + st->ip_off = skb_network_header(skb) - skb->data; + st->tcp_off = skb_transport_header(skb) - skb->data; + st->header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u); if (st->protocol == htons(ETH_P_IP)) { - st->ip_base_len = st->header_len - ETH_HDR_LEN(skb); + st->ip_base_len = st->header_len - st->ip_off; st->ipv4_id = ntohs(ip_hdr(skb)->id); } else { - st->ip_base_len = tcp_hdr(skb)->doff << 2u; + st->ip_base_len = st->header_len - st->tcp_off; st->ipv4_id = 0; } st->seqnum = ntohl(tcp_hdr(skb)->seq); @@ -959,7 +956,7 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, if (!header) return -ENOMEM; - tsoh_th = (struct tcphdr *)(header + SKB_TCP_OFF(skb)); + tsoh_th = (struct tcphdr *)(header + st->tcp_off); /* Copy and update the headers. */ memcpy(header, skb->data, st->header_len); @@ -980,8 +977,7 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, ip_length = st->ip_base_len + st->packet_space; if (st->protocol == htons(ETH_P_IP)) { - struct iphdr *tsoh_iph = - (struct iphdr *)(header + SKB_IPV4_OFF(skb)); + struct iphdr *tsoh_iph = (struct iphdr *)(header + st->ip_off); tsoh_iph->tot_len = htons(ip_length); @@ -990,7 +986,7 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, st->ipv4_id++; } else { struct ipv6hdr *tsoh_iph = - (struct ipv6hdr *)(header + SKB_IPV6_OFF(skb)); + (struct ipv6hdr *)(header + st->ip_off); tsoh_iph->payload_len = htons(ip_length); } -- cgit v1.2.3 From f16aeea0e679d5fd43fc02e99569c52d77d5e5d3 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 27 Jul 2012 19:31:16 +0100 Subject: sfc: Change state names to be clearer, and comment them STATE_INIT and STATE_FINI are equivalent and represent incompletely initialised states; combine them as STATE_UNINIT. Rename STATE_RUNNING to STATE_READY, to avoid confusion with netif_running() and IFF_RUNNING. The comments do not quite match current usage, but this will be corrected in subsequent fixes. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 24 +++++++++++------------- drivers/net/ethernet/sfc/ethtool.c | 2 +- drivers/net/ethernet/sfc/falcon_boards.c | 2 +- drivers/net/ethernet/sfc/net_driver.h | 10 ++++------ 4 files changed, 17 insertions(+), 21 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 3b3f08489a5e..9f88ad86f4e3 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -202,7 +202,7 @@ static void efx_stop_all(struct efx_nic *efx); #define EFX_ASSERT_RESET_SERIALISED(efx) \ do { \ - if ((efx->state == STATE_RUNNING) || \ + if ((efx->state == STATE_READY) || \ (efx->state == STATE_DISABLED)) \ ASSERT_RTNL(); \ } while (0) @@ -1556,7 +1556,7 @@ static void efx_start_all(struct efx_nic *efx) * of these flags are safe to read under just the rtnl lock */ if (efx->port_enabled) return; - if ((efx->state != STATE_RUNNING) && (efx->state != STATE_INIT)) + if ((efx->state != STATE_READY) && (efx->state != STATE_UNINIT)) return; if (!netif_running(efx->net_dev)) return; @@ -2286,11 +2286,11 @@ static void efx_reset_work(struct work_struct *data) if (!pending) return; - /* If we're not RUNNING then don't reset. Leave the reset_pending + /* If we're not READY then don't reset. Leave the reset_pending * flags set so that efx_pci_probe_main will be retried */ - if (efx->state != STATE_RUNNING) { + if (efx->state != STATE_READY) { netif_info(efx, drv, efx->net_dev, - "scheduled reset quenched. NIC not RUNNING\n"); + "scheduled reset quenched; NIC not ready\n"); return; } @@ -2402,7 +2402,7 @@ static int efx_init_struct(struct efx_nic *efx, const struct efx_nic_type *type, INIT_DELAYED_WORK(&efx->selftest_work, efx_selftest_async_work); efx->pci_dev = pci_dev; efx->msg_enable = debug; - efx->state = STATE_INIT; + efx->state = STATE_UNINIT; strlcpy(efx->name, pci_name(pci_dev), sizeof(efx->name)); efx->net_dev = net_dev; @@ -2490,7 +2490,7 @@ static void efx_pci_remove(struct pci_dev *pci_dev) /* Mark the NIC as fini, then stop the interface */ rtnl_lock(); - efx->state = STATE_FINI; + efx->state = STATE_UNINIT; dev_close(efx->net_dev); /* Allow any queued efx_resets() to complete */ @@ -2684,9 +2684,9 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, goto fail4; } - /* Switch to the running state before we expose the device to the OS, + /* Switch to the READY state before we expose the device to the OS, * so that dev_open()|efx_start_all() will actually start the device */ - efx->state = STATE_RUNNING; + efx->state = STATE_READY; rc = efx_register_netdev(efx); if (rc) @@ -2727,7 +2727,7 @@ static int efx_pm_freeze(struct device *dev) { struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); - efx->state = STATE_FINI; + efx->state = STATE_UNINIT; netif_device_detach(efx->net_dev); @@ -2741,8 +2741,6 @@ static int efx_pm_thaw(struct device *dev) { struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); - efx->state = STATE_INIT; - efx_start_interrupts(efx, false); mutex_lock(&efx->mac_lock); @@ -2753,7 +2751,7 @@ static int efx_pm_thaw(struct device *dev) netif_device_attach(efx->net_dev); - efx->state = STATE_RUNNING; + efx->state = STATE_READY; efx->type->resume_wol(efx); diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 8cba2df82b18..5d0e2a3241b1 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -531,7 +531,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev, ASSERT_RTNL(); - if (efx->state != STATE_RUNNING) { + if (efx->state != STATE_READY) { rc = -EIO; goto fail1; } diff --git a/drivers/net/ethernet/sfc/falcon_boards.c b/drivers/net/ethernet/sfc/falcon_boards.c index 8687a6c3db0d..ec1e99d0dcad 100644 --- a/drivers/net/ethernet/sfc/falcon_boards.c +++ b/drivers/net/ethernet/sfc/falcon_boards.c @@ -380,7 +380,7 @@ static ssize_t set_phy_flash_cfg(struct device *dev, new_mode = PHY_MODE_SPECIAL; if (!((old_mode ^ new_mode) & PHY_MODE_SPECIAL)) { err = 0; - } else if (efx->state != STATE_RUNNING || netif_running(efx->net_dev)) { + } else if (efx->state != STATE_READY || netif_running(efx->net_dev)) { err = -EBUSY; } else { /* Reset the PHY, reconfigure the MAC and enable/disable diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index a4fe9a786ef8..7ab1232494ef 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -430,11 +430,9 @@ enum efx_int_mode { #define EFX_INT_MODE_USE_MSI(x) (((x)->interrupt_mode) <= EFX_INT_MODE_MSI) enum nic_state { - STATE_INIT = 0, - STATE_RUNNING = 1, - STATE_FINI = 2, - STATE_DISABLED = 3, - STATE_MAX, + STATE_UNINIT = 0, /* device being probed/removed or is frozen */ + STATE_READY = 1, /* hardware ready and netdev registered */ + STATE_DISABLED = 2, /* device disabled due to hardware errors */ }; /* @@ -654,7 +652,7 @@ struct vfdi_status; * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues * @irq_rx_moderation: IRQ moderation time for RX event queues * @msg_enable: Log message enable flags - * @state: Device state flag. Serialised by the rtnl_lock. + * @state: Device state number (%STATE_*). Serialised by the rtnl_lock. * @reset_pending: Bitmask for pending resets * @tx_queue: TX DMA queues * @rx_queue: RX DMA queues -- cgit v1.2.3 From 61da026d86517def727eb67d7cb8ee5657a12dd9 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 27 Jul 2012 19:35:39 +0100 Subject: sfc: Hold the RTNL lock for more of the suspend/resume cycle I don't think these PM functions can race with userland net device operations, but it's much easier to reason about locking if state is consistently guarded by the same lock. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 9f88ad86f4e3..e5f3a17349af 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2727,6 +2727,8 @@ static int efx_pm_freeze(struct device *dev) { struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + rtnl_lock(); + efx->state = STATE_UNINIT; netif_device_detach(efx->net_dev); @@ -2734,6 +2736,8 @@ static int efx_pm_freeze(struct device *dev) efx_stop_all(efx); efx_stop_interrupts(efx, false); + rtnl_unlock(); + return 0; } @@ -2741,6 +2745,8 @@ static int efx_pm_thaw(struct device *dev) { struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + rtnl_lock(); + efx_start_interrupts(efx, false); mutex_lock(&efx->mac_lock); @@ -2755,6 +2761,8 @@ static int efx_pm_thaw(struct device *dev) efx->type->resume_wol(efx); + rtnl_unlock(); + /* Reschedule any quenched resets scheduled during efx_pm_freeze() */ queue_work(reset_workqueue, &efx->reset_work); -- cgit v1.2.3 From 6032fb56c546c0a14856dc57a92d84560816b217 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 27 Jul 2012 19:35:47 +0100 Subject: sfc: Keep disabled NICs quiescent during suspend/resume Currently we ignore and clear the disabled state. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index e5f3a17349af..f02591bb62f4 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2729,12 +2729,14 @@ static int efx_pm_freeze(struct device *dev) rtnl_lock(); - efx->state = STATE_UNINIT; + if (efx->state != STATE_DISABLED) { + efx->state = STATE_UNINIT; - netif_device_detach(efx->net_dev); + netif_device_detach(efx->net_dev); - efx_stop_all(efx); - efx_stop_interrupts(efx, false); + efx_stop_all(efx); + efx_stop_interrupts(efx, false); + } rtnl_unlock(); @@ -2747,19 +2749,21 @@ static int efx_pm_thaw(struct device *dev) rtnl_lock(); - efx_start_interrupts(efx, false); + if (efx->state != STATE_DISABLED) { + efx_start_interrupts(efx, false); - mutex_lock(&efx->mac_lock); - efx->phy_op->reconfigure(efx); - mutex_unlock(&efx->mac_lock); + mutex_lock(&efx->mac_lock); + efx->phy_op->reconfigure(efx); + mutex_unlock(&efx->mac_lock); - efx_start_all(efx); + efx_start_all(efx); - netif_device_attach(efx->net_dev); + netif_device_attach(efx->net_dev); - efx->state = STATE_READY; + efx->state = STATE_READY; - efx->type->resume_wol(efx); + efx->type->resume_wol(efx); + } rtnl_unlock(); -- cgit v1.2.3 From 5642ceef466365ebc94eb1332d9e6228efa09518 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 27 Jul 2012 19:35:52 +0100 Subject: sfc: Hold RTNL lock (only) when calling efx_stop_interrupts() Interrupt state should be consistently guarded by the RTNL lock once the net device is registered. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index f02591bb62f4..629029e2037d 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2164,9 +2164,9 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method) EFX_ASSERT_RESET_SERIALISED(efx); efx_stop_all(efx); - mutex_lock(&efx->mac_lock); - efx_stop_interrupts(efx, false); + + mutex_lock(&efx->mac_lock); if (efx->port_initialized && method != RESET_TYPE_INVISIBLE) efx->phy_op->fini(efx); efx->type->fini(efx); @@ -2492,11 +2492,11 @@ static void efx_pci_remove(struct pci_dev *pci_dev) rtnl_lock(); efx->state = STATE_UNINIT; dev_close(efx->net_dev); + efx_stop_interrupts(efx, false); /* Allow any queued efx_resets() to complete */ rtnl_unlock(); - efx_stop_interrupts(efx, false); efx_sriov_fini(efx); efx_unregister_netdev(efx); -- cgit v1.2.3 From 8b7325b4e29256881117aff8a162e829c79b47e9 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 27 Jul 2012 20:46:41 +0100 Subject: sfc: Never try to stop and start a NIC that is disabled efx_change_mtu() and efx_realloc_channels() each stop and start much of the NIC, even if it has been disabled. Since efx_start_all() is a no-op when the NIC is disabled, this is probably harmless in the case of efx_change_mtu(), but efx_realloc_channels() also reenables interrupts which could be a bad thing to do. Change efx_start_all() and efx_start_interrupts() to assert that the NIC is not disabled, but make efx_stop_interrupts() do nothing if the NIC is disabled (since it is already stopped), consistent with efx_stop_all(). Update comments for efx_start_all() and efx_stop_all() to describe their purpose and preconditions more accurately. Add a common function to check and log if the NIC is disabled, and use it in efx_net_open(), efx_change_mtu() and efx_realloc_channels(). Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 65 ++++++++++++++++++++++++++++-------------- 1 file changed, 44 insertions(+), 21 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 629029e2037d..977fc3a591e9 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -207,6 +207,16 @@ static void efx_stop_all(struct efx_nic *efx); ASSERT_RTNL(); \ } while (0) +static int efx_check_disabled(struct efx_nic *efx) +{ + if (efx->state == STATE_DISABLED) { + netif_err(efx, drv, efx->net_dev, + "device is disabled due to earlier errors\n"); + return -EIO; + } + return 0; +} + /************************************************************************** * * Event queue processing @@ -740,7 +750,11 @@ efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel; u32 old_rxq_entries, old_txq_entries; unsigned i, next_buffer_table = 0; - int rc = 0; + int rc; + + rc = efx_check_disabled(efx); + if (rc) + return rc; /* Not all channels should be reallocated. We must avoid * reallocating their buffer table entries. @@ -1375,6 +1389,8 @@ static void efx_start_interrupts(struct efx_nic *efx, bool may_keep_eventq) { struct efx_channel *channel; + BUG_ON(efx->state == STATE_DISABLED); + if (efx->legacy_irq) efx->legacy_irq_enabled = true; efx_nic_enable_interrupts(efx); @@ -1392,6 +1408,9 @@ static void efx_stop_interrupts(struct efx_nic *efx, bool may_keep_eventq) { struct efx_channel *channel; + if (efx->state == STATE_DISABLED) + return; + efx_mcdi_mode_poll(efx); efx_nic_disable_interrupts(efx); @@ -1543,22 +1562,21 @@ static int efx_probe_all(struct efx_nic *efx) return rc; } -/* Called after previous invocation(s) of efx_stop_all, restarts the port, - * kernel transmit queues and NAPI processing, and ensures that the port is - * scheduled to be reconfigured. This function is safe to call multiple - * times when the NIC is in any state. +/* If the interface is supposed to be running but is not, start + * the hardware and software data path, regular activity for the port + * (MAC statistics, link polling, etc.) and schedule the port to be + * reconfigured. Interrupts must already be enabled. This function + * is safe to call multiple times, so long as the NIC is not disabled. + * Requires the RTNL lock. */ static void efx_start_all(struct efx_nic *efx) { EFX_ASSERT_RESET_SERIALISED(efx); + BUG_ON(efx->state == STATE_DISABLED); /* Check that it is appropriate to restart the interface. All * of these flags are safe to read under just the rtnl lock */ - if (efx->port_enabled) - return; - if ((efx->state != STATE_READY) && (efx->state != STATE_UNINIT)) - return; - if (!netif_running(efx->net_dev)) + if (efx->port_enabled || !netif_running(efx->net_dev)) return; efx_start_port(efx); @@ -1592,11 +1610,11 @@ static void efx_flush_all(struct efx_nic *efx) cancel_work_sync(&efx->mac_work); } -/* Quiesce hardware and software without bringing the link down. - * Safe to call multiple times, when the nic and interface is in any - * state. The caller is guaranteed to subsequently be in a position - * to modify any hardware and software state they see fit without - * taking locks. */ +/* Quiesce the hardware and software data path, and regular activity + * for the port without bringing the link down. Safe to call multiple + * times with the NIC in almost any state, but interrupts should be + * enabled. Requires the RTNL lock. + */ static void efx_stop_all(struct efx_nic *efx) { EFX_ASSERT_RESET_SERIALISED(efx); @@ -1830,13 +1848,16 @@ static void efx_netpoll(struct net_device *net_dev) static int efx_net_open(struct net_device *net_dev) { struct efx_nic *efx = netdev_priv(net_dev); + int rc; + EFX_ASSERT_RESET_SERIALISED(efx); netif_dbg(efx, ifup, efx->net_dev, "opening device on CPU %d\n", raw_smp_processor_id()); - if (efx->state == STATE_DISABLED) - return -EIO; + rc = efx_check_disabled(efx); + if (rc) + return rc; if (efx->phy_mode & PHY_MODE_SPECIAL) return -EBUSY; if (efx_mcdi_poll_reboot(efx) && efx_reset(efx, RESET_TYPE_ALL)) @@ -1862,10 +1883,8 @@ static int efx_net_stop(struct net_device *net_dev) netif_dbg(efx, ifdown, efx->net_dev, "closing on CPU %d\n", raw_smp_processor_id()); - if (efx->state != STATE_DISABLED) { - /* Stop the device and flush all the channels */ - efx_stop_all(efx); - } + /* Stop the device and flush all the channels */ + efx_stop_all(efx); return 0; } @@ -1925,9 +1944,13 @@ static void efx_watchdog(struct net_device *net_dev) static int efx_change_mtu(struct net_device *net_dev, int new_mtu) { struct efx_nic *efx = netdev_priv(net_dev); + int rc; EFX_ASSERT_RESET_SERIALISED(efx); + rc = efx_check_disabled(efx); + if (rc) + return rc; if (new_mtu > EFX_MAX_MTU) return -EINVAL; -- cgit v1.2.3 From b812f8b7a9b657367eaacab8c34e6711a657a48b Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 27 Jul 2012 20:48:36 +0100 Subject: sfc: Improve log messages in case we abort probe due to a pending reset The current informational message doesn't properly explain what happens, and could also appear if we defer a reset during suspend/resume. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 977fc3a591e9..5555e9f98162 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2311,11 +2311,8 @@ static void efx_reset_work(struct work_struct *data) /* If we're not READY then don't reset. Leave the reset_pending * flags set so that efx_pci_probe_main will be retried */ - if (efx->state != STATE_READY) { - netif_info(efx, drv, efx->net_dev, - "scheduled reset quenched; NIC not ready\n"); + if (efx->state != STATE_READY) return; - } rtnl_lock(); (void)efx_reset(efx, fls(pending) - 1); @@ -2703,6 +2700,8 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, * probably hosed anyway. */ if (efx->reset_pending) { + netif_err(efx, probe, efx->net_dev, + "aborting probe due to scheduled reset\n"); rc = -EIO; goto fail4; } -- cgit v1.2.3 From 7153f623ea47f3feb54209d75b80ed09a497cd4a Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 27 Jul 2012 20:50:52 +0100 Subject: sfc: Fix reset vs probe/remove/PM races involving efx_nic::state We try to defer resets while the device is not READY, but we're not doing this quite correctly. In particular, changes to efx_nic::state are documented as serialised by the RTNL lock, but they aren't. 1. We check whether a reset was requested during probe (suggesting broken hardware) before we allow requested resets to be scheduled. This leaves a window where a requested reset would be deferred indefinitely. 2. Although we cancel the reset work item during device removal, there are still later operations that can cause it to be scheduled again. We need to check the state before scheduling it. 3. Since the state can change between scheduling and running of the work item, we still need to check it there, and we need to do so *after* acquiring the RTNL lock which serialises state changes. 4. We must cancel the reset work item during device removal, if the state could ever have been READY. This wasn't done in some of the failure paths from efx_pci_probe(). Move the cancellation to efx_pci_remove_main(). Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 84 +++++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 41 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 5555e9f98162..d0653406058b 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2112,6 +2112,19 @@ static int efx_register_netdev(struct efx_nic *efx) rtnl_lock(); + /* Enable resets to be scheduled and check whether any were + * already requested. If so, the NIC is probably hosed so we + * abort. + */ + efx->state = STATE_READY; + smp_mb(); /* ensure we change state before checking reset_pending */ + if (efx->reset_pending) { + netif_err(efx, probe, efx->net_dev, + "aborting probe due to scheduled reset\n"); + rc = -EIO; + goto fail_locked; + } + rc = dev_alloc_name(net_dev, net_dev->name); if (rc < 0) goto fail_locked; @@ -2141,14 +2154,14 @@ static int efx_register_netdev(struct efx_nic *efx) return 0; +fail_registered: + rtnl_lock(); + unregister_netdevice(net_dev); fail_locked: + efx->state = STATE_UNINIT; rtnl_unlock(); netif_err(efx, drv, efx->net_dev, "could not register net dev\n"); return rc; - -fail_registered: - unregister_netdev(net_dev); - return rc; } static void efx_unregister_netdev(struct efx_nic *efx) @@ -2171,7 +2184,11 @@ static void efx_unregister_netdev(struct efx_nic *efx) strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name)); device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type); - unregister_netdev(efx->net_dev); + + rtnl_lock(); + unregister_netdevice(efx->net_dev); + efx->state = STATE_UNINIT; + rtnl_unlock(); } /************************************************************************** @@ -2309,13 +2326,15 @@ static void efx_reset_work(struct work_struct *data) if (!pending) return; - /* If we're not READY then don't reset. Leave the reset_pending - * flags set so that efx_pci_probe_main will be retried */ - if (efx->state != STATE_READY) - return; - rtnl_lock(); - (void)efx_reset(efx, fls(pending) - 1); + + /* We checked the state in efx_schedule_reset() but it may + * have changed by now. Now that we have the RTNL lock, + * it cannot change again. + */ + if (efx->state == STATE_READY) + (void)efx_reset(efx, fls(pending) - 1); + rtnl_unlock(); } @@ -2341,6 +2360,13 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) } set_bit(method, &efx->reset_pending); + smp_mb(); /* ensure we change reset_pending before checking state */ + + /* If we're not READY then just leave the flags set as the cue + * to abort probing or reschedule the reset later. + */ + if (ACCESS_ONCE(efx->state) != STATE_READY) + return; /* efx_process_channel() will no longer read events once a * reset is scheduled. So switch back to poll'd MCDI completions. */ @@ -2485,6 +2511,12 @@ static void efx_fini_struct(struct efx_nic *efx) */ static void efx_pci_remove_main(struct efx_nic *efx) { + /* Flush reset_work. It can no longer be scheduled since we + * are not READY. + */ + BUG_ON(efx->state == STATE_READY); + cancel_work_sync(&efx->reset_work); + #ifdef CONFIG_RFS_ACCEL free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap); efx->net_dev->rx_cpu_rmap = NULL; @@ -2510,11 +2542,8 @@ static void efx_pci_remove(struct pci_dev *pci_dev) /* Mark the NIC as fini, then stop the interface */ rtnl_lock(); - efx->state = STATE_UNINIT; dev_close(efx->net_dev); efx_stop_interrupts(efx, false); - - /* Allow any queued efx_resets() to complete */ rtnl_unlock(); efx_sriov_fini(efx); @@ -2522,12 +2551,6 @@ static void efx_pci_remove(struct pci_dev *pci_dev) efx_mtd_remove(efx); - /* Wait for any scheduled resets to complete. No more will be - * scheduled from this point because efx_stop_all() has been - * called, we are no longer registered with driverlink, and - * the net_device's have been removed. */ - cancel_work_sync(&efx->reset_work); - efx_pci_remove_main(efx); efx_fini_io(efx); @@ -2686,30 +2709,9 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, goto fail2; rc = efx_pci_probe_main(efx); - - /* Serialise against efx_reset(). No more resets will be - * scheduled since efx_stop_all() has been called, and we have - * not and never have been registered. - */ - cancel_work_sync(&efx->reset_work); - if (rc) goto fail3; - /* If there was a scheduled reset during probe, the NIC is - * probably hosed anyway. - */ - if (efx->reset_pending) { - netif_err(efx, probe, efx->net_dev, - "aborting probe due to scheduled reset\n"); - rc = -EIO; - goto fail4; - } - - /* Switch to the READY state before we expose the device to the OS, - * so that dev_open()|efx_start_all() will actually start the device */ - efx->state = STATE_READY; - rc = efx_register_netdev(efx); if (rc) goto fail4; -- cgit v1.2.3 From 7bde852afc88909d78e617b70d3e7a3dc6bc04ff Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 27 Jul 2012 20:50:54 +0100 Subject: sfc: Remove overly paranoid locking assertions from netdev operations Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 8 -------- drivers/net/ethernet/sfc/ethtool.c | 2 -- 2 files changed, 10 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index d0653406058b..b29db12756f9 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1767,8 +1767,6 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd) struct efx_nic *efx = netdev_priv(net_dev); struct mii_ioctl_data *data = if_mii(ifr); - EFX_ASSERT_RESET_SERIALISED(efx); - /* Convert phy_id from older PRTAD/DEVAD format */ if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) && (data->phy_id & 0xfc00) == 0x0400) @@ -1850,8 +1848,6 @@ static int efx_net_open(struct net_device *net_dev) struct efx_nic *efx = netdev_priv(net_dev); int rc; - EFX_ASSERT_RESET_SERIALISED(efx); - netif_dbg(efx, ifup, efx->net_dev, "opening device on CPU %d\n", raw_smp_processor_id()); @@ -1946,8 +1942,6 @@ static int efx_change_mtu(struct net_device *net_dev, int new_mtu) struct efx_nic *efx = netdev_priv(net_dev); int rc; - EFX_ASSERT_RESET_SERIALISED(efx); - rc = efx_check_disabled(efx); if (rc) return rc; @@ -1975,8 +1969,6 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data) struct sockaddr *addr = data; char *new_addr = addr->sa_data; - EFX_ASSERT_RESET_SERIALISED(efx); - if (!is_valid_ether_addr(new_addr)) { netif_err(efx, drv, efx->net_dev, "invalid ethernet MAC address requested: %pM\n", diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 5d0e2a3241b1..2bd5c2d35e5d 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -529,8 +529,6 @@ static void efx_ethtool_self_test(struct net_device *net_dev, if (!efx_tests) goto fail; - - ASSERT_RTNL(); if (efx->state != STATE_READY) { rc = -EIO; goto fail1; -- cgit v1.2.3 From 3f65ea5b2aa0f76a463c85ed39955c26faf4f5a7 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 27 Jul 2012 20:50:57 +0100 Subject: sfc: Remove bogus comment about MTU change and RX buffer overrun RX DMA is limited by the length specified in each descriptor and not by the MAC. Over-length frames may get into the RX FIFO regardless of the MAC settings, due to a hardware bug, but they will be truncated by the packet DMA engine and reported as such in the completion event. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index b29db12756f9..4105a6664765 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1953,8 +1953,6 @@ static int efx_change_mtu(struct net_device *net_dev, int new_mtu) netif_dbg(efx, drv, efx->net_dev, "changing MTU to %d\n", new_mtu); mutex_lock(&efx->mac_lock); - /* Reconfigure the MAC before enabling the dma queues so that - * the RX buffers don't overflow */ net_dev->mtu = new_mtu; efx->type->reconfigure_mac(efx); mutex_unlock(&efx->mac_lock); -- cgit v1.2.3 From adeb15aa1ce3413d461ec0958a979e9d64cd764c Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 2 Aug 2012 01:39:38 +0100 Subject: sfc: Assign efx and efx->type as early as possible in efx_pci_probe() We also stop clearing *efx in efx_init_struct(). This is safe because alloc_etherdev_mq() already clears it for us. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 4105a6664765..92f002029481 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2422,13 +2422,12 @@ static const struct efx_phy_operations efx_dummy_phy_operations = { /* This zeroes out and then fills in the invariants in a struct * efx_nic (including all sub-structures). */ -static int efx_init_struct(struct efx_nic *efx, const struct efx_nic_type *type, +static int efx_init_struct(struct efx_nic *efx, struct pci_dev *pci_dev, struct net_device *net_dev) { int i; /* Initialise common structures */ - memset(efx, 0, sizeof(*efx)); spin_lock_init(&efx->biu_lock); #ifdef CONFIG_SFC_MTD INIT_LIST_HEAD(&efx->mtd_list); @@ -2455,8 +2454,6 @@ static int efx_init_struct(struct efx_nic *efx, const struct efx_nic_type *type, goto fail; } - efx->type = type; - EFX_BUG_ON_PARANOID(efx->type->phys_addr_channels > EFX_MAX_CHANNELS); /* Higher numbered interrupt modes are less capable! */ @@ -2660,7 +2657,6 @@ static int efx_pci_probe_main(struct efx_nic *efx) static int __devinit efx_pci_probe(struct pci_dev *pci_dev, const struct pci_device_id *entry) { - const struct efx_nic_type *type = (const struct efx_nic_type *) entry->driver_data; struct net_device *net_dev; struct efx_nic *efx; int rc; @@ -2670,10 +2666,12 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, EFX_MAX_RX_QUEUES); if (!net_dev) return -ENOMEM; - net_dev->features |= (type->offload_features | NETIF_F_SG | + efx = netdev_priv(net_dev); + efx->type = (const struct efx_nic_type *) entry->driver_data; + net_dev->features |= (efx->type->offload_features | NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_TSO | NETIF_F_RXCSUM); - if (type->offload_features & NETIF_F_V6_CSUM) + if (efx->type->offload_features & NETIF_F_V6_CSUM) net_dev->features |= NETIF_F_TSO6; /* Mask for features that also apply to VLAN devices */ net_dev->vlan_features |= (NETIF_F_ALL_CSUM | NETIF_F_SG | @@ -2681,10 +2679,9 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, NETIF_F_RXCSUM); /* All offloads can be toggled */ net_dev->hw_features = net_dev->features & ~NETIF_F_HIGHDMA; - efx = netdev_priv(net_dev); pci_set_drvdata(pci_dev, efx); SET_NETDEV_DEV(net_dev, &pci_dev->dev); - rc = efx_init_struct(efx, type, pci_dev, net_dev); + rc = efx_init_struct(efx, pci_dev, net_dev); if (rc) goto fail1; -- cgit v1.2.3 From 8f8b3d518999fd1c342310910aa1e49112c86d05 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 24 Aug 2012 18:04:38 +0100 Subject: sfc: Fix the initial device operstate Following commit 8f4cccb ('net: Set device operstate at registration time') it is now correct and preferable to set the carrier off before registering a device. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 92f002029481..a606db43c5ba 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2120,6 +2120,9 @@ static int efx_register_netdev(struct efx_nic *efx) goto fail_locked; efx_update_name(efx); + /* Always start with carrier off; PHY events will detect the link */ + netif_carrier_off(net_dev); + rc = register_netdevice(net_dev); if (rc) goto fail_locked; @@ -2130,9 +2133,6 @@ static int efx_register_netdev(struct efx_nic *efx) efx_init_tx_queue_core_txq(tx_queue); } - /* Always start with carrier off; PHY events will detect the link */ - netif_carrier_off(net_dev); - rtnl_unlock(); rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_type); -- cgit v1.2.3 From ba9aa134287f6a59886ea91e0dadaa8477dec9c2 Mon Sep 17 00:00:00 2001 From: david decotigny Date: Fri, 24 Aug 2012 17:22:51 +0000 Subject: forcedeth: fix buffer overflow Found by manual code inspection. Tested: compile, reboot, ethtool -d ethX Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- drivers/net/ethernet/nvidia/forcedeth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index f45def01a98e..51d19d8cb47c 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -4435,7 +4435,7 @@ static void nv_get_regs(struct net_device *dev, struct ethtool_regs *regs, void regs->version = FORCEDETH_REGS_VER; spin_lock_irq(&np->lock); - for (i = 0; i <= np->register_size/sizeof(u32); i++) + for (i = 0; i < np->register_size/sizeof(u32); i++) rbuf[i] = readl(base + i*sizeof(u32)); spin_unlock_irq(&np->lock); } -- cgit v1.2.3 From 1ff39eb66b6ba456995fa19185463d7753cd8798 Mon Sep 17 00:00:00 2001 From: david decotigny Date: Fri, 24 Aug 2012 17:22:52 +0000 Subject: forcedeth: fix TX timeout caused by TX pause on down link On some dual-port forcedeth devices such as MCP55 10de:0373 (rev a3), when autoneg & TX pause are enabled while port is connected but interface is down, the NIC will eventually freeze (TX timeouts, network unreachable). This patch ensures that TX pause is not configured in hardware when interface is down. The TX pause request will be honored when interface is later configured. Tested: - hardware is MCP55 device id 10de:0373 (rev a3), dual-port - eth0 connected and UP, eth1 connected but DOWN - without this patch, following sequence would brick NIC: ifconfig eth0 down ifconfig eth1 up ifconfig eth1 down ethtool -A eth1 autoneg off rx on tx off ifconfig eth1 up ifconfig eth1 down ethtool -A eth1 autoneg on rx on tx on ifconfig eth1 up ifconfig eth1 down ifup eth0 sleep 120 # or longer ethtool eth1 Just in case, sequence to un-brick: ifconfig eth0 down ethtool -A eth1 autoneg off rx on tx off ifconfig eth1 up ifconfig eth1 down ifup eth0 - with this patch: no TX timeout after "bricking" sequence above Details: - The following register accesses have been identified as the ones causing the NIC to freeze in "bricking" sequence above: - write NVREG_TX_PAUSEFRAME_ENABLE_V1 to eth1's register NvRegTxPauseFrame - write NVREG_MISC1_PAUSE_TX | NVREG_MISC1_FORCE to eth1's register NvRegMisc1 - write 0 to eth1's register NvRegTransmitterControl This is what this patch avoids. Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- drivers/net/ethernet/nvidia/forcedeth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 51d19d8cb47c..8b82457c1682 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -3409,7 +3409,7 @@ set_speed: pause_flags = 0; /* setup pause frame */ - if (np->duplex != 0) { + if (netif_running(dev) && (np->duplex != 0)) { if (np->autoneg && np->pause_flags & NV_PAUSEFRAME_AUTONEG) { adv_pause = adv & (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM); lpa_pause = lpa & (LPA_PAUSE_CAP | LPA_PAUSE_ASYM); @@ -5455,6 +5455,7 @@ static int nv_close(struct net_device *dev) netif_stop_queue(dev); spin_lock_irq(&np->lock); + nv_update_pause(dev, 0); /* otherwise stop_tx bricks NIC */ nv_stop_rxtx(dev); nv_txrx_reset(dev); -- cgit v1.2.3 From 3f0a1b58ae1fb72dee348564d03f42cca2338ab8 Mon Sep 17 00:00:00 2001 From: david decotigny Date: Fri, 24 Aug 2012 17:22:53 +0000 Subject: forcedeth: prevent TX timeouts after reboot This complements patch "net-forcedeth: fix TX timeout caused by TX pause on down link" which ensures that a lock-up sequence is not sent to the NIC. Present patch ensures that if a NIC is already locked-up, the driver will recover from it when initializing the device. It does the equivalent of the following recovery sequence: - write NVREG_TX_PAUSEFRAME_ENABLE_V1 to eth1's register NvRegTxPauseFrame - write NVREG_XMITCTL_START to eth1's register NvRegTransmitterControl - write 0 to eth1's register NvRegTransmitterControl (this is at the heart of the "unbricking" sequence mentioned in patch "net-forcedeth: fix TX timeout caused by TX pause on down link") Tested: - hardware is MCP55 device id 10de:0373 (rev a3), dual-port - reboot a kernel without any of patches mentioned - freeze the NIC (details on description for commit "net-forcedeth: fix TX timeout caused by TX pause on down link") - wait 5mn until ping hangs & TX timeout in dmesg - reboot on kernel with present patch - host is immediatly operational, no TX timeout Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- drivers/net/ethernet/nvidia/forcedeth.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 8b82457c1682..876beceaf2d7 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -5905,11 +5905,19 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i goto out_error; } + netif_carrier_off(dev); + + /* Some NICs freeze when TX pause is enabled while NIC is + * down, and this stays across warm reboots. The sequence + * below should be enough to recover from that state. + */ + nv_update_pause(dev, 0); + nv_start_tx(dev); + nv_stop_tx(dev); + if (id->driver_data & DEV_HAS_VLAN) nv_vlan_mode(dev, dev->features); - netif_carrier_off(dev); - dev_info(&pci_dev->dev, "ifname %s, PHY OUI 0x%x @ %d, addr %pM\n", dev->name, np->phy_oui, np->phyaddr, dev->dev_addr); -- cgit v1.2.3 From e8c75e2c1c6965d071d50620278df78f65cfe082 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 25 Aug 2012 22:18:35 +0000 Subject: drivers/net/ethernet/tundra/tsi108_eth.c: delete double assignment Delete successive assignments to the same location. A simplified version of the semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) // @@ expression i; @@ *i = ...; i = ...; // Signed-off-by: Julia Lawall Signed-off-by: David S. Miller --- drivers/net/ethernet/tundra/tsi108_eth.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index 277c93e9ff4d..8fa947a2d929 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -1358,7 +1358,6 @@ static int tsi108_open(struct net_device *dev) break; } - data->rxskbs[i] = skb; data->rxskbs[i] = skb; data->rxring[i].buf0 = virt_to_phys(data->rxskbs[i]->data); data->rxring[i].misc = TSI108_RX_OWN | TSI108_RX_INT; -- cgit v1.2.3 From 4cbdaf6d520b6bd9a1565525e5ad1967cb74e191 Mon Sep 17 00:00:00 2001 From: Sathya Perla Date: Tue, 28 Aug 2012 20:37:40 +0000 Subject: be2net: create RSS rings even in multi-channel configs Changes from commit df505e were incorrectly over-written by commit 10ef9ab. Fixing the same. Change log of the original fix: Currently RSS rings are not created in a multi-channel config. RSS rings can be created on one (out of four) interfaces per port in a multi-channel config. Doing this insulates the driver from a FW bug wherin multi-channel config is wrongly reported even when not enabled. This also helps performance in a multi-channel config, as one interface per port gets RSS rings. Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 90a903d83d87..d86d25cc33cf 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2176,8 +2176,7 @@ static uint be_num_rss_want(struct be_adapter *adapter) { u32 num = 0; if ((adapter->function_caps & BE_FUNCTION_CAPS_RSS) && - !sriov_want(adapter) && be_physfn(adapter) && - !be_is_mc(adapter)) { + !sriov_want(adapter) && be_physfn(adapter)) { num = (adapter->be3_native) ? BE3_MAX_RSS_QS : BE2_MAX_RSS_QS; num = min_t(u32, num, (u32)netif_get_num_default_rss_queues()); } -- cgit v1.2.3 From 7c5a524221dc3cf599a6aa4773eb0c1e2ca38adb Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Tue, 28 Aug 2012 20:37:41 +0000 Subject: be2net: fix max VFs reported by HW BE3 FW allocates VF resources for upto 30 VFs per PF while a max value of 32 may be reported via PCI config space. Fix this in the driver. Signed-off-by: Vasundhara Volam Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be.h | 1 + drivers/net/ethernet/emulex/benet/be_main.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index d266c86a53f7..5b622993ff17 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -110,6 +110,7 @@ static inline char *nic_name(struct pci_dev *pdev) #define MAX_RX_POST BE_NAPI_WEIGHT /* Frags posted at a time */ #define RX_FRAGS_REFILL_WM (RX_Q_LEN - MAX_RX_POST) +#define MAX_VFS 30 /* Max VFs supported by BE3 FW */ #define FW_VER_LEN 32 struct be_dma_mem { diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index d86d25cc33cf..def2f6688964 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2723,6 +2723,8 @@ static int be_get_config(struct be_adapter *adapter) if (pos) { pci_read_config_word(adapter->pdev, pos + PCI_SRIOV_TOTAL_VF, &dev_num_vfs); + if (!lancer_chip(adapter)) + dev_num_vfs = min_t(u16, dev_num_vfs, MAX_VFS); adapter->dev_num_vfs = dev_num_vfs; } return 0; -- cgit v1.2.3 From 8a046d3bfd5126b724a5352a757310229d4d3ff3 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Tue, 28 Aug 2012 20:37:42 +0000 Subject: be2net: fix FW default for VF tx-rate BE3 FW initializes VF tx-rate to 100Mbps. Fix this to 10Gbps. Signed-off-by: Vasundhara Volam Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index def2f6688964..1494f2fc5b95 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2645,8 +2645,8 @@ static int be_vf_setup(struct be_adapter *adapter) } for_all_vfs(adapter, vf_cfg, vf) { - status = be_cmd_link_status_query(adapter, NULL, &lnk_speed, - NULL, vf + 1); + lnk_speed = 1000; + status = be_cmd_set_qos(adapter, lnk_speed, vf + 1); if (status) goto err; vf_cfg->tx_rate = lnk_speed * 10; -- cgit v1.2.3 From cc7d723adb7778e4eff8956f2d137c0729b9a81e Mon Sep 17 00:00:00 2001 From: Sathya Perla Date: Tue, 28 Aug 2012 20:37:43 +0000 Subject: be2net: fixup malloc/free of adapter->pmac_id Free was missing and kcalloc() is better placed in be_ctrl_init() Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 1494f2fc5b95..6d139d6eb564 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3438,6 +3438,7 @@ static void be_ctrl_cleanup(struct be_adapter *adapter) if (mem->va) dma_free_coherent(&adapter->pdev->dev, mem->size, mem->va, mem->dma); + kfree(adapter->pmac_id); } static int be_ctrl_init(struct be_adapter *adapter) @@ -3474,6 +3475,12 @@ static int be_ctrl_init(struct be_adapter *adapter) } memset(rx_filter->va, 0, rx_filter->size); + /* primary mac needs 1 pmac entry */ + adapter->pmac_id = kcalloc(adapter->max_pmac_cnt + 1, + sizeof(*adapter->pmac_id), GFP_KERNEL); + if (!adapter->pmac_id) + return -ENOMEM; + mutex_init(&adapter->mbox_lock); spin_lock_init(&adapter->mcc_lock); spin_lock_init(&adapter->mcc_cq_lock); @@ -3610,12 +3617,6 @@ static int be_get_initial_config(struct be_adapter *adapter) else adapter->max_pmac_cnt = BE_VF_UC_PMAC_COUNT; - /* primary mac needs 1 pmac entry */ - adapter->pmac_id = kcalloc(adapter->max_pmac_cnt + 1, - sizeof(u32), GFP_KERNEL); - if (!adapter->pmac_id) - return -ENOMEM; - status = be_cmd_get_cntl_attributes(adapter); if (status) return status; -- cgit v1.2.3 From 522609f27ac3c4b031b58fee15c36689462a2919 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Tue, 28 Aug 2012 20:37:44 +0000 Subject: be2net: modify log msg for lack of privilege error Signed-off-by: Vasundhara Volam Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_cmds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 7fac97b4bb59..fc68ca070ea0 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -120,7 +120,7 @@ static int be_mcc_compl_process(struct be_adapter *adapter, if (compl_status == MCC_STATUS_UNAUTHORIZED_REQUEST) { dev_warn(&adapter->pdev->dev, - "opcode %d-%d is not permitted\n", + "VF is not privileged to issue opcode %d-%d\n", opcode, subsystem); } else { extd_status = (compl->status >> CQE_STATUS_EXTD_SHIFT) & -- cgit v1.2.3 From 19bcd6c618ac9356c076d711fab7046664b3860a Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 29 Aug 2012 08:07:57 +0000 Subject: net/freescale: do not export any functions from fsl_pq_mdio.c None of the functions in fsl_pq_mdio.c are used by any other source file, so there's no point in exporting them. Merge the header file into the source file, make all the functions static, remove any EXPORT_SYMBOL statements, and delete any #include "fsl_pq_mdio.h" statements. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fsl_pq_mdio.c | 38 ++++++++++++++++---- drivers/net/ethernet/freescale/fsl_pq_mdio.h | 52 ---------------------------- drivers/net/ethernet/freescale/gianfar.c | 1 - drivers/net/ethernet/freescale/ucc_geth.c | 1 - 4 files changed, 31 insertions(+), 61 deletions(-) delete mode 100644 drivers/net/ethernet/freescale/fsl_pq_mdio.h (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index 9527b28d70d1..bc19fe09a1d2 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -45,7 +45,31 @@ #include #include "gianfar.h" -#include "fsl_pq_mdio.h" + +#define MIIMIND_BUSY 0x00000001 +#define MIIMIND_NOTVALID 0x00000004 +#define MIIMCFG_INIT_VALUE 0x00000007 +#define MIIMCFG_RESET 0x80000000 + +#define MII_READ_COMMAND 0x00000001 + +struct fsl_pq_mdio { + u8 res1[16]; + u32 ieventm; /* MDIO Interrupt event register (for etsec2)*/ + u32 imaskm; /* MDIO Interrupt mask register (for etsec2)*/ + u8 res2[4]; + u32 emapm; /* MDIO Event mapping register (for etsec2)*/ + u8 res3[1280]; + u32 miimcfg; /* MII management configuration reg */ + u32 miimcom; /* MII management command reg */ + u32 miimadd; /* MII management address reg */ + u32 miimcon; /* MII management control reg */ + u32 miimstat; /* MII management status reg */ + u32 miimind; /* MII management indication reg */ + u8 res4[28]; + u32 utbipar; /* TBI phy address reg (only on UCC) */ + u8 res5[2728]; +} __packed; /* Number of microseconds to wait for an MII register to respond */ #define MII_TIMEOUT 1000 @@ -64,7 +88,7 @@ struct fsl_pq_mdio_priv { * the local mdio pins, which may not be the same as system mdio bus, used for * controlling the external PHYs, for example. */ -int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id, +static int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id, int regnum, u16 value) { u32 status; @@ -92,7 +116,7 @@ int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id, * and are always tied to the local mdio pins, which may not be the * same as system mdio bus, used for controlling the external PHYs, for eg. */ -int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs, +static int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs, int mii_id, int regnum) { u16 value; @@ -129,7 +153,8 @@ static struct fsl_pq_mdio __iomem *fsl_pq_mdio_get_regs(struct mii_bus *bus) * Write value to the PHY at mii_id at register regnum, * on the bus, waiting until the write is done before returning. */ -int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value) +static int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, + u16 value) { struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus); @@ -141,7 +166,7 @@ int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value) * Read the bus for PHY at addr mii_id, register regnum, and * return the value. Clears miimcom first. */ -int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum) +static int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum) { struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus); @@ -178,7 +203,7 @@ static int fsl_pq_mdio_reset(struct mii_bus *bus) return 0; } -void fsl_pq_mdio_bus_name(char *name, struct device_node *np) +static void fsl_pq_mdio_bus_name(char *name, struct device_node *np) { const u32 *addr; u64 taddr = OF_BAD_ADDR; @@ -190,7 +215,6 @@ void fsl_pq_mdio_bus_name(char *name, struct device_node *np) snprintf(name, MII_BUS_ID_SIZE, "%s@%llx", np->name, (unsigned long long)taddr); } -EXPORT_SYMBOL_GPL(fsl_pq_mdio_bus_name); static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs, struct device_node *np) diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.h b/drivers/net/ethernet/freescale/fsl_pq_mdio.h deleted file mode 100644 index bd17a2a0139b..000000000000 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Freescale PowerQUICC MDIO Driver -- MII Management Bus Implementation - * Driver for the MDIO bus controller on Freescale PowerQUICC processors - * - * Author: Andy Fleming - * Modifier: Sandeep Gopalpet - * - * Copyright 2002-2004, 2008-2009 Freescale Semiconductor, Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - */ -#ifndef __FSL_PQ_MDIO_H -#define __FSL_PQ_MDIO_H - -#define MIIMIND_BUSY 0x00000001 -#define MIIMIND_NOTVALID 0x00000004 -#define MIIMCFG_INIT_VALUE 0x00000007 -#define MIIMCFG_RESET 0x80000000 - -#define MII_READ_COMMAND 0x00000001 - -struct fsl_pq_mdio { - u8 res1[16]; - u32 ieventm; /* MDIO Interrupt event register (for etsec2)*/ - u32 imaskm; /* MDIO Interrupt mask register (for etsec2)*/ - u8 res2[4]; - u32 emapm; /* MDIO Event mapping register (for etsec2)*/ - u8 res3[1280]; - u32 miimcfg; /* MII management configuration reg */ - u32 miimcom; /* MII management command reg */ - u32 miimadd; /* MII management address reg */ - u32 miimcon; /* MII management control reg */ - u32 miimstat; /* MII management status reg */ - u32 miimind; /* MII management indication reg */ - u8 reserved[28]; /* Space holder */ - u32 utbipar; /* TBI phy address reg (only on UCC) */ - u8 res4[2728]; -} __packed; - -int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum); -int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value); -int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id, - int regnum, u16 value); -int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs, int mii_id, int regnum); -int __init fsl_pq_mdio_init(void); -void fsl_pq_mdio_exit(void); -void fsl_pq_mdio_bus_name(char *name, struct device_node *np); -#endif /* FSL_PQ_MDIO_H */ diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 4605f7246687..f762a7fbe51e 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -100,7 +100,6 @@ #include #include "gianfar.h" -#include "fsl_pq_mdio.h" #define TX_TIMEOUT (1*HZ) diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 21c6574c5f15..164288439220 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -42,7 +42,6 @@ #include #include "ucc_geth.h" -#include "fsl_pq_mdio.h" #undef DEBUG -- cgit v1.2.3 From 1aa06d42d98ef96e92857802c31f662fa971247b Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 29 Aug 2012 08:07:58 +0000 Subject: net/fsl_pq_mdio: trim #include statements Remove several unnecessary #include statements. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fsl_pq_mdio.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index bc19fe09a1d2..edaa25ea55a9 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -19,30 +19,18 @@ #include #include #include -#include #include -#include #include #include -#include -#include -#include -#include -#include #include #include -#include #include -#include -#include #include #include #include #include -#include -#include -#include +#include /* for ucc_set_qe_mux_mii_mng() */ #include "gianfar.h" -- cgit v1.2.3 From 69cfb41941638d3070c284f3e8849dc5b356fc3f Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 29 Aug 2012 08:07:59 +0000 Subject: net/fsl_pq_mdio: merge some functions together A few small functions were called only by other functions in the same file, so merge them together. One function, for example, was calculating the device address even though the caller was doing the same thing. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fsl_pq_mdio.c | 92 ++++++++-------------------- 1 file changed, 26 insertions(+), 66 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index edaa25ea55a9..d5b7590b7533 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -68,17 +68,19 @@ struct fsl_pq_mdio_priv { }; /* - * Write value to the PHY at mii_id at register regnum, - * on the bus attached to the local interface, which may be different from the - * generic mdio bus (tied to a single interface), waiting until the write is - * done before returning. This is helpful in programming interfaces like - * the TBI which control interfaces like onchip SERDES and are always tied to - * the local mdio pins, which may not be the same as system mdio bus, used for + * Write value to the PHY at mii_id at register regnum, on the bus attached + * to the local interface, which may be different from the generic mdio bus + * (tied to a single interface), waiting until the write is done before + * returning. This is helpful in programming interfaces like the TBI which + * control interfaces like onchip SERDES and are always tied to the local + * mdio pins, which may not be the same as system mdio bus, used for * controlling the external PHYs, for example. */ -static int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id, - int regnum, u16 value) +static int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, + u16 value) { + struct fsl_pq_mdio_priv *priv = bus->priv; + struct fsl_pq_mdio __iomem *regs = priv->regs; u32 status; /* Set the PHY address and the register address we want to write */ @@ -95,20 +97,21 @@ static int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id, } /* - * Read the bus for PHY at addr mii_id, register regnum, and - * return the value. Clears miimcom first. All PHY operation - * done on the bus attached to the local interface, - * which may be different from the generic mdio bus - * This is helpful in programming interfaces like - * the TBI which, in turn, control interfaces like onchip SERDES - * and are always tied to the local mdio pins, which may not be the + * Read the bus for PHY at addr mii_id, register regnum, and return the value. + * Clears miimcom first. + * + * All PHY operation done on the bus attached to the local interface, which + * may be different from the generic mdio bus. This is helpful in programming + * interfaces like the TBI which, in turn, control interfaces like on-chip + * SERDES and are always tied to the local mdio pins, which may not be the * same as system mdio bus, used for controlling the external PHYs, for eg. */ -static int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs, - int mii_id, int regnum) +static int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum) { - u16 value; + struct fsl_pq_mdio_priv *priv = bus->priv; + struct fsl_pq_mdio __iomem *regs = priv->regs; u32 status; + u16 value; /* Set the PHY address and the register address we want to read */ out_be32(®s->miimadd, (mii_id << 8) | regnum); @@ -130,42 +133,11 @@ static int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs, return value; } -static struct fsl_pq_mdio __iomem *fsl_pq_mdio_get_regs(struct mii_bus *bus) -{ - struct fsl_pq_mdio_priv *priv = bus->priv; - - return priv->regs; -} - -/* - * Write value to the PHY at mii_id at register regnum, - * on the bus, waiting until the write is done before returning. - */ -static int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, - u16 value) -{ - struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus); - - /* Write to the local MII regs */ - return fsl_pq_local_mdio_write(regs, mii_id, regnum, value); -} - -/* - * Read the bus for PHY at addr mii_id, register regnum, and - * return the value. Clears miimcom first. - */ -static int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum) -{ - struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus); - - /* Read the local MII regs */ - return fsl_pq_local_mdio_read(regs, mii_id, regnum); -} - /* Reset the MIIM registers, and wait for the bus to free */ static int fsl_pq_mdio_reset(struct mii_bus *bus) { - struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus); + struct fsl_pq_mdio_priv *priv = bus->priv; + struct fsl_pq_mdio __iomem *regs = priv->regs; u32 status; mutex_lock(&bus->mdio_lock); @@ -191,20 +163,6 @@ static int fsl_pq_mdio_reset(struct mii_bus *bus) return 0; } -static void fsl_pq_mdio_bus_name(char *name, struct device_node *np) -{ - const u32 *addr; - u64 taddr = OF_BAD_ADDR; - - addr = of_get_address(np, 0, NULL, NULL); - if (addr) - taddr = of_translate_address(np, addr); - - snprintf(name, MII_BUS_ID_SIZE, "%s@%llx", np->name, - (unsigned long long)taddr); -} - - static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs, struct device_node *np) { #if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE) @@ -298,7 +256,6 @@ static int fsl_pq_mdio_probe(struct platform_device *ofdev) new_bus->write = &fsl_pq_mdio_write, new_bus->reset = &fsl_pq_mdio_reset, new_bus->priv = priv; - fsl_pq_mdio_bus_name(new_bus->id, np); addrp = of_get_address(np, 0, &size, NULL); if (!addrp) { @@ -313,6 +270,9 @@ static int fsl_pq_mdio_probe(struct platform_device *ofdev) goto err_free_bus; } + snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s@%llx", np->name, + (unsigned long long)addr); + map = ioremap(addr, size); if (!map) { err = -ENOMEM; -- cgit v1.2.3 From 5078ac79588600208ec21d1c7781e5cd8a7ab830 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 29 Aug 2012 08:08:00 +0000 Subject: net/fsl_pq_mdio: various small fixes 1) Replace printk with dev_err 2) Fix some whitespace mistakes 3) Rename "ofdev" to "pdev", since it's a platform_device now 4) Fix an inadvertent compound statement by replacing commas with semicolons Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fsl_pq_mdio.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index d5b7590b7533..44f00a4780d7 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -155,8 +155,7 @@ static int fsl_pq_mdio_reset(struct mii_bus *bus) mutex_unlock(&bus->mdio_lock); if (!status) { - printk(KERN_ERR "%s: The MII Bus is stuck!\n", - bus->name); + dev_err(&bus->dev, "timeout waiting for MII bus\n"); return -EBUSY; } @@ -173,7 +172,7 @@ static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs, struct devi * Also, we have to cast back to struct gfar because of * definition weirdness done in gianfar.h. */ - if(of_device_is_compatible(np, "fsl,gianfar-mdio") || + if (of_device_is_compatible(np, "fsl,gianfar-mdio") || of_device_is_compatible(np, "fsl,gianfar-tbi") || of_device_is_compatible(np, "gianfar")) { enet_regs = (struct gfar __iomem *)regs; @@ -227,9 +226,9 @@ static int get_ucc_id_for_range(u64 start, u64 end, u32 *ucc_id) #endif } -static int fsl_pq_mdio_probe(struct platform_device *ofdev) +static int fsl_pq_mdio_probe(struct platform_device *pdev) { - struct device_node *np = ofdev->dev.of_node; + struct device_node *np = pdev->dev.of_node; struct device_node *tbi; struct fsl_pq_mdio_priv *priv; struct fsl_pq_mdio __iomem *regs = NULL; @@ -252,9 +251,9 @@ static int fsl_pq_mdio_probe(struct platform_device *ofdev) } new_bus->name = "Freescale PowerQUICC MII Bus", - new_bus->read = &fsl_pq_mdio_read, - new_bus->write = &fsl_pq_mdio_write, - new_bus->reset = &fsl_pq_mdio_reset, + new_bus->read = &fsl_pq_mdio_read; + new_bus->write = &fsl_pq_mdio_write; + new_bus->reset = &fsl_pq_mdio_reset; new_bus->priv = priv; addrp = of_get_address(np, 0, &size, NULL); @@ -295,8 +294,8 @@ static int fsl_pq_mdio_probe(struct platform_device *ofdev) goto err_unmap_regs; } - new_bus->parent = &ofdev->dev; - dev_set_drvdata(&ofdev->dev, new_bus); + new_bus->parent = &pdev->dev; + dev_set_drvdata(&pdev->dev, new_bus); if (of_device_is_compatible(np, "fsl,gianfar-mdio") || of_device_is_compatible(np, "fsl,gianfar-tbi") || @@ -348,8 +347,8 @@ static int fsl_pq_mdio_probe(struct platform_device *ofdev) err = of_mdiobus_register(new_bus, np); if (err) { - printk (KERN_ERR "%s: Cannot register as MDIO bus\n", - new_bus->name); + dev_err(&pdev->dev, "cannot register %s as MDIO bus\n", + new_bus->name); goto err_free_irqs; } @@ -367,9 +366,9 @@ err_free_priv: } -static int fsl_pq_mdio_remove(struct platform_device *ofdev) +static int fsl_pq_mdio_remove(struct platform_device *pdev) { - struct device *device = &ofdev->dev; + struct device *device = &pdev->dev; struct mii_bus *bus = dev_get_drvdata(device); struct fsl_pq_mdio_priv *priv = bus->priv; -- cgit v1.2.3 From afae5ad78b342f401c28b0bb1adb3cd494cb125a Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 29 Aug 2012 08:08:01 +0000 Subject: net/fsl_pq_mdio: streamline probing of MDIO nodes Make the device tree probe function more data-driven, so that it no longer searches the 'compatible' property more than once. The of_device_id[] array allows for per-entry private data, so we use that to store details about each type of node that the driver supports. This removes the need to check the 'compatible' property inside the probe function. The driver supports four types on MDIO devices: 1) Gianfar MDIO nodes that only map the MII registers 2) Gianfar MDIO nodes that map the full MDIO register set 3) eTSEC2 MDIO nodes (which map the full MDIO register set) 4) QE MDIO nodes (which map only the MII registers) Gianfar, eTSEC2, and QE have different mappings for the TBIPA register, which is needed to initialize the TBI PHY. In addition, the QE needs a special hack because of the way the device tree is ordered. All of this information is encapsulated in the fsl_pq_mdio_data structure, so when an MDIO node is probed, per-device data and functions are used to determine how to initialize the device. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fsl_pq_mdio.c | 373 ++++++++++++++++----------- 1 file changed, 221 insertions(+), 152 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index 44f00a4780d7..7eef1bb0a65f 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -23,11 +23,10 @@ #include #include #include -#include #include #include #include -#include +#include #include #include /* for ucc_set_qe_mux_mii_mng() */ @@ -41,6 +40,15 @@ #define MII_READ_COMMAND 0x00000001 +struct fsl_pq_mii { + u32 miimcfg; /* MII management configuration reg */ + u32 miimcom; /* MII management command reg */ + u32 miimadd; /* MII management address reg */ + u32 miimcon; /* MII management control reg */ + u32 miimstat; /* MII management status reg */ + u32 miimind; /* MII management indication reg */ +}; + struct fsl_pq_mdio { u8 res1[16]; u32 ieventm; /* MDIO Interrupt event register (for etsec2)*/ @@ -48,12 +56,7 @@ struct fsl_pq_mdio { u8 res2[4]; u32 emapm; /* MDIO Event mapping register (for etsec2)*/ u8 res3[1280]; - u32 miimcfg; /* MII management configuration reg */ - u32 miimcom; /* MII management command reg */ - u32 miimadd; /* MII management address reg */ - u32 miimcon; /* MII management control reg */ - u32 miimstat; /* MII management status reg */ - u32 miimind; /* MII management indication reg */ + struct fsl_pq_mii mii; u8 res4[28]; u32 utbipar; /* TBI phy address reg (only on UCC) */ u8 res5[2728]; @@ -64,7 +67,25 @@ struct fsl_pq_mdio { struct fsl_pq_mdio_priv { void __iomem *map; - struct fsl_pq_mdio __iomem *regs; + struct fsl_pq_mii __iomem *regs; +}; + +/* + * Per-device-type data. Each type of device tree node that we support gets + * one of these. + * + * @mii_offset: the offset of the MII registers within the memory map of the + * node. Some nodes define only the MII registers, and some define the whole + * MAC (which includes the MII registers). + * + * @get_tbipa: determines the address of the TBIPA register + * + * @ucc_configure: a special function for extra QE configuration + */ +struct fsl_pq_mdio_data { + unsigned int mii_offset; /* offset of the MII registers */ + uint32_t __iomem * (*get_tbipa)(void __iomem *p); + void (*ucc_configure)(phys_addr_t start, phys_addr_t end); }; /* @@ -80,7 +101,7 @@ static int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value) { struct fsl_pq_mdio_priv *priv = bus->priv; - struct fsl_pq_mdio __iomem *regs = priv->regs; + struct fsl_pq_mii __iomem *regs = priv->regs; u32 status; /* Set the PHY address and the register address we want to write */ @@ -109,7 +130,7 @@ static int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, static int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum) { struct fsl_pq_mdio_priv *priv = bus->priv; - struct fsl_pq_mdio __iomem *regs = priv->regs; + struct fsl_pq_mii __iomem *regs = priv->regs; u32 status; u16 value; @@ -130,6 +151,7 @@ static int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum) /* Grab the value of the register from miimstat */ value = in_be32(®s->miimstat); + dev_dbg(&bus->dev, "read %04x from address %x/%x\n", value, mii_id, regnum); return value; } @@ -137,7 +159,7 @@ static int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum) static int fsl_pq_mdio_reset(struct mii_bus *bus) { struct fsl_pq_mdio_priv *priv = bus->priv; - struct fsl_pq_mdio __iomem *regs = priv->regs; + struct fsl_pq_mii __iomem *regs = priv->regs; u32 status; mutex_lock(&bus->mdio_lock); @@ -162,84 +184,181 @@ static int fsl_pq_mdio_reset(struct mii_bus *bus) return 0; } -static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs, struct device_node *np) -{ #if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE) - struct gfar __iomem *enet_regs; +/* + * This is mildly evil, but so is our hardware for doing this. + * Also, we have to cast back to struct gfar because of + * definition weirdness done in gianfar.h. + */ +static uint32_t __iomem *get_gfar_tbipa(void __iomem *p) +{ + struct gfar __iomem *enet_regs = p; - /* - * This is mildly evil, but so is our hardware for doing this. - * Also, we have to cast back to struct gfar because of - * definition weirdness done in gianfar.h. - */ - if (of_device_is_compatible(np, "fsl,gianfar-mdio") || - of_device_is_compatible(np, "fsl,gianfar-tbi") || - of_device_is_compatible(np, "gianfar")) { - enet_regs = (struct gfar __iomem *)regs; - return &enet_regs->tbipa; - } else if (of_device_is_compatible(np, "fsl,etsec2-mdio") || - of_device_is_compatible(np, "fsl,etsec2-tbi")) { - return of_iomap(np, 1); - } -#endif - return NULL; + return &enet_regs->tbipa; } - -static int get_ucc_id_for_range(u64 start, u64 end, u32 *ucc_id) +/* + * Return the TBIPAR address for an eTSEC2 node + */ +static uint32_t __iomem *get_etsec_tbipa(void __iomem *p) { + return p; +} +#endif + #if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE) +/* + * Return the TBIPAR address for a QE MDIO node + */ +static uint32_t __iomem *get_ucc_tbipa(void __iomem *p) +{ + struct fsl_pq_mdio __iomem *mdio = p; + + return &mdio->utbipar; +} + +/* + * Find the UCC node that controls the given MDIO node + * + * For some reason, the QE MDIO nodes are not children of the UCC devices + * that control them. Therefore, we need to scan all UCC nodes looking for + * the one that encompases the given MDIO node. We do this by comparing + * physical addresses. The 'start' and 'end' addresses of the MDIO node are + * passed, and the correct UCC node will cover the entire address range. + * + * This assumes that there is only one QE MDIO node in the entire device tree. + */ +static void ucc_configure(phys_addr_t start, phys_addr_t end) +{ + static bool found_mii_master; struct device_node *np = NULL; - int err = 0; - for_each_compatible_node(np, NULL, "ucc_geth") { - struct resource tempres; + if (found_mii_master) + return; - err = of_address_to_resource(np, 0, &tempres); - if (err) + for_each_compatible_node(np, NULL, "ucc_geth") { + struct resource res; + const uint32_t *iprop; + uint32_t id; + int ret; + + ret = of_address_to_resource(np, 0, &res); + if (ret < 0) { + pr_debug("fsl-pq-mdio: no address range in node %s\n", + np->full_name); continue; + } /* if our mdio regs fall within this UCC regs range */ - if ((start >= tempres.start) && (end <= tempres.end)) { - /* Find the id of the UCC */ - const u32 *id; - - id = of_get_property(np, "cell-index", NULL); - if (!id) { - id = of_get_property(np, "device-id", NULL); - if (!id) - continue; + if ((start < res.start) || (end > res.end)) + continue; + + iprop = of_get_property(np, "cell-index", NULL); + if (!iprop) { + iprop = of_get_property(np, "device-id", NULL); + if (!iprop) { + pr_debug("fsl-pq-mdio: no UCC ID in node %s\n", + np->full_name); + continue; } + } - *ucc_id = *id; + id = be32_to_cpup(iprop); - return 0; + /* + * cell-index and device-id for QE nodes are + * numbered from 1, not 0. + */ + if (ucc_set_qe_mux_mii_mng(id - 1) < 0) { + pr_debug("fsl-pq-mdio: invalid UCC ID in node %s\n", + np->full_name); + continue; } + + pr_debug("fsl-pq-mdio: setting node UCC%u to MII master\n", id); + found_mii_master = true; } +} - if (err) - return err; - else - return -EINVAL; -#else - return -ENODEV; #endif -} + +static struct of_device_id fsl_pq_mdio_match[] = { +#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE) + { + .compatible = "fsl,gianfar-tbi", + .data = &(struct fsl_pq_mdio_data) { + .mii_offset = 0, + .get_tbipa = get_gfar_tbipa, + }, + }, + { + .compatible = "fsl,gianfar-mdio", + .data = &(struct fsl_pq_mdio_data) { + .mii_offset = 0, + .get_tbipa = get_gfar_tbipa, + }, + }, + { + .type = "mdio", + .compatible = "gianfar", + .data = &(struct fsl_pq_mdio_data) { + .mii_offset = offsetof(struct fsl_pq_mdio, mii), + .get_tbipa = get_gfar_tbipa, + }, + }, + { + .compatible = "fsl,etsec2-tbi", + .data = &(struct fsl_pq_mdio_data) { + .mii_offset = offsetof(struct fsl_pq_mdio, mii), + .get_tbipa = get_etsec_tbipa, + }, + }, + { + .compatible = "fsl,etsec2-mdio", + .data = &(struct fsl_pq_mdio_data) { + .mii_offset = offsetof(struct fsl_pq_mdio, mii), + .get_tbipa = get_etsec_tbipa, + }, + }, +#endif +#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE) + { + .compatible = "fsl,ucc-mdio", + .data = &(struct fsl_pq_mdio_data) { + .mii_offset = 0, + .get_tbipa = get_ucc_tbipa, + .ucc_configure = ucc_configure, + }, + }, + { + /* Legacy UCC MDIO node */ + .type = "mdio", + .compatible = "ucc_geth_phy", + .data = &(struct fsl_pq_mdio_data) { + .mii_offset = 0, + .get_tbipa = get_ucc_tbipa, + .ucc_configure = ucc_configure, + }, + }, +#endif + {}, +}; +MODULE_DEVICE_TABLE(of, fsl_pq_mdio_match); static int fsl_pq_mdio_probe(struct platform_device *pdev) { + const struct of_device_id *id = + of_match_device(fsl_pq_mdio_match, &pdev->dev); + const struct fsl_pq_mdio_data *data = id->data; struct device_node *np = pdev->dev.of_node; + struct resource res; struct device_node *tbi; struct fsl_pq_mdio_priv *priv; - struct fsl_pq_mdio __iomem *regs = NULL; - void __iomem *map; - u32 __iomem *tbipa; struct mii_bus *new_bus; - int tbiaddr = -1; - const u32 *addrp; - u64 addr = 0, size = 0; int err; + dev_dbg(&pdev->dev, "found %s compatible node\n", id->compatible); + priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; @@ -256,39 +375,35 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) new_bus->reset = &fsl_pq_mdio_reset; new_bus->priv = priv; - addrp = of_get_address(np, 0, &size, NULL); - if (!addrp) { - err = -EINVAL; - goto err_free_bus; - } - - /* Set the PHY base address */ - addr = of_translate_address(np, addrp); - if (addr == OF_BAD_ADDR) { - err = -EINVAL; + err = of_address_to_resource(np, 0, &res); + if (err < 0) { + dev_err(&pdev->dev, "could not obtain address information\n"); goto err_free_bus; } snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s@%llx", np->name, - (unsigned long long)addr); + (unsigned long long)res.start); - map = ioremap(addr, size); - if (!map) { + priv->map = of_iomap(np, 0); + if (!priv->map) { err = -ENOMEM; goto err_free_bus; } - priv->map = map; - if (of_device_is_compatible(np, "fsl,gianfar-mdio") || - of_device_is_compatible(np, "fsl,gianfar-tbi") || - of_device_is_compatible(np, "fsl,ucc-mdio") || - of_device_is_compatible(np, "ucc_geth_phy")) - map -= offsetof(struct fsl_pq_mdio, miimcfg); - regs = map; - priv->regs = regs; + /* + * Some device tree nodes represent only the MII registers, and + * others represent the MAC and MII registers. The 'mii_offset' field + * contains the offset of the MII registers inside the mapped register + * space. + */ + if (data->mii_offset > resource_size(&res)) { + dev_err(&pdev->dev, "invalid register map\n"); + err = -EINVAL; + goto err_unmap_regs; + } + priv->regs = priv->map + data->mii_offset; new_bus->irq = kcalloc(PHY_MAX_ADDR, sizeof(int), GFP_KERNEL); - if (NULL == new_bus->irq) { err = -ENOMEM; goto err_unmap_regs; @@ -297,54 +412,36 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) new_bus->parent = &pdev->dev; dev_set_drvdata(&pdev->dev, new_bus); - if (of_device_is_compatible(np, "fsl,gianfar-mdio") || - of_device_is_compatible(np, "fsl,gianfar-tbi") || - of_device_is_compatible(np, "fsl,etsec2-mdio") || - of_device_is_compatible(np, "fsl,etsec2-tbi") || - of_device_is_compatible(np, "gianfar")) { - tbipa = get_gfar_tbipa(regs, np); - if (!tbipa) { - err = -EINVAL; - goto err_free_irqs; - } - } else if (of_device_is_compatible(np, "fsl,ucc-mdio") || - of_device_is_compatible(np, "ucc_geth_phy")) { - u32 id; - static u32 mii_mng_master; - - tbipa = ®s->utbipar; - - if ((err = get_ucc_id_for_range(addr, addr + size, &id))) - goto err_free_irqs; - - if (!mii_mng_master) { - mii_mng_master = id; - ucc_set_qe_mux_mii_mng(id - 1); + if (data->get_tbipa) { + for_each_child_of_node(np, tbi) { + if (strcmp(tbi->type, "tbi-phy") == 0) { + dev_dbg(&pdev->dev, "found TBI PHY node %s\n", + strrchr(tbi->full_name, '/') + 1); + break; + } } - } else { - err = -ENODEV; - goto err_free_irqs; - } - for_each_child_of_node(np, tbi) { - if (!strncmp(tbi->type, "tbi-phy", 8)) - break; - } + if (tbi) { + const u32 *prop = of_get_property(tbi, "reg", NULL); + uint32_t __iomem *tbipa; - if (tbi) { - const u32 *prop = of_get_property(tbi, "reg", NULL); + if (!prop) { + dev_err(&pdev->dev, + "missing 'reg' property in node %s\n", + tbi->full_name); + err = -EBUSY; + goto error; + } - if (prop) - tbiaddr = *prop; + tbipa = data->get_tbipa(priv->map); - if (tbiaddr == -1) { - err = -EBUSY; - goto err_free_irqs; - } else { - out_be32(tbipa, tbiaddr); + out_be32(tbipa, be32_to_cpup(prop)); } } + if (data->ucc_configure) + data->ucc_configure(res.start, res.end); + err = of_mdiobus_register(new_bus, np); if (err) { dev_err(&pdev->dev, "cannot register %s as MDIO bus\n", @@ -384,34 +481,6 @@ static int fsl_pq_mdio_remove(struct platform_device *pdev) return 0; } -static struct of_device_id fsl_pq_mdio_match[] = { - { - .type = "mdio", - .compatible = "ucc_geth_phy", - }, - { - .type = "mdio", - .compatible = "gianfar", - }, - { - .compatible = "fsl,ucc-mdio", - }, - { - .compatible = "fsl,gianfar-tbi", - }, - { - .compatible = "fsl,gianfar-mdio", - }, - { - .compatible = "fsl,etsec2-tbi", - }, - { - .compatible = "fsl,etsec2-mdio", - }, - {}, -}; -MODULE_DEVICE_TABLE(of, fsl_pq_mdio_match); - static struct platform_driver fsl_pq_mdio_driver = { .driver = { .name = "fsl-pq_mdio", -- cgit v1.2.3 From dd3b8a32e66cc3274a27338335337a5b65611ea5 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 29 Aug 2012 08:08:02 +0000 Subject: net/fsl-pq-mdio: coalesce multiple memory allocations into one Take advantage of the new mdiobus_alloc_size() function to combine three different memory allocations into one. This also simplies the error handling. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fsl_pq_mdio.c | 42 ++++++++++------------------ 1 file changed, 14 insertions(+), 28 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index 7eef1bb0a65f..ebd4638b4977 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -68,6 +68,7 @@ struct fsl_pq_mdio { struct fsl_pq_mdio_priv { void __iomem *map; struct fsl_pq_mii __iomem *regs; + int irqs[PHY_MAX_ADDR]; }; /* @@ -359,26 +360,21 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "found %s compatible node\n", id->compatible); - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) + new_bus = mdiobus_alloc_size(sizeof(*priv)); + if (!new_bus) return -ENOMEM; - new_bus = mdiobus_alloc(); - if (!new_bus) { - err = -ENOMEM; - goto err_free_priv; - } - + priv = new_bus->priv; new_bus->name = "Freescale PowerQUICC MII Bus", new_bus->read = &fsl_pq_mdio_read; new_bus->write = &fsl_pq_mdio_write; new_bus->reset = &fsl_pq_mdio_reset; - new_bus->priv = priv; + new_bus->irq = priv->irqs; err = of_address_to_resource(np, 0, &res); if (err < 0) { dev_err(&pdev->dev, "could not obtain address information\n"); - goto err_free_bus; + goto error; } snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s@%llx", np->name, @@ -387,7 +383,7 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) priv->map = of_iomap(np, 0); if (!priv->map) { err = -ENOMEM; - goto err_free_bus; + goto error; } /* @@ -399,16 +395,10 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) if (data->mii_offset > resource_size(&res)) { dev_err(&pdev->dev, "invalid register map\n"); err = -EINVAL; - goto err_unmap_regs; + goto error; } priv->regs = priv->map + data->mii_offset; - new_bus->irq = kcalloc(PHY_MAX_ADDR, sizeof(int), GFP_KERNEL); - if (NULL == new_bus->irq) { - err = -ENOMEM; - goto err_unmap_regs; - } - new_bus->parent = &pdev->dev; dev_set_drvdata(&pdev->dev, new_bus); @@ -446,19 +436,17 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) if (err) { dev_err(&pdev->dev, "cannot register %s as MDIO bus\n", new_bus->name); - goto err_free_irqs; + goto error; } return 0; -err_free_irqs: - kfree(new_bus->irq); -err_unmap_regs: - iounmap(priv->map); -err_free_bus: +error: + if (priv->map) + iounmap(priv->map); + kfree(new_bus); -err_free_priv: - kfree(priv); + return err; } @@ -474,9 +462,7 @@ static int fsl_pq_mdio_remove(struct platform_device *pdev) dev_set_drvdata(device, NULL); iounmap(priv->map); - bus->priv = NULL; mdiobus_free(bus); - kfree(priv); return 0; } -- cgit v1.2.3 From 761743ebc92df72053e736fce953a5d2e90099d5 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 29 Aug 2012 08:08:03 +0000 Subject: net/fsl_pq_mdio: add support for the Fman 1G MDIO controller The MDIO controller on the Frame Manager (Fman) is compatible with the QE and Gianfar MDIO controllers, but we don't care about the TBI because the Ethernet drivers (FMD) take care of programming it. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fsl_pq_mdio.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index ebd4638b4977..c93a05654b46 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -342,6 +342,15 @@ static struct of_device_id fsl_pq_mdio_match[] = { }, }, #endif + /* No Kconfig option for Fman support yet */ + { + .compatible = "fsl,fman-mdio", + .data = &(struct fsl_pq_mdio_data) { + .mii_offset = 0, + /* Fman TBI operations are handled elsewhere */ + }, + }, + {}, }; MODULE_DEVICE_TABLE(of, fsl_pq_mdio_match); -- cgit v1.2.3 From efc38d2af55d80b4420dab71f6634ad7aa34a38c Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Fri, 17 Aug 2012 06:17:51 +0000 Subject: e1000e: use correct type for read of 32-bit register The POEMB register is 32 bits, not 16. Signed-off-by: Bruce Allan Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/82571.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 080c89093feb..c98586408005 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -653,7 +653,7 @@ static void e1000_put_hw_semaphore_82574(struct e1000_hw *hw) **/ static s32 e1000_set_d0_lplu_state_82574(struct e1000_hw *hw, bool active) { - u16 data = er32(POEMB); + u32 data = er32(POEMB); if (active) data |= E1000_PHY_CTRL_D0A_LPLU; @@ -677,7 +677,7 @@ static s32 e1000_set_d0_lplu_state_82574(struct e1000_hw *hw, bool active) **/ static s32 e1000_set_d3_lplu_state_82574(struct e1000_hw *hw, bool active) { - u16 data = er32(POEMB); + u32 data = er32(POEMB); if (!active) { data &= ~E1000_PHY_CTRL_NOND0A_LPLU; -- cgit v1.2.3 From bc76329d4a788b1c5f2de7208b2fae4e9204223c Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Fri, 17 Aug 2012 06:18:07 +0000 Subject: e1000e: cleanup strict checkpatch MEMORY_BARRIER checks Add comments to memory barriers per strict checkpatch. Signed-off-by: Bruce Allan Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 46c3b1f9ff89..fb6c813f5f86 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3746,6 +3746,10 @@ static irqreturn_t e1000_intr_msi_test(int irq, void *data) e_dbg("icr is %08X\n", icr); if (icr & E1000_ICR_RXSEQ) { adapter->flags &= ~FLAG_MSI_TEST_FAILED; + /* + * Force memory writes to complete before acknowledging the + * interrupt is handled. + */ wmb(); } @@ -3787,6 +3791,10 @@ static int e1000_test_msi_interrupt(struct e1000_adapter *adapter) goto msi_test_failed; } + /* + * Force memory writes to complete before enabling and firing an + * interrupt. + */ wmb(); e1000_irq_enable(adapter); @@ -3798,7 +3806,7 @@ static int e1000_test_msi_interrupt(struct e1000_adapter *adapter) e1000_irq_disable(adapter); - rmb(); + rmb(); /* read flags after interrupt has been fired */ if (adapter->flags & FLAG_MSI_TEST_FAILED) { adapter->int_mode = E1000E_INT_MODE_LEGACY; -- cgit v1.2.3 From 06a402ef51b374f2308b0a6c790b301311df786f Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Fri, 17 Aug 2012 06:17:57 +0000 Subject: e1000e: cleanup strict checkpatch check CHECK: multiple assignments should be avoided Signed-off-by: Bruce Allan Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/ethtool.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 2e76f06720fd..c11ac2756667 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -1942,7 +1942,8 @@ static int e1000_set_coalesce(struct net_device *netdev, return -EINVAL; if (ec->rx_coalesce_usecs == 4) { - adapter->itr = adapter->itr_setting = 4; + adapter->itr_setting = 4; + adapter->itr = adapter->itr_setting; } else if (ec->rx_coalesce_usecs <= 3) { adapter->itr = 20000; adapter->itr_setting = ec->rx_coalesce_usecs; -- cgit v1.2.3 From 419e551caa9e9689aa2f68a8897f9eaf44958eb3 Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Fri, 17 Aug 2012 06:18:02 +0000 Subject: e1000e: cleanup - remove inapplicable comment Early Receive has been disabled in the driver so this comment is no longer applicable. Signed-off-by: Bruce Allan Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index fb6c813f5f86..c35d354f53a0 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3446,7 +3446,7 @@ void e1000e_reset(struct e1000_adapter *adapter) /* * if short on Rx space, Rx wins and must trump Tx - * adjustment or use Early Receive if available + * adjustment */ if (pba < min_rx_space) pba = min_rx_space; -- cgit v1.2.3 From 70443ae9d07f1c1de2431327814b2594b86a99bb Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Fri, 17 Aug 2012 06:18:13 +0000 Subject: e1000e: cleanup - remove unnecessary variable Signed-off-by: Bruce Allan Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index c35d354f53a0..c0815ce26af6 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -4669,7 +4669,7 @@ static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb) struct e1000_buffer *buffer_info; unsigned int i; u32 cmd_length = 0; - u16 ipcse = 0, tucse, mss; + u16 ipcse = 0, mss; u8 ipcss, ipcso, tucss, tucso, hdr_len; if (!skb_is_gso(skb)) @@ -4703,7 +4703,6 @@ static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb) ipcso = (void *)&(ip_hdr(skb)->check) - (void *)skb->data; tucss = skb_transport_offset(skb); tucso = (void *)&(tcp_hdr(skb)->check) - (void *)skb->data; - tucse = 0; cmd_length |= (E1000_TXD_CMD_DEXT | E1000_TXD_CMD_TSE | E1000_TXD_CMD_TCP | (skb->len - (hdr_len))); @@ -4717,7 +4716,7 @@ static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb) context_desc->lower_setup.ip_fields.ipcse = cpu_to_le16(ipcse); context_desc->upper_setup.tcp_fields.tucss = tucss; context_desc->upper_setup.tcp_fields.tucso = tucso; - context_desc->upper_setup.tcp_fields.tucse = cpu_to_le16(tucse); + context_desc->upper_setup.tcp_fields.tucse = 0; context_desc->tcp_seg_setup.fields.mss = cpu_to_le16(mss); context_desc->tcp_seg_setup.fields.hdr_len = hdr_len; context_desc->cmd_and_length = cpu_to_le32(cmd_length); -- cgit v1.2.3 From 076d807024052a2c0d76050edd89cd94d0515684 Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Fri, 17 Aug 2012 06:18:23 +0000 Subject: e1000e: update driver version number Signed-off-by: Bruce Allan Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index c0815ce26af6..095a6be622a7 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -56,7 +56,7 @@ #define DRV_EXTRAVERSION "-k" -#define DRV_VERSION "2.0.0" DRV_EXTRAVERSION +#define DRV_VERSION "2.1.4" DRV_EXTRAVERSION char e1000e_driver_name[] = "e1000e"; const char e1000e_driver_version[] = DRV_VERSION; -- cgit v1.2.3 From 0ac1e8cee674d492d336355b99bf63c906f0a2e4 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 11 May 2012 08:33:26 +0000 Subject: ixgbevf: Add suspend and resume support to the VF This change adds PCI suspend and resume support to ixgbevf. Signed-off-by: Alexander Duyck Signed-off-by: Greg Rose Tested-by: Sibai Li Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 93 ++++++++++++++++++++++- 1 file changed, 89 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 60ef64587412..87f87d81addb 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1866,6 +1866,22 @@ err_set_interrupt: return err; } +/** + * ixgbevf_clear_interrupt_scheme - Clear the current interrupt scheme settings + * @adapter: board private structure to clear interrupt scheme on + * + * We go through and clear interrupt specific resources and reset the structure + * to pre-load conditions + **/ +static void ixgbevf_clear_interrupt_scheme(struct ixgbevf_adapter *adapter) +{ + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + + ixgbevf_free_q_vectors(adapter); + ixgbevf_reset_interrupt_capability(adapter); +} + /** * ixgbevf_sw_init - Initialize general software structures * (struct ixgbevf_adapter) @@ -2889,23 +2905,85 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) return 0; } -static void ixgbevf_shutdown(struct pci_dev *pdev) +static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state) { struct net_device *netdev = pci_get_drvdata(pdev); struct ixgbevf_adapter *adapter = netdev_priv(netdev); +#ifdef CONFIG_PM + int retval = 0; +#endif netif_device_detach(netdev); if (netif_running(netdev)) { + rtnl_lock(); ixgbevf_down(adapter); ixgbevf_free_irq(adapter); ixgbevf_free_all_tx_resources(adapter); ixgbevf_free_all_rx_resources(adapter); + rtnl_unlock(); } - pci_save_state(pdev); + ixgbevf_clear_interrupt_scheme(adapter); + +#ifdef CONFIG_PM + retval = pci_save_state(pdev); + if (retval) + return retval; +#endif pci_disable_device(pdev); + + return 0; +} + +#ifdef CONFIG_PM +static int ixgbevf_resume(struct pci_dev *pdev) +{ + struct ixgbevf_adapter *adapter = pci_get_drvdata(pdev); + struct net_device *netdev = adapter->netdev; + u32 err; + + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + /* + * pci_restore_state clears dev->state_saved so call + * pci_save_state to restore it. + */ + pci_save_state(pdev); + + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n"); + return err; + } + pci_set_master(pdev); + + rtnl_lock(); + err = ixgbevf_init_interrupt_scheme(adapter); + rtnl_unlock(); + if (err) { + dev_err(&pdev->dev, "Cannot initialize interrupts\n"); + return err; + } + + ixgbevf_reset(adapter); + + if (netif_running(netdev)) { + err = ixgbevf_open(netdev); + if (err) + return err; + } + + netif_device_attach(netdev); + + return err; +} + +#endif /* CONFIG_PM */ +static void ixgbevf_shutdown(struct pci_dev *pdev) +{ + ixgbevf_suspend(pdev, PMSG_SUSPEND); } static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev, @@ -2946,7 +3024,7 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev, return stats; } -static const struct net_device_ops ixgbe_netdev_ops = { +static const struct net_device_ops ixgbevf_netdev_ops = { .ndo_open = ixgbevf_open, .ndo_stop = ixgbevf_close, .ndo_start_xmit = ixgbevf_xmit_frame, @@ -2962,7 +3040,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { static void ixgbevf_assign_netdev_ops(struct net_device *dev) { - dev->netdev_ops = &ixgbe_netdev_ops; + dev->netdev_ops = &ixgbevf_netdev_ops; ixgbevf_set_ethtool_ops(dev); dev->watchdog_timeo = 5 * HZ; } @@ -3131,6 +3209,7 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, return 0; err_register: + ixgbevf_clear_interrupt_scheme(adapter); err_sw_init: ixgbevf_reset_interrupt_capability(adapter); iounmap(hw->hw_addr); @@ -3168,6 +3247,7 @@ static void __devexit ixgbevf_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + ixgbevf_clear_interrupt_scheme(adapter); ixgbevf_reset_interrupt_capability(adapter); iounmap(adapter->hw.hw_addr); @@ -3267,6 +3347,11 @@ static struct pci_driver ixgbevf_driver = { .id_table = ixgbevf_pci_tbl, .probe = ixgbevf_probe, .remove = __devexit_p(ixgbevf_remove), +#ifdef CONFIG_PM + /* Power Management Hooks */ + .suspend = ixgbevf_suspend, + .resume = ixgbevf_resume, +#endif .shutdown = ixgbevf_shutdown, .err_handler = &ixgbevf_err_handler }; -- cgit v1.2.3 From dd1fe113e7532c7513ff03f832312d81628a23ff Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:09:48 +0000 Subject: ixgbevf: Cleanup handling of configuration for jumbo frames This change moves the code for notifying the PF of the VF maximum packet size into the vf.c file. The main motivation behind this is that the vf.c file is supposed to contain all of the messages used when communicating with the PF. In addition it creates a separate function for setting the Rx buffer size so that we have on centralized area to review what buffer sizes will be requested by the VF. Signed-off-by: Alexander Duyck Tested-by: Sibai Li Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/ixgbevf.h | 4 +- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 67 ++++++++++++++--------- drivers/net/ethernet/intel/ixgbevf/vf.c | 14 +++++ drivers/net/ethernet/intel/ixgbevf/vf.h | 1 + 4 files changed, 58 insertions(+), 28 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 98cadb0c4dab..eb26fda63c99 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -101,7 +101,9 @@ struct ixgbevf_ring { /* Supported Rx Buffer Sizes */ #define IXGBEVF_RXBUFFER_256 256 /* Used for packet split */ -#define IXGBEVF_RXBUFFER_2048 2048 +#define IXGBEVF_RXBUFFER_3K 3072 +#define IXGBEVF_RXBUFFER_7K 7168 +#define IXGBEVF_RXBUFFER_15K 15360 #define IXGBEVF_MAX_RXBUFFER 16384 /* largest size for single descriptor */ #define IXGBEVF_RX_HDR_SIZE IXGBEVF_RXBUFFER_256 diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 87f87d81addb..a5d9cc5bb257 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1057,15 +1057,46 @@ static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index) srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; - if (rx_ring->rx_buf_len == MAXIMUM_ETHERNET_VLAN_SIZE) - srrctl |= IXGBEVF_RXBUFFER_2048 >> - IXGBE_SRRCTL_BSIZEPKT_SHIFT; - else - srrctl |= rx_ring->rx_buf_len >> - IXGBE_SRRCTL_BSIZEPKT_SHIFT; + srrctl |= ALIGN(rx_ring->rx_buf_len, 1024) >> + IXGBE_SRRCTL_BSIZEPKT_SHIFT; + IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl); } +static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + int i; + u16 rx_buf_len; + + /* notify the PF of our intent to use this size of frame */ + ixgbevf_rlpml_set_vf(hw, max_frame); + + /* PF will allow an extra 4 bytes past for vlan tagged frames */ + max_frame += VLAN_HLEN; + + /* + * Make best use of allocation by using all but 1K of a + * power of 2 allocation that will be used for skb->head. + */ + if ((hw->mac.type == ixgbe_mac_X540_vf) && + (max_frame <= MAXIMUM_ETHERNET_VLAN_SIZE)) + rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE; + else if (max_frame <= IXGBEVF_RXBUFFER_3K) + rx_buf_len = IXGBEVF_RXBUFFER_3K; + else if (max_frame <= IXGBEVF_RXBUFFER_7K) + rx_buf_len = IXGBEVF_RXBUFFER_7K; + else if (max_frame <= IXGBEVF_RXBUFFER_15K) + rx_buf_len = IXGBEVF_RXBUFFER_15K; + else + rx_buf_len = IXGBEVF_MAX_RXBUFFER; + + for (i = 0; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i].rx_buf_len = rx_buf_len; +} + /** * ixgbevf_configure_rx - Configure 82599 VF Receive Unit after Reset * @adapter: board private structure @@ -1076,18 +1107,14 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter) { u64 rdba; struct ixgbe_hw *hw = &adapter->hw; - struct net_device *netdev = adapter->netdev; - int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; int i, j; u32 rdlen; - int rx_buf_len; /* PSRTYPE must be initialized in 82599 */ IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0); - if (netdev->mtu <= ETH_DATA_LEN) - rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE; - else - rx_buf_len = ALIGN(max_frame, 1024); + + /* set_rx_buffer_len must be called before ring initialization */ + ixgbevf_set_rx_buffer_len(adapter); rdlen = adapter->rx_ring[0].count * sizeof(union ixgbe_adv_rx_desc); /* Setup the HW Rx Head and Tail Descriptor Pointers and @@ -1103,7 +1130,6 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter) IXGBE_WRITE_REG(hw, IXGBE_VFRDT(j), 0); adapter->rx_ring[i].head = IXGBE_VFRDH(j); adapter->rx_ring[i].tail = IXGBE_VFRDT(j); - adapter->rx_ring[i].rx_buf_len = rx_buf_len; ixgbevf_configure_srrctl(adapter, j); } @@ -1315,7 +1341,6 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) int i, j = 0; int num_rx_rings = adapter->num_rx_queues; u32 txdctl, rxdctl; - u32 msg[2]; for (i = 0; i < adapter->num_tx_queues; i++) { j = adapter->tx_ring[i].reg_idx; @@ -1356,10 +1381,6 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) hw->mac.ops.set_rar(hw, 0, hw->mac.perm_addr, 0); } - msg[0] = IXGBE_VF_SET_LPE; - msg[1] = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; - hw->mbx.ops.write_posted(hw, msg, 2); - spin_unlock(&adapter->mbx_lock); clear_bit(__IXGBEVF_DOWN, &adapter->state); @@ -2876,10 +2897,8 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p) static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); - struct ixgbe_hw *hw = &adapter->hw; int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; int max_possible_frame = MAXIMUM_ETHERNET_VLAN_SIZE; - u32 msg[2]; if (adapter->hw.mac.type == ixgbe_mac_X540_vf) max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE; @@ -2893,12 +2912,6 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) /* must set new MTU before calling down or up */ netdev->mtu = new_mtu; - if (!netif_running(netdev)) { - msg[0] = IXGBE_VF_SET_LPE; - msg[1] = max_frame; - hw->mbx.ops.write_posted(hw, msg, 2); - } - if (netif_running(netdev)) ixgbevf_reinit_locked(adapter); diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index ec89b86f7ca4..3d555a10f592 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -419,6 +419,20 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw, return 0; } +/** + * ixgbevf_rlpml_set_vf - Set the maximum receive packet length + * @hw: pointer to the HW structure + * @max_size: value to assign to max frame size + **/ +void ixgbevf_rlpml_set_vf(struct ixgbe_hw *hw, u16 max_size) +{ + u32 msgbuf[2]; + + msgbuf[0] = IXGBE_VF_SET_LPE; + msgbuf[1] = max_size; + ixgbevf_write_msg_read_ack(hw, msgbuf, 2); +} + static const struct ixgbe_mac_operations ixgbevf_mac_ops = { .init_hw = ixgbevf_init_hw_vf, .reset_hw = ixgbevf_reset_hw_vf, diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h index 25c951daee5d..07fd87688e35 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.h +++ b/drivers/net/ethernet/intel/ixgbevf/vf.h @@ -170,5 +170,6 @@ struct ixgbevf_info { const struct ixgbe_mac_operations *mac_ops; }; +void ixgbevf_rlpml_set_vf(struct ixgbe_hw *hw, u16 max_size); #endif /* __IXGBE_VF_H__ */ -- cgit v1.2.3 From a5cf5ce92ecefcbeb3265e6f894905ab3ed5c4c2 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 30 Aug 2012 05:49:58 +0000 Subject: net:stmmac: Add check if mdiobus is registered in stmmac_mdio_unregister This patch adds a basic check in stmmac_mdio_unregister to see if mdio bus registeration for this driver was actually sucessfull or not. Use case here is, if BSP considers using mdio-gpio bus along with stmmac driver by passing mdio_bus_data as NULL in platform data. Call to stmmac_mdio_register with mdio_bus_data as NULL returns 0, which is a considered sucessfull call form stmmac. Then again when we unload the driver we just call stmmac_mdio_unregister, this is were the actual problem is stmmac-mdio code dont really know at this instance of calling that stmmac_mdio_register was actually successful. So Adding a check in stmmac_mdio_unregister is always safe. Without this patch stmmac driver calls stmmac_mdio_register from stmmac_release which Segfaults as mii bus was never registered at the first point. Originally the this bug was found when unloading an stmmac driver instance which uses mdio-gpio for smi access. Signed-off-by: Srinivas Kandagatla Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index ade108232048..e1f3d04a8c90 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -258,6 +258,9 @@ int stmmac_mdio_unregister(struct net_device *ndev) { struct stmmac_priv *priv = netdev_priv(ndev); + if (!priv->mii) + return 0; + mdiobus_unregister(priv->mii); priv->mii->priv = NULL; mdiobus_free(priv->mii); -- cgit v1.2.3 From 1f9defa0c267ebefd02b8b25697678f7911e74d8 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 30 Aug 2012 05:50:19 +0000 Subject: net:stmmac: fix broken stmmac_pltfr_remove. This patch fixes stmmac_pltfr_remove function, which is broken because, it is accessing plat variable via freed memory priv pointer which gets freed by free_netdev called from stmmac_dvr_remove. In short this patch caches the plat pointer in local variable before calling stmmac_dvr_remove to prevent code accessing freed memory. Without this patch any attempt to remove the stmmac device will fail as below: Unregistering eth 0 ... Unable to handle kernel paging request at virtual address 6b6b6bab pgd = de5dc000 [6b6b6bab] *pgd=00000000 Internal error: Oops: 5 [#1] PREEMPT SMP Modules linked in: cdev(O+) CPU: 0 Tainted: G O (3.3.1_stm24_0210-b2000+ #25) PC is at stmmac_pltfr_remove+0x2c/0xa0 LR is at stmmac_pltfr_remove+0x28/0xa0 pc : [] lr : [] psr: 60000013 sp : def6be78 ip : de6c5a00 fp : 00000000 r10: 00000028 r9 : c082d81d r8 : 00000001 r7 : de65a600 r6 : df81b240 r5 : c0413fd8 r4 : 00000000 r3 : 6b6b6b6b r2 : def6be6c r1 : c0355e2b r0 : 00000020 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user Control: 10c53c7d Table: 5e5dc04a DAC: 00000015 Process insmod (pid: 738, stack limit = 0xdef6a2f0) Stack: (0xdef6be78 to 0xdef6c000) be60: c0413fe0 c0403658 be80: c0400bb0 c019270c c01926f8 c0191478 00000000 c0414014 c0413fe0 c01914d8 bea0: 00000000 c0413fe0 df8045d0 c019109c c0413fe0 c0400bf0 c0413fd8 c018f04c bec0: 00000000 bf000000 c0413fd8 c01929a0 c0413fd8 bf000000 00000000 c0192bfc bee0: bf00009c bf000014 def6a000 c000859c 00000000 00000001 bf00009c bf00009c bf00: 00000001 bf00009c 00000001 bf0000e4 de65a600 00000001 c082d81d c0058cd0 bf20: bf0000a8 c004fbd8 c0056414 c082d815 c02aea20 bf0001f0 00b0b008 e0846208 bf40: c03ec8a0 e0846000 0000db0d e0850604 e08504de e0853a24 00000204 000002d4 bf60: 00000000 00000000 0000001c 0000001d 00000009 00000000 00000006 00000000 bf80: 00000003 f63d4e2e 0000db0d bef02ed8 00000080 c000d2e8 def6a000 00000000 bfa0: 00000000 c000d140 f63d4e2e 0000db0d 00b0b018 0000db0d 00b0b008 b6f4f298 bfc0: f63d4e2e 0000db0d bef02ed8 00000080 00000003 00000000 00010000 00000000 bfe0: 00b0b008 bef02c64 00008d20 b6ef3784 60000010 00b0b018 5a5a5a5a 5a5a5a5a [] (stmmac_pltfr_remove+0x2c/0xa0) from [] (platform_drv_remove+0x14/0x18) [] (platform_drv_remove+0x14/0x18) from [] (__device_release_driver+0x64/0xa4) [] (__device_release_driver+0x64/0xa4) from [] (device_release_driver+0x20/0x2c) [] (device_release_driver+0x20/0x2c) from [] (bus_remove_device+0xcc/0xdc) [] (bus_remove_device+0xcc/0xdc) from [] (device_del+0x104/0x160) [] (device_del+0x104/0x160) from [] (platform_device_del+0x18/0x58) [] (platform_device_del+0x18/0x58) from [] (platform_device_unregister+0xc/0x18) [] (platform_device_unregister+0xc/0x18) from [] (r_init+0x14/0x2c [cdev]) [] (r_init+0x14/0x2c [cdev]) from [] (do_one_initcall+0x90/0x160) [] (do_one_initcall+0x90/0x160) from [] (sys_init_module+0x15c4/0x1794) [] (sys_init_module+0x15c4/0x1794) from [] (ret_fast_syscall+0x0/0x30) Code: e1a04000 e59f0070 eb039b65 e59636e4 (e5933040) Signed-off-by: Srinivas Kandagatla Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index b93245c11995..b4ffdc7ba4fc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -186,6 +186,7 @@ static int stmmac_pltfr_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *priv = netdev_priv(ndev); + void __iomem *addr = priv->ioaddr; struct resource *res; int ret = stmmac_dvr_remove(ndev); @@ -194,7 +195,7 @@ static int stmmac_pltfr_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); - iounmap((void __force __iomem *)priv->ioaddr); + iounmap(addr); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(res->start, resource_size(res)); -- cgit v1.2.3 From d56631a66c0d0c9d662abfb38cd1f6326eeebd7c Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 30 Aug 2012 05:50:43 +0000 Subject: net:stmmac: Remove bus_id from mdio platform data. This patch removes bus_id from mdio platform data, The reason to remove bus_id is, stmmac mdio bus_id is always same as stmmac bus-id, so there is no point in passing this in different variable. Also stmmac ethernet driver connects to phy with bus_id passed its platform data. So, having single bus-id is much simpler. Signed-off-by: Srinivas Kandagatla Signed-off-by: David S. Miller --- Documentation/networking/stmmac.txt | 5 ----- drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 8 +++----- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 1 - include/linux/stmmac.h | 1 - 4 files changed, 3 insertions(+), 12 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt index c676b9cedbd0..ef9ee71b4d7f 100644 --- a/Documentation/networking/stmmac.txt +++ b/Documentation/networking/stmmac.txt @@ -173,7 +173,6 @@ Where: For MDIO bus The we have: struct stmmac_mdio_bus_data { - int bus_id; int (*phy_reset)(void *priv); unsigned int phy_mask; int *irqs; @@ -181,7 +180,6 @@ For MDIO bus The we have: }; Where: - o bus_id: bus identifier; o phy_reset: hook to reset the phy device attached to the bus. o phy_mask: phy mask passed when register the MDIO bus within the driver. o irqs: list of IRQs, one per PHY. @@ -230,9 +228,6 @@ there are two MAC cores: one MAC is for MDIO Bus/PHY emulation with fixed_link support. static struct stmmac_mdio_bus_data stmmac1_mdio_bus = { - .bus_id = 1, - | - |-> phy device on the bus_id 1 .phy_reset = phy_reset; | |-> function to provide the phy_reset on this board diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index e1f3d04a8c90..0376a5e6b2bf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -177,7 +177,7 @@ int stmmac_mdio_register(struct net_device *ndev) new_bus->write = &stmmac_mdio_write; new_bus->reset = &stmmac_mdio_reset; snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%x", - new_bus->name, mdio_bus_data->bus_id); + new_bus->name, priv->plat->bus_id); new_bus->priv = ndev; new_bus->irq = irqlist; new_bus->phy_mask = mdio_bus_data->phy_mask; @@ -213,12 +213,10 @@ int stmmac_mdio_register(struct net_device *ndev) * and no PHY number was provided to the MAC, * use the one probed here. */ - if ((priv->plat->bus_id == mdio_bus_data->bus_id) && - (priv->plat->phy_addr == -1)) + if (priv->plat->phy_addr == -1) priv->plat->phy_addr = addr; - act = (priv->plat->bus_id == mdio_bus_data->bus_id) && - (priv->plat->phy_addr == addr); + act = (priv->plat->phy_addr == addr); switch (phydev->irq) { case PHY_POLL: irq_str = "POLL"; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 13afb8edfadc..1f069b0f6af5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -40,7 +40,6 @@ static void stmmac_default_data(void) plat_dat.has_gmac = 1; plat_dat.force_sf_dma_mode = 1; - mdio_data.bus_id = 1; mdio_data.phy_reset = NULL; mdio_data.phy_mask = 0; plat_dat.mdio_bus_data = &mdio_data; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index b69bdb1e08b6..a1547ea3920d 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -76,7 +76,6 @@ /* Platfrom data for platform device structure's platform_data field */ struct stmmac_mdio_bus_data { - int bus_id; int (*phy_reset)(void *priv); unsigned int phy_mask; int *irqs; -- cgit v1.2.3 From 3f8bdecd32ab8f52bff1d646e2acb7c241d12a8d Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 30 Aug 2012 05:51:09 +0000 Subject: net:stmmac: convert driver to use devm_request_and_ioremap. This patch moves calls to ioremap and request_mem_region to devm_request_and_ioremap call. Signed-off-by: Srinivas Kandagatla Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/stmmac_platform.c | 40 +++++----------------- 1 file changed, 8 insertions(+), 32 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index b4ffdc7ba4fc..ed112b55ae7f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -78,6 +78,7 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev) { int ret = 0; struct resource *res; + struct device *dev = &pdev->dev; void __iomem *addr = NULL; struct stmmac_priv *priv = NULL; struct plat_stmmacenet_data *plat_dat = NULL; @@ -87,18 +88,10 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev) if (!res) return -ENODEV; - if (!request_mem_region(res->start, resource_size(res), pdev->name)) { - pr_err("%s: ERROR: memory allocation failed" - "cannot get the I/O addr 0x%x\n", - __func__, (unsigned int)res->start); - return -EBUSY; - } - - addr = ioremap(res->start, resource_size(res)); + addr = devm_request_and_ioremap(dev, res); if (!addr) { pr_err("%s: ERROR: memory mapping failed", __func__); - ret = -ENOMEM; - goto out_release_region; + return -ENOMEM; } if (pdev->dev.of_node) { @@ -107,14 +100,13 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev) GFP_KERNEL); if (!plat_dat) { pr_err("%s: ERROR: no memory", __func__); - ret = -ENOMEM; - goto out_unmap; + return -ENOMEM; } ret = stmmac_probe_config_dt(pdev, plat_dat, &mac); if (ret) { pr_err("%s: main dt probe failed", __func__); - goto out_unmap; + return ret; } } else { plat_dat = pdev->dev.platform_data; @@ -124,13 +116,13 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev) if (plat_dat->init) { ret = plat_dat->init(pdev); if (unlikely(ret)) - goto out_unmap; + return ret; } priv = stmmac_dvr_probe(&(pdev->dev), plat_dat, addr); if (!priv) { pr_err("%s: main driver probe failed", __func__); - goto out_unmap; + return -ENODEV; } /* Get MAC address if available (DT) */ @@ -142,8 +134,7 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev) if (priv->dev->irq == -ENXIO) { pr_err("%s: ERROR: MAC IRQ configuration " "information not found\n", __func__); - ret = -ENXIO; - goto out_unmap; + return -ENXIO; } /* @@ -165,15 +156,6 @@ static int __devinit stmmac_pltfr_probe(struct platform_device *pdev) pr_debug("STMMAC platform driver registration completed"); return 0; - -out_unmap: - iounmap(addr); - platform_set_drvdata(pdev, NULL); - -out_release_region: - release_mem_region(res->start, resource_size(res)); - - return ret; } /** @@ -186,8 +168,6 @@ static int stmmac_pltfr_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *priv = netdev_priv(ndev); - void __iomem *addr = priv->ioaddr; - struct resource *res; int ret = stmmac_dvr_remove(ndev); if (priv->plat->exit) @@ -195,10 +175,6 @@ static int stmmac_pltfr_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); - iounmap(addr); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, resource_size(res)); - return ret; } -- cgit v1.2.3 From 2a35cfa591ac63f17815c2d9432b799e37527980 Mon Sep 17 00:00:00 2001 From: Francois Romieu Date: Fri, 31 Aug 2012 23:06:17 +0200 Subject: r8169: add D-Link DGE-560T identifiers. This one includes a 8168. Not to be confused with the sky2 driven one whose PCI vendor and device ID are the same. Reported-by: Neyuki Inaya Signed-off-by: Francois Romieu Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index b47d5b35024e..0c96604e6246 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -287,6 +287,8 @@ static DEFINE_PCI_DEVICE_TABLE(rtl8169_pci_tbl) = { { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8167), 0, 0, RTL_CFG_0 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8168), 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8169), 0, 0, RTL_CFG_0 }, + { PCI_VENDOR_ID_DLINK, 0x4300, + PCI_VENDOR_ID_DLINK, 0x4b10, 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_DLINK, 0x4300), 0, 0, RTL_CFG_0 }, { PCI_DEVICE(PCI_VENDOR_ID_DLINK, 0x4302), 0, 0, RTL_CFG_0 }, { PCI_DEVICE(PCI_VENDOR_ID_AT, 0xc107), 0, 0, RTL_CFG_0 }, -- cgit v1.2.3 From 4907cb7b193a4f91c1fd30cf679c035e3644c64d Mon Sep 17 00:00:00 2001 From: Anatol Pomozov Date: Sat, 1 Sep 2012 10:31:09 -0700 Subject: treewide: fix comment/printk/variable typos Signed-off-by: Anatol Pomozov Signed-off-by: Jiri Kosina --- drivers/dma/intel_mid_dma.c | 2 +- drivers/net/ethernet/3com/typhoon.c | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h | 2 +- drivers/net/wireless/rtlwifi/rtl8192c/fw_common.c | 6 +++--- drivers/net/wireless/rtlwifi/rtl8192de/fw.c | 6 +++--- drivers/scsi/bfa/bfa_ioc.c | 2 +- drivers/scsi/bfa/bfa_ioc.h | 2 +- drivers/scsi/isci/init.c | 2 +- drivers/scsi/isci/request.c | 2 +- drivers/scsi/isci/task.c | 2 +- drivers/scsi/lpfc/lpfc_init.c | 2 +- drivers/scsi/lpfc/lpfc_sli.c | 4 ++-- drivers/video/exynos/exynos_mipi_dsi.c | 2 +- drivers/w1/masters/ds1wm.c | 2 +- fs/ext2/balloc.c | 2 +- fs/ext3/balloc.c | 2 +- fs/ext3/inode.c | 2 +- fs/ext4/inode.c | 14 +++++++------- fs/ext4/mballoc.c | 2 +- include/trace/define_trace.h | 2 +- net/8021q/vlanproc.c | 2 +- 22 files changed, 33 insertions(+), 33 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/dma/intel_mid_dma.c b/drivers/dma/intel_mid_dma.c index 222e907bfaaa..02b21d7d38e5 100644 --- a/drivers/dma/intel_mid_dma.c +++ b/drivers/dma/intel_mid_dma.c @@ -427,7 +427,7 @@ DMA engine callback Functions*/ * intel_mid_dma_tx_submit - callback to submit DMA transaction * @tx: dma engine descriptor * - * Submit the DMA trasaction for this descriptor, start if ch idle + * Submit the DMA transaction for this descriptor, start if ch idle */ static dma_cookie_t intel_mid_dma_tx_submit(struct dma_async_tx_descriptor *tx) { diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index b15366635147..bb9670f29b59 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -364,7 +364,7 @@ typhoon_inc_rxfree_index(u32 *index, const int count) static inline void typhoon_inc_tx_index(u32 *index, const int count) { - /* if we start using the Hi Tx ring, this needs updateing */ + /* if we start using the Hi Tx ring, this needs updating */ typhoon_inc_index(index, count, TXLO_ENTRIES); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 77bcd4cb4ffb..dfa3ee2ddba4 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1458,7 +1458,7 @@ struct bnx2x { int fw_stats_req_sz; /* - * FW statistics data shortcut (points at the begining of + * FW statistics data shortcut (points at the beginning of * fw_stats buffer + fw_stats_req_sz). */ struct bnx2x_fw_stats_data *fw_stats_data; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h index f83e033da6da..acf2fe4ca608 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h @@ -1321,7 +1321,7 @@ void bnx2x_init_mcast_obj(struct bnx2x *bp, * the current command will be enqueued to the tail of the * pending commands list. * - * Return: 0 is operation was sucessfull and there are no pending completions, + * Return: 0 is operation was successfull and there are no pending completions, * negative if there were errors, positive if there are pending * completions. */ diff --git a/drivers/net/wireless/rtlwifi/rtl8192c/fw_common.c b/drivers/net/wireless/rtlwifi/rtl8192c/fw_common.c index 44febfde9493..8a7b864faca3 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192c/fw_common.c +++ b/drivers/net/wireless/rtlwifi/rtl8192c/fw_common.c @@ -315,7 +315,7 @@ static void _rtl92c_fill_h2c_command(struct ieee80211_hw *hw, u16 box_reg = 0, box_extreg = 0; u8 u1b_tmp; bool isfw_read = false; - bool bwrite_sucess = false; + bool bwrite_success = false; u8 wait_h2c_limmit = 100; u8 wait_writeh2c_limmit = 100; u8 boxcontent[4], boxextcontent[2]; @@ -354,7 +354,7 @@ static void _rtl92c_fill_h2c_command(struct ieee80211_hw *hw, } } - while (!bwrite_sucess) { + while (!bwrite_success) { wait_writeh2c_limmit--; if (wait_writeh2c_limmit == 0) { RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, @@ -491,7 +491,7 @@ static void _rtl92c_fill_h2c_command(struct ieee80211_hw *hw, break; } - bwrite_sucess = true; + bwrite_success = true; rtlhal->last_hmeboxnum = boxnum + 1; if (rtlhal->last_hmeboxnum == 4) diff --git a/drivers/net/wireless/rtlwifi/rtl8192de/fw.c b/drivers/net/wireless/rtlwifi/rtl8192de/fw.c index 895ae6c1f354..eb22dccc418b 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192de/fw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192de/fw.c @@ -365,7 +365,7 @@ static void _rtl92d_fill_h2c_command(struct ieee80211_hw *hw, u8 u1b_tmp; bool isfw_read = false; u8 buf_index = 0; - bool bwrite_sucess = false; + bool bwrite_success = false; u8 wait_h2c_limmit = 100; u8 wait_writeh2c_limmit = 100; u8 boxcontent[4], boxextcontent[2]; @@ -408,7 +408,7 @@ static void _rtl92d_fill_h2c_command(struct ieee80211_hw *hw, break; } } - while (!bwrite_sucess) { + while (!bwrite_success) { wait_writeh2c_limmit--; if (wait_writeh2c_limmit == 0) { RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, @@ -515,7 +515,7 @@ static void _rtl92d_fill_h2c_command(struct ieee80211_hw *hw, "switch case not processed\n"); break; } - bwrite_sucess = true; + bwrite_success = true; rtlhal->last_hmeboxnum = boxnum + 1; if (rtlhal->last_hmeboxnum == 4) rtlhal->last_hmeboxnum = 0; diff --git a/drivers/scsi/bfa/bfa_ioc.c b/drivers/scsi/bfa/bfa_ioc.c index 14e6284e48e4..6faff0053370 100644 --- a/drivers/scsi/bfa/bfa_ioc.c +++ b/drivers/scsi/bfa/bfa_ioc.c @@ -5587,7 +5587,7 @@ static bfa_status_t bfa_dconf_flash_write(struct bfa_dconf_mod_s *dconf); static void bfa_dconf_init_cb(void *arg, bfa_status_t status); /* - * Begining state of dconf module. Waiting for an event to start. + * Beginning state of dconf module. Waiting for an event to start. */ static void bfa_dconf_sm_uninit(struct bfa_dconf_mod_s *dconf, enum bfa_dconf_event event) diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h index 1a99d4b5b50f..7b916e04ca56 100644 --- a/drivers/scsi/bfa/bfa_ioc.h +++ b/drivers/scsi/bfa/bfa_ioc.h @@ -530,7 +530,7 @@ struct bfa_diag_results_fwping { struct bfa_diag_qtest_result_s { u32 status; - u16 count; /* sucessful queue test count */ + u16 count; /* successful queue test count */ u8 queue; u8 rsvd; /* 64-bit align */ }; diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c index 47e28b555029..8912567988cf 100644 --- a/drivers/scsi/isci/init.c +++ b/drivers/scsi/isci/init.c @@ -219,7 +219,7 @@ static struct sas_domain_function_template isci_transport_ops = { * @isci_host: This parameter specifies the lldd specific wrapper for the * libsas sas_ha struct. * - * This method returns an error code indicating sucess or failure. The user + * This method returns an error code indicating success or failure. The user * should check for possible memory allocation error return otherwise, a zero * indicates success. */ diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c index 7a0431c73493..c1bafc3f3fb1 100644 --- a/drivers/scsi/isci/request.c +++ b/drivers/scsi/isci/request.c @@ -2240,7 +2240,7 @@ static enum sci_status atapi_data_tc_completion_handler(struct isci_request *ire status = ireq->sci_status; sci_change_state(&idev->sm, SCI_STP_DEV_ATAPI_ERROR); } else { - /* If receiving any non-sucess TC status, no UF + /* If receiving any non-success TC status, no UF * received yet, then an UF for the status fis * is coming after (XXX: suspect this is * actually a protocol error or a bug like the diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c index 6bc74eb012c9..b6f19a1db780 100644 --- a/drivers/scsi/isci/task.c +++ b/drivers/scsi/isci/task.c @@ -532,7 +532,7 @@ int isci_task_abort_task(struct sas_task *task) /* The request has already completed and there * is nothing to do here other than to set the task * done bit, and indicate that the task abort function - * was sucessful. + * was successful. */ spin_lock_irqsave(&task->task_state_lock, flags); task->task_state_flags |= SAS_TASK_STATE_DONE; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 411ed48d79da..be43b4f6bd70 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -6470,7 +6470,7 @@ out_error: * we just use some constant number as place holder. * * Return codes - * 0 - sucessful + * 0 - successful * -ENOMEM - No availble memory * -EIO - The mailbox failed to complete successfully. **/ diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index b4720a109817..7983abbb7aaf 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -4739,7 +4739,7 @@ lpfc_sli4_read_rev(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq, * is attached to. * * Return codes - * 0 - sucessful + * 0 - successful * otherwise - failed to retrieve physical port name **/ static int @@ -15118,7 +15118,7 @@ lpfc_check_next_fcf_pri_level(struct lpfc_hba *phba) /* * if next_fcf_pri was not set above and the list is not empty then * we have failed flogis on all of them. So reset flogi failed - * and start at the begining. + * and start at the beginning. */ if (!next_fcf_pri && !list_empty(&phba->fcf.fcf_pri_list)) { list_for_each_entry(fcf_pri, &phba->fcf.fcf_pri_list, list) { diff --git a/drivers/video/exynos/exynos_mipi_dsi.c b/drivers/video/exynos/exynos_mipi_dsi.c index 9908e75ae761..752a12e625e4 100644 --- a/drivers/video/exynos/exynos_mipi_dsi.c +++ b/drivers/video/exynos/exynos_mipi_dsi.c @@ -461,7 +461,7 @@ static int exynos_mipi_dsi_probe(struct platform_device *pdev) done: platform_set_drvdata(pdev, dsim); - dev_dbg(&pdev->dev, "%s() completed sucessfuly (%s mode)\n", __func__, + dev_dbg(&pdev->dev, "%s() completed successfully (%s mode)\n", __func__, dsim_config->e_interface == DSIM_COMMAND ? "CPU" : "RGB"); return 0; diff --git a/drivers/w1/masters/ds1wm.c b/drivers/w1/masters/ds1wm.c index a0c8965c1a79..649eb0b2d3ff 100644 --- a/drivers/w1/masters/ds1wm.c +++ b/drivers/w1/masters/ds1wm.c @@ -347,7 +347,7 @@ static void ds1wm_search(void *data, struct w1_master *master_dev, "pass: %d entering ASM\n", pass); ds1wm_write_register(ds1wm_data, DS1WM_CMD, DS1WM_CMD_SRA); dev_dbg(&ds1wm_data->pdev->dev, - "pass: %d begining nibble loop\n", pass); + "pass: %d beginning nibble loop\n", pass); r_prime = 0; d = 0; diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index 1c3613998862..905166a3ffb2 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -479,7 +479,7 @@ void ext2_discard_reservation(struct inode *inode) /** * ext2_free_blocks() -- Free given blocks and update quota and i_blocks * @inode: inode - * @block: start physcial block to free + * @block: start physical block to free * @count: number of blocks to free */ void ext2_free_blocks (struct inode * inode, unsigned long block, diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index 25cd60892116..7c6a31d44daf 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -483,7 +483,7 @@ void ext3_discard_reservation(struct inode *inode) * ext3_free_blocks_sb() -- Free given blocks and update quota * @handle: handle to this transaction * @sb: super block - * @block: start physcial block to free + * @block: start physical block to free * @count: number of blocks to free * @pdquot_freed_blocks: pointer to quota */ diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 9a4a5c48b1c9..3aff616d4d03 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -3196,7 +3196,7 @@ out_brelse: * * - Within generic_file_write() for O_SYNC files. * Here, there will be no transaction running. We wait for any running - * trasnaction to commit. + * transaction to commit. * * - Within sys_sync(), kupdate and such. * We wait on commit, if tol to. diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 02bc8cbe7281..189dae6b0964 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3227,7 +3227,7 @@ int ext4_discard_partial_page_buffers(handle_t *handle, * handle: The journal handle * inode: The files inode * page: A locked page that contains the offset "from" - * from: The starting byte offset (from the begining of the file) + * from: The starting byte offset (from the beginning of the file) * to begin discarding * len: The length of bytes to discard * flags: Optional flags that may be used: @@ -3235,11 +3235,11 @@ int ext4_discard_partial_page_buffers(handle_t *handle, * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED * Only zero the regions of the page whose buffer heads * have already been unmapped. This flag is appropriate - * for updateing the contents of a page whose blocks may + * for updating the contents of a page whose blocks may * have already been released, and we only want to zero * out the regions that correspond to those released blocks. * - * Returns zero on sucess or negative on failure. + * Returns zero on success or negative on failure. */ static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, struct inode *inode, struct page *page, loff_t from, @@ -3400,7 +3400,7 @@ int ext4_can_truncate(struct inode *inode) * @offset: The offset where the hole will begin * @len: The length of the hole * - * Returns: 0 on sucess or negative on failure + * Returns: 0 on success or negative on failure */ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) @@ -3922,7 +3922,7 @@ static int ext4_inode_blocks_set(handle_t *handle, if (i_blocks <= ~0U) { /* - * i_blocks can be represnted in a 32 bit variable + * i_blocks can be represented in a 32 bit variable * as multiple of 512 bytes */ raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); @@ -4083,7 +4083,7 @@ out_brelse: * * - Within generic_file_write() for O_SYNC files. * Here, there will be no transaction running. We wait for any running - * trasnaction to commit. + * transaction to commit. * * - Within sys_sync(), kupdate and such. * We wait on commit, if tol to. @@ -4327,7 +4327,7 @@ static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) * worse case, the indexs blocks spread over different block groups * * If datablocks are discontiguous, they are possible to spread over - * different block groups too. If they are contiuguous, with flexbg, + * different block groups too. If they are contiguous, with flexbg, * they could still across block group boundary. * * Also account for superblock, inode, quota and xattr blocks diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 1cd6994fc446..86831411e98b 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4705,7 +4705,7 @@ error_return: * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block - * @block: start physcial block to add to the block group + * @block: start physical block to add to the block group * @count: number of blocks to free * * This marks the blocks as free in the bitmap and buddy. diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index b0b4eb24d592..1905ca8dd399 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -1,5 +1,5 @@ /* - * Trace files that want to automate creationg of all tracepoints defined + * Trace files that want to automate creation of all tracepoints defined * in their file should include this file. The following are macros that the * trace file may define: * diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index c718fd3664b6..4de77ea5fa37 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -105,7 +105,7 @@ static const struct file_operations vlandev_fops = { }; /* - * Proc filesystem derectory entries. + * Proc filesystem directory entries. */ /* Strings */ -- cgit v1.2.3 From 8aa23f0d8601b5bc84c8fc07b9cc45079984ef3d Mon Sep 17 00:00:00 2001 From: Carolyn Wyborny Date: Fri, 8 Jun 2012 05:01:39 +0000 Subject: igb: Add loopback test support for i210 Early release of i210 devices had the loopback test of the ethtool self-test disabled. This patch enables the loopback test for i210 devices. Signed-off-by: Carolyn Wyborny Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_ethtool.c | 51 +++++++++------------------- 1 file changed, 16 insertions(+), 35 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index be02168f1308..c4def55567f5 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1511,33 +1511,22 @@ static int igb_integrated_phy_loopback(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 ctrl_reg = 0; - u16 phy_reg = 0; hw->mac.autoneg = false; - switch (hw->phy.type) { - case e1000_phy_m88: - /* Auto-MDI/MDIX Off */ - igb_write_phy_reg(hw, M88E1000_PHY_SPEC_CTRL, 0x0808); - /* reset to update Auto-MDI/MDIX */ - igb_write_phy_reg(hw, PHY_CONTROL, 0x9140); - /* autoneg off */ - igb_write_phy_reg(hw, PHY_CONTROL, 0x8140); - break; - case e1000_phy_82580: - /* enable MII loopback */ - igb_write_phy_reg(hw, I82580_PHY_LBK_CTRL, 0x8041); - break; - case e1000_phy_i210: - /* set loopback speed in PHY */ - igb_read_phy_reg(hw, (GS40G_PAGE_SELECT & GS40G_PAGE_2), - &phy_reg); - phy_reg |= GS40G_MAC_SPEED_1G; - igb_write_phy_reg(hw, (GS40G_PAGE_SELECT & GS40G_PAGE_2), - phy_reg); - ctrl_reg = rd32(E1000_CTRL_EXT); - default: - break; + if (hw->phy.type == e1000_phy_m88) { + if (hw->phy.id != I210_I_PHY_ID) { + /* Auto-MDI/MDIX Off */ + igb_write_phy_reg(hw, M88E1000_PHY_SPEC_CTRL, 0x0808); + /* reset to update Auto-MDI/MDIX */ + igb_write_phy_reg(hw, PHY_CONTROL, 0x9140); + /* autoneg off */ + igb_write_phy_reg(hw, PHY_CONTROL, 0x8140); + } else { + /* force 1000, set loopback */ + igb_write_phy_reg(hw, I347AT4_PAGE_SELECT, 0); + igb_write_phy_reg(hw, PHY_CONTROL, 0x4140); + } } /* add small delay to avoid loopback test failure */ @@ -1555,7 +1544,7 @@ static int igb_integrated_phy_loopback(struct igb_adapter *adapter) E1000_CTRL_FD | /* Force Duplex to FULL */ E1000_CTRL_SLU); /* Set link up enable bit */ - if ((hw->phy.type == e1000_phy_m88) || (hw->phy.type == e1000_phy_i210)) + if (hw->phy.type == e1000_phy_m88) ctrl_reg |= E1000_CTRL_ILOS; /* Invert Loss of Signal */ wr32(E1000_CTRL, ctrl_reg); @@ -1563,11 +1552,10 @@ static int igb_integrated_phy_loopback(struct igb_adapter *adapter) /* Disable the receiver on the PHY so when a cable is plugged in, the * PHY does not begin to autoneg when a cable is reconnected to the NIC. */ - if ((hw->phy.type == e1000_phy_m88) || (hw->phy.type == e1000_phy_i210)) + if (hw->phy.type == e1000_phy_m88) igb_phy_disable_receiver(adapter); - udelay(500); - + mdelay(500); return 0; } @@ -1827,13 +1815,6 @@ static int igb_loopback_test(struct igb_adapter *adapter, u64 *data) *data = 0; goto out; } - if ((adapter->hw.mac.type == e1000_i210) - || (adapter->hw.mac.type == e1000_i211)) { - dev_err(&adapter->pdev->dev, - "Loopback test not supported on this part at this time.\n"); - *data = 0; - goto out; - } *data = igb_setup_desc_rings(adapter); if (*data) goto out; -- cgit v1.2.3 From 9936a7bbe56df432838fef658aea6bcfdd994021 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Aug 2012 04:46:59 +0000 Subject: igb: reduce Rx header size Reduce skb truesize by 256 bytes. Signed-off-by: Eric Dumazet Cc: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 9e572dd29ab2..0c9f62caa8fa 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -131,9 +131,9 @@ struct vf_data_storage { #define MAXIMUM_ETHERNET_VLAN_SIZE 1522 /* Supported Rx Buffer Sizes */ -#define IGB_RXBUFFER_512 512 +#define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_16384 16384 -#define IGB_RX_HDR_LEN IGB_RXBUFFER_512 +#define IGB_RX_HDR_LEN IGB_RXBUFFER_256 /* How many Tx Descriptors do we need to call netif_wake_queue ? */ #define IGB_TX_QUEUE_WAKE 16 -- cgit v1.2.3 From 42f3c43bf6f2774172b417b629f6e7ccdc794cec Mon Sep 17 00:00:00 2001 From: "Akeem G. Abodunrin" Date: Fri, 17 Aug 2012 03:35:07 +0000 Subject: igb: Supported and Advertised Pause Frame This patch add ethtool supports for Supported and Advertised Pause Frame, based on Adapter Flow Control settings. Signed-off-by: Akeem G. Abodunrin Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_ethtool.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index c4def55567f5..a2944412a55e 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -148,9 +148,9 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) SUPPORTED_100baseT_Full | SUPPORTED_1000baseT_Full| SUPPORTED_Autoneg | - SUPPORTED_TP); - ecmd->advertising = (ADVERTISED_TP | - ADVERTISED_Pause); + SUPPORTED_TP | + SUPPORTED_Pause); + ecmd->advertising = ADVERTISED_TP; if (hw->mac.autoneg == 1) { ecmd->advertising |= ADVERTISED_Autoneg; @@ -158,6 +158,21 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) ecmd->advertising |= hw->phy.autoneg_advertised; } + if (hw->mac.autoneg != 1) + ecmd->advertising &= ~(ADVERTISED_Pause | + ADVERTISED_Asym_Pause); + + if (hw->fc.requested_mode == e1000_fc_full) + ecmd->advertising |= ADVERTISED_Pause; + else if (hw->fc.requested_mode == e1000_fc_rx_pause) + ecmd->advertising |= (ADVERTISED_Pause | + ADVERTISED_Asym_Pause); + else if (hw->fc.requested_mode == e1000_fc_tx_pause) + ecmd->advertising |= ADVERTISED_Asym_Pause; + else + ecmd->advertising &= ~(ADVERTISED_Pause | + ADVERTISED_Asym_Pause); + ecmd->port = PORT_TP; ecmd->phy_address = hw->phy.addr; } else { -- cgit v1.2.3 From ab868256f8d6095e7200d928fcc054b66d0f13a3 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Tue, 14 Aug 2012 02:14:33 +0000 Subject: ixgbe: remove old init remnant Remove a for loop that does nothing in ixgbe_probe(). This is a remnant from when we had IO bars (compare to the ixgb code). Signed-off-by: Eliezer Tamir Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index fa0d6e1561c1..1cbb34f507c9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7169,11 +7169,6 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, goto err_ioremap; } - for (i = 1; i <= 5; i++) { - if (pci_resource_len(pdev, i) == 0) - continue; - } - netdev->netdev_ops = &ixgbe_netdev_ops; ixgbe_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; -- cgit v1.2.3 From 840f3000254d380934086ef0c0aefa78f80eee1e Mon Sep 17 00:00:00 2001 From: Vipul Pandya Date: Wed, 5 Sep 2012 02:01:55 +0000 Subject: cxgb4: Remove duplicate register definitions Removed duplicate definition for SGE_PF_KDOORBELL, SGE_INT_ENABLE3, PCIE_MEM_ACCESS_OFFSET registers. Moved the register field definitions around the register definition. Signed-off-by: Santosh Rastapur Signed-off-by: Vipul Pandya Reviewed-by: Sivakumar Subramani Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 18 ++++----- drivers/net/ethernet/chelsio/cxgb4/sge.c | 4 +- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 12 +++--- drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 54 ++++++------------------- 4 files changed, 30 insertions(+), 58 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 5ed49af23d6a..34d510dd56a8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2470,8 +2470,8 @@ int cxgb4_sync_txq_pidx(struct net_device *dev, u16 qid, u16 pidx, else delta = size - hw_pidx + pidx; wmb(); - t4_write_reg(adap, MYPF_REG(A_SGE_PF_KDOORBELL), - V_QID(qid) | V_PIDX(delta)); + t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL), + QID(qid) | PIDX(delta)); } out: return ret; @@ -2579,8 +2579,8 @@ static void sync_txq_pidx(struct adapter *adap, struct sge_txq *q) else delta = q->size - hw_pidx + q->db_pidx; wmb(); - t4_write_reg(adap, MYPF_REG(A_SGE_PF_KDOORBELL), - V_QID(q->cntxt_id) | V_PIDX(delta)); + t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL), + QID(q->cntxt_id) | PIDX(delta)); } out: q->db_disabled = 0; @@ -2617,9 +2617,9 @@ static void process_db_full(struct work_struct *work) notify_rdma_uld(adap, CXGB4_CONTROL_DB_FULL); drain_db_fifo(adap, dbfifo_drain_delay); - t4_set_reg_field(adap, A_SGE_INT_ENABLE3, - F_DBFIFO_HP_INT | F_DBFIFO_LP_INT, - F_DBFIFO_HP_INT | F_DBFIFO_LP_INT); + t4_set_reg_field(adap, SGE_INT_ENABLE3, + DBFIFO_HP_INT | DBFIFO_LP_INT, + DBFIFO_HP_INT | DBFIFO_LP_INT); notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY); } @@ -2639,8 +2639,8 @@ static void process_db_drop(struct work_struct *work) void t4_db_full(struct adapter *adap) { - t4_set_reg_field(adap, A_SGE_INT_ENABLE3, - F_DBFIFO_HP_INT | F_DBFIFO_LP_INT, 0); + t4_set_reg_field(adap, SGE_INT_ENABLE3, + DBFIFO_HP_INT | DBFIFO_LP_INT, 0); queue_work(workq, &adap->db_full_task); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index d49933ed551f..1fde57d45318 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -769,8 +769,8 @@ static inline void ring_tx_db(struct adapter *adap, struct sge_txq *q, int n) wmb(); /* write descriptors before telling HW */ spin_lock(&q->db_lock); if (!q->db_disabled) { - t4_write_reg(adap, MYPF_REG(A_SGE_PF_KDOORBELL), - V_QID(q->cntxt_id) | V_PIDX(n)); + t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL), + QID(q->cntxt_id) | PIDX(n)); } q->db_pidx = q->pidx; spin_unlock(&q->db_lock); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index fa947dfa4c30..8e988d699d05 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -1018,9 +1018,9 @@ static void sge_intr_handler(struct adapter *adapter) { ERR_INVALID_CIDX_INC, "SGE GTS CIDX increment too large", -1, 0 }, { ERR_CPL_OPCODE_0, "SGE received 0-length CPL", -1, 0 }, - { F_DBFIFO_LP_INT, NULL, -1, 0, t4_db_full }, - { F_DBFIFO_HP_INT, NULL, -1, 0, t4_db_full }, - { F_ERR_DROPPED_DB, NULL, -1, 0, t4_db_dropped }, + { DBFIFO_LP_INT, NULL, -1, 0, t4_db_full }, + { DBFIFO_HP_INT, NULL, -1, 0, t4_db_full }, + { ERR_DROPPED_DB, NULL, -1, 0, t4_db_dropped }, { ERR_DATA_CPL_ON_HIGH_QID1 | ERR_DATA_CPL_ON_HIGH_QID0, "SGE IQID > 1023 received CPL for FL", -1, 0 }, { ERR_BAD_DB_PIDX3, "SGE DBP 3 pidx increment too large", -1, @@ -1520,7 +1520,7 @@ void t4_intr_enable(struct adapter *adapter) ERR_BAD_DB_PIDX2 | ERR_BAD_DB_PIDX1 | ERR_BAD_DB_PIDX0 | ERR_ING_CTXT_PRIO | ERR_EGR_CTXT_PRIO | INGRESS_SIZE_ERR | - F_DBFIFO_HP_INT | F_DBFIFO_LP_INT | + DBFIFO_HP_INT | DBFIFO_LP_INT | EGRESS_SIZE_ERR); t4_write_reg(adapter, MYPF_REG(PL_PF_INT_ENABLE), PF_INTR_MASK); t4_set_reg_field(adapter, PL_INT_MAP0, 0, 1 << pf); @@ -2033,8 +2033,8 @@ int t4_mem_win_read_len(struct adapter *adap, u32 addr, __be32 *data, int len) if ((addr & 3) || (len + off) > MEMWIN0_APERTURE) return -EINVAL; - t4_write_reg(adap, A_PCIE_MEM_ACCESS_OFFSET, addr & ~15); - t4_read_reg(adap, A_PCIE_MEM_ACCESS_OFFSET); + t4_write_reg(adap, PCIE_MEM_ACCESS_OFFSET, addr & ~15); + t4_read_reg(adap, PCIE_MEM_ACCESS_OFFSET); for (i = 0; i < len; i += 4) *data++ = t4_read_reg(adap, (MEMWIN0_BASE + off + i)); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 111fc323f155..8e814bc46822 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -190,58 +190,30 @@ #define SGE_DEBUG_DATA_LOW 0x10d4 #define SGE_INGRESS_QUEUES_PER_PAGE_PF 0x10f4 -#define S_LP_INT_THRESH 12 -#define V_LP_INT_THRESH(x) ((x) << S_LP_INT_THRESH) #define S_HP_INT_THRESH 28 +#define M_HP_INT_THRESH 0xfU #define V_HP_INT_THRESH(x) ((x) << S_HP_INT_THRESH) +#define M_HP_COUNT 0x7ffU +#define S_HP_COUNT 16 +#define G_HP_COUNT(x) (((x) >> S_HP_COUNT) & M_HP_COUNT) +#define S_LP_INT_THRESH 12 +#define M_LP_INT_THRESH 0xfU +#define V_LP_INT_THRESH(x) ((x) << S_LP_INT_THRESH) +#define M_LP_COUNT 0x7ffU +#define S_LP_COUNT 0 +#define G_LP_COUNT(x) (((x) >> S_LP_COUNT) & M_LP_COUNT) #define A_SGE_DBFIFO_STATUS 0x10a4 #define S_ENABLE_DROP 13 #define V_ENABLE_DROP(x) ((x) << S_ENABLE_DROP) #define F_ENABLE_DROP V_ENABLE_DROP(1U) -#define A_SGE_DOORBELL_CONTROL 0x10a8 - -#define A_SGE_CTXT_CMD 0x11fc -#define A_SGE_DBQ_CTXT_BADDR 0x1084 - -#define A_SGE_PF_KDOORBELL 0x0 - -#define S_QID 15 -#define V_QID(x) ((x) << S_QID) - -#define S_PIDX 0 -#define V_PIDX(x) ((x) << S_PIDX) - -#define M_LP_COUNT 0x7ffU -#define S_LP_COUNT 0 -#define G_LP_COUNT(x) (((x) >> S_LP_COUNT) & M_LP_COUNT) - -#define M_HP_COUNT 0x7ffU -#define S_HP_COUNT 16 -#define G_HP_COUNT(x) (((x) >> S_HP_COUNT) & M_HP_COUNT) - -#define A_SGE_INT_ENABLE3 0x1040 - -#define S_DBFIFO_HP_INT 8 -#define V_DBFIFO_HP_INT(x) ((x) << S_DBFIFO_HP_INT) -#define F_DBFIFO_HP_INT V_DBFIFO_HP_INT(1U) - -#define S_DBFIFO_LP_INT 7 -#define V_DBFIFO_LP_INT(x) ((x) << S_DBFIFO_LP_INT) -#define F_DBFIFO_LP_INT V_DBFIFO_LP_INT(1U) - #define S_DROPPED_DB 0 #define V_DROPPED_DB(x) ((x) << S_DROPPED_DB) #define F_DROPPED_DB V_DROPPED_DB(1U) +#define A_SGE_DOORBELL_CONTROL 0x10a8 -#define S_ERR_DROPPED_DB 18 -#define V_ERR_DROPPED_DB(x) ((x) << S_ERR_DROPPED_DB) -#define F_ERR_DROPPED_DB V_ERR_DROPPED_DB(1U) - -#define A_PCIE_MEM_ACCESS_OFFSET 0x306c - -#define M_HP_INT_THRESH 0xfU -#define M_LP_INT_THRESH 0xfU +#define A_SGE_CTXT_CMD 0x11fc +#define A_SGE_DBQ_CTXT_BADDR 0x1084 #define PCIE_PF_CLI 0x44 #define PCIE_INT_CAUSE 0x3004 -- cgit v1.2.3 From 7933aa5c75b880aad6fc26f2df1e3ee6c14f166d Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Tue, 4 Sep 2012 21:06:55 +0000 Subject: bnx2x: use list_move_tail instead of list_del/list_add_tail Using list_move_tail() instead of list_del() + list_add_tail(). spatch with a semantic match is used to found this problem. (http://coccinelle.lip6.fr/) Signed-off-by: Wei Yongjun Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 62f754bd0dfe..5a5fbf57c4b4 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -229,8 +229,7 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp, */ list_add_tail(&spacer.link, &o->pending_comp); mb(); - list_del(&elem->link); - list_add_tail(&elem->link, &o->pending_comp); + list_move_tail(&elem->link, &o->pending_comp); list_del(&spacer.link); } else break; -- cgit v1.2.3 From d6b6d987787876fd381bfeda310c6682d425c0a2 Mon Sep 17 00:00:00 2001 From: Sathya Perla Date: Wed, 5 Sep 2012 01:56:48 +0000 Subject: be2net: use PCIe AER capability This patch allows code to handle the PCIe AER capability. The PCI callbacks for error handling/reset/recovery already exist in be2net and have been tested with EEH/ppc. This patch has been tested using the aer-inject tool. Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 111dc8813f68..84379f4fe837 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -20,6 +20,7 @@ #include "be.h" #include "be_cmds.h" #include +#include MODULE_VERSION(DRV_VER); MODULE_DEVICE_TABLE(pci, be_dev_ids); @@ -3551,6 +3552,8 @@ static void __devexit be_remove(struct pci_dev *pdev) be_ctrl_cleanup(adapter); + pci_disable_pcie_error_reporting(pdev); + pci_set_drvdata(pdev, NULL); pci_release_regions(pdev); pci_disable_device(pdev); @@ -3846,6 +3849,10 @@ static int __devinit be_probe(struct pci_dev *pdev, } } + status = pci_enable_pcie_error_reporting(pdev); + if (status) + dev_err(&pdev->dev, "Could not use PCIe error reporting\n"); + status = be_ctrl_init(adapter); if (status) goto free_netdev; @@ -4068,6 +4075,7 @@ static pci_ers_result_t be_eeh_reset(struct pci_dev *pdev) if (status) return PCI_ERS_RESULT_DISCONNECT; + pci_cleanup_aer_uncorrect_error_status(pdev); return PCI_ERS_RESULT_RECOVERED; } -- cgit v1.2.3 From 79d68b370074044d7a9dd789ee103ffe5ef00bda Mon Sep 17 00:00:00 2001 From: Stuart Hodgson Date: Mon, 16 Jul 2012 17:08:33 +0100 Subject: sfc: Add explicit RX queue flag to channel The PTP channel will have its own RX queue even though it's not a regular traffic channel. Original work by Ben Hutchings Signed-off-by: Stuart Hodgson Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 8 +++++++- drivers/net/ethernet/sfc/net_driver.h | 5 ++++- drivers/net/ethernet/sfc/rx.c | 7 +++++-- 3 files changed, 16 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index a606db43c5ba..342a1f31e5b8 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1451,10 +1451,16 @@ static void efx_set_channels(struct efx_nic *efx) efx->tx_channel_offset = separate_tx_channels ? efx->n_channels - efx->n_tx_channels : 0; - /* We need to adjust the TX queue numbers if we have separate + /* We need to mark which channels really have RX and TX + * queues, and adjust the TX queue numbers if we have separate * RX-only and TX-only channels. */ efx_for_each_channel(channel, efx) { + if (channel->channel < efx->n_rx_channels) + channel->rx_queue.core_index = channel->channel; + else + channel->rx_queue.core_index = -1; + efx_for_each_channel_tx_queue(tx_queue, channel) tx_queue->queue -= (efx->tx_channel_offset * EFX_TXQ_TYPES); diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 7ab1232494ef..24a78a35bddb 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -242,6 +242,8 @@ struct efx_rx_page_state { /** * struct efx_rx_queue - An Efx RX queue * @efx: The associated Efx NIC + * @core_index: Index of network core RX queue. Will be >= 0 iff this + * is associated with a real RX queue. * @buffer: The software buffer ring * @rxd: The hardware descriptor ring * @ptr_mask: The size of the ring minus 1. @@ -263,6 +265,7 @@ struct efx_rx_page_state { */ struct efx_rx_queue { struct efx_nic *efx; + int core_index; struct efx_rx_buffer *buffer; struct efx_special_buffer rxd; unsigned int ptr_mask; @@ -1047,7 +1050,7 @@ static inline bool efx_tx_queue_used(struct efx_tx_queue *tx_queue) static inline bool efx_channel_has_rx_queue(struct efx_channel *channel) { - return channel->channel < channel->efx->n_rx_channels; + return channel->rx_queue.core_index >= 0; } static inline struct efx_rx_queue * diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 719319b89d7a..e997f83f14f5 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -479,7 +479,7 @@ static void efx_rx_packet_gro(struct efx_channel *channel, skb->ip_summed = ((rx_buf->flags & EFX_RX_PKT_CSUMMED) ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE); - skb_record_rx_queue(skb, channel->channel); + skb_record_rx_queue(skb, channel->rx_queue.core_index); gro_result = napi_gro_frags(napi); } else { @@ -571,6 +571,9 @@ static void efx_rx_deliver(struct efx_channel *channel, /* Set the SKB flags */ skb_checksum_none_assert(skb); + /* Record the rx_queue */ + skb_record_rx_queue(skb, channel->rx_queue.core_index); + /* Pass the packet up */ netif_receive_skb(skb); @@ -608,7 +611,7 @@ void __efx_rx_packet(struct efx_channel *channel, struct efx_rx_buffer *rx_buf) * at the ethernet header */ skb->protocol = eth_type_trans(skb, efx->net_dev); - skb_record_rx_queue(skb, channel->channel); + skb_record_rx_queue(skb, channel->rx_queue.core_index); } if (unlikely(!(efx->net_dev->features & NETIF_F_RXCSUM))) -- cgit v1.2.3 From c31e5f9f97fba32103c8bdd286eee8e3aefbee31 Mon Sep 17 00:00:00 2001 From: Stuart Hodgson Date: Wed, 18 Jul 2012 09:52:11 +0100 Subject: sfc: Add channel specific receive_skb handler and post_remove callback Allows an extra channel to override the standard receive_skb handler and also for extra non generic operations to be performed on remove. Also set default rx strategy so only skbs can be delivered to the PTP receive function. Signed-off-by: Stuart Hodgson Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/efx.c | 6 ++++++ drivers/net/ethernet/sfc/efx.h | 1 + drivers/net/ethernet/sfc/net_driver.h | 3 +++ drivers/net/ethernet/sfc/rx.c | 13 +++++++++++-- 4 files changed, 21 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 342a1f31e5b8..8b79a6413fe4 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -734,6 +734,7 @@ static void efx_remove_channel(struct efx_channel *channel) efx_for_each_possible_channel_tx_queue(tx_queue, channel) efx_remove_tx_queue(tx_queue); efx_remove_eventq(channel); + channel->type->post_remove(channel); } static void efx_remove_channels(struct efx_nic *efx) @@ -852,6 +853,7 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue) static const struct efx_channel_type efx_default_channel_type = { .pre_probe = efx_channel_dummy_op_int, + .post_remove = efx_channel_dummy_op_void, .get_name = efx_get_channel_name, .copy = efx_copy_channel, .keep_eventq = false, @@ -862,6 +864,10 @@ int efx_channel_dummy_op_int(struct efx_channel *channel) return 0; } +void efx_channel_dummy_op_void(struct efx_channel *channel) +{ +} + /************************************************************************** * * Port handling diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index 70755c97251a..f11170bc48bf 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -102,6 +102,7 @@ static inline void efx_filter_rfs_expire(struct efx_channel *channel) {} /* Channels */ extern int efx_channel_dummy_op_int(struct efx_channel *channel); +extern void efx_channel_dummy_op_void(struct efx_channel *channel); extern void efx_process_channel_now(struct efx_channel *channel); extern int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries); diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 24a78a35bddb..0f0926e68963 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -393,14 +393,17 @@ struct efx_channel { * @get_name: Generate the channel's name (used for its IRQ handler) * @copy: Copy the channel state prior to reallocation. May be %NULL if * reallocation is not supported. + * @receive_skb: Handle an skb ready to be passed to netif_receive_skb() * @keep_eventq: Flag for whether event queue should be kept initialised * while the device is stopped */ struct efx_channel_type { void (*handle_no_channel)(struct efx_nic *); int (*pre_probe)(struct efx_channel *); + void (*post_remove)(struct efx_channel *); void (*get_name)(struct efx_channel *, char *buf, size_t len); struct efx_channel *(*copy)(const struct efx_channel *); + void (*receive_skb)(struct efx_channel *, struct sk_buff *); bool keep_eventq; }; diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index e997f83f14f5..9e0ad1b75c33 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -575,7 +575,10 @@ static void efx_rx_deliver(struct efx_channel *channel, skb_record_rx_queue(skb, channel->rx_queue.core_index); /* Pass the packet up */ - netif_receive_skb(skb); + if (channel->type->receive_skb) + channel->type->receive_skb(channel, skb); + else + netif_receive_skb(skb); /* Update allocation strategy method */ channel->rx_alloc_level += RX_ALLOC_FACTOR_SKB; @@ -617,7 +620,8 @@ void __efx_rx_packet(struct efx_channel *channel, struct efx_rx_buffer *rx_buf) if (unlikely(!(efx->net_dev->features & NETIF_F_RXCSUM))) rx_buf->flags &= ~EFX_RX_PKT_CSUMMED; - if (likely(rx_buf->flags & (EFX_RX_BUF_PAGE | EFX_RX_PKT_CSUMMED))) + if (likely(rx_buf->flags & (EFX_RX_BUF_PAGE | EFX_RX_PKT_CSUMMED)) && + !channel->type->receive_skb) efx_rx_packet_gro(channel, rx_buf, eh); else efx_rx_deliver(channel, rx_buf); @@ -627,6 +631,11 @@ void efx_rx_strategy(struct efx_channel *channel) { enum efx_rx_alloc_method method = rx_alloc_method; + if (channel->type->receive_skb) { + channel->rx_alloc_push_pages = false; + return; + } + /* Only makes sense to use page based allocation if GRO is enabled */ if (!(channel->efx->net_dev->features & NETIF_F_GRO)) { method = RX_ALLOC_METHOD_SKB; -- cgit v1.2.3 From c3cba721f1b761ca96f6fe437dec738db1069909 Mon Sep 17 00:00:00 2001 From: Stuart Hodgson Date: Mon, 16 Jul 2012 17:40:47 +0100 Subject: sfc: Allow efx_mcdi_rpc to be called in two parts For NIC/System time synchonisation efx_mcdi_rpc needs to be split in efx_mcdi_rpc_start and efx_mcdi_rpc_finish operations. Signed-off-by: Stuart Hodgson Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/mcdi.c | 21 ++++++++++++++++++--- drivers/net/ethernet/sfc/mcdi.h | 6 ++++++ 2 files changed, 24 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index fc5e7bbcbc9e..2707e86def9e 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -320,14 +320,20 @@ static void efx_mcdi_ev_cpl(struct efx_nic *efx, unsigned int seqno, efx_mcdi_complete(mcdi); } -/* Issue the given command by writing the data into the shared memory PDU, - * ring the doorbell and wait for completion. Copyout the result. */ int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const u8 *inbuf, size_t inlen, u8 *outbuf, size_t outlen, size_t *outlen_actual) +{ + efx_mcdi_rpc_start(efx, cmd, inbuf, inlen); + return efx_mcdi_rpc_finish(efx, cmd, inlen, + outbuf, outlen, outlen_actual); +} + +void efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, const u8 *inbuf, + size_t inlen) { struct efx_mcdi_iface *mcdi = efx_mcdi(efx); - int rc; + BUG_ON(efx_nic_rev(efx) < EFX_REV_SIENA_A0); efx_mcdi_acquire(mcdi); @@ -338,6 +344,15 @@ int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, spin_unlock_bh(&mcdi->iface_lock); efx_mcdi_copyin(efx, cmd, inbuf, inlen); +} + +int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, + u8 *outbuf, size_t outlen, size_t *outlen_actual) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + int rc; + + BUG_ON(efx_nic_rev(efx) < EFX_REV_SIENA_A0); if (mcdi->mode == MCDI_MODE_POLL) rc = efx_mcdi_poll(efx); diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index 0bdf3e331832..dc25caaa3983 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -71,6 +71,12 @@ extern int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const u8 *inbuf, size_t inlen, u8 *outbuf, size_t outlen, size_t *outlen_actual); +extern void efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, + const u8 *inbuf, size_t inlen); +extern int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, + u8 *outbuf, size_t outlen, + size_t *outlen_actual); + extern int efx_mcdi_poll_reboot(struct efx_nic *efx); extern void efx_mcdi_mode_poll(struct efx_nic *efx); extern void efx_mcdi_mode_event(struct efx_nic *efx); -- cgit v1.2.3 From 3646f0e5c97703cecfd96cdabb085e78d9b7f680 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 7 Sep 2012 09:33:15 -0700 Subject: netdev: make pci_error_handlers const Signed-off-by: Stephen Hemminger Signed-off-by: Bjorn Helgaas --- drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 2 +- drivers/net/ethernet/atheros/atl1e/atl1e_main.c | 2 +- drivers/net/ethernet/broadcom/bnx2.c | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +- drivers/net/ethernet/broadcom/tg3.c | 2 +- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 2 +- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 2 +- drivers/net/ethernet/emulex/benet/be_main.c | 2 +- drivers/net/ethernet/intel/e100.c | 2 +- drivers/net/ethernet/intel/e1000/e1000_main.c | 2 +- drivers/net/ethernet/intel/e1000e/netdev.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/igbvf/netdev.c | 2 +- drivers/net/ethernet/intel/ixgb/ixgb_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +- drivers/net/ethernet/mellanox/mlx4/main.c | 2 +- drivers/net/ethernet/neterion/s2io.c | 2 +- drivers/net/ethernet/neterion/vxge/vxge-main.c | 2 +- drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 2 +- drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c | 2 +- drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 2 +- drivers/net/ethernet/qlogic/qlge/qlge_main.c | 2 +- 23 files changed, 23 insertions(+), 23 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 1bf5bbfe778e..64c8c2eb05b5 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2685,7 +2685,7 @@ static void atl1c_io_resume(struct pci_dev *pdev) netif_device_attach(netdev); } -static struct pci_error_handlers atl1c_err_handler = { +static const struct pci_error_handlers atl1c_err_handler = { .error_detected = atl1c_io_error_detected, .slot_reset = atl1c_io_slot_reset, .resume = atl1c_io_resume, diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index a98acc8a956f..e213da29e73d 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -2489,7 +2489,7 @@ static void atl1e_io_resume(struct pci_dev *pdev) netif_device_attach(netdev); } -static struct pci_error_handlers atl1e_err_handler = { +static const struct pci_error_handlers atl1e_err_handler = { .error_detected = atl1e_io_error_detected, .slot_reset = atl1e_io_slot_reset, .resume = atl1e_io_resume, diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 79cebd8525ce..a0e8399793b6 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -8742,7 +8742,7 @@ static void bnx2_io_resume(struct pci_dev *pdev) rtnl_unlock(); } -static struct pci_error_handlers bnx2_err_handler = { +static const struct pci_error_handlers bnx2_err_handler = { .error_detected = bnx2_io_error_detected, .slot_reset = bnx2_io_slot_reset, .resume = bnx2_io_resume, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index dd451c3dd83d..81e377408a4e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12171,7 +12171,7 @@ static void bnx2x_io_resume(struct pci_dev *pdev) rtnl_unlock(); } -static struct pci_error_handlers bnx2x_err_handler = { +static const struct pci_error_handlers bnx2x_err_handler = { .error_detected = bnx2x_io_error_detected, .slot_reset = bnx2x_io_slot_reset, .resume = bnx2x_io_resume, diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index bf906c51d82a..5639b5c85c54 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -16397,7 +16397,7 @@ done: rtnl_unlock(); } -static struct pci_error_handlers tg3_err_handler = { +static const struct pci_error_handlers tg3_err_handler = { .error_detected = tg3_io_error_detected, .slot_reset = tg3_io_slot_reset, .resume = tg3_io_resume diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 6505070abcfa..875bbb999aa2 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -3036,7 +3036,7 @@ static void t3_io_resume(struct pci_dev *pdev) t3_resume_ports(adapter); } -static struct pci_error_handlers t3_err_handler = { +static const struct pci_error_handlers t3_err_handler = { .error_detected = t3_io_error_detected, .slot_reset = t3_io_slot_reset, .resume = t3_io_resume, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 5ed49af23d6a..05bdbbbf145c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3453,7 +3453,7 @@ static void eeh_resume(struct pci_dev *pdev) rtnl_unlock(); } -static struct pci_error_handlers cxgb4_eeh = { +static const struct pci_error_handlers cxgb4_eeh = { .error_detected = eeh_err_detected, .slot_reset = eeh_slot_reset, .resume = eeh_resume, diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index c60de89b6669..a00295528281 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4104,7 +4104,7 @@ err: dev_err(&adapter->pdev->dev, "EEH resume failed\n"); } -static struct pci_error_handlers be_eeh_handlers = { +static const struct pci_error_handlers be_eeh_handlers = { .error_detected = be_eeh_err_detected, .slot_reset = be_eeh_reset, .resume = be_eeh_resume, diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 535f94fac4a1..29ce9bd27f94 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -3157,7 +3157,7 @@ static void e100_io_resume(struct pci_dev *pdev) } } -static struct pci_error_handlers e100_err_handler = { +static const struct pci_error_handlers e100_err_handler = { .error_detected = e100_io_error_detected, .slot_reset = e100_io_slot_reset, .resume = e100_io_resume, diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 3bfbb8df8989..524cfb4cac61 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -192,7 +192,7 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev); static void e1000_io_resume(struct pci_dev *pdev); -static struct pci_error_handlers e1000_err_handler = { +static const struct pci_error_handlers e1000_err_handler = { .error_detected = e1000_io_error_detected, .slot_reset = e1000_io_slot_reset, .resume = e1000_io_resume, diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 95b245310f17..1c650ecae88d 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6472,7 +6472,7 @@ static void __devexit e1000_remove(struct pci_dev *pdev) } /* PCI Error Recovery (ERS) */ -static struct pci_error_handlers e1000_err_handler = { +static const struct pci_error_handlers e1000_err_handler = { .error_detected = e1000_io_error_detected, .slot_reset = e1000_io_slot_reset, .resume = e1000_io_resume, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b7c2d5050572..25270648517b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -217,7 +217,7 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *, static pci_ers_result_t igb_io_slot_reset(struct pci_dev *); static void igb_io_resume(struct pci_dev *); -static struct pci_error_handlers igb_err_handler = { +static const struct pci_error_handlers igb_err_handler = { .error_detected = igb_io_error_detected, .slot_reset = igb_io_slot_reset, .resume = igb_io_resume, diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 0696abfe9944..0ac11f527a84 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2833,7 +2833,7 @@ static void __devexit igbvf_remove(struct pci_dev *pdev) } /* PCI Error Recovery (ERS) */ -static struct pci_error_handlers igbvf_err_handler = { +static const struct pci_error_handlers igbvf_err_handler = { .error_detected = igbvf_io_error_detected, .slot_reset = igbvf_io_slot_reset, .resume = igbvf_io_resume, diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index d05fc95befc5..d99a2d51b948 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -115,7 +115,7 @@ static pci_ers_result_t ixgb_io_error_detected (struct pci_dev *pdev, static pci_ers_result_t ixgb_io_slot_reset (struct pci_dev *pdev); static void ixgb_io_resume (struct pci_dev *pdev); -static struct pci_error_handlers ixgb_err_handler = { +static const struct pci_error_handlers ixgb_err_handler = { .error_detected = ixgb_io_error_detected, .slot_reset = ixgb_io_slot_reset, .resume = ixgb_io_resume, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 4326f74f7137..ade4d81a3177 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7677,7 +7677,7 @@ static void ixgbe_io_resume(struct pci_dev *pdev) netif_device_attach(netdev); } -static struct pci_error_handlers ixgbe_err_handler = { +static const struct pci_error_handlers ixgbe_err_handler = { .error_detected = ixgbe_io_error_detected, .slot_reset = ixgbe_io_slot_reset, .resume = ixgbe_io_resume, diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 60ef64587412..6647383c4ddc 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3256,7 +3256,7 @@ static void ixgbevf_io_resume(struct pci_dev *pdev) } /* PCI Error Recovery (ERS) */ -static struct pci_error_handlers ixgbevf_err_handler = { +static const struct pci_error_handlers ixgbevf_err_handler = { .error_detected = ixgbevf_io_error_detected, .slot_reset = ixgbevf_io_slot_reset, .resume = ixgbevf_io_resume, diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 48d0e90194cb..d89e89b415cf 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2301,7 +2301,7 @@ static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev) return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } -static struct pci_error_handlers mlx4_err_handler = { +static const struct pci_error_handlers mlx4_err_handler = { .error_detected = mlx4_pci_err_detected, .slot_reset = mlx4_pci_slot_reset, }; diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index d958c2299372..de50547c187d 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -484,7 +484,7 @@ static DEFINE_PCI_DEVICE_TABLE(s2io_tbl) = { MODULE_DEVICE_TABLE(pci, s2io_tbl); -static struct pci_error_handlers s2io_err_handler = { +static const struct pci_error_handlers s2io_err_handler = { .error_detected = s2io_io_error_detected, .slot_reset = s2io_io_slot_reset, .resume = s2io_io_resume, diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index de2190443510..cfa71a30dc8d 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -4799,7 +4799,7 @@ static void __devexit vxge_remove(struct pci_dev *pdev) __LINE__); } -static struct pci_error_handlers vxge_err_handler = { +static const struct pci_error_handlers vxge_err_handler = { .error_detected = vxge_io_error_detected, .slot_reset = vxge_io_slot_reset, .resume = vxge_io_resume, diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index feb85d56c750..b2a94d02a521 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -2795,7 +2795,7 @@ static const struct dev_pm_ops pch_gbe_pm_ops = { }; #endif -static struct pci_error_handlers pch_gbe_err_handler = { +static const struct pci_error_handlers pch_gbe_err_handler = { .error_detected = pch_gbe_io_error_detected, .slot_reset = pch_gbe_io_slot_reset, .resume = pch_gbe_io_resume diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 342b3a79bd0f..0fa18ae07de5 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -3336,7 +3336,7 @@ netxen_free_vlan_ip_list(struct netxen_adapter *adapter) { } #endif -static struct pci_error_handlers netxen_err_handler = { +static const struct pci_error_handlers netxen_err_handler = { .error_detected = netxen_io_error_detected, .slot_reset = netxen_io_slot_reset, .resume = netxen_io_resume, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 212c12193275..473ce134ca63 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -4522,7 +4522,7 @@ static void qlcnic_restore_indev_addr(struct net_device *dev, unsigned long event) { } #endif -static struct pci_error_handlers qlcnic_err_handler = { +static const struct pci_error_handlers qlcnic_err_handler = { .error_detected = qlcnic_io_error_detected, .slot_reset = qlcnic_io_slot_reset, .resume = qlcnic_io_resume, diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index b53a3b60b648..b262d6156816 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -4847,7 +4847,7 @@ static void qlge_io_resume(struct pci_dev *pdev) netif_device_attach(ndev); } -static struct pci_error_handlers qlge_err_handler = { +static const struct pci_error_handlers qlge_err_handler = { .error_detected = qlge_io_error_detected, .slot_reset = qlge_io_slot_reset, .resume = qlge_io_resume, -- cgit v1.2.3 From 74dd0c42093e0fd70ca7d901d18c2c01a6fd0fd3 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sat, 8 Sep 2012 06:01:01 +0000 Subject: cnic: Add functions to allocate and free UIO rings These functions are needed to free up memory when the rings are no longer needed. Reviewed-by: Eddie Wai Reviewed-by: Bhanu Prakash Gollapudi Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/cnic.c | 59 ++++++++++++++++++++++++------------ 1 file changed, 40 insertions(+), 19 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 3b4fc61f24cf..ff3589405dce 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -823,10 +823,8 @@ static void cnic_free_context(struct cnic_dev *dev) } } -static void __cnic_free_uio(struct cnic_uio_dev *udev) +static void __cnic_free_uio_rings(struct cnic_uio_dev *udev) { - uio_unregister_device(&udev->cnic_uinfo); - if (udev->l2_buf) { dma_free_coherent(&udev->pdev->dev, udev->l2_buf_size, udev->l2_buf, udev->l2_buf_map); @@ -839,6 +837,14 @@ static void __cnic_free_uio(struct cnic_uio_dev *udev) udev->l2_ring = NULL; } +} + +static void __cnic_free_uio(struct cnic_uio_dev *udev) +{ + uio_unregister_device(&udev->cnic_uinfo); + + __cnic_free_uio_rings(udev); + pci_dev_put(udev->pdev); kfree(udev); } @@ -996,6 +1002,34 @@ static int cnic_alloc_kcq(struct cnic_dev *dev, struct kcq_info *info, return 0; } +static int __cnic_alloc_uio_rings(struct cnic_uio_dev *udev, int pages) +{ + struct cnic_local *cp = udev->dev->cnic_priv; + + if (udev->l2_ring) + return 0; + + udev->l2_ring_size = pages * BCM_PAGE_SIZE; + udev->l2_ring = dma_alloc_coherent(&udev->pdev->dev, udev->l2_ring_size, + &udev->l2_ring_map, + GFP_KERNEL | __GFP_COMP); + if (!udev->l2_ring) + return -ENOMEM; + + udev->l2_buf_size = (cp->l2_rx_ring_size + 1) * cp->l2_single_buf_size; + udev->l2_buf_size = PAGE_ALIGN(udev->l2_buf_size); + udev->l2_buf = dma_alloc_coherent(&udev->pdev->dev, udev->l2_buf_size, + &udev->l2_buf_map, + GFP_KERNEL | __GFP_COMP); + if (!udev->l2_buf) { + __cnic_free_uio_rings(udev); + return -ENOMEM; + } + + return 0; + +} + static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages) { struct cnic_local *cp = dev->cnic_priv; @@ -1020,20 +1054,9 @@ static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages) udev->dev = dev; udev->pdev = dev->pcidev; - udev->l2_ring_size = pages * BCM_PAGE_SIZE; - udev->l2_ring = dma_alloc_coherent(&udev->pdev->dev, udev->l2_ring_size, - &udev->l2_ring_map, - GFP_KERNEL | __GFP_COMP); - if (!udev->l2_ring) - goto err_udev; - udev->l2_buf_size = (cp->l2_rx_ring_size + 1) * cp->l2_single_buf_size; - udev->l2_buf_size = PAGE_ALIGN(udev->l2_buf_size); - udev->l2_buf = dma_alloc_coherent(&udev->pdev->dev, udev->l2_buf_size, - &udev->l2_buf_map, - GFP_KERNEL | __GFP_COMP); - if (!udev->l2_buf) - goto err_dma; + if (__cnic_alloc_uio_rings(udev, pages)) + goto err_udev; write_lock(&cnic_dev_lock); list_add(&udev->list, &cnic_udev_list); @@ -1044,9 +1067,7 @@ static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages) cp->udev = udev; return 0; - err_dma: - dma_free_coherent(&udev->pdev->dev, udev->l2_ring_size, - udev->l2_ring, udev->l2_ring_map); + err_udev: kfree(udev); return -ENOMEM; -- cgit v1.2.3 From f81b0ac475f617c93aeb372140b20cae267294c3 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sat, 8 Sep 2012 06:01:02 +0000 Subject: cnic: Free UIO rings when the device is closed. This will free up unneeded memory. Reviewed-by: Eddie Wai Reviewed-by: Bhanu Prakash Gollapudi Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/cnic.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index ff3589405dce..38be4d91783b 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -868,6 +868,8 @@ static void cnic_free_resc(struct cnic_dev *dev) if (udev) { udev->dev = NULL; cp->udev = NULL; + if (udev->uio_dev == -1) + __cnic_free_uio_rings(udev); } cnic_free_context(dev); @@ -1039,6 +1041,11 @@ static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages) list_for_each_entry(udev, &cnic_udev_list, list) { if (udev->pdev == dev->pcidev) { udev->dev = dev; + if (__cnic_alloc_uio_rings(udev, pages)) { + udev->dev = NULL; + read_unlock(&cnic_dev_lock); + return -ENOMEM; + } cp->udev = udev; read_unlock(&cnic_dev_lock); return 0; -- cgit v1.2.3 From 8cc0e028eda5bc07a4b816411448065b6892e383 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sat, 8 Sep 2012 06:01:03 +0000 Subject: cnic: Add function pointers to arm IRQ for different devices. This will make it easier to exit IRQ loop and re-arm IRQ on devices that don't support FCoE. Reviewed-by: Eddie Wai Reviewed-by: Bhanu Prakash Gollapudi Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/cnic.c | 26 ++++++++++++++++++++++---- drivers/net/ethernet/broadcom/cnic.h | 1 + 2 files changed, 23 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 38be4d91783b..ac08b8ec8a24 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -3078,6 +3078,22 @@ static void cnic_ack_bnx2x_e2_msix(struct cnic_dev *dev) IGU_INT_DISABLE, 0); } +static void cnic_arm_bnx2x_msix(struct cnic_dev *dev, u32 idx) +{ + struct cnic_local *cp = dev->cnic_priv; + + cnic_ack_bnx2x_int(dev, cp->bnx2x_igu_sb_id, CSTORM_ID, idx, + IGU_INT_ENABLE, 1); +} + +static void cnic_arm_bnx2x_e2_msix(struct cnic_dev *dev, u32 idx) +{ + struct cnic_local *cp = dev->cnic_priv; + + cnic_ack_igu_sb(dev, cp->bnx2x_igu_sb_id, IGU_SEG_ACCESS_DEF, idx, + IGU_INT_ENABLE, 1); +} + static u32 cnic_service_bnx2x_kcq(struct cnic_dev *dev, struct kcq_info *info) { u32 last_status = *info->status_idx_ptr; @@ -3115,8 +3131,7 @@ static void cnic_service_bnx2x_bh(unsigned long data) cp->kcq1.sw_prod_idx + MAX_KCQ_IDX); if (!BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) { - cnic_ack_bnx2x_int(dev, cp->bnx2x_igu_sb_id, USTORM_ID, - status_idx, IGU_INT_ENABLE, 1); + cp->arm_int(dev, status_idx); break; } @@ -5520,10 +5535,13 @@ static struct cnic_dev *init_bnx2x_cnic(struct net_device *dev) cp->stop_cm = cnic_cm_stop_bnx2x_hw; cp->enable_int = cnic_enable_bnx2x_int; cp->disable_int_sync = cnic_disable_bnx2x_int_sync; - if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) + if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) { cp->ack_int = cnic_ack_bnx2x_e2_msix; - else + cp->arm_int = cnic_arm_bnx2x_e2_msix; + } else { cp->ack_int = cnic_ack_bnx2x_msix; + cp->arm_int = cnic_arm_bnx2x_msix; + } cp->close_conn = cnic_close_bnx2x_conn; return cdev; } diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h index 30328097f516..9643e3a81a7d 100644 --- a/drivers/net/ethernet/broadcom/cnic.h +++ b/drivers/net/ethernet/broadcom/cnic.h @@ -334,6 +334,7 @@ struct cnic_local { void (*enable_int)(struct cnic_dev *); void (*disable_int_sync)(struct cnic_dev *); void (*ack_int)(struct cnic_dev *); + void (*arm_int)(struct cnic_dev *, u32 index); void (*close_conn)(struct cnic_sock *, u32 opcode); }; -- cgit v1.2.3 From 51a8f54d13f1b2e91da214ff1e619628bd68fd27 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sat, 8 Sep 2012 06:01:04 +0000 Subject: cnic: Allocate kcq resource only on devices that support FCoE. To save memory and to exit IRQ loop quicker on devices that don't support FCoE. Reviewed-by: Eddie Wai Reviewed-by: Bhanu Prakash Gollapudi Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/cnic.c | 7 +++---- drivers/net/ethernet/broadcom/cnic.h | 4 ++++ 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index ac08b8ec8a24..c2233143402a 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -1288,7 +1288,7 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev) if (ret) goto error; - if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) { + if (CNIC_SUPPORTS_FCOE(cp)) { ret = cnic_alloc_kcq(dev, &cp->kcq2, true); if (ret) goto error; @@ -3130,7 +3130,7 @@ static void cnic_service_bnx2x_bh(unsigned long data) CNIC_WR16(dev, cp->kcq1.io_addr, cp->kcq1.sw_prod_idx + MAX_KCQ_IDX); - if (!BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) { + if (cp->ethdev->drv_state & CNIC_DRV_STATE_NO_FCOE) { cp->arm_int(dev, status_idx); break; } @@ -5516,8 +5516,7 @@ static struct cnic_dev *init_bnx2x_cnic(struct net_device *dev) if (!(ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI)) cdev->max_iscsi_conn = ethdev->max_iscsi_conn; - if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id) && - !(ethdev->drv_state & CNIC_DRV_STATE_NO_FCOE)) + if (CNIC_SUPPORTS_FCOE(cp)) cdev->max_fcoe_conn = ethdev->max_fcoe_conn; if (cdev->max_fcoe_conn > BNX2X_FCOE_NUM_CONNECTIONS) diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h index 9643e3a81a7d..148604c3fa0c 100644 --- a/drivers/net/ethernet/broadcom/cnic.h +++ b/drivers/net/ethernet/broadcom/cnic.h @@ -475,6 +475,10 @@ struct bnx2x_bd_chain_next { MAX_STAT_COUNTER_ID_E1)) #endif +#define CNIC_SUPPORTS_FCOE(cp) \ + (BNX2X_CHIP_IS_E2_PLUS((cp)->chip_id) && \ + !((cp)->ethdev->drv_state & CNIC_DRV_STATE_NO_FCOE)) + #define CNIC_RAMROD_TMO (HZ / 4) #endif -- cgit v1.2.3 From 82346a7b6a14793a48cc7a0692a007daf0843f99 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sat, 8 Sep 2012 06:01:05 +0000 Subject: cnic: Allocate UIO resources only on devices that support iSCSI. Update version to 2.5.13. Reviewed-by: Eddie Wai Reviewed-by: Bhanu Prakash Gollapudi Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/cnic.c | 5 ++++- drivers/net/ethernet/broadcom/cnic_if.h | 4 ++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index c2233143402a..2107d79d69b3 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -1303,6 +1303,9 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev) if (ret) goto error; + if (cp->ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI) + return 0; + cp->bnx2x_def_status_blk = cp->ethdev->irq_arr[1].status_blk; cp->l2_rx_ring_size = 15; @@ -5351,7 +5354,7 @@ static void cnic_stop_hw(struct cnic_dev *dev) /* Need to wait for the ring shutdown event to complete * before clearing the CNIC_UP flag. */ - while (cp->udev->uio_dev != -1 && i < 15) { + while (cp->udev && cp->udev->uio_dev != -1 && i < 15) { msleep(100); i++; } diff --git a/drivers/net/ethernet/broadcom/cnic_if.h b/drivers/net/ethernet/broadcom/cnic_if.h index 5cb88881bba1..2e92c348083e 100644 --- a/drivers/net/ethernet/broadcom/cnic_if.h +++ b/drivers/net/ethernet/broadcom/cnic_if.h @@ -14,8 +14,8 @@ #include "bnx2x/bnx2x_mfw_req.h" -#define CNIC_MODULE_VERSION "2.5.12" -#define CNIC_MODULE_RELDATE "June 29, 2012" +#define CNIC_MODULE_VERSION "2.5.13" +#define CNIC_MODULE_RELDATE "Sep 07, 2012" #define CNIC_ULP_RDMA 0 #define CNIC_ULP_ISCSI 1 -- cgit v1.2.3 From 08e9acc25a60e845101840ce6db368dc6d77c3c1 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 10 Sep 2012 05:51:04 +0000 Subject: bnx2x: EEE status is read locally This patch aligns the EEE status with that of all other link properties, by changing the way its accessed - instead of a direct read to the shared memory, each function maintain its own copy locally. Signed-off-by: Yuval Mintz Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 4 +-- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 4 +++ drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c | 35 ++++++++++++++++++---- 3 files changed, 36 insertions(+), 7 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index c37a68d68090..5bafcd9df9e0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1647,7 +1647,7 @@ static int bnx2x_get_eee(struct net_device *dev, struct ethtool_eee *edata) return -EOPNOTSUPP; } - eee_cfg = SHMEM2_RD(bp, eee_status[BP_PORT(bp)]); + eee_cfg = bp->link_vars.eee_status; edata->supported = bnx2x_eee_to_adv((eee_cfg & SHMEM_EEE_SUPPORTED_MASK) >> @@ -1684,7 +1684,7 @@ static int bnx2x_set_eee(struct net_device *dev, struct ethtool_eee *edata) return -EOPNOTSUPP; } - eee_cfg = SHMEM2_RD(bp, eee_status[BP_PORT(bp)]); + eee_cfg = bp->link_vars.eee_status; if (!(eee_cfg & SHMEM_EEE_SUPPORTED_MASK)) { DP(BNX2X_MSG_ETHTOOL, "Board does not support EEE!\n"); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index f4beb46c4709..14afa1759378 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -4716,6 +4716,10 @@ void bnx2x_link_status_update(struct link_params *params, vars->link_status = REG_RD(bp, params->shmem_base + offsetof(struct shmem_region, port_mb[port].link_status)); + if (bnx2x_eee_has_cap(params)) + vars->eee_status = REG_RD(bp, params->shmem2_base + + offsetof(struct shmem2_region, + eee_status[params->port])); vars->phy_flags = PHY_XGXS_FLAG; bnx2x_sync_link(params, vars); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c index 332db64dd5be..ab00b352f4a9 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c @@ -39,14 +39,39 @@ static inline long bnx2x_hilo(u32 *hiref) #endif } -static u16 bnx2x_get_port_stats_dma_len(struct bnx2x *bp) +static inline u16 bnx2x_get_port_stats_dma_len(struct bnx2x *bp) { - u16 res = sizeof(struct host_port_stats) >> 2; + u16 res = 0; - /* if PFC stats are not supported by the MFW, don't DMA them */ - if (!(bp->flags & BC_SUPPORTS_PFC_STATS)) - res -= (sizeof(u32)*4) >> 2; + /* 'newest' convention - shmem2 cotains the size of the port stats */ + if (SHMEM2_HAS(bp, sizeof_port_stats)) { + u32 size = SHMEM2_RD(bp, sizeof_port_stats); + if (size) + res = size; + /* prevent newer BC from causing buffer overflow */ + if (res > sizeof(struct host_port_stats)) + res = sizeof(struct host_port_stats); + } + + /* Older convention - all BCs support the port stats' fields up until + * the 'not_used' field + */ + if (!res) { + res = offsetof(struct host_port_stats, not_used) + 4; + + /* if PFC stats are supported by the MFW, DMA them as well */ + if (bp->flags & BC_SUPPORTS_PFC_STATS) { + res += offsetof(struct host_port_stats, + pfc_frames_rx_lo) - + offsetof(struct host_port_stats, + pfc_frames_tx_hi) + 4 ; + } + } + + res >>= 2; + + WARN_ON(res > 2 * DMAE_LEN32_RD_MAX); return res; } -- cgit v1.2.3 From 34dab172f08e0456f3f8a8f6497567cf6744535e Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 10 Sep 2012 05:51:05 +0000 Subject: bnx2x: add EEE support for 4-port devices Prevent functions from disabling EEE to other functions using other ports. Signed-off-by: Yuval Mintz Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 14afa1759378..bf60c07b1ccd 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -6540,7 +6540,6 @@ static int bnx2x_update_link_down(struct link_params *params, /* Prevent LPI Generation by chip */ REG_WR(bp, MISC_REG_CPMU_LP_FW_ENABLE_P0 + (params->port << 2), 0); - REG_WR(bp, MISC_REG_CPMU_LP_DR_ENABLE, 0); REG_WR(bp, MISC_REG_CPMU_LP_MASK_ENT_P0 + (params->port << 2), 0); vars->eee_status &= ~(SHMEM_EEE_LP_ADV_STATUS_MASK | @@ -9932,7 +9931,6 @@ static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy, /* Make Certain LPI is disabled */ REG_WR(bp, MISC_REG_CPMU_LP_FW_ENABLE_P0 + (params->port << 2), 0); - REG_WR(bp, MISC_REG_CPMU_LP_DR_ENABLE, 0); /* Prevent Phy from working in EEE and advertising it */ rc = bnx2x_84833_cmd_hdlr(phy, params, -- cgit v1.2.3 From ec4010ecc26b78476452b499b7a476fb58032379 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 10 Sep 2012 05:51:06 +0000 Subject: bnx2x: EEE code refactoring In order to lay the foundation for 1G EEE support, several segments of code which are common to both 1G and 10G EEE configurations were extracted from the 10G EEE configuration flow to their own functions. E.g., bnx2x_eee_initial_config, bnx2x_eee_advertise, bnx2x_eee_disable, etc. The rest of the EEE functions were relocated and placed in a single, continuous section of the file. Signed-off-by: Yuval Mintz Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 450 +++++++++++++---------- 1 file changed, 258 insertions(+), 192 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index bf60c07b1ccd..f6178a1684d1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -1306,93 +1306,6 @@ int bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos) return 0; } -/******************************************************************/ -/* EEE section */ -/******************************************************************/ -static u8 bnx2x_eee_has_cap(struct link_params *params) -{ - struct bnx2x *bp = params->bp; - - if (REG_RD(bp, params->shmem2_base) <= - offsetof(struct shmem2_region, eee_status[params->port])) - return 0; - - return 1; -} - -static int bnx2x_eee_nvram_to_time(u32 nvram_mode, u32 *idle_timer) -{ - switch (nvram_mode) { - case PORT_FEAT_CFG_EEE_POWER_MODE_BALANCED: - *idle_timer = EEE_MODE_NVRAM_BALANCED_TIME; - break; - case PORT_FEAT_CFG_EEE_POWER_MODE_AGGRESSIVE: - *idle_timer = EEE_MODE_NVRAM_AGGRESSIVE_TIME; - break; - case PORT_FEAT_CFG_EEE_POWER_MODE_LOW_LATENCY: - *idle_timer = EEE_MODE_NVRAM_LATENCY_TIME; - break; - default: - *idle_timer = 0; - break; - } - - return 0; -} - -static int bnx2x_eee_time_to_nvram(u32 idle_timer, u32 *nvram_mode) -{ - switch (idle_timer) { - case EEE_MODE_NVRAM_BALANCED_TIME: - *nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_BALANCED; - break; - case EEE_MODE_NVRAM_AGGRESSIVE_TIME: - *nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_AGGRESSIVE; - break; - case EEE_MODE_NVRAM_LATENCY_TIME: - *nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_LOW_LATENCY; - break; - default: - *nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_DISABLED; - break; - } - - return 0; -} - -static u32 bnx2x_eee_calc_timer(struct link_params *params) -{ - u32 eee_mode, eee_idle; - struct bnx2x *bp = params->bp; - - if (params->eee_mode & EEE_MODE_OVERRIDE_NVRAM) { - if (params->eee_mode & EEE_MODE_OUTPUT_TIME) { - /* time value in eee_mode --> used directly*/ - eee_idle = params->eee_mode & EEE_MODE_TIMER_MASK; - } else { - /* hsi value in eee_mode --> time */ - if (bnx2x_eee_nvram_to_time(params->eee_mode & - EEE_MODE_NVRAM_MASK, - &eee_idle)) - return 0; - } - } else { - /* hsi values in nvram --> time*/ - eee_mode = ((REG_RD(bp, params->shmem_base + - offsetof(struct shmem_region, dev_info. - port_feature_config[params->port]. - eee_power_mode)) & - PORT_FEAT_CFG_EEE_POWER_MODE_MASK) >> - PORT_FEAT_CFG_EEE_POWER_MODE_SHIFT); - - if (bnx2x_eee_nvram_to_time(eee_mode, &eee_idle)) - return 0; - } - - return eee_idle; -} - - /******************************************************************/ /* PFC section */ /******************************************************************/ @@ -2529,16 +2442,6 @@ static void bnx2x_update_mng(struct link_params *params, u32 link_status) port_mb[params->port].link_status), link_status); } -static void bnx2x_update_mng_eee(struct link_params *params, u32 eee_status) -{ - struct bnx2x *bp = params->bp; - - if (bnx2x_eee_has_cap(params)) - REG_WR(bp, params->shmem2_base + - offsetof(struct shmem2_region, - eee_status[params->port]), eee_status); -} - static void bnx2x_update_pfc_nig(struct link_params *params, struct link_vars *vars, struct bnx2x_nig_brb_pfc_port_params *nig_params) @@ -3231,6 +3134,245 @@ static int bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy, EMAC_MDIO_STATUS_10MB); return rc; } + +/******************************************************************/ +/* EEE section */ +/******************************************************************/ +static u8 bnx2x_eee_has_cap(struct link_params *params) +{ + struct bnx2x *bp = params->bp; + + if (REG_RD(bp, params->shmem2_base) <= + offsetof(struct shmem2_region, eee_status[params->port])) + return 0; + + return 1; +} + +static int bnx2x_eee_nvram_to_time(u32 nvram_mode, u32 *idle_timer) +{ + switch (nvram_mode) { + case PORT_FEAT_CFG_EEE_POWER_MODE_BALANCED: + *idle_timer = EEE_MODE_NVRAM_BALANCED_TIME; + break; + case PORT_FEAT_CFG_EEE_POWER_MODE_AGGRESSIVE: + *idle_timer = EEE_MODE_NVRAM_AGGRESSIVE_TIME; + break; + case PORT_FEAT_CFG_EEE_POWER_MODE_LOW_LATENCY: + *idle_timer = EEE_MODE_NVRAM_LATENCY_TIME; + break; + default: + *idle_timer = 0; + break; + } + + return 0; +} + +static int bnx2x_eee_time_to_nvram(u32 idle_timer, u32 *nvram_mode) +{ + switch (idle_timer) { + case EEE_MODE_NVRAM_BALANCED_TIME: + *nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_BALANCED; + break; + case EEE_MODE_NVRAM_AGGRESSIVE_TIME: + *nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_AGGRESSIVE; + break; + case EEE_MODE_NVRAM_LATENCY_TIME: + *nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_LOW_LATENCY; + break; + default: + *nvram_mode = PORT_FEAT_CFG_EEE_POWER_MODE_DISABLED; + break; + } + + return 0; +} + +static u32 bnx2x_eee_calc_timer(struct link_params *params) +{ + u32 eee_mode, eee_idle; + struct bnx2x *bp = params->bp; + + if (params->eee_mode & EEE_MODE_OVERRIDE_NVRAM) { + if (params->eee_mode & EEE_MODE_OUTPUT_TIME) { + /* time value in eee_mode --> used directly*/ + eee_idle = params->eee_mode & EEE_MODE_TIMER_MASK; + } else { + /* hsi value in eee_mode --> time */ + if (bnx2x_eee_nvram_to_time(params->eee_mode & + EEE_MODE_NVRAM_MASK, + &eee_idle)) + return 0; + } + } else { + /* hsi values in nvram --> time*/ + eee_mode = ((REG_RD(bp, params->shmem_base + + offsetof(struct shmem_region, dev_info. + port_feature_config[params->port]. + eee_power_mode)) & + PORT_FEAT_CFG_EEE_POWER_MODE_MASK) >> + PORT_FEAT_CFG_EEE_POWER_MODE_SHIFT); + + if (bnx2x_eee_nvram_to_time(eee_mode, &eee_idle)) + return 0; + } + + return eee_idle; +} + +static int bnx2x_eee_set_timers(struct link_params *params, + struct link_vars *vars) +{ + u32 eee_idle = 0, eee_mode; + struct bnx2x *bp = params->bp; + + eee_idle = bnx2x_eee_calc_timer(params); + + if (eee_idle) { + REG_WR(bp, MISC_REG_CPMU_LP_IDLE_THR_P0 + (params->port << 2), + eee_idle); + } else if ((params->eee_mode & EEE_MODE_ENABLE_LPI) && + (params->eee_mode & EEE_MODE_OVERRIDE_NVRAM) && + (params->eee_mode & EEE_MODE_OUTPUT_TIME)) { + DP(NETIF_MSG_LINK, "Error: Tx LPI is enabled with timer 0\n"); + return -EINVAL; + } + + vars->eee_status &= ~(SHMEM_EEE_TIMER_MASK | SHMEM_EEE_TIME_OUTPUT_BIT); + if (params->eee_mode & EEE_MODE_OUTPUT_TIME) { + /* eee_idle in 1u --> eee_status in 16u */ + eee_idle >>= 4; + vars->eee_status |= (eee_idle & SHMEM_EEE_TIMER_MASK) | + SHMEM_EEE_TIME_OUTPUT_BIT; + } else { + if (bnx2x_eee_time_to_nvram(eee_idle, &eee_mode)) + return -EINVAL; + vars->eee_status |= eee_mode; + } + + return 0; +} + +static int bnx2x_eee_initial_config(struct link_params *params, + struct link_vars *vars, u8 mode) +{ + vars->eee_status |= ((u32) mode) << SHMEM_EEE_SUPPORTED_SHIFT; + + /* Propogate params' bits --> vars (for migration exposure) */ + if (params->eee_mode & EEE_MODE_ENABLE_LPI) + vars->eee_status |= SHMEM_EEE_LPI_REQUESTED_BIT; + else + vars->eee_status &= ~SHMEM_EEE_LPI_REQUESTED_BIT; + + if (params->eee_mode & EEE_MODE_ADV_LPI) + vars->eee_status |= SHMEM_EEE_REQUESTED_BIT; + else + vars->eee_status &= ~SHMEM_EEE_REQUESTED_BIT; + + return bnx2x_eee_set_timers(params, vars); +} + +static int bnx2x_eee_disable(struct bnx2x_phy *phy, + struct link_params *params, + struct link_vars *vars) +{ + struct bnx2x *bp = params->bp; + + /* Make Certain LPI is disabled */ + REG_WR(bp, MISC_REG_CPMU_LP_FW_ENABLE_P0 + (params->port << 2), 0); + + bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, 0x0); + + vars->eee_status &= ~SHMEM_EEE_ADV_STATUS_MASK; + + return 0; +} + +static int bnx2x_eee_advertise(struct bnx2x_phy *phy, + struct link_params *params, + struct link_vars *vars, u8 modes) +{ + struct bnx2x *bp = params->bp; + u16 val = 0; + + /* Mask events preventing LPI generation */ + REG_WR(bp, MISC_REG_CPMU_LP_MASK_EXT_P0 + (params->port << 2), 0xfc20); + + if (modes & SHMEM_EEE_10G_ADV) { + DP(NETIF_MSG_LINK, "Advertise 10GBase-T EEE\n"); + val |= 0x8; + } + if (modes & SHMEM_EEE_1G_ADV) { + DP(NETIF_MSG_LINK, "Advertise 1GBase-T EEE\n"); + val |= 0x4; + } + + bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, val); + + vars->eee_status &= ~SHMEM_EEE_ADV_STATUS_MASK; + vars->eee_status |= (modes << SHMEM_EEE_ADV_STATUS_SHIFT); + + return 0; +} + +static void bnx2x_update_mng_eee(struct link_params *params, u32 eee_status) +{ + struct bnx2x *bp = params->bp; + + if (bnx2x_eee_has_cap(params)) + REG_WR(bp, params->shmem2_base + + offsetof(struct shmem2_region, + eee_status[params->port]), eee_status); +} + +static void bnx2x_eee_an_resolve(struct bnx2x_phy *phy, + struct link_params *params, + struct link_vars *vars) +{ + struct bnx2x *bp = params->bp; + u16 adv = 0, lp = 0; + u32 lp_adv = 0; + u8 neg = 0; + + bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, &adv); + bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_LP_EEE_ADV, &lp); + + if (lp & 0x2) { + lp_adv |= SHMEM_EEE_100M_ADV; + if (adv & 0x2) { + if (vars->line_speed == SPEED_100) + neg = 1; + DP(NETIF_MSG_LINK, "EEE negotiated - 100M\n"); + } + } + if (lp & 0x14) { + lp_adv |= SHMEM_EEE_1G_ADV; + if (adv & 0x14) { + if (vars->line_speed == SPEED_1000) + neg = 1; + DP(NETIF_MSG_LINK, "EEE negotiated - 1G\n"); + } + } + if (lp & 0x68) { + lp_adv |= SHMEM_EEE_10G_ADV; + if (adv & 0x68) { + if (vars->line_speed == SPEED_10000) + neg = 1; + DP(NETIF_MSG_LINK, "EEE negotiated - 10G\n"); + } + } + + vars->eee_status &= ~SHMEM_EEE_LP_ADV_STATUS_MASK; + vars->eee_status |= (lp_adv << SHMEM_EEE_LP_ADV_STATUS_SHIFT); + + if (neg) { + DP(NETIF_MSG_LINK, "EEE is active\n"); + vars->eee_status |= SHMEM_EEE_ACTIVE_BIT; + } + +} + /******************************************************************/ /* BSC access functions from E3 */ /******************************************************************/ @@ -3752,6 +3894,19 @@ static u8 bnx2x_ext_phy_resolve_fc(struct bnx2x_phy *phy, * init configuration, and set/clear SGMII flag. Internal * phy init is done purely in phy_init stage. */ + +static void bnx2x_warpcore_set_lpi_passthrough(struct bnx2x_phy *phy, + struct link_params *params) +{ + struct bnx2x *bp = params->bp; + + DP(NETIF_MSG_LINK, "Configure WC for LPI pass through\n"); + bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD, + MDIO_WC_REG_EEE_COMBO_CONTROL0, 0x7c); + bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD, + MDIO_WC_REG_DIGITAL4_MISC5, 0xc000); +} + static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy, struct link_params *params, struct link_vars *vars) { @@ -4011,13 +4166,7 @@ static void bnx2x_warpcore_set_10G_XFI(struct bnx2x_phy *phy, bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD, MDIO_WC_REG_DIGITAL4_MISC3, 0x8080); - /* Enable LPI pass through */ - DP(NETIF_MSG_LINK, "Configure WC for LPI pass through\n"); - bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD, - MDIO_WC_REG_EEE_COMBO_CONTROL0, - 0x7c); - bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD, - MDIO_WC_REG_DIGITAL4_MISC5, 0xc000); + bnx2x_warpcore_set_lpi_passthrough(phy, params); /* 10G XFI Full Duplex */ bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD, @@ -9886,39 +10035,6 @@ static int bnx2x_84833_hw_reset_phy(struct bnx2x_phy *phy, return 0; } -static int bnx2x_8483x_eee_timers(struct link_params *params, - struct link_vars *vars) -{ - u32 eee_idle = 0, eee_mode; - struct bnx2x *bp = params->bp; - - eee_idle = bnx2x_eee_calc_timer(params); - - if (eee_idle) { - REG_WR(bp, MISC_REG_CPMU_LP_IDLE_THR_P0 + (params->port << 2), - eee_idle); - } else if ((params->eee_mode & EEE_MODE_ENABLE_LPI) && - (params->eee_mode & EEE_MODE_OVERRIDE_NVRAM) && - (params->eee_mode & EEE_MODE_OUTPUT_TIME)) { - DP(NETIF_MSG_LINK, "Error: Tx LPI is enabled with timer 0\n"); - return -EINVAL; - } - - vars->eee_status &= ~(SHMEM_EEE_TIMER_MASK | SHMEM_EEE_TIME_OUTPUT_BIT); - if (params->eee_mode & EEE_MODE_OUTPUT_TIME) { - /* eee_idle in 1u --> eee_status in 16u */ - eee_idle >>= 4; - vars->eee_status |= (eee_idle & SHMEM_EEE_TIMER_MASK) | - SHMEM_EEE_TIME_OUTPUT_BIT; - } else { - if (bnx2x_eee_time_to_nvram(eee_idle, &eee_mode)) - return -EINVAL; - vars->eee_status |= eee_mode; - } - - return 0; -} - static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy, struct link_params *params, struct link_vars *vars) @@ -9929,9 +10045,6 @@ static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "Don't Advertise 10GBase-T EEE\n"); - /* Make Certain LPI is disabled */ - REG_WR(bp, MISC_REG_CPMU_LP_FW_ENABLE_P0 + (params->port << 2), 0); - /* Prevent Phy from working in EEE and advertising it */ rc = bnx2x_84833_cmd_hdlr(phy, params, PHY84833_CMD_SET_EEE_MODE, &cmd_args, 1); @@ -9940,10 +10053,7 @@ static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy, return rc; } - bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, 0); - vars->eee_status &= ~SHMEM_EEE_ADV_STATUS_MASK; - - return 0; + return bnx2x_eee_disable(phy, params, vars); } static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy, @@ -9954,8 +10064,6 @@ static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy, struct bnx2x *bp = params->bp; u16 cmd_args = 1; - DP(NETIF_MSG_LINK, "Advertise 10GBase-T EEE\n"); - rc = bnx2x_84833_cmd_hdlr(phy, params, PHY84833_CMD_SET_EEE_MODE, &cmd_args, 1); if (rc) { @@ -9963,15 +10071,7 @@ static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy, return rc; } - bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_EEE_ADV, 0x8); - - /* Mask events preventing LPI generation */ - REG_WR(bp, MISC_REG_CPMU_LP_MASK_EXT_P0 + (params->port << 2), 0xfc20); - - vars->eee_status &= ~SHMEM_EEE_ADV_STATUS_MASK; - vars->eee_status |= (SHMEM_EEE_10G_ADV << SHMEM_EEE_ADV_STATUS_SHIFT); - - return 0; + return bnx2x_eee_advertise(phy, params, vars, SHMEM_EEE_10G_ADV); } #define PHY84833_CONSTANT_LATENCY 1193 @@ -10105,20 +10205,7 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, /* Configure EEE support */ if ((val >= MDIO_84833_TOP_CFG_FW_EEE) && bnx2x_eee_has_cap(params)) { phy->flags |= FLAGS_EEE_10GBT; - vars->eee_status |= SHMEM_EEE_10G_ADV << - SHMEM_EEE_SUPPORTED_SHIFT; - /* Propogate params' bits --> vars (for migration exposure) */ - if (params->eee_mode & EEE_MODE_ENABLE_LPI) - vars->eee_status |= SHMEM_EEE_LPI_REQUESTED_BIT; - else - vars->eee_status &= ~SHMEM_EEE_LPI_REQUESTED_BIT; - - if (params->eee_mode & EEE_MODE_ADV_LPI) - vars->eee_status |= SHMEM_EEE_REQUESTED_BIT; - else - vars->eee_status &= ~SHMEM_EEE_REQUESTED_BIT; - - rc = bnx2x_8483x_eee_timers(params, vars); + rc = bnx2x_eee_initial_config(params, vars, SHMEM_EEE_10G_ADV); if (rc) { DP(NETIF_MSG_LINK, "Failed to configure EEE timers\n"); bnx2x_8483x_disable_eee(phy, params, vars); @@ -10276,29 +10363,8 @@ static u8 bnx2x_848xx_read_status(struct bnx2x_phy *phy, LINK_STATUS_LINK_PARTNER_10GXFD_CAPABLE; /* Determine if EEE was negotiated */ - if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) { - u32 eee_shmem = 0; - - bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, - MDIO_AN_REG_EEE_ADV, &val1); - bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, - MDIO_AN_REG_LP_EEE_ADV, &val2); - if ((val1 & val2) & 0x8) { - DP(NETIF_MSG_LINK, "EEE negotiated\n"); - vars->eee_status |= SHMEM_EEE_ACTIVE_BIT; - } - - if (val2 & 0x12) - eee_shmem |= SHMEM_EEE_100M_ADV; - if (val2 & 0x4) - eee_shmem |= SHMEM_EEE_1G_ADV; - if (val2 & 0x68) - eee_shmem |= SHMEM_EEE_10G_ADV; - - vars->eee_status &= ~SHMEM_EEE_LP_ADV_STATUS_MASK; - vars->eee_status |= (eee_shmem << - SHMEM_EEE_LP_ADV_STATUS_SHIFT); - } + if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) + bnx2x_eee_an_resolve(phy, params, vars); } return link_up; -- cgit v1.2.3 From f6b6eb696889b65dea83aa097dac94342540c16a Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 10 Sep 2012 05:51:07 +0000 Subject: bnx2x: correct & clean 10G EEE requirements Signed-off-by: Yuval Mintz Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 9 ++++----- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h | 1 - drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h | 1 + 3 files changed, 5 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index f6178a1684d1..839ddd2519d3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -10203,8 +10203,9 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, MDIO_84833_TOP_CFG_FW_REV, &val); /* Configure EEE support */ - if ((val >= MDIO_84833_TOP_CFG_FW_EEE) && bnx2x_eee_has_cap(params)) { - phy->flags |= FLAGS_EEE_10GBT; + if ((val >= MDIO_84833_TOP_CFG_FW_EEE) && + (val != MDIO_84833_TOP_CFG_FW_NO_EEE) && + bnx2x_eee_has_cap(params)) { rc = bnx2x_eee_initial_config(params, vars, SHMEM_EEE_10G_ADV); if (rc) { DP(NETIF_MSG_LINK, "Failed to configure EEE timers\n"); @@ -10224,7 +10225,6 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, return rc; } } else { - phy->flags &= ~FLAGS_EEE_10GBT; vars->eee_status &= ~SHMEM_EEE_SUPPORTED_MASK; } @@ -11619,8 +11619,7 @@ static struct bnx2x_phy phy_84833 = { .def_md_devad = 0, .flags = (FLAGS_FAN_FAILURE_DET_REQ | FLAGS_REARM_LATCH_SIGNAL | - FLAGS_TX_ERROR_CHECK | - FLAGS_EEE_10GBT), + FLAGS_TX_ERROR_CHECK), .rx_preemphasis = {0xffff, 0xffff, 0xffff, 0xffff}, .tx_preemphasis = {0xffff, 0xffff, 0xffff, 0xffff}, .mdio_ctrl = 0, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h index 51cac8130051..3967aa85fc09 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h @@ -155,7 +155,6 @@ struct bnx2x_phy { #define FLAGS_DUMMY_READ (1<<9) #define FLAGS_MDC_MDIO_WA_B0 (1<<10) #define FLAGS_TX_ERROR_CHECK (1<<12) -#define FLAGS_EEE_10GBT (1<<13) /* preemphasis values for the rx side */ u16 rx_preemphasis[4]; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index 28a0bcfe61ff..d32293fcc81c 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -6992,6 +6992,7 @@ Theotherbitsarereservedandshouldbezero*/ /* BCM84833 only */ #define MDIO_84833_TOP_CFG_FW_REV 0x400f #define MDIO_84833_TOP_CFG_FW_EEE 0x10b1 +#define MDIO_84833_TOP_CFG_FW_NO_EEE 0x1f81 #define MDIO_84833_TOP_CFG_XGPHY_STRAP1 0x401a #define MDIO_84833_SUPER_ISOLATE 0x8000 /* These are mailbox register set used by 84833. */ -- cgit v1.2.3 From 26964bb72afd0310c17750c002eebbf022db3b19 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 10 Sep 2012 05:51:08 +0000 Subject: bnx2x: use native EEE instead of auto-greeen This patch enables boards with 54618SE phys and a sufficiently new firmware to use native EEE instead of auto-greeen. Signed-off-by: Yuval Mintz Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 105 +++++++++++++---------- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h | 1 + drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h | 13 ++- 3 files changed, 73 insertions(+), 46 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 839ddd2519d3..c660afdbdf56 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -1584,6 +1584,16 @@ static void bnx2x_umac_enable(struct link_params *params, REG_WR(bp, umac_base + UMAC_REG_COMMAND_CONFIG, val); udelay(50); + /* Configure UMAC for EEE */ + if (vars->eee_status & SHMEM_EEE_ADV_STATUS_MASK) { + DP(NETIF_MSG_LINK, "configured UMAC for EEE\n"); + REG_WR(bp, umac_base + UMAC_REG_UMAC_EEE_CTRL, + UMAC_UMAC_EEE_CTRL_REG_EEE_EN); + REG_WR(bp, umac_base + UMAC_REG_EEE_WAKE_TIMER, 0x11); + } else { + REG_WR(bp, umac_base + UMAC_REG_UMAC_EEE_CTRL, 0x0); + } + /* Set MAC address for source TX Pause/PFC frames (under SW reset) */ REG_WR(bp, umac_base + UMAC_REG_MAC_ADDR0, ((params->mac_addr[2] << 24) | @@ -4263,6 +4273,8 @@ static void bnx2x_warpcore_set_sgmii_speed(struct bnx2x_phy *phy, bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD, MDIO_WC_REG_RX66_CONTROL, val16 & ~(3<<13)); + bnx2x_warpcore_set_lpi_passthrough(phy, params); + if (always_autoneg || phy->req_line_speed == SPEED_AUTO_NEG) { /* SGMII Autoneg */ bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD, @@ -10792,28 +10804,52 @@ static int bnx2x_54618se_config_init(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "Setting 10M force\n"); } - /* Check if we should turn on Auto-GrEEEn */ - bnx2x_cl22_read(bp, phy, MDIO_REG_GPHY_PHYID_LSB, &temp); - if (temp == MDIO_REG_GPHY_ID_54618SE) { - if (params->feature_config_flags & - FEATURE_CONFIG_AUTOGREEEN_ENABLED) { - temp = 6; - DP(NETIF_MSG_LINK, "Enabling Auto-GrEEEn\n"); + if ((phy->flags & FLAGS_EEE) && bnx2x_eee_has_cap(params)) { + int rc; + + bnx2x_cl22_write(bp, phy, MDIO_REG_GPHY_EXP_ACCESS, + MDIO_REG_GPHY_EXP_ACCESS_TOP | + MDIO_REG_GPHY_EXP_TOP_2K_BUF); + bnx2x_cl22_read(bp, phy, MDIO_REG_GPHY_EXP_ACCESS_GATE, &temp); + temp &= 0xfffe; + bnx2x_cl22_write(bp, phy, MDIO_REG_GPHY_EXP_ACCESS_GATE, temp); + + rc = bnx2x_eee_initial_config(params, vars, SHMEM_EEE_1G_ADV); + if (rc) { + DP(NETIF_MSG_LINK, "Failed to configure EEE timers\n"); + bnx2x_eee_disable(phy, params, vars); + } else if ((params->eee_mode & EEE_MODE_ADV_LPI) && + (phy->req_duplex == DUPLEX_FULL) && + (bnx2x_eee_calc_timer(params) || + !(params->eee_mode & EEE_MODE_ENABLE_LPI))) { + /* Need to advertise EEE only when requested, + * and either no LPI assertion was requested, + * or it was requested and a valid timer was set. + * Also notice full duplex is required for EEE. + */ + bnx2x_eee_advertise(phy, params, vars, + SHMEM_EEE_1G_ADV); } else { - temp = 0; - DP(NETIF_MSG_LINK, "Disabling Auto-GrEEEn\n"); + DP(NETIF_MSG_LINK, "Don't Advertise 1GBase-T EEE\n"); + bnx2x_eee_disable(phy, params, vars); + } + } else { + vars->eee_status &= ~SHMEM_EEE_1G_ADV << + SHMEM_EEE_SUPPORTED_SHIFT; + + if (phy->flags & FLAGS_EEE) { + /* Handle legacy auto-grEEEn */ + if (params->feature_config_flags & + FEATURE_CONFIG_AUTOGREEEN_ENABLED) { + temp = 6; + DP(NETIF_MSG_LINK, "Enabling Auto-GrEEEn\n"); + } else { + temp = 0; + DP(NETIF_MSG_LINK, "Don't Adv. EEE\n"); + } + bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, + MDIO_AN_REG_EEE_ADV, temp); } - bnx2x_cl22_write(bp, phy, - MDIO_REG_GPHY_CL45_ADDR_REG, MDIO_AN_DEVAD); - bnx2x_cl22_write(bp, phy, - MDIO_REG_GPHY_CL45_DATA_REG, - MDIO_REG_GPHY_EEE_ADV); - bnx2x_cl22_write(bp, phy, - MDIO_REG_GPHY_CL45_ADDR_REG, - (0x1 << 14) | MDIO_AN_DEVAD); - bnx2x_cl22_write(bp, phy, - MDIO_REG_GPHY_CL45_DATA_REG, - temp); } bnx2x_cl22_write(bp, phy, @@ -10960,29 +10996,6 @@ static u8 bnx2x_54618se_read_status(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "BCM54618SE: link speed is %d\n", vars->line_speed); - /* Report whether EEE is resolved. */ - bnx2x_cl22_read(bp, phy, MDIO_REG_GPHY_PHYID_LSB, &val); - if (val == MDIO_REG_GPHY_ID_54618SE) { - if (vars->link_status & - LINK_STATUS_AUTO_NEGOTIATE_COMPLETE) - val = 0; - else { - bnx2x_cl22_write(bp, phy, - MDIO_REG_GPHY_CL45_ADDR_REG, - MDIO_AN_DEVAD); - bnx2x_cl22_write(bp, phy, - MDIO_REG_GPHY_CL45_DATA_REG, - MDIO_REG_GPHY_EEE_RESOLVED); - bnx2x_cl22_write(bp, phy, - MDIO_REG_GPHY_CL45_ADDR_REG, - (0x1 << 14) | MDIO_AN_DEVAD); - bnx2x_cl22_read(bp, phy, - MDIO_REG_GPHY_CL45_DATA_REG, - &val); - } - DP(NETIF_MSG_LINK, "EEE resolution: 0x%x\n", val); - } - bnx2x_ext_phy_resolve_fc(phy, params, vars); if (vars->link_status & LINK_STATUS_AUTO_NEGOTIATE_COMPLETE) { @@ -11012,6 +11025,10 @@ static u8 bnx2x_54618se_read_status(struct bnx2x_phy *phy, if (val & (1<<11)) vars->link_status |= LINK_STATUS_LINK_PARTNER_1000TFD_CAPABLE; + + if ((phy->flags & FLAGS_EEE) && + bnx2x_eee_has_cap(params)) + bnx2x_eee_an_resolve(phy, params, vars); } } return link_up; @@ -11925,6 +11942,8 @@ static int bnx2x_populate_ext_phy(struct bnx2x *bp, case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54616: case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE: *phy = phy_54618se; + if (phy_type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE) + phy->flags |= FLAGS_EEE; break; case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_SFX7101: *phy = phy_7101; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h index 3967aa85fc09..360ecf9e0739 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h @@ -155,6 +155,7 @@ struct bnx2x_phy { #define FLAGS_DUMMY_READ (1<<9) #define FLAGS_MDC_MDIO_WA_B0 (1<<10) #define FLAGS_TX_ERROR_CHECK (1<<12) +#define FLAGS_EEE (1<<13) /* preemphasis values for the rx side */ u16 rx_preemphasis[4]; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index d32293fcc81c..1b1999d34c71 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -4949,6 +4949,10 @@ #define UMAC_COMMAND_CONFIG_REG_SW_RESET (0x1<<13) #define UMAC_COMMAND_CONFIG_REG_TX_ENA (0x1<<0) #define UMAC_REG_COMMAND_CONFIG 0x8 +/* [RW 16] This is the duration for which MAC must wait to go back to ACTIVE + * state from LPI state when it receives packet for transmission. The + * decrement unit is 1 micro-second. */ +#define UMAC_REG_EEE_WAKE_TIMER 0x6c /* [RW 32] Register Bit 0 refers to Bit 16 of the MAC address; Bit 1 refers * to bit 17 of the MAC address etc. */ #define UMAC_REG_MAC_ADDR0 0xc @@ -4958,6 +4962,8 @@ /* [RW 14] Defines a 14-Bit maximum frame length used by the MAC receive * logic to check frames. */ #define UMAC_REG_MAXFR 0x14 +#define UMAC_REG_UMAC_EEE_CTRL 0x64 +#define UMAC_UMAC_EEE_CTRL_REG_EEE_EN (0x1<<3) /* [RW 8] The event id for aggregated interrupt 0 */ #define USDM_REG_AGG_INT_EVENT_0 0xc4038 #define USDM_REG_AGG_INT_EVENT_1 0xc403c @@ -7161,10 +7167,11 @@ Theotherbitsarereservedandshouldbezero*/ #define MDIO_REG_GPHY_ID_54618SE 0x5cd5 #define MDIO_REG_GPHY_CL45_ADDR_REG 0xd #define MDIO_REG_GPHY_CL45_DATA_REG 0xe -#define MDIO_REG_GPHY_EEE_ADV 0x3c -#define MDIO_REG_GPHY_EEE_1G (0x1 << 2) -#define MDIO_REG_GPHY_EEE_100 (0x1 << 1) #define MDIO_REG_GPHY_EEE_RESOLVED 0x803e +#define MDIO_REG_GPHY_EXP_ACCESS_GATE 0x15 +#define MDIO_REG_GPHY_EXP_ACCESS 0x17 +#define MDIO_REG_GPHY_EXP_ACCESS_TOP 0xd00 +#define MDIO_REG_GPHY_EXP_TOP_2K_BUF 0x40 #define MDIO_REG_GPHY_AUX_STATUS 0x19 #define MDIO_REG_INTR_STATUS 0x1a #define MDIO_REG_INTR_MASK 0x1b -- cgit v1.2.3 From 5c107fda9698bba6828bbca687ca556fd5e7f50c Mon Sep 17 00:00:00 2001 From: Yaniv Rosner Date: Thu, 13 Sep 2012 02:56:19 +0000 Subject: bnx2x: link code refactoring Separate the interrupt setting part of each external PHY to a specific function. This allows calling the interrupt setting in case of link-flap avoidance, since some link owners may not enable the interrupt on their own. Signed-off-by: Yaniv Rosner Signed-off-by: Yuval Mintz Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 192 +++++++++++++---------- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h | 1 + 2 files changed, 114 insertions(+), 79 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index c660afdbdf56..f7e236e68f17 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -7367,6 +7367,22 @@ static void bnx2x_8073_set_pause_cl37(struct link_params *params, msleep(500); } +static void bnx2x_8073_specific_func(struct bnx2x_phy *phy, + struct link_params *params, + u32 action) +{ + struct bnx2x *bp = params->bp; + switch (action) { + case PHY_INIT: + /* Enable LASI */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXCTRL, (1<<2)); + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_LASI_CTRL, 0x0004); + break; + } +} + static int bnx2x_8073_config_init(struct bnx2x_phy *phy, struct link_params *params, struct link_vars *vars) @@ -7387,12 +7403,7 @@ static int bnx2x_8073_config_init(struct bnx2x_phy *phy, bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_1, MISC_REGISTERS_GPIO_OUTPUT_HIGH, gpio_port); - /* Enable LASI */ - bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXCTRL, (1<<2)); - bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, MDIO_PMA_LASI_CTRL, 0x0004); - + bnx2x_8073_specific_func(phy, params, PHY_INIT); bnx2x_8073_set_pause_cl37(params, phy, vars); bnx2x_cl45_read(bp, phy, @@ -8427,7 +8438,7 @@ static void bnx2x_8727_specific_func(struct bnx2x_phy *phy, u32 action) { struct bnx2x *bp = params->bp; - + u16 val; switch (action) { case DISABLE_TX: bnx2x_sfp_set_transmitter(params, phy, 0); @@ -8436,6 +8447,40 @@ static void bnx2x_8727_specific_func(struct bnx2x_phy *phy, if (!(phy->flags & FLAGS_SFP_NOT_APPROVED)) bnx2x_sfp_set_transmitter(params, phy, 1); break; + case PHY_INIT: + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXCTRL, + (1<<2) | (1<<5)); + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_LASI_TXCTRL, + 0); + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_LASI_CTRL, 0x0006); + /* Make MOD_ABS give interrupt on change */ + bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, + MDIO_PMA_REG_8727_PCS_OPT_CTRL, + &val); + val |= (1<<12); + if (phy->flags & FLAGS_NOC) + val |= (3<<5); + /* Set 8727 GPIOs to input to allow reading from the 8727 GPIO0 + * status which reflect SFP+ module over-current + */ + if (!(phy->flags & FLAGS_NOC)) + val &= 0xff8f; /* Reset bits 4-6 */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_PCS_OPT_CTRL, + val); + + /* Set 2-wire transfer rate of SFP+ module EEPROM + * to 100Khz since some DACs(direct attached cables) do + * not work at 400Khz. + */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8727_TWO_WIRE_SLAVE_ADDR, + 0xa001); + break; default: DP(NETIF_MSG_LINK, "Function 0x%x not supported by 8727\n", action); @@ -9218,28 +9263,15 @@ static int bnx2x_8727_config_init(struct bnx2x_phy *phy, struct link_vars *vars) { u32 tx_en_mode; - u16 tmp1, val, mod_abs, tmp2; - u16 rx_alarm_ctrl_val; - u16 lasi_ctrl_val; + u16 tmp1, mod_abs, tmp2; struct bnx2x *bp = params->bp; /* Enable PMD link, MOD_ABS_FLT, and 1G link alarm */ bnx2x_wait_reset_complete(bp, phy, params); - rx_alarm_ctrl_val = (1<<2) | (1<<5) ; - /* Should be 0x6 to enable XS on Tx side. */ - lasi_ctrl_val = 0x0006; DP(NETIF_MSG_LINK, "Initializing BCM8727\n"); - /* Enable LASI */ - bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXCTRL, - rx_alarm_ctrl_val); - bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, MDIO_PMA_LASI_TXCTRL, - 0); - bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, MDIO_PMA_LASI_CTRL, lasi_ctrl_val); + bnx2x_8727_specific_func(phy, params, PHY_INIT); /* Initially configure MOD_ABS to interrupt when module is * presence( bit 8) */ @@ -9255,25 +9287,9 @@ static int bnx2x_8727_config_init(struct bnx2x_phy *phy, bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_PHY_IDENTIFIER, mod_abs); - /* Enable/Disable PHY transmitter output */ bnx2x_set_disable_pmd_transmit(params, phy, 0); - /* Make MOD_ABS give interrupt on change */ - bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_PCS_OPT_CTRL, - &val); - val |= (1<<12); - if (phy->flags & FLAGS_NOC) - val |= (3<<5); - - /* Set 8727 GPIOs to input to allow reading from the 8727 GPIO0 - * status which reflect SFP+ module over-current - */ - if (!(phy->flags & FLAGS_NOC)) - val &= 0xff8f; /* Reset bits 4-6 */ - bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_PCS_OPT_CTRL, val); - bnx2x_8727_power_module(bp, phy, 1); bnx2x_cl45_read(bp, phy, @@ -9283,13 +9299,7 @@ static int bnx2x_8727_config_init(struct bnx2x_phy *phy, MDIO_PMA_DEVAD, MDIO_PMA_LASI_RXSTAT, &tmp1); bnx2x_8727_config_speed(phy, params); - /* Set 2-wire transfer rate of SFP+ module EEPROM - * to 100Khz since some DACs(direct attached cables) do - * not work at 400Khz. - */ - bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_TWO_WIRE_SLAVE_ADDR, - 0xa001); + /* Set TX PreEmphasis if needed */ if ((params->feature_config_flags & @@ -9718,6 +9728,29 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp, 0xFFFB, 0xFFFD); } +static void bnx2x_848xx_specific_func(struct bnx2x_phy *phy, + struct link_params *params, + u32 action) +{ + struct bnx2x *bp = params->bp; + switch (action) { + case PHY_INIT: + if (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) { + /* Save spirom version */ + bnx2x_save_848xx_spirom_version(phy, bp, params->port); + } + /* This phy uses the NIG latch mechanism since link indication + * arrives through its LED4 and not via its LASI signal, so we + * get steady signal instead of clear on read + */ + bnx2x_bits_en(bp, NIG_REG_LATCH_BC_0 + params->port*4, + 1 << NIG_LATCH_BC_ENABLE_MI_INT); + + bnx2x_848xx_set_led(bp, phy); + break; + } +} + static int bnx2x_848xx_cmn_config_init(struct bnx2x_phy *phy, struct link_params *params, struct link_vars *vars) @@ -9725,22 +9758,10 @@ static int bnx2x_848xx_cmn_config_init(struct bnx2x_phy *phy, struct bnx2x *bp = params->bp; u16 autoneg_val, an_1000_val, an_10_100_val, an_10g_val; - if (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) { - /* Save spirom version */ - bnx2x_save_848xx_spirom_version(phy, bp, params->port); - } - /* This phy uses the NIG latch mechanism since link indication - * arrives through its LED4 and not via its LASI signal, so we - * get steady signal instead of clear on read - */ - bnx2x_bits_en(bp, NIG_REG_LATCH_BC_0 + params->port*4, - 1 << NIG_LATCH_BC_ENABLE_MI_INT); - + bnx2x_848xx_specific_func(phy, params, PHY_INIT); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_CTRL, 0x0000); - bnx2x_848xx_set_led(bp, phy); - /* set 1000 speed advertisement */ bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_8481_1000T_CTRL, @@ -10645,6 +10666,35 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, /******************************************************************/ /* 54618SE PHY SECTION */ /******************************************************************/ +static void bnx2x_54618se_specific_func(struct bnx2x_phy *phy, + struct link_params *params, + u32 action) +{ + struct bnx2x *bp = params->bp; + u16 temp; + switch (action) { + case PHY_INIT: + /* Configure LED4: set to INTR (0x6). */ + /* Accessing shadow register 0xe. */ + bnx2x_cl22_write(bp, phy, + MDIO_REG_GPHY_SHADOW, + MDIO_REG_GPHY_SHADOW_LED_SEL2); + bnx2x_cl22_read(bp, phy, + MDIO_REG_GPHY_SHADOW, + &temp); + temp &= ~(0xf << 4); + temp |= (0x6 << 4); + bnx2x_cl22_write(bp, phy, + MDIO_REG_GPHY_SHADOW, + MDIO_REG_GPHY_SHADOW_WR_ENA | temp); + /* Configure INTR based on link status change. */ + bnx2x_cl22_write(bp, phy, + MDIO_REG_INTR_MASK, + ~MDIO_REG_INTR_MASK_LINK_STATUS); + break; + } +} + static int bnx2x_54618se_config_init(struct bnx2x_phy *phy, struct link_params *params, struct link_vars *vars) @@ -10682,24 +10732,8 @@ static int bnx2x_54618se_config_init(struct bnx2x_phy *phy, /* Wait for GPHY to reset */ msleep(50); - /* Configure LED4: set to INTR (0x6). */ - /* Accessing shadow register 0xe. */ - bnx2x_cl22_write(bp, phy, - MDIO_REG_GPHY_SHADOW, - MDIO_REG_GPHY_SHADOW_LED_SEL2); - bnx2x_cl22_read(bp, phy, - MDIO_REG_GPHY_SHADOW, - &temp); - temp &= ~(0xf << 4); - temp |= (0x6 << 4); - bnx2x_cl22_write(bp, phy, - MDIO_REG_GPHY_SHADOW, - MDIO_REG_GPHY_SHADOW_WR_ENA | temp); - /* Configure INTR based on link status change. */ - bnx2x_cl22_write(bp, phy, - MDIO_REG_INTR_MASK, - ~MDIO_REG_INTR_MASK_LINK_STATUS); + bnx2x_54618se_specific_func(phy, params, PHY_INIT); /* Flip the signal detect polarity (set 0x1c.0x1e[8]). */ bnx2x_cl22_write(bp, phy, MDIO_REG_GPHY_SHADOW, @@ -11434,7 +11468,7 @@ static struct bnx2x_phy phy_8073 = { .format_fw_ver = (format_fw_ver_t)bnx2x_format_ver, .hw_reset = (hw_reset_t)NULL, .set_link_led = (set_link_led_t)NULL, - .phy_specific_func = (phy_specific_func_t)NULL + .phy_specific_func = (phy_specific_func_t)bnx2x_8073_specific_func }; static struct bnx2x_phy phy_8705 = { .type = PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8705, @@ -11627,7 +11661,7 @@ static struct bnx2x_phy phy_84823 = { .format_fw_ver = (format_fw_ver_t)bnx2x_848xx_format_ver, .hw_reset = (hw_reset_t)NULL, .set_link_led = (set_link_led_t)bnx2x_848xx_set_link_led, - .phy_specific_func = (phy_specific_func_t)NULL + .phy_specific_func = (phy_specific_func_t)bnx2x_848xx_specific_func }; static struct bnx2x_phy phy_84833 = { @@ -11662,7 +11696,7 @@ static struct bnx2x_phy phy_84833 = { .format_fw_ver = (format_fw_ver_t)bnx2x_848xx_format_ver, .hw_reset = (hw_reset_t)bnx2x_84833_hw_reset_phy, .set_link_led = (set_link_led_t)bnx2x_848xx_set_link_led, - .phy_specific_func = (phy_specific_func_t)NULL + .phy_specific_func = (phy_specific_func_t)bnx2x_848xx_specific_func }; static struct bnx2x_phy phy_54618se = { @@ -11696,7 +11730,7 @@ static struct bnx2x_phy phy_54618se = { .format_fw_ver = (format_fw_ver_t)NULL, .hw_reset = (hw_reset_t)NULL, .set_link_led = (set_link_led_t)bnx2x_5461x_set_link_led, - .phy_specific_func = (phy_specific_func_t)NULL + .phy_specific_func = (phy_specific_func_t)bnx2x_54618se_specific_func }; /*****************************************************************/ /* */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h index 360ecf9e0739..ffc83f3c9123 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h @@ -216,6 +216,7 @@ struct bnx2x_phy { phy_specific_func_t phy_specific_func; #define DISABLE_TX 1 #define ENABLE_TX 2 +#define PHY_INIT 3 }; /* Inputs parameters to the CLC */ -- cgit v1.2.3 From d3a8f13b11e34b377e5fbc544c6780ba83e0346a Mon Sep 17 00:00:00 2001 From: Yaniv Rosner Date: Thu, 13 Sep 2012 02:56:20 +0000 Subject: bnx2x: Link Flap Avoidance Various flows in the bnx2x driver cause a link-flap - if the link is up, it would be toggled down (after a mac/phy reset) and then taken back up. In many of these cases, there is no need to do cause such a flap, as the associated flows should not actually affect the link. This patch adds the 'Link Flap Avoidance' mechanism, which allows the driver to better determine if a given flow requires a link change, and thus minimize the number of link flaps caused by the driver. Signed-off-by: Yaniv Rosner Signed-off-by: Yuval Mintz Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h | 48 +++ drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 435 ++++++++++++++++++++--- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h | 2 + 3 files changed, 437 insertions(+), 48 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 76b6e65790f8..df1400664ab3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -1909,6 +1909,54 @@ struct lldp_local_mib { }; /***END OF DCBX STRUCTURES DECLARATIONS***/ +/***********************************************************/ +/* Elink section */ +/***********************************************************/ +#define SHMEM_LINK_CONFIG_SIZE 2 +struct shmem_lfa { + u32 req_duplex; + #define REQ_DUPLEX_PHY0_MASK 0x0000ffff + #define REQ_DUPLEX_PHY0_SHIFT 0 + #define REQ_DUPLEX_PHY1_MASK 0xffff0000 + #define REQ_DUPLEX_PHY1_SHIFT 16 + u32 req_flow_ctrl; + #define REQ_FLOW_CTRL_PHY0_MASK 0x0000ffff + #define REQ_FLOW_CTRL_PHY0_SHIFT 0 + #define REQ_FLOW_CTRL_PHY1_MASK 0xffff0000 + #define REQ_FLOW_CTRL_PHY1_SHIFT 16 + u32 req_line_speed; /* Also determine AutoNeg */ + #define REQ_LINE_SPD_PHY0_MASK 0x0000ffff + #define REQ_LINE_SPD_PHY0_SHIFT 0 + #define REQ_LINE_SPD_PHY1_MASK 0xffff0000 + #define REQ_LINE_SPD_PHY1_SHIFT 16 + u32 speed_cap_mask[SHMEM_LINK_CONFIG_SIZE]; + u32 additional_config; + #define REQ_FC_AUTO_ADV_MASK 0x0000ffff + #define REQ_FC_AUTO_ADV0_SHIFT 0 + #define NO_LFA_DUE_TO_DCC_MASK 0x00010000 + u32 lfa_sts; + #define LFA_LINK_FLAP_REASON_OFFSET 0 + #define LFA_LINK_FLAP_REASON_MASK 0x000000ff + #define LFA_LINK_DOWN 0x1 + #define LFA_LOOPBACK_ENABLED 0x2 + #define LFA_DUPLEX_MISMATCH 0x3 + #define LFA_MFW_IS_TOO_OLD 0x4 + #define LFA_LINK_SPEED_MISMATCH 0x5 + #define LFA_FLOW_CTRL_MISMATCH 0x6 + #define LFA_SPEED_CAP_MISMATCH 0x7 + #define LFA_DCC_LFA_DISABLED 0x8 + #define LFA_EEE_MISMATCH 0x9 + + #define LINK_FLAP_AVOIDANCE_COUNT_OFFSET 8 + #define LINK_FLAP_AVOIDANCE_COUNT_MASK 0x0000ff00 + + #define LINK_FLAP_COUNT_OFFSET 16 + #define LINK_FLAP_COUNT_MASK 0x00ff0000 + + #define LFA_FLAGS_MASK 0xff000000 + #define SHMEM_LFA_DONT_CLEAR_STAT (1<<24) +}; + struct ncsi_oem_fcoe_features { u32 fcoe_features1; #define FCOE_FEATURES1_IOS_PER_CONNECTION_MASK 0x0000FFFF diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index f7e236e68f17..4eca0f863073 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -321,6 +321,127 @@ static u32 bnx2x_bits_dis(struct bnx2x *bp, u32 reg, u32 bits) return val; } +/* + * bnx2x_check_lfa - This function checks if link reinitialization is required, + * or link flap can be avoided. + * + * @params: link parameters + * Returns 0 if Link Flap Avoidance conditions are met otherwise, the failed + * condition code. + */ +static int bnx2x_check_lfa(struct link_params *params) +{ + u32 link_status, cfg_idx, lfa_mask, cfg_size; + u32 cur_speed_cap_mask, cur_req_fc_auto_adv, additional_config; + u32 saved_val, req_val, eee_status; + struct bnx2x *bp = params->bp; + + additional_config = + REG_RD(bp, params->lfa_base + + offsetof(struct shmem_lfa, additional_config)); + + /* NOTE: must be first condition checked - + * to verify DCC bit is cleared in any case! + */ + if (additional_config & NO_LFA_DUE_TO_DCC_MASK) { + DP(NETIF_MSG_LINK, "No LFA due to DCC flap after clp exit\n"); + REG_WR(bp, params->lfa_base + + offsetof(struct shmem_lfa, additional_config), + additional_config & ~NO_LFA_DUE_TO_DCC_MASK); + return LFA_DCC_LFA_DISABLED; + } + + /* Verify that link is up */ + link_status = REG_RD(bp, params->shmem_base + + offsetof(struct shmem_region, + port_mb[params->port].link_status)); + if (!(link_status & LINK_STATUS_LINK_UP)) + return LFA_LINK_DOWN; + + /* Verify that loopback mode is not set */ + if (params->loopback_mode) + return LFA_LOOPBACK_ENABLED; + + /* Verify that MFW supports LFA */ + if (!params->lfa_base) + return LFA_MFW_IS_TOO_OLD; + + if (params->num_phys == 3) { + cfg_size = 2; + lfa_mask = 0xffffffff; + } else { + cfg_size = 1; + lfa_mask = 0xffff; + } + + /* Compare Duplex */ + saved_val = REG_RD(bp, params->lfa_base + + offsetof(struct shmem_lfa, req_duplex)); + req_val = params->req_duplex[0] | (params->req_duplex[1] << 16); + if ((saved_val & lfa_mask) != (req_val & lfa_mask)) { + DP(NETIF_MSG_LINK, "Duplex mismatch %x vs. %x\n", + (saved_val & lfa_mask), (req_val & lfa_mask)); + return LFA_DUPLEX_MISMATCH; + } + /* Compare Flow Control */ + saved_val = REG_RD(bp, params->lfa_base + + offsetof(struct shmem_lfa, req_flow_ctrl)); + req_val = params->req_flow_ctrl[0] | (params->req_flow_ctrl[1] << 16); + if ((saved_val & lfa_mask) != (req_val & lfa_mask)) { + DP(NETIF_MSG_LINK, "Flow control mismatch %x vs. %x\n", + (saved_val & lfa_mask), (req_val & lfa_mask)); + return LFA_FLOW_CTRL_MISMATCH; + } + /* Compare Link Speed */ + saved_val = REG_RD(bp, params->lfa_base + + offsetof(struct shmem_lfa, req_line_speed)); + req_val = params->req_line_speed[0] | (params->req_line_speed[1] << 16); + if ((saved_val & lfa_mask) != (req_val & lfa_mask)) { + DP(NETIF_MSG_LINK, "Link speed mismatch %x vs. %x\n", + (saved_val & lfa_mask), (req_val & lfa_mask)); + return LFA_LINK_SPEED_MISMATCH; + } + + for (cfg_idx = 0; cfg_idx < cfg_size; cfg_idx++) { + cur_speed_cap_mask = REG_RD(bp, params->lfa_base + + offsetof(struct shmem_lfa, + speed_cap_mask[cfg_idx])); + + if (cur_speed_cap_mask != params->speed_cap_mask[cfg_idx]) { + DP(NETIF_MSG_LINK, "Speed Cap mismatch %x vs. %x\n", + cur_speed_cap_mask, + params->speed_cap_mask[cfg_idx]); + return LFA_SPEED_CAP_MISMATCH; + } + } + + cur_req_fc_auto_adv = + REG_RD(bp, params->lfa_base + + offsetof(struct shmem_lfa, additional_config)) & + REQ_FC_AUTO_ADV_MASK; + + if ((u16)cur_req_fc_auto_adv != params->req_fc_auto_adv) { + DP(NETIF_MSG_LINK, "Flow Ctrl AN mismatch %x vs. %x\n", + cur_req_fc_auto_adv, params->req_fc_auto_adv); + return LFA_FLOW_CTRL_MISMATCH; + } + + eee_status = REG_RD(bp, params->shmem2_base + + offsetof(struct shmem2_region, + eee_status[params->port])); + + if (((eee_status & SHMEM_EEE_LPI_REQUESTED_BIT) ^ + (params->eee_mode & EEE_MODE_ENABLE_LPI)) || + ((eee_status & SHMEM_EEE_REQUESTED_BIT) ^ + (params->eee_mode & EEE_MODE_ADV_LPI))) { + DP(NETIF_MSG_LINK, "EEE mismatch %x vs. %x\n", params->eee_mode, + eee_status); + return LFA_EEE_MISMATCH; + } + + /* LFA conditions are met */ + return 0; +} /******************************************************************/ /* EPIO/GPIO section */ /******************************************************************/ @@ -1519,16 +1640,23 @@ static void bnx2x_set_xumac_nig(struct link_params *params, NIG_REG_P0_MAC_PAUSE_OUT_EN, tx_pause_en); } -static void bnx2x_umac_disable(struct link_params *params) +static void bnx2x_set_umac_rxtx(struct link_params *params, u8 en) { u32 umac_base = params->port ? GRCBASE_UMAC1 : GRCBASE_UMAC0; + u32 val; struct bnx2x *bp = params->bp; if (!(REG_RD(bp, MISC_REG_RESET_REG_2) & (MISC_REGISTERS_RESET_REG_2_UMAC0 << params->port))) return; - + val = REG_RD(bp, umac_base + UMAC_REG_COMMAND_CONFIG); + if (en) + val |= (UMAC_COMMAND_CONFIG_REG_TX_ENA | + UMAC_COMMAND_CONFIG_REG_RX_ENA); + else + val &= ~(UMAC_COMMAND_CONFIG_REG_TX_ENA | + UMAC_COMMAND_CONFIG_REG_RX_ENA); /* Disable RX and TX */ - REG_WR(bp, umac_base + UMAC_REG_COMMAND_CONFIG, 0); + REG_WR(bp, umac_base + UMAC_REG_COMMAND_CONFIG, val); } static void bnx2x_umac_enable(struct link_params *params, @@ -1689,11 +1817,12 @@ static void bnx2x_xmac_init(struct link_params *params, u32 max_speed) } -static void bnx2x_xmac_disable(struct link_params *params) +static void bnx2x_set_xmac_rxtx(struct link_params *params, u8 en) { u8 port = params->port; struct bnx2x *bp = params->bp; u32 pfc_ctrl, xmac_base = (port) ? GRCBASE_XMAC1 : GRCBASE_XMAC0; + u32 val; if (REG_RD(bp, MISC_REG_RESET_REG_2) & MISC_REGISTERS_RESET_REG_2_XMAC) { @@ -1707,7 +1836,12 @@ static void bnx2x_xmac_disable(struct link_params *params) REG_WR(bp, xmac_base + XMAC_REG_PFC_CTRL_HI, (pfc_ctrl | (1<<1))); DP(NETIF_MSG_LINK, "Disable XMAC on port %x\n", port); - REG_WR(bp, xmac_base + XMAC_REG_CTRL, 0); + val = REG_RD(bp, xmac_base + XMAC_REG_CTRL); + if (en) + val |= (XMAC_CTRL_REG_TX_EN | XMAC_CTRL_REG_RX_EN); + else + val &= ~(XMAC_CTRL_REG_TX_EN | XMAC_CTRL_REG_RX_EN); + REG_WR(bp, xmac_base + XMAC_REG_CTRL, val); } } @@ -2738,16 +2872,18 @@ static int bnx2x_bmac2_enable(struct link_params *params, static int bnx2x_bmac_enable(struct link_params *params, struct link_vars *vars, - u8 is_lb) + u8 is_lb, u8 reset_bmac) { int rc = 0; u8 port = params->port; struct bnx2x *bp = params->bp; u32 val; /* Reset and unreset the BigMac */ - REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_CLEAR, - (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); - usleep_range(1000, 2000); + if (reset_bmac) { + REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_CLEAR, + (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); + usleep_range(1000, 2000); + } REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET, (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); @@ -2779,37 +2915,28 @@ static int bnx2x_bmac_enable(struct link_params *params, return rc; } -static void bnx2x_bmac_rx_disable(struct bnx2x *bp, u8 port) +static void bnx2x_set_bmac_rx(struct bnx2x *bp, u32 chip_id, u8 port, u8 en) { u32 bmac_addr = port ? NIG_REG_INGRESS_BMAC1_MEM : NIG_REG_INGRESS_BMAC0_MEM; u32 wb_data[2]; u32 nig_bmac_enable = REG_RD(bp, NIG_REG_BMAC0_REGS_OUT_EN + port*4); + if (CHIP_IS_E2(bp)) + bmac_addr += BIGMAC2_REGISTER_BMAC_CONTROL; + else + bmac_addr += BIGMAC_REGISTER_BMAC_CONTROL; /* Only if the bmac is out of reset */ if (REG_RD(bp, MISC_REG_RESET_REG_2) & (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port) && nig_bmac_enable) { - - if (CHIP_IS_E2(bp)) { - /* Clear Rx Enable bit in BMAC_CONTROL register */ - REG_RD_DMAE(bp, bmac_addr + - BIGMAC2_REGISTER_BMAC_CONTROL, - wb_data, 2); - wb_data[0] &= ~BMAC_CONTROL_RX_ENABLE; - REG_WR_DMAE(bp, bmac_addr + - BIGMAC2_REGISTER_BMAC_CONTROL, - wb_data, 2); - } else { - /* Clear Rx Enable bit in BMAC_CONTROL register */ - REG_RD_DMAE(bp, bmac_addr + - BIGMAC_REGISTER_BMAC_CONTROL, - wb_data, 2); + /* Clear Rx Enable bit in BMAC_CONTROL register */ + REG_RD_DMAE(bp, bmac_addr, wb_data, 2); + if (en) + wb_data[0] |= BMAC_CONTROL_RX_ENABLE; + else wb_data[0] &= ~BMAC_CONTROL_RX_ENABLE; - REG_WR_DMAE(bp, bmac_addr + - BIGMAC_REGISTER_BMAC_CONTROL, - wb_data, 2); - } + REG_WR_DMAE(bp, bmac_addr, wb_data, 2); usleep_range(1000, 2000); } } @@ -4568,7 +4695,7 @@ static void bnx2x_warpcore_config_init(struct bnx2x_phy *phy, "serdes_net_if = 0x%x\n", vars->line_speed, serdes_net_if); bnx2x_set_aer_mmd(params, phy); - + bnx2x_warpcore_reset_lane(bp, phy, 1); vars->phy_flags |= PHY_XGXS_FLAG; if ((serdes_net_if == PORT_HW_CFG_NET_SERDES_IF_SGMII) || (phy->req_line_speed && @@ -6691,12 +6818,9 @@ static int bnx2x_update_link_down(struct link_params *params, usleep_range(10000, 20000); /* Reset BigMac/Xmac */ if (CHIP_IS_E1x(bp) || - CHIP_IS_E2(bp)) { - bnx2x_bmac_rx_disable(bp, params->port); - REG_WR(bp, GRCBASE_MISC + - MISC_REGISTERS_RESET_REG_2_CLEAR, - (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); - } + CHIP_IS_E2(bp)) + bnx2x_set_bmac_rx(bp, params->chip_id, params->port, 0); + if (CHIP_IS_E3(bp)) { /* Prevent LPI Generation by chip */ REG_WR(bp, MISC_REG_CPMU_LP_FW_ENABLE_P0 + (params->port << 2), @@ -6707,8 +6831,8 @@ static int bnx2x_update_link_down(struct link_params *params, SHMEM_EEE_ACTIVE_BIT); bnx2x_update_mng_eee(params, vars->eee_status); - bnx2x_xmac_disable(params); - bnx2x_umac_disable(params); + bnx2x_set_xmac_rxtx(params, 0); + bnx2x_set_umac_rxtx(params, 0); } return 0; @@ -6760,7 +6884,7 @@ static int bnx2x_update_link_up(struct link_params *params, if ((CHIP_IS_E1x(bp) || CHIP_IS_E2(bp))) { if (link_10g) { - if (bnx2x_bmac_enable(params, vars, 0) == + if (bnx2x_bmac_enable(params, vars, 0, 1) == -ESRCH) { DP(NETIF_MSG_LINK, "Found errors on BMAC\n"); vars->link_up = 0; @@ -12257,7 +12381,7 @@ void bnx2x_init_bmac_loopback(struct link_params *params, bnx2x_xgxs_deassert(params); /* set bmac loopback */ - bnx2x_bmac_enable(params, vars, 1); + bnx2x_bmac_enable(params, vars, 1, 1); REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0); } @@ -12349,7 +12473,7 @@ void bnx2x_init_xgxs_loopback(struct link_params *params, if (USES_WARPCORE(bp)) bnx2x_xmac_enable(params, vars, 0); else - bnx2x_bmac_enable(params, vars, 0); + bnx2x_bmac_enable(params, vars, 0, 1); } if (params->loopback_mode == LOOPBACK_XGXS) { @@ -12374,8 +12498,161 @@ void bnx2x_init_xgxs_loopback(struct link_params *params, bnx2x_set_led(params, vars, LED_MODE_OPER, vars->line_speed); } +static void bnx2x_set_rx_filter(struct link_params *params, u8 en) +{ + struct bnx2x *bp = params->bp; + u8 val = en * 0x1F; + + /* Open the gate between the NIG to the BRB */ + if (!CHIP_IS_E1x(bp)) + val |= en * 0x20; + REG_WR(bp, NIG_REG_LLH0_BRB1_DRV_MASK + params->port*4, val); + + if (!CHIP_IS_E1(bp)) { + REG_WR(bp, NIG_REG_LLH0_BRB1_DRV_MASK_MF + params->port*4, + en*0x3); + } + + REG_WR(bp, (params->port ? NIG_REG_LLH1_BRB1_NOT_MCP : + NIG_REG_LLH0_BRB1_NOT_MCP), en); +} +static int bnx2x_avoid_link_flap(struct link_params *params, + struct link_vars *vars) +{ + u32 phy_idx; + u32 dont_clear_stat, lfa_sts; + struct bnx2x *bp = params->bp; + + /* Sync the link parameters */ + bnx2x_link_status_update(params, vars); + + /* + * The module verification was already done by previous link owner, + * so this call is meant only to get warning message + */ + + for (phy_idx = INT_PHY; phy_idx < params->num_phys; phy_idx++) { + struct bnx2x_phy *phy = ¶ms->phy[phy_idx]; + if (phy->phy_specific_func) { + DP(NETIF_MSG_LINK, "Calling PHY specific func\n"); + phy->phy_specific_func(phy, params, PHY_INIT); + } + if ((phy->media_type == ETH_PHY_SFPP_10G_FIBER) || + (phy->media_type == ETH_PHY_SFP_1G_FIBER) || + (phy->media_type == ETH_PHY_DA_TWINAX)) + bnx2x_verify_sfp_module(phy, params); + } + lfa_sts = REG_RD(bp, params->lfa_base + + offsetof(struct shmem_lfa, + lfa_sts)); + + dont_clear_stat = lfa_sts & SHMEM_LFA_DONT_CLEAR_STAT; + + /* Re-enable the NIG/MAC */ + if (CHIP_IS_E3(bp)) { + if (!dont_clear_stat) { + REG_WR(bp, GRCBASE_MISC + + MISC_REGISTERS_RESET_REG_2_CLEAR, + (MISC_REGISTERS_RESET_REG_2_MSTAT0 << + params->port)); + REG_WR(bp, GRCBASE_MISC + + MISC_REGISTERS_RESET_REG_2_SET, + (MISC_REGISTERS_RESET_REG_2_MSTAT0 << + params->port)); + } + if (vars->line_speed < SPEED_10000) + bnx2x_umac_enable(params, vars, 0); + else + bnx2x_xmac_enable(params, vars, 0); + } else { + if (vars->line_speed < SPEED_10000) + bnx2x_emac_enable(params, vars, 0); + else + bnx2x_bmac_enable(params, vars, 0, !dont_clear_stat); + } + + /* Increment LFA count */ + lfa_sts = ((lfa_sts & ~LINK_FLAP_AVOIDANCE_COUNT_MASK) | + (((((lfa_sts & LINK_FLAP_AVOIDANCE_COUNT_MASK) >> + LINK_FLAP_AVOIDANCE_COUNT_OFFSET) + 1) & 0xff) + << LINK_FLAP_AVOIDANCE_COUNT_OFFSET)); + /* Clear link flap reason */ + lfa_sts &= ~LFA_LINK_FLAP_REASON_MASK; + + REG_WR(bp, params->lfa_base + + offsetof(struct shmem_lfa, lfa_sts), lfa_sts); + + /* Disable NIG DRAIN */ + REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0); + + /* Enable interrupts */ + bnx2x_link_int_enable(params); + return 0; +} + +static void bnx2x_cannot_avoid_link_flap(struct link_params *params, + struct link_vars *vars, + int lfa_status) +{ + u32 lfa_sts, cfg_idx, tmp_val; + struct bnx2x *bp = params->bp; + + bnx2x_link_reset(params, vars, 1); + + if (!params->lfa_base) + return; + /* Store the new link parameters */ + REG_WR(bp, params->lfa_base + + offsetof(struct shmem_lfa, req_duplex), + params->req_duplex[0] | (params->req_duplex[1] << 16)); + + REG_WR(bp, params->lfa_base + + offsetof(struct shmem_lfa, req_flow_ctrl), + params->req_flow_ctrl[0] | (params->req_flow_ctrl[1] << 16)); + + REG_WR(bp, params->lfa_base + + offsetof(struct shmem_lfa, req_line_speed), + params->req_line_speed[0] | (params->req_line_speed[1] << 16)); + + for (cfg_idx = 0; cfg_idx < SHMEM_LINK_CONFIG_SIZE; cfg_idx++) { + REG_WR(bp, params->lfa_base + + offsetof(struct shmem_lfa, + speed_cap_mask[cfg_idx]), + params->speed_cap_mask[cfg_idx]); + } + + tmp_val = REG_RD(bp, params->lfa_base + + offsetof(struct shmem_lfa, additional_config)); + tmp_val &= ~REQ_FC_AUTO_ADV_MASK; + tmp_val |= params->req_fc_auto_adv; + + REG_WR(bp, params->lfa_base + + offsetof(struct shmem_lfa, additional_config), tmp_val); + + lfa_sts = REG_RD(bp, params->lfa_base + + offsetof(struct shmem_lfa, lfa_sts)); + + /* Clear the "Don't Clear Statistics" bit, and set reason */ + lfa_sts &= ~SHMEM_LFA_DONT_CLEAR_STAT; + + /* Set link flap reason */ + lfa_sts &= ~LFA_LINK_FLAP_REASON_MASK; + lfa_sts |= ((lfa_status & LFA_LINK_FLAP_REASON_MASK) << + LFA_LINK_FLAP_REASON_OFFSET); + + /* Increment link flap counter */ + lfa_sts = ((lfa_sts & ~LINK_FLAP_COUNT_MASK) | + (((((lfa_sts & LINK_FLAP_COUNT_MASK) >> + LINK_FLAP_COUNT_OFFSET) + 1) & 0xff) + << LINK_FLAP_COUNT_OFFSET)); + REG_WR(bp, params->lfa_base + + offsetof(struct shmem_lfa, lfa_sts), lfa_sts); + /* Proceed with regular link initialization */ +} + int bnx2x_phy_init(struct link_params *params, struct link_vars *vars) { + int lfa_status; struct bnx2x *bp = params->bp; DP(NETIF_MSG_LINK, "Phy Initialization started\n"); DP(NETIF_MSG_LINK, "(1) req_speed %d, req_flowctrl %d\n", @@ -12390,6 +12667,19 @@ int bnx2x_phy_init(struct link_params *params, struct link_vars *vars) vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE; vars->mac_type = MAC_TYPE_NONE; vars->phy_flags = 0; + /* Driver opens NIG-BRB filters */ + bnx2x_set_rx_filter(params, 1); + /* Check if link flap can be avoided */ + lfa_status = bnx2x_check_lfa(params); + + if (lfa_status == 0) { + DP(NETIF_MSG_LINK, "Link Flap Avoidance in progress\n"); + return bnx2x_avoid_link_flap(params, vars); + } + + DP(NETIF_MSG_LINK, "Cannot avoid link flap lfa_sta=0x%x\n", + lfa_status); + bnx2x_cannot_avoid_link_flap(params, vars, lfa_status); /* Disable attentions */ bnx2x_bits_dis(bp, NIG_REG_MASK_INTERRUPT_PORT0 + params->port*4, @@ -12472,13 +12762,12 @@ int bnx2x_link_reset(struct link_params *params, struct link_vars *vars, REG_WR(bp, NIG_REG_EGRESS_EMAC0_OUT_EN + port*4, 0); } - /* Stop BigMac rx */ - if (!CHIP_IS_E3(bp)) - bnx2x_bmac_rx_disable(bp, port); - else { - bnx2x_xmac_disable(params); - bnx2x_umac_disable(params); - } + if (!CHIP_IS_E3(bp)) { + bnx2x_set_bmac_rx(bp, params->chip_id, port, 0); + } else { + bnx2x_set_xmac_rxtx(params, 0); + bnx2x_set_umac_rxtx(params, 0); + } /* Disable emac */ if (!CHIP_IS_E3(bp)) REG_WR(bp, NIG_REG_NIG_EMAC0_EN + port*4, 0); @@ -12536,6 +12825,56 @@ int bnx2x_link_reset(struct link_params *params, struct link_vars *vars, vars->phy_flags = 0; return 0; } +int bnx2x_lfa_reset(struct link_params *params, + struct link_vars *vars) +{ + struct bnx2x *bp = params->bp; + vars->link_up = 0; + vars->phy_flags = 0; + if (!params->lfa_base) + return bnx2x_link_reset(params, vars, 1); + /* + * Activate NIG drain so that during this time the device won't send + * anything while it is unable to response. + */ + REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 1); + + /* + * Close gracefully the gate from BMAC to NIG such that no half packets + * are passed. + */ + if (!CHIP_IS_E3(bp)) + bnx2x_set_bmac_rx(bp, params->chip_id, params->port, 0); + + if (CHIP_IS_E3(bp)) { + bnx2x_set_xmac_rxtx(params, 0); + bnx2x_set_umac_rxtx(params, 0); + } + /* Wait 10ms for the pipe to clean up*/ + usleep_range(10000, 20000); + + /* Clean the NIG-BRB using the network filters in a way that will + * not cut a packet in the middle. + */ + bnx2x_set_rx_filter(params, 0); + + /* + * Re-open the gate between the BMAC and the NIG, after verifying the + * gate to the BRB is closed, otherwise packets may arrive to the + * firmware before driver had initialized it. The target is to achieve + * minimum management protocol down time. + */ + if (!CHIP_IS_E3(bp)) + bnx2x_set_bmac_rx(bp, params->chip_id, params->port, 1); + + if (CHIP_IS_E3(bp)) { + bnx2x_set_xmac_rxtx(params, 1); + bnx2x_set_umac_rxtx(params, 1); + } + /* Disable NIG drain */ + REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0); + return 0; +} /****************************************************************************/ /* Common function */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h index ffc83f3c9123..21c3e42ec6a8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h @@ -305,6 +305,8 @@ struct link_params { struct bnx2x *bp; u16 req_fc_auto_adv; /* Should be set to TX / BOTH when req_flow_ctrl is set to AUTO */ + u16 rsrv1; + u32 lfa_base; }; /* Output parameters */ -- cgit v1.2.3 From 5d07d8680692a208be0466a352c9fde7eec2afa7 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Thu, 13 Sep 2012 02:56:21 +0000 Subject: bnx2x: Utilize Link Flap Avoidance Change various flows in the bnx2x driver which up until now flapped the link - these flows now benefit from the link flap avoidance mechanism. This includes the removal of the link reset made upon nic init, as it is possible the link is already active at that time. Signed-off-by: Yuval Mintz Signed-off-by: Yaniv Rosner Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 12 ++++---- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 16 ++++++++-- .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 10 ++++--- drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h | 3 ++ drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 34 ++++++++++++++-------- 6 files changed, 51 insertions(+), 26 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index af20c6ee2cd9..ca8048757c84 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2283,7 +2283,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) /* Wait for all pending SP commands to complete */ if (!bnx2x_wait_sp_comp(bp, ~0x0UL)) { BNX2X_ERR("Timeout waiting for SP elements to complete\n"); - bnx2x_nic_unload(bp, UNLOAD_CLOSE); + bnx2x_nic_unload(bp, UNLOAD_CLOSE, false); return -EBUSY; } @@ -2331,7 +2331,7 @@ load_error0: } /* must be called with rtnl_lock */ -int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode) +int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link) { int i; bool global = false; @@ -2393,7 +2393,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode) /* Cleanup the chip if needed */ if (unload_mode != UNLOAD_RECOVERY) - bnx2x_chip_cleanup(bp, unload_mode); + bnx2x_chip_cleanup(bp, unload_mode, keep_link); else { /* Send the UNLOAD_REQUEST to the MCP */ bnx2x_send_unload_req(bp, unload_mode); @@ -2417,7 +2417,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode) bnx2x_free_irq(bp); /* Report UNLOAD_DONE to MCP */ - bnx2x_send_unload_done(bp); + bnx2x_send_unload_done(bp, false); } /* @@ -3768,7 +3768,7 @@ int bnx2x_reload_if_running(struct net_device *dev) if (unlikely(!netif_running(dev))) return 0; - bnx2x_nic_unload(bp, UNLOAD_NORMAL); + bnx2x_nic_unload(bp, UNLOAD_NORMAL, true); return bnx2x_nic_load(bp, LOAD_NORMAL); } @@ -3965,7 +3965,7 @@ int bnx2x_suspend(struct pci_dev *pdev, pm_message_t state) netif_device_detach(dev); - bnx2x_nic_unload(bp, UNLOAD_CLOSE); + bnx2x_nic_unload(bp, UNLOAD_CLOSE, false); bnx2x_set_power_state(bp, pci_choose_state(pdev, state)); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 21b553229ea4..96e998c7cae0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -83,8 +83,9 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode); * bnx2x_send_unload_done - send UNLOAD_DONE command to the MCP. * * @bp: driver handle + * @keep_link: true iff link should be kept up */ -void bnx2x_send_unload_done(struct bnx2x *bp); +void bnx2x_send_unload_done(struct bnx2x *bp, bool keep_link); /** * bnx2x_config_rss_pf - configure RSS parameters in a PF. @@ -152,6 +153,14 @@ u8 bnx2x_initial_phy_init(struct bnx2x *bp, int load_mode); */ void bnx2x_link_set(struct bnx2x *bp); +/** + * bnx2x_force_link_reset - Forces link reset, and put the PHY + * in reset as well. + * + * @bp: driver handle + */ +void bnx2x_force_link_reset(struct bnx2x *bp); + /** * bnx2x_link_test - query link status. * @@ -312,12 +321,13 @@ void bnx2x_set_num_queues(struct bnx2x *bp); * * @bp: driver handle * @unload_mode: COMMON, PORT, FUNCTION + * @keep_link: true iff link should be kept up. * * - Cleanup MAC configuration. * - Closes clients. * - etc. */ -void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode); +void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link); /** * bnx2x_acquire_hw_lock - acquire HW lock. @@ -446,7 +456,7 @@ void bnx2x_fw_dump_lvl(struct bnx2x *bp, const char *lvl); bool bnx2x_test_firmware_version(struct bnx2x *bp, bool is_err); /* dev_close main block */ -int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode); +int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link); /* dev_open main block */ int bnx2x_nic_load(struct bnx2x *bp, int load_mode); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 5bafcd9df9e0..3dfa89ae4d45 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -905,6 +905,7 @@ static int bnx2x_nway_reset(struct net_device *dev) if (netif_running(dev)) { bnx2x_stats_handle(bp, STATS_EVENT_STOP); + bnx2x_force_link_reset(bp); bnx2x_link_set(bp); } @@ -1733,6 +1734,7 @@ static int bnx2x_set_eee(struct net_device *dev, struct ethtool_eee *edata) /* Restart link to propogate changes */ if (netif_running(dev)) { bnx2x_stats_handle(bp, STATS_EVENT_STOP); + bnx2x_force_link_reset(bp); bnx2x_link_set(bp); } @@ -2257,7 +2259,7 @@ static int bnx2x_test_ext_loopback(struct bnx2x *bp) if (!netif_running(bp->dev)) return BNX2X_EXT_LOOPBACK_FAILED; - bnx2x_nic_unload(bp, UNLOAD_NORMAL); + bnx2x_nic_unload(bp, UNLOAD_NORMAL, false); rc = bnx2x_nic_load(bp, LOAD_LOOPBACK_EXT); if (rc) { DP(BNX2X_MSG_ETHTOOL, @@ -2408,7 +2410,7 @@ static void bnx2x_self_test(struct net_device *dev, link_up = bp->link_vars.link_up; - bnx2x_nic_unload(bp, UNLOAD_NORMAL); + bnx2x_nic_unload(bp, UNLOAD_NORMAL, false); rc = bnx2x_nic_load(bp, LOAD_DIAG); if (rc) { etest->flags |= ETH_TEST_FL_FAILED; @@ -2440,7 +2442,7 @@ static void bnx2x_self_test(struct net_device *dev, etest->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE; } - bnx2x_nic_unload(bp, UNLOAD_NORMAL); + bnx2x_nic_unload(bp, UNLOAD_NORMAL, false); /* restore input for TX port IF */ REG_WR(bp, NIG_REG_EGRESS_UMP0_IN_EN + port*4, val); @@ -2934,7 +2936,7 @@ static int bnx2x_set_channels(struct net_device *dev, bnx2x_change_num_queues(bp, channels->combined_count); return 0; } - bnx2x_nic_unload(bp, UNLOAD_NORMAL); + bnx2x_nic_unload(bp, UNLOAD_NORMAL, true); bnx2x_change_num_queues(bp, channels->combined_count); return bnx2x_nic_load(bp, LOAD_NORMAL); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index df1400664ab3..c795cfc5a545 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -1286,6 +1286,9 @@ struct drv_func_mb { #define DRV_MSG_CODE_SET_MF_BW_MIN_MASK 0x00ff0000 #define DRV_MSG_CODE_SET_MF_BW_MAX_MASK 0xff000000 + #define DRV_MSG_CODE_UNLOAD_SKIP_LINK_RESET 0x00000002 + + #define DRV_MSG_CODE_LOAD_REQ_WITH_LFA 0x0000100a u32 fw_mb_header; #define FW_MSG_CODE_MASK 0xffff0000 #define FW_MSG_CODE_DRV_LOAD_COMMON 0x10100000 diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h index 21c3e42ec6a8..9165b89a4b19 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h @@ -359,7 +359,7 @@ int bnx2x_phy_init(struct link_params *params, struct link_vars *vars); to 0 */ int bnx2x_link_reset(struct link_params *params, struct link_vars *vars, u8 reset_ext_phy); - +int bnx2x_lfa_reset(struct link_params *params, struct link_vars *vars); /* bnx2x_link_update should be called upon link interrupt */ int bnx2x_link_update(struct link_params *params, struct link_vars *vars); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 21054987257a..dfc5b602bd17 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -2171,7 +2171,6 @@ void bnx2x_link_set(struct bnx2x *bp) { if (!BP_NOMCP(bp)) { bnx2x_acquire_phy_lock(bp); - bnx2x_link_reset(&bp->link_params, &bp->link_vars, 1); bnx2x_phy_init(&bp->link_params, &bp->link_vars); bnx2x_release_phy_lock(bp); @@ -2184,12 +2183,19 @@ static void bnx2x__link_reset(struct bnx2x *bp) { if (!BP_NOMCP(bp)) { bnx2x_acquire_phy_lock(bp); - bnx2x_link_reset(&bp->link_params, &bp->link_vars, 1); + bnx2x_lfa_reset(&bp->link_params, &bp->link_vars); bnx2x_release_phy_lock(bp); } else BNX2X_ERR("Bootcode is missing - can not reset link\n"); } +void bnx2x_force_link_reset(struct bnx2x *bp) +{ + bnx2x_acquire_phy_lock(bp); + bnx2x_link_reset(&bp->link_params, &bp->link_vars, 1); + bnx2x_release_phy_lock(bp); +} + u8 bnx2x_link_test(struct bnx2x *bp, u8 is_serdes) { u8 rc = 0; @@ -6757,7 +6763,6 @@ static int bnx2x_init_hw_port(struct bnx2x *bp) u32 low, high; u32 val; - bnx2x__link_reset(bp); DP(NETIF_MSG_HW, "starting port init port %d\n", port); @@ -8244,12 +8249,15 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode) * bnx2x_send_unload_done - send UNLOAD_DONE command to the MCP. * * @bp: driver handle + * @keep_link: true iff link should be kept up */ -void bnx2x_send_unload_done(struct bnx2x *bp) +void bnx2x_send_unload_done(struct bnx2x *bp, bool keep_link) { + u32 reset_param = keep_link ? DRV_MSG_CODE_UNLOAD_SKIP_LINK_RESET : 0; + /* Report UNLOAD_DONE to MCP */ if (!BP_NOMCP(bp)) - bnx2x_fw_command(bp, DRV_MSG_CODE_UNLOAD_DONE, 0); + bnx2x_fw_command(bp, DRV_MSG_CODE_UNLOAD_DONE, reset_param); } static int bnx2x_func_wait_started(struct bnx2x *bp) @@ -8318,7 +8326,7 @@ static int bnx2x_func_wait_started(struct bnx2x *bp) return 0; } -void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode) +void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link) { int port = BP_PORT(bp); int i, rc = 0; @@ -8440,7 +8448,7 @@ unload_error: /* Report UNLOAD_DONE to MCP */ - bnx2x_send_unload_done(bp); + bnx2x_send_unload_done(bp, keep_link); } void bnx2x_disable_close_the_gate(struct bnx2x *bp) @@ -8852,7 +8860,8 @@ int bnx2x_leader_reset(struct bnx2x *bp) * driver is owner of the HW */ if (!global && !BP_NOMCP(bp)) { - load_code = bnx2x_fw_command(bp, DRV_MSG_CODE_LOAD_REQ, 0); + load_code = bnx2x_fw_command(bp, DRV_MSG_CODE_LOAD_REQ, + DRV_MSG_CODE_LOAD_REQ_WITH_LFA); if (!load_code) { BNX2X_ERR("MCP response failure, aborting\n"); rc = -EAGAIN; @@ -8958,7 +8967,7 @@ static void bnx2x_parity_recover(struct bnx2x *bp) /* Stop the driver */ /* If interface has been removed - break */ - if (bnx2x_nic_unload(bp, UNLOAD_RECOVERY)) + if (bnx2x_nic_unload(bp, UNLOAD_RECOVERY, false)) return; bp->recovery_state = BNX2X_RECOVERY_WAIT; @@ -9124,7 +9133,7 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work) bp->sp_rtnl_state = 0; smp_mb(); - bnx2x_nic_unload(bp, UNLOAD_NORMAL); + bnx2x_nic_unload(bp, UNLOAD_NORMAL, true); bnx2x_nic_load(bp, LOAD_NORMAL); goto sp_rtnl_exit; @@ -9310,7 +9319,8 @@ static void __devinit bnx2x_prev_unload_undi_inc(struct bnx2x *bp, u8 port, static int __devinit bnx2x_prev_mcp_done(struct bnx2x *bp) { - u32 rc = bnx2x_fw_command(bp, DRV_MSG_CODE_UNLOAD_DONE, 0); + u32 rc = bnx2x_fw_command(bp, DRV_MSG_CODE_UNLOAD_DONE, + DRV_MSG_CODE_UNLOAD_SKIP_LINK_RESET); if (!rc) { BNX2X_ERR("MCP response failure, aborting\n"); return -EBUSY; @@ -11005,7 +11015,7 @@ static int bnx2x_close(struct net_device *dev) struct bnx2x *bp = netdev_priv(dev); /* Unload the driver, release IRQs */ - bnx2x_nic_unload(bp, UNLOAD_CLOSE); + bnx2x_nic_unload(bp, UNLOAD_CLOSE, false); /* Power off */ bnx2x_set_power_state(bp, PCI_D3hot); -- cgit v1.2.3 From 2960ed3468773b1a0b2533dd7a562673cc799437 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 24 Aug 2012 15:15:15 +0200 Subject: ARM: netx: move platform_data definitions Platform data for device drivers should be defined in include/linux/platform_data/*.h, not in the architecture and platform specific directories. This moves such data out of the netx include directories Signed-off-by: Arnd Bergmann Acked-by: Mark Brown Acked-by: Greg Kroah-Hartman Acked-by: Nicolas Pitre Acked-by: Sascha Hauer Cc: "David S. Miller" Cc: netdev@vger.kernel.org --- arch/arm/mach-netx/include/mach/eth.h | 27 --------------------------- arch/arm/mach-netx/nxdb500.c | 2 +- arch/arm/mach-netx/nxdkn.c | 2 +- arch/arm/mach-netx/nxeb500hmi.c | 2 +- drivers/net/ethernet/netx-eth.c | 2 +- include/linux/platform_data/eth-netx.h | 27 +++++++++++++++++++++++++++ 6 files changed, 31 insertions(+), 31 deletions(-) delete mode 100644 arch/arm/mach-netx/include/mach/eth.h create mode 100644 include/linux/platform_data/eth-netx.h (limited to 'drivers/net/ethernet') diff --git a/arch/arm/mach-netx/include/mach/eth.h b/arch/arm/mach-netx/include/mach/eth.h deleted file mode 100644 index 88af1ac28ead..000000000000 --- a/arch/arm/mach-netx/include/mach/eth.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * arch/arm/mach-netx/include/mach/eth.h - * - * Copyright (c) 2005 Sascha Hauer , Pengutronix - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * 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. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef ASMARM_ARCH_ETH_H -#define ASMARM_ARCH_ETH_H - -struct netxeth_platform_data { - unsigned int xcno; /* number of xmac/xpec engine this eth uses */ -}; - -#endif diff --git a/arch/arm/mach-netx/nxdb500.c b/arch/arm/mach-netx/nxdb500.c index 180ea899a48a..8b781ff7c9e9 100644 --- a/arch/arm/mach-netx/nxdb500.c +++ b/arch/arm/mach-netx/nxdb500.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include "generic.h" #include "fb.h" diff --git a/arch/arm/mach-netx/nxdkn.c b/arch/arm/mach-netx/nxdkn.c index 58009e29b20e..b26dbce334f2 100644 --- a/arch/arm/mach-netx/nxdkn.c +++ b/arch/arm/mach-netx/nxdkn.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include "generic.h" diff --git a/arch/arm/mach-netx/nxeb500hmi.c b/arch/arm/mach-netx/nxeb500hmi.c index 122e99826ef6..257382efafa0 100644 --- a/arch/arm/mach-netx/nxeb500hmi.c +++ b/arch/arm/mach-netx/nxeb500hmi.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include "generic.h" #include "fb.h" diff --git a/drivers/net/ethernet/netx-eth.c b/drivers/net/ethernet/netx-eth.c index 9d11ab7521bc..63e7af44366f 100644 --- a/drivers/net/ethernet/netx-eth.c +++ b/drivers/net/ethernet/netx-eth.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include /* XC Fifo Offsets */ #define EMPTY_PTR_FIFO(xcno) (0 + ((xcno) << 3)) /* Index of the empty pointer FIFO */ diff --git a/include/linux/platform_data/eth-netx.h b/include/linux/platform_data/eth-netx.h new file mode 100644 index 000000000000..88af1ac28ead --- /dev/null +++ b/include/linux/platform_data/eth-netx.h @@ -0,0 +1,27 @@ +/* + * arch/arm/mach-netx/include/mach/eth.h + * + * Copyright (c) 2005 Sascha Hauer , Pengutronix + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * 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. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef ASMARM_ARCH_ETH_H +#define ASMARM_ARCH_ETH_H + +struct netxeth_platform_data { + unsigned int xcno; /* number of xmac/xpec engine this eth uses */ +}; + +#endif -- cgit v1.2.3 From 2f66fd36a2be8e97a0ea774ba186adf24882cd10 Mon Sep 17 00:00:00 2001 From: Otto Estuardo Solares Cabrera Date: Fri, 24 Aug 2012 08:04:58 +0000 Subject: e1000: add byte queue limits Signed-off-by: Otto Estuardo Solares Cabrera Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000/e1000_main.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 0ae2fcfa5124..3a8368e42ede 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -2014,6 +2014,7 @@ static void e1000_clean_tx_ring(struct e1000_adapter *adapter, e1000_unmap_and_free_tx_resource(adapter, buffer_info); } + netdev_reset_queue(adapter->netdev); size = sizeof(struct e1000_buffer) * tx_ring->count; memset(tx_ring->buffer_info, 0, size); @@ -3262,6 +3263,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, nr_frags, mss); if (count) { + netdev_sent_queue(netdev, skb->len); skb_tx_timestamp(skb); e1000_tx_queue(adapter, tx_ring, tx_flags, count); @@ -3849,6 +3851,7 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter, unsigned int i, eop; unsigned int count = 0; unsigned int total_tx_bytes=0, total_tx_packets=0; + unsigned int bytes_compl = 0, pkts_compl = 0; i = tx_ring->next_to_clean; eop = tx_ring->buffer_info[i].next_to_watch; @@ -3866,6 +3869,11 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter, if (cleaned) { total_tx_packets += buffer_info->segs; total_tx_bytes += buffer_info->bytecount; + if (buffer_info->skb) { + bytes_compl += buffer_info->skb->len; + pkts_compl++; + } + } e1000_unmap_and_free_tx_resource(adapter, buffer_info); tx_desc->upper.data = 0; @@ -3879,6 +3887,8 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter, tx_ring->next_to_clean = i; + netdev_completed_queue(netdev, pkts_compl, bytes_compl); + #define TX_WAKE_THRESHOLD 32 if (unlikely(count && netif_carrier_ok(netdev) && E1000_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD)) { -- cgit v1.2.3 From b35d4d423c602c44d57c43347c0705a12eec6538 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 23 May 2012 05:39:25 +0000 Subject: ixgbe: Fix ordering of things so that PF correctly configures its VLANs The PF was not correctly registering any of its VLANs. As a result any VLAN tagged traffic from the VF would not be delivered to the PF because the VLAN was never assigned to the PF pool. In addition the VF was not allowed to receive traffic from VLAN 0 if it was allowed to receive untagged frames. This change corrects that so that it will correctly receive traffic from VLAN 0. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Tested-by: Sibai Li Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 9 +++++---- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 5 +++++ 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 1cbb34f507c9..ac9156735475 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3660,8 +3660,6 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) if (hw->mac.type == ixgbe_mac_82598EB) netif_set_gso_max_size(adapter->netdev, 32768); - hw->mac.ops.set_vfta(&adapter->hw, 0, 0, true); - #ifdef IXGBE_FCOE if (adapter->netdev->features & NETIF_F_FCOE_MTU) max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); @@ -3861,6 +3859,11 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) #ifdef CONFIG_IXGBE_DCB ixgbe_configure_dcb(adapter); #endif + /* + * We must restore virtualization before VLANs or else + * the VLVF registers will not be populated + */ + ixgbe_configure_virtualization(adapter); ixgbe_set_rx_mode(adapter->netdev); ixgbe_restore_vlan(adapter); @@ -3892,8 +3895,6 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) break; } - ixgbe_configure_virtualization(adapter); - #ifdef IXGBE_FCOE /* configure FCoE L2 filters, redirection table, and Rx control */ ixgbe_configure_fcoe(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 4fea8716ab64..3b1c914cbc50 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -346,6 +346,10 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter) static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, u32 vf) { + /* VLAN 0 is a special case, don't allow it to be removed */ + if (!vid && !add) + return 0; + return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add); } @@ -414,6 +418,7 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) VLAN_PRIO_SHIFT)), vf); ixgbe_set_vmolr(hw, vf, false); } else { + ixgbe_set_vf_vlan(adapter, true, 0, vf); ixgbe_set_vmvir(adapter, 0, vf); ixgbe_set_vmolr(hw, vf, true); } -- cgit v1.2.3 From 9f66d3eec4e5b32f299b6c7bf21dd54df1496f0b Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:09:06 +0000 Subject: ixgbe: Fix VF rate limiting to correctly account for more queues per VF This change fixes the assumptions of the rate limiting code that previously assumed that each VF would only ever have 2 queues. This update makes it so that we now use a queues per pool value that is determined based on the VMDq feature mask. Signed-off-by: Alexander Duyck Acked-By: John Fastabend Tested-by: Phil Schmitt Tested-by: Robert Garrett Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 100 +++++++++++++++---------- 1 file changed, 59 insertions(+), 41 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 3b1c914cbc50..dce48bf64d96 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -815,9 +815,9 @@ out: return err; } -static int ixgbe_link_mbps(int internal_link_speed) +static int ixgbe_link_mbps(struct ixgbe_adapter *adapter) { - switch (internal_link_speed) { + switch (adapter->link_speed) { case IXGBE_LINK_SPEED_100_FULL: return 100; case IXGBE_LINK_SPEED_1GB_FULL: @@ -829,27 +829,30 @@ static int ixgbe_link_mbps(int internal_link_speed) } } -static void ixgbe_set_vf_rate_limit(struct ixgbe_hw *hw, int vf, int tx_rate, - int link_speed) +static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf) { - int rf_dec, rf_int; - u32 bcnrc_val; + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + struct ixgbe_hw *hw = &adapter->hw; + u32 bcnrc_val = 0; + u16 queue, queues_per_pool; + u16 tx_rate = adapter->vfinfo[vf].tx_rate; + + if (tx_rate) { + /* start with base link speed value */ + bcnrc_val = adapter->vf_rate_link_speed; - if (tx_rate != 0) { /* Calculate the rate factor values to set */ - rf_int = link_speed / tx_rate; - rf_dec = (link_speed - (rf_int * tx_rate)); - rf_dec = (rf_dec * (1<mask); + + /* write value for all Tx queues belonging to VF */ + for (queue = 0; queue < queues_per_pool; queue++) { + unsigned int reg_idx = (vf * queues_per_pool) + queue; + + IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, reg_idx); + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val); + } } void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter) { - int actual_link_speed, i; - bool reset_rate = false; + int i; /* VF Tx rate limit was not set */ - if (adapter->vf_rate_link_speed == 0) + if (!adapter->vf_rate_link_speed) return; - actual_link_speed = ixgbe_link_mbps(adapter->link_speed); - if (actual_link_speed != adapter->vf_rate_link_speed) { - reset_rate = true; + if (ixgbe_link_mbps(adapter) != adapter->vf_rate_link_speed) { adapter->vf_rate_link_speed = 0; dev_info(&adapter->pdev->dev, - "Link speed has been changed. VF Transmit rate " - "is disabled\n"); + "Link speed has been changed. VF Transmit rate is disabled\n"); } for (i = 0; i < adapter->num_vfs; i++) { - if (reset_rate) + if (!adapter->vf_rate_link_speed) adapter->vfinfo[i].tx_rate = 0; - ixgbe_set_vf_rate_limit(&adapter->hw, i, - adapter->vfinfo[i].tx_rate, - actual_link_speed); + ixgbe_set_vf_rate_limit(adapter, i); } } int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - struct ixgbe_hw *hw = &adapter->hw; - int actual_link_speed; + int link_speed; - actual_link_speed = ixgbe_link_mbps(adapter->link_speed); - if ((vf >= adapter->num_vfs) || (!adapter->link_up) || - (tx_rate > actual_link_speed) || (actual_link_speed != 10000) || - ((tx_rate != 0) && (tx_rate <= 10))) - /* rate limit cannot be set to 10Mb or less in 10Gb adapters */ + /* verify VF is active */ + if (vf >= adapter->num_vfs) return -EINVAL; - adapter->vf_rate_link_speed = actual_link_speed; - adapter->vfinfo[vf].tx_rate = (u16)tx_rate; - ixgbe_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed); + /* verify link is up */ + if (!adapter->link_up) + return -EINVAL; + + /* verify we are linked at 10Gbps */ + link_speed = ixgbe_link_mbps(adapter); + if (link_speed != 10000) + return -EINVAL; + + /* rate limit cannot be less than 10Mbs or greater than link speed */ + if (tx_rate && ((tx_rate <= 10) || (tx_rate > link_speed))) + return -EINVAL; + + /* store values */ + adapter->vf_rate_link_speed = link_speed; + adapter->vfinfo[vf].tx_rate = tx_rate; + + /* update hardware configuration */ + ixgbe_set_vf_rate_limit(adapter, vf); return 0; } -- cgit v1.2.3 From d6ea07545226cd2590fc21601051dc1493c5ef9e Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Wed, 8 Aug 2012 06:28:37 +0000 Subject: ixgbe: fix reporting of spoofed packets Use %u instead of %d to display u32 variable. Signed-off-by: Emil Tantilov Tested-by: Phil Schmitt Tested-by: Robert Garrett Tested-by: Robert Garrett Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ac9156735475..e641f14eddcd 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5573,7 +5573,7 @@ static void ixgbe_spoof_check(struct ixgbe_adapter *adapter) if (!ssvpc) return; - e_warn(drv, "%d Spoofed packets detected\n", ssvpc); + e_warn(drv, "%u Spoofed packets detected\n", ssvpc); } /** -- cgit v1.2.3 From 00949167d6f34f83e9e185ab4f7a3a94bf4c5a1c Mon Sep 17 00:00:00 2001 From: Catherine Sullivan Date: Fri, 10 Aug 2012 01:59:10 +0000 Subject: ixgbe: add debugfs support This patch adds debugfs support to the ixgbe driver to give users the ability to access kernel information and to simulate kernel events. The filesystem is set up in the following driver/PCI-instance hierarchy: |-- ixgbe |-- PCI instance | |-- attribute files Signed-off-by: Catherine Sullivan Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/Makefile | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 10 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c | 79 ++++++++++++++++++++++++ drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 17 +++++ 4 files changed, 106 insertions(+), 2 deletions(-) create mode 100644 drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index 5fd5d04c26c9..89f40e51fc13 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -32,7 +32,7 @@ obj-$(CONFIG_IXGBE) += ixgbe.o -ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ +ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o ixgbe_debugfs.o\ ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index bffcf1f2357a..5bd26763554c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -597,6 +597,9 @@ struct ixgbe_adapter { #ifdef CONFIG_IXGBE_HWMON struct hwmon_buff ixgbe_hwmon_buff; #endif /* CONFIG_IXGBE_HWMON */ +#ifdef CONFIG_DEBUG_FS + struct dentry *ixgbe_dbg_adapter; +#endif /*CONFIG_DEBUG_FS*/ }; struct ixgbe_fdir_filter { @@ -725,7 +728,12 @@ extern int ixgbe_fcoe_get_hbainfo(struct net_device *netdev, struct netdev_fcoe_hbainfo *info); extern u8 ixgbe_fcoe_get_tc(struct ixgbe_adapter *adapter); #endif /* IXGBE_FCOE */ - +#ifdef CONFIG_DEBUG_FS +extern void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter); +extern void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter); +extern void ixgbe_dbg_init(void); +extern void ixgbe_dbg_exit(void); +#endif /* CONFIG_DEBUG_FS */ static inline struct netdev_queue *txring_txq(const struct ixgbe_ring *ring) { return netdev_get_tx_queue(ring->netdev, ring->queue_index); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c new file mode 100644 index 000000000000..0b08b6c7497c --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -0,0 +1,79 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2012 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#ifdef CONFIG_DEBUG_FS + +#include +#include + +#include "ixgbe.h" + +static struct dentry *ixgbe_dbg_root; + +/** + * ixgbe_dbg_adapter_init - setup the debugfs directory for the adapter + * @adapter: the adapter that is starting up + **/ +void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) +{ + const char *name = pci_name(adapter->pdev); + + adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root); + if (!adapter->ixgbe_dbg_adapter) + e_dev_err("debugfs entry for %s failed\n", name); +} + +/** + * ixgbe_dbg_adapter_exit - clear out the adapter's debugfs entries + * @pf: the pf that is stopping + **/ +void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter) +{ + if (adapter->ixgbe_dbg_adapter) + debugfs_remove_recursive(adapter->ixgbe_dbg_adapter); + adapter->ixgbe_dbg_adapter = NULL; +} + +/** + * ixgbe_dbg_init - start up debugfs for the driver + **/ +void ixgbe_dbg_init(void) +{ + ixgbe_dbg_root = debugfs_create_dir(ixgbe_driver_name, NULL); + if (ixgbe_dbg_root == NULL) + pr_err("init of debugfs failed\n"); +} + +/** + * ixgbe_dbg_exit - clean out the driver's debugfs entries + **/ +void ixgbe_dbg_exit(void) +{ + debugfs_remove_recursive(ixgbe_dbg_root); +} + +#endif /* CONFIG_DEBUG_FS */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index e641f14eddcd..b3b846b32deb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7448,6 +7448,10 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, e_err(probe, "failed to allocate sysfs resources\n"); #endif /* CONFIG_IXGBE_HWMON */ +#ifdef CONFIG_DEBUG_FS + ixgbe_dbg_adapter_init(adapter); +#endif /* CONFIG_DEBUG_FS */ + return 0; err_register: @@ -7482,6 +7486,10 @@ static void __devexit ixgbe_remove(struct pci_dev *pdev) struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; +#ifdef CONFIG_DEBUG_FS + ixgbe_dbg_adapter_exit(adapter); +#endif /*CONFIG_DEBUG_FS */ + set_bit(__IXGBE_DOWN, &adapter->state); cancel_work_sync(&adapter->service_task); @@ -7737,6 +7745,10 @@ static int __init ixgbe_init_module(void) pr_info("%s - version %s\n", ixgbe_driver_string, ixgbe_driver_version); pr_info("%s\n", ixgbe_copyright); +#ifdef CONFIG_DEBUG_FS + ixgbe_dbg_init(); +#endif /* CONFIG_DEBUG_FS */ + #ifdef CONFIG_IXGBE_DCA dca_register_notify(&dca_notifier); #endif @@ -7759,6 +7771,11 @@ static void __exit ixgbe_exit_module(void) dca_unregister_notify(&dca_notifier); #endif pci_unregister_driver(&ixgbe_driver); + +#ifdef CONFIG_DEBUG_FS + ixgbe_dbg_exit(); +#endif /* CONFIG_DEBUG_FS */ + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } -- cgit v1.2.3 From 826ff0de1178669eac123d706f78b455aa0f2c4d Mon Sep 17 00:00:00 2001 From: Catherine Sullivan Date: Fri, 10 Aug 2012 01:59:15 +0000 Subject: ixgbe: added netdev_ops file to debugfs Added the netdev_ops file to debugfs with a command to call the ndo_tx_timeout function to give users the ability to simulate a tx_timeout call made by the kernel. Signed-off-by: Catherine Sullivan Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c | 107 ++++++++++++++++++++++- 1 file changed, 105 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c index 0b08b6c7497c..2dd169ee5e68 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -34,6 +34,102 @@ static struct dentry *ixgbe_dbg_root; +static char ixgbe_dbg_netdev_ops_buf[256] = ""; + +/** + * ixgbe_dbg_netdev_ops_open - prep the debugfs netdev_ops data item + * @inode: inode that was opened + * @filp: file info + * + * Stash the adapter pointer hiding in the inode into the file pointer + * where we can find it later in the read and write calls + **/ +static int ixgbe_dbg_netdev_ops_open(struct inode *inode, struct file *filp) +{ + filp->private_data = inode->i_private; + return 0; +} + +/** + * ixgbe_dbg_netdev_ops_read - read for netdev_ops datum + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_netdev_ops_read(struct file *filp, + char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + char buf[256]; + int bytes_not_copied; + int len; + + /* don't allow partial reads */ + if (*ppos != 0) + return 0; + + len = snprintf(buf, sizeof(buf), "%s: %s\n", + adapter->netdev->name, ixgbe_dbg_netdev_ops_buf); + if (count < len) + return -ENOSPC; + bytes_not_copied = copy_to_user(buffer, buf, len); + if (bytes_not_copied < 0) + return bytes_not_copied; + + *ppos = len; + return len; +} + +/** + * ixgbe_dbg_netdev_ops_write - write into netdev_ops datum + * @filp: the opened file + * @buffer: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_netdev_ops_write(struct file *filp, + const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + int bytes_not_copied; + + /* don't allow partial writes */ + if (*ppos != 0) + return 0; + if (count >= sizeof(ixgbe_dbg_netdev_ops_buf)) + return -ENOSPC; + + bytes_not_copied = copy_from_user(ixgbe_dbg_netdev_ops_buf, + buffer, count); + if (bytes_not_copied < 0) + return bytes_not_copied; + else if (bytes_not_copied < count) + count -= bytes_not_copied; + else + return -ENOSPC; + ixgbe_dbg_netdev_ops_buf[count] = '\0'; + + if (strncmp(ixgbe_dbg_netdev_ops_buf, "tx_timeout", 10) == 0) { + adapter->netdev->netdev_ops->ndo_tx_timeout(adapter->netdev); + e_dev_info("tx_timeout called\n"); + } else { + e_dev_info("Unknown command: %s\n", ixgbe_dbg_netdev_ops_buf); + e_dev_info("Available commands:\n"); + e_dev_info(" tx_timeout\n"); + } + return count; +} + +static const struct file_operations ixgbe_dbg_netdev_ops_fops = { + .owner = THIS_MODULE, + .open = ixgbe_dbg_netdev_ops_open, + .read = ixgbe_dbg_netdev_ops_read, + .write = ixgbe_dbg_netdev_ops_write, +}; + /** * ixgbe_dbg_adapter_init - setup the debugfs directory for the adapter * @adapter: the adapter that is starting up @@ -41,10 +137,17 @@ static struct dentry *ixgbe_dbg_root; void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) { const char *name = pci_name(adapter->pdev); - + struct dentry *pfile; adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root); - if (!adapter->ixgbe_dbg_adapter) + if (adapter->ixgbe_dbg_adapter) { + pfile = debugfs_create_file("netdev_ops", 0600, + adapter->ixgbe_dbg_adapter, adapter, + &ixgbe_dbg_netdev_ops_fops); + if (!pfile) + e_dev_err("debugfs netdev_ops for %s failed\n", name); + } else { e_dev_err("debugfs entry for %s failed\n", name); + } } /** -- cgit v1.2.3 From 91fbd8f081e22a3d296b45766eaf5045925f9313 Mon Sep 17 00:00:00 2001 From: Catherine Sullivan Date: Fri, 10 Aug 2012 01:59:21 +0000 Subject: ixgbe: added reg_ops file to debugfs Added the reg_ops file to debugfs with commands to read and write a register to give users the ability to read and write individual registers on the fly. Signed-off-by: Catherine Sullivan Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c | 118 +++++++++++++++++++++++ 1 file changed, 118 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c index 2dd169ee5e68..8d3a21889099 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -34,6 +34,119 @@ static struct dentry *ixgbe_dbg_root; +static char ixgbe_dbg_reg_ops_buf[256] = ""; + +/** + * ixgbe_dbg_reg_ops_open - prep the debugfs pokee data item when opened + * @inode: inode that was opened + * @filp: file info + * + * Stash the adapter pointer hiding in the inode into the file pointer where + * we can find it later in the read and write calls + **/ +static int ixgbe_dbg_reg_ops_open(struct inode *inode, struct file *filp) +{ + filp->private_data = inode->i_private; + return 0; +} + +/** + * ixgbe_dbg_reg_ops_read - read for reg_ops datum + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_reg_ops_read(struct file *filp, char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + char buf[256]; + int bytes_not_copied; + int len; + + /* don't allow partial reads */ + if (*ppos != 0) + return 0; + + len = snprintf(buf, sizeof(buf), "%s: %s\n", + adapter->netdev->name, ixgbe_dbg_reg_ops_buf); + if (count < len) + return -ENOSPC; + bytes_not_copied = copy_to_user(buffer, buf, len); + if (bytes_not_copied < 0) + return bytes_not_copied; + + *ppos = len; + return len; +} + +/** + * ixgbe_dbg_reg_ops_write - write into reg_ops datum + * @filp: the opened file + * @buffer: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_reg_ops_write(struct file *filp, + const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + int bytes_not_copied; + + /* don't allow partial writes */ + if (*ppos != 0) + return 0; + if (count >= sizeof(ixgbe_dbg_reg_ops_buf)) + return -ENOSPC; + + bytes_not_copied = copy_from_user(ixgbe_dbg_reg_ops_buf, buffer, count); + if (bytes_not_copied < 0) + return bytes_not_copied; + else if (bytes_not_copied < count) + count -= bytes_not_copied; + else + return -ENOSPC; + ixgbe_dbg_reg_ops_buf[count] = '\0'; + + if (strncmp(ixgbe_dbg_reg_ops_buf, "write", 5) == 0) { + u32 reg, value; + int cnt; + cnt = sscanf(&ixgbe_dbg_reg_ops_buf[5], "%x %x", ®, &value); + if (cnt == 2) { + IXGBE_WRITE_REG(&adapter->hw, reg, value); + value = IXGBE_READ_REG(&adapter->hw, reg); + e_dev_info("write: 0x%08x = 0x%08x\n", reg, value); + } else { + e_dev_info("write \n"); + } + } else if (strncmp(ixgbe_dbg_reg_ops_buf, "read", 4) == 0) { + u32 reg, value; + int cnt; + cnt = sscanf(&ixgbe_dbg_reg_ops_buf[4], "%x", ®); + if (cnt == 1) { + value = IXGBE_READ_REG(&adapter->hw, reg); + e_dev_info("read 0x%08x = 0x%08x\n", reg, value); + } else { + e_dev_info("read \n"); + } + } else { + e_dev_info("Unknown command %s\n", ixgbe_dbg_reg_ops_buf); + e_dev_info("Available commands:\n"); + e_dev_info(" read \n"); + e_dev_info(" write \n"); + } + return count; +} + +static const struct file_operations ixgbe_dbg_reg_ops_fops = { + .owner = THIS_MODULE, + .open = ixgbe_dbg_reg_ops_open, + .read = ixgbe_dbg_reg_ops_read, + .write = ixgbe_dbg_reg_ops_write, +}; + static char ixgbe_dbg_netdev_ops_buf[256] = ""; /** @@ -140,6 +253,11 @@ void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) struct dentry *pfile; adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root); if (adapter->ixgbe_dbg_adapter) { + pfile = debugfs_create_file("reg_ops", 0600, + adapter->ixgbe_dbg_adapter, adapter, + &ixgbe_dbg_reg_ops_fops); + if (!pfile) + e_dev_err("debugfs reg_ops for %s failed\n", name); pfile = debugfs_create_file("netdev_ops", 0600, adapter->ixgbe_dbg_adapter, adapter, &ixgbe_dbg_netdev_ops_fops); -- cgit v1.2.3 From 4ffdf91a5feae6f0f1486d038fcbba461345fa62 Mon Sep 17 00:00:00 2001 From: Mark Rustad Date: Wed, 18 Jul 2012 06:05:50 +0000 Subject: ixgbe: Improve statistics accuracy for DDP traffic Noticed that the byte and packet count statistics are under- counting traffic handled by the DDP offload when there is more than one DDP completion processed in a single call to ixgbe_clean_rx_irq. This patch fixes that. I tried to optimize the setting of the rss value so that it only would have to be computed once, and only when there is a DDP completion present. Signed-off-by: Mark Rustad Tested-by: Phil Schmitt Tested-by: Ross Brattain Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 32 +++++++++++++-------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index b3b846b32deb..2dc9d91e2b67 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1785,7 +1785,8 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, unsigned int total_rx_bytes = 0, total_rx_packets = 0; #ifdef IXGBE_FCOE struct ixgbe_adapter *adapter = q_vector->adapter; - int ddp_bytes = 0; + int ddp_bytes; + unsigned int mss = 0; #endif /* IXGBE_FCOE */ u16 cleaned_count = ixgbe_desc_unused(rx_ring); @@ -1839,6 +1840,20 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, /* if ddp, not passing to ULD unless for FCP_RSP or error */ if (ixgbe_rx_is_fcoe(rx_ring, rx_desc)) { ddp_bytes = ixgbe_fcoe_ddp(adapter, rx_desc, skb); + /* include DDPed FCoE data */ + if (ddp_bytes > 0) { + if (!mss) { + mss = rx_ring->netdev->mtu - + sizeof(struct fcoe_hdr) - + sizeof(struct fc_frame_header) - + sizeof(struct fcoe_crc_eof); + if (mss > 512) + mss &= ~511; + } + total_rx_bytes += ddp_bytes; + total_rx_packets += DIV_ROUND_UP(ddp_bytes, + mss); + } if (!ddp_bytes) { dev_kfree_skb_any(skb); continue; @@ -1852,21 +1867,6 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, budget--; } while (likely(budget)); -#ifdef IXGBE_FCOE - /* include DDPed FCoE data */ - if (ddp_bytes > 0) { - unsigned int mss; - - mss = rx_ring->netdev->mtu - sizeof(struct fcoe_hdr) - - sizeof(struct fc_frame_header) - - sizeof(struct fcoe_crc_eof); - if (mss > 512) - mss &= ~511; - total_rx_bytes += ddp_bytes; - total_rx_packets += DIV_ROUND_UP(ddp_bytes, mss); - } - -#endif /* IXGBE_FCOE */ u64_stats_update_begin(&rx_ring->syncp); rx_ring->stats.packets += total_rx_packets; rx_ring->stats.bytes += total_rx_bytes; -- cgit v1.2.3 From 3c89f6d0d4aa92ff252c17f8f6b5c8983ae2b77e Mon Sep 17 00:00:00 2001 From: Matthew Vick Date: Fri, 10 Aug 2012 05:40:43 +0000 Subject: igb: Tidy up wrapping for CONFIG_IGB_PTP. For users without CONFIG_IGB_PTP=y, we should not be compiling any PTP code into the driver. Tidy up the wrapping in igb to support this. Cc: Richard Cochran Signed-off-by: Matthew Vick Acked-by: Jacob Keller Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 8 ++++++-- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 ++-- drivers/net/ethernet/intel/igb/igb_main.c | 23 +++++++++++++++++------ 3 files changed, 25 insertions(+), 10 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 0c9f62caa8fa..a3b5b908448a 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -34,9 +34,11 @@ #include "e1000_mac.h" #include "e1000_82575.h" +#ifdef CONFIG_IGB_PTP #include #include #include +#endif /* CONFIG_IGB_PTP */ #include #include @@ -376,12 +378,15 @@ struct igb_adapter { int node; u32 *shadow_vfta; +#ifdef CONFIG_IGB_PTP struct ptp_clock *ptp_clock; struct ptp_clock_info caps; struct delayed_work overflow_work; spinlock_t tmreg_lock; struct cyclecounter cc; struct timecounter tc; +#endif /* CONFIG_IGB_PTP */ + char fw_version[32]; }; @@ -436,12 +441,11 @@ extern void igb_set_fw_version(struct igb_adapter *); #ifdef CONFIG_IGB_PTP extern void igb_ptp_init(struct igb_adapter *adapter); extern void igb_ptp_remove(struct igb_adapter *adapter); - extern void igb_systim_to_hwtstamp(struct igb_adapter *adapter, struct skb_shared_hwtstamps *hwtstamps, u64 systim); +#endif /* CONFIG_IGB_PTP */ -#endif static inline s32 igb_reset_phy(struct e1000_hw *hw) { if (hw->phy.ops.reset) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index a2944412a55e..0c4e29aa24c7 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2338,8 +2338,8 @@ static int igb_ethtool_get_ts_info(struct net_device *dev, return 0; } +#endif /* CONFIG_IGB_PTP */ -#endif static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, @@ -2370,7 +2370,7 @@ static const struct ethtool_ops igb_ethtool_ops = { .complete = igb_ethtool_complete, #ifdef CONFIG_IGB_PTP .get_ts_info = igb_ethtool_get_ts_info, -#endif +#endif /* CONFIG_IGB_PTP */ }; void igb_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 73cc273ef98b..03477d7451e4 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2180,11 +2180,12 @@ static int __devinit igb_probe(struct pci_dev *pdev, } #endif + #ifdef CONFIG_IGB_PTP /* do hw tstamp init after resetting */ igb_ptp_init(adapter); +#endif /* CONFIG_IGB_PTP */ -#endif dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n"); /* print bus type/speed/width info */ dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n", @@ -2260,8 +2261,8 @@ static void __devexit igb_remove(struct pci_dev *pdev) pm_runtime_get_noresume(&pdev->dev); #ifdef CONFIG_IGB_PTP igb_ptp_remove(adapter); +#endif /* CONFIG_IGB_PTP */ -#endif /* * The watchdog timer may be rescheduled, so explicitly * disable watchdog from being rescheduled. @@ -3184,8 +3185,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, srrctl |= (PAGE_SIZE / 2) >> E1000_SRRCTL_BSIZEPKT_SHIFT; #endif srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; +#ifdef CONFIG_IGB_PTP if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; +#endif /* CONFIG_IGB_PTP */ /* Only set Drop Enable if we are supporting multiple queues */ if (adapter->vfs_allocated_count || adapter->num_rx_queues > 1) srrctl |= E1000_SRRCTL_DROP_EN; @@ -4229,9 +4232,11 @@ static __le32 igb_tx_cmd_type(u32 tx_flags) if (tx_flags & IGB_TX_FLAGS_VLAN) cmd_type |= cpu_to_le32(E1000_ADVTXD_DCMD_VLE); +#ifdef CONFIG_IGB_PTP /* set timestamp bit if present */ if (tx_flags & IGB_TX_FLAGS_TSTAMP) cmd_type |= cpu_to_le32(E1000_ADVTXD_MAC_TSTAMP); +#endif /* CONFIG_IGB_PTP */ /* set segmentation bits for TSO */ if (tx_flags & IGB_TX_FLAGS_TSO) @@ -4462,10 +4467,12 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, first->bytecount = skb->len; first->gso_segs = 1; +#ifdef CONFIG_IGB_PTP if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGB_TX_FLAGS_TSTAMP; } +#endif /* CONFIG_IGB_PTP */ if (vlan_tx_tag_present(skb)) { tx_flags |= IGB_TX_FLAGS_VLAN; @@ -5772,8 +5779,8 @@ static void igb_tx_hwtstamp(struct igb_q_vector *q_vector, igb_systim_to_hwtstamp(adapter, &shhwtstamps, regval); skb_tstamp_tx(buffer_info->skb, &shhwtstamps); } +#endif /* CONFIG_IGB_PTP */ -#endif /** * igb_clean_tx_irq - Reclaim resources after transmit completes * @q_vector: pointer to q_vector containing needed info @@ -5821,8 +5828,8 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) #ifdef CONFIG_IGB_PTP /* retrieve hardware timestamp */ igb_tx_hwtstamp(q_vector, tx_buffer); +#endif /* CONFIG_IGB_PTP */ -#endif /* free the skb */ dev_kfree_skb_any(tx_buffer->skb); tx_buffer->skb = NULL; @@ -6033,8 +6040,8 @@ static void igb_rx_hwtstamp(struct igb_q_vector *q_vector, igb_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); } +#endif /* CONFIG_IGB_PTP */ -#endif static void igb_rx_vlan(struct igb_ring *ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) @@ -6147,7 +6154,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget) #ifdef CONFIG_IGB_PTP igb_rx_hwtstamp(q_vector, rx_desc, skb); -#endif +#endif /* CONFIG_IGB_PTP */ igb_rx_hash(rx_ring, rx_desc, skb); igb_rx_checksum(rx_ring, rx_desc, skb); igb_rx_vlan(rx_ring, rx_desc, skb); @@ -6340,6 +6347,7 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return 0; } +#ifdef CONFIG_IGB_PTP /** * igb_hwtstamp_ioctl - control hardware time stamping * @netdev: @@ -6514,6 +6522,7 @@ static int igb_hwtstamp_ioctl(struct net_device *netdev, return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; } +#endif /* CONFIG_IGB_PTP */ /** * igb_ioctl - @@ -6528,8 +6537,10 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) case SIOCGMIIREG: case SIOCSMIIREG: return igb_mii_ioctl(netdev, ifr, cmd); +#ifdef CONFIG_IGB_PTP case SIOCSHWTSTAMP: return igb_hwtstamp_ioctl(netdev, ifr, cmd); +#endif /* CONFIG_IGB_PTP */ default: return -EOPNOTSUPP; } -- cgit v1.2.3 From a79f4f88261d7fd492121daf85beafff663f1f01 Mon Sep 17 00:00:00 2001 From: Matthew Vick Date: Fri, 10 Aug 2012 05:40:44 +0000 Subject: igb: Update PTP function names/variables and locations. Where possible, move PTP-related functions into igb_ptp.c and update the names of functions and variables to match the established coding style in the files and specify that they are PTP-specific. Cc: Richard Cochran Signed-off-by: Matthew Vick Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 17 +- drivers/net/ethernet/intel/igb/igb_ethtool.c | 34 +- drivers/net/ethernet/intel/igb/igb_main.c | 257 +------------- drivers/net/ethernet/intel/igb/igb_ptp.c | 485 ++++++++++++++++++++------- 4 files changed, 398 insertions(+), 395 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index a3b5b908448a..797346998d52 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -344,7 +344,6 @@ struct igb_adapter { /* OS defined structs */ struct pci_dev *pdev; - struct hwtstamp_config hwtstamp_config; spinlock_t stats64_lock; struct rtnl_link_stats64 stats64; @@ -380,8 +379,8 @@ struct igb_adapter { #ifdef CONFIG_IGB_PTP struct ptp_clock *ptp_clock; - struct ptp_clock_info caps; - struct delayed_work overflow_work; + struct ptp_clock_info ptp_caps; + struct delayed_work ptp_overflow_work; spinlock_t tmreg_lock; struct cyclecounter cc; struct timecounter tc; @@ -440,10 +439,14 @@ extern void igb_power_up_link(struct igb_adapter *); extern void igb_set_fw_version(struct igb_adapter *); #ifdef CONFIG_IGB_PTP extern void igb_ptp_init(struct igb_adapter *adapter); -extern void igb_ptp_remove(struct igb_adapter *adapter); -extern void igb_systim_to_hwtstamp(struct igb_adapter *adapter, - struct skb_shared_hwtstamps *hwtstamps, - u64 systim); +extern void igb_ptp_stop(struct igb_adapter *adapter); +extern void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector, + struct igb_tx_buffer *buffer_info); +extern void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb); +extern int igb_ptp_hwtstamp_ioctl(struct net_device *netdev, + struct ifreq *ifr, int cmd); #endif /* CONFIG_IGB_PTP */ static inline s32 igb_reset_phy(struct e1000_hw *hw) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 0c4e29aa24c7..ffed4d068591 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2295,21 +2295,8 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } } -static int igb_ethtool_begin(struct net_device *netdev) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - pm_runtime_get_sync(&adapter->pdev->dev); - return 0; -} - -static void igb_ethtool_complete(struct net_device *netdev) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - pm_runtime_put(&adapter->pdev->dev); -} - #ifdef CONFIG_IGB_PTP -static int igb_ethtool_get_ts_info(struct net_device *dev, +static int igb_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { struct igb_adapter *adapter = netdev_priv(dev); @@ -2340,6 +2327,19 @@ static int igb_ethtool_get_ts_info(struct net_device *dev, } #endif /* CONFIG_IGB_PTP */ +static int igb_ethtool_begin(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + pm_runtime_get_sync(&adapter->pdev->dev); + return 0; +} + +static void igb_ethtool_complete(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + pm_runtime_put(&adapter->pdev->dev); +} + static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, @@ -2366,11 +2366,11 @@ static const struct ethtool_ops igb_ethtool_ops = { .get_ethtool_stats = igb_get_ethtool_stats, .get_coalesce = igb_get_coalesce, .set_coalesce = igb_set_coalesce, - .begin = igb_ethtool_begin, - .complete = igb_ethtool_complete, #ifdef CONFIG_IGB_PTP - .get_ts_info = igb_ethtool_get_ts_info, + .get_ts_info = igb_get_ts_info, #endif /* CONFIG_IGB_PTP */ + .begin = igb_ethtool_begin, + .complete = igb_ethtool_complete, }; void igb_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 03477d7451e4..6e39f0ca9fc4 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2260,7 +2260,7 @@ static void __devexit igb_remove(struct pci_dev *pdev) pm_runtime_get_noresume(&pdev->dev); #ifdef CONFIG_IGB_PTP - igb_ptp_remove(adapter); + igb_ptp_stop(adapter); #endif /* CONFIG_IGB_PTP */ /* @@ -5750,37 +5750,6 @@ static int igb_poll(struct napi_struct *napi, int budget) return 0; } -#ifdef CONFIG_IGB_PTP -/** - * igb_tx_hwtstamp - utility function which checks for TX time stamp - * @q_vector: pointer to q_vector containing needed info - * @buffer: pointer to igb_tx_buffer structure - * - * If we were asked to do hardware stamping and such a time stamp is - * available, then it must have been for this skb here because we only - * allow only one such packet into the queue. - */ -static void igb_tx_hwtstamp(struct igb_q_vector *q_vector, - struct igb_tx_buffer *buffer_info) -{ - struct igb_adapter *adapter = q_vector->adapter; - struct e1000_hw *hw = &adapter->hw; - struct skb_shared_hwtstamps shhwtstamps; - u64 regval; - - /* if skb does not support hw timestamp or TX stamp not valid exit */ - if (likely(!(buffer_info->tx_flags & IGB_TX_FLAGS_TSTAMP)) || - !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID)) - return; - - regval = rd32(E1000_TXSTMPL); - regval |= (u64)rd32(E1000_TXSTMPH) << 32; - - igb_systim_to_hwtstamp(adapter, &shhwtstamps, regval); - skb_tstamp_tx(buffer_info->skb, &shhwtstamps); -} -#endif /* CONFIG_IGB_PTP */ - /** * igb_clean_tx_irq - Reclaim resources after transmit completes * @q_vector: pointer to q_vector containing needed info @@ -5827,7 +5796,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) #ifdef CONFIG_IGB_PTP /* retrieve hardware timestamp */ - igb_tx_hwtstamp(q_vector, tx_buffer); + igb_ptp_tx_hwtstamp(q_vector, tx_buffer); #endif /* CONFIG_IGB_PTP */ /* free the skb */ @@ -6001,47 +5970,6 @@ static inline void igb_rx_hash(struct igb_ring *ring, skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); } -#ifdef CONFIG_IGB_PTP -static void igb_rx_hwtstamp(struct igb_q_vector *q_vector, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) -{ - struct igb_adapter *adapter = q_vector->adapter; - struct e1000_hw *hw = &adapter->hw; - u64 regval; - - if (!igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP | - E1000_RXDADV_STAT_TS)) - return; - - /* - * If this bit is set, then the RX registers contain the time stamp. No - * other packet will be time stamped until we read these registers, so - * read the registers to make them available again. Because only one - * packet can be time stamped at a time, we know that the register - * values must belong to this one here and therefore we don't need to - * compare any of the additional attributes stored for it. - * - * If nothing went wrong, then it should have a shared tx_flags that we - * can turn into a skb_shared_hwtstamps. - */ - if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - u32 *stamp = (u32 *)skb->data; - regval = le32_to_cpu(*(stamp + 2)); - regval |= (u64)le32_to_cpu(*(stamp + 3)) << 32; - skb_pull(skb, IGB_TS_HDR_LEN); - } else { - if(!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID)) - return; - - regval = rd32(E1000_RXSTMPL); - regval |= (u64)rd32(E1000_RXSTMPH) << 32; - } - - igb_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); -} -#endif /* CONFIG_IGB_PTP */ - static void igb_rx_vlan(struct igb_ring *ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) @@ -6153,7 +6081,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget) } #ifdef CONFIG_IGB_PTP - igb_rx_hwtstamp(q_vector, rx_desc, skb); + igb_ptp_rx_hwtstamp(q_vector, rx_desc, skb); #endif /* CONFIG_IGB_PTP */ igb_rx_hash(rx_ring, rx_desc, skb); igb_rx_checksum(rx_ring, rx_desc, skb); @@ -6347,183 +6275,6 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return 0; } -#ifdef CONFIG_IGB_PTP -/** - * igb_hwtstamp_ioctl - control hardware time stamping - * @netdev: - * @ifreq: - * @cmd: - * - * Outgoing time stamping can be enabled and disabled. Play nice and - * disable it when requested, although it shouldn't case any overhead - * when no packet needs it. At most one packet in the queue may be - * marked for time stamping, otherwise it would be impossible to tell - * for sure to which packet the hardware time stamp belongs. - * - * Incoming time stamping has to be configured via the hardware - * filters. Not all combinations are supported, in particular event - * type has to be specified. Matching the kind of event packet is - * not supported, with the exception of "all V2 events regardless of - * level 2 or 4". - * - **/ -static int igb_hwtstamp_ioctl(struct net_device *netdev, - struct ifreq *ifr, int cmd) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - struct e1000_hw *hw = &adapter->hw; - struct hwtstamp_config config; - u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED; - u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; - u32 tsync_rx_cfg = 0; - bool is_l4 = false; - bool is_l2 = false; - u32 regval; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - - switch (config.tx_type) { - case HWTSTAMP_TX_OFF: - tsync_tx_ctl = 0; - case HWTSTAMP_TX_ON: - break; - default: - return -ERANGE; - } - - switch (config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - tsync_rx_ctl = 0; - break; - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_ALL: - /* - * register TSYNCRXCFG must be set, therefore it is not - * possible to time stamp both Sync and Delay_Req messages - * => fall back to time stamping all packets - */ - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; - tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE; - is_l4 = true; - break; - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; - tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE; - is_l4 = true; - break; - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; - tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE; - is_l2 = true; - is_l4 = true; - config.rx_filter = HWTSTAMP_FILTER_SOME; - break; - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; - tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE; - is_l2 = true; - is_l4 = true; - config.rx_filter = HWTSTAMP_FILTER_SOME; - break; - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2; - config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; - is_l2 = true; - is_l4 = true; - break; - default: - return -ERANGE; - } - - if (hw->mac.type == e1000_82575) { - if (tsync_rx_ctl | tsync_tx_ctl) - return -EINVAL; - return 0; - } - - /* - * Per-packet timestamping only works if all packets are - * timestamped, so enable timestamping in all packets as - * long as one rx filter was configured. - */ - if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) { - tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; - } - - /* enable/disable TX */ - regval = rd32(E1000_TSYNCTXCTL); - regval &= ~E1000_TSYNCTXCTL_ENABLED; - regval |= tsync_tx_ctl; - wr32(E1000_TSYNCTXCTL, regval); - - /* enable/disable RX */ - regval = rd32(E1000_TSYNCRXCTL); - regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK); - regval |= tsync_rx_ctl; - wr32(E1000_TSYNCRXCTL, regval); - - /* define which PTP packets are time stamped */ - wr32(E1000_TSYNCRXCFG, tsync_rx_cfg); - - /* define ethertype filter for timestamped packets */ - if (is_l2) - wr32(E1000_ETQF(3), - (E1000_ETQF_FILTER_ENABLE | /* enable filter */ - E1000_ETQF_1588 | /* enable timestamping */ - ETH_P_1588)); /* 1588 eth protocol type */ - else - wr32(E1000_ETQF(3), 0); - -#define PTP_PORT 319 - /* L4 Queue Filter[3]: filter by destination port and protocol */ - if (is_l4) { - u32 ftqf = (IPPROTO_UDP /* UDP */ - | E1000_FTQF_VF_BP /* VF not compared */ - | E1000_FTQF_1588_TIME_STAMP /* Enable Timestamping */ - | E1000_FTQF_MASK); /* mask all inputs */ - ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */ - - wr32(E1000_IMIR(3), htons(PTP_PORT)); - wr32(E1000_IMIREXT(3), - (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP)); - if (hw->mac.type == e1000_82576) { - /* enable source port check */ - wr32(E1000_SPQF(3), htons(PTP_PORT)); - ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP; - } - wr32(E1000_FTQF(3), ftqf); - } else { - wr32(E1000_FTQF(3), E1000_FTQF_MASK); - } - wrfl(); - - adapter->hwtstamp_config = config; - - /* clear TX/RX time stamp registers, just to be sure */ - regval = rd32(E1000_TXSTMPH); - regval = rd32(E1000_RXSTMPH); - - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} -#endif /* CONFIG_IGB_PTP */ - /** * igb_ioctl - * @netdev: @@ -6539,7 +6290,7 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return igb_mii_ioctl(netdev, ifr, cmd); #ifdef CONFIG_IGB_PTP case SIOCSHWTSTAMP: - return igb_hwtstamp_ioctl(netdev, ifr, cmd); + return igb_ptp_hwtstamp_ioctl(netdev, ifr, cmd); #endif /* CONFIG_IGB_PTP */ default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index c846ea9131a3..34e0d698cbb4 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -69,22 +69,22 @@ * 2^40 * 10^-9 / 60 = 18.3 minutes. */ -#define IGB_OVERFLOW_PERIOD (HZ * 60 * 9) -#define INCPERIOD_82576 (1 << E1000_TIMINCA_16NS_SHIFT) -#define INCVALUE_82576_MASK ((1 << E1000_TIMINCA_16NS_SHIFT) - 1) -#define INCVALUE_82576 (16 << IGB_82576_TSYNC_SHIFT) -#define IGB_NBITS_82580 40 +#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 9) +#define INCPERIOD_82576 (1 << E1000_TIMINCA_16NS_SHIFT) +#define INCVALUE_82576_MASK ((1 << E1000_TIMINCA_16NS_SHIFT) - 1) +#define INCVALUE_82576 (16 << IGB_82576_TSYNC_SHIFT) +#define IGB_NBITS_82580 40 /* * SYSTIM read access for the 82576 */ -static cycle_t igb_82576_systim_read(const struct cyclecounter *cc) +static cycle_t igb_ptp_read_82576(const struct cyclecounter *cc) { - u64 val; - u32 lo, hi; struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc); struct e1000_hw *hw = &igb->hw; + u64 val; + u32 lo, hi; lo = rd32(E1000_SYSTIML); hi = rd32(E1000_SYSTIMH); @@ -99,12 +99,12 @@ static cycle_t igb_82576_systim_read(const struct cyclecounter *cc) * SYSTIM read access for the 82580 */ -static cycle_t igb_82580_systim_read(const struct cyclecounter *cc) +static cycle_t igb_ptp_read_82580(const struct cyclecounter *cc) { - u64 val; - u32 lo, hi, jk; struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc); struct e1000_hw *hw = &igb->hw; + u64 val; + u32 lo, hi, jk; /* * The timestamp latches on lowest register read. For the 82580 @@ -121,17 +121,63 @@ static cycle_t igb_82580_systim_read(const struct cyclecounter *cc) return val; } +/** + * igb_ptp_systim_to_hwtstamp - convert system time value to hw timestamp + * @adapter: board private structure + * @hwtstamps: timestamp structure to update + * @systim: unsigned 64bit system time value. + * + * We need to convert the system time value stored in the RX/TXSTMP registers + * into a hwtstamp which can be used by the upper level timestamping functions. + * + * The 'tmreg_lock' spinlock is used to protect the consistency of the + * system time value. This is needed because reading the 64 bit time + * value involves reading two (or three) 32 bit registers. The first + * read latches the value. Ditto for writing. + * + * In addition, here have extended the system time with an overflow + * counter in software. + **/ +static void igb_ptp_systim_to_hwtstamp(struct igb_adapter *adapter, + struct skb_shared_hwtstamps *hwtstamps, + u64 systim) +{ + unsigned long flags; + u64 ns; + + switch (adapter->hw.mac.type) { + case e1000_i210: + case e1000_i211: + case e1000_i350: + case e1000_82580: + case e1000_82576: + break; + default: + return; + } + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + + ns = timecounter_cyc2time(&adapter->tc, systim); + + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + memset(hwtstamps, 0, sizeof(*hwtstamps)); + hwtstamps->hwtstamp = ns_to_ktime(ns); +} + /* * PTP clock operations */ -static int ptp_82576_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int igb_ptp_adjfreq_82576(struct ptp_clock_info *ptp, s32 ppb) { + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + int neg_adj = 0; u64 rate; u32 incvalue; - int neg_adj = 0; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); - struct e1000_hw *hw = &igb->hw; if (ppb < 0) { neg_adj = 1; @@ -153,13 +199,14 @@ static int ptp_82576_adjfreq(struct ptp_clock_info *ptp, s32 ppb) return 0; } -static int ptp_82580_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int igb_ptp_adjfreq_82580(struct ptp_clock_info *ptp, s32 ppb) { + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + int neg_adj = 0; u64 rate; u32 inca; - int neg_adj = 0; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); - struct e1000_hw *hw = &igb->hw; if (ppb < 0) { neg_adj = 1; @@ -178,11 +225,12 @@ static int ptp_82580_adjfreq(struct ptp_clock_info *ptp, s32 ppb) return 0; } -static int igb_adjtime(struct ptp_clock_info *ptp, s64 delta) +static int igb_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { - s64 now; + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); unsigned long flags; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); + s64 now; spin_lock_irqsave(&igb->tmreg_lock, flags); @@ -195,12 +243,13 @@ static int igb_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int igb_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int igb_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) { + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + unsigned long flags; u64 ns; u32 remainder; - unsigned long flags; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); spin_lock_irqsave(&igb->tmreg_lock, flags); @@ -214,11 +263,13 @@ static int igb_gettime(struct ptp_clock_info *ptp, struct timespec *ts) return 0; } -static int igb_settime(struct ptp_clock_info *ptp, const struct timespec *ts) +static int igb_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec *ts) { - u64 ns; + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); unsigned long flags; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); + u64 ns; ns = ts->tv_sec * 1000000000ULL; ns += ts->tv_nsec; @@ -232,29 +283,265 @@ static int igb_settime(struct ptp_clock_info *ptp, const struct timespec *ts) return 0; } -static int ptp_82576_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, int on) +static int igb_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) { return -EOPNOTSUPP; } -static int ptp_82580_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, int on) +static void igb_ptp_overflow_check(struct work_struct *work) { - return -EOPNOTSUPP; + struct igb_adapter *igb = + container_of(work, struct igb_adapter, ptp_overflow_work.work); + struct timespec ts; + + igb_ptp_gettime(&igb->ptp_caps, &ts); + + pr_debug("igb overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec); + + schedule_delayed_work(&igb->ptp_overflow_work, + IGB_SYSTIM_OVERFLOW_PERIOD); } -static void igb_overflow_check(struct work_struct *work) +/** + * igb_ptp_tx_hwtstamp - utility function which checks for TX time stamp + * @q_vector: pointer to q_vector containing needed info + * @buffer: pointer to igb_tx_buffer structure + * + * If we were asked to do hardware stamping and such a time stamp is + * available, then it must have been for this skb here because we only + * allow only one such packet into the queue. + */ +void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector, + struct igb_tx_buffer *buffer_info) { - struct timespec ts; - struct igb_adapter *igb = - container_of(work, struct igb_adapter, overflow_work.work); + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + struct skb_shared_hwtstamps shhwtstamps; + u64 regval; - igb_gettime(&igb->caps, &ts); + /* if skb does not support hw timestamp or TX stamp not valid exit */ + if (likely(!(buffer_info->tx_flags & IGB_TX_FLAGS_TSTAMP)) || + !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID)) + return; - pr_debug("igb overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec); + regval = rd32(E1000_TXSTMPL); + regval |= (u64)rd32(E1000_TXSTMPH) << 32; - schedule_delayed_work(&igb->overflow_work, IGB_OVERFLOW_PERIOD); + igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + skb_tstamp_tx(buffer_info->skb, &shhwtstamps); +} + +void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + u64 regval; + + if (!igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP | + E1000_RXDADV_STAT_TS)) + return; + + /* + * If this bit is set, then the RX registers contain the time stamp. No + * other packet will be time stamped until we read these registers, so + * read the registers to make them available again. Because only one + * packet can be time stamped at a time, we know that the register + * values must belong to this one here and therefore we don't need to + * compare any of the additional attributes stored for it. + * + * If nothing went wrong, then it should have a shared tx_flags that we + * can turn into a skb_shared_hwtstamps. + */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + u32 *stamp = (u32 *)skb->data; + regval = le32_to_cpu(*(stamp + 2)); + regval |= (u64)le32_to_cpu(*(stamp + 3)) << 32; + skb_pull(skb, IGB_TS_HDR_LEN); + } else { + if (!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID)) + return; + + regval = rd32(E1000_RXSTMPL); + regval |= (u64)rd32(E1000_RXSTMPH) << 32; + } + + igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); +} + +/** + * igb_ptp_hwtstamp_ioctl - control hardware time stamping + * @netdev: + * @ifreq: + * @cmd: + * + * Outgoing time stamping can be enabled and disabled. Play nice and + * disable it when requested, although it shouldn't case any overhead + * when no packet needs it. At most one packet in the queue may be + * marked for time stamping, otherwise it would be impossible to tell + * for sure to which packet the hardware time stamp belongs. + * + * Incoming time stamping has to be configured via the hardware + * filters. Not all combinations are supported, in particular event + * type has to be specified. Matching the kind of event packet is + * not supported, with the exception of "all V2 events regardless of + * level 2 or 4". + * + **/ +int igb_ptp_hwtstamp_ioctl(struct net_device *netdev, + struct ifreq *ifr, int cmd) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct hwtstamp_config config; + u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED; + u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; + u32 tsync_rx_cfg = 0; + bool is_l4 = false; + bool is_l2 = false; + u32 regval; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* reserved for future extensions */ + if (config.flags) + return -EINVAL; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + tsync_tx_ctl = 0; + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + tsync_rx_ctl = 0; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_ALL: + /* + * register TSYNCRXCFG must be set, therefore it is not + * possible to time stamp both Sync and Delay_Req messages + * => fall back to time stamping all packets + */ + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE; + is_l4 = true; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE; + is_l4 = true; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE; + is_l2 = true; + is_l4 = true; + config.rx_filter = HWTSTAMP_FILTER_SOME; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE; + is_l2 = true; + is_l4 = true; + config.rx_filter = HWTSTAMP_FILTER_SOME; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2; + config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + is_l2 = true; + is_l4 = true; + break; + default: + return -ERANGE; + } + + if (hw->mac.type == e1000_82575) { + if (tsync_rx_ctl | tsync_tx_ctl) + return -EINVAL; + return 0; + } + + /* + * Per-packet timestamping only works if all packets are + * timestamped, so enable timestamping in all packets as + * long as one rx filter was configured. + */ + if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) { + tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; + } + + /* enable/disable TX */ + regval = rd32(E1000_TSYNCTXCTL); + regval &= ~E1000_TSYNCTXCTL_ENABLED; + regval |= tsync_tx_ctl; + wr32(E1000_TSYNCTXCTL, regval); + + /* enable/disable RX */ + regval = rd32(E1000_TSYNCRXCTL); + regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK); + regval |= tsync_rx_ctl; + wr32(E1000_TSYNCRXCTL, regval); + + /* define which PTP packets are time stamped */ + wr32(E1000_TSYNCRXCFG, tsync_rx_cfg); + + /* define ethertype filter for timestamped packets */ + if (is_l2) + wr32(E1000_ETQF(3), + (E1000_ETQF_FILTER_ENABLE | /* enable filter */ + E1000_ETQF_1588 | /* enable timestamping */ + ETH_P_1588)); /* 1588 eth protocol type */ + else + wr32(E1000_ETQF(3), 0); + +#define PTP_PORT 319 + /* L4 Queue Filter[3]: filter by destination port and protocol */ + if (is_l4) { + u32 ftqf = (IPPROTO_UDP /* UDP */ + | E1000_FTQF_VF_BP /* VF not compared */ + | E1000_FTQF_1588_TIME_STAMP /* Enable Timestamping */ + | E1000_FTQF_MASK); /* mask all inputs */ + ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */ + + wr32(E1000_IMIR(3), htons(PTP_PORT)); + wr32(E1000_IMIREXT(3), + (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP)); + if (hw->mac.type == e1000_82576) { + /* enable source port check */ + wr32(E1000_SPQF(3), htons(PTP_PORT)); + ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP; + } + wr32(E1000_FTQF(3), ftqf); + } else { + wr32(E1000_FTQF(3), E1000_FTQF_MASK); + } + wrfl(); + + /* clear TX/RX time stamp registers, just to be sure */ + regval = rd32(E1000_TXSTMPH); + regval = rd32(E1000_RXSTMPH); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; } void igb_ptp_init(struct igb_adapter *adapter) @@ -266,39 +553,39 @@ void igb_ptp_init(struct igb_adapter *adapter) case e1000_i211: case e1000_i350: case e1000_82580: - adapter->caps.owner = THIS_MODULE; - strcpy(adapter->caps.name, "igb-82580"); - adapter->caps.max_adj = 62499999; - adapter->caps.n_ext_ts = 0; - adapter->caps.pps = 0; - adapter->caps.adjfreq = ptp_82580_adjfreq; - adapter->caps.adjtime = igb_adjtime; - adapter->caps.gettime = igb_gettime; - adapter->caps.settime = igb_settime; - adapter->caps.enable = ptp_82580_enable; - adapter->cc.read = igb_82580_systim_read; - adapter->cc.mask = CLOCKSOURCE_MASK(IGB_NBITS_82580); - adapter->cc.mult = 1; - adapter->cc.shift = 0; + adapter->ptp_caps.owner = THIS_MODULE; + strcpy(adapter->ptp_caps.name, "igb-82580"); + adapter->ptp_caps.max_adj = 62499999; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.pps = 0; + adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580; + adapter->ptp_caps.adjtime = igb_ptp_adjtime; + adapter->ptp_caps.gettime = igb_ptp_gettime; + adapter->ptp_caps.settime = igb_ptp_settime; + adapter->ptp_caps.enable = igb_ptp_enable; + adapter->cc.read = igb_ptp_read_82580; + adapter->cc.mask = CLOCKSOURCE_MASK(IGB_NBITS_82580); + adapter->cc.mult = 1; + adapter->cc.shift = 0; /* Enable the timer functions by clearing bit 31. */ wr32(E1000_TSAUXC, 0x0); break; case e1000_82576: - adapter->caps.owner = THIS_MODULE; - strcpy(adapter->caps.name, "igb-82576"); - adapter->caps.max_adj = 1000000000; - adapter->caps.n_ext_ts = 0; - adapter->caps.pps = 0; - adapter->caps.adjfreq = ptp_82576_adjfreq; - adapter->caps.adjtime = igb_adjtime; - adapter->caps.gettime = igb_gettime; - adapter->caps.settime = igb_settime; - adapter->caps.enable = ptp_82576_enable; - adapter->cc.read = igb_82576_systim_read; - adapter->cc.mask = CLOCKSOURCE_MASK(64); - adapter->cc.mult = 1; - adapter->cc.shift = IGB_82576_TSYNC_SHIFT; + adapter->ptp_caps.owner = THIS_MODULE; + strcpy(adapter->ptp_caps.name, "igb-82576"); + adapter->ptp_caps.max_adj = 1000000000; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.pps = 0; + adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576; + adapter->ptp_caps.adjtime = igb_ptp_adjtime; + adapter->ptp_caps.gettime = igb_ptp_gettime; + adapter->ptp_caps.settime = igb_ptp_settime; + adapter->ptp_caps.enable = igb_ptp_enable; + adapter->cc.read = igb_ptp_read_82576; + adapter->cc.mask = CLOCKSOURCE_MASK(64); + adapter->cc.mult = 1; + adapter->cc.shift = IGB_82576_TSYNC_SHIFT; /* Dial the nominal frequency. */ wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576); break; @@ -313,13 +600,14 @@ void igb_ptp_init(struct igb_adapter *adapter) timecounter_init(&adapter->tc, &adapter->cc, ktime_to_ns(ktime_get_real())); - INIT_DELAYED_WORK(&adapter->overflow_work, igb_overflow_check); + INIT_DELAYED_WORK(&adapter->ptp_overflow_work, igb_ptp_overflow_check); spin_lock_init(&adapter->tmreg_lock); - schedule_delayed_work(&adapter->overflow_work, IGB_OVERFLOW_PERIOD); + schedule_delayed_work(&adapter->ptp_overflow_work, + IGB_SYSTIM_OVERFLOW_PERIOD); - adapter->ptp_clock = ptp_clock_register(&adapter->caps); + adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps); if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n"); @@ -328,7 +616,13 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->netdev->name); } -void igb_ptp_remove(struct igb_adapter *adapter) +/** + * igb_ptp_stop - Disable PTP device and stop the overflow check. + * @adapter: Board private structure. + * + * This function stops the PTP support and cancels the delayed work. + **/ +void igb_ptp_stop(struct igb_adapter *adapter) { switch (adapter->hw.mac.type) { case e1000_i211: @@ -336,7 +630,7 @@ void igb_ptp_remove(struct igb_adapter *adapter) case e1000_i350: case e1000_82580: case e1000_82576: - cancel_delayed_work_sync(&adapter->overflow_work); + cancel_delayed_work_sync(&adapter->ptp_overflow_work); break; default: return; @@ -348,48 +642,3 @@ void igb_ptp_remove(struct igb_adapter *adapter) adapter->netdev->name); } } - -/** - * igb_systim_to_hwtstamp - convert system time value to hw timestamp - * @adapter: board private structure - * @hwtstamps: timestamp structure to update - * @systim: unsigned 64bit system time value. - * - * We need to convert the system time value stored in the RX/TXSTMP registers - * into a hwtstamp which can be used by the upper level timestamping functions. - * - * The 'tmreg_lock' spinlock is used to protect the consistency of the - * system time value. This is needed because reading the 64 bit time - * value involves reading two (or three) 32 bit registers. The first - * read latches the value. Ditto for writing. - * - * In addition, here have extended the system time with an overflow - * counter in software. - **/ -void igb_systim_to_hwtstamp(struct igb_adapter *adapter, - struct skb_shared_hwtstamps *hwtstamps, - u64 systim) -{ - u64 ns; - unsigned long flags; - - switch (adapter->hw.mac.type) { - case e1000_i210: - case e1000_i211: - case e1000_i350: - case e1000_82580: - case e1000_82576: - break; - default: - return; - } - - spin_lock_irqsave(&adapter->tmreg_lock, flags); - - ns = timecounter_cyc2time(&adapter->tc, systim); - - spin_unlock_irqrestore(&adapter->tmreg_lock, flags); - - memset(hwtstamps, 0, sizeof(*hwtstamps)); - hwtstamps->hwtstamp = ns_to_ktime(ns); -} -- cgit v1.2.3 From a9188028fd8a446413be48e7f6490f2d18a8d07e Mon Sep 17 00:00:00 2001 From: Matthew Vick Date: Tue, 28 Aug 2012 06:33:05 +0000 Subject: igb: Correct PTP support query from ethtool. Update ethtool_get_ts_info to not report any supported functionality on 82575 and add support for V2 Sync and V2 Delay packets. In the case where CONFIG_IGB_PTP is not defined, we should be reporting default values. v2: Correct the function to return EOPNOTSUPP when there is no PTP support or the device does not support PTP. Also fix minor whitespace issue. Signed-off-by: Matthew Vick Cc: Richard Cochran Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_ethtool.c | 62 +++++++++++++++++----------- 1 file changed, 38 insertions(+), 24 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index ffed4d068591..2ea012849825 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2295,37 +2295,53 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } } -#ifdef CONFIG_IGB_PTP static int igb_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *info) + struct ethtool_ts_info *info) { struct igb_adapter *adapter = netdev_priv(dev); - info->so_timestamping = - SOF_TIMESTAMPING_TX_HARDWARE | - SOF_TIMESTAMPING_RX_HARDWARE | - SOF_TIMESTAMPING_RAW_HARDWARE; + switch (adapter->hw.mac.type) { +#ifdef CONFIG_IGB_PTP + case e1000_82576: + case e1000_82580: + case e1000_i350: + case e1000_i210: + case e1000_i211: + info->so_timestamping = + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; - if (adapter->ptp_clock) - info->phc_index = ptp_clock_index(adapter->ptp_clock); - else - info->phc_index = -1; + if (adapter->ptp_clock) + info->phc_index = ptp_clock_index(adapter->ptp_clock); + else + info->phc_index = -1; - info->tx_types = - (1 << HWTSTAMP_TX_OFF) | - (1 << HWTSTAMP_TX_ON); + info->tx_types = + (1 << HWTSTAMP_TX_OFF) | + (1 << HWTSTAMP_TX_ON); - info->rx_filters = - (1 << HWTSTAMP_FILTER_NONE) | - (1 << HWTSTAMP_FILTER_ALL) | - (1 << HWTSTAMP_FILTER_SOME) | - (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); + info->rx_filters = 1 << HWTSTAMP_FILTER_NONE; - return 0; -} + /* 82576 does not support timestamping all packets. */ + if (adapter->hw.mac.type >= e1000_82580) + info->rx_filters |= 1 << HWTSTAMP_FILTER_ALL; + else + info->rx_filters |= + (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); + + return 0; #endif /* CONFIG_IGB_PTP */ + default: + return -EOPNOTSUPP; + } +} static int igb_ethtool_begin(struct net_device *netdev) { @@ -2366,9 +2382,7 @@ static const struct ethtool_ops igb_ethtool_ops = { .get_ethtool_stats = igb_get_ethtool_stats, .get_coalesce = igb_get_coalesce, .set_coalesce = igb_set_coalesce, -#ifdef CONFIG_IGB_PTP .get_ts_info = igb_get_ts_info, -#endif /* CONFIG_IGB_PTP */ .begin = igb_ethtool_begin, .complete = igb_ethtool_complete, }; -- cgit v1.2.3 From 201987e3d03fadf0d87980981b7421198e3e5922 Mon Sep 17 00:00:00 2001 From: Matthew Vick Date: Fri, 10 Aug 2012 05:40:46 +0000 Subject: igb: Store the MAC address in the name in the PTP struct. Change the name of the adapter in the PTP struct to enable easier correlation between interface and PTP device. Cc: Richard Cochran Signed-off-by: Matthew Vick Acked-by: Jacob Keller Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_ptp.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 34e0d698cbb4..e69555f1f73e 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -547,14 +547,15 @@ int igb_ptp_hwtstamp_ioctl(struct net_device *netdev, void igb_ptp_init(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; switch (hw->mac.type) { case e1000_i210: case e1000_i211: case e1000_i350: case e1000_82580: + snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); adapter->ptp_caps.owner = THIS_MODULE; - strcpy(adapter->ptp_caps.name, "igb-82580"); adapter->ptp_caps.max_adj = 62499999; adapter->ptp_caps.n_ext_ts = 0; adapter->ptp_caps.pps = 0; @@ -570,10 +571,9 @@ void igb_ptp_init(struct igb_adapter *adapter) /* Enable the timer functions by clearing bit 31. */ wr32(E1000_TSAUXC, 0x0); break; - case e1000_82576: + snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); adapter->ptp_caps.owner = THIS_MODULE; - strcpy(adapter->ptp_caps.name, "igb-82576"); adapter->ptp_caps.max_adj = 1000000000; adapter->ptp_caps.n_ext_ts = 0; adapter->ptp_caps.pps = 0; @@ -589,7 +589,6 @@ void igb_ptp_init(struct igb_adapter *adapter) /* Dial the nominal frequency. */ wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576); break; - default: adapter->ptp_clock = NULL; return; -- cgit v1.2.3 From 1f6e8178d6851951876ad8524f4de7a0e6b111be Mon Sep 17 00:00:00 2001 From: Matthew Vick Date: Sat, 18 Aug 2012 07:26:33 +0000 Subject: igb: Prevent dropped Tx timestamps via work items and interrupts. In rare circumstances, it's possible a descriptor writeback will occur before a timestamped Tx packet will go out on the wire, leading to the driver believing the hardware failed to timestamp the packet. Schedule a work item for 82576 and use the available time sync interrupt registers on 82580 and above to account for this. Cc: Richard Cochran Signed-off-by: Matthew Vick Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/e1000_defines.h | 5 ++ drivers/net/ethernet/intel/igb/e1000_regs.h | 2 + drivers/net/ethernet/intel/igb/igb.h | 8 +- drivers/net/ethernet/intel/igb/igb_main.c | 61 +++++++++++++-- drivers/net/ethernet/intel/igb/igb_ptp.c | 102 +++++++++++++++++++++---- 5 files changed, 153 insertions(+), 25 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index ec7e4fe3e3ee..0b27e8fe06bf 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -360,6 +360,7 @@ #define E1000_ICR_RXDMT0 0x00000010 /* rx desc min. threshold (0) */ #define E1000_ICR_RXT0 0x00000080 /* rx timer intr (ring 0) */ #define E1000_ICR_VMMB 0x00000100 /* VM MB event */ +#define E1000_ICR_TS 0x00080000 /* Time Sync Interrupt */ #define E1000_ICR_DRSTA 0x40000000 /* Device Reset Asserted */ /* If this bit asserted, the driver should claim the interrupt */ #define E1000_ICR_INT_ASSERTED 0x80000000 @@ -399,6 +400,7 @@ #define E1000_IMS_TXDW E1000_ICR_TXDW /* Transmit desc written back */ #define E1000_IMS_LSC E1000_ICR_LSC /* Link Status Change */ #define E1000_IMS_VMMB E1000_ICR_VMMB /* Mail box activity */ +#define E1000_IMS_TS E1000_ICR_TS /* Time Sync Interrupt */ #define E1000_IMS_RXSEQ E1000_ICR_RXSEQ /* rx sequence error */ #define E1000_IMS_RXDMT0 E1000_ICR_RXDMT0 /* rx desc min. threshold */ #define E1000_IMS_RXT0 E1000_ICR_RXT0 /* rx timer intr */ @@ -510,6 +512,9 @@ #define E1000_TIMINCA_16NS_SHIFT 24 +#define E1000_TSICR_TXTS 0x00000002 +#define E1000_TSIM_TXTS 0x00000002 + #define E1000_MDICNFG_EXT_MDIO 0x80000000 /* MDI ext/int destination */ #define E1000_MDICNFG_COM_MDIO 0x40000000 /* MDI shared w/ lan 0 */ #define E1000_MDICNFG_PHY_MASK 0x03E00000 diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 28394bea5253..faec840a5a8a 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -91,6 +91,8 @@ #define E1000_TIMINCA 0x0B608 /* Increment attributes register - RW */ #define E1000_TSAUXC 0x0B640 /* Timesync Auxiliary Control register */ #define E1000_SYSTIMR 0x0B6F8 /* System time register Residue */ +#define E1000_TSICR 0x0B66C /* Interrupt Cause Register */ +#define E1000_TSIM 0x0B674 /* Interrupt Mask Register */ /* Filtering Registers */ #define E1000_SAQF(_n) (0x5980 + 4 * (_n)) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 797346998d52..43c8e2914263 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -381,6 +381,8 @@ struct igb_adapter { struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_caps; struct delayed_work ptp_overflow_work; + struct work_struct ptp_tx_work; + struct sk_buff *ptp_tx_skb; spinlock_t tmreg_lock; struct cyclecounter cc; struct timecounter tc; @@ -394,6 +396,7 @@ struct igb_adapter { #define IGB_FLAG_QUAD_PORT_A (1 << 2) #define IGB_FLAG_QUEUE_PAIRS (1 << 3) #define IGB_FLAG_DMAC (1 << 4) +#define IGB_FLAG_PTP (1 << 5) /* DMA Coalescing defines */ #define IGB_MIN_TXPBSIZE 20408 @@ -440,8 +443,9 @@ extern void igb_set_fw_version(struct igb_adapter *); #ifdef CONFIG_IGB_PTP extern void igb_ptp_init(struct igb_adapter *adapter); extern void igb_ptp_stop(struct igb_adapter *adapter); -extern void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector, - struct igb_tx_buffer *buffer_info); +extern void igb_ptp_reset(struct igb_adapter *adapter); +extern void igb_ptp_tx_work(struct work_struct *work); +extern void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter); extern void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 6e39f0ca9fc4..19d7666dfccb 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1751,6 +1751,11 @@ void igb_reset(struct igb_adapter *adapter) /* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */ wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE); +#ifdef CONFIG_IGB_PTP + /* Re-enable PTP, where applicable. */ + igb_ptp_reset(adapter); +#endif /* CONFIG_IGB_PTP */ + igb_get_phy_info(hw); } @@ -4234,7 +4239,7 @@ static __le32 igb_tx_cmd_type(u32 tx_flags) #ifdef CONFIG_IGB_PTP /* set timestamp bit if present */ - if (tx_flags & IGB_TX_FLAGS_TSTAMP) + if (unlikely(tx_flags & IGB_TX_FLAGS_TSTAMP)) cmd_type |= cpu_to_le32(E1000_ADVTXD_MAC_TSTAMP); #endif /* CONFIG_IGB_PTP */ @@ -4445,6 +4450,9 @@ static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size) netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, struct igb_ring *tx_ring) { +#ifdef CONFIG_IGB_PTP + struct igb_adapter *adapter = netdev_priv(tx_ring->netdev); +#endif /* CONFIG_IGB_PTP */ struct igb_tx_buffer *first; int tso; u32 tx_flags = 0; @@ -4468,9 +4476,14 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, first->gso_segs = 1; #ifdef CONFIG_IGB_PTP - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + !(adapter->ptp_tx_skb))) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGB_TX_FLAGS_TSTAMP; + + adapter->ptp_tx_skb = skb_get(skb); + if (adapter->hw.mac.type == e1000_82576) + schedule_work(&adapter->ptp_tx_work); } #endif /* CONFIG_IGB_PTP */ @@ -4859,6 +4872,19 @@ static irqreturn_t igb_msix_other(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } +#ifdef CONFIG_IGB_PTP + if (icr & E1000_ICR_TS) { + u32 tsicr = rd32(E1000_TSICR); + + if (tsicr & E1000_TSICR_TXTS) { + /* acknowledge the interrupt */ + wr32(E1000_TSICR, E1000_TSICR_TXTS); + /* retrieve hardware timestamp */ + schedule_work(&adapter->ptp_tx_work); + } + } +#endif /* CONFIG_IGB_PTP */ + wr32(E1000_EIMS, adapter->eims_other); return IRQ_HANDLED; @@ -5650,6 +5676,19 @@ static irqreturn_t igb_intr_msi(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } +#ifdef CONFIG_IGB_PTP + if (icr & E1000_ICR_TS) { + u32 tsicr = rd32(E1000_TSICR); + + if (tsicr & E1000_TSICR_TXTS) { + /* acknowledge the interrupt */ + wr32(E1000_TSICR, E1000_TSICR_TXTS); + /* retrieve hardware timestamp */ + schedule_work(&adapter->ptp_tx_work); + } + } +#endif /* CONFIG_IGB_PTP */ + napi_schedule(&q_vector->napi); return IRQ_HANDLED; @@ -5691,6 +5730,19 @@ static irqreturn_t igb_intr(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } +#ifdef CONFIG_IGB_PTP + if (icr & E1000_ICR_TS) { + u32 tsicr = rd32(E1000_TSICR); + + if (tsicr & E1000_TSICR_TXTS) { + /* acknowledge the interrupt */ + wr32(E1000_TSICR, E1000_TSICR_TXTS); + /* retrieve hardware timestamp */ + schedule_work(&adapter->ptp_tx_work); + } + } +#endif /* CONFIG_IGB_PTP */ + napi_schedule(&q_vector->napi); return IRQ_HANDLED; @@ -5794,11 +5846,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) total_bytes += tx_buffer->bytecount; total_packets += tx_buffer->gso_segs; -#ifdef CONFIG_IGB_PTP - /* retrieve hardware timestamp */ - igb_ptp_tx_hwtstamp(q_vector, tx_buffer); -#endif /* CONFIG_IGB_PTP */ - /* free the skb */ dev_kfree_skb_any(tx_buffer->skb); tx_buffer->skb = NULL; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index e69555f1f73e..d57060c0813d 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -289,6 +289,31 @@ static int igb_ptp_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } +/** + * igb_ptp_tx_work + * @work: pointer to work struct + * + * This work function polls the TSYNCTXCTL valid bit to determine when a + * timestamp has been taken for the current stored skb. + */ +void igb_ptp_tx_work(struct work_struct *work) +{ + struct igb_adapter *adapter = container_of(work, struct igb_adapter, + ptp_tx_work); + struct e1000_hw *hw = &adapter->hw; + u32 tsynctxctl; + + if (!adapter->ptp_tx_skb) + return; + + tsynctxctl = rd32(E1000_TSYNCTXCTL); + if (tsynctxctl & E1000_TSYNCTXCTL_VALID) + igb_ptp_tx_hwtstamp(adapter); + else + /* reschedule to check later */ + schedule_work(&adapter->ptp_tx_work); +} + static void igb_ptp_overflow_check(struct work_struct *work) { struct igb_adapter *igb = @@ -305,31 +330,25 @@ static void igb_ptp_overflow_check(struct work_struct *work) /** * igb_ptp_tx_hwtstamp - utility function which checks for TX time stamp - * @q_vector: pointer to q_vector containing needed info - * @buffer: pointer to igb_tx_buffer structure + * @adapter: Board private structure. * * If we were asked to do hardware stamping and such a time stamp is * available, then it must have been for this skb here because we only * allow only one such packet into the queue. */ -void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector, - struct igb_tx_buffer *buffer_info) +void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) { - struct igb_adapter *adapter = q_vector->adapter; struct e1000_hw *hw = &adapter->hw; struct skb_shared_hwtstamps shhwtstamps; u64 regval; - /* if skb does not support hw timestamp or TX stamp not valid exit */ - if (likely(!(buffer_info->tx_flags & IGB_TX_FLAGS_TSTAMP)) || - !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID)) - return; - regval = rd32(E1000_TXSTMPL); regval |= (u64)rd32(E1000_TXSTMPH) << 32; igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); - skb_tstamp_tx(buffer_info->skb, &shhwtstamps); + skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps); + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; } void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector, @@ -603,16 +622,26 @@ void igb_ptp_init(struct igb_adapter *adapter) spin_lock_init(&adapter->tmreg_lock); + INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); + schedule_delayed_work(&adapter->ptp_overflow_work, IGB_SYSTIM_OVERFLOW_PERIOD); + /* Initialize the time sync interrupts for devices that support it. */ + if (hw->mac.type >= e1000_82580) { + wr32(E1000_TSIM, E1000_TSIM_TXTS); + wr32(E1000_IMS, E1000_IMS_TS); + } + adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps); if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n"); - } else + } else { dev_info(&adapter->pdev->dev, "added PHC on %s\n", adapter->netdev->name); + adapter->flags |= IGB_FLAG_PTP; + } } /** @@ -624,20 +653,61 @@ void igb_ptp_init(struct igb_adapter *adapter) void igb_ptp_stop(struct igb_adapter *adapter) { switch (adapter->hw.mac.type) { - case e1000_i211: - case e1000_i210: - case e1000_i350: - case e1000_82580: case e1000_82576: + case e1000_82580: + case e1000_i350: cancel_delayed_work_sync(&adapter->ptp_overflow_work); break; + case e1000_i210: + case e1000_i211: + /* No delayed work to cancel. */ + break; default: return; } + cancel_work_sync(&adapter->ptp_tx_work); + if (adapter->ptp_clock) { ptp_clock_unregister(adapter->ptp_clock); dev_info(&adapter->pdev->dev, "removed PHC on %s\n", adapter->netdev->name); + adapter->flags &= ~IGB_FLAG_PTP; } } + +/** + * igb_ptp_reset - Re-enable the adapter for PTP following a reset. + * @adapter: Board private structure. + * + * This function handles the reset work required to re-enable the PTP device. + **/ +void igb_ptp_reset(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + if (!(adapter->flags & IGB_FLAG_PTP)) + return; + + switch (adapter->hw.mac.type) { + case e1000_82576: + /* Dial the nominal frequency. */ + wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576); + break; + case e1000_82580: + case e1000_i350: + case e1000_i210: + case e1000_i211: + /* Enable the timer functions and interrupts. */ + wr32(E1000_TSAUXC, 0x0); + wr32(E1000_TSIM, E1000_TSIM_TXTS); + wr32(E1000_IMS, E1000_IMS_TS); + break; + default: + /* No work to do. */ + return; + } + + timecounter_init(&adapter->tc, &adapter->cc, + ktime_to_ns(ktime_get_real())); +} -- cgit v1.2.3 From e57b8bdb4833366fd23d03a066c7eb8acc5736c7 Mon Sep 17 00:00:00 2001 From: Matthew Vick Date: Fri, 17 Aug 2012 01:30:37 +0000 Subject: igb: Add 1588 support to I210/I211. Previously I210/I211 followed the same code flow as 82580/I350 for 1588. However, since the register sets have changed, we must update the implementation to accommodate the register changes. Cc: Richard Cochran Signed-off-by: Matthew Vick Acked-by: Jacob Keller Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/e1000_defines.h | 3 + drivers/net/ethernet/intel/igb/igb_ptp.c | 216 +++++++++++++++++++------ 2 files changed, 174 insertions(+), 45 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 0b27e8fe06bf..cae3070da922 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -322,6 +322,9 @@ #define E1000_FCRTC_RTH_COAL_SHIFT 4 #define E1000_PCIEMISC_LX_DECISION 0x00000080 /* Lx power decision */ +/* Timestamp in Rx buffer */ +#define E1000_RXPBS_CFG_TS_EN 0x80000000 + /* SerDes Control */ #define E1000_SCTL_DISABLE_SERDES_LOOPBACK 0x0400 diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index d57060c0813d..e13ba1d5369f 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -121,6 +121,41 @@ static cycle_t igb_ptp_read_82580(const struct cyclecounter *cc) return val; } +/* + * SYSTIM read access for I210/I211 + */ + +static void igb_ptp_read_i210(struct igb_adapter *adapter, struct timespec *ts) +{ + struct e1000_hw *hw = &adapter->hw; + u32 sec, nsec, jk; + + /* + * The timestamp latches on lowest register read. For I210/I211, the + * lowest register is SYSTIMR. Since we only need to provide nanosecond + * resolution, we can ignore it. + */ + jk = rd32(E1000_SYSTIMR); + nsec = rd32(E1000_SYSTIML); + sec = rd32(E1000_SYSTIMH); + + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} + +static void igb_ptp_write_i210(struct igb_adapter *adapter, + const struct timespec *ts) +{ + struct e1000_hw *hw = &adapter->hw; + + /* + * Writing the SYSTIMR register is not necessary as it only provides + * sub-nanosecond resolution. + */ + wr32(E1000_SYSTIML, ts->tv_nsec); + wr32(E1000_SYSTIMH, ts->tv_sec); +} + /** * igb_ptp_systim_to_hwtstamp - convert system time value to hw timestamp * @adapter: board private structure @@ -146,24 +181,28 @@ static void igb_ptp_systim_to_hwtstamp(struct igb_adapter *adapter, u64 ns; switch (adapter->hw.mac.type) { + case e1000_82576: + case e1000_82580: + case e1000_i350: + spin_lock_irqsave(&adapter->tmreg_lock, flags); + + ns = timecounter_cyc2time(&adapter->tc, systim); + + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + memset(hwtstamps, 0, sizeof(*hwtstamps)); + hwtstamps->hwtstamp = ns_to_ktime(ns); + break; case e1000_i210: case e1000_i211: - case e1000_i350: - case e1000_82580: - case e1000_82576: + memset(hwtstamps, 0, sizeof(*hwtstamps)); + /* Upper 32 bits contain s, lower 32 bits contain ns. */ + hwtstamps->hwtstamp = ktime_set(systim >> 32, + systim & 0xFFFFFFFF); break; default: - return; + break; } - - spin_lock_irqsave(&adapter->tmreg_lock, flags); - - ns = timecounter_cyc2time(&adapter->tc, systim); - - spin_unlock_irqrestore(&adapter->tmreg_lock, flags); - - memset(hwtstamps, 0, sizeof(*hwtstamps)); - hwtstamps->hwtstamp = ns_to_ktime(ns); } /* @@ -225,7 +264,7 @@ static int igb_ptp_adjfreq_82580(struct ptp_clock_info *ptp, s32 ppb) return 0; } -static int igb_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +static int igb_ptp_adjtime_82576(struct ptp_clock_info *ptp, s64 delta) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); @@ -243,7 +282,26 @@ static int igb_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int igb_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int igb_ptp_adjtime_i210(struct ptp_clock_info *ptp, s64 delta) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + unsigned long flags; + struct timespec now, then = ns_to_timespec(delta); + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + igb_ptp_read_i210(igb, &now); + now = timespec_add(now, then); + igb_ptp_write_i210(igb, (const struct timespec *)&now); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + return 0; +} + +static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp, + struct timespec *ts) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); @@ -263,8 +321,24 @@ static int igb_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) return 0; } -static int igb_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) +static int igb_ptp_gettime_i210(struct ptp_clock_info *ptp, + struct timespec *ts) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + unsigned long flags; + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + igb_ptp_read_i210(igb, ts); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + return 0; +} + +static int igb_ptp_settime_82576(struct ptp_clock_info *ptp, + const struct timespec *ts) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); @@ -283,6 +357,22 @@ static int igb_ptp_settime(struct ptp_clock_info *ptp, return 0; } +static int igb_ptp_settime_i210(struct ptp_clock_info *ptp, + const struct timespec *ts) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + unsigned long flags; + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + igb_ptp_write_i210(igb, ts); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + return 0; +} + static int igb_ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { @@ -320,7 +410,7 @@ static void igb_ptp_overflow_check(struct work_struct *work) container_of(work, struct igb_adapter, ptp_overflow_work.work); struct timespec ts; - igb_ptp_gettime(&igb->ptp_caps, &ts); + igb->ptp_caps.gettime(&igb->ptp_caps, &ts); pr_debug("igb overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec); @@ -506,6 +596,13 @@ int igb_ptp_hwtstamp_ioctl(struct net_device *netdev, if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) { tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; + + if ((hw->mac.type == e1000_i210) || + (hw->mac.type == e1000_i211)) { + regval = rd32(E1000_RXPBS); + regval |= E1000_RXPBS_CFG_TS_EN; + wr32(E1000_RXPBS, regval); + } } /* enable/disable TX */ @@ -556,7 +653,9 @@ int igb_ptp_hwtstamp_ioctl(struct net_device *netdev, wrfl(); /* clear TX/RX time stamp registers, just to be sure */ + regval = rd32(E1000_TXSTMPL); regval = rd32(E1000_TXSTMPH); + regval = rd32(E1000_RXSTMPL); regval = rd32(E1000_RXSTMPH); return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? @@ -569,19 +668,35 @@ void igb_ptp_init(struct igb_adapter *adapter) struct net_device *netdev = adapter->netdev; switch (hw->mac.type) { - case e1000_i210: - case e1000_i211: - case e1000_i350: + case e1000_82576: + snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); + adapter->ptp_caps.owner = THIS_MODULE; + adapter->ptp_caps.max_adj = 1000000000; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.pps = 0; + adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576; + adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; + adapter->ptp_caps.gettime = igb_ptp_gettime_82576; + adapter->ptp_caps.settime = igb_ptp_settime_82576; + adapter->ptp_caps.enable = igb_ptp_enable; + adapter->cc.read = igb_ptp_read_82576; + adapter->cc.mask = CLOCKSOURCE_MASK(64); + adapter->cc.mult = 1; + adapter->cc.shift = IGB_82576_TSYNC_SHIFT; + /* Dial the nominal frequency. */ + wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576); + break; case e1000_82580: + case e1000_i350: snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); adapter->ptp_caps.owner = THIS_MODULE; adapter->ptp_caps.max_adj = 62499999; adapter->ptp_caps.n_ext_ts = 0; adapter->ptp_caps.pps = 0; adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580; - adapter->ptp_caps.adjtime = igb_ptp_adjtime; - adapter->ptp_caps.gettime = igb_ptp_gettime; - adapter->ptp_caps.settime = igb_ptp_settime; + adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; + adapter->ptp_caps.gettime = igb_ptp_gettime_82576; + adapter->ptp_caps.settime = igb_ptp_settime_82576; adapter->ptp_caps.enable = igb_ptp_enable; adapter->cc.read = igb_ptp_read_82580; adapter->cc.mask = CLOCKSOURCE_MASK(IGB_NBITS_82580); @@ -590,23 +705,20 @@ void igb_ptp_init(struct igb_adapter *adapter) /* Enable the timer functions by clearing bit 31. */ wr32(E1000_TSAUXC, 0x0); break; - case e1000_82576: + case e1000_i210: + case e1000_i211: snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); adapter->ptp_caps.owner = THIS_MODULE; - adapter->ptp_caps.max_adj = 1000000000; + adapter->ptp_caps.max_adj = 62499999; adapter->ptp_caps.n_ext_ts = 0; adapter->ptp_caps.pps = 0; - adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576; - adapter->ptp_caps.adjtime = igb_ptp_adjtime; - adapter->ptp_caps.gettime = igb_ptp_gettime; - adapter->ptp_caps.settime = igb_ptp_settime; + adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580; + adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210; + adapter->ptp_caps.gettime = igb_ptp_gettime_i210; + adapter->ptp_caps.settime = igb_ptp_settime_i210; adapter->ptp_caps.enable = igb_ptp_enable; - adapter->cc.read = igb_ptp_read_82576; - adapter->cc.mask = CLOCKSOURCE_MASK(64); - adapter->cc.mult = 1; - adapter->cc.shift = IGB_82576_TSYNC_SHIFT; - /* Dial the nominal frequency. */ - wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576); + /* Enable the timer functions by clearing bit 31. */ + wr32(E1000_TSAUXC, 0x0); break; default: adapter->ptp_clock = NULL; @@ -615,17 +727,24 @@ void igb_ptp_init(struct igb_adapter *adapter) wrfl(); - timecounter_init(&adapter->tc, &adapter->cc, - ktime_to_ns(ktime_get_real())); + spin_lock_init(&adapter->tmreg_lock); + INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); - INIT_DELAYED_WORK(&adapter->ptp_overflow_work, igb_ptp_overflow_check); + /* Initialize the clock and overflow work for devices that need it. */ + if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) { + struct timespec ts = ktime_to_timespec(ktime_get_real()); - spin_lock_init(&adapter->tmreg_lock); + igb_ptp_settime_i210(&adapter->ptp_caps, &ts); + } else { + timecounter_init(&adapter->tc, &adapter->cc, + ktime_to_ns(ktime_get_real())); - INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); + INIT_DELAYED_WORK(&adapter->ptp_overflow_work, + igb_ptp_overflow_check); - schedule_delayed_work(&adapter->ptp_overflow_work, - IGB_SYSTIM_OVERFLOW_PERIOD); + schedule_delayed_work(&adapter->ptp_overflow_work, + IGB_SYSTIM_OVERFLOW_PERIOD); + } /* Initialize the time sync interrupts for devices that support it. */ if (hw->mac.type >= e1000_82580) { @@ -708,6 +827,13 @@ void igb_ptp_reset(struct igb_adapter *adapter) return; } - timecounter_init(&adapter->tc, &adapter->cc, - ktime_to_ns(ktime_get_real())); + /* Re-initialize the timer. */ + if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) { + struct timespec ts = ktime_to_timespec(ktime_get_real()); + + igb_ptp_settime_i210(&adapter->ptp_caps, &ts); + } else { + timecounter_init(&adapter->tc, &adapter->cc, + ktime_to_ns(ktime_get_real())); + } } -- cgit v1.2.3 From 576eda8b08e00cbb0cf29ba777c2cb461c98cbbc Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Wed, 19 Sep 2012 02:46:37 +0100 Subject: sfc: Fix maximum array sizes for various MCDI commands The maximum array sizes have been calculated on the basis of a maximum SDU size of 255 bytes, whereas the actual maximum is 252 bytes. Constructing a larger SDU will result in a BUG_ON in efx_mcdi_copyin. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/mcdi_pcol.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h index db4beed97669..50389326bec8 100644 --- a/drivers/net/ethernet/sfc/mcdi_pcol.h +++ b/drivers/net/ethernet/sfc/mcdi_pcol.h @@ -491,12 +491,12 @@ /* MC_CMD_GET_FPGAREG_OUT msgresponse */ #define MC_CMD_GET_FPGAREG_OUT_LENMIN 1 -#define MC_CMD_GET_FPGAREG_OUT_LENMAX 255 +#define MC_CMD_GET_FPGAREG_OUT_LENMAX 252 #define MC_CMD_GET_FPGAREG_OUT_LEN(num) (0+1*(num)) #define MC_CMD_GET_FPGAREG_OUT_BUFFER_OFST 0 #define MC_CMD_GET_FPGAREG_OUT_BUFFER_LEN 1 #define MC_CMD_GET_FPGAREG_OUT_BUFFER_MINNUM 1 -#define MC_CMD_GET_FPGAREG_OUT_BUFFER_MAXNUM 255 +#define MC_CMD_GET_FPGAREG_OUT_BUFFER_MAXNUM 252 /***********************************/ @@ -507,13 +507,13 @@ /* MC_CMD_PUT_FPGAREG_IN msgrequest */ #define MC_CMD_PUT_FPGAREG_IN_LENMIN 5 -#define MC_CMD_PUT_FPGAREG_IN_LENMAX 255 +#define MC_CMD_PUT_FPGAREG_IN_LENMAX 252 #define MC_CMD_PUT_FPGAREG_IN_LEN(num) (4+1*(num)) #define MC_CMD_PUT_FPGAREG_IN_ADDR_OFST 0 #define MC_CMD_PUT_FPGAREG_IN_BUFFER_OFST 4 #define MC_CMD_PUT_FPGAREG_IN_BUFFER_LEN 1 #define MC_CMD_PUT_FPGAREG_IN_BUFFER_MINNUM 1 -#define MC_CMD_PUT_FPGAREG_IN_BUFFER_MAXNUM 251 +#define MC_CMD_PUT_FPGAREG_IN_BUFFER_MAXNUM 248 /* MC_CMD_PUT_FPGAREG_OUT msgresponse */ #define MC_CMD_PUT_FPGAREG_OUT_LEN 0 @@ -560,7 +560,7 @@ /* MC_CMD_PTP_IN_TRANSMIT msgrequest */ #define MC_CMD_PTP_IN_TRANSMIT_LENMIN 13 -#define MC_CMD_PTP_IN_TRANSMIT_LENMAX 255 +#define MC_CMD_PTP_IN_TRANSMIT_LENMAX 252 #define MC_CMD_PTP_IN_TRANSMIT_LEN(num) (12+1*(num)) /* MC_CMD_PTP_IN_CMD_OFST 0 */ /* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ @@ -568,7 +568,7 @@ #define MC_CMD_PTP_IN_TRANSMIT_PACKET_OFST 12 #define MC_CMD_PTP_IN_TRANSMIT_PACKET_LEN 1 #define MC_CMD_PTP_IN_TRANSMIT_PACKET_MINNUM 1 -#define MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM 243 +#define MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM 240 /* MC_CMD_PTP_IN_READ_NIC_TIME msgrequest */ #define MC_CMD_PTP_IN_READ_NIC_TIME_LEN 8 @@ -1145,7 +1145,7 @@ /* MC_CMD_PUTS_IN msgrequest */ #define MC_CMD_PUTS_IN_LENMIN 13 -#define MC_CMD_PUTS_IN_LENMAX 255 +#define MC_CMD_PUTS_IN_LENMAX 252 #define MC_CMD_PUTS_IN_LEN(num) (12+1*(num)) #define MC_CMD_PUTS_IN_DEST_OFST 0 #define MC_CMD_PUTS_IN_UART_LBN 0 @@ -1157,7 +1157,7 @@ #define MC_CMD_PUTS_IN_STRING_OFST 12 #define MC_CMD_PUTS_IN_STRING_LEN 1 #define MC_CMD_PUTS_IN_STRING_MINNUM 1 -#define MC_CMD_PUTS_IN_STRING_MAXNUM 243 +#define MC_CMD_PUTS_IN_STRING_MAXNUM 240 /* MC_CMD_PUTS_OUT msgresponse */ #define MC_CMD_PUTS_OUT_LEN 0 @@ -1947,12 +1947,12 @@ /* MC_CMD_NVRAM_READ_OUT msgresponse */ #define MC_CMD_NVRAM_READ_OUT_LENMIN 1 -#define MC_CMD_NVRAM_READ_OUT_LENMAX 255 +#define MC_CMD_NVRAM_READ_OUT_LENMAX 252 #define MC_CMD_NVRAM_READ_OUT_LEN(num) (0+1*(num)) #define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_OFST 0 #define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_LEN 1 #define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MINNUM 1 -#define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MAXNUM 255 +#define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MAXNUM 252 /***********************************/ @@ -1963,7 +1963,7 @@ /* MC_CMD_NVRAM_WRITE_IN msgrequest */ #define MC_CMD_NVRAM_WRITE_IN_LENMIN 13 -#define MC_CMD_NVRAM_WRITE_IN_LENMAX 255 +#define MC_CMD_NVRAM_WRITE_IN_LENMAX 252 #define MC_CMD_NVRAM_WRITE_IN_LEN(num) (12+1*(num)) #define MC_CMD_NVRAM_WRITE_IN_TYPE_OFST 0 /* Enum values, see field(s): */ @@ -1973,7 +1973,7 @@ #define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_OFST 12 #define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_LEN 1 #define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MINNUM 1 -#define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM 243 +#define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM 240 /* MC_CMD_NVRAM_WRITE_OUT msgresponse */ #define MC_CMD_NVRAM_WRITE_OUT_LEN 0 @@ -2305,13 +2305,13 @@ /* MC_CMD_GET_PHY_MEDIA_INFO_OUT msgresponse */ #define MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMIN 5 -#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX 255 +#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX 252 #define MC_CMD_GET_PHY_MEDIA_INFO_OUT_LEN(num) (4+1*(num)) #define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATALEN_OFST 0 #define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST 4 #define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_LEN 1 #define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MINNUM 1 -#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MAXNUM 251 +#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MAXNUM 248 /***********************************/ -- cgit v1.2.3 From 7c236c43b838221e17220bcb39e8e8d8c7123713 Mon Sep 17 00:00:00 2001 From: Stuart Hodgson Date: Mon, 3 Sep 2012 11:09:36 +0100 Subject: sfc: Add support for IEEE-1588 PTP Add PTP IEEE-1588 support and make accesible via the PHC subsystem. This work is based on prior code by Andrew Jackson Signed-off-by: Stuart Hodgson [bwh: - Add byte order conversion in efx_ptp_send_times() - Simplify conversion of PPS event times - Add the built-in vs module check to CONFIG_SFC_PTP dependencies] Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/Kconfig | 7 + drivers/net/ethernet/sfc/Makefile | 1 + drivers/net/ethernet/sfc/efx.c | 3 + drivers/net/ethernet/sfc/ethtool.c | 1 + drivers/net/ethernet/sfc/mcdi.c | 5 + drivers/net/ethernet/sfc/mcdi_pcol.h | 1 + drivers/net/ethernet/sfc/net_driver.h | 19 +- drivers/net/ethernet/sfc/nic.h | 36 + drivers/net/ethernet/sfc/ptp.c | 1483 +++++++++++++++++++++++++++++++++ drivers/net/ethernet/sfc/siena.c | 1 + drivers/net/ethernet/sfc/tx.c | 6 + 11 files changed, 1562 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/sfc/ptp.c (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig index fb3cbc27063c..25906c1d1b15 100644 --- a/drivers/net/ethernet/sfc/Kconfig +++ b/drivers/net/ethernet/sfc/Kconfig @@ -34,3 +34,10 @@ config SFC_SRIOV This enables support for the SFC9000 I/O Virtualization features, allowing accelerated network performance in virtualized environments. +config SFC_PTP + bool "Solarflare SFC9000-family PTP support" + depends on SFC && PTP_1588_CLOCK && !(SFC=y && PTP_1588_CLOCK=m) + default y + ---help--- + This enables support for the Precision Time Protocol (PTP) + on SFC9000-family NICs diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile index ea1f8db57318..e11f2ecf69d9 100644 --- a/drivers/net/ethernet/sfc/Makefile +++ b/drivers/net/ethernet/sfc/Makefile @@ -5,5 +5,6 @@ sfc-y += efx.o nic.o falcon.o siena.o tx.o rx.o filter.o \ mcdi.o mcdi_phy.o mcdi_mon.o sfc-$(CONFIG_SFC_MTD) += mtd.o sfc-$(CONFIG_SFC_SRIOV) += siena_sriov.o +sfc-$(CONFIG_SFC_PTP) += ptp.o obj-$(CONFIG_SFC) += sfc.o diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 8b79a6413fe4..96bd980e828d 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1779,6 +1779,9 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd) struct efx_nic *efx = netdev_priv(net_dev); struct mii_ioctl_data *data = if_mii(ifr); + if (cmd == SIOCSHWTSTAMP) + return efx_ptp_ioctl(efx, ifr, cmd); + /* Convert phy_id from older PRTAD/DEVAD format */ if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) && (data->phy_id & 0xfc00) == 0x0400) diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index f8e7e204981f..9df556c01b8e 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -1174,6 +1174,7 @@ const struct ethtool_ops efx_ethtool_ops = { .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, .get_rxfh_indir = efx_ethtool_get_rxfh_indir, .set_rxfh_indir = efx_ethtool_set_rxfh_indir, + .get_ts_info = efx_ptp_get_ts_info, .get_module_info = efx_ethtool_get_module_info, .get_module_eeprom = efx_ethtool_get_module_eeprom, }; diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 2707e86def9e..294df4bca4a6 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -578,6 +578,11 @@ void efx_mcdi_process_event(struct efx_channel *channel, case MCDI_EVENT_CODE_FLR: efx_sriov_flr(efx, MCDI_EVENT_FIELD(*event, FLR_VF)); break; + case MCDI_EVENT_CODE_PTP_RX: + case MCDI_EVENT_CODE_PTP_FAULT: + case MCDI_EVENT_CODE_PTP_PPS: + efx_ptp_event(efx, event); + break; default: netif_err(efx, hw, efx->net_dev, "Unknown MCDI event 0x%x\n", diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h index 50389326bec8..9d426d0457bd 100644 --- a/drivers/net/ethernet/sfc/mcdi_pcol.h +++ b/drivers/net/ethernet/sfc/mcdi_pcol.h @@ -289,6 +289,7 @@ #define MCDI_EVENT_CODE_TX_FLUSH 0xc /* enum */ #define MCDI_EVENT_CODE_PTP_RX 0xd /* enum */ #define MCDI_EVENT_CODE_PTP_FAULT 0xe /* enum */ +#define MCDI_EVENT_CODE_PTP_PPS 0xf /* enum */ #define MCDI_EVENT_CMDDONE_DATA_OFST 0 #define MCDI_EVENT_CMDDONE_DATA_LBN 0 #define MCDI_EVENT_CMDDONE_DATA_WIDTH 32 diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 0f0926e68963..797dbed25d94 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -56,7 +56,8 @@ #define EFX_MAX_CHANNELS 32U #define EFX_MAX_RX_QUEUES EFX_MAX_CHANNELS #define EFX_EXTRA_CHANNEL_IOV 0 -#define EFX_MAX_EXTRA_CHANNELS 1U +#define EFX_EXTRA_CHANNEL_PTP 1 +#define EFX_MAX_EXTRA_CHANNELS 2U /* Checksum generation is a per-queue option in hardware, so each * queue visible to the networking core is backed by two hardware TX @@ -68,6 +69,9 @@ #define EFX_TXQ_TYPES 4 #define EFX_MAX_TX_QUEUES (EFX_TXQ_TYPES * EFX_MAX_CHANNELS) +/* Forward declare Precision Time Protocol (PTP) support structure. */ +struct efx_ptp_data; + struct efx_self_tests; /** @@ -736,6 +740,7 @@ struct vfdi_status; * %local_addr_list. Protected by %local_lock. * @local_lock: Mutex protecting %local_addr_list and %local_page_list. * @peer_work: Work item to broadcast peer addresses to VMs. + * @ptp_data: PTP state data * @monitor_work: Hardware monitor workitem * @biu_lock: BIU (bus interface unit) lock * @last_irq_cpu: Last CPU to handle a possible test interrupt. This @@ -863,6 +868,10 @@ struct efx_nic { struct work_struct peer_work; #endif +#ifdef CONFIG_SFC_PTP + struct efx_ptp_data *ptp_data; +#endif + /* The following fields may be written more often */ struct delayed_work monitor_work ____cacheline_aligned_in_smp; @@ -1125,5 +1134,13 @@ static inline void clear_bit_le(unsigned nr, unsigned char *addr) #define EFX_MAX_FRAME_LEN(mtu) \ ((((mtu) + ETH_HLEN + VLAN_HLEN + 4/* FCS */ + 7) & ~7) + 16) +static inline bool efx_xmit_with_hwtstamp(struct sk_buff *skb) +{ + return skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP; +} +static inline void efx_xmit_hwtstamp_pending(struct sk_buff *skb) +{ + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; +} #endif /* EFX_NET_DRIVER_H */ diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index bab5cd9f5740..438cef11f727 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -11,6 +11,7 @@ #ifndef EFX_NIC_H #define EFX_NIC_H +#include #include #include "net_driver.h" #include "efx.h" @@ -250,6 +251,41 @@ extern int efx_sriov_get_vf_config(struct net_device *dev, int vf, extern int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf, bool spoofchk); +struct ethtool_ts_info; +#ifdef CONFIG_SFC_PTP +extern void efx_ptp_probe(struct efx_nic *efx); +extern int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd); +extern int efx_ptp_get_ts_info(struct net_device *net_dev, + struct ethtool_ts_info *ts_info); +extern bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb); +extern int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb); +extern void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev); +#else +static inline void efx_ptp_probe(struct efx_nic *efx) {} +static inline int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd) +{ + return -EOPNOTSUPP; +} +static inline int efx_ptp_get_ts_info(struct net_device *net_dev, + struct ethtool_ts_info *ts_info) +{ + ts_info->so_timestamping = (SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE); + ts_info->phc_index = -1; + + return 0; +} +static inline bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb) +{ + return false; +} +static inline int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb) +{ + return NETDEV_TX_OK; +} +static inline void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) {} +#endif + extern const struct efx_nic_type falcon_a1_nic_type; extern const struct efx_nic_type falcon_b0_nic_type; extern const struct efx_nic_type siena_a0_nic_type; diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c new file mode 100644 index 000000000000..2b07a4eae07e --- /dev/null +++ b/drivers/net/ethernet/sfc/ptp.c @@ -0,0 +1,1483 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2011 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +/* Theory of operation: + * + * PTP support is assisted by firmware running on the MC, which provides + * the hardware timestamping capabilities. Both transmitted and received + * PTP event packets are queued onto internal queues for subsequent processing; + * this is because the MC operations are relatively long and would block + * block NAPI/interrupt operation. + * + * Receive event processing: + * The event contains the packet's UUID and sequence number, together + * with the hardware timestamp. The PTP receive packet queue is searched + * for this UUID/sequence number and, if found, put on a pending queue. + * Packets not matching are delivered without timestamps (MCDI events will + * always arrive after the actual packet). + * It is important for the operation of the PTP protocol that the ordering + * of packets between the event and general port is maintained. + * + * Work queue processing: + * If work waiting, synchronise host/hardware time + * + * Transmit: send packet through MC, which returns the transmission time + * that is converted to an appropriate timestamp. + * + * Receive: the packet's reception time is converted to an appropriate + * timestamp. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "net_driver.h" +#include "efx.h" +#include "mcdi.h" +#include "mcdi_pcol.h" +#include "io.h" +#include "regs.h" +#include "nic.h" + +/* Maximum number of events expected to make up a PTP event */ +#define MAX_EVENT_FRAGS 3 + +/* Maximum delay, ms, to begin synchronisation */ +#define MAX_SYNCHRONISE_WAIT_MS 2 + +/* How long, at most, to spend synchronising */ +#define SYNCHRONISE_PERIOD_NS 250000 + +/* How often to update the shared memory time */ +#define SYNCHRONISATION_GRANULARITY_NS 200 + +/* Minimum permitted length of a (corrected) synchronisation time */ +#define MIN_SYNCHRONISATION_NS 120 + +/* Maximum permitted length of a (corrected) synchronisation time */ +#define MAX_SYNCHRONISATION_NS 1000 + +/* How many (MC) receive events that can be queued */ +#define MAX_RECEIVE_EVENTS 8 + +/* Length of (modified) moving average. */ +#define AVERAGE_LENGTH 16 + +/* How long an unmatched event or packet can be held */ +#define PKT_EVENT_LIFETIME_MS 10 + +/* Offsets into PTP packet for identification. These offsets are from the + * start of the IP header, not the MAC header. Note that neither PTP V1 nor + * PTP V2 permit the use of IPV4 options. + */ +#define PTP_DPORT_OFFSET 22 + +#define PTP_V1_VERSION_LENGTH 2 +#define PTP_V1_VERSION_OFFSET 28 + +#define PTP_V1_UUID_LENGTH 6 +#define PTP_V1_UUID_OFFSET 50 + +#define PTP_V1_SEQUENCE_LENGTH 2 +#define PTP_V1_SEQUENCE_OFFSET 58 + +/* The minimum length of a PTP V1 packet for offsets, etc. to be valid: + * includes IP header. + */ +#define PTP_V1_MIN_LENGTH 64 + +#define PTP_V2_VERSION_LENGTH 1 +#define PTP_V2_VERSION_OFFSET 29 + +/* Although PTP V2 UUIDs are comprised a ClockIdentity (8) and PortNumber (2), + * the MC only captures the last six bytes of the clock identity. These values + * reflect those, not the ones used in the standard. The standard permits + * mapping of V1 UUIDs to V2 UUIDs with these same values. + */ +#define PTP_V2_MC_UUID_LENGTH 6 +#define PTP_V2_MC_UUID_OFFSET 50 + +#define PTP_V2_SEQUENCE_LENGTH 2 +#define PTP_V2_SEQUENCE_OFFSET 58 + +/* The minimum length of a PTP V2 packet for offsets, etc. to be valid: + * includes IP header. + */ +#define PTP_V2_MIN_LENGTH 63 + +#define PTP_MIN_LENGTH 63 + +#define PTP_ADDRESS 0xe0000181 /* 224.0.1.129 */ +#define PTP_EVENT_PORT 319 +#define PTP_GENERAL_PORT 320 + +/* Annoyingly the format of the version numbers are different between + * versions 1 and 2 so it isn't possible to simply look for 1 or 2. + */ +#define PTP_VERSION_V1 1 + +#define PTP_VERSION_V2 2 +#define PTP_VERSION_V2_MASK 0x0f + +enum ptp_packet_state { + PTP_PACKET_STATE_UNMATCHED = 0, + PTP_PACKET_STATE_MATCHED, + PTP_PACKET_STATE_TIMED_OUT, + PTP_PACKET_STATE_MATCH_UNWANTED +}; + +/* NIC synchronised with single word of time only comprising + * partial seconds and full nanoseconds: 10^9 ~ 2^30 so 2 bits for seconds. + */ +#define MC_NANOSECOND_BITS 30 +#define MC_NANOSECOND_MASK ((1 << MC_NANOSECOND_BITS) - 1) +#define MC_SECOND_MASK ((1 << (32 - MC_NANOSECOND_BITS)) - 1) + +/* Maximum parts-per-billion adjustment that is acceptable */ +#define MAX_PPB 1000000 + +/* Number of bits required to hold the above */ +#define MAX_PPB_BITS 20 + +/* Number of extra bits allowed when calculating fractional ns. + * EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS + MAX_PPB_BITS should + * be less than 63. + */ +#define PPB_EXTRA_BITS 2 + +/* Precalculate scale word to avoid long long division at runtime */ +#define PPB_SCALE_WORD ((1LL << (PPB_EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS +\ + MAX_PPB_BITS)) / 1000000000LL) + +#define PTP_SYNC_ATTEMPTS 4 + +/** + * struct efx_ptp_match - Matching structure, stored in sk_buff's cb area. + * @words: UUID and (partial) sequence number + * @expiry: Time after which the packet should be delivered irrespective of + * event arrival. + * @state: The state of the packet - whether it is ready for processing or + * whether that is of no interest. + */ +struct efx_ptp_match { + u32 words[DIV_ROUND_UP(PTP_V1_UUID_LENGTH, 4)]; + unsigned long expiry; + enum ptp_packet_state state; +}; + +/** + * struct efx_ptp_event_rx - A PTP receive event (from MC) + * @seq0: First part of (PTP) UUID + * @seq1: Second part of (PTP) UUID and sequence number + * @hwtimestamp: Event timestamp + */ +struct efx_ptp_event_rx { + struct list_head link; + u32 seq0; + u32 seq1; + ktime_t hwtimestamp; + unsigned long expiry; +}; + +/** + * struct efx_ptp_timeset - Synchronisation between host and MC + * @host_start: Host time immediately before hardware timestamp taken + * @seconds: Hardware timestamp, seconds + * @nanoseconds: Hardware timestamp, nanoseconds + * @host_end: Host time immediately after hardware timestamp taken + * @waitns: Number of nanoseconds between hardware timestamp being read and + * host end time being seen + * @window: Difference of host_end and host_start + * @valid: Whether this timeset is valid + */ +struct efx_ptp_timeset { + u32 host_start; + u32 seconds; + u32 nanoseconds; + u32 host_end; + u32 waitns; + u32 window; /* Derived: end - start, allowing for wrap */ +}; + +/** + * struct efx_ptp_data - Precision Time Protocol (PTP) state + * @channel: The PTP channel + * @rxq: Receive queue (awaiting timestamps) + * @txq: Transmit queue + * @evt_list: List of MC receive events awaiting packets + * @evt_free_list: List of free events + * @evt_lock: Lock for manipulating evt_list and evt_free_list + * @rx_evts: Instantiated events (on evt_list and evt_free_list) + * @workwq: Work queue for processing pending PTP operations + * @work: Work task + * @reset_required: A serious error has occurred and the PTP task needs to be + * reset (disable, enable). + * @rxfilter_event: Receive filter when operating + * @rxfilter_general: Receive filter when operating + * @config: Current timestamp configuration + * @enabled: PTP operation enabled + * @mode: Mode in which PTP operating (PTP version) + * @evt_frags: Partly assembled PTP events + * @evt_frag_idx: Current fragment number + * @evt_code: Last event code + * @start: Address at which MC indicates ready for synchronisation + * @host_time_pps: Host time at last PPS + * @last_sync_ns: Last number of nanoseconds between readings when synchronising + * @base_sync_ns: Number of nanoseconds for last synchronisation. + * @base_sync_valid: Whether base_sync_time is valid. + * @current_adjfreq: Current ppb adjustment. + * @phc_clock: Pointer to registered phc device + * @phc_clock_info: Registration structure for phc device + * @pps_work: pps work task for handling pps events + * @pps_workwq: pps work queue + * @nic_ts_enabled: Flag indicating if NIC generated TS events are handled + * @txbuf: Buffer for use when transmitting (PTP) packets to MC (avoids + * allocations in main data path). + * @debug_ptp_dir: PTP debugfs directory + * @missed_rx_sync: Number of packets received without syncrhonisation. + * @good_syncs: Number of successful synchronisations. + * @no_time_syncs: Number of synchronisations with no good times. + * @bad_sync_durations: Number of synchronisations with bad durations. + * @bad_syncs: Number of failed synchronisations. + * @last_sync_time: Number of nanoseconds for last synchronisation. + * @sync_timeouts: Number of synchronisation timeouts + * @fast_syncs: Number of synchronisations requiring short delay + * @min_sync_delta: Minimum time between event and synchronisation + * @max_sync_delta: Maximum time between event and synchronisation + * @average_sync_delta: Average time between event and synchronisation. + * Modified moving average. + * @last_sync_delta: Last time between event and synchronisation + * @mc_stats: Context value for MC statistics + * @timeset: Last set of synchronisation statistics. + */ +struct efx_ptp_data { + struct efx_channel *channel; + struct sk_buff_head rxq; + struct sk_buff_head txq; + struct list_head evt_list; + struct list_head evt_free_list; + spinlock_t evt_lock; + struct efx_ptp_event_rx rx_evts[MAX_RECEIVE_EVENTS]; + struct workqueue_struct *workwq; + struct work_struct work; + bool reset_required; + u32 rxfilter_event; + u32 rxfilter_general; + bool rxfilter_installed; + struct hwtstamp_config config; + bool enabled; + unsigned int mode; + efx_qword_t evt_frags[MAX_EVENT_FRAGS]; + int evt_frag_idx; + int evt_code; + struct efx_buffer start; + struct pps_event_time host_time_pps; + unsigned last_sync_ns; + unsigned base_sync_ns; + bool base_sync_valid; + s64 current_adjfreq; + struct ptp_clock *phc_clock; + struct ptp_clock_info phc_clock_info; + struct work_struct pps_work; + struct workqueue_struct *pps_workwq; + bool nic_ts_enabled; + u8 txbuf[ALIGN(MC_CMD_PTP_IN_TRANSMIT_LEN( + MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM), 4)]; + struct efx_ptp_timeset + timeset[MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_MAXNUM]; +}; + +static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta); +static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta); +static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts); +static int efx_phc_settime(struct ptp_clock_info *ptp, + const struct timespec *e_ts); +static int efx_phc_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *request, int on); + +/* Enable MCDI PTP support. */ +static int efx_ptp_enable(struct efx_nic *efx) +{ + u8 inbuf[MC_CMD_PTP_IN_ENABLE_LEN]; + + MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ENABLE); + MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_QUEUE, + efx->ptp_data->channel->channel); + MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_MODE, efx->ptp_data->mode); + + return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), + NULL, 0, NULL); +} + +/* Disable MCDI PTP support. + * + * Note that this function should never rely on the presence of ptp_data - + * may be called before that exists. + */ +static int efx_ptp_disable(struct efx_nic *efx) +{ + u8 inbuf[MC_CMD_PTP_IN_DISABLE_LEN]; + + MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_DISABLE); + return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), + NULL, 0, NULL); +} + +static void efx_ptp_deliver_rx_queue(struct sk_buff_head *q) +{ + struct sk_buff *skb; + + while ((skb = skb_dequeue(q))) { + local_bh_disable(); + netif_receive_skb(skb); + local_bh_enable(); + } +} + +static void efx_ptp_handle_no_channel(struct efx_nic *efx) +{ + netif_err(efx, drv, efx->net_dev, + "ERROR: PTP requires MSI-X and 1 additional interrupt" + "vector. PTP disabled\n"); +} + +/* Repeatedly send the host time to the MC which will capture the hardware + * time. + */ +static void efx_ptp_send_times(struct efx_nic *efx, + struct pps_event_time *last_time) +{ + struct pps_event_time now; + struct timespec limit; + struct efx_ptp_data *ptp = efx->ptp_data; + struct timespec start; + int *mc_running = ptp->start.addr; + + pps_get_ts(&now); + start = now.ts_real; + limit = now.ts_real; + timespec_add_ns(&limit, SYNCHRONISE_PERIOD_NS); + + /* Write host time for specified period or until MC is done */ + while ((timespec_compare(&now.ts_real, &limit) < 0) && + ACCESS_ONCE(*mc_running)) { + struct timespec update_time; + unsigned int host_time; + + /* Don't update continuously to avoid saturating the PCIe bus */ + update_time = now.ts_real; + timespec_add_ns(&update_time, SYNCHRONISATION_GRANULARITY_NS); + do { + pps_get_ts(&now); + } while ((timespec_compare(&now.ts_real, &update_time) < 0) && + ACCESS_ONCE(*mc_running)); + + /* Synchronise NIC with single word of time only */ + host_time = (now.ts_real.tv_sec << MC_NANOSECOND_BITS | + now.ts_real.tv_nsec); + /* Update host time in NIC memory */ + _efx_writed(efx, cpu_to_le32(host_time), + FR_CZ_MC_TREG_SMEM + MC_SMEM_P0_PTP_TIME_OFST); + } + *last_time = now; +} + +/* Read a timeset from the MC's results and partial process. */ +static void efx_ptp_read_timeset(u8 *data, struct efx_ptp_timeset *timeset) +{ + unsigned start_ns, end_ns; + + timeset->host_start = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTSTART); + timeset->seconds = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_SECONDS); + timeset->nanoseconds = MCDI_DWORD(data, + PTP_OUT_SYNCHRONIZE_NANOSECONDS); + timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND), + timeset->waitns = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_WAITNS); + + /* Ignore seconds */ + start_ns = timeset->host_start & MC_NANOSECOND_MASK; + end_ns = timeset->host_end & MC_NANOSECOND_MASK; + /* Allow for rollover */ + if (end_ns < start_ns) + end_ns += NSEC_PER_SEC; + /* Determine duration of operation */ + timeset->window = end_ns - start_ns; +} + +/* Process times received from MC. + * + * Extract times from returned results, and establish the minimum value + * seen. The minimum value represents the "best" possible time and events + * too much greater than this are rejected - the machine is, perhaps, too + * busy. A number of readings are taken so that, hopefully, at least one good + * synchronisation will be seen in the results. + */ +static int efx_ptp_process_times(struct efx_nic *efx, u8 *synch_buf, + size_t response_length, + const struct pps_event_time *last_time) +{ + unsigned number_readings = (response_length / + MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_LEN); + unsigned i; + unsigned min; + unsigned min_set = 0; + unsigned total; + unsigned ngood = 0; + unsigned last_good = 0; + struct efx_ptp_data *ptp = efx->ptp_data; + bool min_valid = false; + u32 last_sec; + u32 start_sec; + struct timespec delta; + + if (number_readings == 0) + return -EAGAIN; + + /* Find minimum value in this set of results, discarding clearly + * erroneous results. + */ + for (i = 0; i < number_readings; i++) { + efx_ptp_read_timeset(synch_buf, &ptp->timeset[i]); + synch_buf += MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_LEN; + if (ptp->timeset[i].window > SYNCHRONISATION_GRANULARITY_NS) { + if (min_valid) { + if (ptp->timeset[i].window < min_set) + min_set = ptp->timeset[i].window; + } else { + min_valid = true; + min_set = ptp->timeset[i].window; + } + } + } + + if (min_valid) { + if (ptp->base_sync_valid && (min_set > ptp->base_sync_ns)) + min = ptp->base_sync_ns; + else + min = min_set; + } else { + min = SYNCHRONISATION_GRANULARITY_NS; + } + + /* Discard excessively long synchronise durations. The MC times + * when it finishes reading the host time so the corrected window + * time should be fairly constant for a given platform. + */ + total = 0; + for (i = 0; i < number_readings; i++) + if (ptp->timeset[i].window > ptp->timeset[i].waitns) { + unsigned win; + + win = ptp->timeset[i].window - ptp->timeset[i].waitns; + if (win >= MIN_SYNCHRONISATION_NS && + win < MAX_SYNCHRONISATION_NS) { + total += ptp->timeset[i].window; + ngood++; + last_good = i; + } + } + + if (ngood == 0) { + netif_warn(efx, drv, efx->net_dev, + "PTP no suitable synchronisations %dns %dns\n", + ptp->base_sync_ns, min_set); + return -EAGAIN; + } + + /* Average minimum this synchronisation */ + ptp->last_sync_ns = DIV_ROUND_UP(total, ngood); + if (!ptp->base_sync_valid || (ptp->last_sync_ns < ptp->base_sync_ns)) { + ptp->base_sync_valid = true; + ptp->base_sync_ns = ptp->last_sync_ns; + } + + /* Calculate delay from actual PPS to last_time */ + delta.tv_nsec = + ptp->timeset[last_good].nanoseconds + + last_time->ts_real.tv_nsec - + (ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK); + + /* It is possible that the seconds rolled over between taking + * the start reading and the last value written by the host. The + * timescales are such that a gap of more than one second is never + * expected. + */ + start_sec = ptp->timeset[last_good].host_start >> MC_NANOSECOND_BITS; + last_sec = last_time->ts_real.tv_sec & MC_SECOND_MASK; + if (start_sec != last_sec) { + if (((start_sec + 1) & MC_SECOND_MASK) != last_sec) { + netif_warn(efx, hw, efx->net_dev, + "PTP bad synchronisation seconds\n"); + return -EAGAIN; + } else { + delta.tv_sec = 1; + } + } else { + delta.tv_sec = 0; + } + + ptp->host_time_pps = *last_time; + pps_sub_ts(&ptp->host_time_pps, delta); + + return 0; +} + +/* Synchronize times between the host and the MC */ +static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + u8 synch_buf[MC_CMD_PTP_OUT_SYNCHRONIZE_LENMAX]; + size_t response_length; + int rc; + unsigned long timeout; + struct pps_event_time last_time = {}; + unsigned int loops = 0; + int *start = ptp->start.addr; + + MCDI_SET_DWORD(synch_buf, PTP_IN_OP, MC_CMD_PTP_OP_SYNCHRONIZE); + MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_NUMTIMESETS, + num_readings); + MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_START_ADDR_LO, + (u32)ptp->start.dma_addr); + MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_START_ADDR_HI, + (u32)((u64)ptp->start.dma_addr >> 32)); + + /* Clear flag that signals MC ready */ + ACCESS_ONCE(*start) = 0; + efx_mcdi_rpc_start(efx, MC_CMD_PTP, synch_buf, + MC_CMD_PTP_IN_SYNCHRONIZE_LEN); + + /* Wait for start from MCDI (or timeout) */ + timeout = jiffies + msecs_to_jiffies(MAX_SYNCHRONISE_WAIT_MS); + while (!ACCESS_ONCE(*start) && (time_before(jiffies, timeout))) { + udelay(20); /* Usually start MCDI execution quickly */ + loops++; + } + + if (ACCESS_ONCE(*start)) + efx_ptp_send_times(efx, &last_time); + + /* Collect results */ + rc = efx_mcdi_rpc_finish(efx, MC_CMD_PTP, + MC_CMD_PTP_IN_SYNCHRONIZE_LEN, + synch_buf, sizeof(synch_buf), + &response_length); + if (rc == 0) + rc = efx_ptp_process_times(efx, synch_buf, response_length, + &last_time); + + return rc; +} + +/* Transmit a PTP packet, via the MCDI interface, to the wire. */ +static int efx_ptp_xmit_skb(struct efx_nic *efx, struct sk_buff *skb) +{ + u8 *txbuf = efx->ptp_data->txbuf; + struct skb_shared_hwtstamps timestamps; + int rc = -EIO; + /* MCDI driver requires word aligned lengths */ + size_t len = ALIGN(MC_CMD_PTP_IN_TRANSMIT_LEN(skb->len), 4); + u8 txtime[MC_CMD_PTP_OUT_TRANSMIT_LEN]; + + MCDI_SET_DWORD(txbuf, PTP_IN_OP, MC_CMD_PTP_OP_TRANSMIT); + MCDI_SET_DWORD(txbuf, PTP_IN_TRANSMIT_LENGTH, skb->len); + if (skb_shinfo(skb)->nr_frags != 0) { + rc = skb_linearize(skb); + if (rc != 0) + goto fail; + } + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + rc = skb_checksum_help(skb); + if (rc != 0) + goto fail; + } + skb_copy_from_linear_data(skb, + &txbuf[MC_CMD_PTP_IN_TRANSMIT_PACKET_OFST], + len); + rc = efx_mcdi_rpc(efx, MC_CMD_PTP, txbuf, len, txtime, + sizeof(txtime), &len); + if (rc != 0) + goto fail; + + memset(×tamps, 0, sizeof(timestamps)); + timestamps.hwtstamp = ktime_set( + MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_SECONDS), + MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_NANOSECONDS)); + + skb_tstamp_tx(skb, ×tamps); + + rc = 0; + +fail: + dev_kfree_skb(skb); + + return rc; +} + +static void efx_ptp_drop_time_expired_events(struct efx_nic *efx) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + struct list_head *cursor; + struct list_head *next; + + /* Drop time-expired events */ + spin_lock_bh(&ptp->evt_lock); + if (!list_empty(&ptp->evt_list)) { + list_for_each_safe(cursor, next, &ptp->evt_list) { + struct efx_ptp_event_rx *evt; + + evt = list_entry(cursor, struct efx_ptp_event_rx, + link); + if (time_after(jiffies, evt->expiry)) { + list_del(&evt->link); + list_add(&evt->link, &ptp->evt_free_list); + netif_warn(efx, hw, efx->net_dev, + "PTP rx event dropped\n"); + } + } + } + spin_unlock_bh(&ptp->evt_lock); +} + +static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx, + struct sk_buff *skb) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + bool evts_waiting; + struct list_head *cursor; + struct list_head *next; + struct efx_ptp_match *match; + enum ptp_packet_state rc = PTP_PACKET_STATE_UNMATCHED; + + spin_lock_bh(&ptp->evt_lock); + evts_waiting = !list_empty(&ptp->evt_list); + spin_unlock_bh(&ptp->evt_lock); + + if (!evts_waiting) + return PTP_PACKET_STATE_UNMATCHED; + + match = (struct efx_ptp_match *)skb->cb; + /* Look for a matching timestamp in the event queue */ + spin_lock_bh(&ptp->evt_lock); + list_for_each_safe(cursor, next, &ptp->evt_list) { + struct efx_ptp_event_rx *evt; + + evt = list_entry(cursor, struct efx_ptp_event_rx, link); + if ((evt->seq0 == match->words[0]) && + (evt->seq1 == match->words[1])) { + struct skb_shared_hwtstamps *timestamps; + + /* Match - add in hardware timestamp */ + timestamps = skb_hwtstamps(skb); + timestamps->hwtstamp = evt->hwtimestamp; + + match->state = PTP_PACKET_STATE_MATCHED; + rc = PTP_PACKET_STATE_MATCHED; + list_del(&evt->link); + list_add(&evt->link, &ptp->evt_free_list); + break; + } + } + spin_unlock_bh(&ptp->evt_lock); + + return rc; +} + +/* Process any queued receive events and corresponding packets + * + * q is returned with all the packets that are ready for delivery. + * true is returned if at least one of those packets requires + * synchronisation. + */ +static bool efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + bool rc = false; + struct sk_buff *skb; + + while ((skb = skb_dequeue(&ptp->rxq))) { + struct efx_ptp_match *match; + + match = (struct efx_ptp_match *)skb->cb; + if (match->state == PTP_PACKET_STATE_MATCH_UNWANTED) { + __skb_queue_tail(q, skb); + } else if (efx_ptp_match_rx(efx, skb) == + PTP_PACKET_STATE_MATCHED) { + rc = true; + __skb_queue_tail(q, skb); + } else if (time_after(jiffies, match->expiry)) { + match->state = PTP_PACKET_STATE_TIMED_OUT; + netif_warn(efx, rx_err, efx->net_dev, + "PTP packet - no timestamp seen\n"); + __skb_queue_tail(q, skb); + } else { + /* Replace unprocessed entry and stop */ + skb_queue_head(&ptp->rxq, skb); + break; + } + } + + return rc; +} + +/* Complete processing of a received packet */ +static inline void efx_ptp_process_rx(struct efx_nic *efx, struct sk_buff *skb) +{ + local_bh_disable(); + netif_receive_skb(skb); + local_bh_enable(); +} + +static int efx_ptp_start(struct efx_nic *efx) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + struct efx_filter_spec rxfilter; + int rc; + + ptp->reset_required = false; + + /* Must filter on both event and general ports to ensure + * that there is no packet re-ordering. + */ + efx_filter_init_rx(&rxfilter, EFX_FILTER_PRI_REQUIRED, 0, + efx_rx_queue_index( + efx_channel_get_rx_queue(ptp->channel))); + rc = efx_filter_set_ipv4_local(&rxfilter, IPPROTO_UDP, + htonl(PTP_ADDRESS), + htons(PTP_EVENT_PORT)); + if (rc != 0) + return rc; + + rc = efx_filter_insert_filter(efx, &rxfilter, true); + if (rc < 0) + return rc; + ptp->rxfilter_event = rc; + + efx_filter_init_rx(&rxfilter, EFX_FILTER_PRI_REQUIRED, 0, + efx_rx_queue_index( + efx_channel_get_rx_queue(ptp->channel))); + rc = efx_filter_set_ipv4_local(&rxfilter, IPPROTO_UDP, + htonl(PTP_ADDRESS), + htons(PTP_GENERAL_PORT)); + if (rc != 0) + goto fail; + + rc = efx_filter_insert_filter(efx, &rxfilter, true); + if (rc < 0) + goto fail; + ptp->rxfilter_general = rc; + + rc = efx_ptp_enable(efx); + if (rc != 0) + goto fail2; + + ptp->evt_frag_idx = 0; + ptp->current_adjfreq = 0; + ptp->rxfilter_installed = true; + + return 0; + +fail2: + efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, + ptp->rxfilter_general); +fail: + efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, + ptp->rxfilter_event); + + return rc; +} + +static int efx_ptp_stop(struct efx_nic *efx) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + int rc = efx_ptp_disable(efx); + struct list_head *cursor; + struct list_head *next; + + if (ptp->rxfilter_installed) { + efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, + ptp->rxfilter_general); + efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, + ptp->rxfilter_event); + ptp->rxfilter_installed = false; + } + + /* Make sure RX packets are really delivered */ + efx_ptp_deliver_rx_queue(&efx->ptp_data->rxq); + skb_queue_purge(&efx->ptp_data->txq); + + /* Drop any pending receive events */ + spin_lock_bh(&efx->ptp_data->evt_lock); + list_for_each_safe(cursor, next, &efx->ptp_data->evt_list) { + list_del(cursor); + list_add(cursor, &efx->ptp_data->evt_free_list); + } + spin_unlock_bh(&efx->ptp_data->evt_lock); + + return rc; +} + +static void efx_ptp_pps_worker(struct work_struct *work) +{ + struct efx_ptp_data *ptp = + container_of(work, struct efx_ptp_data, pps_work); + struct efx_nic *efx = ptp->channel->efx; + struct ptp_clock_event ptp_evt; + + if (efx_ptp_synchronize(efx, PTP_SYNC_ATTEMPTS)) + return; + + ptp_evt.type = PTP_CLOCK_PPSUSR; + ptp_evt.pps_times = ptp->host_time_pps; + ptp_clock_event(ptp->phc_clock, &ptp_evt); +} + +/* Process any pending transmissions and timestamp any received packets. + */ +static void efx_ptp_worker(struct work_struct *work) +{ + struct efx_ptp_data *ptp_data = + container_of(work, struct efx_ptp_data, work); + struct efx_nic *efx = ptp_data->channel->efx; + struct sk_buff *skb; + struct sk_buff_head tempq; + + if (ptp_data->reset_required) { + efx_ptp_stop(efx); + efx_ptp_start(efx); + return; + } + + efx_ptp_drop_time_expired_events(efx); + + __skb_queue_head_init(&tempq); + if (efx_ptp_process_events(efx, &tempq) || + !skb_queue_empty(&ptp_data->txq)) { + + while ((skb = skb_dequeue(&ptp_data->txq))) + efx_ptp_xmit_skb(efx, skb); + } + + while ((skb = __skb_dequeue(&tempq))) + efx_ptp_process_rx(efx, skb); +} + +/* Initialise PTP channel and state. + * + * Setting core_index to zero causes the queue to be initialised and doesn't + * overlap with 'rxq0' because ptp.c doesn't use skb_record_rx_queue. + */ +static int efx_ptp_probe_channel(struct efx_channel *channel) +{ + struct efx_nic *efx = channel->efx; + struct efx_ptp_data *ptp; + int rc = 0; + unsigned int pos; + + channel->irq_moderation = 0; + channel->rx_queue.core_index = 0; + + ptp = kzalloc(sizeof(struct efx_ptp_data), GFP_KERNEL); + efx->ptp_data = ptp; + if (!efx->ptp_data) + return -ENOMEM; + + rc = efx_nic_alloc_buffer(efx, &ptp->start, sizeof(int)); + if (rc != 0) + goto fail1; + + ptp->channel = channel; + skb_queue_head_init(&ptp->rxq); + skb_queue_head_init(&ptp->txq); + ptp->workwq = create_singlethread_workqueue("sfc_ptp"); + if (!ptp->workwq) { + rc = -ENOMEM; + goto fail2; + } + + INIT_WORK(&ptp->work, efx_ptp_worker); + ptp->config.flags = 0; + ptp->config.tx_type = HWTSTAMP_TX_OFF; + ptp->config.rx_filter = HWTSTAMP_FILTER_NONE; + INIT_LIST_HEAD(&ptp->evt_list); + INIT_LIST_HEAD(&ptp->evt_free_list); + spin_lock_init(&ptp->evt_lock); + for (pos = 0; pos < MAX_RECEIVE_EVENTS; pos++) + list_add(&ptp->rx_evts[pos].link, &ptp->evt_free_list); + + ptp->phc_clock_info.owner = THIS_MODULE; + snprintf(ptp->phc_clock_info.name, + sizeof(ptp->phc_clock_info.name), + "%pm", efx->net_dev->perm_addr); + ptp->phc_clock_info.max_adj = MAX_PPB; + ptp->phc_clock_info.n_alarm = 0; + ptp->phc_clock_info.n_ext_ts = 0; + ptp->phc_clock_info.n_per_out = 0; + ptp->phc_clock_info.pps = 1; + ptp->phc_clock_info.adjfreq = efx_phc_adjfreq; + ptp->phc_clock_info.adjtime = efx_phc_adjtime; + ptp->phc_clock_info.gettime = efx_phc_gettime; + ptp->phc_clock_info.settime = efx_phc_settime; + ptp->phc_clock_info.enable = efx_phc_enable; + + ptp->phc_clock = ptp_clock_register(&ptp->phc_clock_info); + if (!ptp->phc_clock) + goto fail3; + + INIT_WORK(&ptp->pps_work, efx_ptp_pps_worker); + ptp->pps_workwq = create_singlethread_workqueue("sfc_pps"); + if (!ptp->pps_workwq) { + rc = -ENOMEM; + goto fail4; + } + ptp->nic_ts_enabled = false; + + return 0; +fail4: + ptp_clock_unregister(efx->ptp_data->phc_clock); + +fail3: + destroy_workqueue(efx->ptp_data->workwq); + +fail2: + efx_nic_free_buffer(efx, &ptp->start); + +fail1: + kfree(efx->ptp_data); + efx->ptp_data = NULL; + + return rc; +} + +static void efx_ptp_remove_channel(struct efx_channel *channel) +{ + struct efx_nic *efx = channel->efx; + + if (!efx->ptp_data) + return; + + (void)efx_ptp_disable(channel->efx); + + cancel_work_sync(&efx->ptp_data->work); + cancel_work_sync(&efx->ptp_data->pps_work); + + skb_queue_purge(&efx->ptp_data->rxq); + skb_queue_purge(&efx->ptp_data->txq); + + ptp_clock_unregister(efx->ptp_data->phc_clock); + + destroy_workqueue(efx->ptp_data->workwq); + destroy_workqueue(efx->ptp_data->pps_workwq); + + efx_nic_free_buffer(efx, &efx->ptp_data->start); + kfree(efx->ptp_data); +} + +static void efx_ptp_get_channel_name(struct efx_channel *channel, + char *buf, size_t len) +{ + snprintf(buf, len, "%s-ptp", channel->efx->name); +} + +/* Determine whether this packet should be processed by the PTP module + * or transmitted conventionally. + */ +bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb) +{ + return efx->ptp_data && + efx->ptp_data->enabled && + skb->len >= PTP_MIN_LENGTH && + skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM && + likely(skb->protocol == htons(ETH_P_IP)) && + ip_hdr(skb)->protocol == IPPROTO_UDP && + udp_hdr(skb)->dest == htons(PTP_EVENT_PORT); +} + +/* Receive a PTP packet. Packets are queued until the arrival of + * the receive timestamp from the MC - this will probably occur after the + * packet arrival because of the processing in the MC. + */ +static void efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) +{ + struct efx_nic *efx = channel->efx; + struct efx_ptp_data *ptp = efx->ptp_data; + struct efx_ptp_match *match = (struct efx_ptp_match *)skb->cb; + u8 *data; + unsigned int version; + + match->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS); + + /* Correct version? */ + if (ptp->mode == MC_CMD_PTP_MODE_V1) { + if (skb->len < PTP_V1_MIN_LENGTH) { + netif_receive_skb(skb); + return; + } + version = ntohs(*(__be16 *)&skb->data[PTP_V1_VERSION_OFFSET]); + if (version != PTP_VERSION_V1) { + netif_receive_skb(skb); + return; + } + } else { + if (skb->len < PTP_V2_MIN_LENGTH) { + netif_receive_skb(skb); + return; + } + version = skb->data[PTP_V2_VERSION_OFFSET]; + + BUG_ON(ptp->mode != MC_CMD_PTP_MODE_V2); + BUILD_BUG_ON(PTP_V1_UUID_OFFSET != PTP_V2_MC_UUID_OFFSET); + BUILD_BUG_ON(PTP_V1_UUID_LENGTH != PTP_V2_MC_UUID_LENGTH); + BUILD_BUG_ON(PTP_V1_SEQUENCE_OFFSET != PTP_V2_SEQUENCE_OFFSET); + BUILD_BUG_ON(PTP_V1_SEQUENCE_LENGTH != PTP_V2_SEQUENCE_LENGTH); + + if ((version & PTP_VERSION_V2_MASK) != PTP_VERSION_V2) { + netif_receive_skb(skb); + return; + } + } + + /* Does this packet require timestamping? */ + if (ntohs(*(__be16 *)&skb->data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) { + struct skb_shared_hwtstamps *timestamps; + + match->state = PTP_PACKET_STATE_UNMATCHED; + + /* Clear all timestamps held: filled in later */ + timestamps = skb_hwtstamps(skb); + memset(timestamps, 0, sizeof(*timestamps)); + + /* Extract UUID/Sequence information */ + data = skb->data + PTP_V1_UUID_OFFSET; + match->words[0] = (data[0] | + (data[1] << 8) | + (data[2] << 16) | + (data[3] << 24)); + match->words[1] = (data[4] | + (data[5] << 8) | + (skb->data[PTP_V1_SEQUENCE_OFFSET + + PTP_V1_SEQUENCE_LENGTH - 1] << + 16)); + } else { + match->state = PTP_PACKET_STATE_MATCH_UNWANTED; + } + + skb_queue_tail(&ptp->rxq, skb); + queue_work(ptp->workwq, &ptp->work); +} + +/* Transmit a PTP packet. This has to be transmitted by the MC + * itself, through an MCDI call. MCDI calls aren't permitted + * in the transmit path so defer the actual transmission to a suitable worker. + */ +int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + + skb_queue_tail(&ptp->txq, skb); + + if ((udp_hdr(skb)->dest == htons(PTP_EVENT_PORT)) && + (skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM)) + efx_xmit_hwtstamp_pending(skb); + queue_work(ptp->workwq, &ptp->work); + + return NETDEV_TX_OK; +} + +static int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted, + unsigned int new_mode) +{ + if ((enable_wanted != efx->ptp_data->enabled) || + (enable_wanted && (efx->ptp_data->mode != new_mode))) { + int rc; + + if (enable_wanted) { + /* Change of mode requires disable */ + if (efx->ptp_data->enabled && + (efx->ptp_data->mode != new_mode)) { + efx->ptp_data->enabled = false; + rc = efx_ptp_stop(efx); + if (rc != 0) + return rc; + } + + /* Set new operating mode and establish + * baseline synchronisation, which must + * succeed. + */ + efx->ptp_data->mode = new_mode; + rc = efx_ptp_start(efx); + if (rc == 0) { + rc = efx_ptp_synchronize(efx, + PTP_SYNC_ATTEMPTS * 2); + if (rc != 0) + efx_ptp_stop(efx); + } + } else { + rc = efx_ptp_stop(efx); + } + + if (rc != 0) + return rc; + + efx->ptp_data->enabled = enable_wanted; + } + + return 0; +} + +static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init) +{ + bool enable_wanted = false; + unsigned int new_mode; + int rc; + + if (init->flags) + return -EINVAL; + + if ((init->tx_type != HWTSTAMP_TX_OFF) && + (init->tx_type != HWTSTAMP_TX_ON)) + return -ERANGE; + + new_mode = efx->ptp_data->mode; + /* Determine whether any PTP HW operations are required */ + switch (init->rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + init->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + new_mode = MC_CMD_PTP_MODE_V1; + enable_wanted = true; + break; + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + /* Although these three are accepted only IPV4 packets will be + * timestamped + */ + init->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; + new_mode = MC_CMD_PTP_MODE_V2; + enable_wanted = true; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + /* Non-IP + IPv6 timestamping not supported */ + return -ERANGE; + break; + default: + return -ERANGE; + } + + if (init->tx_type != HWTSTAMP_TX_OFF) + enable_wanted = true; + + rc = efx_ptp_change_mode(efx, enable_wanted, new_mode); + if (rc != 0) + return rc; + + efx->ptp_data->config = *init; + + return 0; +} + +int +efx_ptp_get_ts_info(struct net_device *net_dev, struct ethtool_ts_info *ts_info) +{ + struct efx_nic *efx = netdev_priv(net_dev); + struct efx_ptp_data *ptp = efx->ptp_data; + + if (!ptp) + return -EOPNOTSUPP; + + ts_info->so_timestamping = (SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE); + ts_info->phc_index = ptp_clock_index(ptp->phc_clock); + ts_info->tx_types = 1 << HWTSTAMP_TX_OFF | 1 << HWTSTAMP_TX_ON; + ts_info->rx_filters = (1 << HWTSTAMP_FILTER_NONE | + 1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT | + 1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC | + 1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ | + 1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT | + 1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC | + 1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ); + return 0; +} + +int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd) +{ + struct hwtstamp_config config; + int rc; + + /* Not a PTP enabled port */ + if (!efx->ptp_data) + return -EOPNOTSUPP; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + rc = efx_ptp_ts_init(efx, &config); + if (rc != 0) + return rc; + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) + ? -EFAULT : 0; +} + +static void ptp_event_failure(struct efx_nic *efx, int expected_frag_len) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + + netif_err(efx, hw, efx->net_dev, + "PTP unexpected event length: got %d expected %d\n", + ptp->evt_frag_idx, expected_frag_len); + ptp->reset_required = true; + queue_work(ptp->workwq, &ptp->work); +} + +/* Process a completed receive event. Put it on the event queue and + * start worker thread. This is required because event and their + * correspoding packets may come in either order. + */ +static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp) +{ + struct efx_ptp_event_rx *evt = NULL; + + if (ptp->evt_frag_idx != 3) { + ptp_event_failure(efx, 3); + return; + } + + spin_lock_bh(&ptp->evt_lock); + if (!list_empty(&ptp->evt_free_list)) { + evt = list_first_entry(&ptp->evt_free_list, + struct efx_ptp_event_rx, link); + list_del(&evt->link); + + evt->seq0 = EFX_QWORD_FIELD(ptp->evt_frags[2], MCDI_EVENT_DATA); + evt->seq1 = (EFX_QWORD_FIELD(ptp->evt_frags[2], + MCDI_EVENT_SRC) | + (EFX_QWORD_FIELD(ptp->evt_frags[1], + MCDI_EVENT_SRC) << 8) | + (EFX_QWORD_FIELD(ptp->evt_frags[0], + MCDI_EVENT_SRC) << 16)); + evt->hwtimestamp = ktime_set( + EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA), + EFX_QWORD_FIELD(ptp->evt_frags[1], MCDI_EVENT_DATA)); + evt->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS); + list_add_tail(&evt->link, &ptp->evt_list); + + queue_work(ptp->workwq, &ptp->work); + } else { + netif_err(efx, rx_err, efx->net_dev, "No free PTP event"); + } + spin_unlock_bh(&ptp->evt_lock); +} + +static void ptp_event_fault(struct efx_nic *efx, struct efx_ptp_data *ptp) +{ + int code = EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA); + if (ptp->evt_frag_idx != 1) { + ptp_event_failure(efx, 1); + return; + } + + netif_err(efx, hw, efx->net_dev, "PTP error %d\n", code); +} + +static void ptp_event_pps(struct efx_nic *efx, struct efx_ptp_data *ptp) +{ + if (ptp->nic_ts_enabled) + queue_work(ptp->pps_workwq, &ptp->pps_work); +} + +void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE); + + if (!ptp->enabled) + return; + + if (ptp->evt_frag_idx == 0) { + ptp->evt_code = code; + } else if (ptp->evt_code != code) { + netif_err(efx, hw, efx->net_dev, + "PTP out of sequence event %d\n", code); + ptp->evt_frag_idx = 0; + } + + ptp->evt_frags[ptp->evt_frag_idx++] = *ev; + if (!MCDI_EVENT_FIELD(*ev, CONT)) { + /* Process resulting event */ + switch (code) { + case MCDI_EVENT_CODE_PTP_RX: + ptp_event_rx(efx, ptp); + break; + case MCDI_EVENT_CODE_PTP_FAULT: + ptp_event_fault(efx, ptp); + break; + case MCDI_EVENT_CODE_PTP_PPS: + ptp_event_pps(efx, ptp); + break; + default: + netif_err(efx, hw, efx->net_dev, + "PTP unknown event %d\n", code); + break; + } + ptp->evt_frag_idx = 0; + } else if (MAX_EVENT_FRAGS == ptp->evt_frag_idx) { + netif_err(efx, hw, efx->net_dev, + "PTP too many event fragments\n"); + ptp->evt_frag_idx = 0; + } +} + +static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) +{ + struct efx_ptp_data *ptp_data = container_of(ptp, + struct efx_ptp_data, + phc_clock_info); + struct efx_nic *efx = ptp_data->channel->efx; + u8 inadj[MC_CMD_PTP_IN_ADJUST_LEN]; + s64 adjustment_ns; + int rc; + + if (delta > MAX_PPB) + delta = MAX_PPB; + else if (delta < -MAX_PPB) + delta = -MAX_PPB; + + /* Convert ppb to fixed point ns. */ + adjustment_ns = (((s64)delta * PPB_SCALE_WORD) >> + (PPB_EXTRA_BITS + MAX_PPB_BITS)); + + MCDI_SET_DWORD(inadj, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST); + MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_FREQ_LO, (u32)adjustment_ns); + MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_FREQ_HI, + (u32)(adjustment_ns >> 32)); + MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_SECONDS, 0); + MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_NANOSECONDS, 0); + rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inadj, sizeof(inadj), + NULL, 0, NULL); + if (rc != 0) + return rc; + + ptp_data->current_adjfreq = delta; + return 0; +} + +static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct efx_ptp_data *ptp_data = container_of(ptp, + struct efx_ptp_data, + phc_clock_info); + struct efx_nic *efx = ptp_data->channel->efx; + struct timespec delta_ts = ns_to_timespec(delta); + u8 inbuf[MC_CMD_PTP_IN_ADJUST_LEN]; + + MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST); + MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_FREQ_LO, 0); + MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_FREQ_HI, 0); + MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_SECONDS, (u32)delta_ts.tv_sec); + MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_NANOSECONDS, (u32)delta_ts.tv_nsec); + return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), + NULL, 0, NULL); +} + +static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +{ + struct efx_ptp_data *ptp_data = container_of(ptp, + struct efx_ptp_data, + phc_clock_info); + struct efx_nic *efx = ptp_data->channel->efx; + u8 inbuf[MC_CMD_PTP_IN_READ_NIC_TIME_LEN]; + u8 outbuf[MC_CMD_PTP_OUT_READ_NIC_TIME_LEN]; + int rc; + + MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_READ_NIC_TIME); + + rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), NULL); + if (rc != 0) + return rc; + + ts->tv_sec = MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_SECONDS); + ts->tv_nsec = MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_NANOSECONDS); + return 0; +} + +static int efx_phc_settime(struct ptp_clock_info *ptp, + const struct timespec *e_ts) +{ + /* Get the current NIC time, efx_phc_gettime. + * Subtract from the desired time to get the offset + * call efx_phc_adjtime with the offset + */ + int rc; + struct timespec time_now; + struct timespec delta; + + rc = efx_phc_gettime(ptp, &time_now); + if (rc != 0) + return rc; + + delta = timespec_sub(*e_ts, time_now); + + efx_phc_adjtime(ptp, timespec_to_ns(&delta)); + if (rc != 0) + return rc; + + return 0; +} + +static int efx_phc_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *request, + int enable) +{ + struct efx_ptp_data *ptp_data = container_of(ptp, + struct efx_ptp_data, + phc_clock_info); + if (request->type != PTP_CLK_REQ_PPS) + return -EOPNOTSUPP; + + ptp_data->nic_ts_enabled = !!enable; + return 0; +} + +static const struct efx_channel_type efx_ptp_channel_type = { + .handle_no_channel = efx_ptp_handle_no_channel, + .pre_probe = efx_ptp_probe_channel, + .post_remove = efx_ptp_remove_channel, + .get_name = efx_ptp_get_channel_name, + /* no copy operation; there is no need to reallocate this channel */ + .receive_skb = efx_ptp_rx, + .keep_eventq = false, +}; + +void efx_ptp_probe(struct efx_nic *efx) +{ + /* Check whether PTP is implemented on this NIC. The DISABLE + * operation will succeed if and only if it is implemented. + */ + if (efx_ptp_disable(efx) == 0) + efx->extra_channel_type[EFX_EXTRA_CHANNEL_PTP] = + &efx_ptp_channel_type; +} diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c index 6bafd216e55e..84b41bf08a38 100644 --- a/drivers/net/ethernet/sfc/siena.c +++ b/drivers/net/ethernet/sfc/siena.c @@ -335,6 +335,7 @@ static int siena_probe_nic(struct efx_nic *efx) goto fail5; efx_sriov_probe(efx); + efx_ptp_probe(efx); return 0; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index ebca75ed78dc..5e090e54298e 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -339,6 +339,12 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, EFX_WARN_ON_PARANOID(!netif_device_present(net_dev)); + /* PTP "event" packet */ + if (unlikely(efx_xmit_with_hwtstamp(skb)) && + unlikely(efx_ptp_is_ptp_tx(efx, skb))) { + return efx_ptp_tx(efx, skb); + } + index = skb_get_queue_mapping(skb); type = skb->ip_summed == CHECKSUM_PARTIAL ? EFX_TXQ_TYPE_OFFLOAD : 0; if (index >= efx->n_tx_channels) { -- cgit v1.2.3 From bfeed902946a31692e7a24ed355b6d13ac37d014 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 7 Sep 2012 00:58:10 +0100 Subject: sfc: Convert firmware subtypes to native byte order in efx_mcdi_get_board_cfg() On big-endian systems the MTD partition names currently have mangled subtype numbers and are not recognised by the firmware update tool (sfupdate). Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/mcdi.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 294df4bca4a6..578e5f72aabe 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -661,9 +661,8 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, u16 *fw_subtype_list, u32 *capabilities) { uint8_t outbuf[MC_CMD_GET_BOARD_CFG_OUT_LENMIN]; - size_t outlen; + size_t outlen, offset, i; int port_num = efx_port_num(efx); - int offset; int rc; BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_IN_LEN != 0); @@ -683,11 +682,16 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, : MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST; if (mac_address) memcpy(mac_address, outbuf + offset, ETH_ALEN); - if (fw_subtype_list) - memcpy(fw_subtype_list, - outbuf + MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST, - MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MINNUM * - sizeof(fw_subtype_list[0])); + if (fw_subtype_list) { + offset = MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST; + for (i = 0; + i < MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MINNUM; + i++) { + fw_subtype_list[i] = + le16_to_cpup((__le16 *)(outbuf + offset)); + offset += 2; + } + } if (capabilities) { if (port_num) *capabilities = MCDI_DWORD(outbuf, -- cgit v1.2.3 From e3f5ec1108ee01b555d5894722884e40dbec058f Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 5 Jul 2011 00:04:42 +0100 Subject: sfc: Support variable-length response to MCDI GET_BOARD_CFG Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/mcdi.c | 6 ++++-- drivers/net/ethernet/sfc/mtd.c | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 578e5f72aabe..e855f4cddb4e 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -683,12 +683,14 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, if (mac_address) memcpy(mac_address, outbuf + offset, ETH_ALEN); if (fw_subtype_list) { + /* Byte-swap and truncate or zero-pad as necessary */ offset = MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST; for (i = 0; - i < MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MINNUM; + i < MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM; i++) { fw_subtype_list[i] = - le16_to_cpup((__le16 *)(outbuf + offset)); + (offset + 2 <= outlen) ? + le16_to_cpup((__le16 *)(outbuf + offset)) : 0; offset += 2; } } diff --git a/drivers/net/ethernet/sfc/mtd.c b/drivers/net/ethernet/sfc/mtd.c index 758148379b0e..8f4604d5d642 100644 --- a/drivers/net/ethernet/sfc/mtd.c +++ b/drivers/net/ethernet/sfc/mtd.c @@ -627,7 +627,8 @@ static int siena_mtd_get_fw_subtypes(struct efx_nic *efx, struct efx_mtd *efx_mtd) { struct efx_mtd_partition *part; - uint16_t fw_subtype_list[MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MINNUM]; + uint16_t fw_subtype_list[ + MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM]; int rc; rc = efx_mcdi_get_board_cfg(efx, NULL, fw_subtype_list, NULL); -- cgit v1.2.3 From e5621545e2461730af23054f355d348109881eb9 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 5 Jul 2011 00:05:56 +0100 Subject: sfc: Expose FPGA bitfile partition through MTD Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/mtd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/mtd.c b/drivers/net/ethernet/sfc/mtd.c index 8f4604d5d642..08f825b71ac8 100644 --- a/drivers/net/ethernet/sfc/mtd.c +++ b/drivers/net/ethernet/sfc/mtd.c @@ -585,6 +585,7 @@ static const struct siena_nvram_type_info siena_nvram_types[] = { [MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT1] = { 1, "sfc_exp_rom_cfg" }, [MC_CMD_NVRAM_TYPE_PHY_PORT0] = { 0, "sfc_phy_fw" }, [MC_CMD_NVRAM_TYPE_PHY_PORT1] = { 1, "sfc_phy_fw" }, + [MC_CMD_NVRAM_TYPE_FPGA] = { 0, "sfc_fpga" }, }; static int siena_mtd_probe_partition(struct efx_nic *efx, @@ -598,7 +599,8 @@ static int siena_mtd_probe_partition(struct efx_nic *efx, bool protected; int rc; - if (type >= ARRAY_SIZE(siena_nvram_types)) + if (type >= ARRAY_SIZE(siena_nvram_types) || + siena_nvram_types[type].name == NULL) return -ENODEV; info = &siena_nvram_types[type]; -- cgit v1.2.3 From 25ce200215666956d96d1a62a20c75a2f3b9d38e Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 17 Jul 2012 20:45:55 +0100 Subject: sfc: Bump version to 3.2 The key new feature for 3.2 is PTP support. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/net_driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 797dbed25d94..c1a010cda89b 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -37,7 +37,7 @@ * **************************************************************************/ -#define EFX_DRIVER_VERSION "3.1" +#define EFX_DRIVER_VERSION "3.2" #ifdef DEBUG #define EFX_BUG_ON_PARANOID(x) BUG_ON(x) -- cgit v1.2.3 From 450783747f42dfa3883920acfad4acdd93ce69af Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Wed, 19 Sep 2012 02:53:34 +0100 Subject: sfc: Avoid generating over-length MC_CMD_FLUSH_RX_QUEUES request MCDI supports requests up to 252 bytes long, which is only enough to pass 63 RX queue IDs to MC_CMD_FLUSH_RX_QUEUES. However a VF may have up to 64 RX queues, and if we try to flush them all we will generate an over-length request and BUG() in efx_mcdi_copyin(). Currently all VF drivers limit themselves to 32 RX queues, so reducing the limit to 63 does no harm. Also add a BUILD_BUG_ON in efx_mcdi_flush_rxqs() so we remember to deal with the same problem there if EFX_MAX_CHANNELS is increased. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/mcdi.c | 3 +++ drivers/net/ethernet/sfc/siena_sriov.c | 7 +++++++ 2 files changed, 10 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index e855f4cddb4e..aea43cbd0520 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -1195,6 +1195,9 @@ int efx_mcdi_flush_rxqs(struct efx_nic *efx) __le32 *qid; int rc, count; + BUILD_BUG_ON(EFX_MAX_CHANNELS > + MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM); + qid = kmalloc(EFX_MAX_CHANNELS * sizeof(*qid), GFP_KERNEL); if (qid == NULL) return -ENOMEM; diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c index 9cb3b84ecae9..a8f48a455849 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.c +++ b/drivers/net/ethernet/sfc/siena_sriov.c @@ -21,6 +21,9 @@ /* Number of longs required to track all the VIs in a VF */ #define VI_MASK_LENGTH BITS_TO_LONGS(1 << EFX_VI_SCALE_MAX) +/* Maximum number of RX queues supported */ +#define VF_MAX_RX_QUEUES 63 + /** * enum efx_vf_tx_filter_mode - TX MAC filtering behaviour * @VF_TX_FILTER_OFF: Disabled @@ -578,6 +581,7 @@ static int efx_vfdi_init_rxq(struct efx_vf *vf) efx_oword_t reg; if (bad_vf_index(efx, vf_evq) || bad_vf_index(efx, vf_rxq) || + vf_rxq >= VF_MAX_RX_QUEUES || bad_buf_count(buf_count, EFX_MAX_DMAQ_SIZE)) { if (net_ratelimit()) netif_err(efx, hw, efx->net_dev, @@ -683,6 +687,9 @@ static int efx_vfdi_fini_all_queues(struct efx_vf *vf) __le32 *rxqs; int rc; + BUILD_BUG_ON(VF_MAX_RX_QUEUES > + MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM); + rxqs = kmalloc(count * sizeof(*rxqs), GFP_KERNEL); if (rxqs == NULL) return VFDI_RC_ENOMEM; -- cgit v1.2.3 From a019c5e25190107a88377cde8918c169d15a7add Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Sep 2012 20:34:35 +0000 Subject: net: seeq: use __iomem pointers for MMIO ARM is moving to stricter checks on readl/write functions, so we need to use the correct types everywhere. Cc: netdev@vger.kernel.org Cc: "David S. Miller" Signed-off-by: Arnd Bergmann --- drivers/net/ethernet/seeq/ether3.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c index df808ac8cb65..6a40dd03a32f 100644 --- a/drivers/net/ethernet/seeq/ether3.c +++ b/drivers/net/ethernet/seeq/ether3.c @@ -99,13 +99,13 @@ typedef enum { * The SEEQ8005 doesn't like us writing to its registers * too quickly. */ -static inline void ether3_outb(int v, const void __iomem *r) +static inline void ether3_outb(int v, void __iomem *r) { writeb(v, r); udelay(1); } -static inline void ether3_outw(int v, const void __iomem *r) +static inline void ether3_outw(int v, void __iomem *r) { writew(v, r); udelay(1); -- cgit v1.2.3 From 1d3ff76759b70e201e6b379c37ac106c487ff506 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 14 Sep 2012 00:33:48 +0000 Subject: i825xx: znet: fix compiler warnings when building a 64-bit kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When building 64-bit kernel with this driver we get following warnings from the compiler: drivers/net/ethernet/i825xx/znet.c: In function ‘hardware_init’: drivers/net/ethernet/i825xx/znet.c:863:29: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] drivers/net/ethernet/i825xx/znet.c:870:29: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] Fix these by calling isa_virt_to_bus() before passing the pointers to set_dma_addr(). Signed-off-by: Mika Westerberg Signed-off-by: David S. Miller --- drivers/net/ethernet/i825xx/znet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/i825xx/znet.c b/drivers/net/ethernet/i825xx/znet.c index ba4e0cea3506..c9479e081b8a 100644 --- a/drivers/net/ethernet/i825xx/znet.c +++ b/drivers/net/ethernet/i825xx/znet.c @@ -865,14 +865,14 @@ static void hardware_init(struct net_device *dev) disable_dma(znet->rx_dma); /* reset by an interrupting task. */ clear_dma_ff(znet->rx_dma); set_dma_mode(znet->rx_dma, DMA_RX_MODE); - set_dma_addr(znet->rx_dma, (unsigned int) znet->rx_start); + set_dma_addr(znet->rx_dma, isa_virt_to_bus(znet->rx_start)); set_dma_count(znet->rx_dma, RX_BUF_SIZE); enable_dma(znet->rx_dma); /* Now set up the Tx channel. */ disable_dma(znet->tx_dma); clear_dma_ff(znet->tx_dma); set_dma_mode(znet->tx_dma, DMA_TX_MODE); - set_dma_addr(znet->tx_dma, (unsigned int) znet->tx_start); + set_dma_addr(znet->tx_dma, isa_virt_to_bus(znet->tx_start)); set_dma_count(znet->tx_dma, znet->tx_buf_len<<1); enable_dma(znet->tx_dma); release_dma_lock(flags); -- cgit v1.2.3 From 6b6e27255f29a6191ef8ad96bfcc392ab2ef6c71 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 17 Sep 2012 10:03:26 +0000 Subject: netdev: make address const in device address management The internal functions for add/deleting addresses don't change their argument. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 +-- drivers/net/macvlan.c | 4 +-- include/linux/netdevice.h | 28 +++++++++---------- net/bridge/br_fdb.c | 6 ++-- net/bridge/br_private.h | 4 +-- net/core/dev_addr_lists.c | 40 ++++++++++++++------------- 6 files changed, 44 insertions(+), 42 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 2dc9d91e2b67..70d27a361857 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6890,7 +6890,7 @@ static int ixgbe_set_features(struct net_device *netdev, static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr, + const unsigned char *addr, u16 flags) { struct ixgbe_adapter *adapter = netdev_priv(dev); @@ -6927,7 +6927,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, static int ixgbe_ndo_fdb_del(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr) + const unsigned char *addr) { struct ixgbe_adapter *adapter = netdev_priv(dev); int err = -EOPNOTSUPP; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 66a9bfe7b1c8..815dfcfbc7b9 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -548,7 +548,7 @@ static int macvlan_vlan_rx_kill_vid(struct net_device *dev, static int macvlan_fdb_add(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr, + const unsigned char *addr, u16 flags) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -567,7 +567,7 @@ static int macvlan_fdb_add(struct ndmsg *ndm, static int macvlan_fdb_del(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr) + const unsigned char *addr) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ae3153c0db0a..82264e717e53 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -907,10 +907,10 @@ struct netdev_fcoe_hbainfo { * Must return >0 or -errno if it changed dev->features itself. * * int (*ndo_fdb_add)(struct ndmsg *ndm, struct net_device *dev, - * unsigned char *addr, u16 flags) + * const unsigned char *addr, u16 flags) * Adds an FDB entry to dev for addr. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct net_device *dev, - * unsigned char *addr) + * const unsigned char *addr) * Deletes the FDB entry from dev coresponding to addr. * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, int idx) @@ -1017,11 +1017,11 @@ struct net_device_ops { int (*ndo_fdb_add)(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr, + const unsigned char *addr, u16 flags); int (*ndo_fdb_del)(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr); + const unsigned char *addr); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, @@ -2561,9 +2561,9 @@ extern void __hw_addr_flush(struct netdev_hw_addr_list *list); extern void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ -extern int dev_addr_add(struct net_device *dev, unsigned char *addr, +extern int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); -extern int dev_addr_del(struct net_device *dev, unsigned char *addr, +extern int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); extern int dev_addr_add_multiple(struct net_device *to_dev, struct net_device *from_dev, @@ -2575,20 +2575,20 @@ extern void dev_addr_flush(struct net_device *dev); extern int dev_addr_init(struct net_device *dev); /* Functions used for unicast addresses handling */ -extern int dev_uc_add(struct net_device *dev, unsigned char *addr); -extern int dev_uc_add_excl(struct net_device *dev, unsigned char *addr); -extern int dev_uc_del(struct net_device *dev, unsigned char *addr); +extern int dev_uc_add(struct net_device *dev, const unsigned char *addr); +extern int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr); +extern int dev_uc_del(struct net_device *dev, const unsigned char *addr); extern int dev_uc_sync(struct net_device *to, struct net_device *from); extern void dev_uc_unsync(struct net_device *to, struct net_device *from); extern void dev_uc_flush(struct net_device *dev); extern void dev_uc_init(struct net_device *dev); /* Functions used for multicast addresses handling */ -extern int dev_mc_add(struct net_device *dev, unsigned char *addr); -extern int dev_mc_add_global(struct net_device *dev, unsigned char *addr); -extern int dev_mc_add_excl(struct net_device *dev, unsigned char *addr); -extern int dev_mc_del(struct net_device *dev, unsigned char *addr); -extern int dev_mc_del_global(struct net_device *dev, unsigned char *addr); +extern int dev_mc_add(struct net_device *dev, const unsigned char *addr); +extern int dev_mc_add_global(struct net_device *dev, const unsigned char *addr); +extern int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr); +extern int dev_mc_del(struct net_device *dev, const unsigned char *addr); +extern int dev_mc_del_global(struct net_device *dev, const unsigned char *addr); extern int dev_mc_sync(struct net_device *to, struct net_device *from); extern void dev_mc_unsync(struct net_device *to, struct net_device *from); extern void dev_mc_flush(struct net_device *dev); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index ddf93efc133c..02861190a3d4 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -609,7 +609,7 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, /* Add new permanent fdb entry with RTM_NEWNEIGH */ int br_fdb_add(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr, u16 nlh_flags) + const unsigned char *addr, u16 nlh_flags) { struct net_bridge_port *p; int err = 0; @@ -639,7 +639,7 @@ int br_fdb_add(struct ndmsg *ndm, struct net_device *dev, return err; } -static int fdb_delete_by_addr(struct net_bridge_port *p, u8 *addr) +static int fdb_delete_by_addr(struct net_bridge_port *p, const u8 *addr) { struct net_bridge *br = p->br; struct hlist_head *head = &br->hash[br_mac_hash(addr)]; @@ -655,7 +655,7 @@ static int fdb_delete_by_addr(struct net_bridge_port *p, u8 *addr) /* Remove neighbor entry with RTM_DELNEIGH */ int br_fdb_delete(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr) + const unsigned char *addr) { struct net_bridge_port *p; int err; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index f507d2af9646..11a984b87e62 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -363,10 +363,10 @@ extern void br_fdb_update(struct net_bridge *br, extern int br_fdb_delete(struct ndmsg *ndm, struct net_device *dev, - unsigned char *addr); + const unsigned char *addr); extern int br_fdb_add(struct ndmsg *nlh, struct net_device *dev, - unsigned char *addr, + const unsigned char *addr, u16 nlh_flags); extern int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index c4cc2bc49f06..87cc17db2d56 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -22,7 +22,7 @@ */ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, - unsigned char *addr, int addr_len, + const unsigned char *addr, int addr_len, unsigned char addr_type, bool global) { struct netdev_hw_addr *ha; @@ -46,7 +46,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, - unsigned char *addr, int addr_len, + const unsigned char *addr, int addr_len, unsigned char addr_type, bool global) { struct netdev_hw_addr *ha; @@ -72,14 +72,15 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, return __hw_addr_create_ex(list, addr, addr_len, addr_type, global); } -static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) +static int __hw_addr_add(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false); } static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, - unsigned char *addr, int addr_len, + const unsigned char *addr, int addr_len, unsigned char addr_type, bool global) { struct netdev_hw_addr *ha; @@ -104,8 +105,9 @@ static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, return -ENOENT; } -static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) +static int __hw_addr_del(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) { return __hw_addr_del_ex(list, addr, addr_len, addr_type, false); } @@ -278,7 +280,7 @@ EXPORT_SYMBOL(dev_addr_init); * * The caller must hold the rtnl_mutex. */ -int dev_addr_add(struct net_device *dev, unsigned char *addr, +int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; @@ -303,7 +305,7 @@ EXPORT_SYMBOL(dev_addr_add); * * The caller must hold the rtnl_mutex. */ -int dev_addr_del(struct net_device *dev, unsigned char *addr, +int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; @@ -390,7 +392,7 @@ EXPORT_SYMBOL(dev_addr_del_multiple); * @dev: device * @addr: address to add */ -int dev_uc_add_excl(struct net_device *dev, unsigned char *addr) +int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { struct netdev_hw_addr *ha; int err; @@ -421,7 +423,7 @@ EXPORT_SYMBOL(dev_uc_add_excl); * Add a secondary unicast address to the device or increase * the reference count if it already exists. */ -int dev_uc_add(struct net_device *dev, unsigned char *addr) +int dev_uc_add(struct net_device *dev, const unsigned char *addr) { int err; @@ -443,7 +445,7 @@ EXPORT_SYMBOL(dev_uc_add); * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. */ -int dev_uc_del(struct net_device *dev, unsigned char *addr) +int dev_uc_del(struct net_device *dev, const unsigned char *addr) { int err; @@ -543,7 +545,7 @@ EXPORT_SYMBOL(dev_uc_init); * @dev: device * @addr: address to add */ -int dev_mc_add_excl(struct net_device *dev, unsigned char *addr) +int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { struct netdev_hw_addr *ha; int err; @@ -566,7 +568,7 @@ out: } EXPORT_SYMBOL(dev_mc_add_excl); -static int __dev_mc_add(struct net_device *dev, unsigned char *addr, +static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, bool global) { int err; @@ -587,7 +589,7 @@ static int __dev_mc_add(struct net_device *dev, unsigned char *addr, * Add a multicast address to the device or increase * the reference count if it already exists. */ -int dev_mc_add(struct net_device *dev, unsigned char *addr) +int dev_mc_add(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, false); } @@ -600,13 +602,13 @@ EXPORT_SYMBOL(dev_mc_add); * * Add a global multicast address to the device. */ -int dev_mc_add_global(struct net_device *dev, unsigned char *addr) +int dev_mc_add_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, true); } EXPORT_SYMBOL(dev_mc_add_global); -static int __dev_mc_del(struct net_device *dev, unsigned char *addr, +static int __dev_mc_del(struct net_device *dev, const unsigned char *addr, bool global) { int err; @@ -628,7 +630,7 @@ static int __dev_mc_del(struct net_device *dev, unsigned char *addr, * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ -int dev_mc_del(struct net_device *dev, unsigned char *addr) +int dev_mc_del(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, false); } @@ -642,7 +644,7 @@ EXPORT_SYMBOL(dev_mc_del); * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ -int dev_mc_del_global(struct net_device *dev, unsigned char *addr) +int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, true); } -- cgit v1.2.3 From aee77e4accbeb2c86b1d294cd84fec4a12dde3bd Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Sun, 9 Sep 2012 13:55:26 +0000 Subject: r8169: use unlimited DMA burst for TX The r8169 driver currently limits the DMA burst for TX to 1024 bytes. I have a box where this prevents the interface from using the gigabit line to its full potential. This patch solves the problem by setting TX_DMA_BURST to unlimited. The box has an ASRock B75M motherboard with on-board RTL8168evl/8111evl (XID 0c900880). TSO is enabled. I used netperf (TCP_STREAM test) to measure the dependency of TX throughput on MTU. I did it for three different values of TX_DMA_BURST ('5'=512, '6'=1024, '7'=unlimited). This chart shows the results: http://michich.fedorapeople.org/r8169/r8169-effects-of-TX_DMA_BURST.png Interesting points: - With the current DMA burst limit (1024): - at the default MTU=1500 I get only 842 Mbit/s. - when going from small MTU, the performance rises monotonically with increasing MTU only up to a peak at MTU=1076 (908 MBit/s). Then there's a sudden drop to 762 MBit/s from which the throughput rises monotonically again with further MTU increases. - With a smaller DMA burst limit (512): - there's a similar peak at MTU=1076 and another one at MTU=564. - With unlimited DMA burst: - at the default MTU=1500 I get nice 940 Mbit/s. - the throughput rises monotonically with increasing MTU with no strange peaks. Notice that the peaks occur at MTU sizes that are multiples of the DMA burst limit plus 52. Why 52? Because: 20 (IP header) + 20 (TCP header) + 12 (TCP options) = 52 The Realtek-provided r8168 driver (v8.032.00) uses unlimited TX DMA burst too, except for CFG_METHOD_1 where the TX DMA burst is set to 512 bytes. CFG_METHOD_1 appears to be the oldest MAC version of "RTL8168B/8111B", i.e. RTL_GIGA_MAC_VER_11 in r8169. Not sure if this MAC version really needs the smaller burst limit, or if any other versions have similar requirements. Signed-off-by: Michal Schmidt Acked-by: Francois Romieu Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 0c96604e6246..8b4e0a93f45e 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -77,7 +77,7 @@ static const int multicast_filter_limit = 32; #define MAX_READ_REQUEST_SHIFT 12 -#define TX_DMA_BURST 6 /* Maximum PCI burst, '6' is 1024 */ +#define TX_DMA_BURST 7 /* Maximum PCI burst, '7' is unlimited */ #define SafeMtu 0x1c20 /* ... actually life sucks beyond ~7k */ #define InterFrameGap 0x03 /* 3 means InterFrameGap = the shortest one */ -- cgit v1.2.3 From ae1c07a6b7ced6c0c94c99e3b53f4e7856fa8bff Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 8 Aug 2012 05:23:22 +0000 Subject: igb: Remove artificial restriction on RQDPC stat reading For some reason the reading of the RQDPC register was being artificially limited to 4K. Instead of limiting the value we should read the value and add the full amount. Otherwise this can lead to a misleading number of dropped packets when the actual value is in fact much higher. Signed-off-by: Alexander Duyck Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 19d7666dfccb..246646b61a1a 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4681,11 +4681,13 @@ void igb_update_stats(struct igb_adapter *adapter, bytes = 0; packets = 0; for (i = 0; i < adapter->num_rx_queues; i++) { - u32 rqdpc_tmp = rd32(E1000_RQDPC(i)) & 0x0FFF; + u32 rqdpc = rd32(E1000_RQDPC(i)); struct igb_ring *ring = adapter->rx_ring[i]; - ring->rx_stats.drops += rqdpc_tmp; - net_stats->rx_fifo_errors += rqdpc_tmp; + if (rqdpc) { + ring->rx_stats.drops += rqdpc; + net_stats->rx_fifo_errors += rqdpc; + } do { start = u64_stats_fetch_begin_bh(&ring->rx_syncp); -- cgit v1.2.3 From e5461112d993b5038954554b5c871d14e45ecc5c Mon Sep 17 00:00:00 2001 From: "Akeem G. Abodunrin" Date: Thu, 6 Sep 2012 01:28:31 +0000 Subject: igb: Support to enable EEE on all eee_supported devices Current implementation enables EEE on only i350 device. This patch enables EEE on all eee_supported devices. Also, configured LPI clock to keep running before EEE is enabled on i210 and i211 devices. Signed-off-by: Akeem G. Abodunrin Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/e1000_82575.c | 17 +++++++++++++---- drivers/net/ethernet/intel/igb/e1000_defines.h | 3 ++- drivers/net/ethernet/intel/igb/e1000_regs.h | 1 + 3 files changed, 16 insertions(+), 5 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index ba994fb4cec6..ca4641e2f748 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -2223,11 +2223,10 @@ out: s32 igb_set_eee_i350(struct e1000_hw *hw) { s32 ret_val = 0; - u32 ipcnfg, eeer, ctrl_ext; + u32 ipcnfg, eeer; - ctrl_ext = rd32(E1000_CTRL_EXT); - if ((hw->mac.type != e1000_i350) || - (ctrl_ext & E1000_CTRL_EXT_LINK_MODE_MASK)) + if ((hw->mac.type < e1000_i350) || + (hw->phy.media_type != e1000_media_type_copper)) goto out; ipcnfg = rd32(E1000_IPCNFG); eeer = rd32(E1000_EEER); @@ -2240,6 +2239,14 @@ s32 igb_set_eee_i350(struct e1000_hw *hw) E1000_EEER_RX_LPI_EN | E1000_EEER_LPI_FC); + /* keep the LPI clock running before EEE is enabled */ + if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) { + u32 eee_su; + eee_su = rd32(E1000_EEE_SU); + eee_su &= ~E1000_EEE_SU_LPI_CLK_STP; + wr32(E1000_EEE_SU, eee_su); + } + } else { ipcnfg &= ~(E1000_IPCNFG_EEE_1G_AN | E1000_IPCNFG_EEE_100M_AN); @@ -2249,6 +2256,8 @@ s32 igb_set_eee_i350(struct e1000_hw *hw) } wr32(E1000_IPCNFG, ipcnfg); wr32(E1000_EEER, eeer); + rd32(E1000_IPCNFG); + rd32(E1000_EEER); out: return ret_val; diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index cae3070da922..de4b41ec3c40 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -857,8 +857,9 @@ #define E1000_IPCNFG_EEE_100M_AN 0x00000004 /* EEE Enable 100M AN */ #define E1000_EEER_TX_LPI_EN 0x00010000 /* EEE Tx LPI Enable */ #define E1000_EEER_RX_LPI_EN 0x00020000 /* EEE Rx LPI Enable */ -#define E1000_EEER_FRC_AN 0x10000000 /* Enable EEE in loopback */ +#define E1000_EEER_FRC_AN 0x10000000 /* Enable EEE in loopback */ #define E1000_EEER_LPI_FC 0x00040000 /* EEE Enable on FC */ +#define E1000_EEE_SU_LPI_CLK_STP 0X00800000 /* EEE LPI Clock Stop */ /* SerDes Control */ #define E1000_GEN_CTL_READY 0x80000000 diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index faec840a5a8a..e5db48594e8a 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -349,6 +349,7 @@ /* Energy Efficient Ethernet "EEE" register */ #define E1000_IPCNFG 0x0E38 /* Internal PHY Configuration */ #define E1000_EEER 0x0E30 /* Energy Efficient Ethernet */ +#define E1000_EEE_SU 0X0E34 /* EEE Setup */ /* Thermal Sensor Register */ #define E1000_THSTAT 0x08110 /* Thermal Sensor Status */ -- cgit v1.2.3 From 31186785186415eaf2b66025969d2364a07c9e83 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 20 Jul 2012 08:09:58 +0000 Subject: ixgbevf: Add support for VF API negotiation This change makes it so that the VF can support the PF/VF API negotiation protocol. Specifically in this case we are adding support for API 1.0 which will mean that the VF is capable of cleaning up buffers that span multiple descriptors without triggering an error. Signed-off-by: Alexander Duyck Tested-by: Sibai Li Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/defines.h | 1 + drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 23 ++++++++++++++ drivers/net/ethernet/intel/ixgbevf/mbx.h | 21 +++++++++++-- drivers/net/ethernet/intel/ixgbevf/vf.c | 37 +++++++++++++++++++++++ drivers/net/ethernet/intel/ixgbevf/vf.h | 3 ++ 5 files changed, 83 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h index 418af827b230..da17ccf5c09d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/defines.h +++ b/drivers/net/ethernet/intel/ixgbevf/defines.h @@ -272,5 +272,6 @@ struct ixgbe_adv_tx_context_desc { /* Error Codes */ #define IXGBE_ERR_INVALID_MAC_ADDR -1 #define IXGBE_ERR_RESET_FAILED -2 +#define IXGBE_ERR_INVALID_ARGUMENT -3 #endif /* _IXGBEVF_DEFINES_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index a5d9cc5bb257..c5ffe1dd3fcd 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1334,6 +1334,25 @@ static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter) adapter->stats.base_vfmprc = adapter->stats.last_vfmprc; } +static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int api[] = { ixgbe_mbox_api_10, + ixgbe_mbox_api_unknown }; + int err = 0, idx = 0; + + spin_lock(&adapter->mbx_lock); + + while (api[idx] != ixgbe_mbox_api_unknown) { + err = ixgbevf_negotiate_api_version(hw, api[idx]); + if (!err) + break; + idx++; + } + + spin_unlock(&adapter->mbx_lock); +} + static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -1399,6 +1418,8 @@ void ixgbevf_up(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; + ixgbevf_negotiate_api(adapter); + ixgbevf_configure(adapter); ixgbevf_up_complete(adapter); @@ -2388,6 +2409,8 @@ static int ixgbevf_open(struct net_device *netdev) } } + ixgbevf_negotiate_api(adapter); + /* allocate transmit descriptors */ err = ixgbevf_setup_all_tx_resources(adapter); if (err) diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h index cf9131c5c115..946ce86f337f 100644 --- a/drivers/net/ethernet/intel/ixgbevf/mbx.h +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h @@ -76,12 +76,29 @@ /* bits 23:16 are used for exra info for certain messages */ #define IXGBE_VT_MSGINFO_MASK (0xFF << IXGBE_VT_MSGINFO_SHIFT) +/* definitions to support mailbox API version negotiation */ + +/* + * each element denotes a version of the API; existing numbers may not + * change; any additions must go at the end + */ +enum ixgbe_pfvf_api_rev { + ixgbe_mbox_api_10, /* API version 1.0, linux/freebsd VF driver */ + ixgbe_mbox_api_20, /* API version 2.0, solaris Phase1 VF driver */ + /* This value should always be last */ + ixgbe_mbox_api_unknown, /* indicates that API version is not known */ +}; + +/* mailbox API, legacy requests */ #define IXGBE_VF_RESET 0x01 /* VF requests reset */ #define IXGBE_VF_SET_MAC_ADDR 0x02 /* VF requests PF to set MAC addr */ #define IXGBE_VF_SET_MULTICAST 0x03 /* VF requests PF to set MC addr */ #define IXGBE_VF_SET_VLAN 0x04 /* VF requests PF to set VLAN */ -#define IXGBE_VF_SET_LPE 0x05 /* VF requests PF to set VMOLR.LPE */ -#define IXGBE_VF_SET_MACVLAN 0x06 /* VF requests PF for unicast filter */ + +/* mailbox API, version 1.0 VF requests */ +#define IXGBE_VF_SET_LPE 0x05 /* VF requests PF to set VMOLR.LPE */ +#define IXGBE_VF_SET_MACVLAN 0x06 /* VF requests PF for unicast filter */ +#define IXGBE_VF_API_NEGOTIATE 0x08 /* negotiate API version */ /* length of permanent address message returned from PF */ #define IXGBE_VF_PERMADDR_MSG_LEN 4 diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 3d555a10f592..690801bd15b0 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -79,6 +79,9 @@ static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw) /* Call adapter stop to disable tx/rx and clear interrupts */ hw->mac.ops.stop_adapter(hw); + /* reset the api version */ + hw->api_version = ixgbe_mbox_api_10; + IXGBE_WRITE_REG(hw, IXGBE_VFCTRL, IXGBE_CTRL_RST); IXGBE_WRITE_FLUSH(hw); @@ -433,6 +436,40 @@ void ixgbevf_rlpml_set_vf(struct ixgbe_hw *hw, u16 max_size) ixgbevf_write_msg_read_ack(hw, msgbuf, 2); } +/** + * ixgbevf_negotiate_api_version - Negotiate supported API version + * @hw: pointer to the HW structure + * @api: integer containing requested API version + **/ +int ixgbevf_negotiate_api_version(struct ixgbe_hw *hw, int api) +{ + int err; + u32 msg[3]; + + /* Negotiate the mailbox API version */ + msg[0] = IXGBE_VF_API_NEGOTIATE; + msg[1] = api; + msg[2] = 0; + err = hw->mbx.ops.write_posted(hw, msg, 3); + + if (!err) + err = hw->mbx.ops.read_posted(hw, msg, 3); + + if (!err) { + msg[0] &= ~IXGBE_VT_MSGTYPE_CTS; + + /* Store value and return 0 on success */ + if (msg[0] == (IXGBE_VF_API_NEGOTIATE | IXGBE_VT_MSGTYPE_ACK)) { + hw->api_version = api; + return 0; + } + + err = IXGBE_ERR_INVALID_ARGUMENT; + } + + return err; +} + static const struct ixgbe_mac_operations ixgbevf_mac_ops = { .init_hw = ixgbevf_init_hw_vf, .reset_hw = ixgbevf_reset_hw_vf, diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h index 07fd87688e35..47f11a584d8c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.h +++ b/drivers/net/ethernet/intel/ixgbevf/vf.h @@ -137,6 +137,8 @@ struct ixgbe_hw { u8 revision_id; bool adapter_stopped; + + int api_version; }; struct ixgbevf_hw_stats { @@ -171,5 +173,6 @@ struct ixgbevf_info { }; void ixgbevf_rlpml_set_vf(struct ixgbe_hw *hw, u16 max_size); +int ixgbevf_negotiate_api_version(struct ixgbe_hw *hw, int api); #endif /* __IXGBE_VF_H__ */ -- cgit v1.2.3 From 012dc19a45b2b9cc2ebd14aaa401cf782c2abba4 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 19 Sep 2012 21:35:57 +0000 Subject: ixgbevf: scheduling while atomic in reset hw path In ixgbevf_reset_hw_vf() msleep is called while holding mbx_lock resulting in a schedule while atomic bug with trace below. This patch uses mdelay instead. BUG: scheduling while atomic: ip/6539/0x00000002 2 locks held by ip/6539: #0: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0x17/0x19 #1: (&(&adapter->mbx_lock)->rlock){+.+...}, at: [] ixgbevf_reset+0x30/0xc1 [ixgbevf] Modules linked in: ixgbevf ixgbe mdio libfc scsi_transport_fc 8021q scsi_tgt garp stp llc cpufreq_ondemand acpi_cpufreq freq_table mperf ipv6 uinput igb coretemp hwmon crc32c_intel ioatdma i2c_i801 shpchp microcode lpc_ich mfd_core i2c_core joydev dca pcspkr serio_raw pata_acpi ata_generic usb_storage pata_jmicron Pid: 6539, comm: ip Not tainted 3.6.0-rc3jk-net-next+ #104 Call Trace: [] __schedule_bug+0x6a/0x79 [] __schedule+0xa2/0x684 [] ? trace_hardirqs_off+0xd/0xf [] schedule+0x64/0x66 [] schedule_timeout+0xa6/0xca [] ? lock_timer_base+0x52/0x52 [] ? __udelay+0x15/0x17 [] schedule_timeout_uninterruptible+0x1e/0x20 [] msleep+0x1b/0x22 [] ixgbevf_reset_hw_vf+0x90/0xe5 [ixgbevf] [] ixgbevf_reset+0x3b/0xc1 [ixgbevf] [] ixgbevf_open+0x43/0x43e [ixgbevf] [] ? dev_set_rx_mode+0x2e/0x33 [] __dev_open+0xa0/0xe5 [] __dev_change_flags+0xbe/0x142 [] dev_change_flags+0x21/0x56 [] do_setlink+0x2e2/0x7f4 [] ? native_sched_clock+0x37/0x39 [] rtnl_newlink+0x277/0x4bb [] ? rtnl_newlink+0xb4/0x4bb [] ? selinux_capable+0x32/0x3a [] ? ns_capable+0x4f/0x67 [] ? rtnl_lock+0x17/0x19 [] rtnetlink_rcv_msg+0x236/0x253 [] ? rtnetlink_rcv+0x2d/0x2d [] netlink_rcv_skb+0x43/0x94 [] rtnetlink_rcv+0x26/0x2d [] netlink_unicast+0xee/0x174 [] netlink_sendmsg+0x26a/0x288 [] ? rcu_read_unlock+0x56/0x67 [] __sock_sendmsg_nosec+0x58/0x61 [] __sock_sendmsg+0x3d/0x48 [] sock_sendmsg+0x6e/0x87 [] ? might_fault+0xa5/0xac [] ? copy_from_user+0x2a/0x2c [] ? verify_iovec+0x54/0xaa [] __sys_sendmsg+0x206/0x288 [] ? up_read+0x23/0x3d [] ? fcheck_files+0xac/0xea [] ? fget_light+0x3a/0xb9 [] sys_sendmsg+0x42/0x60 [] system_call_fastpath+0x16/0x1b CC: Eric Dumazet Signed-off-by: John Fastabend Tested-By: Robert Garrett Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/vf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 690801bd15b0..87b3f3bf1c1f 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -100,7 +100,7 @@ static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw) msgbuf[0] = IXGBE_VF_RESET; mbx->ops.write_posted(hw, msgbuf, 1); - msleep(10); + mdelay(10); /* set our "perm_addr" based on info provided by PF */ /* also set up the mc_filter_type which is piggy backed -- cgit v1.2.3 From 0bfd6075cf23d960198235b52f2fe941d7b397a2 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 21 Sep 2012 15:23:12 -0400 Subject: sunbmac: Remove unused local variable. Commit eb716c54b1c71ad28ab20461bff831bd481066c4 ("sunbmac: remove unnecessary setting of skb->dev") caused the local varible 'dev' in bigmac_init_rings to become unused. And now the compiler warns about it. Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sunbmac.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index 967fe8cb476e..c9c977bf02ac 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -212,7 +212,6 @@ static void bigmac_clean_rings(struct bigmac *bp) static void bigmac_init_rings(struct bigmac *bp, int from_irq) { struct bmac_init_block *bb = bp->bmac_block; - struct net_device *dev = bp->dev; int i; gfp_t gfp_flags = GFP_KERNEL; -- cgit v1.2.3 From f557147c4615f5e03abb673bd566901783565666 Mon Sep 17 00:00:00 2001 From: Stefan Assmann Date: Sat, 18 Aug 2012 04:06:11 +0000 Subject: igb: Change how we check for pre-existing and assigned VFs Adapt the pre-existing and assigned VFs code to the ixgbe way introduced in commit 9297127b9cdd8d30c829ef5fd28b7cc0323a7bcd. Instead of searching the enabled VFs we use pci_num_vf to determine enabled VFs. By comparing to which PF an assigned VF is owned it's possible to decide whether to leave it enabled or not. Signed-off-by: Stefan Assmann Acked-by: Greg Rose Tested-by: Robert Garrett Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 1 - drivers/net/ethernet/intel/igb/igb_main.c | 104 +++++++----------------------- 2 files changed, 22 insertions(+), 83 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 43c8e2914263..6f17f698fafe 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -101,7 +101,6 @@ struct vf_data_storage { u16 pf_vlan; /* When set, guest VLAN config not allowed. */ u16 pf_qos; u16 tx_rate; - struct pci_dev *vfdev; }; #define IGB_VF_FLAG_CTS 0x00000001 /* VF is clear to send data */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 246646b61a1a..073009671e7a 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -172,8 +172,7 @@ static void igb_check_vf_rate_limit(struct igb_adapter *); #ifdef CONFIG_PCI_IOV static int igb_vf_configure(struct igb_adapter *adapter, int vf); -static int igb_find_enabled_vfs(struct igb_adapter *adapter); -static int igb_check_vf_assignment(struct igb_adapter *adapter); +static bool igb_vfs_are_assigned(struct igb_adapter *adapter); #endif #ifdef CONFIG_PM @@ -2300,11 +2299,11 @@ static void __devexit igb_remove(struct pci_dev *pdev) /* reclaim resources allocated to VFs */ if (adapter->vf_data) { /* disable iov and allow time for transactions to clear */ - if (!igb_check_vf_assignment(adapter)) { + if (igb_vfs_are_assigned(adapter)) { + dev_info(&pdev->dev, "Unloading driver while VFs are assigned - VFs will not be deallocated\n"); + } else { pci_disable_sriov(pdev); msleep(500); - } else { - dev_info(&pdev->dev, "VF(s) assigned to guests!\n"); } kfree(adapter->vf_data); @@ -2344,7 +2343,7 @@ static void __devinit igb_probe_vfs(struct igb_adapter * adapter) #ifdef CONFIG_PCI_IOV struct pci_dev *pdev = adapter->pdev; struct e1000_hw *hw = &adapter->hw; - int old_vfs = igb_find_enabled_vfs(adapter); + int old_vfs = pci_num_vf(adapter->pdev); int i; /* Virtualization features not supported on i210 family. */ @@ -5037,102 +5036,43 @@ static int igb_notify_dca(struct notifier_block *nb, unsigned long event, static int igb_vf_configure(struct igb_adapter *adapter, int vf) { unsigned char mac_addr[ETH_ALEN]; - struct pci_dev *pdev = adapter->pdev; - struct e1000_hw *hw = &adapter->hw; - struct pci_dev *pvfdev; - unsigned int device_id; - u16 thisvf_devfn; eth_random_addr(mac_addr); igb_set_vf_mac(adapter, vf, mac_addr); - switch (adapter->hw.mac.type) { - case e1000_82576: - device_id = IGB_82576_VF_DEV_ID; - /* VF Stride for 82576 is 2 */ - thisvf_devfn = (pdev->devfn + 0x80 + (vf << 1)) | - (pdev->devfn & 1); - break; - case e1000_i350: - device_id = IGB_I350_VF_DEV_ID; - /* VF Stride for I350 is 4 */ - thisvf_devfn = (pdev->devfn + 0x80 + (vf << 2)) | - (pdev->devfn & 3); - break; - default: - device_id = 0; - thisvf_devfn = 0; - break; - } - - pvfdev = pci_get_device(hw->vendor_id, device_id, NULL); - while (pvfdev) { - if (pvfdev->devfn == thisvf_devfn) - break; - pvfdev = pci_get_device(hw->vendor_id, - device_id, pvfdev); - } - - if (pvfdev) - adapter->vf_data[vf].vfdev = pvfdev; - else - dev_err(&pdev->dev, - "Couldn't find pci dev ptr for VF %4.4x\n", - thisvf_devfn); - return pvfdev != NULL; + return 0; } -static int igb_find_enabled_vfs(struct igb_adapter *adapter) +static bool igb_vfs_are_assigned(struct igb_adapter *adapter) { - struct e1000_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; - struct pci_dev *pvfdev; - u16 vf_devfn = 0; - u16 vf_stride; - unsigned int device_id; - int vfs_found = 0; + struct pci_dev *vfdev; + int dev_id; switch (adapter->hw.mac.type) { case e1000_82576: - device_id = IGB_82576_VF_DEV_ID; - /* VF Stride for 82576 is 2 */ - vf_stride = 2; + dev_id = IGB_82576_VF_DEV_ID; break; case e1000_i350: - device_id = IGB_I350_VF_DEV_ID; - /* VF Stride for I350 is 4 */ - vf_stride = 4; + dev_id = IGB_I350_VF_DEV_ID; break; default: - device_id = 0; - vf_stride = 0; - break; - } - - vf_devfn = pdev->devfn + 0x80; - pvfdev = pci_get_device(hw->vendor_id, device_id, NULL); - while (pvfdev) { - if (pvfdev->devfn == vf_devfn && - (pvfdev->bus->number >= pdev->bus->number)) - vfs_found++; - vf_devfn += vf_stride; - pvfdev = pci_get_device(hw->vendor_id, - device_id, pvfdev); + return false; } - return vfs_found; -} - -static int igb_check_vf_assignment(struct igb_adapter *adapter) -{ - int i; - for (i = 0; i < adapter->vfs_allocated_count; i++) { - if (adapter->vf_data[i].vfdev) { - if (adapter->vf_data[i].vfdev->dev_flags & - PCI_DEV_FLAGS_ASSIGNED) + /* loop through all the VFs to see if we own any that are assigned */ + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, NULL); + while (vfdev) { + /* if we don't own it we don't care */ + if (vfdev->is_virtfn && vfdev->physfn == pdev) { + /* if it is assigned we cannot release it */ + if (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) return true; } + + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, vfdev); } + return false; } -- cgit v1.2.3 From 3dbdf96928dcdece134113c8ffa137f1a3b5dd88 Mon Sep 17 00:00:00 2001 From: Carolyn Wyborny Date: Wed, 12 Sep 2012 04:36:24 +0000 Subject: igb: Fix stats output on i210/i211 parts. Due to a hardware issue, on i210 and i211 parts, the TNCRS statistic provides an invalid value. This patch changes the update stats function to increment the stat only for non-i210/i211 parts. Signed-off-by: Carolyn Wyborny Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 073009671e7a..60cf3ebf4bb7 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4776,7 +4776,11 @@ void igb_update_stats(struct igb_adapter *adapter, reg = rd32(E1000_CTRL_EXT); if (!(reg & E1000_CTRL_EXT_LINK_MODE_MASK)) { adapter->stats.rxerrc += rd32(E1000_RXERRC); - adapter->stats.tncrs += rd32(E1000_TNCRS); + + /* this stat has invalid values on i210/i211 */ + if ((hw->mac.type != e1000_i210) && + (hw->mac.type != e1000_i211)) + adapter->stats.tncrs += rd32(E1000_TNCRS); } adapter->stats.tsctc += rd32(E1000_TSCTC); -- cgit v1.2.3 From f33005a637bffca72fe373d1e91f2dfbc8fae157 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 13 Sep 2012 06:27:55 +0000 Subject: igb: Remove logic that was doing NUMA pseudo-aware allocations This change removes the code that was doing the NUMA allocations for the q_vectors, rings, and ring resources. The problem is the logic used assumed that the NUMA nodes were always interleved and that is not always the case. At some point I hope to add this functionality back in a more controlled manner in the future. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 3 - drivers/net/ethernet/intel/igb/igb_main.c | 95 +++++-------------------------- 2 files changed, 13 insertions(+), 85 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 6f17f698fafe..9cad05894193 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -213,7 +213,6 @@ struct igb_q_vector { struct igb_ring_container rx, tx; struct napi_struct napi; - int numa_node; u16 itr_val; u8 set_itr; @@ -258,7 +257,6 @@ struct igb_ring { }; /* Items past this point are only used during ring alloc / free */ dma_addr_t dma; /* phys address of the ring */ - int numa_node; /* node to alloc ring memory on */ }; enum e1000_ring_flags_t { @@ -373,7 +371,6 @@ struct igb_adapter { int vf_rate_link_speed; u32 rss_queues; u32 wvbr; - int node; u32 *shadow_vfta; #ifdef CONFIG_IGB_PTP diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 60cf3ebf4bb7..c9997d83de07 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -682,52 +682,29 @@ static int igb_alloc_queues(struct igb_adapter *adapter) { struct igb_ring *ring; int i; - int orig_node = adapter->node; for (i = 0; i < adapter->num_tx_queues; i++) { - if (orig_node == -1) { - int cur_node = next_online_node(adapter->node); - if (cur_node == MAX_NUMNODES) - cur_node = first_online_node; - adapter->node = cur_node; - } - ring = kzalloc_node(sizeof(struct igb_ring), GFP_KERNEL, - adapter->node); - if (!ring) - ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); + ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); if (!ring) goto err; ring->count = adapter->tx_ring_count; ring->queue_index = i; ring->dev = &adapter->pdev->dev; ring->netdev = adapter->netdev; - ring->numa_node = adapter->node; /* For 82575, context index must be unique per ring. */ if (adapter->hw.mac.type == e1000_82575) set_bit(IGB_RING_FLAG_TX_CTX_IDX, &ring->flags); adapter->tx_ring[i] = ring; } - /* Restore the adapter's original node */ - adapter->node = orig_node; for (i = 0; i < adapter->num_rx_queues; i++) { - if (orig_node == -1) { - int cur_node = next_online_node(adapter->node); - if (cur_node == MAX_NUMNODES) - cur_node = first_online_node; - adapter->node = cur_node; - } - ring = kzalloc_node(sizeof(struct igb_ring), GFP_KERNEL, - adapter->node); - if (!ring) - ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); + ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); if (!ring) goto err; ring->count = adapter->rx_ring_count; ring->queue_index = i; ring->dev = &adapter->pdev->dev; ring->netdev = adapter->netdev; - ring->numa_node = adapter->node; /* set flag indicating ring supports SCTP checksum offload */ if (adapter->hw.mac.type >= e1000_82576) set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags); @@ -741,16 +718,12 @@ static int igb_alloc_queues(struct igb_adapter *adapter) adapter->rx_ring[i] = ring; } - /* Restore the adapter's original node */ - adapter->node = orig_node; igb_cache_ring_register(adapter); return 0; err: - /* Restore the adapter's original node */ - adapter->node = orig_node; igb_free_queues(adapter); return -ENOMEM; @@ -1116,24 +1089,10 @@ static int igb_alloc_q_vectors(struct igb_adapter *adapter) struct igb_q_vector *q_vector; struct e1000_hw *hw = &adapter->hw; int v_idx; - int orig_node = adapter->node; for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) { - if ((adapter->num_q_vectors == (adapter->num_rx_queues + - adapter->num_tx_queues)) && - (adapter->num_rx_queues == v_idx)) - adapter->node = orig_node; - if (orig_node == -1) { - int cur_node = next_online_node(adapter->node); - if (cur_node == MAX_NUMNODES) - cur_node = first_online_node; - adapter->node = cur_node; - } - q_vector = kzalloc_node(sizeof(struct igb_q_vector), GFP_KERNEL, - adapter->node); - if (!q_vector) - q_vector = kzalloc(sizeof(struct igb_q_vector), - GFP_KERNEL); + q_vector = kzalloc(sizeof(struct igb_q_vector), + GFP_KERNEL); if (!q_vector) goto err_out; q_vector->adapter = adapter; @@ -1142,14 +1101,10 @@ static int igb_alloc_q_vectors(struct igb_adapter *adapter) netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll, 64); adapter->q_vector[v_idx] = q_vector; } - /* Restore the adapter's original node */ - adapter->node = orig_node; return 0; err_out: - /* Restore the adapter's original node */ - adapter->node = orig_node; igb_free_q_vectors(adapter); return -ENOMEM; } @@ -2423,8 +2378,6 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter) VLAN_HLEN; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; - adapter->node = -1; - spin_lock_init(&adapter->stats64_lock); #ifdef CONFIG_PCI_IOV switch (hw->mac.type) { @@ -2671,13 +2624,11 @@ static int igb_close(struct net_device *netdev) int igb_setup_tx_resources(struct igb_ring *tx_ring) { struct device *dev = tx_ring->dev; - int orig_node = dev_to_node(dev); int size; size = sizeof(struct igb_tx_buffer) * tx_ring->count; - tx_ring->tx_buffer_info = vzalloc_node(size, tx_ring->numa_node); - if (!tx_ring->tx_buffer_info) - tx_ring->tx_buffer_info = vzalloc(size); + + tx_ring->tx_buffer_info = vzalloc(size); if (!tx_ring->tx_buffer_info) goto err; @@ -2685,18 +2636,10 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring) tx_ring->size = tx_ring->count * sizeof(union e1000_adv_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); - set_dev_node(dev, tx_ring->numa_node); tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); - set_dev_node(dev, orig_node); - if (!tx_ring->desc) - tx_ring->desc = dma_alloc_coherent(dev, - tx_ring->size, - &tx_ring->dma, - GFP_KERNEL); - if (!tx_ring->desc) goto err; @@ -2707,8 +2650,8 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring) err: vfree(tx_ring->tx_buffer_info); - dev_err(dev, - "Unable to allocate memory for the transmit descriptor ring\n"); + tx_ring->tx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n"); return -ENOMEM; } @@ -2825,34 +2768,23 @@ static void igb_configure_tx(struct igb_adapter *adapter) int igb_setup_rx_resources(struct igb_ring *rx_ring) { struct device *dev = rx_ring->dev; - int orig_node = dev_to_node(dev); - int size, desc_len; + int size; size = sizeof(struct igb_rx_buffer) * rx_ring->count; - rx_ring->rx_buffer_info = vzalloc_node(size, rx_ring->numa_node); - if (!rx_ring->rx_buffer_info) - rx_ring->rx_buffer_info = vzalloc(size); + + rx_ring->rx_buffer_info = vzalloc(size); if (!rx_ring->rx_buffer_info) goto err; - desc_len = sizeof(union e1000_adv_rx_desc); /* Round up to nearest 4K */ - rx_ring->size = rx_ring->count * desc_len; + rx_ring->size = rx_ring->count * sizeof(union e1000_adv_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); - set_dev_node(dev, rx_ring->numa_node); rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); - set_dev_node(dev, orig_node); - if (!rx_ring->desc) - rx_ring->desc = dma_alloc_coherent(dev, - rx_ring->size, - &rx_ring->dma, - GFP_KERNEL); - if (!rx_ring->desc) goto err; @@ -2864,8 +2796,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) err: vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; - dev_err(dev, "Unable to allocate memory for the receive descriptor" - " ring\n"); + dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n"); return -ENOMEM; } -- cgit v1.2.3 From f4128785b8f3f1fd7dc81b972661003d639a4676 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 13 Sep 2012 06:28:01 +0000 Subject: igb: Change Tx cleanup loop to do/while instead of for This change makes it so that Tx cleanup is done in a do/while loop instead of a for loop. The main motivation behind this is the fact that we should never be invoked with a budget less than 1 so we can skip checking the budget before processing the first descriptor. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index c9997d83de07..91f542c50f61 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -5690,7 +5690,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) struct igb_adapter *adapter = q_vector->adapter; struct igb_ring *tx_ring = q_vector->tx.ring; struct igb_tx_buffer *tx_buffer; - union e1000_adv_tx_desc *tx_desc, *eop_desc; + union e1000_adv_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; unsigned int budget = q_vector->tx.work_limit; unsigned int i = tx_ring->next_to_clean; @@ -5702,16 +5702,16 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) tx_desc = IGB_TX_DESC(tx_ring, i); i -= tx_ring->count; - for (; budget; budget--) { - eop_desc = tx_buffer->next_to_watch; - - /* prevent any other reads prior to eop_desc */ - rmb(); + do { + union e1000_adv_tx_desc *eop_desc = tx_buffer->next_to_watch; /* if next_to_watch is not set then there is no work pending */ if (!eop_desc) break; + /* prevent any other reads prior to eop_desc */ + rmb(); + /* if DD is not set pending work has not been completed */ if (!(eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD))) break; @@ -5767,7 +5767,13 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) tx_buffer = tx_ring->tx_buffer_info; tx_desc = IGB_TX_DESC(tx_ring, 0); } - } + + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); netdev_tx_completed_queue(txring_txq(tx_ring), total_packets, total_bytes); @@ -5783,12 +5789,10 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) { struct e1000_hw *hw = &adapter->hw; - eop_desc = tx_buffer->next_to_watch; - /* Detect a transmit hang in hardware, this serializes the * check with the clearing of time_stamp and movement of i */ clear_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags); - if (eop_desc && + if (tx_buffer->next_to_watch && time_after(jiffies, tx_buffer->time_stamp + (adapter->tx_timeout_factor * HZ)) && !(rd32(E1000_STATUS) & E1000_STATUS_TXOFF)) { @@ -5812,9 +5816,9 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) tx_ring->next_to_use, tx_ring->next_to_clean, tx_buffer->time_stamp, - eop_desc, + tx_buffer->next_to_watch, jiffies, - eop_desc->wb.status); + tx_buffer->next_to_watch->wb.status); netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); -- cgit v1.2.3 From 797fd4be7b6968ea752ae47367ae95454124a698 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 13 Sep 2012 06:28:11 +0000 Subject: igb: Change how we populate the RSS indirection table This patch cleans up our RSS indirection table configuration so that we generate the same table regardless of CPU endianness. In addition it changes the table setup so that instead of doing a modulo based setup it is instead a divisor based setup. The advantage to this is that we should be able to take the Rx hash and compute the Rx queue with very little CPU overhead if needed. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 55 +++++++++++++++---------------- 1 file changed, 26 insertions(+), 29 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 91f542c50f61..27688d9d2b64 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2834,11 +2834,7 @@ static void igb_setup_mrqc(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 mrqc, rxcsum; - u32 j, num_rx_queues, shift = 0, shift2 = 0; - union e1000_reta { - u32 dword; - u8 bytes[4]; - } reta; + u32 j, num_rx_queues, shift = 0; static const u8 rsshash[40] = { 0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2, 0x41, 0x67, 0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0, 0xd0, 0xca, 0x2b, 0xcb, @@ -2856,35 +2852,36 @@ static void igb_setup_mrqc(struct igb_adapter *adapter) num_rx_queues = adapter->rss_queues; - if (adapter->vfs_allocated_count) { - /* 82575 and 82576 supports 2 RSS queues for VMDq */ - switch (hw->mac.type) { - case e1000_i350: - case e1000_82580: - num_rx_queues = 1; - shift = 0; - break; - case e1000_82576: + switch (hw->mac.type) { + case e1000_82575: + shift = 6; + break; + case e1000_82576: + /* 82576 supports 2 RSS queues for SR-IOV */ + if (adapter->vfs_allocated_count) { shift = 3; num_rx_queues = 2; - break; - case e1000_82575: - shift = 2; - shift2 = 6; - default: - break; } - } else { - if (hw->mac.type == e1000_82575) - shift = 6; + break; + default: + break; } - for (j = 0; j < (32 * 4); j++) { - reta.bytes[j & 3] = (j % num_rx_queues) << shift; - if (shift2) - reta.bytes[j & 3] |= num_rx_queues << shift2; - if ((j & 3) == 3) - wr32(E1000_RETA(j >> 2), reta.dword); + /* + * Populate the indirection table 4 entries at a time. To do this + * we are generating the results for n and n+2 and then interleaving + * those with the results with n+1 and n+3. + */ + for (j = 0; j < 32; j++) { + /* first pass generates n and n+2 */ + u32 base = ((j * 0x00040004) + 0x00020000) * num_rx_queues; + u32 reta = (base & 0x07800780) >> (7 - shift); + + /* second pass generates n+1 and n+3 */ + base += 0x00010001 * num_rx_queues; + reta |= (base & 0x07800780) << (1 + shift); + + wr32(E1000_RETA(j), reta); } /* -- cgit v1.2.3 From a57fe23e240b95282e60d643cd8ada3d2a66d8c6 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 13 Sep 2012 06:28:16 +0000 Subject: igb: Simplify how we populate the RSS key Instead of storing the RSS key as a character array we can simplify the configuration by making it a u32 array. This allows us to just write one value per register without any unnecessary operations to construct the value. This change will produce the same exact key, the only difference is that I translated the u8 array to a u32 array which will be correctly ordered on writes to hardware by the cpu_to_le32 operations that are built into the writel calls. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 27688d9d2b64..db6e456688a1 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2835,20 +2835,14 @@ static void igb_setup_mrqc(struct igb_adapter *adapter) struct e1000_hw *hw = &adapter->hw; u32 mrqc, rxcsum; u32 j, num_rx_queues, shift = 0; - static const u8 rsshash[40] = { - 0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2, 0x41, 0x67, - 0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0, 0xd0, 0xca, 0x2b, 0xcb, - 0xae, 0x7b, 0x30, 0xb4, 0x77, 0xcb, 0x2d, 0xa3, 0x80, 0x30, - 0xf2, 0x0c, 0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa }; + static const u32 rsskey[10] = { 0xDA565A6D, 0xC20E5B25, 0x3D256741, + 0xB08FA343, 0xCB2BCAD0, 0xB4307BAE, + 0xA32DCB77, 0x0CF23080, 0x3BB7426A, + 0xFA01ACBE }; /* Fill out hash function seeds */ - for (j = 0; j < 10; j++) { - u32 rsskey = rsshash[(j * 4)]; - rsskey |= rsshash[(j * 4) + 1] << 8; - rsskey |= rsshash[(j * 4) + 2] << 16; - rsskey |= rsshash[(j * 4) + 3] << 24; - array_wr32(E1000_RSSRK(0), j, rsskey); - } + for (j = 0; j < 10; j++) + wr32(E1000_RSSRK(j), rsskey[j]); num_rx_queues = adapter->rss_queues; -- cgit v1.2.3 From c9f14bf3a49f86e6402a6e3476a180f2bdc8a71b Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 18 Sep 2012 01:56:27 +0000 Subject: igb: Use dma_unmap_addr and dma_unmap_len defines This change is meant to improve performance on systems that do not require the DMA unmap calls. On those systems we do not need to make use of the unmap address for Tx or the unmap length so we can drop both thereby reducing the size of the Tx buffer info structure. In addition I have changed the logic to check for unmap length instead of unmap address when checking to see if a buffer needs to be unmapped from DMA use. The reasons for this change is that on some platforms it is possible to receive a valid DMA address of 0 from an IOMMU. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 4 +- drivers/net/ethernet/intel/igb/igb_main.c | 64 +++++++++++++++---------------- 2 files changed, 34 insertions(+), 34 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 9cad05894193..8aad230c0592 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -168,8 +168,8 @@ struct igb_tx_buffer { unsigned int bytecount; u16 gso_segs; __be16 protocol; - dma_addr_t dma; - u32 length; + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); u32 tx_flags; }; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index db6e456688a1..60bf46534835 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -403,8 +403,8 @@ static void igb_dump(struct igb_adapter *adapter) buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean]; pr_info(" %5d %5X %5X %016llX %04X %p %016llX\n", n, tx_ring->next_to_use, tx_ring->next_to_clean, - (u64)buffer_info->dma, - buffer_info->length, + (u64)dma_unmap_addr(buffer_info, dma), + dma_unmap_len(buffer_info, len), buffer_info->next_to_watch, (u64)buffer_info->time_stamp); } @@ -455,8 +455,8 @@ static void igb_dump(struct igb_adapter *adapter) " %04X %p %016llX %p%s\n", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - (u64)buffer_info->dma, - buffer_info->length, + (u64)dma_unmap_addr(buffer_info, dma), + dma_unmap_len(buffer_info, len), buffer_info->next_to_watch, (u64)buffer_info->time_stamp, buffer_info->skb, next_desc); @@ -465,7 +465,8 @@ static void igb_dump(struct igb_adapter *adapter) print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 1, buffer_info->skb->data, - buffer_info->length, true); + dma_unmap_len(buffer_info, len), + true); } } @@ -3198,20 +3199,20 @@ void igb_unmap_and_free_tx_resource(struct igb_ring *ring, { if (tx_buffer->skb) { dev_kfree_skb_any(tx_buffer->skb); - if (tx_buffer->dma) + if (dma_unmap_len(tx_buffer, len)) dma_unmap_single(ring->dev, - tx_buffer->dma, - tx_buffer->length, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); - } else if (tx_buffer->dma) { + } else if (dma_unmap_len(tx_buffer, len)) { dma_unmap_page(ring->dev, - tx_buffer->dma, - tx_buffer->length, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); } tx_buffer->next_to_watch = NULL; tx_buffer->skb = NULL; - tx_buffer->dma = 0; + dma_unmap_len_set(tx_buffer, len, 0); /* buffer_info must be completely set up in the transmit path */ } @@ -4206,7 +4207,7 @@ static void igb_tx_map(struct igb_ring *tx_ring, const u8 hdr_len) { struct sk_buff *skb = first->skb; - struct igb_tx_buffer *tx_buffer_info; + struct igb_tx_buffer *tx_buffer; union e1000_adv_tx_desc *tx_desc; dma_addr_t dma; struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; @@ -4227,8 +4228,8 @@ static void igb_tx_map(struct igb_ring *tx_ring, goto dma_error; /* record length, and DMA address */ - first->length = size; - first->dma = dma; + dma_unmap_len_set(first, len, size); + dma_unmap_addr_set(first, dma, dma); tx_desc->read.buffer_addr = cpu_to_le64(dma); for (;;) { @@ -4270,9 +4271,9 @@ static void igb_tx_map(struct igb_ring *tx_ring, if (dma_mapping_error(tx_ring->dev, dma)) goto dma_error; - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - tx_buffer_info->length = size; - tx_buffer_info->dma = dma; + tx_buffer = &tx_ring->tx_buffer_info[i]; + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); tx_desc->read.olinfo_status = 0; tx_desc->read.buffer_addr = cpu_to_le64(dma); @@ -4323,9 +4324,9 @@ dma_error: /* clear dma mappings for failed tx_buffer_info map */ for (;;) { - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); - if (tx_buffer_info == first) + tx_buffer = &tx_ring->tx_buffer_info[i]; + igb_unmap_and_free_tx_resource(tx_ring, tx_buffer); + if (tx_buffer == first) break; if (i == 0) i = tx_ring->count; @@ -5716,18 +5717,19 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) /* free the skb */ dev_kfree_skb_any(tx_buffer->skb); - tx_buffer->skb = NULL; /* unmap skb header data */ dma_unmap_single(tx_ring->dev, - tx_buffer->dma, - tx_buffer->length, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); + /* clear tx_buffer data */ + tx_buffer->skb = NULL; + dma_unmap_len_set(tx_buffer, len, 0); + /* clear last DMA location and unmap remaining buffers */ while (tx_desc != eop_desc) { - tx_buffer->dma = 0; - tx_buffer++; tx_desc++; i++; @@ -5738,17 +5740,15 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) } /* unmap any remaining paged data */ - if (tx_buffer->dma) { + if (dma_unmap_len(tx_buffer, len)) { dma_unmap_page(tx_ring->dev, - tx_buffer->dma, - tx_buffer->length, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); } } - /* clear last DMA location */ - tx_buffer->dma = 0; - /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; tx_desc++; -- cgit v1.2.3 From 1ef761582c074448bae5be97abde5934667e7710 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Sat, 22 Sep 2012 07:02:03 +0000 Subject: ptp: link the phc device to its parent device PTP Hardware Clock devices appear as class devices in sysfs. This patch changes the registration API to use the parent device, clarifying the clock's relationship to the underlying device. Signed-off-by: Richard Cochran Acked-by: Ben Hutchings Acked-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar_ptp.c | 2 +- drivers/net/ethernet/intel/igb/igb_ptp.c | 3 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 3 ++- drivers/net/ethernet/sfc/ptp.c | 3 ++- drivers/net/phy/dp83640.c | 2 +- drivers/ptp/ptp_clock.c | 5 +++-- drivers/ptp/ptp_ixp46x.c | 2 +- drivers/ptp/ptp_pch.c | 2 +- include/linux/ptp_clock_kernel.h | 7 +++++-- 9 files changed, 18 insertions(+), 11 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c index c08e5d40fecb..18762a3ccce4 100644 --- a/drivers/net/ethernet/freescale/gianfar_ptp.c +++ b/drivers/net/ethernet/freescale/gianfar_ptp.c @@ -510,7 +510,7 @@ static int gianfar_ptp_probe(struct platform_device *dev) spin_unlock_irqrestore(&etsects->lock, flags); - etsects->clock = ptp_clock_register(&etsects->caps); + etsects->clock = ptp_clock_register(&etsects->caps, &dev->dev); if (IS_ERR(etsects->clock)) { err = PTR_ERR(etsects->clock); goto no_clock; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index e13ba1d5369f..ee21445157a3 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -752,7 +752,8 @@ void igb_ptp_init(struct igb_adapter *adapter) wr32(E1000_IMS, E1000_IMS_TS); } - adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps); + adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, + &adapter->pdev->dev); if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n"); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 3456d5617143..39881cb17a4b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -960,7 +960,8 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter) /* (Re)start the overflow check */ adapter->flags2 |= IXGBE_FLAG2_OVERFLOW_CHECK_ENABLED; - adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps); + adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, + &adapter->pdev->dev); if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; e_dev_err("ptp_clock_register failed\n"); diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 2b07a4eae07e..5b3dd028ce85 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -931,7 +931,8 @@ static int efx_ptp_probe_channel(struct efx_channel *channel) ptp->phc_clock_info.settime = efx_phc_settime; ptp->phc_clock_info.enable = efx_phc_enable; - ptp->phc_clock = ptp_clock_register(&ptp->phc_clock_info); + ptp->phc_clock = ptp_clock_register(&ptp->phc_clock_info, + &efx->pci_dev->dev); if (!ptp->phc_clock) goto fail3; diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index b0da0226661f..24e05c43bff8 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -980,7 +980,7 @@ static int dp83640_probe(struct phy_device *phydev) if (choose_this_phy(clock, phydev)) { clock->chosen = dp83640; - clock->ptp_clock = ptp_clock_register(&clock->caps); + clock->ptp_clock = ptp_clock_register(&clock->caps, &phydev->dev); if (IS_ERR(clock->ptp_clock)) { err = PTR_ERR(clock->ptp_clock); goto no_register; diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index c470ddf1a6fa..79f4bce061bd 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -182,7 +182,8 @@ static void delete_ptp_clock(struct posix_clock *pc) /* public interface */ -struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info) +struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, + struct device *parent) { struct ptp_clock *ptp; int err = 0, index, major = MAJOR(ptp_devt); @@ -215,7 +216,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info) init_waitqueue_head(&ptp->tsev_wq); /* Create a new device in our class. */ - ptp->dev = device_create(ptp_class, NULL, ptp->devid, ptp, + ptp->dev = device_create(ptp_class, parent, ptp->devid, ptp, "ptp%d", ptp->index); if (IS_ERR(ptp->dev)) goto no_device; diff --git a/drivers/ptp/ptp_ixp46x.c b/drivers/ptp/ptp_ixp46x.c index e03c40692b00..d49b85164fd2 100644 --- a/drivers/ptp/ptp_ixp46x.c +++ b/drivers/ptp/ptp_ixp46x.c @@ -298,7 +298,7 @@ static int __init ptp_ixp_init(void) ixp_clock.caps = ptp_ixp_caps; - ixp_clock.ptp_clock = ptp_clock_register(&ixp_clock.caps); + ixp_clock.ptp_clock = ptp_clock_register(&ixp_clock.caps, NULL); if (IS_ERR(ixp_clock.ptp_clock)) return PTR_ERR(ixp_clock.ptp_clock); diff --git a/drivers/ptp/ptp_pch.c b/drivers/ptp/ptp_pch.c index 3a9c17eced10..e624e4dd2abb 100644 --- a/drivers/ptp/ptp_pch.c +++ b/drivers/ptp/ptp_pch.c @@ -627,7 +627,7 @@ pch_probe(struct pci_dev *pdev, const struct pci_device_id *id) } chip->caps = ptp_pch_caps; - chip->ptp_clock = ptp_clock_register(&chip->caps); + chip->ptp_clock = ptp_clock_register(&chip->caps, &pdev->dev); if (IS_ERR(chip->ptp_clock)) return PTR_ERR(chip->ptp_clock); diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index a644b29f1161..56c71b27112e 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -21,6 +21,7 @@ #ifndef _PTP_CLOCK_KERNEL_H_ #define _PTP_CLOCK_KERNEL_H_ +#include #include #include @@ -93,10 +94,12 @@ struct ptp_clock; /** * ptp_clock_register() - register a PTP hardware clock driver * - * @info: Structure describing the new clock. + * @info: Structure describing the new clock. + * @parent: Pointer to the parent device of the new clock. */ -extern struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info); +extern struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, + struct device *parent); /** * ptp_clock_unregister() - unregister a PTP hardware clock driver -- cgit v1.2.3 From 5894bab7f452d61941a6d3215dec43221ac0be4b Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 22 Sep 2012 18:11:32 -0400 Subject: net: Make ZNET driver config depend on X86. We're now using isa_virt_to_bus(), and there really isn't a generic and consistent test for whether a platform provides this interface or not. This driver is also for an x86-only device. Signed-off-by: David S. Miller --- drivers/net/ethernet/i825xx/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/i825xx/Kconfig b/drivers/net/ethernet/i825xx/Kconfig index fed5080a6b62..959faf7388e2 100644 --- a/drivers/net/ethernet/i825xx/Kconfig +++ b/drivers/net/ethernet/i825xx/Kconfig @@ -150,7 +150,7 @@ config SUN3_82586 config ZNET tristate "Zenith Z-Note support (EXPERIMENTAL)" - depends on EXPERIMENTAL && ISA_DMA_API + depends on EXPERIMENTAL && ISA_DMA_API && X86 ---help--- The Zenith Z-Note notebook computer has a built-in network (Ethernet) card, and this is the Linux driver for it. Note that the -- cgit v1.2.3 From 4b2cd27f834e526f933aa63ce91964b7581271f4 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 2 Aug 2012 01:16:59 +0000 Subject: ixgbevf: Fix code for handling timeout The VF driver was not designed to correctly handle a message timeout. As a result it is possible for one bad message to invalidate all messages following it until the part is reset. Instead we should copy the example in igbvf of how to handle a mailbox event and message timeout. Signed-off-by: Alexander Duyck Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 46 +++++---------------- drivers/net/ethernet/intel/ixgbevf/mbx.c | 15 +++++-- drivers/net/ethernet/intel/ixgbevf/vf.c | 49 ++++++++++++++++++----- 3 files changed, 58 insertions(+), 52 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index c5ffe1dd3fcd..7aa31eebc356 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -716,40 +716,15 @@ static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector) } } -static irqreturn_t ixgbevf_msix_mbx(int irq, void *data) +static irqreturn_t ixgbevf_msix_other(int irq, void *data) { struct ixgbevf_adapter *adapter = data; struct ixgbe_hw *hw = &adapter->hw; - u32 msg; - bool got_ack = false; - if (!hw->mbx.ops.check_for_ack(hw)) - got_ack = true; + hw->mac.get_link_status = 1; - if (!hw->mbx.ops.check_for_msg(hw)) { - hw->mbx.ops.read(hw, &msg, 1); - - if ((msg & IXGBE_MBVFICR_VFREQ_MASK) == IXGBE_PF_CONTROL_MSG) - mod_timer(&adapter->watchdog_timer, - round_jiffies(jiffies + 1)); - - if (msg & IXGBE_VT_MSGTYPE_NACK) - pr_warn("Last Request of type %2.2x to PF Nacked\n", - msg & 0xFF); - /* - * Restore the PFSTS bit in case someone is polling for a - * return message from the PF - */ - hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFSTS; - } - - /* - * checking for the ack clears the PFACK bit. Place - * it back in the v2p_mailbox cache so that anyone - * polling for an ack will not miss it - */ - if (got_ack) - hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFACK; + if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies); IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_other); @@ -899,10 +874,10 @@ static int ixgbevf_request_msix_irqs(struct ixgbevf_adapter *adapter) } err = request_irq(adapter->msix_entries[vector].vector, - &ixgbevf_msix_mbx, 0, netdev->name, adapter); + &ixgbevf_msix_other, 0, netdev->name, adapter); if (err) { hw_dbg(&adapter->hw, - "request_irq for msix_mbx failed: %d\n", err); + "request_irq for msix_other failed: %d\n", err); goto free_queue_irqs; } @@ -1411,6 +1386,7 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) ixgbevf_save_reset_stats(adapter); ixgbevf_init_last_counter_stats(adapter); + hw->mac.get_link_status = 1; mod_timer(&adapter->watchdog_timer, jiffies); } @@ -1589,8 +1565,6 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter) void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter) { - struct ixgbe_hw *hw = &adapter->hw; - WARN_ON(in_interrupt()); while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state)) @@ -1603,10 +1577,8 @@ void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter) * watchdog task will continue to schedule reset tasks until * the PF is up and running. */ - if (!hw->mac.ops.reset_hw(hw)) { - ixgbevf_down(adapter); - ixgbevf_up(adapter); - } + ixgbevf_down(adapter); + ixgbevf_up(adapter); clear_bit(__IXGBEVF_RESETTING, &adapter->state); } diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c index 9c955900fe64..d5028ddf4b31 100644 --- a/drivers/net/ethernet/intel/ixgbevf/mbx.c +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c @@ -86,14 +86,17 @@ static s32 ixgbevf_poll_for_ack(struct ixgbe_hw *hw) static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size) { struct ixgbe_mbx_info *mbx = &hw->mbx; - s32 ret_val = IXGBE_ERR_MBX; + s32 ret_val = -IXGBE_ERR_MBX; + + if (!mbx->ops.read) + goto out; ret_val = ixgbevf_poll_for_msg(hw); /* if ack received read message, otherwise we timed out */ if (!ret_val) ret_val = mbx->ops.read(hw, msg, size); - +out: return ret_val; } @@ -109,7 +112,11 @@ static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size) static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size) { struct ixgbe_mbx_info *mbx = &hw->mbx; - s32 ret_val; + s32 ret_val = -IXGBE_ERR_MBX; + + /* exit if either we can't write or there isn't a defined timeout */ + if (!mbx->ops.write || !mbx->timeout) + goto out; /* send msg */ ret_val = mbx->ops.write(hw, msg, size); @@ -117,7 +124,7 @@ static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size) /* if msg sent wait until we receive an ack */ if (!ret_val) ret_val = ixgbevf_poll_for_ack(hw); - +out: return ret_val; } diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 87b3f3bf1c1f..a5e66c79f632 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -392,20 +392,23 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw, bool *link_up, bool autoneg_wait_to_complete) { + struct ixgbe_mbx_info *mbx = &hw->mbx; + struct ixgbe_mac_info *mac = &hw->mac; + s32 ret_val = 0; u32 links_reg; + u32 in_msg = 0; - if (!(hw->mbx.ops.check_for_rst(hw))) { - *link_up = false; - *speed = 0; - return -1; - } + /* If we were hit with a reset drop the link */ + if (!mbx->ops.check_for_rst(hw) || !mbx->timeout) + mac->get_link_status = true; - links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS); + if (!mac->get_link_status) + goto out; - if (links_reg & IXGBE_LINKS_UP) - *link_up = true; - else - *link_up = false; + /* if link status is down no point in checking to see if pf is up */ + links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS); + if (!(links_reg & IXGBE_LINKS_UP)) + goto out; switch (links_reg & IXGBE_LINKS_SPEED_82599) { case IXGBE_LINKS_SPEED_10G_82599: @@ -419,7 +422,31 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw, break; } - return 0; + /* if the read failed it could just be a mailbox collision, best wait + * until we are called again and don't report an error */ + if (mbx->ops.read(hw, &in_msg, 1)) + goto out; + + if (!(in_msg & IXGBE_VT_MSGTYPE_CTS)) { + /* msg is not CTS and is NACK we must have lost CTS status */ + if (in_msg & IXGBE_VT_MSGTYPE_NACK) + ret_val = -1; + goto out; + } + + /* the pf is talking, if we timed out in the past we reinit */ + if (!mbx->timeout) { + ret_val = -1; + goto out; + } + + /* if we passed all the tests above then the link is up and we no + * longer need to check for link */ + mac->get_link_status = false; + +out: + *link_up = !mac->get_link_status; + return ret_val; } /** -- cgit v1.2.3 From 0584d999328f3033c038118fb891c9efd5f361df Mon Sep 17 00:00:00 2001 From: Greg Rose Date: Wed, 8 Aug 2012 00:00:58 +0000 Subject: ixgbe: Do not read the spoofed packets counter when not in IOV mode The counter is not valid unless the controller is running in IOV mode. Signed-off-by: Greg Rose Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 70d27a361857..29465be2a14a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5560,8 +5560,9 @@ static void ixgbe_spoof_check(struct ixgbe_adapter *adapter) { u32 ssvpc; - /* Do not perform spoof check for 82598 */ - if (adapter->hw.mac.type == ixgbe_mac_82598EB) + /* Do not perform spoof check for 82598 or if not in IOV mode */ + if (adapter->hw.mac.type == ixgbe_mac_82598EB || + adapter->num_vfs == 0) return; ssvpc = IXGBE_READ_REG(&adapter->hw, IXGBE_SSVPC); -- cgit v1.2.3 From b3d58a8fa6c8d4bcd6b2b64656be166aff9183b0 Mon Sep 17 00:00:00 2001 From: Narendra K Date: Tue, 14 Aug 2012 00:00:14 +0000 Subject: ixgbevf - Remove unused parameter in ixgbevf_receive_skb Remove 'rx_ring' parameter as it is not used in ixgbevf_receive_skb Signed-off-by: Narendra K Acked-by: Greg Rose Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 7aa31eebc356..cb215c65f463 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -272,12 +272,10 @@ cont_loop: * @q_vector: structure containing interrupt and ring information * @skb: packet to send up * @status: hardware indication of status of receive - * @rx_ring: rx descriptor ring (for a specific queue) to setup * @rx_desc: rx descriptor **/ static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector, struct sk_buff *skb, u8 status, - struct ixgbevf_ring *ring, union ixgbe_adv_rx_desc *rx_desc) { struct ixgbevf_adapter *adapter = q_vector->adapter; @@ -461,7 +459,7 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, } skb->protocol = eth_type_trans(skb, rx_ring->netdev); - ixgbevf_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc); + ixgbevf_receive_skb(q_vector, skb, staterr, rx_desc); next_desc: rx_desc->wb.upper.status_error = 0; -- cgit v1.2.3 From ac6ed8f00aca7dd1abf0c90bcb3c8e46e7f44243 Mon Sep 17 00:00:00 2001 From: Greg Rose Date: Fri, 31 Aug 2012 05:59:28 +0000 Subject: ixgbevf: Fix AIM (Adaptive Interrupt Moderation) While fixing up a patch from Alex Duyck to use q_vectors in ring containers to update the ITR I bungled it and missed actually updating the counters in the ring container q_vectors. This patch fixes my mistake and makes interrupt moderation actually work. Signed-off-by: Greg Rose Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index cb215c65f463..37bbd86529e3 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -263,6 +263,8 @@ cont_loop: tx_ring->total_bytes += total_bytes; tx_ring->total_packets += total_packets; u64_stats_update_end(&tx_ring->syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; return count < tx_ring->count; } @@ -488,6 +490,8 @@ next_desc: rx_ring->total_packets += total_rx_packets; rx_ring->total_bytes += total_rx_bytes; u64_stats_update_end(&rx_ring->syncp); + q_vector->rx.total_packets += total_rx_packets; + q_vector->rx.total_bytes += total_rx_bytes; return !!budget; } -- cgit v1.2.3 From 5c60f81a2553213856b3bb80f18003e56a6a110d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Sat, 1 Sep 2012 05:12:38 +0000 Subject: ixgbevf: Add fix to VF to handle multi-descriptor buffers This change fixes the ixgbevf driver so that it can correctly drop a frame should it receive a jumbo frame. Signed-off-by: Alexander Duyck Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/ixgbevf.h | 5 +++++ drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 14 ++++++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index eb26fda63c99..383b4e1cd175 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -261,6 +261,11 @@ enum ixbgevf_state_t { __IXGBEVF_DOWN }; +struct ixgbevf_cb { + struct sk_buff *prev; +}; +#define IXGBE_CB(skb) ((struct ixgbevf_cb *)(skb)->cb) + enum ixgbevf_boards { board_82599_vf, board_X540_vf, diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 37bbd86529e3..2ba15ae2335c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -433,11 +433,21 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, if (!(staterr & IXGBE_RXD_STAT_EOP)) { skb->next = next_buffer->skb; - skb->next->prev = skb; + IXGBE_CB(skb->next)->prev = skb; adapter->non_eop_descs++; goto next_desc; } + /* we should not be chaining buffers, if we did drop the skb */ + if (IXGBE_CB(skb)->prev) { + do { + struct sk_buff *this = skb; + skb = IXGBE_CB(skb)->prev; + dev_kfree_skb(this); + } while (skb); + goto next_desc; + } + /* ERR_MASK will only have valid bits if EOP set */ if (unlikely(staterr & IXGBE_RXDADV_ERR_FRAME_ERR_MASK)) { dev_kfree_skb_irq(skb); @@ -1439,7 +1449,7 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter, rx_buffer_info->skb = NULL; do { struct sk_buff *this = skb; - skb = skb->prev; + skb = IXGBE_CB(skb)->prev; dev_kfree_skb(this); } while (skb); } -- cgit v1.2.3 From 2ddc7fe1cd1b2e0502f12b89c60b6e1ca66837dd Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 21 Aug 2012 00:15:13 +0000 Subject: ixgbevf: Return error on failure to enable VLAN With recent kernel changes we can now return errors on a failure to setup a VLAN filter. This patch takes advantage of that opportunity so that we can return either an EIO error in the case of a mailbox failure, or an EACCESS error in the case of being denied access to the VLAN filter table by the PF. Signed-off-by: Alexander Duyck Tested-by: Robert Garrett Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 21 ++++++++++++++++----- drivers/net/ethernet/intel/ixgbevf/vf.c | 20 ++++++++++++++++++-- 2 files changed, 34 insertions(+), 7 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 2ba15ae2335c..cf372ee49d0c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1126,36 +1126,47 @@ static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + int err; + + if (!hw->mac.ops.set_vfta) + return -EOPNOTSUPP; spin_lock(&adapter->mbx_lock); /* add VID to filter table */ - if (hw->mac.ops.set_vfta) - hw->mac.ops.set_vfta(hw, vid, 0, true); + err = hw->mac.ops.set_vfta(hw, vid, 0, true); spin_unlock(&adapter->mbx_lock); + /* translate error return types so error makes sense */ + if (err == IXGBE_ERR_MBX) + return -EIO; + + if (err == IXGBE_ERR_INVALID_ARGUMENT) + return -EACCES; + set_bit(vid, adapter->active_vlans); - return 0; + return err; } static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + int err = -EOPNOTSUPP; spin_lock(&adapter->mbx_lock); /* remove VID from filter table */ if (hw->mac.ops.set_vfta) - hw->mac.ops.set_vfta(hw, vid, 0, false); + err = hw->mac.ops.set_vfta(hw, vid, 0, false); spin_unlock(&adapter->mbx_lock); clear_bit(vid, adapter->active_vlans); - return 0; + return err; } static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter) diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index a5e66c79f632..0c7447e6fcc8 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -349,16 +349,32 @@ static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, static s32 ixgbevf_set_vfta_vf(struct ixgbe_hw *hw, u32 vlan, u32 vind, bool vlan_on) { + struct ixgbe_mbx_info *mbx = &hw->mbx; u32 msgbuf[2]; + s32 err; msgbuf[0] = IXGBE_VF_SET_VLAN; msgbuf[1] = vlan; /* Setting the 8 bit field MSG INFO to TRUE indicates "add" */ msgbuf[0] |= vlan_on << IXGBE_VT_MSGINFO_SHIFT; - ixgbevf_write_msg_read_ack(hw, msgbuf, 2); + err = mbx->ops.write_posted(hw, msgbuf, 2); + if (err) + goto mbx_err; - return 0; + err = mbx->ops.read_posted(hw, msgbuf, 2); + if (err) + goto mbx_err; + + /* remove extra bits from the message */ + msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; + msgbuf[0] &= ~(0xFF << IXGBE_VT_MSGINFO_SHIFT); + + if (msgbuf[0] != (IXGBE_VF_SET_VLAN | IXGBE_VT_MSGTYPE_ACK)) + err = IXGBE_ERR_INVALID_ARGUMENT; + +mbx_err: + return err; } /** -- cgit v1.2.3 From 5889335c506bc50b03266251ac3c8711b674ba7a Mon Sep 17 00:00:00 2001 From: Merav Sicron Date: Sun, 23 Sep 2012 03:12:23 +0000 Subject: bnx2x: Improve code around bnx2x_tests_str_arr This patch changes the definition of bnx2x_tests_str_arr from static char pointer to static const char bi-directional array. Also the bnx2x_get_strings function is simplified. Reported-by: Joe Perches Reported-by: David Laight Signed-off-by: Merav Sicron Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index f923125e1c20..a19c9e088278 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1607,7 +1607,7 @@ static int bnx2x_set_pauseparam(struct net_device *dev, return 0; } -static char *bnx2x_tests_str_arr[BNX2X_NUM_TESTS_SF] = { +static const char bnx2x_tests_str_arr[BNX2X_NUM_TESTS_SF][ETH_GSTRING_LEN] = { "register_test (offline) ", "memory_test (offline) ", "int_loopback_test (offline)", @@ -2536,7 +2536,7 @@ static int bnx2x_get_sset_count(struct net_device *dev, int stringset) static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { struct bnx2x *bp = netdev_priv(dev); - int i, j, k, offset, start; + int i, j, k, start; char queue_name[MAX_QUEUE_NAME_LEN+1]; switch (stringset) { @@ -2572,13 +2572,8 @@ static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf) start = 0; else start = 4; - for (i = 0, j = start; j < (start + BNX2X_NUM_TESTS(bp)); - i++, j++) { - offset = sprintf(buf+32*i, "%s", - bnx2x_tests_str_arr[j]); - *(buf+offset) = '\0'; - } - break; + memcpy(buf, bnx2x_tests_str_arr + start, + ETH_GSTRING_LEN * BNX2X_NUM_TESTS(bp)); } } -- cgit v1.2.3 From b98b8babd6e3370fadb7c6eaacb00eb2f6344a6c Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Sun, 23 Sep 2012 22:39:08 +0000 Subject: gianfar: Change default HW Tx queue scheduling mode This is primarily to address transmission timeout occurrences, when multiple H/W Tx queues are being used concurrently. Because in the priority scheduling mode the controller does not service the Tx queues equally (but in ascending index order), Tx timeouts are being triggered rightaway for a basic test with multiple simultaneous connections like: iperf -c -n 100M -P 8 resulting in kernel trace: NETDEV WATCHDOG: eth1 (fsl-gianfar): transmit queue timed out ------------[ cut here ]------------ WARNING: at net/sched/sch_generic.c:255 ... and controller reset during intense traffic, and possibly further complications. This patch changes the default H/W Tx scheduling setting (TXSCHED) for multi-queue devices, from priority scheduling mode to a weighted round robin mode with equal weights for all H/W Tx queues, and addresses the issue above. Signed-off-by: Claudiu Manoil Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.c | 11 ++++++++++- drivers/net/ethernet/freescale/gianfar.h | 11 ++++++++++- 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 4d5b58ce1298..a1b52ec3b930 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -394,7 +394,13 @@ static void gfar_init_mac(struct net_device *ndev) if (ndev->features & NETIF_F_IP_CSUM) tctrl |= TCTRL_INIT_CSUM; - tctrl |= TCTRL_TXSCHED_PRIO; + if (priv->prio_sched_en) + tctrl |= TCTRL_TXSCHED_PRIO; + else { + tctrl |= TCTRL_TXSCHED_WRRS; + gfar_write(®s->tr03wt, DEFAULT_WRRS_WEIGHT); + gfar_write(®s->tr47wt, DEFAULT_WRRS_WEIGHT); + } gfar_write(®s->tctrl, tctrl); @@ -1160,6 +1166,9 @@ static int gfar_probe(struct platform_device *ofdev) priv->rx_filer_enable = 1; /* Enable most messages by default */ priv->msg_enable = (NETIF_MSG_IFUP << 1 ) - 1; + /* use pritority h/w tx queue scheduling for single queue devices */ + if (priv->num_tx_queues == 1) + priv->prio_sched_en = 1; /* Carrier starts down, phylib will bring it up */ netif_carrier_off(dev); diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index 2136c7ff5e6d..4141ef2ddafc 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -301,8 +301,16 @@ extern const char gfar_driver_version[]; #define TCTRL_TFCPAUSE 0x00000008 #define TCTRL_TXSCHED_MASK 0x00000006 #define TCTRL_TXSCHED_INIT 0x00000000 +/* priority scheduling */ #define TCTRL_TXSCHED_PRIO 0x00000002 +/* weighted round-robin scheduling (WRRS) */ #define TCTRL_TXSCHED_WRRS 0x00000004 +/* default WRRS weight and policy setting, + * tailored to the tr03wt and tr47wt registers: + * equal weight for all Tx Qs, measured in 64byte units + */ +#define DEFAULT_WRRS_WEIGHT 0x18181818 + #define TCTRL_INIT_CSUM (TCTRL_TUCSEN | TCTRL_IPCSEN) #define IEVENT_INIT_CLEAR 0xffffffff @@ -1098,7 +1106,8 @@ struct gfar_private { extended_hash:1, bd_stash_en:1, rx_filer_enable:1, - wol_en:1; /* Wake-on-LAN enabled */ + wol_en:1, /* Wake-on-LAN enabled */ + prio_sched_en:1; /* Enable priorty based Tx scheduling in Hw */ unsigned short padding; /* PHY stuff */ -- cgit v1.2.3 From 718cffc4ac65f01c6f1efd6baec8b4b5ff0c76b5 Mon Sep 17 00:00:00 2001 From: "Steven J. Hill" Date: Mon, 24 Sep 2012 04:47:16 +0000 Subject: net: mipsnet: Remove the MIPSsim Ethernet driver. The MIPSsim platform is no longer supported or used. This patch deletes the Ethernet driver. Signed-off-by: Steven J. Hill Signed-off-by: David S. Miller --- drivers/net/ethernet/Kconfig | 9 -- drivers/net/ethernet/Makefile | 1 - drivers/net/ethernet/mipsnet.c | 345 ----------------------------------------- 3 files changed, 355 deletions(-) delete mode 100644 drivers/net/ethernet/mipsnet.c (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index a11af5cc4844..e4ff38949112 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -89,15 +89,6 @@ source "drivers/net/ethernet/marvell/Kconfig" source "drivers/net/ethernet/mellanox/Kconfig" source "drivers/net/ethernet/micrel/Kconfig" source "drivers/net/ethernet/microchip/Kconfig" - -config MIPS_SIM_NET - tristate "MIPS simulator Network device" - depends on MIPS_SIM - ---help--- - The MIPSNET device is a simple Ethernet network device which is - emulated by the MIPS Simulator. - If you are not using a MIPSsim or are unsure, say N. - source "drivers/net/ethernet/myricom/Kconfig" config FEALNX diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 878ad32b93f2..d4473072654a 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -40,7 +40,6 @@ obj-$(CONFIG_NET_VENDOR_MARVELL) += marvell/ obj-$(CONFIG_NET_VENDOR_MELLANOX) += mellanox/ obj-$(CONFIG_NET_VENDOR_MICREL) += micrel/ obj-$(CONFIG_NET_VENDOR_MICROCHIP) += microchip/ -obj-$(CONFIG_MIPS_SIM_NET) += mipsnet.o obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/ obj-$(CONFIG_FEALNX) += fealnx.o obj-$(CONFIG_NET_VENDOR_NATSEMI) += natsemi/ diff --git a/drivers/net/ethernet/mipsnet.c b/drivers/net/ethernet/mipsnet.c deleted file mode 100644 index db5285befe2a..000000000000 --- a/drivers/net/ethernet/mipsnet.c +++ /dev/null @@ -1,345 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define MIPSNET_VERSION "2007-11-17" - -/* - * Net status/control block as seen by sw in the core. - */ -struct mipsnet_regs { - /* - * Device info for probing, reads as MIPSNET%d where %d is some - * form of version. - */ - u64 devId; /*0x00 */ - - /* - * read only busy flag. - * Set and cleared by the Net Device to indicate that an rx or a tx - * is in progress. - */ - u32 busy; /*0x08 */ - - /* - * Set by the Net Device. - * The device will set it once data has been received. - * The value is the number of bytes that should be read from - * rxDataBuffer. The value will decrease till 0 until all the data - * from rxDataBuffer has been read. - */ - u32 rxDataCount; /*0x0c */ -#define MIPSNET_MAX_RXTX_DATACOUNT (1 << 16) - - /* - * Settable from the MIPS core, cleared by the Net Device. - * The core should set the number of bytes it wants to send, - * then it should write those bytes of data to txDataBuffer. - * The device will clear txDataCount has been processed (not - * necessarily sent). - */ - u32 txDataCount; /*0x10 */ - - /* - * Interrupt control - * - * Used to clear the interrupted generated by this dev. - * Write a 1 to clear the interrupt. (except bit31). - * - * Bit0 is set if it was a tx-done interrupt. - * Bit1 is set when new rx-data is available. - * Until this bit is cleared there will be no other RXs. - * - * Bit31 is used for testing, it clears after a read. - * Writing 1 to this bit will cause an interrupt to be generated. - * To clear the test interrupt, write 0 to this register. - */ - u32 interruptControl; /*0x14 */ -#define MIPSNET_INTCTL_TXDONE (1u << 0) -#define MIPSNET_INTCTL_RXDONE (1u << 1) -#define MIPSNET_INTCTL_TESTBIT (1u << 31) - - /* - * Readonly core-specific interrupt info for the device to signal - * the core. The meaning of the contents of this field might change. - */ - /* XXX: the whole memIntf interrupt scheme is messy: the device - * should have no control what so ever of what VPE/register set is - * being used. - * The MemIntf should only expose interrupt lines, and something in - * the config should be responsible for the line<->core/vpe bindings. - */ - u32 interruptInfo; /*0x18 */ - - /* - * This is where the received data is read out. - * There is more data to read until rxDataReady is 0. - * Only 1 byte at this regs offset is used. - */ - u32 rxDataBuffer; /*0x1c */ - - /* - * This is where the data to transmit is written. - * Data should be written for the amount specified in the - * txDataCount register. - * Only 1 byte at this regs offset is used. - */ - u32 txDataBuffer; /*0x20 */ -}; - -#define regaddr(dev, field) \ - (dev->base_addr + offsetof(struct mipsnet_regs, field)) - -static char mipsnet_string[] = "mipsnet"; - -/* - * Copy data from the MIPSNET rx data port - */ -static int ioiocpy_frommipsnet(struct net_device *dev, unsigned char *kdata, - int len) -{ - for (; len > 0; len--, kdata++) - *kdata = inb(regaddr(dev, rxDataBuffer)); - - return inl(regaddr(dev, rxDataCount)); -} - -static inline void mipsnet_put_todevice(struct net_device *dev, - struct sk_buff *skb) -{ - int count_to_go = skb->len; - char *buf_ptr = skb->data; - - outl(skb->len, regaddr(dev, txDataCount)); - - for (; count_to_go; buf_ptr++, count_to_go--) - outb(*buf_ptr, regaddr(dev, txDataBuffer)); - - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - - dev_kfree_skb(skb); -} - -static int mipsnet_xmit(struct sk_buff *skb, struct net_device *dev) -{ - /* - * Only one packet at a time. Once TXDONE interrupt is serviced, the - * queue will be restarted. - */ - netif_stop_queue(dev); - mipsnet_put_todevice(dev, skb); - - return NETDEV_TX_OK; -} - -static inline ssize_t mipsnet_get_fromdev(struct net_device *dev, size_t len) -{ - struct sk_buff *skb; - - if (!len) - return len; - - skb = netdev_alloc_skb(dev, len + NET_IP_ALIGN); - if (!skb) { - dev->stats.rx_dropped++; - return -ENOMEM; - } - - skb_reserve(skb, NET_IP_ALIGN); - if (ioiocpy_frommipsnet(dev, skb_put(skb, len), len)) - return -EFAULT; - - skb->protocol = eth_type_trans(skb, dev); - skb->ip_summed = CHECKSUM_UNNECESSARY; - - netif_rx(skb); - - dev->stats.rx_packets++; - dev->stats.rx_bytes += len; - - return len; -} - -static irqreturn_t mipsnet_interrupt(int irq, void *dev_id) -{ - struct net_device *dev = dev_id; - u32 int_flags; - irqreturn_t ret = IRQ_NONE; - - if (irq != dev->irq) - goto out_badirq; - - /* TESTBIT is cleared on read. */ - int_flags = inl(regaddr(dev, interruptControl)); - if (int_flags & MIPSNET_INTCTL_TESTBIT) { - /* TESTBIT takes effect after a write with 0. */ - outl(0, regaddr(dev, interruptControl)); - ret = IRQ_HANDLED; - } else if (int_flags & MIPSNET_INTCTL_TXDONE) { - /* Only one packet at a time, we are done. */ - dev->stats.tx_packets++; - netif_wake_queue(dev); - outl(MIPSNET_INTCTL_TXDONE, - regaddr(dev, interruptControl)); - ret = IRQ_HANDLED; - } else if (int_flags & MIPSNET_INTCTL_RXDONE) { - mipsnet_get_fromdev(dev, inl(regaddr(dev, rxDataCount))); - outl(MIPSNET_INTCTL_RXDONE, regaddr(dev, interruptControl)); - ret = IRQ_HANDLED; - } - return ret; - -out_badirq: - printk(KERN_INFO "%s: %s(): irq %d for unknown device\n", - dev->name, __func__, irq); - return ret; -} - -static int mipsnet_open(struct net_device *dev) -{ - int err; - - err = request_irq(dev->irq, mipsnet_interrupt, - IRQF_SHARED, dev->name, (void *) dev); - if (err) { - release_region(dev->base_addr, sizeof(struct mipsnet_regs)); - return err; - } - - netif_start_queue(dev); - - /* test interrupt handler */ - outl(MIPSNET_INTCTL_TESTBIT, regaddr(dev, interruptControl)); - - return 0; -} - -static int mipsnet_close(struct net_device *dev) -{ - netif_stop_queue(dev); - free_irq(dev->irq, dev); - return 0; -} - -static void mipsnet_set_mclist(struct net_device *dev) -{ -} - -static const struct net_device_ops mipsnet_netdev_ops = { - .ndo_open = mipsnet_open, - .ndo_stop = mipsnet_close, - .ndo_start_xmit = mipsnet_xmit, - .ndo_set_rx_mode = mipsnet_set_mclist, - .ndo_change_mtu = eth_change_mtu, - .ndo_validate_addr = eth_validate_addr, - .ndo_set_mac_address = eth_mac_addr, -}; - -static int __devinit mipsnet_probe(struct platform_device *dev) -{ - struct net_device *netdev; - int err; - - netdev = alloc_etherdev(0); - if (!netdev) { - err = -ENOMEM; - goto out; - } - - platform_set_drvdata(dev, netdev); - - netdev->netdev_ops = &mipsnet_netdev_ops; - - /* - * TODO: probe for these or load them from PARAM - */ - netdev->base_addr = 0x4200; - netdev->irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_MB0 + - inl(regaddr(netdev, interruptInfo)); - - /* Get the io region now, get irq on open() */ - if (!request_region(netdev->base_addr, sizeof(struct mipsnet_regs), - "mipsnet")) { - err = -EBUSY; - goto out_free_netdev; - } - - /* - * Lacking any better mechanism to allocate a MAC address we use a - * random one ... - */ - eth_hw_addr_random(netdev); - - err = register_netdev(netdev); - if (err) { - printk(KERN_ERR "MIPSNet: failed to register netdev.\n"); - goto out_free_region; - } - - return 0; - -out_free_region: - release_region(netdev->base_addr, sizeof(struct mipsnet_regs)); - -out_free_netdev: - free_netdev(netdev); - -out: - return err; -} - -static int __devexit mipsnet_device_remove(struct platform_device *device) -{ - struct net_device *dev = platform_get_drvdata(device); - - unregister_netdev(dev); - release_region(dev->base_addr, sizeof(struct mipsnet_regs)); - free_netdev(dev); - platform_set_drvdata(device, NULL); - - return 0; -} - -static struct platform_driver mipsnet_driver = { - .driver = { - .name = mipsnet_string, - .owner = THIS_MODULE, - }, - .probe = mipsnet_probe, - .remove = __devexit_p(mipsnet_device_remove), -}; - -static int __init mipsnet_init_module(void) -{ - int err; - - printk(KERN_INFO "MIPSNet Ethernet driver. Version: %s. " - "(c)2005 MIPS Technologies, Inc.\n", MIPSNET_VERSION); - - err = platform_driver_register(&mipsnet_driver); - if (err) - printk(KERN_ERR "Driver registration failed\n"); - - return err; -} - -static void __exit mipsnet_exit_module(void) -{ - platform_driver_unregister(&mipsnet_driver); -} - -module_init(mipsnet_init_module); -module_exit(mipsnet_exit_module); -- cgit v1.2.3 From 3eb4afbfceb44750d9afb832e6c992adec9fc571 Mon Sep 17 00:00:00 2001 From: Vipul Pandya Date: Wed, 26 Sep 2012 02:39:36 +0000 Subject: cxgb4: Fix incorrect values for MEMWIN*_APERTURE and MEMWIN*_BASE Signed-off-by: Jay Hernandez Signed-off-by: Vipul Pandya Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index ec2dafe8ae5b..f3fe23669f8a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -67,12 +67,12 @@ enum { }; enum { - MEMWIN0_APERTURE = 65536, - MEMWIN0_BASE = 0x30000, + MEMWIN0_APERTURE = 2048, + MEMWIN0_BASE = 0x1b800, MEMWIN1_APERTURE = 32768, MEMWIN1_BASE = 0x28000, - MEMWIN2_APERTURE = 2048, - MEMWIN2_BASE = 0x1b800, + MEMWIN2_APERTURE = 65536, + MEMWIN2_BASE = 0x30000, }; enum dev_master { -- cgit v1.2.3 From 5afc8b84eb7b29e4646d6e8ca7e6d7196031d6f7 Mon Sep 17 00:00:00 2001 From: Vipul Pandya Date: Wed, 26 Sep 2012 02:39:37 +0000 Subject: cxgb4: Add functions to read memory via PCIE memory window This patch implements two new functions t4_mem_win_read and t4_memory_read. These new functions can be used to read memory via the PCIE memory window. Please note, for proper execution of these functions PCIE_MEM_ACCESS_BASE_WIN registers must be setup correctly like how setup_memwin in the cxgb4 driver does it. Signed-off-by: Jay Hernandez Signed-off-by: Vipul Pandya Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 2 + drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 137 +++++++++++++++++++++++++++++ drivers/net/ethernet/chelsio/cxgb4/t4_hw.h | 80 +++++++++++++++++ 3 files changed, 219 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index f3fe23669f8a..7de740a8b764 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -664,6 +664,8 @@ int t4_wait_dev_ready(struct adapter *adap); int t4_link_start(struct adapter *adap, unsigned int mbox, unsigned int port, struct link_config *lc); int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port); +int t4_memory_write(struct adapter *adap, int mtype, u32 addr, u32 len, + __be32 *buf); int t4_seeprom_wp(struct adapter *adapter, bool enable); int t4_load_fw(struct adapter *adapter, const u8 *fw_data, unsigned int size); int t4_check_fw_version(struct adapter *adapter); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 8e988d699d05..259d0dcb0089 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -330,6 +330,143 @@ int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *ecc) return 0; } +/* + * t4_mem_win_rw - read/write memory through PCIE memory window + * @adap: the adapter + * @addr: address of first byte requested + * @data: MEMWIN0_APERTURE bytes of data containing the requested address + * @dir: direction of transfer 1 => read, 0 => write + * + * Read/write MEMWIN0_APERTURE bytes of data from MC starting at a + * MEMWIN0_APERTURE-byte-aligned address that covers the requested + * address @addr. + */ +static int t4_mem_win_rw(struct adapter *adap, u32 addr, __be32 *data, int dir) +{ + int i; + + /* + * Setup offset into PCIE memory window. Address must be a + * MEMWIN0_APERTURE-byte-aligned address. (Read back MA register to + * ensure that changes propagate before we attempt to use the new + * values.) + */ + t4_write_reg(adap, PCIE_MEM_ACCESS_OFFSET, + addr & ~(MEMWIN0_APERTURE - 1)); + t4_read_reg(adap, PCIE_MEM_ACCESS_OFFSET); + + /* Collecting data 4 bytes at a time upto MEMWIN0_APERTURE */ + for (i = 0; i < MEMWIN0_APERTURE; i = i+0x4) { + if (dir) + *data++ = t4_read_reg(adap, (MEMWIN0_BASE + i)); + else + t4_write_reg(adap, (MEMWIN0_BASE + i), *data++); + } + + return 0; +} + +/** + * t4_memory_rw - read/write EDC 0, EDC 1 or MC via PCIE memory window + * @adap: the adapter + * @mtype: memory type: MEM_EDC0, MEM_EDC1 or MEM_MC + * @addr: address within indicated memory type + * @len: amount of memory to transfer + * @buf: host memory buffer + * @dir: direction of transfer 1 => read, 0 => write + * + * Reads/writes an [almost] arbitrary memory region in the firmware: the + * firmware memory address, length and host buffer must be aligned on + * 32-bit boudaries. The memory is transferred as a raw byte sequence + * from/to the firmware's memory. If this memory contains data + * structures which contain multi-byte integers, it's the callers + * responsibility to perform appropriate byte order conversions. + */ +static int t4_memory_rw(struct adapter *adap, int mtype, u32 addr, u32 len, + __be32 *buf, int dir) +{ + u32 pos, start, end, offset, memoffset; + int ret; + + /* + * Argument sanity checks ... + */ + if ((addr & 0x3) || (len & 0x3)) + return -EINVAL; + + /* + * Offset into the region of memory which is being accessed + * MEM_EDC0 = 0 + * MEM_EDC1 = 1 + * MEM_MC = 2 + */ + memoffset = (mtype * (5 * 1024 * 1024)); + + /* Determine the PCIE_MEM_ACCESS_OFFSET */ + addr = addr + memoffset; + + /* + * The underlaying EDC/MC read routines read MEMWIN0_APERTURE bytes + * at a time so we need to round down the start and round up the end. + * We'll start copying out of the first line at (addr - start) a word + * at a time. + */ + start = addr & ~(MEMWIN0_APERTURE-1); + end = (addr + len + MEMWIN0_APERTURE-1) & ~(MEMWIN0_APERTURE-1); + offset = (addr - start)/sizeof(__be32); + + for (pos = start; pos < end; pos += MEMWIN0_APERTURE, offset = 0) { + __be32 data[MEMWIN0_APERTURE/sizeof(__be32)]; + + /* + * If we're writing, copy the data from the caller's memory + * buffer + */ + if (!dir) { + /* + * If we're doing a partial write, then we need to do + * a read-modify-write ... + */ + if (offset || len < MEMWIN0_APERTURE) { + ret = t4_mem_win_rw(adap, pos, data, 1); + if (ret) + return ret; + } + while (offset < (MEMWIN0_APERTURE/sizeof(__be32)) && + len > 0) { + data[offset++] = *buf++; + len -= sizeof(__be32); + } + } + + /* + * Transfer a block of memory and bail if there's an error. + */ + ret = t4_mem_win_rw(adap, pos, data, dir); + if (ret) + return ret; + + /* + * If we're reading, copy the data into the caller's memory + * buffer. + */ + if (dir) + while (offset < (MEMWIN0_APERTURE/sizeof(__be32)) && + len > 0) { + *buf++ = data[offset++]; + len -= sizeof(__be32); + } + } + + return 0; +} + +int t4_memory_write(struct adapter *adap, int mtype, u32 addr, u32 len, + __be32 *buf) +{ + return t4_memory_rw(adap, mtype, addr, len, buf, 0); +} + #define EEPROM_STAT_ADDR 0x7bfc #define VPD_BASE 0 #define VPD_LEN 512 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h index c26b455f37de..f534ed7e10e9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h @@ -58,6 +58,7 @@ enum { enum { SF_PAGE_SIZE = 256, /* serial flash page size */ + SF_SEC_SIZE = 64 * 1024, /* serial flash sector size */ }; enum { RSP_TYPE_FLBUF, RSP_TYPE_CPL, RSP_TYPE_INTR }; /* response entry types */ @@ -137,4 +138,83 @@ struct rsp_ctrl { #define QINTR_CNT_EN 0x1 #define QINTR_TIMER_IDX(x) ((x) << 1) #define QINTR_TIMER_IDX_GET(x) (((x) >> 1) & 0x7) + +/* + * Flash layout. + */ +#define FLASH_START(start) ((start) * SF_SEC_SIZE) +#define FLASH_MAX_SIZE(nsecs) ((nsecs) * SF_SEC_SIZE) + +enum { + /* + * Various Expansion-ROM boot images, etc. + */ + FLASH_EXP_ROM_START_SEC = 0, + FLASH_EXP_ROM_NSECS = 6, + FLASH_EXP_ROM_START = FLASH_START(FLASH_EXP_ROM_START_SEC), + FLASH_EXP_ROM_MAX_SIZE = FLASH_MAX_SIZE(FLASH_EXP_ROM_NSECS), + + /* + * iSCSI Boot Firmware Table (iBFT) and other driver-related + * parameters ... + */ + FLASH_IBFT_START_SEC = 6, + FLASH_IBFT_NSECS = 1, + FLASH_IBFT_START = FLASH_START(FLASH_IBFT_START_SEC), + FLASH_IBFT_MAX_SIZE = FLASH_MAX_SIZE(FLASH_IBFT_NSECS), + + /* + * Boot configuration data. + */ + FLASH_BOOTCFG_START_SEC = 7, + FLASH_BOOTCFG_NSECS = 1, + FLASH_BOOTCFG_START = FLASH_START(FLASH_BOOTCFG_START_SEC), + FLASH_BOOTCFG_MAX_SIZE = FLASH_MAX_SIZE(FLASH_BOOTCFG_NSECS), + + /* + * Location of firmware image in FLASH. + */ + FLASH_FW_START_SEC = 8, + FLASH_FW_NSECS = 8, + FLASH_FW_START = FLASH_START(FLASH_FW_START_SEC), + FLASH_FW_MAX_SIZE = FLASH_MAX_SIZE(FLASH_FW_NSECS), + + /* + * iSCSI persistent/crash information. + */ + FLASH_ISCSI_CRASH_START_SEC = 29, + FLASH_ISCSI_CRASH_NSECS = 1, + FLASH_ISCSI_CRASH_START = FLASH_START(FLASH_ISCSI_CRASH_START_SEC), + FLASH_ISCSI_CRASH_MAX_SIZE = FLASH_MAX_SIZE(FLASH_ISCSI_CRASH_NSECS), + + /* + * FCoE persistent/crash information. + */ + FLASH_FCOE_CRASH_START_SEC = 30, + FLASH_FCOE_CRASH_NSECS = 1, + FLASH_FCOE_CRASH_START = FLASH_START(FLASH_FCOE_CRASH_START_SEC), + FLASH_FCOE_CRASH_MAX_SIZE = FLASH_MAX_SIZE(FLASH_FCOE_CRASH_NSECS), + + /* + * Location of Firmware Configuration File in FLASH. Since the FPGA + * "FLASH" is smaller we need to store the Configuration File in a + * different location -- which will overlap the end of the firmware + * image if firmware ever gets that large ... + */ + FLASH_CFG_START_SEC = 31, + FLASH_CFG_NSECS = 1, + FLASH_CFG_START = FLASH_START(FLASH_CFG_START_SEC), + FLASH_CFG_MAX_SIZE = FLASH_MAX_SIZE(FLASH_CFG_NSECS), + + FLASH_FPGA_CFG_START_SEC = 15, + FLASH_FPGA_CFG_START = FLASH_START(FLASH_FPGA_CFG_START_SEC), + + /* + * Sectors 32-63 are reserved for FLASH failover. + */ +}; + +#undef FLASH_START +#undef FLASH_MAX_SIZE + #endif /* __T4_HW_H */ -- cgit v1.2.3 From 52367a763d8046190754ab43743e42638564a2d1 Mon Sep 17 00:00:00 2001 From: Vipul Pandya Date: Wed, 26 Sep 2012 02:39:38 +0000 Subject: cxgb4/cxgb4vf: Code cleanup to enable T4 Configuration File support This patch adds new enums and macros to enable T4 configuration file support. It also removes duplicate macro definitions. It fixes the build failure in cxgb4vf driver introduced because of old macro definition removal. It also performs SGE initialization based on T4 configuration file is provided or not. If it is provided then it uses the parameters provided in it otherwise it uses hard coded values. Signed-off-by: Jay Hernandez Signed-off-by: Vipul Pandya Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 18 +- drivers/net/ethernet/chelsio/cxgb4/sge.c | 337 +++++++++++++++++++++----- drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 35 ++- drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 41 +++- drivers/net/ethernet/chelsio/cxgb4vf/sge.c | 5 +- 5 files changed, 365 insertions(+), 71 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 7de740a8b764..ae040cf255a4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -315,6 +315,9 @@ enum { /* adapter flags */ USING_MSI = (1 << 1), USING_MSIX = (1 << 2), FW_OK = (1 << 4), + USING_SOFT_PARAMS = (1 << 6), + MASTER_PF = (1 << 7), + FW_OFLD_CONN = (1 << 9), }; struct rx_sw_desc; @@ -467,6 +470,11 @@ struct sge { u16 rdma_rxq[NCHAN]; u16 timer_val[SGE_NTIMERS]; u8 counter_val[SGE_NCOUNTERS]; + u32 fl_pg_order; /* large page allocation size */ + u32 stat_len; /* length of status page at ring end */ + u32 pktshift; /* padding between CPL & packet data */ + u32 fl_align; /* response queue message alignment */ + u32 fl_starve_thres; /* Free List starvation threshold */ unsigned int starve_thres; u8 idma_state[2]; unsigned int egr_start; @@ -619,7 +627,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq, struct net_device *dev, unsigned int iqid); irqreturn_t t4_sge_intr_msix(int irq, void *cookie); -void t4_sge_init(struct adapter *adap); +int t4_sge_init(struct adapter *adap); void t4_sge_start(struct adapter *adap); void t4_sge_stop(struct adapter *adap); extern int dbfifo_int_thresh; @@ -638,6 +646,14 @@ static inline unsigned int us_to_core_ticks(const struct adapter *adap, return (us * adap->params.vpd.cclk) / 1000; } +static inline unsigned int core_ticks_to_us(const struct adapter *adapter, + unsigned int ticks) +{ + /* add Core Clock / 2 to round ticks to nearest uS */ + return ((ticks * 1000 + adapter->params.vpd.cclk/2) / + adapter->params.vpd.cclk); +} + void t4_set_reg_field(struct adapter *adap, unsigned int addr, u32 mask, u32 val); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 1fde57d45318..3ecc087d732d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -68,9 +68,6 @@ */ #define RX_PKT_SKB_LEN 512 -/* Ethernet header padding prepended to RX_PKTs */ -#define RX_PKT_PAD 2 - /* * Max number of Tx descriptors we clean up at a time. Should be modest as * freeing skbs isn't cheap and it happens while holding locks. We just need @@ -137,13 +134,6 @@ */ #define MAX_CTRL_WR_LEN SGE_MAX_WR_LEN -enum { - /* packet alignment in FL buffers */ - FL_ALIGN = L1_CACHE_BYTES < 32 ? 32 : L1_CACHE_BYTES, - /* egress status entry size */ - STAT_LEN = L1_CACHE_BYTES > 64 ? 128 : 64 -}; - struct tx_sw_desc { /* SW state per Tx descriptor */ struct sk_buff *skb; struct ulptx_sgl *sgl; @@ -155,16 +145,57 @@ struct rx_sw_desc { /* SW state per Rx descriptor */ }; /* - * The low bits of rx_sw_desc.dma_addr have special meaning. + * Rx buffer sizes for "useskbs" Free List buffers (one ingress packet pe skb + * buffer). We currently only support two sizes for 1500- and 9000-byte MTUs. + * We could easily support more but there doesn't seem to be much need for + * that ... + */ +#define FL_MTU_SMALL 1500 +#define FL_MTU_LARGE 9000 + +static inline unsigned int fl_mtu_bufsize(struct adapter *adapter, + unsigned int mtu) +{ + struct sge *s = &adapter->sge; + + return ALIGN(s->pktshift + ETH_HLEN + VLAN_HLEN + mtu, s->fl_align); +} + +#define FL_MTU_SMALL_BUFSIZE(adapter) fl_mtu_bufsize(adapter, FL_MTU_SMALL) +#define FL_MTU_LARGE_BUFSIZE(adapter) fl_mtu_bufsize(adapter, FL_MTU_LARGE) + +/* + * Bits 0..3 of rx_sw_desc.dma_addr have special meaning. The hardware uses + * these to specify the buffer size as an index into the SGE Free List Buffer + * Size register array. We also use bit 4, when the buffer has been unmapped + * for DMA, but this is of course never sent to the hardware and is only used + * to prevent double unmappings. All of the above requires that the Free List + * Buffers which we allocate have the bottom 5 bits free (0) -- i.e. are + * 32-byte or or a power of 2 greater in alignment. Since the SGE's minimal + * Free List Buffer alignment is 32 bytes, this works out for us ... */ enum { - RX_LARGE_BUF = 1 << 0, /* buffer is larger than PAGE_SIZE */ - RX_UNMAPPED_BUF = 1 << 1, /* buffer is not mapped */ + RX_BUF_FLAGS = 0x1f, /* bottom five bits are special */ + RX_BUF_SIZE = 0x0f, /* bottom three bits are for buf sizes */ + RX_UNMAPPED_BUF = 0x10, /* buffer is not mapped */ + + /* + * XXX We shouldn't depend on being able to use these indices. + * XXX Especially when some other Master PF has initialized the + * XXX adapter or we use the Firmware Configuration File. We + * XXX should really search through the Host Buffer Size register + * XXX array for the appropriately sized buffer indices. + */ + RX_SMALL_PG_BUF = 0x0, /* small (PAGE_SIZE) page buffer */ + RX_LARGE_PG_BUF = 0x1, /* buffer large (FL_PG_ORDER) page buffer */ + + RX_SMALL_MTU_BUF = 0x2, /* small MTU buffer */ + RX_LARGE_MTU_BUF = 0x3, /* large MTU buffer */ }; static inline dma_addr_t get_buf_addr(const struct rx_sw_desc *d) { - return d->dma_addr & ~(dma_addr_t)(RX_LARGE_BUF | RX_UNMAPPED_BUF); + return d->dma_addr & ~(dma_addr_t)RX_BUF_FLAGS; } static inline bool is_buf_mapped(const struct rx_sw_desc *d) @@ -392,14 +423,35 @@ static inline void reclaim_completed_tx(struct adapter *adap, struct sge_txq *q, } } -static inline int get_buf_size(const struct rx_sw_desc *d) +static inline int get_buf_size(struct adapter *adapter, + const struct rx_sw_desc *d) { -#if FL_PG_ORDER > 0 - return (d->dma_addr & RX_LARGE_BUF) ? (PAGE_SIZE << FL_PG_ORDER) : - PAGE_SIZE; -#else - return PAGE_SIZE; -#endif + struct sge *s = &adapter->sge; + unsigned int rx_buf_size_idx = d->dma_addr & RX_BUF_SIZE; + int buf_size; + + switch (rx_buf_size_idx) { + case RX_SMALL_PG_BUF: + buf_size = PAGE_SIZE; + break; + + case RX_LARGE_PG_BUF: + buf_size = PAGE_SIZE << s->fl_pg_order; + break; + + case RX_SMALL_MTU_BUF: + buf_size = FL_MTU_SMALL_BUFSIZE(adapter); + break; + + case RX_LARGE_MTU_BUF: + buf_size = FL_MTU_LARGE_BUFSIZE(adapter); + break; + + default: + BUG_ON(1); + } + + return buf_size; } /** @@ -418,7 +470,8 @@ static void free_rx_bufs(struct adapter *adap, struct sge_fl *q, int n) if (is_buf_mapped(d)) dma_unmap_page(adap->pdev_dev, get_buf_addr(d), - get_buf_size(d), PCI_DMA_FROMDEVICE); + get_buf_size(adap, d), + PCI_DMA_FROMDEVICE); put_page(d->page); d->page = NULL; if (++q->cidx == q->size) @@ -444,7 +497,7 @@ static void unmap_rx_buf(struct adapter *adap, struct sge_fl *q) if (is_buf_mapped(d)) dma_unmap_page(adap->pdev_dev, get_buf_addr(d), - get_buf_size(d), PCI_DMA_FROMDEVICE); + get_buf_size(adap, d), PCI_DMA_FROMDEVICE); d->page = NULL; if (++q->cidx == q->size) q->cidx = 0; @@ -485,6 +538,7 @@ static inline void set_rx_sw_desc(struct rx_sw_desc *sd, struct page *pg, static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n, gfp_t gfp) { + struct sge *s = &adap->sge; struct page *pg; dma_addr_t mapping; unsigned int cred = q->avail; @@ -493,25 +547,27 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n, gfp |= __GFP_NOWARN | __GFP_COLD; -#if FL_PG_ORDER > 0 + if (s->fl_pg_order == 0) + goto alloc_small_pages; + /* * Prefer large buffers */ while (n) { - pg = alloc_pages(gfp | __GFP_COMP, FL_PG_ORDER); + pg = alloc_pages(gfp | __GFP_COMP, s->fl_pg_order); if (unlikely(!pg)) { q->large_alloc_failed++; break; /* fall back to single pages */ } mapping = dma_map_page(adap->pdev_dev, pg, 0, - PAGE_SIZE << FL_PG_ORDER, + PAGE_SIZE << s->fl_pg_order, PCI_DMA_FROMDEVICE); if (unlikely(dma_mapping_error(adap->pdev_dev, mapping))) { - __free_pages(pg, FL_PG_ORDER); + __free_pages(pg, s->fl_pg_order); goto out; /* do not try small pages for this error */ } - mapping |= RX_LARGE_BUF; + mapping |= RX_LARGE_PG_BUF; *d++ = cpu_to_be64(mapping); set_rx_sw_desc(sd, pg, mapping); @@ -525,8 +581,8 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n, } n--; } -#endif +alloc_small_pages: while (n--) { pg = __skb_alloc_page(gfp, NULL); if (unlikely(!pg)) { @@ -1519,6 +1575,8 @@ static noinline int handle_trace_pkt(struct adapter *adap, static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl, const struct cpl_rx_pkt *pkt) { + struct adapter *adapter = rxq->rspq.adap; + struct sge *s = &adapter->sge; int ret; struct sk_buff *skb; @@ -1529,8 +1587,8 @@ static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl, return; } - copy_frags(skb, gl, RX_PKT_PAD); - skb->len = gl->tot_len - RX_PKT_PAD; + copy_frags(skb, gl, s->pktshift); + skb->len = gl->tot_len - s->pktshift; skb->data_len = skb->len; skb->truesize += skb->data_len; skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -1566,6 +1624,7 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, struct sk_buff *skb; const struct cpl_rx_pkt *pkt; struct sge_eth_rxq *rxq = container_of(q, struct sge_eth_rxq, rspq); + struct sge *s = &q->adap->sge; if (unlikely(*(u8 *)rsp == CPL_TRACE_PKT)) return handle_trace_pkt(q->adap, si); @@ -1585,7 +1644,7 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, return 0; } - __skb_pull(skb, RX_PKT_PAD); /* remove ethernet header padding */ + __skb_pull(skb, s->pktshift); /* remove ethernet header padding */ skb->protocol = eth_type_trans(skb, q->netdev); skb_record_rx_queue(skb, q->idx); if (skb->dev->features & NETIF_F_RXHASH) @@ -1696,6 +1755,8 @@ static int process_responses(struct sge_rspq *q, int budget) int budget_left = budget; const struct rsp_ctrl *rc; struct sge_eth_rxq *rxq = container_of(q, struct sge_eth_rxq, rspq); + struct adapter *adapter = q->adap; + struct sge *s = &adapter->sge; while (likely(budget_left)) { rc = (void *)q->cur_desc + (q->iqe_len - sizeof(*rc)); @@ -1722,7 +1783,7 @@ static int process_responses(struct sge_rspq *q, int budget) /* gather packet fragments */ for (frags = 0, fp = si.frags; ; frags++, fp++) { rsd = &rxq->fl.sdesc[rxq->fl.cidx]; - bufsz = get_buf_size(rsd); + bufsz = get_buf_size(adapter, rsd); fp->page = rsd->page; fp->offset = q->offset; fp->size = min(bufsz, len); @@ -1747,7 +1808,7 @@ static int process_responses(struct sge_rspq *q, int budget) si.nfrags = frags + 1; ret = q->handler(q, q->cur_desc, &si); if (likely(ret == 0)) - q->offset += ALIGN(fp->size, FL_ALIGN); + q->offset += ALIGN(fp->size, s->fl_align); else restore_rx_bufs(&si, &rxq->fl, frags); } else if (likely(rsp_type == RSP_TYPE_CPL)) { @@ -1983,6 +2044,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, { int ret, flsz = 0; struct fw_iq_cmd c; + struct sge *s = &adap->sge; struct port_info *pi = netdev_priv(dev); /* Size needs to be multiple of 16, including status entry. */ @@ -2015,11 +2077,11 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, fl->size = roundup(fl->size, 8); fl->desc = alloc_ring(adap->pdev_dev, fl->size, sizeof(__be64), sizeof(struct rx_sw_desc), &fl->addr, - &fl->sdesc, STAT_LEN, NUMA_NO_NODE); + &fl->sdesc, s->stat_len, NUMA_NO_NODE); if (!fl->desc) goto fl_nomem; - flsz = fl->size / 8 + STAT_LEN / sizeof(struct tx_desc); + flsz = fl->size / 8 + s->stat_len / sizeof(struct tx_desc); c.iqns_to_fl0congen = htonl(FW_IQ_CMD_FL0PACKEN | FW_IQ_CMD_FL0FETCHRO(1) | FW_IQ_CMD_FL0DATARO(1) | @@ -2096,14 +2158,15 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, { int ret, nentries; struct fw_eq_eth_cmd c; + struct sge *s = &adap->sge; struct port_info *pi = netdev_priv(dev); /* Add status entries */ - nentries = txq->q.size + STAT_LEN / sizeof(struct tx_desc); + nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc); txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size, sizeof(struct tx_desc), sizeof(struct tx_sw_desc), - &txq->q.phys_addr, &txq->q.sdesc, STAT_LEN, + &txq->q.phys_addr, &txq->q.sdesc, s->stat_len, netdev_queue_numa_node_read(netdevq)); if (!txq->q.desc) return -ENOMEM; @@ -2149,10 +2212,11 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, { int ret, nentries; struct fw_eq_ctrl_cmd c; + struct sge *s = &adap->sge; struct port_info *pi = netdev_priv(dev); /* Add status entries */ - nentries = txq->q.size + STAT_LEN / sizeof(struct tx_desc); + nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc); txq->q.desc = alloc_ring(adap->pdev_dev, nentries, sizeof(struct tx_desc), 0, &txq->q.phys_addr, @@ -2200,14 +2264,15 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq, { int ret, nentries; struct fw_eq_ofld_cmd c; + struct sge *s = &adap->sge; struct port_info *pi = netdev_priv(dev); /* Add status entries */ - nentries = txq->q.size + STAT_LEN / sizeof(struct tx_desc); + nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc); txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size, sizeof(struct tx_desc), sizeof(struct tx_sw_desc), - &txq->q.phys_addr, &txq->q.sdesc, STAT_LEN, + &txq->q.phys_addr, &txq->q.sdesc, s->stat_len, NUMA_NO_NODE); if (!txq->q.desc) return -ENOMEM; @@ -2251,8 +2316,10 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq, static void free_txq(struct adapter *adap, struct sge_txq *q) { + struct sge *s = &adap->sge; + dma_free_coherent(adap->pdev_dev, - q->size * sizeof(struct tx_desc) + STAT_LEN, + q->size * sizeof(struct tx_desc) + s->stat_len, q->desc, q->phys_addr); q->cntxt_id = 0; q->sdesc = NULL; @@ -2262,6 +2329,7 @@ static void free_txq(struct adapter *adap, struct sge_txq *q) static void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq, struct sge_fl *fl) { + struct sge *s = &adap->sge; unsigned int fl_id = fl ? fl->cntxt_id : 0xffff; adap->sge.ingr_map[rq->cntxt_id - adap->sge.ingr_start] = NULL; @@ -2276,7 +2344,7 @@ static void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq, if (fl) { free_rx_bufs(adap, fl, fl->avail); - dma_free_coherent(adap->pdev_dev, fl->size * 8 + STAT_LEN, + dma_free_coherent(adap->pdev_dev, fl->size * 8 + s->stat_len, fl->desc, fl->addr); kfree(fl->sdesc); fl->sdesc = NULL; @@ -2408,18 +2476,112 @@ void t4_sge_stop(struct adapter *adap) * Performs SGE initialization needed every time after a chip reset. * We do not initialize any of the queues here, instead the driver * top-level must request them individually. + * + * Called in two different modes: + * + * 1. Perform actual hardware initialization and record hard-coded + * parameters which were used. This gets used when we're the + * Master PF and the Firmware Configuration File support didn't + * work for some reason. + * + * 2. We're not the Master PF or initialization was performed with + * a Firmware Configuration File. In this case we need to grab + * any of the SGE operating parameters that we need to have in + * order to do our job and make sure we can live with them ... */ -void t4_sge_init(struct adapter *adap) + +static int t4_sge_init_soft(struct adapter *adap) { - unsigned int i, v; struct sge *s = &adap->sge; - unsigned int fl_align_log = ilog2(FL_ALIGN); + u32 fl_small_pg, fl_large_pg, fl_small_mtu, fl_large_mtu; + u32 timer_value_0_and_1, timer_value_2_and_3, timer_value_4_and_5; + u32 ingress_rx_threshold; - t4_set_reg_field(adap, SGE_CONTROL, PKTSHIFT_MASK | - INGPADBOUNDARY_MASK | EGRSTATUSPAGESIZE, - INGPADBOUNDARY(fl_align_log - 5) | PKTSHIFT(2) | - RXPKTCPLMODE | - (STAT_LEN == 128 ? EGRSTATUSPAGESIZE : 0)); + /* + * Verify that CPL messages are going to the Ingress Queue for + * process_responses() and that only packet data is going to the + * Free Lists. + */ + if ((t4_read_reg(adap, SGE_CONTROL) & RXPKTCPLMODE_MASK) != + RXPKTCPLMODE(X_RXPKTCPLMODE_SPLIT)) { + dev_err(adap->pdev_dev, "bad SGE CPL MODE\n"); + return -EINVAL; + } + + /* + * Validate the Host Buffer Register Array indices that we want to + * use ... + * + * XXX Note that we should really read through the Host Buffer Size + * XXX register array and find the indices of the Buffer Sizes which + * XXX meet our needs! + */ + #define READ_FL_BUF(x) \ + t4_read_reg(adap, SGE_FL_BUFFER_SIZE0+(x)*sizeof(u32)) + + fl_small_pg = READ_FL_BUF(RX_SMALL_PG_BUF); + fl_large_pg = READ_FL_BUF(RX_LARGE_PG_BUF); + fl_small_mtu = READ_FL_BUF(RX_SMALL_MTU_BUF); + fl_large_mtu = READ_FL_BUF(RX_LARGE_MTU_BUF); + + #undef READ_FL_BUF + + if (fl_small_pg != PAGE_SIZE || + (fl_large_pg != 0 && (fl_large_pg <= fl_small_pg || + (fl_large_pg & (fl_large_pg-1)) != 0))) { + dev_err(adap->pdev_dev, "bad SGE FL page buffer sizes [%d, %d]\n", + fl_small_pg, fl_large_pg); + return -EINVAL; + } + if (fl_large_pg) + s->fl_pg_order = ilog2(fl_large_pg) - PAGE_SHIFT; + + if (fl_small_mtu < FL_MTU_SMALL_BUFSIZE(adap) || + fl_large_mtu < FL_MTU_LARGE_BUFSIZE(adap)) { + dev_err(adap->pdev_dev, "bad SGE FL MTU sizes [%d, %d]\n", + fl_small_mtu, fl_large_mtu); + return -EINVAL; + } + + /* + * Retrieve our RX interrupt holdoff timer values and counter + * threshold values from the SGE parameters. + */ + timer_value_0_and_1 = t4_read_reg(adap, SGE_TIMER_VALUE_0_AND_1); + timer_value_2_and_3 = t4_read_reg(adap, SGE_TIMER_VALUE_2_AND_3); + timer_value_4_and_5 = t4_read_reg(adap, SGE_TIMER_VALUE_4_AND_5); + s->timer_val[0] = core_ticks_to_us(adap, + TIMERVALUE0_GET(timer_value_0_and_1)); + s->timer_val[1] = core_ticks_to_us(adap, + TIMERVALUE1_GET(timer_value_0_and_1)); + s->timer_val[2] = core_ticks_to_us(adap, + TIMERVALUE2_GET(timer_value_2_and_3)); + s->timer_val[3] = core_ticks_to_us(adap, + TIMERVALUE3_GET(timer_value_2_and_3)); + s->timer_val[4] = core_ticks_to_us(adap, + TIMERVALUE4_GET(timer_value_4_and_5)); + s->timer_val[5] = core_ticks_to_us(adap, + TIMERVALUE5_GET(timer_value_4_and_5)); + + ingress_rx_threshold = t4_read_reg(adap, SGE_INGRESS_RX_THRESHOLD); + s->counter_val[0] = THRESHOLD_0_GET(ingress_rx_threshold); + s->counter_val[1] = THRESHOLD_1_GET(ingress_rx_threshold); + s->counter_val[2] = THRESHOLD_2_GET(ingress_rx_threshold); + s->counter_val[3] = THRESHOLD_3_GET(ingress_rx_threshold); + + return 0; +} + +static int t4_sge_init_hard(struct adapter *adap) +{ + struct sge *s = &adap->sge; + + /* + * Set up our basic SGE mode to deliver CPL messages to our Ingress + * Queue and Packet Date to the Free List. + */ + t4_set_reg_field(adap, SGE_CONTROL, RXPKTCPLMODE_MASK, + RXPKTCPLMODE_MASK); /* * Set up to drop DOORBELL writes when the DOORBELL FIFO overflows @@ -2433,13 +2595,24 @@ void t4_sge_init(struct adapter *adap) t4_set_reg_field(adap, A_SGE_DOORBELL_CONTROL, F_ENABLE_DROP, F_ENABLE_DROP); - for (i = v = 0; i < 32; i += 4) - v |= (PAGE_SHIFT - 10) << i; - t4_write_reg(adap, SGE_HOST_PAGE_SIZE, v); - t4_write_reg(adap, SGE_FL_BUFFER_SIZE0, PAGE_SIZE); -#if FL_PG_ORDER > 0 - t4_write_reg(adap, SGE_FL_BUFFER_SIZE1, PAGE_SIZE << FL_PG_ORDER); -#endif + /* + * SGE_FL_BUFFER_SIZE0 (RX_SMALL_PG_BUF) is set up by + * t4_fixup_host_params(). + */ + s->fl_pg_order = FL_PG_ORDER; + if (s->fl_pg_order) + t4_write_reg(adap, + SGE_FL_BUFFER_SIZE0+RX_LARGE_PG_BUF*sizeof(u32), + PAGE_SIZE << FL_PG_ORDER); + t4_write_reg(adap, SGE_FL_BUFFER_SIZE0+RX_SMALL_MTU_BUF*sizeof(u32), + FL_MTU_SMALL_BUFSIZE(adap)); + t4_write_reg(adap, SGE_FL_BUFFER_SIZE0+RX_LARGE_MTU_BUF*sizeof(u32), + FL_MTU_LARGE_BUFSIZE(adap)); + + /* + * Note that the SGE Ingress Packet Count Interrupt Threshold and + * Timer Holdoff values must be supplied by our caller. + */ t4_write_reg(adap, SGE_INGRESS_RX_THRESHOLD, THRESHOLD_0(s->counter_val[0]) | THRESHOLD_1(s->counter_val[1]) | @@ -2449,14 +2622,54 @@ void t4_sge_init(struct adapter *adap) TIMERVALUE0(us_to_core_ticks(adap, s->timer_val[0])) | TIMERVALUE1(us_to_core_ticks(adap, s->timer_val[1]))); t4_write_reg(adap, SGE_TIMER_VALUE_2_AND_3, - TIMERVALUE0(us_to_core_ticks(adap, s->timer_val[2])) | - TIMERVALUE1(us_to_core_ticks(adap, s->timer_val[3]))); + TIMERVALUE2(us_to_core_ticks(adap, s->timer_val[2])) | + TIMERVALUE3(us_to_core_ticks(adap, s->timer_val[3]))); t4_write_reg(adap, SGE_TIMER_VALUE_4_AND_5, - TIMERVALUE0(us_to_core_ticks(adap, s->timer_val[4])) | - TIMERVALUE1(us_to_core_ticks(adap, s->timer_val[5]))); + TIMERVALUE4(us_to_core_ticks(adap, s->timer_val[4])) | + TIMERVALUE5(us_to_core_ticks(adap, s->timer_val[5]))); + + return 0; +} + +int t4_sge_init(struct adapter *adap) +{ + struct sge *s = &adap->sge; + u32 sge_control; + int ret; + + /* + * Ingress Padding Boundary and Egress Status Page Size are set up by + * t4_fixup_host_params(). + */ + sge_control = t4_read_reg(adap, SGE_CONTROL); + s->pktshift = PKTSHIFT_GET(sge_control); + s->stat_len = (sge_control & EGRSTATUSPAGESIZE_MASK) ? 128 : 64; + s->fl_align = 1 << (INGPADBOUNDARY_GET(sge_control) + + X_INGPADBOUNDARY_SHIFT); + + if (adap->flags & USING_SOFT_PARAMS) + ret = t4_sge_init_soft(adap); + else + ret = t4_sge_init_hard(adap); + if (ret < 0) + return ret; + + /* + * A FL with <= fl_starve_thres buffers is starving and a periodic + * timer will attempt to refill it. This needs to be larger than the + * SGE's Egress Congestion Threshold. If it isn't, then we can get + * stuck waiting for new packets while the SGE is waiting for us to + * give it more Free List entries. (Note that the SGE's Egress + * Congestion Threshold is in units of 2 Free List pointers.) + */ + s->fl_starve_thres + = EGRTHRESHOLD_GET(t4_read_reg(adap, SGE_CONM_CTRL))*2 + 1; + setup_timer(&s->rx_timer, sge_rx_timer_cb, (unsigned long)adap); setup_timer(&s->tx_timer, sge_tx_timer_cb, (unsigned long)adap); s->starve_thres = core_ticks_per_usec(adap) * 1000000; /* 1 s */ s->idma_state[0] = s->idma_state[1] = 0; spin_lock_init(&s->intrq_lock); + + return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 8e814bc46822..2767ca6dbe99 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -86,10 +86,17 @@ #define CIDXINC_SHIFT 0 #define CIDXINC(x) ((x) << CIDXINC_SHIFT) +#define X_RXPKTCPLMODE_SPLIT 1 +#define X_INGPADBOUNDARY_SHIFT 5 + #define SGE_CONTROL 0x1008 #define DCASYSTYPE 0x00080000U -#define RXPKTCPLMODE 0x00040000U -#define EGRSTATUSPAGESIZE 0x00020000U +#define RXPKTCPLMODE_MASK 0x00040000U +#define RXPKTCPLMODE_SHIFT 18 +#define RXPKTCPLMODE(x) ((x) << RXPKTCPLMODE_SHIFT) +#define EGRSTATUSPAGESIZE_MASK 0x00020000U +#define EGRSTATUSPAGESIZE_SHIFT 17 +#define EGRSTATUSPAGESIZE(x) ((x) << EGRSTATUSPAGESIZE_SHIFT) #define PKTSHIFT_MASK 0x00001c00U #define PKTSHIFT_SHIFT 10 #define PKTSHIFT(x) ((x) << PKTSHIFT_SHIFT) @@ -173,6 +180,12 @@ #define THRESHOLD_3(x) ((x) << THRESHOLD_3_SHIFT) #define THRESHOLD_3_GET(x) (((x) & THRESHOLD_3_MASK) >> THRESHOLD_3_SHIFT) +#define SGE_CONM_CTRL 0x1094 +#define EGRTHRESHOLD_MASK 0x00003f00U +#define EGRTHRESHOLDshift 8 +#define EGRTHRESHOLD(x) ((x) << EGRTHRESHOLDshift) +#define EGRTHRESHOLD_GET(x) (((x) & EGRTHRESHOLD_MASK) >> EGRTHRESHOLDshift) + #define SGE_TIMER_VALUE_0_AND_1 0x10b8 #define TIMERVALUE0_MASK 0xffff0000U #define TIMERVALUE0_SHIFT 16 @@ -184,7 +197,25 @@ #define TIMERVALUE1_GET(x) (((x) & TIMERVALUE1_MASK) >> TIMERVALUE1_SHIFT) #define SGE_TIMER_VALUE_2_AND_3 0x10bc +#define TIMERVALUE2_MASK 0xffff0000U +#define TIMERVALUE2_SHIFT 16 +#define TIMERVALUE2(x) ((x) << TIMERVALUE2_SHIFT) +#define TIMERVALUE2_GET(x) (((x) & TIMERVALUE2_MASK) >> TIMERVALUE2_SHIFT) +#define TIMERVALUE3_MASK 0x0000ffffU +#define TIMERVALUE3_SHIFT 0 +#define TIMERVALUE3(x) ((x) << TIMERVALUE3_SHIFT) +#define TIMERVALUE3_GET(x) (((x) & TIMERVALUE3_MASK) >> TIMERVALUE3_SHIFT) + #define SGE_TIMER_VALUE_4_AND_5 0x10c0 +#define TIMERVALUE4_MASK 0xffff0000U +#define TIMERVALUE4_SHIFT 16 +#define TIMERVALUE4(x) ((x) << TIMERVALUE4_SHIFT) +#define TIMERVALUE4_GET(x) (((x) & TIMERVALUE4_MASK) >> TIMERVALUE4_SHIFT) +#define TIMERVALUE5_MASK 0x0000ffffU +#define TIMERVALUE5_SHIFT 0 +#define TIMERVALUE5(x) ((x) << TIMERVALUE5_SHIFT) +#define TIMERVALUE5_GET(x) (((x) & TIMERVALUE5_MASK) >> TIMERVALUE5_SHIFT) + #define SGE_DEBUG_INDEX 0x10cc #define SGE_DEBUG_DATA_HIGH 0x10d0 #define SGE_DEBUG_DATA_LOW 0x10d4 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index ad53f796b574..94e3484b7d93 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -401,6 +401,14 @@ enum fw_caps_config_fcoe { FW_CAPS_CONFIG_FCOE_TARGET = 0x00000002, }; +enum fw_memtype_cf { + FW_MEMTYPE_CF_EDC0 = 0x0, + FW_MEMTYPE_CF_EDC1 = 0x1, + FW_MEMTYPE_CF_EXTMEM = 0x2, + FW_MEMTYPE_CF_FLASH = 0x4, + FW_MEMTYPE_CF_INTERNAL = 0x5, +}; + struct fw_caps_config_cmd { __be32 op_to_write; __be32 retval_len16; @@ -416,10 +424,15 @@ struct fw_caps_config_cmd { __be16 r4; __be16 iscsicaps; __be16 fcoecaps; - __be32 r5; - __be64 r6; + __be32 cfcsum; + __be32 finiver; + __be32 finicsum; }; +#define FW_CAPS_CONFIG_CMD_CFVALID (1U << 27) +#define FW_CAPS_CONFIG_CMD_MEMTYPE_CF(x) ((x) << 24) +#define FW_CAPS_CONFIG_CMD_MEMADDR64K_CF(x) ((x) << 16) + /* * params command mnemonics */ @@ -451,6 +464,7 @@ enum fw_params_param_dev { FW_PARAMS_PARAM_DEV_INTVER_FCOE = 0x0A, FW_PARAMS_PARAM_DEV_FWREV = 0x0B, FW_PARAMS_PARAM_DEV_TPREV = 0x0C, + FW_PARAMS_PARAM_DEV_CF = 0x0D, }; /* @@ -492,6 +506,8 @@ enum fw_params_param_pfvf { FW_PARAMS_PARAM_PFVF_IQFLINT_END = 0x2A, FW_PARAMS_PARAM_PFVF_EQ_START = 0x2B, FW_PARAMS_PARAM_PFVF_EQ_END = 0x2C, + FW_PARAMS_PARAM_PFVF_ACTIVE_FILTER_START = 0x2D, + FW_PARAMS_PARAM_PFVF_ACTIVE_FILTER_END = 0x2E }; /* @@ -507,8 +523,16 @@ enum fw_params_param_dmaq { #define FW_PARAMS_MNEM(x) ((x) << 24) #define FW_PARAMS_PARAM_X(x) ((x) << 16) -#define FW_PARAMS_PARAM_Y(x) ((x) << 8) -#define FW_PARAMS_PARAM_Z(x) ((x) << 0) +#define FW_PARAMS_PARAM_Y_SHIFT 8 +#define FW_PARAMS_PARAM_Y_MASK 0xffU +#define FW_PARAMS_PARAM_Y(x) ((x) << FW_PARAMS_PARAM_Y_SHIFT) +#define FW_PARAMS_PARAM_Y_GET(x) (((x) >> FW_PARAMS_PARAM_Y_SHIFT) &\ + FW_PARAMS_PARAM_Y_MASK) +#define FW_PARAMS_PARAM_Z_SHIFT 0 +#define FW_PARAMS_PARAM_Z_MASK 0xffu +#define FW_PARAMS_PARAM_Z(x) ((x) << FW_PARAMS_PARAM_Z_SHIFT) +#define FW_PARAMS_PARAM_Z_GET(x) (((x) >> FW_PARAMS_PARAM_Z_SHIFT) &\ + FW_PARAMS_PARAM_Z_MASK) #define FW_PARAMS_PARAM_XYZ(x) ((x) << 0) #define FW_PARAMS_PARAM_YZ(x) ((x) << 0) @@ -1599,6 +1623,15 @@ struct fw_debug_cmd { } u; }; +#define FW_PCIE_FW_ERR (1U << 31) +#define FW_PCIE_FW_INIT (1U << 30) +#define FW_PCIE_FW_MASTER_VLD (1U << 15) +#define FW_PCIE_FW_MASTER_MASK 0x7 +#define FW_PCIE_FW_MASTER_SHIFT 12 +#define FW_PCIE_FW_MASTER(x) ((x) << FW_PCIE_FW_MASTER_SHIFT) +#define FW_PCIE_FW_MASTER_GET(x) (((x) >> FW_PCIE_FW_MASTER_SHIFT) & \ + FW_PCIE_FW_MASTER_MASK) + struct fw_hdr { u8 ver; u8 reserved1; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index 8877fbfefb63..f16745f4b36b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -2421,7 +2421,7 @@ int t4vf_sge_init(struct adapter *adapter) fl0, fl1); return -EINVAL; } - if ((sge_params->sge_control & RXPKTCPLMODE) == 0) { + if ((sge_params->sge_control & RXPKTCPLMODE_MASK) == 0) { dev_err(adapter->pdev_dev, "bad SGE CPL MODE\n"); return -EINVAL; } @@ -2431,7 +2431,8 @@ int t4vf_sge_init(struct adapter *adapter) */ if (fl1) FL_PG_ORDER = ilog2(fl1) - PAGE_SHIFT; - STAT_LEN = ((sge_params->sge_control & EGRSTATUSPAGESIZE) ? 128 : 64); + STAT_LEN = ((sge_params->sge_control & EGRSTATUSPAGESIZE_MASK) + ? 128 : 64); PKTSHIFT = PKTSHIFT_GET(sge_params->sge_control); FL_ALIGN = 1 << (INGPADBOUNDARY_GET(sge_params->sge_control) + SGE_INGPADBOUNDARY_SHIFT); -- cgit v1.2.3 From 636f9d371f70f22961fd598fe18380057518ca31 Mon Sep 17 00:00:00 2001 From: Vipul Pandya Date: Wed, 26 Sep 2012 02:39:39 +0000 Subject: cxgb4: Add support for T4 configuration file Starting with T4 firmware version 1.3.11.0 the firmware now supports device configuration via a Firmware Configuration File. The Firmware Configuration File was primarily developed in order to centralize all of the configuration, resource allocation, etc. for Unified Wire operation where multiple Physical / Virtual Function Drivers would be using a T4 adapter simultaneously. The Firmware Configuration file can live in three locations as shown below in order of precedence. 1) User defined configuration file: /lib/firmware/cxgb4/t4-config.txt 2) Factory Default configuration file written to FLASH within the manufacturing process. 3) Hardwired driver configuration. Signed-off-by: Jay Hernandez Signed-off-by: Vipul Pandya Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 15 + drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 570 ++++++++++++++++++++---- drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h | 2 + drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 392 +++++++++++++++- drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 37 +- drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 37 +- 6 files changed, 920 insertions(+), 133 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index ae040cf255a4..777cbb4f62bb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -211,6 +211,9 @@ struct tp_err_stats { struct tp_params { unsigned int ntxchan; /* # of Tx channels */ unsigned int tre; /* log2 of core clocks per TP tick */ + + uint32_t dack_re; /* DACK timer resolution */ + unsigned short tx_modq[NCHAN]; /* channel to modulation queue map */ }; struct vpd_params { @@ -519,6 +522,8 @@ struct adapter { struct net_device *port[MAX_NPORTS]; u8 chan_map[NCHAN]; /* channel -> port map */ + unsigned int l2t_start; + unsigned int l2t_end; struct l2t_data *l2t; void *uld_handle[CXGB4_ULD_MAX]; struct list_head list_node; @@ -683,7 +688,9 @@ int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port); int t4_memory_write(struct adapter *adap, int mtype, u32 addr, u32 len, __be32 *buf); int t4_seeprom_wp(struct adapter *adapter, bool enable); +int get_vpd_params(struct adapter *adapter, struct vpd_params *p); int t4_load_fw(struct adapter *adapter, const u8 *fw_data, unsigned int size); +unsigned int t4_flash_cfg_addr(struct adapter *adapter); int t4_check_fw_version(struct adapter *adapter); int t4_prep_adapter(struct adapter *adapter); int t4_port_init(struct adapter *adap, int mbox, int pf, int vf); @@ -698,6 +705,8 @@ int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p); void t4_read_mtu_tbl(struct adapter *adap, u16 *mtus, u8 *mtu_log); +void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr, + unsigned int mask, unsigned int val); void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, struct tp_tcp_stats *v6); void t4_load_mtus(struct adapter *adap, const unsigned short *mtus, @@ -713,6 +722,12 @@ int t4_fw_hello(struct adapter *adap, unsigned int mbox, unsigned int evt_mbox, int t4_fw_bye(struct adapter *adap, unsigned int mbox); int t4_early_init(struct adapter *adap, unsigned int mbox); int t4_fw_reset(struct adapter *adap, unsigned int mbox, int reset); +int t4_fw_config_file(struct adapter *adap, unsigned int mbox, + unsigned int mtype, unsigned int maddr, + u32 *finiver, u32 *finicsum, u32 *cfcsum); +int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, + unsigned int cache_line_size); +int t4_fw_initialize(struct adapter *adap, unsigned int mbox); int t4_query_params(struct adapter *adap, unsigned int mbox, unsigned int pf, unsigned int vf, unsigned int nparams, const u32 *params, u32 *val); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 34d510dd56a8..cb3e663c30dc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -193,6 +193,7 @@ static DEFINE_PCI_DEVICE_TABLE(cxgb4_pci_tbl) = { }; #define FW_FNAME "cxgb4/t4fw.bin" +#define FW_CFNAME "cxgb4/t4-config.txt" MODULE_DESCRIPTION(DRV_DESC); MODULE_AUTHOR("Chelsio Communications"); @@ -201,6 +202,17 @@ MODULE_VERSION(DRV_VERSION); MODULE_DEVICE_TABLE(pci, cxgb4_pci_tbl); MODULE_FIRMWARE(FW_FNAME); +/* + * Normally we're willing to become the firmware's Master PF but will be happy + * if another PF has already become the Master and initialized the adapter. + * Setting "force_init" will cause this driver to forcibly establish itself as + * the Master PF and initialize the adapter. + */ +static uint force_init; + +module_param(force_init, uint, 0644); +MODULE_PARM_DESC(force_init, "Forcibly become Master PF and initialize adapter"); + static int dflt_msg_enable = DFLT_MSG_ENABLE; module_param(dflt_msg_enable, int, 0644); @@ -236,6 +248,20 @@ module_param_array(intr_cnt, uint, NULL, 0644); MODULE_PARM_DESC(intr_cnt, "thresholds 1..3 for queue interrupt packet counters"); +/* + * Normally we tell the chip to deliver Ingress Packets into our DMA buffers + * offset by 2 bytes in order to have the IP headers line up on 4-byte + * boundaries. This is a requirement for many architectures which will throw + * a machine check fault if an attempt is made to access one of the 4-byte IP + * header fields on a non-4-byte boundary. And it's a major performance issue + * even on some architectures which allow it like some implementations of the + * x86 ISA. However, some architectures don't mind this and for some very + * edge-case performance sensitive applications (like forwarding large volumes + * of small packets), setting this DMA offset to 0 will decrease the number of + * PCI-E Bus transfers enough to measurably affect performance. + */ +static int rx_dma_offset = 2; + static bool vf_acls; #ifdef CONFIG_PCI_IOV @@ -3076,6 +3102,10 @@ static void setup_memwin(struct adapter *adap) t4_write_reg(adap, PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN, 2), (bar0 + MEMWIN2_BASE) | BIR(0) | WINDOW(ilog2(MEMWIN2_APERTURE) - 10)); +} + +static void setup_memwin_rdma(struct adapter *adap) +{ if (adap->vres.ocq.size) { unsigned int start, sz_kb; @@ -3153,6 +3183,232 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c) */ #define MAX_ATIDS 8192U +/* + * Phase 0 of initialization: contact FW, obtain config, perform basic init. + * + * If the firmware we're dealing with has Configuration File support, then + * we use that to perform all configuration + */ + +/* + * Tweak configuration based on module parameters, etc. Most of these have + * defaults assigned to them by Firmware Configuration Files (if we're using + * them) but need to be explicitly set if we're using hard-coded + * initialization. But even in the case of using Firmware Configuration + * Files, we'd like to expose the ability to change these via module + * parameters so these are essentially common tweaks/settings for + * Configuration Files and hard-coded initialization ... + */ +static int adap_init0_tweaks(struct adapter *adapter) +{ + /* + * Fix up various Host-Dependent Parameters like Page Size, Cache + * Line Size, etc. The firmware default is for a 4KB Page Size and + * 64B Cache Line Size ... + */ + t4_fixup_host_params(adapter, PAGE_SIZE, L1_CACHE_BYTES); + + /* + * Process module parameters which affect early initialization. + */ + if (rx_dma_offset != 2 && rx_dma_offset != 0) { + dev_err(&adapter->pdev->dev, + "Ignoring illegal rx_dma_offset=%d, using 2\n", + rx_dma_offset); + rx_dma_offset = 2; + } + t4_set_reg_field(adapter, SGE_CONTROL, + PKTSHIFT_MASK, + PKTSHIFT(rx_dma_offset)); + + /* + * Don't include the "IP Pseudo Header" in CPL_RX_PKT checksums: Linux + * adds the pseudo header itself. + */ + t4_tp_wr_bits_indirect(adapter, TP_INGRESS_CONFIG, + CSUM_HAS_PSEUDO_HDR, 0); + + return 0; +} + +/* + * Attempt to initialize the adapter via a Firmware Configuration File. + */ +static int adap_init0_config(struct adapter *adapter, int reset) +{ + struct fw_caps_config_cmd caps_cmd; + const struct firmware *cf; + unsigned long mtype = 0, maddr = 0; + u32 finiver, finicsum, cfcsum; + int ret, using_flash; + + /* + * Reset device if necessary. + */ + if (reset) { + ret = t4_fw_reset(adapter, adapter->mbox, + PIORSTMODE | PIORST); + if (ret < 0) + goto bye; + } + + /* + * If we have a T4 configuration file under /lib/firmware/cxgb4/, + * then use that. Otherwise, use the configuration file stored + * in the adapter flash ... + */ + ret = request_firmware(&cf, FW_CFNAME, adapter->pdev_dev); + if (ret < 0) { + using_flash = 1; + mtype = FW_MEMTYPE_CF_FLASH; + maddr = t4_flash_cfg_addr(adapter); + } else { + u32 params[7], val[7]; + + using_flash = 0; + if (cf->size >= FLASH_CFG_MAX_SIZE) + ret = -ENOMEM; + else { + params[0] = (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_CF)); + ret = t4_query_params(adapter, adapter->mbox, + adapter->fn, 0, 1, params, val); + if (ret == 0) { + /* + * For t4_memory_write() below addresses and + * sizes have to be in terms of multiples of 4 + * bytes. So, if the Configuration File isn't + * a multiple of 4 bytes in length we'll have + * to write that out separately since we can't + * guarantee that the bytes following the + * residual byte in the buffer returned by + * request_firmware() are zeroed out ... + */ + size_t resid = cf->size & 0x3; + size_t size = cf->size & ~0x3; + __be32 *data = (__be32 *)cf->data; + + mtype = FW_PARAMS_PARAM_Y_GET(val[0]); + maddr = FW_PARAMS_PARAM_Z_GET(val[0]) << 16; + + ret = t4_memory_write(adapter, mtype, maddr, + size, data); + if (ret == 0 && resid != 0) { + union { + __be32 word; + char buf[4]; + } last; + int i; + + last.word = data[size >> 2]; + for (i = resid; i < 4; i++) + last.buf[i] = 0; + ret = t4_memory_write(adapter, mtype, + maddr + size, + 4, &last.word); + } + } + } + + release_firmware(cf); + if (ret) + goto bye; + } + + /* + * Issue a Capability Configuration command to the firmware to get it + * to parse the Configuration File. We don't use t4_fw_config_file() + * because we want the ability to modify various features after we've + * processed the configuration file ... + */ + memset(&caps_cmd, 0, sizeof(caps_cmd)); + caps_cmd.op_to_write = + htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) | + FW_CMD_REQUEST | + FW_CMD_READ); + caps_cmd.retval_len16 = + htonl(FW_CAPS_CONFIG_CMD_CFVALID | + FW_CAPS_CONFIG_CMD_MEMTYPE_CF(mtype) | + FW_CAPS_CONFIG_CMD_MEMADDR64K_CF(maddr >> 16) | + FW_LEN16(caps_cmd)); + ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd), + &caps_cmd); + if (ret < 0) + goto bye; + + finiver = ntohl(caps_cmd.finiver); + finicsum = ntohl(caps_cmd.finicsum); + cfcsum = ntohl(caps_cmd.cfcsum); + if (finicsum != cfcsum) + dev_warn(adapter->pdev_dev, "Configuration File checksum "\ + "mismatch: [fini] csum=%#x, computed csum=%#x\n", + finicsum, cfcsum); + + /* + * If we're a pure NIC driver then disable all offloading facilities. + * This will allow the firmware to optimize aspects of the hardware + * configuration which will result in improved performance. + */ + caps_cmd.ofldcaps = 0; + caps_cmd.iscsicaps = 0; + caps_cmd.rdmacaps = 0; + caps_cmd.fcoecaps = 0; + + /* + * And now tell the firmware to use the configuration we just loaded. + */ + caps_cmd.op_to_write = + htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) | + FW_CMD_REQUEST | + FW_CMD_WRITE); + caps_cmd.retval_len16 = htonl(FW_LEN16(caps_cmd)); + ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd), + NULL); + if (ret < 0) + goto bye; + + /* + * Tweak configuration based on system architecture, module + * parameters, etc. + */ + ret = adap_init0_tweaks(adapter); + if (ret < 0) + goto bye; + + /* + * And finally tell the firmware to initialize itself using the + * parameters from the Configuration File. + */ + ret = t4_fw_initialize(adapter, adapter->mbox); + if (ret < 0) + goto bye; + + /* + * Return successfully and note that we're operating with parameters + * not supplied by the driver, rather than from hard-wired + * initialization constants burried in the driver. + */ + adapter->flags |= USING_SOFT_PARAMS; + dev_info(adapter->pdev_dev, "Successfully configured using Firmware "\ + "Configuration File %s, version %#x, computed checksum %#x\n", + (using_flash + ? "in device FLASH" + : "/lib/firmware/" FW_CFNAME), + finiver, cfcsum); + return 0; + + /* + * Something bad happened. Return the error ... (If the "error" + * is that there's no Configuration File on the adapter we don't + * want to issue a warning since this is fairly common.) + */ +bye: + if (ret != -ENOENT) + dev_warn(adapter->pdev_dev, "Configuration file error %d\n", + -ret); + return ret; +} + /* * Phase 0 of initialization: contact FW, obtain config, perform basic init. */ @@ -3162,72 +3418,197 @@ static int adap_init0(struct adapter *adap) u32 v, port_vec; enum dev_state state; u32 params[7], val[7]; - struct fw_caps_config_cmd c; + int reset = 1, j; - ret = t4_check_fw_version(adap); - if (ret == -EINVAL || ret > 0) { - if (upgrade_fw(adap) >= 0) /* recache FW version */ - ret = t4_check_fw_version(adap); - } - if (ret < 0) - return ret; - - /* contact FW, request master */ - ret = t4_fw_hello(adap, adap->fn, adap->fn, MASTER_MUST, &state); + /* + * Contact FW, advertising Master capability (and potentially forcing + * ourselves as the Master PF if our module parameter force_init is + * set). + */ + ret = t4_fw_hello(adap, adap->mbox, adap->fn, + force_init ? MASTER_MUST : MASTER_MAY, + &state); if (ret < 0) { dev_err(adap->pdev_dev, "could not connect to FW, error %d\n", ret); return ret; } + if (ret == adap->mbox) + adap->flags |= MASTER_PF; + if (force_init && state == DEV_STATE_INIT) + state = DEV_STATE_UNINIT; - /* reset device */ - ret = t4_fw_reset(adap, adap->fn, PIORSTMODE | PIORST); - if (ret < 0) - goto bye; - - for (v = 0; v < SGE_NTIMERS - 1; v++) - adap->sge.timer_val[v] = min(intr_holdoff[v], MAX_SGE_TIMERVAL); - adap->sge.timer_val[SGE_NTIMERS - 1] = MAX_SGE_TIMERVAL; - adap->sge.counter_val[0] = 1; - for (v = 1; v < SGE_NCOUNTERS; v++) - adap->sge.counter_val[v] = min(intr_cnt[v - 1], - THRESHOLD_3_MASK); -#define FW_PARAM_DEV(param) \ - (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | \ - FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_##param)) + /* + * If we're the Master PF Driver and the device is uninitialized, + * then let's consider upgrading the firmware ... (We always want + * to check the firmware version number in order to A. get it for + * later reporting and B. to warn if the currently loaded firmware + * is excessively mismatched relative to the driver.) + */ + ret = t4_check_fw_version(adap); + if ((adap->flags & MASTER_PF) && state != DEV_STATE_INIT) { + if (ret == -EINVAL || ret > 0) { + if (upgrade_fw(adap) >= 0) { + /* + * Note that the chip was reset as part of the + * firmware upgrade so we don't reset it again + * below and grab the new firmware version. + */ + reset = 0; + ret = t4_check_fw_version(adap); + } + } + if (ret < 0) + return ret; + } - params[0] = FW_PARAM_DEV(CCLK); - ret = t4_query_params(adap, adap->fn, adap->fn, 0, 1, params, val); + /* + * Grab VPD parameters. This should be done after we establish a + * connection to the firmware since some of the VPD parameters + * (notably the Core Clock frequency) are retrieved via requests to + * the firmware. On the other hand, we need these fairly early on + * so we do this right after getting ahold of the firmware. + */ + ret = get_vpd_params(adap, &adap->params.vpd); if (ret < 0) goto bye; - adap->params.vpd.cclk = val[0]; - ret = adap_init1(adap, &c); + /* + * Find out what ports are available to us. + */ + v = + FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_PORTVEC); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1, &v, &port_vec); if (ret < 0) goto bye; + adap->params.nports = hweight32(port_vec); + adap->params.portvec = port_vec; + + /* + * If the firmware is initialized already (and we're not forcing a + * master initialization), note that we're living with existing + * adapter parameters. Otherwise, it's time to try initializing the + * adapter ... + */ + if (state == DEV_STATE_INIT) { + dev_info(adap->pdev_dev, "Coming up as %s: "\ + "Adapter already initialized\n", + adap->flags & MASTER_PF ? "MASTER" : "SLAVE"); + adap->flags |= USING_SOFT_PARAMS; + } else { + dev_info(adap->pdev_dev, "Coming up as MASTER: "\ + "Initializing adapter\n"); + /* + * Find out whether we're dealing with a version of + * the firmware which has configuration file support. + */ + params[0] = (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_CF)); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1, + params, val); + + /* + * If the firmware doesn't support Configuration + * Files warn user and exit, + */ + if (ret < 0) + dev_warn(adap->pdev_dev, "Firmware doesn't support "\ + "configuration file.\n"); + else { + /* + * The firmware provides us with a memory + * buffer where we can load a Configuration + * File from the host if we want to override + * the Configuration File in flash. + */ + + ret = adap_init0_config(adap, reset); + if (ret == -ENOENT) { + dev_info(adap->pdev_dev, + "No Configuration File present " + "on adapter.\n"); + } + } + if (ret < 0) { + dev_err(adap->pdev_dev, + "could not initialize adapter, error %d\n", + -ret); + goto bye; + } + } + + /* + * If we're living with non-hard-coded parameters (either from a + * Firmware Configuration File or values programmed by a different PF + * Driver), give the SGE code a chance to pull in anything that it + * needs ... Note that this must be called after we retrieve our VPD + * parameters in order to know how to convert core ticks to seconds. + */ + if (adap->flags & USING_SOFT_PARAMS) { + ret = t4_sge_init(adap); + if (ret < 0) + goto bye; + } + + /* + * Grab some of our basic fundamental operating parameters. + */ +#define FW_PARAM_DEV(param) \ + (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | \ + FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_##param)) + #define FW_PARAM_PFVF(param) \ - (FW_PARAMS_MNEM(FW_PARAMS_MNEM_PFVF) | \ - FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_PFVF_##param) | \ - FW_PARAMS_PARAM_Y(adap->fn)) + FW_PARAMS_MNEM(FW_PARAMS_MNEM_PFVF) | \ + FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_PFVF_##param)| \ + FW_PARAMS_PARAM_Y(0) | \ + FW_PARAMS_PARAM_Z(0) - params[0] = FW_PARAM_DEV(PORTVEC); + params[0] = FW_PARAM_PFVF(EQ_START); params[1] = FW_PARAM_PFVF(L2T_START); params[2] = FW_PARAM_PFVF(L2T_END); params[3] = FW_PARAM_PFVF(FILTER_START); params[4] = FW_PARAM_PFVF(FILTER_END); params[5] = FW_PARAM_PFVF(IQFLINT_START); - params[6] = FW_PARAM_PFVF(EQ_START); - ret = t4_query_params(adap, adap->fn, adap->fn, 0, 7, params, val); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, params, val); if (ret < 0) goto bye; - port_vec = val[0]; + adap->sge.egr_start = val[0]; + adap->l2t_start = val[1]; + adap->l2t_end = val[2]; adap->tids.ftid_base = val[3]; adap->tids.nftids = val[4] - val[3] + 1; adap->sge.ingr_start = val[5]; - adap->sge.egr_start = val[6]; - if (c.ofldcaps) { + /* query params related to active filter region */ + params[0] = FW_PARAM_PFVF(ACTIVE_FILTER_START); + params[1] = FW_PARAM_PFVF(ACTIVE_FILTER_END); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val); + /* If Active filter size is set we enable establishing + * offload connection through firmware work request + */ + if ((val[0] != val[1]) && (ret >= 0)) { + adap->flags |= FW_OFLD_CONN; + adap->tids.aftid_base = val[0]; + adap->tids.aftid_end = val[1]; + } + +#ifdef CONFIG_CHELSIO_T4_OFFLOAD + /* + * Get device capabilities so we can determine what resources we need + * to manage. + */ + memset(&caps_cmd, 0, sizeof(caps_cmd)); + caps_cmd.op_to_write = htonl(V_FW_CMD_OP(FW_CAPS_CONFIG_CMD) | + F_FW_CMD_REQUEST | F_FW_CMD_READ); + caps_cmd.cfvalid_to_len16 = htonl(FW_LEN16(caps_cmd)); + ret = t4_wr_mbox(adap, adap->mbox, &caps_cmd, sizeof(caps_cmd), + &caps_cmd); + if (ret < 0) + goto bye; + + if (caps_cmd.toecaps) { /* query offload-related parameters */ params[0] = FW_PARAM_DEV(NTID); params[1] = FW_PARAM_PFVF(SERVER_START); @@ -3235,28 +3616,55 @@ static int adap_init0(struct adapter *adap) params[3] = FW_PARAM_PFVF(TDDP_START); params[4] = FW_PARAM_PFVF(TDDP_END); params[5] = FW_PARAM_DEV(FLOWC_BUFFIFO_SZ); - ret = t4_query_params(adap, adap->fn, adap->fn, 0, 6, params, - val); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, + params, val); if (ret < 0) goto bye; adap->tids.ntids = val[0]; adap->tids.natids = min(adap->tids.ntids / 2, MAX_ATIDS); adap->tids.stid_base = val[1]; adap->tids.nstids = val[2] - val[1] + 1; + /* + * Setup server filter region. Divide the availble filter + * region into two parts. Regular filters get 1/3rd and server + * filters get 2/3rd part. This is only enabled if workarond + * path is enabled. + * 1. For regular filters. + * 2. Server filter: This are special filters which are used + * to redirect SYN packets to offload queue. + */ + if (adap->flags & FW_OFLD_CONN && !is_bypass(adap)) { + adap->tids.sftid_base = adap->tids.ftid_base + + DIV_ROUND_UP(adap->tids.nftids, 3); + adap->tids.nsftids = adap->tids.nftids - + DIV_ROUND_UP(adap->tids.nftids, 3); + adap->tids.nftids = adap->tids.sftid_base - + adap->tids.ftid_base; + } adap->vres.ddp.start = val[3]; adap->vres.ddp.size = val[4] - val[3] + 1; adap->params.ofldq_wr_cred = val[5]; + + params[0] = FW_PARAM_PFVF(ETHOFLD_START); + params[1] = FW_PARAM_PFVF(ETHOFLD_END); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, + params, val); + if ((val[0] != val[1]) && (ret >= 0)) { + adap->tids.uotid_base = val[0]; + adap->tids.nuotids = val[1] - val[0] + 1; + } + adap->params.offload = 1; } - if (c.rdmacaps) { + if (caps_cmd.rdmacaps) { params[0] = FW_PARAM_PFVF(STAG_START); params[1] = FW_PARAM_PFVF(STAG_END); params[2] = FW_PARAM_PFVF(RQ_START); params[3] = FW_PARAM_PFVF(RQ_END); params[4] = FW_PARAM_PFVF(PBL_START); params[5] = FW_PARAM_PFVF(PBL_END); - ret = t4_query_params(adap, adap->fn, adap->fn, 0, 6, params, - val); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, + params, val); if (ret < 0) goto bye; adap->vres.stag.start = val[0]; @@ -3272,8 +3680,7 @@ static int adap_init0(struct adapter *adap) params[3] = FW_PARAM_PFVF(CQ_END); params[4] = FW_PARAM_PFVF(OCQ_START); params[5] = FW_PARAM_PFVF(OCQ_END); - ret = t4_query_params(adap, adap->fn, adap->fn, 0, 6, params, - val); + ret = t4_query_params(adap, 0, 0, 0, 6, params, val); if (ret < 0) goto bye; adap->vres.qp.start = val[0]; @@ -3283,11 +3690,11 @@ static int adap_init0(struct adapter *adap) adap->vres.ocq.start = val[4]; adap->vres.ocq.size = val[5] - val[4] + 1; } - if (c.iscsicaps) { + if (caps_cmd.iscsicaps) { params[0] = FW_PARAM_PFVF(ISCSI_START); params[1] = FW_PARAM_PFVF(ISCSI_END); - ret = t4_query_params(adap, adap->fn, adap->fn, 0, 2, params, - val); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, + params, val); if (ret < 0) goto bye; adap->vres.iscsi.start = val[0]; @@ -3295,63 +3702,33 @@ static int adap_init0(struct adapter *adap) } #undef FW_PARAM_PFVF #undef FW_PARAM_DEV +#endif /* CONFIG_CHELSIO_T4_OFFLOAD */ - adap->params.nports = hweight32(port_vec); - adap->params.portvec = port_vec; - adap->flags |= FW_OK; - - /* These are finalized by FW initialization, load their values now */ + /* + * These are finalized by FW initialization, load their values now. + */ v = t4_read_reg(adap, TP_TIMER_RESOLUTION); adap->params.tp.tre = TIMERRESOLUTION_GET(v); + adap->params.tp.dack_re = DELAYEDACKRESOLUTION_GET(v); t4_read_mtu_tbl(adap, adap->params.mtus, NULL); t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd, adap->params.b_wnd); -#ifdef CONFIG_PCI_IOV - /* - * Provision resource limits for Virtual Functions. We currently - * grant them all the same static resource limits except for the Port - * Access Rights Mask which we're assigning based on the PF. All of - * the static provisioning stuff for both the PF and VF really needs - * to be managed in a persistent manner for each device which the - * firmware controls. - */ - { - int pf, vf; - - for (pf = 0; pf < ARRAY_SIZE(num_vf); pf++) { - if (num_vf[pf] <= 0) - continue; - - /* VF numbering starts at 1! */ - for (vf = 1; vf <= num_vf[pf]; vf++) { - ret = t4_cfg_pfvf(adap, adap->fn, pf, vf, - VFRES_NEQ, VFRES_NETHCTRL, - VFRES_NIQFLINT, VFRES_NIQ, - VFRES_TC, VFRES_NVI, - FW_PFVF_CMD_CMASK_MASK, - pfvfres_pmask(adap, pf, vf), - VFRES_NEXACTF, - VFRES_R_CAPS, VFRES_WX_CAPS); - if (ret < 0) - dev_warn(adap->pdev_dev, "failed to " - "provision pf/vf=%d/%d; " - "err=%d\n", pf, vf, ret); - } - } - } -#endif + /* MODQ_REQ_MAP defaults to setting queues 0-3 to chan 0-3 */ + for (j = 0; j < NCHAN; j++) + adap->params.tp.tx_modq[j] = j; - setup_memwin(adap); + adap->flags |= FW_OK; return 0; /* - * If a command timed out or failed with EIO FW does not operate within - * its spec or something catastrophic happened to HW/FW, stop issuing - * commands. + * Something bad happened. If a command timed out or failed with EIO + * FW does not operate within its spec or something catastrophic + * happened to HW/FW, stop issuing commands. */ -bye: if (ret != -ETIMEDOUT && ret != -EIO) - t4_fw_bye(adap, adap->fn); +bye: + if (ret != -ETIMEDOUT && ret != -EIO) + t4_fw_bye(adap, adap->mbox); return ret; } @@ -3814,7 +4191,9 @@ static int __devinit init_one(struct pci_dev *pdev, err = t4_prep_adapter(adapter); if (err) goto out_unmap_bar; + setup_memwin(adapter); err = adap_init0(adapter); + setup_memwin_rdma(adapter); if (err) goto out_unmap_bar; @@ -3956,8 +4335,11 @@ static void __devexit remove_one(struct pci_dev *pdev) { struct adapter *adapter = pci_get_drvdata(pdev); +#ifdef CONFIG_PCI_IOV pci_disable_sriov(pdev); +#endif + if (adapter) { int i; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h index d79980c5fc63..1b899fea1a91 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h @@ -100,6 +100,8 @@ struct tid_info { unsigned int nftids; unsigned int ftid_base; + unsigned int aftid_base; + unsigned int aftid_end; spinlock_t atid_lock ____cacheline_aligned_in_smp; union aopen_entry *afree; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 259d0dcb0089..419432d42049 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -492,8 +492,9 @@ int t4_seeprom_wp(struct adapter *adapter, bool enable) * * Reads card parameters stored in VPD EEPROM. */ -static int get_vpd_params(struct adapter *adapter, struct vpd_params *p) +int get_vpd_params(struct adapter *adapter, struct vpd_params *p) { + u32 cclk_param, cclk_val; int i, ret; int ec, sn; u8 vpd[VPD_LEN], csum; @@ -555,6 +556,19 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p) i = pci_vpd_info_field_size(vpd + sn - PCI_VPD_INFO_FLD_HDR_SIZE); memcpy(p->sn, vpd + sn, min(i, SERNUM_LEN)); strim(p->sn); + + /* + * Ask firmware for the Core Clock since it knows how to translate the + * Reference Clock ('V2') VPD field into a Core Clock value ... + */ + cclk_param = (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_CCLK)); + ret = t4_query_params(adapter, adapter->mbox, 0, 0, + 1, &cclk_param, &cclk_val); + if (ret) + return ret; + p->cclk = cclk_val; + return 0; } @@ -854,6 +868,77 @@ static int t4_flash_erase_sectors(struct adapter *adapter, int start, int end) return ret; } +/** + * t4_flash_cfg_addr - return the address of the flash configuration file + * @adapter: the adapter + * + * Return the address within the flash where the Firmware Configuration + * File is stored. + */ +unsigned int t4_flash_cfg_addr(struct adapter *adapter) +{ + if (adapter->params.sf_size == 0x100000) + return FLASH_FPGA_CFG_START; + else + return FLASH_CFG_START; +} + +/** + * t4_load_cfg - download config file + * @adap: the adapter + * @cfg_data: the cfg text file to write + * @size: text file size + * + * Write the supplied config text file to the card's serial flash. + */ +int t4_load_cfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) +{ + int ret, i, n; + unsigned int addr; + unsigned int flash_cfg_start_sec; + unsigned int sf_sec_size = adap->params.sf_size / adap->params.sf_nsec; + + addr = t4_flash_cfg_addr(adap); + flash_cfg_start_sec = addr / SF_SEC_SIZE; + + if (size > FLASH_CFG_MAX_SIZE) { + dev_err(adap->pdev_dev, "cfg file too large, max is %u bytes\n", + FLASH_CFG_MAX_SIZE); + return -EFBIG; + } + + i = DIV_ROUND_UP(FLASH_CFG_MAX_SIZE, /* # of sectors spanned */ + sf_sec_size); + ret = t4_flash_erase_sectors(adap, flash_cfg_start_sec, + flash_cfg_start_sec + i - 1); + /* + * If size == 0 then we're simply erasing the FLASH sectors associated + * with the on-adapter Firmware Configuration File. + */ + if (ret || size == 0) + goto out; + + /* this will write to the flash up to SF_PAGE_SIZE at a time */ + for (i = 0; i < size; i += SF_PAGE_SIZE) { + if ((size - i) < SF_PAGE_SIZE) + n = size - i; + else + n = SF_PAGE_SIZE; + ret = t4_write_flash(adap, addr, n, cfg_data); + if (ret) + goto out; + + addr += SF_PAGE_SIZE; + cfg_data += SF_PAGE_SIZE; + } + +out: + if (ret) + dev_err(adap->pdev_dev, "config file %s failed %d\n", + (size == 0 ? "clear" : "download"), ret); + return ret; +} + /** * t4_load_fw - download firmware * @adap: the adapter @@ -1853,6 +1938,23 @@ void t4_read_mtu_tbl(struct adapter *adap, u16 *mtus, u8 *mtu_log) } } +/** + * t4_tp_wr_bits_indirect - set/clear bits in an indirect TP register + * @adap: the adapter + * @addr: the indirect TP register address + * @mask: specifies the field within the register to modify + * @val: new value for the field + * + * Sets a field of an indirect TP register to the given value. + */ +void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr, + unsigned int mask, unsigned int val) +{ + t4_write_reg(adap, TP_PIO_ADDR, addr); + val |= t4_read_reg(adap, TP_PIO_DATA) & ~mask; + t4_write_reg(adap, TP_PIO_DATA, val); +} + /** * init_cong_ctrl - initialize congestion control parameters * @a: the alpha values for congestion control @@ -2137,9 +2239,9 @@ int t4_fwaddrspace_write(struct adapter *adap, unsigned int mbox, struct fw_ldst_cmd c; memset(&c, 0, sizeof(c)); - c.op_to_addrspace = htonl(V_FW_CMD_OP(FW_LDST_CMD) | F_FW_CMD_REQUEST | - F_FW_CMD_WRITE | - V_FW_LDST_CMD_ADDRSPACE(FW_LDST_ADDRSPC_FIRMWARE)); + c.op_to_addrspace = htonl(FW_CMD_OP(FW_LDST_CMD) | FW_CMD_REQUEST | + FW_CMD_WRITE | + FW_LDST_CMD_ADDRSPACE(FW_LDST_ADDRSPC_FIRMWARE)); c.cycles_to_len16 = htonl(FW_LEN16(c)); c.u.addrval.addr = htonl(addr); c.u.addrval.val = htonl(val); @@ -2239,39 +2341,129 @@ int t4_mdio_wr(struct adapter *adap, unsigned int mbox, unsigned int phy_addr, } /** - * t4_fw_hello - establish communication with FW - * @adap: the adapter - * @mbox: mailbox to use for the FW command - * @evt_mbox: mailbox to receive async FW events - * @master: specifies the caller's willingness to be the device master - * @state: returns the current device state + * t4_fw_hello - establish communication with FW + * @adap: the adapter + * @mbox: mailbox to use for the FW command + * @evt_mbox: mailbox to receive async FW events + * @master: specifies the caller's willingness to be the device master + * @state: returns the current device state (if non-NULL) * - * Issues a command to establish communication with FW. + * Issues a command to establish communication with FW. Returns either + * an error (negative integer) or the mailbox of the Master PF. */ int t4_fw_hello(struct adapter *adap, unsigned int mbox, unsigned int evt_mbox, enum dev_master master, enum dev_state *state) { int ret; struct fw_hello_cmd c; + u32 v; + unsigned int master_mbox; + int retries = FW_CMD_HELLO_RETRIES; +retry: + memset(&c, 0, sizeof(c)); INIT_CMD(c, HELLO, WRITE); c.err_to_mbasyncnot = htonl( FW_HELLO_CMD_MASTERDIS(master == MASTER_CANT) | FW_HELLO_CMD_MASTERFORCE(master == MASTER_MUST) | - FW_HELLO_CMD_MBMASTER(master == MASTER_MUST ? mbox : 0xff) | - FW_HELLO_CMD_MBASYNCNOT(evt_mbox)); + FW_HELLO_CMD_MBMASTER(master == MASTER_MUST ? mbox : + FW_HELLO_CMD_MBMASTER_MASK) | + FW_HELLO_CMD_MBASYNCNOT(evt_mbox) | + FW_HELLO_CMD_STAGE(fw_hello_cmd_stage_os) | + FW_HELLO_CMD_CLEARINIT); + /* + * Issue the HELLO command to the firmware. If it's not successful + * but indicates that we got a "busy" or "timeout" condition, retry + * the HELLO until we exhaust our retry limit. + */ ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), &c); - if (ret == 0 && state) { - u32 v = ntohl(c.err_to_mbasyncnot); - if (v & FW_HELLO_CMD_INIT) - *state = DEV_STATE_INIT; - else if (v & FW_HELLO_CMD_ERR) + if (ret < 0) { + if ((ret == -EBUSY || ret == -ETIMEDOUT) && retries-- > 0) + goto retry; + return ret; + } + + v = ntohl(c.err_to_mbasyncnot); + master_mbox = FW_HELLO_CMD_MBMASTER_GET(v); + if (state) { + if (v & FW_HELLO_CMD_ERR) *state = DEV_STATE_ERR; + else if (v & FW_HELLO_CMD_INIT) + *state = DEV_STATE_INIT; else *state = DEV_STATE_UNINIT; } - return ret; + + /* + * If we're not the Master PF then we need to wait around for the + * Master PF Driver to finish setting up the adapter. + * + * Note that we also do this wait if we're a non-Master-capable PF and + * there is no current Master PF; a Master PF may show up momentarily + * and we wouldn't want to fail pointlessly. (This can happen when an + * OS loads lots of different drivers rapidly at the same time). In + * this case, the Master PF returned by the firmware will be + * FW_PCIE_FW_MASTER_MASK so the test below will work ... + */ + if ((v & (FW_HELLO_CMD_ERR|FW_HELLO_CMD_INIT)) == 0 && + master_mbox != mbox) { + int waiting = FW_CMD_HELLO_TIMEOUT; + + /* + * Wait for the firmware to either indicate an error or + * initialized state. If we see either of these we bail out + * and report the issue to the caller. If we exhaust the + * "hello timeout" and we haven't exhausted our retries, try + * again. Otherwise bail with a timeout error. + */ + for (;;) { + u32 pcie_fw; + + msleep(50); + waiting -= 50; + + /* + * If neither Error nor Initialialized are indicated + * by the firmware keep waiting till we exaust our + * timeout ... and then retry if we haven't exhausted + * our retries ... + */ + pcie_fw = t4_read_reg(adap, MA_PCIE_FW); + if (!(pcie_fw & (FW_PCIE_FW_ERR|FW_PCIE_FW_INIT))) { + if (waiting <= 0) { + if (retries-- > 0) + goto retry; + + return -ETIMEDOUT; + } + continue; + } + + /* + * We either have an Error or Initialized condition + * report errors preferentially. + */ + if (state) { + if (pcie_fw & FW_PCIE_FW_ERR) + *state = DEV_STATE_ERR; + else if (pcie_fw & FW_PCIE_FW_INIT) + *state = DEV_STATE_INIT; + } + + /* + * If we arrived before a Master PF was selected and + * there's not a valid Master PF, grab its identity + * for our caller. + */ + if (master_mbox == FW_PCIE_FW_MASTER_MASK && + (pcie_fw & FW_PCIE_FW_MASTER_VLD)) + master_mbox = FW_PCIE_FW_MASTER_GET(pcie_fw); + break; + } + } + + return master_mbox; } /** @@ -2322,6 +2514,163 @@ int t4_fw_reset(struct adapter *adap, unsigned int mbox, int reset) return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL); } +/** + * t4_fw_config_file - setup an adapter via a Configuration File + * @adap: the adapter + * @mbox: mailbox to use for the FW command + * @mtype: the memory type where the Configuration File is located + * @maddr: the memory address where the Configuration File is located + * @finiver: return value for CF [fini] version + * @finicsum: return value for CF [fini] checksum + * @cfcsum: return value for CF computed checksum + * + * Issue a command to get the firmware to process the Configuration + * File located at the specified mtype/maddress. If the Configuration + * File is processed successfully and return value pointers are + * provided, the Configuration File "[fini] section version and + * checksum values will be returned along with the computed checksum. + * It's up to the caller to decide how it wants to respond to the + * checksums not matching but it recommended that a prominant warning + * be emitted in order to help people rapidly identify changed or + * corrupted Configuration Files. + * + * Also note that it's possible to modify things like "niccaps", + * "toecaps",etc. between processing the Configuration File and telling + * the firmware to use the new configuration. Callers which want to + * do this will need to "hand-roll" their own CAPS_CONFIGS commands for + * Configuration Files if they want to do this. + */ +int t4_fw_config_file(struct adapter *adap, unsigned int mbox, + unsigned int mtype, unsigned int maddr, + u32 *finiver, u32 *finicsum, u32 *cfcsum) +{ + struct fw_caps_config_cmd caps_cmd; + int ret; + + /* + * Tell the firmware to process the indicated Configuration File. + * If there are no errors and the caller has provided return value + * pointers for the [fini] section version, checksum and computed + * checksum, pass those back to the caller. + */ + memset(&caps_cmd, 0, sizeof(caps_cmd)); + caps_cmd.op_to_write = + htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) | + FW_CMD_REQUEST | + FW_CMD_READ); + caps_cmd.retval_len16 = + htonl(FW_CAPS_CONFIG_CMD_CFVALID | + FW_CAPS_CONFIG_CMD_MEMTYPE_CF(mtype) | + FW_CAPS_CONFIG_CMD_MEMADDR64K_CF(maddr >> 16) | + FW_LEN16(caps_cmd)); + ret = t4_wr_mbox(adap, mbox, &caps_cmd, sizeof(caps_cmd), &caps_cmd); + if (ret < 0) + return ret; + + if (finiver) + *finiver = ntohl(caps_cmd.finiver); + if (finicsum) + *finicsum = ntohl(caps_cmd.finicsum); + if (cfcsum) + *cfcsum = ntohl(caps_cmd.cfcsum); + + /* + * And now tell the firmware to use the configuration we just loaded. + */ + caps_cmd.op_to_write = + htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) | + FW_CMD_REQUEST | + FW_CMD_WRITE); + caps_cmd.retval_len16 = htonl(FW_LEN16(caps_cmd)); + return t4_wr_mbox(adap, mbox, &caps_cmd, sizeof(caps_cmd), NULL); +} + +/** + * t4_fixup_host_params - fix up host-dependent parameters + * @adap: the adapter + * @page_size: the host's Base Page Size + * @cache_line_size: the host's Cache Line Size + * + * Various registers in T4 contain values which are dependent on the + * host's Base Page and Cache Line Sizes. This function will fix all of + * those registers with the appropriate values as passed in ... + */ +int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, + unsigned int cache_line_size) +{ + unsigned int page_shift = fls(page_size) - 1; + unsigned int sge_hps = page_shift - 10; + unsigned int stat_len = cache_line_size > 64 ? 128 : 64; + unsigned int fl_align = cache_line_size < 32 ? 32 : cache_line_size; + unsigned int fl_align_log = fls(fl_align) - 1; + + t4_write_reg(adap, SGE_HOST_PAGE_SIZE, + HOSTPAGESIZEPF0(sge_hps) | + HOSTPAGESIZEPF1(sge_hps) | + HOSTPAGESIZEPF2(sge_hps) | + HOSTPAGESIZEPF3(sge_hps) | + HOSTPAGESIZEPF4(sge_hps) | + HOSTPAGESIZEPF5(sge_hps) | + HOSTPAGESIZEPF6(sge_hps) | + HOSTPAGESIZEPF7(sge_hps)); + + t4_set_reg_field(adap, SGE_CONTROL, + INGPADBOUNDARY(INGPADBOUNDARY_MASK) | + EGRSTATUSPAGESIZE_MASK, + INGPADBOUNDARY(fl_align_log - 5) | + EGRSTATUSPAGESIZE(stat_len != 64)); + + /* + * Adjust various SGE Free List Host Buffer Sizes. + * + * This is something of a crock since we're using fixed indices into + * the array which are also known by the sge.c code and the T4 + * Firmware Configuration File. We need to come up with a much better + * approach to managing this array. For now, the first four entries + * are: + * + * 0: Host Page Size + * 1: 64KB + * 2: Buffer size corresponding to 1500 byte MTU (unpacked mode) + * 3: Buffer size corresponding to 9000 byte MTU (unpacked mode) + * + * For the single-MTU buffers in unpacked mode we need to include + * space for the SGE Control Packet Shift, 14 byte Ethernet header, + * possible 4 byte VLAN tag, all rounded up to the next Ingress Packet + * Padding boundry. All of these are accommodated in the Factory + * Default Firmware Configuration File but we need to adjust it for + * this host's cache line size. + */ + t4_write_reg(adap, SGE_FL_BUFFER_SIZE0, page_size); + t4_write_reg(adap, SGE_FL_BUFFER_SIZE2, + (t4_read_reg(adap, SGE_FL_BUFFER_SIZE2) + fl_align-1) + & ~(fl_align-1)); + t4_write_reg(adap, SGE_FL_BUFFER_SIZE3, + (t4_read_reg(adap, SGE_FL_BUFFER_SIZE3) + fl_align-1) + & ~(fl_align-1)); + + t4_write_reg(adap, ULP_RX_TDDP_PSZ, HPZ0(page_shift - 12)); + + return 0; +} + +/** + * t4_fw_initialize - ask FW to initialize the device + * @adap: the adapter + * @mbox: mailbox to use for the FW command + * + * Issues a command to FW to partially initialize the device. This + * performs initialization that generally doesn't depend on user input. + */ +int t4_fw_initialize(struct adapter *adap, unsigned int mbox) +{ + struct fw_initialize_cmd c; + + memset(&c, 0, sizeof(c)); + INIT_CMD(c, INITIALIZE, WRITE); + return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL); +} + /** * t4_query_params - query FW or device parameters * @adap: the adapter @@ -2974,10 +3323,6 @@ int __devinit t4_prep_adapter(struct adapter *adapter) return ret; } - ret = get_vpd_params(adapter, &adapter->params.vpd); - if (ret < 0) - return ret; - init_cong_ctrl(adapter->params.a_wnd, adapter->params.b_wnd); /* @@ -2985,6 +3330,7 @@ int __devinit t4_prep_adapter(struct adapter *adapter) */ adapter->params.nports = 1; adapter->params.portvec = 1; + adapter->params.vpd.cclk = 50000; return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 2767ca6dbe99..779b23f8f591 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -115,6 +115,35 @@ #define GLOBALENABLE 0x00000001U #define SGE_HOST_PAGE_SIZE 0x100c + +#define HOSTPAGESIZEPF7_MASK 0x0000000fU +#define HOSTPAGESIZEPF7_SHIFT 28 +#define HOSTPAGESIZEPF7(x) ((x) << HOSTPAGESIZEPF7_SHIFT) + +#define HOSTPAGESIZEPF6_MASK 0x0000000fU +#define HOSTPAGESIZEPF6_SHIFT 24 +#define HOSTPAGESIZEPF6(x) ((x) << HOSTPAGESIZEPF6_SHIFT) + +#define HOSTPAGESIZEPF5_MASK 0x0000000fU +#define HOSTPAGESIZEPF5_SHIFT 20 +#define HOSTPAGESIZEPF5(x) ((x) << HOSTPAGESIZEPF5_SHIFT) + +#define HOSTPAGESIZEPF4_MASK 0x0000000fU +#define HOSTPAGESIZEPF4_SHIFT 16 +#define HOSTPAGESIZEPF4(x) ((x) << HOSTPAGESIZEPF4_SHIFT) + +#define HOSTPAGESIZEPF3_MASK 0x0000000fU +#define HOSTPAGESIZEPF3_SHIFT 12 +#define HOSTPAGESIZEPF3(x) ((x) << HOSTPAGESIZEPF3_SHIFT) + +#define HOSTPAGESIZEPF2_MASK 0x0000000fU +#define HOSTPAGESIZEPF2_SHIFT 8 +#define HOSTPAGESIZEPF2(x) ((x) << HOSTPAGESIZEPF2_SHIFT) + +#define HOSTPAGESIZEPF1_MASK 0x0000000fU +#define HOSTPAGESIZEPF1_SHIFT 4 +#define HOSTPAGESIZEPF1(x) ((x) << HOSTPAGESIZEPF1_SHIFT) + #define HOSTPAGESIZEPF0_MASK 0x0000000fU #define HOSTPAGESIZEPF0_SHIFT 0 #define HOSTPAGESIZEPF0(x) ((x) << HOSTPAGESIZEPF0_SHIFT) @@ -162,6 +191,8 @@ #define SGE_INT_ENABLE3 0x1040 #define SGE_FL_BUFFER_SIZE0 0x1044 #define SGE_FL_BUFFER_SIZE1 0x1048 +#define SGE_FL_BUFFER_SIZE2 0x104c +#define SGE_FL_BUFFER_SIZE3 0x1050 #define SGE_INGRESS_RX_THRESHOLD 0x10a0 #define THRESHOLD_0_MASK 0x3f000000U #define THRESHOLD_0_SHIFT 24 @@ -367,7 +398,7 @@ #define MEM_WRAP_CLIENT_NUM_MASK 0x0000000fU #define MEM_WRAP_CLIENT_NUM_SHIFT 0 #define MEM_WRAP_CLIENT_NUM_GET(x) (((x) & MEM_WRAP_CLIENT_NUM_MASK) >> MEM_WRAP_CLIENT_NUM_SHIFT) - +#define MA_PCIE_FW 0x30b8 #define MA_PARITY_ERROR_STATUS 0x77f4 #define EDC_0_BASE_ADDR 0x7900 @@ -469,6 +500,10 @@ #define TIMERRESOLUTION_MASK 0x00ff0000U #define TIMERRESOLUTION_SHIFT 16 #define TIMERRESOLUTION_GET(x) (((x) & TIMERRESOLUTION_MASK) >> TIMERRESOLUTION_SHIFT) +#define DELAYEDACKRESOLUTION_MASK 0x000000ffU +#define DELAYEDACKRESOLUTION_SHIFT 0 +#define DELAYEDACKRESOLUTION_GET(x) \ + (((x) & DELAYEDACKRESOLUTION_MASK) >> DELAYEDACKRESOLUTION_SHIFT) #define TP_SHIFT_CNT 0x7dc0 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 94e3484b7d93..3f85019106fa 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -155,6 +155,17 @@ struct fw_eth_tx_pkt_vm_wr { #define FW_CMD_MAX_TIMEOUT 3000 +/* + * If a host driver does a HELLO and discovers that there's already a MASTER + * selected, we may have to wait for that MASTER to finish issuing RESET, + * configuration and INITIALIZE commands. Also, there's a possibility that + * our own HELLO may get lost if it happens right as the MASTER is issuign a + * RESET command, so we need to be willing to make a few retries of our HELLO. + */ +#define FW_CMD_HELLO_TIMEOUT (3 * FW_CMD_MAX_TIMEOUT) +#define FW_CMD_HELLO_RETRIES 3 + + enum fw_cmd_opcodes { FW_LDST_CMD = 0x01, FW_RESET_CMD = 0x03, @@ -307,6 +318,10 @@ struct fw_reset_cmd { __be32 r3; }; +enum fw_hellow_cmd { + fw_hello_cmd_stage_os = 0x0 +}; + struct fw_hello_cmd { __be32 op_to_write; __be32 retval_len16; @@ -315,8 +330,14 @@ struct fw_hello_cmd { #define FW_HELLO_CMD_INIT (1U << 30) #define FW_HELLO_CMD_MASTERDIS(x) ((x) << 29) #define FW_HELLO_CMD_MASTERFORCE(x) ((x) << 28) -#define FW_HELLO_CMD_MBMASTER(x) ((x) << 24) +#define FW_HELLO_CMD_MBMASTER_MASK 0xfU +#define FW_HELLO_CMD_MBMASTER_SHIFT 24 +#define FW_HELLO_CMD_MBMASTER(x) ((x) << FW_HELLO_CMD_MBMASTER_SHIFT) +#define FW_HELLO_CMD_MBMASTER_GET(x) \ + (((x) >> FW_HELLO_CMD_MBMASTER_SHIFT) & FW_HELLO_CMD_MBMASTER_MASK) #define FW_HELLO_CMD_MBASYNCNOT(x) ((x) << 20) +#define FW_HELLO_CMD_STAGE(x) ((x) << 17) +#define FW_HELLO_CMD_CLEARINIT (1U << 16) __be32 fwrev; }; @@ -1654,18 +1675,4 @@ struct fw_hdr { #define FW_HDR_FW_VER_MICRO_GET(x) (((x) >> 8) & 0xff) #define FW_HDR_FW_VER_BUILD_GET(x) (((x) >> 0) & 0xff) -#define S_FW_CMD_OP 24 -#define V_FW_CMD_OP(x) ((x) << S_FW_CMD_OP) - -#define S_FW_CMD_REQUEST 23 -#define V_FW_CMD_REQUEST(x) ((x) << S_FW_CMD_REQUEST) -#define F_FW_CMD_REQUEST V_FW_CMD_REQUEST(1U) - -#define S_FW_CMD_WRITE 21 -#define V_FW_CMD_WRITE(x) ((x) << S_FW_CMD_WRITE) -#define F_FW_CMD_WRITE V_FW_CMD_WRITE(1U) - -#define S_FW_LDST_CMD_ADDRSPACE 0 -#define V_FW_LDST_CMD_ADDRSPACE(x) ((x) << S_FW_LDST_CMD_ADDRSPACE) - #endif /* _T4FW_INTERFACE_H_ */ -- cgit v1.2.3 From 13ee15d396da78079918c5be7510ea1847393d4c Mon Sep 17 00:00:00 2001 From: Vipul Pandya Date: Wed, 26 Sep 2012 02:39:40 +0000 Subject: cxgb4: Add support for T4 hardwired driver configuration settings In case if user defined configuration file at /lib/firmware/cxgb4/t4-config.txt location and also factory default configuration file written to FLASH are not present then driver will use hardwired configuration settings. Signed-off-by: Jay Hernandez Signed-off-by: Vipul Pandya Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 4 + drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 390 ++++++++++++++++++++++-- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 22 ++ drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 56 ++++ drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 2 + 5 files changed, 442 insertions(+), 32 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 777cbb4f62bb..6827ce338f6a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -318,6 +318,7 @@ enum { /* adapter flags */ USING_MSI = (1 << 1), USING_MSIX = (1 << 2), FW_OK = (1 << 4), + RSS_TNLALLLOOKUP = (1 << 5), USING_SOFT_PARAMS = (1 << 6), MASTER_PF = (1 << 7), FW_OFLD_CONN = (1 << 9), @@ -677,6 +678,9 @@ static inline int t4_wr_mbox_ns(struct adapter *adap, int mbox, const void *cmd, return t4_wr_mbox_meat(adap, mbox, cmd, size, rpl, false); } +void t4_write_indirect(struct adapter *adap, unsigned int addr_reg, + unsigned int data_reg, const u32 *vals, + unsigned int nregs, unsigned int start_idx); void t4_intr_enable(struct adapter *adapter); void t4_intr_disable(struct adapter *adapter); int t4_slow_intr_handler(struct adapter *adapter); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index cb3e663c30dc..b9cd08df39b3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -78,28 +78,45 @@ */ #define MAX_SGE_TIMERVAL 200U -#ifdef CONFIG_PCI_IOV -/* - * Virtual Function provisioning constants. We need two extra Ingress Queues - * with Interrupt capability to serve as the VF's Firmware Event Queue and - * Forwarded Interrupt Queue (when using MSI mode) -- neither will have Free - * Lists associated with them). For each Ethernet/Control Egress Queue and - * for each Free List, we need an Egress Context. - */ enum { + /* + * Physical Function provisioning constants. + */ + PFRES_NVI = 4, /* # of Virtual Interfaces */ + PFRES_NETHCTRL = 128, /* # of EQs used for ETH or CTRL Qs */ + PFRES_NIQFLINT = 128, /* # of ingress Qs/w Free List(s)/intr + */ + PFRES_NEQ = 256, /* # of egress queues */ + PFRES_NIQ = 0, /* # of ingress queues */ + PFRES_TC = 0, /* PCI-E traffic class */ + PFRES_NEXACTF = 128, /* # of exact MPS filters */ + + PFRES_R_CAPS = FW_CMD_CAP_PF, + PFRES_WX_CAPS = FW_CMD_CAP_PF, + +#ifdef CONFIG_PCI_IOV + /* + * Virtual Function provisioning constants. We need two extra Ingress + * Queues with Interrupt capability to serve as the VF's Firmware + * Event Queue and Forwarded Interrupt Queue (when using MSI mode) -- + * neither will have Free Lists associated with them). For each + * Ethernet/Control Egress Queue and for each Free List, we need an + * Egress Context. + */ VFRES_NPORTS = 1, /* # of "ports" per VF */ VFRES_NQSETS = 2, /* # of "Queue Sets" per VF */ VFRES_NVI = VFRES_NPORTS, /* # of Virtual Interfaces */ VFRES_NETHCTRL = VFRES_NQSETS, /* # of EQs used for ETH or CTRL Qs */ VFRES_NIQFLINT = VFRES_NQSETS+2,/* # of ingress Qs/w Free List(s)/intr */ - VFRES_NIQ = 0, /* # of non-fl/int ingress queues */ VFRES_NEQ = VFRES_NQSETS*2, /* # of egress queues */ + VFRES_NIQ = 0, /* # of non-fl/int ingress queues */ VFRES_TC = 0, /* PCI-E traffic class */ VFRES_NEXACTF = 16, /* # of exact MPS filters */ VFRES_R_CAPS = FW_CMD_CAP_DMAQ|FW_CMD_CAP_VF|FW_CMD_CAP_PORT, VFRES_WX_CAPS = FW_CMD_CAP_DMAQ|FW_CMD_CAP_VF, +#endif }; /* @@ -146,7 +163,6 @@ static unsigned int pfvfres_pmask(struct adapter *adapter, } /*NOTREACHED*/ } -#endif enum { MAX_TXQ_ENTRIES = 16384, @@ -213,6 +229,17 @@ static uint force_init; module_param(force_init, uint, 0644); MODULE_PARM_DESC(force_init, "Forcibly become Master PF and initialize adapter"); +/* + * Normally if the firmware we connect to has Configuration File support, we + * use that and only fall back to the old Driver-based initialization if the + * Configuration File fails for some reason. If force_old_init is set, then + * we'll always use the old Driver-based initialization sequence. + */ +static uint force_old_init; + +module_param(force_old_init, uint, 0644); +MODULE_PARM_DESC(force_old_init, "Force old initialization sequence"); + static int dflt_msg_enable = DFLT_MSG_ENABLE; module_param(dflt_msg_enable, int, 0644); @@ -274,6 +301,30 @@ module_param_array(num_vf, uint, NULL, 0644); MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3"); #endif +/* + * The filter TCAM has a fixed portion and a variable portion. The fixed + * portion can match on source/destination IP IPv4/IPv6 addresses and TCP/UDP + * ports. The variable portion is 36 bits which can include things like Exact + * Match MAC Index (9 bits), Ether Type (16 bits), IP Protocol (8 bits), + * [Inner] VLAN Tag (17 bits), etc. which, if all were somehow selected, would + * far exceed the 36-bit budget for this "compressed" header portion of the + * filter. Thus, we have a scarce resource which must be carefully managed. + * + * By default we set this up to mostly match the set of filter matching + * capabilities of T3 but with accommodations for some of T4's more + * interesting features: + * + * { IP Fragment (1), MPS Match Type (3), IP Protocol (8), + * [Inner] VLAN (17), Port (3), FCoE (1) } + */ +enum { + TP_VLAN_PRI_MAP_DEFAULT = HW_TPL_FR_MT_PR_IV_P_FC, + TP_VLAN_PRI_MAP_FIRST = FCOE_SHIFT, + TP_VLAN_PRI_MAP_LAST = FRAGMENTATION_SHIFT, +}; + +static unsigned int tp_vlan_pri_map = TP_VLAN_PRI_MAP_DEFAULT; + static struct dentry *cxgb4_debugfs_root; static LIST_HEAD(adapter_list); @@ -3409,6 +3460,262 @@ bye: return ret; } +/* + * Attempt to initialize the adapter via hard-coded, driver supplied + * parameters ... + */ +static int adap_init0_no_config(struct adapter *adapter, int reset) +{ + struct sge *s = &adapter->sge; + struct fw_caps_config_cmd caps_cmd; + u32 v; + int i, ret; + + /* + * Reset device if necessary + */ + if (reset) { + ret = t4_fw_reset(adapter, adapter->mbox, + PIORSTMODE | PIORST); + if (ret < 0) + goto bye; + } + + /* + * Get device capabilities and select which we'll be using. + */ + memset(&caps_cmd, 0, sizeof(caps_cmd)); + caps_cmd.op_to_write = htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) | + FW_CMD_REQUEST | FW_CMD_READ); + caps_cmd.retval_len16 = htonl(FW_LEN16(caps_cmd)); + ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd), + &caps_cmd); + if (ret < 0) + goto bye; + +#ifndef CONFIG_CHELSIO_T4_OFFLOAD + /* + * If we're a pure NIC driver then disable all offloading facilities. + * This will allow the firmware to optimize aspects of the hardware + * configuration which will result in improved performance. + */ + caps_cmd.ofldcaps = 0; + caps_cmd.iscsicaps = 0; + caps_cmd.rdmacaps = 0; + caps_cmd.fcoecaps = 0; +#endif + + if (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_VM)) { + if (!vf_acls) + caps_cmd.niccaps ^= htons(FW_CAPS_CONFIG_NIC_VM); + else + caps_cmd.niccaps = htons(FW_CAPS_CONFIG_NIC_VM); + } else if (vf_acls) { + dev_err(adapter->pdev_dev, "virtualization ACLs not supported"); + goto bye; + } + caps_cmd.op_to_write = htonl(FW_CMD_OP(FW_CAPS_CONFIG_CMD) | + FW_CMD_REQUEST | FW_CMD_WRITE); + ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd), + NULL); + if (ret < 0) + goto bye; + + /* + * Tweak configuration based on system architecture, module + * parameters, etc. + */ + ret = adap_init0_tweaks(adapter); + if (ret < 0) + goto bye; + + /* + * Select RSS Global Mode we want to use. We use "Basic Virtual" + * mode which maps each Virtual Interface to its own section of + * the RSS Table and we turn on all map and hash enables ... + */ + adapter->flags |= RSS_TNLALLLOOKUP; + ret = t4_config_glbl_rss(adapter, adapter->mbox, + FW_RSS_GLB_CONFIG_CMD_MODE_BASICVIRTUAL, + FW_RSS_GLB_CONFIG_CMD_TNLMAPEN | + FW_RSS_GLB_CONFIG_CMD_HASHTOEPLITZ | + ((adapter->flags & RSS_TNLALLLOOKUP) ? + FW_RSS_GLB_CONFIG_CMD_TNLALLLKP : 0)); + if (ret < 0) + goto bye; + + /* + * Set up our own fundamental resource provisioning ... + */ + ret = t4_cfg_pfvf(adapter, adapter->mbox, adapter->fn, 0, + PFRES_NEQ, PFRES_NETHCTRL, + PFRES_NIQFLINT, PFRES_NIQ, + PFRES_TC, PFRES_NVI, + FW_PFVF_CMD_CMASK_MASK, + pfvfres_pmask(adapter, adapter->fn, 0), + PFRES_NEXACTF, + PFRES_R_CAPS, PFRES_WX_CAPS); + if (ret < 0) + goto bye; + + /* + * Perform low level SGE initialization. We need to do this before we + * send the firmware the INITIALIZE command because that will cause + * any other PF Drivers which are waiting for the Master + * Initialization to proceed forward. + */ + for (i = 0; i < SGE_NTIMERS - 1; i++) + s->timer_val[i] = min(intr_holdoff[i], MAX_SGE_TIMERVAL); + s->timer_val[SGE_NTIMERS - 1] = MAX_SGE_TIMERVAL; + s->counter_val[0] = 1; + for (i = 1; i < SGE_NCOUNTERS; i++) + s->counter_val[i] = min(intr_cnt[i - 1], + THRESHOLD_0_GET(THRESHOLD_0_MASK)); + t4_sge_init(adapter); + +#ifdef CONFIG_PCI_IOV + /* + * Provision resource limits for Virtual Functions. We currently + * grant them all the same static resource limits except for the Port + * Access Rights Mask which we're assigning based on the PF. All of + * the static provisioning stuff for both the PF and VF really needs + * to be managed in a persistent manner for each device which the + * firmware controls. + */ + { + int pf, vf; + + for (pf = 0; pf < ARRAY_SIZE(num_vf); pf++) { + if (num_vf[pf] <= 0) + continue; + + /* VF numbering starts at 1! */ + for (vf = 1; vf <= num_vf[pf]; vf++) { + ret = t4_cfg_pfvf(adapter, adapter->mbox, + pf, vf, + VFRES_NEQ, VFRES_NETHCTRL, + VFRES_NIQFLINT, VFRES_NIQ, + VFRES_TC, VFRES_NVI, + FW_PFVF_CMD_CMASK_GET( + FW_PFVF_CMD_CMASK_MASK), + pfvfres_pmask( + adapter, pf, vf), + VFRES_NEXACTF, + VFRES_R_CAPS, VFRES_WX_CAPS); + if (ret < 0) + dev_warn(adapter->pdev_dev, + "failed to "\ + "provision pf/vf=%d/%d; " + "err=%d\n", pf, vf, ret); + } + } + } +#endif + + /* + * Set up the default filter mode. Later we'll want to implement this + * via a firmware command, etc. ... This needs to be done before the + * firmare initialization command ... If the selected set of fields + * isn't equal to the default value, we'll need to make sure that the + * field selections will fit in the 36-bit budget. + */ + if (tp_vlan_pri_map != TP_VLAN_PRI_MAP_DEFAULT) { + int i, bits = 0; + + for (i = TP_VLAN_PRI_MAP_FIRST; i <= TP_VLAN_PRI_MAP_LAST; i++) + switch (tp_vlan_pri_map & (1 << i)) { + case 0: + /* compressed filter field not enabled */ + break; + case FCOE_MASK: + bits += 1; + break; + case PORT_MASK: + bits += 3; + break; + case VNIC_ID_MASK: + bits += 17; + break; + case VLAN_MASK: + bits += 17; + break; + case TOS_MASK: + bits += 8; + break; + case PROTOCOL_MASK: + bits += 8; + break; + case ETHERTYPE_MASK: + bits += 16; + break; + case MACMATCH_MASK: + bits += 9; + break; + case MPSHITTYPE_MASK: + bits += 3; + break; + case FRAGMENTATION_MASK: + bits += 1; + break; + } + + if (bits > 36) { + dev_err(adapter->pdev_dev, + "tp_vlan_pri_map=%#x needs %d bits > 36;"\ + " using %#x\n", tp_vlan_pri_map, bits, + TP_VLAN_PRI_MAP_DEFAULT); + tp_vlan_pri_map = TP_VLAN_PRI_MAP_DEFAULT; + } + } + v = tp_vlan_pri_map; + t4_write_indirect(adapter, TP_PIO_ADDR, TP_PIO_DATA, + &v, 1, TP_VLAN_PRI_MAP); + + /* + * We need Five Tuple Lookup mode to be set in TP_GLOBAL_CONFIG order + * to support any of the compressed filter fields above. Newer + * versions of the firmware do this automatically but it doesn't hurt + * to set it here. Meanwhile, we do _not_ need to set Lookup Every + * Packet in TP_INGRESS_CONFIG to support matching non-TCP packets + * since the firmware automatically turns this on and off when we have + * a non-zero number of filters active (since it does have a + * performance impact). + */ + if (tp_vlan_pri_map) + t4_set_reg_field(adapter, TP_GLOBAL_CONFIG, + FIVETUPLELOOKUP_MASK, + FIVETUPLELOOKUP_MASK); + + /* + * Tweak some settings. + */ + t4_write_reg(adapter, TP_SHIFT_CNT, SYNSHIFTMAX(6) | + RXTSHIFTMAXR1(4) | RXTSHIFTMAXR2(15) | + PERSHIFTBACKOFFMAX(8) | PERSHIFTMAX(8) | + KEEPALIVEMAXR1(4) | KEEPALIVEMAXR2(9)); + + /* + * Get basic stuff going by issuing the Firmware Initialize command. + * Note that this _must_ be after all PFVF commands ... + */ + ret = t4_fw_initialize(adapter, adapter->mbox); + if (ret < 0) + goto bye; + + /* + * Return successfully! + */ + dev_info(adapter->pdev_dev, "Successfully configured using built-in "\ + "driver parameters\n"); + return 0; + + /* + * Something bad happened. Return the error ... + */ +bye: + return ret; +} + /* * Phase 0 of initialization: contact FW, obtain config, perform basic init. */ @@ -3474,7 +3781,9 @@ static int adap_init0(struct adapter *adap) goto bye; /* - * Find out what ports are available to us. + * Find out what ports are available to us. Note that we need to do + * this before calling adap_init0_no_config() since it needs nports + * and portvec ... */ v = FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | @@ -3500,35 +3809,52 @@ static int adap_init0(struct adapter *adap) } else { dev_info(adap->pdev_dev, "Coming up as MASTER: "\ "Initializing adapter\n"); - /* - * Find out whether we're dealing with a version of - * the firmware which has configuration file support. - */ - params[0] = (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | - FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_CF)); - ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1, - params, val); /* * If the firmware doesn't support Configuration * Files warn user and exit, */ if (ret < 0) - dev_warn(adap->pdev_dev, "Firmware doesn't support "\ + dev_warn(adap->pdev_dev, "Firmware doesn't support " "configuration file.\n"); + if (force_old_init) + ret = adap_init0_no_config(adap, reset); else { /* - * The firmware provides us with a memory - * buffer where we can load a Configuration - * File from the host if we want to override - * the Configuration File in flash. + * Find out whether we're dealing with a version of + * the firmware which has configuration file support. */ + params[0] = (FW_PARAMS_MNEM(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X(FW_PARAMS_PARAM_DEV_CF)); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1, + params, val); - ret = adap_init0_config(adap, reset); - if (ret == -ENOENT) { - dev_info(adap->pdev_dev, - "No Configuration File present " - "on adapter.\n"); + /* + * If the firmware doesn't support Configuration + * Files, use the old Driver-based, hard-wired + * initialization. Otherwise, try using the + * Configuration File support and fall back to the + * Driver-based initialization if there's no + * Configuration File found. + */ + if (ret < 0) + ret = adap_init0_no_config(adap, reset); + else { + /* + * The firmware provides us with a memory + * buffer where we can load a Configuration + * File from the host if we want to override + * the Configuration File in flash. + */ + + ret = adap_init0_config(adap, reset); + if (ret == -ENOENT) { + dev_info(adap->pdev_dev, + "No Configuration File present " + "on adapter. Using hard-wired " + "configuration parameters.\n"); + ret = adap_init0_no_config(adap, reset); + } } } if (ret < 0) { @@ -3601,14 +3927,14 @@ static int adap_init0(struct adapter *adap) */ memset(&caps_cmd, 0, sizeof(caps_cmd)); caps_cmd.op_to_write = htonl(V_FW_CMD_OP(FW_CAPS_CONFIG_CMD) | - F_FW_CMD_REQUEST | F_FW_CMD_READ); - caps_cmd.cfvalid_to_len16 = htonl(FW_LEN16(caps_cmd)); + FW_CMD_REQUEST | FW_CMD_READ); + caps_cmd.retval_len16 = htonl(FW_LEN16(caps_cmd)); ret = t4_wr_mbox(adap, adap->mbox, &caps_cmd, sizeof(caps_cmd), &caps_cmd); if (ret < 0) goto bye; - if (caps_cmd.toecaps) { + if (caps_cmd.ofldcaps) { /* query offload-related parameters */ params[0] = FW_PARAM_DEV(NTID); params[1] = FW_PARAM_PFVF(SERVER_START); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 419432d42049..61f002d22013 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -120,6 +120,28 @@ static void t4_read_indirect(struct adapter *adap, unsigned int addr_reg, } } +/** + * t4_write_indirect - write indirectly addressed registers + * @adap: the adapter + * @addr_reg: register holding the indirect addresses + * @data_reg: register holding the value for the indirect registers + * @vals: values to write + * @nregs: how many indirect registers to write + * @start_idx: address of first indirect register to write + * + * Writes a sequential block of registers that are accessed indirectly + * through an address/data register pair. + */ +void t4_write_indirect(struct adapter *adap, unsigned int addr_reg, + unsigned int data_reg, const u32 *vals, + unsigned int nregs, unsigned int start_idx) +{ + while (nregs--) { + t4_write_reg(adap, addr_reg, start_idx++); + t4_write_reg(adap, data_reg, *vals++); + } +} + /* * Get the reply to a mailbox command and store it in @rpl in big-endian order. */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 779b23f8f591..732c6da2636f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -491,6 +491,13 @@ #define VLANEXTENABLE_MASK 0x0000f000U #define VLANEXTENABLE_SHIFT 12 +#define TP_GLOBAL_CONFIG 0x7d08 +#define FIVETUPLELOOKUP_SHIFT 17 +#define FIVETUPLELOOKUP_MASK 0x00060000U +#define FIVETUPLELOOKUP(x) ((x) << FIVETUPLELOOKUP_SHIFT) +#define FIVETUPLELOOKUP_GET(x) (((x) & FIVETUPLELOOKUP_MASK) >> \ + FIVETUPLELOOKUP_SHIFT) + #define TP_PARA_REG2 0x7d68 #define MAXRXDATA_MASK 0xffff0000U #define MAXRXDATA_SHIFT 16 @@ -506,6 +513,41 @@ (((x) & DELAYEDACKRESOLUTION_MASK) >> DELAYEDACKRESOLUTION_SHIFT) #define TP_SHIFT_CNT 0x7dc0 +#define SYNSHIFTMAX_SHIFT 24 +#define SYNSHIFTMAX_MASK 0xff000000U +#define SYNSHIFTMAX(x) ((x) << SYNSHIFTMAX_SHIFT) +#define SYNSHIFTMAX_GET(x) (((x) & SYNSHIFTMAX_MASK) >> \ + SYNSHIFTMAX_SHIFT) +#define RXTSHIFTMAXR1_SHIFT 20 +#define RXTSHIFTMAXR1_MASK 0x00f00000U +#define RXTSHIFTMAXR1(x) ((x) << RXTSHIFTMAXR1_SHIFT) +#define RXTSHIFTMAXR1_GET(x) (((x) & RXTSHIFTMAXR1_MASK) >> \ + RXTSHIFTMAXR1_SHIFT) +#define RXTSHIFTMAXR2_SHIFT 16 +#define RXTSHIFTMAXR2_MASK 0x000f0000U +#define RXTSHIFTMAXR2(x) ((x) << RXTSHIFTMAXR2_SHIFT) +#define RXTSHIFTMAXR2_GET(x) (((x) & RXTSHIFTMAXR2_MASK) >> \ + RXTSHIFTMAXR2_SHIFT) +#define PERSHIFTBACKOFFMAX_SHIFT 12 +#define PERSHIFTBACKOFFMAX_MASK 0x0000f000U +#define PERSHIFTBACKOFFMAX(x) ((x) << PERSHIFTBACKOFFMAX_SHIFT) +#define PERSHIFTBACKOFFMAX_GET(x) (((x) & PERSHIFTBACKOFFMAX_MASK) >> \ + PERSHIFTBACKOFFMAX_SHIFT) +#define PERSHIFTMAX_SHIFT 8 +#define PERSHIFTMAX_MASK 0x00000f00U +#define PERSHIFTMAX(x) ((x) << PERSHIFTMAX_SHIFT) +#define PERSHIFTMAX_GET(x) (((x) & PERSHIFTMAX_MASK) >> \ + PERSHIFTMAX_SHIFT) +#define KEEPALIVEMAXR1_SHIFT 4 +#define KEEPALIVEMAXR1_MASK 0x000000f0U +#define KEEPALIVEMAXR1(x) ((x) << KEEPALIVEMAXR1_SHIFT) +#define KEEPALIVEMAXR1_GET(x) (((x) & KEEPALIVEMAXR1_MASK) >> \ + KEEPALIVEMAXR1_SHIFT) +#define KEEPALIVEMAXR2_SHIFT 0 +#define KEEPALIVEMAXR2_MASK 0x0000000fU +#define KEEPALIVEMAXR2(x) ((x) << KEEPALIVEMAXR2_SHIFT) +#define KEEPALIVEMAXR2_GET(x) (((x) & KEEPALIVEMAXR2_MASK) >> \ + KEEPALIVEMAXR2_SHIFT) #define TP_CCTRL_TABLE 0x7ddc #define TP_MTU_TABLE 0x7de4 @@ -539,6 +581,20 @@ #define TP_INT_CAUSE 0x7e74 #define FLMTXFLSTEMPTY 0x40000000U +#define TP_VLAN_PRI_MAP 0x140 +#define FRAGMENTATION_SHIFT 9 +#define FRAGMENTATION_MASK 0x00000200U +#define MPSHITTYPE_MASK 0x00000100U +#define MACMATCH_MASK 0x00000080U +#define ETHERTYPE_MASK 0x00000040U +#define PROTOCOL_MASK 0x00000020U +#define TOS_MASK 0x00000010U +#define VLAN_MASK 0x00000008U +#define VNIC_ID_MASK 0x00000004U +#define PORT_MASK 0x00000002U +#define FCOE_SHIFT 0 +#define FCOE_MASK 0x00000001U + #define TP_INGRESS_CONFIG 0x141 #define VNIC 0x00000800U #define CSUM_HAS_PSEUDO_HDR 0x00000400U diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 3f85019106fa..b1d556128f84 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -79,6 +79,8 @@ struct fw_wr_hdr { #define FW_WR_FLOWID(x) ((x) << 8) #define FW_WR_LEN16(x) ((x) << 0) +#define HW_TPL_FR_MT_PR_IV_P_FC 0X32B + struct fw_ulptx_wr { __be32 op_to_compl; __be32 flowid_len16; -- cgit v1.2.3 From 1648a22b16ab05bd99dd8e2f33ca80bbcea60031 Mon Sep 17 00:00:00 2001 From: Vipul Pandya Date: Wed, 26 Sep 2012 02:39:41 +0000 Subject: cxgb4: Inform caller if driver didn't upgrade firmware If a card had already been initialized, on reloading cxgb4 driver firmware required an upgrade but the upgrade did not happen. In that case a mailbox timeout would occur during T4 configuration file stuff. The fix is to let the caller know the firmware was not upgraded so a reset would be issued before starting the T4 config stuff. Signed-off-by: Jay Hernandez Signed-off-by: Vipul Pandya Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index b9cd08df39b3..a3f866d5b8f1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -933,7 +933,13 @@ static int upgrade_fw(struct adapter *adap) if (!ret) dev_info(dev, "firmware upgraded to version %pI4 from " FW_FNAME "\n", &hdr->fw_ver); + } else { + /* + * Tell our caller that we didn't upgrade the firmware. + */ + ret = -EINVAL; } + out: release_firmware(fw); return ret; } -- cgit v1.2.3 From 26f7cbc0a5a42d8cc0c7725d10317089a8215f97 Mon Sep 17 00:00:00 2001 From: Vipul Pandya Date: Wed, 26 Sep 2012 02:39:42 +0000 Subject: cxgb4: Don't attempt to upgrade T4 firmware when cxgb4 will end up as a slave This patch adds a new common code routine to upgrade an adapter's firmware. This routine handles all of the complexities of working with the the existing adapter firmware in order to quiesce the adapter and uP, etc. For an automatic upgrade it will send a HELLO command to check if cxgb4 want/can upgrade firmware, i.e. if cxgb4 is MASTER and has newer firmware that it wants to load and call the new common code routine t4_fw_upgrade. Note that it should not issue a RESET command after a successful firmware upgrade. Signed-off-by: Jay Hernandez Signed-off-by: Vipul Pandya Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 4 + drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 14 +- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 171 ++++++++++++++++++++++++ drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 3 + drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 19 ++- 5 files changed, 206 insertions(+), 5 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 6827ce338f6a..745a1f53361f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -726,6 +726,10 @@ int t4_fw_hello(struct adapter *adap, unsigned int mbox, unsigned int evt_mbox, int t4_fw_bye(struct adapter *adap, unsigned int mbox); int t4_early_init(struct adapter *adap, unsigned int mbox); int t4_fw_reset(struct adapter *adap, unsigned int mbox, int reset); +int t4_fw_halt(struct adapter *adap, unsigned int mbox, int force); +int t4_fw_restart(struct adapter *adap, unsigned int mbox, int reset); +int t4_fw_upgrade(struct adapter *adap, unsigned int mbox, + const u8 *fw_data, unsigned int size, int force); int t4_fw_config_file(struct adapter *adap, unsigned int mbox, unsigned int mtype, unsigned int maddr, u32 *finiver, u32 *finicsum, u32 *cfcsum); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index a3f866d5b8f1..94b784610319 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -929,10 +929,18 @@ static int upgrade_fw(struct adapter *adap) */ if (FW_HDR_FW_VER_MAJOR_GET(adap->params.fw_vers) != FW_VERSION_MAJOR || vers > adap->params.fw_vers) { - ret = -t4_load_fw(adap, fw->data, fw->size); + dev_info(dev, "upgrading firmware ...\n"); + ret = t4_fw_upgrade(adap, adap->mbox, fw->data, fw->size, + /*force=*/false); if (!ret) - dev_info(dev, "firmware upgraded to version %pI4 from " - FW_FNAME "\n", &hdr->fw_ver); + dev_info(dev, "firmware successfully upgraded to " + FW_FNAME " (%d.%d.%d.%d)\n", + FW_HDR_FW_VER_MAJOR_GET(vers), + FW_HDR_FW_VER_MINOR_GET(vers), + FW_HDR_FW_VER_MICRO_GET(vers), + FW_HDR_FW_VER_BUILD_GET(vers)); + else + dev_err(dev, "firmware upgrade failed! err=%d\n", -ret); } else { /* * Tell our caller that we didn't upgrade the firmware. diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 61f002d22013..ab732b378c4f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -2536,6 +2536,177 @@ int t4_fw_reset(struct adapter *adap, unsigned int mbox, int reset) return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL); } +/** + * t4_fw_halt - issue a reset/halt to FW and put uP into RESET + * @adap: the adapter + * @mbox: mailbox to use for the FW RESET command (if desired) + * @force: force uP into RESET even if FW RESET command fails + * + * Issues a RESET command to firmware (if desired) with a HALT indication + * and then puts the microprocessor into RESET state. The RESET command + * will only be issued if a legitimate mailbox is provided (mbox <= + * FW_PCIE_FW_MASTER_MASK). + * + * This is generally used in order for the host to safely manipulate the + * adapter without fear of conflicting with whatever the firmware might + * be doing. The only way out of this state is to RESTART the firmware + * ... + */ +int t4_fw_halt(struct adapter *adap, unsigned int mbox, int force) +{ + int ret = 0; + + /* + * If a legitimate mailbox is provided, issue a RESET command + * with a HALT indication. + */ + if (mbox <= FW_PCIE_FW_MASTER_MASK) { + struct fw_reset_cmd c; + + memset(&c, 0, sizeof(c)); + INIT_CMD(c, RESET, WRITE); + c.val = htonl(PIORST | PIORSTMODE); + c.halt_pkd = htonl(FW_RESET_CMD_HALT(1U)); + ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL); + } + + /* + * Normally we won't complete the operation if the firmware RESET + * command fails but if our caller insists we'll go ahead and put the + * uP into RESET. This can be useful if the firmware is hung or even + * missing ... We'll have to take the risk of putting the uP into + * RESET without the cooperation of firmware in that case. + * + * We also force the firmware's HALT flag to be on in case we bypassed + * the firmware RESET command above or we're dealing with old firmware + * which doesn't have the HALT capability. This will serve as a flag + * for the incoming firmware to know that it's coming out of a HALT + * rather than a RESET ... if it's new enough to understand that ... + */ + if (ret == 0 || force) { + t4_set_reg_field(adap, CIM_BOOT_CFG, UPCRST, UPCRST); + t4_set_reg_field(adap, PCIE_FW, FW_PCIE_FW_HALT, + FW_PCIE_FW_HALT); + } + + /* + * And we always return the result of the firmware RESET command + * even when we force the uP into RESET ... + */ + return ret; +} + +/** + * t4_fw_restart - restart the firmware by taking the uP out of RESET + * @adap: the adapter + * @reset: if we want to do a RESET to restart things + * + * Restart firmware previously halted by t4_fw_halt(). On successful + * return the previous PF Master remains as the new PF Master and there + * is no need to issue a new HELLO command, etc. + * + * We do this in two ways: + * + * 1. If we're dealing with newer firmware we'll simply want to take + * the chip's microprocessor out of RESET. This will cause the + * firmware to start up from its start vector. And then we'll loop + * until the firmware indicates it's started again (PCIE_FW.HALT + * reset to 0) or we timeout. + * + * 2. If we're dealing with older firmware then we'll need to RESET + * the chip since older firmware won't recognize the PCIE_FW.HALT + * flag and automatically RESET itself on startup. + */ +int t4_fw_restart(struct adapter *adap, unsigned int mbox, int reset) +{ + if (reset) { + /* + * Since we're directing the RESET instead of the firmware + * doing it automatically, we need to clear the PCIE_FW.HALT + * bit. + */ + t4_set_reg_field(adap, PCIE_FW, FW_PCIE_FW_HALT, 0); + + /* + * If we've been given a valid mailbox, first try to get the + * firmware to do the RESET. If that works, great and we can + * return success. Otherwise, if we haven't been given a + * valid mailbox or the RESET command failed, fall back to + * hitting the chip with a hammer. + */ + if (mbox <= FW_PCIE_FW_MASTER_MASK) { + t4_set_reg_field(adap, CIM_BOOT_CFG, UPCRST, 0); + msleep(100); + if (t4_fw_reset(adap, mbox, + PIORST | PIORSTMODE) == 0) + return 0; + } + + t4_write_reg(adap, PL_RST, PIORST | PIORSTMODE); + msleep(2000); + } else { + int ms; + + t4_set_reg_field(adap, CIM_BOOT_CFG, UPCRST, 0); + for (ms = 0; ms < FW_CMD_MAX_TIMEOUT; ) { + if (!(t4_read_reg(adap, PCIE_FW) & FW_PCIE_FW_HALT)) + return 0; + msleep(100); + ms += 100; + } + return -ETIMEDOUT; + } + return 0; +} + +/** + * t4_fw_upgrade - perform all of the steps necessary to upgrade FW + * @adap: the adapter + * @mbox: mailbox to use for the FW RESET command (if desired) + * @fw_data: the firmware image to write + * @size: image size + * @force: force upgrade even if firmware doesn't cooperate + * + * Perform all of the steps necessary for upgrading an adapter's + * firmware image. Normally this requires the cooperation of the + * existing firmware in order to halt all existing activities + * but if an invalid mailbox token is passed in we skip that step + * (though we'll still put the adapter microprocessor into RESET in + * that case). + * + * On successful return the new firmware will have been loaded and + * the adapter will have been fully RESET losing all previous setup + * state. On unsuccessful return the adapter may be completely hosed ... + * positive errno indicates that the adapter is ~probably~ intact, a + * negative errno indicates that things are looking bad ... + */ +int t4_fw_upgrade(struct adapter *adap, unsigned int mbox, + const u8 *fw_data, unsigned int size, int force) +{ + const struct fw_hdr *fw_hdr = (const struct fw_hdr *)fw_data; + int reset, ret; + + ret = t4_fw_halt(adap, mbox, force); + if (ret < 0 && !force) + return ret; + + ret = t4_load_fw(adap, fw_data, size); + if (ret < 0) + return ret; + + /* + * Older versions of the firmware don't understand the new + * PCIE_FW.HALT flag and so won't know to perform a RESET when they + * restart. So for newly loaded older firmware we'll have to do the + * RESET for it so it starts up on a clean slate. We can tell if + * the newly loaded firmware will handle this right by checking + * its header flags to see if it advertises the capability. + */ + reset = ((ntohl(fw_hdr->flags) & FW_HDR_FLAGS_RESET_HALT) == 0); + return t4_fw_restart(adap, mbox, reset); +} + + /** * t4_fw_config_file - setup an adapter via a Configuration File * @adap: the adapter diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 732c6da2636f..a1a8b57200f6 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -321,6 +321,8 @@ #define WINDOW(x) ((x) << WINDOW_SHIFT) #define PCIE_MEM_ACCESS_OFFSET 0x306c +#define PCIE_FW 0x30b8 + #define PCIE_CORE_UTL_SYSTEM_BUS_AGENT_STATUS 0x5908 #define RNPP 0x80000000U #define RPCP 0x20000000U @@ -419,6 +421,7 @@ #define CIM_BOOT_CFG 0x7b00 #define BOOTADDR_MASK 0xffffff00U +#define UPCRST 0x1U #define CIM_PF_MAILBOX_DATA 0x240 #define CIM_PF_MAILBOX_CTRL 0x280 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index b1d556128f84..a6364632b490 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -317,9 +317,15 @@ struct fw_reset_cmd { __be32 op_to_write; __be32 retval_len16; __be32 val; - __be32 r3; + __be32 halt_pkd; }; +#define FW_RESET_CMD_HALT_SHIFT 31 +#define FW_RESET_CMD_HALT_MASK 0x1 +#define FW_RESET_CMD_HALT(x) ((x) << FW_RESET_CMD_HALT_SHIFT) +#define FW_RESET_CMD_HALT_GET(x) \ + (((x) >> FW_RESET_CMD_HALT_SHIFT) & FW_RESET_CMD_HALT_MASK) + enum fw_hellow_cmd { fw_hello_cmd_stage_os = 0x0 }; @@ -1648,6 +1654,7 @@ struct fw_debug_cmd { #define FW_PCIE_FW_ERR (1U << 31) #define FW_PCIE_FW_INIT (1U << 30) +#define FW_PCIE_FW_HALT (1U << 29) #define FW_PCIE_FW_MASTER_VLD (1U << 15) #define FW_PCIE_FW_MASTER_MASK 0x7 #define FW_PCIE_FW_MASTER_SHIFT 12 @@ -1669,7 +1676,11 @@ struct fw_hdr { u8 intfver_iscsi; u8 intfver_fcoe; u8 reserved2; - __be32 reserved3[27]; + __u32 reserved3; + __u32 reserved4; + __u32 reserved5; + __be32 flags; + __be32 reserved6[23]; }; #define FW_HDR_FW_VER_MAJOR_GET(x) (((x) >> 24) & 0xff) @@ -1677,4 +1688,8 @@ struct fw_hdr { #define FW_HDR_FW_VER_MICRO_GET(x) (((x) >> 8) & 0xff) #define FW_HDR_FW_VER_BUILD_GET(x) (((x) >> 0) & 0xff) +enum fw_hdr_flags { + FW_HDR_FLAGS_RESET_HALT = 0x00000001, +}; + #endif /* _T4FW_INTERFACE_H_ */ -- cgit v1.2.3 From 51af6d7c1f31e0f3d42c87d53657ec7acb6e3462 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Tue, 25 Sep 2012 02:50:42 +0000 Subject: be2net: fix vfs enumeration Current VFs enumeration algorithm used in be_find_vfs does not take domain number into the match. The match found in igb/ixgbe is more elegant and safe. Signed-off-by: Ivan Vecera Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 84379f4fe837..966d9afb652f 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1076,7 +1076,7 @@ static int be_set_vf_tx_rate(struct net_device *netdev, static int be_find_vfs(struct be_adapter *adapter, int vf_state) { struct pci_dev *dev, *pdev = adapter->pdev; - int vfs = 0, assigned_vfs = 0, pos, vf_fn; + int vfs = 0, assigned_vfs = 0, pos; u16 offset, stride; pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); @@ -1087,9 +1087,7 @@ static int be_find_vfs(struct be_adapter *adapter, int vf_state) dev = pci_get_device(pdev->vendor, PCI_ANY_ID, NULL); while (dev) { - vf_fn = (pdev->devfn + offset + stride * vfs) & 0xFFFF; - if (dev->is_virtfn && dev->devfn == vf_fn && - dev->bus->number == pdev->bus->number) { + if (dev->is_virtfn && dev->physfn == pdev) { vfs++; if (dev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) assigned_vfs++; -- cgit v1.2.3 From e905ed57baa82e15ce9c158a8f1e81f171042504 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 27 Sep 2012 18:31:58 -0400 Subject: bna: Fix warning false positive. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit GCC can't see that in all non-error-return paths we do in fact set *using_dac to something. Add an explicit initialization to remove this warning: drivers/net/ethernet/brocade/bna/bnad.c: In function ‘bnad_pci_probe’: drivers/net/ethernet/brocade/bna/bnad.c:3079:5: warning: ‘using_dac’ may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/ethernet/brocade/bna/bnad.c:3233:7: note: ‘using_dac’ was declared here Signed-off-by: David S. Miller --- drivers/net/ethernet/brocade/bna/bnad.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index b441f33258e7..ce1eac529470 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -3268,6 +3268,7 @@ bnad_pci_probe(struct pci_dev *pdev, * Output : using_dac = 1 for 64 bit DMA * = 0 for 32 bit DMA */ + using_dac = false; err = bnad_pci_init(bnad, pdev, &using_dac); if (err) goto unlock_mutex; -- cgit v1.2.3 From d9f72f359e00a45a6cd7cc2d5121b04b9dc927e1 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 27 Sep 2012 22:19:02 -0400 Subject: Revert "be2net: fix vfs enumeration" This reverts commit 51af6d7c1f31e0f3d42c87d53657ec7acb6e3462. Breaks the build with CONFIG_PCI_ATS not enabled. Reported-by: Stephen Rothwell Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 966d9afb652f..84379f4fe837 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1076,7 +1076,7 @@ static int be_set_vf_tx_rate(struct net_device *netdev, static int be_find_vfs(struct be_adapter *adapter, int vf_state) { struct pci_dev *dev, *pdev = adapter->pdev; - int vfs = 0, assigned_vfs = 0, pos; + int vfs = 0, assigned_vfs = 0, pos, vf_fn; u16 offset, stride; pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); @@ -1087,7 +1087,9 @@ static int be_find_vfs(struct be_adapter *adapter, int vf_state) dev = pci_get_device(pdev->vendor, PCI_ANY_ID, NULL); while (dev) { - if (dev->is_virtfn && dev->physfn == pdev) { + vf_fn = (pdev->devfn + offset + stride * vfs) & 0xFFFF; + if (dev->is_virtfn && dev->devfn == vf_fn && + dev->bus->number == pdev->bus->number) { vfs++; if (dev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) assigned_vfs++; -- cgit v1.2.3 From 49a359e31762f798f3abef00c7d6b807a644eadf Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 28 Sep 2012 07:12:37 +0000 Subject: tg3: Introduce separate functions to allocate/free RX/TX rings. This is preparation work to allow the number of RX and TX rings to be configured separately. Reviewed-by: Nithin Nayak Sujir Reviewed-by: Benjamin Li Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 220 +++++++++++++++++++++++------------- drivers/net/ethernet/broadcom/tg3.h | 2 + 2 files changed, 146 insertions(+), 76 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index bf906c51d82a..93b8120bbf68 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -7607,15 +7607,11 @@ static int tg3_init_rings(struct tg3 *tp) return 0; } -/* - * Must not be invoked with interrupt sources disabled and - * the hardware shutdown down. - */ -static void tg3_free_consistent(struct tg3 *tp) +static void tg3_mem_tx_release(struct tg3 *tp) { int i; - for (i = 0; i < tp->irq_cnt; i++) { + for (i = 0; i < tp->irq_max; i++) { struct tg3_napi *tnapi = &tp->napi[i]; if (tnapi->tx_ring) { @@ -7626,17 +7622,114 @@ static void tg3_free_consistent(struct tg3 *tp) kfree(tnapi->tx_buffers); tnapi->tx_buffers = NULL; + } +} - if (tnapi->rx_rcb) { - dma_free_coherent(&tp->pdev->dev, - TG3_RX_RCB_RING_BYTES(tp), - tnapi->rx_rcb, - tnapi->rx_rcb_mapping); - tnapi->rx_rcb = NULL; - } +static int tg3_mem_tx_acquire(struct tg3 *tp) +{ + int i; + struct tg3_napi *tnapi = &tp->napi[0]; + + /* If multivector TSS is enabled, vector 0 does not handle + * tx interrupts. Don't allocate any resources for it. + */ + if (tg3_flag(tp, ENABLE_TSS)) + tnapi++; + + for (i = 0; i < tp->txq_cnt; i++, tnapi++) { + tnapi->tx_buffers = kzalloc(sizeof(struct tg3_tx_ring_info) * + TG3_TX_RING_SIZE, GFP_KERNEL); + if (!tnapi->tx_buffers) + goto err_out; + + tnapi->tx_ring = dma_alloc_coherent(&tp->pdev->dev, + TG3_TX_RING_BYTES, + &tnapi->tx_desc_mapping, + GFP_KERNEL); + if (!tnapi->tx_ring) + goto err_out; + } + + return 0; + +err_out: + tg3_mem_tx_release(tp); + return -ENOMEM; +} + +static void tg3_mem_rx_release(struct tg3 *tp) +{ + int i; + + for (i = 0; i < tp->irq_max; i++) { + struct tg3_napi *tnapi = &tp->napi[i]; tg3_rx_prodring_fini(tp, &tnapi->prodring); + if (!tnapi->rx_rcb) + continue; + + dma_free_coherent(&tp->pdev->dev, + TG3_RX_RCB_RING_BYTES(tp), + tnapi->rx_rcb, + tnapi->rx_rcb_mapping); + tnapi->rx_rcb = NULL; + } +} + +static int tg3_mem_rx_acquire(struct tg3 *tp) +{ + unsigned int i, limit; + + limit = tp->rxq_cnt; + + /* If RSS is enabled, we need a (dummy) producer ring + * set on vector zero. This is the true hw prodring. + */ + if (tg3_flag(tp, ENABLE_RSS)) + limit++; + + for (i = 0; i < limit; i++) { + struct tg3_napi *tnapi = &tp->napi[i]; + + if (tg3_rx_prodring_init(tp, &tnapi->prodring)) + goto err_out; + + /* If multivector RSS is enabled, vector 0 + * does not handle rx or tx interrupts. + * Don't allocate any resources for it. + */ + if (!i && tg3_flag(tp, ENABLE_RSS)) + continue; + + tnapi->rx_rcb = dma_alloc_coherent(&tp->pdev->dev, + TG3_RX_RCB_RING_BYTES(tp), + &tnapi->rx_rcb_mapping, + GFP_KERNEL); + if (!tnapi->rx_rcb) + goto err_out; + + memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp)); + } + + return 0; + +err_out: + tg3_mem_rx_release(tp); + return -ENOMEM; +} + +/* + * Must not be invoked with interrupt sources disabled and + * the hardware shutdown down. + */ +static void tg3_free_consistent(struct tg3 *tp) +{ + int i; + + for (i = 0; i < tp->irq_cnt; i++) { + struct tg3_napi *tnapi = &tp->napi[i]; + if (tnapi->hw_status) { dma_free_coherent(&tp->pdev->dev, TG3_HW_STATUS_SIZE, tnapi->hw_status, @@ -7645,6 +7738,9 @@ static void tg3_free_consistent(struct tg3 *tp) } } + tg3_mem_rx_release(tp); + tg3_mem_tx_release(tp); + if (tp->hw_stats) { dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats), tp->hw_stats, tp->stats_mapping); @@ -7683,72 +7779,38 @@ static int tg3_alloc_consistent(struct tg3 *tp) memset(tnapi->hw_status, 0, TG3_HW_STATUS_SIZE); sblk = tnapi->hw_status; - if (tg3_rx_prodring_init(tp, &tnapi->prodring)) - goto err_out; + if (tg3_flag(tp, ENABLE_RSS)) { + u16 *prodptr = 0; - /* If multivector TSS is enabled, vector 0 does not handle - * tx interrupts. Don't allocate any resources for it. - */ - if ((!i && !tg3_flag(tp, ENABLE_TSS)) || - (i && tg3_flag(tp, ENABLE_TSS))) { - tnapi->tx_buffers = kzalloc( - sizeof(struct tg3_tx_ring_info) * - TG3_TX_RING_SIZE, GFP_KERNEL); - if (!tnapi->tx_buffers) - goto err_out; - - tnapi->tx_ring = dma_alloc_coherent(&tp->pdev->dev, - TG3_TX_RING_BYTES, - &tnapi->tx_desc_mapping, - GFP_KERNEL); - if (!tnapi->tx_ring) - goto err_out; - } - - /* - * When RSS is enabled, the status block format changes - * slightly. The "rx_jumbo_consumer", "reserved", - * and "rx_mini_consumer" members get mapped to the - * other three rx return ring producer indexes. - */ - switch (i) { - default: - if (tg3_flag(tp, ENABLE_RSS)) { - tnapi->rx_rcb_prod_idx = NULL; + /* + * When RSS is enabled, the status block format changes + * slightly. The "rx_jumbo_consumer", "reserved", + * and "rx_mini_consumer" members get mapped to the + * other three rx return ring producer indexes. + */ + switch (i) { + case 1: + prodptr = &sblk->idx[0].rx_producer; + break; + case 2: + prodptr = &sblk->rx_jumbo_consumer; + break; + case 3: + prodptr = &sblk->reserved; + break; + case 4: + prodptr = &sblk->rx_mini_consumer; break; } - /* Fall through */ - case 1: + tnapi->rx_rcb_prod_idx = prodptr; + } else { tnapi->rx_rcb_prod_idx = &sblk->idx[0].rx_producer; - break; - case 2: - tnapi->rx_rcb_prod_idx = &sblk->rx_jumbo_consumer; - break; - case 3: - tnapi->rx_rcb_prod_idx = &sblk->reserved; - break; - case 4: - tnapi->rx_rcb_prod_idx = &sblk->rx_mini_consumer; - break; } - - /* - * If multivector RSS is enabled, vector 0 does not handle - * rx or tx interrupts. Don't allocate any resources for it. - */ - if (!i && tg3_flag(tp, ENABLE_RSS)) - continue; - - tnapi->rx_rcb = dma_alloc_coherent(&tp->pdev->dev, - TG3_RX_RCB_RING_BYTES(tp), - &tnapi->rx_rcb_mapping, - GFP_KERNEL); - if (!tnapi->rx_rcb) - goto err_out; - - memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp)); } + if (tg3_mem_tx_acquire(tp) || tg3_mem_rx_acquire(tp)) + goto err_out; + return 0; err_out: @@ -10154,6 +10216,7 @@ static bool tg3_enable_msix(struct tg3 *tp) * one to the number of vectors we are requesting. */ tp->irq_cnt = min_t(unsigned, tp->irq_cnt + 1, tp->irq_max); + tp->rxq_cnt = tp->irq_cnt - 1; } for (i = 0; i < tp->irq_max; i++) { @@ -10170,14 +10233,13 @@ static bool tg3_enable_msix(struct tg3 *tp) netdev_notice(tp->dev, "Requested %d MSI-X vectors, received %d\n", tp->irq_cnt, rc); tp->irq_cnt = rc; + tp->rxq_cnt = max(rc - 1, 1); } for (i = 0; i < tp->irq_max; i++) tp->napi[i].irq_vec = msix_ent[i].vector; - netif_set_real_num_tx_queues(tp->dev, 1); - rc = tp->irq_cnt > 1 ? tp->irq_cnt - 1 : 1; - if (netif_set_real_num_rx_queues(tp->dev, rc)) { + if (netif_set_real_num_rx_queues(tp->dev, tp->rxq_cnt)) { pci_disable_msix(tp->pdev); return false; } @@ -10188,7 +10250,8 @@ static bool tg3_enable_msix(struct tg3 *tp) if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720) { tg3_flag_set(tp, ENABLE_TSS); - netif_set_real_num_tx_queues(tp->dev, tp->irq_cnt - 1); + tp->txq_cnt = tp->rxq_cnt; + netif_set_real_num_tx_queues(tp->dev, tp->txq_cnt); } } @@ -10224,6 +10287,11 @@ defcfg: if (!tg3_flag(tp, USING_MSIX)) { tp->irq_cnt = 1; tp->napi[0].irq_vec = tp->pdev->irq; + } + + if (tp->irq_cnt == 1) { + tp->txq_cnt = 1; + tp->rxq_cnt = 1; netif_set_real_num_tx_queues(tp->dev, 1); netif_set_real_num_rx_queues(tp->dev, 1); } diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index 6d52cb286826..5838dea79563 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -3037,6 +3037,7 @@ struct tg3 { void (*write32_tx_mbox) (struct tg3 *, u32, u32); u32 dma_limit; + u32 txq_cnt; /* begin "rx thread" cacheline section */ struct tg3_napi napi[TG3_IRQ_MAX_VECS]; @@ -3051,6 +3052,7 @@ struct tg3 { u32 rx_std_max_post; u32 rx_offset; u32 rx_pkt_map_sz; + u32 rxq_cnt; bool rx_refill; -- cgit v1.2.3 From 9102426a87f9b7edb943e17f76d46ee412083e10 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 28 Sep 2012 07:12:38 +0000 Subject: tg3: Allow number of rx and tx rings to be set independently. irq_cnt is no longer necessarily equal to the number rx or tx rings. Reviewed-by: Nithin Nayak Sujir Reviewed-by: Benjamin Li Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 74 ++++++++++++++++++++++++------------- drivers/net/ethernet/broadcom/tg3.h | 5 ++- 2 files changed, 53 insertions(+), 26 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 93b8120bbf68..330356bdaf0c 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6278,7 +6278,7 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget) u32 jmb_prod_idx = dpr->rx_jmb_prod_idx; tp->rx_refill = false; - for (i = 1; i < tp->irq_cnt; i++) + for (i = 1; i <= tp->rxq_cnt; i++) err |= tg3_rx_prodring_xfer(tp, dpr, &tp->napi[i].prodring); @@ -8654,13 +8654,12 @@ static void __tg3_set_rx_mode(struct net_device *dev) } } -static void tg3_rss_init_dflt_indir_tbl(struct tg3 *tp) +static void tg3_rss_init_dflt_indir_tbl(struct tg3 *tp, u32 qcnt) { int i; for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++) - tp->rss_ind_tbl[i] = - ethtool_rxfh_indir_default(i, tp->irq_cnt - 1); + tp->rss_ind_tbl[i] = ethtool_rxfh_indir_default(i, qcnt); } static void tg3_rss_check_indir_tbl(struct tg3 *tp) @@ -8682,7 +8681,7 @@ static void tg3_rss_check_indir_tbl(struct tg3 *tp) } if (i != TG3_RSS_INDIR_TBL_SIZE) - tg3_rss_init_dflt_indir_tbl(tp); + tg3_rss_init_dflt_indir_tbl(tp, tp->rxq_cnt); } static void tg3_rss_write_indir_tbl(struct tg3 *tp) @@ -10203,22 +10202,36 @@ static int tg3_request_firmware(struct tg3 *tp) return 0; } -static bool tg3_enable_msix(struct tg3 *tp) +static u32 tg3_irq_count(struct tg3 *tp) { - int i, rc; - struct msix_entry msix_ent[tp->irq_max]; + u32 irq_cnt = max(tp->rxq_cnt, tp->txq_cnt); - tp->irq_cnt = netif_get_num_default_rss_queues(); - if (tp->irq_cnt > 1) { + if (irq_cnt > 1) { /* We want as many rx rings enabled as there are cpus. * In multiqueue MSI-X mode, the first MSI-X vector * only deals with link interrupts, etc, so we add * one to the number of vectors we are requesting. */ - tp->irq_cnt = min_t(unsigned, tp->irq_cnt + 1, tp->irq_max); - tp->rxq_cnt = tp->irq_cnt - 1; + irq_cnt = min_t(unsigned, irq_cnt + 1, tp->irq_max); } + return irq_cnt; +} + +static bool tg3_enable_msix(struct tg3 *tp) +{ + int i, rc; + struct msix_entry msix_ent[tp->irq_max]; + + tp->rxq_cnt = netif_get_num_default_rss_queues(); + if (tp->rxq_cnt > tp->rxq_max) + tp->rxq_cnt = tp->rxq_max; + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720) + tp->txq_cnt = min(tp->rxq_cnt, tp->txq_max); + + tp->irq_cnt = tg3_irq_count(tp); + for (i = 0; i < tp->irq_max; i++) { msix_ent[i].entry = i; msix_ent[i].vector = 0; @@ -10234,6 +10247,8 @@ static bool tg3_enable_msix(struct tg3 *tp) tp->irq_cnt, rc); tp->irq_cnt = rc; tp->rxq_cnt = max(rc - 1, 1); + if (tp->txq_cnt) + tp->txq_cnt = min(tp->rxq_cnt, tp->txq_max); } for (i = 0; i < tp->irq_max; i++) @@ -10244,16 +10259,15 @@ static bool tg3_enable_msix(struct tg3 *tp) return false; } - if (tp->irq_cnt > 1) { - tg3_flag_set(tp, ENABLE_RSS); + if (tp->irq_cnt == 1) + return true; - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720) { - tg3_flag_set(tp, ENABLE_TSS); - tp->txq_cnt = tp->rxq_cnt; - netif_set_real_num_tx_queues(tp->dev, tp->txq_cnt); - } - } + tg3_flag_set(tp, ENABLE_RSS); + + if (tp->txq_cnt > 1) + tg3_flag_set(tp, ENABLE_TSS); + + netif_set_real_num_tx_queues(tp->dev, tp->txq_cnt); return true; } @@ -11275,11 +11289,11 @@ static int tg3_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, switch (info->cmd) { case ETHTOOL_GRXRINGS: if (netif_running(tp->dev)) - info->data = tp->irq_cnt; + info->data = tp->rxq_cnt; else { info->data = num_online_cpus(); - if (info->data > TG3_IRQ_MAX_VECS_RSS) - info->data = TG3_IRQ_MAX_VECS_RSS; + if (info->data > TG3_RSS_MAX_NUM_QS) + info->data = TG3_RSS_MAX_NUM_QS; } /* The first interrupt vector only @@ -14600,10 +14614,20 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) if (tg3_flag(tp, 57765_PLUS)) { tg3_flag_set(tp, SUPPORT_MSIX); tp->irq_max = TG3_IRQ_MAX_VECS; - tg3_rss_init_dflt_indir_tbl(tp); } } + tp->txq_max = 1; + tp->rxq_max = 1; + if (tp->irq_max > 1) { + tp->rxq_max = TG3_RSS_MAX_NUM_QS; + tg3_rss_init_dflt_indir_tbl(tp, TG3_RSS_MAX_NUM_QS); + + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720) + tp->txq_max = tp->irq_max - 1; + } + if (tg3_flag(tp, 5755_PLUS) || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) tg3_flag_set(tp, SHORT_DMA_BUG); diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index 5838dea79563..2abe94cfd47f 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -2860,7 +2860,8 @@ struct tg3_rx_prodring_set { dma_addr_t rx_jmb_mapping; }; -#define TG3_IRQ_MAX_VECS_RSS 5 +#define TG3_RSS_MAX_NUM_QS 4 +#define TG3_IRQ_MAX_VECS_RSS (TG3_RSS_MAX_NUM_QS + 1) #define TG3_IRQ_MAX_VECS TG3_IRQ_MAX_VECS_RSS struct tg3_napi { @@ -3038,6 +3039,7 @@ struct tg3 { u32); u32 dma_limit; u32 txq_cnt; + u32 txq_max; /* begin "rx thread" cacheline section */ struct tg3_napi napi[TG3_IRQ_MAX_VECS]; @@ -3053,6 +3055,7 @@ struct tg3 { u32 rx_offset; u32 rx_pkt_map_sz; u32 rxq_cnt; + u32 rxq_max; bool rx_refill; -- cgit v1.2.3 From a489b6d999547799b789ad0683f867d3ae5ed128 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 28 Sep 2012 07:12:39 +0000 Subject: tg3: Separate coalescing setup for rx and tx since the number of rings can be different. Reviewed-by: Nithin Nayak Sujir Reviewed-by: Benjamin Li Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 74 ++++++++++++++++++++++--------------- 1 file changed, 45 insertions(+), 29 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 330356bdaf0c..ddf260cc2db7 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -8331,9 +8331,10 @@ static void tg3_set_bdinfo(struct tg3 *tp, u32 bdinfo_addr, nic_addr); } -static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec) + +static void tg3_coal_tx_init(struct tg3 *tp, struct ethtool_coalesce *ec) { - int i; + int i = 0; if (!tg3_flag(tp, ENABLE_TSS)) { tw32(HOSTCC_TXCOL_TICKS, ec->tx_coalesce_usecs); @@ -8343,31 +8344,43 @@ static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec) tw32(HOSTCC_TXCOL_TICKS, 0); tw32(HOSTCC_TXMAX_FRAMES, 0); tw32(HOSTCC_TXCOAL_MAXF_INT, 0); + + for (; i < tp->txq_cnt; i++) { + u32 reg; + + reg = HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18; + tw32(reg, ec->tx_coalesce_usecs); + reg = HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18; + tw32(reg, ec->tx_max_coalesced_frames); + reg = HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18; + tw32(reg, ec->tx_max_coalesced_frames_irq); + } + } + + for (; i < tp->irq_max - 1; i++) { + tw32(HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18, 0); + tw32(HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18, 0); + tw32(HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18, 0); } +} + +static void tg3_coal_rx_init(struct tg3 *tp, struct ethtool_coalesce *ec) +{ + int i = 0; + u32 limit = tp->rxq_cnt; if (!tg3_flag(tp, ENABLE_RSS)) { tw32(HOSTCC_RXCOL_TICKS, ec->rx_coalesce_usecs); tw32(HOSTCC_RXMAX_FRAMES, ec->rx_max_coalesced_frames); tw32(HOSTCC_RXCOAL_MAXF_INT, ec->rx_max_coalesced_frames_irq); + limit--; } else { tw32(HOSTCC_RXCOL_TICKS, 0); tw32(HOSTCC_RXMAX_FRAMES, 0); tw32(HOSTCC_RXCOAL_MAXF_INT, 0); } - if (!tg3_flag(tp, 5705_PLUS)) { - u32 val = ec->stats_block_coalesce_usecs; - - tw32(HOSTCC_RXCOAL_TICK_INT, ec->rx_coalesce_usecs_irq); - tw32(HOSTCC_TXCOAL_TICK_INT, ec->tx_coalesce_usecs_irq); - - if (!netif_carrier_ok(tp->dev)) - val = 0; - - tw32(HOSTCC_STAT_COAL_TICKS, val); - } - - for (i = 0; i < tp->irq_cnt - 1; i++) { + for (; i < limit; i++) { u32 reg; reg = HOSTCC_RXCOL_TICKS_VEC1 + i * 0x18; @@ -8376,27 +8389,30 @@ static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec) tw32(reg, ec->rx_max_coalesced_frames); reg = HOSTCC_RXCOAL_MAXF_INT_VEC1 + i * 0x18; tw32(reg, ec->rx_max_coalesced_frames_irq); - - if (tg3_flag(tp, ENABLE_TSS)) { - reg = HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18; - tw32(reg, ec->tx_coalesce_usecs); - reg = HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18; - tw32(reg, ec->tx_max_coalesced_frames); - reg = HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18; - tw32(reg, ec->tx_max_coalesced_frames_irq); - } } for (; i < tp->irq_max - 1; i++) { tw32(HOSTCC_RXCOL_TICKS_VEC1 + i * 0x18, 0); tw32(HOSTCC_RXMAX_FRAMES_VEC1 + i * 0x18, 0); tw32(HOSTCC_RXCOAL_MAXF_INT_VEC1 + i * 0x18, 0); + } +} - if (tg3_flag(tp, ENABLE_TSS)) { - tw32(HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18, 0); - tw32(HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18, 0); - tw32(HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18, 0); - } +static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec) +{ + tg3_coal_tx_init(tp, ec); + tg3_coal_rx_init(tp, ec); + + if (!tg3_flag(tp, 5705_PLUS)) { + u32 val = ec->stats_block_coalesce_usecs; + + tw32(HOSTCC_RXCOAL_TICK_INT, ec->rx_coalesce_usecs_irq); + tw32(HOSTCC_TXCOAL_TICK_INT, ec->tx_coalesce_usecs_irq); + + if (!netif_carrier_ok(tp->dev)) + val = 0; + + tw32(HOSTCC_STAT_COAL_TICKS, val); } } -- cgit v1.2.3 From d8f4cd3880eff5a382ca6771062e91b58b2955db Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 28 Sep 2012 07:12:40 +0000 Subject: tg3: Refactor tg3_open() by introducing tg3_start() that handles all initialization steps from IRQ allocation. This function will be needed when adding support for changing the number of rx and tx rings. Reviewed-by: Nithin Nayak Sujir Reviewed-by: Benjamin Li Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 78 +++++++++++++++++++++---------------- 1 file changed, 45 insertions(+), 33 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index ddf260cc2db7..9bd99ce46e5f 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -10339,38 +10339,11 @@ static void tg3_ints_fini(struct tg3 *tp) tg3_flag_clear(tp, ENABLE_TSS); } -static int tg3_open(struct net_device *dev) +static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq) { - struct tg3 *tp = netdev_priv(dev); + struct net_device *dev = tp->dev; int i, err; - if (tp->fw_needed) { - err = tg3_request_firmware(tp); - if (tp->pci_chip_rev_id == CHIPREV_ID_5701_A0) { - if (err) - return err; - } else if (err) { - netdev_warn(tp->dev, "TSO capability disabled\n"); - tg3_flag_clear(tp, TSO_CAPABLE); - } else if (!tg3_flag(tp, TSO_CAPABLE)) { - netdev_notice(tp->dev, "TSO capability restored\n"); - tg3_flag_set(tp, TSO_CAPABLE); - } - } - - netif_carrier_off(tp->dev); - - err = tg3_power_up(tp); - if (err) - return err; - - tg3_full_lock(tp, 0); - - tg3_disable_ints(tp); - tg3_flag_clear(tp, INIT_COMPLETE); - - tg3_full_unlock(tp); - /* * Setup interrupts first so we know how * many NAPI resources to allocate @@ -10404,7 +10377,7 @@ static int tg3_open(struct net_device *dev) tg3_full_lock(tp, 0); - err = tg3_init_hw(tp, 1); + err = tg3_init_hw(tp, reset_phy); if (err) { tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); tg3_free_rings(tp); @@ -10415,7 +10388,7 @@ static int tg3_open(struct net_device *dev) if (err) goto err_out3; - if (tg3_flag(tp, USING_MSI)) { + if (test_irq && tg3_flag(tp, USING_MSI)) { err = tg3_test_msi(tp); if (err) { @@ -10471,8 +10444,47 @@ err_out2: err_out1: tg3_ints_fini(tp); - tg3_frob_aux_power(tp, false); - pci_set_power_state(tp->pdev, PCI_D3hot); + + return err; +} + +static int tg3_open(struct net_device *dev) +{ + struct tg3 *tp = netdev_priv(dev); + int err; + + if (tp->fw_needed) { + err = tg3_request_firmware(tp); + if (tp->pci_chip_rev_id == CHIPREV_ID_5701_A0) { + if (err) + return err; + } else if (err) { + netdev_warn(tp->dev, "TSO capability disabled\n"); + tg3_flag_clear(tp, TSO_CAPABLE); + } else if (!tg3_flag(tp, TSO_CAPABLE)) { + netdev_notice(tp->dev, "TSO capability restored\n"); + tg3_flag_set(tp, TSO_CAPABLE); + } + } + + netif_carrier_off(tp->dev); + + err = tg3_power_up(tp); + if (err) + return err; + + tg3_full_lock(tp, 0); + + tg3_disable_ints(tp); + tg3_flag_clear(tp, INIT_COMPLETE); + + tg3_full_unlock(tp); + + err = tg3_start(tp, true, true); + if (err) { + tg3_frob_aux_power(tp, false); + pci_set_power_state(tp->pdev, PCI_D3hot); + } return err; } -- cgit v1.2.3 From 6513859479b0fe1232cddd100db269191c1691e1 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 28 Sep 2012 07:12:41 +0000 Subject: tg3: Refactor tg3_close() by introducing tg3_stop() that does the opposite of tg3_start(). This function will be useful when adding the support for changing the numbe of rx and tx rings. Reviewed-by: Nithin Nayak Sujir Reviewed-by: Benjamin Li Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 70 ++++++++++++++++++++----------------- 1 file changed, 38 insertions(+), 32 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 9bd99ce46e5f..3f2197e41a52 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -10448,6 +10448,43 @@ err_out1: return err; } +static void tg3_stop(struct tg3 *tp) +{ + int i; + + tg3_napi_disable(tp); + tg3_reset_task_cancel(tp); + + netif_tx_disable(tp->dev); + + tg3_timer_stop(tp); + + tg3_hwmon_close(tp); + + tg3_phy_stop(tp); + + tg3_full_lock(tp, 1); + + tg3_disable_ints(tp); + + tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); + tg3_free_rings(tp); + tg3_flag_clear(tp, INIT_COMPLETE); + + tg3_full_unlock(tp); + + for (i = tp->irq_cnt - 1; i >= 0; i--) { + struct tg3_napi *tnapi = &tp->napi[i]; + free_irq(tnapi->irq_vec, tnapi); + } + + tg3_ints_fini(tp); + + tg3_napi_fini(tp); + + tg3_free_consistent(tp); +} + static int tg3_open(struct net_device *dev) { struct tg3 *tp = netdev_priv(dev); @@ -10490,45 +10527,14 @@ static int tg3_open(struct net_device *dev) static int tg3_close(struct net_device *dev) { - int i; struct tg3 *tp = netdev_priv(dev); - tg3_napi_disable(tp); - tg3_reset_task_cancel(tp); - - netif_tx_stop_all_queues(dev); - - tg3_timer_stop(tp); - - tg3_hwmon_close(tp); - - tg3_phy_stop(tp); - - tg3_full_lock(tp, 1); - - tg3_disable_ints(tp); - - tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); - tg3_free_rings(tp); - tg3_flag_clear(tp, INIT_COMPLETE); - - tg3_full_unlock(tp); - - for (i = tp->irq_cnt - 1; i >= 0; i--) { - struct tg3_napi *tnapi = &tp->napi[i]; - free_irq(tnapi->irq_vec, tnapi); - } - - tg3_ints_fini(tp); + tg3_stop(tp); /* Clear stats across close / open calls */ memset(&tp->net_stats_prev, 0, sizeof(tp->net_stats_prev)); memset(&tp->estats_prev, 0, sizeof(tp->estats_prev)); - tg3_napi_fini(tp); - - tg3_free_consistent(tp); - tg3_power_down(tp); netif_carrier_off(tp->dev); -- cgit v1.2.3 From 0968169c9271ddf05a7531274ffe4829f9d068b2 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 28 Sep 2012 07:12:42 +0000 Subject: tg3: Add support for ethtool -L|-l to get/set the number of rings. Default remains the same. Reviewed-by: Nithin Nayak Sujir Reviewed-by: Benjamin Li Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 64 +++++++++++++++++++++++++++++++++++-- drivers/net/ethernet/broadcom/tg3.h | 2 ++ 2 files changed, 63 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 3f2197e41a52..74eea2fbb4fe 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -10239,11 +10239,15 @@ static bool tg3_enable_msix(struct tg3 *tp) int i, rc; struct msix_entry msix_ent[tp->irq_max]; - tp->rxq_cnt = netif_get_num_default_rss_queues(); + tp->txq_cnt = tp->txq_req; + tp->rxq_cnt = tp->rxq_req; + if (!tp->rxq_cnt) + tp->rxq_cnt = netif_get_num_default_rss_queues(); if (tp->rxq_cnt > tp->rxq_max) tp->rxq_cnt = tp->rxq_max; - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720) + if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720) && + !tp->txq_req) tp->txq_cnt = min(tp->rxq_cnt, tp->txq_max); tp->irq_cnt = tg3_irq_count(tp); @@ -11384,6 +11388,58 @@ static int tg3_set_rxfh_indir(struct net_device *dev, const u32 *indir) return 0; } +static void tg3_get_channels(struct net_device *dev, + struct ethtool_channels *channel) +{ + struct tg3 *tp = netdev_priv(dev); + u32 deflt_qs = netif_get_num_default_rss_queues(); + + channel->max_rx = tp->rxq_max; + channel->max_tx = tp->txq_max; + + if (netif_running(dev)) { + channel->rx_count = tp->rxq_cnt; + channel->tx_count = tp->txq_cnt; + } else { + if (tp->rxq_req) + channel->rx_count = tp->rxq_req; + else + channel->rx_count = min(deflt_qs, tp->rxq_max); + + if (tp->txq_req) + channel->tx_count = tp->txq_req; + else + channel->tx_count = min(deflt_qs, tp->txq_max); + } +} + +static int tg3_set_channels(struct net_device *dev, + struct ethtool_channels *channel) +{ + struct tg3 *tp = netdev_priv(dev); + + if (!tg3_flag(tp, SUPPORT_MSIX)) + return -EOPNOTSUPP; + + if (channel->rx_count > tp->rxq_max || + channel->tx_count > tp->txq_max) + return -EINVAL; + + tp->rxq_req = channel->rx_count; + tp->txq_req = channel->tx_count; + + if (!netif_running(dev)) + return 0; + + tg3_stop(tp); + + netif_carrier_off(dev); + + tg3_start(tp, true, false); + + return 0; +} + static void tg3_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { switch (stringset) { @@ -12632,6 +12688,8 @@ static const struct ethtool_ops tg3_ethtool_ops = { .get_rxfh_indir_size = tg3_get_rxfh_indir_size, .get_rxfh_indir = tg3_get_rxfh_indir, .set_rxfh_indir = tg3_set_rxfh_indir, + .get_channels = tg3_get_channels, + .set_channels = tg3_set_channels, .get_ts_info = ethtool_op_get_ts_info, }; diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index 2abe94cfd47f..d9308c32102e 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -3038,6 +3038,7 @@ struct tg3 { void (*write32_tx_mbox) (struct tg3 *, u32, u32); u32 dma_limit; + u32 txq_req; u32 txq_cnt; u32 txq_max; @@ -3054,6 +3055,7 @@ struct tg3 { u32 rx_std_max_post; u32 rx_offset; u32 rx_pkt_map_sz; + u32 rxq_req; u32 rxq_cnt; u32 rxq_max; bool rx_refill; -- cgit v1.2.3 From cf6d6ea660f46a030a5185cf577856bdd547c2bf Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 28 Sep 2012 07:12:43 +0000 Subject: tg3: Disable multiple TX rings by default due to hardware flaw Simple round-robin hardware TX scheduling can cause starvation of TX rings with small packets when other TX rings have large TSO or jumbo packets. In the simplest case, consider 2 TCP streams running in opposite directions. The TSO TX traffic will hash to one ring and the ACKs for the incoming data on a different TCP connection will hash to a different TX ring. The hardware fetches one complete TSO packet (up to 64K data) before servicing the other TX ring. When it gets to the other TX ring, it will only fetch one packet (64-byte ACK packet in this case). After that, it will switch back to the 1st ring filled with more TSO packets. Because only one ACK can go out roughly every 500 usec in this case, the incoming data rate becomes very low. Update version to 3.125. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 74eea2fbb4fe..24f6623c82ab 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -92,10 +92,10 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits) #define DRV_MODULE_NAME "tg3" #define TG3_MAJ_NUM 3 -#define TG3_MIN_NUM 124 +#define TG3_MIN_NUM 125 #define DRV_MODULE_VERSION \ __stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM) -#define DRV_MODULE_RELDATE "March 21, 2012" +#define DRV_MODULE_RELDATE "September 26, 2012" #define RESET_KIND_SHUTDOWN 0 #define RESET_KIND_INIT 1 @@ -10245,10 +10245,13 @@ static bool tg3_enable_msix(struct tg3 *tp) tp->rxq_cnt = netif_get_num_default_rss_queues(); if (tp->rxq_cnt > tp->rxq_max) tp->rxq_cnt = tp->rxq_max; - if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720) && - !tp->txq_req) - tp->txq_cnt = min(tp->rxq_cnt, tp->txq_max); + + /* Disable multiple TX rings by default. Simple round-robin hardware + * scheduling of the TX rings can cause starvation of rings with + * small packets when other rings have TSO or jumbo packets. + */ + if (!tp->txq_req) + tp->txq_cnt = 1; tp->irq_cnt = tg3_irq_count(tp); -- cgit v1.2.3 From 5ee4979ba5e71307e67ba24a49aa59a3481ae766 Mon Sep 17 00:00:00 2001 From: Sathya Perla Date: Fri, 28 Sep 2012 04:39:41 +0000 Subject: be2net: remove type argument of be_cmd_mac_addr_query() All invocations of this routine use the same type value. Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_cmds.c | 4 ++-- drivers/net/ethernet/emulex/benet/be_cmds.h | 2 +- drivers/net/ethernet/emulex/benet/be_main.c | 18 ++++++------------ 3 files changed, 9 insertions(+), 15 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 701b3e9a715b..6fbfb207fa5a 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -717,7 +717,7 @@ int be_cmd_eq_create(struct be_adapter *adapter, /* Use MCC */ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, - u8 type, bool permanent, u32 if_handle, u32 pmac_id) + bool permanent, u32 if_handle, u32 pmac_id) { struct be_mcc_wrb *wrb; struct be_cmd_req_mac_query *req; @@ -734,7 +734,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_MAC_QUERY, sizeof(*req), wrb, NULL); - req->type = type; + req->type = MAC_ADDRESS_TYPE_NETWORK; if (permanent) { req->permanent = 1; } else { diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 250f19b5f7b6..1f5b83975f21 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -1687,7 +1687,7 @@ struct be_cmd_req_set_ext_fat_caps { extern int be_pci_fnum_get(struct be_adapter *adapter); extern int be_fw_wait_ready(struct be_adapter *adapter); extern int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, - u8 type, bool permanent, u32 if_handle, u32 pmac_id); + bool permanent, u32 if_handle, u32 pmac_id); extern int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, u32 if_id, u32 *pmac_id, u32 domain); extern int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 84379f4fe837..fa1743036a88 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -241,9 +241,8 @@ static int be_mac_addr_set(struct net_device *netdev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - status = be_cmd_mac_addr_query(adapter, current_mac, - MAC_ADDRESS_TYPE_NETWORK, false, - adapter->if_handle, 0); + status = be_cmd_mac_addr_query(adapter, current_mac, false, + adapter->if_handle, 0); if (status) goto err; @@ -2693,21 +2692,16 @@ static int be_get_mac_addr(struct be_adapter *adapter, u8 *mac, u32 if_handle, status = be_cmd_get_mac_from_list(adapter, mac, active_mac, pmac_id, 0); if (*active_mac) { - status = be_cmd_mac_addr_query(adapter, mac, - MAC_ADDRESS_TYPE_NETWORK, - false, if_handle, - *pmac_id); + status = be_cmd_mac_addr_query(adapter, mac, false, + if_handle, *pmac_id); } } else if (be_physfn(adapter)) { /* For BE3, for PF get permanent MAC */ - status = be_cmd_mac_addr_query(adapter, mac, - MAC_ADDRESS_TYPE_NETWORK, true, - 0, 0); + status = be_cmd_mac_addr_query(adapter, mac, true, 0, 0); *active_mac = false; } else { /* For BE3, for VF get soft MAC assigned by PF*/ - status = be_cmd_mac_addr_query(adapter, mac, - MAC_ADDRESS_TYPE_NETWORK, false, + status = be_cmd_mac_addr_query(adapter, mac, false, if_handle, 0); *active_mac = true; } -- cgit v1.2.3 From 55f5c3c55b5a682c4bb37628979c5909f9de7b30 Mon Sep 17 00:00:00 2001 From: Sathya Perla Date: Fri, 28 Sep 2012 04:39:42 +0000 Subject: be2net: fix wrong handling of be_setup() failure in be_probe() Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index fa1743036a88..b712091bc218 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3889,7 +3889,7 @@ static int __devinit be_probe(struct pci_dev *pdev, status = be_setup(adapter); if (status) - goto msix_disable; + goto stats_clean; be_netdev_init(netdev); status = register_netdev(netdev); @@ -3910,8 +3910,6 @@ static int __devinit be_probe(struct pci_dev *pdev, unsetup: be_clear(adapter); -msix_disable: - be_msix_disable(adapter); stats_clean: be_stats_cleanup(adapter); ctrl_clean: -- cgit v1.2.3 From 323ff71e566994f77761e221361de5b4a52a612f Mon Sep 17 00:00:00 2001 From: Sathya Perla Date: Fri, 28 Sep 2012 04:39:43 +0000 Subject: be2net: cleanup code related to be_link_status_query() 1) link_status_query() is always called to query the link-speed (speed after applying qos). When there is no qos setting, link-speed is derived from port-speed. Do all this inside this routine and hide this from the callers. 2) adpater->phy.forced_port_speed is not being set anywhere after being initialized. Get rid of this variable. 3) Ignore async link_speed notifications till the initial value has been fetched from FW. Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be.h | 1 - drivers/net/ethernet/emulex/benet/be_cmds.c | 46 +++++++++++++++------ drivers/net/ethernet/emulex/benet/be_cmds.h | 4 +- drivers/net/ethernet/emulex/benet/be_ethtool.c | 57 ++++++-------------------- drivers/net/ethernet/emulex/benet/be_main.c | 4 +- 5 files changed, 48 insertions(+), 64 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 5b622993ff17..cf4c05bdf5fe 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -337,7 +337,6 @@ struct phy_info { u16 auto_speeds_supported; u16 fixed_speeds_supported; int link_speed; - int forced_port_speed; u32 dac_cable_len; u32 advertising; u32 supported; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 6fbfb207fa5a..46a19affbc21 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -165,14 +165,13 @@ static void be_async_grp5_cos_priority_process(struct be_adapter *adapter, } } -/* Grp5 QOS Speed evt */ +/* Grp5 QOS Speed evt: qos_link_speed is in units of 10 Mbps */ static void be_async_grp5_qos_speed_process(struct be_adapter *adapter, struct be_async_event_grp5_qos_link_speed *evt) { - if (evt->physical_port == adapter->port_num) { - /* qos_link_speed is in units of 10 Mbps */ - adapter->phy.link_speed = evt->qos_link_speed * 10; - } + if (adapter->phy.link_speed >= 0 && + evt->physical_port == adapter->port_num) + adapter->phy.link_speed = le16_to_cpu(evt->qos_link_speed) * 10; } /*Grp5 PVID evt*/ @@ -1326,9 +1325,28 @@ err: return status; } -/* Uses synchronous mcc */ -int be_cmd_link_status_query(struct be_adapter *adapter, u8 *mac_speed, - u16 *link_speed, u8 *link_status, u32 dom) +static int be_mac_to_link_speed(int mac_speed) +{ + switch (mac_speed) { + case PHY_LINK_SPEED_ZERO: + return 0; + case PHY_LINK_SPEED_10MBPS: + return 10; + case PHY_LINK_SPEED_100MBPS: + return 100; + case PHY_LINK_SPEED_1GBPS: + return 1000; + case PHY_LINK_SPEED_10GBPS: + return 10000; + } + return 0; +} + +/* Uses synchronous mcc + * Returns link_speed in Mbps + */ +int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed, + u8 *link_status, u32 dom) { struct be_mcc_wrb *wrb; struct be_cmd_req_link_status *req; @@ -1357,11 +1375,13 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u8 *mac_speed, status = be_mcc_notify_wait(adapter); if (!status) { struct be_cmd_resp_link_status *resp = embedded_payload(wrb); - if (resp->mac_speed != PHY_LINK_SPEED_ZERO) { - if (link_speed) - *link_speed = le16_to_cpu(resp->link_speed); - if (mac_speed) - *mac_speed = resp->mac_speed; + if (link_speed) { + *link_speed = resp->link_speed ? + le16_to_cpu(resp->link_speed) * 10 : + be_mac_to_link_speed(resp->mac_speed); + + if (!resp->logical_link_status) + *link_speed = 0; } if (link_status) *link_status = resp->logical_link_status; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 1f5b83975f21..0936e21e3cff 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -1714,8 +1714,8 @@ extern int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q, int type); extern int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q); -extern int be_cmd_link_status_query(struct be_adapter *adapter, u8 *mac_speed, - u16 *link_speed, u8 *link_status, u32 dom); +extern int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed, + u8 *link_status, u32 dom); extern int be_cmd_reset(struct be_adapter *adapter); extern int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index c0e700653f96..8e6fb0ba6aa9 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -512,28 +512,6 @@ static u32 convert_to_et_setting(u32 if_type, u32 if_speeds) return val; } -static int convert_to_et_speed(u32 be_speed) -{ - int et_speed = SPEED_10000; - - switch (be_speed) { - case PHY_LINK_SPEED_10MBPS: - et_speed = SPEED_10; - break; - case PHY_LINK_SPEED_100MBPS: - et_speed = SPEED_100; - break; - case PHY_LINK_SPEED_1GBPS: - et_speed = SPEED_1000; - break; - case PHY_LINK_SPEED_10GBPS: - et_speed = SPEED_10000; - break; - } - - return et_speed; -} - bool be_pause_supported(struct be_adapter *adapter) { return (adapter->phy.interface_type == PHY_TYPE_SFP_PLUS_10GB || @@ -544,27 +522,16 @@ bool be_pause_supported(struct be_adapter *adapter) static int be_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) { struct be_adapter *adapter = netdev_priv(netdev); - u8 port_speed = 0; - u16 link_speed = 0; u8 link_status; - u32 et_speed = 0; + u16 link_speed = 0; int status; - if (adapter->phy.link_speed < 0 || !(netdev->flags & IFF_UP)) { - if (adapter->phy.forced_port_speed < 0) { - status = be_cmd_link_status_query(adapter, &port_speed, - &link_speed, &link_status, 0); - if (!status) - be_link_status_update(adapter, link_status); - if (link_speed) - et_speed = link_speed * 10; - else if (link_status) - et_speed = convert_to_et_speed(port_speed); - } else { - et_speed = adapter->phy.forced_port_speed; - } - - ethtool_cmd_speed_set(ecmd, et_speed); + if (adapter->phy.link_speed < 0) { + status = be_cmd_link_status_query(adapter, &link_speed, + &link_status, 0); + if (!status) + be_link_status_update(adapter, link_status); + ethtool_cmd_speed_set(ecmd, link_speed); status = be_cmd_get_phy_info(adapter); if (status) @@ -773,8 +740,8 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data) { struct be_adapter *adapter = netdev_priv(netdev); - u8 mac_speed = 0; - u16 qos_link_speed = 0; + int status; + u8 link_status = 0; memset(data, 0, sizeof(u64) * ETHTOOL_TESTS_NUM); @@ -798,11 +765,11 @@ be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data) test->flags |= ETH_TEST_FL_FAILED; } - if (be_cmd_link_status_query(adapter, &mac_speed, - &qos_link_speed, NULL, 0) != 0) { + status = be_cmd_link_status_query(adapter, NULL, &link_status, 0); + if (status) { test->flags |= ETH_TEST_FL_FAILED; data[4] = -1; - } else if (!mac_speed) { + } else if (!link_status) { test->flags |= ETH_TEST_FL_FAILED; data[4] = 1; } diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index b712091bc218..4855dd627c7f 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2440,8 +2440,7 @@ static int be_open(struct net_device *netdev) be_eq_notify(adapter, eqo->q.id, true, false, 0); } - status = be_cmd_link_status_query(adapter, NULL, NULL, - &link_status, 0); + status = be_cmd_link_status_query(adapter, NULL, &link_status, 0); if (!status) be_link_status_update(adapter, link_status); @@ -2670,7 +2669,6 @@ static void be_setup_init(struct be_adapter *adapter) adapter->be3_native = false; adapter->promiscuous = false; adapter->eq_next_idx = 0; - adapter->phy.forced_port_speed = -1; } static int be_get_mac_addr(struct be_adapter *adapter, u8 *mac, u32 if_handle, -- cgit v1.2.3 From d379142bc4d9b78cdd9fc5aa696ca1ea083fb7d4 Mon Sep 17 00:00:00 2001 From: Sathya Perla Date: Fri, 28 Sep 2012 04:39:44 +0000 Subject: be2net: fixup log messages Added and modified a few log messages mostly in probe path. Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_cmds.c | 3 +++ drivers/net/ethernet/emulex/benet/be_main.c | 34 ++++++++++++++++++++++++----- 2 files changed, 31 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 46a19affbc21..af60bb26e330 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -2425,6 +2425,9 @@ int be_cmd_req_native_mode(struct be_adapter *adapter) struct be_cmd_resp_set_func_cap *resp = embedded_payload(wrb); adapter->be3_native = le32_to_cpu(resp->cap_flags) & CAPABILITY_BE3_NATIVE_ERX_API; + if (!adapter->be3_native) + dev_warn(&adapter->pdev->dev, + "adapter not in advanced mode\n"); } err: mutex_unlock(&adapter->mbox_lock); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 4855dd627c7f..6accb0c0273a 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1896,6 +1896,8 @@ static int be_tx_qs_create(struct be_adapter *adapter) return status; } + dev_info(&adapter->pdev->dev, "created %d TX queue(s)\n", + adapter->num_tx_qs); return 0; } @@ -1946,10 +1948,9 @@ static int be_rx_cqs_create(struct be_adapter *adapter) return rc; } - if (adapter->num_rx_qs != MAX_RX_QS) - dev_info(&adapter->pdev->dev, - "Created only %d receive queues\n", adapter->num_rx_qs); - + dev_info(&adapter->pdev->dev, + "created %d RSS queue(s) and 1 default RX queue\n", + adapter->num_rx_qs - 1); return 0; } @@ -2187,6 +2188,7 @@ static void be_msix_enable(struct be_adapter *adapter) { #define BE_MIN_MSIX_VECTORS 1 int i, status, num_vec, num_roce_vec = 0; + struct device *dev = &adapter->pdev->dev; /* If RSS queues are not used, need a vec for default RX Q */ num_vec = min(be_num_rss_want(adapter), num_online_cpus()); @@ -2211,6 +2213,8 @@ static void be_msix_enable(struct be_adapter *adapter) num_vec) == 0) goto done; } + + dev_warn(dev, "MSIx enable failed\n"); return; done: if (be_roce_supported(adapter)) { @@ -2224,6 +2228,7 @@ done: } } else adapter->num_msix_vec = num_vec; + dev_info(dev, "enabled %d MSI-x vector(s)\n", adapter->num_msix_vec); return; } @@ -3797,6 +3802,23 @@ static bool be_reset_required(struct be_adapter *adapter) return be_find_vfs(adapter, ENABLED) > 0 ? false : true; } +static char *mc_name(struct be_adapter *adapter) +{ + if (adapter->function_mode & FLEX10_MODE) + return "FLEX10"; + else if (adapter->function_mode & VNIC_MODE) + return "vNIC"; + else if (adapter->function_mode & UMC_ENABLED) + return "UMC"; + else + return ""; +} + +static inline char *func_name(struct be_adapter *adapter) +{ + return be_physfn(adapter) ? "PF" : "VF"; +} + static int __devinit be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id) { @@ -3901,8 +3923,8 @@ static int __devinit be_probe(struct pci_dev *pdev, be_cmd_query_port_name(adapter, &port_name); - dev_info(&pdev->dev, "%s: %s port %c\n", netdev->name, nic_name(pdev), - port_name); + dev_info(&pdev->dev, "%s: %s %s port %c\n", nic_name(pdev), + func_name(adapter), mc_name(adapter), port_name); return 0; -- cgit v1.2.3 From 426dd00d76ad7c96250f5b5f871847d545fef33c Mon Sep 17 00:00:00 2001 From: Dotan Barak Date: Thu, 23 Aug 2012 14:09:04 +0000 Subject: mlx4_core: Fix wrong offset in parsing query device caps response The wrong offset was used when parsing the number of XRCs in mlx4_QUERY_DEV_CAP(). Signed-off-by: Dotan Barak Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/fw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index c69648487321..7cf8ec5f3827 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -559,7 +559,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev_cap->max_pds = 1 << (field & 0x3f); MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_XRC_OFFSET); dev_cap->reserved_xrcds = field >> 4; - MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_PD_OFFSET); + MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_XRC_OFFSET); dev_cap->max_xrcds = 1 << (field & 0x1f); MLX4_GET(size, outbox, QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET); -- cgit v1.2.3 From a084feebd24764fab9657a586ea65484ddbd79cf Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 23 Aug 2012 14:09:05 +0000 Subject: mlx4_core: Remove annoying debug message in the resource tracker This innocent print makes it very hard to actually use the mlx4_core debug messages -- for example, the module load sequence of a device with two VFs yielded 3200 debug prints, with 2800 of them being this one. Let's just remove it. Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 293c9e820c49..362b25e1f2e7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -360,8 +360,6 @@ static int get_res(struct mlx4_dev *dev, int slave, u64 res_id, r->from_state = r->state; r->state = RES_ANY_BUSY; - mlx4_dbg(dev, "res %s id 0x%llx to busy\n", - ResourceType(type), r->res_id); if (res) *((struct res_common **)res) = r; -- cgit v1.2.3 From e2c76824ca16a3e8443cc7b26abcb21af7c27b10 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:41 +0000 Subject: mlx4_core: Add proxy and tunnel QPs to the reserved QP area In addition, pass the proxy and tunnel QP numbers to slaves so the driver can perform special QP paravirtualization. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/fw.c | 14 +++++++++++ drivers/net/ethernet/mellanox/mlx4/fw.h | 3 +++ drivers/net/ethernet/mellanox/mlx4/main.c | 5 ++++ drivers/net/ethernet/mellanox/mlx4/qp.c | 29 +++++++++++++++++++--- .../net/ethernet/mellanox/mlx4/resource_tracker.c | 3 ++- include/linux/mlx4/device.h | 13 +++++++++- 6 files changed, 62 insertions(+), 5 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index c69648487321..35be90178bef 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -184,6 +184,8 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, #define QUERY_FUNC_CAP_MCG_QUOTA_OFFSET 0x28 #define QUERY_FUNC_CAP_MAX_EQ_OFFSET 0x2c #define QUERY_FUNC_CAP_RESERVED_EQ_OFFSET 0X30 +#define QUERY_FUNC_CAP_BASE_TUNNEL_QPN_OFFSET 0x44 +#define QUERY_FUNC_CAP_BASE_PROXY_QPN_OFFSET 0x48 #define QUERY_FUNC_CAP_FMR_FLAG 0x80 #define QUERY_FUNC_CAP_FLAG_RDMA 0x40 @@ -247,6 +249,12 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, size = dev->caps.num_mgms + dev->caps.num_amgms; MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET); + size = dev->caps.base_tunnel_sqpn + 8 * slave; + MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_BASE_TUNNEL_QPN_OFFSET); + + size = dev->caps.sqp_start + 8 * slave; + MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_BASE_PROXY_QPN_OFFSET); + } else err = -EINVAL; @@ -312,6 +320,12 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, struct mlx4_func_cap *func_cap) MLX4_GET(size, outbox, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET); func_cap->mcg_quota = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_BASE_TUNNEL_QPN_OFFSET); + func_cap->base_tunnel_qpn = size & 0xFFFFFF; + + MLX4_GET(size, outbox, QUERY_FUNC_CAP_BASE_PROXY_QPN_OFFSET); + func_cap->base_proxy_qpn = size & 0xFFFFFF; + for (i = 1; i <= func_cap->num_ports; ++i) { err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 1, MLX4_CMD_QUERY_FUNC_CAP, diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 83fcbbf1b169..ced1de57c818 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -134,6 +134,9 @@ struct mlx4_func_cap { int max_eq; int reserved_eq; int mcg_quota; + u32 base_qpn; + u32 base_tunnel_qpn; + u32 base_proxy_qpn; u8 physical_port[MLX4_MAX_PORTS + 1]; u8 port_flags[MLX4_MAX_PORTS + 1]; }; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 2f816c6aed72..06ef3afbc49a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -384,6 +384,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] + dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH]; + dev->caps.sqp_demux = (mlx4_is_master(dev)) ? MLX4_MAX_NUM_SLAVES : 0; return 0; } /*The function checks if there are live vf, return the num of them*/ @@ -541,6 +542,10 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) return -ENODEV; } + /* Calculate our sqp_start */ + dev->caps.sqp_start = func_cap.base_proxy_qpn; + dev->caps.base_tunnel_sqpn = func_cap.base_tunnel_qpn; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index fb2b36759cbf..b8da72b29cf7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -406,7 +406,7 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) * We also reserve the MSB of the 24-bit QP number to indicate * that a QP is an XRC QP. */ - dev->caps.sqp_start = + dev->caps.base_sqpn = ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8); { @@ -437,13 +437,36 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) } + /* Reserve 8 real SQPs in both native and SRIOV modes. + * In addition, in SRIOV mode, reserve 8 proxy SQPs per function + * (for all PFs and VFs), and 8 corresponding tunnel QPs. + * Each proxy SQP works opposite its own tunnel QP. + * + * The QPs are arranged as follows: + * a. 8 real SQPs + * b. All the proxy SQPs (8 per function) + * c. All the tunnel QPs (8 per function) + */ + err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps, - (1 << 23) - 1, dev->caps.sqp_start + 8, + (1 << 23) - 1, dev->caps.base_sqpn + 8 + + 16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev), reserved_from_top); + + /* In mfunc, sqp_start is the base of the proxy SQPs, since the PF also + * uses paravirtualized SQPs. + * In native mode, sqp_start is the base of the real SQPs. */ + if (mlx4_is_mfunc(dev)) { + dev->caps.sqp_start = dev->caps.base_sqpn + + 8 * (mlx4_master_func_num(dev) + 1); + dev->caps.base_tunnel_sqpn = dev->caps.sqp_start + 8 * MLX4_MFUNC_MAX; + } else + dev->caps.sqp_start = dev->caps.base_sqpn; + if (err) return err; - return mlx4_CONF_SPECIAL_QP(dev, dev->caps.sqp_start); + return mlx4_CONF_SPECIAL_QP(dev, dev->caps.base_sqpn); } void mlx4_cleanup_qp_table(struct mlx4_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 293c9e820c49..3c57a83e6287 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -1105,7 +1105,8 @@ static void res_end_move(struct mlx4_dev *dev, int slave, static int valid_reserved(struct mlx4_dev *dev, int slave, int qpn) { - return mlx4_is_qp_reserved(dev, qpn); + return mlx4_is_qp_reserved(dev, qpn) && + (mlx4_is_master(dev) || mlx4_is_guest_proxy(dev, slave, qpn)); } static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 07aa8232e631..d5c82b7216de 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -693,7 +693,18 @@ static inline int mlx4_is_master(struct mlx4_dev *dev) static inline int mlx4_is_qp_reserved(struct mlx4_dev *dev, u32 qpn) { - return (qpn < dev->caps.sqp_start + 8); + return (qpn < dev->caps.base_sqpn + 8 + + 16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev)); +} + +static inline int mlx4_is_guest_proxy(struct mlx4_dev *dev, int slave, u32 qpn) +{ + int base = dev->caps.sqp_start + slave * 8; + + if (qpn >= base && qpn < base + 8) + return 1; + + return 0; } static inline int mlx4_is_mfunc(struct mlx4_dev *dev) -- cgit v1.2.3 From fc06573dfaf8a33bc0533bb70c49de13fa5232a4 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:42 +0000 Subject: IB/mlx4: Initialize SR-IOV IB support for slaves in master context Allocate SR-IOV paravirtualization resources and MAD demuxing contexts on the master. This has two parts. The first part is to initialize the structures to contain the contexts. This is done at master startup time in mlx4_ib_init_sriov(). The second part is to actually create the tunneling resources required on the master to support a slave. This is performed the master detects that a slave has started up (MLX4_DEV_EVENT_SLAVE_INIT event generated when a slave initializes its comm channel). For the master, there is no such startup event, so it creates its own tunneling resources when it starts up. In addition, the master also creates the real special QPs. The ib_core layer on the master causes creation of proxy special QPs, since the master is also paravirtualized at the ib_core layer. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/mad.c | 684 +++++++++++++++++++++++++++++++ drivers/infiniband/hw/mlx4/main.c | 80 +++- drivers/infiniband/hw/mlx4/mlx4_ib.h | 34 ++ drivers/net/ethernet/mellanox/mlx4/cmd.c | 3 + include/linux/mlx4/device.h | 3 +- include/linux/mlx4/driver.h | 2 + 6 files changed, 798 insertions(+), 8 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 9c2ae7efd00f..e98849338a94 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -44,6 +44,35 @@ enum { MLX4_IB_VENDOR_CLASS2 = 0xa }; +#define MLX4_TUN_SEND_WRID_SHIFT 34 +#define MLX4_TUN_QPN_SHIFT 32 +#define MLX4_TUN_WRID_RECV (((u64) 1) << MLX4_TUN_SEND_WRID_SHIFT) +#define MLX4_TUN_SET_WRID_QPN(a) (((u64) ((a) & 0x3)) << MLX4_TUN_QPN_SHIFT) + +#define MLX4_TUN_IS_RECV(a) (((a) >> MLX4_TUN_SEND_WRID_SHIFT) & 0x1) +#define MLX4_TUN_WRID_QPN(a) (((a) >> MLX4_TUN_QPN_SHIFT) & 0x3) + +struct mlx4_mad_rcv_buf { + struct ib_grh grh; + u8 payload[256]; +} __packed; + +struct mlx4_mad_snd_buf { + u8 payload[256]; +} __packed; + +struct mlx4_tunnel_mad { + struct ib_grh grh; + struct mlx4_ib_tunnel_header hdr; + struct ib_mad mad; +} __packed; + +struct mlx4_rcv_tunnel_mad { + struct mlx4_rcv_tunnel_hdr hdr; + struct ib_grh grh; + struct ib_mad mad; +} __packed; + int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int ignore_mkey, int ignore_bkey, int port, struct ib_wc *in_wc, struct ib_grh *in_grh, void *in_mad, void *response_mad) @@ -516,3 +545,658 @@ void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u8 port_num, ib_dispatch_event(&event); } + +static void mlx4_ib_tunnel_comp_handler(struct ib_cq *cq, void *arg) +{ + unsigned long flags; + struct mlx4_ib_demux_pv_ctx *ctx = cq->cq_context; + struct mlx4_ib_dev *dev = to_mdev(ctx->ib_dev); + spin_lock_irqsave(&dev->sriov.going_down_lock, flags); + if (!dev->sriov.is_going_down && ctx->state == DEMUX_PV_STATE_ACTIVE) + queue_work(ctx->wq, &ctx->work); + spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags); +} + +static int mlx4_ib_post_pv_qp_buf(struct mlx4_ib_demux_pv_ctx *ctx, + struct mlx4_ib_demux_pv_qp *tun_qp, + int index) +{ + struct ib_sge sg_list; + struct ib_recv_wr recv_wr, *bad_recv_wr; + int size; + + size = (tun_qp->qp->qp_type == IB_QPT_UD) ? + sizeof (struct mlx4_tunnel_mad) : sizeof (struct mlx4_mad_rcv_buf); + + sg_list.addr = tun_qp->ring[index].map; + sg_list.length = size; + sg_list.lkey = ctx->mr->lkey; + + recv_wr.next = NULL; + recv_wr.sg_list = &sg_list; + recv_wr.num_sge = 1; + recv_wr.wr_id = (u64) index | MLX4_TUN_WRID_RECV | + MLX4_TUN_SET_WRID_QPN(tun_qp->proxy_qpt); + ib_dma_sync_single_for_device(ctx->ib_dev, tun_qp->ring[index].map, + size, DMA_FROM_DEVICE); + return ib_post_recv(tun_qp->qp, &recv_wr, &bad_recv_wr); +} + +static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx, + enum ib_qp_type qp_type, int is_tun) +{ + int i; + struct mlx4_ib_demux_pv_qp *tun_qp; + int rx_buf_size, tx_buf_size; + + if (qp_type > IB_QPT_GSI) + return -EINVAL; + + tun_qp = &ctx->qp[qp_type]; + + tun_qp->ring = kzalloc(sizeof (struct mlx4_ib_buf) * MLX4_NUM_TUNNEL_BUFS, + GFP_KERNEL); + if (!tun_qp->ring) + return -ENOMEM; + + tun_qp->tx_ring = kcalloc(MLX4_NUM_TUNNEL_BUFS, + sizeof (struct mlx4_ib_tun_tx_buf), + GFP_KERNEL); + if (!tun_qp->tx_ring) { + kfree(tun_qp->ring); + tun_qp->ring = NULL; + return -ENOMEM; + } + + if (is_tun) { + rx_buf_size = sizeof (struct mlx4_tunnel_mad); + tx_buf_size = sizeof (struct mlx4_rcv_tunnel_mad); + } else { + rx_buf_size = sizeof (struct mlx4_mad_rcv_buf); + tx_buf_size = sizeof (struct mlx4_mad_snd_buf); + } + + for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) { + tun_qp->ring[i].addr = kmalloc(rx_buf_size, GFP_KERNEL); + if (!tun_qp->ring[i].addr) + goto err; + tun_qp->ring[i].map = ib_dma_map_single(ctx->ib_dev, + tun_qp->ring[i].addr, + rx_buf_size, + DMA_FROM_DEVICE); + } + + for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) { + tun_qp->tx_ring[i].buf.addr = + kmalloc(tx_buf_size, GFP_KERNEL); + if (!tun_qp->tx_ring[i].buf.addr) + goto tx_err; + tun_qp->tx_ring[i].buf.map = + ib_dma_map_single(ctx->ib_dev, + tun_qp->tx_ring[i].buf.addr, + tx_buf_size, + DMA_TO_DEVICE); + tun_qp->tx_ring[i].ah = NULL; + } + spin_lock_init(&tun_qp->tx_lock); + tun_qp->tx_ix_head = 0; + tun_qp->tx_ix_tail = 0; + tun_qp->proxy_qpt = qp_type; + + return 0; + +tx_err: + while (i > 0) { + --i; + ib_dma_unmap_single(ctx->ib_dev, tun_qp->tx_ring[i].buf.map, + tx_buf_size, DMA_TO_DEVICE); + kfree(tun_qp->tx_ring[i].buf.addr); + } + kfree(tun_qp->tx_ring); + tun_qp->tx_ring = NULL; + i = MLX4_NUM_TUNNEL_BUFS; +err: + while (i > 0) { + --i; + ib_dma_unmap_single(ctx->ib_dev, tun_qp->ring[i].map, + rx_buf_size, DMA_FROM_DEVICE); + kfree(tun_qp->ring[i].addr); + } + kfree(tun_qp->ring); + tun_qp->ring = NULL; + return -ENOMEM; +} + +static void mlx4_ib_free_pv_qp_bufs(struct mlx4_ib_demux_pv_ctx *ctx, + enum ib_qp_type qp_type, int is_tun) +{ + int i; + struct mlx4_ib_demux_pv_qp *tun_qp; + int rx_buf_size, tx_buf_size; + + if (qp_type > IB_QPT_GSI) + return; + + tun_qp = &ctx->qp[qp_type]; + if (is_tun) { + rx_buf_size = sizeof (struct mlx4_tunnel_mad); + tx_buf_size = sizeof (struct mlx4_rcv_tunnel_mad); + } else { + rx_buf_size = sizeof (struct mlx4_mad_rcv_buf); + tx_buf_size = sizeof (struct mlx4_mad_snd_buf); + } + + + for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) { + ib_dma_unmap_single(ctx->ib_dev, tun_qp->ring[i].map, + rx_buf_size, DMA_FROM_DEVICE); + kfree(tun_qp->ring[i].addr); + } + + for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) { + ib_dma_unmap_single(ctx->ib_dev, tun_qp->tx_ring[i].buf.map, + tx_buf_size, DMA_TO_DEVICE); + kfree(tun_qp->tx_ring[i].buf.addr); + if (tun_qp->tx_ring[i].ah) + ib_destroy_ah(tun_qp->tx_ring[i].ah); + } + kfree(tun_qp->tx_ring); + kfree(tun_qp->ring); +} + +static void mlx4_ib_tunnel_comp_worker(struct work_struct *work) +{ + /* dummy until next patch in series */ +} + +static void pv_qp_event_handler(struct ib_event *event, void *qp_context) +{ + struct mlx4_ib_demux_pv_ctx *sqp = qp_context; + + /* It's worse than that! He's dead, Jim! */ + pr_err("Fatal error (%d) on a MAD QP on port %d\n", + event->event, sqp->port); +} + +static int create_pv_sqp(struct mlx4_ib_demux_pv_ctx *ctx, + enum ib_qp_type qp_type, int create_tun) +{ + int i, ret; + struct mlx4_ib_demux_pv_qp *tun_qp; + struct mlx4_ib_qp_tunnel_init_attr qp_init_attr; + struct ib_qp_attr attr; + int qp_attr_mask_INIT; + + if (qp_type > IB_QPT_GSI) + return -EINVAL; + + tun_qp = &ctx->qp[qp_type]; + + memset(&qp_init_attr, 0, sizeof qp_init_attr); + qp_init_attr.init_attr.send_cq = ctx->cq; + qp_init_attr.init_attr.recv_cq = ctx->cq; + qp_init_attr.init_attr.sq_sig_type = IB_SIGNAL_ALL_WR; + qp_init_attr.init_attr.cap.max_send_wr = MLX4_NUM_TUNNEL_BUFS; + qp_init_attr.init_attr.cap.max_recv_wr = MLX4_NUM_TUNNEL_BUFS; + qp_init_attr.init_attr.cap.max_send_sge = 1; + qp_init_attr.init_attr.cap.max_recv_sge = 1; + if (create_tun) { + qp_init_attr.init_attr.qp_type = IB_QPT_UD; + qp_init_attr.init_attr.create_flags = MLX4_IB_SRIOV_TUNNEL_QP; + qp_init_attr.port = ctx->port; + qp_init_attr.slave = ctx->slave; + qp_init_attr.proxy_qp_type = qp_type; + qp_attr_mask_INIT = IB_QP_STATE | IB_QP_PKEY_INDEX | + IB_QP_QKEY | IB_QP_PORT; + } else { + qp_init_attr.init_attr.qp_type = qp_type; + qp_init_attr.init_attr.create_flags = MLX4_IB_SRIOV_SQP; + qp_attr_mask_INIT = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_QKEY; + } + qp_init_attr.init_attr.port_num = ctx->port; + qp_init_attr.init_attr.qp_context = ctx; + qp_init_attr.init_attr.event_handler = pv_qp_event_handler; + tun_qp->qp = ib_create_qp(ctx->pd, &qp_init_attr.init_attr); + if (IS_ERR(tun_qp->qp)) { + ret = PTR_ERR(tun_qp->qp); + tun_qp->qp = NULL; + pr_err("Couldn't create %s QP (%d)\n", + create_tun ? "tunnel" : "special", ret); + return ret; + } + + memset(&attr, 0, sizeof attr); + attr.qp_state = IB_QPS_INIT; + attr.pkey_index = + to_mdev(ctx->ib_dev)->pkeys.virt2phys_pkey[ctx->slave][ctx->port - 1][0]; + attr.qkey = IB_QP1_QKEY; + attr.port_num = ctx->port; + ret = ib_modify_qp(tun_qp->qp, &attr, qp_attr_mask_INIT); + if (ret) { + pr_err("Couldn't change %s qp state to INIT (%d)\n", + create_tun ? "tunnel" : "special", ret); + goto err_qp; + } + attr.qp_state = IB_QPS_RTR; + ret = ib_modify_qp(tun_qp->qp, &attr, IB_QP_STATE); + if (ret) { + pr_err("Couldn't change %s qp state to RTR (%d)\n", + create_tun ? "tunnel" : "special", ret); + goto err_qp; + } + attr.qp_state = IB_QPS_RTS; + attr.sq_psn = 0; + ret = ib_modify_qp(tun_qp->qp, &attr, IB_QP_STATE | IB_QP_SQ_PSN); + if (ret) { + pr_err("Couldn't change %s qp state to RTS (%d)\n", + create_tun ? "tunnel" : "special", ret); + goto err_qp; + } + + for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) { + ret = mlx4_ib_post_pv_qp_buf(ctx, tun_qp, i); + if (ret) { + pr_err(" mlx4_ib_post_pv_buf error" + " (err = %d, i = %d)\n", ret, i); + goto err_qp; + } + } + return 0; + +err_qp: + ib_destroy_qp(tun_qp->qp); + tun_qp->qp = NULL; + return ret; +} + +/* + * IB MAD completion callback for real SQPs + */ +static void mlx4_ib_sqp_comp_worker(struct work_struct *work) +{ + /* dummy until next patch in series */ +} + +static int alloc_pv_object(struct mlx4_ib_dev *dev, int slave, int port, + struct mlx4_ib_demux_pv_ctx **ret_ctx) +{ + struct mlx4_ib_demux_pv_ctx *ctx; + + *ret_ctx = NULL; + ctx = kzalloc(sizeof (struct mlx4_ib_demux_pv_ctx), GFP_KERNEL); + if (!ctx) { + pr_err("failed allocating pv resource context " + "for port %d, slave %d\n", port, slave); + return -ENOMEM; + } + + ctx->ib_dev = &dev->ib_dev; + ctx->port = port; + ctx->slave = slave; + *ret_ctx = ctx; + return 0; +} + +static void free_pv_object(struct mlx4_ib_dev *dev, int slave, int port) +{ + if (dev->sriov.demux[port - 1].tun[slave]) { + kfree(dev->sriov.demux[port - 1].tun[slave]); + dev->sriov.demux[port - 1].tun[slave] = NULL; + } +} + +static int create_pv_resources(struct ib_device *ibdev, int slave, int port, + int create_tun, struct mlx4_ib_demux_pv_ctx *ctx) +{ + int ret, cq_size; + + ctx->state = DEMUX_PV_STATE_STARTING; + /* have QP0 only on port owner, and only if link layer is IB */ + if (ctx->slave == mlx4_master_func_num(to_mdev(ctx->ib_dev)->dev) && + rdma_port_get_link_layer(ibdev, ctx->port) == IB_LINK_LAYER_INFINIBAND) + ctx->has_smi = 1; + + if (ctx->has_smi) { + ret = mlx4_ib_alloc_pv_bufs(ctx, IB_QPT_SMI, create_tun); + if (ret) { + pr_err("Failed allocating qp0 tunnel bufs (%d)\n", ret); + goto err_out; + } + } + + ret = mlx4_ib_alloc_pv_bufs(ctx, IB_QPT_GSI, create_tun); + if (ret) { + pr_err("Failed allocating qp1 tunnel bufs (%d)\n", ret); + goto err_out_qp0; + } + + cq_size = 2 * MLX4_NUM_TUNNEL_BUFS; + if (ctx->has_smi) + cq_size *= 2; + + ctx->cq = ib_create_cq(ctx->ib_dev, mlx4_ib_tunnel_comp_handler, + NULL, ctx, cq_size, 0); + if (IS_ERR(ctx->cq)) { + ret = PTR_ERR(ctx->cq); + pr_err("Couldn't create tunnel CQ (%d)\n", ret); + goto err_buf; + } + + ctx->pd = ib_alloc_pd(ctx->ib_dev); + if (IS_ERR(ctx->pd)) { + ret = PTR_ERR(ctx->pd); + pr_err("Couldn't create tunnel PD (%d)\n", ret); + goto err_cq; + } + + ctx->mr = ib_get_dma_mr(ctx->pd, IB_ACCESS_LOCAL_WRITE); + if (IS_ERR(ctx->mr)) { + ret = PTR_ERR(ctx->mr); + pr_err("Couldn't get tunnel DMA MR (%d)\n", ret); + goto err_pd; + } + + if (ctx->has_smi) { + ret = create_pv_sqp(ctx, IB_QPT_SMI, create_tun); + if (ret) { + pr_err("Couldn't create %s QP0 (%d)\n", + create_tun ? "tunnel for" : "", ret); + goto err_mr; + } + } + + ret = create_pv_sqp(ctx, IB_QPT_GSI, create_tun); + if (ret) { + pr_err("Couldn't create %s QP1 (%d)\n", + create_tun ? "tunnel for" : "", ret); + goto err_qp0; + } + + if (create_tun) + INIT_WORK(&ctx->work, mlx4_ib_tunnel_comp_worker); + else + INIT_WORK(&ctx->work, mlx4_ib_sqp_comp_worker); + + ctx->wq = to_mdev(ibdev)->sriov.demux[port - 1].wq; + + ret = ib_req_notify_cq(ctx->cq, IB_CQ_NEXT_COMP); + if (ret) { + pr_err("Couldn't arm tunnel cq (%d)\n", ret); + goto err_wq; + } + ctx->state = DEMUX_PV_STATE_ACTIVE; + return 0; + +err_wq: + ctx->wq = NULL; + ib_destroy_qp(ctx->qp[1].qp); + ctx->qp[1].qp = NULL; + + +err_qp0: + if (ctx->has_smi) + ib_destroy_qp(ctx->qp[0].qp); + ctx->qp[0].qp = NULL; + +err_mr: + ib_dereg_mr(ctx->mr); + ctx->mr = NULL; + +err_pd: + ib_dealloc_pd(ctx->pd); + ctx->pd = NULL; + +err_cq: + ib_destroy_cq(ctx->cq); + ctx->cq = NULL; + +err_buf: + mlx4_ib_free_pv_qp_bufs(ctx, IB_QPT_GSI, create_tun); + +err_out_qp0: + if (ctx->has_smi) + mlx4_ib_free_pv_qp_bufs(ctx, IB_QPT_SMI, create_tun); +err_out: + ctx->state = DEMUX_PV_STATE_DOWN; + return ret; +} + +static void destroy_pv_resources(struct mlx4_ib_dev *dev, int slave, int port, + struct mlx4_ib_demux_pv_ctx *ctx, int flush) +{ + if (!ctx) + return; + if (ctx->state > DEMUX_PV_STATE_DOWN) { + ctx->state = DEMUX_PV_STATE_DOWNING; + if (flush) + flush_workqueue(ctx->wq); + if (ctx->has_smi) { + ib_destroy_qp(ctx->qp[0].qp); + ctx->qp[0].qp = NULL; + mlx4_ib_free_pv_qp_bufs(ctx, IB_QPT_SMI, 1); + } + ib_destroy_qp(ctx->qp[1].qp); + ctx->qp[1].qp = NULL; + mlx4_ib_free_pv_qp_bufs(ctx, IB_QPT_GSI, 1); + ib_dereg_mr(ctx->mr); + ctx->mr = NULL; + ib_dealloc_pd(ctx->pd); + ctx->pd = NULL; + ib_destroy_cq(ctx->cq); + ctx->cq = NULL; + ctx->state = DEMUX_PV_STATE_DOWN; + } +} + +static int mlx4_ib_tunnels_update(struct mlx4_ib_dev *dev, int slave, + int port, int do_init) +{ + int ret = 0; + + if (!do_init) { + /* for master, destroy real sqp resources */ + if (slave == mlx4_master_func_num(dev->dev)) + destroy_pv_resources(dev, slave, port, + dev->sriov.sqps[port - 1], 1); + /* destroy the tunnel qp resources */ + destroy_pv_resources(dev, slave, port, + dev->sriov.demux[port - 1].tun[slave], 1); + return 0; + } + + /* create the tunnel qp resources */ + ret = create_pv_resources(&dev->ib_dev, slave, port, 1, + dev->sriov.demux[port - 1].tun[slave]); + + /* for master, create the real sqp resources */ + if (!ret && slave == mlx4_master_func_num(dev->dev)) + ret = create_pv_resources(&dev->ib_dev, slave, port, 0, + dev->sriov.sqps[port - 1]); + return ret; +} + +void mlx4_ib_tunnels_update_work(struct work_struct *work) +{ + struct mlx4_ib_demux_work *dmxw; + + dmxw = container_of(work, struct mlx4_ib_demux_work, work); + mlx4_ib_tunnels_update(dmxw->dev, dmxw->slave, (int) dmxw->port, + dmxw->do_init); + kfree(dmxw); + return; +} + +static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev, + struct mlx4_ib_demux_ctx *ctx, + int port) +{ + char name[12]; + int ret = 0; + int i; + + ctx->tun = kcalloc(dev->dev->caps.sqp_demux, + sizeof (struct mlx4_ib_demux_pv_ctx *), GFP_KERNEL); + if (!ctx->tun) + return -ENOMEM; + + ctx->dev = dev; + ctx->port = port; + ctx->ib_dev = &dev->ib_dev; + + for (i = 0; i < dev->dev->caps.sqp_demux; i++) { + ret = alloc_pv_object(dev, i, port, &ctx->tun[i]); + if (ret) { + ret = -ENOMEM; + goto err_wq; + } + } + + snprintf(name, sizeof name, "mlx4_ibt%d", port); + ctx->wq = create_singlethread_workqueue(name); + if (!ctx->wq) { + pr_err("Failed to create tunnelling WQ for port %d\n", port); + ret = -ENOMEM; + goto err_wq; + } + + snprintf(name, sizeof name, "mlx4_ibud%d", port); + ctx->ud_wq = create_singlethread_workqueue(name); + if (!ctx->ud_wq) { + pr_err("Failed to create up/down WQ for port %d\n", port); + ret = -ENOMEM; + goto err_udwq; + } + + return 0; + +err_udwq: + destroy_workqueue(ctx->wq); + ctx->wq = NULL; + +err_wq: + for (i = 0; i < dev->dev->caps.sqp_demux; i++) + free_pv_object(dev, i, port); + kfree(ctx->tun); + ctx->tun = NULL; + return ret; +} + +static void mlx4_ib_free_sqp_ctx(struct mlx4_ib_demux_pv_ctx *sqp_ctx) +{ + if (sqp_ctx->state > DEMUX_PV_STATE_DOWN) { + sqp_ctx->state = DEMUX_PV_STATE_DOWNING; + flush_workqueue(sqp_ctx->wq); + if (sqp_ctx->has_smi) { + ib_destroy_qp(sqp_ctx->qp[0].qp); + sqp_ctx->qp[0].qp = NULL; + mlx4_ib_free_pv_qp_bufs(sqp_ctx, IB_QPT_SMI, 0); + } + ib_destroy_qp(sqp_ctx->qp[1].qp); + sqp_ctx->qp[1].qp = NULL; + mlx4_ib_free_pv_qp_bufs(sqp_ctx, IB_QPT_GSI, 0); + ib_dereg_mr(sqp_ctx->mr); + sqp_ctx->mr = NULL; + ib_dealloc_pd(sqp_ctx->pd); + sqp_ctx->pd = NULL; + ib_destroy_cq(sqp_ctx->cq); + sqp_ctx->cq = NULL; + sqp_ctx->state = DEMUX_PV_STATE_DOWN; + } +} + +static void mlx4_ib_free_demux_ctx(struct mlx4_ib_demux_ctx *ctx) +{ + int i; + if (ctx) { + struct mlx4_ib_dev *dev = to_mdev(ctx->ib_dev); + for (i = 0; i < dev->dev->caps.sqp_demux; i++) { + if (!ctx->tun[i]) + continue; + if (ctx->tun[i]->state > DEMUX_PV_STATE_DOWN) + ctx->tun[i]->state = DEMUX_PV_STATE_DOWNING; + } + flush_workqueue(ctx->wq); + for (i = 0; i < dev->dev->caps.sqp_demux; i++) { + destroy_pv_resources(dev, i, ctx->port, ctx->tun[i], 0); + free_pv_object(dev, i, ctx->port); + } + kfree(ctx->tun); + destroy_workqueue(ctx->ud_wq); + destroy_workqueue(ctx->wq); + } +} + +static void mlx4_ib_master_tunnels(struct mlx4_ib_dev *dev, int do_init) +{ + int i; + + if (!mlx4_is_master(dev->dev)) + return; + /* initialize or tear down tunnel QPs for the master */ + for (i = 0; i < dev->dev->caps.num_ports; i++) + mlx4_ib_tunnels_update(dev, mlx4_master_func_num(dev->dev), i + 1, do_init); + return; +} + +int mlx4_ib_init_sriov(struct mlx4_ib_dev *dev) +{ + int i = 0; + int err; + + if (!mlx4_is_mfunc(dev->dev)) + return 0; + + dev->sriov.is_going_down = 0; + spin_lock_init(&dev->sriov.going_down_lock); + + mlx4_ib_warn(&dev->ib_dev, "multi-function enabled\n"); + + if (mlx4_is_slave(dev->dev)) { + mlx4_ib_warn(&dev->ib_dev, "operating in qp1 tunnel mode\n"); + return 0; + } + + mlx4_ib_warn(&dev->ib_dev, "initializing demux service for %d qp1 clients\n", + dev->dev->caps.sqp_demux); + for (i = 0; i < dev->num_ports; i++) { + err = alloc_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1, + &dev->sriov.sqps[i]); + if (err) + goto demux_err; + err = mlx4_ib_alloc_demux_ctx(dev, &dev->sriov.demux[i], i + 1); + if (err) + goto demux_err; + } + mlx4_ib_master_tunnels(dev, 1); + return 0; + +demux_err: + while (i > 0) { + free_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1); + mlx4_ib_free_demux_ctx(&dev->sriov.demux[i]); + --i; + } + + return err; +} + +void mlx4_ib_close_sriov(struct mlx4_ib_dev *dev) +{ + int i; + unsigned long flags; + + if (!mlx4_is_mfunc(dev->dev)) + return; + + spin_lock_irqsave(&dev->sriov.going_down_lock, flags); + dev->sriov.is_going_down = 1; + spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags); + if (mlx4_is_master(dev->dev)) + for (i = 0; i < dev->num_ports; i++) { + flush_workqueue(dev->sriov.demux[i].ud_wq); + mlx4_ib_free_sqp_ctx(dev->sriov.sqps[i]); + kfree(dev->sriov.sqps[i]); + dev->sriov.sqps[i] = NULL; + mlx4_ib_free_demux_ctx(&dev->sriov.demux[i]); + } +} diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index cc05579ebce7..3f7f77f93a1c 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1357,11 +1357,14 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) if (mlx4_ib_mad_init(ibdev)) goto err_reg; + if (mlx4_ib_init_sriov(ibdev)) + goto err_mad; + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE && !iboe->nb.notifier_call) { iboe->nb.notifier_call = mlx4_ib_netdev_event; err = register_netdevice_notifier(&iboe->nb); if (err) - goto err_reg; + goto err_sriov; } for (j = 0; j < ARRAY_SIZE(mlx4_class_attributes); ++j) { @@ -1379,6 +1382,12 @@ err_notif: pr_warn("failure unregistering notifier\n"); flush_workqueue(wq); +err_sriov: + mlx4_ib_close_sriov(ibdev); + +err_mad: + mlx4_ib_mad_cleanup(ibdev); + err_reg: ib_unregister_device(&ibdev->ib_dev); @@ -1407,6 +1416,7 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) struct mlx4_ib_dev *ibdev = ibdev_ptr; int p; + mlx4_ib_close_sriov(ibdev); mlx4_ib_mad_cleanup(ibdev); ib_unregister_device(&ibdev->ib_dev); if (ibdev->iboe.nb.notifier_call) { @@ -1428,6 +1438,51 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) ib_dealloc_device(&ibdev->ib_dev); } +static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init) +{ + struct mlx4_ib_demux_work **dm = NULL; + struct mlx4_dev *dev = ibdev->dev; + int i; + unsigned long flags; + + if (!mlx4_is_master(dev)) + return; + + dm = kcalloc(dev->caps.num_ports, sizeof *dm, GFP_ATOMIC); + if (!dm) { + pr_err("failed to allocate memory for tunneling qp update\n"); + goto out; + } + + for (i = 0; i < dev->caps.num_ports; i++) { + dm[i] = kmalloc(sizeof (struct mlx4_ib_demux_work), GFP_ATOMIC); + if (!dm[i]) { + pr_err("failed to allocate memory for tunneling qp update work struct\n"); + for (i = 0; i < dev->caps.num_ports; i++) { + if (dm[i]) + kfree(dm[i]); + } + goto out; + } + } + /* initialize or tear down tunnel QPs for the slave */ + for (i = 0; i < dev->caps.num_ports; i++) { + INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work); + dm[i]->port = i + 1; + dm[i]->slave = slave; + dm[i]->do_init = do_init; + dm[i]->dev = ibdev; + spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags); + if (!ibdev->sriov.is_going_down) + queue_work(ibdev->sriov.demux[i].ud_wq, &dm[i]->work); + spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags); + } +out: + if (dm) + kfree(dm); + return; +} + static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, enum mlx4_dev_event event, unsigned long param) { @@ -1435,22 +1490,23 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr); struct mlx4_eqe *eqe = NULL; struct ib_event_work *ew; - int port = 0; + int p = 0; if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE) eqe = (struct mlx4_eqe *)param; else - port = (u8)param; - - if (port > ibdev->num_ports) - return; + p = (int) param; switch (event) { case MLX4_DEV_EVENT_PORT_UP: + if (p > ibdev->num_ports) + return; ibev.event = IB_EVENT_PORT_ACTIVE; break; case MLX4_DEV_EVENT_PORT_DOWN: + if (p > ibdev->num_ports) + return; ibev.event = IB_EVENT_PORT_ERR; break; @@ -1472,12 +1528,22 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, handle_port_mgmt_change_event(&ew->work); return; + case MLX4_DEV_EVENT_SLAVE_INIT: + /* here, p is the slave id */ + do_slave_init(ibdev, p, 1); + return; + + case MLX4_DEV_EVENT_SLAVE_SHUTDOWN: + /* here, p is the slave id */ + do_slave_init(ibdev, p, 0); + return; + default: return; } ibev.device = ibdev_ptr; - ibev.element.port_num = port; + ibev.element.port_num = (u8) p; ib_dispatch_event(&ibev); } diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 1248d576b031..137941d79870 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -176,6 +176,10 @@ enum mlx4_ib_qp_type { MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI | MLX4_IB_QPT_TUN_SMI_OWNER | \ MLX4_IB_QPT_TUN_SMI | MLX4_IB_QPT_TUN_GSI) +enum { + MLX4_NUM_TUNNEL_BUFS = 256, +}; + struct mlx4_ib_tunnel_header { struct mlx4_av av; __be32 remote_qpn; @@ -263,6 +267,15 @@ struct mlx4_ib_ah { union mlx4_ext_av av; }; +struct mlx4_ib_demux_work { + struct work_struct work; + struct mlx4_ib_dev *dev; + int slave; + int do_init; + u8 port; + +}; + struct mlx4_ib_tun_tx_buf { struct mlx4_ib_buf buf; struct ib_ah *ah; @@ -278,9 +291,17 @@ struct mlx4_ib_demux_pv_qp { unsigned tx_ix_tail; }; +enum mlx4_ib_demux_pv_state { + DEMUX_PV_STATE_DOWN, + DEMUX_PV_STATE_STARTING, + DEMUX_PV_STATE_ACTIVE, + DEMUX_PV_STATE_DOWNING, +}; + struct mlx4_ib_demux_pv_ctx { int port; int slave; + enum mlx4_ib_demux_pv_state state; int has_smi; struct ib_device *ib_dev; struct ib_cq *cq; @@ -319,6 +340,13 @@ struct mlx4_ib_iboe { union ib_gid gid_table[MLX4_MAX_PORTS][128]; }; +struct pkey_mgt { + u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS]; + u16 phys_pkey_cache[MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS]; + struct list_head pkey_port_list[MLX4_MFUNC_MAX]; + struct kobject *device_parent[MLX4_MFUNC_MAX]; +}; + struct mlx4_ib_dev { struct ib_device ib_dev; struct mlx4_dev *dev; @@ -340,6 +368,7 @@ struct mlx4_ib_dev { int counters[MLX4_MAX_PORTS]; int *eq_table; int eq_added; + struct pkey_mgt pkeys; }; struct ib_event_work { @@ -424,6 +453,9 @@ static inline struct mlx4_ib_ah *to_mah(struct ib_ah *ibah) return container_of(ibah, struct mlx4_ib_ah, ibah); } +int mlx4_ib_init_sriov(struct mlx4_ib_dev *dev); +void mlx4_ib_close_sriov(struct mlx4_ib_dev *dev); + int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt, struct mlx4_db *db); void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_db *db); @@ -515,4 +547,6 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u8 port_num, enum ib_event_type type); +void mlx4_ib_tunnels_update_work(struct work_struct *work); + #endif /* MLX4_IB_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index c8fef4353021..cb9bebe28276 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1340,6 +1340,8 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, if (MLX4_COMM_CMD_FLR == slave_state[slave].last_cmd) goto inform_slave_state; + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN, slave); + /* write the version in the event field */ reply |= mlx4_comm_get_version(); @@ -1376,6 +1378,7 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, goto reset_slave; slave_state[slave].vhcr_dma |= param; slave_state[slave].active = true; + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_INIT, slave); break; case MLX4_COMM_CMD_VHCR_POST: if ((slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_EN) && diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index d5c82b7216de..b6b8d341b6c8 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -54,7 +54,8 @@ enum { }; enum { - MLX4_MAX_PORTS = 2 + MLX4_MAX_PORTS = 2, + MLX4_MAX_PORT_PKEYS = 128 }; /* base qkey for use in sriov tunnel-qp/proxy-qp communication. diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index d813704b963b..c257e1b211be 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -45,6 +45,8 @@ enum mlx4_dev_event { MLX4_DEV_EVENT_PORT_DOWN, MLX4_DEV_EVENT_PORT_REINIT, MLX4_DEV_EVENT_PORT_MGMT_CHANGE, + MLX4_DEV_EVENT_SLAVE_INIT, + MLX4_DEV_EVENT_SLAVE_SHUTDOWN, }; struct mlx4_interface { -- cgit v1.2.3 From 54679e148287f0ca1bdd09264c908bacb9f19b3f Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:43 +0000 Subject: mlx4: Implement QP paravirtualization and maintain phys_pkey_cache for smp_snoop This requires: 1. Replacing the paravirtualized P_Key index (inserted by the guest) with the real P_Key index. 2. For UD QPs, placing the guest's true source GID index in the address path structure mgid field, and setting the ud_force_mgid bit so that the mgid is taken from the QP context and not from the WQE when posting sends. 3. For UC and RC QPs, placing the guest's true source GID index in the address path structure mgid field. 4. For tunnel and proxy QPs, setting the Q_Key value reserved for that proxy/tunnel pair. Since not all the above adjustments occur in all the QP transitions, the QP transitions require separate wrapper functions. Secondly, initialize the P_Key virtualization table to its default values: Master virtualized table is 1-1 with the real P_Key table, guest virtualized table has P_Key index 0 mapped to the real P_Key index 0, and all the other P_Key indices mapped to the reserved (invalid) P_Key at index 127. Finally, add logic in smp_snoop for maintaining the phys_P_Key_cache. and generating events on the master only if a P_Key actually changed. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/mad.c | 33 +++- drivers/infiniband/hw/mlx4/main.c | 35 ++++ drivers/net/ethernet/mellanox/mlx4/cmd.c | 12 +- drivers/net/ethernet/mellanox/mlx4/main.c | 11 ++ drivers/net/ethernet/mellanox/mlx4/mlx4.h | 47 +++++ .../net/ethernet/mellanox/mlx4/resource_tracker.c | 217 ++++++++++++++++++++- include/linux/mlx4/device.h | 3 + 7 files changed, 344 insertions(+), 14 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index e98849338a94..318d5bcf821b 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -185,6 +185,10 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad, { struct ib_port_info *pinfo; u16 lid; + __be16 *base; + u32 bn, pkey_change_bitmap; + int i; + struct mlx4_ib_dev *dev = to_mdev(ibdev); if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED || @@ -209,8 +213,33 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad, break; case IB_SMP_ATTR_PKEY_TABLE: - mlx4_ib_dispatch_event(dev, port_num, - IB_EVENT_PKEY_CHANGE); + if (!mlx4_is_mfunc(dev->dev)) { + mlx4_ib_dispatch_event(dev, port_num, + IB_EVENT_PKEY_CHANGE); + break; + } + + bn = be32_to_cpu(((struct ib_smp *)mad)->attr_mod) & 0xFFFF; + base = (__be16 *) &(((struct ib_smp *)mad)->data[0]); + pkey_change_bitmap = 0; + for (i = 0; i < 32; i++) { + pr_debug("PKEY[%d] = x%x\n", + i + bn*32, be16_to_cpu(base[i])); + if (be16_to_cpu(base[i]) != + dev->pkeys.phys_pkey_cache[port_num - 1][i + bn*32]) { + pkey_change_bitmap |= (1 << i); + dev->pkeys.phys_pkey_cache[port_num - 1][i + bn*32] = + be16_to_cpu(base[i]); + } + } + pr_debug("PKEY Change event: port=%d, " + "block=0x%x, change_bitmap=0x%x\n", + port_num, bn, pkey_change_bitmap); + + if (pkey_change_bitmap) + mlx4_ib_dispatch_event(dev, port_num, + IB_EVENT_PKEY_CHANGE); + break; case IB_SMP_ATTR_GUID_INFO: diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 3f7f77f93a1c..8e10ec2af7b6 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1121,6 +1121,38 @@ static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event return NOTIFY_DONE; } +static void init_pkeys(struct mlx4_ib_dev *ibdev) +{ + int port; + int slave; + int i; + + if (mlx4_is_master(ibdev->dev)) { + for (slave = 0; slave <= ibdev->dev->num_vfs; ++slave) { + for (port = 1; port <= ibdev->dev->caps.num_ports; ++port) { + for (i = 0; + i < ibdev->dev->phys_caps.pkey_phys_table_len[port]; + ++i) { + ibdev->pkeys.virt2phys_pkey[slave][port - 1][i] = + /* master has the identity virt2phys pkey mapping */ + (slave == mlx4_master_func_num(ibdev->dev) || !i) ? i : + ibdev->dev->phys_caps.pkey_phys_table_len[port] - 1; + mlx4_sync_pkey_table(ibdev->dev, slave, port, i, + ibdev->pkeys.virt2phys_pkey[slave][port - 1][i]); + } + } + } + /* initialize pkey cache */ + for (port = 1; port <= ibdev->dev->caps.num_ports; ++port) { + for (i = 0; + i < ibdev->dev->phys_caps.pkey_phys_table_len[port]; + ++i) + ibdev->pkeys.phys_pkey_cache[port-1][i] = + (i) ? 0 : 0xFFFF; + } + } +} + static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) { char name[32]; @@ -1375,6 +1407,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->ib_active = true; + if (mlx4_is_mfunc(ibdev->dev)) + init_pkeys(ibdev); + return ibdev; err_notif: diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index cb9bebe28276..662a3c5da739 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -950,7 +950,7 @@ static struct mlx4_cmd_info cmd_info[] = { .out_is_imm = false, .encode_slave_id = false, .verify = NULL, - .wrapper = mlx4_GEN_QP_wrapper + .wrapper = mlx4_INIT2INIT_QP_wrapper }, { .opcode = MLX4_CMD_INIT2RTR_QP, @@ -968,7 +968,7 @@ static struct mlx4_cmd_info cmd_info[] = { .out_is_imm = false, .encode_slave_id = false, .verify = NULL, - .wrapper = mlx4_GEN_QP_wrapper + .wrapper = mlx4_RTR2RTS_QP_wrapper }, { .opcode = MLX4_CMD_RTS2RTS_QP, @@ -977,7 +977,7 @@ static struct mlx4_cmd_info cmd_info[] = { .out_is_imm = false, .encode_slave_id = false, .verify = NULL, - .wrapper = mlx4_GEN_QP_wrapper + .wrapper = mlx4_RTS2RTS_QP_wrapper }, { .opcode = MLX4_CMD_SQERR2RTS_QP, @@ -986,7 +986,7 @@ static struct mlx4_cmd_info cmd_info[] = { .out_is_imm = false, .encode_slave_id = false, .verify = NULL, - .wrapper = mlx4_GEN_QP_wrapper + .wrapper = mlx4_SQERR2RTS_QP_wrapper }, { .opcode = MLX4_CMD_2ERR_QP, @@ -1013,7 +1013,7 @@ static struct mlx4_cmd_info cmd_info[] = { .out_is_imm = false, .encode_slave_id = false, .verify = NULL, - .wrapper = mlx4_GEN_QP_wrapper + .wrapper = mlx4_SQD2SQD_QP_wrapper }, { .opcode = MLX4_CMD_SQD2RTS_QP, @@ -1022,7 +1022,7 @@ static struct mlx4_cmd_info cmd_info[] = { .out_is_imm = false, .encode_slave_id = false, .verify = NULL, - .wrapper = mlx4_GEN_QP_wrapper + .wrapper = mlx4_SQD2RTS_QP_wrapper }, { .opcode = MLX4_CMD_2RST_QP, diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 06ef3afbc49a..2294b7173180 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -424,6 +424,17 @@ int mlx4_get_parav_qkey(struct mlx4_dev *dev, u32 qpn, u32 *qkey) } EXPORT_SYMBOL(mlx4_get_parav_qkey); +void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, int i, int val) +{ + struct mlx4_priv *priv = container_of(dev, struct mlx4_priv, dev); + + if (!mlx4_is_master(dev)) + return; + + priv->virt2phys_pkey[slave][port - 1][i] = val; +} +EXPORT_SYMBOL(mlx4_sync_pkey_table); + int mlx4_is_slave_active(struct mlx4_dev *dev, int slave) { struct mlx4_priv *priv = mlx4_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index dba69d98734a..7d27c3158d0c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -807,6 +807,8 @@ struct mlx4_priv { struct io_mapping *bf_mapping; int reserved_mtts; int fs_hash_mode; + u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS]; + }; static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev) @@ -1011,16 +1013,61 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *inbox, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd); +int mlx4_INIT2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd); +int mlx4_RTR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); +int mlx4_RTS2RTS_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); +int mlx4_SQERR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); +int mlx4_2ERR_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); +int mlx4_RTS2SQD_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); +int mlx4_SQD2SQD_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); +int mlx4_SQD2RTS_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); int mlx4_2RST_QP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd); +int mlx4_QUERY_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 3c57a83e6287..49e9de725d0a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -242,6 +242,15 @@ static int res_tracker_insert(struct rb_root *root, struct res_common *res) return 0; } +enum qp_transition { + QP_TRANS_INIT2RTR, + QP_TRANS_RTR2RTS, + QP_TRANS_RTS2RTS, + QP_TRANS_SQERR2RTS, + QP_TRANS_SQD2SQD, + QP_TRANS_SQD2RTS +}; + /* For Debug uses */ static const char *ResourceType(enum mlx4_resource rt) { @@ -308,14 +317,41 @@ void mlx4_free_resource_tracker(struct mlx4_dev *dev, } } -static void update_ud_gid(struct mlx4_dev *dev, - struct mlx4_qp_context *qp_ctx, u8 slave) +static void update_pkey_index(struct mlx4_dev *dev, int slave, + struct mlx4_cmd_mailbox *inbox) { - u32 ts = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff; + u8 sched = *(u8 *)(inbox->buf + 64); + u8 orig_index = *(u8 *)(inbox->buf + 35); + u8 new_index; + struct mlx4_priv *priv = mlx4_priv(dev); + int port; + + port = (sched >> 6 & 1) + 1; + + new_index = priv->virt2phys_pkey[slave][port - 1][orig_index]; + *(u8 *)(inbox->buf + 35) = new_index; + + mlx4_dbg(dev, "port = %d, orig pkey index = %d, " + "new pkey index = %d\n", port, orig_index, new_index); +} + +static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox, + u8 slave) +{ + struct mlx4_qp_context *qp_ctx = inbox->buf + 8; + enum mlx4_qp_optpar optpar = be32_to_cpu(*(__be32 *) inbox->buf); + u32 ts = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff; if (MLX4_QP_ST_UD == ts) qp_ctx->pri_path.mgid_index = 0x80 | slave; + if (MLX4_QP_ST_RC == ts || MLX4_QP_ST_UC == ts) { + if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) + qp_ctx->pri_path.mgid_index = slave & 0x7F; + if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) + qp_ctx->alt_path.mgid_index = slave & 0x7F; + } + mlx4_dbg(dev, "slave %d, new gid index: 0x%x ", slave, qp_ctx->pri_path.mgid_index); } @@ -1109,6 +1145,11 @@ static int valid_reserved(struct mlx4_dev *dev, int slave, int qpn) (mlx4_is_master(dev) || mlx4_is_guest_proxy(dev, slave, qpn)); } +static int fw_reserved(struct mlx4_dev *dev, int qpn) +{ + return qpn < dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW]; +} + static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, u64 in_param, u64 *out_param) { @@ -1146,7 +1187,7 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, if (err) return err; - if (!valid_reserved(dev, slave, qpn)) { + if (!fw_reserved(dev, qpn)) { err = __mlx4_qp_alloc_icm(dev, qpn); if (err) { res_abort_move(dev, slave, RES_QP, qpn); @@ -1499,7 +1540,7 @@ static int qp_free_res(struct mlx4_dev *dev, int slave, int op, int cmd, if (err) return err; - if (!valid_reserved(dev, slave, qpn)) + if (!fw_reserved(dev, qpn)) __mlx4_qp_free_icm(dev, qpn); res_end_move(dev, slave, RES_QP, qpn); @@ -1939,6 +1980,19 @@ static u32 qp_get_srqn(struct mlx4_qp_context *qpc) return be32_to_cpu(qpc->srqn) & 0x1ffffff; } +static void adjust_proxy_tun_qkey(struct mlx4_dev *dev, struct mlx4_vhcr *vhcr, + struct mlx4_qp_context *context) +{ + u32 qpn = vhcr->in_modifier & 0xffffff; + u32 qkey = 0; + + if (mlx4_get_parav_qkey(dev, qpn, &qkey)) + return; + + /* adjust qkey in qp context */ + context->qkey = cpu_to_be32(qkey); +} + int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, @@ -1991,6 +2045,8 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, goto ex_put_scq; } + adjust_proxy_tun_qkey(dev, vhcr, qpc); + update_pkey_index(dev, slave, inbox); err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd); if (err) goto ex_put_srq; @@ -2136,6 +2192,48 @@ static int get_containing_mtt(struct mlx4_dev *dev, int slave, int start, return err; } +static int verify_qp_parameters(struct mlx4_dev *dev, + struct mlx4_cmd_mailbox *inbox, + enum qp_transition transition, u8 slave) +{ + u32 qp_type; + struct mlx4_qp_context *qp_ctx; + enum mlx4_qp_optpar optpar; + + qp_ctx = inbox->buf + 8; + qp_type = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff; + optpar = be32_to_cpu(*(__be32 *) inbox->buf); + + switch (qp_type) { + case MLX4_QP_ST_RC: + case MLX4_QP_ST_UC: + switch (transition) { + case QP_TRANS_INIT2RTR: + case QP_TRANS_RTR2RTS: + case QP_TRANS_RTS2RTS: + case QP_TRANS_SQD2SQD: + case QP_TRANS_SQD2RTS: + if (slave != mlx4_master_func_num(dev)) + /* slaves have only gid index 0 */ + if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) + if (qp_ctx->pri_path.mgid_index) + return -EINVAL; + if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) + if (qp_ctx->alt_path.mgid_index) + return -EINVAL; + break; + default: + break; + } + + break; + default: + break; + } + + return 0; +} + int mlx4_WRITE_MTT_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, @@ -2623,16 +2721,123 @@ out: return err; } +int mlx4_INIT2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + struct mlx4_qp_context *context = inbox->buf + 8; + adjust_proxy_tun_qkey(dev, vhcr, context); + update_pkey_index(dev, slave, inbox); + return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd); +} + int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd) { + int err; struct mlx4_qp_context *qpc = inbox->buf + 8; - update_ud_gid(dev, qpc, (u8)slave); + err = verify_qp_parameters(dev, inbox, QP_TRANS_INIT2RTR, slave); + if (err) + return err; + + update_pkey_index(dev, slave, inbox); + update_gid(dev, inbox, (u8)slave); + adjust_proxy_tun_qkey(dev, vhcr, qpc); + + return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd); +} + +int mlx4_RTR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + int err; + struct mlx4_qp_context *context = inbox->buf + 8; + + err = verify_qp_parameters(dev, inbox, QP_TRANS_RTR2RTS, slave); + if (err) + return err; + + update_pkey_index(dev, slave, inbox); + update_gid(dev, inbox, (u8)slave); + adjust_proxy_tun_qkey(dev, vhcr, context); + return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd); +} + +int mlx4_RTS2RTS_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + int err; + struct mlx4_qp_context *context = inbox->buf + 8; + + err = verify_qp_parameters(dev, inbox, QP_TRANS_RTS2RTS, slave); + if (err) + return err; + + update_pkey_index(dev, slave, inbox); + update_gid(dev, inbox, (u8)slave); + adjust_proxy_tun_qkey(dev, vhcr, context); + return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd); +} + + +int mlx4_SQERR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + struct mlx4_qp_context *context = inbox->buf + 8; + adjust_proxy_tun_qkey(dev, vhcr, context); + return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd); +} + +int mlx4_SQD2SQD_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + int err; + struct mlx4_qp_context *context = inbox->buf + 8; + + err = verify_qp_parameters(dev, inbox, QP_TRANS_SQD2SQD, slave); + if (err) + return err; + + adjust_proxy_tun_qkey(dev, vhcr, context); + update_gid(dev, inbox, (u8)slave); + update_pkey_index(dev, slave, inbox); + return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd); +} + +int mlx4_SQD2RTS_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + int err; + struct mlx4_qp_context *context = inbox->buf + 8; + + err = verify_qp_parameters(dev, inbox, QP_TRANS_SQD2RTS, slave); + if (err) + return err; + adjust_proxy_tun_qkey(dev, vhcr, context); + update_gid(dev, inbox, (u8)slave); + update_pkey_index(dev, slave, inbox); return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd); } diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b6b8d341b6c8..9803fd5d3dba 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -940,6 +940,9 @@ int mlx4_flow_attach(struct mlx4_dev *dev, struct mlx4_net_trans_rule *rule, u64 *reg_id); int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id); +void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, + int i, int val); + int mlx4_get_parav_qkey(struct mlx4_dev *dev, u32 qpn, u32 *qkey); #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 0a9a01884d447c216eff75f8f274a0a3e82c7cee Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:45 +0000 Subject: mlx4: MAD_IFC paravirtualization The MAD_IFC firmware command fulfills two functions. First, it is used in the QP0/QP1 MAD-handling flow to obtain information from the FW (for answering queries), and for setting variables in the HCA (MAD SET packets). For this, MAD_IFC should provide the FW (physical) view of the data. This is the view that OpenSM needs. We call this the "network view". In the second case, MAD_IFC is used by various verbs to obtain data regarding the local HCA (e.g., ib_query_device()). We call this the "host view". This data needs to be paravirtualized. MAD_IFC therefore needs a wrapper function, and also needs another flag indicating whether it should provide the network view (when it is called by ib_process_mad in special-qp packet handling), or the host view (when it is called while implementing a verb). There are currently 2 flag parameters in mlx4_MAD_IFC already: ignore_bkey and ignore_mkey. These two parameters are replaced by a single "mad_ifc_flags" parameter, with different bits set for each flag. A third flag is added: "network-view/host-view". Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/mad.c | 20 ++-- drivers/infiniband/hw/mlx4/main.c | 64 ++++++++---- drivers/infiniband/hw/mlx4/mlx4_ib.h | 14 ++- drivers/net/ethernet/mellanox/mlx4/cmd.c | 162 +++++++++++++++++++++++++++++++ 4 files changed, 234 insertions(+), 26 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 8dfbf69f8370..ba2580693f79 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -75,7 +75,7 @@ struct mlx4_rcv_tunnel_mad { struct ib_mad mad; } __packed; -int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int ignore_mkey, int ignore_bkey, +int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags, int port, struct ib_wc *in_wc, struct ib_grh *in_grh, void *in_mad, void *response_mad) { @@ -102,10 +102,13 @@ int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int ignore_mkey, int ignore_bkey, * Key check traps can't be generated unless we have in_wc to * tell us where to send the trap. */ - if (ignore_mkey || !in_wc) + if ((mad_ifc_flags & MLX4_MAD_IFC_IGNORE_MKEY) || !in_wc) op_modifier |= 0x1; - if (ignore_bkey || !in_wc) + if ((mad_ifc_flags & MLX4_MAD_IFC_IGNORE_BKEY) || !in_wc) op_modifier |= 0x2; + if (mlx4_is_mfunc(dev->dev) && + (mad_ifc_flags & MLX4_MAD_IFC_NET_VIEW || in_wc)) + op_modifier |= 0x8; if (in_wc) { struct { @@ -138,10 +141,10 @@ int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int ignore_mkey, int ignore_bkey, in_modifier |= in_wc->slid << 16; } - err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma, - in_modifier, op_modifier, + err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma, in_modifier, + mlx4_is_master(dev->dev) ? (op_modifier & ~0x8) : op_modifier, MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C, - MLX4_CMD_NATIVE); + (op_modifier & 0x8) ? MLX4_CMD_NATIVE : MLX4_CMD_WRAPPED); if (!err) memcpy(response_mad, outmailbox->buf, 256); @@ -614,8 +617,9 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, prev_lid = pattr.lid; err = mlx4_MAD_IFC(to_mdev(ibdev), - mad_flags & IB_MAD_IGNORE_MKEY, - mad_flags & IB_MAD_IGNORE_BKEY, + (mad_flags & IB_MAD_IGNORE_MKEY ? MLX4_MAD_IFC_IGNORE_MKEY : 0) | + (mad_flags & IB_MAD_IGNORE_BKEY ? MLX4_MAD_IFC_IGNORE_BKEY : 0) | + MLX4_MAD_IFC_NET_VIEW, port_num, in_wc, in_grh, in_mad, out_mad); if (err) return IB_MAD_RESULT_FAILURE; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 8e10ec2af7b6..45a6cc04036b 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -98,7 +98,8 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_NODE_INFO; - err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, 1, NULL, NULL, in_mad, out_mad); + err = mlx4_MAD_IFC(to_mdev(ibdev), MLX4_MAD_IFC_IGNORE_KEYS, + 1, NULL, NULL, in_mad, out_mad); if (err) goto out; @@ -182,11 +183,12 @@ mlx4_ib_port_link_layer(struct ib_device *device, u8 port_num) } static int ib_link_query_port(struct ib_device *ibdev, u8 port, - struct ib_port_attr *props) + struct ib_port_attr *props, int netw_view) { struct ib_smp *in_mad = NULL; struct ib_smp *out_mad = NULL; int ext_active_speed; + int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS; int err = -ENOMEM; in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); @@ -198,7 +200,10 @@ static int ib_link_query_port(struct ib_device *ibdev, u8 port, in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; in_mad->attr_mod = cpu_to_be32(port); - err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, + if (mlx4_is_mfunc(to_mdev(ibdev)->dev) && netw_view) + mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW; + + err = mlx4_MAD_IFC(to_mdev(ibdev), mad_ifc_flags, port, NULL, NULL, in_mad, out_mad); if (err) goto out; @@ -211,7 +216,10 @@ static int ib_link_query_port(struct ib_device *ibdev, u8 port, props->state = out_mad->data[32] & 0xf; props->phys_state = out_mad->data[33] >> 4; props->port_cap_flags = be32_to_cpup((__be32 *) (out_mad->data + 20)); - props->gid_tbl_len = to_mdev(ibdev)->dev->caps.gid_table_len[port]; + if (netw_view) + props->gid_tbl_len = out_mad->data[50]; + else + props->gid_tbl_len = to_mdev(ibdev)->dev->caps.gid_table_len[port]; props->max_msg_sz = to_mdev(ibdev)->dev->caps.max_msg_sz; props->pkey_tbl_len = to_mdev(ibdev)->dev->caps.pkey_table_len[port]; props->bad_pkey_cntr = be16_to_cpup((__be16 *) (out_mad->data + 46)); @@ -244,7 +252,7 @@ static int ib_link_query_port(struct ib_device *ibdev, u8 port, in_mad->attr_id = MLX4_ATTR_EXTENDED_PORT_INFO; in_mad->attr_mod = cpu_to_be32(port); - err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, port, + err = mlx4_MAD_IFC(to_mdev(ibdev), mad_ifc_flags, port, NULL, NULL, in_mad, out_mad); if (err) goto out; @@ -270,7 +278,7 @@ static u8 state_to_phys_state(enum ib_port_state state) } static int eth_link_query_port(struct ib_device *ibdev, u8 port, - struct ib_port_attr *props) + struct ib_port_attr *props, int netw_view) { struct mlx4_ib_dev *mdev = to_mdev(ibdev); @@ -320,20 +328,27 @@ out: return err; } -static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port, - struct ib_port_attr *props) +int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port, + struct ib_port_attr *props, int netw_view) { int err; memset(props, 0, sizeof *props); err = mlx4_ib_port_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND ? - ib_link_query_port(ibdev, port, props) : - eth_link_query_port(ibdev, port, props); + ib_link_query_port(ibdev, port, props, netw_view) : + eth_link_query_port(ibdev, port, props, netw_view); return err; } +static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port, + struct ib_port_attr *props) +{ + /* returns host view */ + return __mlx4_ib_query_port(ibdev, port, props, 0); +} + static int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, union ib_gid *gid) { @@ -350,7 +365,8 @@ static int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; in_mad->attr_mod = cpu_to_be32(port); - err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad); + err = mlx4_MAD_IFC(to_mdev(ibdev), MLX4_MAD_IFC_IGNORE_KEYS, port, + NULL, NULL, in_mad, out_mad); if (err) goto out; @@ -360,7 +376,8 @@ static int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, in_mad->attr_id = IB_SMP_ATTR_GUID_INFO; in_mad->attr_mod = cpu_to_be32(index / 8); - err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad); + err = mlx4_MAD_IFC(to_mdev(ibdev), MLX4_MAD_IFC_IGNORE_KEYS, port, + NULL, NULL, in_mad, out_mad); if (err) goto out; @@ -391,11 +408,12 @@ static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, return iboe_query_gid(ibdev, port, index, gid); } -static int mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, - u16 *pkey) +int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, + u16 *pkey, int netw_view) { struct ib_smp *in_mad = NULL; struct ib_smp *out_mad = NULL; + int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS; int err = -ENOMEM; in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); @@ -407,7 +425,11 @@ static int mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, in_mad->attr_id = IB_SMP_ATTR_PKEY_TABLE; in_mad->attr_mod = cpu_to_be32(index / 32); - err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad); + if (mlx4_is_mfunc(to_mdev(ibdev)->dev) && netw_view) + mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW; + + err = mlx4_MAD_IFC(to_mdev(ibdev), mad_ifc_flags, port, NULL, NULL, + in_mad, out_mad); if (err) goto out; @@ -419,6 +441,11 @@ out: return err; } +static int mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey) +{ + return __mlx4_ib_query_pkey(ibdev, port, index, pkey, 0); +} + static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask, struct ib_device_modify *props) { @@ -849,6 +876,7 @@ static int init_node_data(struct mlx4_ib_dev *dev) { struct ib_smp *in_mad = NULL; struct ib_smp *out_mad = NULL; + int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS; int err = -ENOMEM; in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); @@ -858,8 +886,10 @@ static int init_node_data(struct mlx4_ib_dev *dev) init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_NODE_DESC; + if (mlx4_is_master(dev->dev)) + mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW; - err = mlx4_MAD_IFC(dev, 1, 1, 1, NULL, NULL, in_mad, out_mad); + err = mlx4_MAD_IFC(dev, mad_ifc_flags, 1, NULL, NULL, in_mad, out_mad); if (err) goto out; @@ -867,7 +897,7 @@ static int init_node_data(struct mlx4_ib_dev *dev) in_mad->attr_id = IB_SMP_ATTR_NODE_INFO; - err = mlx4_MAD_IFC(dev, 1, 1, 1, NULL, NULL, in_mad, out_mad); + err = mlx4_MAD_IFC(dev, mad_ifc_flags, 1, NULL, NULL, in_mad, out_mad); if (err) goto out; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 137941d79870..ac71d56ffc7e 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -176,6 +176,14 @@ enum mlx4_ib_qp_type { MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI | MLX4_IB_QPT_TUN_SMI_OWNER | \ MLX4_IB_QPT_TUN_SMI | MLX4_IB_QPT_TUN_GSI) +enum mlx4_ib_mad_ifc_flags { + MLX4_MAD_IFC_IGNORE_MKEY = 1, + MLX4_MAD_IFC_IGNORE_BKEY = 2, + MLX4_MAD_IFC_IGNORE_KEYS = (MLX4_MAD_IFC_IGNORE_MKEY | + MLX4_MAD_IFC_IGNORE_BKEY), + MLX4_MAD_IFC_NET_VIEW = 4, +}; + enum { MLX4_NUM_TUNNEL_BUFS = 256, }; @@ -512,7 +520,7 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, int mlx4_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr, struct ib_recv_wr **bad_wr); -int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int ignore_mkey, int ignore_bkey, +int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags, int port, struct ib_wc *in_wc, struct ib_grh *in_grh, void *in_mad, void *response_mad); int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, @@ -527,6 +535,10 @@ int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, int npages, u64 iova); int mlx4_ib_unmap_fmr(struct list_head *fmr_list); int mlx4_ib_fmr_dealloc(struct ib_fmr *fmr); +int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port, + struct ib_port_attr *props, int netw_view); +int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, + u16 *pkey, int netw_view); int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr, u8 *mac, int *is_mcast, u8 port); diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 662a3c5da739..a13d8a69b3bc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -40,6 +40,7 @@ #include #include +#include #include @@ -627,6 +628,149 @@ static int mlx4_ACCESS_MEM(struct mlx4_dev *dev, u64 master_addr, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); } +static int query_pkey_block(struct mlx4_dev *dev, u8 port, u16 index, u16 *pkey, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox) +{ + struct ib_smp *in_mad = (struct ib_smp *)(inbox->buf); + struct ib_smp *out_mad = (struct ib_smp *)(outbox->buf); + int err; + int i; + + if (index & 0x1f) + return -EINVAL; + + in_mad->attr_mod = cpu_to_be32(index / 32); + + err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, port, 3, + MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C, + MLX4_CMD_NATIVE); + if (err) + return err; + + for (i = 0; i < 32; ++i) + pkey[i] = be16_to_cpu(((__be16 *) out_mad->data)[i]); + + return err; +} + +static int get_full_pkey_table(struct mlx4_dev *dev, u8 port, u16 *table, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox) +{ + int i; + int err; + + for (i = 0; i < dev->caps.pkey_table_len[port]; i += 32) { + err = query_pkey_block(dev, port, i, table + i, inbox, outbox); + if (err) + return err; + } + + return 0; +} +#define PORT_CAPABILITY_LOCATION_IN_SMP 20 +#define PORT_STATE_OFFSET 32 + +static enum ib_port_state vf_port_state(struct mlx4_dev *dev, int port, int vf) +{ + /* will be modified when add alias_guid feature */ + return IB_PORT_DOWN; +} + +static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + struct ib_smp *smp = inbox->buf; + u32 index; + u8 port; + u16 *table; + int err; + int vidx, pidx; + struct mlx4_priv *priv = mlx4_priv(dev); + struct ib_smp *outsmp = outbox->buf; + __be16 *outtab = (__be16 *)(outsmp->data); + __be32 slave_cap_mask; + port = vhcr->in_modifier; + + if (smp->base_version == 1 && + smp->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED && + smp->class_version == 1) { + if (smp->method == IB_MGMT_METHOD_GET) { + if (smp->attr_id == IB_SMP_ATTR_PKEY_TABLE) { + index = be32_to_cpu(smp->attr_mod); + if (port < 1 || port > dev->caps.num_ports) + return -EINVAL; + table = kcalloc(dev->caps.pkey_table_len[port], sizeof *table, GFP_KERNEL); + if (!table) + return -ENOMEM; + /* need to get the full pkey table because the paravirtualized + * pkeys may be scattered among several pkey blocks. + */ + err = get_full_pkey_table(dev, port, table, inbox, outbox); + if (!err) { + for (vidx = index * 32; vidx < (index + 1) * 32; ++vidx) { + pidx = priv->virt2phys_pkey[slave][port - 1][vidx]; + outtab[vidx % 32] = cpu_to_be16(table[pidx]); + } + } + kfree(table); + return err; + } + if (smp->attr_id == IB_SMP_ATTR_PORT_INFO) { + /*get the slave specific caps:*/ + /*do the command */ + err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, + vhcr->in_modifier, vhcr->op_modifier, + vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE); + /* modify the response for slaves */ + if (!err && slave != mlx4_master_func_num(dev)) { + u8 *state = outsmp->data + PORT_STATE_OFFSET; + + *state = (*state & 0xf0) | vf_port_state(dev, port, slave); + slave_cap_mask = priv->mfunc.master.slave_state[slave].ib_cap_mask[port]; + memcpy(outsmp->data + PORT_CAPABILITY_LOCATION_IN_SMP, &slave_cap_mask, 4); + } + return err; + } + if (smp->attr_id == IB_SMP_ATTR_GUID_INFO) { + /* compute slave's gid block */ + smp->attr_mod = cpu_to_be32(slave / 8); + /* execute cmd */ + err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, + vhcr->in_modifier, vhcr->op_modifier, + vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE); + if (!err) { + /* if needed, move slave gid to index 0 */ + if (slave % 8) + memcpy(outsmp->data, + outsmp->data + (slave % 8) * 8, 8); + /* delete all other gids */ + memset(outsmp->data + 8, 0, 56); + } + return err; + } + } + } + if (slave != mlx4_master_func_num(dev) && + ((smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) || + (smp->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED && + smp->method == IB_MGMT_METHOD_SET))) { + mlx4_err(dev, "slave %d is trying to execute a Subnet MGMT MAD, " + "class 0x%x, method 0x%x for attr 0x%x. Rejecting\n", + slave, smp->method, smp->mgmt_class, + be16_to_cpu(smp->attr_id)); + return -EPERM; + } + /*default:*/ + return mlx4_cmd_box(dev, inbox->dma, outbox->dma, + vhcr->in_modifier, vhcr->op_modifier, + vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE); +} + int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, @@ -1060,6 +1204,24 @@ static struct mlx4_cmd_info cmd_info[] = { .verify = NULL, .wrapper = mlx4_GEN_QP_wrapper }, + { + .opcode = MLX4_CMD_CONF_SPECIAL_QP, + .has_inbox = false, + .has_outbox = false, + .out_is_imm = false, + .encode_slave_id = false, + .verify = NULL, /* XXX verify: only demux can do this */ + .wrapper = NULL + }, + { + .opcode = MLX4_CMD_MAD_IFC, + .has_inbox = true, + .has_outbox = true, + .out_is_imm = false, + .encode_slave_id = false, + .verify = NULL, + .wrapper = mlx4_MAD_IFC_wrapper + }, { .opcode = MLX4_CMD_QUERY_IF_STAT, .has_inbox = false, -- cgit v1.2.3 From 993c401e207946fa56f69c51e39f015e7108497b Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:48 +0000 Subject: mlx4_core: Add IB port-state machine and port mgmt event propagation For an IB port, a slave should not show port active until that slave has a valid alias-guid (provided by the subnet manager). Therefore the port-up event should be passed to a slave only after both the port is up, and the slave's alias-guid has been set. Also, provide the infrastructure for propagating port-management events (client-reregister, etc) to slaves. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/eq.c | 237 ++++++++++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 1 + include/linux/mlx4/device.h | 28 ++++ 3 files changed, 250 insertions(+), 16 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 99a04648fab0..c425826b1fc0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -200,6 +200,196 @@ static void mlx4_slave_event(struct mlx4_dev *dev, int slave, slave_event(dev, slave, eqe); } +int mlx4_gen_pkey_eqe(struct mlx4_dev *dev, int slave, u8 port) +{ + struct mlx4_eqe eqe; + + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_slave_state *s_slave = &priv->mfunc.master.slave_state[slave]; + + if (!s_slave->active) + return 0; + + memset(&eqe, 0, sizeof eqe); + + eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT; + eqe.subtype = MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE; + eqe.event.port_mgmt_change.port = port; + + return mlx4_GEN_EQE(dev, slave, &eqe); +} +EXPORT_SYMBOL(mlx4_gen_pkey_eqe); + +int mlx4_gen_guid_change_eqe(struct mlx4_dev *dev, int slave, u8 port) +{ + struct mlx4_eqe eqe; + + /*don't send if we don't have the that slave */ + if (dev->num_vfs < slave) + return 0; + memset(&eqe, 0, sizeof eqe); + + eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT; + eqe.subtype = MLX4_DEV_PMC_SUBTYPE_GUID_INFO; + eqe.event.port_mgmt_change.port = port; + + return mlx4_GEN_EQE(dev, slave, &eqe); +} +EXPORT_SYMBOL(mlx4_gen_guid_change_eqe); + +int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port, + u8 port_subtype_change) +{ + struct mlx4_eqe eqe; + + /*don't send if we don't have the that slave */ + if (dev->num_vfs < slave) + return 0; + memset(&eqe, 0, sizeof eqe); + + eqe.type = MLX4_EVENT_TYPE_PORT_CHANGE; + eqe.subtype = port_subtype_change; + eqe.event.port_change.port = cpu_to_be32(port << 28); + + mlx4_dbg(dev, "%s: sending: %d to slave: %d on port: %d\n", __func__, + port_subtype_change, slave, port); + return mlx4_GEN_EQE(dev, slave, &eqe); +} +EXPORT_SYMBOL(mlx4_gen_port_state_change_eqe); + +enum slave_port_state mlx4_get_slave_port_state(struct mlx4_dev *dev, int slave, u8 port) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_slave_state *s_state = priv->mfunc.master.slave_state; + if (slave >= dev->num_slaves || port > MLX4_MAX_PORTS) { + pr_err("%s: Error: asking for slave:%d, port:%d\n", + __func__, slave, port); + return SLAVE_PORT_DOWN; + } + return s_state[slave].port_state[port]; +} +EXPORT_SYMBOL(mlx4_get_slave_port_state); + +static int mlx4_set_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, + enum slave_port_state state) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_slave_state *s_state = priv->mfunc.master.slave_state; + + if (slave >= dev->num_slaves || port > MLX4_MAX_PORTS || port == 0) { + pr_err("%s: Error: asking for slave:%d, port:%d\n", + __func__, slave, port); + return -1; + } + s_state[slave].port_state[port] = state; + + return 0; +} + +static void set_all_slave_state(struct mlx4_dev *dev, u8 port, int event) +{ + int i; + enum slave_port_gen_event gen_event; + + for (i = 0; i < dev->num_slaves; i++) + set_and_calc_slave_port_state(dev, i, port, event, &gen_event); +} +/************************************************************************** + The function get as input the new event to that port, + and according to the prev state change the slave's port state. + The events are: + MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN, + MLX4_PORT_STATE_DEV_EVENT_PORT_UP + MLX4_PORT_STATE_IB_EVENT_GID_VALID + MLX4_PORT_STATE_IB_EVENT_GID_INVALID +***************************************************************************/ +int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, + u8 port, int event, + enum slave_port_gen_event *gen_event) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_slave_state *ctx = NULL; + unsigned long flags; + int ret = -1; + enum slave_port_state cur_state = + mlx4_get_slave_port_state(dev, slave, port); + + *gen_event = SLAVE_PORT_GEN_EVENT_NONE; + + if (slave >= dev->num_slaves || port > MLX4_MAX_PORTS || port == 0) { + pr_err("%s: Error: asking for slave:%d, port:%d\n", + __func__, slave, port); + return ret; + } + + ctx = &priv->mfunc.master.slave_state[slave]; + spin_lock_irqsave(&ctx->lock, flags); + + mlx4_dbg(dev, "%s: slave: %d, current state: %d new event :%d\n", + __func__, slave, cur_state, event); + + switch (cur_state) { + case SLAVE_PORT_DOWN: + if (MLX4_PORT_STATE_DEV_EVENT_PORT_UP == event) + mlx4_set_slave_port_state(dev, slave, port, + SLAVE_PENDING_UP); + break; + case SLAVE_PENDING_UP: + if (MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN == event) + mlx4_set_slave_port_state(dev, slave, port, + SLAVE_PORT_DOWN); + else if (MLX4_PORT_STATE_IB_PORT_STATE_EVENT_GID_VALID == event) { + mlx4_set_slave_port_state(dev, slave, port, + SLAVE_PORT_UP); + *gen_event = SLAVE_PORT_GEN_EVENT_UP; + } + break; + case SLAVE_PORT_UP: + if (MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN == event) { + mlx4_set_slave_port_state(dev, slave, port, + SLAVE_PORT_DOWN); + *gen_event = SLAVE_PORT_GEN_EVENT_DOWN; + } else if (MLX4_PORT_STATE_IB_EVENT_GID_INVALID == + event) { + mlx4_set_slave_port_state(dev, slave, port, + SLAVE_PENDING_UP); + *gen_event = SLAVE_PORT_GEN_EVENT_DOWN; + } + break; + default: + pr_err("%s: BUG!!! UNKNOWN state: " + "slave:%d, port:%d\n", __func__, slave, port); + goto out; + } + ret = mlx4_get_slave_port_state(dev, slave, port); + mlx4_dbg(dev, "%s: slave: %d, current state: %d new event" + " :%d gen_event: %d\n", + __func__, slave, cur_state, event, *gen_event); + +out: + spin_unlock_irqrestore(&ctx->lock, flags); + return ret; +} + +EXPORT_SYMBOL(set_and_calc_slave_port_state); + +int mlx4_gen_slaves_port_mgt_ev(struct mlx4_dev *dev, u8 port, int attr) +{ + struct mlx4_eqe eqe; + + memset(&eqe, 0, sizeof eqe); + + eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT; + eqe.subtype = MLX4_DEV_PMC_SUBTYPE_PORT_INFO; + eqe.event.port_mgmt_change.port = port; + eqe.event.port_mgmt_change.params.port_info.changed_attr = + cpu_to_be32((u32) attr); + + slave_event(dev, ALL_SLAVES, &eqe); + return 0; +} +EXPORT_SYMBOL(mlx4_gen_slaves_port_mgt_ev); + void mlx4_master_handle_slave_flr(struct work_struct *work) { struct mlx4_mfunc_master_ctx *master = @@ -251,6 +441,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) u32 flr_slave; u8 update_slave_state; int i; + enum slave_port_gen_event gen_event; while ((eqe = next_eqe_sw(eq))) { /* @@ -347,35 +538,49 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) case MLX4_EVENT_TYPE_PORT_CHANGE: port = be32_to_cpu(eqe->event.port_change.port) >> 28; if (eqe->subtype == MLX4_PORT_CHANGE_SUBTYPE_DOWN) { - mlx4_dispatch_event(dev, - MLX4_DEV_EVENT_PORT_DOWN, + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_DOWN, port); mlx4_priv(dev)->sense.do_sense_port[port] = 1; - if (mlx4_is_master(dev)) - /*change the state of all slave's port - * to down:*/ - for (i = 0; i < dev->num_slaves; i++) { - mlx4_dbg(dev, "%s: Sending " - "MLX4_PORT_CHANGE_SUBTYPE_DOWN" + if (!mlx4_is_master(dev)) + break; + for (i = 0; i < dev->num_slaves; i++) { + if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) { + if (i == mlx4_master_func_num(dev)) + continue; + mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN" " to slave: %d, port:%d\n", __func__, i, port); - if (i == dev->caps.function) - continue; mlx4_slave_event(dev, i, eqe); + } else { /* IB port */ + set_and_calc_slave_port_state(dev, i, port, + MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN, + &gen_event); + /*we can be in pending state, then do not send port_down event*/ + if (SLAVE_PORT_GEN_EVENT_DOWN == gen_event) { + if (i == mlx4_master_func_num(dev)) + continue; + mlx4_slave_event(dev, i, eqe); + } } + } } else { - mlx4_dispatch_event(dev, - MLX4_DEV_EVENT_PORT_UP, - port); + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_UP, port); + mlx4_priv(dev)->sense.do_sense_port[port] = 0; - if (mlx4_is_master(dev)) { + if (!mlx4_is_master(dev)) + break; + if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) for (i = 0; i < dev->num_slaves; i++) { - if (i == dev->caps.function) + if (i == mlx4_master_func_num(dev)) continue; mlx4_slave_event(dev, i, eqe); } - } + else /* IB port */ + /* port-up event will be sent to a slave when the + * slave's alias-guid is set. This is done in alias_GUID.c + */ + set_all_slave_state(dev, port, MLX4_DEV_EVENT_PORT_UP); } break; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 7d27c3158d0c..23f74759f403 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -452,6 +452,7 @@ struct mlx4_slave_state { /*initialized via the kzalloc*/ u8 is_slave_going_down; u32 cookie; + enum slave_port_state port_state[MLX4_MAX_PORTS + 1]; }; struct slave_list { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 9803fd5d3dba..380e01671d1e 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -192,6 +192,25 @@ enum { MLX4_FATAL_WARNING_SUBTYPE_WARMING = 0, }; +enum slave_port_state { + SLAVE_PORT_DOWN = 0, + SLAVE_PENDING_UP, + SLAVE_PORT_UP, +}; + +enum slave_port_gen_event { + SLAVE_PORT_GEN_EVENT_DOWN = 0, + SLAVE_PORT_GEN_EVENT_UP, + SLAVE_PORT_GEN_EVENT_NONE, +}; + +enum slave_port_state_event { + MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN, + MLX4_PORT_STATE_DEV_EVENT_PORT_UP, + MLX4_PORT_STATE_IB_PORT_STATE_EVENT_GID_VALID, + MLX4_PORT_STATE_IB_EVENT_GID_INVALID, +}; + enum { MLX4_PERM_LOCAL_READ = 1 << 10, MLX4_PERM_LOCAL_WRITE = 1 << 11, @@ -945,4 +964,13 @@ void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, int mlx4_get_parav_qkey(struct mlx4_dev *dev, u32 qpn, u32 *qkey); +int mlx4_is_slave_active(struct mlx4_dev *dev, int slave); +int mlx4_gen_pkey_eqe(struct mlx4_dev *dev, int slave, u8 port); +int mlx4_gen_guid_change_eqe(struct mlx4_dev *dev, int slave, u8 port); +int mlx4_gen_slaves_port_mgt_ev(struct mlx4_dev *dev, u8 port, int attr); +int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port, u8 port_subtype_change); +enum slave_port_state mlx4_get_slave_port_state(struct mlx4_dev *dev, int slave, u8 port); +int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int event, enum slave_port_gen_event *gen_event); + + #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From a0c64a17aba88c29d55ba989b96ac6ccb1268f0a Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:49 +0000 Subject: mlx4: Add alias_guid mechanism For IB ports, we paravirtualize the GUID at index 0 on slaves. The GUID at index 0 seen by a slave is the actual GUID occupying the GUID table at the slave-id index. The driver, by default, requests at startup time that subnet manager populate its entire guid table with GUIDs. These guids are then mapped (paravirtualized) to the slaves, and appear for each slave as its GUID at index 0. Until each slave has such a guid, its port status is DOWN. The guid table is cached to support special QP paravirtualization, and event propagation to slaves on guid change (we test to see if the guid really changed before propagating an event to the slave). To support this caching, add capability to __mlx4_ib_query_gid() to obtain the network view (i.e., physical view) gid at index X, not just the host (paravirtualized) view. Based on a patch from Erez Shitrit Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/Makefile | 2 +- drivers/infiniband/hw/mlx4/alias_GUID.c | 688 +++++++++++++++++++++++++++++++ drivers/infiniband/hw/mlx4/mad.c | 19 +- drivers/infiniband/hw/mlx4/main.c | 37 +- drivers/infiniband/hw/mlx4/mlx4_ib.h | 74 ++++ drivers/net/ethernet/mellanox/mlx4/cmd.c | 6 +- 6 files changed, 816 insertions(+), 10 deletions(-) create mode 100644 drivers/infiniband/hw/mlx4/alias_GUID.c (limited to 'drivers/net/ethernet') diff --git a/drivers/infiniband/hw/mlx4/Makefile b/drivers/infiniband/hw/mlx4/Makefile index bf0aa901c313..31d4c8aac679 100644 --- a/drivers/infiniband/hw/mlx4/Makefile +++ b/drivers/infiniband/hw/mlx4/Makefile @@ -1,3 +1,3 @@ obj-$(CONFIG_MLX4_INFINIBAND) += mlx4_ib.o -mlx4_ib-y := ah.o cq.o doorbell.o mad.o main.o mr.o qp.o srq.o mcg.o cm.o +mlx4_ib-y := ah.o cq.o doorbell.o mad.o main.o mr.o qp.o srq.o mcg.o cm.o alias_GUID.o diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c new file mode 100644 index 000000000000..ef6d356927c3 --- /dev/null +++ b/drivers/infiniband/hw/mlx4/alias_GUID.c @@ -0,0 +1,688 @@ +/* + * Copyright (c) 2012 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + /***********************************************************/ +/*This file support the handling of the Alias GUID feature. */ +/***********************************************************/ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "mlx4_ib.h" + +/* +The driver keeps the current state of all guids, as they are in the HW. +Whenever we receive an smp mad GUIDInfo record, the data will be cached. +*/ + +struct mlx4_alias_guid_work_context { + u8 port; + struct mlx4_ib_dev *dev ; + struct ib_sa_query *sa_query; + struct completion done; + int query_id; + struct list_head list; + int block_num; +}; + +struct mlx4_next_alias_guid_work { + u8 port; + u8 block_num; + struct mlx4_sriov_alias_guid_info_rec_det rec_det; +}; + + +void mlx4_ib_update_cache_on_guid_change(struct mlx4_ib_dev *dev, int block_num, + u8 port_num, u8 *p_data) +{ + int i; + u64 guid_indexes; + int slave_id; + int port_index = port_num - 1; + + if (!mlx4_is_master(dev->dev)) + return; + + guid_indexes = be64_to_cpu((__force __be64) dev->sriov.alias_guid. + ports_guid[port_num - 1]. + all_rec_per_port[block_num].guid_indexes); + pr_debug("port: %d, guid_indexes: 0x%llx\n", port_num, guid_indexes); + + for (i = 0; i < NUM_ALIAS_GUID_IN_REC; i++) { + /* The location of the specific index starts from bit number 4 + * until bit num 11 */ + if (test_bit(i + 4, (unsigned long *)&guid_indexes)) { + slave_id = (block_num * NUM_ALIAS_GUID_IN_REC) + i ; + if (slave_id >= dev->dev->num_slaves) { + pr_debug("The last slave: %d\n", slave_id); + return; + } + + /* cache the guid: */ + memcpy(&dev->sriov.demux[port_index].guid_cache[slave_id], + &p_data[i * GUID_REC_SIZE], + GUID_REC_SIZE); + } else + pr_debug("Guid number: %d in block: %d" + " was not updated\n", i, block_num); + } +} + +static __be64 get_cached_alias_guid(struct mlx4_ib_dev *dev, int port, int index) +{ + if (index >= NUM_ALIAS_GUID_PER_PORT) { + pr_err("%s: ERROR: asked for index:%d\n", __func__, index); + return (__force __be64) ((u64) 0xFFFFFFFFFFFFFFFFUL); + } + return *(__be64 *)&dev->sriov.demux[port - 1].guid_cache[index]; +} + + +static ib_sa_comp_mask get_aguid_comp_mask_from_ix(int index) +{ + return IB_SA_COMP_MASK(4 + index); +} + +/* + * Whenever new GUID is set/unset (guid table change) create event and + * notify the relevant slave (master also should be notified). + * If the GUID value is not as we have in the cache the slave will not be + * updated; in this case it waits for the smp_snoop or the port management + * event to call the function and to update the slave. + * block_number - the index of the block (16 blocks available) + * port_number - 1 or 2 + */ +void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, + int block_num, u8 port_num, + u8 *p_data) +{ + int i; + u64 guid_indexes; + int slave_id; + enum slave_port_state new_state; + enum slave_port_state prev_state; + __be64 tmp_cur_ag, form_cache_ag; + enum slave_port_gen_event gen_event; + + if (!mlx4_is_master(dev->dev)) + return; + + guid_indexes = be64_to_cpu((__force __be64) dev->sriov.alias_guid. + ports_guid[port_num - 1]. + all_rec_per_port[block_num].guid_indexes); + pr_debug("port: %d, guid_indexes: 0x%llx\n", port_num, guid_indexes); + + /*calculate the slaves and notify them*/ + for (i = 0; i < NUM_ALIAS_GUID_IN_REC; i++) { + /* the location of the specific index runs from bits 4..11 */ + if (!(test_bit(i + 4, (unsigned long *)&guid_indexes))) + continue; + + slave_id = (block_num * NUM_ALIAS_GUID_IN_REC) + i ; + if (slave_id >= dev->dev->num_slaves) + return; + tmp_cur_ag = *(__be64 *)&p_data[i * GUID_REC_SIZE]; + form_cache_ag = get_cached_alias_guid(dev, port_num, + (NUM_ALIAS_GUID_IN_REC * block_num) + i); + /* + * Check if guid is not the same as in the cache, + * If it is different, wait for the snoop_smp or the port mgmt + * change event to update the slave on its port state change + */ + if (tmp_cur_ag != form_cache_ag) + continue; + mlx4_gen_guid_change_eqe(dev->dev, slave_id, port_num); + + /*2 cases: Valid GUID, and Invalid Guid*/ + + if (tmp_cur_ag != MLX4_NOT_SET_GUID) { /*valid GUID*/ + prev_state = mlx4_get_slave_port_state(dev->dev, slave_id, port_num); + new_state = set_and_calc_slave_port_state(dev->dev, slave_id, port_num, + MLX4_PORT_STATE_IB_PORT_STATE_EVENT_GID_VALID, + &gen_event); + pr_debug("slave: %d, port: %d prev_port_state: %d," + " new_port_state: %d, gen_event: %d\n", + slave_id, port_num, prev_state, new_state, gen_event); + if (gen_event == SLAVE_PORT_GEN_EVENT_UP) { + pr_debug("sending PORT_UP event to slave: %d, port: %d\n", + slave_id, port_num); + mlx4_gen_port_state_change_eqe(dev->dev, slave_id, + port_num, MLX4_PORT_CHANGE_SUBTYPE_ACTIVE); + } + } else { /* request to invalidate GUID */ + set_and_calc_slave_port_state(dev->dev, slave_id, port_num, + MLX4_PORT_STATE_IB_EVENT_GID_INVALID, + &gen_event); + pr_debug("sending PORT DOWN event to slave: %d, port: %d\n", + slave_id, port_num); + mlx4_gen_port_state_change_eqe(dev->dev, slave_id, port_num, + MLX4_PORT_CHANGE_SUBTYPE_DOWN); + } + } +} + +static void aliasguid_query_handler(int status, + struct ib_sa_guidinfo_rec *guid_rec, + void *context) +{ + struct mlx4_ib_dev *dev; + struct mlx4_alias_guid_work_context *cb_ctx = context; + u8 port_index ; + int i; + struct mlx4_sriov_alias_guid_info_rec_det *rec; + unsigned long flags, flags1; + + if (!context) + return; + + dev = cb_ctx->dev; + port_index = cb_ctx->port - 1; + rec = &dev->sriov.alias_guid.ports_guid[port_index]. + all_rec_per_port[cb_ctx->block_num]; + + if (status) { + rec->status = MLX4_GUID_INFO_STATUS_IDLE; + pr_debug("(port: %d) failed: status = %d\n", + cb_ctx->port, status); + goto out; + } + + if (guid_rec->block_num != cb_ctx->block_num) { + pr_err("block num mismatch: %d != %d\n", + cb_ctx->block_num, guid_rec->block_num); + goto out; + } + + pr_debug("lid/port: %d/%d, block_num: %d\n", + be16_to_cpu(guid_rec->lid), cb_ctx->port, + guid_rec->block_num); + + rec = &dev->sriov.alias_guid.ports_guid[port_index]. + all_rec_per_port[guid_rec->block_num]; + + rec->status = MLX4_GUID_INFO_STATUS_SET; + rec->method = MLX4_GUID_INFO_RECORD_SET; + + for (i = 0 ; i < NUM_ALIAS_GUID_IN_REC; i++) { + __be64 tmp_cur_ag; + tmp_cur_ag = *(__be64 *)&guid_rec->guid_info_list[i * GUID_REC_SIZE]; + /* check if the SM didn't assign one of the records. + * if it didn't, if it was not sysadmin request: + * ask the SM to give a new GUID, (instead of the driver request). + */ + if (tmp_cur_ag == MLX4_NOT_SET_GUID) { + mlx4_ib_warn(&dev->ib_dev, "%s:Record num %d in " + "block_num: %d was declined by SM, " + "ownership by %d (0 = driver, 1=sysAdmin," + " 2=None)\n", __func__, i, + guid_rec->block_num, rec->ownership); + if (rec->ownership == MLX4_GUID_DRIVER_ASSIGN) { + /* if it is driver assign, asks for new GUID from SM*/ + *(__be64 *)&rec->all_recs[i * GUID_REC_SIZE] = + MLX4_NOT_SET_GUID; + + /* Mark the record as not assigned, and let it + * be sent again in the next work sched.*/ + rec->status = MLX4_GUID_INFO_STATUS_IDLE; + rec->guid_indexes |= get_aguid_comp_mask_from_ix(i); + } + } else { + /* properly assigned record. */ + /* We save the GUID we just got from the SM in the + * admin_guid in order to be persistent, and in the + * request from the sm the process will ask for the same GUID */ + if (rec->ownership == MLX4_GUID_SYSADMIN_ASSIGN && + tmp_cur_ag != *(__be64 *)&rec->all_recs[i * GUID_REC_SIZE]) { + /* the sysadmin assignment failed.*/ + mlx4_ib_warn(&dev->ib_dev, "%s: Failed to set" + " admin guid after SysAdmin " + "configuration. " + "Record num %d in block_num:%d " + "was declined by SM, " + "new val(0x%llx) was kept\n", + __func__, i, + guid_rec->block_num, + be64_to_cpu(*(__be64 *) & + rec->all_recs[i * GUID_REC_SIZE])); + } else { + memcpy(&rec->all_recs[i * GUID_REC_SIZE], + &guid_rec->guid_info_list[i * GUID_REC_SIZE], + GUID_REC_SIZE); + } + } + } + /* + The func is call here to close the cases when the + sm doesn't send smp, so in the sa response the driver + notifies the slave. + */ + mlx4_ib_notify_slaves_on_guid_change(dev, guid_rec->block_num, + cb_ctx->port, + guid_rec->guid_info_list); +out: + spin_lock_irqsave(&dev->sriov.going_down_lock, flags); + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1); + if (!dev->sriov.is_going_down) + queue_delayed_work(dev->sriov.alias_guid.ports_guid[port_index].wq, + &dev->sriov.alias_guid.ports_guid[port_index]. + alias_guid_work, 0); + if (cb_ctx->sa_query) { + list_del(&cb_ctx->list); + kfree(cb_ctx); + } else + complete(&cb_ctx->done); + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags1); + spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags); +} + +static void invalidate_guid_record(struct mlx4_ib_dev *dev, u8 port, int index) +{ + int i; + u64 cur_admin_val; + ib_sa_comp_mask comp_mask = 0; + + dev->sriov.alias_guid.ports_guid[port - 1].all_rec_per_port[index].status + = MLX4_GUID_INFO_STATUS_IDLE; + dev->sriov.alias_guid.ports_guid[port - 1].all_rec_per_port[index].method + = MLX4_GUID_INFO_RECORD_SET; + + /* calculate the comp_mask for that record.*/ + for (i = 0; i < NUM_ALIAS_GUID_IN_REC; i++) { + cur_admin_val = + *(u64 *)&dev->sriov.alias_guid.ports_guid[port - 1]. + all_rec_per_port[index].all_recs[GUID_REC_SIZE * i]; + /* + check the admin value: if it's for delete (~00LL) or + it is the first guid of the first record (hw guid) or + the records is not in ownership of the sysadmin and the sm doesn't + need to assign GUIDs, then don't put it up for assignment. + */ + if (MLX4_GUID_FOR_DELETE_VAL == cur_admin_val || + (!index && !i) || + MLX4_GUID_NONE_ASSIGN == dev->sriov.alias_guid. + ports_guid[port - 1].all_rec_per_port[index].ownership) + continue; + comp_mask |= get_aguid_comp_mask_from_ix(i); + } + dev->sriov.alias_guid.ports_guid[port - 1]. + all_rec_per_port[index].guid_indexes = comp_mask; +} + +static int set_guid_rec(struct ib_device *ibdev, + u8 port, int index, + struct mlx4_sriov_alias_guid_info_rec_det *rec_det) +{ + int err; + struct mlx4_ib_dev *dev = to_mdev(ibdev); + struct ib_sa_guidinfo_rec guid_info_rec; + ib_sa_comp_mask comp_mask; + struct ib_port_attr attr; + struct mlx4_alias_guid_work_context *callback_context; + unsigned long resched_delay, flags, flags1; + struct list_head *head = + &dev->sriov.alias_guid.ports_guid[port - 1].cb_list; + + err = __mlx4_ib_query_port(ibdev, port, &attr, 1); + if (err) { + pr_debug("mlx4_ib_query_port failed (err: %d), port: %d\n", + err, port); + return err; + } + /*check the port was configured by the sm, otherwise no need to send */ + if (attr.state != IB_PORT_ACTIVE) { + pr_debug("port %d not active...rescheduling\n", port); + resched_delay = 5 * HZ; + err = -EAGAIN; + goto new_schedule; + } + + callback_context = kmalloc(sizeof *callback_context, GFP_KERNEL); + if (!callback_context) { + err = -ENOMEM; + resched_delay = HZ * 5; + goto new_schedule; + } + callback_context->port = port; + callback_context->dev = dev; + callback_context->block_num = index; + + memset(&guid_info_rec, 0, sizeof (struct ib_sa_guidinfo_rec)); + + guid_info_rec.lid = cpu_to_be16(attr.lid); + guid_info_rec.block_num = index; + + memcpy(guid_info_rec.guid_info_list, rec_det->all_recs, + GUID_REC_SIZE * NUM_ALIAS_GUID_IN_REC); + comp_mask = IB_SA_GUIDINFO_REC_LID | IB_SA_GUIDINFO_REC_BLOCK_NUM | + rec_det->guid_indexes; + + init_completion(&callback_context->done); + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1); + list_add_tail(&callback_context->list, head); + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags1); + + callback_context->query_id = + ib_sa_guid_info_rec_query(dev->sriov.alias_guid.sa_client, + ibdev, port, &guid_info_rec, + comp_mask, rec_det->method, 1000, + GFP_KERNEL, aliasguid_query_handler, + callback_context, + &callback_context->sa_query); + if (callback_context->query_id < 0) { + pr_debug("ib_sa_guid_info_rec_query failed, query_id: " + "%d. will reschedule to the next 1 sec.\n", + callback_context->query_id); + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1); + list_del(&callback_context->list); + kfree(callback_context); + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags1); + resched_delay = 1 * HZ; + err = -EAGAIN; + goto new_schedule; + } + err = 0; + goto out; + +new_schedule: + spin_lock_irqsave(&dev->sriov.going_down_lock, flags); + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1); + invalidate_guid_record(dev, port, index); + if (!dev->sriov.is_going_down) { + queue_delayed_work(dev->sriov.alias_guid.ports_guid[port - 1].wq, + &dev->sriov.alias_guid.ports_guid[port - 1].alias_guid_work, + resched_delay); + } + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags1); + spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags); + +out: + return err; +} + +void mlx4_ib_invalidate_all_guid_record(struct mlx4_ib_dev *dev, int port) +{ + int i; + unsigned long flags, flags1; + + pr_debug("port %d\n", port); + + spin_lock_irqsave(&dev->sriov.going_down_lock, flags); + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1); + for (i = 0; i < NUM_ALIAS_GUID_REC_IN_PORT; i++) + invalidate_guid_record(dev, port, i); + + if (mlx4_is_master(dev->dev) && !dev->sriov.is_going_down) { + /* + make sure no work waits in the queue, if the work is already + queued(not on the timer) the cancel will fail. That is not a problem + because we just want the work started. + */ + __cancel_delayed_work(&dev->sriov.alias_guid. + ports_guid[port - 1].alias_guid_work); + queue_delayed_work(dev->sriov.alias_guid.ports_guid[port - 1].wq, + &dev->sriov.alias_guid.ports_guid[port - 1].alias_guid_work, + 0); + } + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags1); + spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags); +} + +/* The function returns the next record that was + * not configured (or failed to be configured) */ +static int get_next_record_to_update(struct mlx4_ib_dev *dev, u8 port, + struct mlx4_next_alias_guid_work *rec) +{ + int j; + unsigned long flags; + + for (j = 0; j < NUM_ALIAS_GUID_REC_IN_PORT; j++) { + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags); + if (dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[j].status == + MLX4_GUID_INFO_STATUS_IDLE) { + memcpy(&rec->rec_det, + &dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[j], + sizeof (struct mlx4_sriov_alias_guid_info_rec_det)); + rec->port = port; + rec->block_num = j; + dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[j].status = + MLX4_GUID_INFO_STATUS_PENDING; + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags); + return 0; + } + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags); + } + return -ENOENT; +} + +static void set_administratively_guid_record(struct mlx4_ib_dev *dev, int port, + int rec_index, + struct mlx4_sriov_alias_guid_info_rec_det *rec_det) +{ + dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[rec_index].guid_indexes = + rec_det->guid_indexes; + memcpy(dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[rec_index].all_recs, + rec_det->all_recs, NUM_ALIAS_GUID_IN_REC * GUID_REC_SIZE); + dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[rec_index].status = + rec_det->status; +} + +static void set_all_slaves_guids(struct mlx4_ib_dev *dev, int port) +{ + int j; + struct mlx4_sriov_alias_guid_info_rec_det rec_det ; + + for (j = 0 ; j < NUM_ALIAS_GUID_REC_IN_PORT ; j++) { + memset(rec_det.all_recs, 0, NUM_ALIAS_GUID_IN_REC * GUID_REC_SIZE); + rec_det.guid_indexes = (!j ? 0 : IB_SA_GUIDINFO_REC_GID0) | + IB_SA_GUIDINFO_REC_GID1 | IB_SA_GUIDINFO_REC_GID2 | + IB_SA_GUIDINFO_REC_GID3 | IB_SA_GUIDINFO_REC_GID4 | + IB_SA_GUIDINFO_REC_GID5 | IB_SA_GUIDINFO_REC_GID6 | + IB_SA_GUIDINFO_REC_GID7; + rec_det.status = MLX4_GUID_INFO_STATUS_IDLE; + set_administratively_guid_record(dev, port, j, &rec_det); + } +} + +static void alias_guid_work(struct work_struct *work) +{ + struct delayed_work *delay = to_delayed_work(work); + int ret = 0; + struct mlx4_next_alias_guid_work *rec; + struct mlx4_sriov_alias_guid_port_rec_det *sriov_alias_port = + container_of(delay, struct mlx4_sriov_alias_guid_port_rec_det, + alias_guid_work); + struct mlx4_sriov_alias_guid *sriov_alias_guid = sriov_alias_port->parent; + struct mlx4_ib_sriov *ib_sriov = container_of(sriov_alias_guid, + struct mlx4_ib_sriov, + alias_guid); + struct mlx4_ib_dev *dev = container_of(ib_sriov, struct mlx4_ib_dev, sriov); + + rec = kzalloc(sizeof *rec, GFP_KERNEL); + if (!rec) { + pr_err("alias_guid_work: No Memory\n"); + return; + } + + pr_debug("starting [port: %d]...\n", sriov_alias_port->port + 1); + ret = get_next_record_to_update(dev, sriov_alias_port->port, rec); + if (ret) { + pr_debug("No more records to update.\n"); + goto out; + } + + set_guid_rec(&dev->ib_dev, rec->port + 1, rec->block_num, + &rec->rec_det); + +out: + kfree(rec); +} + + +void mlx4_ib_init_alias_guid_work(struct mlx4_ib_dev *dev, int port) +{ + unsigned long flags, flags1; + + if (!mlx4_is_master(dev->dev)) + return; + spin_lock_irqsave(&dev->sriov.going_down_lock, flags); + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1); + if (!dev->sriov.is_going_down) { + queue_delayed_work(dev->sriov.alias_guid.ports_guid[port].wq, + &dev->sriov.alias_guid.ports_guid[port].alias_guid_work, 0); + } + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags1); + spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags); +} + +void mlx4_ib_destroy_alias_guid_service(struct mlx4_ib_dev *dev) +{ + int i; + struct mlx4_ib_sriov *sriov = &dev->sriov; + struct mlx4_alias_guid_work_context *cb_ctx; + struct mlx4_sriov_alias_guid_port_rec_det *det; + struct ib_sa_query *sa_query; + unsigned long flags; + + for (i = 0 ; i < dev->num_ports; i++) { + cancel_delayed_work(&dev->sriov.alias_guid.ports_guid[i].alias_guid_work); + det = &sriov->alias_guid.ports_guid[i]; + spin_lock_irqsave(&sriov->alias_guid.ag_work_lock, flags); + while (!list_empty(&det->cb_list)) { + cb_ctx = list_entry(det->cb_list.next, + struct mlx4_alias_guid_work_context, + list); + sa_query = cb_ctx->sa_query; + cb_ctx->sa_query = NULL; + list_del(&cb_ctx->list); + spin_unlock_irqrestore(&sriov->alias_guid.ag_work_lock, flags); + ib_sa_cancel_query(cb_ctx->query_id, sa_query); + wait_for_completion(&cb_ctx->done); + kfree(cb_ctx); + spin_lock_irqsave(&sriov->alias_guid.ag_work_lock, flags); + } + spin_unlock_irqrestore(&sriov->alias_guid.ag_work_lock, flags); + } + for (i = 0 ; i < dev->num_ports; i++) { + flush_workqueue(dev->sriov.alias_guid.ports_guid[i].wq); + destroy_workqueue(dev->sriov.alias_guid.ports_guid[i].wq); + } + ib_sa_unregister_client(dev->sriov.alias_guid.sa_client); + kfree(dev->sriov.alias_guid.sa_client); +} + +int mlx4_ib_init_alias_guid_service(struct mlx4_ib_dev *dev) +{ + char alias_wq_name[15]; + int ret = 0; + int i, j, k; + union ib_gid gid; + + if (!mlx4_is_master(dev->dev)) + return 0; + dev->sriov.alias_guid.sa_client = + kzalloc(sizeof *dev->sriov.alias_guid.sa_client, GFP_KERNEL); + if (!dev->sriov.alias_guid.sa_client) + return -ENOMEM; + + ib_sa_register_client(dev->sriov.alias_guid.sa_client); + + spin_lock_init(&dev->sriov.alias_guid.ag_work_lock); + + for (i = 1; i <= dev->num_ports; ++i) { + if (dev->ib_dev.query_gid(&dev->ib_dev , i, 0, &gid)) { + ret = -EFAULT; + goto err_unregister; + } + } + + for (i = 0 ; i < dev->num_ports; i++) { + memset(&dev->sriov.alias_guid.ports_guid[i], 0, + sizeof (struct mlx4_sriov_alias_guid_port_rec_det)); + /*Check if the SM doesn't need to assign the GUIDs*/ + for (j = 0; j < NUM_ALIAS_GUID_REC_IN_PORT; j++) { + if (mlx4_ib_sm_guid_assign) { + dev->sriov.alias_guid.ports_guid[i]. + all_rec_per_port[j]. + ownership = MLX4_GUID_DRIVER_ASSIGN; + continue; + } + dev->sriov.alias_guid.ports_guid[i].all_rec_per_port[j]. + ownership = MLX4_GUID_NONE_ASSIGN; + /*mark each val as it was deleted, + till the sysAdmin will give it valid val*/ + for (k = 0; k < NUM_ALIAS_GUID_IN_REC; k++) { + *(__be64 *)&dev->sriov.alias_guid.ports_guid[i]. + all_rec_per_port[j].all_recs[GUID_REC_SIZE * k] = + cpu_to_be64(MLX4_GUID_FOR_DELETE_VAL); + } + } + INIT_LIST_HEAD(&dev->sriov.alias_guid.ports_guid[i].cb_list); + /*prepare the records, set them to be allocated by sm*/ + for (j = 0 ; j < NUM_ALIAS_GUID_REC_IN_PORT; j++) + invalidate_guid_record(dev, i + 1, j); + + dev->sriov.alias_guid.ports_guid[i].parent = &dev->sriov.alias_guid; + dev->sriov.alias_guid.ports_guid[i].port = i; + if (mlx4_ib_sm_guid_assign) + set_all_slaves_guids(dev, i); + + snprintf(alias_wq_name, sizeof alias_wq_name, "alias_guid%d", i); + dev->sriov.alias_guid.ports_guid[i].wq = + create_singlethread_workqueue(alias_wq_name); + if (!dev->sriov.alias_guid.ports_guid[i].wq) { + ret = -ENOMEM; + goto err_thread; + } + INIT_DELAYED_WORK(&dev->sriov.alias_guid.ports_guid[i].alias_guid_work, + alias_guid_work); + } + return 0; + +err_thread: + for (--i; i >= 0; i--) { + destroy_workqueue(dev->sriov.alias_guid.ports_guid[i].wq); + dev->sriov.alias_guid.ports_guid[i].wq = NULL; + } + +err_unregister: + ib_sa_unregister_client(dev->sriov.alias_guid.sa_client); + kfree(dev->sriov.alias_guid.sa_client); + dev->sriov.alias_guid.sa_client = NULL; + pr_err("init_alias_guid_service: Failed. (ret:%d)\n", ret); + return ret; +} diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 2f13894299ee..b8cb25ebce50 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -791,8 +791,10 @@ void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev) static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u8 port_num) { - /* re-configure the mcg's */ + /* re-configure the alias-guid and mcg's */ if (mlx4_is_master(dev->dev)) { + mlx4_ib_invalidate_all_guid_record(dev, port_num); + if (!dev->sriov.is_going_down) mlx4_ib_mcg_port_cleanup(&dev->sriov.demux[port_num - 1], 0); } @@ -1808,9 +1810,20 @@ int mlx4_ib_init_sriov(struct mlx4_ib_dev *dev) return 0; } + err = mlx4_ib_init_alias_guid_service(dev); + if (err) { + mlx4_ib_warn(&dev->ib_dev, "Failed init alias guid process.\n"); + goto paravirt_err; + } + mlx4_ib_warn(&dev->ib_dev, "initializing demux service for %d qp1 clients\n", dev->dev->caps.sqp_demux); for (i = 0; i < dev->num_ports; i++) { + union ib_gid gid; + err = __mlx4_ib_query_gid(&dev->ib_dev, i + 1, 0, &gid, 1); + if (err) + goto demux_err; + dev->sriov.demux[i].guid_cache[0] = gid.global.interface_id; err = alloc_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1, &dev->sriov.sqps[i]); if (err) @@ -1828,6 +1841,9 @@ demux_err: mlx4_ib_free_demux_ctx(&dev->sriov.demux[i]); --i; } + mlx4_ib_destroy_alias_guid_service(dev); + +paravirt_err: mlx4_ib_cm_paravirt_clean(dev, -1); return err; @@ -1854,5 +1870,6 @@ void mlx4_ib_close_sriov(struct mlx4_ib_dev *dev) } mlx4_ib_cm_paravirt_clean(dev, -1); + mlx4_ib_destroy_alias_guid_service(dev); } } diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index b959fe4665dd..7d97578fbbaa 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -59,6 +59,10 @@ MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_VERSION(DRV_VERSION); +int mlx4_ib_sm_guid_assign = 1; +module_param_named(sm_guid_assign, mlx4_ib_sm_guid_assign, int, 0444); +MODULE_PARM_DESC(sm_guid_assign, "Enable SM alias_GUID assignment if sm_guid_assign > 0 (Default: 1)"); + static const char mlx4_ib_version[] = DRV_NAME ": Mellanox ConnectX InfiniBand driver v" DRV_VERSION " (" DRV_RELDATE ")\n"; @@ -349,12 +353,15 @@ static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port, return __mlx4_ib_query_port(ibdev, port, props, 0); } -static int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, - union ib_gid *gid) +int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, + union ib_gid *gid, int netw_view) { struct ib_smp *in_mad = NULL; struct ib_smp *out_mad = NULL; int err = -ENOMEM; + struct mlx4_ib_dev *dev = to_mdev(ibdev); + int clear = 0; + int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS; in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); @@ -365,18 +372,29 @@ static int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; in_mad->attr_mod = cpu_to_be32(port); - err = mlx4_MAD_IFC(to_mdev(ibdev), MLX4_MAD_IFC_IGNORE_KEYS, port, - NULL, NULL, in_mad, out_mad); + if (mlx4_is_mfunc(dev->dev) && netw_view) + mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW; + + err = mlx4_MAD_IFC(dev, mad_ifc_flags, port, NULL, NULL, in_mad, out_mad); if (err) goto out; memcpy(gid->raw, out_mad->data + 8, 8); + if (mlx4_is_mfunc(dev->dev) && !netw_view) { + if (index) { + /* For any index > 0, return the null guid */ + err = 0; + clear = 1; + goto out; + } + } + init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_GUID_INFO; in_mad->attr_mod = cpu_to_be32(index / 8); - err = mlx4_MAD_IFC(to_mdev(ibdev), MLX4_MAD_IFC_IGNORE_KEYS, port, + err = mlx4_MAD_IFC(dev, mad_ifc_flags, port, NULL, NULL, in_mad, out_mad); if (err) goto out; @@ -384,6 +402,8 @@ static int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, memcpy(gid->raw + 8, out_mad->data + (index % 8) * 8, 8); out: + if (clear) + memset(gid->raw + 8, 0, 8); kfree(in_mad); kfree(out_mad); return err; @@ -403,7 +423,7 @@ static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, union ib_gid *gid) { if (rdma_port_get_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND) - return __mlx4_ib_query_gid(ibdev, port, index, gid); + return __mlx4_ib_query_gid(ibdev, port, index, gid, 0); else return iboe_query_gid(ibdev, port, index, gid); } @@ -1566,6 +1586,11 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, case MLX4_DEV_EVENT_PORT_UP: if (p > ibdev->num_ports) return; + if (mlx4_is_master(dev) && + rdma_port_get_link_layer(&ibdev->ib_dev, p) == + IB_LINK_LAYER_INFINIBAND) { + mlx4_ib_invalidate_all_guid_record(ibdev, p); + } ibev.event = IB_EVENT_PORT_ACTIVE; break; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 7476e2439f6b..f3f75f8229a7 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -64,6 +65,9 @@ enum { #define MLX4_IB_SQ_HEADROOM(shift) ((MLX4_IB_MAX_HEADROOM >> (shift)) + 1) #define MLX4_IB_SQ_MAX_SPARE (MLX4_IB_SQ_HEADROOM(MLX4_IB_SQ_MIN_WQE_SHIFT)) +/*module param to indicate if SM assigns the alias_GUID*/ +extern int mlx4_ib_sm_guid_assign; + struct mlx4_ib_ucontext { struct ib_ucontext ibucontext; struct mlx4_uar uar; @@ -277,6 +281,57 @@ struct mlx4_ib_ah { union mlx4_ext_av av; }; +/****************************************/ +/* alias guid support */ +/****************************************/ +#define NUM_PORT_ALIAS_GUID 2 +#define NUM_ALIAS_GUID_IN_REC 8 +#define NUM_ALIAS_GUID_REC_IN_PORT 16 +#define GUID_REC_SIZE 8 +#define NUM_ALIAS_GUID_PER_PORT 128 +#define MLX4_NOT_SET_GUID (0x00LL) +#define MLX4_GUID_FOR_DELETE_VAL (~(0x00LL)) + +enum mlx4_guid_alias_rec_status { + MLX4_GUID_INFO_STATUS_IDLE, + MLX4_GUID_INFO_STATUS_SET, + MLX4_GUID_INFO_STATUS_PENDING, +}; + +enum mlx4_guid_alias_rec_ownership { + MLX4_GUID_DRIVER_ASSIGN, + MLX4_GUID_SYSADMIN_ASSIGN, + MLX4_GUID_NONE_ASSIGN, /*init state of each record*/ +}; + +enum mlx4_guid_alias_rec_method { + MLX4_GUID_INFO_RECORD_SET = IB_MGMT_METHOD_SET, + MLX4_GUID_INFO_RECORD_DELETE = IB_SA_METHOD_DELETE, +}; + +struct mlx4_sriov_alias_guid_info_rec_det { + u8 all_recs[GUID_REC_SIZE * NUM_ALIAS_GUID_IN_REC]; + ib_sa_comp_mask guid_indexes; /*indicates what from the 8 records are valid*/ + enum mlx4_guid_alias_rec_status status; /*indicates the administraively status of the record.*/ + u8 method; /*set or delete*/ + enum mlx4_guid_alias_rec_ownership ownership; /*indicates who assign that alias_guid record*/ +}; + +struct mlx4_sriov_alias_guid_port_rec_det { + struct mlx4_sriov_alias_guid_info_rec_det all_rec_per_port[NUM_ALIAS_GUID_REC_IN_PORT]; + struct workqueue_struct *wq; + struct delayed_work alias_guid_work; + u8 port; + struct mlx4_sriov_alias_guid *parent; + struct list_head cb_list; +}; + +struct mlx4_sriov_alias_guid { + struct mlx4_sriov_alias_guid_port_rec_det ports_guid[MLX4_MAX_PORTS]; + spinlock_t ag_work_lock; + struct ib_sa_client *sa_client; +}; + struct mlx4_ib_demux_work { struct work_struct work; struct mlx4_ib_dev *dev; @@ -349,6 +404,8 @@ struct mlx4_ib_sriov { spinlock_t going_down_lock; int is_going_down; + struct mlx4_sriov_alias_guid alias_guid; + /* CM paravirtualization fields */ struct list_head cm_list; spinlock_t id_map_lock; @@ -555,6 +612,9 @@ int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port, int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey, int netw_view); +int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, + union ib_gid *gid, int netw_view); + int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr, u8 *mac, int *is_mcast, u8 port); @@ -606,4 +666,18 @@ int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id void mlx4_ib_cm_paravirt_init(struct mlx4_ib_dev *dev); void mlx4_ib_cm_paravirt_clean(struct mlx4_ib_dev *dev, int slave_id); +/* alias guid support */ +void mlx4_ib_init_alias_guid_work(struct mlx4_ib_dev *dev, int port); +int mlx4_ib_init_alias_guid_service(struct mlx4_ib_dev *dev); +void mlx4_ib_destroy_alias_guid_service(struct mlx4_ib_dev *dev); +void mlx4_ib_invalidate_all_guid_record(struct mlx4_ib_dev *dev, int port); + +void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, + int block_num, + u8 port_num, u8 *p_data); + +void mlx4_ib_update_cache_on_guid_change(struct mlx4_ib_dev *dev, + int block_num, u8 port_num, + u8 *p_data); + #endif /* MLX4_IB_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index a13d8a69b3bc..ea5c884ab899 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -674,8 +674,10 @@ static int get_full_pkey_table(struct mlx4_dev *dev, u8 port, u16 *table, static enum ib_port_state vf_port_state(struct mlx4_dev *dev, int port, int vf) { - /* will be modified when add alias_guid feature */ - return IB_PORT_DOWN; + if (mlx4_get_slave_port_state(dev, vf, port) == SLAVE_PORT_UP) + return IB_PORT_ACTIVE; + else + return IB_PORT_DOWN; } static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, -- cgit v1.2.3 From 2a4fae148cf4b60e73faf0a427302697917409d9 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:50 +0000 Subject: IB/mlx4: Propagate P_Key and guid change port management events to slaves P_Key change and guid change events are not of interest to all slaves, but only to those slaves which "see" the table slots whose contents have change. For example, if the guid at port 1, index 5 has changed in the PPF, we wish to propagate the gid-change event only to the function which has that guid index mapped to its port/guid table (in this case it is slave #5). Other functions should not get the event, since the event does not affect them. Similarly with P_Keys -- P_Key change events are forwarded only to slaves which have that P_Key index mapped to their virtual P_Key table. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/mad.c | 162 ++++++++++++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx4/fw.c | 6 ++ 2 files changed, 161 insertions(+), 7 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index b8cb25ebce50..591c2891159b 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -54,6 +54,15 @@ enum { #define MLX4_TUN_IS_RECV(a) (((a) >> MLX4_TUN_SEND_WRID_SHIFT) & 0x1) #define MLX4_TUN_WRID_QPN(a) (((a) >> MLX4_TUN_QPN_SHIFT) & 0x3) + /* Port mgmt change event handling */ + +#define GET_BLK_PTR_FROM_EQE(eqe) be32_to_cpu(eqe->event.port_mgmt_change.params.tbl_change_info.block_ptr) +#define GET_MASK_FROM_EQE(eqe) be32_to_cpu(eqe->event.port_mgmt_change.params.tbl_change_info.tbl_entries_mask) +#define NUM_IDX_IN_PKEY_TBL_BLK 32 +#define GUID_TBL_ENTRY_SIZE 8 /* size in bytes */ +#define GUID_TBL_BLK_NUM_ENTRIES 8 +#define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES) + struct mlx4_mad_rcv_buf { struct ib_grh grh; u8 payload[256]; @@ -76,6 +85,9 @@ struct mlx4_rcv_tunnel_mad { } __packed; static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u8 port_num); +static void handle_lid_change_event(struct mlx4_ib_dev *dev, u8 port_num); +static void __propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num, + int block, u32 change_bitmap); __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx) { @@ -220,8 +232,7 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad, handle_client_rereg_event(dev, port_num); if (prev_lid != lid) - mlx4_ib_dispatch_event(dev, port_num, - IB_EVENT_LID_CHANGE); + handle_lid_change_event(dev, port_num); break; case IB_SMP_ATTR_PKEY_TABLE: @@ -231,6 +242,9 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad, break; } + /* at this point, we are running in the master. + * Slaves do not receive SMPs. + */ bn = be32_to_cpu(((struct ib_smp *)mad)->attr_mod) & 0xFFFF; base = (__be16 *) &(((struct ib_smp *)mad)->data[0]); pkey_change_bitmap = 0; @@ -248,10 +262,13 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad, "block=0x%x, change_bitmap=0x%x\n", port_num, bn, pkey_change_bitmap); - if (pkey_change_bitmap) + if (pkey_change_bitmap) { mlx4_ib_dispatch_event(dev, port_num, IB_EVENT_PKEY_CHANGE); - + if (!dev->sriov.is_going_down) + __propagate_pkey_ev(dev, port_num, bn, + pkey_change_bitmap); + } break; case IB_SMP_ATTR_GUID_INFO: @@ -259,12 +276,56 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad, if (!mlx4_is_master(dev->dev)) mlx4_ib_dispatch_event(dev, port_num, IB_EVENT_GID_CHANGE); + /*if master, notify relevant slaves*/ + if (mlx4_is_master(dev->dev) && + !dev->sriov.is_going_down) { + bn = be32_to_cpu(((struct ib_smp *)mad)->attr_mod); + mlx4_ib_update_cache_on_guid_change(dev, bn, port_num, + (u8 *)(&((struct ib_smp *)mad)->data)); + mlx4_ib_notify_slaves_on_guid_change(dev, bn, port_num, + (u8 *)(&((struct ib_smp *)mad)->data)); + } break; + default: break; } } +static void __propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num, + int block, u32 change_bitmap) +{ + int i, ix, slave, err; + int have_event = 0; + + for (slave = 0; slave < dev->dev->caps.sqp_demux; slave++) { + if (slave == mlx4_master_func_num(dev->dev)) + continue; + if (!mlx4_is_slave_active(dev->dev, slave)) + continue; + + have_event = 0; + for (i = 0; i < 32; i++) { + if (!(change_bitmap & (1 << i))) + continue; + for (ix = 0; + ix < dev->dev->caps.pkey_table_len[port_num]; ix++) { + if (dev->pkeys.virt2phys_pkey[slave][port_num - 1] + [ix] == i + 32 * block) { + err = mlx4_gen_pkey_eqe(dev->dev, slave, port_num); + pr_debug("propagate_pkey_ev: slave %d," + " port %d, ix %d (%d)\n", + slave, port_num, ix, err); + have_event = 1; + break; + } + } + if (have_event) + break; + } + } +} + static void node_desc_override(struct ib_device *dev, struct ib_mad *mad) { @@ -789,18 +850,90 @@ void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev) } } +static void handle_lid_change_event(struct mlx4_ib_dev *dev, u8 port_num) +{ + mlx4_ib_dispatch_event(dev, port_num, IB_EVENT_LID_CHANGE); + + if (mlx4_is_master(dev->dev) && !dev->sriov.is_going_down) + mlx4_gen_slaves_port_mgt_ev(dev->dev, port_num, + MLX4_EQ_PORT_INFO_LID_CHANGE_MASK); +} + static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u8 port_num) { /* re-configure the alias-guid and mcg's */ if (mlx4_is_master(dev->dev)) { mlx4_ib_invalidate_all_guid_record(dev, port_num); - if (!dev->sriov.is_going_down) + if (!dev->sriov.is_going_down) { mlx4_ib_mcg_port_cleanup(&dev->sriov.demux[port_num - 1], 0); + mlx4_gen_slaves_port_mgt_ev(dev->dev, port_num, + MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK); + } } mlx4_ib_dispatch_event(dev, port_num, IB_EVENT_CLIENT_REREGISTER); } +static void propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num, + struct mlx4_eqe *eqe) +{ + __propagate_pkey_ev(dev, port_num, GET_BLK_PTR_FROM_EQE(eqe), + GET_MASK_FROM_EQE(eqe)); +} + +static void handle_slaves_guid_change(struct mlx4_ib_dev *dev, u8 port_num, + u32 guid_tbl_blk_num, u32 change_bitmap) +{ + struct ib_smp *in_mad = NULL; + struct ib_smp *out_mad = NULL; + u16 i; + + if (!mlx4_is_mfunc(dev->dev) || !mlx4_is_master(dev->dev)) + return; + + in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL); + out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); + if (!in_mad || !out_mad) { + mlx4_ib_warn(&dev->ib_dev, "failed to allocate memory for guid info mads\n"); + goto out; + } + + guid_tbl_blk_num *= 4; + + for (i = 0; i < 4; i++) { + if (change_bitmap && (!((change_bitmap >> (8 * i)) & 0xff))) + continue; + memset(in_mad, 0, sizeof *in_mad); + memset(out_mad, 0, sizeof *out_mad); + + in_mad->base_version = 1; + in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; + in_mad->class_version = 1; + in_mad->method = IB_MGMT_METHOD_GET; + in_mad->attr_id = IB_SMP_ATTR_GUID_INFO; + in_mad->attr_mod = cpu_to_be32(guid_tbl_blk_num + i); + + if (mlx4_MAD_IFC(dev, + MLX4_MAD_IFC_IGNORE_KEYS | MLX4_MAD_IFC_NET_VIEW, + port_num, NULL, NULL, in_mad, out_mad)) { + mlx4_ib_warn(&dev->ib_dev, "Failed in get GUID INFO MAD_IFC\n"); + goto out; + } + + mlx4_ib_update_cache_on_guid_change(dev, guid_tbl_blk_num + i, + port_num, + (u8 *)(&((struct ib_smp *)out_mad)->data)); + mlx4_ib_notify_slaves_on_guid_change(dev, guid_tbl_blk_num + i, + port_num, + (u8 *)(&((struct ib_smp *)out_mad)->data)); + } + +out: + kfree(in_mad); + kfree(out_mad); + return; +} + void handle_port_mgmt_change_event(struct work_struct *work) { struct ib_event_work *ew = container_of(work, struct ib_event_work, work); @@ -808,6 +941,8 @@ void handle_port_mgmt_change_event(struct work_struct *work) struct mlx4_eqe *eqe = &(ew->ib_eqe); u8 port = eqe->event.port_mgmt_change.port; u32 changed_attr; + u32 tbl_block; + u32 change_bitmap; switch (eqe->subtype) { case MLX4_DEV_PMC_SUBTYPE_PORT_INFO: @@ -823,11 +958,16 @@ void handle_port_mgmt_change_event(struct work_struct *work) /* Check if it is a lid change event */ if (changed_attr & MLX4_EQ_PORT_INFO_LID_CHANGE_MASK) - mlx4_ib_dispatch_event(dev, port, IB_EVENT_LID_CHANGE); + handle_lid_change_event(dev, port); /* Generate GUID changed event */ - if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK) + if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK) { mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE); + /*if master, notify all slaves*/ + if (mlx4_is_master(dev->dev)) + mlx4_gen_slaves_port_mgt_ev(dev->dev, port, + MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK); + } if (changed_attr & MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK) handle_client_rereg_event(dev, port); @@ -835,11 +975,19 @@ void handle_port_mgmt_change_event(struct work_struct *work) case MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE: mlx4_ib_dispatch_event(dev, port, IB_EVENT_PKEY_CHANGE); + if (mlx4_is_master(dev->dev) && !dev->sriov.is_going_down) + propagate_pkey_ev(dev, port, eqe); break; case MLX4_DEV_PMC_SUBTYPE_GUID_INFO: /* paravirtualized master's guid is guid 0 -- does not change */ if (!mlx4_is_master(dev->dev)) mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE); + /*if master, notify relevant slaves*/ + else if (!dev->sriov.is_going_down) { + tbl_block = GET_BLK_PTR_FROM_EQE(eqe); + change_bitmap = GET_MASK_FROM_EQE(eqe); + handle_slaves_guid_change(dev, port, tbl_block, change_bitmap); + } break; default: pr_warn("Unsupported subtype 0x%x for " diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 35be90178bef..b78803937897 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -729,6 +729,7 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd) { + u64 flags; int err = 0; u8 field; @@ -737,6 +738,11 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, if (err) return err; + /* add port mng change event capability unconditionally to slaves */ + MLX4_GET(flags, outbox->buf, QUERY_DEV_CAP_EXT_FLAGS_OFFSET); + flags |= MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV; + MLX4_PUT(outbox->buf, flags, QUERY_DEV_CAP_EXT_FLAGS_OFFSET); + /* For guests, report Blueflame disabled */ MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_BF_OFFSET); field &= 0x7f; -- cgit v1.2.3 From efcd235d736ab05ef2b29d7fe1493a2f52b07b66 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:52 +0000 Subject: net/mlx4_core: Adjustments to SET_PORT for IB SR-IOV 1. Slaves may not set the IS_SM capability for the port. 2. DEV_MGMT may not be set in multifunction mode. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/port.c | 10 ++++++++++ include/linux/mlx4/device.h | 5 +++++ 2 files changed, 15 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index e36dd0f2fa73..4c51b05efa28 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -732,6 +732,16 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod, new_cap_mask = ((__be32 *) inbox->buf)[1]; } + /* slave may not set the IS_SM capability for the port */ + if (slave != mlx4_master_func_num(dev) && + (be32_to_cpu(new_cap_mask) & MLX4_PORT_CAP_IS_SM)) + return -EINVAL; + + /* No DEV_MGMT in multifunc mode */ + if (mlx4_is_mfunc(dev) && + (be32_to_cpu(new_cap_mask) & MLX4_PORT_CAP_DEV_MGMT_SUP)) + return -EINVAL; + agg_cap_mask = 0; slave_cap_mask = priv->mfunc.master.slave_state[slave].ib_cap_mask[port]; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 380e01671d1e..b3f9b4500b9b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -53,6 +53,11 @@ enum { MLX4_FLAG_SRIOV = 1 << 4, }; +enum { + MLX4_PORT_CAP_IS_SM = 1 << 1, + MLX4_PORT_CAP_DEV_MGMT_SUP = 1 << 19, +}; + enum { MLX4_MAX_PORTS = 2, MLX4_MAX_PORT_PKEYS = 128 -- cgit v1.2.3 From 980e90010f15362b3b02ed4875ef2758aee3de72 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:53 +0000 Subject: mlx4_core: INIT/CLOSE port logic for IB ports in SR-IOV mode Normally, INIT_PORT and CLOSE_PORT are invoked when special QP0 transitions to RTR, or transitions to ERR/RESET respectively. In SR-IOV mode, however, the master is also paravirtualized. This in turn requires that we not do INIT_PORT until the entire QP0 path (real QP0 and proxy QP0) is ready to receive. When the real QP0 goes down, we should indicate that the port is not active. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/fw.c | 71 +++++++++++++++++++++++++++------ drivers/net/ethernet/mellanox/mlx4/qp.c | 38 ++++++++++++++++-- 2 files changed, 92 insertions(+), 17 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index b78803937897..bf159c0fe82b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -1365,6 +1365,19 @@ out: return err; } +/* for IB-type ports only in SRIOV mode. Checks that both proxy QP0 + * and real QP0 are active, so that the paravirtualized QP0 is ready + * to operate */ +static int check_qp0_state(struct mlx4_dev *dev, int function, int port) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + /* irrelevant if not infiniband */ + if (priv->mfunc.master.qp0_state[port].proxy_qp0_active && + priv->mfunc.master.qp0_state[port].qp0_active) + return 1; + return 0; +} + int mlx4_INIT_PORT_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, @@ -1381,14 +1394,29 @@ int mlx4_INIT_PORT_wrapper(struct mlx4_dev *dev, int slave, if (dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB) return -ENODEV; - /* Enable port only if it was previously disabled */ - if (!priv->mfunc.master.init_port_ref[port]) { - err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_INIT_PORT, - MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); - if (err) - return err; + if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) { + /* Enable port only if it was previously disabled */ + if (!priv->mfunc.master.init_port_ref[port]) { + err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_INIT_PORT, + MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); + if (err) + return err; + } + priv->mfunc.master.slave_state[slave].init_port_mask |= (1 << port); + } else { + if (slave == mlx4_master_func_num(dev)) { + if (check_qp0_state(dev, slave, port) && + !priv->mfunc.master.qp0_state[port].port_active) { + err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_INIT_PORT, + MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); + if (err) + return err; + priv->mfunc.master.qp0_state[port].port_active = 1; + priv->mfunc.master.slave_state[slave].init_port_mask |= (1 << port); + } + } else + priv->mfunc.master.slave_state[slave].init_port_mask |= (1 << port); } - priv->mfunc.master.slave_state[slave].init_port_mask |= (1 << port); ++priv->mfunc.master.init_port_ref[port]; return 0; } @@ -1463,13 +1491,30 @@ int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave, if (dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB) return -ENODEV; - if (priv->mfunc.master.init_port_ref[port] == 1) { - err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, 1000, - MLX4_CMD_NATIVE); - if (err) - return err; + + if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) { + if (priv->mfunc.master.init_port_ref[port] == 1) { + err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, + 1000, MLX4_CMD_NATIVE); + if (err) + return err; + } + priv->mfunc.master.slave_state[slave].init_port_mask &= ~(1 << port); + } else { + /* infiniband port */ + if (slave == mlx4_master_func_num(dev)) { + if (!priv->mfunc.master.qp0_state[port].qp0_active && + priv->mfunc.master.qp0_state[port].port_active) { + err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, + 1000, MLX4_CMD_NATIVE); + if (err) + return err; + priv->mfunc.master.slave_state[slave].init_port_mask &= ~(1 << port); + priv->mfunc.master.qp0_state[port].port_active = 0; + } + } else + priv->mfunc.master.slave_state[slave].init_port_mask &= ~(1 << port); } - priv->mfunc.master.slave_state[slave].init_port_mask &= ~(1 << port); --priv->mfunc.master.init_port_ref[port]; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index b8da72b29cf7..436ef6c69add 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -67,10 +67,18 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type) complete(&qp->free); } -static int is_qp0(struct mlx4_dev *dev, struct mlx4_qp *qp) +/* used for INIT/CLOSE port logic */ +static int is_qp0(struct mlx4_dev *dev, struct mlx4_qp *qp, int *real_qp0, int *proxy_qp0) { - return qp->qpn >= dev->caps.sqp_start && + /* qp0 is either the proxy qp0, or the real qp0 */ + *proxy_qp0 = qp->qpn >= dev->caps.sqp_start && qp->qpn <= dev->caps.sqp_start + 1; + + *real_qp0 = mlx4_is_master(dev) && + qp->qpn >= dev->caps.base_sqpn && + qp->qpn <= dev->caps.base_sqpn + 1; + + return *real_qp0 || *proxy_qp0; } static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt, @@ -122,6 +130,8 @@ static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt, struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_cmd_mailbox *mailbox; int ret = 0; + int real_qp0 = 0; + int proxy_qp0 = 0; u8 port; if (cur_state >= MLX4_QP_NUM_STATE || new_state >= MLX4_QP_NUM_STATE || @@ -133,9 +143,12 @@ static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt, MLX4_CMD_2RST_QP, MLX4_CMD_TIME_CLASS_A, native); if (mlx4_is_master(dev) && cur_state != MLX4_QP_STATE_ERR && cur_state != MLX4_QP_STATE_RST && - is_qp0(dev, qp)) { + is_qp0(dev, qp, &real_qp0, &proxy_qp0)) { port = (qp->qpn & 1) + 1; - priv->mfunc.master.qp0_state[port].qp0_active = 0; + if (proxy_qp0) + priv->mfunc.master.qp0_state[port].proxy_qp0_active = 0; + else + priv->mfunc.master.qp0_state[port].qp0_active = 0; } return ret; } @@ -162,6 +175,23 @@ static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt, new_state == MLX4_QP_STATE_RST ? 2 : 0, op[cur_state][new_state], MLX4_CMD_TIME_CLASS_C, native); + if (mlx4_is_master(dev) && is_qp0(dev, qp, &real_qp0, &proxy_qp0)) { + port = (qp->qpn & 1) + 1; + if (cur_state != MLX4_QP_STATE_ERR && + cur_state != MLX4_QP_STATE_RST && + new_state == MLX4_QP_STATE_ERR) { + if (proxy_qp0) + priv->mfunc.master.qp0_state[port].proxy_qp0_active = 0; + else + priv->mfunc.master.qp0_state[port].qp0_active = 0; + } else if (new_state == MLX4_QP_STATE_RTR) { + if (proxy_qp0) + priv->mfunc.master.qp0_state[port].proxy_qp0_active = 1; + else + priv->mfunc.master.qp0_state[port].qp0_active = 1; + } + } + mlx4_free_cmd_mailbox(dev, mailbox); return ret; } -- cgit v1.2.3 From 992e8e6e8781b71fd475bd1fd0555da7dba59966 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:54 +0000 Subject: IB/mlx4: Miscellaneous adjustments for SR-IOV IB support 1. Allow only master to change node description. 2. Prevent AH leakage in send mads. 3. Take device part number from PCI structure, so that guests see the VF part number (and not the PF part number). 4. Place the device revision ID into caps structure at startup. 5. SET_PORT in update_gids_task needs to go through wrapper on master. 6. In mlx4_ib_event(), PORT_MGMT_EVENT needs be handled in a work queue on the master, since it propagates events to slaves using GEN_EQE. 7. Do not support FMR on slaves. 8. Add spinlock to slave_event(), since it is called both in interrupt context and in process context (due to 6 above, and also if smp_snoop is used). This fix was found and implemented by Saeed Mahameed Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/mad.c | 6 +++++- drivers/infiniband/hw/mlx4/main.c | 26 ++++++++++++++++++-------- drivers/net/ethernet/mellanox/mlx4/cmd.c | 1 + drivers/net/ethernet/mellanox/mlx4/eq.c | 8 ++++++-- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 1 + 5 files changed, 31 insertions(+), 11 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index b689dbd6d8f6..b91b4865d635 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -709,7 +709,9 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, if (!out_mad->mad_hdr.status) { if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV)) smp_snoop(ibdev, port_num, in_mad, prev_lid); - node_desc_override(ibdev, out_mad); + /* slaves get node desc from FW */ + if (!mlx4_is_slave(to_mdev(ibdev)->dev)) + node_desc_override(ibdev, out_mad); } /* set return bit in status of directed route responses */ @@ -792,6 +794,8 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, static void send_handler(struct ib_mad_agent *agent, struct ib_mad_send_wc *mad_send_wc) { + if (mad_send_wc->send_buf->context[0]) + ib_destroy_ah(mad_send_wc->send_buf->context[0]); ib_free_send_mad(mad_send_wc->send_buf); } diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 7d97578fbbaa..46303b209ce6 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -138,7 +138,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->vendor_id = be32_to_cpup((__be32 *) (out_mad->data + 36)) & 0xffffff; - props->vendor_part_id = be16_to_cpup((__be16 *) (out_mad->data + 30)); + props->vendor_part_id = dev->dev->pdev->device; props->hw_ver = be32_to_cpup((__be32 *) (out_mad->data + 32)); memcpy(&props->sys_image_guid, out_mad->data + 4, 8); @@ -478,6 +478,9 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask, if (!(mask & IB_DEVICE_MODIFY_NODE_DESC)) return 0; + if (mlx4_is_slave(to_mdev(ibdev)->dev)) + return -EOPNOTSUPP; + spin_lock_irqsave(&to_mdev(ibdev)->sm_lock, flags); memcpy(ibdev->node_desc, props->node_desc, 64); spin_unlock_irqrestore(&to_mdev(ibdev)->sm_lock, flags); @@ -493,7 +496,7 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask, memset(mailbox->buf, 0, 256); memcpy(mailbox->buf, props->node_desc, 64); mlx4_cmd(to_mdev(ibdev)->dev, mailbox->dma, 1, 0, - MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); + MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); mlx4_free_cmd_mailbox(to_mdev(ibdev)->dev, mailbox); @@ -921,6 +924,7 @@ static int init_node_data(struct mlx4_ib_dev *dev) if (err) goto out; + dev->dev->rev_id = be32_to_cpup((__be32 *) (out_mad->data + 32)); memcpy(&dev->ib_dev.node_guid, out_mad->data + 12, 8); out: @@ -1009,7 +1013,7 @@ static void update_gids_task(struct work_struct *work) err = mlx4_cmd(dev, mailbox->dma, MLX4_SET_PORT_GID_TABLE << 8 | gw->port, 1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B, - MLX4_CMD_NATIVE); + MLX4_CMD_WRAPPED); if (err) pr_warn("set port command failed\n"); else { @@ -1400,10 +1404,12 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->ib_dev.detach_mcast = mlx4_ib_mcg_detach; ibdev->ib_dev.process_mad = mlx4_ib_process_mad; - ibdev->ib_dev.alloc_fmr = mlx4_ib_fmr_alloc; - ibdev->ib_dev.map_phys_fmr = mlx4_ib_map_phys_fmr; - ibdev->ib_dev.unmap_fmr = mlx4_ib_unmap_fmr; - ibdev->ib_dev.dealloc_fmr = mlx4_ib_fmr_dealloc; + if (!mlx4_is_slave(ibdev->dev)) { + ibdev->ib_dev.alloc_fmr = mlx4_ib_fmr_alloc; + ibdev->ib_dev.map_phys_fmr = mlx4_ib_map_phys_fmr; + ibdev->ib_dev.unmap_fmr = mlx4_ib_unmap_fmr; + ibdev->ib_dev.dealloc_fmr = mlx4_ib_fmr_dealloc; + } if (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) { ibdev->ib_dev.alloc_xrcd = mlx4_ib_alloc_xrcd; @@ -1615,7 +1621,11 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, INIT_WORK(&ew->work, handle_port_mgmt_change_event); memcpy(&ew->ib_eqe, eqe, sizeof *eqe); ew->ib_dev = ibdev; - handle_port_mgmt_change_event(&ew->work); + /* need to queue only for port owner, which uses GEN_EQE */ + if (mlx4_is_master(dev)) + queue_work(wq, &ew->work); + else + handle_port_mgmt_change_event(&ew->work); return; case MLX4_DEV_EVENT_SLAVE_INIT: diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index ea5c884ab899..78fdbd653fa9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1757,6 +1757,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) INIT_WORK(&priv->mfunc.master.slave_flr_event_work, mlx4_master_handle_slave_flr); spin_lock_init(&priv->mfunc.master.slave_state_lock); + spin_lock_init(&priv->mfunc.master.slave_eq.event_lock); priv->mfunc.master.comm_wq = create_singlethread_workqueue("mlx4_comm"); if (!priv->mfunc.master.comm_wq) diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index c425826b1fc0..51c764901ad2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -164,13 +164,16 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_slave_event_eq *slave_eq = &priv->mfunc.master.slave_eq; - struct mlx4_eqe *s_eqe = - &slave_eq->event_eqe[slave_eq->prod & (SLAVE_EVENT_EQ_SIZE - 1)]; + struct mlx4_eqe *s_eqe; + unsigned long flags; + spin_lock_irqsave(&slave_eq->event_lock, flags); + s_eqe = &slave_eq->event_eqe[slave_eq->prod & (SLAVE_EVENT_EQ_SIZE - 1)]; if ((!!(s_eqe->owner & 0x80)) ^ (!!(slave_eq->prod & SLAVE_EVENT_EQ_SIZE))) { mlx4_warn(dev, "Master failed to generate an EQE for slave: %d. " "No free EQE on slave events queue\n", slave); + spin_unlock_irqrestore(&slave_eq->event_lock, flags); return; } @@ -183,6 +186,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe) queue_work(priv->mfunc.master.comm_wq, &priv->mfunc.master.slave_event_work); + spin_unlock_irqrestore(&slave_eq->event_lock, flags); } static void mlx4_slave_event(struct mlx4_dev *dev, int slave, diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 23f74759f403..399793a23457 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -473,6 +473,7 @@ struct mlx4_slave_event_eq { u32 eqn; u32 cons; u32 prod; + spinlock_t event_lock; struct mlx4_eqe event_eqe[SLAVE_EVENT_EQ_SIZE]; }; -- cgit v1.2.3 From 026149cbaada391d98f1cbec47c488cb548f753a Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:55 +0000 Subject: mlx4: Activate SR-IOV mode for IB Remove the error returns for IB ports from mlx4_ib_add, mlx4_INIT_PORT_wrapper, and mlx4_CLOSE_PORT_wrapper. Currently, SRIOV is supported only for devices for which the link layer is IB on all ports; RoCE support will be added later. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/main.c | 8 ++++++-- drivers/net/ethernet/mellanox/mlx4/fw.c | 6 ------ include/linux/mlx4/device.h | 4 ++++ 3 files changed, 10 insertions(+), 8 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 46303b209ce6..e849347ef99a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1293,11 +1293,15 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) pr_info_once("%s", mlx4_ib_version); - if (mlx4_is_mfunc(dev)) { - pr_warn("IB not yet supported in SRIOV\n"); + mlx4_foreach_non_ib_transport_port(i, dev) + num_ports++; + + if (mlx4_is_mfunc(dev) && num_ports) { + dev_err(&dev->pdev->dev, "RoCE is not supported over SRIOV as yet\n"); return NULL; } + num_ports = 0; mlx4_foreach_ib_transport_port(i, dev) num_ports++; diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index bf159c0fe82b..1d74e8541146 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -1391,9 +1391,6 @@ int mlx4_INIT_PORT_wrapper(struct mlx4_dev *dev, int slave, if (priv->mfunc.master.slave_state[slave].init_port_mask & (1 << port)) return 0; - if (dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB) - return -ENODEV; - if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) { /* Enable port only if it was previously disabled */ if (!priv->mfunc.master.init_port_ref[port]) { @@ -1489,9 +1486,6 @@ int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave, (1 << port))) return 0; - if (dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB) - return -ENODEV; - if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) { if (priv->mfunc.master.init_port_ref[port] == 1) { err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b3f9b4500b9b..9b243df789ef 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -697,6 +697,10 @@ struct mlx4_init_port_param { for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \ if ((type) == (dev)->caps.port_mask[(port)]) +#define mlx4_foreach_non_ib_transport_port(port, dev) \ + for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \ + if (((dev)->caps.port_mask[port] != MLX4_PORT_TYPE_IB)) + #define mlx4_foreach_ib_transport_port(port, dev) \ for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \ if (((dev)->caps.port_mask[port] == MLX4_PORT_TYPE_IB) || \ -- cgit v1.2.3 From afa8fd1db9f295a0c4130bc6d87bf8b05bdd0523 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:56 +0000 Subject: mlx4: Paravirtualize Node Guids for slaves This is necessary in order to support > 1 VF/PF in a VM for software that uses the node guid as a discriminator, such as librdmacm. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/mad.c | 14 ++++++++++++++ drivers/infiniband/hw/mlx4/mlx4_ib.h | 3 +++ drivers/net/ethernet/mellanox/mlx4/cmd.c | 11 +++++++++++ drivers/net/ethernet/mellanox/mlx4/main.c | 22 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx4/mlx4.h | 1 + include/linux/mlx4/device.h | 2 ++ 6 files changed, 53 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index b91b4865d635..603a114b3dfe 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -35,6 +35,7 @@ #include #include +#include #include #include #include @@ -89,6 +90,12 @@ static void handle_lid_change_event(struct mlx4_ib_dev *dev, u8 port_num); static void __propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num, int block, u32 change_bitmap); +__be64 mlx4_ib_gen_node_guid(void) +{ +#define NODE_GUID_HI ((u64) (((u64)IB_OPENIB_OUI) << 40)) + return cpu_to_be64(NODE_GUID_HI | random32()); +} + __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx) { return cpu_to_be64(atomic_inc_return(&ctx->tid)) | @@ -1962,6 +1969,13 @@ int mlx4_ib_init_sriov(struct mlx4_ib_dev *dev) return 0; } + for (i = 0; i < dev->dev->caps.sqp_demux; i++) { + if (i == mlx4_master_func_num(dev->dev)) + mlx4_put_slave_node_guid(dev->dev, i, dev->ib_dev.node_guid); + else + mlx4_put_slave_node_guid(dev->dev, i, mlx4_ib_gen_node_guid()); + } + err = mlx4_ib_init_alias_guid_service(dev); if (err) { mlx4_ib_warn(&dev->ib_dev, "Failed init alias guid process.\n"); diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index e57a220a4d55..e04cbc9a54a5 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -723,4 +723,7 @@ int mlx4_ib_device_register_sysfs(struct mlx4_ib_dev *device) ; void mlx4_ib_device_unregister_sysfs(struct mlx4_ib_dev *device); +__be64 mlx4_ib_gen_node_guid(void); + + #endif /* MLX4_IB_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 78fdbd653fa9..90774b7e47a4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -696,6 +696,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, struct ib_smp *outsmp = outbox->buf; __be16 *outtab = (__be16 *)(outsmp->data); __be32 slave_cap_mask; + __be64 slave_node_guid; port = vhcr->in_modifier; if (smp->base_version == 1 && @@ -755,6 +756,16 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, } return err; } + if (smp->attr_id == IB_SMP_ATTR_NODE_INFO) { + err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, + vhcr->in_modifier, vhcr->op_modifier, + vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE); + if (!err) { + slave_node_guid = mlx4_get_slave_node_guid(dev, slave); + memcpy(outsmp->data + 12, &slave_node_guid, 8); + } + return err; + } } } if (slave != mlx4_master_func_num(dev) && diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 2294b7173180..76f69fdd01d5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -435,6 +435,28 @@ void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, int i, int } EXPORT_SYMBOL(mlx4_sync_pkey_table); +void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid) +{ + struct mlx4_priv *priv = container_of(dev, struct mlx4_priv, dev); + + if (!mlx4_is_master(dev)) + return; + + priv->slave_node_guids[slave] = guid; +} +EXPORT_SYMBOL(mlx4_put_slave_node_guid); + +__be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave) +{ + struct mlx4_priv *priv = container_of(dev, struct mlx4_priv, dev); + + if (!mlx4_is_master(dev)) + return 0; + + return priv->slave_node_guids[slave]; +} +EXPORT_SYMBOL(mlx4_get_slave_node_guid); + int mlx4_is_slave_active(struct mlx4_dev *dev, int slave) { struct mlx4_priv *priv = mlx4_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 399793a23457..4b1fbd84a68f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -810,6 +810,7 @@ struct mlx4_priv { int reserved_mtts; int fs_hash_mode; u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS]; + __be64 slave_node_guids[MLX4_MFUNC_MAX]; }; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 9b243df789ef..c0f8f74a0a5e 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -981,5 +981,7 @@ int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port, u8 enum slave_port_state mlx4_get_slave_port_state(struct mlx4_dev *dev, int slave, u8 port); int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int event, enum slave_port_gen_event *gen_event); +void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid); +__be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave); #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 47605df953985c2b792ac9f3ddf70d270b89adb8 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:40:57 +0000 Subject: mlx4: Modify proxy/tunnel QP mechanism so that guests do no calculations Previously, the structure of a guest's proxy QPs followed the structure of the PPF special qps (qp0 port 1, qp0 port 2, qp1 port 1, qp1 port 2, ...). The guest then did offset calculations on the sqp_base qp number that the PPF passed to it in QUERY_FUNC_CAP(). This is now changed so that the guest does no offset calculations regarding proxy or tunnel QPs to use. This change frees the PPF from needing to adhere to a specific order in allocating proxy and tunnel QPs. Now QUERY_FUNC_CAP provides each port individually with its proxy qp0, proxy qp1, tunnel qp0, and tunnel qp1 QP numbers, and these are used directly where required (with no offset calculations). To accomplish this change, several fields were added to the phys_caps structure for use by the PPF and by non-SR-IOV mode: base_sqpn -- in non-sriov mode, this was formerly sqp_start. base_proxy_sqpn -- the first physical proxy qp number -- used by PPF base_tunnel_sqpn -- the first physical tunnel qp number -- used by PPF. The current code in the PPF still adheres to the previous layout of sqps, proxy-sqps and tunnel-sqps. However, the PPF can change this layout without affecting VF or (paravirtualized) PF code. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/mad.c | 12 +-- drivers/infiniband/hw/mlx4/qp.c | 104 ++++++++++++------ drivers/net/ethernet/mellanox/mlx4/fw.c | 173 +++++++++++++++++------------- drivers/net/ethernet/mellanox/mlx4/fw.h | 14 +-- drivers/net/ethernet/mellanox/mlx4/main.c | 61 ++++++++--- drivers/net/ethernet/mellanox/mlx4/qp.c | 71 ++++++++---- include/linux/mlx4/device.h | 16 +-- 7 files changed, 290 insertions(+), 161 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 603a114b3dfe..658a622791fb 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -505,7 +505,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, } else tun_pkey_ix = dev->pkeys.virt2phys_pkey[slave][port - 1][0]; - dqpn = dev->dev->caps.sqp_start + 8 * slave + port + (dest_qpt * 2) - 1; + dqpn = dev->dev->phys_caps.base_proxy_sqpn + 8 * slave + port + (dest_qpt * 2) - 1; /* get tunnel tx data buf for slave */ src_qp = tun_qp->qp; @@ -1074,9 +1074,9 @@ static int mlx4_ib_multiplex_sa_handler(struct ib_device *ibdev, int port, static int is_proxy_qp0(struct mlx4_ib_dev *dev, int qpn, int slave) { - int slave_start = dev->dev->caps.sqp_start + 8 * slave; + int proxy_start = dev->dev->phys_caps.base_proxy_sqpn + 8 * slave; - return (qpn >= slave_start && qpn <= slave_start + 1); + return (qpn >= proxy_start && qpn <= proxy_start + 1); } @@ -1191,14 +1191,14 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc int slave; /* Get slave that sent this packet */ - if (wc->src_qp < dev->dev->caps.sqp_start || - wc->src_qp >= dev->dev->caps.base_tunnel_sqpn || + if (wc->src_qp < dev->dev->phys_caps.base_proxy_sqpn || + wc->src_qp >= dev->dev->phys_caps.base_proxy_sqpn + 8 * MLX4_MFUNC_MAX || (wc->src_qp & 0x1) != ctx->port - 1 || wc->src_qp & 0x4) { mlx4_ib_warn(ctx->ib_dev, "can't multiplex bad sqp:%d\n", wc->src_qp); return; } - slave = ((wc->src_qp & ~0x7) - dev->dev->caps.sqp_start) / 8; + slave = ((wc->src_qp & ~0x7) - dev->dev->phys_caps.base_proxy_sqpn) / 8; if (slave != ctx->slave) { mlx4_ib_warn(ctx->ib_dev, "can't multiplex bad sqp:%d: " "belongs to another slave\n", wc->src_qp); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index a8622510de42..96fe103f5973 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -116,33 +116,57 @@ static int is_tunnel_qp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) if (!mlx4_is_master(dev->dev)) return 0; - return qp->mqp.qpn >= dev->dev->caps.base_sqpn && - qp->mqp.qpn < dev->dev->caps.base_sqpn + - 8 + 16 * MLX4_MFUNC_MAX; + return qp->mqp.qpn >= dev->dev->phys_caps.base_tunnel_sqpn && + qp->mqp.qpn < dev->dev->phys_caps.base_tunnel_sqpn + + 8 * MLX4_MFUNC_MAX; } static int is_sqp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) { - return ((mlx4_is_master(dev->dev) && - qp->mqp.qpn >= dev->dev->caps.base_sqpn && - qp->mqp.qpn <= dev->dev->caps.base_sqpn + 3) || - (qp->mqp.qpn >= dev->dev->caps.sqp_start && - qp->mqp.qpn <= dev->dev->caps.sqp_start + 3)); + int proxy_sqp = 0; + int real_sqp = 0; + int i; + /* PPF or Native -- real SQP */ + real_sqp = ((mlx4_is_master(dev->dev) || !mlx4_is_mfunc(dev->dev)) && + qp->mqp.qpn >= dev->dev->phys_caps.base_sqpn && + qp->mqp.qpn <= dev->dev->phys_caps.base_sqpn + 3); + if (real_sqp) + return 1; + /* VF or PF -- proxy SQP */ + if (mlx4_is_mfunc(dev->dev)) { + for (i = 0; i < dev->dev->caps.num_ports; i++) { + if (qp->mqp.qpn == dev->dev->caps.qp0_proxy[i] || + qp->mqp.qpn == dev->dev->caps.qp1_proxy[i]) { + proxy_sqp = 1; + break; + } + } + } + return proxy_sqp; } /* used for INIT/CLOSE port logic */ static int is_qp0(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) { - int qp0; - - /* qp0 is either the proxy qp0, or the real qp0 */ - qp0 = (qp->mqp.qpn >= dev->dev->caps.sqp_start && - qp->mqp.qpn <= dev->dev->caps.sqp_start + 1) || - (mlx4_is_master(dev->dev) && - qp->mqp.qpn >= dev->dev->caps.base_sqpn && - qp->mqp.qpn <= dev->dev->caps.base_sqpn + 1); - - return qp0; + int proxy_qp0 = 0; + int real_qp0 = 0; + int i; + /* PPF or Native -- real QP0 */ + real_qp0 = ((mlx4_is_master(dev->dev) || !mlx4_is_mfunc(dev->dev)) && + qp->mqp.qpn >= dev->dev->phys_caps.base_sqpn && + qp->mqp.qpn <= dev->dev->phys_caps.base_sqpn + 1); + if (real_qp0) + return 1; + /* VF or PF -- proxy QP0 */ + if (mlx4_is_mfunc(dev->dev)) { + for (i = 0; i < dev->dev->caps.num_ports; i++) { + if (qp->mqp.qpn == dev->dev->caps.qp0_proxy[i]) { + proxy_qp0 = 1; + break; + } + } + } + return proxy_qp0; } static void *get_wqe(struct mlx4_ib_qp *qp, int offset) @@ -607,8 +631,10 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, qp_type = MLX4_IB_QPT_TUN_SMI_OWNER; else qp_type = MLX4_IB_QPT_TUN_SMI; - qpn = dev->dev->caps.base_tunnel_sqpn + 8 * tnl_init->slave + - tnl_init->proxy_qp_type * 2 + tnl_init->port - 1; + /* we are definitely in the PPF here, since we are creating + * tunnel QPs. base_tunnel_sqpn is therefore valid. */ + qpn = dev->dev->phys_caps.base_tunnel_sqpn + 8 * tnl_init->slave + + tnl_init->proxy_qp_type * 2 + tnl_init->port - 1; sqpn = qpn; } @@ -630,12 +656,6 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, qp->mlx4_ib_qp_type = qp_type; - if (mlx4_is_mfunc(dev->dev) && - (qp_type == MLX4_IB_QPT_SMI || qp_type == MLX4_IB_QPT_GSI)) { - qpn -= 8; - sqpn -= 8; - } - mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); @@ -935,6 +955,23 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, del_gid_entries(qp); } +static u32 get_sqp_num(struct mlx4_ib_dev *dev, struct ib_qp_init_attr *attr) +{ + /* Native or PPF */ + if (!mlx4_is_mfunc(dev->dev) || + (mlx4_is_master(dev->dev) && + attr->create_flags & MLX4_IB_SRIOV_SQP)) { + return dev->dev->phys_caps.base_sqpn + + (attr->qp_type == IB_QPT_SMI ? 0 : 2) + + attr->port_num - 1; + } + /* PF or VF -- creating proxies */ + if (attr->qp_type == IB_QPT_SMI) + return dev->dev->caps.qp0_proxy[attr->port_num - 1]; + else + return dev->dev->caps.qp1_proxy[attr->port_num - 1]; +} + struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *init_attr, struct ib_udata *udata) @@ -998,9 +1035,7 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd, return ERR_PTR(-EINVAL); err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata, - to_mdev(pd->device)->dev->caps.sqp_start + - (init_attr->qp_type == IB_QPT_SMI ? 0 : 2) + - init_attr->port_num - 1, + get_sqp_num(to_mdev(pd->device), init_attr), &qp); if (err) return ERR_PTR(err); @@ -1643,8 +1678,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp, sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->wr.ud.remote_qpn); else sqp->ud_header.bth.destination_qpn = - cpu_to_be32(mdev->dev->caps.base_tunnel_sqpn + - sqp->qp.port - 1); + cpu_to_be32(mdev->dev->caps.qp0_tunnel[sqp->qp.port - 1]); sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1)); if (mlx4_get_parav_qkey(mdev->dev, sqp->qp.mqp.qpn, &qkey)) @@ -2012,10 +2046,10 @@ static void set_tunnel_datagram_seg(struct mlx4_ib_dev *dev, cpu_to_be32(0xf0000000); memcpy(dseg->av, &sqp_av, sizeof (struct mlx4_av)); - dseg->dqpn = cpu_to_be32(dev->dev->caps.base_tunnel_sqpn + - qpt * 2 + port - 1); - /* use well-known qkey from the QPC */ - dseg->qkey = cpu_to_be32(0x80000000); + /* This function used only for sending on QP1 proxies */ + dseg->dqpn = cpu_to_be32(dev->dev->caps.qp1_tunnel[port - 1]); + /* Use QKEY from the QP context, which is set by master */ + dseg->qkey = cpu_to_be32(IB_QP_SET_QKEY); } static void build_tunnel_header(struct ib_send_wr *wr, void *wqe, unsigned *mlx_seg_len) diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 1d74e8541146..e2ed36e2fb29 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -184,8 +184,6 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, #define QUERY_FUNC_CAP_MCG_QUOTA_OFFSET 0x28 #define QUERY_FUNC_CAP_MAX_EQ_OFFSET 0x2c #define QUERY_FUNC_CAP_RESERVED_EQ_OFFSET 0X30 -#define QUERY_FUNC_CAP_BASE_TUNNEL_QPN_OFFSET 0x44 -#define QUERY_FUNC_CAP_BASE_PROXY_QPN_OFFSET 0x48 #define QUERY_FUNC_CAP_FMR_FLAG 0x80 #define QUERY_FUNC_CAP_FLAG_RDMA 0x40 @@ -196,21 +194,39 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, #define QUERY_FUNC_CAP_RDMA_PROPS_OFFSET 0x8 #define QUERY_FUNC_CAP_ETH_PROPS_OFFSET 0xc +#define QUERY_FUNC_CAP_QP0_TUNNEL 0x10 +#define QUERY_FUNC_CAP_QP0_PROXY 0x14 +#define QUERY_FUNC_CAP_QP1_TUNNEL 0x18 +#define QUERY_FUNC_CAP_QP1_PROXY 0x1c + #define QUERY_FUNC_CAP_ETH_PROPS_FORCE_MAC 0x40 #define QUERY_FUNC_CAP_ETH_PROPS_FORCE_VLAN 0x80 #define QUERY_FUNC_CAP_RDMA_PROPS_FORCE_PHY_WQE_GID 0x80 if (vhcr->op_modifier == 1) { - field = vhcr->in_modifier; - MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_PHYS_PORT_OFFSET); - field = 0; /* ensure force vlan and force mac bits are not set */ MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_ETH_PROPS_OFFSET); /* ensure that phy_wqe_gid bit is not set */ MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_RDMA_PROPS_OFFSET); + field = vhcr->in_modifier; /* phys-port = logical-port */ + MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_PHYS_PORT_OFFSET); + + /* size is now the QP number */ + size = dev->phys_caps.base_tunnel_sqpn + 8 * slave + field - 1; + MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP0_TUNNEL); + + size += 2; + MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP1_TUNNEL); + + size = dev->phys_caps.base_proxy_sqpn + 8 * slave + field - 1; + MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP0_PROXY); + + size += 2; + MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP1_PROXY); + } else if (vhcr->op_modifier == 0) { /* enable rdma and ethernet interfaces */ field = (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA); @@ -249,117 +265,124 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, size = dev->caps.num_mgms + dev->caps.num_amgms; MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET); - size = dev->caps.base_tunnel_sqpn + 8 * slave; - MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_BASE_TUNNEL_QPN_OFFSET); - - size = dev->caps.sqp_start + 8 * slave; - MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_BASE_PROXY_QPN_OFFSET); - } else err = -EINVAL; return err; } -int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, struct mlx4_func_cap *func_cap) +int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port, + struct mlx4_func_cap *func_cap) { struct mlx4_cmd_mailbox *mailbox; u32 *outbox; - u8 field; + u8 field, op_modifier; u32 size; - int i; int err = 0; + op_modifier = !!gen_or_port; /* 0 = general, 1 = logical port */ mailbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(mailbox)) return PTR_ERR(mailbox); - err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_FUNC_CAP, + err = mlx4_cmd_box(dev, 0, mailbox->dma, gen_or_port, op_modifier, + MLX4_CMD_QUERY_FUNC_CAP, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (err) goto out; outbox = mailbox->buf; - MLX4_GET(field, outbox, QUERY_FUNC_CAP_FLAGS_OFFSET); - if (!(field & (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA))) { - mlx4_err(dev, "The host supports neither eth nor rdma interfaces\n"); - err = -EPROTONOSUPPORT; - goto out; - } - func_cap->flags = field; - - MLX4_GET(field, outbox, QUERY_FUNC_CAP_NUM_PORTS_OFFSET); - func_cap->num_ports = field; + if (!op_modifier) { + MLX4_GET(field, outbox, QUERY_FUNC_CAP_FLAGS_OFFSET); + if (!(field & (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA))) { + mlx4_err(dev, "The host supports neither eth nor rdma interfaces\n"); + err = -EPROTONOSUPPORT; + goto out; + } + func_cap->flags = field; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_PF_BHVR_OFFSET); - func_cap->pf_context_behaviour = size; + MLX4_GET(field, outbox, QUERY_FUNC_CAP_NUM_PORTS_OFFSET); + func_cap->num_ports = field; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP_QUOTA_OFFSET); - func_cap->qp_quota = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_PF_BHVR_OFFSET); + func_cap->pf_context_behaviour = size; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_SRQ_QUOTA_OFFSET); - func_cap->srq_quota = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP_QUOTA_OFFSET); + func_cap->qp_quota = size & 0xFFFFFF; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_CQ_QUOTA_OFFSET); - func_cap->cq_quota = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_SRQ_QUOTA_OFFSET); + func_cap->srq_quota = size & 0xFFFFFF; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_MAX_EQ_OFFSET); - func_cap->max_eq = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_CQ_QUOTA_OFFSET); + func_cap->cq_quota = size & 0xFFFFFF; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET); - func_cap->reserved_eq = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_MAX_EQ_OFFSET); + func_cap->max_eq = size & 0xFFFFFF; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_MPT_QUOTA_OFFSET); - func_cap->mpt_quota = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET); + func_cap->reserved_eq = size & 0xFFFFFF; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_MTT_QUOTA_OFFSET); - func_cap->mtt_quota = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_MPT_QUOTA_OFFSET); + func_cap->mpt_quota = size & 0xFFFFFF; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET); - func_cap->mcg_quota = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_MTT_QUOTA_OFFSET); + func_cap->mtt_quota = size & 0xFFFFFF; - MLX4_GET(size, outbox, QUERY_FUNC_CAP_BASE_TUNNEL_QPN_OFFSET); - func_cap->base_tunnel_qpn = size & 0xFFFFFF; + MLX4_GET(size, outbox, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET); + func_cap->mcg_quota = size & 0xFFFFFF; + goto out; + } - MLX4_GET(size, outbox, QUERY_FUNC_CAP_BASE_PROXY_QPN_OFFSET); - func_cap->base_proxy_qpn = size & 0xFFFFFF; + /* logical port query */ + if (gen_or_port > dev->caps.num_ports) { + err = -EINVAL; + goto out; + } - for (i = 1; i <= func_cap->num_ports; ++i) { - err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 1, - MLX4_CMD_QUERY_FUNC_CAP, - MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); - if (err) + if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_ETH) { + MLX4_GET(field, outbox, QUERY_FUNC_CAP_ETH_PROPS_OFFSET); + if (field & QUERY_FUNC_CAP_ETH_PROPS_FORCE_VLAN) { + mlx4_err(dev, "VLAN is enforced on this port\n"); + err = -EPROTONOSUPPORT; goto out; + } - if (dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH) { - MLX4_GET(field, outbox, QUERY_FUNC_CAP_ETH_PROPS_OFFSET); - if (field & QUERY_FUNC_CAP_ETH_PROPS_FORCE_VLAN) { - mlx4_err(dev, "VLAN is enforced on this port\n"); - err = -EPROTONOSUPPORT; - goto out; - } - - if (field & QUERY_FUNC_CAP_ETH_PROPS_FORCE_MAC) { - mlx4_err(dev, "Force mac is enabled on this port\n"); - err = -EPROTONOSUPPORT; - goto out; - } - } else if (dev->caps.port_type[i] == MLX4_PORT_TYPE_IB) { - MLX4_GET(field, outbox, QUERY_FUNC_CAP_RDMA_PROPS_OFFSET); - if (field & QUERY_FUNC_CAP_RDMA_PROPS_FORCE_PHY_WQE_GID) { - mlx4_err(dev, "phy_wqe_gid is " - "enforced on this ib port\n"); - err = -EPROTONOSUPPORT; - goto out; - } + if (field & QUERY_FUNC_CAP_ETH_PROPS_FORCE_MAC) { + mlx4_err(dev, "Force mac is enabled on this port\n"); + err = -EPROTONOSUPPORT; + goto out; + } + } else if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_IB) { + MLX4_GET(field, outbox, QUERY_FUNC_CAP_RDMA_PROPS_OFFSET); + if (field & QUERY_FUNC_CAP_RDMA_PROPS_FORCE_PHY_WQE_GID) { + mlx4_err(dev, "phy_wqe_gid is " + "enforced on this ib port\n"); + err = -EPROTONOSUPPORT; + goto out; } + } - MLX4_GET(field, outbox, QUERY_FUNC_CAP_PHYS_PORT_OFFSET); - func_cap->physical_port[i] = field; + MLX4_GET(field, outbox, QUERY_FUNC_CAP_PHYS_PORT_OFFSET); + func_cap->physical_port = field; + if (func_cap->physical_port != gen_or_port) { + err = -ENOSYS; + goto out; } + MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP0_TUNNEL); + func_cap->qp0_tunnel_qpn = size & 0xFFFFFF; + + MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP0_PROXY); + func_cap->qp0_proxy_qpn = size & 0xFFFFFF; + + MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP1_TUNNEL); + func_cap->qp1_tunnel_qpn = size & 0xFFFFFF; + + MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP1_PROXY); + func_cap->qp1_proxy_qpn = size & 0xFFFFFF; + /* All other resources are allocated by the master, but we still report * 'num' and 'reserved' capabilities as follows: * - num remains the maximum resource index diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index ced1de57c818..85abe9c11a22 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -134,11 +134,12 @@ struct mlx4_func_cap { int max_eq; int reserved_eq; int mcg_quota; - u32 base_qpn; - u32 base_tunnel_qpn; - u32 base_proxy_qpn; - u8 physical_port[MLX4_MAX_PORTS + 1]; - u8 port_flags[MLX4_MAX_PORTS + 1]; + u32 qp0_tunnel_qpn; + u32 qp0_proxy_qpn; + u32 qp1_tunnel_qpn; + u32 qp1_proxy_qpn; + u8 physical_port; + u8 port_flags; }; struct mlx4_adapter { @@ -195,7 +196,8 @@ struct mlx4_set_ib_param { }; int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap); -int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, struct mlx4_func_cap *func_cap); +int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port, + struct mlx4_func_cap *func_cap); int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 76f69fdd01d5..1e2ab9d00f1c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -410,15 +410,16 @@ static int mlx4_how_many_lives_vf(struct mlx4_dev *dev) int mlx4_get_parav_qkey(struct mlx4_dev *dev, u32 qpn, u32 *qkey) { u32 qk = MLX4_RESERVED_QKEY_BASE; - if (qpn >= dev->caps.base_tunnel_sqpn + 8 * MLX4_MFUNC_MAX || - qpn < dev->caps.sqp_start) + + if (qpn >= dev->phys_caps.base_tunnel_sqpn + 8 * MLX4_MFUNC_MAX || + qpn < dev->phys_caps.base_proxy_sqpn) return -EINVAL; - if (qpn >= dev->caps.base_tunnel_sqpn) + if (qpn >= dev->phys_caps.base_tunnel_sqpn) /* tunnel qp */ - qk += qpn - dev->caps.base_tunnel_sqpn; + qk += qpn - dev->phys_caps.base_tunnel_sqpn; else - qk += qpn - dev->caps.sqp_start; + qk += qpn - dev->phys_caps.base_proxy_sqpn; *qkey = qk; return 0; } @@ -527,9 +528,10 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) } memset(&func_cap, 0, sizeof(func_cap)); - err = mlx4_QUERY_FUNC_CAP(dev, &func_cap); + err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap); if (err) { - mlx4_err(dev, "QUERY_FUNC_CAP command failed, aborting.\n"); + mlx4_err(dev, "QUERY_FUNC_CAP general command failed, aborting (%d).\n", + err); return err; } @@ -557,12 +559,33 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) return -ENODEV; } + dev->caps.qp0_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); + dev->caps.qp0_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); + dev->caps.qp1_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); + dev->caps.qp1_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); + + if (!dev->caps.qp0_tunnel || !dev->caps.qp0_proxy || + !dev->caps.qp1_tunnel || !dev->caps.qp1_proxy) { + err = -ENOMEM; + goto err_mem; + } + for (i = 1; i <= dev->caps.num_ports; ++i) { + err = mlx4_QUERY_FUNC_CAP(dev, (u32) i, &func_cap); + if (err) { + mlx4_err(dev, "QUERY_FUNC_CAP port command failed for" + " port %d, aborting (%d).\n", i, err); + goto err_mem; + } + dev->caps.qp0_tunnel[i - 1] = func_cap.qp0_tunnel_qpn; + dev->caps.qp0_proxy[i - 1] = func_cap.qp0_proxy_qpn; + dev->caps.qp1_tunnel[i - 1] = func_cap.qp1_tunnel_qpn; + dev->caps.qp1_proxy[i - 1] = func_cap.qp1_proxy_qpn; dev->caps.port_mask[i] = dev->caps.port_type[i]; if (mlx4_get_slave_pkey_gid_tbl_len(dev, i, &dev->caps.gid_table_len[i], &dev->caps.pkey_table_len[i])) - return -ENODEV; + goto err_mem; } if (dev->caps.uar_page_size * (dev->caps.num_uars - @@ -572,14 +595,20 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) "PCI resource 2 size of 0x%llx, aborting.\n", dev->caps.uar_page_size * dev->caps.num_uars, (unsigned long long) pci_resource_len(dev->pdev, 2)); - return -ENODEV; + goto err_mem; } - /* Calculate our sqp_start */ - dev->caps.sqp_start = func_cap.base_proxy_qpn; - dev->caps.base_tunnel_sqpn = func_cap.base_tunnel_qpn; - return 0; + +err_mem: + kfree(dev->caps.qp0_tunnel); + kfree(dev->caps.qp0_proxy); + kfree(dev->caps.qp1_tunnel); + kfree(dev->caps.qp1_proxy); + dev->caps.qp0_tunnel = dev->caps.qp0_proxy = + dev->caps.qp1_tunnel = dev->caps.qp1_proxy = NULL; + + return err; } /* @@ -2261,6 +2290,12 @@ static void mlx4_remove_one(struct pci_dev *pdev) if (!mlx4_is_slave(dev)) mlx4_free_ownership(dev); + + kfree(dev->caps.qp0_tunnel); + kfree(dev->caps.qp0_proxy); + kfree(dev->caps.qp1_tunnel); + kfree(dev->caps.qp1_proxy); + kfree(priv); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 436ef6c69add..81e2abe07bbb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -68,15 +68,15 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type) } /* used for INIT/CLOSE port logic */ -static int is_qp0(struct mlx4_dev *dev, struct mlx4_qp *qp, int *real_qp0, int *proxy_qp0) +static int is_master_qp0(struct mlx4_dev *dev, struct mlx4_qp *qp, int *real_qp0, int *proxy_qp0) { + /* this procedure is called after we already know we are on the master */ /* qp0 is either the proxy qp0, or the real qp0 */ - *proxy_qp0 = qp->qpn >= dev->caps.sqp_start && - qp->qpn <= dev->caps.sqp_start + 1; + u32 pf_proxy_offset = dev->phys_caps.base_proxy_sqpn + 8 * mlx4_master_func_num(dev); + *proxy_qp0 = qp->qpn >= pf_proxy_offset && qp->qpn <= pf_proxy_offset + 1; - *real_qp0 = mlx4_is_master(dev) && - qp->qpn >= dev->caps.base_sqpn && - qp->qpn <= dev->caps.base_sqpn + 1; + *real_qp0 = qp->qpn >= dev->phys_caps.base_sqpn && + qp->qpn <= dev->phys_caps.base_sqpn + 1; return *real_qp0 || *proxy_qp0; } @@ -143,7 +143,7 @@ static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt, MLX4_CMD_2RST_QP, MLX4_CMD_TIME_CLASS_A, native); if (mlx4_is_master(dev) && cur_state != MLX4_QP_STATE_ERR && cur_state != MLX4_QP_STATE_RST && - is_qp0(dev, qp, &real_qp0, &proxy_qp0)) { + is_master_qp0(dev, qp, &real_qp0, &proxy_qp0)) { port = (qp->qpn & 1) + 1; if (proxy_qp0) priv->mfunc.master.qp0_state[port].proxy_qp0_active = 0; @@ -175,7 +175,7 @@ static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt, new_state == MLX4_QP_STATE_RST ? 2 : 0, op[cur_state][new_state], MLX4_CMD_TIME_CLASS_C, native); - if (mlx4_is_master(dev) && is_qp0(dev, qp, &real_qp0, &proxy_qp0)) { + if (mlx4_is_master(dev) && is_master_qp0(dev, qp, &real_qp0, &proxy_qp0)) { port = (qp->qpn & 1) + 1; if (cur_state != MLX4_QP_STATE_ERR && cur_state != MLX4_QP_STATE_RST && @@ -422,6 +422,7 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table; int err; int reserved_from_top = 0; + int k; spin_lock_init(&qp_table->lock); INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC); @@ -436,7 +437,7 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) * We also reserve the MSB of the 24-bit QP number to indicate * that a QP is an XRC QP. */ - dev->caps.base_sqpn = + dev->phys_caps.base_sqpn = ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8); { @@ -479,24 +480,54 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) */ err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps, - (1 << 23) - 1, dev->caps.base_sqpn + 8 + + (1 << 23) - 1, dev->phys_caps.base_sqpn + 8 + 16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev), reserved_from_top); + if (err) + return err; - /* In mfunc, sqp_start is the base of the proxy SQPs, since the PF also - * uses paravirtualized SQPs. - * In native mode, sqp_start is the base of the real SQPs. */ if (mlx4_is_mfunc(dev)) { - dev->caps.sqp_start = dev->caps.base_sqpn + - 8 * (mlx4_master_func_num(dev) + 1); - dev->caps.base_tunnel_sqpn = dev->caps.sqp_start + 8 * MLX4_MFUNC_MAX; - } else - dev->caps.sqp_start = dev->caps.base_sqpn; + /* for PPF use */ + dev->phys_caps.base_proxy_sqpn = dev->phys_caps.base_sqpn + 8; + dev->phys_caps.base_tunnel_sqpn = dev->phys_caps.base_sqpn + 8 + 8 * MLX4_MFUNC_MAX; + + /* In mfunc, calculate proxy and tunnel qp offsets for the PF here, + * since the PF does not call mlx4_slave_caps */ + dev->caps.qp0_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); + dev->caps.qp0_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); + dev->caps.qp1_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); + dev->caps.qp1_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); + + if (!dev->caps.qp0_tunnel || !dev->caps.qp0_proxy || + !dev->caps.qp1_tunnel || !dev->caps.qp1_proxy) { + err = -ENOMEM; + goto err_mem; + } + for (k = 0; k < dev->caps.num_ports; k++) { + dev->caps.qp0_proxy[k] = dev->phys_caps.base_proxy_sqpn + + 8 * mlx4_master_func_num(dev) + k; + dev->caps.qp0_tunnel[k] = dev->caps.qp0_proxy[k] + 8 * MLX4_MFUNC_MAX; + dev->caps.qp1_proxy[k] = dev->phys_caps.base_proxy_sqpn + + 8 * mlx4_master_func_num(dev) + MLX4_MAX_PORTS + k; + dev->caps.qp1_tunnel[k] = dev->caps.qp1_proxy[k] + 8 * MLX4_MFUNC_MAX; + } + } + + + err = mlx4_CONF_SPECIAL_QP(dev, dev->phys_caps.base_sqpn); if (err) - return err; + goto err_mem; + return 0; - return mlx4_CONF_SPECIAL_QP(dev, dev->caps.base_sqpn); +err_mem: + kfree(dev->caps.qp0_tunnel); + kfree(dev->caps.qp0_proxy); + kfree(dev->caps.qp1_tunnel); + kfree(dev->caps.qp1_proxy); + dev->caps.qp0_tunnel = dev->caps.qp0_proxy = + dev->caps.qp1_tunnel = dev->caps.qp1_proxy = NULL; + return err; } void mlx4_cleanup_qp_table(struct mlx4_dev *dev) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index c0f8f74a0a5e..6d1acb04cd17 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -328,6 +328,9 @@ struct mlx4_phys_caps { u32 gid_phys_table_len[MLX4_MAX_PORTS + 1]; u32 pkey_phys_table_len[MLX4_MAX_PORTS + 1]; u32 num_phys_eqs; + u32 base_sqpn; + u32 base_proxy_sqpn; + u32 base_tunnel_sqpn; }; struct mlx4_caps { @@ -358,9 +361,10 @@ struct mlx4_caps { int max_rq_desc_sz; int max_qp_init_rdma; int max_qp_dest_rdma; - int sqp_start; - u32 base_sqpn; - u32 base_tunnel_sqpn; + u32 *qp0_proxy; + u32 *qp1_proxy; + u32 *qp0_tunnel; + u32 *qp1_tunnel; int num_srqs; int max_srq_wqes; int max_srq_sge; @@ -722,15 +726,15 @@ static inline int mlx4_is_master(struct mlx4_dev *dev) static inline int mlx4_is_qp_reserved(struct mlx4_dev *dev, u32 qpn) { - return (qpn < dev->caps.base_sqpn + 8 + + return (qpn < dev->phys_caps.base_sqpn + 8 + 16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev)); } static inline int mlx4_is_guest_proxy(struct mlx4_dev *dev, int slave, u32 qpn) { - int base = dev->caps.sqp_start + slave * 8; + int guest_proxy_base = dev->phys_caps.base_proxy_sqpn + slave * 8; - if (qpn >= base && qpn < base + 8) + if (qpn >= guest_proxy_base && qpn < guest_proxy_base + 8) return 1; return 0; -- cgit v1.2.3 From 69612b9ff44ddc305b727a1f78de2248f9d70bf0 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Sun, 23 Sep 2012 09:18:24 -0700 Subject: mlx4_core: Trivial readability fix: "0X30" -> "0x30" Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/fw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index e2ed36e2fb29..419914bf4834 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -183,7 +183,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, #define QUERY_FUNC_CAP_MTT_QUOTA_OFFSET 0x24 #define QUERY_FUNC_CAP_MCG_QUOTA_OFFSET 0x28 #define QUERY_FUNC_CAP_MAX_EQ_OFFSET 0x2c -#define QUERY_FUNC_CAP_RESERVED_EQ_OFFSET 0X30 +#define QUERY_FUNC_CAP_RESERVED_EQ_OFFSET 0x30 #define QUERY_FUNC_CAP_FMR_FLAG 0x80 #define QUERY_FUNC_CAP_FLAG_RDMA 0x40 -- cgit v1.2.3 From 84b1f1538fadd066cc9877c2276f3fefd8a79bc4 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Tue, 25 Sep 2012 17:09:42 -0700 Subject: mlx4_core: Trivial cleanups to driver log messages Also put format string onto one line. Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/main.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 1e2ab9d00f1c..296288c7cb37 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2036,12 +2036,11 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) } if (num_vfs) { - mlx4_warn(dev, "Enabling sriov with:%d vfs\n", num_vfs); + mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", num_vfs); err = pci_enable_sriov(pdev, num_vfs); if (err) { - mlx4_err(dev, "Failed to enable sriov," - "continuing without sriov enabled" - " (err = %d).\n", err); + mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n", + err); err = 0; } else { mlx4_warn(dev, "Running in master mode\n"); @@ -2284,7 +2283,7 @@ static void mlx4_remove_one(struct pci_dev *pdev) if (dev->flags & MLX4_FLAG_MSI_X) pci_disable_msix(pdev); if (dev->flags & MLX4_FLAG_SRIOV) { - mlx4_warn(dev, "Disabling sriov\n"); + mlx4_warn(dev, "Disabling SR-IOV\n"); pci_disable_sriov(pdev); } -- cgit v1.2.3 From f3d4c89ee4a8c993cc334a67f84a3fb724a1dd35 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Tue, 25 Sep 2012 21:24:07 -0700 Subject: mlx4_core: Fix crash on uninitialized priv->cmd.slave_sem On an SR-IOV master device, __mlx4_init_one() calls mlx4_init_hca() before mlx4_multi_func_init(). However, for unlucky configurations, mlx4_init_hca() might call mlx4_SENSE_PORT() (via mlx4_dev_cap()), and that calls mlx4_cmd_imm() with MLX4_CMD_WRAPPED set. However, on a multifunction device with MLX4_CMD_WRAPPED, __mlx4_cmd() calls into mlx4_slave_cmd(), and that immediately tries to do down(&priv->cmd.slave_sem); but priv->cmd.slave_sem isn't initialized until mlx4_multi_func_init() (which we haven't called yet). The next thing it tries to do is access priv->mfunc.vhcr, but that hasn't been allocated yet. Fix this by moving the initialization of slave_sem and vhcr up into mlx4_cmd_init(). Also, since slave_sem is really just being used as a mutex, convert it into a slave_cmd_mutex. Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 51 +++++++++++++++++++------------ drivers/net/ethernet/mellanox/mlx4/main.c | 11 ++++--- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 2 +- 3 files changed, 38 insertions(+), 26 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 90774b7e47a4..3d1899ff1076 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -395,7 +395,8 @@ static int mlx4_slave_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param, struct mlx4_vhcr_cmd *vhcr = priv->mfunc.vhcr; int ret; - down(&priv->cmd.slave_sem); + mutex_lock(&priv->cmd.slave_cmd_mutex); + vhcr->in_param = cpu_to_be64(in_param); vhcr->out_param = out_param ? cpu_to_be64(*out_param) : 0; vhcr->in_modifier = cpu_to_be32(in_modifier); @@ -403,6 +404,7 @@ static int mlx4_slave_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param, vhcr->token = cpu_to_be16(CMD_POLL_TOKEN); vhcr->status = 0; vhcr->flags = !!(priv->cmd.use_events) << 6; + if (mlx4_is_master(dev)) { ret = mlx4_master_process_vhcr(dev, dev->caps.function, vhcr); if (!ret) { @@ -439,7 +441,8 @@ static int mlx4_slave_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param, mlx4_err(dev, "failed execution of VHCR_POST command" "opcode 0x%x\n", op); } - up(&priv->cmd.slave_sem); + + mutex_unlock(&priv->cmd.slave_cmd_mutex); return ret; } @@ -1559,14 +1562,15 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, if ((slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_EN) && (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_POST)) goto reset_slave; - down(&priv->cmd.slave_sem); + + mutex_lock(&priv->cmd.slave_cmd_mutex); if (mlx4_master_process_vhcr(dev, slave, NULL)) { mlx4_err(dev, "Failed processing vhcr for slave:%d," " resetting slave.\n", slave); - up(&priv->cmd.slave_sem); + mutex_unlock(&priv->cmd.slave_cmd_mutex); goto reset_slave; } - up(&priv->cmd.slave_sem); + mutex_unlock(&priv->cmd.slave_cmd_mutex); break; default: mlx4_warn(dev, "Bad comm cmd:%d from slave:%d\n", cmd, slave); @@ -1707,14 +1711,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) struct mlx4_slave_state *s_state; int i, j, err, port; - priv->mfunc.vhcr = dma_alloc_coherent(&(dev->pdev->dev), PAGE_SIZE, - &priv->mfunc.vhcr_dma, - GFP_KERNEL); - if (!priv->mfunc.vhcr) { - mlx4_err(dev, "Couldn't allocate vhcr.\n"); - return -ENOMEM; - } - if (mlx4_is_master(dev)) priv->mfunc.comm = ioremap(pci_resource_start(dev->pdev, priv->fw.comm_bar) + @@ -1777,7 +1773,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) if (mlx4_init_resource_tracker(dev)) goto err_thread; - sema_init(&priv->cmd.slave_sem, 1); err = mlx4_ARM_COMM_CHANNEL(dev); if (err) { mlx4_err(dev, " Failed to arm comm channel eq: %x\n", @@ -1791,8 +1786,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) mlx4_err(dev, "Couldn't sync toggles\n"); goto err_comm; } - - sema_init(&priv->cmd.slave_sem, 1); } return 0; @@ -1822,6 +1815,7 @@ int mlx4_cmd_init(struct mlx4_dev *dev) struct mlx4_priv *priv = mlx4_priv(dev); mutex_init(&priv->cmd.hcr_mutex); + mutex_init(&priv->cmd.slave_cmd_mutex); sema_init(&priv->cmd.poll_sem, 1); priv->cmd.use_events = 0; priv->cmd.toggle = 1; @@ -1838,14 +1832,30 @@ int mlx4_cmd_init(struct mlx4_dev *dev) } } + if (mlx4_is_mfunc(dev)) { + priv->mfunc.vhcr = dma_alloc_coherent(&(dev->pdev->dev), PAGE_SIZE, + &priv->mfunc.vhcr_dma, + GFP_KERNEL); + if (!priv->mfunc.vhcr) { + mlx4_err(dev, "Couldn't allocate VHCR.\n"); + goto err_hcr; + } + } + priv->cmd.pool = pci_pool_create("mlx4_cmd", dev->pdev, MLX4_MAILBOX_SIZE, MLX4_MAILBOX_SIZE, 0); if (!priv->cmd.pool) - goto err_hcr; + goto err_vhcr; return 0; +err_vhcr: + if (mlx4_is_mfunc(dev)) + dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE, + priv->mfunc.vhcr, priv->mfunc.vhcr_dma); + priv->mfunc.vhcr = NULL; + err_hcr: if (!mlx4_is_slave(dev)) iounmap(priv->cmd.hcr); @@ -1868,9 +1878,6 @@ void mlx4_multi_func_cleanup(struct mlx4_dev *dev) } iounmap(priv->mfunc.comm); - dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE, - priv->mfunc.vhcr, priv->mfunc.vhcr_dma); - priv->mfunc.vhcr = NULL; } void mlx4_cmd_cleanup(struct mlx4_dev *dev) @@ -1881,6 +1888,10 @@ void mlx4_cmd_cleanup(struct mlx4_dev *dev) if (!mlx4_is_slave(dev)) iounmap(priv->cmd.hcr); + if (mlx4_is_mfunc(dev)) + dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE, + priv->mfunc.vhcr, priv->mfunc.vhcr_dma); + priv->mfunc.vhcr = NULL; } /* diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 296288c7cb37..1e9f816a94db 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1159,10 +1159,10 @@ static void mlx4_slave_exit(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); - down(&priv->cmd.slave_sem); + mutex_lock(&priv->cmd.slave_cmd_mutex); if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, MLX4_COMM_TIME)) mlx4_warn(dev, "Failed to close slave function.\n"); - up(&priv->cmd.slave_sem); + mutex_unlock(&priv->cmd.slave_cmd_mutex); } static int map_bf_area(struct mlx4_dev *dev) @@ -1214,7 +1214,7 @@ static int mlx4_init_slave(struct mlx4_dev *dev) u32 slave_read; u32 cmd_channel_ver; - down(&priv->cmd.slave_sem); + mutex_lock(&priv->cmd.slave_cmd_mutex); priv->cmd.max_cmds = 1; mlx4_warn(dev, "Sending reset\n"); ret_from_reset = mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, @@ -1263,12 +1263,13 @@ static int mlx4_init_slave(struct mlx4_dev *dev) goto err; if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR_EN, dma, MLX4_COMM_TIME)) goto err; - up(&priv->cmd.slave_sem); + + mutex_unlock(&priv->cmd.slave_cmd_mutex); return 0; err: mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, 0); - up(&priv->cmd.slave_sem); + mutex_unlock(&priv->cmd.slave_cmd_mutex); return -EIO; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 4b1fbd84a68f..71eed05426ec 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -513,9 +513,9 @@ struct mlx4_cmd { struct pci_pool *pool; void __iomem *hcr; struct mutex hcr_mutex; + struct mutex slave_cmd_mutex; struct semaphore poll_sem; struct semaphore event_sem; - struct semaphore slave_sem; int max_cmds; spinlock_t context_lock; int free_head; -- cgit v1.2.3 From 839f12434c7618d326b9d1ece5eca643e5e48d0a Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Thu, 27 Sep 2012 09:23:41 -0700 Subject: mlx4_core: Stash PCI ID driver_data in mlx4_priv structure That way we can check flags later on, when we've finished with the pci_device_id structure. Also convert the "is VF" flag to an enum: "Never do in the preprocessor what can be done in C." Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/main.c | 29 ++++++++++++++++------------- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 6 ++++++ 2 files changed, 22 insertions(+), 13 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 1e9f816a94db..c9732ca4191e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -95,8 +95,6 @@ MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num" " Not in use with device managed" " flow steering"); -#define MLX4_VF (1 << 0) - #define HCA_GLOBAL_CAP_MASK 0 #define PF_CONTEXT_BEHAVIOUR_MASK 0 @@ -1916,7 +1914,7 @@ static void mlx4_free_ownership(struct mlx4_dev *dev) iounmap(owner); } -static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) +static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) { struct mlx4_priv *priv; struct mlx4_dev *dev; @@ -1939,12 +1937,11 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) /* * Check for BARs. */ - if (((id == NULL) || !(id->driver_data & MLX4_VF)) && + if (!(pci_dev_data & MLX4_PCI_DEV_IS_VF) && !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) { dev_err(&pdev->dev, "Missing DCS, aborting." - "(id == 0X%p, id->driver_data: 0x%lx," - " pci_resource_flags(pdev, 0):0x%lx)\n", id, - id ? id->driver_data : 0, pci_resource_flags(pdev, 0)); + "(driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n", + pci_dev_data, pci_resource_flags(pdev, 0)); err = -ENODEV; goto err_disable_pdev; } @@ -2009,7 +2006,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) dev->rev_id = pdev->revision; /* Detect if this device is a virtual function */ - if (id && id->driver_data & MLX4_VF) { + if (pci_dev_data & MLX4_PCI_DEV_IS_VF) { /* When acting as pf, we normally skip vfs unless explicitly * requested to probe them. */ if (num_vfs && extended_func_num(pdev) > probe_vf) { @@ -2156,6 +2153,7 @@ slave_start: mlx4_sense_init(dev); mlx4_start_sense(dev); + priv->pci_dev_data = pci_dev_data; pci_set_drvdata(pdev, dev); return 0; @@ -2225,7 +2223,7 @@ static int __devinit mlx4_init_one(struct pci_dev *pdev, { printk_once(KERN_INFO "%s", mlx4_version); - return __mlx4_init_one(pdev, id); + return __mlx4_init_one(pdev, id->driver_data); } static void mlx4_remove_one(struct pci_dev *pdev) @@ -2305,8 +2303,13 @@ static void mlx4_remove_one(struct pci_dev *pdev) int mlx4_restart_one(struct pci_dev *pdev) { + struct mlx4_dev *dev = pci_get_drvdata(pdev); + struct mlx4_priv *priv = mlx4_priv(dev); + int pci_dev_data; + + pci_dev_data = priv->pci_dev_data; mlx4_remove_one(pdev); - return __mlx4_init_one(pdev, NULL); + return __mlx4_init_one(pdev, pci_dev_data); } static DEFINE_PCI_DEVICE_TABLE(mlx4_pci_table) = { @@ -2335,11 +2338,11 @@ static DEFINE_PCI_DEVICE_TABLE(mlx4_pci_table) = { /* MT26478 ConnectX2 40GigE PCIe gen2 */ { PCI_VDEVICE(MELLANOX, 0x676e), 0 }, /* MT25400 Family [ConnectX-2 Virtual Function] */ - { PCI_VDEVICE(MELLANOX, 0x1002), MLX4_VF }, + { PCI_VDEVICE(MELLANOX, 0x1002), MLX4_PCI_DEV_IS_VF }, /* MT27500 Family [ConnectX-3] */ { PCI_VDEVICE(MELLANOX, 0x1003), 0 }, /* MT27500 Family [ConnectX-3 Virtual Function] */ - { PCI_VDEVICE(MELLANOX, 0x1004), MLX4_VF }, + { PCI_VDEVICE(MELLANOX, 0x1004), MLX4_PCI_DEV_IS_VF }, { PCI_VDEVICE(MELLANOX, 0x1005), 0 }, /* MT27510 Family */ { PCI_VDEVICE(MELLANOX, 0x1006), 0 }, /* MT27511 Family */ { PCI_VDEVICE(MELLANOX, 0x1007), 0 }, /* MT27520 Family */ @@ -2368,7 +2371,7 @@ static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev, static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev) { - int ret = __mlx4_init_one(pdev, NULL); + int ret = __mlx4_init_one(pdev, 0); return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 71eed05426ec..ac58189ae6da 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -768,6 +768,10 @@ struct _rule_hw { }; }; +enum { + MLX4_PCI_DEV_IS_VF = 1 << 0, +}; + struct mlx4_priv { struct mlx4_dev dev; @@ -775,6 +779,8 @@ struct mlx4_priv { struct list_head ctx_list; spinlock_t ctx_lock; + int pci_dev_data; + struct list_head pgdir_list; struct mutex pgdir_mutex; -- cgit v1.2.3 From ca3e57a599e1f3624a6164a5c3a655859368f7aa Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Thu, 27 Sep 2012 09:53:05 -0700 Subject: mlx4_core: Clean up enabling of SENSE_PORT for older (ConnectX-1/-2) HCAs Instead of having a hard-coded "PCI device ID != 0x1003" (which obviously breaks as newer devices with ID != 0x1003 become available), instead let's set a flag in our PCI device table for the older devices where we're supposed to force using SENSE_PORT. This also avoids enabling SENSE_PORT for virtual functions by mistake. Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/main.c | 28 ++++++++++++++-------------- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 1 + 2 files changed, 15 insertions(+), 14 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index c9732ca4191e..877d1122f787 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -297,8 +297,8 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) mlx4_dbg(dev, "Steering mode is: %s\n", mlx4_steering_mode_str(dev->caps.steering_mode)); - /* Sense port always allowed on supported devices for ConnectX1 and 2 */ - if (dev->pdev->device != 0x1003) + /* Sense port always allowed on supported devices for ConnectX-1 and -2 */ + if (mlx4_priv(dev)->pci_dev_data & MLX4_PCI_DEV_FORCE_SENSE_PORT) dev->caps.flags |= MLX4_DEV_CAP_FLAG_SENSE_SUPPORT; dev->caps.log_num_macs = log_num_mac; @@ -2314,29 +2314,29 @@ int mlx4_restart_one(struct pci_dev *pdev) static DEFINE_PCI_DEVICE_TABLE(mlx4_pci_table) = { /* MT25408 "Hermon" SDR */ - { PCI_VDEVICE(MELLANOX, 0x6340), 0 }, + { PCI_VDEVICE(MELLANOX, 0x6340), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT25408 "Hermon" DDR */ - { PCI_VDEVICE(MELLANOX, 0x634a), 0 }, + { PCI_VDEVICE(MELLANOX, 0x634a), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT25408 "Hermon" QDR */ - { PCI_VDEVICE(MELLANOX, 0x6354), 0 }, + { PCI_VDEVICE(MELLANOX, 0x6354), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT25408 "Hermon" DDR PCIe gen2 */ - { PCI_VDEVICE(MELLANOX, 0x6732), 0 }, + { PCI_VDEVICE(MELLANOX, 0x6732), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT25408 "Hermon" QDR PCIe gen2 */ - { PCI_VDEVICE(MELLANOX, 0x673c), 0 }, + { PCI_VDEVICE(MELLANOX, 0x673c), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT25408 "Hermon" EN 10GigE */ - { PCI_VDEVICE(MELLANOX, 0x6368), 0 }, + { PCI_VDEVICE(MELLANOX, 0x6368), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT25408 "Hermon" EN 10GigE PCIe gen2 */ - { PCI_VDEVICE(MELLANOX, 0x6750), 0 }, + { PCI_VDEVICE(MELLANOX, 0x6750), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT25458 ConnectX EN 10GBASE-T 10GigE */ - { PCI_VDEVICE(MELLANOX, 0x6372), 0 }, + { PCI_VDEVICE(MELLANOX, 0x6372), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT25458 ConnectX EN 10GBASE-T+Gen2 10GigE */ - { PCI_VDEVICE(MELLANOX, 0x675a), 0 }, + { PCI_VDEVICE(MELLANOX, 0x675a), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT26468 ConnectX EN 10GigE PCIe gen2*/ - { PCI_VDEVICE(MELLANOX, 0x6764), 0 }, + { PCI_VDEVICE(MELLANOX, 0x6764), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT26438 ConnectX EN 40GigE PCIe gen2 5GT/s */ - { PCI_VDEVICE(MELLANOX, 0x6746), 0 }, + { PCI_VDEVICE(MELLANOX, 0x6746), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT26478 ConnectX2 40GigE PCIe gen2 */ - { PCI_VDEVICE(MELLANOX, 0x676e), 0 }, + { PCI_VDEVICE(MELLANOX, 0x676e), MLX4_PCI_DEV_FORCE_SENSE_PORT }, /* MT25400 Family [ConnectX-2 Virtual Function] */ { PCI_VDEVICE(MELLANOX, 0x1002), MLX4_PCI_DEV_IS_VF }, /* MT27500 Family [ConnectX-3] */ diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index ac58189ae6da..1cf42036d7bb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -770,6 +770,7 @@ struct _rule_hw { enum { MLX4_PCI_DEV_IS_VF = 1 << 0, + MLX4_PCI_DEV_FORCE_SENSE_PORT = 1 << 1, }; struct mlx4_priv { -- cgit v1.2.3 From aadf4f3f66a7b710b05b31ac0839fbbf59e41f7c Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Thu, 27 Sep 2012 10:01:19 -0700 Subject: mlx4_core: Disable SENSE_PORT for multifunction devices In the current driver, the SENSE_PORT firmware command is issued as a "wrapped" command, but the command handling code doesn't have a wrapper, so it will never do anything other than log an error message. The latest ConnectX-3 2.11.500 firmware reports the SENSE_PORT capability even in multi-function (SR-IOV) mode, so the driver will try to issue the command. At least until the driver has a proper wrapper for SENSE_PORT, make sure we disable the command for multi-function devices. Signed-off-by: Roland Dreier --- drivers/net/ethernet/mellanox/mlx4/main.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 877d1122f787..bc1e5d41c292 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -300,6 +300,9 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) /* Sense port always allowed on supported devices for ConnectX-1 and -2 */ if (mlx4_priv(dev)->pci_dev_data & MLX4_PCI_DEV_FORCE_SENSE_PORT) dev->caps.flags |= MLX4_DEV_CAP_FLAG_SENSE_SUPPORT; + /* Don't do sense port on multifunction devices (for now at least) */ + if (mlx4_is_mfunc(dev)) + dev->caps.flags &= ~MLX4_DEV_CAP_FLAG_SENSE_SUPPORT; dev->caps.log_num_macs = log_num_mac; dev->caps.log_num_vlans = MLX4_LOG_NUM_VLANS; -- cgit v1.2.3 From 2f6a02604e962295569749913081365ec9ec1372 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Mon, 1 Oct 2012 01:56:55 +0000 Subject: be2net: fix vfs enumeration Current VFs enumeration algorithm used in be_find_vfs does not take domain number into the match. The match found in igb/ixgbe is more elegant and safe. This 2nd version uses pci_physfn instead of checking dev->physfn directly. Signed-off-by: Ivan Vecera Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 6accb0c0273a..8dd42b309f38 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1075,7 +1075,7 @@ static int be_set_vf_tx_rate(struct net_device *netdev, static int be_find_vfs(struct be_adapter *adapter, int vf_state) { struct pci_dev *dev, *pdev = adapter->pdev; - int vfs = 0, assigned_vfs = 0, pos, vf_fn; + int vfs = 0, assigned_vfs = 0, pos; u16 offset, stride; pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); @@ -1086,9 +1086,7 @@ static int be_find_vfs(struct be_adapter *adapter, int vf_state) dev = pci_get_device(pdev->vendor, PCI_ANY_ID, NULL); while (dev) { - vf_fn = (pdev->devfn + offset + stride * vfs) & 0xFFFF; - if (dev->is_virtfn && dev->devfn == vf_fn && - dev->bus->number == pdev->bus->number) { + if (dev->is_virtfn && pci_physfn(dev) == pdev) { vfs++; if (dev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) assigned_vfs++; -- cgit v1.2.3 From 96bed4b954fd5ef69e32f3c1d2c7c6bdda181316 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 1 Oct 2012 03:46:19 +0000 Subject: bnx2x,cnic: use FW 7.8.2 This patch moves the bnx2x and cnic drivers into using FW 7.8.2 which was recently submitted into the linux-firmware tree. A short summary of minor bugs fixed by this FW: 1. In switch dependent mode, fix several issues regarding inner vlan vs. DCB priorities. 2. iSCSI - not all packets were completed on a forward channel. 3. DCB - fixed for 4-port devices. 4. Fixed false parity reported in CAM memories when operating near -5% on the 1.0V core supply. 5. ETS default settings are set to fairness between traffic classes (rather than strict priority), and uses the same chip receive buffer configuration for both PFC and pause. For a complete list of fixes made by this FW, see commit 236367db in the linux-firmware git repository. Signed-off-by: Yuval Mintz Signed-off-by: Dmitry Kravkov Signed-off-by: Ariel Elior Signed-off-by: Eilon Greenstein Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 12 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c | 12 +- .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 31 +- .../net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h | 3 - drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h | 58 +-- drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 504 --------------------- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c | 2 +- drivers/net/ethernet/broadcom/cnic.c | 12 +- drivers/net/ethernet/broadcom/cnic_defs.h | 2 +- drivers/net/ethernet/broadcom/cnic_if.h | 4 +- 11 files changed, 79 insertions(+), 563 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index f67e700fe59d..30f04a389227 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3026,8 +3026,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) first_bd = tx_start_bd; tx_start_bd->bd_flags.as_bitfield = ETH_TX_BD_FLAGS_START_BD; - SET_FLAG(tx_start_bd->general_data, ETH_TX_START_BD_ETH_ADDR_TYPE, - mac_type); + SET_FLAG(tx_start_bd->general_data, + ETH_TX_START_BD_PARSE_NBDS, + 0); /* header nbd */ SET_FLAG(tx_start_bd->general_data, ETH_TX_START_BD_HDR_NBDS, 1); @@ -3077,13 +3078,20 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) &pbd_e2->dst_mac_addr_lo, eth->h_dest); } + + SET_FLAG(pbd_e2_parsing_data, + ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE, mac_type); } else { + u16 global_data = 0; pbd_e1x = &txdata->tx_desc_ring[bd_prod].parse_bd_e1x; memset(pbd_e1x, 0, sizeof(struct eth_tx_parse_bd_e1x)); /* Set PBD in checksum offload case */ if (xmit_type & XMIT_CSUM) hlen = bnx2x_set_pbd_csum(bp, skb, pbd_e1x, xmit_type); + SET_FLAG(global_data, + ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE, mac_type); + pbd_e1x->global_data |= cpu_to_le16(global_data); } /* Setup the data pointer of the first BD of the packet */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c index 8a73374e52a7..2245c3895409 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c @@ -91,25 +91,21 @@ static void bnx2x_pfc_set(struct bnx2x *bp) /* * Rx COS configuration * Changing PFC RX configuration . - * In RX COS0 will always be configured to lossy and COS1 to lossless + * In RX COS0 will always be configured to lossless and COS1 to lossy */ for (i = 0 ; i < MAX_PFC_PRIORITIES ; i++) { pri_bit = 1 << i; - if (pri_bit & DCBX_PFC_PRI_PAUSE_MASK(bp)) + if (!(pri_bit & DCBX_PFC_PRI_PAUSE_MASK(bp))) val |= 1 << (i * 4); } pfc_params.pkt_priority_to_cos = val; /* RX COS0 */ - pfc_params.llfc_low_priority_classes = 0; + pfc_params.llfc_low_priority_classes = DCBX_PFC_PRI_PAUSE_MASK(bp); /* RX COS1 */ - pfc_params.llfc_high_priority_classes = DCBX_PFC_PRI_PAUSE_MASK(bp); - - /* BRB configuration */ - pfc_params.cos0_pauseable = false; - pfc_params.cos1_pauseable = true; + pfc_params.llfc_high_priority_classes = 0; bnx2x_acquire_phy_lock(bp); bp->link_params.feature_config_flags |= FEATURE_CONFIG_PFC_ENABLED; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index a19c9e088278..c65295dded39 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -2040,8 +2040,6 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode) u16 pkt_prod, bd_prod; struct sw_tx_bd *tx_buf; struct eth_tx_start_bd *tx_start_bd; - struct eth_tx_parse_bd_e1x *pbd_e1x = NULL; - struct eth_tx_parse_bd_e2 *pbd_e2 = NULL; dma_addr_t mapping; union eth_rx_cqe *cqe; u8 cqe_fp_flags, cqe_fp_type; @@ -2132,22 +2130,33 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode) tx_start_bd->nbytes = cpu_to_le16(skb_headlen(skb)); tx_start_bd->vlan_or_ethertype = cpu_to_le16(pkt_prod); tx_start_bd->bd_flags.as_bitfield = ETH_TX_BD_FLAGS_START_BD; - SET_FLAG(tx_start_bd->general_data, - ETH_TX_START_BD_ETH_ADDR_TYPE, - UNICAST_ADDRESS); SET_FLAG(tx_start_bd->general_data, ETH_TX_START_BD_HDR_NBDS, 1); + SET_FLAG(tx_start_bd->general_data, + ETH_TX_START_BD_PARSE_NBDS, + 0); /* turn on parsing and get a BD */ bd_prod = TX_BD(NEXT_TX_IDX(bd_prod)); - pbd_e1x = &txdata->tx_desc_ring[bd_prod].parse_bd_e1x; - pbd_e2 = &txdata->tx_desc_ring[bd_prod].parse_bd_e2; - - memset(pbd_e2, 0, sizeof(struct eth_tx_parse_bd_e2)); - memset(pbd_e1x, 0, sizeof(struct eth_tx_parse_bd_e1x)); - + if (CHIP_IS_E1x(bp)) { + u16 global_data = 0; + struct eth_tx_parse_bd_e1x *pbd_e1x = + &txdata->tx_desc_ring[bd_prod].parse_bd_e1x; + memset(pbd_e1x, 0, sizeof(struct eth_tx_parse_bd_e1x)); + SET_FLAG(global_data, + ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE, UNICAST_ADDRESS); + pbd_e1x->global_data = cpu_to_le16(global_data); + } else { + u32 parsing_data = 0; + struct eth_tx_parse_bd_e2 *pbd_e2 = + &txdata->tx_desc_ring[bd_prod].parse_bd_e2; + memset(pbd_e2, 0, sizeof(struct eth_tx_parse_bd_e2)); + SET_FLAG(parsing_data, + ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE, UNICAST_ADDRESS); + pbd_e2->parsing_data = cpu_to_le32(parsing_data); + } wmb(); txdata->tx_db.data.prod += 2; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h index bbc66ced9c25..620fe939ecfd 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h @@ -88,9 +88,6 @@ #define TSTORM_ASSERT_LIST_INDEX_OFFSET (IRO[102].base) #define TSTORM_ASSERT_LIST_OFFSET(assertListEntry) \ (IRO[101].base + ((assertListEntry) * IRO[101].m1)) -#define TSTORM_COMMON_SAFC_WORKAROUND_ENABLE_OFFSET (IRO[107].base) -#define TSTORM_COMMON_SAFC_WORKAROUND_TIMEOUT_10USEC_OFFSET \ - (IRO[108].base) #define TSTORM_FUNCTION_COMMON_CONFIG_OFFSET(pfId) \ (IRO[201].base + ((pfId) * IRO[201].m1)) #define TSTORM_FUNC_EN_OFFSET(funcId) \ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index c795cfc5a545..18704929e642 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -2789,8 +2789,8 @@ struct afex_stats { }; #define BCM_5710_FW_MAJOR_VERSION 7 -#define BCM_5710_FW_MINOR_VERSION 2 -#define BCM_5710_FW_REVISION_VERSION 51 +#define BCM_5710_FW_MINOR_VERSION 8 +#define BCM_5710_FW_REVISION_VERSION 2 #define BCM_5710_FW_ENGINEERING_VERSION 0 #define BCM_5710_FW_COMPILE_FLAGS 1 @@ -3912,10 +3912,8 @@ struct eth_rss_update_ramrod_data { #define ETH_RSS_UPDATE_RAMROD_DATA_IPV6_TCP_CAPABILITY_SHIFT 4 #define ETH_RSS_UPDATE_RAMROD_DATA_IPV6_UDP_CAPABILITY (0x1<<5) #define ETH_RSS_UPDATE_RAMROD_DATA_IPV6_UDP_CAPABILITY_SHIFT 5 -#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY (0x1<<6) -#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY_SHIFT 6 -#define __ETH_RSS_UPDATE_RAMROD_DATA_RESERVED0 (0x1<<7) -#define __ETH_RSS_UPDATE_RAMROD_DATA_RESERVED0_SHIFT 7 +#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY (0x1<<7) +#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY_SHIFT 7 u8 rss_result_mask; u8 rss_mode; __le32 __reserved2; @@ -4131,27 +4129,29 @@ struct eth_tx_start_bd { #define ETH_TX_START_BD_HDR_NBDS_SHIFT 0 #define ETH_TX_START_BD_FORCE_VLAN_MODE (0x1<<4) #define ETH_TX_START_BD_FORCE_VLAN_MODE_SHIFT 4 -#define ETH_TX_START_BD_RESREVED (0x1<<5) -#define ETH_TX_START_BD_RESREVED_SHIFT 5 -#define ETH_TX_START_BD_ETH_ADDR_TYPE (0x3<<6) -#define ETH_TX_START_BD_ETH_ADDR_TYPE_SHIFT 6 +#define ETH_TX_START_BD_PARSE_NBDS (0x3<<5) +#define ETH_TX_START_BD_PARSE_NBDS_SHIFT 5 +#define ETH_TX_START_BD_RESREVED (0x1<<7) +#define ETH_TX_START_BD_RESREVED_SHIFT 7 }; /* * Tx parsing BD structure for ETH E1/E1h */ struct eth_tx_parse_bd_e1x { - u8 global_data; + __le16 global_data; #define ETH_TX_PARSE_BD_E1X_IP_HDR_START_OFFSET_W (0xF<<0) #define ETH_TX_PARSE_BD_E1X_IP_HDR_START_OFFSET_W_SHIFT 0 -#define ETH_TX_PARSE_BD_E1X_RESERVED0 (0x1<<4) -#define ETH_TX_PARSE_BD_E1X_RESERVED0_SHIFT 4 -#define ETH_TX_PARSE_BD_E1X_PSEUDO_CS_WITHOUT_LEN (0x1<<5) -#define ETH_TX_PARSE_BD_E1X_PSEUDO_CS_WITHOUT_LEN_SHIFT 5 -#define ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN (0x1<<6) -#define ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN_SHIFT 6 -#define ETH_TX_PARSE_BD_E1X_NS_FLG (0x1<<7) -#define ETH_TX_PARSE_BD_E1X_NS_FLG_SHIFT 7 +#define ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE (0x3<<4) +#define ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE_SHIFT 4 +#define ETH_TX_PARSE_BD_E1X_PSEUDO_CS_WITHOUT_LEN (0x1<<6) +#define ETH_TX_PARSE_BD_E1X_PSEUDO_CS_WITHOUT_LEN_SHIFT 6 +#define ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN (0x1<<7) +#define ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN_SHIFT 7 +#define ETH_TX_PARSE_BD_E1X_NS_FLG (0x1<<8) +#define ETH_TX_PARSE_BD_E1X_NS_FLG_SHIFT 8 +#define ETH_TX_PARSE_BD_E1X_RESERVED0 (0x7F<<9) +#define ETH_TX_PARSE_BD_E1X_RESERVED0_SHIFT 9 u8 tcp_flags; #define ETH_TX_PARSE_BD_E1X_FIN_FLG (0x1<<0) #define ETH_TX_PARSE_BD_E1X_FIN_FLG_SHIFT 0 @@ -4170,7 +4170,6 @@ struct eth_tx_parse_bd_e1x { #define ETH_TX_PARSE_BD_E1X_CWR_FLG (0x1<<7) #define ETH_TX_PARSE_BD_E1X_CWR_FLG_SHIFT 7 u8 ip_hlen_w; - s8 reserved; __le16 total_hlen_w; __le16 tcp_pseudo_csum; __le16 lso_mss; @@ -4189,14 +4188,16 @@ struct eth_tx_parse_bd_e2 { __le16 src_mac_addr_mid; __le16 src_mac_addr_hi; __le32 parsing_data; -#define ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W (0x1FFF<<0) +#define ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W (0x7FF<<0) #define ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W_SHIFT 0 -#define ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW (0xF<<13) -#define ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW_SHIFT 13 -#define ETH_TX_PARSE_BD_E2_LSO_MSS (0x3FFF<<17) -#define ETH_TX_PARSE_BD_E2_LSO_MSS_SHIFT 17 -#define ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR (0x1<<31) -#define ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR_SHIFT 31 +#define ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW (0xF<<11) +#define ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW_SHIFT 11 +#define ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR (0x1<<15) +#define ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR_SHIFT 15 +#define ETH_TX_PARSE_BD_E2_LSO_MSS (0x3FFF<<16) +#define ETH_TX_PARSE_BD_E2_LSO_MSS_SHIFT 16 +#define ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE (0x3<<30) +#define ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE_SHIFT 30 }; /* @@ -4964,7 +4965,8 @@ struct flow_control_configuration { * */ struct function_start_data { - __le16 function_mode; + u8 function_mode; + u8 reserved; __le16 sd_vlan_tag; __le16 vif_id; u8 path_id; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h index 559c396d45cc..c8f10f0e8a0d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h @@ -566,7 +566,7 @@ static const struct { u32 e2; /* 57712 */ u32 e3; /* 578xx */ } reg_mask; /* Register mask (all valid bits) */ - char name[7]; /* Block's longest name is 6 characters long + char name[8]; /* Block's longest name is 7 characters long * (name + suffix) */ } bnx2x_blocks_parity_data[] = { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index bcc112b82831..e2e45ee5df33 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -161,120 +161,6 @@ #define EDC_MODE_LIMITING 0x0044 #define EDC_MODE_PASSIVE_DAC 0x0055 -/* BRB default for class 0 E2 */ -#define DEFAULT0_E2_BRB_MAC_PAUSE_XOFF_THR 170 -#define DEFAULT0_E2_BRB_MAC_PAUSE_XON_THR 250 -#define DEFAULT0_E2_BRB_MAC_FULL_XOFF_THR 10 -#define DEFAULT0_E2_BRB_MAC_FULL_XON_THR 50 - -/* BRB thresholds for E2*/ -#define PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE 170 -#define PFC_E2_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE 0 - -#define PFC_E2_BRB_MAC_PAUSE_XON_THR_PAUSE 250 -#define PFC_E2_BRB_MAC_PAUSE_XON_THR_NON_PAUSE 0 - -#define PFC_E2_BRB_MAC_FULL_XOFF_THR_PAUSE 10 -#define PFC_E2_BRB_MAC_FULL_XOFF_THR_NON_PAUSE 90 - -#define PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE 50 -#define PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE 250 - -/* BRB default for class 0 E3A0 */ -#define DEFAULT0_E3A0_BRB_MAC_PAUSE_XOFF_THR 290 -#define DEFAULT0_E3A0_BRB_MAC_PAUSE_XON_THR 410 -#define DEFAULT0_E3A0_BRB_MAC_FULL_XOFF_THR 10 -#define DEFAULT0_E3A0_BRB_MAC_FULL_XON_THR 50 - -/* BRB thresholds for E3A0 */ -#define PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE 290 -#define PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE 0 - -#define PFC_E3A0_BRB_MAC_PAUSE_XON_THR_PAUSE 410 -#define PFC_E3A0_BRB_MAC_PAUSE_XON_THR_NON_PAUSE 0 - -#define PFC_E3A0_BRB_MAC_FULL_XOFF_THR_PAUSE 10 -#define PFC_E3A0_BRB_MAC_FULL_XOFF_THR_NON_PAUSE 170 - -#define PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE 50 -#define PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE 410 - -/* BRB default for E3B0 */ -#define DEFAULT0_E3B0_BRB_MAC_PAUSE_XOFF_THR 330 -#define DEFAULT0_E3B0_BRB_MAC_PAUSE_XON_THR 490 -#define DEFAULT0_E3B0_BRB_MAC_FULL_XOFF_THR 15 -#define DEFAULT0_E3B0_BRB_MAC_FULL_XON_THR 55 - -/* BRB thresholds for E3B0 2 port mode*/ -#define PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE 1025 -#define PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE 0 - -#define PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_PAUSE 1025 -#define PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE 0 - -#define PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_PAUSE 10 -#define PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE 1025 - -#define PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_PAUSE 50 -#define PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_NON_PAUSE 1025 - -/* only for E3B0*/ -#define PFC_E3B0_2P_BRB_FULL_LB_XOFF_THR 1025 -#define PFC_E3B0_2P_BRB_FULL_LB_XON_THR 1025 - -/* Lossy +Lossless GUARANTIED == GUART */ -#define PFC_E3B0_2P_MIX_PAUSE_LB_GUART 284 -/* Lossless +Lossless*/ -#define PFC_E3B0_2P_PAUSE_LB_GUART 236 -/* Lossy +Lossy*/ -#define PFC_E3B0_2P_NON_PAUSE_LB_GUART 342 - -/* Lossy +Lossless*/ -#define PFC_E3B0_2P_MIX_PAUSE_MAC_0_CLASS_T_GUART 284 -/* Lossless +Lossless*/ -#define PFC_E3B0_2P_PAUSE_MAC_0_CLASS_T_GUART 236 -/* Lossy +Lossy*/ -#define PFC_E3B0_2P_NON_PAUSE_MAC_0_CLASS_T_GUART 336 -#define PFC_E3B0_2P_BRB_MAC_0_CLASS_T_GUART_HYST 80 - -#define PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART 0 -#define PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART_HYST 0 - -/* BRB thresholds for E3B0 4 port mode */ -#define PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_PAUSE 304 -#define PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE 0 - -#define PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_PAUSE 384 -#define PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE 0 - -#define PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_PAUSE 10 -#define PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE 304 - -#define PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE 50 -#define PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE 384 - -/* only for E3B0*/ -#define PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR 304 -#define PFC_E3B0_4P_BRB_FULL_LB_XON_THR 384 -#define PFC_E3B0_4P_LB_GUART 120 - -#define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART 120 -#define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST 80 - -#define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART 80 -#define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST 120 - -/* Pause defines*/ -#define DEFAULT_E3B0_BRB_FULL_LB_XOFF_THR 330 -#define DEFAULT_E3B0_BRB_FULL_LB_XON_THR 490 -#define DEFAULT_E3B0_LB_GUART 40 - -#define DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART 40 -#define DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART_HYST 0 - -#define DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART 40 -#define DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART_HYST 0 - /* ETS defines*/ #define DCBX_INVALID_COS (0xFF) @@ -2144,391 +2030,6 @@ static void bnx2x_update_pfc_bmac2(struct link_params *params, REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_BMAC_CONTROL, wb_data, 2); } -/* PFC BRB internal port configuration params */ -struct bnx2x_pfc_brb_threshold_val { - u32 pause_xoff; - u32 pause_xon; - u32 full_xoff; - u32 full_xon; -}; - -struct bnx2x_pfc_brb_e3b0_val { - u32 per_class_guaranty_mode; - u32 lb_guarantied_hyst; - u32 full_lb_xoff_th; - u32 full_lb_xon_threshold; - u32 lb_guarantied; - u32 mac_0_class_t_guarantied; - u32 mac_0_class_t_guarantied_hyst; - u32 mac_1_class_t_guarantied; - u32 mac_1_class_t_guarantied_hyst; -}; - -struct bnx2x_pfc_brb_th_val { - struct bnx2x_pfc_brb_threshold_val pauseable_th; - struct bnx2x_pfc_brb_threshold_val non_pauseable_th; - struct bnx2x_pfc_brb_threshold_val default_class0; - struct bnx2x_pfc_brb_threshold_val default_class1; - -}; -static int bnx2x_pfc_brb_get_config_params( - struct link_params *params, - struct bnx2x_pfc_brb_th_val *config_val) -{ - struct bnx2x *bp = params->bp; - DP(NETIF_MSG_LINK, "Setting PFC BRB configuration\n"); - - config_val->default_class1.pause_xoff = 0; - config_val->default_class1.pause_xon = 0; - config_val->default_class1.full_xoff = 0; - config_val->default_class1.full_xon = 0; - - if (CHIP_IS_E2(bp)) { - /* Class0 defaults */ - config_val->default_class0.pause_xoff = - DEFAULT0_E2_BRB_MAC_PAUSE_XOFF_THR; - config_val->default_class0.pause_xon = - DEFAULT0_E2_BRB_MAC_PAUSE_XON_THR; - config_val->default_class0.full_xoff = - DEFAULT0_E2_BRB_MAC_FULL_XOFF_THR; - config_val->default_class0.full_xon = - DEFAULT0_E2_BRB_MAC_FULL_XON_THR; - /* Pause able*/ - config_val->pauseable_th.pause_xoff = - PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE; - config_val->pauseable_th.pause_xon = - PFC_E2_BRB_MAC_PAUSE_XON_THR_PAUSE; - config_val->pauseable_th.full_xoff = - PFC_E2_BRB_MAC_FULL_XOFF_THR_PAUSE; - config_val->pauseable_th.full_xon = - PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE; - /* Non pause able*/ - config_val->non_pauseable_th.pause_xoff = - PFC_E2_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE; - config_val->non_pauseable_th.pause_xon = - PFC_E2_BRB_MAC_PAUSE_XON_THR_NON_PAUSE; - config_val->non_pauseable_th.full_xoff = - PFC_E2_BRB_MAC_FULL_XOFF_THR_NON_PAUSE; - config_val->non_pauseable_th.full_xon = - PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE; - } else if (CHIP_IS_E3A0(bp)) { - /* Class0 defaults */ - config_val->default_class0.pause_xoff = - DEFAULT0_E3A0_BRB_MAC_PAUSE_XOFF_THR; - config_val->default_class0.pause_xon = - DEFAULT0_E3A0_BRB_MAC_PAUSE_XON_THR; - config_val->default_class0.full_xoff = - DEFAULT0_E3A0_BRB_MAC_FULL_XOFF_THR; - config_val->default_class0.full_xon = - DEFAULT0_E3A0_BRB_MAC_FULL_XON_THR; - /* Pause able */ - config_val->pauseable_th.pause_xoff = - PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE; - config_val->pauseable_th.pause_xon = - PFC_E3A0_BRB_MAC_PAUSE_XON_THR_PAUSE; - config_val->pauseable_th.full_xoff = - PFC_E3A0_BRB_MAC_FULL_XOFF_THR_PAUSE; - config_val->pauseable_th.full_xon = - PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE; - /* Non pause able*/ - config_val->non_pauseable_th.pause_xoff = - PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE; - config_val->non_pauseable_th.pause_xon = - PFC_E3A0_BRB_MAC_PAUSE_XON_THR_NON_PAUSE; - config_val->non_pauseable_th.full_xoff = - PFC_E3A0_BRB_MAC_FULL_XOFF_THR_NON_PAUSE; - config_val->non_pauseable_th.full_xon = - PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE; - } else if (CHIP_IS_E3B0(bp)) { - /* Class0 defaults */ - config_val->default_class0.pause_xoff = - DEFAULT0_E3B0_BRB_MAC_PAUSE_XOFF_THR; - config_val->default_class0.pause_xon = - DEFAULT0_E3B0_BRB_MAC_PAUSE_XON_THR; - config_val->default_class0.full_xoff = - DEFAULT0_E3B0_BRB_MAC_FULL_XOFF_THR; - config_val->default_class0.full_xon = - DEFAULT0_E3B0_BRB_MAC_FULL_XON_THR; - - if (params->phy[INT_PHY].flags & - FLAGS_4_PORT_MODE) { - config_val->pauseable_th.pause_xoff = - PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_PAUSE; - config_val->pauseable_th.pause_xon = - PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_PAUSE; - config_val->pauseable_th.full_xoff = - PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_PAUSE; - config_val->pauseable_th.full_xon = - PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE; - /* Non pause able*/ - config_val->non_pauseable_th.pause_xoff = - PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE; - config_val->non_pauseable_th.pause_xon = - PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE; - config_val->non_pauseable_th.full_xoff = - PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE; - config_val->non_pauseable_th.full_xon = - PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE; - } else { - config_val->pauseable_th.pause_xoff = - PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE; - config_val->pauseable_th.pause_xon = - PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_PAUSE; - config_val->pauseable_th.full_xoff = - PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_PAUSE; - config_val->pauseable_th.full_xon = - PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_PAUSE; - /* Non pause able*/ - config_val->non_pauseable_th.pause_xoff = - PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE; - config_val->non_pauseable_th.pause_xon = - PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE; - config_val->non_pauseable_th.full_xoff = - PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE; - config_val->non_pauseable_th.full_xon = - PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_NON_PAUSE; - } - } else - return -EINVAL; - - return 0; -} - -static void bnx2x_pfc_brb_get_e3b0_config_params( - struct link_params *params, - struct bnx2x_pfc_brb_e3b0_val - *e3b0_val, - struct bnx2x_nig_brb_pfc_port_params *pfc_params, - const u8 pfc_enabled) -{ - if (pfc_enabled && pfc_params) { - e3b0_val->per_class_guaranty_mode = 1; - e3b0_val->lb_guarantied_hyst = 80; - - if (params->phy[INT_PHY].flags & - FLAGS_4_PORT_MODE) { - e3b0_val->full_lb_xoff_th = - PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR; - e3b0_val->full_lb_xon_threshold = - PFC_E3B0_4P_BRB_FULL_LB_XON_THR; - e3b0_val->lb_guarantied = - PFC_E3B0_4P_LB_GUART; - e3b0_val->mac_0_class_t_guarantied = - PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART; - e3b0_val->mac_0_class_t_guarantied_hyst = - PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST; - e3b0_val->mac_1_class_t_guarantied = - PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART; - e3b0_val->mac_1_class_t_guarantied_hyst = - PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST; - } else { - e3b0_val->full_lb_xoff_th = - PFC_E3B0_2P_BRB_FULL_LB_XOFF_THR; - e3b0_val->full_lb_xon_threshold = - PFC_E3B0_2P_BRB_FULL_LB_XON_THR; - e3b0_val->mac_0_class_t_guarantied_hyst = - PFC_E3B0_2P_BRB_MAC_0_CLASS_T_GUART_HYST; - e3b0_val->mac_1_class_t_guarantied = - PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART; - e3b0_val->mac_1_class_t_guarantied_hyst = - PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART_HYST; - - if (pfc_params->cos0_pauseable != - pfc_params->cos1_pauseable) { - /* Nonpauseable= Lossy + pauseable = Lossless*/ - e3b0_val->lb_guarantied = - PFC_E3B0_2P_MIX_PAUSE_LB_GUART; - e3b0_val->mac_0_class_t_guarantied = - PFC_E3B0_2P_MIX_PAUSE_MAC_0_CLASS_T_GUART; - } else if (pfc_params->cos0_pauseable) { - /* Lossless +Lossless*/ - e3b0_val->lb_guarantied = - PFC_E3B0_2P_PAUSE_LB_GUART; - e3b0_val->mac_0_class_t_guarantied = - PFC_E3B0_2P_PAUSE_MAC_0_CLASS_T_GUART; - } else { - /* Lossy +Lossy*/ - e3b0_val->lb_guarantied = - PFC_E3B0_2P_NON_PAUSE_LB_GUART; - e3b0_val->mac_0_class_t_guarantied = - PFC_E3B0_2P_NON_PAUSE_MAC_0_CLASS_T_GUART; - } - } - } else { - e3b0_val->per_class_guaranty_mode = 0; - e3b0_val->lb_guarantied_hyst = 0; - e3b0_val->full_lb_xoff_th = - DEFAULT_E3B0_BRB_FULL_LB_XOFF_THR; - e3b0_val->full_lb_xon_threshold = - DEFAULT_E3B0_BRB_FULL_LB_XON_THR; - e3b0_val->lb_guarantied = - DEFAULT_E3B0_LB_GUART; - e3b0_val->mac_0_class_t_guarantied = - DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART; - e3b0_val->mac_0_class_t_guarantied_hyst = - DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART_HYST; - e3b0_val->mac_1_class_t_guarantied = - DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART; - e3b0_val->mac_1_class_t_guarantied_hyst = - DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART_HYST; - } -} -static int bnx2x_update_pfc_brb(struct link_params *params, - struct link_vars *vars, - struct bnx2x_nig_brb_pfc_port_params - *pfc_params) -{ - struct bnx2x *bp = params->bp; - struct bnx2x_pfc_brb_th_val config_val = { {0} }; - struct bnx2x_pfc_brb_threshold_val *reg_th_config = - &config_val.pauseable_th; - struct bnx2x_pfc_brb_e3b0_val e3b0_val = {0}; - const int set_pfc = params->feature_config_flags & - FEATURE_CONFIG_PFC_ENABLED; - const u8 pfc_enabled = (set_pfc && pfc_params); - int bnx2x_status = 0; - u8 port = params->port; - - /* default - pause configuration */ - reg_th_config = &config_val.pauseable_th; - bnx2x_status = bnx2x_pfc_brb_get_config_params(params, &config_val); - if (bnx2x_status) - return bnx2x_status; - - if (pfc_enabled) { - /* First COS */ - if (pfc_params->cos0_pauseable) - reg_th_config = &config_val.pauseable_th; - else - reg_th_config = &config_val.non_pauseable_th; - } else - reg_th_config = &config_val.default_class0; - /* The number of free blocks below which the pause signal to class 0 - * of MAC #n is asserted. n=0,1 - */ - REG_WR(bp, (port) ? BRB1_REG_PAUSE_0_XOFF_THRESHOLD_1 : - BRB1_REG_PAUSE_0_XOFF_THRESHOLD_0 , - reg_th_config->pause_xoff); - /* The number of free blocks above which the pause signal to class 0 - * of MAC #n is de-asserted. n=0,1 - */ - REG_WR(bp, (port) ? BRB1_REG_PAUSE_0_XON_THRESHOLD_1 : - BRB1_REG_PAUSE_0_XON_THRESHOLD_0 , reg_th_config->pause_xon); - /* The number of free blocks below which the full signal to class 0 - * of MAC #n is asserted. n=0,1 - */ - REG_WR(bp, (port) ? BRB1_REG_FULL_0_XOFF_THRESHOLD_1 : - BRB1_REG_FULL_0_XOFF_THRESHOLD_0 , reg_th_config->full_xoff); - /* The number of free blocks above which the full signal to class 0 - * of MAC #n is de-asserted. n=0,1 - */ - REG_WR(bp, (port) ? BRB1_REG_FULL_0_XON_THRESHOLD_1 : - BRB1_REG_FULL_0_XON_THRESHOLD_0 , reg_th_config->full_xon); - - if (pfc_enabled) { - /* Second COS */ - if (pfc_params->cos1_pauseable) - reg_th_config = &config_val.pauseable_th; - else - reg_th_config = &config_val.non_pauseable_th; - } else - reg_th_config = &config_val.default_class1; - /* The number of free blocks below which the pause signal to - * class 1 of MAC #n is asserted. n=0,1 - */ - REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XOFF_THRESHOLD_1 : - BRB1_REG_PAUSE_1_XOFF_THRESHOLD_0, - reg_th_config->pause_xoff); - - /* The number of free blocks above which the pause signal to - * class 1 of MAC #n is de-asserted. n=0,1 - */ - REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XON_THRESHOLD_1 : - BRB1_REG_PAUSE_1_XON_THRESHOLD_0, - reg_th_config->pause_xon); - /* The number of free blocks below which the full signal to - * class 1 of MAC #n is asserted. n=0,1 - */ - REG_WR(bp, (port) ? BRB1_REG_FULL_1_XOFF_THRESHOLD_1 : - BRB1_REG_FULL_1_XOFF_THRESHOLD_0, - reg_th_config->full_xoff); - /* The number of free blocks above which the full signal to - * class 1 of MAC #n is de-asserted. n=0,1 - */ - REG_WR(bp, (port) ? BRB1_REG_FULL_1_XON_THRESHOLD_1 : - BRB1_REG_FULL_1_XON_THRESHOLD_0, - reg_th_config->full_xon); - - if (CHIP_IS_E3B0(bp)) { - bnx2x_pfc_brb_get_e3b0_config_params( - params, - &e3b0_val, - pfc_params, - pfc_enabled); - - REG_WR(bp, BRB1_REG_PER_CLASS_GUARANTY_MODE, - e3b0_val.per_class_guaranty_mode); - - /* The hysteresis on the guarantied buffer space for the Lb - * port before signaling XON. - */ - REG_WR(bp, BRB1_REG_LB_GUARANTIED_HYST, - e3b0_val.lb_guarantied_hyst); - - /* The number of free blocks below which the full signal to the - * LB port is asserted. - */ - REG_WR(bp, BRB1_REG_FULL_LB_XOFF_THRESHOLD, - e3b0_val.full_lb_xoff_th); - /* The number of free blocks above which the full signal to the - * LB port is de-asserted. - */ - REG_WR(bp, BRB1_REG_FULL_LB_XON_THRESHOLD, - e3b0_val.full_lb_xon_threshold); - /* The number of blocks guarantied for the MAC #n port. n=0,1 - */ - - /* The number of blocks guarantied for the LB port. */ - REG_WR(bp, BRB1_REG_LB_GUARANTIED, - e3b0_val.lb_guarantied); - - /* The number of blocks guarantied for the MAC #n port. */ - REG_WR(bp, BRB1_REG_MAC_GUARANTIED_0, - 2 * e3b0_val.mac_0_class_t_guarantied); - REG_WR(bp, BRB1_REG_MAC_GUARANTIED_1, - 2 * e3b0_val.mac_1_class_t_guarantied); - /* The number of blocks guarantied for class #t in MAC0. t=0,1 - */ - REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED, - e3b0_val.mac_0_class_t_guarantied); - REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED, - e3b0_val.mac_0_class_t_guarantied); - /* The hysteresis on the guarantied buffer space for class in - * MAC0. t=0,1 - */ - REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED_HYST, - e3b0_val.mac_0_class_t_guarantied_hyst); - REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED_HYST, - e3b0_val.mac_0_class_t_guarantied_hyst); - - /* The number of blocks guarantied for class #t in MAC1.t=0,1 - */ - REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED, - e3b0_val.mac_1_class_t_guarantied); - REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED, - e3b0_val.mac_1_class_t_guarantied); - /* The hysteresis on the guarantied buffer space for class #t - * in MAC1. t=0,1 - */ - REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED_HYST, - e3b0_val.mac_1_class_t_guarantied_hyst); - REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED_HYST, - e3b0_val.mac_1_class_t_guarantied_hyst); - } - - return bnx2x_status; -} - /****************************************************************************** * Description: * This function is needed because NIG ARB_CREDIT_WEIGHT_X are @@ -2705,11 +2206,6 @@ int bnx2x_update_pfc(struct link_params *params, /* Update NIG params */ bnx2x_update_pfc_nig(params, vars, pfc_params); - /* Update BRB params */ - bnx2x_status = bnx2x_update_pfc_brb(params, vars, pfc_params); - if (bnx2x_status) - return bnx2x_status; - if (!vars->link_up) return bnx2x_status; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 5a5fbf57c4b4..71971a161bd1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -5619,7 +5619,7 @@ static inline int bnx2x_func_send_start(struct bnx2x *bp, memset(rdata, 0, sizeof(*rdata)); /* Fill the ramrod data with provided parameters */ - rdata->function_mode = cpu_to_le16(start_params->mf_mode); + rdata->function_mode = (u8)start_params->mf_mode; rdata->sd_vlan_tag = cpu_to_le16(start_params->sd_vlan_tag); rdata->path_id = BP_PATH(bp); rdata->network_cos_mode = start_params->network_cos_mode; diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 2107d79d69b3..cc8434fd606e 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -4891,6 +4891,9 @@ static void cnic_init_bnx2x_tx_ring(struct cnic_dev *dev, buf_map = udev->l2_buf_map; for (i = 0; i < MAX_TX_DESC_CNT; i += 3, txbd += 3) { struct eth_tx_start_bd *start_bd = &txbd->start_bd; + struct eth_tx_parse_bd_e1x *pbd_e1x = + &((txbd + 1)->parse_bd_e1x); + struct eth_tx_parse_bd_e2 *pbd_e2 = &((txbd + 1)->parse_bd_e2); struct eth_tx_bd *reg_bd = &((txbd + 2)->reg_bd); start_bd->addr_hi = cpu_to_le32((u64) buf_map >> 32); @@ -4900,10 +4903,15 @@ static void cnic_init_bnx2x_tx_ring(struct cnic_dev *dev, start_bd->nbytes = cpu_to_le16(0x10); start_bd->nbd = cpu_to_le16(3); start_bd->bd_flags.as_bitfield = ETH_TX_BD_FLAGS_START_BD; - start_bd->general_data = (UNICAST_ADDRESS << - ETH_TX_START_BD_ETH_ADDR_TYPE_SHIFT); + start_bd->general_data &= ~ETH_TX_START_BD_PARSE_NBDS; start_bd->general_data |= (1 << ETH_TX_START_BD_HDR_NBDS_SHIFT); + if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id)) + pbd_e2->parsing_data = (UNICAST_ADDRESS << + ETH_TX_PARSE_BD_E2_ETH_ADDR_TYPE_SHIFT); + else + pbd_e1x->global_data = (UNICAST_ADDRESS << + ETH_TX_PARSE_BD_E1X_ETH_ADDR_TYPE_SHIFT); } val = (u64) ring_map >> 32; diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h index 382c98b0cc0c..ede3db35d757 100644 --- a/drivers/net/ethernet/broadcom/cnic_defs.h +++ b/drivers/net/ethernet/broadcom/cnic_defs.h @@ -896,7 +896,7 @@ struct tstorm_tcp_tcp_ag_context_section { u32 snd_nxt; u32 rtt_seq; u32 rtt_time; - u32 __reserved66; + u32 wnd_right_edge_local; u32 wnd_right_edge; u32 tcp_agg_vars1; #define TSTORM_TCP_TCP_AG_CONTEXT_SECTION_FIN_SENT_FLAG (0x1<<0) diff --git a/drivers/net/ethernet/broadcom/cnic_if.h b/drivers/net/ethernet/broadcom/cnic_if.h index 2e92c348083e..865095aad1f6 100644 --- a/drivers/net/ethernet/broadcom/cnic_if.h +++ b/drivers/net/ethernet/broadcom/cnic_if.h @@ -14,8 +14,8 @@ #include "bnx2x/bnx2x_mfw_req.h" -#define CNIC_MODULE_VERSION "2.5.13" -#define CNIC_MODULE_RELDATE "Sep 07, 2012" +#define CNIC_MODULE_VERSION "2.5.14" +#define CNIC_MODULE_RELDATE "Sep 30, 2012" #define CNIC_ULP_RDMA 0 #define CNIC_ULP_ISCSI 1 -- cgit v1.2.3 From 515e12401f43f2fe7511d228dfe3e186be8aab6e Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 1 Oct 2012 03:46:20 +0000 Subject: bnx2x: update version to 1.78.00-0. Signed-off-by: Yuval Mintz Signed-off-by: Ariel Elior Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 6d1a24acb77e..38650843ca21 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -23,8 +23,8 @@ * (you will need to reboot afterwards) */ /* #define BNX2X_STOP_ON_ERROR */ -#define DRV_MODULE_VERSION "1.72.51-0" -#define DRV_MODULE_RELDATE "2012/06/18" +#define DRV_MODULE_VERSION "1.78.00-0" +#define DRV_MODULE_RELDATE "2012/09/27" #define BNX2X_BC_VER 0x040200 #if defined(CONFIG_DCB) -- cgit v1.2.3 From 8112ec3b8722680251aecdcc23dfd81aa7af6340 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Sep 2012 07:53:26 +0000 Subject: mlx4: dont orphan skbs in mlx4_en_xmit() After commit e22979d96a55d (mlx4_en: Moving to Interrupts for TX completions) we no longer need to orphan skbs in mlx4_en_xmit() since skb wont stay a long time in TX ring before their release. Orphaning skbs in ndo_start_xmit() should be avoided as much as possible, since it breaks TCP Small Queue or other flow control mechanisms (per socket limits) Signed-off-by: Eric Dumazet Acked-by: Yevgeny Petrilin Cc: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 10bba09c44ea..c10e3a6de09f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -712,10 +712,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) if (bounce) tx_desc = mlx4_en_bounce_to_desc(priv, ring, index, desc_size); - /* Run destructor before passing skb to HW */ - if (likely(!skb_shared(skb))) - skb_orphan(skb); - if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && !vlan_tag) { *(__be32 *) (&tx_desc->ctrl.vlan_tag) |= cpu_to_be32(ring->doorbell_qpn); op_own |= htonl((bf_index & 0xffff) << 8); -- cgit v1.2.3 From 342b7b741d76bc8aadeff844634348bb2a343d19 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Thu, 27 Sep 2012 09:19:34 +0000 Subject: net: ti cpsw ethernet: set IFCTL_A bit in MACCONTROL For RMII/RGMII mode operation in 100Mbps, the CPSW needs to set the IFCTL_A bits in the MACCONTROL register. For all other PHY modes, this bit is unused, so setting it unconditionally shouldn't cause any trouble. Signed-off-by: Daniel Mack Cc: Mugunthan V N Cc: Vaibhav Hiremath Cc: David S. Miller Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpsw.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 0cbc0e59252c..df55e2403746 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -386,6 +386,11 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave, mac_control |= BIT(7); /* GIGABITEN */ if (phy->duplex) mac_control |= BIT(0); /* FULLDUPLEXEN */ + + /* set speed_in input in case RMII mode is used in 100Mbps */ + if (phy->speed == 100) + mac_control |= BIT(15); + *link = true; } else { mac_control = 0; -- cgit v1.2.3 From d7559982701ac500662b2e8e150ff34f7faf0281 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 26 Sep 2012 07:24:27 +0000 Subject: net: ti cpsw ethernet: allow reading phy interface mode from DT Allow users to specify the phy interface of the CPSW slaves. The new node parameter is called "phy_if_mode" and is optional. The original behaviour of the driver is preserved when not given. Signed-off-by: Daniel Mack Cc: Mugunthan V N Cc: Vaibhav Hiremath Cc: David S. Miller Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/cpsw.txt | 3 +++ drivers/net/ethernet/ti/cpsw.c | 3 +++ 2 files changed, 6 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index dcaabe9fe869..d87f7d2b7b0a 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -25,6 +25,8 @@ Required properties: - slave_reg_ofs : Specifies slave register offset - sliver_reg_ofs : Specifies slave sliver register offset - phy_id : Specifies slave phy id +- phy_if_mode : Specified slave phy interface mode (optional) + (one of the PHY_INTERFACE_MODE_* as numerical value) - mac-address : Specifies slave MAC address Optional properties: @@ -62,6 +64,7 @@ Examples: slave_reg_ofs = <0x208>; sliver_reg_ofs = <0xd80>; phy_id = "davinci_mdio.16:00"; + phy_if_mode = <6>; /* PHY_INTERFACE_MODE_RGMII */ /* Filled in by U-Boot */ mac-address = [ 00 00 00 00 00 00 ]; }; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index df55e2403746..3e12db6f9c0c 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -855,6 +855,9 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, } slave_data->sliver_reg_ofs = prop; + if (!of_property_read_u32(slave_node, "phy_if_mode", &prop)) + slave_data->phy_if = prop; + mac_addr = of_get_mac_address(slave_node); if (mac_addr) memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); -- cgit v1.2.3 From d4e62648274857a2b3a5bc62f910c062e71b2d9b Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 1 Oct 2012 17:39:31 -0400 Subject: Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT" This reverts commit d7559982701ac500662b2e8e150ff34f7faf0281. It wasn't meant to be applied, commit 342b7b741d76bc8aadeff844634348bb2a343d19 ("net: ti cpsw ethernet: set IFCTL_A bit in MACCONTROL") was redone in such a way to make this commit unnecessary. Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/cpsw.txt | 3 --- drivers/net/ethernet/ti/cpsw.c | 3 --- 2 files changed, 6 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index d87f7d2b7b0a..dcaabe9fe869 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -25,8 +25,6 @@ Required properties: - slave_reg_ofs : Specifies slave register offset - sliver_reg_ofs : Specifies slave sliver register offset - phy_id : Specifies slave phy id -- phy_if_mode : Specified slave phy interface mode (optional) - (one of the PHY_INTERFACE_MODE_* as numerical value) - mac-address : Specifies slave MAC address Optional properties: @@ -64,7 +62,6 @@ Examples: slave_reg_ofs = <0x208>; sliver_reg_ofs = <0xd80>; phy_id = "davinci_mdio.16:00"; - phy_if_mode = <6>; /* PHY_INTERFACE_MODE_RGMII */ /* Filled in by U-Boot */ mac-address = [ 00 00 00 00 00 00 ]; }; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 3e12db6f9c0c..df55e2403746 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -855,9 +855,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, } slave_data->sliver_reg_ofs = prop; - if (!of_property_read_u32(slave_node, "phy_if_mode", &prop)) - slave_data->phy_if = prop; - mac_addr = of_get_mac_address(slave_node); if (mac_addr) memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); -- cgit v1.2.3 From de0a41484c47d783dd4d442914815076aa2caac2 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Mon, 1 Oct 2012 11:43:49 -0400 Subject: tg3: unconditionally select HWMON support when tg3 is enabled. There is the seldom used corner case where HWMON=m at the same time as TIGON3=y (typically randconfigs) which will cause a link fail like: drivers/built-in.o: In function `tg3_close': tg3.c:(.text+0x16bd86): undefined reference to `hwmon_device_unregister' drivers/built-in.o: In function `tg3_hwmon_open': tg3.c:(.text+0x16fc4b): undefined reference to `hwmon_device_register' make[1]: *** [vmlinux] Error 1 Fix it as suggested by DaveM[1] by having the Kconfig logic simply select HWMON when TIGON3 is selected. This gets rid of all the extra IS_ENABLED ifdeffery in tg3.c as a side benefit. [1] http://marc.info/?l=linux-netdev&m=134250573718151&w=2 Cc: Michael Chan Reported-by: Benjamin Herrenschmidt Reported-by: Anisse Astier Suggested-by: David S. Miller Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/Kconfig | 1 + drivers/net/ethernet/broadcom/tg3.c | 9 --------- 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index f15e72e81ac4..4bd416b72e65 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -101,6 +101,7 @@ config TIGON3 tristate "Broadcom Tigon3 support" depends on PCI select PHYLIB + select HWMON ---help--- This driver supports Broadcom Tigon3 based gigabit Ethernet cards. diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 24f6623c82ab..008ea14b638e 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -44,10 +44,8 @@ #include #include #include -#if IS_ENABLED(CONFIG_HWMON) #include #include -#endif #include #include @@ -9594,7 +9592,6 @@ static int tg3_init_hw(struct tg3 *tp, int reset_phy) return tg3_reset_hw(tp, reset_phy); } -#if IS_ENABLED(CONFIG_HWMON) static void tg3_sd_scan_scratchpad(struct tg3 *tp, struct tg3_ocir *ocir) { int i; @@ -9647,22 +9644,17 @@ static const struct attribute_group tg3_group = { .attrs = tg3_attributes, }; -#endif - static void tg3_hwmon_close(struct tg3 *tp) { -#if IS_ENABLED(CONFIG_HWMON) if (tp->hwmon_dev) { hwmon_device_unregister(tp->hwmon_dev); tp->hwmon_dev = NULL; sysfs_remove_group(&tp->pdev->dev.kobj, &tg3_group); } -#endif } static void tg3_hwmon_open(struct tg3 *tp) { -#if IS_ENABLED(CONFIG_HWMON) int i, err; u32 size = 0; struct pci_dev *pdev = tp->pdev; @@ -9694,7 +9686,6 @@ static void tg3_hwmon_open(struct tg3 *tp) dev_err(&pdev->dev, "Cannot register hwmon device, aborting\n"); sysfs_remove_group(&pdev->dev.kobj, &tg3_group); } -#endif } -- cgit v1.2.3 From edc7d57327bd08bfd04f41531d49b176369db218 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 1 Oct 2012 12:32:33 +0000 Subject: netlink: add attributes to fdb interface Later changes need to be able to refer to neighbour attributes when doing fdb_add. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/macvlan.c | 2 +- include/linux/netdevice.h | 4 +++- net/bridge/br_fdb.c | 3 ++- net/bridge/br_private.h | 2 +- net/core/rtnetlink.c | 6 ++++-- 6 files changed, 12 insertions(+), 7 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 29465be2a14a..0ba6d9561bdb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6889,7 +6889,7 @@ static int ixgbe_set_features(struct net_device *netdev, return 0; } -static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, +static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 flags) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 815dfcfbc7b9..68a43fe602e7 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -546,7 +546,7 @@ static int macvlan_vlan_rx_kill_vid(struct net_device *dev, return 0; } -static int macvlan_fdb_add(struct ndmsg *ndm, +static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 flags) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dd320bb22a5a..807a610f193c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -904,7 +904,8 @@ struct netdev_fcoe_hbainfo { * feature set might be less than what was returned by ndo_fix_features()). * Must return >0 or -errno if it changed dev->features itself. * - * int (*ndo_fdb_add)(struct ndmsg *ndm, struct net_device *dev, + * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], + * struct net_device *dev, * const unsigned char *addr, u16 flags) * Adds an FDB entry to dev for addr. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct net_device *dev, @@ -1014,6 +1015,7 @@ struct net_device_ops { void (*ndo_neigh_destroy)(struct neighbour *n); int (*ndo_fdb_add)(struct ndmsg *ndm, + struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 flags); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 02861190a3d4..d9576e6de2b8 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -608,7 +608,8 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, } /* Add new permanent fdb entry with RTM_NEWNEIGH */ -int br_fdb_add(struct ndmsg *ndm, struct net_device *dev, +int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, const unsigned char *addr, u16 nlh_flags) { struct net_bridge_port *p; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 11a984b87e62..9b278c4ebee1 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -364,7 +364,7 @@ extern void br_fdb_update(struct net_bridge *br, extern int br_fdb_delete(struct ndmsg *ndm, struct net_device *dev, const unsigned char *addr); -extern int br_fdb_add(struct ndmsg *nlh, +extern int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 nlh_flags); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 92575370d9f0..76d4c2c3c89b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2090,7 +2090,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && (dev->priv_flags & IFF_BRIDGE_PORT)) { master = dev->master; - err = master->netdev_ops->ndo_fdb_add(ndm, dev, addr, + err = master->netdev_ops->ndo_fdb_add(ndm, tb, + dev, addr, nlh->nlmsg_flags); if (err) goto out; @@ -2100,7 +2101,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) /* Embedded bridge, macvlan, and any other device support */ if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_add) { - err = dev->netdev_ops->ndo_fdb_add(ndm, dev, addr, + err = dev->netdev_ops->ndo_fdb_add(ndm, tb, + dev, addr, nlh->nlmsg_flags); if (!err) { -- cgit v1.2.3 From 726ba0e14a7915effee9e8e652a37306d9637d13 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 2 Oct 2012 01:43:45 +0100 Subject: sfc: Fix null function pointer in efx_sriov_channel_type Commit c31e5f9 ('sfc: Add channel specific receive_skb handler and post_remove callback') added the function pointer field efx_channel_type::post_remove and an unconditional call through it. This field should have been initialised to efx_channel_dummy_op_void in the existing instances of efx_channel_type, but this was only done in efx_default_channel_type. Consequently, if a device has SR-IOV enabled then removing the driver or device will result in an oops. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/siena_sriov.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c index a8f48a455849..d49b53dc2a50 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.c +++ b/drivers/net/ethernet/sfc/siena_sriov.c @@ -1035,6 +1035,7 @@ efx_sriov_get_channel_name(struct efx_channel *channel, char *buf, size_t len) static const struct efx_channel_type efx_sriov_channel_type = { .handle_no_channel = efx_sriov_handle_no_channel, .pre_probe = efx_sriov_probe_channel, + .post_remove = efx_channel_dummy_op_void, .get_name = efx_sriov_get_channel_name, /* no copy operation; channel must not be reallocated */ .keep_eventq = true, -- cgit v1.2.3 From 9724a8504c875145f5a513bb8eca50671cee23b4 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 11 Sep 2012 21:37:36 +0100 Subject: sfc: Add parentheses around use of bitfield macro arguments Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/bitfield.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/bitfield.h b/drivers/net/ethernet/sfc/bitfield.h index b26a954c27fc..5400a33f254f 100644 --- a/drivers/net/ethernet/sfc/bitfield.h +++ b/drivers/net/ethernet/sfc/bitfield.h @@ -120,10 +120,10 @@ typedef union efx_oword { * [0,high-low), with garbage in bits [high-low+1,...). */ #define EFX_EXTRACT_NATIVE(native_element, min, max, low, high) \ - (((low > max) || (high < min)) ? 0 : \ - ((low > min) ? \ - ((native_element) >> (low - min)) : \ - ((native_element) << (min - low)))) + ((low) > (max) || (high) < (min) ? 0 : \ + (low) > (min) ? \ + (native_element) >> ((low) - (min)) : \ + (native_element) << ((min) - (low))) /* * Extract bit field portion [low,high) from the 64-bit little-endian @@ -142,27 +142,27 @@ typedef union efx_oword { #define EFX_EXTRACT_OWORD64(oword, low, high) \ ((EFX_EXTRACT64((oword).u64[0], 0, 63, low, high) | \ EFX_EXTRACT64((oword).u64[1], 64, 127, low, high)) & \ - EFX_MASK64(high + 1 - low)) + EFX_MASK64((high) + 1 - (low))) #define EFX_EXTRACT_QWORD64(qword, low, high) \ (EFX_EXTRACT64((qword).u64[0], 0, 63, low, high) & \ - EFX_MASK64(high + 1 - low)) + EFX_MASK64((high) + 1 - (low))) #define EFX_EXTRACT_OWORD32(oword, low, high) \ ((EFX_EXTRACT32((oword).u32[0], 0, 31, low, high) | \ EFX_EXTRACT32((oword).u32[1], 32, 63, low, high) | \ EFX_EXTRACT32((oword).u32[2], 64, 95, low, high) | \ EFX_EXTRACT32((oword).u32[3], 96, 127, low, high)) & \ - EFX_MASK32(high + 1 - low)) + EFX_MASK32((high) + 1 - (low))) #define EFX_EXTRACT_QWORD32(qword, low, high) \ ((EFX_EXTRACT32((qword).u32[0], 0, 31, low, high) | \ EFX_EXTRACT32((qword).u32[1], 32, 63, low, high)) & \ - EFX_MASK32(high + 1 - low)) + EFX_MASK32((high) + 1 - (low))) #define EFX_EXTRACT_DWORD(dword, low, high) \ (EFX_EXTRACT32((dword).u32[0], 0, 31, low, high) & \ - EFX_MASK32(high + 1 - low)) + EFX_MASK32((high) + 1 - (low))) #define EFX_OWORD_FIELD64(oword, field) \ EFX_EXTRACT_OWORD64(oword, EFX_LOW_BIT(field), \ @@ -442,10 +442,10 @@ typedef union efx_oword { cpu_to_le32(EFX_INSERT_NATIVE(min, max, low, high, value)) #define EFX_INPLACE_MASK64(min, max, low, high) \ - EFX_INSERT64(min, max, low, high, EFX_MASK64(high + 1 - low)) + EFX_INSERT64(min, max, low, high, EFX_MASK64((high) + 1 - (low))) #define EFX_INPLACE_MASK32(min, max, low, high) \ - EFX_INSERT32(min, max, low, high, EFX_MASK32(high + 1 - low)) + EFX_INSERT32(min, max, low, high, EFX_MASK32((high) + 1 - (low))) #define EFX_SET_OWORD64(oword, low, high, value) do { \ (oword).u64[0] = (((oword).u64[0] \ -- cgit v1.2.3 From 0a6e5008a9df678b48f8d4e57601aa4270df6c14 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 11 Sep 2012 21:46:41 +0100 Subject: sfc: Fix MCDI structure field lookup The least significant bit number (LBN) of a field within an MCDI structure is counted from the start of the structure, not the containing dword. In MCDI_ARRAY_FIELD() we need to mask it rather than using the usual EFX_DWORD_FIELD() macro. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/mcdi.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index dc25caaa3983..3ba2e5b5a9cc 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -113,11 +113,13 @@ extern void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev); #define MCDI_EVENT_FIELD(_ev, _field) \ EFX_QWORD_FIELD(_ev, MCDI_EVENT_ ## _field) #define MCDI_ARRAY_FIELD(_buf, _field1, _type, _index, _field2) \ - EFX_DWORD_FIELD( \ + EFX_EXTRACT_DWORD( \ *((efx_dword_t *) \ (MCDI_ARRAY_PTR(_buf, _field1, _type, _index) + \ (MC_CMD_ ## _type ## _TYPEDEF_ ## _field2 ## _OFST & ~3))), \ - MC_CMD_ ## _type ## _TYPEDEF_ ## _field2) + MC_CMD_ ## _type ## _TYPEDEF_ ## _field2 ## _LBN & 0x1f, \ + (MC_CMD_ ## _type ## _TYPEDEF_ ## _field2 ## _LBN & 0x1f) + \ + MC_CMD_ ## _type ## _TYPEDEF_ ## _field2 ## _WIDTH - 1) extern void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len); extern int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating, -- cgit v1.2.3 From 1ac0226eb04e56cacee080fb71938eb50b5245eb Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 13 Sep 2012 02:22:52 +0100 Subject: sfc: Fix loopback self-test with separate_tx_channels=1 The loopback self-test iterates over all the TX queues of channel 0, which is not very interesting when that's an RX-only channel. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/ethtool.c | 3 ++- drivers/net/ethernet/sfc/selftest.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 9df556c01b8e..cf772074145a 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -337,7 +337,8 @@ static int efx_fill_loopback_test(struct efx_nic *efx, unsigned int test_index, struct ethtool_string *strings, u64 *data) { - struct efx_channel *channel = efx_get_channel(efx, 0); + struct efx_channel *channel = + efx_get_channel(efx, efx->tx_channel_offset); struct efx_tx_queue *tx_queue; efx_for_each_channel_tx_queue(tx_queue, channel) { diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c index 96068d15b601..ce72ae4f399f 100644 --- a/drivers/net/ethernet/sfc/selftest.c +++ b/drivers/net/ethernet/sfc/selftest.c @@ -614,7 +614,8 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct efx_self_tests *tests, { enum efx_loopback_mode mode; struct efx_loopback_state *state; - struct efx_channel *channel = efx_get_channel(efx, 0); + struct efx_channel *channel = + efx_get_channel(efx, efx->tx_channel_offset); struct efx_tx_queue *tx_queue; int rc = 0; -- cgit v1.2.3 From 9e0f9a10576a7769869ce1f76f5b336da20667a6 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 4 Sep 2012 18:57:25 +0100 Subject: sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP This filter flag cannot yet be set through the ethtool command and will not be supported on future hardware. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/ethtool.c | 8 ++---- drivers/net/ethernet/sfc/filter.c | 53 +++++--------------------------------- drivers/net/ethernet/sfc/filter.h | 7 +---- 3 files changed, 10 insertions(+), 58 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index cf772074145a..90f078eff8e6 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -961,9 +961,7 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx, int rc; /* Check that user wants us to choose the location */ - if (rule->location != RX_CLS_LOC_ANY && - rule->location != RX_CLS_LOC_FIRST && - rule->location != RX_CLS_LOC_LAST) + if (rule->location != RX_CLS_LOC_ANY) return -EINVAL; /* Range-check ring_cookie */ @@ -977,9 +975,7 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx, rule->m_ext.data[1])) return -EINVAL; - efx_filter_init_rx(&spec, EFX_FILTER_PRI_MANUAL, - (rule->location == RX_CLS_LOC_FIRST) ? - EFX_FILTER_FLAG_RX_OVERRIDE_IP : 0, + efx_filter_init_rx(&spec, EFX_FILTER_PRI_MANUAL, 0, (rule->ring_cookie == RX_CLS_FLOW_DISC) ? 0xfff : rule->ring_cookie); diff --git a/drivers/net/ethernet/sfc/filter.c b/drivers/net/ethernet/sfc/filter.c index c3fd61f0a95c..e89bad78312e 100644 --- a/drivers/net/ethernet/sfc/filter.c +++ b/drivers/net/ethernet/sfc/filter.c @@ -161,10 +161,6 @@ static void efx_filter_push_rx_config(struct efx_nic *efx) filter_ctl, FRF_CZ_UNICAST_NOMATCH_RSS_ENABLED, !!(table->spec[EFX_FILTER_INDEX_UC_DEF].flags & EFX_FILTER_FLAG_RX_RSS)); - EFX_SET_OWORD_FIELD( - filter_ctl, FRF_CZ_UNICAST_NOMATCH_IP_OVERRIDE, - !!(table->spec[EFX_FILTER_INDEX_UC_DEF].flags & - EFX_FILTER_FLAG_RX_OVERRIDE_IP)); EFX_SET_OWORD_FIELD( filter_ctl, FRF_CZ_MULTICAST_NOMATCH_Q_ID, table->spec[EFX_FILTER_INDEX_MC_DEF].dmaq_id); @@ -172,10 +168,6 @@ static void efx_filter_push_rx_config(struct efx_nic *efx) filter_ctl, FRF_CZ_MULTICAST_NOMATCH_RSS_ENABLED, !!(table->spec[EFX_FILTER_INDEX_MC_DEF].flags & EFX_FILTER_FLAG_RX_RSS)); - EFX_SET_OWORD_FIELD( - filter_ctl, FRF_CZ_MULTICAST_NOMATCH_IP_OVERRIDE, - !!(table->spec[EFX_FILTER_INDEX_MC_DEF].flags & - EFX_FILTER_FLAG_RX_OVERRIDE_IP)); } efx_writeo(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL); @@ -480,14 +472,12 @@ static u32 efx_filter_build(efx_oword_t *filter, struct efx_filter_spec *spec) case EFX_FILTER_TABLE_RX_MAC: { bool is_wild = spec->type == EFX_FILTER_MAC_WILD; - EFX_POPULATE_OWORD_8( + EFX_POPULATE_OWORD_7( *filter, FRF_CZ_RMFT_RSS_EN, !!(spec->flags & EFX_FILTER_FLAG_RX_RSS), FRF_CZ_RMFT_SCATTER_EN, !!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER), - FRF_CZ_RMFT_IP_OVERRIDE, - !!(spec->flags & EFX_FILTER_FLAG_RX_OVERRIDE_IP), FRF_CZ_RMFT_RXQ_ID, spec->dmaq_id, FRF_CZ_RMFT_WILDCARD_MATCH, is_wild, FRF_CZ_RMFT_DEST_MAC_HI, spec->data[2], @@ -569,31 +559,15 @@ static int efx_filter_search(struct efx_filter_table *table, /* * Construct/deconstruct external filter IDs. These must be ordered * by matching priority, for RX NFC semantics. - * - * Each RX MAC filter entry has a flag for whether it can override an - * RX IP filter that also matches. So we assign locations for MAC - * filters with overriding behaviour, then for IP filters, then for - * MAC filters without overriding behaviour. */ -#define EFX_FILTER_MATCH_PRI_RX_MAC_OVERRIDE_IP 0 -#define EFX_FILTER_MATCH_PRI_RX_DEF_OVERRIDE_IP 1 -#define EFX_FILTER_MATCH_PRI_NORMAL_BASE 2 - #define EFX_FILTER_INDEX_WIDTH 13 #define EFX_FILTER_INDEX_MASK ((1 << EFX_FILTER_INDEX_WIDTH) - 1) static inline u32 efx_filter_make_id(enum efx_filter_table_id table_id, unsigned int index, u8 flags) { - unsigned int match_pri = EFX_FILTER_MATCH_PRI_NORMAL_BASE + table_id; - - if (flags & EFX_FILTER_FLAG_RX_OVERRIDE_IP) { - if (table_id == EFX_FILTER_TABLE_RX_MAC) - match_pri = EFX_FILTER_MATCH_PRI_RX_MAC_OVERRIDE_IP; - else if (table_id == EFX_FILTER_TABLE_RX_DEF) - match_pri = EFX_FILTER_MATCH_PRI_RX_DEF_OVERRIDE_IP; - } + unsigned int match_pri = table_id; return match_pri << EFX_FILTER_INDEX_WIDTH | index; } @@ -602,14 +576,7 @@ static inline enum efx_filter_table_id efx_filter_id_table_id(u32 id) { unsigned int match_pri = id >> EFX_FILTER_INDEX_WIDTH; - switch (match_pri) { - case EFX_FILTER_MATCH_PRI_RX_MAC_OVERRIDE_IP: - return EFX_FILTER_TABLE_RX_MAC; - case EFX_FILTER_MATCH_PRI_RX_DEF_OVERRIDE_IP: - return EFX_FILTER_TABLE_RX_DEF; - default: - return match_pri - EFX_FILTER_MATCH_PRI_NORMAL_BASE; - } + return match_pri; } static inline unsigned int efx_filter_id_index(u32 id) @@ -621,10 +588,7 @@ static inline u8 efx_filter_id_flags(u32 id) { unsigned int match_pri = id >> EFX_FILTER_INDEX_WIDTH; - if (match_pri < EFX_FILTER_MATCH_PRI_NORMAL_BASE) - return EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_RX_OVERRIDE_IP; - else if (match_pri <= - EFX_FILTER_MATCH_PRI_NORMAL_BASE + EFX_FILTER_TABLE_RX_DEF) + if (match_pri <= EFX_FILTER_TABLE_RX_DEF) return EFX_FILTER_FLAG_RX; else return EFX_FILTER_FLAG_TX; @@ -637,8 +601,7 @@ u32 efx_filter_get_rx_id_limit(struct efx_nic *efx) do { if (state->table[table_id].size != 0) - return ((EFX_FILTER_MATCH_PRI_NORMAL_BASE + table_id) - << EFX_FILTER_INDEX_WIDTH) + + return (table_id << EFX_FILTER_INDEX_WIDTH) + state->table[table_id].size; } while (table_id--); @@ -781,8 +744,7 @@ int efx_filter_remove_id_safe(struct efx_nic *efx, spin_lock_bh(&state->lock); if (test_bit(filter_idx, table->used_bitmap) && - spec->priority == priority && - !((spec->flags ^ filter_flags) & EFX_FILTER_FLAG_RX_OVERRIDE_IP)) { + spec->priority == priority) { efx_filter_table_clear_entry(efx, table, filter_idx); if (table->used == 0) efx_filter_table_reset_search_depth(table); @@ -833,8 +795,7 @@ int efx_filter_get_filter_safe(struct efx_nic *efx, spin_lock_bh(&state->lock); if (test_bit(filter_idx, table->used_bitmap) && - spec->priority == priority && - !((spec->flags ^ filter_flags) & EFX_FILTER_FLAG_RX_OVERRIDE_IP)) { + spec->priority == priority) { *spec_buf = *spec; rc = 0; } else { diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h index 3c77802aed6c..5cb54723b824 100644 --- a/drivers/net/ethernet/sfc/filter.h +++ b/drivers/net/ethernet/sfc/filter.h @@ -61,16 +61,12 @@ enum efx_filter_priority { * according to the indirection table. * @EFX_FILTER_FLAG_RX_SCATTER: Enable DMA scatter on the receiving * queue. - * @EFX_FILTER_FLAG_RX_OVERRIDE_IP: Enables a MAC filter to override - * any IP filter that matches the same packet. By default, IP - * filters take precedence. * @EFX_FILTER_FLAG_RX: Filter is for RX * @EFX_FILTER_FLAG_TX: Filter is for TX */ enum efx_filter_flags { EFX_FILTER_FLAG_RX_RSS = 0x01, EFX_FILTER_FLAG_RX_SCATTER = 0x02, - EFX_FILTER_FLAG_RX_OVERRIDE_IP = 0x04, EFX_FILTER_FLAG_RX = 0x08, EFX_FILTER_FLAG_TX = 0x10, }; @@ -88,8 +84,7 @@ enum efx_filter_flags { * * The @priority field is used by software to determine whether a new * filter may replace an old one. The hardware priority of a filter - * depends on the filter type and %EFX_FILTER_FLAG_RX_OVERRIDE_IP - * flag. + * depends on the filter type. */ struct efx_filter_spec { u8 type:4; -- cgit v1.2.3 From 6ac7ef1487a040483d89a95045efc5185a71268f Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 24 Aug 2012 20:12:20 +0100 Subject: sfc: Fix the reported priorities of different filter types Each RX filter table contains filters with two different levels of specificity: TCP/IPv4 and UDP/IPv4 filters match the local address and port and optionally the remote address and port; Ethernet filters match the local address and optionally the VID. The more specific filters always override less specific filters within the same table, and should be numbered accordingly. Signed-off-by: Ben Hutchings --- drivers/net/ethernet/sfc/filter.c | 69 ++++++++++++++++++++++++++++++--------- 1 file changed, 53 insertions(+), 16 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/sfc/filter.c b/drivers/net/ethernet/sfc/filter.c index e89bad78312e..8af42cd1feda 100644 --- a/drivers/net/ethernet/sfc/filter.c +++ b/drivers/net/ethernet/sfc/filter.c @@ -557,26 +557,62 @@ static int efx_filter_search(struct efx_filter_table *table, } /* - * Construct/deconstruct external filter IDs. These must be ordered - * by matching priority, for RX NFC semantics. + * Construct/deconstruct external filter IDs. At least the RX filter + * IDs must be ordered by matching priority, for RX NFC semantics. + * + * Deconstruction needs to be robust against invalid IDs so that + * efx_filter_remove_id_safe() and efx_filter_get_filter_safe() can + * accept user-provided IDs. */ +#define EFX_FILTER_MATCH_PRI_COUNT 5 + +static const u8 efx_filter_type_match_pri[EFX_FILTER_TYPE_COUNT] = { + [EFX_FILTER_TCP_FULL] = 0, + [EFX_FILTER_UDP_FULL] = 0, + [EFX_FILTER_TCP_WILD] = 1, + [EFX_FILTER_UDP_WILD] = 1, + [EFX_FILTER_MAC_FULL] = 2, + [EFX_FILTER_MAC_WILD] = 3, + [EFX_FILTER_UC_DEF] = 4, + [EFX_FILTER_MC_DEF] = 4, +}; + +static const enum efx_filter_table_id efx_filter_range_table[] = { + EFX_FILTER_TABLE_RX_IP, /* RX match pri 0 */ + EFX_FILTER_TABLE_RX_IP, + EFX_FILTER_TABLE_RX_MAC, + EFX_FILTER_TABLE_RX_MAC, + EFX_FILTER_TABLE_RX_DEF, /* RX match pri 4 */ + EFX_FILTER_TABLE_COUNT, /* TX match pri 0; invalid */ + EFX_FILTER_TABLE_COUNT, /* invalid */ + EFX_FILTER_TABLE_TX_MAC, + EFX_FILTER_TABLE_TX_MAC, /* TX match pri 3 */ +}; + #define EFX_FILTER_INDEX_WIDTH 13 #define EFX_FILTER_INDEX_MASK ((1 << EFX_FILTER_INDEX_WIDTH) - 1) -static inline u32 efx_filter_make_id(enum efx_filter_table_id table_id, - unsigned int index, u8 flags) +static inline u32 +efx_filter_make_id(const struct efx_filter_spec *spec, unsigned int index) { - unsigned int match_pri = table_id; + unsigned int range; + + range = efx_filter_type_match_pri[spec->type]; + if (!(spec->flags & EFX_FILTER_FLAG_RX)) + range += EFX_FILTER_MATCH_PRI_COUNT; - return match_pri << EFX_FILTER_INDEX_WIDTH | index; + return range << EFX_FILTER_INDEX_WIDTH | index; } static inline enum efx_filter_table_id efx_filter_id_table_id(u32 id) { - unsigned int match_pri = id >> EFX_FILTER_INDEX_WIDTH; + unsigned int range = id >> EFX_FILTER_INDEX_WIDTH; - return match_pri; + if (range < ARRAY_SIZE(efx_filter_range_table)) + return efx_filter_range_table[range]; + else + return EFX_FILTER_TABLE_COUNT; /* invalid */ } static inline unsigned int efx_filter_id_index(u32 id) @@ -586,9 +622,9 @@ static inline unsigned int efx_filter_id_index(u32 id) static inline u8 efx_filter_id_flags(u32 id) { - unsigned int match_pri = id >> EFX_FILTER_INDEX_WIDTH; + unsigned int range = id >> EFX_FILTER_INDEX_WIDTH; - if (match_pri <= EFX_FILTER_TABLE_RX_DEF) + if (range < EFX_FILTER_MATCH_PRI_COUNT) return EFX_FILTER_FLAG_RX; else return EFX_FILTER_FLAG_TX; @@ -597,13 +633,15 @@ static inline u8 efx_filter_id_flags(u32 id) u32 efx_filter_get_rx_id_limit(struct efx_nic *efx) { struct efx_filter_state *state = efx->filter_state; - unsigned int table_id = EFX_FILTER_TABLE_RX_DEF; + unsigned int range = EFX_FILTER_MATCH_PRI_COUNT - 1; + enum efx_filter_table_id table_id; do { + table_id = efx_filter_range_table[range]; if (state->table[table_id].size != 0) - return (table_id << EFX_FILTER_INDEX_WIDTH) + + return range << EFX_FILTER_INDEX_WIDTH | state->table[table_id].size; - } while (table_id--); + } while (range--); return 0; } @@ -681,7 +719,7 @@ s32 efx_filter_insert_filter(struct efx_nic *efx, struct efx_filter_spec *spec, netif_vdbg(efx, hw, efx->net_dev, "%s: filter type %d index %d rxq %u set", __func__, spec->type, filter_idx, spec->dmaq_id); - rc = efx_filter_make_id(table->id, filter_idx, spec->flags); + rc = efx_filter_make_id(spec, filter_idx); out: spin_unlock_bh(&state->lock); @@ -888,8 +926,7 @@ s32 efx_filter_get_rx_ids(struct efx_nic *efx, goto out; } buf[count++] = efx_filter_make_id( - table_id, filter_idx, - table->spec[filter_idx].flags); + &table->spec[filter_idx], filter_idx); } } } -- cgit v1.2.3